From d43be2554b58621a21cb5f54b32db2263b3008b6 Mon Sep 17 00:00:00 2001
From: Bernard Zhao <bernard@vivo.com>
Date: Mon, 27 Apr 2020 01:05:23 -0700
Subject: drivers: video: hdmi: cleanup coding style in video a bit

Eliminate the magic numbers, add vendor infoframe size macro
like other hdmi modules.

Signed-off-by: Bernard Zhao <bernard@vivo.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: opensource.kernel@vivo.com
[b.zolnierkie: add "hdmi" to the patch summary]
[b.zolnierkie: fix "vender" -> vendor" typo in the patch description]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200427080530.3234-1-bernard@vivo.com
---
 include/linux/hdmi.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 9613d796cfb1..ff25aeb95ee4 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -57,6 +57,7 @@ enum hdmi_infoframe_type {
 #define HDMI_SPD_INFOFRAME_SIZE    25
 #define HDMI_AUDIO_INFOFRAME_SIZE  10
 #define HDMI_DRM_INFOFRAME_SIZE    26
+#define HDMI_VENDOR_INFOFRAME_SIZE  4
 
 #define HDMI_INFOFRAME_SIZE(type)	\
 	(HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE)
-- 
cgit v1.2.3


From 7b97d868b7ab2448859668de9222b8af43f76e78 Mon Sep 17 00:00:00 2001
From: "zhangyi (F)" <yi.zhang@huawei.com>
Date: Tue, 9 Jun 2020 15:35:40 +0800
Subject: ext4, jbd2: ensure panic by fix a race between jbd2 abort and ext4
 error handlers

In the ext4 filesystem with errors=panic, if one process is recording
errno in the superblock when invoking jbd2_journal_abort() due to some
error cases, it could be raced by another __ext4_abort() which is
setting the SB_RDONLY flag but missing panic because errno has not been
recorded.

jbd2_journal_commit_transaction()
 jbd2_journal_abort()
  journal->j_flags |= JBD2_ABORT;
  jbd2_journal_update_sb_errno()
                                    | ext4_journal_check_start()
                                    |  __ext4_abort()
                                    |   sb->s_flags |= SB_RDONLY;
                                    |   if (!JBD2_REC_ERR)
                                    |        return;
  journal->j_flags |= JBD2_REC_ERR;

Finally, it will no longer trigger panic because the filesystem has
already been set read-only. Fix this by introduce j_abort_mutex to make
sure journal abort is completed before panic, and remove JBD2_REC_ERR
flag.

Fixes: 4327ba52afd03 ("ext4, jbd2: ensure entering into panic after recording an error in superblock")
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200609073540.3810702-1-yi.zhang@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c      | 16 +++++-----------
 fs/jbd2/journal.c    | 17 ++++++++++++-----
 include/linux/jbd2.h |  6 +++++-
 3 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 127b8efa8d54..2660a7e47eef 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -522,9 +522,6 @@ static void ext4_handle_error(struct super_block *sb)
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
 	} else if (test_opt(sb, ERRORS_PANIC)) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
 	}
@@ -725,23 +722,20 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	va_end(args);
 
 	if (sb_rdonly(sb) == 0) {
-		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (EXT4_SB(sb)->s_journal)
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		/*
 		 * Make sure updated value of ->s_mount_flags will be visible
 		 * before ->s_flags update
 		 */
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
-		if (EXT4_SB(sb)->s_journal)
-			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 	}
-	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
+	if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
 		panic("EXT4-fs panic from previous error\n");
-	}
 }
 
 void __ext4_msg(struct super_block *sb,
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a49d0e670ddf..e4944436e733 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1140,6 +1140,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
 	spin_lock_init(&journal->j_revoke_lock);
@@ -1402,7 +1403,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 		printk(KERN_ERR "JBD2: Error %d detected when updating "
 		       "journal superblock for %s.\n", ret,
 		       journal->j_devname);
-		jbd2_journal_abort(journal, ret);
+		if (!is_journal_aborted(journal))
+			jbd2_journal_abort(journal, ret);
 	}
 
 	return ret;
@@ -2153,6 +2155,13 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 {
 	transaction_t *transaction;
 
+	/*
+	 * Lock the aborting procedure until everything is done, this avoid
+	 * races between filesystem's error handling flow (e.g. ext4_abort()),
+	 * ensure panic after the error info is written into journal's
+	 * superblock.
+	 */
+	mutex_lock(&journal->j_abort_mutex);
 	/*
 	 * ESHUTDOWN always takes precedence because a file system check
 	 * caused by any other journal abort error is not required after
@@ -2167,6 +2176,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 			journal->j_errno = errno;
 			jbd2_journal_update_sb_errno(journal);
 		}
+		mutex_unlock(&journal->j_abort_mutex);
 		return;
 	}
 
@@ -2188,10 +2198,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 	 * layer could realise that a filesystem check is needed.
 	 */
 	jbd2_journal_update_sb_errno(journal);
-
-	write_lock(&journal->j_state_lock);
-	journal->j_flags |= JBD2_REC_ERR;
-	write_unlock(&journal->j_state_lock);
+	mutex_unlock(&journal->j_abort_mutex);
 }
 
 /**
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f613d8529863..d56128df2aff 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -765,6 +765,11 @@ struct journal_s
 	 */
 	int			j_errno;
 
+	/**
+	 * @j_abort_mutex: Lock the whole aborting procedure.
+	 */
+	struct mutex		j_abort_mutex;
+
 	/**
 	 * @j_sb_buffer: The first part of the superblock buffer.
 	 */
@@ -1247,7 +1252,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
-#define JBD2_REC_ERR	0x080	/* The errno in the sb has been recorded */
 
 /*
  * Function declarations for the journaling transaction and buffer
-- 
cgit v1.2.3


From e7e3b9d23f3bc6774cce585ef4fcb02462e04065 Mon Sep 17 00:00:00 2001
From: Gwendal Grignou <gwendal@chromium.org>
Date: Tue, 26 May 2020 21:35:17 -0700
Subject: iio: cros_ec: Reapply range at resume

EC does not currently preserve range across sensor reinit.
If sensor is powered down at suspend, it will default to the EC default
range at resume, not the range set by the host.

Save range if modified, and apply at resume.

Signed-off-by: Gwendal Grignou <gwendal@chromium.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../iio/common/cros_ec_sensors/cros_ec_sensors.c    |  5 +++++
 .../common/cros_ec_sensors/cros_ec_sensors_core.c   | 21 +++++++++++++++++++++
 drivers/iio/light/cros_ec_light_prox.c              |  6 +++++-
 drivers/iio/pressure/cros_ec_baro.c                 |  8 ++++++--
 include/linux/iio/common/cros_ec_sensors_core.h     | 11 ++++++++++-
 5 files changed, 47 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index a66941fdb385..130ab8ce0269 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -200,6 +200,10 @@ static int cros_ec_sensors_write(struct iio_dev *indio_dev,
 		st->core.param.sensor_range.roundup = 1;
 
 		ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+		if (ret == 0) {
+			st->core.range_updated = true;
+			st->core.curr_range = val;
+		}
 		break;
 	default:
 		ret = cros_ec_sensors_core_write(
@@ -315,6 +319,7 @@ MODULE_DEVICE_TABLE(platform, cros_ec_sensors_ids);
 static struct platform_driver cros_ec_sensors_platform_driver = {
 	.driver = {
 		.name	= "cros-ec-sensors",
+		.pm	= &cros_ec_sensors_pm_ops,
 	},
 	.probe		= cros_ec_sensors_probe,
 	.id_table	= cros_ec_sensors_ids,
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index c831915ca7e5..cda459b61206 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -824,5 +824,26 @@ int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st,
 }
 EXPORT_SYMBOL_GPL(cros_ec_sensors_core_write);
 
+static int __maybe_unused cros_ec_sensors_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
+	struct cros_ec_sensors_core_state *st = iio_priv(indio_dev);
+	int ret = 0;
+
+	if (st->range_updated) {
+		mutex_lock(&st->cmd_lock);
+		st->param.cmd = MOTIONSENSE_CMD_SENSOR_RANGE;
+		st->param.sensor_range.data = st->curr_range;
+		st->param.sensor_range.roundup = 1;
+		ret = cros_ec_motion_send_host_cmd(st, 0);
+		mutex_unlock(&st->cmd_lock);
+	}
+	return ret;
+}
+
+SIMPLE_DEV_PM_OPS(cros_ec_sensors_pm_ops, NULL, cros_ec_sensors_resume);
+EXPORT_SYMBOL_GPL(cros_ec_sensors_pm_ops);
+
 MODULE_DESCRIPTION("ChromeOS EC sensor hub core functions");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c
index 2198b50909ed..fed79ba27fda 100644
--- a/drivers/iio/light/cros_ec_light_prox.c
+++ b/drivers/iio/light/cros_ec_light_prox.c
@@ -145,8 +145,11 @@ static int cros_ec_light_prox_write(struct iio_dev *indio_dev,
 		break;
 	case IIO_CHAN_INFO_CALIBSCALE:
 		st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_RANGE;
-		st->core.param.sensor_range.data = (val << 16) | (val2 / 100);
+		st->core.curr_range = (val << 16) | (val2 / 100);
+		st->core.param.sensor_range.data = st->core.curr_range;
 		ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+		if (ret == 0)
+			st->core.range_updated = true;
 		break;
 	default:
 		ret = cros_ec_sensors_core_write(&st->core, chan, val, val2,
@@ -256,6 +259,7 @@ MODULE_DEVICE_TABLE(platform, cros_ec_light_prox_ids);
 static struct platform_driver cros_ec_light_prox_platform_driver = {
 	.driver = {
 		.name	= "cros-ec-light-prox",
+		.pm	= &cros_ec_sensors_pm_ops,
 	},
 	.probe		= cros_ec_light_prox_probe,
 	.id_table	= cros_ec_light_prox_ids,
diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c
index c079b8960082..f0938b6fbba0 100644
--- a/drivers/iio/pressure/cros_ec_baro.c
+++ b/drivers/iio/pressure/cros_ec_baro.c
@@ -96,8 +96,11 @@ static int cros_ec_baro_write(struct iio_dev *indio_dev,
 		/* Always roundup, so caller gets at least what it asks for. */
 		st->core.param.sensor_range.roundup = 1;
 
-		if (cros_ec_motion_send_host_cmd(&st->core, 0))
-			ret = -EIO;
+		ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+		if (ret == 0) {
+			st->core.range_updated = true;
+			st->core.curr_range = val;
+		}
 		break;
 	default:
 		ret = cros_ec_sensors_core_write(&st->core, chan, val, val2,
@@ -199,6 +202,7 @@ MODULE_DEVICE_TABLE(platform, cros_ec_baro_ids);
 static struct platform_driver cros_ec_baro_platform_driver = {
 	.driver = {
 		.name	= "cros-ec-baro",
+		.pm	= &cros_ec_sensors_pm_ops,
 	},
 	.probe		= cros_ec_baro_probe,
 	.id_table	= cros_ec_baro_ids,
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index 7bc961defa87..caa8bb279a34 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -42,6 +42,10 @@ typedef irqreturn_t (*cros_ec_sensors_capture_t)(int irq, void *p);
  * @resp:			motion sensor response structure
  * @type:			type of motion sensor
  * @loc:			location where the motion sensor is placed
+ * @range_updated:		True if the range of the sensor has been
+ *				updated.
+ * @curr_range:			If updated, the current range value.
+ *				It will be reapplied at every resume.
  * @calib:			calibration parameters. Note that trigger
  *				captured data will always provide the calibrated
  *				data
@@ -65,6 +69,9 @@ struct cros_ec_sensors_core_state {
 	enum motionsensor_type type;
 	enum motionsensor_location loc;
 
+	bool range_updated;
+	int curr_range;
+
 	struct calib_data {
 		s16 offset;
 		u16 scale;
@@ -114,7 +121,9 @@ int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st,
 			       struct iio_chan_spec const *chan,
 			       int val, int val2, long mask);
 
-/* List of extended channel specification for all sensors */
+extern const struct dev_pm_ops cros_ec_sensors_pm_ops;
+
+/* List of extended channel specification for all sensors. */
 extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[];
 extern const struct attribute *cros_ec_sensor_fifo_attributes[];
 
-- 
cgit v1.2.3


From 18d563858d97dbefc9a16c8210ef2f97dc264202 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Thu, 21 May 2020 18:53:22 +0100
Subject: iio: make iio_device_get_drvdata take a const struct iio_dev *.

As this just calls dev_get_drvdata underneath which is happy with
a const struct device * we should change and avoid potentially
casting away a const in order to then put it back again.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Jean-Baptiste Maneyrol <jmaneyrol@invensense.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index a1be82e74c93..e846a0a7001e 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -669,7 +669,7 @@ static inline void iio_device_set_drvdata(struct iio_dev *indio_dev, void *data)
  *
  * Returns the data previously set with iio_device_set_drvdata()
  */
-static inline void *iio_device_get_drvdata(struct iio_dev *indio_dev)
+static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
 {
 	return dev_get_drvdata(&indio_dev->dev);
 }
-- 
cgit v1.2.3


From 78289b4a58b58e9a8a76ef43ffbaf04a097e33c6 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 3 Jun 2020 14:40:18 +0300
Subject: iio: core: pass parent device as parameter during allocation

The change passes the parent device to the iio_device_alloc() call. This
also updates the devm_iio_device_alloc() call to consider the device object
as the parent device by default.

Having it passed like this, should ensure that any IIO device object
already has a device object as parent, allowing for neater control, like
passing the 'indio_dev' object for other stuff [like buffers/triggers/etc],
and potentially creating iiom_xxx(indio_dev) functions.

With this patch, only the 'drivers/platform/x86/toshiba_acpi.c' needs an
update to pass the parent object as a parameter.

In the next patch all devm_iio_device_alloc() calls will be handled.

Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dummy/iio_simple_dummy.c         | 14 ++++++++------
 drivers/iio/industrialio-core.c              | 11 ++++++-----
 drivers/platform/x86/toshiba_acpi.c          |  3 +--
 drivers/staging/iio/Documentation/device.txt |  4 +---
 include/linux/iio/iio.h                      |  4 ++--
 5 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/dummy/iio_simple_dummy.c b/drivers/iio/dummy/iio_simple_dummy.c
index 6cb02299a215..b35ae7c039f7 100644
--- a/drivers/iio/dummy/iio_simple_dummy.c
+++ b/drivers/iio/dummy/iio_simple_dummy.c
@@ -566,6 +566,13 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	struct iio_dev *indio_dev;
 	struct iio_dummy_state *st;
 	struct iio_sw_device *swd;
+	struct device *parent = NULL;
+
+	/*
+	 * With hardware: Set the parent device.
+	 * parent = &spi->dev;
+	 * parent = &client->dev;
+	 */
 
 	swd = kzalloc(sizeof(*swd), GFP_KERNEL);
 	if (!swd) {
@@ -580,7 +587,7 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	 * It also has a region (accessed by iio_priv()
 	 * for chip specific state information.
 	 */
-	indio_dev = iio_device_alloc(sizeof(*st));
+	indio_dev = iio_device_alloc(parent, sizeof(*st));
 	if (!indio_dev) {
 		ret = -ENOMEM;
 		goto error_ret;
@@ -590,11 +597,6 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	mutex_init(&st->lock);
 
 	iio_dummy_init_device(indio_dev);
-	/*
-	 * With hardware: Set the parent device.
-	 * indio_dev->dev.parent = &spi->dev;
-	 * indio_dev->dev.parent = &client->dev;
-	 */
 
 	 /*
 	 * Make the iio_dev struct available to remove function.
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 1527f01a44f1..75661661aaba 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1493,7 +1493,7 @@ struct device_type iio_device_type = {
  * iio_device_alloc() - allocate an iio_dev from a driver
  * @sizeof_priv:	Space to allocate for private structure.
  **/
-struct iio_dev *iio_device_alloc(int sizeof_priv)
+struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 {
 	struct iio_dev *dev;
 	size_t alloc_size;
@@ -1510,6 +1510,7 @@ struct iio_dev *iio_device_alloc(int sizeof_priv)
 	if (!dev)
 		return NULL;
 
+	dev->dev.parent = parent;
 	dev->dev.groups = dev->groups;
 	dev->dev.type = &iio_device_type;
 	dev->dev.bus = &iio_bus_type;
@@ -1551,7 +1552,7 @@ static void devm_iio_device_release(struct device *dev, void *res)
 
 /**
  * devm_iio_device_alloc - Resource-managed iio_device_alloc()
- * @dev:		Device to allocate iio_dev for
+ * @parent:		Device to allocate iio_dev for, and parent for this IIO device
  * @sizeof_priv:	Space to allocate for private structure.
  *
  * Managed iio_device_alloc. iio_dev allocated with this function is
@@ -1560,7 +1561,7 @@ static void devm_iio_device_release(struct device *dev, void *res)
  * RETURNS:
  * Pointer to allocated iio_dev on success, NULL on failure.
  */
-struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv)
+struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv)
 {
 	struct iio_dev **ptr, *iio_dev;
 
@@ -1569,10 +1570,10 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv)
 	if (!ptr)
 		return NULL;
 
-	iio_dev = iio_device_alloc(sizeof_priv);
+	iio_dev = iio_device_alloc(parent, sizeof_priv);
 	if (iio_dev) {
 		*ptr = iio_dev;
-		devres_add(dev, ptr);
+		devres_add(parent, ptr);
 	} else {
 		devres_free(ptr);
 	}
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 1ddab5a6dead..36fff00af9eb 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -3114,7 +3114,7 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev)
 
 	toshiba_accelerometer_available(dev);
 	if (dev->accelerometer_supported) {
-		dev->indio_dev = iio_device_alloc(sizeof(*dev));
+		dev->indio_dev = iio_device_alloc(&acpi_dev->dev, sizeof(*dev));
 		if (!dev->indio_dev) {
 			pr_err("Unable to allocate iio device\n");
 			goto iio_error;
@@ -3124,7 +3124,6 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev)
 
 		dev->indio_dev->info = &toshiba_iio_accel_info;
 		dev->indio_dev->name = "Toshiba accelerometer";
-		dev->indio_dev->dev.parent = &acpi_dev->dev;
 		dev->indio_dev->modes = INDIO_DIRECT_MODE;
 		dev->indio_dev->channels = toshiba_iio_accel_channels;
 		dev->indio_dev->num_channels =
diff --git a/drivers/staging/iio/Documentation/device.txt b/drivers/staging/iio/Documentation/device.txt
index ec42544a46aa..0d1275b1eb3f 100644
--- a/drivers/staging/iio/Documentation/device.txt
+++ b/drivers/staging/iio/Documentation/device.txt
@@ -8,7 +8,7 @@ The crucial structure for device drivers in iio is iio_dev.
 
 First allocate one using:
 
-struct iio_dev *indio_dev = iio_device_alloc(sizeof(struct chip_state));
+struct iio_dev *indio_dev = iio_device_alloc(parent, sizeof(struct chip_state));
 where chip_state is a structure of local state data for this instance of
 the chip.
 
@@ -16,8 +16,6 @@ That data can be accessed using iio_priv(struct iio_dev *).
 
 Then fill in the following:
 
-- indio_dev->dev.parent
-	Struct device associated with the underlying hardware.
 - indio_dev->name
 	Name of the device being driven - made available as the name
 	attribute in sysfs.
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index e846a0a7001e..655e34a08d94 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -676,7 +676,7 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
 
 /* Can we make this smaller? */
 #define IIO_ALIGN L1_CACHE_BYTES
-struct iio_dev *iio_device_alloc(int sizeof_priv);
+struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv);
 
 static inline void *iio_priv(const struct iio_dev *indio_dev)
 {
@@ -690,7 +690,7 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv)
 }
 
 void iio_device_free(struct iio_dev *indio_dev);
-struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv);
+struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv);
 struct iio_trigger *devm_iio_trigger_alloc(struct device *dev,
 						const char *fmt, ...);
 /**
-- 
cgit v1.2.3


From f5d017938e7a6517b85f7fd215213a28e11291fb Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 3 Jun 2020 14:40:19 +0300
Subject: iio: core: add iio_device_set_parent() helper

By default, the device allocation will also assign a parent device to the
IIO device object. In cases where devm_iio_device_alloc() is used,
sometimes the parent device must be different than the device used to
manage the allocation.

In that case, this helper should be used to change the parent, hence the
requirement to call this between allocation & registration.

This pattern/requirement is not very common in the IIO space, and it may be
cleaned up later.
But until then, assigning the parent manually between allocation &
registration is slightly easier.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 655e34a08d94..1c1d02107722 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -649,6 +649,26 @@ static inline struct iio_dev *iio_device_get(struct iio_dev *indio_dev)
 	return indio_dev ? dev_to_iio_dev(get_device(&indio_dev->dev)) : NULL;
 }
 
+/**
+ * iio_device_set_parent() - assign parent device to the IIO device object
+ * @indio_dev: 		IIO device structure
+ * @parent:		reference to parent device object
+ *
+ * This utility must be called between IIO device allocation
+ * (via devm_iio_device_alloc()) & IIO device registration
+ * (via {devm_}iio_device_register()).
+ * By default, the device allocation will also assign a parent device to
+ * the IIO device object. In cases where devm_iio_device_alloc() is used,
+ * sometimes the parent device must be different than the device used to
+ * manage the allocation.
+ * In that case, this helper should be used to change the parent, hence the
+ * requirement to call this between allocation & registration.
+ **/
+static inline void iio_device_set_parent(struct iio_dev *indio_dev,
+					 struct device *parent)
+{
+	indio_dev->dev.parent = parent;
+}
 
 /**
  * iio_device_set_drvdata() - Set device driver data
-- 
cgit v1.2.3


From 376bd28d03c97b4d53f5797d5f9b3522c8bd4d3d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 4 Jun 2020 18:09:41 +1000
Subject: crypto: ccp - Fix sparse warnings in sev-dev

This patch fixes a bunch of sparse warnings in sev-dev where the
__user marking is incorrectly handled.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: 7360e4b14350 ("crypto: ccp: Implement SEV_PEK_CERT_IMPORT...")
Fixes: e799035609e1 ("crypto: ccp: Implement SEV_PEK_CSR ioctl...")
Fixes: 76a2b524a4b1 ("crypto: ccp: Implement SEV_PDH_CERT_EXPORT...")
Fixes: d6112ea0cb34 ("crypto: ccp - introduce SEV_GET_ID2 command")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev.c | 23 ++++++++++++++++-------
 include/linux/psp-sev.h      |  2 +-
 2 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index a2426334be61..476113e12489 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -376,6 +376,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable)
 	struct sev_device *sev = psp_master->sev_data;
 	struct sev_user_data_pek_csr input;
 	struct sev_data_pek_csr *data;
+	void __user *input_address;
 	void *blob = NULL;
 	int ret;
 
@@ -394,6 +395,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable)
 		goto cmd;
 
 	/* allocate a physically contiguous buffer to store the CSR blob */
+	input_address = (void __user *)input.address;
 	if (input.length > SEV_FW_BLOB_MAX_SIZE) {
 		ret = -EFAULT;
 		goto e_free;
@@ -426,7 +428,7 @@ cmd:
 	}
 
 	if (blob) {
-		if (copy_to_user((void __user *)input.address, blob, input.length))
+		if (copy_to_user(input_address, blob, input.length))
 			ret = -EFAULT;
 	}
 
@@ -437,7 +439,7 @@ e_free:
 	return ret;
 }
 
-void *psp_copy_user_blob(u64 __user uaddr, u32 len)
+void *psp_copy_user_blob(u64 uaddr, u32 len)
 {
 	if (!uaddr || !len)
 		return ERR_PTR(-EINVAL);
@@ -446,7 +448,7 @@ void *psp_copy_user_blob(u64 __user uaddr, u32 len)
 	if (len > SEV_FW_BLOB_MAX_SIZE)
 		return ERR_PTR(-EINVAL);
 
-	return memdup_user((void __user *)(uintptr_t)uaddr, len);
+	return memdup_user((void __user *)uaddr, len);
 }
 EXPORT_SYMBOL_GPL(psp_copy_user_blob);
 
@@ -621,6 +623,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 {
 	struct sev_user_data_get_id2 input;
 	struct sev_data_get_id *data;
+	void __user *input_address;
 	void *id_blob = NULL;
 	int ret;
 
@@ -631,6 +634,8 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
 		return -EFAULT;
 
+	input_address = (void __user *)input.address;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -660,8 +665,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 	}
 
 	if (id_blob) {
-		if (copy_to_user((void __user *)input.address,
-				 id_blob, data->len)) {
+		if (copy_to_user(input_address, id_blob, data->len)) {
 			ret = -EFAULT;
 			goto e_free;
 		}
@@ -720,6 +724,8 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable)
 	struct sev_user_data_pdh_cert_export input;
 	void *pdh_blob = NULL, *cert_blob = NULL;
 	struct sev_data_pdh_cert_export *data;
+	void __user *input_cert_chain_address;
+	void __user *input_pdh_cert_address;
 	int ret;
 
 	/* If platform is not in INIT state then transition it to INIT. */
@@ -745,6 +751,9 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable)
 	    !input.cert_chain_address)
 		goto cmd;
 
+	input_pdh_cert_address = (void __user *)input.pdh_cert_address;
+	input_cert_chain_address = (void __user *)input.cert_chain_address;
+
 	/* Allocate a physically contiguous buffer to store the PDH blob. */
 	if (input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) {
 		ret = -EFAULT;
@@ -788,7 +797,7 @@ cmd:
 	}
 
 	if (pdh_blob) {
-		if (copy_to_user((void __user *)input.pdh_cert_address,
+		if (copy_to_user(input_pdh_cert_address,
 				 pdh_blob, input.pdh_cert_len)) {
 			ret = -EFAULT;
 			goto e_free_cert;
@@ -796,7 +805,7 @@ cmd:
 	}
 
 	if (cert_blob) {
-		if (copy_to_user((void __user *)input.cert_chain_address,
+		if (copy_to_user(input_cert_chain_address,
 				 cert_blob, input.cert_chain_len))
 			ret = -EFAULT;
 	}
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 7fbc8679145c..49d155cd2dfe 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -597,7 +597,7 @@ int sev_guest_df_flush(int *error);
  */
 int sev_guest_decommission(struct sev_data_decommission *data, int *error);
 
-void *psp_copy_user_blob(u64 __user uaddr, u32 len);
+void *psp_copy_user_blob(u64 uaddr, u32 len);
 
 #else	/* !CONFIG_CRYPTO_DEV_SP_PSP */
 
-- 
cgit v1.2.3


From e012d15a238f24795081ef1e43ffe2859b6538ed Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 15 Jun 2020 08:46:47 +0200
Subject: gpio: driver.h: fix kernel-doc markup

There is one parameter with a wrong name at kernel-doc macro:

./include/linux/gpio/driver.h:499: warning: Function parameter or member 'gc' not described in 'gpiochip_add_data'
./include/linux/gpio/driver.h:499: warning: Excess function parameter 'chip' description in 'gpiochip_add_data'

Fix it.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 include/linux/gpio/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c4f272af7af5..c11261f3c724 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -481,7 +481,7 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 /**
  * gpiochip_add_data() - register a gpio_chip
- * @chip: the chip to register, with chip->base initialized
+ * @gc: the chip to register, with chip->base initialized
  * @data: driver-private data associated with this chip
  *
  * Context: potentially before irqs will work
-- 
cgit v1.2.3


From 8e742aa79780b13cd300a42198c1a4cea9c89905 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Wed, 10 Jun 2020 13:48:51 +0200
Subject: syscalls: Fix offset type of ksys_ftruncate()

After the commit below, truncate() on x86 32bit uses ksys_ftruncate(). But
ksys_ftruncate() truncates the offset to unsigned long.

Switch the type of offset to loff_t which is what do_sys_ftruncate()
expects.

Fixes: 121b32a58a3a (x86/entry/32: Use IA32-specific wrappers for syscalls taking 64-bit arguments)
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Brian Gerst <brgerst@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20200610114851.28549-1-jslaby@suse.cz
---
 include/linux/syscalls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7c354c2955f5..b951a87da987 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1360,7 +1360,7 @@ static inline long ksys_lchown(const char __user *filename, uid_t user,
 
 extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 
-static inline long ksys_ftruncate(unsigned int fd, unsigned long length)
+static inline long ksys_ftruncate(unsigned int fd, loff_t length)
 {
 	return do_sys_ftruncate(fd, length, 1);
 }
-- 
cgit v1.2.3


From e17d43b93e544f5016c0251d2074c15568d5d963 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 12 May 2020 15:19:08 +0300
Subject: perf: Add perf text poke event

Record (single instruction) changes to the kernel text (i.e.
self-modifying code) in order to support tracers like Intel PT and
ARM CoreSight.

A copy of the running kernel code is needed as a reference point (e.g.
from /proc/kcore). The text poke event records the old bytes and the
new bytes so that the event can be processed forwards or backwards.

The basic problem is recording the modified instruction in an
unambiguous manner given SMP instruction cache (in)coherence. That is,
when modifying an instruction concurrently any solution with one or
multiple timestamps is not sufficient:

	CPU0				CPU1
 0
 1	write insn A
 2					execute insn A
 3	sync-I$
 4

Due to I$, CPU1 might execute either the old or new A. No matter where
we record tracepoints on CPU0, one simply cannot tell what CPU1 will
have observed, except that at 0 it must be the old one and at 4 it
must be the new one.

To solve this, take inspiration from x86 text poking, which has to
solve this exact problem due to variable length instruction encoding
and I-fetch windows.

 1) overwrite the instruction with a breakpoint and sync I$

This guarantees that that code flow will never hit the target
instruction anymore, on any CPU (or rather, it will cause an
exception).

 2) issue the TEXT_POKE event

 3) overwrite the breakpoint with the new instruction and sync I$

Now we know that any execution after the TEXT_POKE event will either
observe the breakpoint (and hit the exception) or the new instruction.

So by guarding the TEXT_POKE event with an exception on either side;
we can now tell, without doubt, which instruction another CPU will
have observed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200512121922.8997-2-adrian.hunter@intel.com
---
 include/linux/perf_event.h      |  8 ++++
 include/uapi/linux/perf_event.h | 21 +++++++++-
 kernel/events/core.c            | 90 ++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 117 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b4bb32082342..46fe5cfb5163 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1232,6 +1232,9 @@ extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
+extern void perf_event_text_poke(const void *addr,
+				 const void *old_bytes, size_t old_len,
+				 const void *new_bytes, size_t new_len);
 
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
@@ -1479,6 +1482,11 @@ static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_text_poke(const void *addr,
+					const void *old_bytes,
+					size_t old_len,
+					const void *new_bytes,
+					size_t new_len)			{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7b2d6fc9e6ed..e5bee6c17b86 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -383,7 +383,8 @@ struct perf_event_attr {
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
 				cgroup         :  1, /* include cgroup events */
-				__reserved_1   : 31;
+				text_poke      :  1, /* include text poke events */
+				__reserved_1   : 30;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1024,6 +1025,24 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_CGROUP			= 19,
 
+	/*
+	 * Records changes to kernel text i.e. self-modified code. 'old_len' is
+	 * the number of old bytes, 'new_len' is the number of new bytes. Either
+	 * 'old_len' or 'new_len' may be zero to indicate, for example, the
+	 * addition or removal of a trampoline. 'bytes' contains the old bytes
+	 * followed immediately by the new bytes.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				addr;
+	 *	u16				old_len;
+	 *	u16				new_len;
+	 *	u8				bytes[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_TEXT_POKE			= 20,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 856d98c36f56..9b8f92500833 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -394,6 +394,7 @@ static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
 static atomic_t nr_cgroup_events __read_mostly;
+static atomic_t nr_text_poke_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -4575,7 +4576,7 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch ||
+	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
 	return false;
@@ -4651,6 +4652,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_dec(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_dec(&nr_text_poke_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -8628,6 +8631,89 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_text_poke_event {
+	const void		*old_bytes;
+	const void		*new_bytes;
+	size_t			pad;
+	u16			old_len;
+	u16			new_len;
+
+	struct {
+		struct perf_event_header	header;
+
+		u64				addr;
+	} event_id;
+};
+
+static int perf_event_text_poke_match(struct perf_event *event)
+{
+	return event->attr.text_poke;
+}
+
+static void perf_event_text_poke_output(struct perf_event *event, void *data)
+{
+	struct perf_text_poke_event *text_poke_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u64 padding = 0;
+	int ret;
+
+	if (!perf_event_text_poke_match(event))
+		return;
+
+	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, text_poke_event->event_id);
+	perf_output_put(&handle, text_poke_event->old_len);
+	perf_output_put(&handle, text_poke_event->new_len);
+
+	__output_copy(&handle, text_poke_event->old_bytes, text_poke_event->old_len);
+	__output_copy(&handle, text_poke_event->new_bytes, text_poke_event->new_len);
+
+	if (text_poke_event->pad)
+		__output_copy(&handle, &padding, text_poke_event->pad);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_text_poke(const void *addr, const void *old_bytes,
+			  size_t old_len, const void *new_bytes, size_t new_len)
+{
+	struct perf_text_poke_event text_poke_event;
+	size_t tot, pad;
+
+	if (!atomic_read(&nr_text_poke_events))
+		return;
+
+	tot  = sizeof(text_poke_event.old_len) + old_len;
+	tot += sizeof(text_poke_event.new_len) + new_len;
+	pad  = ALIGN(tot, sizeof(u64)) - tot;
+
+	text_poke_event = (struct perf_text_poke_event){
+		.old_bytes    = old_bytes,
+		.new_bytes    = new_bytes,
+		.pad          = pad,
+		.old_len      = old_len,
+		.new_len      = new_len,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_TEXT_POKE,
+				.misc = PERF_RECORD_MISC_KERNEL,
+				.size = sizeof(text_poke_event.event_id) + tot + pad,
+			},
+			.addr = (unsigned long)addr,
+		},
+	};
+
+	perf_iterate_sb(perf_event_text_poke_output, &text_poke_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -10945,6 +11031,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_inc(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_inc(&nr_text_poke_events);
 
 	if (inc) {
 		/*
-- 
cgit v1.2.3


From d002b8bc6dbc20e9043e279196cff8795dba05fe Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 28 May 2020 11:00:58 +0300
Subject: kprobes: Add symbols for kprobe insn pages

Symbols are needed for tools to describe instruction addresses. Pages
allocated for kprobe's purposes need symbols to be created for them.
Add such symbols to be visible via /proc/kallsyms.

Note: kprobe insn pages are not used if ftrace is configured. To see the
effect of this patch, the kernel must be configured with:

	# CONFIG_FUNCTION_TRACER is not set
	CONFIG_KPROBES=y

and for optimised kprobes:

	CONFIG_OPTPROBES=y

Example on x86:

	# perf probe __schedule
	Added new event:
	  probe:__schedule     (on __schedule)
	# cat /proc/kallsyms | grep '\[__builtin__kprobes\]'
	ffffffffc00d4000 t kprobe_insn_page     [__builtin__kprobes]
	ffffffffc00d6000 t kprobe_optinsn_page  [__builtin__kprobes]

Note: This patch adds "__builtin__kprobes" as a module name in
/proc/kallsyms for symbols for pages allocated for kprobes' purposes, even
though "__builtin__kprobes" is not a module.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200528080058.20230-1-adrian.hunter@intel.com
---
 include/linux/kprobes.h | 15 +++++++++++++++
 kernel/kallsyms.c       | 37 +++++++++++++++++++++++++++++++++----
 kernel/kprobes.c        | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 594265bfd390..13fc58a74c04 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -373,6 +378,11 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 16c8c605f4b0..c6cc293c0e67 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -496,11 +498,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +551,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +576,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 50cd84f53df0..058c0be3464b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -118,6 +118,7 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_INSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
@@ -290,12 +291,34 @@ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
 	return ret;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_OPTINSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
 	/* .insn_size is initialized later */
 	.nr_garbage = 0,
@@ -2197,6 +2220,28 @@ static void kprobe_remove_ksym_blacklist(unsigned long entry)
 	kprobe_remove_area_blacklist(entry, entry + 1);
 }
 
+int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+				   char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym)
+{
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
+	if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym))
+		return 0;
+#ifdef CONFIG_OPTPROBES
+	if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym))
+		return 0;
+#endif
+#endif
+	if (!arch_kprobe_get_kallsym(&symnum, value, type, sym))
+		return 0;
+	return -ERANGE;
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
-- 
cgit v1.2.3


From fc0ea795f53c8d7040fa42471f74fe51d78d0834 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 12 May 2020 15:19:13 +0300
Subject: ftrace: Add symbols for ftrace trampolines

Symbols are needed for tools to describe instruction addresses. Pages
allocated for ftrace's purposes need symbols to be created for them.
Add such symbols to be visible via /proc/kallsyms.

Example on x86 with CONFIG_DYNAMIC_FTRACE=y

	# echo function > /sys/kernel/debug/tracing/current_tracer
	# cat /proc/kallsyms | grep '\[__builtin__ftrace\]'
	ffffffffc0238000 t ftrace_trampoline    [__builtin__ftrace]

Note: This patch adds "__builtin__ftrace" as a module name in /proc/kallsyms for
symbols for pages allocated for ftrace's purposes, even though "__builtin__ftrace"
is not a module.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200512121922.8997-7-adrian.hunter@intel.com
---
 include/linux/ftrace.h | 12 +++++---
 kernel/kallsyms.c      |  5 ++++
 kernel/trace/ftrace.c  | 77 ++++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 88 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e339dac91ee6..ce2c06f72e86 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -58,9 +58,6 @@ struct ftrace_direct_func;
 const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
-int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
-			   char *type, char *name,
-			   char *module_name, int *exported);
 #else
 static inline const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
@@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 {
 	return NULL;
 }
+#endif
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
 static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 					 char *type, char *name,
 					 char *module_name, int *exported)
@@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 }
 #endif
 
-
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -207,6 +210,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
+	struct list_head		list;
 #endif
 };
 
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index c6cc293c0e67..834bfdc43235 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -482,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c163c3531faf..31675b209db2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2764,6 +2764,38 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
+/* List of trace_ops that have allocated trampolines */
+static LIST_HEAD(ftrace_ops_trampoline_list);
+
+static void ftrace_add_trampoline_to_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_add_rcu(&ops->list, &ftrace_ops_trampoline_list);
+}
+
+static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_del_rcu(&ops->list);
+}
+
+/*
+ * "__builtin__ftrace" is used as a module name in /proc/kallsyms for symbols
+ * for pages allocated for ftrace purposes, even though "__builtin__ftrace" is
+ * not a module.
+ */
+#define FTRACE_TRAMPOLINE_MOD "__builtin__ftrace"
+#define FTRACE_TRAMPOLINE_SYM "ftrace_trampoline"
+
+static void ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
+	    ops->trampoline)
+		ftrace_remove_trampoline_from_kallsyms(ops);
+
+	arch_ftrace_trampoline_free(ops);
+}
+
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2934,7 +2966,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 			synchronize_rcu_tasks();
 
  free_ops:
-		arch_ftrace_trampoline_free(ops);
+		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
@@ -6178,6 +6210,27 @@ struct ftrace_mod_map {
 	unsigned int		num_funcs;
 };
 
+static int ftrace_get_trampoline_kallsym(unsigned int symnum,
+					 unsigned long *value, char *type,
+					 char *name, char *module_name,
+					 int *exported)
+{
+	struct ftrace_ops *op;
+
+	list_for_each_entry_rcu(op, &ftrace_ops_trampoline_list, list) {
+		if (!op->trampoline || symnum--)
+			continue;
+		*value = op->trampoline;
+		*type = 't';
+		strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+		strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+		*exported = 0;
+		return 0;
+	}
+
+	return -ERANGE;
+}
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6514,6 +6567,7 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 {
 	struct ftrace_mod_map *mod_map;
 	struct ftrace_mod_func *mod_func;
+	int ret;
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
@@ -6540,8 +6594,10 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 		WARN_ON(1);
 		break;
 	}
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
 	preempt_enable();
-	return -ERANGE;
+	return ret;
 }
 
 #else
@@ -6553,6 +6609,18 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	return NULL;
 }
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name, char *module_name,
+			   int *exported)
+{
+	int ret;
+
+	preempt_disable();
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
+	preempt_enable();
+	return ret;
+}
 #endif /* CONFIG_MODULES */
 
 struct ftrace_init_func {
@@ -6733,7 +6801,12 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
+	unsigned long trampoline = ops->trampoline;
+
 	arch_ftrace_update_trampoline(ops);
+	if (ops->trampoline && ops->trampoline != trampoline &&
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+		ftrace_add_trampoline_to_kallsyms(ops);
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)
-- 
cgit v1.2.3


From 3dc167ba5729ddd2d8e3fa1841653792c295d3f1 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 19 May 2020 19:25:06 +0200
Subject: sched/cputime: Improve cputime_adjust()

People report that utime and stime from /proc/<pid>/stat become very
wrong when the numbers are big enough, especially if you watch these
counters incrementally.

Specifically, the current implementation of: stime*rtime/total,
results in a saw-tooth function on top of the desired line, where the
teeth grow in size the larger the values become. IOW, it has a
relative error.

The result is that, when watching incrementally as time progresses
(for large values), we'll see periods of pure stime or utime increase,
irrespective of the actual ratio we're striving for.

Replace scale_stime() with a math64.h helper: mul_u64_u64_div_u64()
that is far more accurate. This also allows architectures to override
the implementation -- for instance they can opt for the old algorithm
if this new one turns out to be too expensive for them.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200519172506.GA317395@hirez.programming.kicks-ass.net
---
 arch/x86/include/asm/div64.h | 14 ++++++++++++--
 include/linux/math64.h       |  2 ++
 kernel/sched/cputime.c       | 46 +-------------------------------------------
 lib/math/div64.c             | 41 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9b8cb50768c2..b8f1dc0761e4 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -74,16 +74,26 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 #else
 # include <asm-generic/div64.h>
 
-static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+/*
+ * Will generate an #DE when the result doesn't fit u64, could fix with an
+ * __ex_table[] entry when it becomes an issue.
+ */
+static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div)
 {
 	u64 q;
 
 	asm ("mulq %2; divq %3" : "=a" (q)
-				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "a" (a), "rm" (mul), "rm" (div)
 				: "rdx");
 
 	return q;
 }
+#define mul_u64_u64_div_u64 mul_u64_u64_div_u64
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	return mul_u64_u64_div_u64(a, mul, div);
+}
 #define mul_u64_u32_div	mul_u64_u32_div
 
 #endif /* CONFIG_X86_32 */
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 11a267413e8e..d097119419e6 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -263,6 +263,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
+u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
+
 #define DIV64_U64_ROUND_UP(ll, d)	\
 	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ff9435dee1df..5a55d2300452 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -519,50 +519,6 @@ void account_idle_ticks(unsigned long ticks)
 	account_idle_time(cputime);
 }
 
-/*
- * Perform (stime * rtime) / total, but avoid multiplication overflow by
- * losing precision when the numbers are big.
- */
-static u64 scale_stime(u64 stime, u64 rtime, u64 total)
-{
-	u64 scaled;
-
-	for (;;) {
-		/* Make sure "rtime" is the bigger of stime/rtime */
-		if (stime > rtime)
-			swap(rtime, stime);
-
-		/* Make sure 'total' fits in 32 bits */
-		if (total >> 32)
-			goto drop_precision;
-
-		/* Does rtime (and thus stime) fit in 32 bits? */
-		if (!(rtime >> 32))
-			break;
-
-		/* Can we just balance rtime/stime rather than dropping bits? */
-		if (stime >> 31)
-			goto drop_precision;
-
-		/* We can grow stime and shrink rtime and try to make them both fit */
-		stime <<= 1;
-		rtime >>= 1;
-		continue;
-
-drop_precision:
-		/* We drop from rtime, it has more bits than stime */
-		rtime >>= 1;
-		total >>= 1;
-	}
-
-	/*
-	 * Make sure gcc understands that this is a 32x32->64 multiply,
-	 * followed by a 64/32->64 divide.
-	 */
-	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
-	return scaled;
-}
-
 /*
  * Adjust tick based cputime random precision against scheduler runtime
  * accounting.
@@ -622,7 +578,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 		goto update;
 	}
 
-	stime = scale_stime(stime, rtime, stime + utime);
+	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
 
 update:
 	/*
diff --git a/lib/math/div64.c b/lib/math/div64.c
index 368ca7fd0d82..3952a07130d8 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -190,3 +190,44 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return __iter_div_u64_rem(dividend, divisor, remainder);
 }
 EXPORT_SYMBOL(iter_div_u64_rem);
+
+#ifndef mul_u64_u64_div_u64
+u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c)
+{
+	u64 res = 0, div, rem;
+	int shift;
+
+	/* can a * b overflow ? */
+	if (ilog2(a) + ilog2(b) > 62) {
+		/*
+		 * (b * a) / c is equal to
+		 *
+		 *      (b / c) * a +
+		 *      (b % c) * a / c
+		 *
+		 * if nothing overflows. Can the 1st multiplication
+		 * overflow? Yes, but we do not care: this can only
+		 * happen if the end result can't fit in u64 anyway.
+		 *
+		 * So the code below does
+		 *
+		 *      res = (b / c) * a;
+		 *      b = b % c;
+		 */
+		div = div64_u64_rem(b, c, &rem);
+		res = div * a;
+		b = rem;
+
+		shift = ilog2(a) + ilog2(b) - 62;
+		if (shift > 0) {
+			/* drop precision */
+			b >>= shift;
+			c >>= shift;
+			if (!c)
+				return res;
+		}
+	}
+
+	return res + div64_u64(a * b, c);
+}
+#endif
-- 
cgit v1.2.3


From 461daba06bdcb9c7a3f92b9bbd110e1f7d093ffc Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Thu, 28 May 2020 12:54:42 -0700
Subject: psi: eliminate kthread_worker from psi trigger scheduling mechanism

Each psi group requires a dedicated kthread_delayed_work and
kthread_worker. Since no other work can be performed using psi_group's
kthread_worker, the same result can be obtained using a task_struct and
a timer directly. This makes psi triggering simpler by removing lists
and locks involved with kthread_worker usage and eliminates the need for
poll_scheduled atomic use in the hot path.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200528195442.190116-1-surenb@google.com
---
 include/linux/psi_types.h |   7 +--
 kernel/sched/psi.c        | 113 ++++++++++++++++++++++++++--------------------
 2 files changed, 68 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 4b7258495a04..b95f3211566a 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -153,9 +153,10 @@ struct psi_group {
 	unsigned long avg[NR_PSI_STATES - 1][3];
 
 	/* Monitor work control */
-	atomic_t poll_scheduled;
-	struct kthread_worker __rcu *poll_kworker;
-	struct kthread_delayed_work poll_work;
+	struct task_struct __rcu *poll_task;
+	struct timer_list poll_timer;
+	wait_queue_head_t poll_wait;
+	atomic_t poll_wakeup;
 
 	/* Protects data used by the monitor */
 	struct mutex trigger_lock;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 8f45cdb6463b..e53b711bd643 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,7 +190,6 @@ static void group_init(struct psi_group *group)
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
-	atomic_set(&group->poll_scheduled, 0);
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
 	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
@@ -199,7 +198,7 @@ static void group_init(struct psi_group *group)
 	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
 	group->polling_until = 0;
-	rcu_assign_pointer(group->poll_kworker, NULL);
+	rcu_assign_pointer(group->poll_task, NULL);
 }
 
 void __init psi_init(void)
@@ -547,47 +546,38 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	return now + group->poll_min_period;
 }
 
-/*
- * Schedule polling if it's not already scheduled. It's safe to call even from
- * hotpath because even though kthread_queue_delayed_work takes worker->lock
- * spinlock that spinlock is never contended due to poll_scheduled atomic
- * preventing such competition.
- */
+/* Schedule polling if it's not already scheduled. */
 static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
 {
-	struct kthread_worker *kworker;
+	struct task_struct *task;
 
-	/* Do not reschedule if already scheduled */
-	if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+	/*
+	 * Do not reschedule if already scheduled.
+	 * Possible race with a timer scheduled after this check but before
+	 * mod_timer below can be tolerated because group->polling_next_update
+	 * will keep updates on schedule.
+	 */
+	if (timer_pending(&group->poll_timer))
 		return;
 
 	rcu_read_lock();
 
-	kworker = rcu_dereference(group->poll_kworker);
+	task = rcu_dereference(group->poll_task);
 	/*
 	 * kworker might be NULL in case psi_trigger_destroy races with
 	 * psi_task_change (hotpath) which can't use locks
 	 */
-	if (likely(kworker))
-		kthread_queue_delayed_work(kworker, &group->poll_work, delay);
-	else
-		atomic_set(&group->poll_scheduled, 0);
+	if (likely(task))
+		mod_timer(&group->poll_timer, jiffies + delay);
 
 	rcu_read_unlock();
 }
 
-static void psi_poll_work(struct kthread_work *work)
+static void psi_poll_work(struct psi_group *group)
 {
-	struct kthread_delayed_work *dwork;
-	struct psi_group *group;
 	u32 changed_states;
 	u64 now;
 
-	dwork = container_of(work, struct kthread_delayed_work, work);
-	group = container_of(dwork, struct psi_group, poll_work);
-
-	atomic_set(&group->poll_scheduled, 0);
-
 	mutex_lock(&group->trigger_lock);
 
 	now = sched_clock();
@@ -623,6 +613,35 @@ out:
 	mutex_unlock(&group->trigger_lock);
 }
 
+static int psi_poll_worker(void *data)
+{
+	struct psi_group *group = (struct psi_group *)data;
+	struct sched_param param = {
+		.sched_priority = 1,
+	};
+
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+
+	while (true) {
+		wait_event_interruptible(group->poll_wait,
+				atomic_cmpxchg(&group->poll_wakeup, 1, 0) ||
+				kthread_should_stop());
+		if (kthread_should_stop())
+			break;
+
+		psi_poll_work(group);
+	}
+	return 0;
+}
+
+static void poll_timer_fn(struct timer_list *t)
+{
+	struct psi_group *group = from_timer(group, t, poll_timer);
+
+	atomic_set(&group->poll_wakeup, 1);
+	wake_up_interruptible(&group->poll_wait);
+}
+
 static void record_times(struct psi_group_cpu *groupc, int cpu,
 			 bool memstall_tick)
 {
@@ -1099,22 +1118,20 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 
 	mutex_lock(&group->trigger_lock);
 
-	if (!rcu_access_pointer(group->poll_kworker)) {
-		struct sched_param param = {
-			.sched_priority = 1,
-		};
-		struct kthread_worker *kworker;
+	if (!rcu_access_pointer(group->poll_task)) {
+		struct task_struct *task;
 
-		kworker = kthread_create_worker(0, "psimon");
-		if (IS_ERR(kworker)) {
+		task = kthread_create(psi_poll_worker, group, "psimon");
+		if (IS_ERR(task)) {
 			kfree(t);
 			mutex_unlock(&group->trigger_lock);
-			return ERR_CAST(kworker);
+			return ERR_CAST(task);
 		}
-		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-		kthread_init_delayed_work(&group->poll_work,
-				psi_poll_work);
-		rcu_assign_pointer(group->poll_kworker, kworker);
+		atomic_set(&group->poll_wakeup, 0);
+		init_waitqueue_head(&group->poll_wait);
+		wake_up_process(task);
+		timer_setup(&group->poll_timer, poll_timer_fn, 0);
+		rcu_assign_pointer(group->poll_task, task);
 	}
 
 	list_add(&t->node, &group->triggers);
@@ -1132,7 +1149,7 @@ static void psi_trigger_destroy(struct kref *ref)
 {
 	struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
 	struct psi_group *group = t->group;
-	struct kthread_worker *kworker_to_destroy = NULL;
+	struct task_struct *task_to_destroy = NULL;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
@@ -1158,13 +1175,13 @@ static void psi_trigger_destroy(struct kref *ref)
 			period = min(period, div_u64(tmp->win.size,
 					UPDATES_PER_WINDOW));
 		group->poll_min_period = period;
-		/* Destroy poll_kworker when the last trigger is destroyed */
+		/* Destroy poll_task when the last trigger is destroyed */
 		if (group->poll_states == 0) {
 			group->polling_until = 0;
-			kworker_to_destroy = rcu_dereference_protected(
-					group->poll_kworker,
+			task_to_destroy = rcu_dereference_protected(
+					group->poll_task,
 					lockdep_is_held(&group->trigger_lock));
-			rcu_assign_pointer(group->poll_kworker, NULL);
+			rcu_assign_pointer(group->poll_task, NULL);
 		}
 	}
 
@@ -1172,25 +1189,23 @@ static void psi_trigger_destroy(struct kref *ref)
 
 	/*
 	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_kworker RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_kworker
+	 * poll_task RCUs to complete their read-side critical sections
+	 * before destroying the trigger and optionally the poll_task
 	 */
 	synchronize_rcu();
 	/*
 	 * Destroy the kworker after releasing trigger_lock to prevent a
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
-	if (kworker_to_destroy) {
+	if (task_to_destroy) {
 		/*
 		 * After the RCU grace period has expired, the worker
-		 * can no longer be found through group->poll_kworker.
+		 * can no longer be found through group->poll_task.
 		 * But it might have been already scheduled before
 		 * that - deschedule it cleanly before destroying it.
 		 */
-		kthread_cancel_delayed_work_sync(&group->poll_work);
-		atomic_set(&group->poll_scheduled, 0);
-
-		kthread_destroy_worker(kworker_to_destroy);
+		del_timer_sync(&group->poll_timer);
+		kthread_stop(task_to_destroy);
 	}
 	kfree(t);
 }
-- 
cgit v1.2.3


From 9cc5b8656892a72438ee7deb5e80f5be47643b8b Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 27 May 2020 16:29:09 +0200
Subject: isolcpus: Affine unbound kernel threads to housekeeping cpus

This is a kernel enhancement that configures the cpu affinity of kernel
threads via kernel boot option nohz_full=.

When this option is specified, the cpumask is immediately applied upon
kthread launch. This does not affect kernel threads that specify cpu
and node.

This allows CPU isolation (that is not allowing certain threads
to execute on certain CPUs) without using the isolcpus=domain parameter,
making it possible to enable load balancing on such CPUs
during runtime (see kernel-parameters.txt).

Note-1: this is based off on Wind River's patch at
https://github.com/starlingx-staging/stx-integ/blob/master/kernel/kernel-std/centos/patches/affine-compute-kernel-threads.patch

Difference being that this patch is limited to modifying kernel thread
cpumask. Behaviour of other threads can be controlled via cgroups or
sched_setaffinity.

Note-2: Wind River's patch was based off Christoph Lameter's patch at
https://lwn.net/Articles/565932/ with the only difference being
the kernel parameter changed from kthread to kthread_cpus.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200527142909.23372-3-frederic@kernel.org
---
 include/linux/sched/isolation.h | 1 +
 kernel/kthread.c                | 6 ++++--
 kernel/sched/isolation.c        | 3 ++-
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 0fbcbacd1b29..cc9f393e2a70 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -14,6 +14,7 @@ enum hk_flags {
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
 	HK_FLAG_MANAGED_IRQ	= (1 << 7),
+	HK_FLAG_KTHREAD		= (1 << 8),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b86d37cda109..032b610912b0 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -27,6 +27,7 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 #include <trace/events/sched.h>
 
 
@@ -383,7 +384,8 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(task, cpu_possible_mask);
+		set_cpus_allowed_ptr(task,
+				     housekeeping_cpumask(HK_FLAG_KTHREAD));
 	}
 	kfree(create);
 	return task;
@@ -608,7 +610,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, cpu_possible_mask);
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 808244f3ddd9..5a6ea03f9882 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,7 +140,8 @@ static int __init housekeeping_nohz_full_setup(char *str)
 {
 	unsigned int flags;
 
-	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
+		HK_FLAG_MISC | HK_FLAG_KTHREAD;
 
 	return housekeeping_setup(str, flags);
 }
-- 
cgit v1.2.3


From b4098bfc5efb1fd7ecf40165132a1283aeea3500 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 26 Jul 2019 16:54:10 +0200
Subject: sched/deadline: Impose global limits on sched_attr::sched_period

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726161357.397880775@infradead.org
---
 include/linux/sched/sysctl.h |  3 +++
 kernel/sched/deadline.c      | 23 +++++++++++++++++++++--
 kernel/sysctl.c              | 14 ++++++++++++++
 3 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 660ac49f2b53..24be30a40814 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -61,6 +61,9 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
+extern unsigned int sysctl_sched_dl_period_max;
+extern unsigned int sysctl_sched_dl_period_min;
+
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 504d2f51b0d6..f31964ad9c2e 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2634,6 +2634,14 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_flags = dl_se->flags;
 }
 
+/*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+
 /*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
@@ -2646,6 +2654,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  */
 bool __checkparam_dl(const struct sched_attr *attr)
 {
+	u64 period, max, min;
+
 	/* special dl tasks don't actually use any parameter */
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return true;
@@ -2669,12 +2679,21 @@ bool __checkparam_dl(const struct sched_attr *attr)
 	    attr->sched_period & (1ULL << 63))
 		return false;
 
+	period = attr->sched_period;
+	if (!period)
+		period = attr->sched_deadline;
+
 	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
+	if (period < attr->sched_deadline ||
 	    attr->sched_deadline < attr->sched_runtime)
 		return false;
 
+	max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
+	min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
+
+	if (period < min || period > max)
+		return false;
+
 	return true;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db1ce7af2563..4aea67d3d552 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1779,6 +1779,20 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
+	{
+		.procname	= "sched_deadline_period_max_us",
+		.data		= &sysctl_sched_dl_period_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sched_deadline_period_min_us",
+		.data		= &sysctl_sched_dl_period_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "sched_rr_timeslice_ms",
 		.data		= &sysctl_sched_rr_timeslice,
-- 
cgit v1.2.3


From e79302ae8c8cceb51cf642d5ace9da02668cb7b4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 2 Jun 2020 17:04:03 +0200
Subject: kcsan: Remove __no_kcsan_or_inline

There are no more user of this function attribute, also, with us now
actively supporting '__no_kcsan inline' it doesn't make sense to have
in any case.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 Documentation/dev-tools/kcsan.rst | 6 ------
 include/linux/compiler_types.h    | 5 +----
 2 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/dev-tools/kcsan.rst b/Documentation/dev-tools/kcsan.rst
index ce4bbd918648..b38379f06194 100644
--- a/Documentation/dev-tools/kcsan.rst
+++ b/Documentation/dev-tools/kcsan.rst
@@ -114,12 +114,6 @@ the below options are available:
   To dynamically limit for which functions to generate reports, see the
   `DebugFS interface`_ blacklist/whitelist feature.
 
-  For ``__always_inline`` functions, replace ``__always_inline`` with
-  ``__no_kcsan_or_inline`` (which implies ``__always_inline``)::
-
-    static __no_kcsan_or_inline void foo(void) {
-        ...
-
 * To disable data race detection for a particular compilation unit, add to the
   ``Makefile``::
 
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 21aed0981edf..938249809511 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -193,10 +193,7 @@ struct ftrace_likely_data {
 
 #define __no_kcsan __no_sanitize_thread
 #ifdef __SANITIZE_THREAD__
-# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused
-# define __no_sanitize_or_inline __no_kcsan_or_inline
-#else
-# define __no_kcsan_or_inline __always_inline
+# define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused
 #endif
 
 #ifndef __no_sanitize_or_inline
-- 
cgit v1.2.3


From 5ddbc4082e1072eeeae52ff561a88620a05be08f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 2 Jun 2020 18:47:11 +0200
Subject: x86, kcsan: Add __no_kcsan to noinstr

The 'noinstr' function attribute means no-instrumentation, this should
very much include *SAN. Because lots of that is broken at present,
only include KCSAN for now, as that is limited to clang11, which has
sane function attribute behaviour.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/compiler_types.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 938249809511..a8b4266084a1 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -118,10 +118,6 @@ struct ftrace_likely_data {
 #define notrace			__attribute__((__no_instrument_function__))
 #endif
 
-/* Section for code which can't be instrumented at all */
-#define noinstr								\
-	noinline notrace __attribute((__section__(".noinstr.text")))
-
 /*
  * it doesn't make sense on ARM (currently the only user of __naked)
  * to trace naked functions because then mcount is called without
@@ -200,6 +196,10 @@ struct ftrace_likely_data {
 #define __no_sanitize_or_inline __always_inline
 #endif
 
+/* Section for code which can't be instrumented at all */
+#define noinstr								\
+	noinline notrace __attribute((__section__(".noinstr.text"))) __no_kcsan
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
-- 
cgit v1.2.3


From 5144f8a8dfd7b3681f0a2b5bf599a210b2315018 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Thu, 4 Jun 2020 07:58:11 +0200
Subject: compiler_types.h: Add __no_sanitize_{address,undefined} to noinstr

Adds the portable definitions for __no_sanitize_address, and
__no_sanitize_undefined, and subsequently changes noinstr to use the
attributes to disable instrumentation via KASAN or UBSAN.

Reported-by: syzbot+dc1fa714cb070b184db5@syzkaller.appspotmail.com
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Link: https://lore.kernel.org/lkml/000000000000d2474c05a6c938fe@google.com/
---
 include/linux/compiler-clang.h | 8 ++++++++
 include/linux/compiler-gcc.h   | 6 ++++++
 include/linux/compiler_types.h | 3 ++-
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index ee37256ec8bd..5e55302e3bf6 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -33,6 +33,14 @@
 #define __no_sanitize_thread
 #endif
 
+#if __has_feature(undefined_behavior_sanitizer)
+/* GCC does not have __SANITIZE_UNDEFINED__ */
+#define __no_sanitize_undefined \
+		__attribute__((no_sanitize("undefined")))
+#else
+#define __no_sanitize_undefined
+#endif
+
 /*
  * Not all versions of clang implement the the type-generic versions
  * of the builtin overflow checkers. Fortunately, clang implements
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7dd4e0349ef3..1c74464c80c6 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -150,6 +150,12 @@
 #define __no_sanitize_thread
 #endif
 
+#if __has_attribute(__no_sanitize_undefined__)
+#define __no_sanitize_undefined __attribute__((no_sanitize_undefined))
+#else
+#define __no_sanitize_undefined
+#endif
+
 #if GCC_VERSION >= 50100
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index a8b4266084a1..85b8d2370c24 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -198,7 +198,8 @@ struct ftrace_likely_data {
 
 /* Section for code which can't be instrumented at all */
 #define noinstr								\
-	noinline notrace __attribute((__section__(".noinstr.text"))) __no_kcsan
+	noinline notrace __attribute((__section__(".noinstr.text")))	\
+	__no_kcsan __no_sanitize_address __no_sanitize_undefined
 
 #endif /* __KERNEL__ */
 
-- 
cgit v1.2.3


From 6b643a07a7e41f9e11cfbb9bba4c5c9791ac2997 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 3 Jun 2020 20:09:06 +0200
Subject: x86/entry, ubsan, objtool: Whitelist __ubsan_handle_*()

The UBSAN instrumentation only inserts external CALLs when things go
'BAD', much like WARN(). So treat them similar to WARN()s for noinstr,
that is: allow them, at the risk of taking the machine down, to get
their message out.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Marco Elver <elver@google.com>
---
 include/linux/compiler_types.h |  2 +-
 tools/objtool/check.c          | 28 +++++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 85b8d2370c24..14513e88b7e0 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -199,7 +199,7 @@ struct ftrace_likely_data {
 /* Section for code which can't be instrumented at all */
 #define noinstr								\
 	noinline notrace __attribute((__section__(".noinstr.text")))	\
-	__no_kcsan __no_sanitize_address __no_sanitize_undefined
+	__no_kcsan __no_sanitize_address
 
 #endif /* __KERNEL__ */
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5fbb90a80d23..3e214f879ada 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2190,10 +2190,36 @@ static inline const char *call_dest_name(struct instruction *insn)
 	return "{dynamic}";
 }
 
+static inline bool noinstr_call_dest(struct symbol *func)
+{
+	/*
+	 * We can't deal with indirect function calls at present;
+	 * assume they're instrumented.
+	 */
+	if (!func)
+		return false;
+
+	/*
+	 * If the symbol is from a noinstr section; we good.
+	 */
+	if (func->sec->noinstr)
+		return true;
+
+	/*
+	 * The __ubsan_handle_*() calls are like WARN(), they only happen when
+	 * something 'BAD' happened. At the risk of taking the machine down,
+	 * let them proceed to get the message out.
+	 */
+	if (!strncmp(func->name, "__ubsan_handle_", 15))
+		return true;
+
+	return false;
+}
+
 static int validate_call(struct instruction *insn, struct insn_state *state)
 {
 	if (state->noinstr && state->instr <= 0 &&
-	    (!insn->call_dest || !insn->call_dest->sec->noinstr)) {
+	    !noinstr_call_dest(insn->call_dest)) {
 		WARN_FUNC("call to %s() leaves .noinstr.text section",
 				insn->sec, insn->offset, call_dest_name(insn));
 		return 1;
-- 
cgit v1.2.3


From 7318d4cc14c8c8a5dde2b0b72ea50fd2545f0b7a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 21 Apr 2020 12:09:13 +0200
Subject: sched: Provide sched_set_fifo()

SCHED_FIFO (or any static priority scheduler) is a broken scheduler
model; it is fundamentally incapable of resource management, the one
thing an OS is actually supposed to do.

It is impossible to compose static priority workloads. One cannot take
two well designed and functional static priority workloads and mash
them together and still expect them to work.

Therefore it doesn't make sense to expose the priority field; the
kernel is fundamentally incapable of setting a sensible value, it
needs systems knowledge that it doesn't have.

Take away sched_setschedule() / sched_setattr() from modules and
replace them with:

  - sched_set_fifo(p); create a FIFO task (at prio 50)
  - sched_set_fifo_low(p); create a task higher than NORMAL,
	which ends up being a FIFO task at prio 1.
  - sched_set_normal(p, nice); (re)set the task to normal

This stops the proliferation of randomly chosen, and irrelevant, FIFO
priorities that dont't really mean anything anyway.

The system administrator/integrator, whoever has insight into the
actual system design and requirements (userspace) can set-up
appropriate priorities if and when needed.

Cc: airlied@redhat.com
Cc: alexander.deucher@amd.com
Cc: awalls@md.metrocast.net
Cc: axboe@kernel.dk
Cc: broonie@kernel.org
Cc: daniel.lezcano@linaro.org
Cc: gregkh@linuxfoundation.org
Cc: hannes@cmpxchg.org
Cc: herbert@gondor.apana.org.au
Cc: hverkuil@xs4all.nl
Cc: john.stultz@linaro.org
Cc: nico@fluxnic.net
Cc: paulmck@kernel.org
Cc: rafael.j.wysocki@intel.com
Cc: rmk+kernel@arm.linux.org.uk
Cc: sudeep.holla@arm.com
Cc: tglx@linutronix.de
Cc: ulf.hansson@linaro.org
Cc: wim@linux-watchdog.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/sched.h |  3 +++
 kernel/sched/core.c   | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b62e6aaf28f0..b792b8f0f4cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1653,6 +1653,9 @@ extern int idle_cpu(int cpu);
 extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
+extern int sched_set_fifo(struct task_struct *p);
+extern int sched_set_fifo_low(struct task_struct *p);
+extern int sched_set_normal(struct task_struct *p, int nice);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);
 extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0208b71bef80..40d3939b0520 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5124,6 +5124,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Use sched_set_fifo(), read its comment.
+ *
  * Return: 0 on success. An error code otherwise.
  *
  * NOTE that the task may be already dead.
@@ -5166,6 +5168,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
 
+/*
+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
+ * incapable of resource management, which is the one thing an OS really should
+ * be doing.
+ *
+ * This is of course the reason it is limited to privileged users only.
+ *
+ * Worse still; it is fundamentally impossible to compose static priority
+ * workloads. You cannot take two correctly working static prio workloads
+ * and smash them together and still expect them to work.
+ *
+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
+ *
+ *   MAX_RT_PRIO / 2
+ *
+ * The administrator _MUST_ configure the system, the kernel simply doesn't
+ * know enough information to make a sensible choice.
+ */
+int sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo);
+
+/*
+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
+ */
+int sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+int sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	return sched_setattr_nocheck(p, &attr);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
+
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
-- 
cgit v1.2.3


From 8b700983de82f79e05b2c1136d6513ea4c9b22c4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 22 Apr 2020 13:10:04 +0200
Subject: sched: Remove sched_set_*() return value

Ingo suggested that since the new sched_set_*() functions are
implemented using the 'nocheck' variants, they really shouldn't ever
fail, so remove the return value.

Cc: axboe@kernel.dk
Cc: daniel.lezcano@linaro.org
Cc: sudeep.holla@arm.com
Cc: airlied@redhat.com
Cc: broonie@kernel.org
Cc: paulmck@kernel.org
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/block/drbd/drbd_receiver.c    |  4 +---
 drivers/firmware/psci/psci_checker.c  |  3 +--
 drivers/gpu/drm/msm/msm_drv.c         |  5 +----
 drivers/platform/chrome/cros_ec_spi.c |  7 +++----
 include/linux/sched.h                 |  6 +++---
 kernel/rcu/rcutorture.c               |  5 +----
 kernel/sched/core.c                   | 12 ++++++------
 7 files changed, 16 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 140fd98274b1..280615efef74 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -6020,9 +6020,7 @@ int drbd_ack_receiver(struct drbd_thread *thi)
 	int expect   = header_size;
 	bool ping_timeout_active = false;
 
-	rv = sched_set_fifo_low(current);
-	if (rv < 0)
-		drbd_err(connection, "drbd_ack_receiver: ERROR set priority, ret=%d\n", rv);
+	sched_set_fifo_low(current);
 
 	while (get_t_state(thi) == RUNNING) {
 		drbd_thread_current_set_cpu(thi);
diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c
index a5279a430274..6fff482847e7 100644
--- a/drivers/firmware/psci/psci_checker.c
+++ b/drivers/firmware/psci/psci_checker.c
@@ -281,8 +281,7 @@ static int suspend_test_thread(void *arg)
 	wait_for_completion(&suspend_threads_started);
 
 	/* Set maximum priority to preempt all other threads on this CPU. */
-	if (sched_set_fifo(current))
-		pr_warn("Failed to set suspend thread scheduler on CPU %d\n", cpu);
+	sched_set_fifo(current);
 
 	dev = this_cpu_read(cpuidle_devices);
 	drv = cpuidle_get_cpu_driver(dev);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 89a8b9c7e044..556cca38487c 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -509,10 +509,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 			goto err_msm_uninit;
 		}
 
-		ret = sched_set_fifo(priv->event_thread[i].thread);
-		if (ret)
-			dev_warn(dev, "event_thread set priority failed:%d\n",
-				 ret);
+		sched_set_fifo(priv->event_thread[i].thread);
 	}
 
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c
index c20a43a97040..d09260382550 100644
--- a/drivers/platform/chrome/cros_ec_spi.c
+++ b/drivers/platform/chrome/cros_ec_spi.c
@@ -725,10 +725,9 @@ static int cros_ec_spi_devm_high_pri_alloc(struct device *dev,
 	if (err)
 		return err;
 
-	err = sched_set_fifo(ec_spi->high_pri_worker->task);
-	if (err)
-		dev_err(dev, "Can't set cros_ec high pri priority: %d\n", err);
-	return err;
+	sched_set_fifo(ec_spi->high_pri_worker->task);
+
+	return 0;
 }
 
 static int cros_ec_spi_probe(struct spi_device *spi)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b792b8f0f4cf..ae7664492af2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1653,9 +1653,9 @@ extern int idle_cpu(int cpu);
 extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
-extern int sched_set_fifo(struct task_struct *p);
-extern int sched_set_fifo_low(struct task_struct *p);
-extern int sched_set_normal(struct task_struct *p, int nice);
+extern void sched_set_fifo(struct task_struct *p);
+extern void sched_set_fifo_low(struct task_struct *p);
+extern void sched_set_normal(struct task_struct *p, int nice);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);
 extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index bbc3c8a9e7b9..b4c1146de414 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -893,10 +893,7 @@ static int rcu_torture_boost(void *arg)
 	VERBOSE_TOROUT_STRING("rcu_torture_boost started");
 
 	/* Set real-time priority. */
-	if (sched_set_fifo_low(current) < 0) {
-		VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
-		n_rcu_torture_boost_rterror++;
-	}
+	sched_set_fifo_low(current);
 
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f882d3d74dad..41d3778ea80e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5183,30 +5183,30 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
  * The administrator _MUST_ configure the system, the kernel simply doesn't
  * know enough information to make a sensible choice.
  */
-int sched_set_fifo(struct task_struct *p)
+void sched_set_fifo(struct task_struct *p)
 {
 	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
-	return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp);
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
 }
 EXPORT_SYMBOL_GPL(sched_set_fifo);
 
 /*
  * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
  */
-int sched_set_fifo_low(struct task_struct *p)
+void sched_set_fifo_low(struct task_struct *p)
 {
 	struct sched_param sp = { .sched_priority = 1 };
-	return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp);
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
 }
 EXPORT_SYMBOL_GPL(sched_set_fifo_low);
 
-int sched_set_normal(struct task_struct *p, int nice)
+void sched_set_normal(struct task_struct *p, int nice)
 {
 	struct sched_attr attr = {
 		.sched_policy = SCHED_NORMAL,
 		.sched_nice = nice,
 	};
-	return sched_setattr_nocheck(p, &attr);
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
 }
 EXPORT_SYMBOL_GPL(sched_set_normal);
 
-- 
cgit v1.2.3


From 7dfc06a0f25b593a9f51992f540c0f80a57f3629 Mon Sep 17 00:00:00 2001
From: Fabian Vogt <fvogt@suse.de>
Date: Mon, 15 Jun 2020 09:16:36 +0200
Subject: efi/tpm: Verify event log header before parsing

It is possible that the first event in the event log is not actually a
log header at all, but rather a normal event. This leads to the cast in
__calc_tpm2_event_size being an invalid conversion, which means that
the values read are effectively garbage. Depending on the first event's
contents, this leads either to apparently normal behaviour, a crash or
a freeze.

While this behaviour of the firmware is not in accordance with the
TCG Client EFI Specification, this happens on a Dell Precision 5510
with the TPM enabled but hidden from the OS ("TPM On" disabled, state
otherwise untouched). The EFI firmware claims that the TPM is present
and active and that it supports the TCG 2.0 event log format.

Fortunately, this can be worked around by simply checking the header
of the first event and the event log header signature itself.

Commit b4f1874c6216 ("tpm: check event log version before reading final
events") addressed a similar issue also found on Dell models.

Fixes: 6b0326190205 ("efi: Attempt to get the TCG2 event log in the boot stub")
Signed-off-by: Fabian Vogt <fvogt@suse.de>
Link: https://lore.kernel.org/r/1927248.evlx2EsYKh@linux-e202.suse.de
Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1165773
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/tpm_eventlog.h | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 4f8c90c93c29..64356b199e94 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -81,6 +81,8 @@ struct tcg_efi_specid_event_algs {
 	u16 digest_size;
 } __packed;
 
+#define TCG_SPECID_SIG "Spec ID Event03"
+
 struct tcg_efi_specid_event_head {
 	u8 signature[16];
 	u32 platform_class;
@@ -171,6 +173,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 	int i;
 	int j;
 	u32 count, event_type;
+	const u8 zero_digest[sizeof(event_header->digest)] = {0};
 
 	marker = event;
 	marker_start = marker;
@@ -198,10 +201,19 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 	count = READ_ONCE(event->count);
 	event_type = READ_ONCE(event->event_type);
 
+	/* Verify that it's the log header */
+	if (event_header->pcr_idx != 0 ||
+	    event_header->event_type != NO_ACTION ||
+	    memcmp(event_header->digest, zero_digest, sizeof(zero_digest))) {
+		size = 0;
+		goto out;
+	}
+
 	efispecid = (struct tcg_efi_specid_event_head *)event_header->event;
 
 	/* Check if event is malformed. */
-	if (count > efispecid->num_algs) {
+	if (memcmp(efispecid->signature, TCG_SPECID_SIG,
+		   sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) {
 		size = 0;
 		goto out;
 	}
-- 
cgit v1.2.3


From 2963795122f50b36ed16e3ba880c3ed2de1bda6e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 27 May 2020 12:14:25 -0500
Subject: efi: Replace zero-length array and use struct_size() helper

The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:

struct foo {
        int stuff;
        struct boo array[];
};

By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.

Also, notice that, dynamic memory allocations won't be affected by
this change:

"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]

sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.

Lastly, make use of the sizeof_field() helper instead of an open-coded
version.

This issue was found with the help of Coccinelle and audited _manually_.

[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour")

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200527171425.GA4053@embeddedor
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c | 3 ++-
 include/linux/efi.h        | 7 ++-----
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 7f1657b6c30d..edc5d36caf54 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -622,7 +622,8 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
 			rsv = (void *)(p + prsv % PAGE_SIZE);
 
 			/* reserve the entry itself */
-			memblock_reserve(prsv, EFI_MEMRESERVE_SIZE(rsv->size));
+			memblock_reserve(prsv,
+					 struct_size(rsv, entry, rsv->size));
 
 			for (i = 0; i < atomic_read(&rsv->count); i++) {
 				memblock_reserve(rsv->entry[i].base,
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2c6495f72f79..c3449c9699d0 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1236,14 +1236,11 @@ struct linux_efi_memreserve {
 	struct {
 		phys_addr_t	base;
 		phys_addr_t	size;
-	} entry[0];
+	} entry[];
 };
 
-#define EFI_MEMRESERVE_SIZE(count) (sizeof(struct linux_efi_memreserve) + \
-	(count) * sizeof(((struct linux_efi_memreserve *)0)->entry[0]))
-
 #define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \
-	/ sizeof(((struct linux_efi_memreserve *)0)->entry[0]))
+	/ sizeof_field(struct linux_efi_memreserve, entry[0]))
 
 void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
 
-- 
cgit v1.2.3


From 4b9e7edb5afc4e3c27d6623f5008bf53ae96cf1a Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 15 Jun 2020 09:23:13 +0200
Subject: regmap: convert all regmap_update_bits() and co. macros to static
 inlines

There's no reason to have these as macros. Let's convert them all to
static inlines for better readability and stronger typing.

Suggested-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Link: https://lore.kernel.org/r/20200615072313.11106-1-brgl@bgdev.pl
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regmap.h | 222 ++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 192 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index cb666b9c6b6a..f4917efed5c3 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -80,36 +80,6 @@ struct reg_sequence {
 				}
 #define REG_SEQ0(_reg, _def)	REG_SEQ(_reg, _def, 0)
 
-#define	regmap_update_bits(map, reg, mask, val) \
-	regmap_update_bits_base(map, reg, mask, val, NULL, false, false)
-#define	regmap_update_bits_async(map, reg, mask, val)\
-	regmap_update_bits_base(map, reg, mask, val, NULL, true, false)
-#define	regmap_update_bits_check(map, reg, mask, val, change)\
-	regmap_update_bits_base(map, reg, mask, val, change, false, false)
-#define	regmap_update_bits_check_async(map, reg, mask, val, change)\
-	regmap_update_bits_base(map, reg, mask, val, change, true, false)
-
-#define	regmap_write_bits(map, reg, mask, val) \
-	regmap_update_bits_base(map, reg, mask, val, NULL, false, true)
-
-#define	regmap_field_write(field, val) \
-	regmap_field_update_bits_base(field, ~0, val, NULL, false, false)
-#define	regmap_field_force_write(field, val) \
-	regmap_field_update_bits_base(field, ~0, val, NULL, false, true)
-#define	regmap_field_update_bits(field, mask, val)\
-	regmap_field_update_bits_base(field, mask, val, NULL, false, false)
-#define	regmap_field_force_update_bits(field, mask, val) \
-	regmap_field_update_bits_base(field, mask, val, NULL, false, true)
-
-#define	regmap_fields_write(field, id, val) \
-	regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false)
-#define	regmap_fields_force_write(field, id, val) \
-	regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, true)
-#define	regmap_fields_update_bits(field, id, mask, val)\
-	regmap_fields_update_bits_base(field, id, mask, val, NULL, false, false)
-#define	regmap_fields_force_update_bits(field, id, mask, val) \
-	regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true)
-
 /**
  * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs
  *
@@ -1054,6 +1024,42 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 int regmap_update_bits_base(struct regmap *map, unsigned int reg,
 			    unsigned int mask, unsigned int val,
 			    bool *change, bool async, bool force);
+
+static inline int regmap_update_bits(struct regmap *map, unsigned int reg,
+				     unsigned int mask, unsigned int val)
+{
+	return regmap_update_bits_base(map, reg, mask, val, NULL, false, false);
+}
+
+static inline int regmap_update_bits_async(struct regmap *map, unsigned int reg,
+					   unsigned int mask, unsigned int val)
+{
+	return regmap_update_bits_base(map, reg, mask, val, NULL, true, false);
+}
+
+static inline int regmap_update_bits_check(struct regmap *map, unsigned int reg,
+					   unsigned int mask, unsigned int val,
+					   bool *change)
+{
+	return regmap_update_bits_base(map, reg, mask, val,
+				       change, false, false);
+}
+
+static inline int
+regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
+			       unsigned int mask, unsigned int val,
+			       bool *change)
+{
+	return regmap_update_bits_base(map, reg, mask, val,
+				       change, true, false);
+}
+
+static inline int regmap_write_bits(struct regmap *map, unsigned int reg,
+				    unsigned int mask, unsigned int val)
+{
+	return regmap_update_bits_base(map, reg, mask, val, NULL, false, true);
+}
+
 int regmap_get_val_bytes(struct regmap *map);
 int regmap_get_max_register(struct regmap *map);
 int regmap_get_reg_stride(struct regmap *map);
@@ -1152,6 +1158,65 @@ int regmap_fields_read(struct regmap_field *field, unsigned int id,
 int regmap_fields_update_bits_base(struct regmap_field *field,  unsigned int id,
 				   unsigned int mask, unsigned int val,
 				   bool *change, bool async, bool force);
+
+static inline int regmap_field_write(struct regmap_field *field,
+				     unsigned int val)
+{
+	return regmap_field_update_bits_base(field, ~0, val,
+					     NULL, false, false);
+}
+
+static inline int regmap_field_force_write(struct regmap_field *field,
+					   unsigned int val)
+{
+	return regmap_field_update_bits_base(field, ~0, val, NULL, false, true);
+}
+
+static inline int regmap_field_update_bits(struct regmap_field *field,
+					   unsigned int mask, unsigned int val)
+{
+	return regmap_field_update_bits_base(field, mask, val,
+					     NULL, false, false);
+}
+
+static inline int
+regmap_field_force_update_bits(struct regmap_field *field,
+			       unsigned int mask, unsigned int val)
+{
+	return regmap_field_update_bits_base(field, mask, val,
+					     NULL, false, true);
+}
+
+static inline int regmap_fields_write(struct regmap_field *field,
+				      unsigned int id, unsigned int val)
+{
+	return regmap_fields_update_bits_base(field, id, ~0, val,
+					      NULL, false, false);
+}
+
+static inline int regmap_fields_force_write(struct regmap_field *field,
+					    unsigned int id, unsigned int val)
+{
+	return regmap_fields_update_bits_base(field, id, ~0, val,
+					      NULL, false, true);
+}
+
+static inline int
+regmap_fields_update_bits(struct regmap_field *field, unsigned int id,
+			  unsigned int mask, unsigned int val)
+{
+	return regmap_fields_update_bits_base(field, id, mask, val,
+					      NULL, false, false);
+}
+
+static inline int
+regmap_fields_force_update_bits(struct regmap_field *field, unsigned int id,
+				unsigned int mask, unsigned int val)
+{
+	return regmap_fields_update_bits_base(field, id, mask, val,
+					      NULL, false, true);
+}
+
 /**
  * struct regmap_irq_type - IRQ type definitions.
  *
@@ -1458,6 +1523,103 @@ static inline int regmap_fields_update_bits_base(struct regmap_field *field,
 	return -EINVAL;
 }
 
+static inline int regmap_update_bits(struct regmap *map, unsigned int reg,
+				     unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_update_bits_async(struct regmap *map, unsigned int reg,
+					   unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_update_bits_check(struct regmap *map, unsigned int reg,
+					   unsigned int mask, unsigned int val,
+					   bool *change)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int
+regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
+			       unsigned int mask, unsigned int val,
+			       bool *change)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_write_bits(struct regmap *map, unsigned int reg,
+				    unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_field_write(struct regmap_field *field,
+				     unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_field_force_write(struct regmap_field *field,
+					   unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_field_update_bits(struct regmap_field *field,
+					   unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int
+regmap_field_force_update_bits(struct regmap_field *field,
+			       unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_fields_write(struct regmap_field *field,
+				      unsigned int id, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_fields_force_write(struct regmap_field *field,
+					    unsigned int id, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int
+regmap_fields_update_bits(struct regmap_field *field, unsigned int id,
+			  unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int
+regmap_fields_force_update_bits(struct regmap_field *field, unsigned int id,
+				unsigned int mask, unsigned int val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
 static inline int regmap_get_val_bytes(struct regmap *map)
 {
 	WARN_ONCE(1, "regmap API is disabled");
-- 
cgit v1.2.3


From 8e04187c1bc7953f6dfad3400c58b1b0b0ad767b Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@intel.com>
Date: Thu, 11 Jun 2020 11:25:07 +0800
Subject: spi: altera: add SPI core parameters support via platform data.

This patch introduced SPI core parameters in platform data, it
allows passing these SPI core parameters via platform data.

Signed-off-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/1591845911-10197-3-git-send-email-yilun.xu@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-altera.c   | 25 ++++++++++++++++++++++---
 include/linux/spi/altera.h | 24 ++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/spi/altera.h

(limited to 'include/linux')

diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c
index d5fa0c5706b0..e6e6708c7c47 100644
--- a/drivers/spi/spi-altera.c
+++ b/drivers/spi/spi-altera.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/spi/altera.h>
 #include <linux/spi/spi.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -40,6 +41,8 @@
 #define ALTERA_SPI_CONTROL_IE_MSK	0x100
 #define ALTERA_SPI_CONTROL_SSO_MSK	0x400
 
+#define ALTERA_SPI_MAX_CS		32
+
 struct altera_spi {
 	void __iomem *base;
 	int irq;
@@ -182,6 +185,7 @@ static irqreturn_t altera_spi_irq(int irq, void *dev)
 
 static int altera_spi_probe(struct platform_device *pdev)
 {
+	struct altera_spi_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct altera_spi *hw;
 	struct spi_master *master;
 	int err = -ENODEV;
@@ -192,9 +196,24 @@ static int altera_spi_probe(struct platform_device *pdev)
 
 	/* setup the master state. */
 	master->bus_num = pdev->id;
-	master->num_chipselect = 16;
-	master->mode_bits = SPI_CS_HIGH;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
+
+	if (pdata) {
+		if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) {
+			dev_err(&pdev->dev,
+				"Invalid number of chipselect: %hu\n",
+				pdata->num_chipselect);
+			return -EINVAL;
+		}
+
+		master->num_chipselect = pdata->num_chipselect;
+		master->mode_bits = pdata->mode_bits;
+		master->bits_per_word_mask = pdata->bits_per_word_mask;
+	} else {
+		master->num_chipselect = 16;
+		master->mode_bits = SPI_CS_HIGH;
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
+	}
+
 	master->dev.of_node = pdev->dev.of_node;
 	master->transfer_one = altera_spi_txrx;
 	master->set_cs = altera_spi_set_cs;
diff --git a/include/linux/spi/altera.h b/include/linux/spi/altera.h
new file mode 100644
index 000000000000..344a3fce56a4
--- /dev/null
+++ b/include/linux/spi/altera.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Header File for Altera SPI Driver.
+ */
+#ifndef __LINUX_SPI_ALTERA_H
+#define __LINUX_SPI_ALTERA_H
+
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+#include <linux/types.h>
+
+/**
+ * struct altera_spi_platform_data - Platform data of the Altera SPI driver
+ * @mode_bits:		Mode bits of SPI master.
+ * @num_chipselect:	Number of chipselects.
+ * @bits_per_word_mask:	bitmask of supported bits_per_word for transfers.
+ */
+struct altera_spi_platform_data {
+	u16				mode_bits;
+	u16				num_chipselect;
+	u32				bits_per_word_mask;
+};
+
+#endif /* __LINUX_SPI_ALTERA_H */
-- 
cgit v1.2.3


From 1fccd182a4694a848f2d6f3b1820d6fc71d9c99d Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@intel.com>
Date: Thu, 11 Jun 2020 11:25:08 +0800
Subject: spi: altera: add platform data for slave information.

This patch introduces platform data for slave information, it allows
spi-altera to add new spi devices once master registration is done.

Signed-off-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/1591845911-10197-4-git-send-email-yilun.xu@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-altera.c   | 11 +++++++++++
 include/linux/spi/altera.h |  5 +++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c
index e6e6708c7c47..aa9d1a257433 100644
--- a/drivers/spi/spi-altera.c
+++ b/drivers/spi/spi-altera.c
@@ -189,6 +189,7 @@ static int altera_spi_probe(struct platform_device *pdev)
 	struct altera_spi *hw;
 	struct spi_master *master;
 	int err = -ENODEV;
+	u16 i;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct altera_spi));
 	if (!master)
@@ -244,6 +245,16 @@ static int altera_spi_probe(struct platform_device *pdev)
 	err = devm_spi_register_master(&pdev->dev, master);
 	if (err)
 		goto exit;
+
+	if (pdata) {
+		for (i = 0; i < pdata->num_devices; i++) {
+			if (!spi_new_device(master, pdata->devices + i))
+				dev_warn(&pdev->dev,
+					 "unable to create SPI device: %s\n",
+					 pdata->devices[i].modalias);
+		}
+	}
+
 	dev_info(&pdev->dev, "base %p, irq %d\n", hw->base, hw->irq);
 
 	return 0;
diff --git a/include/linux/spi/altera.h b/include/linux/spi/altera.h
index 344a3fce56a4..2d42641499a6 100644
--- a/include/linux/spi/altera.h
+++ b/include/linux/spi/altera.h
@@ -14,11 +14,16 @@
  * @mode_bits:		Mode bits of SPI master.
  * @num_chipselect:	Number of chipselects.
  * @bits_per_word_mask:	bitmask of supported bits_per_word for transfers.
+ * @num_devices:	Number of devices that shall be added when the driver
+ *			is probed.
+ * @devices:		The devices to add.
  */
 struct altera_spi_platform_data {
 	u16				mode_bits;
 	u16				num_chipselect;
 	u32				bits_per_word_mask;
+	u16				num_devices;
+	struct spi_board_info		*devices;
 };
 
 #endif /* __LINUX_SPI_ALTERA_H */
-- 
cgit v1.2.3


From 7bb7ee8704fea9fec9eea53322b8464c3ed70a3d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 Jun 2020 08:46:23 +0200
Subject: scsi: libata: Provide an ata_scsi_dma_need_drain stub for !CONFIG_ATA

SAS drivers can be compiled with ata support disabled.  Provide a stub so
that the drivers don't have to ifdef around wiring up
ata_scsi_dma_need_drain.

Link: https://lore.kernel.org/r/20200615064624.37317-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/libata.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/libata.h b/include/linux/libata.h
index af832852e620..042e584daca7 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1092,7 +1092,11 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 #define ATA_SCSI_COMPAT_IOCTL /* empty */
 #endif
 extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
+#if IS_ENABLED(CONFIG_ATA)
 bool ata_scsi_dma_need_drain(struct request *rq);
+#else
+#define ata_scsi_dma_need_drain NULL
+#endif
 extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
 			    unsigned int cmd, void __user *arg);
 extern bool ata_link_online(struct ata_link *link);
-- 
cgit v1.2.3


From 466f966b1f4545acad150331911784d3f49ab1c3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: dmaengine: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 drivers/dma/milbeaut-hdmac.c | 2 +-
 drivers/dma/milbeaut-xdmac.c | 2 +-
 drivers/dma/moxart-dma.c     | 2 +-
 drivers/dma/ti/edma.c        | 2 +-
 drivers/dma/ti/k3-udma.c     | 2 +-
 drivers/dma/timb_dma.c       | 2 +-
 include/linux/dmaengine.h    | 4 ++--
 7 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 8853d442430b..a8cfb59f6efe 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -77,7 +77,7 @@ struct milbeaut_hdmac_device {
 	struct dma_device ddev;
 	struct clk *clk;
 	void __iomem *reg_base;
-	struct milbeaut_hdmac_chan channels[0];
+	struct milbeaut_hdmac_chan channels[];
 };
 
 static struct milbeaut_hdmac_chan *
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index ab3d2f395378..85a597228fb0 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -74,7 +74,7 @@ struct milbeaut_xdmac_chan {
 struct milbeaut_xdmac_device {
 	struct dma_device ddev;
 	void __iomem *reg_base;
-	struct milbeaut_xdmac_chan channels[0];
+	struct milbeaut_xdmac_chan channels[];
 };
 
 static struct milbeaut_xdmac_chan *
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index 4ab493d46375..347146a6e1d0 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -127,7 +127,7 @@ struct moxart_desc {
 	unsigned int			dma_cycles;
 	struct virt_dma_desc		vd;
 	uint8_t				es;
-	struct moxart_sg		sg[0];
+	struct moxart_sg		sg[];
 };
 
 struct moxart_chan {
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index c4a5c170c1f9..35d81bd857f1 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -211,7 +211,7 @@ struct edma_desc {
 	u32				residue;
 	u32				residue_stat;
 
-	struct edma_pset		pset[0];
+	struct edma_pset		pset[];
 };
 
 struct edma_cc;
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 945b7c604f91..c91e2dc1bb72 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -170,7 +170,7 @@ struct udma_desc {
 	void *metadata; /* pointer to provided metadata buffer (EPIP, PSdata) */
 
 	unsigned int hwdesc_count;
-	struct udma_hwdesc hwdesc[0];
+	struct udma_hwdesc hwdesc[];
 };
 
 enum udma_chan_state {
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 39382694fdfc..68e48bf54d78 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -88,7 +88,7 @@ struct timb_dma {
 	struct dma_device	dma;
 	void __iomem		*membase;
 	struct tasklet_struct	tasklet;
-	struct timb_dma_chan	channels[0];
+	struct timb_dma_chan	channels[];
 };
 
 static struct device *chan2dev(struct dma_chan *chan)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index e1c03339918f..6283917edd90 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -153,7 +153,7 @@ struct dma_interleaved_template {
 	bool dst_sgl;
 	size_t numf;
 	size_t frame_size;
-	struct data_chunk sgl[0];
+	struct data_chunk sgl[];
 };
 
 /**
@@ -535,7 +535,7 @@ struct dmaengine_unmap_data {
 	struct device *dev;
 	struct kref kref;
 	size_t len;
-	dma_addr_t addr[0];
+	dma_addr_t addr[];
 };
 
 struct dma_async_tx_descriptor;
-- 
cgit v1.2.3


From d6562f1ca877e0c2b020be0a66d59592e9f37f24 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: can: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/can/skb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index a954def26c0d..900b9f4e0605 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -34,7 +34,7 @@
 struct can_skb_priv {
 	int ifindex;
 	int skbcnt;
-	struct can_frame cf[0];
+	struct can_frame cf[];
 };
 
 static inline struct can_skb_priv *can_skb_prv(struct sk_buff *skb)
-- 
cgit v1.2.3


From 6b5679d2378324d0ed1c02c8e828b3b8687d3b08 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: cb710: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/cb710.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/cb710.h b/include/linux/cb710.h
index 60de3fedd3a7..405657a9a0d5 100644
--- a/include/linux/cb710.h
+++ b/include/linux/cb710.h
@@ -36,7 +36,7 @@ struct cb710_chip {
 	unsigned		slot_mask;
 	unsigned		slots;
 	spinlock_t		irq_lock;
-	struct cb710_slot	slot[0];
+	struct cb710_slot	slot[];
 };
 
 /* NOTE: cb710_chip.slots is modified only during device init/exit and
-- 
cgit v1.2.3


From 67cd46244611ca7b0d5447dac9a0cbd76b875210 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: FS-Cache: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/fscache-cache.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index ce0b5fbf239d..3f0b19dcfae7 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -46,7 +46,7 @@ struct fscache_cache_tag {
 	unsigned long		flags;
 #define FSCACHE_TAG_RESERVED	0		/* T if tag is reserved for a cache */
 	atomic_t		usage;
-	char			name[0];	/* tag name */
+	char			name[];	/* tag name */
 };
 
 /*
-- 
cgit v1.2.3


From 764e515f41c82220b20099962f47ec952c9ca6de Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: KVM: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/kvm_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 62ec926c78a0..d564855243d8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -409,7 +409,7 @@ struct kvm_irq_routing_table {
 	 * Array indexed by gsi. Each entry contains list of irq chips
 	 * the gsi is connected to.
 	 */
-	struct hlist_head map[0];
+	struct hlist_head map[];
 };
 #endif
 
-- 
cgit v1.2.3


From 50b6951feb621ac6a246a6f773edc0a3b9b7f3b4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: kexec: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/kexec.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 1776eb2e43a4..ea67910ae6b7 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -208,7 +208,7 @@ struct crash_mem_range {
 struct crash_mem {
 	unsigned int max_nr_ranges;
 	unsigned int nr_ranges;
-	struct crash_mem_range ranges[0];
+	struct crash_mem_range ranges[];
 };
 
 extern int crash_exclude_mem_range(struct crash_mem *mem,
-- 
cgit v1.2.3


From 67a862a94d5d55fbfde6942c81f9e51f943f452c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: kprobes: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/kprobes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 594265bfd390..e210af75ee38 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -161,7 +161,7 @@ struct kretprobe_instance {
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
 	void *fp;
-	char data[0];
+	char data[];
 };
 
 struct kretprobe_blackpoint {
-- 
cgit v1.2.3


From 9c5fbf05cb00cc9e6f1baf42751c6bfe1e6859ba Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: libata: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/libata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/libata.h b/include/linux/libata.h
index af832852e620..8bf5e59a7859 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -609,7 +609,7 @@ struct ata_host {
 	struct task_struct	*eh_owner;
 
 	struct ata_port		*simplex_claimed;	/* channel owning the DMA */
-	struct ata_port		*ports[0];
+	struct ata_port		*ports[];
 };
 
 struct ata_queued_cmd {
-- 
cgit v1.2.3


From af6bb61cc0a25fba4411f4348f01011c9a769047 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: sctp: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/sctp.h | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 8ccd82105de8..76731230bbc5 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -221,7 +221,7 @@ struct sctp_datahdr {
 	__be16 stream;
 	__be16 ssn;
 	__u32 ppid;
-	__u8  payload[0];
+	__u8  payload[];
 };
 
 struct sctp_data_chunk {
@@ -269,7 +269,7 @@ struct sctp_inithdr {
 	__be16 num_outbound_streams;
 	__be16 num_inbound_streams;
 	__be32 initial_tsn;
-	__u8  params[0];
+	__u8  params[];
 };
 
 struct sctp_init_chunk {
@@ -299,13 +299,13 @@ struct sctp_cookie_preserve_param {
 /* Section 3.3.2.1 Host Name Address (11) */
 struct sctp_hostname_param {
 	struct sctp_paramhdr param_hdr;
-	uint8_t hostname[0];
+	uint8_t hostname[];
 };
 
 /* Section 3.3.2.1 Supported Address Types (12) */
 struct sctp_supported_addrs_param {
 	struct sctp_paramhdr param_hdr;
-	__be16 types[0];
+	__be16 types[];
 };
 
 /* ADDIP Section 3.2.6 Adaptation Layer Indication */
@@ -317,25 +317,25 @@ struct sctp_adaptation_ind_param {
 /* ADDIP Section 4.2.7 Supported Extensions Parameter */
 struct sctp_supported_ext_param {
 	struct sctp_paramhdr param_hdr;
-	__u8 chunks[0];
+	__u8 chunks[];
 };
 
 /* AUTH Section 3.1 Random */
 struct sctp_random_param {
 	struct sctp_paramhdr param_hdr;
-	__u8 random_val[0];
+	__u8 random_val[];
 };
 
 /* AUTH Section 3.2 Chunk List */
 struct sctp_chunks_param {
 	struct sctp_paramhdr param_hdr;
-	__u8 chunks[0];
+	__u8 chunks[];
 };
 
 /* AUTH Section 3.3 HMAC Algorithm */
 struct sctp_hmac_algo_param {
 	struct sctp_paramhdr param_hdr;
-	__be16 hmac_ids[0];
+	__be16 hmac_ids[];
 };
 
 /* RFC 2960.  Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2):
@@ -350,7 +350,7 @@ struct sctp_initack_chunk {
 /* Section 3.3.3.1 State Cookie (7) */
 struct sctp_cookie_param {
 	struct sctp_paramhdr p;
-	__u8 body[0];
+	__u8 body[];
 };
 
 /* Section 3.3.3.1 Unrecognized Parameters (8) */
@@ -384,7 +384,7 @@ struct sctp_sackhdr {
 	__be32 a_rwnd;
 	__be16 num_gap_ack_blocks;
 	__be16 num_dup_tsns;
-	union sctp_sack_variable variable[0];
+	union sctp_sack_variable variable[];
 };
 
 struct sctp_sack_chunk {
@@ -436,7 +436,7 @@ struct sctp_shutdown_chunk {
 struct sctp_errhdr {
 	__be16 cause;
 	__be16 length;
-	__u8  variable[0];
+	__u8  variable[];
 };
 
 struct sctp_operr_chunk {
@@ -594,7 +594,7 @@ struct sctp_fwdtsn_skip {
 
 struct sctp_fwdtsn_hdr {
 	__be32 new_cum_tsn;
-	struct sctp_fwdtsn_skip skip[0];
+	struct sctp_fwdtsn_skip skip[];
 };
 
 struct sctp_fwdtsn_chunk {
@@ -611,7 +611,7 @@ struct sctp_ifwdtsn_skip {
 
 struct sctp_ifwdtsn_hdr {
 	__be32 new_cum_tsn;
-	struct sctp_ifwdtsn_skip skip[0];
+	struct sctp_ifwdtsn_skip skip[];
 };
 
 struct sctp_ifwdtsn_chunk {
@@ -658,7 +658,7 @@ struct sctp_addip_param {
 
 struct sctp_addiphdr {
 	__be32	serial;
-	__u8	params[0];
+	__u8	params[];
 };
 
 struct sctp_addip_chunk {
@@ -718,7 +718,7 @@ struct sctp_addip_chunk {
 struct sctp_authhdr {
 	__be16 shkey_id;
 	__be16 hmac_id;
-	__u8   hmac[0];
+	__u8   hmac[];
 };
 
 struct sctp_auth_chunk {
@@ -733,7 +733,7 @@ struct sctp_infox {
 
 struct sctp_reconf_chunk {
 	struct sctp_chunkhdr chunk_hdr;
-	__u8 params[0];
+	__u8 params[];
 };
 
 struct sctp_strreset_outreq {
@@ -741,13 +741,13 @@ struct sctp_strreset_outreq {
 	__be32 request_seq;
 	__be32 response_seq;
 	__be32 send_reset_at_tsn;
-	__be16 list_of_streams[0];
+	__be16 list_of_streams[];
 };
 
 struct sctp_strreset_inreq {
 	struct sctp_paramhdr param_hdr;
 	__be32 request_seq;
-	__be16 list_of_streams[0];
+	__be16 list_of_streams[];
 };
 
 struct sctp_strreset_tsnreq {
-- 
cgit v1.2.3


From 5cab1634e485ce7b33839f762f3bb9b5f009dc87 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 28 May 2020 09:35:11 -0500
Subject: tifm: Replace zero-length array with flexible-array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/tifm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/tifm.h b/include/linux/tifm.h
index 299cbb8c63bb..44073d06710f 100644
--- a/include/linux/tifm.h
+++ b/include/linux/tifm.h
@@ -124,7 +124,7 @@ struct tifm_adapter {
 	int                 (*has_ms_pif)(struct tifm_adapter *fm,
 					  struct tifm_dev *sock);
 
-	struct tifm_dev     *sockets[0];
+	struct tifm_dev     *sockets[];
 };
 
 struct tifm_adapter *tifm_alloc_adapter(unsigned int num_sockets,
-- 
cgit v1.2.3


From 9357b04624013294e4204b1a837d0a611b9048c3 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Wed, 27 May 2020 17:47:31 +0200
Subject: reset: Move reset-simple header out of drivers/reset

The reset-simple code can be useful for drivers outside of drivers/reset
that have a few reset controls as part of their features. Let's move it to
include/linux/reset.

Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/reset-simple.c        |  3 +--
 drivers/reset/reset-simple.h        | 41 -------------------------------------
 drivers/reset/reset-socfpga.c       |  3 +--
 drivers/reset/reset-sunxi.c         |  3 +--
 drivers/reset/reset-uniphier-glue.c |  3 +--
 include/linux/reset/reset-simple.h  | 41 +++++++++++++++++++++++++++++++++++++
 6 files changed, 45 insertions(+), 49 deletions(-)
 delete mode 100644 drivers/reset/reset-simple.h
 create mode 100644 include/linux/reset/reset-simple.h

(limited to 'include/linux')

diff --git a/drivers/reset/reset-simple.c b/drivers/reset/reset-simple.c
index 067e7e7b34f1..c854aa351640 100644
--- a/drivers/reset/reset-simple.c
+++ b/drivers/reset/reset-simple.c
@@ -18,10 +18,9 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
+#include <linux/reset/reset-simple.h>
 #include <linux/spinlock.h>
 
-#include "reset-simple.h"
-
 static inline struct reset_simple_data *
 to_reset_simple_data(struct reset_controller_dev *rcdev)
 {
diff --git a/drivers/reset/reset-simple.h b/drivers/reset/reset-simple.h
deleted file mode 100644
index 08ccb25a55e6..000000000000
--- a/drivers/reset/reset-simple.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Simple Reset Controller ops
- *
- * Based on Allwinner SoCs Reset Controller driver
- *
- * Copyright 2013 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.com>
- */
-
-#ifndef __RESET_SIMPLE_H__
-#define __RESET_SIMPLE_H__
-
-#include <linux/io.h>
-#include <linux/reset-controller.h>
-#include <linux/spinlock.h>
-
-/**
- * struct reset_simple_data - driver data for simple reset controllers
- * @lock: spinlock to protect registers during read-modify-write cycles
- * @membase: memory mapped I/O register range
- * @rcdev: reset controller device base structure
- * @active_low: if true, bits are cleared to assert the reset. Otherwise, bits
- *              are set to assert the reset. Note that this says nothing about
- *              the voltage level of the actual reset line.
- * @status_active_low: if true, bits read back as cleared while the reset is
- *                     asserted. Otherwise, bits read back as set while the
- *                     reset is asserted.
- */
-struct reset_simple_data {
-	spinlock_t			lock;
-	void __iomem			*membase;
-	struct reset_controller_dev	rcdev;
-	bool				active_low;
-	bool				status_active_low;
-};
-
-extern const struct reset_control_ops reset_simple_ops;
-
-#endif /* __RESET_SIMPLE_H__ */
diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c
index 96953992c2bb..bdd984296196 100644
--- a/drivers/reset/reset-socfpga.c
+++ b/drivers/reset/reset-socfpga.c
@@ -11,13 +11,12 @@
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
+#include <linux/reset/reset-simple.h>
 #include <linux/reset/socfpga.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
-#include "reset-simple.h"
-
 #define SOCFPGA_NR_BANKS	8
 
 static int a10_reset_init(struct device_node *np)
diff --git a/drivers/reset/reset-sunxi.c b/drivers/reset/reset-sunxi.c
index e7f169e57bcf..e752594b6971 100644
--- a/drivers/reset/reset-sunxi.c
+++ b/drivers/reset/reset-sunxi.c
@@ -14,13 +14,12 @@
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
+#include <linux/reset/reset-simple.h>
 #include <linux/reset/sunxi.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
-#include "reset-simple.h"
-
 static int sunxi_reset_init(struct device_node *np)
 {
 	struct reset_simple_data *data;
diff --git a/drivers/reset/reset-uniphier-glue.c b/drivers/reset/reset-uniphier-glue.c
index 2b188b3bb69a..027990b79f61 100644
--- a/drivers/reset/reset-uniphier-glue.c
+++ b/drivers/reset/reset-uniphier-glue.c
@@ -9,8 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
-
-#include "reset-simple.h"
+#include <linux/reset/reset-simple.h>
 
 #define MAX_CLKS	2
 #define MAX_RSTS	2
diff --git a/include/linux/reset/reset-simple.h b/include/linux/reset/reset-simple.h
new file mode 100644
index 000000000000..08ccb25a55e6
--- /dev/null
+++ b/include/linux/reset/reset-simple.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Simple Reset Controller ops
+ *
+ * Based on Allwinner SoCs Reset Controller driver
+ *
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#ifndef __RESET_SIMPLE_H__
+#define __RESET_SIMPLE_H__
+
+#include <linux/io.h>
+#include <linux/reset-controller.h>
+#include <linux/spinlock.h>
+
+/**
+ * struct reset_simple_data - driver data for simple reset controllers
+ * @lock: spinlock to protect registers during read-modify-write cycles
+ * @membase: memory mapped I/O register range
+ * @rcdev: reset controller device base structure
+ * @active_low: if true, bits are cleared to assert the reset. Otherwise, bits
+ *              are set to assert the reset. Note that this says nothing about
+ *              the voltage level of the actual reset line.
+ * @status_active_low: if true, bits read back as cleared while the reset is
+ *                     asserted. Otherwise, bits read back as set while the
+ *                     reset is asserted.
+ */
+struct reset_simple_data {
+	spinlock_t			lock;
+	void __iomem			*membase;
+	struct reset_controller_dev	rcdev;
+	bool				active_low;
+	bool				status_active_low;
+};
+
+extern const struct reset_control_ops reset_simple_ops;
+
+#endif /* __RESET_SIMPLE_H__ */
-- 
cgit v1.2.3


From a9701376ed0fb61a5be4bb438daf26bd9cfa24b5 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Wed, 27 May 2020 17:47:32 +0200
Subject: reset: simple: Add reset callback

The reset-simple code lacks a reset callback that is still pretty easy to
implement. The only real thing to consider is the delay needed for a device
to be reset, so let's expose that as part of the reset-simple driver data.

Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/reset-simple.c       | 20 ++++++++++++++++++++
 include/linux/reset/reset-simple.h |  7 +++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/reset/reset-simple.c b/drivers/reset/reset-simple.c
index c854aa351640..e066614818a3 100644
--- a/drivers/reset/reset-simple.c
+++ b/drivers/reset/reset-simple.c
@@ -11,6 +11,7 @@
  * Maxime Ripard <maxime.ripard@free-electrons.com>
  */
 
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -63,6 +64,24 @@ static int reset_simple_deassert(struct reset_controller_dev *rcdev,
 	return reset_simple_update(rcdev, id, false);
 }
 
+static int reset_simple_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int ret;
+
+	if (!data->reset_us)
+		return -ENOTSUPP;
+
+	ret = reset_simple_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	usleep_range(data->reset_us, data->reset_us * 2);
+
+	return reset_simple_deassert(rcdev, id);
+}
+
 static int reset_simple_status(struct reset_controller_dev *rcdev,
 			       unsigned long id)
 {
@@ -80,6 +99,7 @@ static int reset_simple_status(struct reset_controller_dev *rcdev,
 const struct reset_control_ops reset_simple_ops = {
 	.assert		= reset_simple_assert,
 	.deassert	= reset_simple_deassert,
+	.reset		= reset_simple_reset,
 	.status		= reset_simple_status,
 };
 EXPORT_SYMBOL_GPL(reset_simple_ops);
diff --git a/include/linux/reset/reset-simple.h b/include/linux/reset/reset-simple.h
index 08ccb25a55e6..c3e44f45b0f7 100644
--- a/include/linux/reset/reset-simple.h
+++ b/include/linux/reset/reset-simple.h
@@ -27,6 +27,12 @@
  * @status_active_low: if true, bits read back as cleared while the reset is
  *                     asserted. Otherwise, bits read back as set while the
  *                     reset is asserted.
+ * @reset_us: Minimum delay in microseconds needed that needs to be
+ *            waited for between an assert and a deassert to reset the
+ *            device. If multiple consumers with different delay
+ *            requirements are connected to this controller, it must
+ *            be the largest minimum delay. 0 means that such a delay is
+ *            unknown and the reset operation is unsupported.
  */
 struct reset_simple_data {
 	spinlock_t			lock;
@@ -34,6 +40,7 @@ struct reset_simple_data {
 	struct reset_controller_dev	rcdev;
 	bool				active_low;
 	bool				status_active_low;
+	unsigned int			reset_us;
 };
 
 extern const struct reset_control_ops reset_simple_ops;
-- 
cgit v1.2.3


From 33aea07f30c261eff7ba229f19fd1b161e0fb851 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Tue, 16 Jun 2020 01:15:29 +0200
Subject: compiler_attributes.h: Support no_sanitize_undefined check with GCC 4

UBSAN is supported since GCC 4.9, which unfortunately did not yet have
__has_attribute(). To work around, the __GCC4_has_attribute workaround
requires defining which compiler version supports the given attribute.

In the case of no_sanitize_undefined, it is the first version that
supports UBSAN, which is GCC 4.9.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Link: https://lkml.kernel.org/r/20200615231529.GA119644@google.com
---
 include/linux/compiler_attributes.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index cdf016596659..c8f03d2969df 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -40,6 +40,7 @@
 # define __GCC4_has_attribute___noclone__             1
 # define __GCC4_has_attribute___nonstring__           0
 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8)
+# define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9)
 # define __GCC4_has_attribute___fallthrough__         0
 #endif
 
-- 
cgit v1.2.3


From 8a307d3601bcca99723b1a45e785adc3c9d3a476 Mon Sep 17 00:00:00 2001
From: Artur Świgoń <a.swigon@samsung.com>
Date: Thu, 21 May 2020 14:28:39 +0200
Subject: interconnect: Export of_icc_get_from_provider()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch makes the above function public (for use in exynos-bus devfreq
driver).

Signed-off-by: Artur Świgoń <a.swigon@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Link: https://lore.kernel.org/r/20200521122841.8867-2-s.nawrocki@samsung.com
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 3 ++-
 include/linux/interconnect-provider.h | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index e5f998744501..9e2d55d94fb4 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -334,7 +334,7 @@ EXPORT_SYMBOL_GPL(of_icc_xlate_onecell);
  * Returns a valid pointer to struct icc_node on success or ERR_PTR()
  * on failure.
  */
-static struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
 {
 	struct icc_node *node = ERR_PTR(-EPROBE_DEFER);
 	struct icc_provider *provider;
@@ -353,6 +353,7 @@ static struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
 
 	return node;
 }
+EXPORT_SYMBOL_GPL(of_icc_get_from_provider);
 
 static void devm_icc_release(struct device *dev, void *res)
 {
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 0c494534b4d3..c92be2a90fa0 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -103,6 +103,7 @@ void icc_node_del(struct icc_node *node);
 int icc_nodes_remove(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 int icc_provider_del(struct icc_provider *provider);
+struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec);
 
 #else
 
@@ -154,6 +155,11 @@ static inline int icc_provider_del(struct icc_provider *provider)
 	return -ENOTSUPP;
 }
 
+static inline struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
 #endif /* CONFIG_INTERCONNECT */
 
 #endif /* __LINUX_INTERCONNECT_PROVIDER_H */
-- 
cgit v1.2.3


From 65461e26b1fe73bde4326367ee23cc1a24e6c33e Mon Sep 17 00:00:00 2001
From: Artur Świgoń <a.swigon@samsung.com>
Date: Thu, 21 May 2020 14:28:41 +0200
Subject: interconnect: Allow inter-provider pairs to be configured
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for a new boolean 'inter_set' field in struct
icc_provider. Setting it to 'true' enables calling '->set' for
inter-provider node pairs. All existing users of the interconnect
framework allocate this structure with kzalloc, and are therefore
unaffected by this change.

This makes it easier for hierarchies like exynos-bus, where every bus
is probed separately and registers a separate interconnect provider, to
model constraints between buses.

Signed-off-by: Artur Świgoń <a.swigon@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20200521122841.8867-4-s.nawrocki@samsung.com
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 11 +++++------
 include/linux/interconnect-provider.h |  2 ++
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 8b4d50d59e16..609e206bf598 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -263,23 +263,22 @@ static int aggregate_requests(struct icc_node *node)
 static int apply_constraints(struct icc_path *path)
 {
 	struct icc_node *next, *prev = NULL;
+	struct icc_provider *p;
 	int ret = -EINVAL;
 	int i;
 
 	for (i = 0; i < path->num_nodes; i++) {
 		next = path->reqs[i].node;
+		p = next->provider;
 
-		/*
-		 * Both endpoints should be valid master-slave pairs of the
-		 * same interconnect provider that will be configured.
-		 */
-		if (!prev || next->provider != prev->provider) {
+		/* both endpoints should be valid master-slave pairs */
+		if (!prev || (p != prev->provider && !p->inter_set)) {
 			prev = next;
 			continue;
 		}
 
 		/* set the constraints */
-		ret = next->provider->set(prev, next);
+		ret = p->set(prev, next);
 		if (ret)
 			goto out;
 
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index c92be2a90fa0..38701925ab91 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -41,6 +41,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
  * @xlate: provider-specific callback for mapping nodes from phandle arguments
  * @dev: the device this interconnect provider belongs to
  * @users: count of active users
+ * @inter_set: whether inter-provider pairs will be configured with @set
  * @data: pointer to private data
  */
 struct icc_provider {
@@ -53,6 +54,7 @@ struct icc_provider {
 	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
 	struct device		*dev;
 	int			users;
+	bool			inter_set;
 	void			*data;
 };
 
-- 
cgit v1.2.3


From 12a400b016ab955be8e4c569346fa18aaceed9d7 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Tue, 16 Jun 2020 16:43:23 +0300
Subject: interconnect: Mark all dummy functions as static inline

There are a few dummy stub functions that are not marked as static inline
yet. Currently this header file is not included in any other file outside
of drivers/interconnect/, but that might not be the case in the future.
If this file gets included and the framework is disabled, we will be see
warnings. Let's fix this in advance.

Link: https://lore.kernel.org/r/20200228145945.13579-1-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 include/linux/interconnect-provider.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 38701925ab91..4735518de515 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -120,7 +120,7 @@ static inline struct icc_node *icc_node_create(int id)
 	return ERR_PTR(-ENOTSUPP);
 }
 
-void icc_node_destroy(int id)
+static inline void icc_node_destroy(int id)
 {
 }
 
@@ -129,16 +129,16 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id)
 	return -ENOTSUPP;
 }
 
-int icc_link_destroy(struct icc_node *src, struct icc_node *dst)
+static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst)
 {
 	return -ENOTSUPP;
 }
 
-void icc_node_add(struct icc_node *node, struct icc_provider *provider)
+static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider)
 {
 }
 
-void icc_node_del(struct icc_node *node)
+static inline void icc_node_del(struct icc_node *node)
 {
 }
 
-- 
cgit v1.2.3


From 22d2cfdffa5bff3566e16cb7320e13ceb814674b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 4 Jun 2020 11:12:34 +0200
Subject: libceph: move away from global osd_req_flags

osd_req_flags is overly general and doesn't suit its only user
(read_from_replica option) well:

- applying osd_req_flags in account_request() affects all OSD
  requests, including linger (i.e. watch and notify).  However,
  linger requests should always go to the primary even though
  some of them are reads (e.g. notify has side effects but it
  is a read because it doesn't result in mutation on the OSDs).

- calls to class methods that are reads are allowed to go to
  the replica, but most such calls issued for "rbd map" and/or
  exclusive lock transitions are requested to be resent to the
  primary via EAGAIN, doubling the latency.

Get rid of global osd_req_flags and set read_from_replica flag
only on specific OSD requests instead.

Fixes: 8ad44d5e0d1e ("libceph: read_from_replica option")
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 drivers/block/rbd.c          |  4 +++-
 include/linux/ceph/libceph.h |  4 ++--
 net/ceph/ceph_common.c       | 14 ++++++--------
 net/ceph/osd_client.c        |  7 ++-----
 4 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 7420648a1de6..4f61e9209461 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1451,8 +1451,10 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req)
 static void rbd_osd_format_read(struct ceph_osd_request *osd_req)
 {
 	struct rbd_obj_request *obj_request = osd_req->r_priv;
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+	struct ceph_options *opt = rbd_dev->rbd_client->client->options;
 
-	osd_req->r_flags = CEPH_OSD_FLAG_READ;
+	osd_req->r_flags = CEPH_OSD_FLAG_READ | opt->read_from_replica;
 	osd_req->r_snapid = obj_request->img_request->snap_id;
 }
 
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 2247e71beb83..e5ed1c541e7f 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -52,8 +52,7 @@ struct ceph_options {
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
 	unsigned long osd_request_timeout;	/* jiffies */
-
-	u32 osd_req_flags;  /* CEPH_OSD_FLAG_*, applied to each OSD request */
+	u32 read_from_replica;  /* CEPH_OSD_FLAG_BALANCE/LOCALIZE_READS */
 
 	/*
 	 * any type that can't be simply compared or doesn't need
@@ -76,6 +75,7 @@ struct ceph_options {
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0  /* no timeout */
+#define CEPH_READ_FROM_REPLICA_DEFAULT	0  /* read from primary */
 
 #define CEPH_MONC_HUNT_INTERVAL		msecs_to_jiffies(3 * 1000)
 #define CEPH_MONC_PING_INTERVAL		msecs_to_jiffies(10 * 1000)
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index afe0e8184c23..4e7edd707a14 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -332,6 +332,7 @@ struct ceph_options *ceph_alloc_options(void)
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
 	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
+	opt->read_from_replica = CEPH_READ_FROM_REPLICA_DEFAULT;
 	return opt;
 }
 EXPORT_SYMBOL(ceph_alloc_options);
@@ -490,16 +491,13 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
 	case Opt_read_from_replica:
 		switch (result.uint_32) {
 		case Opt_read_from_replica_no:
-			opt->osd_req_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS |
-						CEPH_OSD_FLAG_LOCALIZE_READS);
+			opt->read_from_replica = 0;
 			break;
 		case Opt_read_from_replica_balance:
-			opt->osd_req_flags |= CEPH_OSD_FLAG_BALANCE_READS;
-			opt->osd_req_flags &= ~CEPH_OSD_FLAG_LOCALIZE_READS;
+			opt->read_from_replica = CEPH_OSD_FLAG_BALANCE_READS;
 			break;
 		case Opt_read_from_replica_localize:
-			opt->osd_req_flags |= CEPH_OSD_FLAG_LOCALIZE_READS;
-			opt->osd_req_flags &= ~CEPH_OSD_FLAG_BALANCE_READS;
+			opt->read_from_replica = CEPH_OSD_FLAG_LOCALIZE_READS;
 			break;
 		default:
 			BUG();
@@ -613,9 +611,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
 		}
 		seq_putc(m, ',');
 	}
-	if (opt->osd_req_flags & CEPH_OSD_FLAG_BALANCE_READS) {
+	if (opt->read_from_replica == CEPH_OSD_FLAG_BALANCE_READS) {
 		seq_puts(m, "read_from_replica=balance,");
-	} else if (opt->osd_req_flags & CEPH_OSD_FLAG_LOCALIZE_READS) {
+	} else if (opt->read_from_replica == CEPH_OSD_FLAG_LOCALIZE_READS) {
 		seq_puts(m, "read_from_replica=localize,");
 	}
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 4fea3c33af2a..a37d159019a0 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1117,10 +1117,10 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 				       truncate_size, truncate_seq);
 	}
 
-	req->r_flags = flags;
 	req->r_base_oloc.pool = layout->pool_id;
 	req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
 	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
+	req->r_flags = flags | osdc->client->options->read_from_replica;
 
 	req->r_snapid = vino.snap;
 	if (flags & CEPH_OSD_FLAG_WRITE)
@@ -2431,14 +2431,11 @@ promote:
 
 static void account_request(struct ceph_osd_request *req)
 {
-	struct ceph_osd_client *osdc = req->r_osdc;
-
 	WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK));
 	WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE)));
 
 	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
-	req->r_flags |= osdc->client->options->osd_req_flags;
-	atomic_inc(&osdc->num_requests);
+	atomic_inc(&req->r_osdc->num_requests);
 
 	req->r_start_stamp = jiffies;
 	req->r_start_latency = ktime_get();
-- 
cgit v1.2.3


From 2fd2bc7f49324e7b439e3c5584762abd0a9a13bc Mon Sep 17 00:00:00 2001
From: Colton Lewis <colton.w.lewis@protonmail.com>
Date: Sun, 14 Jun 2020 04:08:04 +0000
Subject: gpu: host1x: Correct trivial kernel-doc inconsistencies

Silence documentation build warnings by adding kernel-doc fields.

./include/linux/host1x.h:69: warning: Function parameter or member 'parent' not described in 'host1x_client'
./include/linux/host1x.h:69: warning: Function parameter or member 'usecount' not described in 'host1x_client'
./include/linux/host1x.h:69: warning: Function parameter or member 'lock' not described in 'host1x_client'

Signed-off-by: Colton Lewis <colton.w.lewis@protonmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 include/linux/host1x.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index c230b4e70d75..a3a568bf9686 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -48,6 +48,9 @@ struct host1x_client_ops {
  * @channel: host1x channel associated with this client
  * @syncpts: array of syncpoints requested for this client
  * @num_syncpts: number of syncpoints requested for this client
+ * @parent: pointer to parent structure
+ * @usecount: reference count for this structure
+ * @lock: mutex for mutually exclusive concurrency
  */
 struct host1x_client {
 	struct list_head list;
-- 
cgit v1.2.3


From e370f886fefc23b9ca3011760d9376f1947eb321 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Tue, 16 Jun 2020 15:39:25 +0200
Subject: EDAC: Remove edac_get_dimm_by_index()

It is unused now.

Signed-off-by: Borislav Petkov <bp@suse.de>
---
 include/linux/edac.h | 29 +++++++----------------------
 1 file changed, 7 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/edac.h b/include/linux/edac.h
index 6eb7d55d7c3d..15e8f3d8a895 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -594,27 +594,6 @@ struct mem_ctl_info {
 		     ? (mci)->dimms[(dimm)->idx + 1]		\
 		     : NULL)
 
-/**
- * edac_get_dimm_by_index - Get DIMM info at @index from a memory
- * 			    controller
- *
- * @mci:	MC descriptor struct mem_ctl_info
- * @index:	index in the memory controller's DIMM array
- *
- * Returns a struct dimm_info * or NULL on failure.
- */
-static inline struct dimm_info *
-edac_get_dimm_by_index(struct mem_ctl_info *mci, int index)
-{
-	if (index < 0 || index >= mci->tot_dimms)
-		return NULL;
-
-	if (WARN_ON_ONCE(mci->dimms[index]->idx != index))
-		return NULL;
-
-	return mci->dimms[index];
-}
-
 /**
  * edac_get_dimm - Get DIMM info from a memory controller given by
  *                 [layer0,layer1,layer2] position
@@ -650,6 +629,12 @@ static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci,
 	if (mci->n_layers > 2)
 		index = index * mci->layers[2].size + layer2;
 
-	return edac_get_dimm_by_index(mci, index);
+	if (index < 0 || index >= mci->tot_dimms)
+		return NULL;
+
+	if (WARN_ON_ONCE(mci->dimms[index]->idx != index))
+		return NULL;
+
+	return mci->dimms[index];
 }
 #endif /* _LINUX_EDAC_H_ */
-- 
cgit v1.2.3


From 278a5fbaed89dacd04e9d052f4594ffd0e0585de Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Fri, 24 May 2019 11:30:34 +0200
Subject: open: add close_range()

This adds the close_range() syscall. It allows to efficiently close a range
of file descriptors up to all file descriptors of a calling task.

I was contacted by FreeBSD as they wanted to have the same close_range()
syscall as we proposed here. We've coordinated this and in the meantime, Kyle
was fast enough to merge close_range() into FreeBSD already in April:
https://reviews.freebsd.org/D21627
https://svnweb.freebsd.org/base?view=revision&revision=359836
and the current plan is to backport close_range() to FreeBSD 12.2 (cf. [2])
once its merged in Linux too. Python is in the process of switching to
close_range() on FreeBSD and they are waiting on us to merge this to switch on
Linux as well: https://bugs.python.org/issue38061

The syscall came up in a recent discussion around the new mount API and
making new file descriptor types cloexec by default. During this
discussion, Al suggested the close_range() syscall (cf. [1]). Note, a
syscall in this manner has been requested by various people over time.

First, it helps to close all file descriptors of an exec()ing task. This
can be done safely via (quoting Al's example from [1] verbatim):

        /* that exec is sensitive */
        unshare(CLONE_FILES);
        /* we don't want anything past stderr here */
        close_range(3, ~0U);
        execve(....);

The code snippet above is one way of working around the problem that file
descriptors are not cloexec by default. This is aggravated by the fact that
we can't just switch them over without massively regressing userspace. For
a whole class of programs having an in-kernel method of closing all file
descriptors is very helpful (e.g. demons, service managers, programming
language standard libraries, container managers etc.).
(Please note, unshare(CLONE_FILES) should only be needed if the calling
task is multi-threaded and shares the file descriptor table with another
thread in which case two threads could race with one thread allocating file
descriptors and the other one closing them via close_range(). For the
general case close_range() before the execve() is sufficient.)

Second, it allows userspace to avoid implementing closing all file
descriptors by parsing through /proc/<pid>/fd/* and calling close() on each
file descriptor. From looking at various large(ish) userspace code bases
this or similar patterns are very common in:
- service managers (cf. [4])
- libcs (cf. [6])
- container runtimes (cf. [5])
- programming language runtimes/standard libraries
  - Python (cf. [2])
  - Rust (cf. [7], [8])
As Dmitry pointed out there's even a long-standing glibc bug about missing
kernel support for this task (cf. [3]).
In addition, the syscall will also work for tasks that do not have procfs
mounted and on kernels that do not have procfs support compiled in. In such
situations the only way to make sure that all file descriptors are closed
is to call close() on each file descriptor up to UINT_MAX or RLIMIT_NOFILE,
OPEN_MAX trickery (cf. comment [8] on Rust).

The performance is striking. For good measure, comparing the following
simple close_all_fds() userspace implementation that is essentially just
glibc's version in [6]:

static int close_all_fds(void)
{
        int dir_fd;
        DIR *dir;
        struct dirent *direntp;

        dir = opendir("/proc/self/fd");
        if (!dir)
                return -1;
        dir_fd = dirfd(dir);
        while ((direntp = readdir(dir))) {
                int fd;
                if (strcmp(direntp->d_name, ".") == 0)
                        continue;
                if (strcmp(direntp->d_name, "..") == 0)
                        continue;
                fd = atoi(direntp->d_name);
                if (fd == dir_fd || fd == 0 || fd == 1 || fd == 2)
                        continue;
                close(fd);
        }
        closedir(dir);
        return 0;
}

to close_range() yields:
1. closing 4 open files:
   - close_all_fds(): ~280 us
   - close_range():    ~24 us

2. closing 1000 open files:
   - close_all_fds(): ~5000 us
   - close_range():   ~800 us

close_range() is designed to allow for some flexibility. Specifically, it
does not simply always close all open file descriptors of a task. Instead,
callers can specify an upper bound.
This is e.g. useful for scenarios where specific file descriptors are
created with well-known numbers that are supposed to be excluded from
getting closed.
For extra paranoia close_range() comes with a flags argument. This can e.g.
be used to implement extension. Once can imagine userspace wanting to stop
at the first error instead of ignoring errors under certain circumstances.
There might be other valid ideas in the future. In any case, a flag
argument doesn't hurt and keeps us on the safe side.

From an implementation side this is kept rather dumb. It saw some input
from David and Jann but all nonsense is obviously my own!
- Errors to close file descriptors are currently ignored. (Could be changed
  by setting a flag in the future if needed.)
- __close_range() is a rather simplistic wrapper around __close_fd().
  My reasoning behind this is based on the nature of how __close_fd() needs
  to release an fd. But maybe I misunderstood specifics:
  We take the files_lock and rcu-dereference the fdtable of the calling
  task, we find the entry in the fdtable, get the file and need to release
  files_lock before calling filp_close().
  In the meantime the fdtable might have been altered so we can't just
  retake the spinlock and keep the old rcu-reference of the fdtable
  around. Instead we need to grab a fresh reference to the fdtable.
  If my reasoning is correct then there's really no point in fancyfying
  __close_range(): We just need to rcu-dereference the fdtable of the
  calling task once to cap the max_fd value correctly and then go on
  calling __close_fd() in a loop.

/* References */
[1]: https://lore.kernel.org/lkml/20190516165021.GD17978@ZenIV.linux.org.uk/
[2]: https://github.com/python/cpython/blob/9e4f2f3a6b8ee995c365e86d976937c141d867f8/Modules/_posixsubprocess.c#L220
[3]: https://sourceware.org/bugzilla/show_bug.cgi?id=10353#c7
[4]: https://github.com/systemd/systemd/blob/5238e9575906297608ff802a27e2ff9effa3b338/src/basic/fd-util.c#L217
[5]: https://github.com/lxc/lxc/blob/ddf4b77e11a4d08f09b7b9cd13e593f8c047edc5/src/lxc/start.c#L236
[6]: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/grantpt.c;h=2030e07fa6e652aac32c775b8c6e005844c3c4eb;hb=HEAD#l17
     Note that this is an internal implementation that is not exported.
     Currently, libc seems to not provide an exported version of this
     because of missing kernel support to do this.
     Note, in a recent patch series Florian made grantpt() a nop thereby
     removing the code referenced here.
[7]: https://github.com/rust-lang/rust/issues/12148
[8]: https://github.com/rust-lang/rust/blob/5f47c0613ed4eb46fca3633c1297364c09e5e451/src/libstd/sys/unix/process2.rs#L303-L308
     Rust's solution is slightly different but is equally unperformant.
     Rust calls getdtablesize() which is a glibc library function that
     simply returns the current RLIMIT_NOFILE or OPEN_MAX values. Rust then
     goes on to call close() on each fd. That's obviously overkill for most
     tasks. Rarely, tasks - especially non-demons - hit RLIMIT_NOFILE or
     OPEN_MAX.
     Let's be nice and assume an unprivileged user with RLIMIT_NOFILE set
     to 1024. Even in this case, there's a very high chance that in the
     common case Rust is calling the close() syscall 1021 times pointlessly
     if the task just has 0, 1, and 2 open.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Kyle Evans <self@kyle-evans.net>
Cc: Jann Horn <jannh@google.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: linux-api@vger.kernel.org
---
 fs/file.c                | 64 ++++++++++++++++++++++++++++++++++++++++++------
 fs/open.c                | 20 +++++++++++++++
 include/linux/fdtable.h  |  2 ++
 include/linux/syscalls.h |  2 ++
 4 files changed, 80 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index abb8b7081d7a..1b8ff05e8311 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/export.h>
 #include <linux/fs.h>
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
@@ -620,12 +621,9 @@ void fd_install(unsigned int fd, struct file *file)
 
 EXPORT_SYMBOL(fd_install);
 
-/*
- * The same warnings as for __alloc_fd()/__fd_install() apply here...
- */
-int __close_fd(struct files_struct *files, unsigned fd)
+static struct file *pick_file(struct files_struct *files, unsigned fd)
 {
-	struct file *file;
+	struct file *file = NULL;
 	struct fdtable *fdt;
 
 	spin_lock(&files->file_lock);
@@ -637,15 +635,65 @@ int __close_fd(struct files_struct *files, unsigned fd)
 		goto out_unlock;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
 	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-	return filp_close(file, files);
 
 out_unlock:
 	spin_unlock(&files->file_lock);
-	return -EBADF;
+	return file;
+}
+
+/*
+ * The same warnings as for __alloc_fd()/__fd_install() apply here...
+ */
+int __close_fd(struct files_struct *files, unsigned fd)
+{
+	struct file *file;
+
+	file = pick_file(files, fd);
+	if (!file)
+		return -EBADF;
+
+	return filp_close(file, files);
 }
 EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
 
+/**
+ * __close_range() - Close all file descriptors in a given range.
+ *
+ * @fd:     starting file descriptor to close
+ * @max_fd: last file descriptor to close
+ *
+ * This closes a range of file descriptors. All file descriptors
+ * from @fd up to and including @max_fd are closed.
+ */
+int __close_range(struct files_struct *files, unsigned fd, unsigned max_fd)
+{
+	unsigned int cur_max;
+
+	if (fd > max_fd)
+		return -EINVAL;
+
+	rcu_read_lock();
+	cur_max = files_fdtable(files)->max_fds;
+	rcu_read_unlock();
+
+	/* cap to last valid index into fdtable */
+	cur_max--;
+
+	max_fd = min(max_fd, cur_max);
+	while (fd <= max_fd) {
+		struct file *file;
+
+		file = pick_file(files, fd++);
+		if (!file)
+			continue;
+
+		filp_close(file, files);
+		cond_resched();
+	}
+
+	return 0;
+}
+
 /*
  * variant of __close_fd that gets a ref on the file for later fput.
  * The caller must ensure that filp_close() called on the file, and then
diff --git a/fs/open.c b/fs/open.c
index 6cd48a61cda3..073ea3c45347 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1310,6 +1310,26 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	return retval;
 }
 
+/**
+ * close_range() - Close all file descriptors in a given range.
+ *
+ * @fd:     starting file descriptor to close
+ * @max_fd: last file descriptor to close
+ * @flags:  reserved for future extensions
+ *
+ * This closes a range of file descriptors. All file descriptors
+ * from @fd up to and including @max_fd are closed.
+ * Currently, errors to close a given file descriptor are ignored.
+ */
+SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
+		unsigned int, flags)
+{
+	if (flags)
+		return -EINVAL;
+
+	return __close_range(current->files, fd, max_fd);
+}
+
 /*
  * This routine simulates a hangup on the tty, to arrange that users
  * are given clean terminals at login time.
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index f07c55ea0c22..fcd07181a365 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -121,6 +121,8 @@ extern void __fd_install(struct files_struct *files,
 		      unsigned int fd, struct file *file);
 extern int __close_fd(struct files_struct *files,
 		      unsigned int fd);
+extern int __close_range(struct files_struct *files, unsigned int fd,
+			 unsigned int max_fd);
 extern int __close_fd_get_file(unsigned int fd, struct file **res);
 
 extern struct kmem_cache *files_cachep;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7c354c2955f5..b22382db89cf 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -444,6 +444,8 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
 asmlinkage long sys_openat2(int dfd, const char __user *filename,
 			    struct open_how *how, size_t size);
 asmlinkage long sys_close(unsigned int fd);
+asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd,
+				unsigned int flags);
 asmlinkage long sys_vhangup(void);
 
 /* fs/pipe.c */
-- 
cgit v1.2.3


From 60997c3d45d9a67daf01c56d805ae4fec37e0bd8 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 3 Jun 2020 21:48:55 +0200
Subject: close_range: add CLOSE_RANGE_UNSHARE

One of the use-cases of close_range() is to drop file descriptors just before
execve(). This would usually be expressed in the sequence:

unshare(CLONE_FILES);
close_range(3, ~0U);

as pointed out by Linus it might be desirable to have this be a part of
close_range() itself under a new flag CLOSE_RANGE_UNSHARE.

This expands {dup,unshare)_fd() to take a max_fds argument that indicates the
maximum number of file descriptors to copy from the old struct files. When the
user requests that all file descriptors are supposed to be closed via
close_range(min, max) then we can cap via unshare_fd(min) and hence don't need
to do any of the heavy fput() work for everything above min.

The patch makes it so that if CLOSE_RANGE_UNSHARE is requested and we do in
fact currently share our file descriptor table we create a new private copy.
We then close all fds in the requested range and finally after we're done we
install the new fd table.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/file.c                        | 65 +++++++++++++++++++++++++++++++++++-----
 fs/open.c                        |  5 +---
 include/linux/fdtable.h          |  8 +++--
 include/uapi/linux/close_range.h |  9 ++++++
 kernel/fork.c                    | 11 +++----
 5 files changed, 79 insertions(+), 19 deletions(-)
 create mode 100644 include/uapi/linux/close_range.h

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 1b8ff05e8311..340bc9569f9d 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -19,6 +19,7 @@
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/close_range.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -265,12 +266,22 @@ static unsigned int count_open_files(struct fdtable *fdt)
 	return i;
 }
 
+static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
+{
+	unsigned int count;
+
+	count = count_open_files(fdt);
+	if (max_fds < NR_OPEN_DEFAULT)
+		max_fds = NR_OPEN_DEFAULT;
+	return min(count, max_fds);
+}
+
 /*
  * Allocate a new files structure and copy contents from the
  * passed in files structure.
  * errorp will be valid only when the returned files_struct is NULL.
  */
-struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
+struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
 {
 	struct files_struct *newf;
 	struct file **old_fds, **new_fds;
@@ -297,7 +308,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 
 	spin_lock(&oldf->file_lock);
 	old_fdt = files_fdtable(oldf);
-	open_files = count_open_files(old_fdt);
+	open_files = sane_fdtable_size(old_fdt, max_fds);
 
 	/*
 	 * Check whether we need to allocate a larger fd array and fd set.
@@ -328,7 +339,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 		 */
 		spin_lock(&oldf->file_lock);
 		old_fdt = files_fdtable(oldf);
-		open_files = count_open_files(old_fdt);
+		open_files = sane_fdtable_size(old_fdt, max_fds);
 	}
 
 	copy_fd_bitmaps(new_fdt, old_fdt, open_files);
@@ -665,32 +676,72 @@ EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
  * This closes a range of file descriptors. All file descriptors
  * from @fd up to and including @max_fd are closed.
  */
-int __close_range(struct files_struct *files, unsigned fd, unsigned max_fd)
+int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 {
 	unsigned int cur_max;
+	struct task_struct *me = current;
+	struct files_struct *cur_fds = me->files, *fds = NULL;
+
+	if (flags & ~CLOSE_RANGE_UNSHARE)
+		return -EINVAL;
 
 	if (fd > max_fd)
 		return -EINVAL;
 
 	rcu_read_lock();
-	cur_max = files_fdtable(files)->max_fds;
+	cur_max = files_fdtable(cur_fds)->max_fds;
 	rcu_read_unlock();
 
 	/* cap to last valid index into fdtable */
 	cur_max--;
 
+	if (flags & CLOSE_RANGE_UNSHARE) {
+		int ret;
+		unsigned int max_unshare_fds = NR_OPEN_MAX;
+
+		/*
+		 * If the requested range is greater than the current maximum,
+		 * we're closing everything so only copy all file descriptors
+		 * beneath the lowest file descriptor.
+		 */
+		if (max_fd >= cur_max)
+			max_unshare_fds = fd;
+
+		ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
+		if (ret)
+			return ret;
+
+		/*
+		 * We used to share our file descriptor table, and have now
+		 * created a private one, make sure we're using it below.
+		 */
+		if (fds)
+			swap(cur_fds, fds);
+	}
+
 	max_fd = min(max_fd, cur_max);
 	while (fd <= max_fd) {
 		struct file *file;
 
-		file = pick_file(files, fd++);
+		file = pick_file(cur_fds, fd++);
 		if (!file)
 			continue;
 
-		filp_close(file, files);
+		filp_close(file, cur_fds);
 		cond_resched();
 	}
 
+	if (fds) {
+		/*
+		 * We're done closing the files we were supposed to. Time to install
+		 * the new file descriptor table and drop the old one.
+		 */
+		task_lock(me);
+		me->files = cur_fds;
+		task_unlock(me);
+		put_files_struct(fds);
+	}
+
 	return 0;
 }
 
diff --git a/fs/open.c b/fs/open.c
index 073ea3c45347..5e62f18adc5b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1324,10 +1324,7 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
 		unsigned int, flags)
 {
-	if (flags)
-		return -EINVAL;
-
-	return __close_range(current->files, fd, max_fd);
+	return __close_range(fd, max_fd, flags);
 }
 
 /*
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index fcd07181a365..a32bf47c593e 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -22,6 +22,7 @@
  * as this is the granularity returned by copy_fdset().
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
+#define NR_OPEN_MAX ~0U
 
 struct fdtable {
 	unsigned int max_fds;
@@ -109,7 +110,7 @@ struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
 void reset_files_struct(struct files_struct *);
 int unshare_files(struct files_struct **);
-struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy;
+struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
 int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
@@ -121,9 +122,10 @@ extern void __fd_install(struct files_struct *files,
 		      unsigned int fd, struct file *file);
 extern int __close_fd(struct files_struct *files,
 		      unsigned int fd);
-extern int __close_range(struct files_struct *files, unsigned int fd,
-			 unsigned int max_fd);
+extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
 extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+		      struct files_struct **new_fdp);
 
 extern struct kmem_cache *files_cachep;
 
diff --git a/include/uapi/linux/close_range.h b/include/uapi/linux/close_range.h
new file mode 100644
index 000000000000..6928a9fdee3c
--- /dev/null
+++ b/include/uapi/linux/close_range.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_CLOSE_RANGE_H
+#define _UAPI_LINUX_CLOSE_RANGE_H
+
+/* Unshare the file descriptor table before closing file descriptors. */
+#define CLOSE_RANGE_UNSHARE	(1U << 1)
+
+#endif /* _UAPI_LINUX_CLOSE_RANGE_H */
+
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..8948121c8454 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1474,7 +1474,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 		goto out;
 	}
 
-	newf = dup_fd(oldf, &error);
+	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
 	if (!newf)
 		goto out;
 
@@ -2907,14 +2907,15 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
+int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+	       struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
 	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, &error);
+		*new_fdp = dup_fd(fd, max_fds, &error);
 		if (!*new_fdp)
 			return error;
 	}
@@ -2974,7 +2975,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, &new_fd);
+	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3063,7 +3064,7 @@ int unshare_files(struct files_struct **displaced)
 	struct files_struct *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, &copy);
+	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
 	if (error || !copy) {
 		*displaced = NULL;
 		return error;
-- 
cgit v1.2.3


From 9b38cc704e844e41d9cf74e647bff1d249512cb3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 12 May 2020 17:03:18 +0900
Subject: kretprobe: Prevent triggering kretprobe from within kprobe_flush_task

Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave.
My test was also able to trigger lockdep output:

 ============================================
 WARNING: possible recursive locking detected
 5.6.0-rc6+ #6 Not tainted
 --------------------------------------------
 sched-messaging/2767 is trying to acquire lock:
 ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0

 but task is already holding lock:
 ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&(kretprobe_table_locks[i].lock));
   lock(&(kretprobe_table_locks[i].lock));

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 1 lock held by sched-messaging/2767:
  #0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50

 stack backtrace:
 CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6
 Call Trace:
  dump_stack+0x96/0xe0
  __lock_acquire.cold.57+0x173/0x2b7
  ? native_queued_spin_lock_slowpath+0x42b/0x9e0
  ? lockdep_hardirqs_on+0x590/0x590
  ? __lock_acquire+0xf63/0x4030
  lock_acquire+0x15a/0x3d0
  ? kretprobe_hash_lock+0x52/0xa0
  _raw_spin_lock_irqsave+0x36/0x70
  ? kretprobe_hash_lock+0x52/0xa0
  kretprobe_hash_lock+0x52/0xa0
  trampoline_handler+0xf8/0x940
  ? kprobe_fault_handler+0x380/0x380
  ? find_held_lock+0x3a/0x1c0
  kretprobe_trampoline+0x25/0x50
  ? lock_acquired+0x392/0xbc0
  ? _raw_spin_lock_irqsave+0x50/0x70
  ? __get_valid_kprobe+0x1f0/0x1f0
  ? _raw_spin_unlock_irqrestore+0x3b/0x40
  ? finish_task_switch+0x4b9/0x6d0
  ? __switch_to_asm+0x34/0x70
  ? __switch_to_asm+0x40/0x70

The code within the kretprobe handler checks for probe reentrancy,
so we won't trigger any _raw_spin_lock_irqsave probe in there.

The problem is in outside kprobe_flush_task, where we call:

  kprobe_flush_task
    kretprobe_table_lock
      raw_spin_lock_irqsave
        _raw_spin_lock_irqsave

where _raw_spin_lock_irqsave triggers the kretprobe and installs
kretprobe_trampoline handler on _raw_spin_lock_irqsave return.

The kretprobe_trampoline handler is then executed with already
locked kretprobe_table_locks, and first thing it does is to
lock kretprobe_table_locks ;-) the whole lockup path like:

  kprobe_flush_task
    kretprobe_table_lock
      raw_spin_lock_irqsave
        _raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed

        ---> kretprobe_table_locks locked

        kretprobe_trampoline
          trampoline_handler
            kretprobe_hash_lock(current, &head, &flags);  <--- deadlock

Adding kprobe_busy_begin/end helpers that mark code with fake
probe installed to prevent triggering of another kprobe within
this code.

Using these helpers in kprobe_flush_task, so the probe recursion
protection check is hit and the probe is never set to prevent
above lockup.

Link: http://lkml.kernel.org/r/158927059835.27680.7011202830041561604.stgit@devnote2

Fixes: ef53d9c5e4da ("kprobes: improve kretprobe scalability with hashed locking")
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Gustavo A . R . Silva" <gustavoars@kernel.org>
Cc: Anders Roxell <anders.roxell@linaro.org>
Cc: "Naveen N . Rao" <naveen.n.rao@linux.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Reported-by: "Ziqian SUN (Zamir)" <zsun@redhat.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/kernel/kprobes/core.c | 16 +++-------------
 include/linux/kprobes.h        |  4 ++++
 kernel/kprobes.c               | 24 ++++++++++++++++++++++++
 3 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3bafe1bd4dc7..8a5ec10e95dc 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -753,16 +753,11 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
-static struct kprobe kretprobe_kprobe = {
-	.addr = (void *)kretprobe_trampoline,
-};
-
 /*
  * Called from kretprobe_trampoline
  */
 __used __visible void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -772,16 +767,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
-	preempt_disable();
-
 	/*
 	 * Set a dummy kprobe for avoiding kretprobe recursion.
 	 * Since kretprobe never run in kprobe handler, kprobe must not
 	 * be running at this point.
 	 */
-	kcb = get_kprobe_ctlblk();
-	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	kprobe_busy_begin();
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -857,7 +848,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+			__this_cpu_write(current_kprobe, &kprobe_busy);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -873,8 +864,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
+	kprobe_busy_end();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 594265bfd390..05ed663e6c7b 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -350,6 +350,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
+extern struct kprobe kprobe_busy;
+void kprobe_busy_begin(void);
+void kprobe_busy_end(void);
+
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 5cb7791c16b3..4a904cc56d68 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1241,6 +1241,26 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
+struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
  * so that we can recycle any function-return probe instances associated
@@ -1258,6 +1278,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	kprobe_busy_begin();
+
 	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
@@ -1271,6 +1293,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
+
+	kprobe_busy_end();
 }
 NOKPROBE_SYMBOL(kprobe_flush_task);
 
-- 
cgit v1.2.3


From b19d57d0f3cc6f1022edf94daf1d70506a09e3c2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 8 Jun 2020 20:22:33 -0500
Subject: overflow.h: Add flex_array_size() helper

Add flex_array_size() helper for the calculation of the size, in bytes,
of a flexible array member contained within an enclosing structure.

Example of usage:

struct something {
	size_t count;
	struct foo items[];
};

struct something *instance;

instance = kmalloc(struct_size(instance, items, count), GFP_KERNEL);
instance->count = count;
memcpy(instance->items, src, flex_array_size(instance, items, instance->count));

The helper returns SIZE_MAX on overflow instead of wrapping around.

Additionally replaces parameter "n" with "count" in struct_size() helper
for greater clarity and unification.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20200609012233.GA3371@embeddedor
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/overflow.h | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 659045046468..93fcef105061 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -304,16 +304,33 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c)
  * struct_size() - Calculate size of structure with trailing array.
  * @p: Pointer to the structure.
  * @member: Name of the array member.
- * @n: Number of elements in the array.
+ * @count: Number of elements in the array.
  *
  * Calculates size of memory needed for structure @p followed by an
- * array of @n @member elements.
+ * array of @count number of @member elements.
  *
  * Return: number of bytes needed or SIZE_MAX on overflow.
  */
-#define struct_size(p, member, n)					\
-	__ab_c_size(n,							\
+#define struct_size(p, member, count)					\
+	__ab_c_size(count,						\
 		    sizeof(*(p)->member) + __must_be_array((p)->member),\
 		    sizeof(*(p)))
 
+/**
+ * flex_array_size() - Calculate size of a flexible array member
+ *                     within an enclosing structure.
+ *
+ * @p: Pointer to the structure.
+ * @member: Name of the flexible array member.
+ * @count: Number of elements in the array.
+ *
+ * Calculates size of a flexible array of @count number of @member
+ * elements, at the end of structure @p.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define flex_array_size(p, member, count)				\
+	array_size(count,						\
+		    sizeof(*(p)->member) + __must_be_array((p)->member))
+
 #endif /* __LINUX_OVERFLOW_H */
-- 
cgit v1.2.3


From 26749b3201ab05e288fbf78fbc8585dfa2da3218 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 Jun 2020 08:52:31 +0200
Subject: dma-direct: mark __dma_direct_alloc_pages static

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h | 2 --
 kernel/dma/direct.c        | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 136f984df0d9..cdfa400f89b3 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -77,8 +77,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
-struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		gfp_t gfp, unsigned long attrs);
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 9ec6a5c3fc57..30c41b57acd9 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -109,7 +109,7 @@ static inline bool dma_should_free_from_pool(struct device *dev,
 	return false;
 }
 
-struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
+static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, unsigned long attrs)
 {
 	size_t alloc_size = PAGE_ALIGN(size);
-- 
cgit v1.2.3


From 2a55280a3675203496d302463b941834228b9875 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Sun, 7 Jun 2020 15:41:35 +0200
Subject: efi/libstub: arm: Print CPU boot mode and MMU state at boot

On 32-bit ARM, we may boot at HYP mode, or with the MMU and caches off
(or both), even though the EFI spec does not actually support this.
While booting at HYP mode is something we might tolerate, fiddling
with the caches is a more serious issue, as disabling the caches is
tricky to do safely from C code, and running without the Dcache makes
it impossible to support unaligned memory accesses, which is another
explicit requirement imposed by the EFI spec.

So take note of the CPU mode and MMU state in the EFI stub diagnostic
output so that we can easily diagnose any issues that may arise from
this. E.g.,

  EFI stub: Entering in SVC mode with MMU enabled

Also, capture the CPSR and SCTLR system register values at EFI stub
entry, and after ExitBootServices() returns, and check whether the
MMU and Dcache were disabled at any point. If this is the case, a
diagnostic message like the following will be emitted:

  efi: [Firmware Bug]: EFI stub was entered with MMU and Dcache disabled, please fix your firmware!
  efi: CPSR at EFI stub entry        : 0x600001d3
  efi: SCTLR at EFI stub entry       : 0x00c51838
  efi: CPSR after ExitBootServices() : 0x600001d3
  efi: SCTLR after ExitBootServices(): 0x00c50838

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Leif Lindholm <leif@nuviainc.com>
---
 arch/arm/include/asm/efi.h                |  7 ++++
 drivers/firmware/efi/arm-init.c           | 34 +++++++++++++++++--
 drivers/firmware/efi/libstub/arm32-stub.c | 54 ++++++++++++++++++++++++++++++-
 drivers/firmware/efi/libstub/efi-stub.c   |  3 ++
 drivers/firmware/efi/libstub/efistub.h    |  2 ++
 include/linux/efi.h                       |  1 +
 6 files changed, 98 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 84dc0ba822f5..5dcf3c6011b7 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -87,4 +87,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 	return dram_base + SZ_512M;
 }
 
+struct efi_arm_entry_state {
+	u32	cpsr_before_ebs;
+	u32	sctlr_before_ebs;
+	u32	cpsr_after_ebs;
+	u32	sctlr_after_ebs;
+};
+
 #endif /* _ASM_ARM_EFI_H */
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 6f4baf70db16..71c445d20258 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -52,9 +52,11 @@ static phys_addr_t __init efi_to_phys(unsigned long addr)
 }
 
 static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR;
+static __initdata unsigned long cpu_state_table = EFI_INVALID_TABLE_ADDR;
 
 static const efi_config_table_type_t arch_tables[] __initconst = {
 	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table},
+	{LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table},
 	{}
 };
 
@@ -240,9 +242,37 @@ void __init efi_init(void)
 
 	init_screen_info();
 
+#ifdef CONFIG_ARM
 	/* ARM does not permit early mappings to persist across paging_init() */
-	if (IS_ENABLED(CONFIG_ARM))
-		efi_memmap_unmap();
+	efi_memmap_unmap();
+
+	if (cpu_state_table != EFI_INVALID_TABLE_ADDR) {
+		struct efi_arm_entry_state *state;
+		bool dump_state = true;
+
+		state = early_memremap_ro(cpu_state_table,
+					  sizeof(struct efi_arm_entry_state));
+		if (state == NULL) {
+			pr_warn("Unable to map CPU entry state table.\n");
+			return;
+		}
+
+		if ((state->sctlr_before_ebs & 1) == 0)
+			pr_warn(FW_BUG "EFI stub was entered with MMU and Dcache disabled, please fix your firmware!\n");
+		else if ((state->sctlr_after_ebs & 1) == 0)
+			pr_warn(FW_BUG "ExitBootServices() returned with MMU and Dcache disabled, please fix your firmware!\n");
+		else
+			dump_state = false;
+
+		if (dump_state || efi_enabled(EFI_DBG)) {
+			pr_info("CPSR at EFI stub entry        : 0x%08x\n", state->cpsr_before_ebs);
+			pr_info("SCTLR at EFI stub entry       : 0x%08x\n", state->sctlr_before_ebs);
+			pr_info("CPSR after ExitBootServices() : 0x%08x\n", state->cpsr_after_ebs);
+			pr_info("SCTLR after ExitBootServices(): 0x%08x\n", state->sctlr_after_ebs);
+		}
+		early_memunmap(state, sizeof(struct efi_arm_entry_state));
+	}
+#endif
 }
 
 static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 40243f524556..d08e5d55838c 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -7,10 +7,49 @@
 
 #include "efistub.h"
 
+static efi_guid_t cpu_state_guid = LINUX_EFI_ARM_CPU_STATE_TABLE_GUID;
+
+struct efi_arm_entry_state *efi_entry_state;
+
+static void get_cpu_state(u32 *cpsr, u32 *sctlr)
+{
+	asm("mrs %0, cpsr" : "=r"(*cpsr));
+	if ((*cpsr & MODE_MASK) == HYP_MODE)
+		asm("mrc p15, 4, %0, c1, c0, 0" : "=r"(*sctlr));
+	else
+		asm("mrc p15, 0, %0, c1, c0, 0" : "=r"(*sctlr));
+}
+
 efi_status_t check_platform_features(void)
 {
+	efi_status_t status;
+	u32 cpsr, sctlr;
 	int block;
 
+	get_cpu_state(&cpsr, &sctlr);
+
+	efi_info("Entering in %s mode with MMU %sabled\n",
+		 ((cpsr & MODE_MASK) == HYP_MODE) ? "HYP" : "SVC",
+		 (sctlr & 1) ? "en" : "dis");
+
+	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA,
+			     sizeof(*efi_entry_state),
+			     (void **)&efi_entry_state);
+	if (status != EFI_SUCCESS) {
+		efi_err("allocate_pool() failed\n");
+		return status;
+	}
+
+	efi_entry_state->cpsr_before_ebs = cpsr;
+	efi_entry_state->sctlr_before_ebs = sctlr;
+
+	status = efi_bs_call(install_configuration_table, &cpu_state_guid,
+			     efi_entry_state);
+	if (status != EFI_SUCCESS) {
+		efi_err("install_configuration_table() failed\n");
+		goto free_state;
+	}
+
 	/* non-LPAE kernels can run anywhere */
 	if (!IS_ENABLED(CONFIG_ARM_LPAE))
 		return EFI_SUCCESS;
@@ -19,9 +58,22 @@ efi_status_t check_platform_features(void)
 	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
 	if (block < 5) {
 		efi_err("This LPAE kernel is not supported by your CPU\n");
-		return EFI_UNSUPPORTED;
+		status = EFI_UNSUPPORTED;
+		goto drop_table;
 	}
 	return EFI_SUCCESS;
+
+drop_table:
+	efi_bs_call(install_configuration_table, &cpu_state_guid, NULL);
+free_state:
+	efi_bs_call(free_pool, efi_entry_state);
+	return status;
+}
+
+void efi_handle_post_ebs_state(void)
+{
+	get_cpu_state(&efi_entry_state->cpsr_after_ebs,
+		      &efi_entry_state->sctlr_after_ebs);
 }
 
 static efi_guid_t screen_info_guid = LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID;
diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index e97370bdfdb0..3318ec3f8e5b 100644
--- a/drivers/firmware/efi/libstub/efi-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -329,6 +329,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	if (status != EFI_SUCCESS)
 		goto fail_free_initrd;
 
+	if (IS_ENABLED(CONFIG_ARM))
+		efi_handle_post_ebs_state();
+
 	efi_enter_kernel(image_addr, fdt_addr, fdt_totalsize((void *)fdt_addr));
 	/* not reached */
 
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index ac756f1fdb1a..2c9d42264c29 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -777,4 +777,6 @@ efi_status_t efi_load_initrd(efi_loaded_image_t *image,
 			     unsigned long soft_limit,
 			     unsigned long hard_limit);
 
+void efi_handle_post_ebs_state(void);
+
 #endif
diff --git a/include/linux/efi.h b/include/linux/efi.h
index c3449c9699d0..bb35f3305e55 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -350,6 +350,7 @@ void efi_native_runtime_setup(void);
  * associated with ConOut
  */
 #define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID	EFI_GUID(0xe03fc20a, 0x85dc, 0x406e,  0xb9, 0x0e, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95)
+#define LINUX_EFI_ARM_CPU_STATE_TABLE_GUID	EFI_GUID(0xef79e4aa, 0x3c3d, 0x4989,  0xb9, 0x02, 0x07, 0xa9, 0x43, 0xe5, 0x50, 0xd2)
 #define LINUX_EFI_LOADER_ENTRY_GUID		EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf,  0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f)
 #define LINUX_EFI_RANDOM_SEED_TABLE_GUID	EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2,  0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b)
 #define LINUX_EFI_TPM_EVENT_LOG_GUID		EFI_GUID(0xb7799cb0, 0xeca2, 0x4943,  0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa)
-- 
cgit v1.2.3


From 47ec7f09bc107720905c96bc37771e4ed1ff0aed Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 13 May 2020 11:47:49 -0700
Subject: dmaengine: cookie bypass for out of order completion

The cookie tracking in dmaengine expects all submissions completed in
order. Some DMA devices like Intel DSA can complete submissions out of
order, especially if configured with a work queue sharing multiple DMA
engines. Add a status DMA_OUT_OF_ORDER that tx_status can be returned for
those DMA devices. The user should use callbacks to track the completion
rather than the DMA cookie. This would address the issue of dmatest
complaining that descriptors are "busy" when the cookie count goes
backwards due to out of order completion. Add DMA_COMPLETION_NO_ORDER
DMA capability to allow the driver to flag the device's ability to complete
operations out of order.

Reported-by: Swathi Kovvuri <swathi.kovvuri@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Swathi Kovvuri <swathi.kovvuri@intel.com>
Link: https://lore.kernel.org/r/158939557151.20335.12404113976045569870.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/driver-api/dmaengine/provider.rst | 19 +++++++++++++++++++
 drivers/dma/dmatest.c                           | 11 ++++++++++-
 drivers/dma/idxd/dma.c                          |  3 ++-
 include/linux/dmaengine.h                       |  2 ++
 4 files changed, 33 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 56e5833e8a07..ce68315482b1 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -239,6 +239,22 @@ Currently, the types available are:
     want to transfer a portion of uncompressed data directly to the
     display to print it
 
+- DMA_COMPLETION_NO_ORDER
+
+  - The device does not support in order completion.
+
+  - The driver should return DMA_OUT_OF_ORDER for device_tx_status if
+    the device is setting this capability.
+
+  - All cookie tracking and checking API should be treated as invalid if
+    the device exports this capability.
+
+  - At this point, this is incompatible with polling option for dmatest.
+
+  - If this cap is set, the user is recommended to provide an unique
+    identifier for each descriptor sent to the DMA device in order to
+    properly track the completion.
+
 These various types will also affect how the source and destination
 addresses change over time.
 
@@ -399,6 +415,9 @@ supported.
   - In the case of a cyclic transfer, it should only take into
     account the current period.
 
+  - Should return DMA_OUT_OF_ORDER if the device does not support in order
+    completion and is completing the operation out of order.
+
   - This function can be called in an interrupt context.
 
 - device_config
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index b175229a4b01..18f10154ba19 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -829,7 +829,10 @@ static int dmatest_func(void *data)
 			result("test timed out", total_tests, src->off, dst->off,
 			       len, 0);
 			goto error_unmap_continue;
-		} else if (status != DMA_COMPLETE) {
+		} else if (status != DMA_COMPLETE &&
+			   !(dma_has_cap(DMA_COMPLETION_NO_ORDER,
+					 dev->cap_mask) &&
+			     status == DMA_OUT_OF_ORDER)) {
 			result(status == DMA_ERROR ?
 			       "completion error status" :
 			       "completion busy status", total_tests, src->off,
@@ -1007,6 +1010,12 @@ static int dmatest_add_channel(struct dmatest_info *info,
 	dtc->chan = chan;
 	INIT_LIST_HEAD(&dtc->threads);
 
+	if (dma_has_cap(DMA_COMPLETION_NO_ORDER, dma_dev->cap_mask) &&
+	    info->params.polled) {
+		info->params.polled = false;
+		pr_warn("DMA_COMPLETION_NO_ORDER, polled disabled\n");
+	}
+
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
 		if (dmatest == 0) {
 			cnt = dmatest_add_threads(info, dtc, DMA_MEMCPY);
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index c64c1429d160..0c892cbd72e0 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -133,7 +133,7 @@ static enum dma_status idxd_dma_tx_status(struct dma_chan *dma_chan,
 					  dma_cookie_t cookie,
 					  struct dma_tx_state *txstate)
 {
-	return dma_cookie_status(dma_chan, cookie, txstate);
+	return DMA_OUT_OF_ORDER;
 }
 
 /*
@@ -174,6 +174,7 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	INIT_LIST_HEAD(&dma->channels);
 	dma->dev = &idxd->pdev->dev;
 
+	dma_cap_set(DMA_COMPLETION_NO_ORDER, dma->cap_mask);
 	dma->device_release = idxd_dma_release;
 
 	if (idxd->hw.opcap.bits[0] & IDXD_OPCAP_MEMMOVE) {
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index e1c03339918f..9f9a13a2c01f 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -39,6 +39,7 @@ enum dma_status {
 	DMA_IN_PROGRESS,
 	DMA_PAUSED,
 	DMA_ERROR,
+	DMA_OUT_OF_ORDER,
 };
 
 /**
@@ -61,6 +62,7 @@ enum dma_transaction_type {
 	DMA_SLAVE,
 	DMA_CYCLIC,
 	DMA_INTERLEAVE,
+	DMA_COMPLETION_NO_ORDER,
 /* last transaction type for creation of the capabilities mask */
 	DMA_TX_TYPE_END,
 };
-- 
cgit v1.2.3


From 2accfa69050c2a0d6fc6106f609208b3e9622b26 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 17 Jun 2020 07:14:10 -0700
Subject: cpu/speculation: Add prototype for cpu_show_srbds()

0-day is not happy that there is no prototype for cpu_show_srbds():

  drivers/base/cpu.c:565:16: error: no previous prototype for 'cpu_show_srbds'

Fixes: 7e5b3c267d25 ("x86/speculation: Add Special Register Buffer Data Sampling (SRBDS) mitigation")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200617141410.93338-1-linux@roeck-us.net
---
 include/linux/cpu.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 52692587f7fe..8aa84c052fdf 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -64,6 +64,7 @@ extern ssize_t cpu_show_tsx_async_abort(struct device *dev,
 					char *buf);
 extern ssize_t cpu_show_itlb_multihit(struct device *dev,
 				      struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
-- 
cgit v1.2.3


From c935cd62d3fe985d7f0ebea185d2759e8992e96f Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 17 Jun 2020 17:17:19 +1000
Subject: lockdep: Split header file into lockdep and lockdep_types

There is a header file inclusion loop between asm-generic/bug.h
and linux/kernel.h.  This causes potential compile failurs depending
on the which file is included first.  One way of breaking this loop
is to stop spinlock_types.h from including lockdep.h.  This patch
splits lockdep.h into two files for this purpose.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Petr Mladek <pmladek@suse.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/E1jlSJz-0003hE-8g@fornost.hmeau.com
---
 include/linux/lockdep.h        | 178 +------------------------------------
 include/linux/lockdep_types.h  | 196 +++++++++++++++++++++++++++++++++++++++++
 include/linux/spinlock.h       |   1 +
 include/linux/spinlock_types.h |   2 +-
 4 files changed, 200 insertions(+), 177 deletions(-)
 create mode 100644 include/linux/lockdep_types.h

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 8fce5c98a4b0..3b73cf84f77d 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -10,181 +10,20 @@
 #ifndef __LINUX_LOCKDEP_H
 #define __LINUX_LOCKDEP_H
 
+#include <linux/lockdep_types.h>
+
 struct task_struct;
-struct lockdep_map;
 
 /* for sysctl */
 extern int prove_locking;
 extern int lock_stat;
 
-#define MAX_LOCKDEP_SUBCLASSES		8UL
-
-#include <linux/types.h>
-
-enum lockdep_wait_type {
-	LD_WAIT_INV = 0,	/* not checked, catch all */
-
-	LD_WAIT_FREE,		/* wait free, rcu etc.. */
-	LD_WAIT_SPIN,		/* spin loops, raw_spinlock_t etc.. */
-
-#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
-	LD_WAIT_CONFIG,		/* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */
-#else
-	LD_WAIT_CONFIG = LD_WAIT_SPIN,
-#endif
-	LD_WAIT_SLEEP,		/* sleeping locks, mutex_t etc.. */
-
-	LD_WAIT_MAX,		/* must be last */
-};
-
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
-#include <linux/list.h>
 #include <linux/debug_locks.h>
 #include <linux/stacktrace.h>
 
-/*
- * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
- * the total number of states... :-(
- */
-#define XXX_LOCK_USAGE_STATES		(1+2*4)
-
-/*
- * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
- * cached in the instance of lockdep_map
- *
- * Currently main class (subclass == 0) and signle depth subclass
- * are cached in lockdep_map. This optimization is mainly targeting
- * on rq->lock. double_rq_lock() acquires this highly competitive with
- * single depth.
- */
-#define NR_LOCKDEP_CACHING_CLASSES	2
-
-/*
- * A lockdep key is associated with each lock object. For static locks we use
- * the lock address itself as the key. Dynamically allocated lock objects can
- * have a statically or dynamically allocated key. Dynamically allocated lock
- * keys must be registered before being used and must be unregistered before
- * the key memory is freed.
- */
-struct lockdep_subclass_key {
-	char __one_byte;
-} __attribute__ ((__packed__));
-
-/* hash_entry is used to keep track of dynamically allocated keys. */
-struct lock_class_key {
-	union {
-		struct hlist_node		hash_entry;
-		struct lockdep_subclass_key	subkeys[MAX_LOCKDEP_SUBCLASSES];
-	};
-};
-
-extern struct lock_class_key __lockdep_no_validate__;
-
-struct lock_trace;
-
-#define LOCKSTAT_POINTS		4
-
-/*
- * The lock-class itself. The order of the structure members matters.
- * reinit_class() zeroes the key member and all subsequent members.
- */
-struct lock_class {
-	/*
-	 * class-hash:
-	 */
-	struct hlist_node		hash_entry;
-
-	/*
-	 * Entry in all_lock_classes when in use. Entry in free_lock_classes
-	 * when not in use. Instances that are being freed are on one of the
-	 * zapped_classes lists.
-	 */
-	struct list_head		lock_entry;
-
-	/*
-	 * These fields represent a directed graph of lock dependencies,
-	 * to every node we attach a list of "forward" and a list of
-	 * "backward" graph nodes.
-	 */
-	struct list_head		locks_after, locks_before;
-
-	const struct lockdep_subclass_key *key;
-	unsigned int			subclass;
-	unsigned int			dep_gen_id;
-
-	/*
-	 * IRQ/softirq usage tracking bits:
-	 */
-	unsigned long			usage_mask;
-	const struct lock_trace		*usage_traces[XXX_LOCK_USAGE_STATES];
-
-	/*
-	 * Generation counter, when doing certain classes of graph walking,
-	 * to ensure that we check one node only once:
-	 */
-	int				name_version;
-	const char			*name;
-
-	short				wait_type_inner;
-	short				wait_type_outer;
-
-#ifdef CONFIG_LOCK_STAT
-	unsigned long			contention_point[LOCKSTAT_POINTS];
-	unsigned long			contending_point[LOCKSTAT_POINTS];
-#endif
-} __no_randomize_layout;
-
-#ifdef CONFIG_LOCK_STAT
-struct lock_time {
-	s64				min;
-	s64				max;
-	s64				total;
-	unsigned long			nr;
-};
-
-enum bounce_type {
-	bounce_acquired_write,
-	bounce_acquired_read,
-	bounce_contended_write,
-	bounce_contended_read,
-	nr_bounce_types,
-
-	bounce_acquired = bounce_acquired_write,
-	bounce_contended = bounce_contended_write,
-};
-
-struct lock_class_stats {
-	unsigned long			contention_point[LOCKSTAT_POINTS];
-	unsigned long			contending_point[LOCKSTAT_POINTS];
-	struct lock_time		read_waittime;
-	struct lock_time		write_waittime;
-	struct lock_time		read_holdtime;
-	struct lock_time		write_holdtime;
-	unsigned long			bounces[nr_bounce_types];
-};
-
-struct lock_class_stats lock_stats(struct lock_class *class);
-void clear_lock_stats(struct lock_class *class);
-#endif
-
-/*
- * Map the lock object (the lock instance) to the lock-class object.
- * This is embedded into specific lock instances:
- */
-struct lockdep_map {
-	struct lock_class_key		*key;
-	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
-	const char			*name;
-	short				wait_type_outer; /* can be taken in this context */
-	short				wait_type_inner; /* presents this context */
-#ifdef CONFIG_LOCK_STAT
-	int				cpu;
-	unsigned long			ip;
-#endif
-};
-
 static inline void lockdep_copy_map(struct lockdep_map *to,
 				    struct lockdep_map *from)
 {
@@ -440,8 +279,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 
 extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
 
-struct pin_cookie { unsigned int val; };
-
 #define NIL_COOKIE (struct pin_cookie){ .val = 0U, }
 
 extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock);
@@ -520,10 +357,6 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lockdep_reset()		do { debug_locks = 1; } while (0)
 # define lockdep_free_key_range(start, size)	do { } while (0)
 # define lockdep_sys_exit() 			do { } while (0)
-/*
- * The class key takes no space if lockdep is disabled:
- */
-struct lock_class_key { };
 
 static inline void lockdep_register_key(struct lock_class_key *key)
 {
@@ -533,11 +366,6 @@ static inline void lockdep_unregister_key(struct lock_class_key *key)
 {
 }
 
-/*
- * The lockdep_map takes no space if lockdep is disabled:
- */
-struct lockdep_map { };
-
 #define lockdep_depth(tsk)	(0)
 
 #define lockdep_is_held_type(l, r)		(1)
@@ -549,8 +377,6 @@ struct lockdep_map { };
 
 #define lockdep_recursing(tsk)			(0)
 
-struct pin_cookie { };
-
 #define NIL_COOKIE (struct pin_cookie){ }
 
 #define lockdep_pin_lock(l)			({ struct pin_cookie cookie = { }; cookie; })
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
new file mode 100644
index 000000000000..7b9350624577
--- /dev/null
+++ b/include/linux/lockdep_types.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Runtime locking correctness validator
+ *
+ *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ * see Documentation/locking/lockdep-design.rst for more details.
+ */
+#ifndef __LINUX_LOCKDEP_TYPES_H
+#define __LINUX_LOCKDEP_TYPES_H
+
+#include <linux/types.h>
+
+#define MAX_LOCKDEP_SUBCLASSES		8UL
+
+enum lockdep_wait_type {
+	LD_WAIT_INV = 0,	/* not checked, catch all */
+
+	LD_WAIT_FREE,		/* wait free, rcu etc.. */
+	LD_WAIT_SPIN,		/* spin loops, raw_spinlock_t etc.. */
+
+#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
+	LD_WAIT_CONFIG,		/* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */
+#else
+	LD_WAIT_CONFIG = LD_WAIT_SPIN,
+#endif
+	LD_WAIT_SLEEP,		/* sleeping locks, mutex_t etc.. */
+
+	LD_WAIT_MAX,		/* must be last */
+};
+
+#ifdef CONFIG_LOCKDEP
+
+#include <linux/list.h>
+
+/*
+ * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
+ * the total number of states... :-(
+ */
+#define XXX_LOCK_USAGE_STATES		(1+2*4)
+
+/*
+ * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
+ * cached in the instance of lockdep_map
+ *
+ * Currently main class (subclass == 0) and signle depth subclass
+ * are cached in lockdep_map. This optimization is mainly targeting
+ * on rq->lock. double_rq_lock() acquires this highly competitive with
+ * single depth.
+ */
+#define NR_LOCKDEP_CACHING_CLASSES	2
+
+/*
+ * A lockdep key is associated with each lock object. For static locks we use
+ * the lock address itself as the key. Dynamically allocated lock objects can
+ * have a statically or dynamically allocated key. Dynamically allocated lock
+ * keys must be registered before being used and must be unregistered before
+ * the key memory is freed.
+ */
+struct lockdep_subclass_key {
+	char __one_byte;
+} __attribute__ ((__packed__));
+
+/* hash_entry is used to keep track of dynamically allocated keys. */
+struct lock_class_key {
+	union {
+		struct hlist_node		hash_entry;
+		struct lockdep_subclass_key	subkeys[MAX_LOCKDEP_SUBCLASSES];
+	};
+};
+
+extern struct lock_class_key __lockdep_no_validate__;
+
+struct lock_trace;
+
+#define LOCKSTAT_POINTS		4
+
+/*
+ * The lock-class itself. The order of the structure members matters.
+ * reinit_class() zeroes the key member and all subsequent members.
+ */
+struct lock_class {
+	/*
+	 * class-hash:
+	 */
+	struct hlist_node		hash_entry;
+
+	/*
+	 * Entry in all_lock_classes when in use. Entry in free_lock_classes
+	 * when not in use. Instances that are being freed are on one of the
+	 * zapped_classes lists.
+	 */
+	struct list_head		lock_entry;
+
+	/*
+	 * These fields represent a directed graph of lock dependencies,
+	 * to every node we attach a list of "forward" and a list of
+	 * "backward" graph nodes.
+	 */
+	struct list_head		locks_after, locks_before;
+
+	const struct lockdep_subclass_key *key;
+	unsigned int			subclass;
+	unsigned int			dep_gen_id;
+
+	/*
+	 * IRQ/softirq usage tracking bits:
+	 */
+	unsigned long			usage_mask;
+	const struct lock_trace		*usage_traces[XXX_LOCK_USAGE_STATES];
+
+	/*
+	 * Generation counter, when doing certain classes of graph walking,
+	 * to ensure that we check one node only once:
+	 */
+	int				name_version;
+	const char			*name;
+
+	short				wait_type_inner;
+	short				wait_type_outer;
+
+#ifdef CONFIG_LOCK_STAT
+	unsigned long			contention_point[LOCKSTAT_POINTS];
+	unsigned long			contending_point[LOCKSTAT_POINTS];
+#endif
+} __no_randomize_layout;
+
+#ifdef CONFIG_LOCK_STAT
+struct lock_time {
+	s64				min;
+	s64				max;
+	s64				total;
+	unsigned long			nr;
+};
+
+enum bounce_type {
+	bounce_acquired_write,
+	bounce_acquired_read,
+	bounce_contended_write,
+	bounce_contended_read,
+	nr_bounce_types,
+
+	bounce_acquired = bounce_acquired_write,
+	bounce_contended = bounce_contended_write,
+};
+
+struct lock_class_stats {
+	unsigned long			contention_point[LOCKSTAT_POINTS];
+	unsigned long			contending_point[LOCKSTAT_POINTS];
+	struct lock_time		read_waittime;
+	struct lock_time		write_waittime;
+	struct lock_time		read_holdtime;
+	struct lock_time		write_holdtime;
+	unsigned long			bounces[nr_bounce_types];
+};
+
+struct lock_class_stats lock_stats(struct lock_class *class);
+void clear_lock_stats(struct lock_class *class);
+#endif
+
+/*
+ * Map the lock object (the lock instance) to the lock-class object.
+ * This is embedded into specific lock instances:
+ */
+struct lockdep_map {
+	struct lock_class_key		*key;
+	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
+	const char			*name;
+	short				wait_type_outer; /* can be taken in this context */
+	short				wait_type_inner; /* presents this context */
+#ifdef CONFIG_LOCK_STAT
+	int				cpu;
+	unsigned long			ip;
+#endif
+};
+
+struct pin_cookie { unsigned int val; };
+
+#else /* !CONFIG_LOCKDEP */
+
+/*
+ * The class key takes no space if lockdep is disabled:
+ */
+struct lock_class_key { };
+
+/*
+ * The lockdep_map takes no space if lockdep is disabled:
+ */
+struct lockdep_map { };
+
+struct pin_cookie { };
+
+#endif /* !LOCKDEP */
+
+#endif /* __LINUX_LOCKDEP_TYPES_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index d3770b3f9d9a..f2f12d746dbd 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -56,6 +56,7 @@
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
+#include <linux/lockdep.h>
 #include <asm/barrier.h>
 #include <asm/mmiowb.h>
 
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 6102e6bff3ae..b981caafe8bf 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -15,7 +15,7 @@
 # include <linux/spinlock_types_up.h>
 #endif
 
-#include <linux/lockdep.h>
+#include <linux/lockdep_types.h>
 
 typedef struct raw_spinlock {
 	arch_spinlock_t raw_lock;
-- 
cgit v1.2.3


From fe557319aa06c23cffc9346000f119547e0f289a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Jun 2020 09:37:53 +0200
Subject: maccess: rename probe_kernel_{read,write} to
 copy_{from,to}_kernel_nofault

Better describe what these functions do.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/ftrace.c           |  3 ++-
 arch/arm/kernel/kgdb.c             |  2 +-
 arch/arm64/kernel/insn.c           |  4 ++--
 arch/csky/kernel/ftrace.c          |  5 ++--
 arch/ia64/kernel/ftrace.c          |  6 ++---
 arch/mips/kernel/kprobes.c         |  6 ++---
 arch/nds32/kernel/ftrace.c         |  5 ++--
 arch/parisc/kernel/ftrace.c        |  2 +-
 arch/parisc/kernel/kgdb.c          |  4 ++--
 arch/parisc/lib/memcpy.c           |  2 +-
 arch/powerpc/kernel/module_64.c    |  6 +++--
 arch/powerpc/kernel/trace/ftrace.c |  4 ++--
 arch/powerpc/lib/inst.c            |  6 ++---
 arch/powerpc/perf/core-book3s.c    |  3 ++-
 arch/riscv/kernel/ftrace.c         |  3 ++-
 arch/riscv/kernel/kgdb.c           |  4 ++--
 arch/riscv/kernel/patch.c          |  4 ++--
 arch/s390/kernel/ftrace.c          |  4 ++--
 arch/sh/kernel/ftrace.c            |  6 ++---
 arch/um/kernel/maccess.c           |  2 +-
 arch/x86/include/asm/ptrace.h      |  4 ++--
 arch/x86/kernel/dumpstack.c        |  2 +-
 arch/x86/kernel/ftrace.c           | 10 ++++----
 arch/x86/kernel/kgdb.c             |  6 ++---
 arch/x86/kernel/kprobes/core.c     |  5 ++--
 arch/x86/kernel/kprobes/opt.c      |  2 +-
 arch/x86/kernel/traps.c            |  3 ++-
 arch/x86/mm/fault.c                |  2 +-
 arch/x86/mm/init_32.c              |  2 +-
 arch/x86/mm/maccess.c              |  4 ++--
 arch/x86/xen/enlighten_pv.c        |  2 +-
 drivers/char/mem.c                 |  2 +-
 drivers/dio/dio.c                  |  6 +++--
 drivers/input/serio/hp_sdc.c       |  2 +-
 drivers/misc/kgdbts.c              |  6 ++---
 drivers/video/fbdev/hpfb.c         |  2 +-
 fs/proc/kcore.c                    |  3 ++-
 include/linux/uaccess.h            | 13 +++++-----
 kernel/debug/debug_core.c          |  6 ++---
 kernel/debug/gdbstub.c             |  6 ++---
 kernel/debug/kdb/kdb_main.c        |  3 ++-
 kernel/debug/kdb/kdb_support.c     |  7 +++---
 kernel/kthread.c                   |  2 +-
 kernel/trace/bpf_trace.c           |  4 ++--
 kernel/trace/trace_kprobe.c        |  4 ++--
 kernel/workqueue.c                 | 10 ++++----
 mm/debug.c                         |  8 +++----
 mm/maccess.c                       | 49 +++++++++++++++++++-------------------
 mm/rodata_test.c                   |  2 +-
 mm/slub.c                          |  2 +-
 50 files changed, 138 insertions(+), 122 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 10499d44964a..9a79ef6b1876 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 		old = __opcode_to_mem_arm(old);
 
 	if (validate) {
-		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+		if (copy_from_kernel_nofault(&replaced, (void *)pc,
+				MCOUNT_INSN_SIZE))
 			return -EFAULT;
 
 		if (replaced != old)
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 6a95b9296640..7bd30c0a4280 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	/* patch_text() only supports int-sized breakpoints */
 	BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE);
 
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 684d871ae38d..a107375005bc 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -135,7 +135,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
 	int ret;
 	__le32 val;
 
-	ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
+	ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE);
 	if (!ret)
 		*insnp = le32_to_cpu(val);
 
@@ -151,7 +151,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)
 	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
-	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
+	ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
 	raw_spin_unlock_irqrestore(&patch_lock, flags);
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
index 3c425b84e3be..b4a7ec1517ff 100644
--- a/arch/csky/kernel/ftrace.c
+++ b/arch/csky/kernel/ftrace.c
@@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook)
 	uint16_t olds[7];
 	unsigned long hook_pos = hook - 2;
 
-	if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops)))
+	if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos,
+			sizeof(nops)))
 		return -EFAULT;
 
 	if (memcmp((void *)nops, (void *)olds, sizeof(nops))) {
@@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target,
 
 	make_jbsr(target, hook, call, nolr);
 
-	ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
+	ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops,
 				 sizeof(nops));
 	if (ret)
 		return -EPERM;
diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c
index cee411e647ca..b2ab2d58fb30 100644
--- a/arch/ia64/kernel/ftrace.c
+++ b/arch/ia64/kernel/ftrace.c
@@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		goto skip_check;
 
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
@@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 
 skip_check:
 	/* replace the text with the new text */
-	if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE))
+	if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 	flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
 
@@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr)
 	unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE];
 	unsigned long ip = rec->ip;
 
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 	if (rec->flags & FTRACE_FL_CONVERTED) {
 		struct ftrace_call_insn *call_insn, *tmp_call;
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 6cfae2411c04..d043c2f897fc 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 		goto out;
 	}
 
-	if ((probe_kernel_read(&prev_insn, p->addr - 1,
-				sizeof(mips_instruction)) == 0) &&
-				insn_has_delayslot(prev_insn)) {
+	if (copy_from_kernel_nofault(&prev_insn, p->addr - 1,
+			sizeof(mips_instruction)) == 0 &&
+	    insn_has_delayslot(prev_insn)) {
 		pr_notice("Kprobes for branch delayslot are not supported\n");
 		ret = -EINVAL;
 		goto out;
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 22ab77ea27ad..3763b3f8c3db 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn,
 	unsigned long orig_insn[3];
 
 	if (validate) {
-		if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE))
+		if (copy_from_kernel_nofault(orig_insn, (void *)pc,
+				MCOUNT_INSN_SIZE))
 			return -EFAULT;
 		if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE))
 			return -EINVAL;
 	}
 
-	if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE))
+	if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index b836fc61a24f..1df0f67ed667 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	ip = (void *)(rec->ip + 4 - size);
 
-	ret = probe_kernel_read(insn, ip, size);
+	ret = copy_from_kernel_nofault(insn, ip, size);
 	if (ret)
 		return ret;
 
diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c
index 664278db9b97..c4554ac13eac 100644
--- a/arch/parisc/kernel/kgdb.c
+++ b/arch/parisc/kernel/kgdb.c
@@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
-	int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
-				BREAK_INSTR_SIZE);
+	int ret = copy_from_kernel_nofault(bpt->saved_instr,
+			(char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
 	if (ret)
 		return ret;
 
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 94a9fe2702c2..4b75388190b4 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count)
 EXPORT_SYMBOL(raw_copy_in_user);
 EXPORT_SYMBOL(memcpy);
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	if ((unsigned long)unsafe_src < PAGE_SIZE)
 		return false;
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index f4c2fa190192..ae2b188365b1 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -756,7 +756,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
 
 	stub = (struct ppc64_stub_entry *)addr;
 
-	if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
+	if (copy_from_kernel_nofault(&magic, &stub->magic,
+			sizeof(magic))) {
 		pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
 		return -EFAULT;
 	}
@@ -766,7 +767,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
 		return -EFAULT;
 	}
 
-	if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) {
+	if (copy_from_kernel_nofault(&funcdata, &stub->funcdata,
+			sizeof(funcdata))) {
 		pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
                 return -EFAULT;
 	}
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5e399628f51a..c1fede6ec934 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -226,7 +226,7 @@ __ftrace_make_nop(struct module *mod,
 	unsigned long ip = rec->ip;
 	unsigned long tramp;
 
-	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure that that this is still a 24bit jump */
@@ -249,7 +249,7 @@ __ftrace_make_nop(struct module *mod,
 	pr_devel("ip:%lx jumps to %lx", ip, tramp);
 
 	/* Find where the trampoline jumps to */
-	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+	if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) {
 		pr_err("Failed to read %lx\n", tramp);
 		return -EFAULT;
 	}
diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c
index aedfd6e31e53..6c7a20af9fd6 100644
--- a/arch/powerpc/lib/inst.c
+++ b/arch/powerpc/lib/inst.c
@@ -33,11 +33,11 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
 	unsigned int val, suffix;
 	int err;
 
-	err = probe_kernel_read(&val, src, sizeof(val));
+	err = copy_from_kernel_nofault(&val, src, sizeof(val));
 	if (err)
 		return err;
 	if (get_op(val) == OP_PREFIX) {
-		err = probe_kernel_read(&suffix, (void *)src + 4, 4);
+		err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4);
 		*inst = ppc_inst_prefix(val, suffix);
 	} else {
 		*inst = ppc_inst(val);
@@ -64,7 +64,7 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
 	unsigned int val;
 	int err;
 
-	err = probe_kernel_read(&val, src, sizeof(val));
+	err = copy_from_kernel_nofault(&val, src, sizeof(val));
 	if (!err)
 		*inst = ppc_inst(val);
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 13b9dd5e4a76..efe97ff82557 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -418,7 +418,8 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	__u64 target;
 
 	if (is_kernel_addr(addr)) {
-		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+		if (copy_from_kernel_nofault(&instr, (void *)addr,
+				sizeof(instr)))
 			return 0;
 
 		return branch_target((struct ppc_inst *)&instr);
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 08396614d6f4..2ff63d0cbb50 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 	 * Read the text we want to modify;
 	 * return must be -EFAULT on read error
 	 */
-	if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+			MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/*
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index f16ade84a11f..a21fb21883e7 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -153,7 +153,7 @@ int do_single_step(struct pt_regs *regs)
 	stepped_address = addr;
 
 	/* Replace the op code with the break instruction */
-	error = probe_kernel_write((void *)stepped_address,
+	error = copy_to_kernel_nofault((void *)stepped_address,
 				   arch_kgdb_ops.gdb_bpt_instr,
 				   BREAK_INSTR_SIZE);
 	/* Flush and return */
@@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs)
 static void undo_single_step(struct pt_regs *regs)
 {
 	if (stepped_opcode != 0) {
-		probe_kernel_write((void *)stepped_address,
+		copy_to_kernel_nofault((void *)stepped_address,
 				   (void *)&stepped_opcode, BREAK_INSTR_SIZE);
 		flush_icache_range(stepped_address,
 				   stepped_address + BREAK_INSTR_SIZE);
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index d4a64dfed342..3fe7a5296aa5 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len)
 
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
-	ret = probe_kernel_write(waddr, insn, len);
+	ret = copy_to_kernel_nofault(waddr, insn, len);
 
 	patch_unmap(FIX_TEXT_POKE0);
 
@@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write);
 #else
 static int patch_insn_write(void *addr, const void *insn, size_t len)
 {
-	return probe_kernel_write(addr, insn, len);
+	return copy_to_kernel_nofault(addr, insn, len);
 }
 NOKPROBE_SYMBOL(patch_insn_write);
 #endif /* CONFIG_MMU */
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 44e01dd1e624..b388e87a08bf 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -83,7 +83,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 {
 	struct ftrace_insn orig, new, old;
 
-	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+	if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
 	if (addr == MCOUNT_ADDR) {
 		/* Initial code replacement */
@@ -105,7 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	struct ftrace_insn orig, new, old;
 
-	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+	if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
 	/* Replace nop with an ftrace call. */
 	ftrace_generate_nop_insn(&orig);
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 1b04270e5460..0646c5961846 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -119,7 +119,7 @@ static void ftrace_mod_code(void)
 	 * But if one were to fail, then they all should, and if one were
 	 * to succeed, then they all should.
 	 */
-	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+	mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
 
 	/* if we fail, then kill any new writers */
@@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	 */
 
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
@@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr,
 {
 	unsigned char code[MCOUNT_INSN_SIZE];
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	if (old_addr != __raw_readl((unsigned long *)code))
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
index e929c0966696..8ccd56813f68 100644
--- a/arch/um/kernel/maccess.c
+++ b/arch/um/kernel/maccess.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <os.h>
 
-bool probe_kernel_read_allowed(const void *src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *src, size_t size)
 {
 	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ebedeab48704..255b2dde2c1b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs
 }
 
 /* To avoid include hell, we can't include uaccess.h */
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
 
 /**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
@@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 	addr = regs_get_kernel_stack_nth_addr(regs, n);
 	if (addr) {
-		ret = probe_kernel_read(&val, addr, sizeof(val));
+		ret = copy_from_kernel_nofault(&val, addr, sizeof(val));
 		if (!ret)
 			return val;
 	}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 456511b2284e..b037cfa7c0c5 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -106,7 +106,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 	bad_ip = user_mode(regs) &&
 		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue,
+	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
 					OPCODE_BUFSIZE)) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c84d28e90a58..51504566b3a6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code)
 	 * sure what we read is what we expected it to be before modifying it.
 	 */
 	/* read the text we want to modify */
-	if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
+	if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
 		WARN_ON(1);
 		return -EFAULT;
 	}
@@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
@@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/* The trampoline ends with ret(q) */
 	retq = (unsigned long)ftrace_stub;
-	ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+	ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
-		ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+		ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 		if (WARN_ON(ret < 0))
 			goto fail;
 	}
@@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr)
 	union text_poke_insn call;
 	int ret;
 
-	ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE);
+	ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE);
 	if (WARN_ON_ONCE(ret < 0))
 		return NULL;
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index c44fe7d8d9a4..68acd30c6b87 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	int err;
 
 	bpt->type = BP_BREAKPOINT;
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-	err = probe_kernel_write((char *)bpt->bpt_addr,
+	err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
 	if (!err)
 		return err;
@@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 	return 0;
 
 knl_write:
-	return probe_kernel_write((char *)bpt->bpt_addr,
+	return copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3bafe1bd4dc7..f09985c87d73 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -243,7 +243,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	 * Fortunately, we know that the original code is the ideal 5-byte
 	 * long NOP.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
@@ -346,7 +346,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 		return 0;
 
 	/* This can access kernel text if given address is not recovered */
-	if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(dest, (void *)recovered_insn,
+			MAX_INSN_SIZE))
 		return 0;
 
 	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 321c19950285..7af4c61dde52 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -56,7 +56,7 @@ found:
 	 * overwritten by jump destination address. In this case, original
 	 * bytes must be recovered from op->optinsn.copied_insn buffer.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index af75109485c2..7003f2e7b163 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -488,7 +488,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs,
 	u8 insn_buf[MAX_INSN_SIZE];
 	struct insn insn;
 
-	if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
+			MAX_INSN_SIZE))
 		return GP_NO_HINT;
 
 	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 66be9bd60307..e996aa3833b8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		return;
 	}
 
-	if (probe_kernel_read(&desc, (void *)(gdt->address + offset),
+	if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
 			      sizeof(struct ldttss_desc))) {
 		pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
 			 name, index);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bda909e3e37e..8b4afad84f4a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -737,7 +737,7 @@ static void __init test_wp_bit(void)
 
 	__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
 
-	if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+	if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
 		clear_fixmap(FIX_WP_TEST);
 		printk(KERN_CONT "Ok.\n");
 		return;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index e1d7d7477c22..92ec176a7293 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
 	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	unsigned long vaddr = (unsigned long)unsafe_src;
 
@@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
 }
 #else
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
 }
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 33b309d65955..acc49fa6a097 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	preempt_disable();
 
-	probe_kernel_read(&dummy, v, 1);
+	copy_from_kernel_nofault(&dummy, v, 1);
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 31cae88a730b..934c92dcb9ab 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -171,7 +171,7 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 			if (!ptr)
 				goto failed;
 
-			probe = probe_kernel_read(bounce, ptr, sz);
+			probe = copy_from_kernel_nofault(bounce, ptr, sz);
 			unxlate_dev_mem_ptr(p, ptr);
 			if (probe)
 				goto failed;
diff --git a/drivers/dio/dio.c b/drivers/dio/dio.c
index c9aa15fb86a9..193b40e7aec0 100644
--- a/drivers/dio/dio.c
+++ b/drivers/dio/dio.c
@@ -135,7 +135,8 @@ int __init dio_find(int deviceid)
 		else
 			va = ioremap(pa, PAGE_SIZE);
 
-                if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+		if (copy_from_kernel_nofault(&i,
+				(unsigned char *)va + DIO_IDOFF, 1)) {
 			if (scode >= DIOII_SCBASE)
 				iounmap(va);
                         continue;             /* no board present at that select code */
@@ -208,7 +209,8 @@ static int __init dio_init(void)
 		else
 			va = ioremap(pa, PAGE_SIZE);
 
-                if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+		if (copy_from_kernel_nofault(&i,
+				(unsigned char *)va + DIO_IDOFF, 1)) {
 			if (scode >= DIOII_SCBASE)
 				iounmap(va);
                         continue;              /* no board present at that select code */
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index 654252361653..13eacf6ab431 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -1021,7 +1021,7 @@ static int __init hp_sdc_register(void)
 	hp_sdc.base_io	 = (unsigned long) 0xf0428000;
 	hp_sdc.data_io	 = (unsigned long) hp_sdc.base_io + 1;
 	hp_sdc.status_io = (unsigned long) hp_sdc.base_io + 3;
-	if (!probe_kernel_read(&i, (unsigned char *)hp_sdc.data_io, 1))
+	if (!copy_from_kernel_nofault(&i, (unsigned char *)hp_sdc.data_io, 1))
 		hp_sdc.dev = (void *)1;
 	hp_sdc.dev_err   = hp_sdc_init();
 #endif
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index bccd341e9ae1..d5d2af4d10e6 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -828,7 +828,7 @@ static void run_plant_and_detach_test(int is_early)
 	char before[BREAK_INSTR_SIZE];
 	char after[BREAK_INSTR_SIZE];
 
-	probe_kernel_read(before, (char *)kgdbts_break_test,
+	copy_from_kernel_nofault(before, (char *)kgdbts_break_test,
 	  BREAK_INSTR_SIZE);
 	init_simple_test();
 	ts.tst = plant_and_detach_test;
@@ -836,8 +836,8 @@ static void run_plant_and_detach_test(int is_early)
 	/* Activate test with initial breakpoint */
 	if (!is_early)
 		kgdb_breakpoint();
-	probe_kernel_read(after, (char *)kgdbts_break_test,
-	  BREAK_INSTR_SIZE);
+	copy_from_kernel_nofault(after, (char *)kgdbts_break_test,
+			BREAK_INSTR_SIZE);
 	if (memcmp(before, after, BREAK_INSTR_SIZE)) {
 		printk(KERN_CRIT "kgdbts: ERROR kgdb corrupted memory\n");
 		panic("kgdb memory corruption");
diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
index f02be0db335e..8d418abdd767 100644
--- a/drivers/video/fbdev/hpfb.c
+++ b/drivers/video/fbdev/hpfb.c
@@ -402,7 +402,7 @@ int __init hpfb_init(void)
 	if (err)
 		return err;
 
-	err = probe_kernel_read(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
+	err = copy_from_kernel_nofault(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
 
 	if (!err && (i == DIO_ID_FBUFFER) && topcat_sid_ok(sid = DIO_SECID(INTFBVADDR))) {
 		if (!request_mem_region(INTFBPADDR, DIO_DEVSIZE, "Internal Topcat"))
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 8ba492d44e68..e502414b3556 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -512,7 +512,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 				 * Using bounce buffer to bypass the
 				 * hardened user copy kernel text checks.
 				 */
-				if (probe_kernel_read(buf, (void *) start, tsz)) {
+				if (copy_from_kernel_nofault(buf, (void *)start,
+						tsz)) {
 					if (clear_user(buffer, tsz)) {
 						ret = -EFAULT;
 						goto out;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 7bcadca22100..70a3d9cd9113 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -301,13 +301,14 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
 	return 0;
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size);
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size);
 
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
-extern long probe_user_read(void *dst, const void __user *src, size_t size);
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
+long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size);
 
-extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
-extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long probe_user_read(void *dst, const void __user *src, size_t size);
+extern long notrace probe_user_write(void __user *dst, const void *src,
+		size_t size);
 
 long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,
 		long count);
@@ -324,7 +325,7 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count);
  * Returns 0 on success, or -EFAULT.
  */
 #define probe_kernel_address(addr, retval)		\
-	probe_kernel_read(&retval, addr, sizeof(retval))
+	copy_from_kernel_nofault(&retval, addr, sizeof(retval))
 
 #ifndef user_access_begin
 #define user_access_begin(ptr,len) access_ok(ptr, len)
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index ccc0f98abdd4..bc8d25f2ac8a 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -169,18 +169,18 @@ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
 
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-	err = probe_kernel_write((char *)bpt->bpt_addr,
+	err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
 	return err;
 }
 
 int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	return probe_kernel_write((char *)bpt->bpt_addr,
+	return copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 4b280fc7dd67..61774aec46b4 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -247,7 +247,7 @@ char *kgdb_mem2hex(char *mem, char *buf, int count)
 	 */
 	tmp = buf + count;
 
-	err = probe_kernel_read(tmp, mem, count);
+	err = copy_from_kernel_nofault(tmp, mem, count);
 	if (err)
 		return NULL;
 	while (count > 0) {
@@ -283,7 +283,7 @@ int kgdb_hex2mem(char *buf, char *mem, int count)
 		*tmp_raw |= hex_to_bin(*tmp_hex--) << 4;
 	}
 
-	return probe_kernel_write(mem, tmp_raw, count);
+	return copy_to_kernel_nofault(mem, tmp_raw, count);
 }
 
 /*
@@ -335,7 +335,7 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count)
 		size++;
 	}
 
-	return probe_kernel_write(mem, c, size);
+	return copy_to_kernel_nofault(mem, c, size);
 }
 
 #if DBG_MAX_REG_NUM > 0
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index ec190569f690..5c7949061671 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2326,7 +2326,8 @@ void kdb_ps1(const struct task_struct *p)
 	int cpu;
 	unsigned long tmp;
 
-	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+	if (!p ||
+	    copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
 		return;
 
 	cpu = kdb_process_cpu(p);
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index b8e6306e7e13..004c5b6c87f8 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -325,7 +325,7 @@ char *kdb_strdup(const char *str, gfp_t type)
  */
 int kdb_getarea_size(void *res, unsigned long addr, size_t size)
 {
-	int ret = probe_kernel_read((char *)res, (char *)addr, size);
+	int ret = copy_from_kernel_nofault((char *)res, (char *)addr, size);
 	if (ret) {
 		if (!KDB_STATE(SUPPRESS)) {
 			kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr);
@@ -350,7 +350,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size)
  */
 int kdb_putarea_size(unsigned long addr, void *res, size_t size)
 {
-	int ret = probe_kernel_read((char *)addr, (char *)res, size);
+	int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size);
 	if (ret) {
 		if (!KDB_STATE(SUPPRESS)) {
 			kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr);
@@ -624,7 +624,8 @@ char kdb_task_state_char (const struct task_struct *p)
 	char state;
 	unsigned long tmp;
 
-	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+	if (!p ||
+	    copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
 		return 'E';
 
 	cpu = kdb_process_cpu(p);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 8e3d2d7fdf5e..132f84a5fde3 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -201,7 +201,7 @@ void *kthread_probe_data(struct task_struct *task)
 	struct kthread *kthread = to_kthread(task);
 	void *data = NULL;
 
-	probe_kernel_read(&data, &kthread->data, sizeof(data));
+	copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
 	return data;
 }
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e729c9e587a0..204afc12425f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,7 +196,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 
 	if (unlikely(ret < 0))
 		goto fail;
-	ret = probe_kernel_read(dst, unsafe_ptr, size);
+	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		goto fail;
 	return ret;
@@ -661,7 +661,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 
 			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
 
-			err = probe_kernel_read(bufs->buf[memcpy_cnt],
+			err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
 						(void *) (long) args[fmt_cnt],
 						copy_size);
 			if (err < 0)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6048f1be26d2..841c74863ff8 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1222,7 +1222,7 @@ fetch_store_strlen(unsigned long addr)
 #endif
 
 	do {
-		ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
@@ -1300,7 +1300,7 @@ probe_mem_read(void *dest, void *src, size_t size)
 	if ((unsigned long)src < TASK_SIZE)
 		return probe_mem_read_user(dest, src, size);
 #endif
-	return probe_kernel_read(dest, src, size);
+	return copy_from_kernel_nofault(dest, src, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 9fbe1e237563..c41c3c17b86a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4638,11 +4638,11 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	 * Carefully copy the associated workqueue's workfn, name and desc.
 	 * Keep the original last '\0' in case the original is garbage.
 	 */
-	probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
-	probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
-	probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
-	probe_kernel_read(name, wq->name, sizeof(name) - 1);
-	probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
+	copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn));
+	copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq));
+	copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq));
+	copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1);
+	copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1);
 
 	if (fn || name[0] || desc[0]) {
 		printk("%sWorkqueue: %s %ps", log_lvl, name, fn);
diff --git a/mm/debug.c b/mm/debug.c
index b5b1de8c71ac..4f376514744d 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -120,9 +120,9 @@ void __dump_page(struct page *page, const char *reason)
 		 * mapping can be invalid pointer and we don't want to crash
 		 * accessing it, so probe everything depending on it carefully
 		 */
-		if (probe_kernel_read(&host, &mapping->host,
+		if (copy_from_kernel_nofault(&host, &mapping->host,
 					sizeof(struct inode *)) ||
-		    probe_kernel_read(&a_ops, &mapping->a_ops,
+		    copy_from_kernel_nofault(&a_ops, &mapping->a_ops,
 				sizeof(struct address_space_operations *))) {
 			pr_warn("failed to read mapping->host or a_ops, mapping not a valid kernel address?\n");
 			goto out_mapping;
@@ -133,7 +133,7 @@ void __dump_page(struct page *page, const char *reason)
 			goto out_mapping;
 		}
 
-		if (probe_kernel_read(&dentry_first,
+		if (copy_from_kernel_nofault(&dentry_first,
 			&host->i_dentry.first, sizeof(struct hlist_node *))) {
 			pr_warn("mapping->a_ops:%ps with invalid mapping->host inode address %px\n",
 				a_ops, host);
@@ -146,7 +146,7 @@ void __dump_page(struct page *page, const char *reason)
 		}
 
 		dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-		if (probe_kernel_read(&dentry, dentry_ptr,
+		if (copy_from_kernel_nofault(&dentry, dentry_ptr,
 							sizeof(struct dentry))) {
 			pr_warn("mapping->aops:%ps with invalid mapping->host->i_dentry.first %px\n",
 				a_ops, dentry_ptr);
diff --git a/mm/maccess.c b/mm/maccess.c
index 88845eda5047..cc5d8c6233c0 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -6,14 +6,15 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 
-bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src,
+		size_t size)
 {
 	return true;
 }
 
 #ifdef HAVE_GET_KERNEL_NOFAULT
 
-#define probe_kernel_read_loop(dst, src, len, type, err_label)		\
+#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label)	\
 	while (len >= sizeof(type)) {					\
 		__get_kernel_nofault(dst, src, type, err_label);		\
 		dst += sizeof(type);					\
@@ -21,25 +22,25 @@ bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 		len -= sizeof(type);					\
 	}
 
-long probe_kernel_read(void *dst, const void *src, size_t size)
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size)
 {
-	if (!probe_kernel_read_allowed(src, size))
+	if (!copy_from_kernel_nofault_allowed(src, size))
 		return -ERANGE;
 
 	pagefault_disable();
-	probe_kernel_read_loop(dst, src, size, u64, Efault);
-	probe_kernel_read_loop(dst, src, size, u32, Efault);
-	probe_kernel_read_loop(dst, src, size, u16, Efault);
-	probe_kernel_read_loop(dst, src, size, u8, Efault);
+	copy_from_kernel_nofault_loop(dst, src, size, u64, Efault);
+	copy_from_kernel_nofault_loop(dst, src, size, u32, Efault);
+	copy_from_kernel_nofault_loop(dst, src, size, u16, Efault);
+	copy_from_kernel_nofault_loop(dst, src, size, u8, Efault);
 	pagefault_enable();
 	return 0;
 Efault:
 	pagefault_enable();
 	return -EFAULT;
 }
-EXPORT_SYMBOL_GPL(probe_kernel_read);
+EXPORT_SYMBOL_GPL(copy_from_kernel_nofault);
 
-#define probe_kernel_write_loop(dst, src, len, type, err_label)		\
+#define copy_to_kernel_nofault_loop(dst, src, len, type, err_label)	\
 	while (len >= sizeof(type)) {					\
 		__put_kernel_nofault(dst, src, type, err_label);		\
 		dst += sizeof(type);					\
@@ -47,13 +48,13 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
 		len -= sizeof(type);					\
 	}
 
-long probe_kernel_write(void *dst, const void *src, size_t size)
+long copy_to_kernel_nofault(void *dst, const void *src, size_t size)
 {
 	pagefault_disable();
-	probe_kernel_write_loop(dst, src, size, u64, Efault);
-	probe_kernel_write_loop(dst, src, size, u32, Efault);
-	probe_kernel_write_loop(dst, src, size, u16, Efault);
-	probe_kernel_write_loop(dst, src, size, u8, Efault);
+	copy_to_kernel_nofault_loop(dst, src, size, u64, Efault);
+	copy_to_kernel_nofault_loop(dst, src, size, u32, Efault);
+	copy_to_kernel_nofault_loop(dst, src, size, u16, Efault);
+	copy_to_kernel_nofault_loop(dst, src, size, u8, Efault);
 	pagefault_enable();
 	return 0;
 Efault:
@@ -67,7 +68,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 
 	if (unlikely(count <= 0))
 		return 0;
-	if (!probe_kernel_read_allowed(unsafe_addr, count))
+	if (!copy_from_kernel_nofault_allowed(unsafe_addr, count))
 		return -ERANGE;
 
 	pagefault_disable();
@@ -87,7 +88,7 @@ Efault:
 }
 #else /* HAVE_GET_KERNEL_NOFAULT */
 /**
- * probe_kernel_read(): safely attempt to read from kernel-space
+ * copy_from_kernel_nofault(): safely attempt to read from kernel-space
  * @dst: pointer to the buffer that shall take the data
  * @src: address to read from
  * @size: size of the data chunk
@@ -98,15 +99,15 @@ Efault:
  *
  * We ensure that the copy_from_user is executed in atomic context so that
  * do_page_fault() doesn't attempt to take mmap_lock.  This makes
- * probe_kernel_read() suitable for use within regions where the caller
+ * copy_from_kernel_nofault() suitable for use within regions where the caller
  * already holds mmap_lock, or other locks which nest inside mmap_lock.
  */
-long probe_kernel_read(void *dst, const void *src, size_t size)
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
 
-	if (!probe_kernel_read_allowed(src, size))
+	if (!copy_from_kernel_nofault_allowed(src, size))
 		return -ERANGE;
 
 	set_fs(KERNEL_DS);
@@ -120,10 +121,10 @@ long probe_kernel_read(void *dst, const void *src, size_t size)
 		return -EFAULT;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(probe_kernel_read);
+EXPORT_SYMBOL_GPL(copy_from_kernel_nofault);
 
 /**
- * probe_kernel_write(): safely attempt to write to a location
+ * copy_to_kernel_nofault(): safely attempt to write to a location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
  * @size: size of the data chunk
@@ -131,7 +132,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_kernel_write(void *dst, const void *src, size_t size)
+long copy_to_kernel_nofault(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
@@ -174,7 +175,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 
 	if (unlikely(count <= 0))
 		return 0;
-	if (!probe_kernel_read_allowed(unsafe_addr, count))
+	if (!copy_from_kernel_nofault_allowed(unsafe_addr, count))
 		return -ERANGE;
 
 	set_fs(KERNEL_DS);
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index 5e313fa93276..2a99df7beeb3 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -25,7 +25,7 @@ void rodata_test(void)
 	}
 
 	/* test 2: write to the variable; this should fault */
-	if (!probe_kernel_write((void *)&rodata_test_data,
+	if (!copy_to_kernel_nofault((void *)&rodata_test_data,
 				(void *)&zero, sizeof(zero))) {
 		pr_err("test data was not read only\n");
 		return;
diff --git a/mm/slub.c b/mm/slub.c
index b8f798b50d44..fe81773fd97e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -292,7 +292,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 		return get_freepointer(s, object);
 
 	freepointer_addr = (unsigned long)object + s->offset;
-	probe_kernel_read(&p, (void **)freepointer_addr, sizeof(p));
+	copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p));
 	return freelist_ptr(s, p, freepointer_addr);
 }
 
-- 
cgit v1.2.3


From c0ee37e85e0e47402b8bbe35b6cec8e06937ca58 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Jun 2020 09:37:54 +0200
Subject: maccess: rename probe_user_{read,write} to
 copy_{from,to}_user_nofault

Better describe what these functions do.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kernel/process.c          |  3 ++-
 arch/powerpc/kvm/book3s_64_mmu_radix.c |  4 ++--
 arch/powerpc/lib/inst.c                |  6 +++---
 arch/powerpc/oprofile/backtrace.c      |  6 ++++--
 arch/powerpc/perf/callchain_32.c       |  2 +-
 arch/powerpc/perf/callchain_64.c       |  2 +-
 arch/powerpc/perf/core-book3s.c        |  3 ++-
 arch/powerpc/sysdev/fsl_pci.c          |  4 ++--
 include/linux/uaccess.h                |  4 ++--
 kernel/trace/bpf_trace.c               |  4 ++--
 kernel/trace/trace_kprobe.c            |  2 +-
 mm/maccess.c                           | 12 ++++++------
 12 files changed, 28 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7bb7faf84490..d4d0d1048500 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1305,7 +1305,8 @@ void show_user_instructions(struct pt_regs *regs)
 		for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
 			int instr;
 
-			if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) {
+			if (copy_from_user_nofault(&instr, (void __user *)pc,
+					sizeof(instr))) {
 				seq_buf_printf(&s, "XXXXXXXX ");
 				continue;
 			}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 3cb0c9843d01..e738ea652192 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -64,9 +64,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	isync();
 
 	if (is_load)
-		ret = probe_user_read(to, (const void __user *)from, n);
+		ret = copy_from_user_nofault(to, (const void __user *)from, n);
 	else
-		ret = probe_user_write((void __user *)to, from, n);
+		ret = copy_to_user_nofault((void __user *)to, from, n);
 
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c
index 6c7a20af9fd6..9cc17eb62462 100644
--- a/arch/powerpc/lib/inst.c
+++ b/arch/powerpc/lib/inst.c
@@ -15,11 +15,11 @@ int probe_user_read_inst(struct ppc_inst *inst,
 	unsigned int val, suffix;
 	int err;
 
-	err = probe_user_read(&val, nip, sizeof(val));
+	err = copy_from_user_nofault(&val, nip, sizeof(val));
 	if (err)
 		return err;
 	if (get_op(val) == OP_PREFIX) {
-		err = probe_user_read(&suffix, (void __user *)nip + 4, 4);
+		err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4);
 		*inst = ppc_inst_prefix(val, suffix);
 	} else {
 		*inst = ppc_inst(val);
@@ -51,7 +51,7 @@ int probe_user_read_inst(struct ppc_inst *inst,
 	unsigned int val;
 	int err;
 
-	err = probe_user_read(&val, nip, sizeof(val));
+	err = copy_from_user_nofault(&val, nip, sizeof(val));
 	if (!err)
 		*inst = ppc_inst(val);
 
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index 6f347fa29f41..9db7ada79d10 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first)
 	 * which means that we've done all that we can do from
 	 * interrupt context.
 	 */
-	if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame)))
+	if (copy_from_user_nofault(stack_frame, (void __user *)p,
+			sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
@@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first)
 {
 	unsigned long stack_frame[3];
 
-	if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame)))
+	if (copy_from_user_nofault(stack_frame, (void __user *)sp,
+			sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index f7d888d39cd3..542e68b8eae0 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -44,7 +44,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	rc = probe_user_read(ret, ptr, sizeof(*ret));
+	rc = copy_from_user_nofault(ret, ptr, sizeof(*ret));
 
 	if (IS_ENABLED(CONFIG_PPC64) && rc)
 		return read_user_stack_slow(ptr, ret, 4);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 814d1c2c2b9c..fa2a1b83b9b0 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -50,7 +50,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	    ((unsigned long)ptr & 7))
 		return -EFAULT;
 
-	if (!probe_user_read(ret, ptr, sizeof(*ret)))
+	if (!copy_from_user_nofault(ret, ptr, sizeof(*ret)))
 		return 0;
 
 	return read_user_stack_slow(ptr, ret, 8);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index efe97ff82557..cd6a742ac6ef 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -426,7 +426,8 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	}
 
 	/* Userspace: need copy instruction here then translate it */
-	if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr)))
+	if (copy_from_user_nofault(&instr, (unsigned int __user *)addr,
+			sizeof(instr)))
 		return 0;
 
 	target = branch_target((struct ppc_inst *)&instr);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 4a8874bc1057..73fa37ca40ef 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1066,8 +1066,8 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 
 	if (is_in_pci_mem_space(addr)) {
 		if (user_mode(regs))
-			ret = probe_user_read(&inst, (void __user *)regs->nip,
-					      sizeof(inst));
+			ret = copy_from_user_nofault(&inst,
+					(void __user *)regs->nip, sizeof(inst));
 		else
 			ret = probe_kernel_address((void *)regs->nip, inst);
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70a3d9cd9113..bef48da242cc 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -306,8 +306,8 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size);
 long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
 long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size);
 
-extern long probe_user_read(void *dst, const void __user *src, size_t size);
-extern long notrace probe_user_write(void __user *dst, const void *src,
+long copy_from_user_nofault(void *dst, const void __user *src, size_t size);
+long notrace copy_to_user_nofault(void __user *dst, const void *src,
 		size_t size);
 
 long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 204afc12425f..dc05626979b8 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -141,7 +141,7 @@ bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr)
 {
 	int ret;
 
-	ret = probe_user_read(dst, unsafe_ptr, size);
+	ret = copy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
 	return ret;
@@ -326,7 +326,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
-	return probe_user_write(unsafe_ptr, src, size);
+	return copy_to_user_nofault(unsafe_ptr, src, size);
 }
 
 static const struct bpf_func_proto bpf_probe_write_user_proto = {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 841c74863ff8..aefb6065b508 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1290,7 +1290,7 @@ probe_mem_read_user(void *dest, void *src, size_t size)
 {
 	const void __user *uaddr =  (__force const void __user *)src;
 
-	return probe_user_read(dest, uaddr, size);
+	return copy_from_user_nofault(dest, uaddr, size);
 }
 
 static nokprobe_inline int
diff --git a/mm/maccess.c b/mm/maccess.c
index cc5d8c6233c0..f98ff91e32c6 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -194,7 +194,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 #endif /* HAVE_GET_KERNEL_NOFAULT */
 
 /**
- * probe_user_read(): safely attempt to read from a user-space location
+ * copy_from_user_nofault(): safely attempt to read from a user-space location
  * @dst: pointer to the buffer that shall take the data
  * @src: address to read from. This must be a user address.
  * @size: size of the data chunk
@@ -202,7 +202,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
  * Safely read from user address @src to the buffer at @dst. If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_user_read(void *dst, const void __user *src, size_t size)
+long copy_from_user_nofault(void *dst, const void __user *src, size_t size)
 {
 	long ret = -EFAULT;
 	mm_segment_t old_fs = get_fs();
@@ -219,10 +219,10 @@ long probe_user_read(void *dst, const void __user *src, size_t size)
 		return -EFAULT;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(probe_user_read);
+EXPORT_SYMBOL_GPL(copy_from_user_nofault);
 
 /**
- * probe_user_write(): safely attempt to write to a user-space location
+ * copy_to_user_nofault(): safely attempt to write to a user-space location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
  * @size: size of the data chunk
@@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(probe_user_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_user_write(void __user *dst, const void *src, size_t size)
+long copy_to_user_nofault(void __user *dst, const void *src, size_t size)
 {
 	long ret = -EFAULT;
 	mm_segment_t old_fs = get_fs();
@@ -247,7 +247,7 @@ long probe_user_write(void __user *dst, const void *src, size_t size)
 		return -EFAULT;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(probe_user_write);
+EXPORT_SYMBOL_GPL(copy_to_user_nofault);
 
 /**
  * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user
-- 
cgit v1.2.3


From a9d887dc1c60ed67f2271d66560cdcf864c4a578 Mon Sep 17 00:00:00 2001
From: Guru Das Srinagesh <gurus@codeaurora.org>
Date: Tue, 2 Jun 2020 15:31:16 -0700
Subject: pwm: Convert period and duty cycle to u64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Because period and duty cycle are defined as ints with units of
nanoseconds, the maximum time duration that can be set is limited to
~2.147 seconds. Change their definitions to u64 in the structs of the
PWM framework so that higher durations may be set.

Also use the right format specifiers in debug prints in both core.c,
pwm-stm32-lp.c as well as video/fbdev/ssd1307fb.c.

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Guru Das Srinagesh <gurus@codeaurora.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c              | 14 +++++++-------
 drivers/pwm/pwm-stm32-lp.c      |  2 +-
 drivers/pwm/sysfs.c             |  8 ++++----
 drivers/video/fbdev/ssd1307fb.c |  2 +-
 include/linux/pwm.h             | 12 ++++++------
 5 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 004b2ea9b5fd..276e939a5684 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -510,12 +510,12 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
 	    last->period > s2.period &&
 	    last->period <= state->period)
 		dev_warn(chip->dev,
-			 ".apply didn't pick the best available period (requested: %u, applied: %u, possible: %u)\n",
+			 ".apply didn't pick the best available period (requested: %llu, applied: %llu, possible: %llu)\n",
 			 state->period, s2.period, last->period);
 
 	if (state->enabled && state->period < s2.period)
 		dev_warn(chip->dev,
-			 ".apply is supposed to round down period (requested: %u, applied: %u)\n",
+			 ".apply is supposed to round down period (requested: %llu, applied: %llu)\n",
 			 state->period, s2.period);
 
 	if (state->enabled &&
@@ -524,14 +524,14 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
 	    last->duty_cycle > s2.duty_cycle &&
 	    last->duty_cycle <= state->duty_cycle)
 		dev_warn(chip->dev,
-			 ".apply didn't pick the best available duty cycle (requested: %u/%u, applied: %u/%u, possible: %u/%u)\n",
+			 ".apply didn't pick the best available duty cycle (requested: %llu/%llu, applied: %llu/%llu, possible: %llu/%llu)\n",
 			 state->duty_cycle, state->period,
 			 s2.duty_cycle, s2.period,
 			 last->duty_cycle, last->period);
 
 	if (state->enabled && state->duty_cycle < s2.duty_cycle)
 		dev_warn(chip->dev,
-			 ".apply is supposed to round down duty_cycle (requested: %u/%u, applied: %u/%u)\n",
+			 ".apply is supposed to round down duty_cycle (requested: %llu/%llu, applied: %llu/%llu)\n",
 			 state->duty_cycle, state->period,
 			 s2.duty_cycle, s2.period);
 
@@ -558,7 +558,7 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
 	    (s1.enabled && s1.period != last->period) ||
 	    (s1.enabled && s1.duty_cycle != last->duty_cycle)) {
 		dev_err(chip->dev,
-			".apply is not idempotent (ena=%d pol=%d %u/%u) -> (ena=%d pol=%d %u/%u)\n",
+			".apply is not idempotent (ena=%d pol=%d %llu/%llu) -> (ena=%d pol=%d %llu/%llu)\n",
 			s1.enabled, s1.polarity, s1.duty_cycle, s1.period,
 			last->enabled, last->polarity, last->duty_cycle,
 			last->period);
@@ -1284,8 +1284,8 @@ static void pwm_dbg_show(struct pwm_chip *chip, struct seq_file *s)
 		if (state.enabled)
 			seq_puts(s, " enabled");
 
-		seq_printf(s, " period: %u ns", state.period);
-		seq_printf(s, " duty: %u ns", state.duty_cycle);
+		seq_printf(s, " period: %llu ns", state.period);
+		seq_printf(s, " duty: %llu ns", state.duty_cycle);
 		seq_printf(s, " polarity: %s",
 			   state.polarity ? "inverse" : "normal");
 
diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index 67fca62524dc..134c14621ee0 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -61,7 +61,7 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	do_div(div, NSEC_PER_SEC);
 	if (!div) {
 		/* Clock is too slow to achieve requested period. */
-		dev_dbg(priv->chip.dev, "Can't reach %u ns\n",	state->period);
+		dev_dbg(priv->chip.dev, "Can't reach %llu ns\n", state->period);
 		return -EINVAL;
 	}
 
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 2389b8669846..449dbc0f49ed 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -42,7 +42,7 @@ static ssize_t period_show(struct device *child,
 
 	pwm_get_state(pwm, &state);
 
-	return sprintf(buf, "%u\n", state.period);
+	return sprintf(buf, "%llu\n", state.period);
 }
 
 static ssize_t period_store(struct device *child,
@@ -52,10 +52,10 @@ static ssize_t period_store(struct device *child,
 	struct pwm_export *export = child_to_pwm_export(child);
 	struct pwm_device *pwm = export->pwm;
 	struct pwm_state state;
-	unsigned int val;
+	u64 val;
 	int ret;
 
-	ret = kstrtouint(buf, 0, &val);
+	ret = kstrtou64(buf, 0, &val);
 	if (ret)
 		return ret;
 
@@ -77,7 +77,7 @@ static ssize_t duty_cycle_show(struct device *child,
 
 	pwm_get_state(pwm, &state);
 
-	return sprintf(buf, "%u\n", state.duty_cycle);
+	return sprintf(buf, "%llu\n", state.duty_cycle);
 }
 
 static ssize_t duty_cycle_store(struct device *child,
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 8e06ba912d60..09425ec317ba 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -312,7 +312,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
 		/* Enable the PWM */
 		pwm_enable(par->pwm);
 
-		dev_dbg(&par->client->dev, "Using PWM%d with a %dns period.\n",
+		dev_dbg(&par->client->dev, "Using PWM%d with a %lluns period.\n",
 			par->pwm->pwm, pwm_get_period(par->pwm));
 	}
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 2635b2a55090..a13ff383fa1d 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -39,7 +39,7 @@ enum pwm_polarity {
  * current PWM hardware state.
  */
 struct pwm_args {
-	unsigned int period;
+	u64 period;
 	enum pwm_polarity polarity;
 };
 
@@ -56,8 +56,8 @@ enum {
  * @enabled: PWM enabled status
  */
 struct pwm_state {
-	unsigned int period;
-	unsigned int duty_cycle;
+	u64 period;
+	u64 duty_cycle;
 	enum pwm_polarity polarity;
 	bool enabled;
 };
@@ -107,13 +107,13 @@ static inline bool pwm_is_enabled(const struct pwm_device *pwm)
 	return state.enabled;
 }
 
-static inline void pwm_set_period(struct pwm_device *pwm, unsigned int period)
+static inline void pwm_set_period(struct pwm_device *pwm, u64 period)
 {
 	if (pwm)
 		pwm->state.period = period;
 }
 
-static inline unsigned int pwm_get_period(const struct pwm_device *pwm)
+static inline u64 pwm_get_period(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
 
@@ -128,7 +128,7 @@ static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty)
 		pwm->state.duty_cycle = duty;
 }
 
-static inline unsigned int pwm_get_duty_cycle(const struct pwm_device *pwm)
+static inline u64 pwm_get_duty_cycle(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
 
-- 
cgit v1.2.3


From 7d34ca3854845398cb36866d14bbdc43dcec1ad0 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Tue, 9 Jun 2020 18:19:33 -0700
Subject: driver core: Add device_is_dependent() to linux/device.h

DT implementation of fw_devlink needs this function to detect cycles. So
make it available.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/base/core.c    | 2 +-
 include/linux/device.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67d39a90b45c..320a0e1d628a 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -121,7 +121,7 @@ int device_links_read_lock_held(void)
  * Check if @target depends on @dev or any device dependent on it (its child or
  * its consumer etc).  Return 1 if that is the case or 0 otherwise.
  */
-static int device_is_dependent(struct device *dev, void *target)
+int device_is_dependent(struct device *dev, void *target)
 {
 	struct device_link *link;
 	int ret;
diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..33cece5d9a4c 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -829,6 +829,7 @@ extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
 extern const char *device_get_devnode(struct device *dev,
 				      umode_t *mode, kuid_t *uid, kgid_t *gid,
 				      const char **tmp);
+extern int device_is_dependent(struct device *dev, void *target);
 
 static inline bool device_supports_offline(struct device *dev)
 {
-- 
cgit v1.2.3


From f097eb38f71391ff2cf078788bad5a00eb3bd96a Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 9 Jun 2020 10:17:26 +0200
Subject: timekeeping: Fix kerneldoc system_device_crosststamp & al

Make kernel doc comments actually work and fix the syncronized typo.

[ tglx: Added the missing /** and fixed up formatting ]

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200609081726.5657-1-kurt@linutronix.de
---
 include/linux/timekeeping.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index b27e2ffa96c1..d5471d6fa778 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -222,9 +222,9 @@ extern bool timekeeping_rtc_skipresume(void);
 
 extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
-/*
+/**
  * struct system_time_snapshot - simultaneous raw/real time capture with
- *	counter value
+ *				 counter value
  * @cycles:	Clocksource counter value to produce the system times
  * @real:	Realtime system time
  * @raw:	Monotonic raw system time
@@ -239,9 +239,9 @@ struct system_time_snapshot {
 	u8		cs_was_changed_seq;
 };
 
-/*
+/**
  * struct system_device_crosststamp - system/device cross-timestamp
- *	(syncronized capture)
+ *				      (synchronized capture)
  * @device:		Device time
  * @sys_realtime:	Realtime simultaneous with device time
  * @sys_monoraw:	Monotonic raw simultaneous with device time
@@ -252,12 +252,12 @@ struct system_device_crosststamp {
 	ktime_t sys_monoraw;
 };
 
-/*
+/**
  * struct system_counterval_t - system counter value with the pointer to the
- *	corresponding clocksource
+ *				corresponding clocksource
  * @cycles:	System counter value
  * @cs:		Clocksource corresponding to system counter value. Used by
- *	timekeeping code to verify comparibility of two cycle values
+ *		timekeeping code to verify comparibility of two cycle values
  */
 struct system_counterval_t {
 	u64			cycles;
-- 
cgit v1.2.3


From e0bcc58d876c6ece9720310509a908b7637e37cf Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@st.com>
Date: Wed, 3 Jun 2020 14:54:36 +0200
Subject: mfd: stm32: Add defines to be used for clkevent purpose

Add defines to be able to enable/clear irq and configure one shot mode.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/stm32-lptimer.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h
index 605f62264825..90b20550c1c8 100644
--- a/include/linux/mfd/stm32-lptimer.h
+++ b/include/linux/mfd/stm32-lptimer.h
@@ -27,10 +27,15 @@
 #define STM32_LPTIM_CMPOK		BIT(3)
 
 /* STM32_LPTIM_ICR - bit fields */
+#define STM32_LPTIM_ARRMCF		BIT(1)
 #define STM32_LPTIM_CMPOKCF_ARROKCF	GENMASK(4, 3)
 
+/* STM32_LPTIM_IER - bit flieds */
+#define STM32_LPTIM_ARRMIE	BIT(1)
+
 /* STM32_LPTIM_CR - bit fields */
 #define STM32_LPTIM_CNTSTRT	BIT(2)
+#define STM32_LPTIM_SNGSTRT	BIT(1)
 #define STM32_LPTIM_ENABLE	BIT(0)
 
 /* STM32_LPTIM_CFGR - bit fields */
-- 
cgit v1.2.3


From 7f8a137f736f7366820c485c5a0d34d65b9d0125 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 15 Jun 2020 14:53:22 +0100
Subject: mfd: madera: Remove unused forward declaration of madera_codec_pdata

This forward declaration is redundant since the header including the
full data structure is included.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/madera/pdata.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h
index fa9595dd42ba..601cbbc10370 100644
--- a/include/linux/mfd/madera/pdata.h
+++ b/include/linux/mfd/madera/pdata.h
@@ -21,7 +21,6 @@
 
 struct gpio_desc;
 struct pinctrl_map;
-struct madera_codec_pdata;
 
 /**
  * struct madera_pdata - Configuration data for Madera devices
-- 
cgit v1.2.3


From 6c27219e34911601955b72c754adfc11c527ba7b Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Mon, 8 Jun 2020 11:17:36 +0200
Subject: mfd: Add support for the Khadas System control Microcontroller

This Microcontroller is present on the Khadas VIM1, VIM2, VIM3 and Edge
boards.

It has multiple boot control features like password check, power-on
options, power-off control and system FAN control on recent boards.

This implements a very basic MFD driver with the fan control and User
NVMEM cells.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig            |  21 ++++++
 drivers/mfd/Makefile           |   1 +
 drivers/mfd/khadas-mcu.c       | 142 +++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/khadas-mcu.h |  91 ++++++++++++++++++++++++++
 4 files changed, 255 insertions(+)
 create mode 100644 drivers/mfd/khadas-mcu.c
 create mode 100644 include/linux/mfd/khadas-mcu.h

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index a37d7d171382..d13bb0abfd6f 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2053,6 +2053,27 @@ config MFD_WCD934X
 	  This driver provides common support WCD934x audio codec and its
 	  associated Pin Controller, Soundwire Controller and Audio codec.
 
+config MFD_KHADAS_MCU
+	tristate "Support for Khadas System control Microcontroller"
+	depends on I2C
+	depends on ARCH_MESON || ARCH_ROCKCHIP || COMPILE_TEST
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Support for the Khadas System control Microcontroller interface
+	  present on their VIM and Edge boards.
+
+	  This Microcontroller is present on the Khadas VIM1, VIM2, VIM3 and
+	  Edge boards.
+
+	  It provides multiple boot control features like password check,
+	  power-on options, power-off control and system FAN control on recent
+	  boards.
+
+	  This driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the functionality
+	  of the device.
+
 menu "Multimedia Capabilities Port drivers"
 	depends on ARCH_SA1100
 
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 9367a92f795a..1c8d6be3347d 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -262,5 +262,6 @@ obj-$(CONFIG_MFD_ROHM_BD70528)	+= rohm-bd70528.o
 obj-$(CONFIG_MFD_ROHM_BD71828)	+= rohm-bd71828.o
 obj-$(CONFIG_MFD_ROHM_BD718XX)	+= rohm-bd718x7.o
 obj-$(CONFIG_MFD_STMFX) 	+= stmfx.o
+obj-$(CONFIG_MFD_KHADAS_MCU) 	+= khadas-mcu.o
 
 obj-$(CONFIG_SGI_MFD_IOC3)	+= ioc3.o
diff --git a/drivers/mfd/khadas-mcu.c b/drivers/mfd/khadas-mcu.c
new file mode 100644
index 000000000000..44d5bb462dab
--- /dev/null
+++ b/drivers/mfd/khadas-mcu.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Khadas System control Microcontroller
+ *
+ * Copyright (C) 2020 BayLibre SAS
+ *
+ * Author(s): Neil Armstrong <narmstrong@baylibre.com>
+ */
+#include <linux/bitfield.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/khadas-mcu.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+static bool khadas_mcu_reg_volatile(struct device *dev, unsigned int reg)
+{
+	if (reg >= KHADAS_MCU_USER_DATA_0_REG &&
+	    reg < KHADAS_MCU_PWR_OFF_CMD_REG)
+		return true;
+
+	switch (reg) {
+	case KHADAS_MCU_PWR_OFF_CMD_REG:
+	case KHADAS_MCU_PASSWD_START_REG:
+	case KHADAS_MCU_CHECK_VEN_PASSWD_REG:
+	case KHADAS_MCU_CHECK_USER_PASSWD_REG:
+	case KHADAS_MCU_WOL_INIT_START_REG:
+	case KHADAS_MCU_CMD_FAN_STATUS_CTRL_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool khadas_mcu_reg_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case KHADAS_MCU_PASSWD_VEN_0_REG:
+	case KHADAS_MCU_PASSWD_VEN_1_REG:
+	case KHADAS_MCU_PASSWD_VEN_2_REG:
+	case KHADAS_MCU_PASSWD_VEN_3_REG:
+	case KHADAS_MCU_PASSWD_VEN_4_REG:
+	case KHADAS_MCU_PASSWD_VEN_5_REG:
+	case KHADAS_MCU_MAC_0_REG:
+	case KHADAS_MCU_MAC_1_REG:
+	case KHADAS_MCU_MAC_2_REG:
+	case KHADAS_MCU_MAC_3_REG:
+	case KHADAS_MCU_MAC_4_REG:
+	case KHADAS_MCU_MAC_5_REG:
+	case KHADAS_MCU_USID_0_REG:
+	case KHADAS_MCU_USID_1_REG:
+	case KHADAS_MCU_USID_2_REG:
+	case KHADAS_MCU_USID_3_REG:
+	case KHADAS_MCU_USID_4_REG:
+	case KHADAS_MCU_USID_5_REG:
+	case KHADAS_MCU_VERSION_0_REG:
+	case KHADAS_MCU_VERSION_1_REG:
+	case KHADAS_MCU_DEVICE_NO_0_REG:
+	case KHADAS_MCU_DEVICE_NO_1_REG:
+	case KHADAS_MCU_FACTORY_TEST_REG:
+	case KHADAS_MCU_SHUTDOWN_NORMAL_STATUS_REG:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static const struct regmap_config khadas_mcu_regmap_config = {
+	.reg_bits	= 8,
+	.reg_stride	= 1,
+	.val_bits	= 8,
+	.max_register	= KHADAS_MCU_CMD_FAN_STATUS_CTRL_REG,
+	.volatile_reg	= khadas_mcu_reg_volatile,
+	.writeable_reg	= khadas_mcu_reg_writeable,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
+static struct mfd_cell khadas_mcu_fan_cells[] = {
+	/* VIM1/2 Rev13+ and VIM3 only */
+	{ .name = "khadas-mcu-fan-ctrl", },
+};
+
+static struct mfd_cell khadas_mcu_cells[] = {
+	{ .name = "khadas-mcu-user-mem", },
+};
+
+static int khadas_mcu_probe(struct i2c_client *client,
+		       const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct khadas_mcu *ddata;
+	int ret;
+
+	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, ddata);
+
+	ddata->dev = dev;
+
+	ddata->regmap = devm_regmap_init_i2c(client, &khadas_mcu_regmap_config);
+	if (IS_ERR(ddata->regmap)) {
+		ret = PTR_ERR(ddata->regmap);
+		dev_err(dev, "Failed to allocate register map: %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+				   khadas_mcu_cells,
+				   ARRAY_SIZE(khadas_mcu_cells),
+				   NULL, 0, NULL);
+	if (ret)
+		return ret;
+
+	if (of_find_property(dev->of_node, "#cooling-cells", NULL))
+		return devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+					    khadas_mcu_fan_cells,
+					    ARRAY_SIZE(khadas_mcu_fan_cells),
+					    NULL, 0, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id khadas_mcu_of_match[] = {
+	{ .compatible = "khadas,mcu", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, khadas_mcu_of_match);
+
+static struct i2c_driver khadas_mcu_driver = {
+	.driver = {
+		.name = "khadas-mcu-core",
+		.of_match_table = of_match_ptr(khadas_mcu_of_match),
+	},
+	.probe = khadas_mcu_probe,
+};
+module_i2c_driver(khadas_mcu_driver);
+
+MODULE_DESCRIPTION("Khadas MCU core driver");
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/khadas-mcu.h b/include/linux/mfd/khadas-mcu.h
new file mode 100644
index 000000000000..a99ba2ed0e4e
--- /dev/null
+++ b/include/linux/mfd/khadas-mcu.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Khadas System control Microcontroller Register map
+ *
+ * Copyright (C) 2020 BayLibre SAS
+ *
+ * Author(s): Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef MFD_KHADAS_MCU_H
+#define MFD_KHADAS_MCU_H
+
+#define KHADAS_MCU_PASSWD_VEN_0_REG		0x00 /* RO */
+#define KHADAS_MCU_PASSWD_VEN_1_REG		0x01 /* RO */
+#define KHADAS_MCU_PASSWD_VEN_2_REG		0x02 /* RO */
+#define KHADAS_MCU_PASSWD_VEN_3_REG		0x03 /* RO */
+#define KHADAS_MCU_PASSWD_VEN_4_REG		0x04 /* RO */
+#define KHADAS_MCU_PASSWD_VEN_5_REG		0x05 /* RO */
+#define KHADAS_MCU_MAC_0_REG			0x06 /* RO */
+#define KHADAS_MCU_MAC_1_REG			0x07 /* RO */
+#define KHADAS_MCU_MAC_2_REG			0x08 /* RO */
+#define KHADAS_MCU_MAC_3_REG			0x09 /* RO */
+#define KHADAS_MCU_MAC_4_REG			0x0a /* RO */
+#define KHADAS_MCU_MAC_5_REG			0x0b /* RO */
+#define KHADAS_MCU_USID_0_REG			0x0c /* RO */
+#define KHADAS_MCU_USID_1_REG			0x0d /* RO */
+#define KHADAS_MCU_USID_2_REG			0x0e /* RO */
+#define KHADAS_MCU_USID_3_REG			0x0f /* RO */
+#define KHADAS_MCU_USID_4_REG			0x10 /* RO */
+#define KHADAS_MCU_USID_5_REG			0x11 /* RO */
+#define KHADAS_MCU_VERSION_0_REG		0x12 /* RO */
+#define KHADAS_MCU_VERSION_1_REG		0x13 /* RO */
+#define KHADAS_MCU_DEVICE_NO_0_REG		0x14 /* RO */
+#define KHADAS_MCU_DEVICE_NO_1_REG		0x15 /* RO */
+#define KHADAS_MCU_FACTORY_TEST_REG		0x16 /* R */
+#define KHADAS_MCU_BOOT_MODE_REG		0x20 /* RW */
+#define KHADAS_MCU_BOOT_EN_WOL_REG		0x21 /* RW */
+#define KHADAS_MCU_BOOT_EN_RTC_REG		0x22 /* RW */
+#define KHADAS_MCU_BOOT_EN_EXP_REG		0x23 /* RW */
+#define KHADAS_MCU_BOOT_EN_IR_REG		0x24 /* RW */
+#define KHADAS_MCU_BOOT_EN_DCIN_REG		0x25 /* RW */
+#define KHADAS_MCU_BOOT_EN_KEY_REG		0x26 /* RW */
+#define KHADAS_MCU_KEY_MODE_REG			0x27 /* RW */
+#define KHADAS_MCU_LED_MODE_ON_REG		0x28 /* RW */
+#define KHADAS_MCU_LED_MODE_OFF_REG		0x29 /* RW */
+#define KHADAS_MCU_SHUTDOWN_NORMAL_REG		0x2c /* RW */
+#define KHADAS_MCU_MAC_SWITCH_REG		0x2d /* RW */
+#define KHADAS_MCU_MCU_SLEEP_MODE_REG		0x2e /* RW */
+#define KHADAS_MCU_IR_CODE1_0_REG		0x2f /* RW */
+#define KHADAS_MCU_IR_CODE1_1_REG		0x30 /* RW */
+#define KHADAS_MCU_IR_CODE1_2_REG		0x31 /* RW */
+#define KHADAS_MCU_IR_CODE1_3_REG		0x32 /* RW */
+#define KHADAS_MCU_USB_PCIE_SWITCH_REG		0x33 /* RW */
+#define KHADAS_MCU_IR_CODE2_0_REG		0x34 /* RW */
+#define KHADAS_MCU_IR_CODE2_1_REG		0x35 /* RW */
+#define KHADAS_MCU_IR_CODE2_2_REG		0x36 /* RW */
+#define KHADAS_MCU_IR_CODE2_3_REG		0x37 /* RW */
+#define KHADAS_MCU_PASSWD_USER_0_REG		0x40 /* RW */
+#define KHADAS_MCU_PASSWD_USER_1_REG		0x41 /* RW */
+#define KHADAS_MCU_PASSWD_USER_2_REG		0x42 /* RW */
+#define KHADAS_MCU_PASSWD_USER_3_REG		0x43 /* RW */
+#define KHADAS_MCU_PASSWD_USER_4_REG		0x44 /* RW */
+#define KHADAS_MCU_PASSWD_USER_5_REG		0x45 /* RW */
+#define KHADAS_MCU_USER_DATA_0_REG		0x46 /* RW 56 bytes */
+#define KHADAS_MCU_PWR_OFF_CMD_REG		0x80 /* WO */
+#define KHADAS_MCU_PASSWD_START_REG		0x81 /* WO */
+#define KHADAS_MCU_CHECK_VEN_PASSWD_REG		0x82 /* WO */
+#define KHADAS_MCU_CHECK_USER_PASSWD_REG	0x83 /* WO */
+#define KHADAS_MCU_SHUTDOWN_NORMAL_STATUS_REG	0x86 /* RO */
+#define KHADAS_MCU_WOL_INIT_START_REG		0x87 /* WO */
+#define KHADAS_MCU_CMD_FAN_STATUS_CTRL_REG	0x88 /* WO */
+
+enum {
+	KHADAS_BOARD_VIM1 = 0x1,
+	KHADAS_BOARD_VIM2,
+	KHADAS_BOARD_VIM3,
+	KHADAS_BOARD_EDGE = 0x11,
+	KHADAS_BOARD_EDGE_V,
+};
+
+/**
+ * struct khadas_mcu - Khadas MCU structure
+ * @device:		device reference used for logs
+ * @regmap:		register map
+ */
+struct khadas_mcu {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+#endif /* MFD_KHADAS_MCU_H */
-- 
cgit v1.2.3


From ab183d460daac6292cb0cfd989d88b37b2437844 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 16 Jun 2020 13:45:36 +0300
Subject: RDMA/mlx5: Add missed RST2INIT and INIT2INIT steps during ECE
 handshake

Missed steps during ECE handshake left userspace application with less
options for the ECE handshake. Pass ECE options in the additional
transitions.

Fixes: 50aec2c3135e ("RDMA/mlx5: Return ECE data after modify QP")
Link: https://lore.kernel.org/r/20200616104536.2426384-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qpc.c |  8 ++++++++
 include/linux/mlx5/mlx5_ifc.h    | 10 ++++++----
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index c19d91d6dce8..7c3968ef9cd1 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -346,6 +346,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	int ece = 0;
 
 	switch (opcode) {
+	case MLX5_CMD_OP_INIT2INIT_QP:
+		ece = MLX5_GET(init2init_qp_out, out, ece);
+		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		ece = MLX5_GET(init2rtr_qp_out, out, ece);
 		break;
@@ -355,6 +358,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	case MLX5_CMD_OP_RTS2RTS_QP:
 		ece = MLX5_GET(rts2rts_qp_out, out, ece);
 		break;
+	case MLX5_CMD_OP_RST2INIT_QP:
+		ece = MLX5_GET(rst2init_qp_out, out, ece);
+		break;
 	default:
 		break;
 	}
@@ -406,6 +412,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(rst2init_qp_in, mbox->in, ece, ece);
 		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		if (MBOX_ALLOC(mbox, init2rtr_qp))
@@ -439,6 +446,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(init2init_qp_in, mbox->in, ece, ece);
 		break;
 	default:
 		return -EINVAL;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 116bd9bb347f..ca1887dd0423 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -4283,7 +4283,8 @@ struct mlx5_ifc_rst2init_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_rst2init_qp_in_bits {
@@ -4300,7 +4301,7 @@ struct mlx5_ifc_rst2init_qp_in_bits {
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
@@ -6619,7 +6620,8 @@ struct mlx5_ifc_init2init_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_init2init_qp_in_bits {
@@ -6636,7 +6638,7 @@ struct mlx5_ifc_init2init_qp_in_bits {
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-- 
cgit v1.2.3


From b5292111de9bb70cba3489075970889765302136 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Wed, 3 Jun 2020 15:48:19 +0800
Subject: libata: Use per port sync for detach

Commit 130f4caf145c ("libata: Ensure ata_port probe has completed before
detach") may cause system freeze during suspend.

Using async_synchronize_full() in PM callbacks is wrong, since async
callbacks that are already scheduled may wait for not-yet-scheduled
callbacks, causes a circular dependency.

Instead of using big hammer like async_synchronize_full(), use async
cookie to make sure port probe are synced, without affecting other
scheduled PM callbacks.

Fixes: 130f4caf145c ("libata: Ensure ata_port probe has completed before detach")
Suggested-by: John Garry <john.garry@huawei.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: John Garry <john.garry@huawei.com>
BugLink: https://bugs.launchpad.net/bugs/1867983
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ata/libata-core.c | 11 +++++------
 include/linux/libata.h    |  3 +++
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 69361ec43db5..b1cd4d97bc2a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -42,7 +42,6 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
-#include <linux/async.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/glob.h>
@@ -5778,7 +5777,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	/* perform each probe asynchronously */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
-		async_schedule(async_port_probe, ap);
+		ap->cookie = async_schedule(async_port_probe, ap);
 	}
 
 	return 0;
@@ -5920,11 +5919,11 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
-	/* Ensure ata_port probe has completed */
-	async_synchronize_full();
-
-	for (i = 0; i < host->n_ports; i++)
+	for (i = 0; i < host->n_ports; i++) {
+		/* Ensure ata_port probe has completed */
+		async_synchronize_cookie(host->ports[i]->cookie + 1);
 		ata_port_detach(host->ports[i]);
+	}
 
 	/* the host is dead now, dissociate ACPI */
 	ata_acpi_dissociate(host);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index af832852e620..8a4843704d28 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -22,6 +22,7 @@
 #include <linux/acpi.h>
 #include <linux/cdrom.h>
 #include <linux/sched.h>
+#include <linux/async.h>
 
 /*
  * Define if arch has non-standard setup.  This is a _PCI_ standard
@@ -872,6 +873,8 @@ struct ata_port {
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
 
+	async_cookie_t		cookie;
+
 	int			em_message_type;
 	void			*private_data;
 
-- 
cgit v1.2.3


From 3373a3461aa15b7f9a871fa4cb2c9ef21ac20b47 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Thu, 18 Jun 2020 12:21:38 +0800
Subject: block: make function 'kill_bdev' static

kill_bdev does not have any external user, so make it static.

Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c     | 5 ++---
 include/linux/fs.h | 2 --
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 08c87db3a92b..0ae656e022fd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -75,7 +75,7 @@ static void bdev_write_inode(struct block_device *bdev)
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
-void kill_bdev(struct block_device *bdev)
+static void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
@@ -84,8 +84,7 @@ void kill_bdev(struct block_device *bdev)
 
 	invalidate_bh_lrus();
 	truncate_inode_pages(mapping, 0);
-}	
-EXPORT_SYMBOL(kill_bdev);
+}
 
 /* Invalidate clean unused buffers and pagecache. */
 void invalidate_bdev(struct block_device *bdev)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6c4ab4dc1cd7..3f881a892ea7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2592,7 +2592,6 @@ extern void bdput(struct block_device *);
 extern void invalidate_bdev(struct block_device *);
 extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 extern int sync_blockdev(struct block_device *bdev);
-extern void kill_bdev(struct block_device *);
 extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern void emergency_thaw_bdev(struct super_block *sb);
@@ -2608,7 +2607,6 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb)
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }
-static inline void kill_bdev(struct block_device *bdev) {}
 static inline void invalidate_bdev(struct block_device *bdev) {}
 
 static inline struct super_block *freeze_bdev(struct block_device *sb)
-- 
cgit v1.2.3


From 670d0a4b10704667765f7d18f7592993d02783aa Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Thu, 18 Jun 2020 00:02:26 +0200
Subject: sparse: use identifiers to define address spaces

Currently, address spaces in warnings are displayed as '<asn:X>' with
'X' being the address space's arbitrary number.

But since sparse v0.6.0-rc1 (late December 2018), sparse allows you to
define the address spaces using an identifier instead of a number.  This
identifier is then directly used in the warnings.

So, use the identifiers '__user', '__iomem', '__percpu' & '__rcu' for
the corresponding address spaces.  The default address space, __kernel,
being not displayed in warnings, stays defined as '0'.

With this change, warnings that used to be displayed as:

	cast removes address space '<asn:1>' of expression
	... void [noderef] <asn:2> *

will now be displayed as:

	cast removes address space '__user' of expression
	... void [noderef] __iomem *

This also moves the __kernel annotation to be the first one, since it is
quite different from the others because it's the default one, and so:

 - it's never displayed

 - it's normally not needed, nor in type annotations, nor in cast
   between address spaces. The only time it's needed is when it's
   combined with a typeof to express "the same type as this one but
   without the address space"

 - it can't be defined with a name, '0' must be used.

So, it seemed strange to me to have it in the middle of the other
ones.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler_types.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 21aed0981edf..e368384445b6 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -5,20 +5,20 @@
 #ifndef __ASSEMBLY__
 
 #ifdef __CHECKER__
-# define __user		__attribute__((noderef, address_space(1)))
 # define __kernel	__attribute__((address_space(0)))
+# define __user		__attribute__((noderef, address_space(__user)))
 # define __safe		__attribute__((safe))
 # define __force	__attribute__((force))
 # define __nocast	__attribute__((nocast))
-# define __iomem	__attribute__((noderef, address_space(2)))
+# define __iomem	__attribute__((noderef, address_space(__iomem)))
 # define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
 # define __releases(x)	__attribute__((context(x,1,0)))
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu	__attribute__((noderef, address_space(3)))
-# define __rcu		__attribute__((noderef, address_space(4)))
+# define __percpu	__attribute__((noderef, address_space(__percpu)))
+# define __rcu		__attribute__((noderef, address_space(__rcu)))
 # define __private	__attribute__((noderef))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
-- 
cgit v1.2.3


From 25f12ae45fc1931a1dce3cc59f9989a9d87834b0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Jun 2020 09:37:55 +0200
Subject: maccess: rename probe_kernel_address to get_kernel_nofault

Better describe what this helper does, and match the naming of
copy_from_kernel_nofault.

Also switch the argument order around, so that it acts and looks
like get_user().

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/traps.c             |  2 +-
 arch/arm/mm/alignment.c             |  4 ++--
 arch/arm64/kernel/traps.c           |  2 +-
 arch/ia64/include/asm/sections.h    |  2 +-
 arch/parisc/kernel/process.c        |  2 +-
 arch/powerpc/include/asm/sections.h |  2 +-
 arch/powerpc/kernel/kgdb.c          |  2 +-
 arch/powerpc/kernel/kprobes.c       |  2 +-
 arch/powerpc/kernel/process.c       |  2 +-
 arch/powerpc/sysdev/fsl_pci.c       |  2 +-
 arch/riscv/kernel/kgdb.c            |  4 ++--
 arch/riscv/kernel/traps.c           |  4 ++--
 arch/s390/mm/fault.c                |  2 +-
 arch/sh/kernel/traps.c              |  2 +-
 arch/x86/kernel/probe_roms.c        | 20 ++++++++++----------
 arch/x86/kernel/traps.c             |  2 +-
 arch/x86/mm/fault.c                 |  6 +++---
 arch/x86/pci/pcbios.c               |  2 +-
 include/linux/uaccess.h             | 10 +++++-----
 lib/test_lockup.c                   |  6 +++---
 20 files changed, 40 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 65a3b1e75480..49ce15c3612d 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc)
 	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
-	if (probe_kernel_address((unsigned *)pc, bkpt))
+	if (get_kernel_nofault(bkpt, (unsigned *)pc))
 		return 0;
 
 	return bkpt == insn;
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 84718eddae60..81a627e6e1c5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_arm(instr);
 
@@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_thumb16(instr);
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 50cc30acf106..227b2d9bae3d 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -376,7 +376,7 @@ static int call_undef_hook(struct pt_regs *regs)
 
 	if (!user_mode(regs)) {
 		__le32 instr_le;
-		if (probe_kernel_address((__force __le32 *)pc, instr_le))
+		if (get_kernel_nofault(instr_le, (__force __le32 *)pc))
 			goto exit;
 		instr = le32_to_cpu(instr_le);
 	} else if (compat_thumb_mode(regs)) {
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index cea15f2dd38d..ad4fc06e5f4b 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct fdesc *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->ip, p))
+	if (!get_kernel_nofault(p, &desc->ip))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 230a6422b99f..6c435dbccca0 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr)
 	Elf64_Fdesc *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->addr, p))
+	if (!get_kernel_nofault(p, &desc->addr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index d19871763ed4..bd311616fca8 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct ppc64_opd_entry *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->funcaddr, p))
+	if (!get_kernel_nofault(p, &desc->funcaddr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 652b2852bea3..e14a1862a3ca 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	unsigned int instr;
 	struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
 
-	err = probe_kernel_address(addr, instr);
+	err = get_kernel_nofault(instr, addr);
 	if (err)
 		return err;
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 6f96f65ebfe8..9cc792a3a6a9 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -289,7 +289,7 @@ int kprobe_handler(struct pt_regs *regs)
 	if (!p) {
 		unsigned int instr;
 
-		if (probe_kernel_address(addr, instr))
+		if (get_kernel_nofault(instr, addr))
 			goto no_kprobe;
 
 		if (instr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d4d0d1048500..30955a0c32d0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1271,7 +1271,7 @@ static void show_instructions(struct pt_regs *regs)
 #endif
 
 		if (!__kernel_text_address(pc) ||
-		    probe_kernel_address((const void *)pc, instr)) {
+		    get_kernel_nofault(instr, (const void *)pc)) {
 			pr_cont("XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 73fa37ca40ef..040b9d01c079 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1069,7 +1069,7 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 			ret = copy_from_user_nofault(&inst,
 					(void __user *)regs->nip, sizeof(inst));
 		else
-			ret = probe_kernel_address((void *)regs->nip, inst);
+			ret = get_kernel_nofault(inst, (void *)regs->nip);
 
 		if (!ret && mcheck_handle_load(regs, inst)) {
 			regs->nip += 4;
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index a21fb21883e7..c3275f42d1ac 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -62,7 +62,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 	unsigned int rs1_num, rs2_num;
 	int op_code;
 
-	if (probe_kernel_address((void *)pc, op_code))
+	if (get_kernel_nofault(op_code, (void *)pc))
 		return -EINVAL;
 	if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
 		if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
@@ -146,7 +146,7 @@ int do_single_step(struct pt_regs *regs)
 		return error;
 
 	/* Store the op code in the stepped address */
-	error = probe_kernel_address((void *)addr, stepped_opcode);
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
 	if (error)
 		return error;
 
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index ecec1778e3a4..7d95cce5e47c 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 {
 	bug_insn_t insn;
 
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 
 	return GET_INSN_LENGTH(insn);
@@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc)
 
 	if (pc < VMALLOC_START)
 		return 0;
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 	if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
 		return (insn == __BUG_INSN_32);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 6a24751557f0..d53c2e2ea1fd 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -105,7 +105,7 @@ static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long asce, unsigned long address)
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index a33025451fcd..9c3d32b80038 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr)
 
 	if (addr < PAGE_OFFSET)
 		return 0;
-	if (probe_kernel_address((insn_size_t *)addr, opcode))
+	if (get_kernel_nofault(opcode, (insn_size_t *)addr))
 		return 0;
 	if (opcode == TRAPA_BUG_OPCODE)
 		return 1;
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index ee0286390a4c..65b0dd2bf25c 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -99,7 +99,7 @@ static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
 	unsigned short device;
 
 	do {
-		if (probe_kernel_address(rom_list, device) != 0)
+		if (get_kernel_nofault(device, rom_list) != 0)
 			device = 0;
 
 		if (device && match_id(pdev, vendor, device))
@@ -125,13 +125,13 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 			break;
 
 		rom = isa_bus_to_virt(res->start);
-		if (probe_kernel_address(rom + 0x18, offset) != 0)
+		if (get_kernel_nofault(offset, rom + 0x18) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+		if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+		if (get_kernel_nofault(device, rom + offset + 0x6) != 0)
 			continue;
 
 		if (match_id(pdev, vendor, device)) {
@@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 			break;
 		}
 
-		if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
-		    probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+		if (get_kernel_nofault(list, rom + offset + 0x8) == 0 &&
+		    get_kernel_nofault(rev, rom + offset + 0xc) == 0 &&
 		    rev >= 3 && list &&
 		    probe_list(pdev, vendor, rom + offset + list)) {
 			oprom = res;
@@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom)
 	const unsigned short * const ptr = (const unsigned short *)rom;
 	unsigned short sig;
 
-	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
+	return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE;
 }
 
 static int __init romchecksum(const unsigned char *rom, unsigned long length)
 {
 	unsigned char sum, c;
 
-	for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
+	for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--)
 		sum += c;
 	return !length && !sum;
 }
@@ -211,7 +211,7 @@ void __init probe_roms(void)
 
 		video_rom_resource.start = start;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
@@ -249,7 +249,7 @@ void __init probe_roms(void)
 		if (!romsignature(rom))
 			continue;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7003f2e7b163..f9727b96961f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -91,7 +91,7 @@ int is_valid_bugaddr(unsigned long addr)
 	if (addr < TASK_SIZE_MAX)
 		return 0;
 
-	if (probe_kernel_address((unsigned short *)addr, ud))
+	if (get_kernel_nofault(ud, (unsigned short *)addr))
 		return 0;
 
 	return ud == INSN_UD0 || ud == INSN_UD2;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e996aa3833b8..1ead568c0101 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		return !instr_lo || (instr_lo>>1) == 1;
 	case 0x00:
 		/* Prefetch instruction is 0x0F0D or 0x0F18 */
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			return 0;
 
 		*prefetch = (instr_lo == 0xF) &&
@@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 	while (instr < max_instr) {
 		unsigned char opcode;
 
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			break;
 
 		instr++;
@@ -301,7 +301,7 @@ static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long address)
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 9c97d814125e..4f15280732ed 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void)
 	     check <= (union bios32 *) __va(0xffff0);
 	     ++check) {
 		long sig;
-		if (probe_kernel_address(&check->fields.signature, sig))
+		if (get_kernel_nofault(sig, &check->fields.signature))
 			continue;
 
 		if (check->fields.signature != BIOS32_SIGNATURE)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index bef48da242cc..a508a3c08879 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -318,14 +318,14 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
 long strnlen_user_nofault(const void __user *unsafe_addr, long count);
 
 /**
- * probe_kernel_address(): safely attempt to read from a location
- * @addr: address to read from
- * @retval: read into this variable
+ * get_kernel_nofault(): safely attempt to read from a location
+ * @val: read into this variable
+ * @ptr: address to read from
  *
  * Returns 0 on success, or -EFAULT.
  */
-#define probe_kernel_address(addr, retval)		\
-	copy_from_kernel_nofault(&retval, addr, sizeof(retval))
+#define get_kernel_nofault(val, ptr)		\
+	copy_from_kernel_nofault(&(val), (ptr), sizeof(val))
 
 #ifndef user_access_begin
 #define user_access_begin(ptr,len) access_ok(ptr, len)
diff --git a/lib/test_lockup.c b/lib/test_lockup.c
index f258743a0d83..bd7c7ff39f6b 100644
--- a/lib/test_lockup.c
+++ b/lib/test_lockup.c
@@ -419,8 +419,8 @@ static bool test_kernel_ptr(unsigned long addr, int size)
 	/* should be at least readable kernel address */
 	if (access_ok(ptr, 1) ||
 	    access_ok(ptr + size - 1, 1) ||
-	    probe_kernel_address(ptr, buf) ||
-	    probe_kernel_address(ptr + size - 1, buf)) {
+	    get_kernel_nofault(buf, ptr) ||
+	    get_kernel_nofault(buf, ptr + size - 1)) {
 		pr_err("invalid kernel ptr: %#lx\n", addr);
 		return true;
 	}
@@ -437,7 +437,7 @@ static bool __maybe_unused test_magic(unsigned long addr, int offset,
 	if (!addr)
 		return false;
 
-	if (probe_kernel_address(ptr, magic) || magic != expected) {
+	if (get_kernel_nofault(magic, ptr) || magic != expected) {
 		pr_err("invalid magic at %#lx + %#x = %#x, expected %#x\n",
 		       addr, offset, magic, expected);
 		return true;
-- 
cgit v1.2.3


From 0c389d89abc28edf70ae847ee2fa55acb267b826 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 18 Jun 2020 12:10:37 -0700
Subject: maccess: make get_kernel_nofault() check for minimal type
 compatibility

Now that we've renamed probe_kernel_address() to get_kernel_nofault()
and made it look and behave more in line with get_user(), some of the
subtle type behavior differences end up being more obvious and possibly
dangerous.

When you do

        get_user(val, user_ptr);

the type of the access comes from the "user_ptr" part, and the above
basically acts as

        val = *user_ptr;

by design (except, of course, for the fact that the actual dereference
is done with a user access).

Note how in the above case, the type of the end result comes from the
pointer argument, and then the value is cast to the type of 'val' as
part of the assignment.

So the type of the pointer is ultimately the more important type both
for the access itself.

But 'get_kernel_nofault()' may now _look_ similar, but it behaves very
differently.  When you do

        get_kernel_nofault(val, kernel_ptr);

it behaves like

        val = *(typeof(val) *)kernel_ptr;

except, of course, for the fact that the actual dereference is done with
exception handling so that a faulting access is suppressed and returned
as the error code.

But note how different the casting behavior of the two superficially
similar accesses are: one does the actual access in the size of the type
the pointer points to, while the other does the access in the size of
the target, and ignores the pointer type entirely.

Actually changing get_kernel_nofault() to act like get_user() is almost
certainly the right thing to do eventually, but in the meantime this
patch adds logit to at least verify that the pointer type is compatible
with the type of the result.

In many cases, this involves just casting the pointer to 'void *' to
make it obvious that the type of the pointer is not the important part.
It's not how 'get_user()' acts, but at least the behavioral difference
is now obvious and explicit.

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/traps.c             | 2 +-
 arch/ia64/include/asm/sections.h    | 2 +-
 arch/parisc/kernel/process.c        | 2 +-
 arch/powerpc/include/asm/sections.h | 2 +-
 arch/powerpc/kernel/kgdb.c          | 2 +-
 arch/x86/kernel/probe_roms.c        | 4 ++--
 include/linux/uaccess.h             | 6 ++++--
 7 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 49ce15c3612d..17d5a785df28 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc)
 	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
-	if (get_kernel_nofault(bkpt, (unsigned *)pc))
+	if (get_kernel_nofault(bkpt, (void *)pc))
 		return 0;
 
 	return bkpt == insn;
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index ad4fc06e5f4b..3a033d2008b3 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct fdesc *desc = ptr;
 	void *p;
 
-	if (!get_kernel_nofault(p, &desc->ip))
+	if (!get_kernel_nofault(p, (void *)&desc->ip))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 6c435dbccca0..b7abb12edd3a 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr)
 	Elf64_Fdesc *desc = ptr;
 	void *p;
 
-	if (!get_kernel_nofault(p, &desc->addr))
+	if (!get_kernel_nofault(p, (void *)&desc->addr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index bd311616fca8..324d7b298ec3 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct ppc64_opd_entry *desc = ptr;
 	void *p;
 
-	if (!get_kernel_nofault(p, &desc->funcaddr))
+	if (!get_kernel_nofault(p, (void *)&desc->funcaddr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index e14a1862a3ca..409080208a6c 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	unsigned int instr;
 	struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
 
-	err = get_kernel_nofault(instr, addr);
+	err = get_kernel_nofault(instr, (unsigned *) addr);
 	if (err)
 		return err;
 
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 65b0dd2bf25c..9e1def3744f2 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -94,7 +94,7 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short
 }
 
 static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
-		       const unsigned char *rom_list)
+		       const void *rom_list)
 {
 	unsigned short device;
 
@@ -119,7 +119,7 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
 		struct resource *res = &adapter_rom_resources[i];
 		unsigned short offset, vendor, device, list, rev;
-		const unsigned char *rom;
+		const void *rom;
 
 		if (res->end == 0)
 			break;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index a508a3c08879..0a76ddc07d59 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -324,8 +324,10 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count);
  *
  * Returns 0 on success, or -EFAULT.
  */
-#define get_kernel_nofault(val, ptr)		\
-	copy_from_kernel_nofault(&(val), (ptr), sizeof(val))
+#define get_kernel_nofault(val, ptr) ({				\
+	const typeof(val) *__gk_ptr = (ptr);			\
+	copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\
+})
 
 #ifndef user_access_begin
 #define user_access_begin(ptr,len) access_ok(ptr, len)
-- 
cgit v1.2.3


From fb7861d14c8d7edac65b2fcb6e8031cb138457b2 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 15:52:05 +0000
Subject: net: core: reduce recursion limit value

In the current code, ->ndo_start_xmit() can be executed recursively only
10 times because of stack memory.
But, in the case of the vxlan, 10 recursion limit value results in
a stack overflow.
In the current code, the nested interface is limited by 8 depth.
There is no critical reason that the recursion limitation value should
be 10.
So, it would be good to be the same value with the limitation value of
nesting interface depth.

Test commands:
    ip link add vxlan10 type vxlan vni 10 dstport 4789 srcport 4789 4789
    ip link set vxlan10 up
    ip a a 192.168.10.1/24 dev vxlan10
    ip n a 192.168.10.2 dev vxlan10 lladdr fc:22:33:44:55:66 nud permanent

    for i in {9..0}
    do
        let A=$i+1
	ip link add vxlan$i type vxlan vni $i dstport 4789 srcport 4789 4789
	ip link set vxlan$i up
	ip a a 192.168.$i.1/24 dev vxlan$i
	ip n a 192.168.$i.2 dev vxlan$i lladdr fc:22:33:44:55:66 nud permanent
	bridge fdb add fc:22:33:44:55:66 dev vxlan$A dst 192.168.$i.2 self
    done
    hping3 192.168.10.2 -2 -d 60000

Splat looks like:
[  103.814237][ T1127] =============================================================================
[  103.871955][ T1127] BUG kmalloc-2k (Tainted: G    B            ): Padding overwritten. 0x00000000897a2e4f-0x000
[  103.873187][ T1127] -----------------------------------------------------------------------------
[  103.873187][ T1127]
[  103.874252][ T1127] INFO: Slab 0x000000005cccc724 objects=5 used=5 fp=0x0000000000000000 flags=0x10000000001020
[  103.881323][ T1127] CPU: 3 PID: 1127 Comm: hping3 Tainted: G    B             5.7.0+ #575
[  103.882131][ T1127] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  103.883006][ T1127] Call Trace:
[  103.883324][ T1127]  dump_stack+0x96/0xdb
[  103.883716][ T1127]  slab_err+0xad/0xd0
[  103.884106][ T1127]  ? _raw_spin_unlock+0x1f/0x30
[  103.884620][ T1127]  ? get_partial_node.isra.78+0x140/0x360
[  103.885214][ T1127]  slab_pad_check.part.53+0xf7/0x160
[  103.885769][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.886316][ T1127]  check_slab+0x97/0xb0
[  103.886763][ T1127]  alloc_debug_processing+0x84/0x1a0
[  103.887308][ T1127]  ___slab_alloc+0x5a5/0x630
[  103.887765][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.888265][ T1127]  ? lock_downgrade+0x730/0x730
[  103.888762][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.889244][ T1127]  ? __slab_alloc+0x3e/0x80
[  103.889675][ T1127]  __slab_alloc+0x3e/0x80
[  103.890108][ T1127]  __kmalloc_node_track_caller+0xc7/0x420
[ ... ]

Fixes: 11a766ce915f ("net: Increase xmit RECURSION_LIMIT to 10.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6fc613ed8eae..39e28e11863c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3157,7 +3157,7 @@ static inline int dev_recursion_level(void)
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
-#define XMIT_RECURSION_LIMIT	10
+#define XMIT_RECURSION_LIMIT	8
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-- 
cgit v1.2.3


From 91c7eaa686c3b7ae2d5b2aed22a45a02c8baa30e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 18 Jun 2020 11:42:53 +0200
Subject: USB: rename USB quirk to USB_QUIRK_ENDPOINT_IGNORE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The USB core has a quirk flag to ignore specific endpoints, so rename it
to be more obvious what this quirk does.

Cc: Johan Hovold <johan@kernel.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Richard Dodd <richard.o.dodd@gmail.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Jonathan Cox <jonathan@jdcox.net>
Cc: Bastien Nocera <hadess@hadess.net>
Cc: "Thiébaud Weksteen" <tweek@google.com>
Cc: Nishad Kamdar <nishadkamdar@gmail.com>
Link: https://lore.kernel.org/r/20200618094300.1887727-2-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/config.c  |  8 ++++----
 drivers/usb/core/quirks.c  | 18 +++++++++---------
 drivers/usb/core/usb.h     |  2 +-
 include/linux/usb/quirks.h |  4 ++--
 4 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b7918f695434..37442f423a41 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -298,10 +298,10 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno,
 		goto skip_to_next_endpoint_or_interface_descriptor;
 	}
 
-	/* Ignore blacklisted endpoints */
-	if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) {
-		if (usb_endpoint_is_blacklisted(udev, ifp, d)) {
-			dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n",
+	/* Ignore some endpoints */
+	if (udev->quirks & USB_QUIRK_ENDPOINT_IGNORE) {
+		if (usb_endpoint_is_ignored(udev, ifp, d)) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has an ignored endpoint with address 0x%X, skipping\n",
 					cfgno, inum, asnum,
 					d->bEndpointAddress);
 			goto skip_to_next_endpoint_or_interface_descriptor;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 3e8efe759c3e..20dccf34182d 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -359,7 +359,7 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	/* Sound Devices USBPre2 */
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
-			USB_QUIRK_ENDPOINT_BLACKLIST },
+			USB_QUIRK_ENDPOINT_IGNORE },
 
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
@@ -493,24 +493,24 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = {
 };
 
 /*
- * Entries for blacklisted endpoints that should be ignored when parsing
- * configuration descriptors.
+ * Entries for endpoints that should be ignored when parsing configuration
+ * descriptors.
  *
- * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST.
+ * Matched for devices with USB_QUIRK_ENDPOINT_IGNORE.
  */
-static const struct usb_device_id usb_endpoint_blacklist[] = {
+static const struct usb_device_id usb_endpoint_ignore[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
 	{ }
 };
 
-bool usb_endpoint_is_blacklisted(struct usb_device *udev,
-		struct usb_host_interface *intf,
-		struct usb_endpoint_descriptor *epd)
+bool usb_endpoint_is_ignored(struct usb_device *udev,
+			     struct usb_host_interface *intf,
+			     struct usb_endpoint_descriptor *epd)
 {
 	const struct usb_device_id *id;
 	unsigned int address;
 
-	for (id = usb_endpoint_blacklist; id->match_flags; ++id) {
+	for (id = usb_endpoint_ignore; id->match_flags; ++id) {
 		if (!usb_match_device(udev, id))
 			continue;
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 19e4c550bc73..98e7d1ee63dc 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -37,7 +37,7 @@ extern void usb_authorize_interface(struct usb_interface *);
 extern void usb_detect_quirks(struct usb_device *udev);
 extern void usb_detect_interface_quirks(struct usb_device *udev);
 extern void usb_release_quirk_list(void);
-extern bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+extern bool usb_endpoint_is_ignored(struct usb_device *udev,
 		struct usb_host_interface *intf,
 		struct usb_endpoint_descriptor *epd);
 extern int usb_remove_device(struct usb_device *udev);
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 22c1f579afe3..5e4c497f54d6 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -69,7 +69,7 @@
 /* Hub needs extra delay after resetting its port. */
 #define USB_QUIRK_HUB_SLOW_RESET		BIT(14)
 
-/* device has blacklisted endpoints */
-#define USB_QUIRK_ENDPOINT_BLACKLIST		BIT(15)
+/* device has endpoints that should be ignored */
+#define USB_QUIRK_ENDPOINT_IGNORE		BIT(15)
 
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 390fd0475af565d2fc31de98fcc84f3c2922e008 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 15 Jun 2020 09:58:15 +0200
Subject: i2c: remove deprecated i2c_new_device API

All in-tree users have been converted to the new i2c_new_client_device
function, so remove this deprecated one.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c | 25 -------------------------
 include/linux/i2c.h         |  8 +++-----
 2 files changed, 3 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index d1f278f73011..26f03a14a478 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -815,31 +815,6 @@ out_err_silent:
 }
 EXPORT_SYMBOL_GPL(i2c_new_client_device);
 
-/**
- * i2c_new_device - instantiate an i2c device
- * @adap: the adapter managing the device
- * @info: describes one I2C device; bus_num is ignored
- * Context: can sleep
- *
- * This deprecated function has the same functionality as
- * @i2c_new_client_device, it just returns NULL instead of an ERR_PTR in case of
- * an error for compatibility with current I2C API. It will be removed once all
- * users are converted.
- *
- * This returns the new i2c client, which may be saved for later use with
- * i2c_unregister_device(); or NULL to indicate an error.
- */
-struct i2c_client *
-i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
-{
-	struct i2c_client *ret;
-
-	ret = i2c_new_client_device(adap, info);
-	return IS_ERR(ret) ? NULL : ret;
-}
-EXPORT_SYMBOL_GPL(i2c_new_device);
-
-
 /**
  * i2c_unregister_device - reverse effect of i2c_new_*_device()
  * @client: value returned from i2c_new_*_device()
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index c10617bb980a..b8b8963f8bb9 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -408,7 +408,7 @@ static inline bool i2c_detect_slave_mode(struct device *dev) { return false; }
  * that are present.  This information is used to grow the driver model tree.
  * For mainboards this is done statically using i2c_register_board_info();
  * bus numbers identify adapters that aren't yet available.  For add-on boards,
- * i2c_new_device() does this dynamically with the adapter already known.
+ * i2c_new_client_device() does this dynamically with the adapter already known.
  */
 struct i2c_board_info {
 	char		type[I2C_NAME_SIZE];
@@ -439,13 +439,11 @@ struct i2c_board_info {
 
 
 #if IS_ENABLED(CONFIG_I2C)
-/* Add-on boards should register/unregister their devices; e.g. a board
+/*
+ * Add-on boards should register/unregister their devices; e.g. a board
  * with integrated I2C, a config eeprom, sensors, and a codec that's
  * used in conjunction with the primary hardware.
  */
-struct i2c_client *
-i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info);
-
 struct i2c_client *
 i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info);
 
-- 
cgit v1.2.3


From 5bf74682118b3003c8f9b0b0ec596e473fc6eb82 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Wed, 17 Jun 2020 18:46:35 +0200
Subject: Drivers: hv: vmbus: Remove the target_vp field from the vmbus_channel
 struct

The field is read only in __vmbus_open() and it is already stored twice
(after a call to hv_cpu_number_to_vp_number()) in target_cpu_store() and
init_vp_index(); there is no need to "cache" its value in the channel
data structure.

Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200617164642.37393-2-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c      |  3 ++-
 drivers/hv/channel_mgmt.c |  3 ---
 drivers/hv/vmbus_drv.c    |  2 --
 include/linux/hyperv.h    | 15 +++++++--------
 4 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 90070b337c10..8848d1548b3f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -18,6 +18,7 @@
 #include <linux/uio.h>
 #include <linux/interrupt.h>
 #include <asm/page.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -176,7 +177,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	open_msg->child_relid = newchannel->offermsg.child_relid;
 	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
 	open_msg->downstream_ringbuffer_pageoffset = newchannel->ringbuffer_send_offset;
-	open_msg->target_vp = newchannel->target_vp;
+	open_msg->target_vp = hv_cpu_number_to_vp_number(newchannel->target_cpu);
 
 	if (userdatalen)
 		memcpy(open_msg->userdata, userdata, userdatalen);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 417a95e5094d..278e39221807 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -704,8 +704,6 @@ static void init_vp_index(struct vmbus_channel *channel)
 		 */
 		channel->numa_node = cpu_to_node(VMBUS_CONNECT_CPU);
 		channel->target_cpu = VMBUS_CONNECT_CPU;
-		channel->target_vp =
-			hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 		if (perf_chn)
 			hv_set_alloced_cpu(VMBUS_CONNECT_CPU);
 		return;
@@ -739,7 +737,6 @@ static void init_vp_index(struct vmbus_channel *channel)
 	cpumask_set_cpu(target_cpu, alloced_mask);
 
 	channel->target_cpu = target_cpu;
-	channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);
 
 	free_cpumask_var(available_mask);
 }
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 9147ee9d5f7d..d2ddb46f1359 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -23,7 +23,6 @@
 #include <linux/cpu.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm/mshyperv.h>
 #include <linux/delay.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
@@ -1779,7 +1778,6 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	 */
 
 	channel->target_cpu = target_cpu;
-	channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);
 	channel->numa_node = cpu_to_node(target_cpu);
 
 	/* See init_vp_index(). */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 40df3103e890..738efdb194b0 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -803,15 +803,14 @@ struct vmbus_channel {
 	u64 sig_event;
 
 	/*
-	 * Starting with win8, this field will be used to specify
-	 * the target virtual processor on which to deliver the interrupt for
-	 * the host to guest communication.
-	 * Prior to win8, incoming channel interrupts would only
-	 * be delivered on cpu 0. Setting this value to 0 would
-	 * preserve the earlier behavior.
+	 * Starting with win8, this field will be used to specify the
+	 * target CPU on which to deliver the interrupt for the host
+	 * to guest communication.
+	 *
+	 * Prior to win8, incoming channel interrupts would only be
+	 * delivered on CPU 0. Setting this value to 0 would preserve
+	 * the earlier behavior.
 	 */
-	u32 target_vp;
-	/* The corresponding CPUID in the guest */
 	u32 target_cpu;
 	int numa_node;
 	/*
-- 
cgit v1.2.3


From 458d090fbad59d1f849ee15e78d0471784d428b6 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Wed, 17 Jun 2020 18:46:36 +0200
Subject: Drivers: hv: vmbus: Remove the numa_node field from the vmbus_channel
 struct

The field is read only in numa_node_show() and it is already stored twice
(after a call to cpu_to_node()) in target_cpu_store() and init_vp_index();
there is no need to "cache" its value in the channel data structure.

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200617164642.37393-3-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel_mgmt.c | 2 --
 drivers/hv/vmbus_drv.c    | 3 +--
 include/linux/hyperv.h    | 1 -
 3 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 278e39221807..36dd8b6c544a 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -702,7 +702,6 @@ static void init_vp_index(struct vmbus_channel *channel)
 		 * In case alloc_cpumask_var() fails, bind it to
 		 * VMBUS_CONNECT_CPU.
 		 */
-		channel->numa_node = cpu_to_node(VMBUS_CONNECT_CPU);
 		channel->target_cpu = VMBUS_CONNECT_CPU;
 		if (perf_chn)
 			hv_set_alloced_cpu(VMBUS_CONNECT_CPU);
@@ -719,7 +718,6 @@ static void init_vp_index(struct vmbus_channel *channel)
 			continue;
 		break;
 	}
-	channel->numa_node = numa_node;
 	alloced_mask = &hv_context.hv_numa_map[numa_node];
 
 	if (cpumask_weight(alloced_mask) ==
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index d2ddb46f1359..de44d76c8ace 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -226,7 +226,7 @@ static ssize_t numa_node_show(struct device *dev,
 	if (!hv_dev->channel)
 		return -ENODEV;
 
-	return sprintf(buf, "%d\n", hv_dev->channel->numa_node);
+	return sprintf(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu));
 }
 static DEVICE_ATTR_RO(numa_node);
 #endif
@@ -1778,7 +1778,6 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	 */
 
 	channel->target_cpu = target_cpu;
-	channel->numa_node = cpu_to_node(target_cpu);
 
 	/* See init_vp_index(). */
 	if (hv_is_perf_channel(channel))
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 738efdb194b0..690394b79d72 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -812,7 +812,6 @@ struct vmbus_channel {
 	 * the earlier behavior.
 	 */
 	u32 target_cpu;
-	int numa_node;
 	/*
 	 * Support for sub-channels. For high performance devices,
 	 * it will be useful to have multiple sub-channels to support
-- 
cgit v1.2.3


From e32b16c31339e37d3cdc814f2773b74c1dbf660c Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Thu, 28 May 2020 04:36:03 -0700
Subject: platform/chrome: cros_ec: Update mux state bits

Sync the EC_CMD_USB_PD_MUX_INFO mux state bit fields with the Chrome EC
code base. The newly added bit fields will be used for cros-ec-typec mux
control.

Signed-off-by: Prashant Malani <pmalani@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
---
 include/linux/platform_data/cros_ec_commands.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 69210881ebac..a7b0fc440c35 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -5207,11 +5207,15 @@ struct ec_params_usb_pd_mux_info {
 } __ec_align1;
 
 /* Flags representing mux state */
-#define USB_PD_MUX_USB_ENABLED       BIT(0) /* USB connected */
-#define USB_PD_MUX_DP_ENABLED        BIT(1) /* DP connected */
-#define USB_PD_MUX_POLARITY_INVERTED BIT(2) /* CC line Polarity inverted */
-#define USB_PD_MUX_HPD_IRQ           BIT(3) /* HPD IRQ is asserted */
-#define USB_PD_MUX_HPD_LVL           BIT(4) /* HPD level is asserted */
+#define USB_PD_MUX_NONE               0      /* Open switch */
+#define USB_PD_MUX_USB_ENABLED        BIT(0) /* USB connected */
+#define USB_PD_MUX_DP_ENABLED         BIT(1) /* DP connected */
+#define USB_PD_MUX_POLARITY_INVERTED  BIT(2) /* CC line Polarity inverted */
+#define USB_PD_MUX_HPD_IRQ            BIT(3) /* HPD IRQ is asserted */
+#define USB_PD_MUX_HPD_LVL            BIT(4) /* HPD level is asserted */
+#define USB_PD_MUX_SAFE_MODE          BIT(5) /* DP is in safe mode */
+#define USB_PD_MUX_TBT_COMPAT_ENABLED BIT(6) /* TBT compat enabled */
+#define USB_PD_MUX_USB4_ENABLED       BIT(7) /* USB4 enabled */
 
 struct ec_response_usb_pd_mux_info {
 	uint8_t flags; /* USB_PD_MUX_*-encoded USB mux state */
-- 
cgit v1.2.3


From 8e2a46a40fa76570e535e5baa2d351510b6e61fa Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 15 Jun 2020 08:50:25 +0200
Subject: docs: move remaining stuff under Documentation/*.txt to
 Documentation/staging

There are several files that I was unable to find a proper place
for them, and 3 ones that are still in plain old text format.

Let's place those stuff behind the carpet, as we'd like to keep the
root directory clean.

We can later discuss and move those into better places.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/11bd0d75e65a874f7c276a0aeab0fe13f3376f5f.1592203650.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/crc32.txt               | 189 --------
 Documentation/index.rst               |  13 +
 Documentation/kprobes.txt             | 801 ----------------------------------
 Documentation/lzo.txt                 | 202 ---------
 Documentation/remoteproc.txt          | 359 ---------------
 Documentation/rpmsg.txt               | 341 ---------------
 Documentation/speculation.txt         |  90 ----
 Documentation/staging/crc32.rst       | 189 ++++++++
 Documentation/staging/index.rst       |  32 ++
 Documentation/staging/kprobes.rst     | 801 ++++++++++++++++++++++++++++++++++
 Documentation/staging/lzo.rst         | 202 +++++++++
 Documentation/staging/remoteproc.rst  | 359 +++++++++++++++
 Documentation/staging/rpmsg.rst       | 341 +++++++++++++++
 Documentation/staging/speculation.rst |  92 ++++
 Documentation/staging/static-keys.rst | 331 ++++++++++++++
 Documentation/staging/tee.rst         | 277 ++++++++++++
 Documentation/staging/xz.rst          | 127 ++++++
 Documentation/static-keys.txt         | 331 --------------
 Documentation/tee.txt                 | 276 ------------
 Documentation/trace/kprobetrace.rst   |   2 +-
 Documentation/xz.txt                  | 127 ------
 MAINTAINERS                           |   8 +-
 include/linux/jump_label.h            |   2 +-
 lib/crc32.c                           |   2 +-
 lib/lzo/lzo1x_decompress_safe.c       |   2 +-
 lib/xz/Kconfig                        |   2 +-
 samples/kprobes/kprobe_example.c      |   2 +-
 samples/kprobes/kretprobe_example.c   |   2 +-
 28 files changed, 2775 insertions(+), 2727 deletions(-)
 delete mode 100644 Documentation/crc32.txt
 delete mode 100644 Documentation/kprobes.txt
 delete mode 100644 Documentation/lzo.txt
 delete mode 100644 Documentation/remoteproc.txt
 delete mode 100644 Documentation/rpmsg.txt
 delete mode 100644 Documentation/speculation.txt
 create mode 100644 Documentation/staging/crc32.rst
 create mode 100644 Documentation/staging/index.rst
 create mode 100644 Documentation/staging/kprobes.rst
 create mode 100644 Documentation/staging/lzo.rst
 create mode 100644 Documentation/staging/remoteproc.rst
 create mode 100644 Documentation/staging/rpmsg.rst
 create mode 100644 Documentation/staging/speculation.rst
 create mode 100644 Documentation/staging/static-keys.rst
 create mode 100644 Documentation/staging/tee.rst
 create mode 100644 Documentation/staging/xz.rst
 delete mode 100644 Documentation/static-keys.txt
 delete mode 100644 Documentation/tee.txt
 delete mode 100644 Documentation/xz.txt

(limited to 'include/linux')

diff --git a/Documentation/crc32.txt b/Documentation/crc32.txt
deleted file mode 100644
index 8a6860f33b4e..000000000000
--- a/Documentation/crc32.txt
+++ /dev/null
@@ -1,189 +0,0 @@
-=================================
-brief tutorial on CRC computation
-=================================
-
-A CRC is a long-division remainder.  You add the CRC to the message,
-and the whole thing (message+CRC) is a multiple of the given
-CRC polynomial.  To check the CRC, you can either check that the
-CRC matches the recomputed value, *or* you can check that the
-remainder computed on the message+CRC is 0.  This latter approach
-is used by a lot of hardware implementations, and is why so many
-protocols put the end-of-frame flag after the CRC.
-
-It's actually the same long division you learned in school, except that:
-
-- We're working in binary, so the digits are only 0 and 1, and
-- When dividing polynomials, there are no carries.  Rather than add and
-  subtract, we just xor.  Thus, we tend to get a bit sloppy about
-  the difference between adding and subtracting.
-
-Like all division, the remainder is always smaller than the divisor.
-To produce a 32-bit CRC, the divisor is actually a 33-bit CRC polynomial.
-Since it's 33 bits long, bit 32 is always going to be set, so usually the
-CRC is written in hex with the most significant bit omitted.  (If you're
-familiar with the IEEE 754 floating-point format, it's the same idea.)
-
-Note that a CRC is computed over a string of *bits*, so you have
-to decide on the endianness of the bits within each byte.  To get
-the best error-detecting properties, this should correspond to the
-order they're actually sent.  For example, standard RS-232 serial is
-little-endian; the most significant bit (sometimes used for parity)
-is sent last.  And when appending a CRC word to a message, you should
-do it in the right order, matching the endianness.
-
-Just like with ordinary division, you proceed one digit (bit) at a time.
-Each step of the division you take one more digit (bit) of the dividend
-and append it to the current remainder.  Then you figure out the
-appropriate multiple of the divisor to subtract to being the remainder
-back into range.  In binary, this is easy - it has to be either 0 or 1,
-and to make the XOR cancel, it's just a copy of bit 32 of the remainder.
-
-When computing a CRC, we don't care about the quotient, so we can
-throw the quotient bit away, but subtract the appropriate multiple of
-the polynomial from the remainder and we're back to where we started,
-ready to process the next bit.
-
-A big-endian CRC written this way would be coded like::
-
-	for (i = 0; i < input_bits; i++) {
-		multiple = remainder & 0x80000000 ? CRCPOLY : 0;
-		remainder = (remainder << 1 | next_input_bit()) ^ multiple;
-	}
-
-Notice how, to get at bit 32 of the shifted remainder, we look
-at bit 31 of the remainder *before* shifting it.
-
-But also notice how the next_input_bit() bits we're shifting into
-the remainder don't actually affect any decision-making until
-32 bits later.  Thus, the first 32 cycles of this are pretty boring.
-Also, to add the CRC to a message, we need a 32-bit-long hole for it at
-the end, so we have to add 32 extra cycles shifting in zeros at the
-end of every message.
-
-These details lead to a standard trick: rearrange merging in the
-next_input_bit() until the moment it's needed.  Then the first 32 cycles
-can be precomputed, and merging in the final 32 zero bits to make room
-for the CRC can be skipped entirely.  This changes the code to::
-
-	for (i = 0; i < input_bits; i++) {
-		remainder ^= next_input_bit() << 31;
-		multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
-		remainder = (remainder << 1) ^ multiple;
-	}
-
-With this optimization, the little-endian code is particularly simple::
-
-	for (i = 0; i < input_bits; i++) {
-		remainder ^= next_input_bit();
-		multiple = (remainder & 1) ? CRCPOLY : 0;
-		remainder = (remainder >> 1) ^ multiple;
-	}
-
-The most significant coefficient of the remainder polynomial is stored
-in the least significant bit of the binary "remainder" variable.
-The other details of endianness have been hidden in CRCPOLY (which must
-be bit-reversed) and next_input_bit().
-
-As long as next_input_bit is returning the bits in a sensible order, we don't
-*have* to wait until the last possible moment to merge in additional bits.
-We can do it 8 bits at a time rather than 1 bit at a time::
-
-	for (i = 0; i < input_bytes; i++) {
-		remainder ^= next_input_byte() << 24;
-		for (j = 0; j < 8; j++) {
-			multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
-			remainder = (remainder << 1) ^ multiple;
-		}
-	}
-
-Or in little-endian::
-
-	for (i = 0; i < input_bytes; i++) {
-		remainder ^= next_input_byte();
-		for (j = 0; j < 8; j++) {
-			multiple = (remainder & 1) ? CRCPOLY : 0;
-			remainder = (remainder >> 1) ^ multiple;
-		}
-	}
-
-If the input is a multiple of 32 bits, you can even XOR in a 32-bit
-word at a time and increase the inner loop count to 32.
-
-You can also mix and match the two loop styles, for example doing the
-bulk of a message byte-at-a-time and adding bit-at-a-time processing
-for any fractional bytes at the end.
-
-To reduce the number of conditional branches, software commonly uses
-the byte-at-a-time table method, popularized by Dilip V. Sarwate,
-"Computation of Cyclic Redundancy Checks via Table Look-Up", Comm. ACM
-v.31 no.8 (August 1998) p. 1008-1013.
-
-Here, rather than just shifting one bit of the remainder to decide
-in the correct multiple to subtract, we can shift a byte at a time.
-This produces a 40-bit (rather than a 33-bit) intermediate remainder,
-and the correct multiple of the polynomial to subtract is found using
-a 256-entry lookup table indexed by the high 8 bits.
-
-(The table entries are simply the CRC-32 of the given one-byte messages.)
-
-When space is more constrained, smaller tables can be used, e.g. two
-4-bit shifts followed by a lookup in a 16-entry table.
-
-It is not practical to process much more than 8 bits at a time using this
-technique, because tables larger than 256 entries use too much memory and,
-more importantly, too much of the L1 cache.
-
-To get higher software performance, a "slicing" technique can be used.
-See "High Octane CRC Generation with the Intel Slicing-by-8 Algorithm",
-ftp://download.intel.com/technology/comms/perfnet/download/slicing-by-8.pdf
-
-This does not change the number of table lookups, but does increase
-the parallelism.  With the classic Sarwate algorithm, each table lookup
-must be completed before the index of the next can be computed.
-
-A "slicing by 2" technique would shift the remainder 16 bits at a time,
-producing a 48-bit intermediate remainder.  Rather than doing a single
-lookup in a 65536-entry table, the two high bytes are looked up in
-two different 256-entry tables.  Each contains the remainder required
-to cancel out the corresponding byte.  The tables are different because the
-polynomials to cancel are different.  One has non-zero coefficients from
-x^32 to x^39, while the other goes from x^40 to x^47.
-
-Since modern processors can handle many parallel memory operations, this
-takes barely longer than a single table look-up and thus performs almost
-twice as fast as the basic Sarwate algorithm.
-
-This can be extended to "slicing by 4" using 4 256-entry tables.
-Each step, 32 bits of data is fetched, XORed with the CRC, and the result
-broken into bytes and looked up in the tables.  Because the 32-bit shift
-leaves the low-order bits of the intermediate remainder zero, the
-final CRC is simply the XOR of the 4 table look-ups.
-
-But this still enforces sequential execution: a second group of table
-look-ups cannot begin until the previous groups 4 table look-ups have all
-been completed.  Thus, the processor's load/store unit is sometimes idle.
-
-To make maximum use of the processor, "slicing by 8" performs 8 look-ups
-in parallel.  Each step, the 32-bit CRC is shifted 64 bits and XORed
-with 64 bits of input data.  What is important to note is that 4 of
-those 8 bytes are simply copies of the input data; they do not depend
-on the previous CRC at all.  Thus, those 4 table look-ups may commence
-immediately, without waiting for the previous loop iteration.
-
-By always having 4 loads in flight, a modern superscalar processor can
-be kept busy and make full use of its L1 cache.
-
-Two more details about CRC implementation in the real world:
-
-Normally, appending zero bits to a message which is already a multiple
-of a polynomial produces a larger multiple of that polynomial.  Thus,
-a basic CRC will not detect appended zero bits (or bytes).  To enable
-a CRC to detect this condition, it's common to invert the CRC before
-appending it.  This makes the remainder of the message+crc come out not
-as zero, but some fixed non-zero value.  (The CRC of the inversion
-pattern, 0xffffffff.)
-
-The same problem applies to zero bits prepended to the message, and a
-similar solution is used.  Instead of starting the CRC computation with
-a remainder of 0, an initial remainder of all ones is used.  As long as
-you start the same way on decoding, it doesn't make a difference.
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 71eca3171574..3b491af0122d 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -182,6 +182,19 @@ subprojects.
 
    filesystems/ext4/index
 
+Other documentation
+-------------------
+
+There are several unsorted documents that don't seem to fit on other parts
+of the documentation body, or may require some adjustments and/or conversion
+to ReStructured Text format, or are simply too old.
+
+.. toctree::
+   :maxdepth: 2
+
+   staging/index
+
+
 Translations
 ------------
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
deleted file mode 100644
index 8baab8832c5b..000000000000
--- a/Documentation/kprobes.txt
+++ /dev/null
@@ -1,801 +0,0 @@
-=======================
-Kernel Probes (Kprobes)
-=======================
-
-:Author: Jim Keniston <jkenisto@us.ibm.com>
-:Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
-:Author: Masami Hiramatsu <mhiramat@redhat.com>
-
-.. CONTENTS
-
-  1. Concepts: Kprobes, and Return Probes
-  2. Architectures Supported
-  3. Configuring Kprobes
-  4. API Reference
-  5. Kprobes Features and Limitations
-  6. Probe Overhead
-  7. TODO
-  8. Kprobes Example
-  9. Kretprobes Example
-  10. Deprecated Features
-  Appendix A: The kprobes debugfs interface
-  Appendix B: The kprobes sysctl interface
-
-Concepts: Kprobes and Return Probes
-=========================================
-
-Kprobes enables you to dynamically break into any kernel routine and
-collect debugging and performance information non-disruptively. You
-can trap at almost any kernel code address [1]_, specifying a handler
-routine to be invoked when the breakpoint is hit.
-
-.. [1] some parts of the kernel code can not be trapped, see
-       :ref:`kprobes_blacklist`)
-
-There are currently two types of probes: kprobes, and kretprobes
-(also called return probes).  A kprobe can be inserted on virtually
-any instruction in the kernel.  A return probe fires when a specified
-function returns.
-
-In the typical case, Kprobes-based instrumentation is packaged as
-a kernel module.  The module's init function installs ("registers")
-one or more probes, and the exit function unregisters them.  A
-registration function such as register_kprobe() specifies where
-the probe is to be inserted and what handler is to be called when
-the probe is hit.
-
-There are also ``register_/unregister_*probes()`` functions for batch
-registration/unregistration of a group of ``*probes``. These functions
-can speed up unregistration process when you have to unregister
-a lot of probes at once.
-
-The next four subsections explain how the different types of
-probes work and how jump optimization works.  They explain certain
-things that you'll need to know in order to make the best use of
-Kprobes -- e.g., the difference between a pre_handler and
-a post_handler, and how to use the maxactive and nmissed fields of
-a kretprobe.  But if you're in a hurry to start using Kprobes, you
-can skip ahead to :ref:`kprobes_archs_supported`.
-
-How Does a Kprobe Work?
------------------------
-
-When a kprobe is registered, Kprobes makes a copy of the probed
-instruction and replaces the first byte(s) of the probed instruction
-with a breakpoint instruction (e.g., int3 on i386 and x86_64).
-
-When a CPU hits the breakpoint instruction, a trap occurs, the CPU's
-registers are saved, and control passes to Kprobes via the
-notifier_call_chain mechanism.  Kprobes executes the "pre_handler"
-associated with the kprobe, passing the handler the addresses of the
-kprobe struct and the saved registers.
-
-Next, Kprobes single-steps its copy of the probed instruction.
-(It would be simpler to single-step the actual instruction in place,
-but then Kprobes would have to temporarily remove the breakpoint
-instruction.  This would open a small time window when another CPU
-could sail right past the probepoint.)
-
-After the instruction is single-stepped, Kprobes executes the
-"post_handler," if any, that is associated with the kprobe.
-Execution then continues with the instruction following the probepoint.
-
-Changing Execution Path
------------------------
-
-Since kprobes can probe into a running kernel code, it can change the
-register set, including instruction pointer. This operation requires
-maximum care, such as keeping the stack frame, recovering the execution
-path etc. Since it operates on a running kernel and needs deep knowledge
-of computer architecture and concurrent computing, you can easily shoot
-your foot.
-
-If you change the instruction pointer (and set up other related
-registers) in pre_handler, you must return !0 so that kprobes stops
-single stepping and just returns to the given address.
-This also means post_handler should not be called anymore.
-
-Note that this operation may be harder on some architectures which use
-TOC (Table of Contents) for function call, since you have to setup a new
-TOC for your function in your module, and recover the old one after
-returning from it.
-
-Return Probes
--------------
-
-How Does a Return Probe Work?
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-When you call register_kretprobe(), Kprobes establishes a kprobe at
-the entry to the function.  When the probed function is called and this
-probe is hit, Kprobes saves a copy of the return address, and replaces
-the return address with the address of a "trampoline."  The trampoline
-is an arbitrary piece of code -- typically just a nop instruction.
-At boot time, Kprobes registers a kprobe at the trampoline.
-
-When the probed function executes its return instruction, control
-passes to the trampoline and that probe is hit.  Kprobes' trampoline
-handler calls the user-specified return handler associated with the
-kretprobe, then sets the saved instruction pointer to the saved return
-address, and that's where execution resumes upon return from the trap.
-
-While the probed function is executing, its return address is
-stored in an object of type kretprobe_instance.  Before calling
-register_kretprobe(), the user sets the maxactive field of the
-kretprobe struct to specify how many instances of the specified
-function can be probed simultaneously.  register_kretprobe()
-pre-allocates the indicated number of kretprobe_instance objects.
-
-For example, if the function is non-recursive and is called with a
-spinlock held, maxactive = 1 should be enough.  If the function is
-non-recursive and can never relinquish the CPU (e.g., via a semaphore
-or preemption), NR_CPUS should be enough.  If maxactive <= 0, it is
-set to a default value.  If CONFIG_PREEMPT is enabled, the default
-is max(10, 2*NR_CPUS).  Otherwise, the default is NR_CPUS.
-
-It's not a disaster if you set maxactive too low; you'll just miss
-some probes.  In the kretprobe struct, the nmissed field is set to
-zero when the return probe is registered, and is incremented every
-time the probed function is entered but there is no kretprobe_instance
-object available for establishing the return probe.
-
-Kretprobe entry-handler
-^^^^^^^^^^^^^^^^^^^^^^^
-
-Kretprobes also provides an optional user-specified handler which runs
-on function entry. This handler is specified by setting the entry_handler
-field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the
-function entry is hit, the user-defined entry_handler, if any, is invoked.
-If the entry_handler returns 0 (success) then a corresponding return handler
-is guaranteed to be called upon function return. If the entry_handler
-returns a non-zero error then Kprobes leaves the return address as is, and
-the kretprobe has no further effect for that particular function instance.
-
-Multiple entry and return handler invocations are matched using the unique
-kretprobe_instance object associated with them. Additionally, a user
-may also specify per return-instance private data to be part of each
-kretprobe_instance object. This is especially useful when sharing private
-data between corresponding user entry and return handlers. The size of each
-private data object can be specified at kretprobe registration time by
-setting the data_size field of the kretprobe struct. This data can be
-accessed through the data field of each kretprobe_instance object.
-
-In case probed function is entered but there is no kretprobe_instance
-object available, then in addition to incrementing the nmissed count,
-the user entry_handler invocation is also skipped.
-
-.. _kprobes_jump_optimization:
-
-How Does Jump Optimization Work?
---------------------------------
-
-If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
-is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
-the "debug.kprobes_optimization" kernel parameter is set to 1 (see
-sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
-instruction instead of a breakpoint instruction at each probepoint.
-
-Init a Kprobe
-^^^^^^^^^^^^^
-
-When a probe is registered, before attempting this optimization,
-Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
-address. So, even if it's not possible to optimize this particular
-probepoint, there'll be a probe there.
-
-Safety Check
-^^^^^^^^^^^^
-
-Before optimizing a probe, Kprobes performs the following safety checks:
-
-- Kprobes verifies that the region that will be replaced by the jump
-  instruction (the "optimized region") lies entirely within one function.
-  (A jump instruction is multiple bytes, and so may overlay multiple
-  instructions.)
-
-- Kprobes analyzes the entire function and verifies that there is no
-  jump into the optimized region.  Specifically:
-
-  - the function contains no indirect jump;
-  - the function contains no instruction that causes an exception (since
-    the fixup code triggered by the exception could jump back into the
-    optimized region -- Kprobes checks the exception tables to verify this);
-  - there is no near jump to the optimized region (other than to the first
-    byte).
-
-- For each instruction in the optimized region, Kprobes verifies that
-  the instruction can be executed out of line.
-
-Preparing Detour Buffer
-^^^^^^^^^^^^^^^^^^^^^^^
-
-Next, Kprobes prepares a "detour" buffer, which contains the following
-instruction sequence:
-
-- code to push the CPU's registers (emulating a breakpoint trap)
-- a call to the trampoline code which calls user's probe handlers.
-- code to restore registers
-- the instructions from the optimized region
-- a jump back to the original execution path.
-
-Pre-optimization
-^^^^^^^^^^^^^^^^
-
-After preparing the detour buffer, Kprobes verifies that none of the
-following situations exist:
-
-- The probe has a post_handler.
-- Other instructions in the optimized region are probed.
-- The probe is disabled.
-
-In any of the above cases, Kprobes won't start optimizing the probe.
-Since these are temporary situations, Kprobes tries to start
-optimizing it again if the situation is changed.
-
-If the kprobe can be optimized, Kprobes enqueues the kprobe to an
-optimizing list, and kicks the kprobe-optimizer workqueue to optimize
-it.  If the to-be-optimized probepoint is hit before being optimized,
-Kprobes returns control to the original instruction path by setting
-the CPU's instruction pointer to the copied code in the detour buffer
--- thus at least avoiding the single-step.
-
-Optimization
-^^^^^^^^^^^^
-
-The Kprobe-optimizer doesn't insert the jump instruction immediately;
-rather, it calls synchronize_rcu() for safety first, because it's
-possible for a CPU to be interrupted in the middle of executing the
-optimized region [3]_.  As you know, synchronize_rcu() can ensure
-that all interruptions that were active when synchronize_rcu()
-was called are done, but only if CONFIG_PREEMPT=n.  So, this version
-of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
-
-After that, the Kprobe-optimizer calls stop_machine() to replace
-the optimized region with a jump instruction to the detour buffer,
-using text_poke_smp().
-
-Unoptimization
-^^^^^^^^^^^^^^
-
-When an optimized kprobe is unregistered, disabled, or blocked by
-another kprobe, it will be unoptimized.  If this happens before
-the optimization is complete, the kprobe is just dequeued from the
-optimized list.  If the optimization has been done, the jump is
-replaced with the original code (except for an int3 breakpoint in
-the first byte) by using text_poke_smp().
-
-.. [3] Please imagine that the 2nd instruction is interrupted and then
-   the optimizer replaces the 2nd instruction with the jump *address*
-   while the interrupt handler is running. When the interrupt
-   returns to original address, there is no valid instruction,
-   and it causes an unexpected result.
-
-.. [4] This optimization-safety checking may be replaced with the
-   stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
-   kernel.
-
-NOTE for geeks:
-The jump optimization changes the kprobe's pre_handler behavior.
-Without optimization, the pre_handler can change the kernel's execution
-path by changing regs->ip and returning 1.  However, when the probe
-is optimized, that modification is ignored.  Thus, if you want to
-tweak the kernel's execution path, you need to suppress optimization,
-using one of the following techniques:
-
-- Specify an empty function for the kprobe's post_handler.
-
-or
-
-- Execute 'sysctl -w debug.kprobes_optimization=n'
-
-.. _kprobes_blacklist:
-
-Blacklist
----------
-
-Kprobes can probe most of the kernel except itself. This means
-that there are some functions where kprobes cannot probe. Probing
-(trapping) such functions can cause a recursive trap (e.g. double
-fault) or the nested probe handler may never be called.
-Kprobes manages such functions as a blacklist.
-If you want to add a function into the blacklist, you just need
-to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro
-to specify a blacklisted function.
-Kprobes checks the given probe address against the blacklist and
-rejects registering it, if the given address is in the blacklist.
-
-.. _kprobes_archs_supported:
-
-Architectures Supported
-=======================
-
-Kprobes and return probes are implemented on the following
-architectures:
-
-- i386 (Supports jump optimization)
-- x86_64 (AMD-64, EM64T) (Supports jump optimization)
-- ppc64
-- ia64 (Does not support probes on instruction slot1.)
-- sparc64 (Return probes not yet implemented.)
-- arm
-- ppc
-- mips
-- s390
-- parisc
-
-Configuring Kprobes
-===================
-
-When configuring the kernel using make menuconfig/xconfig/oldconfig,
-ensure that CONFIG_KPROBES is set to "y". Under "General setup", look
-for "Kprobes".
-
-So that you can load and unload Kprobes-based instrumentation modules,
-make sure "Loadable module support" (CONFIG_MODULES) and "Module
-unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
-
-Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL
-are set to "y", since kallsyms_lookup_name() is used by the in-kernel
-kprobe address resolution code.
-
-If you need to insert a probe in the middle of a function, you may find
-it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
-so you can use "objdump -d -l vmlinux" to see the source-to-object
-code mapping.
-
-API Reference
-=============
-
-The Kprobes API includes a "register" function and an "unregister"
-function for each type of probe. The API also includes "register_*probes"
-and "unregister_*probes" functions for (un)registering arrays of probes.
-Here are terse, mini-man-page specifications for these functions and
-the associated probe handlers that you'll write. See the files in the
-samples/kprobes/ sub-directory for examples.
-
-register_kprobe
----------------
-
-::
-
-	#include <linux/kprobes.h>
-	int register_kprobe(struct kprobe *kp);
-
-Sets a breakpoint at the address kp->addr.  When the breakpoint is
-hit, Kprobes calls kp->pre_handler.  After the probed instruction
-is single-stepped, Kprobe calls kp->post_handler.  If a fault
-occurs during execution of kp->pre_handler or kp->post_handler,
-or during single-stepping of the probed instruction, Kprobes calls
-kp->fault_handler.  Any or all handlers can be NULL. If kp->flags
-is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
-so, its handlers aren't hit until calling enable_kprobe(kp).
-
-.. note::
-
-   1. With the introduction of the "symbol_name" field to struct kprobe,
-      the probepoint address resolution will now be taken care of by the kernel.
-      The following will now work::
-
-	kp.symbol_name = "symbol_name";
-
-      (64-bit powerpc intricacies such as function descriptors are handled
-      transparently)
-
-   2. Use the "offset" field of struct kprobe if the offset into the symbol
-      to install a probepoint is known. This field is used to calculate the
-      probepoint.
-
-   3. Specify either the kprobe "symbol_name" OR the "addr". If both are
-      specified, kprobe registration will fail with -EINVAL.
-
-   4. With CISC architectures (such as i386 and x86_64), the kprobes code
-      does not validate if the kprobe.addr is at an instruction boundary.
-      Use "offset" with caution.
-
-register_kprobe() returns 0 on success, or a negative errno otherwise.
-
-User's pre-handler (kp->pre_handler)::
-
-	#include <linux/kprobes.h>
-	#include <linux/ptrace.h>
-	int pre_handler(struct kprobe *p, struct pt_regs *regs);
-
-Called with p pointing to the kprobe associated with the breakpoint,
-and regs pointing to the struct containing the registers saved when
-the breakpoint was hit.  Return 0 here unless you're a Kprobes geek.
-
-User's post-handler (kp->post_handler)::
-
-	#include <linux/kprobes.h>
-	#include <linux/ptrace.h>
-	void post_handler(struct kprobe *p, struct pt_regs *regs,
-			  unsigned long flags);
-
-p and regs are as described for the pre_handler.  flags always seems
-to be zero.
-
-User's fault-handler (kp->fault_handler)::
-
-	#include <linux/kprobes.h>
-	#include <linux/ptrace.h>
-	int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
-
-p and regs are as described for the pre_handler.  trapnr is the
-architecture-specific trap number associated with the fault (e.g.,
-on i386, 13 for a general protection fault or 14 for a page fault).
-Returns 1 if it successfully handled the exception.
-
-register_kretprobe
-------------------
-
-::
-
-	#include <linux/kprobes.h>
-	int register_kretprobe(struct kretprobe *rp);
-
-Establishes a return probe for the function whose address is
-rp->kp.addr.  When that function returns, Kprobes calls rp->handler.
-You must set rp->maxactive appropriately before you call
-register_kretprobe(); see "How Does a Return Probe Work?" for details.
-
-register_kretprobe() returns 0 on success, or a negative errno
-otherwise.
-
-User's return-probe handler (rp->handler)::
-
-	#include <linux/kprobes.h>
-	#include <linux/ptrace.h>
-	int kretprobe_handler(struct kretprobe_instance *ri,
-			      struct pt_regs *regs);
-
-regs is as described for kprobe.pre_handler.  ri points to the
-kretprobe_instance object, of which the following fields may be
-of interest:
-
-- ret_addr: the return address
-- rp: points to the corresponding kretprobe object
-- task: points to the corresponding task struct
-- data: points to per return-instance private data; see "Kretprobe
-	entry-handler" for details.
-
-The regs_return_value(regs) macro provides a simple abstraction to
-extract the return value from the appropriate register as defined by
-the architecture's ABI.
-
-The handler's return value is currently ignored.
-
-unregister_*probe
-------------------
-
-::
-
-	#include <linux/kprobes.h>
-	void unregister_kprobe(struct kprobe *kp);
-	void unregister_kretprobe(struct kretprobe *rp);
-
-Removes the specified probe.  The unregister function can be called
-at any time after the probe has been registered.
-
-.. note::
-
-   If the functions find an incorrect probe (ex. an unregistered probe),
-   they clear the addr field of the probe.
-
-register_*probes
-----------------
-
-::
-
-	#include <linux/kprobes.h>
-	int register_kprobes(struct kprobe **kps, int num);
-	int register_kretprobes(struct kretprobe **rps, int num);
-
-Registers each of the num probes in the specified array.  If any
-error occurs during registration, all probes in the array, up to
-the bad probe, are safely unregistered before the register_*probes
-function returns.
-
-- kps/rps: an array of pointers to ``*probe`` data structures
-- num: the number of the array entries.
-
-.. note::
-
-   You have to allocate(or define) an array of pointers and set all
-   of the array entries before using these functions.
-
-unregister_*probes
-------------------
-
-::
-
-	#include <linux/kprobes.h>
-	void unregister_kprobes(struct kprobe **kps, int num);
-	void unregister_kretprobes(struct kretprobe **rps, int num);
-
-Removes each of the num probes in the specified array at once.
-
-.. note::
-
-   If the functions find some incorrect probes (ex. unregistered
-   probes) in the specified array, they clear the addr field of those
-   incorrect probes. However, other probes in the array are
-   unregistered correctly.
-
-disable_*probe
---------------
-
-::
-
-	#include <linux/kprobes.h>
-	int disable_kprobe(struct kprobe *kp);
-	int disable_kretprobe(struct kretprobe *rp);
-
-Temporarily disables the specified ``*probe``. You can enable it again by using
-enable_*probe(). You must specify the probe which has been registered.
-
-enable_*probe
--------------
-
-::
-
-	#include <linux/kprobes.h>
-	int enable_kprobe(struct kprobe *kp);
-	int enable_kretprobe(struct kretprobe *rp);
-
-Enables ``*probe`` which has been disabled by disable_*probe(). You must specify
-the probe which has been registered.
-
-Kprobes Features and Limitations
-================================
-
-Kprobes allows multiple probes at the same address. Also,
-a probepoint for which there is a post_handler cannot be optimized.
-So if you install a kprobe with a post_handler, at an optimized
-probepoint, the probepoint will be unoptimized automatically.
-
-In general, you can install a probe anywhere in the kernel.
-In particular, you can probe interrupt handlers.  Known exceptions
-are discussed in this section.
-
-The register_*probe functions will return -EINVAL if you attempt
-to install a probe in the code that implements Kprobes (mostly
-kernel/kprobes.c and ``arch/*/kernel/kprobes.c``, but also functions such
-as do_page_fault and notifier_call_chain).
-
-If you install a probe in an inline-able function, Kprobes makes
-no attempt to chase down all inline instances of the function and
-install probes there.  gcc may inline a function without being asked,
-so keep this in mind if you're not seeing the probe hits you expect.
-
-A probe handler can modify the environment of the probed function
--- e.g., by modifying kernel data structures, or by modifying the
-contents of the pt_regs struct (which are restored to the registers
-upon return from the breakpoint).  So Kprobes can be used, for example,
-to install a bug fix or to inject faults for testing.  Kprobes, of
-course, has no way to distinguish the deliberately injected faults
-from the accidental ones.  Don't drink and probe.
-
-Kprobes makes no attempt to prevent probe handlers from stepping on
-each other -- e.g., probing printk() and then calling printk() from a
-probe handler.  If a probe handler hits a probe, that second probe's
-handlers won't be run in that instance, and the kprobe.nmissed member
-of the second probe will be incremented.
-
-As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
-the same handler) may run concurrently on different CPUs.
-
-Kprobes does not use mutexes or allocate memory except during
-registration and unregistration.
-
-Probe handlers are run with preemption disabled or interrupt disabled,
-which depends on the architecture and optimization state.  (e.g.,
-kretprobe handlers and optimized kprobe handlers run without interrupt
-disabled on x86/x86-64).  In any case, your handler should not yield
-the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
-
-Since a return probe is implemented by replacing the return
-address with the trampoline's address, stack backtraces and calls
-to __builtin_return_address() will typically yield the trampoline's
-address instead of the real return address for kretprobed functions.
-(As far as we can tell, __builtin_return_address() is used only
-for instrumentation and error reporting.)
-
-If the number of times a function is called does not match the number
-of times it returns, registering a return probe on that function may
-produce undesirable results. In such a case, a line:
-kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c
-gets printed. With this information, one will be able to correlate the
-exact instance of the kretprobe that caused the problem. We have the
-do_exit() case covered. do_execve() and do_fork() are not an issue.
-We're unaware of other specific cases where this could be a problem.
-
-If, upon entry to or exit from a function, the CPU is running on
-a stack other than that of the current task, registering a return
-probe on that function may produce undesirable results.  For this
-reason, Kprobes doesn't support return probes (or kprobes)
-on the x86_64 version of __switch_to(); the registration functions
-return -EINVAL.
-
-On x86/x86-64, since the Jump Optimization of Kprobes modifies
-instructions widely, there are some limitations to optimization. To
-explain it, we introduce some terminology. Imagine a 3-instruction
-sequence consisting of a two 2-byte instructions and one 3-byte
-instruction.
-
-::
-
-		IA
-		|
-	[-2][-1][0][1][2][3][4][5][6][7]
-		[ins1][ins2][  ins3 ]
-		[<-     DCR       ->]
-		[<- JTPR ->]
-
-	ins1: 1st Instruction
-	ins2: 2nd Instruction
-	ins3: 3rd Instruction
-	IA:  Insertion Address
-	JTPR: Jump Target Prohibition Region
-	DCR: Detoured Code Region
-
-The instructions in DCR are copied to the out-of-line buffer
-of the kprobe, because the bytes in DCR are replaced by
-a 5-byte jump instruction. So there are several limitations.
-
-a) The instructions in DCR must be relocatable.
-b) The instructions in DCR must not include a call instruction.
-c) JTPR must not be targeted by any jump or call instruction.
-d) DCR must not straddle the border between functions.
-
-Anyway, these limitations are checked by the in-kernel instruction
-decoder, so you don't need to worry about that.
-
-Probe Overhead
-==============
-
-On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
-microseconds to process.  Specifically, a benchmark that hits the same
-probepoint repeatedly, firing a simple handler each time, reports 1-2
-million hits per second, depending on the architecture.  A return-probe
-hit typically takes 50-75% longer than a kprobe hit.
-When you have a return probe set on a function, adding a kprobe at
-the entry to that function adds essentially no overhead.
-
-Here are sample overhead figures (in usec) for different architectures::
-
-  k = kprobe; r = return probe; kr = kprobe + return probe
-  on same function
-
-  i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
-  k = 0.57 usec; r = 0.92; kr = 0.99
-
-  x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
-  k = 0.49 usec; r = 0.80; kr = 0.82
-
-  ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
-  k = 0.77 usec; r = 1.26; kr = 1.45
-
-Optimized Probe Overhead
-------------------------
-
-Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
-process. Here are sample overhead figures (in usec) for x86 architectures::
-
-  k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
-  r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
-
-  i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
-  k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
-
-  x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
-  k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
-
-TODO
-====
-
-a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
-   programming interface for probe-based instrumentation.  Try it out.
-b. Kernel return probes for sparc64.
-c. Support for other architectures.
-d. User-space probes.
-e. Watchpoint probes (which fire on data references).
-
-Kprobes Example
-===============
-
-See samples/kprobes/kprobe_example.c
-
-Kretprobes Example
-==================
-
-See samples/kprobes/kretprobe_example.c
-
-For additional information on Kprobes, refer to the following URLs:
-
-- http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
-- http://www.redhat.com/magazine/005mar05/features/kprobes/
-- http://www-users.cs.umn.edu/~boutcher/kprobes/
-- http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
-
-Deprecated Features
-===================
-
-Jprobes is now a deprecated feature. People who are depending on it should
-migrate to other tracing features or use older kernels. Please consider to
-migrate your tool to one of the following options:
-
-- Use trace-event to trace target function with arguments.
-
-  trace-event is a low-overhead (and almost no visible overhead if it
-  is off) statically defined event interface. You can define new events
-  and trace it via ftrace or any other tracing tools.
-
-  See the following urls:
-
-    - https://lwn.net/Articles/379903/
-    - https://lwn.net/Articles/381064/
-    - https://lwn.net/Articles/383362/
-
-- Use ftrace dynamic events (kprobe event) with perf-probe.
-
-  If you build your kernel with debug info (CONFIG_DEBUG_INFO=y), you can
-  find which register/stack is assigned to which local variable or arguments
-  by using perf-probe and set up new event to trace it.
-
-  See following documents:
-
-  - Documentation/trace/kprobetrace.rst
-  - Documentation/trace/events.rst
-  - tools/perf/Documentation/perf-probe.txt
-
-
-The kprobes debugfs interface
-=============================
-
-
-With recent kernels (> 2.6.20) the list of registered kprobes is visible
-under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).
-
-/sys/kernel/debug/kprobes/list: Lists all registered probes on the system::
-
-	c015d71a  k  vfs_read+0x0
-	c03dedc5  r  tcp_v4_rcv+0x0
-
-The first column provides the kernel address where the probe is inserted.
-The second column identifies the type of probe (k - kprobe and r - kretprobe)
-while the third column specifies the symbol+offset of the probe.
-If the probed function belongs to a module, the module name is also
-specified. Following columns show probe status. If the probe is on
-a virtual address that is no longer valid (module init sections, module
-virtual addresses that correspond to modules that've been unloaded),
-such probes are marked with [GONE]. If the probe is temporarily disabled,
-such probes are marked with [DISABLED]. If the probe is optimized, it is
-marked with [OPTIMIZED]. If the probe is ftrace-based, it is marked with
-[FTRACE].
-
-/sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
-
-Provides a knob to globally and forcibly turn registered kprobes ON or OFF.
-By default, all kprobes are enabled. By echoing "0" to this file, all
-registered probes will be disarmed, till such time a "1" is echoed to this
-file. Note that this knob just disarms and arms all kprobes and doesn't
-change each probe's disabling state. This means that disabled kprobes (marked
-[DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
-
-
-The kprobes sysctl interface
-============================
-
-/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
-
-When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
-a knob to globally and forcibly turn jump optimization (see section
-:ref:`kprobes_jump_optimization`) ON or OFF. By default, jump optimization
-is allowed (ON). If you echo "0" to this file or set
-"debug.kprobes_optimization" to 0 via sysctl, all optimized probes will be
-unoptimized, and any new probes registered after that will not be optimized.
-
-Note that this knob *changes* the optimized state. This means that optimized
-probes (marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
-removed). If the knob is turned on, they will be optimized again.
-
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
deleted file mode 100644
index f65b51523014..000000000000
--- a/Documentation/lzo.txt
+++ /dev/null
@@ -1,202 +0,0 @@
-===========================================================
-LZO stream format as understood by Linux's LZO decompressor
-===========================================================
-
-Introduction
-============
-
-  This is not a specification. No specification seems to be publicly available
-  for the LZO stream format. This document describes what input format the LZO
-  decompressor as implemented in the Linux kernel understands. The file subject
-  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
-  the compressor nor on any other implementations though it seems likely that
-  the format matches the standard one. The purpose of this document is to
-  better understand what the code does in order to propose more efficient fixes
-  for future bug reports.
-
-Description
-===========
-
-  The stream is composed of a series of instructions, operands, and data. The
-  instructions consist in a few bits representing an opcode, and bits forming
-  the operands for the instruction, whose size and position depend on the
-  opcode and on the number of literals copied by previous instruction. The
-  operands are used to indicate:
-
-    - a distance when copying data from the dictionary (past output buffer)
-    - a length (number of bytes to copy from dictionary)
-    - the number of literals to copy, which is retained in variable "state"
-      as a piece of information for next instructions.
-
-  Optionally depending on the opcode and operands, extra data may follow. These
-  extra data can be a complement for the operand (eg: a length or a distance
-  encoded on larger values), or a literal to be copied to the output buffer.
-
-  The first byte of the block follows a different encoding from other bytes, it
-  seems to be optimized for literal use only, since there is no dictionary yet
-  prior to that byte.
-
-  Lengths are always encoded on a variable size starting with a small number
-  of bits in the operand. If the number of bits isn't enough to represent the
-  length, up to 255 may be added in increments by consuming more bytes with a
-  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
-  around 255:1). The variable length encoding using #bits is always the same::
-
-       length = byte & ((1 << #bits) - 1)
-       if (!length) {
-               length = ((1 << #bits) - 1)
-               length += 255*(number of zero bytes)
-               length += first-non-zero-byte
-       }
-       length += constant (generally 2 or 3)
-
-  For references to the dictionary, distances are relative to the output
-  pointer. Distances are encoded using very few bits belonging to certain
-  ranges, resulting in multiple copy instructions using different encodings.
-  Certain encodings involve one extra byte, others involve two extra bytes
-  forming a little-endian 16-bit quantity (marked LE16 below).
-
-  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
-  are copied before starting the next instruction. The number of literals that
-  were copied may change the meaning and behaviour of the next instruction. In
-  practice, only one instruction needs to know whether 0, less than 4, or more
-  literals were copied. This is the information stored in the <state> variable
-  in this implementation. This number of immediate literals to be copied is
-  generally encoded in the last two bits of the instruction but may also be
-  taken from the last two bits of an extra operand (eg: distance).
-
-  End of stream is declared when a block copy of distance 0 is seen. Only one
-  instruction may encode this distance (0001HLLL), it takes one LE16 operand
-  for the distance, thus requiring 3 bytes.
-
-  .. important::
-
-     In the code some length checks are missing because certain instructions
-     are called under the assumption that a certain number of bytes follow
-     because it has already been guaranteed before parsing the instructions.
-     They just have to "refill" this credit if they consume extra bytes. This
-     is an implementation design choice independent on the algorithm or
-     encoding.
-
-Versions
-
-0: Original version
-1: LZO-RLE
-
-Version 1 of LZO implements an extension to encode runs of zeros using run
-length encoding. This improves speed for data with many zeros, which is a
-common case for zram. This modifies the bitstream in a backwards compatible way
-(v1 can correctly decompress v0 compressed data, but v0 cannot read v1 data).
-
-For maximum compatibility, both versions are available under different names
-(lzo and lzo-rle). Differences in the encoding are noted in this document with
-e.g.: version 1 only.
-
-Byte sequences
-==============
-
-  First byte encoding::
-
-      0..16   : follow regular instruction encoding, see below. It is worth
-                noting that code 16 will represent a block copy from the
-                dictionary which is empty, and that it will always be
-                invalid at this place.
-
-      17      : bitstream version. If the first byte is 17, and compressed
-                stream length is at least 5 bytes (length of shortest possible
-                versioned bitstream), the next byte gives the bitstream version
-                (version 1 only).
-                Otherwise, the bitstream version is 0.
-
-      18..21  : copy 0..3 literals
-                state = (byte - 17) = 0..3  [ copy <state> literals ]
-                skip byte
-
-      22..255 : copy literal string
-                length = (byte - 17) = 4..238
-                state = 4 [ don't copy extra literals ]
-                skip byte
-
-  Instruction encoding::
-
-      0 0 0 0 X X X X  (0..15)
-        Depends on the number of literals copied by the last instruction.
-        If last instruction did not copy any literal (state == 0), this
-        encoding will be a copy of 4 or more literal, and must be interpreted
-        like this :
-
-           0 0 0 0 L L L L  (0..15)  : copy long literal string
-           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
-           state = 4  (no extra literals are copied)
-
-        If last instruction used to copy between 1 to 3 literals (encoded in
-        the instruction's opcode or distance), the instruction is a copy of a
-        2-byte block from the dictionary within a 1kB distance. It is worth
-        noting that this instruction provides little savings since it uses 2
-        bytes to encode a copy of 2 other bytes but it encodes the number of
-        following literals for free. It must be interpreted like this :
-
-           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
-           length = 2
-           state = S (copy S literals after this block)
-         Always followed by exactly one byte : H H H H H H H H
-           distance = (H << 2) + D + 1
-
-        If last instruction used to copy 4 or more literals (as detected by
-        state == 4), the instruction becomes a copy of a 3-byte block from the
-        dictionary from a 2..3kB distance, and must be interpreted like this :
-
-           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
-           length = 3
-           state = S (copy S literals after this block)
-         Always followed by exactly one byte : H H H H H H H H
-           distance = (H << 2) + D + 2049
-
-      0 0 0 1 H L L L  (16..31)
-           Copy of a block within 16..48kB distance (preferably less than 10B)
-           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
-        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
-           distance = 16384 + (H << 14) + D
-           state = S (copy S literals after this block)
-           End of stream is reached if distance == 16384
-           In version 1 only, to prevent ambiguity with the RLE case when
-           ((distance & 0x803f) == 0x803f) && (261 <= length <= 264), the
-           compressor must not emit block copies where distance and length
-           meet these conditions.
-
-        In version 1 only, this instruction is also used to encode a run of
-           zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
-           In this case, it is followed by a fourth byte, X.
-           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4
-
-      0 0 1 L L L L L  (32..63)
-           Copy of small block within 16kB distance (preferably less than 34B)
-           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
-        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
-           distance = D + 1
-           state = S (copy S literals after this block)
-
-      0 1 L D D D S S  (64..127)
-           Copy 3-4 bytes from block within 2kB distance
-           state = S (copy S literals after this block)
-           length = 3 + L
-         Always followed by exactly one byte : H H H H H H H H
-           distance = (H << 3) + D + 1
-
-      1 L L D D D S S  (128..255)
-           Copy 5-8 bytes from block within 2kB distance
-           state = S (copy S literals after this block)
-           length = 5 + L
-         Always followed by exactly one byte : H H H H H H H H
-           distance = (H << 3) + D + 1
-
-Authors
-=======
-
-  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
-  analysis of the decompression code available in Linux 3.16-rc5, and updated
-  by Dave Rodgman <dave.rodgman@arm.com> on 2018/10/30 to introduce run-length
-  encoding. The code is tricky, it is possible that this document contains
-  mistakes or that a few corner cases were overlooked. In any case, please
-  report any doubt, fix, or proposed updates to the author(s) so that the
-  document can be updated.
diff --git a/Documentation/remoteproc.txt b/Documentation/remoteproc.txt
deleted file mode 100644
index 2be1147256e0..000000000000
--- a/Documentation/remoteproc.txt
+++ /dev/null
@@ -1,359 +0,0 @@
-==========================
-Remote Processor Framework
-==========================
-
-Introduction
-============
-
-Modern SoCs typically have heterogeneous remote processor devices in asymmetric
-multiprocessing (AMP) configurations, which may be running different instances
-of operating system, whether it's Linux or any other flavor of real-time OS.
-
-OMAP4, for example, has dual Cortex-A9, dual Cortex-M3 and a C64x+ DSP.
-In a typical configuration, the dual cortex-A9 is running Linux in a SMP
-configuration, and each of the other three cores (two M3 cores and a DSP)
-is running its own instance of RTOS in an AMP configuration.
-
-The remoteproc framework allows different platforms/architectures to
-control (power on, load firmware, power off) those remote processors while
-abstracting the hardware differences, so the entire driver doesn't need to be
-duplicated. In addition, this framework also adds rpmsg virtio devices
-for remote processors that supports this kind of communication. This way,
-platform-specific remoteproc drivers only need to provide a few low-level
-handlers, and then all rpmsg drivers will then just work
-(for more information about the virtio-based rpmsg bus and its drivers,
-please read Documentation/rpmsg.txt).
-Registration of other types of virtio devices is now also possible. Firmwares
-just need to publish what kind of virtio devices do they support, and then
-remoteproc will add those devices. This makes it possible to reuse the
-existing virtio drivers with remote processor backends at a minimal development
-cost.
-
-User API
-========
-
-::
-
-  int rproc_boot(struct rproc *rproc)
-
-Boot a remote processor (i.e. load its firmware, power it on, ...).
-
-If the remote processor is already powered on, this function immediately
-returns (successfully).
-
-Returns 0 on success, and an appropriate error value otherwise.
-Note: to use this function you should already have a valid rproc
-handle. There are several ways to achieve that cleanly (devres, pdata,
-the way remoteproc_rpmsg.c does this, or, if this becomes prevalent, we
-might also consider using dev_archdata for this).
-
-::
-
-  void rproc_shutdown(struct rproc *rproc)
-
-Power off a remote processor (previously booted with rproc_boot()).
-In case @rproc is still being used by an additional user(s), then
-this function will just decrement the power refcount and exit,
-without really powering off the device.
-
-Every call to rproc_boot() must (eventually) be accompanied by a call
-to rproc_shutdown(). Calling rproc_shutdown() redundantly is a bug.
-
-.. note::
-
-  we're not decrementing the rproc's refcount, only the power refcount.
-  which means that the @rproc handle stays valid even after
-  rproc_shutdown() returns, and users can still use it with a subsequent
-  rproc_boot(), if needed.
-
-::
-
-  struct rproc *rproc_get_by_phandle(phandle phandle)
-
-Find an rproc handle using a device tree phandle. Returns the rproc
-handle on success, and NULL on failure. This function increments
-the remote processor's refcount, so always use rproc_put() to
-decrement it back once rproc isn't needed anymore.
-
-Typical usage
-=============
-
-::
-
-  #include <linux/remoteproc.h>
-
-  /* in case we were given a valid 'rproc' handle */
-  int dummy_rproc_example(struct rproc *my_rproc)
-  {
-	int ret;
-
-	/* let's power on and boot our remote processor */
-	ret = rproc_boot(my_rproc);
-	if (ret) {
-		/*
-		 * something went wrong. handle it and leave.
-		 */
-	}
-
-	/*
-	 * our remote processor is now powered on... give it some work
-	 */
-
-	/* let's shut it down now */
-	rproc_shutdown(my_rproc);
-  }
-
-API for implementors
-====================
-
-::
-
-  struct rproc *rproc_alloc(struct device *dev, const char *name,
-				const struct rproc_ops *ops,
-				const char *firmware, int len)
-
-Allocate a new remote processor handle, but don't register
-it yet. Required parameters are the underlying device, the
-name of this remote processor, platform-specific ops handlers,
-the name of the firmware to boot this rproc with, and the
-length of private data needed by the allocating rproc driver (in bytes).
-
-This function should be used by rproc implementations during
-initialization of the remote processor.
-
-After creating an rproc handle using this function, and when ready,
-implementations should then call rproc_add() to complete
-the registration of the remote processor.
-
-On success, the new rproc is returned, and on failure, NULL.
-
-.. note::
-
-  **never** directly deallocate @rproc, even if it was not registered
-  yet. Instead, when you need to unroll rproc_alloc(), use rproc_free().
-
-::
-
-  void rproc_free(struct rproc *rproc)
-
-Free an rproc handle that was allocated by rproc_alloc.
-
-This function essentially unrolls rproc_alloc(), by decrementing the
-rproc's refcount. It doesn't directly free rproc; that would happen
-only if there are no other references to rproc and its refcount now
-dropped to zero.
-
-::
-
-  int rproc_add(struct rproc *rproc)
-
-Register @rproc with the remoteproc framework, after it has been
-allocated with rproc_alloc().
-
-This is called by the platform-specific rproc implementation, whenever
-a new remote processor device is probed.
-
-Returns 0 on success and an appropriate error code otherwise.
-Note: this function initiates an asynchronous firmware loading
-context, which will look for virtio devices supported by the rproc's
-firmware.
-
-If found, those virtio devices will be created and added, so as a result
-of registering this remote processor, additional virtio drivers might get
-probed.
-
-::
-
-  int rproc_del(struct rproc *rproc)
-
-Unroll rproc_add().
-
-This function should be called when the platform specific rproc
-implementation decides to remove the rproc device. it should
-_only_ be called if a previous invocation of rproc_add()
-has completed successfully.
-
-After rproc_del() returns, @rproc is still valid, and its
-last refcount should be decremented by calling rproc_free().
-
-Returns 0 on success and -EINVAL if @rproc isn't valid.
-
-::
-
-  void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type)
-
-Report a crash in a remoteproc
-
-This function must be called every time a crash is detected by the
-platform specific rproc implementation. This should not be called from a
-non-remoteproc driver. This function can be called from atomic/interrupt
-context.
-
-Implementation callbacks
-========================
-
-These callbacks should be provided by platform-specific remoteproc
-drivers::
-
-  /**
-   * struct rproc_ops - platform-specific device handlers
-   * @start:	power on the device and boot it
-   * @stop:	power off the device
-   * @kick:	kick a virtqueue (virtqueue id given as a parameter)
-   */
-  struct rproc_ops {
-	int (*start)(struct rproc *rproc);
-	int (*stop)(struct rproc *rproc);
-	void (*kick)(struct rproc *rproc, int vqid);
-  };
-
-Every remoteproc implementation should at least provide the ->start and ->stop
-handlers. If rpmsg/virtio functionality is also desired, then the ->kick handler
-should be provided as well.
-
-The ->start() handler takes an rproc handle and should then power on the
-device and boot it (use rproc->priv to access platform-specific private data).
-The boot address, in case needed, can be found in rproc->bootaddr (remoteproc
-core puts there the ELF entry point).
-On success, 0 should be returned, and on failure, an appropriate error code.
-
-The ->stop() handler takes an rproc handle and powers the device down.
-On success, 0 is returned, and on failure, an appropriate error code.
-
-The ->kick() handler takes an rproc handle, and an index of a virtqueue
-where new message was placed in. Implementations should interrupt the remote
-processor and let it know it has pending messages. Notifying remote processors
-the exact virtqueue index to look in is optional: it is easy (and not
-too expensive) to go through the existing virtqueues and look for new buffers
-in the used rings.
-
-Binary Firmware Structure
-=========================
-
-At this point remoteproc supports ELF32 and ELF64 firmware binaries. However,
-it is quite expected that other platforms/devices which we'd want to
-support with this framework will be based on different binary formats.
-
-When those use cases show up, we will have to decouple the binary format
-from the framework core, so we can support several binary formats without
-duplicating common code.
-
-When the firmware is parsed, its various segments are loaded to memory
-according to the specified device address (might be a physical address
-if the remote processor is accessing memory directly).
-
-In addition to the standard ELF segments, most remote processors would
-also include a special section which we call "the resource table".
-
-The resource table contains system resources that the remote processor
-requires before it should be powered on, such as allocation of physically
-contiguous memory, or iommu mapping of certain on-chip peripherals.
-Remotecore will only power up the device after all the resource table's
-requirement are met.
-
-In addition to system resources, the resource table may also contain
-resource entries that publish the existence of supported features
-or configurations by the remote processor, such as trace buffers and
-supported virtio devices (and their configurations).
-
-The resource table begins with this header::
-
-  /**
-   * struct resource_table - firmware resource table header
-   * @ver: version number
-   * @num: number of resource entries
-   * @reserved: reserved (must be zero)
-   * @offset: array of offsets pointing at the various resource entries
-   *
-   * The header of the resource table, as expressed by this structure,
-   * contains a version number (should we need to change this format in the
-   * future), the number of available resource entries, and their offsets
-   * in the table.
-   */
-  struct resource_table {
-	u32 ver;
-	u32 num;
-	u32 reserved[2];
-	u32 offset[0];
-  } __packed;
-
-Immediately following this header are the resource entries themselves,
-each of which begins with the following resource entry header::
-
-  /**
-   * struct fw_rsc_hdr - firmware resource entry header
-   * @type: resource type
-   * @data: resource data
-   *
-   * Every resource entry begins with a 'struct fw_rsc_hdr' header providing
-   * its @type. The content of the entry itself will immediately follow
-   * this header, and it should be parsed according to the resource type.
-   */
-  struct fw_rsc_hdr {
-	u32 type;
-	u8 data[0];
-  } __packed;
-
-Some resources entries are mere announcements, where the host is informed
-of specific remoteproc configuration. Other entries require the host to
-do something (e.g. allocate a system resource). Sometimes a negotiation
-is expected, where the firmware requests a resource, and once allocated,
-the host should provide back its details (e.g. address of an allocated
-memory region).
-
-Here are the various resource types that are currently supported::
-
-  /**
-   * enum fw_resource_type - types of resource entries
-   *
-   * @RSC_CARVEOUT:   request for allocation of a physically contiguous
-   *		    memory region.
-   * @RSC_DEVMEM:     request to iommu_map a memory-based peripheral.
-   * @RSC_TRACE:	    announces the availability of a trace buffer into which
-   *		    the remote processor will be writing logs.
-   * @RSC_VDEV:       declare support for a virtio device, and serve as its
-   *		    virtio header.
-   * @RSC_LAST:       just keep this one at the end
-   * @RSC_VENDOR_START:	start of the vendor specific resource types range
-   * @RSC_VENDOR_END:	end of the vendor specific resource types range
-   *
-   * Please note that these values are used as indices to the rproc_handle_rsc
-   * lookup table, so please keep them sane. Moreover, @RSC_LAST is used to
-   * check the validity of an index before the lookup table is accessed, so
-   * please update it as needed.
-   */
-  enum fw_resource_type {
-	RSC_CARVEOUT		= 0,
-	RSC_DEVMEM		= 1,
-	RSC_TRACE		= 2,
-	RSC_VDEV		= 3,
-	RSC_LAST		= 4,
-	RSC_VENDOR_START	= 128,
-	RSC_VENDOR_END		= 512,
-  };
-
-For more details regarding a specific resource type, please see its
-dedicated structure in include/linux/remoteproc.h.
-
-We also expect that platform-specific resource entries will show up
-at some point. When that happens, we could easily add a new RSC_PLATFORM
-type, and hand those resources to the platform-specific rproc driver to handle.
-
-Virtio and remoteproc
-=====================
-
-The firmware should provide remoteproc information about virtio devices
-that it supports, and their configurations: a RSC_VDEV resource entry
-should specify the virtio device id (as in virtio_ids.h), virtio features,
-virtio config space, vrings information, etc.
-
-When a new remote processor is registered, the remoteproc framework
-will look for its resource table and will register the virtio devices
-it supports. A firmware may support any number of virtio devices, and
-of any type (a single remote processor can also easily support several
-rpmsg virtio devices this way, if desired).
-
-Of course, RSC_VDEV resource entries are only good enough for static
-allocation of virtio devices. Dynamic allocations will also be made possible
-using the rpmsg bus (similar to how we already do dynamic allocations of
-rpmsg channels; read more about it in rpmsg.txt).
diff --git a/Documentation/rpmsg.txt b/Documentation/rpmsg.txt
deleted file mode 100644
index 24b7a9e1a5f9..000000000000
--- a/Documentation/rpmsg.txt
+++ /dev/null
@@ -1,341 +0,0 @@
-============================================
-Remote Processor Messaging (rpmsg) Framework
-============================================
-
-.. note::
-
-  This document describes the rpmsg bus and how to write rpmsg drivers.
-  To learn how to add rpmsg support for new platforms, check out remoteproc.txt
-  (also a resident of Documentation/).
-
-Introduction
-============
-
-Modern SoCs typically employ heterogeneous remote processor devices in
-asymmetric multiprocessing (AMP) configurations, which may be running
-different instances of operating system, whether it's Linux or any other
-flavor of real-time OS.
-
-OMAP4, for example, has dual Cortex-A9, dual Cortex-M3 and a C64x+ DSP.
-Typically, the dual cortex-A9 is running Linux in a SMP configuration,
-and each of the other three cores (two M3 cores and a DSP) is running
-its own instance of RTOS in an AMP configuration.
-
-Typically AMP remote processors employ dedicated DSP codecs and multimedia
-hardware accelerators, and therefore are often used to offload CPU-intensive
-multimedia tasks from the main application processor.
-
-These remote processors could also be used to control latency-sensitive
-sensors, drive random hardware blocks, or just perform background tasks
-while the main CPU is idling.
-
-Users of those remote processors can either be userland apps (e.g. multimedia
-frameworks talking with remote OMX components) or kernel drivers (controlling
-hardware accessible only by the remote processor, reserving kernel-controlled
-resources on behalf of the remote processor, etc..).
-
-Rpmsg is a virtio-based messaging bus that allows kernel drivers to communicate
-with remote processors available on the system. In turn, drivers could then
-expose appropriate user space interfaces, if needed.
-
-When writing a driver that exposes rpmsg communication to userland, please
-keep in mind that remote processors might have direct access to the
-system's physical memory and other sensitive hardware resources (e.g. on
-OMAP4, remote cores and hardware accelerators may have direct access to the
-physical memory, gpio banks, dma controllers, i2c bus, gptimers, mailbox
-devices, hwspinlocks, etc..). Moreover, those remote processors might be
-running RTOS where every task can access the entire memory/devices exposed
-to the processor. To minimize the risks of rogue (or buggy) userland code
-exploiting remote bugs, and by that taking over the system, it is often
-desired to limit userland to specific rpmsg channels (see definition below)
-it can send messages on, and if possible, minimize how much control
-it has over the content of the messages.
-
-Every rpmsg device is a communication channel with a remote processor (thus
-rpmsg devices are called channels). Channels are identified by a textual name
-and have a local ("source") rpmsg address, and remote ("destination") rpmsg
-address.
-
-When a driver starts listening on a channel, its rx callback is bound with
-a unique rpmsg local address (a 32-bit integer). This way when inbound messages
-arrive, the rpmsg core dispatches them to the appropriate driver according
-to their destination address (this is done by invoking the driver's rx handler
-with the payload of the inbound message).
-
-
-User API
-========
-
-::
-
-  int rpmsg_send(struct rpmsg_channel *rpdev, void *data, int len);
-
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
-and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
-
-In case there are no TX buffers available, the function will block until
-one becomes available (i.e. until the remote processor consumes
-a tx buffer and puts it back on virtio's used descriptor ring),
-or a timeout of 15 seconds elapses. When the latter happens,
--ERESTARTSYS is returned.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  int rpmsg_sendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst);
-
-sends a message across to the remote processor on a given channel,
-to a destination address provided by the caller.
-
-The caller should specify the channel, the data it wants to send,
-its length (in bytes), and an explicit destination address.
-
-The message will then be sent to the remote processor to which the
-channel belongs, using the channel's src address, and the user-provided
-dst address (thus the channel's dst address will be ignored).
-
-In case there are no TX buffers available, the function will block until
-one becomes available (i.e. until the remote processor consumes
-a tx buffer and puts it back on virtio's used descriptor ring),
-or a timeout of 15 seconds elapses. When the latter happens,
--ERESTARTSYS is returned.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  int rpmsg_send_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
-							void *data, int len);
-
-
-sends a message across to the remote processor, using the src and dst
-addresses provided by the user.
-
-The caller should specify the channel, the data it wants to send,
-its length (in bytes), and explicit source and destination addresses.
-The message will then be sent to the remote processor to which the
-channel belongs, but the channel's src and dst addresses will be
-ignored (and the user-provided addresses will be used instead).
-
-In case there are no TX buffers available, the function will block until
-one becomes available (i.e. until the remote processor consumes
-a tx buffer and puts it back on virtio's used descriptor ring),
-or a timeout of 15 seconds elapses. When the latter happens,
--ERESTARTSYS is returned.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  int rpmsg_trysend(struct rpmsg_channel *rpdev, void *data, int len);
-
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
-and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
-
-In case there are no TX buffers available, the function will immediately
-return -ENOMEM without waiting until one becomes available.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  int rpmsg_trysendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst)
-
-
-sends a message across to the remote processor on a given channel,
-to a destination address provided by the user.
-
-The user should specify the channel, the data it wants to send,
-its length (in bytes), and an explicit destination address.
-
-The message will then be sent to the remote processor to which the
-channel belongs, using the channel's src address, and the user-provided
-dst address (thus the channel's dst address will be ignored).
-
-In case there are no TX buffers available, the function will immediately
-return -ENOMEM without waiting until one becomes available.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  int rpmsg_trysend_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
-							void *data, int len);
-
-
-sends a message across to the remote processor, using source and
-destination addresses provided by the user.
-
-The user should specify the channel, the data it wants to send,
-its length (in bytes), and explicit source and destination addresses.
-The message will then be sent to the remote processor to which the
-channel belongs, but the channel's src and dst addresses will be
-ignored (and the user-provided addresses will be used instead).
-
-In case there are no TX buffers available, the function will immediately
-return -ENOMEM without waiting until one becomes available.
-
-The function can only be called from a process context (for now).
-Returns 0 on success and an appropriate error value on failure.
-
-::
-
-  struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_channel *rpdev,
-		void (*cb)(struct rpmsg_channel *, void *, int, void *, u32),
-		void *priv, u32 addr);
-
-every rpmsg address in the system is bound to an rx callback (so when
-inbound messages arrive, they are dispatched by the rpmsg bus using the
-appropriate callback handler) by means of an rpmsg_endpoint struct.
-
-This function allows drivers to create such an endpoint, and by that,
-bind a callback, and possibly some private data too, to an rpmsg address
-(either one that is known in advance, or one that will be dynamically
-assigned for them).
-
-Simple rpmsg drivers need not call rpmsg_create_ept, because an endpoint
-is already created for them when they are probed by the rpmsg bus
-(using the rx callback they provide when they registered to the rpmsg bus).
-
-So things should just work for simple drivers: they already have an
-endpoint, their rx callback is bound to their rpmsg address, and when
-relevant inbound messages arrive (i.e. messages which their dst address
-equals to the src address of their rpmsg channel), the driver's handler
-is invoked to process it.
-
-That said, more complicated drivers might do need to allocate
-additional rpmsg addresses, and bind them to different rx callbacks.
-To accomplish that, those drivers need to call this function.
-Drivers should provide their channel (so the new endpoint would bind
-to the same remote processor their channel belongs to), an rx callback
-function, an optional private data (which is provided back when the
-rx callback is invoked), and an address they want to bind with the
-callback. If addr is RPMSG_ADDR_ANY, then rpmsg_create_ept will
-dynamically assign them an available rpmsg address (drivers should have
-a very good reason why not to always use RPMSG_ADDR_ANY here).
-
-Returns a pointer to the endpoint on success, or NULL on error.
-
-::
-
-  void rpmsg_destroy_ept(struct rpmsg_endpoint *ept);
-
-
-destroys an existing rpmsg endpoint. user should provide a pointer
-to an rpmsg endpoint that was previously created with rpmsg_create_ept().
-
-::
-
-  int register_rpmsg_driver(struct rpmsg_driver *rpdrv);
-
-
-registers an rpmsg driver with the rpmsg bus. user should provide
-a pointer to an rpmsg_driver struct, which contains the driver's
-->probe() and ->remove() functions, an rx callback, and an id_table
-specifying the names of the channels this driver is interested to
-be probed with.
-
-::
-
-  void unregister_rpmsg_driver(struct rpmsg_driver *rpdrv);
-
-
-unregisters an rpmsg driver from the rpmsg bus. user should provide
-a pointer to a previously-registered rpmsg_driver struct.
-Returns 0 on success, and an appropriate error value on failure.
-
-
-Typical usage
-=============
-
-The following is a simple rpmsg driver, that sends an "hello!" message
-on probe(), and whenever it receives an incoming message, it dumps its
-content to the console.
-
-::
-
-  #include <linux/kernel.h>
-  #include <linux/module.h>
-  #include <linux/rpmsg.h>
-
-  static void rpmsg_sample_cb(struct rpmsg_channel *rpdev, void *data, int len,
-						void *priv, u32 src)
-  {
-	print_hex_dump(KERN_INFO, "incoming message:", DUMP_PREFIX_NONE,
-						16, 1, data, len, true);
-  }
-
-  static int rpmsg_sample_probe(struct rpmsg_channel *rpdev)
-  {
-	int err;
-
-	dev_info(&rpdev->dev, "chnl: 0x%x -> 0x%x\n", rpdev->src, rpdev->dst);
-
-	/* send a message on our channel */
-	err = rpmsg_send(rpdev, "hello!", 6);
-	if (err) {
-		pr_err("rpmsg_send failed: %d\n", err);
-		return err;
-	}
-
-	return 0;
-  }
-
-  static void rpmsg_sample_remove(struct rpmsg_channel *rpdev)
-  {
-	dev_info(&rpdev->dev, "rpmsg sample client driver is removed\n");
-  }
-
-  static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
-	{ .name	= "rpmsg-client-sample" },
-	{ },
-  };
-  MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);
-
-  static struct rpmsg_driver rpmsg_sample_client = {
-	.drv.name	= KBUILD_MODNAME,
-	.id_table	= rpmsg_driver_sample_id_table,
-	.probe		= rpmsg_sample_probe,
-	.callback	= rpmsg_sample_cb,
-	.remove		= rpmsg_sample_remove,
-  };
-  module_rpmsg_driver(rpmsg_sample_client);
-
-.. note::
-
-   a similar sample which can be built and loaded can be found
-   in samples/rpmsg/.
-
-Allocations of rpmsg channels
-=============================
-
-At this point we only support dynamic allocations of rpmsg channels.
-
-This is possible only with remote processors that have the VIRTIO_RPMSG_F_NS
-virtio device feature set. This feature bit means that the remote
-processor supports dynamic name service announcement messages.
-
-When this feature is enabled, creation of rpmsg devices (i.e. channels)
-is completely dynamic: the remote processor announces the existence of a
-remote rpmsg service by sending a name service message (which contains
-the name and rpmsg addr of the remote service, see struct rpmsg_ns_msg).
-
-This message is then handled by the rpmsg bus, which in turn dynamically
-creates and registers an rpmsg channel (which represents the remote service).
-If/when a relevant rpmsg driver is registered, it will be immediately probed
-by the bus, and can then start sending messages to the remote service.
-
-The plan is also to add static creation of rpmsg channels via the virtio
-config space, but it's not implemented yet.
diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt
deleted file mode 100644
index 50d7ea857cff..000000000000
--- a/Documentation/speculation.txt
+++ /dev/null
@@ -1,90 +0,0 @@
-This document explains potential effects of speculation, and how undesirable
-effects can be mitigated portably using common APIs.
-
-===========
-Speculation
-===========
-
-To improve performance and minimize average latencies, many contemporary CPUs
-employ speculative execution techniques such as branch prediction, performing
-work which may be discarded at a later stage.
-
-Typically speculative execution cannot be observed from architectural state,
-such as the contents of registers. However, in some cases it is possible to
-observe its impact on microarchitectural state, such as the presence or
-absence of data in caches. Such state may form side-channels which can be
-observed to extract secret information.
-
-For example, in the presence of branch prediction, it is possible for bounds
-checks to be ignored by code which is speculatively executed. Consider the
-following code::
-
-	int load_array(int *array, unsigned int index)
-	{
-		if (index >= MAX_ARRAY_ELEMS)
-			return 0;
-		else
-			return array[index];
-	}
-
-Which, on arm64, may be compiled to an assembly sequence such as::
-
-	CMP	<index>, #MAX_ARRAY_ELEMS
-	B.LT	less
-	MOV	<returnval>, #0
-	RET
-  less:
-	LDR	<returnval>, [<array>, <index>]
-	RET
-
-It is possible that a CPU mis-predicts the conditional branch, and
-speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This
-value will subsequently be discarded, but the speculated load may affect
-microarchitectural state which can be subsequently measured.
-
-More complex sequences involving multiple dependent memory accesses may
-result in sensitive information being leaked. Consider the following
-code, building on the prior example::
-
-	int load_dependent_arrays(int *arr1, int *arr2, int index)
-	{
-		int val1, val2,
-
-		val1 = load_array(arr1, index);
-		val2 = load_array(arr2, val1);
-
-		return val2;
-	}
-
-Under speculation, the first call to load_array() may return the value
-of an out-of-bounds address, while the second call will influence
-microarchitectural state dependent on this value. This may provide an
-arbitrary read primitive.
-
-====================================
-Mitigating speculation side-channels
-====================================
-
-The kernel provides a generic API to ensure that bounds checks are
-respected even under speculation. Architectures which are affected by
-speculation-based side-channels are expected to implement these
-primitives.
-
-The array_index_nospec() helper in <linux/nospec.h> can be used to
-prevent information from being leaked via side-channels.
-
-A call to array_index_nospec(index, size) returns a sanitized index
-value that is bounded to [0, size) even under cpu speculation
-conditions.
-
-This can be used to protect the earlier load_array() example::
-
-	int load_array(int *array, unsigned int index)
-	{
-		if (index >= MAX_ARRAY_ELEMS)
-			return 0;
-		else {
-			index = array_index_nospec(index, MAX_ARRAY_ELEMS);
-			return array[index];
-		}
-	}
diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst
new file mode 100644
index 000000000000..8a6860f33b4e
--- /dev/null
+++ b/Documentation/staging/crc32.rst
@@ -0,0 +1,189 @@
+=================================
+brief tutorial on CRC computation
+=================================
+
+A CRC is a long-division remainder.  You add the CRC to the message,
+and the whole thing (message+CRC) is a multiple of the given
+CRC polynomial.  To check the CRC, you can either check that the
+CRC matches the recomputed value, *or* you can check that the
+remainder computed on the message+CRC is 0.  This latter approach
+is used by a lot of hardware implementations, and is why so many
+protocols put the end-of-frame flag after the CRC.
+
+It's actually the same long division you learned in school, except that:
+
+- We're working in binary, so the digits are only 0 and 1, and
+- When dividing polynomials, there are no carries.  Rather than add and
+  subtract, we just xor.  Thus, we tend to get a bit sloppy about
+  the difference between adding and subtracting.
+
+Like all division, the remainder is always smaller than the divisor.
+To produce a 32-bit CRC, the divisor is actually a 33-bit CRC polynomial.
+Since it's 33 bits long, bit 32 is always going to be set, so usually the
+CRC is written in hex with the most significant bit omitted.  (If you're
+familiar with the IEEE 754 floating-point format, it's the same idea.)
+
+Note that a CRC is computed over a string of *bits*, so you have
+to decide on the endianness of the bits within each byte.  To get
+the best error-detecting properties, this should correspond to the
+order they're actually sent.  For example, standard RS-232 serial is
+little-endian; the most significant bit (sometimes used for parity)
+is sent last.  And when appending a CRC word to a message, you should
+do it in the right order, matching the endianness.
+
+Just like with ordinary division, you proceed one digit (bit) at a time.
+Each step of the division you take one more digit (bit) of the dividend
+and append it to the current remainder.  Then you figure out the
+appropriate multiple of the divisor to subtract to being the remainder
+back into range.  In binary, this is easy - it has to be either 0 or 1,
+and to make the XOR cancel, it's just a copy of bit 32 of the remainder.
+
+When computing a CRC, we don't care about the quotient, so we can
+throw the quotient bit away, but subtract the appropriate multiple of
+the polynomial from the remainder and we're back to where we started,
+ready to process the next bit.
+
+A big-endian CRC written this way would be coded like::
+
+	for (i = 0; i < input_bits; i++) {
+		multiple = remainder & 0x80000000 ? CRCPOLY : 0;
+		remainder = (remainder << 1 | next_input_bit()) ^ multiple;
+	}
+
+Notice how, to get at bit 32 of the shifted remainder, we look
+at bit 31 of the remainder *before* shifting it.
+
+But also notice how the next_input_bit() bits we're shifting into
+the remainder don't actually affect any decision-making until
+32 bits later.  Thus, the first 32 cycles of this are pretty boring.
+Also, to add the CRC to a message, we need a 32-bit-long hole for it at
+the end, so we have to add 32 extra cycles shifting in zeros at the
+end of every message.
+
+These details lead to a standard trick: rearrange merging in the
+next_input_bit() until the moment it's needed.  Then the first 32 cycles
+can be precomputed, and merging in the final 32 zero bits to make room
+for the CRC can be skipped entirely.  This changes the code to::
+
+	for (i = 0; i < input_bits; i++) {
+		remainder ^= next_input_bit() << 31;
+		multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
+		remainder = (remainder << 1) ^ multiple;
+	}
+
+With this optimization, the little-endian code is particularly simple::
+
+	for (i = 0; i < input_bits; i++) {
+		remainder ^= next_input_bit();
+		multiple = (remainder & 1) ? CRCPOLY : 0;
+		remainder = (remainder >> 1) ^ multiple;
+	}
+
+The most significant coefficient of the remainder polynomial is stored
+in the least significant bit of the binary "remainder" variable.
+The other details of endianness have been hidden in CRCPOLY (which must
+be bit-reversed) and next_input_bit().
+
+As long as next_input_bit is returning the bits in a sensible order, we don't
+*have* to wait until the last possible moment to merge in additional bits.
+We can do it 8 bits at a time rather than 1 bit at a time::
+
+	for (i = 0; i < input_bytes; i++) {
+		remainder ^= next_input_byte() << 24;
+		for (j = 0; j < 8; j++) {
+			multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
+			remainder = (remainder << 1) ^ multiple;
+		}
+	}
+
+Or in little-endian::
+
+	for (i = 0; i < input_bytes; i++) {
+		remainder ^= next_input_byte();
+		for (j = 0; j < 8; j++) {
+			multiple = (remainder & 1) ? CRCPOLY : 0;
+			remainder = (remainder >> 1) ^ multiple;
+		}
+	}
+
+If the input is a multiple of 32 bits, you can even XOR in a 32-bit
+word at a time and increase the inner loop count to 32.
+
+You can also mix and match the two loop styles, for example doing the
+bulk of a message byte-at-a-time and adding bit-at-a-time processing
+for any fractional bytes at the end.
+
+To reduce the number of conditional branches, software commonly uses
+the byte-at-a-time table method, popularized by Dilip V. Sarwate,
+"Computation of Cyclic Redundancy Checks via Table Look-Up", Comm. ACM
+v.31 no.8 (August 1998) p. 1008-1013.
+
+Here, rather than just shifting one bit of the remainder to decide
+in the correct multiple to subtract, we can shift a byte at a time.
+This produces a 40-bit (rather than a 33-bit) intermediate remainder,
+and the correct multiple of the polynomial to subtract is found using
+a 256-entry lookup table indexed by the high 8 bits.
+
+(The table entries are simply the CRC-32 of the given one-byte messages.)
+
+When space is more constrained, smaller tables can be used, e.g. two
+4-bit shifts followed by a lookup in a 16-entry table.
+
+It is not practical to process much more than 8 bits at a time using this
+technique, because tables larger than 256 entries use too much memory and,
+more importantly, too much of the L1 cache.
+
+To get higher software performance, a "slicing" technique can be used.
+See "High Octane CRC Generation with the Intel Slicing-by-8 Algorithm",
+ftp://download.intel.com/technology/comms/perfnet/download/slicing-by-8.pdf
+
+This does not change the number of table lookups, but does increase
+the parallelism.  With the classic Sarwate algorithm, each table lookup
+must be completed before the index of the next can be computed.
+
+A "slicing by 2" technique would shift the remainder 16 bits at a time,
+producing a 48-bit intermediate remainder.  Rather than doing a single
+lookup in a 65536-entry table, the two high bytes are looked up in
+two different 256-entry tables.  Each contains the remainder required
+to cancel out the corresponding byte.  The tables are different because the
+polynomials to cancel are different.  One has non-zero coefficients from
+x^32 to x^39, while the other goes from x^40 to x^47.
+
+Since modern processors can handle many parallel memory operations, this
+takes barely longer than a single table look-up and thus performs almost
+twice as fast as the basic Sarwate algorithm.
+
+This can be extended to "slicing by 4" using 4 256-entry tables.
+Each step, 32 bits of data is fetched, XORed with the CRC, and the result
+broken into bytes and looked up in the tables.  Because the 32-bit shift
+leaves the low-order bits of the intermediate remainder zero, the
+final CRC is simply the XOR of the 4 table look-ups.
+
+But this still enforces sequential execution: a second group of table
+look-ups cannot begin until the previous groups 4 table look-ups have all
+been completed.  Thus, the processor's load/store unit is sometimes idle.
+
+To make maximum use of the processor, "slicing by 8" performs 8 look-ups
+in parallel.  Each step, the 32-bit CRC is shifted 64 bits and XORed
+with 64 bits of input data.  What is important to note is that 4 of
+those 8 bytes are simply copies of the input data; they do not depend
+on the previous CRC at all.  Thus, those 4 table look-ups may commence
+immediately, without waiting for the previous loop iteration.
+
+By always having 4 loads in flight, a modern superscalar processor can
+be kept busy and make full use of its L1 cache.
+
+Two more details about CRC implementation in the real world:
+
+Normally, appending zero bits to a message which is already a multiple
+of a polynomial produces a larger multiple of that polynomial.  Thus,
+a basic CRC will not detect appended zero bits (or bytes).  To enable
+a CRC to detect this condition, it's common to invert the CRC before
+appending it.  This makes the remainder of the message+crc come out not
+as zero, but some fixed non-zero value.  (The CRC of the inversion
+pattern, 0xffffffff.)
+
+The same problem applies to zero bits prepended to the message, and a
+similar solution is used.  Instead of starting the CRC computation with
+a remainder of 0, an initial remainder of all ones is used.  As long as
+you start the same way on decoding, it doesn't make a difference.
diff --git a/Documentation/staging/index.rst b/Documentation/staging/index.rst
new file mode 100644
index 000000000000..8e98517675ca
--- /dev/null
+++ b/Documentation/staging/index.rst
@@ -0,0 +1,32 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Unsorted Documentation
+======================
+
+.. toctree::
+   :maxdepth: 2
+
+   crc32
+   kprobes
+   lzo
+   remoteproc
+   rpmsg
+   speculation
+   static-keys
+   tee
+   xz
+
+Atomic Types
+============
+
+.. literalinclude:: ../atomic_t.txt
+
+Atomic bitops
+=============
+
+.. literalinclude:: ../atomic_bitops.txt
+
+Memory Barriers
+===============
+
+.. literalinclude:: ../memory-barriers.txt
diff --git a/Documentation/staging/kprobes.rst b/Documentation/staging/kprobes.rst
new file mode 100644
index 000000000000..8baab8832c5b
--- /dev/null
+++ b/Documentation/staging/kprobes.rst
@@ -0,0 +1,801 @@
+=======================
+Kernel Probes (Kprobes)
+=======================
+
+:Author: Jim Keniston <jkenisto@us.ibm.com>
+:Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+:Author: Masami Hiramatsu <mhiramat@redhat.com>
+
+.. CONTENTS
+
+  1. Concepts: Kprobes, and Return Probes
+  2. Architectures Supported
+  3. Configuring Kprobes
+  4. API Reference
+  5. Kprobes Features and Limitations
+  6. Probe Overhead
+  7. TODO
+  8. Kprobes Example
+  9. Kretprobes Example
+  10. Deprecated Features
+  Appendix A: The kprobes debugfs interface
+  Appendix B: The kprobes sysctl interface
+
+Concepts: Kprobes and Return Probes
+=========================================
+
+Kprobes enables you to dynamically break into any kernel routine and
+collect debugging and performance information non-disruptively. You
+can trap at almost any kernel code address [1]_, specifying a handler
+routine to be invoked when the breakpoint is hit.
+
+.. [1] some parts of the kernel code can not be trapped, see
+       :ref:`kprobes_blacklist`)
+
+There are currently two types of probes: kprobes, and kretprobes
+(also called return probes).  A kprobe can be inserted on virtually
+any instruction in the kernel.  A return probe fires when a specified
+function returns.
+
+In the typical case, Kprobes-based instrumentation is packaged as
+a kernel module.  The module's init function installs ("registers")
+one or more probes, and the exit function unregisters them.  A
+registration function such as register_kprobe() specifies where
+the probe is to be inserted and what handler is to be called when
+the probe is hit.
+
+There are also ``register_/unregister_*probes()`` functions for batch
+registration/unregistration of a group of ``*probes``. These functions
+can speed up unregistration process when you have to unregister
+a lot of probes at once.
+
+The next four subsections explain how the different types of
+probes work and how jump optimization works.  They explain certain
+things that you'll need to know in order to make the best use of
+Kprobes -- e.g., the difference between a pre_handler and
+a post_handler, and how to use the maxactive and nmissed fields of
+a kretprobe.  But if you're in a hurry to start using Kprobes, you
+can skip ahead to :ref:`kprobes_archs_supported`.
+
+How Does a Kprobe Work?
+-----------------------
+
+When a kprobe is registered, Kprobes makes a copy of the probed
+instruction and replaces the first byte(s) of the probed instruction
+with a breakpoint instruction (e.g., int3 on i386 and x86_64).
+
+When a CPU hits the breakpoint instruction, a trap occurs, the CPU's
+registers are saved, and control passes to Kprobes via the
+notifier_call_chain mechanism.  Kprobes executes the "pre_handler"
+associated with the kprobe, passing the handler the addresses of the
+kprobe struct and the saved registers.
+
+Next, Kprobes single-steps its copy of the probed instruction.
+(It would be simpler to single-step the actual instruction in place,
+but then Kprobes would have to temporarily remove the breakpoint
+instruction.  This would open a small time window when another CPU
+could sail right past the probepoint.)
+
+After the instruction is single-stepped, Kprobes executes the
+"post_handler," if any, that is associated with the kprobe.
+Execution then continues with the instruction following the probepoint.
+
+Changing Execution Path
+-----------------------
+
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
+
+Return Probes
+-------------
+
+How Does a Return Probe Work?
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+When you call register_kretprobe(), Kprobes establishes a kprobe at
+the entry to the function.  When the probed function is called and this
+probe is hit, Kprobes saves a copy of the return address, and replaces
+the return address with the address of a "trampoline."  The trampoline
+is an arbitrary piece of code -- typically just a nop instruction.
+At boot time, Kprobes registers a kprobe at the trampoline.
+
+When the probed function executes its return instruction, control
+passes to the trampoline and that probe is hit.  Kprobes' trampoline
+handler calls the user-specified return handler associated with the
+kretprobe, then sets the saved instruction pointer to the saved return
+address, and that's where execution resumes upon return from the trap.
+
+While the probed function is executing, its return address is
+stored in an object of type kretprobe_instance.  Before calling
+register_kretprobe(), the user sets the maxactive field of the
+kretprobe struct to specify how many instances of the specified
+function can be probed simultaneously.  register_kretprobe()
+pre-allocates the indicated number of kretprobe_instance objects.
+
+For example, if the function is non-recursive and is called with a
+spinlock held, maxactive = 1 should be enough.  If the function is
+non-recursive and can never relinquish the CPU (e.g., via a semaphore
+or preemption), NR_CPUS should be enough.  If maxactive <= 0, it is
+set to a default value.  If CONFIG_PREEMPT is enabled, the default
+is max(10, 2*NR_CPUS).  Otherwise, the default is NR_CPUS.
+
+It's not a disaster if you set maxactive too low; you'll just miss
+some probes.  In the kretprobe struct, the nmissed field is set to
+zero when the return probe is registered, and is incremented every
+time the probed function is entered but there is no kretprobe_instance
+object available for establishing the return probe.
+
+Kretprobe entry-handler
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Kretprobes also provides an optional user-specified handler which runs
+on function entry. This handler is specified by setting the entry_handler
+field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the
+function entry is hit, the user-defined entry_handler, if any, is invoked.
+If the entry_handler returns 0 (success) then a corresponding return handler
+is guaranteed to be called upon function return. If the entry_handler
+returns a non-zero error then Kprobes leaves the return address as is, and
+the kretprobe has no further effect for that particular function instance.
+
+Multiple entry and return handler invocations are matched using the unique
+kretprobe_instance object associated with them. Additionally, a user
+may also specify per return-instance private data to be part of each
+kretprobe_instance object. This is especially useful when sharing private
+data between corresponding user entry and return handlers. The size of each
+private data object can be specified at kretprobe registration time by
+setting the data_size field of the kretprobe struct. This data can be
+accessed through the data field of each kretprobe_instance object.
+
+In case probed function is entered but there is no kretprobe_instance
+object available, then in addition to incrementing the nmissed count,
+the user entry_handler invocation is also skipped.
+
+.. _kprobes_jump_optimization:
+
+How Does Jump Optimization Work?
+--------------------------------
+
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
+the "debug.kprobes_optimization" kernel parameter is set to 1 (see
+sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
+instruction instead of a breakpoint instruction at each probepoint.
+
+Init a Kprobe
+^^^^^^^^^^^^^
+
+When a probe is registered, before attempting this optimization,
+Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
+address. So, even if it's not possible to optimize this particular
+probepoint, there'll be a probe there.
+
+Safety Check
+^^^^^^^^^^^^
+
+Before optimizing a probe, Kprobes performs the following safety checks:
+
+- Kprobes verifies that the region that will be replaced by the jump
+  instruction (the "optimized region") lies entirely within one function.
+  (A jump instruction is multiple bytes, and so may overlay multiple
+  instructions.)
+
+- Kprobes analyzes the entire function and verifies that there is no
+  jump into the optimized region.  Specifically:
+
+  - the function contains no indirect jump;
+  - the function contains no instruction that causes an exception (since
+    the fixup code triggered by the exception could jump back into the
+    optimized region -- Kprobes checks the exception tables to verify this);
+  - there is no near jump to the optimized region (other than to the first
+    byte).
+
+- For each instruction in the optimized region, Kprobes verifies that
+  the instruction can be executed out of line.
+
+Preparing Detour Buffer
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Next, Kprobes prepares a "detour" buffer, which contains the following
+instruction sequence:
+
+- code to push the CPU's registers (emulating a breakpoint trap)
+- a call to the trampoline code which calls user's probe handlers.
+- code to restore registers
+- the instructions from the optimized region
+- a jump back to the original execution path.
+
+Pre-optimization
+^^^^^^^^^^^^^^^^
+
+After preparing the detour buffer, Kprobes verifies that none of the
+following situations exist:
+
+- The probe has a post_handler.
+- Other instructions in the optimized region are probed.
+- The probe is disabled.
+
+In any of the above cases, Kprobes won't start optimizing the probe.
+Since these are temporary situations, Kprobes tries to start
+optimizing it again if the situation is changed.
+
+If the kprobe can be optimized, Kprobes enqueues the kprobe to an
+optimizing list, and kicks the kprobe-optimizer workqueue to optimize
+it.  If the to-be-optimized probepoint is hit before being optimized,
+Kprobes returns control to the original instruction path by setting
+the CPU's instruction pointer to the copied code in the detour buffer
+-- thus at least avoiding the single-step.
+
+Optimization
+^^^^^^^^^^^^
+
+The Kprobe-optimizer doesn't insert the jump instruction immediately;
+rather, it calls synchronize_rcu() for safety first, because it's
+possible for a CPU to be interrupted in the middle of executing the
+optimized region [3]_.  As you know, synchronize_rcu() can ensure
+that all interruptions that were active when synchronize_rcu()
+was called are done, but only if CONFIG_PREEMPT=n.  So, this version
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
+
+After that, the Kprobe-optimizer calls stop_machine() to replace
+the optimized region with a jump instruction to the detour buffer,
+using text_poke_smp().
+
+Unoptimization
+^^^^^^^^^^^^^^
+
+When an optimized kprobe is unregistered, disabled, or blocked by
+another kprobe, it will be unoptimized.  If this happens before
+the optimization is complete, the kprobe is just dequeued from the
+optimized list.  If the optimization has been done, the jump is
+replaced with the original code (except for an int3 breakpoint in
+the first byte) by using text_poke_smp().
+
+.. [3] Please imagine that the 2nd instruction is interrupted and then
+   the optimizer replaces the 2nd instruction with the jump *address*
+   while the interrupt handler is running. When the interrupt
+   returns to original address, there is no valid instruction,
+   and it causes an unexpected result.
+
+.. [4] This optimization-safety checking may be replaced with the
+   stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+   kernel.
+
+NOTE for geeks:
+The jump optimization changes the kprobe's pre_handler behavior.
+Without optimization, the pre_handler can change the kernel's execution
+path by changing regs->ip and returning 1.  However, when the probe
+is optimized, that modification is ignored.  Thus, if you want to
+tweak the kernel's execution path, you need to suppress optimization,
+using one of the following techniques:
+
+- Specify an empty function for the kprobe's post_handler.
+
+or
+
+- Execute 'sysctl -w debug.kprobes_optimization=n'
+
+.. _kprobes_blacklist:
+
+Blacklist
+---------
+
+Kprobes can probe most of the kernel except itself. This means
+that there are some functions where kprobes cannot probe. Probing
+(trapping) such functions can cause a recursive trap (e.g. double
+fault) or the nested probe handler may never be called.
+Kprobes manages such functions as a blacklist.
+If you want to add a function into the blacklist, you just need
+to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro
+to specify a blacklisted function.
+Kprobes checks the given probe address against the blacklist and
+rejects registering it, if the given address is in the blacklist.
+
+.. _kprobes_archs_supported:
+
+Architectures Supported
+=======================
+
+Kprobes and return probes are implemented on the following
+architectures:
+
+- i386 (Supports jump optimization)
+- x86_64 (AMD-64, EM64T) (Supports jump optimization)
+- ppc64
+- ia64 (Does not support probes on instruction slot1.)
+- sparc64 (Return probes not yet implemented.)
+- arm
+- ppc
+- mips
+- s390
+- parisc
+
+Configuring Kprobes
+===================
+
+When configuring the kernel using make menuconfig/xconfig/oldconfig,
+ensure that CONFIG_KPROBES is set to "y". Under "General setup", look
+for "Kprobes".
+
+So that you can load and unload Kprobes-based instrumentation modules,
+make sure "Loadable module support" (CONFIG_MODULES) and "Module
+unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
+
+Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL
+are set to "y", since kallsyms_lookup_name() is used by the in-kernel
+kprobe address resolution code.
+
+If you need to insert a probe in the middle of a function, you may find
+it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
+so you can use "objdump -d -l vmlinux" to see the source-to-object
+code mapping.
+
+API Reference
+=============
+
+The Kprobes API includes a "register" function and an "unregister"
+function for each type of probe. The API also includes "register_*probes"
+and "unregister_*probes" functions for (un)registering arrays of probes.
+Here are terse, mini-man-page specifications for these functions and
+the associated probe handlers that you'll write. See the files in the
+samples/kprobes/ sub-directory for examples.
+
+register_kprobe
+---------------
+
+::
+
+	#include <linux/kprobes.h>
+	int register_kprobe(struct kprobe *kp);
+
+Sets a breakpoint at the address kp->addr.  When the breakpoint is
+hit, Kprobes calls kp->pre_handler.  After the probed instruction
+is single-stepped, Kprobe calls kp->post_handler.  If a fault
+occurs during execution of kp->pre_handler or kp->post_handler,
+or during single-stepping of the probed instruction, Kprobes calls
+kp->fault_handler.  Any or all handlers can be NULL. If kp->flags
+is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
+so, its handlers aren't hit until calling enable_kprobe(kp).
+
+.. note::
+
+   1. With the introduction of the "symbol_name" field to struct kprobe,
+      the probepoint address resolution will now be taken care of by the kernel.
+      The following will now work::
+
+	kp.symbol_name = "symbol_name";
+
+      (64-bit powerpc intricacies such as function descriptors are handled
+      transparently)
+
+   2. Use the "offset" field of struct kprobe if the offset into the symbol
+      to install a probepoint is known. This field is used to calculate the
+      probepoint.
+
+   3. Specify either the kprobe "symbol_name" OR the "addr". If both are
+      specified, kprobe registration will fail with -EINVAL.
+
+   4. With CISC architectures (such as i386 and x86_64), the kprobes code
+      does not validate if the kprobe.addr is at an instruction boundary.
+      Use "offset" with caution.
+
+register_kprobe() returns 0 on success, or a negative errno otherwise.
+
+User's pre-handler (kp->pre_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int pre_handler(struct kprobe *p, struct pt_regs *regs);
+
+Called with p pointing to the kprobe associated with the breakpoint,
+and regs pointing to the struct containing the registers saved when
+the breakpoint was hit.  Return 0 here unless you're a Kprobes geek.
+
+User's post-handler (kp->post_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	void post_handler(struct kprobe *p, struct pt_regs *regs,
+			  unsigned long flags);
+
+p and regs are as described for the pre_handler.  flags always seems
+to be zero.
+
+User's fault-handler (kp->fault_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
+
+p and regs are as described for the pre_handler.  trapnr is the
+architecture-specific trap number associated with the fault (e.g.,
+on i386, 13 for a general protection fault or 14 for a page fault).
+Returns 1 if it successfully handled the exception.
+
+register_kretprobe
+------------------
+
+::
+
+	#include <linux/kprobes.h>
+	int register_kretprobe(struct kretprobe *rp);
+
+Establishes a return probe for the function whose address is
+rp->kp.addr.  When that function returns, Kprobes calls rp->handler.
+You must set rp->maxactive appropriately before you call
+register_kretprobe(); see "How Does a Return Probe Work?" for details.
+
+register_kretprobe() returns 0 on success, or a negative errno
+otherwise.
+
+User's return-probe handler (rp->handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int kretprobe_handler(struct kretprobe_instance *ri,
+			      struct pt_regs *regs);
+
+regs is as described for kprobe.pre_handler.  ri points to the
+kretprobe_instance object, of which the following fields may be
+of interest:
+
+- ret_addr: the return address
+- rp: points to the corresponding kretprobe object
+- task: points to the corresponding task struct
+- data: points to per return-instance private data; see "Kretprobe
+	entry-handler" for details.
+
+The regs_return_value(regs) macro provides a simple abstraction to
+extract the return value from the appropriate register as defined by
+the architecture's ABI.
+
+The handler's return value is currently ignored.
+
+unregister_*probe
+------------------
+
+::
+
+	#include <linux/kprobes.h>
+	void unregister_kprobe(struct kprobe *kp);
+	void unregister_kretprobe(struct kretprobe *rp);
+
+Removes the specified probe.  The unregister function can be called
+at any time after the probe has been registered.
+
+.. note::
+
+   If the functions find an incorrect probe (ex. an unregistered probe),
+   they clear the addr field of the probe.
+
+register_*probes
+----------------
+
+::
+
+	#include <linux/kprobes.h>
+	int register_kprobes(struct kprobe **kps, int num);
+	int register_kretprobes(struct kretprobe **rps, int num);
+
+Registers each of the num probes in the specified array.  If any
+error occurs during registration, all probes in the array, up to
+the bad probe, are safely unregistered before the register_*probes
+function returns.
+
+- kps/rps: an array of pointers to ``*probe`` data structures
+- num: the number of the array entries.
+
+.. note::
+
+   You have to allocate(or define) an array of pointers and set all
+   of the array entries before using these functions.
+
+unregister_*probes
+------------------
+
+::
+
+	#include <linux/kprobes.h>
+	void unregister_kprobes(struct kprobe **kps, int num);
+	void unregister_kretprobes(struct kretprobe **rps, int num);
+
+Removes each of the num probes in the specified array at once.
+
+.. note::
+
+   If the functions find some incorrect probes (ex. unregistered
+   probes) in the specified array, they clear the addr field of those
+   incorrect probes. However, other probes in the array are
+   unregistered correctly.
+
+disable_*probe
+--------------
+
+::
+
+	#include <linux/kprobes.h>
+	int disable_kprobe(struct kprobe *kp);
+	int disable_kretprobe(struct kretprobe *rp);
+
+Temporarily disables the specified ``*probe``. You can enable it again by using
+enable_*probe(). You must specify the probe which has been registered.
+
+enable_*probe
+-------------
+
+::
+
+	#include <linux/kprobes.h>
+	int enable_kprobe(struct kprobe *kp);
+	int enable_kretprobe(struct kretprobe *rp);
+
+Enables ``*probe`` which has been disabled by disable_*probe(). You must specify
+the probe which has been registered.
+
+Kprobes Features and Limitations
+================================
+
+Kprobes allows multiple probes at the same address. Also,
+a probepoint for which there is a post_handler cannot be optimized.
+So if you install a kprobe with a post_handler, at an optimized
+probepoint, the probepoint will be unoptimized automatically.
+
+In general, you can install a probe anywhere in the kernel.
+In particular, you can probe interrupt handlers.  Known exceptions
+are discussed in this section.
+
+The register_*probe functions will return -EINVAL if you attempt
+to install a probe in the code that implements Kprobes (mostly
+kernel/kprobes.c and ``arch/*/kernel/kprobes.c``, but also functions such
+as do_page_fault and notifier_call_chain).
+
+If you install a probe in an inline-able function, Kprobes makes
+no attempt to chase down all inline instances of the function and
+install probes there.  gcc may inline a function without being asked,
+so keep this in mind if you're not seeing the probe hits you expect.
+
+A probe handler can modify the environment of the probed function
+-- e.g., by modifying kernel data structures, or by modifying the
+contents of the pt_regs struct (which are restored to the registers
+upon return from the breakpoint).  So Kprobes can be used, for example,
+to install a bug fix or to inject faults for testing.  Kprobes, of
+course, has no way to distinguish the deliberately injected faults
+from the accidental ones.  Don't drink and probe.
+
+Kprobes makes no attempt to prevent probe handlers from stepping on
+each other -- e.g., probing printk() and then calling printk() from a
+probe handler.  If a probe handler hits a probe, that second probe's
+handlers won't be run in that instance, and the kprobe.nmissed member
+of the second probe will be incremented.
+
+As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
+the same handler) may run concurrently on different CPUs.
+
+Kprobes does not use mutexes or allocate memory except during
+registration and unregistration.
+
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state.  (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64).  In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
+
+Since a return probe is implemented by replacing the return
+address with the trampoline's address, stack backtraces and calls
+to __builtin_return_address() will typically yield the trampoline's
+address instead of the real return address for kretprobed functions.
+(As far as we can tell, __builtin_return_address() is used only
+for instrumentation and error reporting.)
+
+If the number of times a function is called does not match the number
+of times it returns, registering a return probe on that function may
+produce undesirable results. In such a case, a line:
+kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c
+gets printed. With this information, one will be able to correlate the
+exact instance of the kretprobe that caused the problem. We have the
+do_exit() case covered. do_execve() and do_fork() are not an issue.
+We're unaware of other specific cases where this could be a problem.
+
+If, upon entry to or exit from a function, the CPU is running on
+a stack other than that of the current task, registering a return
+probe on that function may produce undesirable results.  For this
+reason, Kprobes doesn't support return probes (or kprobes)
+on the x86_64 version of __switch_to(); the registration functions
+return -EINVAL.
+
+On x86/x86-64, since the Jump Optimization of Kprobes modifies
+instructions widely, there are some limitations to optimization. To
+explain it, we introduce some terminology. Imagine a 3-instruction
+sequence consisting of a two 2-byte instructions and one 3-byte
+instruction.
+
+::
+
+		IA
+		|
+	[-2][-1][0][1][2][3][4][5][6][7]
+		[ins1][ins2][  ins3 ]
+		[<-     DCR       ->]
+		[<- JTPR ->]
+
+	ins1: 1st Instruction
+	ins2: 2nd Instruction
+	ins3: 3rd Instruction
+	IA:  Insertion Address
+	JTPR: Jump Target Prohibition Region
+	DCR: Detoured Code Region
+
+The instructions in DCR are copied to the out-of-line buffer
+of the kprobe, because the bytes in DCR are replaced by
+a 5-byte jump instruction. So there are several limitations.
+
+a) The instructions in DCR must be relocatable.
+b) The instructions in DCR must not include a call instruction.
+c) JTPR must not be targeted by any jump or call instruction.
+d) DCR must not straddle the border between functions.
+
+Anyway, these limitations are checked by the in-kernel instruction
+decoder, so you don't need to worry about that.
+
+Probe Overhead
+==============
+
+On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
+microseconds to process.  Specifically, a benchmark that hits the same
+probepoint repeatedly, firing a simple handler each time, reports 1-2
+million hits per second, depending on the architecture.  A return-probe
+hit typically takes 50-75% longer than a kprobe hit.
+When you have a return probe set on a function, adding a kprobe at
+the entry to that function adds essentially no overhead.
+
+Here are sample overhead figures (in usec) for different architectures::
+
+  k = kprobe; r = return probe; kr = kprobe + return probe
+  on same function
+
+  i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
+  k = 0.57 usec; r = 0.92; kr = 0.99
+
+  x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
+  k = 0.49 usec; r = 0.80; kr = 0.82
+
+  ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
+  k = 0.77 usec; r = 1.26; kr = 1.45
+
+Optimized Probe Overhead
+------------------------
+
+Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
+process. Here are sample overhead figures (in usec) for x86 architectures::
+
+  k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+  r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+
+  i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+  k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+
+  x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+  k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+
+TODO
+====
+
+a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
+   programming interface for probe-based instrumentation.  Try it out.
+b. Kernel return probes for sparc64.
+c. Support for other architectures.
+d. User-space probes.
+e. Watchpoint probes (which fire on data references).
+
+Kprobes Example
+===============
+
+See samples/kprobes/kprobe_example.c
+
+Kretprobes Example
+==================
+
+See samples/kprobes/kretprobe_example.c
+
+For additional information on Kprobes, refer to the following URLs:
+
+- http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
+- http://www.redhat.com/magazine/005mar05/features/kprobes/
+- http://www-users.cs.umn.edu/~boutcher/kprobes/
+- http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
+
+Deprecated Features
+===================
+
+Jprobes is now a deprecated feature. People who are depending on it should
+migrate to other tracing features or use older kernels. Please consider to
+migrate your tool to one of the following options:
+
+- Use trace-event to trace target function with arguments.
+
+  trace-event is a low-overhead (and almost no visible overhead if it
+  is off) statically defined event interface. You can define new events
+  and trace it via ftrace or any other tracing tools.
+
+  See the following urls:
+
+    - https://lwn.net/Articles/379903/
+    - https://lwn.net/Articles/381064/
+    - https://lwn.net/Articles/383362/
+
+- Use ftrace dynamic events (kprobe event) with perf-probe.
+
+  If you build your kernel with debug info (CONFIG_DEBUG_INFO=y), you can
+  find which register/stack is assigned to which local variable or arguments
+  by using perf-probe and set up new event to trace it.
+
+  See following documents:
+
+  - Documentation/trace/kprobetrace.rst
+  - Documentation/trace/events.rst
+  - tools/perf/Documentation/perf-probe.txt
+
+
+The kprobes debugfs interface
+=============================
+
+
+With recent kernels (> 2.6.20) the list of registered kprobes is visible
+under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).
+
+/sys/kernel/debug/kprobes/list: Lists all registered probes on the system::
+
+	c015d71a  k  vfs_read+0x0
+	c03dedc5  r  tcp_v4_rcv+0x0
+
+The first column provides the kernel address where the probe is inserted.
+The second column identifies the type of probe (k - kprobe and r - kretprobe)
+while the third column specifies the symbol+offset of the probe.
+If the probed function belongs to a module, the module name is also
+specified. Following columns show probe status. If the probe is on
+a virtual address that is no longer valid (module init sections, module
+virtual addresses that correspond to modules that've been unloaded),
+such probes are marked with [GONE]. If the probe is temporarily disabled,
+such probes are marked with [DISABLED]. If the probe is optimized, it is
+marked with [OPTIMIZED]. If the probe is ftrace-based, it is marked with
+[FTRACE].
+
+/sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
+
+Provides a knob to globally and forcibly turn registered kprobes ON or OFF.
+By default, all kprobes are enabled. By echoing "0" to this file, all
+registered probes will be disarmed, till such time a "1" is echoed to this
+file. Note that this knob just disarms and arms all kprobes and doesn't
+change each probe's disabling state. This means that disabled kprobes (marked
+[DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
+
+
+The kprobes sysctl interface
+============================
+
+/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
+
+When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
+a knob to globally and forcibly turn jump optimization (see section
+:ref:`kprobes_jump_optimization`) ON or OFF. By default, jump optimization
+is allowed (ON). If you echo "0" to this file or set
+"debug.kprobes_optimization" to 0 via sysctl, all optimized probes will be
+unoptimized, and any new probes registered after that will not be optimized.
+
+Note that this knob *changes* the optimized state. This means that optimized
+probes (marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+removed). If the knob is turned on, they will be optimized again.
+
diff --git a/Documentation/staging/lzo.rst b/Documentation/staging/lzo.rst
new file mode 100644
index 000000000000..f65b51523014
--- /dev/null
+++ b/Documentation/staging/lzo.rst
@@ -0,0 +1,202 @@
+===========================================================
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+============
+
+  This is not a specification. No specification seems to be publicly available
+  for the LZO stream format. This document describes what input format the LZO
+  decompressor as implemented in the Linux kernel understands. The file subject
+  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+  the compressor nor on any other implementations though it seems likely that
+  the format matches the standard one. The purpose of this document is to
+  better understand what the code does in order to propose more efficient fixes
+  for future bug reports.
+
+Description
+===========
+
+  The stream is composed of a series of instructions, operands, and data. The
+  instructions consist in a few bits representing an opcode, and bits forming
+  the operands for the instruction, whose size and position depend on the
+  opcode and on the number of literals copied by previous instruction. The
+  operands are used to indicate:
+
+    - a distance when copying data from the dictionary (past output buffer)
+    - a length (number of bytes to copy from dictionary)
+    - the number of literals to copy, which is retained in variable "state"
+      as a piece of information for next instructions.
+
+  Optionally depending on the opcode and operands, extra data may follow. These
+  extra data can be a complement for the operand (eg: a length or a distance
+  encoded on larger values), or a literal to be copied to the output buffer.
+
+  The first byte of the block follows a different encoding from other bytes, it
+  seems to be optimized for literal use only, since there is no dictionary yet
+  prior to that byte.
+
+  Lengths are always encoded on a variable size starting with a small number
+  of bits in the operand. If the number of bits isn't enough to represent the
+  length, up to 255 may be added in increments by consuming more bytes with a
+  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+  around 255:1). The variable length encoding using #bits is always the same::
+
+       length = byte & ((1 << #bits) - 1)
+       if (!length) {
+               length = ((1 << #bits) - 1)
+               length += 255*(number of zero bytes)
+               length += first-non-zero-byte
+       }
+       length += constant (generally 2 or 3)
+
+  For references to the dictionary, distances are relative to the output
+  pointer. Distances are encoded using very few bits belonging to certain
+  ranges, resulting in multiple copy instructions using different encodings.
+  Certain encodings involve one extra byte, others involve two extra bytes
+  forming a little-endian 16-bit quantity (marked LE16 below).
+
+  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+  are copied before starting the next instruction. The number of literals that
+  were copied may change the meaning and behaviour of the next instruction. In
+  practice, only one instruction needs to know whether 0, less than 4, or more
+  literals were copied. This is the information stored in the <state> variable
+  in this implementation. This number of immediate literals to be copied is
+  generally encoded in the last two bits of the instruction but may also be
+  taken from the last two bits of an extra operand (eg: distance).
+
+  End of stream is declared when a block copy of distance 0 is seen. Only one
+  instruction may encode this distance (0001HLLL), it takes one LE16 operand
+  for the distance, thus requiring 3 bytes.
+
+  .. important::
+
+     In the code some length checks are missing because certain instructions
+     are called under the assumption that a certain number of bytes follow
+     because it has already been guaranteed before parsing the instructions.
+     They just have to "refill" this credit if they consume extra bytes. This
+     is an implementation design choice independent on the algorithm or
+     encoding.
+
+Versions
+
+0: Original version
+1: LZO-RLE
+
+Version 1 of LZO implements an extension to encode runs of zeros using run
+length encoding. This improves speed for data with many zeros, which is a
+common case for zram. This modifies the bitstream in a backwards compatible way
+(v1 can correctly decompress v0 compressed data, but v0 cannot read v1 data).
+
+For maximum compatibility, both versions are available under different names
+(lzo and lzo-rle). Differences in the encoding are noted in this document with
+e.g.: version 1 only.
+
+Byte sequences
+==============
+
+  First byte encoding::
+
+      0..16   : follow regular instruction encoding, see below. It is worth
+                noting that code 16 will represent a block copy from the
+                dictionary which is empty, and that it will always be
+                invalid at this place.
+
+      17      : bitstream version. If the first byte is 17, and compressed
+                stream length is at least 5 bytes (length of shortest possible
+                versioned bitstream), the next byte gives the bitstream version
+                (version 1 only).
+                Otherwise, the bitstream version is 0.
+
+      18..21  : copy 0..3 literals
+                state = (byte - 17) = 0..3  [ copy <state> literals ]
+                skip byte
+
+      22..255 : copy literal string
+                length = (byte - 17) = 4..238
+                state = 4 [ don't copy extra literals ]
+                skip byte
+
+  Instruction encoding::
+
+      0 0 0 0 X X X X  (0..15)
+        Depends on the number of literals copied by the last instruction.
+        If last instruction did not copy any literal (state == 0), this
+        encoding will be a copy of 4 or more literal, and must be interpreted
+        like this :
+
+           0 0 0 0 L L L L  (0..15)  : copy long literal string
+           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+           state = 4  (no extra literals are copied)
+
+        If last instruction used to copy between 1 to 3 literals (encoded in
+        the instruction's opcode or distance), the instruction is a copy of a
+        2-byte block from the dictionary within a 1kB distance. It is worth
+        noting that this instruction provides little savings since it uses 2
+        bytes to encode a copy of 2 other bytes but it encodes the number of
+        following literals for free. It must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
+           length = 2
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 1
+
+        If last instruction used to copy 4 or more literals (as detected by
+        state == 4), the instruction becomes a copy of a 3-byte block from the
+        dictionary from a 2..3kB distance, and must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
+           length = 3
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 2049
+
+      0 0 0 1 H L L L  (16..31)
+           Copy of a block within 16..48kB distance (preferably less than 10B)
+           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = 16384 + (H << 14) + D
+           state = S (copy S literals after this block)
+           End of stream is reached if distance == 16384
+           In version 1 only, to prevent ambiguity with the RLE case when
+           ((distance & 0x803f) == 0x803f) && (261 <= length <= 264), the
+           compressor must not emit block copies where distance and length
+           meet these conditions.
+
+        In version 1 only, this instruction is also used to encode a run of
+           zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
+           In this case, it is followed by a fourth byte, X.
+           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4
+
+      0 0 1 L L L L L  (32..63)
+           Copy of small block within 16kB distance (preferably less than 34B)
+           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = D + 1
+           state = S (copy S literals after this block)
+
+      0 1 L D D D S S  (64..127)
+           Copy 3-4 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 3 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+      1 L L D D D S S  (128..255)
+           Copy 5-8 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 5 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+Authors
+=======
+
+  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+  analysis of the decompression code available in Linux 3.16-rc5, and updated
+  by Dave Rodgman <dave.rodgman@arm.com> on 2018/10/30 to introduce run-length
+  encoding. The code is tricky, it is possible that this document contains
+  mistakes or that a few corner cases were overlooked. In any case, please
+  report any doubt, fix, or proposed updates to the author(s) so that the
+  document can be updated.
diff --git a/Documentation/staging/remoteproc.rst b/Documentation/staging/remoteproc.rst
new file mode 100644
index 000000000000..9cccd3dd6a4b
--- /dev/null
+++ b/Documentation/staging/remoteproc.rst
@@ -0,0 +1,359 @@
+==========================
+Remote Processor Framework
+==========================
+
+Introduction
+============
+
+Modern SoCs typically have heterogeneous remote processor devices in asymmetric
+multiprocessing (AMP) configurations, which may be running different instances
+of operating system, whether it's Linux or any other flavor of real-time OS.
+
+OMAP4, for example, has dual Cortex-A9, dual Cortex-M3 and a C64x+ DSP.
+In a typical configuration, the dual cortex-A9 is running Linux in a SMP
+configuration, and each of the other three cores (two M3 cores and a DSP)
+is running its own instance of RTOS in an AMP configuration.
+
+The remoteproc framework allows different platforms/architectures to
+control (power on, load firmware, power off) those remote processors while
+abstracting the hardware differences, so the entire driver doesn't need to be
+duplicated. In addition, this framework also adds rpmsg virtio devices
+for remote processors that supports this kind of communication. This way,
+platform-specific remoteproc drivers only need to provide a few low-level
+handlers, and then all rpmsg drivers will then just work
+(for more information about the virtio-based rpmsg bus and its drivers,
+please read Documentation/staging/rpmsg.rst).
+Registration of other types of virtio devices is now also possible. Firmwares
+just need to publish what kind of virtio devices do they support, and then
+remoteproc will add those devices. This makes it possible to reuse the
+existing virtio drivers with remote processor backends at a minimal development
+cost.
+
+User API
+========
+
+::
+
+  int rproc_boot(struct rproc *rproc)
+
+Boot a remote processor (i.e. load its firmware, power it on, ...).
+
+If the remote processor is already powered on, this function immediately
+returns (successfully).
+
+Returns 0 on success, and an appropriate error value otherwise.
+Note: to use this function you should already have a valid rproc
+handle. There are several ways to achieve that cleanly (devres, pdata,
+the way remoteproc_rpmsg.c does this, or, if this becomes prevalent, we
+might also consider using dev_archdata for this).
+
+::
+
+  void rproc_shutdown(struct rproc *rproc)
+
+Power off a remote processor (previously booted with rproc_boot()).
+In case @rproc is still being used by an additional user(s), then
+this function will just decrement the power refcount and exit,
+without really powering off the device.
+
+Every call to rproc_boot() must (eventually) be accompanied by a call
+to rproc_shutdown(). Calling rproc_shutdown() redundantly is a bug.
+
+.. note::
+
+  we're not decrementing the rproc's refcount, only the power refcount.
+  which means that the @rproc handle stays valid even after
+  rproc_shutdown() returns, and users can still use it with a subsequent
+  rproc_boot(), if needed.
+
+::
+
+  struct rproc *rproc_get_by_phandle(phandle phandle)
+
+Find an rproc handle using a device tree phandle. Returns the rproc
+handle on success, and NULL on failure. This function increments
+the remote processor's refcount, so always use rproc_put() to
+decrement it back once rproc isn't needed anymore.
+
+Typical usage
+=============
+
+::
+
+  #include <linux/remoteproc.h>
+
+  /* in case we were given a valid 'rproc' handle */
+  int dummy_rproc_example(struct rproc *my_rproc)
+  {
+	int ret;
+
+	/* let's power on and boot our remote processor */
+	ret = rproc_boot(my_rproc);
+	if (ret) {
+		/*
+		 * something went wrong. handle it and leave.
+		 */
+	}
+
+	/*
+	 * our remote processor is now powered on... give it some work
+	 */
+
+	/* let's shut it down now */
+	rproc_shutdown(my_rproc);
+  }
+
+API for implementors
+====================
+
+::
+
+  struct rproc *rproc_alloc(struct device *dev, const char *name,
+				const struct rproc_ops *ops,
+				const char *firmware, int len)
+
+Allocate a new remote processor handle, but don't register
+it yet. Required parameters are the underlying device, the
+name of this remote processor, platform-specific ops handlers,
+the name of the firmware to boot this rproc with, and the
+length of private data needed by the allocating rproc driver (in bytes).
+
+This function should be used by rproc implementations during
+initialization of the remote processor.
+
+After creating an rproc handle using this function, and when ready,
+implementations should then call rproc_add() to complete
+the registration of the remote processor.
+
+On success, the new rproc is returned, and on failure, NULL.
+
+.. note::
+
+  **never** directly deallocate @rproc, even if it was not registered
+  yet. Instead, when you need to unroll rproc_alloc(), use rproc_free().
+
+::
+
+  void rproc_free(struct rproc *rproc)
+
+Free an rproc handle that was allocated by rproc_alloc.
+
+This function essentially unrolls rproc_alloc(), by decrementing the
+rproc's refcount. It doesn't directly free rproc; that would happen
+only if there are no other references to rproc and its refcount now
+dropped to zero.
+
+::
+
+  int rproc_add(struct rproc *rproc)
+
+Register @rproc with the remoteproc framework, after it has been
+allocated with rproc_alloc().
+
+This is called by the platform-specific rproc implementation, whenever
+a new remote processor device is probed.
+
+Returns 0 on success and an appropriate error code otherwise.
+Note: this function initiates an asynchronous firmware loading
+context, which will look for virtio devices supported by the rproc's
+firmware.
+
+If found, those virtio devices will be created and added, so as a result
+of registering this remote processor, additional virtio drivers might get
+probed.
+
+::
+
+  int rproc_del(struct rproc *rproc)
+
+Unroll rproc_add().
+
+This function should be called when the platform specific rproc
+implementation decides to remove the rproc device. it should
+_only_ be called if a previous invocation of rproc_add()
+has completed successfully.
+
+After rproc_del() returns, @rproc is still valid, and its
+last refcount should be decremented by calling rproc_free().
+
+Returns 0 on success and -EINVAL if @rproc isn't valid.
+
+::
+
+  void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type)
+
+Report a crash in a remoteproc
+
+This function must be called every time a crash is detected by the
+platform specific rproc implementation. This should not be called from a
+non-remoteproc driver. This function can be called from atomic/interrupt
+context.
+
+Implementation callbacks
+========================
+
+These callbacks should be provided by platform-specific remoteproc
+drivers::
+
+  /**
+   * struct rproc_ops - platform-specific device handlers
+   * @start:	power on the device and boot it
+   * @stop:	power off the device
+   * @kick:	kick a virtqueue (virtqueue id given as a parameter)
+   */
+  struct rproc_ops {
+	int (*start)(struct rproc *rproc);
+	int (*stop)(struct rproc *rproc);
+	void (*kick)(struct rproc *rproc, int vqid);
+  };
+
+Every remoteproc implementation should at least provide the ->start and ->stop
+handlers. If rpmsg/virtio functionality is also desired, then the ->kick handler
+should be provided as well.
+
+The ->start() handler takes an rproc handle and should then power on the
+device and boot it (use rproc->priv to access platform-specific private data).
+The boot address, in case needed, can be found in rproc->bootaddr (remoteproc
+core puts there the ELF entry point).
+On success, 0 should be returned, and on failure, an appropriate error code.
+
+The ->stop() handler takes an rproc handle and powers the device down.
+On success, 0 is returned, and on failure, an appropriate error code.
+
+The ->kick() handler takes an rproc handle, and an index of a virtqueue
+where new message was placed in. Implementations should interrupt the remote
+processor and let it know it has pending messages. Notifying remote processors
+the exact virtqueue index to look in is optional: it is easy (and not
+too expensive) to go through the existing virtqueues and look for new buffers
+in the used rings.
+
+Binary Firmware Structure
+=========================
+
+At this point remoteproc supports ELF32 and ELF64 firmware binaries. However,
+it is quite expected that other platforms/devices which we'd want to
+support with this framework will be based on different binary formats.
+
+When those use cases show up, we will have to decouple the binary format
+from the framework core, so we can support several binary formats without
+duplicating common code.
+
+When the firmware is parsed, its various segments are loaded to memory
+according to the specified device address (might be a physical address
+if the remote processor is accessing memory directly).
+
+In addition to the standard ELF segments, most remote processors would
+also include a special section which we call "the resource table".
+
+The resource table contains system resources that the remote processor
+requires before it should be powered on, such as allocation of physically
+contiguous memory, or iommu mapping of certain on-chip peripherals.
+Remotecore will only power up the device after all the resource table's
+requirement are met.
+
+In addition to system resources, the resource table may also contain
+resource entries that publish the existence of supported features
+or configurations by the remote processor, such as trace buffers and
+supported virtio devices (and their configurations).
+
+The resource table begins with this header::
+
+  /**
+   * struct resource_table - firmware resource table header
+   * @ver: version number
+   * @num: number of resource entries
+   * @reserved: reserved (must be zero)
+   * @offset: array of offsets pointing at the various resource entries
+   *
+   * The header of the resource table, as expressed by this structure,
+   * contains a version number (should we need to change this format in the
+   * future), the number of available resource entries, and their offsets
+   * in the table.
+   */
+  struct resource_table {
+	u32 ver;
+	u32 num;
+	u32 reserved[2];
+	u32 offset[0];
+  } __packed;
+
+Immediately following this header are the resource entries themselves,
+each of which begins with the following resource entry header::
+
+  /**
+   * struct fw_rsc_hdr - firmware resource entry header
+   * @type: resource type
+   * @data: resource data
+   *
+   * Every resource entry begins with a 'struct fw_rsc_hdr' header providing
+   * its @type. The content of the entry itself will immediately follow
+   * this header, and it should be parsed according to the resource type.
+   */
+  struct fw_rsc_hdr {
+	u32 type;
+	u8 data[0];
+  } __packed;
+
+Some resources entries are mere announcements, where the host is informed
+of specific remoteproc configuration. Other entries require the host to
+do something (e.g. allocate a system resource). Sometimes a negotiation
+is expected, where the firmware requests a resource, and once allocated,
+the host should provide back its details (e.g. address of an allocated
+memory region).
+
+Here are the various resource types that are currently supported::
+
+  /**
+   * enum fw_resource_type - types of resource entries
+   *
+   * @RSC_CARVEOUT:   request for allocation of a physically contiguous
+   *		    memory region.
+   * @RSC_DEVMEM:     request to iommu_map a memory-based peripheral.
+   * @RSC_TRACE:	    announces the availability of a trace buffer into which
+   *		    the remote processor will be writing logs.
+   * @RSC_VDEV:       declare support for a virtio device, and serve as its
+   *		    virtio header.
+   * @RSC_LAST:       just keep this one at the end
+   * @RSC_VENDOR_START:	start of the vendor specific resource types range
+   * @RSC_VENDOR_END:	end of the vendor specific resource types range
+   *
+   * Please note that these values are used as indices to the rproc_handle_rsc
+   * lookup table, so please keep them sane. Moreover, @RSC_LAST is used to
+   * check the validity of an index before the lookup table is accessed, so
+   * please update it as needed.
+   */
+  enum fw_resource_type {
+	RSC_CARVEOUT		= 0,
+	RSC_DEVMEM		= 1,
+	RSC_TRACE		= 2,
+	RSC_VDEV		= 3,
+	RSC_LAST		= 4,
+	RSC_VENDOR_START	= 128,
+	RSC_VENDOR_END		= 512,
+  };
+
+For more details regarding a specific resource type, please see its
+dedicated structure in include/linux/remoteproc.h.
+
+We also expect that platform-specific resource entries will show up
+at some point. When that happens, we could easily add a new RSC_PLATFORM
+type, and hand those resources to the platform-specific rproc driver to handle.
+
+Virtio and remoteproc
+=====================
+
+The firmware should provide remoteproc information about virtio devices
+that it supports, and their configurations: a RSC_VDEV resource entry
+should specify the virtio device id (as in virtio_ids.h), virtio features,
+virtio config space, vrings information, etc.
+
+When a new remote processor is registered, the remoteproc framework
+will look for its resource table and will register the virtio devices
+it supports. A firmware may support any number of virtio devices, and
+of any type (a single remote processor can also easily support several
+rpmsg virtio devices this way, if desired).
+
+Of course, RSC_VDEV resource entries are only good enough for static
+allocation of virtio devices. Dynamic allocations will also be made possible
+using the rpmsg bus (similar to how we already do dynamic allocations of
+rpmsg channels; read more about it in rpmsg.txt).
diff --git a/Documentation/staging/rpmsg.rst b/Documentation/staging/rpmsg.rst
new file mode 100644
index 000000000000..24b7a9e1a5f9
--- /dev/null
+++ b/Documentation/staging/rpmsg.rst
@@ -0,0 +1,341 @@
+============================================
+Remote Processor Messaging (rpmsg) Framework
+============================================
+
+.. note::
+
+  This document describes the rpmsg bus and how to write rpmsg drivers.
+  To learn how to add rpmsg support for new platforms, check out remoteproc.txt
+  (also a resident of Documentation/).
+
+Introduction
+============
+
+Modern SoCs typically employ heterogeneous remote processor devices in
+asymmetric multiprocessing (AMP) configurations, which may be running
+different instances of operating system, whether it's Linux or any other
+flavor of real-time OS.
+
+OMAP4, for example, has dual Cortex-A9, dual Cortex-M3 and a C64x+ DSP.
+Typically, the dual cortex-A9 is running Linux in a SMP configuration,
+and each of the other three cores (two M3 cores and a DSP) is running
+its own instance of RTOS in an AMP configuration.
+
+Typically AMP remote processors employ dedicated DSP codecs and multimedia
+hardware accelerators, and therefore are often used to offload CPU-intensive
+multimedia tasks from the main application processor.
+
+These remote processors could also be used to control latency-sensitive
+sensors, drive random hardware blocks, or just perform background tasks
+while the main CPU is idling.
+
+Users of those remote processors can either be userland apps (e.g. multimedia
+frameworks talking with remote OMX components) or kernel drivers (controlling
+hardware accessible only by the remote processor, reserving kernel-controlled
+resources on behalf of the remote processor, etc..).
+
+Rpmsg is a virtio-based messaging bus that allows kernel drivers to communicate
+with remote processors available on the system. In turn, drivers could then
+expose appropriate user space interfaces, if needed.
+
+When writing a driver that exposes rpmsg communication to userland, please
+keep in mind that remote processors might have direct access to the
+system's physical memory and other sensitive hardware resources (e.g. on
+OMAP4, remote cores and hardware accelerators may have direct access to the
+physical memory, gpio banks, dma controllers, i2c bus, gptimers, mailbox
+devices, hwspinlocks, etc..). Moreover, those remote processors might be
+running RTOS where every task can access the entire memory/devices exposed
+to the processor. To minimize the risks of rogue (or buggy) userland code
+exploiting remote bugs, and by that taking over the system, it is often
+desired to limit userland to specific rpmsg channels (see definition below)
+it can send messages on, and if possible, minimize how much control
+it has over the content of the messages.
+
+Every rpmsg device is a communication channel with a remote processor (thus
+rpmsg devices are called channels). Channels are identified by a textual name
+and have a local ("source") rpmsg address, and remote ("destination") rpmsg
+address.
+
+When a driver starts listening on a channel, its rx callback is bound with
+a unique rpmsg local address (a 32-bit integer). This way when inbound messages
+arrive, the rpmsg core dispatches them to the appropriate driver according
+to their destination address (this is done by invoking the driver's rx handler
+with the payload of the inbound message).
+
+
+User API
+========
+
+::
+
+  int rpmsg_send(struct rpmsg_channel *rpdev, void *data, int len);
+
+sends a message across to the remote processor on a given channel.
+The caller should specify the channel, the data it wants to send,
+and its length (in bytes). The message will be sent on the specified
+channel, i.e. its source and destination address fields will be
+set to the channel's src and dst addresses.
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  int rpmsg_sendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst);
+
+sends a message across to the remote processor on a given channel,
+to a destination address provided by the caller.
+
+The caller should specify the channel, the data it wants to send,
+its length (in bytes), and an explicit destination address.
+
+The message will then be sent to the remote processor to which the
+channel belongs, using the channel's src address, and the user-provided
+dst address (thus the channel's dst address will be ignored).
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  int rpmsg_send_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+							void *data, int len);
+
+
+sends a message across to the remote processor, using the src and dst
+addresses provided by the user.
+
+The caller should specify the channel, the data it wants to send,
+its length (in bytes), and explicit source and destination addresses.
+The message will then be sent to the remote processor to which the
+channel belongs, but the channel's src and dst addresses will be
+ignored (and the user-provided addresses will be used instead).
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  int rpmsg_trysend(struct rpmsg_channel *rpdev, void *data, int len);
+
+sends a message across to the remote processor on a given channel.
+The caller should specify the channel, the data it wants to send,
+and its length (in bytes). The message will be sent on the specified
+channel, i.e. its source and destination address fields will be
+set to the channel's src and dst addresses.
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  int rpmsg_trysendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst)
+
+
+sends a message across to the remote processor on a given channel,
+to a destination address provided by the user.
+
+The user should specify the channel, the data it wants to send,
+its length (in bytes), and an explicit destination address.
+
+The message will then be sent to the remote processor to which the
+channel belongs, using the channel's src address, and the user-provided
+dst address (thus the channel's dst address will be ignored).
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  int rpmsg_trysend_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+							void *data, int len);
+
+
+sends a message across to the remote processor, using source and
+destination addresses provided by the user.
+
+The user should specify the channel, the data it wants to send,
+its length (in bytes), and explicit source and destination addresses.
+The message will then be sent to the remote processor to which the
+channel belongs, but the channel's src and dst addresses will be
+ignored (and the user-provided addresses will be used instead).
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
+
+  struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_channel *rpdev,
+		void (*cb)(struct rpmsg_channel *, void *, int, void *, u32),
+		void *priv, u32 addr);
+
+every rpmsg address in the system is bound to an rx callback (so when
+inbound messages arrive, they are dispatched by the rpmsg bus using the
+appropriate callback handler) by means of an rpmsg_endpoint struct.
+
+This function allows drivers to create such an endpoint, and by that,
+bind a callback, and possibly some private data too, to an rpmsg address
+(either one that is known in advance, or one that will be dynamically
+assigned for them).
+
+Simple rpmsg drivers need not call rpmsg_create_ept, because an endpoint
+is already created for them when they are probed by the rpmsg bus
+(using the rx callback they provide when they registered to the rpmsg bus).
+
+So things should just work for simple drivers: they already have an
+endpoint, their rx callback is bound to their rpmsg address, and when
+relevant inbound messages arrive (i.e. messages which their dst address
+equals to the src address of their rpmsg channel), the driver's handler
+is invoked to process it.
+
+That said, more complicated drivers might do need to allocate
+additional rpmsg addresses, and bind them to different rx callbacks.
+To accomplish that, those drivers need to call this function.
+Drivers should provide their channel (so the new endpoint would bind
+to the same remote processor their channel belongs to), an rx callback
+function, an optional private data (which is provided back when the
+rx callback is invoked), and an address they want to bind with the
+callback. If addr is RPMSG_ADDR_ANY, then rpmsg_create_ept will
+dynamically assign them an available rpmsg address (drivers should have
+a very good reason why not to always use RPMSG_ADDR_ANY here).
+
+Returns a pointer to the endpoint on success, or NULL on error.
+
+::
+
+  void rpmsg_destroy_ept(struct rpmsg_endpoint *ept);
+
+
+destroys an existing rpmsg endpoint. user should provide a pointer
+to an rpmsg endpoint that was previously created with rpmsg_create_ept().
+
+::
+
+  int register_rpmsg_driver(struct rpmsg_driver *rpdrv);
+
+
+registers an rpmsg driver with the rpmsg bus. user should provide
+a pointer to an rpmsg_driver struct, which contains the driver's
+->probe() and ->remove() functions, an rx callback, and an id_table
+specifying the names of the channels this driver is interested to
+be probed with.
+
+::
+
+  void unregister_rpmsg_driver(struct rpmsg_driver *rpdrv);
+
+
+unregisters an rpmsg driver from the rpmsg bus. user should provide
+a pointer to a previously-registered rpmsg_driver struct.
+Returns 0 on success, and an appropriate error value on failure.
+
+
+Typical usage
+=============
+
+The following is a simple rpmsg driver, that sends an "hello!" message
+on probe(), and whenever it receives an incoming message, it dumps its
+content to the console.
+
+::
+
+  #include <linux/kernel.h>
+  #include <linux/module.h>
+  #include <linux/rpmsg.h>
+
+  static void rpmsg_sample_cb(struct rpmsg_channel *rpdev, void *data, int len,
+						void *priv, u32 src)
+  {
+	print_hex_dump(KERN_INFO, "incoming message:", DUMP_PREFIX_NONE,
+						16, 1, data, len, true);
+  }
+
+  static int rpmsg_sample_probe(struct rpmsg_channel *rpdev)
+  {
+	int err;
+
+	dev_info(&rpdev->dev, "chnl: 0x%x -> 0x%x\n", rpdev->src, rpdev->dst);
+
+	/* send a message on our channel */
+	err = rpmsg_send(rpdev, "hello!", 6);
+	if (err) {
+		pr_err("rpmsg_send failed: %d\n", err);
+		return err;
+	}
+
+	return 0;
+  }
+
+  static void rpmsg_sample_remove(struct rpmsg_channel *rpdev)
+  {
+	dev_info(&rpdev->dev, "rpmsg sample client driver is removed\n");
+  }
+
+  static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
+	{ .name	= "rpmsg-client-sample" },
+	{ },
+  };
+  MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);
+
+  static struct rpmsg_driver rpmsg_sample_client = {
+	.drv.name	= KBUILD_MODNAME,
+	.id_table	= rpmsg_driver_sample_id_table,
+	.probe		= rpmsg_sample_probe,
+	.callback	= rpmsg_sample_cb,
+	.remove		= rpmsg_sample_remove,
+  };
+  module_rpmsg_driver(rpmsg_sample_client);
+
+.. note::
+
+   a similar sample which can be built and loaded can be found
+   in samples/rpmsg/.
+
+Allocations of rpmsg channels
+=============================
+
+At this point we only support dynamic allocations of rpmsg channels.
+
+This is possible only with remote processors that have the VIRTIO_RPMSG_F_NS
+virtio device feature set. This feature bit means that the remote
+processor supports dynamic name service announcement messages.
+
+When this feature is enabled, creation of rpmsg devices (i.e. channels)
+is completely dynamic: the remote processor announces the existence of a
+remote rpmsg service by sending a name service message (which contains
+the name and rpmsg addr of the remote service, see struct rpmsg_ns_msg).
+
+This message is then handled by the rpmsg bus, which in turn dynamically
+creates and registers an rpmsg channel (which represents the remote service).
+If/when a relevant rpmsg driver is registered, it will be immediately probed
+by the bus, and can then start sending messages to the remote service.
+
+The plan is also to add static creation of rpmsg channels via the virtio
+config space, but it's not implemented yet.
diff --git a/Documentation/staging/speculation.rst b/Documentation/staging/speculation.rst
new file mode 100644
index 000000000000..8045d99bcf12
--- /dev/null
+++ b/Documentation/staging/speculation.rst
@@ -0,0 +1,92 @@
+===========
+Speculation
+===========
+
+This document explains potential effects of speculation, and how undesirable
+effects can be mitigated portably using common APIs.
+
+------------------------------------------------------------------------------
+
+To improve performance and minimize average latencies, many contemporary CPUs
+employ speculative execution techniques such as branch prediction, performing
+work which may be discarded at a later stage.
+
+Typically speculative execution cannot be observed from architectural state,
+such as the contents of registers. However, in some cases it is possible to
+observe its impact on microarchitectural state, such as the presence or
+absence of data in caches. Such state may form side-channels which can be
+observed to extract secret information.
+
+For example, in the presence of branch prediction, it is possible for bounds
+checks to be ignored by code which is speculatively executed. Consider the
+following code::
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else
+			return array[index];
+	}
+
+Which, on arm64, may be compiled to an assembly sequence such as::
+
+	CMP	<index>, #MAX_ARRAY_ELEMS
+	B.LT	less
+	MOV	<returnval>, #0
+	RET
+  less:
+	LDR	<returnval>, [<array>, <index>]
+	RET
+
+It is possible that a CPU mis-predicts the conditional branch, and
+speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This
+value will subsequently be discarded, but the speculated load may affect
+microarchitectural state which can be subsequently measured.
+
+More complex sequences involving multiple dependent memory accesses may
+result in sensitive information being leaked. Consider the following
+code, building on the prior example::
+
+	int load_dependent_arrays(int *arr1, int *arr2, int index)
+	{
+		int val1, val2,
+
+		val1 = load_array(arr1, index);
+		val2 = load_array(arr2, val1);
+
+		return val2;
+	}
+
+Under speculation, the first call to load_array() may return the value
+of an out-of-bounds address, while the second call will influence
+microarchitectural state dependent on this value. This may provide an
+arbitrary read primitive.
+
+====================================
+Mitigating speculation side-channels
+====================================
+
+The kernel provides a generic API to ensure that bounds checks are
+respected even under speculation. Architectures which are affected by
+speculation-based side-channels are expected to implement these
+primitives.
+
+The array_index_nospec() helper in <linux/nospec.h> can be used to
+prevent information from being leaked via side-channels.
+
+A call to array_index_nospec(index, size) returns a sanitized index
+value that is bounded to [0, size) even under cpu speculation
+conditions.
+
+This can be used to protect the earlier load_array() example::
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else {
+			index = array_index_nospec(index, MAX_ARRAY_ELEMS);
+			return array[index];
+		}
+	}
diff --git a/Documentation/staging/static-keys.rst b/Documentation/staging/static-keys.rst
new file mode 100644
index 000000000000..38290b9f25eb
--- /dev/null
+++ b/Documentation/staging/static-keys.rst
@@ -0,0 +1,331 @@
+===========
+Static Keys
+===========
+
+.. warning::
+
+   DEPRECATED API:
+
+   The use of 'struct static_key' directly, is now DEPRECATED. In addition
+   static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following::
+
+	struct static_key false = STATIC_KEY_INIT_FALSE;
+	struct static_key true = STATIC_KEY_INIT_TRUE;
+	static_key_true()
+	static_key_false()
+
+   The updated API replacements are::
+
+	DEFINE_STATIC_KEY_TRUE(key);
+	DEFINE_STATIC_KEY_FALSE(key);
+	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
+	static_branch_likely()
+	static_branch_unlikely()
+
+Abstract
+========
+
+Static keys allows the inclusion of seldom used features in
+performance-sensitive fast-path kernel code, via a GCC feature and a code
+patching technique. A quick example::
+
+	DEFINE_STATIC_KEY_FALSE(key);
+
+	...
+
+        if (static_branch_unlikely(&key))
+                do unlikely code
+        else
+                do likely code
+
+	...
+	static_branch_enable(&key);
+	...
+	static_branch_disable(&key);
+	...
+
+The static_branch_unlikely() branch will be generated into the code with as little
+impact to the likely code path as possible.
+
+
+Motivation
+==========
+
+
+Currently, tracepoints are implemented using a conditional branch. The
+conditional check requires checking a global variable for each tracepoint.
+Although the overhead of this check is small, it increases when the memory
+cache comes under pressure (memory cache lines for these global variables may
+be shared with other memory accesses). As we increase the number of tracepoints
+in the kernel this overhead may become more of an issue. In addition,
+tracepoints are often dormant (disabled) and provide no direct kernel
+functionality. Thus, it is highly desirable to reduce their impact as much as
+possible. Although tracepoints are the original motivation for this work, other
+kernel code paths should be able to make use of the static keys facility.
+
+
+Solution
+========
+
+
+gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:
+
+https://gcc.gnu.org/ml/gcc-patches/2009-07/msg01556.html
+
+Using the 'asm goto', we can create branches that are either taken or not taken
+by default, without the need to check memory. Then, at run-time, we can patch
+the branch site to change the branch direction.
+
+For example, if we have a simple branch that is disabled by default::
+
+	if (static_branch_unlikely(&key))
+		printk("I am the true branch\n");
+
+Thus, by default the 'printk' will not be emitted. And the code generated will
+consist of a single atomic 'no-op' instruction (5 bytes on x86), in the
+straight-line code path. When the branch is 'flipped', we will patch the
+'no-op' in the straight-line codepath with a 'jump' instruction to the
+out-of-line true branch. Thus, changing branch direction is expensive but
+branch selection is basically 'free'. That is the basic tradeoff of this
+optimization.
+
+This lowlevel patching mechanism is called 'jump label patching', and it gives
+the basis for the static keys facility.
+
+Static key label API, usage and examples
+========================================
+
+
+In order to make use of this optimization you must first define a key::
+
+	DEFINE_STATIC_KEY_TRUE(key);
+
+or::
+
+	DEFINE_STATIC_KEY_FALSE(key);
+
+
+The key must be global, that is, it can't be allocated on the stack or dynamically
+allocated at run-time.
+
+The key is then used in code as::
+
+        if (static_branch_unlikely(&key))
+                do unlikely code
+        else
+                do likely code
+
+Or::
+
+        if (static_branch_likely(&key))
+                do likely code
+        else
+                do unlikely code
+
+Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may
+be used in either static_branch_likely() or static_branch_unlikely()
+statements.
+
+Branch(es) can be set true via::
+
+	static_branch_enable(&key);
+
+or false via::
+
+	static_branch_disable(&key);
+
+The branch(es) can then be switched via reference counts::
+
+	static_branch_inc(&key);
+	...
+	static_branch_dec(&key);
+
+Thus, 'static_branch_inc()' means 'make the branch true', and
+'static_branch_dec()' means 'make the branch false' with appropriate
+reference counting. For example, if the key is initialized true, a
+static_branch_dec(), will switch the branch to false. And a subsequent
+static_branch_inc(), will change the branch back to true. Likewise, if the
+key is initialized false, a 'static_branch_inc()', will change the branch to
+true. And then a 'static_branch_dec()', will again make the branch false.
+
+The state and the reference count can be retrieved with 'static_key_enabled()'
+and 'static_key_count()'.  In general, if you use these functions, they
+should be protected with the same mutex used around the enable/disable
+or increment/decrement function.
+
+Note that switching branches results in some locks being taken,
+particularly the CPU hotplug lock (in order to avoid races against
+CPUs being brought in the kernel while the kernel is getting
+patched). Calling the static key API from within a hotplug notifier is
+thus a sure deadlock recipe. In order to still allow use of the
+functionality, the following functions are provided:
+
+	static_key_enable_cpuslocked()
+	static_key_disable_cpuslocked()
+	static_branch_enable_cpuslocked()
+	static_branch_disable_cpuslocked()
+
+These functions are *not* general purpose, and must only be used when
+you really know that you're in the above context, and no other.
+
+Where an array of keys is required, it can be defined as::
+
+	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+
+or::
+
+	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
+
+4) Architecture level code patching interface, 'jump labels'
+
+
+There are a few functions and macros that architectures must implement in order
+to take advantage of this optimization. If there is no architecture support, we
+simply fall back to a traditional, load, test, and jump sequence. Also, the
+struct jump_entry table must be at least 4-byte aligned because the
+static_key->entry field makes use of the two least significant bits.
+
+* ``select HAVE_ARCH_JUMP_LABEL``,
+    see: arch/x86/Kconfig
+
+* ``#define JUMP_LABEL_NOP_SIZE``,
+    see: arch/x86/include/asm/jump_label.h
+
+* ``__always_inline bool arch_static_branch(struct static_key *key, bool branch)``,
+    see: arch/x86/include/asm/jump_label.h
+
+* ``__always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)``,
+    see: arch/x86/include/asm/jump_label.h
+
+* ``void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type)``,
+    see: arch/x86/kernel/jump_label.c
+
+* ``__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type)``,
+    see: arch/x86/kernel/jump_label.c
+
+* ``struct jump_entry``,
+    see: arch/x86/include/asm/jump_label.h
+
+
+5) Static keys / jump label analysis, results (x86_64):
+
+
+As an example, let's add the following branch to 'getppid()', such that the
+system call now looks like::
+
+  SYSCALL_DEFINE0(getppid)
+  {
+        int pid;
+
+  +     if (static_branch_unlikely(&key))
+  +             printk("I am the true branch\n");
+
+        rcu_read_lock();
+        pid = task_tgid_vnr(rcu_dereference(current->real_parent));
+        rcu_read_unlock();
+
+        return pid;
+  }
+
+The resulting instructions with jump labels generated by GCC is::
+
+  ffffffff81044290 <sys_getppid>:
+  ffffffff81044290:       55                      push   %rbp
+  ffffffff81044291:       48 89 e5                mov    %rsp,%rbp
+  ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>
+  ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+  ffffffff810442a0:       00 00
+  ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+  ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+  ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+  ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>
+  ffffffff810442bc:       5d                      pop    %rbp
+  ffffffff810442bd:       48 98                   cltq
+  ffffffff810442bf:       c3                      retq
+  ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi
+  ffffffff810442c7:       31 c0                   xor    %eax,%eax
+  ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>
+  ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>
+
+Without the jump label optimization it looks like::
+
+  ffffffff810441f0 <sys_getppid>:
+  ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>
+  ffffffff810441f6:       55                      push   %rbp
+  ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp
+  ffffffff810441fa:       85 c0                   test   %eax,%eax
+  ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>
+  ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+  ffffffff81044205:       00 00
+  ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+  ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+  ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+  ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>
+  ffffffff81044221:       5d                      pop    %rbp
+  ffffffff81044222:       48 98                   cltq
+  ffffffff81044224:       c3                      retq
+  ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi
+  ffffffff8104422c:       31 c0                   xor    %eax,%eax
+  ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>
+  ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>
+  ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)
+  ffffffff8104423c:       00 00 00 00
+
+Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction
+vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched
+to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump
+label case adds::
+
+  6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
+
+If we then include the padding bytes, the jump label code saves, 16 total bytes
+of instruction memory for this small function. In this case the non-jump label
+function is 80 bytes long. Thus, we have saved 20% of the instruction
+footprint. We can in fact improve this even further, since the 5-byte no-op
+really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp.
+However, we have not yet implemented optimal no-op sizes (they are currently
+hard-coded).
+
+Since there are a number of static key API uses in the scheduler paths,
+'pipe-test' (also known as 'perf bench sched pipe') can be used to show the
+performance improvement. Testing done on 3.3.0-rc2:
+
+jump label disabled::
+
+ Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
+
+        855.700314 task-clock                #    0.534 CPUs utilized            ( +-  0.11% )
+           200,003 context-switches          #    0.234 M/sec                    ( +-  0.00% )
+                 0 CPU-migrations            #    0.000 M/sec                    ( +- 39.58% )
+               487 page-faults               #    0.001 M/sec                    ( +-  0.02% )
+     1,474,374,262 cycles                    #    1.723 GHz                      ( +-  0.17% )
+   <not supported> stalled-cycles-frontend
+   <not supported> stalled-cycles-backend
+     1,178,049,567 instructions              #    0.80  insns per cycle          ( +-  0.06% )
+       208,368,926 branches                  #  243.507 M/sec                    ( +-  0.06% )
+         5,569,188 branch-misses             #    2.67% of all branches          ( +-  0.54% )
+
+       1.601607384 seconds time elapsed                                          ( +-  0.07% )
+
+jump label enabled::
+
+ Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
+
+        841.043185 task-clock                #    0.533 CPUs utilized            ( +-  0.12% )
+           200,004 context-switches          #    0.238 M/sec                    ( +-  0.00% )
+                 0 CPU-migrations            #    0.000 M/sec                    ( +- 40.87% )
+               487 page-faults               #    0.001 M/sec                    ( +-  0.05% )
+     1,432,559,428 cycles                    #    1.703 GHz                      ( +-  0.18% )
+   <not supported> stalled-cycles-frontend
+   <not supported> stalled-cycles-backend
+     1,175,363,994 instructions              #    0.82  insns per cycle          ( +-  0.04% )
+       206,859,359 branches                  #  245.956 M/sec                    ( +-  0.04% )
+         4,884,119 branch-misses             #    2.36% of all branches          ( +-  0.85% )
+
+       1.579384366 seconds time elapsed
+
+The percentage of saved branches is .7%, and we've saved 12% on
+'branch-misses'. This is where we would expect to get the most savings, since
+this optimization is about reducing the number of branches. In addition, we've
+saved .2% on instructions, and 2.8% on cycles and 1.4% on elapsed time.
diff --git a/Documentation/staging/tee.rst b/Documentation/staging/tee.rst
new file mode 100644
index 000000000000..62e8ba64d04f
--- /dev/null
+++ b/Documentation/staging/tee.rst
@@ -0,0 +1,277 @@
+=============
+TEE subsystem
+=============
+
+This document describes the TEE subsystem in Linux.
+
+A TEE (Trusted Execution Environment) is a trusted OS running in some
+secure environment, for example, TrustZone on ARM CPUs, or a separate
+secure co-processor etc. A TEE driver handles the details needed to
+communicate with the TEE.
+
+This subsystem deals with:
+
+- Registration of TEE drivers
+
+- Managing shared memory between Linux and the TEE
+
+- Providing a generic API to the TEE
+
+The TEE interface
+=================
+
+include/uapi/linux/tee.h defines the generic interface to a TEE.
+
+User space (the client) connects to the driver by opening /dev/tee[0-9]* or
+/dev/teepriv[0-9]*.
+
+- TEE_IOC_SHM_ALLOC allocates shared memory and returns a file descriptor
+  which user space can mmap. When user space doesn't need the file
+  descriptor any more, it should be closed. When shared memory isn't needed
+  any longer it should be unmapped with munmap() to allow the reuse of
+  memory.
+
+- TEE_IOC_VERSION lets user space know which TEE this driver handles and
+  its capabilities.
+
+- TEE_IOC_OPEN_SESSION opens a new session to a Trusted Application.
+
+- TEE_IOC_INVOKE invokes a function in a Trusted Application.
+
+- TEE_IOC_CANCEL may cancel an ongoing TEE_IOC_OPEN_SESSION or TEE_IOC_INVOKE.
+
+- TEE_IOC_CLOSE_SESSION closes a session to a Trusted Application.
+
+There are two classes of clients, normal clients and supplicants. The latter is
+a helper process for the TEE to access resources in Linux, for example file
+system access. A normal client opens /dev/tee[0-9]* and a supplicant opens
+/dev/teepriv[0-9].
+
+Much of the communication between clients and the TEE is opaque to the
+driver. The main job for the driver is to receive requests from the
+clients, forward them to the TEE and send back the results. In the case of
+supplicants the communication goes in the other direction, the TEE sends
+requests to the supplicant which then sends back the result.
+
+The TEE kernel interface
+========================
+
+Kernel provides a TEE bus infrastructure where a Trusted Application is
+represented as a device identified via Universally Unique Identifier (UUID) and
+client drivers register a table of supported device UUIDs.
+
+TEE bus infrastructure registers following APIs:
+-  match(): iterates over the client driver UUID table to find a corresponding
+   match for device UUID. If a match is found, then this particular device is
+   probed via corresponding probe API registered by the client driver. This
+   process happens whenever a device or a client driver is registered with TEE
+   bus.
+-  uevent(): notifies user-space (udev) whenever a new device is registered on
+   TEE bus for auto-loading of modularized client drivers.
+
+TEE bus device enumeration is specific to underlying TEE implementation, so it
+is left open for TEE drivers to provide corresponding implementation.
+
+Then TEE client driver can talk to a matched Trusted Application using APIs
+listed in include/linux/tee_drv.h.
+
+TEE client driver example
+-------------------------
+
+Suppose a TEE client driver needs to communicate with a Trusted Application
+having UUID: ``ac6a4085-0e82-4c33-bf98-8eb8e118b6c2``, so driver registration
+snippet would look like::
+
+	static const struct tee_client_device_id client_id_table[] = {
+		{UUID_INIT(0xac6a4085, 0x0e82, 0x4c33,
+			   0xbf, 0x98, 0x8e, 0xb8, 0xe1, 0x18, 0xb6, 0xc2)},
+		{}
+	};
+
+	MODULE_DEVICE_TABLE(tee, client_id_table);
+
+	static struct tee_client_driver client_driver = {
+		.id_table	= client_id_table,
+		.driver		= {
+			.name		= DRIVER_NAME,
+			.bus		= &tee_bus_type,
+			.probe		= client_probe,
+			.remove		= client_remove,
+		},
+	};
+
+	static int __init client_init(void)
+	{
+		return driver_register(&client_driver.driver);
+	}
+
+	static void __exit client_exit(void)
+	{
+		driver_unregister(&client_driver.driver);
+	}
+
+	module_init(client_init);
+	module_exit(client_exit);
+
+OP-TEE driver
+=============
+
+The OP-TEE driver handles OP-TEE [1] based TEEs. Currently it is only the ARM
+TrustZone based OP-TEE solution that is supported.
+
+Lowest level of communication with OP-TEE builds on ARM SMC Calling
+Convention (SMCCC) [2], which is the foundation for OP-TEE's SMC interface
+[3] used internally by the driver. Stacked on top of that is OP-TEE Message
+Protocol [4].
+
+OP-TEE SMC interface provides the basic functions required by SMCCC and some
+additional functions specific for OP-TEE. The most interesting functions are:
+
+- OPTEE_SMC_FUNCID_CALLS_UID (part of SMCCC) returns the version information
+  which is then returned by TEE_IOC_VERSION
+
+- OPTEE_SMC_CALL_GET_OS_UUID returns the particular OP-TEE implementation, used
+  to tell, for instance, a TrustZone OP-TEE apart from an OP-TEE running on a
+  separate secure co-processor.
+
+- OPTEE_SMC_CALL_WITH_ARG drives the OP-TEE message protocol
+
+- OPTEE_SMC_GET_SHM_CONFIG lets the driver and OP-TEE agree on which memory
+  range to used for shared memory between Linux and OP-TEE.
+
+The GlobalPlatform TEE Client API [5] is implemented on top of the generic
+TEE API.
+
+Picture of the relationship between the different components in the
+OP-TEE architecture::
+
+      User space                  Kernel                   Secure world
+      ~~~~~~~~~~                  ~~~~~~                   ~~~~~~~~~~~~
+   +--------+                                             +-------------+
+   | Client |                                             | Trusted     |
+   +--------+                                             | Application |
+      /\                                                  +-------------+
+      || +----------+                                           /\
+      || |tee-      |                                           ||
+      || |supplicant|                                           \/
+      || +----------+                                     +-------------+
+      \/      /\                                          | TEE Internal|
+   +-------+  ||                                          | API         |
+   + TEE   |  ||            +--------+--------+           +-------------+
+   | Client|  ||            | TEE    | OP-TEE |           | OP-TEE      |
+   | API   |  \/            | subsys | driver |           | Trusted OS  |
+   +-------+----------------+----+-------+----+-----------+-------------+
+   |      Generic TEE API        |       |     OP-TEE MSG               |
+   |      IOCTL (TEE_IOC_*)      |       |     SMCCC (OPTEE_SMC_CALL_*) |
+   +-----------------------------+       +------------------------------+
+
+RPC (Remote Procedure Call) are requests from secure world to kernel driver
+or tee-supplicant. An RPC is identified by a special range of SMCCC return
+values from OPTEE_SMC_CALL_WITH_ARG. RPC messages which are intended for the
+kernel are handled by the kernel driver. Other RPC messages will be forwarded to
+tee-supplicant without further involvement of the driver, except switching
+shared memory buffer representation.
+
+OP-TEE device enumeration
+-------------------------
+
+OP-TEE provides a pseudo Trusted Application: drivers/tee/optee/device.c in
+order to support device enumeration. In other words, OP-TEE driver invokes this
+application to retrieve a list of Trusted Applications which can be registered
+as devices on the TEE bus.
+
+AMD-TEE driver
+==============
+
+The AMD-TEE driver handles the communication with AMD's TEE environment. The
+TEE environment is provided by AMD Secure Processor.
+
+The AMD Secure Processor (formerly called Platform Security Processor or PSP)
+is a dedicated processor that features ARM TrustZone technology, along with a
+software-based Trusted Execution Environment (TEE) designed to enable
+third-party Trusted Applications. This feature is currently enabled only for
+APUs.
+
+The following picture shows a high level overview of AMD-TEE::
+
+                                             |
+    x86                                      |
+                                             |
+ User space            (Kernel space)        |    AMD Secure Processor (PSP)
+ ~~~~~~~~~~            ~~~~~~~~~~~~~~        |    ~~~~~~~~~~~~~~~~~~~~~~~~~~
+                                             |
+ +--------+                                  |       +-------------+
+ | Client |                                  |       | Trusted     |
+ +--------+                                  |       | Application |
+     /\                                      |       +-------------+
+     ||                                      |             /\
+     ||                                      |             ||
+     ||                                      |             \/
+     ||                                      |         +----------+
+     ||                                      |         |   TEE    |
+     ||                                      |         | Internal |
+     \/                                      |         |   API    |
+ +---------+           +-----------+---------+         +----------+
+ | TEE     |           | TEE       | AMD-TEE |         | AMD-TEE  |
+ | Client  |           | subsystem | driver  |         | Trusted  |
+ | API     |           |           |         |         |   OS     |
+ +---------+-----------+----+------+---------+---------+----------+
+ |   Generic TEE API        |      | ASP     |      Mailbox       |
+ |   IOCTL (TEE_IOC_*)      |      | driver  | Register Protocol  |
+ +--------------------------+      +---------+--------------------+
+
+At the lowest level (in x86), the AMD Secure Processor (ASP) driver uses the
+CPU to PSP mailbox regsister to submit commands to the PSP. The format of the
+command buffer is opaque to the ASP driver. It's role is to submit commands to
+the secure processor and return results to AMD-TEE driver. The interface
+between AMD-TEE driver and AMD Secure Processor driver can be found in [6].
+
+The AMD-TEE driver packages the command buffer payload for processing in TEE.
+The command buffer format for the different TEE commands can be found in [7].
+
+The TEE commands supported by AMD-TEE Trusted OS are:
+
+* TEE_CMD_ID_LOAD_TA          - loads a Trusted Application (TA) binary into
+                                TEE environment.
+* TEE_CMD_ID_UNLOAD_TA        - unloads TA binary from TEE environment.
+* TEE_CMD_ID_OPEN_SESSION     - opens a session with a loaded TA.
+* TEE_CMD_ID_CLOSE_SESSION    - closes session with loaded TA
+* TEE_CMD_ID_INVOKE_CMD       - invokes a command with loaded TA
+* TEE_CMD_ID_MAP_SHARED_MEM   - maps shared memory
+* TEE_CMD_ID_UNMAP_SHARED_MEM - unmaps shared memory
+
+AMD-TEE Trusted OS is the firmware running on AMD Secure Processor.
+
+The AMD-TEE driver registers itself with TEE subsystem and implements the
+following driver function callbacks:
+
+* get_version - returns the driver implementation id and capability.
+* open - sets up the driver context data structure.
+* release - frees up driver resources.
+* open_session - loads the TA binary and opens session with loaded TA.
+* close_session -  closes session with loaded TA and unloads it.
+* invoke_func - invokes a command with loaded TA.
+
+cancel_req driver callback is not supported by AMD-TEE.
+
+The GlobalPlatform TEE Client API [5] can be used by the user space (client) to
+talk to AMD's TEE. AMD's TEE provides a secure environment for loading, opening
+a session, invoking commands and clossing session with TA.
+
+References
+==========
+
+[1] https://github.com/OP-TEE/optee_os
+
+[2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+
+[3] drivers/tee/optee/optee_smc.h
+
+[4] drivers/tee/optee/optee_msg.h
+
+[5] http://www.globalplatform.org/specificationsdevice.asp look for
+    "TEE Client API Specification v1.0" and click download.
+
+[6] include/linux/psp-tee.h
+
+[7] drivers/tee/amdtee/amdtee_if.h
diff --git a/Documentation/staging/xz.rst b/Documentation/staging/xz.rst
new file mode 100644
index 000000000000..b2f5ff12a161
--- /dev/null
+++ b/Documentation/staging/xz.rst
@@ -0,0 +1,127 @@
+============================
+XZ data compression in Linux
+============================
+
+Introduction
+============
+
+XZ is a general purpose data compression format with high compression
+ratio and relatively fast decompression. The primary compression
+algorithm (filter) is LZMA2. Additional filters can be used to improve
+compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters
+improve compression ratio of executable data.
+
+The XZ decompressor in Linux is called XZ Embedded. It supports
+the LZMA2 filter and optionally also BCJ filters. CRC32 is supported
+for integrity checking. The home page of XZ Embedded is at
+<https://tukaani.org/xz/embedded.html>, where you can find the
+latest version and also information about using the code outside
+the Linux kernel.
+
+For userspace, XZ Utils provide a zlib-like compression library
+and a gzip-like command line tool. XZ Utils can be downloaded from
+<https://tukaani.org/xz/>.
+
+XZ related components in the kernel
+===================================
+
+The xz_dec module provides XZ decompressor with single-call (buffer
+to buffer) and multi-call (stateful) APIs. The usage of the xz_dec
+module is documented in include/linux/xz.h.
+
+The xz_dec_test module is for testing xz_dec. xz_dec_test is not
+useful unless you are hacking the XZ decompressor. xz_dec_test
+allocates a char device major dynamically to which one can write
+.xz files from userspace. The decompressed output is thrown away.
+Keep an eye on dmesg to see diagnostics printed by xz_dec_test.
+See the xz_dec_test source code for the details.
+
+For decompressing the kernel image, initramfs, and initrd, there
+is a wrapper function in lib/decompress_unxz.c. Its API is the
+same as in other decompress_*.c files, which is defined in
+include/linux/decompress/generic.h.
+
+scripts/xz_wrap.sh is a wrapper for the xz command line tool found
+from XZ Utils. The wrapper sets compression options to values suitable
+for compressing the kernel image.
+
+For kernel makefiles, two commands are provided for use with
+$(call if_needed). The kernel image should be compressed with
+$(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2
+dictionary. It will also append a four-byte trailer containing the
+uncompressed size of the file, which is needed by the boot code.
+Other things should be compressed with $(call if_needed,xzmisc)
+which will use no BCJ filter and 1 MiB LZMA2 dictionary.
+
+Notes on compression options
+============================
+
+Since the XZ Embedded supports only streams with no integrity check or
+CRC32, make sure that you don't use some other integrity check type
+when encoding files that are supposed to be decoded by the kernel. With
+liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32
+when encoding. With the xz command line tool, use --check=none or
+--check=crc32.
+
+Using CRC32 is strongly recommended unless there is some other layer
+which will verify the integrity of the uncompressed data anyway.
+Double checking the integrity would probably be waste of CPU cycles.
+Note that the headers will always have a CRC32 which will be validated
+by the decoder; you can only change the integrity check type (or
+disable it) for the actual uncompressed data.
+
+In userspace, LZMA2 is typically used with dictionary sizes of several
+megabytes. The decoder needs to have the dictionary in RAM, thus big
+dictionaries cannot be used for files that are intended to be decoded
+by the kernel. 1 MiB is probably the maximum reasonable dictionary
+size for in-kernel use (maybe more is OK for initramfs). The presets
+in XZ Utils may not be optimal when creating files for the kernel,
+so don't hesitate to use custom settings. Example::
+
+	xz --check=crc32 --lzma2=dict=512KiB inputfile
+
+An exception to above dictionary size limitation is when the decoder
+is used in single-call mode. Decompressing the kernel itself is an
+example of this situation. In single-call mode, the memory usage
+doesn't depend on the dictionary size, and it is perfectly fine to
+use a big dictionary: for maximum compression, the dictionary should
+be at least as big as the uncompressed data itself.
+
+Future plans
+============
+
+Creating a limited XZ encoder may be considered if people think it is
+useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at
+the fastest settings, so it isn't clear if LZMA2 encoder is wanted
+into the kernel.
+
+Support for limited random-access reading is planned for the
+decompression code. I don't know if it could have any use in the
+kernel, but I know that it would be useful in some embedded projects
+outside the Linux kernel.
+
+Conformance to the .xz file format specification
+================================================
+
+There are a couple of corner cases where things have been simplified
+at expense of detecting errors as early as possible. These should not
+matter in practice all, since they don't cause security issues. But
+it is good to know this if testing the code e.g. with the test files
+from XZ Utils.
+
+Reporting bugs
+==============
+
+Before reporting a bug, please check that it's not fixed already
+at upstream. See <https://tukaani.org/xz/embedded.html> to get the
+latest code.
+
+Report bugs to <lasse.collin@tukaani.org> or visit #tukaani on
+Freenode and talk to Larhzu. I don't actively read LKML or other
+kernel-related mailing lists, so if there's something I should know,
+you should email to me personally or use IRC.
+
+Don't bother Igor Pavlov with questions about the XZ implementation
+in the kernel or about XZ Utils. While these two implementations
+include essential code that is directly based on Igor Pavlov's code,
+these implementations aren't maintained nor supported by him.
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
deleted file mode 100644
index 38290b9f25eb..000000000000
--- a/Documentation/static-keys.txt
+++ /dev/null
@@ -1,331 +0,0 @@
-===========
-Static Keys
-===========
-
-.. warning::
-
-   DEPRECATED API:
-
-   The use of 'struct static_key' directly, is now DEPRECATED. In addition
-   static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following::
-
-	struct static_key false = STATIC_KEY_INIT_FALSE;
-	struct static_key true = STATIC_KEY_INIT_TRUE;
-	static_key_true()
-	static_key_false()
-
-   The updated API replacements are::
-
-	DEFINE_STATIC_KEY_TRUE(key);
-	DEFINE_STATIC_KEY_FALSE(key);
-	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
-	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
-	static_branch_likely()
-	static_branch_unlikely()
-
-Abstract
-========
-
-Static keys allows the inclusion of seldom used features in
-performance-sensitive fast-path kernel code, via a GCC feature and a code
-patching technique. A quick example::
-
-	DEFINE_STATIC_KEY_FALSE(key);
-
-	...
-
-        if (static_branch_unlikely(&key))
-                do unlikely code
-        else
-                do likely code
-
-	...
-	static_branch_enable(&key);
-	...
-	static_branch_disable(&key);
-	...
-
-The static_branch_unlikely() branch will be generated into the code with as little
-impact to the likely code path as possible.
-
-
-Motivation
-==========
-
-
-Currently, tracepoints are implemented using a conditional branch. The
-conditional check requires checking a global variable for each tracepoint.
-Although the overhead of this check is small, it increases when the memory
-cache comes under pressure (memory cache lines for these global variables may
-be shared with other memory accesses). As we increase the number of tracepoints
-in the kernel this overhead may become more of an issue. In addition,
-tracepoints are often dormant (disabled) and provide no direct kernel
-functionality. Thus, it is highly desirable to reduce their impact as much as
-possible. Although tracepoints are the original motivation for this work, other
-kernel code paths should be able to make use of the static keys facility.
-
-
-Solution
-========
-
-
-gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:
-
-https://gcc.gnu.org/ml/gcc-patches/2009-07/msg01556.html
-
-Using the 'asm goto', we can create branches that are either taken or not taken
-by default, without the need to check memory. Then, at run-time, we can patch
-the branch site to change the branch direction.
-
-For example, if we have a simple branch that is disabled by default::
-
-	if (static_branch_unlikely(&key))
-		printk("I am the true branch\n");
-
-Thus, by default the 'printk' will not be emitted. And the code generated will
-consist of a single atomic 'no-op' instruction (5 bytes on x86), in the
-straight-line code path. When the branch is 'flipped', we will patch the
-'no-op' in the straight-line codepath with a 'jump' instruction to the
-out-of-line true branch. Thus, changing branch direction is expensive but
-branch selection is basically 'free'. That is the basic tradeoff of this
-optimization.
-
-This lowlevel patching mechanism is called 'jump label patching', and it gives
-the basis for the static keys facility.
-
-Static key label API, usage and examples
-========================================
-
-
-In order to make use of this optimization you must first define a key::
-
-	DEFINE_STATIC_KEY_TRUE(key);
-
-or::
-
-	DEFINE_STATIC_KEY_FALSE(key);
-
-
-The key must be global, that is, it can't be allocated on the stack or dynamically
-allocated at run-time.
-
-The key is then used in code as::
-
-        if (static_branch_unlikely(&key))
-                do unlikely code
-        else
-                do likely code
-
-Or::
-
-        if (static_branch_likely(&key))
-                do likely code
-        else
-                do unlikely code
-
-Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may
-be used in either static_branch_likely() or static_branch_unlikely()
-statements.
-
-Branch(es) can be set true via::
-
-	static_branch_enable(&key);
-
-or false via::
-
-	static_branch_disable(&key);
-
-The branch(es) can then be switched via reference counts::
-
-	static_branch_inc(&key);
-	...
-	static_branch_dec(&key);
-
-Thus, 'static_branch_inc()' means 'make the branch true', and
-'static_branch_dec()' means 'make the branch false' with appropriate
-reference counting. For example, if the key is initialized true, a
-static_branch_dec(), will switch the branch to false. And a subsequent
-static_branch_inc(), will change the branch back to true. Likewise, if the
-key is initialized false, a 'static_branch_inc()', will change the branch to
-true. And then a 'static_branch_dec()', will again make the branch false.
-
-The state and the reference count can be retrieved with 'static_key_enabled()'
-and 'static_key_count()'.  In general, if you use these functions, they
-should be protected with the same mutex used around the enable/disable
-or increment/decrement function.
-
-Note that switching branches results in some locks being taken,
-particularly the CPU hotplug lock (in order to avoid races against
-CPUs being brought in the kernel while the kernel is getting
-patched). Calling the static key API from within a hotplug notifier is
-thus a sure deadlock recipe. In order to still allow use of the
-functionality, the following functions are provided:
-
-	static_key_enable_cpuslocked()
-	static_key_disable_cpuslocked()
-	static_branch_enable_cpuslocked()
-	static_branch_disable_cpuslocked()
-
-These functions are *not* general purpose, and must only be used when
-you really know that you're in the above context, and no other.
-
-Where an array of keys is required, it can be defined as::
-
-	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
-
-or::
-
-	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
-
-4) Architecture level code patching interface, 'jump labels'
-
-
-There are a few functions and macros that architectures must implement in order
-to take advantage of this optimization. If there is no architecture support, we
-simply fall back to a traditional, load, test, and jump sequence. Also, the
-struct jump_entry table must be at least 4-byte aligned because the
-static_key->entry field makes use of the two least significant bits.
-
-* ``select HAVE_ARCH_JUMP_LABEL``,
-    see: arch/x86/Kconfig
-
-* ``#define JUMP_LABEL_NOP_SIZE``,
-    see: arch/x86/include/asm/jump_label.h
-
-* ``__always_inline bool arch_static_branch(struct static_key *key, bool branch)``,
-    see: arch/x86/include/asm/jump_label.h
-
-* ``__always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)``,
-    see: arch/x86/include/asm/jump_label.h
-
-* ``void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type)``,
-    see: arch/x86/kernel/jump_label.c
-
-* ``__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type)``,
-    see: arch/x86/kernel/jump_label.c
-
-* ``struct jump_entry``,
-    see: arch/x86/include/asm/jump_label.h
-
-
-5) Static keys / jump label analysis, results (x86_64):
-
-
-As an example, let's add the following branch to 'getppid()', such that the
-system call now looks like::
-
-  SYSCALL_DEFINE0(getppid)
-  {
-        int pid;
-
-  +     if (static_branch_unlikely(&key))
-  +             printk("I am the true branch\n");
-
-        rcu_read_lock();
-        pid = task_tgid_vnr(rcu_dereference(current->real_parent));
-        rcu_read_unlock();
-
-        return pid;
-  }
-
-The resulting instructions with jump labels generated by GCC is::
-
-  ffffffff81044290 <sys_getppid>:
-  ffffffff81044290:       55                      push   %rbp
-  ffffffff81044291:       48 89 e5                mov    %rsp,%rbp
-  ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>
-  ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
-  ffffffff810442a0:       00 00
-  ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
-  ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
-  ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
-  ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>
-  ffffffff810442bc:       5d                      pop    %rbp
-  ffffffff810442bd:       48 98                   cltq
-  ffffffff810442bf:       c3                      retq
-  ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi
-  ffffffff810442c7:       31 c0                   xor    %eax,%eax
-  ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>
-  ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>
-
-Without the jump label optimization it looks like::
-
-  ffffffff810441f0 <sys_getppid>:
-  ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>
-  ffffffff810441f6:       55                      push   %rbp
-  ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp
-  ffffffff810441fa:       85 c0                   test   %eax,%eax
-  ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>
-  ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
-  ffffffff81044205:       00 00
-  ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
-  ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
-  ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
-  ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>
-  ffffffff81044221:       5d                      pop    %rbp
-  ffffffff81044222:       48 98                   cltq
-  ffffffff81044224:       c3                      retq
-  ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi
-  ffffffff8104422c:       31 c0                   xor    %eax,%eax
-  ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>
-  ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>
-  ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)
-  ffffffff8104423c:       00 00 00 00
-
-Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction
-vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched
-to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump
-label case adds::
-
-  6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
-
-If we then include the padding bytes, the jump label code saves, 16 total bytes
-of instruction memory for this small function. In this case the non-jump label
-function is 80 bytes long. Thus, we have saved 20% of the instruction
-footprint. We can in fact improve this even further, since the 5-byte no-op
-really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp.
-However, we have not yet implemented optimal no-op sizes (they are currently
-hard-coded).
-
-Since there are a number of static key API uses in the scheduler paths,
-'pipe-test' (also known as 'perf bench sched pipe') can be used to show the
-performance improvement. Testing done on 3.3.0-rc2:
-
-jump label disabled::
-
- Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
-
-        855.700314 task-clock                #    0.534 CPUs utilized            ( +-  0.11% )
-           200,003 context-switches          #    0.234 M/sec                    ( +-  0.00% )
-                 0 CPU-migrations            #    0.000 M/sec                    ( +- 39.58% )
-               487 page-faults               #    0.001 M/sec                    ( +-  0.02% )
-     1,474,374,262 cycles                    #    1.723 GHz                      ( +-  0.17% )
-   <not supported> stalled-cycles-frontend
-   <not supported> stalled-cycles-backend
-     1,178,049,567 instructions              #    0.80  insns per cycle          ( +-  0.06% )
-       208,368,926 branches                  #  243.507 M/sec                    ( +-  0.06% )
-         5,569,188 branch-misses             #    2.67% of all branches          ( +-  0.54% )
-
-       1.601607384 seconds time elapsed                                          ( +-  0.07% )
-
-jump label enabled::
-
- Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
-
-        841.043185 task-clock                #    0.533 CPUs utilized            ( +-  0.12% )
-           200,004 context-switches          #    0.238 M/sec                    ( +-  0.00% )
-                 0 CPU-migrations            #    0.000 M/sec                    ( +- 40.87% )
-               487 page-faults               #    0.001 M/sec                    ( +-  0.05% )
-     1,432,559,428 cycles                    #    1.703 GHz                      ( +-  0.18% )
-   <not supported> stalled-cycles-frontend
-   <not supported> stalled-cycles-backend
-     1,175,363,994 instructions              #    0.82  insns per cycle          ( +-  0.04% )
-       206,859,359 branches                  #  245.956 M/sec                    ( +-  0.04% )
-         4,884,119 branch-misses             #    2.36% of all branches          ( +-  0.85% )
-
-       1.579384366 seconds time elapsed
-
-The percentage of saved branches is .7%, and we've saved 12% on
-'branch-misses'. This is where we would expect to get the most savings, since
-this optimization is about reducing the number of branches. In addition, we've
-saved .2% on instructions, and 2.8% on cycles and 1.4% on elapsed time.
diff --git a/Documentation/tee.txt b/Documentation/tee.txt
deleted file mode 100644
index 350dd40cba45..000000000000
--- a/Documentation/tee.txt
+++ /dev/null
@@ -1,276 +0,0 @@
-=============
-TEE subsystem
-=============
-
-This document describes the TEE subsystem in Linux.
-
-A TEE (Trusted Execution Environment) is a trusted OS running in some
-secure environment, for example, TrustZone on ARM CPUs, or a separate
-secure co-processor etc. A TEE driver handles the details needed to
-communicate with the TEE.
-
-This subsystem deals with:
-
-- Registration of TEE drivers
-
-- Managing shared memory between Linux and the TEE
-
-- Providing a generic API to the TEE
-
-The TEE interface
-=================
-
-include/uapi/linux/tee.h defines the generic interface to a TEE.
-
-User space (the client) connects to the driver by opening /dev/tee[0-9]* or
-/dev/teepriv[0-9]*.
-
-- TEE_IOC_SHM_ALLOC allocates shared memory and returns a file descriptor
-  which user space can mmap. When user space doesn't need the file
-  descriptor any more, it should be closed. When shared memory isn't needed
-  any longer it should be unmapped with munmap() to allow the reuse of
-  memory.
-
-- TEE_IOC_VERSION lets user space know which TEE this driver handles and
-  its capabilities.
-
-- TEE_IOC_OPEN_SESSION opens a new session to a Trusted Application.
-
-- TEE_IOC_INVOKE invokes a function in a Trusted Application.
-
-- TEE_IOC_CANCEL may cancel an ongoing TEE_IOC_OPEN_SESSION or TEE_IOC_INVOKE.
-
-- TEE_IOC_CLOSE_SESSION closes a session to a Trusted Application.
-
-There are two classes of clients, normal clients and supplicants. The latter is
-a helper process for the TEE to access resources in Linux, for example file
-system access. A normal client opens /dev/tee[0-9]* and a supplicant opens
-/dev/teepriv[0-9].
-
-Much of the communication between clients and the TEE is opaque to the
-driver. The main job for the driver is to receive requests from the
-clients, forward them to the TEE and send back the results. In the case of
-supplicants the communication goes in the other direction, the TEE sends
-requests to the supplicant which then sends back the result.
-
-The TEE kernel interface
-========================
-
-Kernel provides a TEE bus infrastructure where a Trusted Application is
-represented as a device identified via Universally Unique Identifier (UUID) and
-client drivers register a table of supported device UUIDs.
-
-TEE bus infrastructure registers following APIs:
--  match(): iterates over the client driver UUID table to find a corresponding
-   match for device UUID. If a match is found, then this particular device is
-   probed via corresponding probe API registered by the client driver. This
-   process happens whenever a device or a client driver is registered with TEE
-   bus.
--  uevent(): notifies user-space (udev) whenever a new device is registered on
-   TEE bus for auto-loading of modularized client drivers.
-
-TEE bus device enumeration is specific to underlying TEE implementation, so it
-is left open for TEE drivers to provide corresponding implementation.
-
-Then TEE client driver can talk to a matched Trusted Application using APIs
-listed in include/linux/tee_drv.h.
-
-TEE client driver example
--------------------------
-
-Suppose a TEE client driver needs to communicate with a Trusted Application
-having UUID: ``ac6a4085-0e82-4c33-bf98-8eb8e118b6c2``, so driver registration
-snippet would look like::
-
-	static const struct tee_client_device_id client_id_table[] = {
-		{UUID_INIT(0xac6a4085, 0x0e82, 0x4c33,
-			   0xbf, 0x98, 0x8e, 0xb8, 0xe1, 0x18, 0xb6, 0xc2)},
-		{}
-	};
-
-	MODULE_DEVICE_TABLE(tee, client_id_table);
-
-	static struct tee_client_driver client_driver = {
-		.id_table	= client_id_table,
-		.driver		= {
-			.name		= DRIVER_NAME,
-			.bus		= &tee_bus_type,
-			.probe		= client_probe,
-			.remove		= client_remove,
-		},
-	};
-
-	static int __init client_init(void)
-	{
-		return driver_register(&client_driver.driver);
-	}
-
-	static void __exit client_exit(void)
-	{
-		driver_unregister(&client_driver.driver);
-	}
-
-	module_init(client_init);
-	module_exit(client_exit);
-
-OP-TEE driver
-=============
-
-The OP-TEE driver handles OP-TEE [1] based TEEs. Currently it is only the ARM
-TrustZone based OP-TEE solution that is supported.
-
-Lowest level of communication with OP-TEE builds on ARM SMC Calling
-Convention (SMCCC) [2], which is the foundation for OP-TEE's SMC interface
-[3] used internally by the driver. Stacked on top of that is OP-TEE Message
-Protocol [4].
-
-OP-TEE SMC interface provides the basic functions required by SMCCC and some
-additional functions specific for OP-TEE. The most interesting functions are:
-
-- OPTEE_SMC_FUNCID_CALLS_UID (part of SMCCC) returns the version information
-  which is then returned by TEE_IOC_VERSION
-
-- OPTEE_SMC_CALL_GET_OS_UUID returns the particular OP-TEE implementation, used
-  to tell, for instance, a TrustZone OP-TEE apart from an OP-TEE running on a
-  separate secure co-processor.
-
-- OPTEE_SMC_CALL_WITH_ARG drives the OP-TEE message protocol
-
-- OPTEE_SMC_GET_SHM_CONFIG lets the driver and OP-TEE agree on which memory
-  range to used for shared memory between Linux and OP-TEE.
-
-The GlobalPlatform TEE Client API [5] is implemented on top of the generic
-TEE API.
-
-Picture of the relationship between the different components in the
-OP-TEE architecture::
-
-      User space                  Kernel                   Secure world
-      ~~~~~~~~~~                  ~~~~~~                   ~~~~~~~~~~~~
-   +--------+                                             +-------------+
-   | Client |                                             | Trusted     |
-   +--------+                                             | Application |
-      /\                                                  +-------------+
-      || +----------+                                           /\
-      || |tee-      |                                           ||
-      || |supplicant|                                           \/
-      || +----------+                                     +-------------+
-      \/      /\                                          | TEE Internal|
-   +-------+  ||                                          | API         |
-   + TEE   |  ||            +--------+--------+           +-------------+
-   | Client|  ||            | TEE    | OP-TEE |           | OP-TEE      |
-   | API   |  \/            | subsys | driver |           | Trusted OS  |
-   +-------+----------------+----+-------+----+-----------+-------------+
-   |      Generic TEE API        |       |     OP-TEE MSG               |
-   |      IOCTL (TEE_IOC_*)      |       |     SMCCC (OPTEE_SMC_CALL_*) |
-   +-----------------------------+       +------------------------------+
-
-RPC (Remote Procedure Call) are requests from secure world to kernel driver
-or tee-supplicant. An RPC is identified by a special range of SMCCC return
-values from OPTEE_SMC_CALL_WITH_ARG. RPC messages which are intended for the
-kernel are handled by the kernel driver. Other RPC messages will be forwarded to
-tee-supplicant without further involvement of the driver, except switching
-shared memory buffer representation.
-
-OP-TEE device enumeration
--------------------------
-
-OP-TEE provides a pseudo Trusted Application: drivers/tee/optee/device.c in
-order to support device enumeration. In other words, OP-TEE driver invokes this
-application to retrieve a list of Trusted Applications which can be registered
-as devices on the TEE bus.
-
-AMD-TEE driver
-==============
-
-The AMD-TEE driver handles the communication with AMD's TEE environment. The
-TEE environment is provided by AMD Secure Processor.
-
-The AMD Secure Processor (formerly called Platform Security Processor or PSP)
-is a dedicated processor that features ARM TrustZone technology, along with a
-software-based Trusted Execution Environment (TEE) designed to enable
-third-party Trusted Applications. This feature is currently enabled only for
-APUs.
-
-The following picture shows a high level overview of AMD-TEE::
-
-                                             |
-    x86                                      |
-                                             |
- User space            (Kernel space)        |    AMD Secure Processor (PSP)
- ~~~~~~~~~~            ~~~~~~~~~~~~~~        |    ~~~~~~~~~~~~~~~~~~~~~~~~~~
-                                             |
- +--------+                                  |       +-------------+
- | Client |                                  |       | Trusted     |
- +--------+                                  |       | Application |
-     /\                                      |       +-------------+
-     ||                                      |             /\
-     ||                                      |             ||
-     ||                                      |             \/
-     ||                                      |         +----------+
-     ||                                      |         |   TEE    |
-     ||                                      |         | Internal |
-     \/                                      |         |   API    |
- +---------+           +-----------+---------+         +----------+
- | TEE     |           | TEE       | AMD-TEE |         | AMD-TEE  |
- | Client  |           | subsystem | driver  |         | Trusted  |
- | API     |           |           |         |         |   OS     |
- +---------+-----------+----+------+---------+---------+----------+
- |   Generic TEE API        |      | ASP     |      Mailbox       |
- |   IOCTL (TEE_IOC_*)      |      | driver  | Register Protocol  |
- +--------------------------+      +---------+--------------------+
-
-At the lowest level (in x86), the AMD Secure Processor (ASP) driver uses the
-CPU to PSP mailbox regsister to submit commands to the PSP. The format of the
-command buffer is opaque to the ASP driver. It's role is to submit commands to
-the secure processor and return results to AMD-TEE driver. The interface
-between AMD-TEE driver and AMD Secure Processor driver can be found in [6].
-
-The AMD-TEE driver packages the command buffer payload for processing in TEE.
-The command buffer format for the different TEE commands can be found in [7].
-
-The TEE commands supported by AMD-TEE Trusted OS are:
-* TEE_CMD_ID_LOAD_TA          - loads a Trusted Application (TA) binary into
-                                TEE environment.
-* TEE_CMD_ID_UNLOAD_TA        - unloads TA binary from TEE environment.
-* TEE_CMD_ID_OPEN_SESSION     - opens a session with a loaded TA.
-* TEE_CMD_ID_CLOSE_SESSION    - closes session with loaded TA
-* TEE_CMD_ID_INVOKE_CMD       - invokes a command with loaded TA
-* TEE_CMD_ID_MAP_SHARED_MEM   - maps shared memory
-* TEE_CMD_ID_UNMAP_SHARED_MEM - unmaps shared memory
-
-AMD-TEE Trusted OS is the firmware running on AMD Secure Processor.
-
-The AMD-TEE driver registers itself with TEE subsystem and implements the
-following driver function callbacks:
-
-* get_version - returns the driver implementation id and capability.
-* open - sets up the driver context data structure.
-* release - frees up driver resources.
-* open_session - loads the TA binary and opens session with loaded TA.
-* close_session -  closes session with loaded TA and unloads it.
-* invoke_func - invokes a command with loaded TA.
-
-cancel_req driver callback is not supported by AMD-TEE.
-
-The GlobalPlatform TEE Client API [5] can be used by the user space (client) to
-talk to AMD's TEE. AMD's TEE provides a secure environment for loading, opening
-a session, invoking commands and clossing session with TA.
-
-References
-==========
-
-[1] https://github.com/OP-TEE/optee_os
-
-[2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
-
-[3] drivers/tee/optee/optee_smc.h
-
-[4] drivers/tee/optee/optee_msg.h
-
-[5] http://www.globalplatform.org/specificationsdevice.asp look for
-    "TEE Client API Specification v1.0" and click download.
-
-[6] include/linux/psp-tee.h
-
-[7] drivers/tee/amdtee/amdtee_if.h
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index cc4c5fc313df..c1709165c553 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -40,7 +40,7 @@ Synopsis of kprobe_events
  MEMADDR	: Address where the probe is inserted.
  MAXACTIVE	: Maximum number of instances of the specified function that
 		  can be probed simultaneously, or 0 for the default value
-		  as defined in Documentation/kprobes.txt section 1.3.1.
+		  as defined in Documentation/staging/kprobes.rst section 1.3.1.
 
  FETCHARGS	: Arguments. Each probe can have up to 128 args.
   %REG		: Fetch register REG
diff --git a/Documentation/xz.txt b/Documentation/xz.txt
deleted file mode 100644
index b2f5ff12a161..000000000000
--- a/Documentation/xz.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-============================
-XZ data compression in Linux
-============================
-
-Introduction
-============
-
-XZ is a general purpose data compression format with high compression
-ratio and relatively fast decompression. The primary compression
-algorithm (filter) is LZMA2. Additional filters can be used to improve
-compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters
-improve compression ratio of executable data.
-
-The XZ decompressor in Linux is called XZ Embedded. It supports
-the LZMA2 filter and optionally also BCJ filters. CRC32 is supported
-for integrity checking. The home page of XZ Embedded is at
-<https://tukaani.org/xz/embedded.html>, where you can find the
-latest version and also information about using the code outside
-the Linux kernel.
-
-For userspace, XZ Utils provide a zlib-like compression library
-and a gzip-like command line tool. XZ Utils can be downloaded from
-<https://tukaani.org/xz/>.
-
-XZ related components in the kernel
-===================================
-
-The xz_dec module provides XZ decompressor with single-call (buffer
-to buffer) and multi-call (stateful) APIs. The usage of the xz_dec
-module is documented in include/linux/xz.h.
-
-The xz_dec_test module is for testing xz_dec. xz_dec_test is not
-useful unless you are hacking the XZ decompressor. xz_dec_test
-allocates a char device major dynamically to which one can write
-.xz files from userspace. The decompressed output is thrown away.
-Keep an eye on dmesg to see diagnostics printed by xz_dec_test.
-See the xz_dec_test source code for the details.
-
-For decompressing the kernel image, initramfs, and initrd, there
-is a wrapper function in lib/decompress_unxz.c. Its API is the
-same as in other decompress_*.c files, which is defined in
-include/linux/decompress/generic.h.
-
-scripts/xz_wrap.sh is a wrapper for the xz command line tool found
-from XZ Utils. The wrapper sets compression options to values suitable
-for compressing the kernel image.
-
-For kernel makefiles, two commands are provided for use with
-$(call if_needed). The kernel image should be compressed with
-$(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2
-dictionary. It will also append a four-byte trailer containing the
-uncompressed size of the file, which is needed by the boot code.
-Other things should be compressed with $(call if_needed,xzmisc)
-which will use no BCJ filter and 1 MiB LZMA2 dictionary.
-
-Notes on compression options
-============================
-
-Since the XZ Embedded supports only streams with no integrity check or
-CRC32, make sure that you don't use some other integrity check type
-when encoding files that are supposed to be decoded by the kernel. With
-liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32
-when encoding. With the xz command line tool, use --check=none or
---check=crc32.
-
-Using CRC32 is strongly recommended unless there is some other layer
-which will verify the integrity of the uncompressed data anyway.
-Double checking the integrity would probably be waste of CPU cycles.
-Note that the headers will always have a CRC32 which will be validated
-by the decoder; you can only change the integrity check type (or
-disable it) for the actual uncompressed data.
-
-In userspace, LZMA2 is typically used with dictionary sizes of several
-megabytes. The decoder needs to have the dictionary in RAM, thus big
-dictionaries cannot be used for files that are intended to be decoded
-by the kernel. 1 MiB is probably the maximum reasonable dictionary
-size for in-kernel use (maybe more is OK for initramfs). The presets
-in XZ Utils may not be optimal when creating files for the kernel,
-so don't hesitate to use custom settings. Example::
-
-	xz --check=crc32 --lzma2=dict=512KiB inputfile
-
-An exception to above dictionary size limitation is when the decoder
-is used in single-call mode. Decompressing the kernel itself is an
-example of this situation. In single-call mode, the memory usage
-doesn't depend on the dictionary size, and it is perfectly fine to
-use a big dictionary: for maximum compression, the dictionary should
-be at least as big as the uncompressed data itself.
-
-Future plans
-============
-
-Creating a limited XZ encoder may be considered if people think it is
-useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at
-the fastest settings, so it isn't clear if LZMA2 encoder is wanted
-into the kernel.
-
-Support for limited random-access reading is planned for the
-decompression code. I don't know if it could have any use in the
-kernel, but I know that it would be useful in some embedded projects
-outside the Linux kernel.
-
-Conformance to the .xz file format specification
-================================================
-
-There are a couple of corner cases where things have been simplified
-at expense of detecting errors as early as possible. These should not
-matter in practice all, since they don't cause security issues. But
-it is good to know this if testing the code e.g. with the test files
-from XZ Utils.
-
-Reporting bugs
-==============
-
-Before reporting a bug, please check that it's not fixed already
-at upstream. See <https://tukaani.org/xz/embedded.html> to get the
-latest code.
-
-Report bugs to <lasse.collin@tukaani.org> or visit #tukaani on
-Freenode and talk to Larhzu. I don't actively read LKML or other
-kernel-related mailing lists, so if there's something I should know,
-you should email to me personally or use IRC.
-
-Don't bother Igor Pavlov with questions about the XZ implementation
-in the kernel or about XZ Utils. While these two implementations
-include essential code that is directly based on Igor Pavlov's code,
-these implementations aren't maintained nor supported by him.
diff --git a/MAINTAINERS b/MAINTAINERS
index f66fc236a325..ad90b3992887 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9597,7 +9597,7 @@ M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
 S:	Maintained
-F:	Documentation/kprobes.txt
+F:	Documentation/staging/kprobes.rst
 F:	include/asm-generic/kprobes.h
 F:	include/linux/kprobes.h
 F:	kernel/kprobes.c
@@ -14500,7 +14500,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rproc-next
 F:	Documentation/ABI/testing/sysfs-class-remoteproc
 F:	Documentation/devicetree/bindings/remoteproc/
-F:	Documentation/remoteproc.txt
+F:	Documentation/staging/remoteproc.rst
 F:	drivers/remoteproc/
 F:	include/linux/remoteproc.h
 F:	include/linux/remoteproc/
@@ -14512,7 +14512,7 @@ L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rpmsg-next
 F:	Documentation/ABI/testing/sysfs-bus-rpmsg
-F:	Documentation/rpmsg.txt
+F:	Documentation/staging/rpmsg.rst
 F:	drivers/rpmsg/
 F:	include/linux/rpmsg.h
 F:	include/linux/rpmsg/
@@ -16761,7 +16761,7 @@ TEE SUBSYSTEM
 M:	Jens Wiklander <jens.wiklander@linaro.org>
 L:	tee-dev@lists.linaro.org
 S:	Maintained
-F:	Documentation/tee.txt
+F:	Documentation/staging/tee.rst
 F:	drivers/tee/
 F:	include/linux/tee_drv.h
 F:	include/uapi/linux/tee.h
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 3526c0aee954..32809624d422 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -68,7 +68,7 @@
  * Lacking toolchain and or architecture support, static keys fall back to a
  * simple conditional branch.
  *
- * Additional babbling in: Documentation/static-keys.txt
+ * Additional babbling in: Documentation/staging/static-keys.rst
  */
 
 #ifndef __ASSEMBLY__
diff --git a/lib/crc32.c b/lib/crc32.c
index 4a20455d1f61..35a03d03f973 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -24,7 +24,7 @@
  * Version 2.  See the file COPYING for more details.
  */
 
-/* see: Documentation/crc32.txt for a description of algorithms */
+/* see: Documentation/staging/crc32.rst for a description of algorithms */
 
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 2717c7963acd..7892a40cf765 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -32,7 +32,7 @@
  * depending on the base count. Since the base count is taken from a u8
  * and a few bits, it is safe to assume that it will always be lower than
  * or equal to 2*255, thus we can always prevent any overflow by accepting
- * two less 255 steps. See Documentation/lzo.txt for more information.
+ * two less 255 steps. See Documentation/staging/lzo.rst for more information.
  */
 #define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
 
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 22528743d4ce..5cb50245a878 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -5,7 +5,7 @@ config XZ_DEC
 	help
 	  LZMA2 compression algorithm and BCJ filters are supported using
 	  the .xz file format as the container. For integrity checking,
-	  CRC32 is supported. See Documentation/xz.txt for more information.
+	  CRC32 is supported. See Documentation/staging/xz.rst for more information.
 
 if XZ_DEC
 
diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c
index 501911d1b327..240f2435ce6f 100644
--- a/samples/kprobes/kprobe_example.c
+++ b/samples/kprobes/kprobe_example.c
@@ -5,7 +5,7 @@
  * stack trace and selected registers when _do_fork() is called.
  *
  * For more information on theory of operation of kprobes, see
- * Documentation/kprobes.txt
+ * Documentation/staging/kprobes.rst
  *
  * You will see the trace data in /var/log/messages and on the console
  * whenever _do_fork() is invoked to create a new process.
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index 013e8e6ebae9..78a2da6fb3cd 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -11,7 +11,7 @@
  * If no func_name is specified, _do_fork is instrumented
  *
  * For more information on theory of operation of kretprobes, see
- * Documentation/kprobes.txt
+ * Documentation/staging/kprobes.rst
  *
  * Build and insert the kernel module as done in the kprobe example.
  * You will see the trace data in /var/log/messages and on the console
-- 
cgit v1.2.3


From cc7a21b6fbd945f8d8f61422ccd27203c1fafeb7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 Jun 2020 12:02:59 -0700
Subject: ipv6: icmp6: avoid indirect call for icmpv6_send()

If IPv6 is builtin, we do not need an expensive indirect call
to reach icmp6_send().

v2: put inline keyword before the type to avoid sparse warnings.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/icmpv6.h | 22 +++++++++++++++++++++-
 net/ipv6/icmp.c        |  5 +++--
 net/ipv6/ip6_icmp.c    | 10 +++++-----
 3 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 33d379602314..1b3371ae8193 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -13,12 +13,32 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb)
 #include <linux/netdevice.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info);
 
 typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 			     const struct in6_addr *force_saddr);
+#if IS_BUILTIN(CONFIG_IPV6)
+void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+		const struct in6_addr *force_saddr);
+static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+{
+	icmp6_send(skb, type, code, info, NULL);
+}
+static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn)
+{
+	BUILD_BUG_ON(fn != icmp6_send);
+	return 0;
+}
+static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn)
+{
+	BUILD_BUG_ON(fn != icmp6_send);
+	return 0;
+}
+#else
+extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info);
 extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn);
 extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn);
+#endif
+
 int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
 			       unsigned int data_len);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index fc5000370030..91e0f2fd2523 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -439,8 +439,8 @@ static int icmp6_iif(const struct sk_buff *skb)
 /*
  *	Send an ICMP message in response to a packet in error
  */
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-		       const struct in6_addr *force_saddr)
+void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+		const struct in6_addr *force_saddr)
 {
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -625,6 +625,7 @@ out:
 out_bh_enable:
 	local_bh_enable();
 }
+EXPORT_SYMBOL(icmp6_send);
 
 /* Slightly more convenient version of icmp6_send.
  */
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index e0086758b6ee..70c8c2f36c98 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -9,6 +9,8 @@
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#if !IS_BUILTIN(CONFIG_IPV6)
+
 static ip6_icmp_send_t __rcu *ip6_icmp_send;
 
 int inet6_register_icmp_sender(ip6_icmp_send_t *fn)
@@ -37,14 +39,12 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 
 	rcu_read_lock();
 	send = rcu_dereference(ip6_icmp_send);
-
-	if (!send)
-		goto out;
-	send(skb, type, code, info, NULL);
-out:
+	if (send)
+		send(skb, type, code, info, NULL);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(icmpv6_send);
+#endif
 
 #if IS_ENABLED(CONFIG_NF_NAT)
 #include <net/netfilter/nf_conntrack.h>
-- 
cgit v1.2.3


From c746053d275c8b6ff1d713addabf049c9c9a58fc Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 18 Jun 2020 14:45:58 +0100
Subject: net: phy: add support for probing MMDs >= 8 for devices-in-package

Add support for probing MMDs above 7 for a valid devices-in-package
specifier, but only probe the vendor MMDs for this if they also report
that there the device is present in status register 2.  This avoids
issues where the MMD is implemented, but does not provide IEEE 802.3
compliant registers (such as the MV88X3310 PHY.)

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 40 ++++++++++++++++++++++++++++++++++++++--
 include/linux/phy.h          |  2 ++
 2 files changed, 40 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 09096c3ceb86..8d9af2772853 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -661,6 +661,28 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 }
 EXPORT_SYMBOL(phy_device_create);
 
+/* phy_c45_probe_present - checks to see if a MMD is present in the package
+ * @bus: the target MII bus
+ * @prtad: PHY package address on the MII bus
+ * @devad: PHY device (MMD) address
+ *
+ * Read the MDIO_STAT2 register, and check whether a device is responding
+ * at this address.
+ *
+ * Returns: negative error number on bus access error, zero if no device
+ * is responding, or positive if a device is present.
+ */
+static int phy_c45_probe_present(struct mii_bus *bus, int prtad, int devad)
+{
+	int stat2;
+
+	stat2 = mdiobus_c45_read(bus, prtad, devad, MDIO_STAT2);
+	if (stat2 < 0)
+		return stat2;
+
+	return (stat2 & MDIO_STAT2_DEVPRST) == MDIO_STAT2_DEVPRST_VAL;
+}
+
 /* get_phy_c45_devs_in_pkg - reads a MMD's devices in package registers.
  * @bus: the target MII bus
  * @addr: PHY address on the MII bus
@@ -711,12 +733,26 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr,
 {
 	const int num_ids = ARRAY_SIZE(c45_ids->device_ids);
 	u32 *devs = &c45_ids->devices_in_package;
-	int i, phy_reg;
+	int i, ret, phy_reg;
 
 	/* Find first non-zero Devices In package. Device zero is reserved
 	 * for 802.3 c45 complied PHYs, so don't probe it at first.
 	 */
-	for (i = 1; i < num_ids && *devs == 0; i++) {
+	for (i = 1; i < MDIO_MMD_NUM && *devs == 0; i++) {
+		if (i == MDIO_MMD_VEND1 || i == MDIO_MMD_VEND2) {
+			/* Check that there is a device present at this
+			 * address before reading the devices-in-package
+			 * register to avoid reading garbage from the PHY.
+			 * Some PHYs (88x3310) vendor space is not IEEE802.3
+			 * compliant.
+			 */
+			ret = phy_c45_probe_present(bus, addr, i);
+			if (ret < 0)
+				return -EIO;
+
+			if (!ret)
+				continue;
+		}
 		phy_reg = get_phy_c45_devs_in_pkg(bus, addr, i, devs);
 		if (phy_reg < 0)
 			return -EIO;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8c05d0fb5c00..abe318387331 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -388,6 +388,8 @@ enum phy_state {
 	PHY_CABLETEST,
 };
 
+#define MDIO_MMD_NUM 32
+
 /**
  * struct phy_c45_device_ids - 802.3-c45 Device Identifiers
  * @devices_in_package: Bit vector of devices present.
-- 
cgit v1.2.3


From 320ed3bf900075614c43499dc01db8d25717b986 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 18 Jun 2020 14:46:08 +0100
Subject: net: phy: split devices_in_package

We have two competing requirements for the devices_in_package field.
We want to use it as a bit array indicating which MMDs are present, but
we also want to know if the Clause 22 registers are present.

Since "devices in package" is a term used in the 802.3 specification,
keep this as the as-specified values read from the PHY, and introduce
a new member "mmds_present" to indicate which MMDs are actually
present in the PHY, derived from the "devices in package" value.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c    | 4 ++--
 drivers/net/phy/phy_device.c | 6 +++---
 drivers/net/phy/phylink.c    | 8 ++++----
 include/linux/phy.h          | 4 +++-
 4 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index defe09d94422..bd11e62bfdfe 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -219,7 +219,7 @@ int genphy_c45_read_link(struct phy_device *phydev)
 	int val, devad;
 	bool link = true;
 
-	if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) {
+	if (phydev->c45_ids.mmds_present & MDIO_DEVS_AN) {
 		val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
 		if (val < 0)
 			return val;
@@ -409,7 +409,7 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev)
 	int val;
 
 	linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported);
-	if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) {
+	if (phydev->c45_ids.mmds_present & MDIO_DEVS_AN) {
 		val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
 		if (val < 0)
 			return val;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8e11e3d3a801..c1f81c4d0bb3 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -709,9 +709,6 @@ static int get_phy_c45_devs_in_pkg(struct mii_bus *bus, int addr, int dev_addr,
 		return -EIO;
 	*devices_in_package |= phy_reg;
 
-	/* Bit 0 doesn't represent a device, it indicates c22 regs presence */
-	*devices_in_package &= ~BIT(0);
-
 	return 0;
 }
 
@@ -789,6 +786,8 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr,
 	}
 
 	c45_ids->devices_in_package = devs_in_pkg;
+	/* Bit 0 doesn't represent a device, it indicates c22 regs presence */
+	c45_ids->mmds_present = devs_in_pkg & ~BIT(0);
 
 	return 0;
 }
@@ -857,6 +856,7 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
 	int r;
 
 	c45_ids.devices_in_package = 0;
+	c45_ids.mmds_present = 0;
 	memset(c45_ids.device_ids, 0xff, sizeof(c45_ids.device_ids));
 
 	if (is_c45)
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 0ab65fb75258..7ce787c227b3 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1638,11 +1638,11 @@ static int phylink_phy_read(struct phylink *pl, unsigned int phy_id,
 		case MII_BMSR:
 		case MII_PHYSID1:
 		case MII_PHYSID2:
-			devad = __ffs(phydev->c45_ids.devices_in_package);
+			devad = __ffs(phydev->c45_ids.mmds_present);
 			break;
 		case MII_ADVERTISE:
 		case MII_LPA:
-			if (!(phydev->c45_ids.devices_in_package & MDIO_DEVS_AN))
+			if (!(phydev->c45_ids.mmds_present & MDIO_DEVS_AN))
 				return -EINVAL;
 			devad = MDIO_MMD_AN;
 			if (reg == MII_ADVERTISE)
@@ -1678,11 +1678,11 @@ static int phylink_phy_write(struct phylink *pl, unsigned int phy_id,
 		case MII_BMSR:
 		case MII_PHYSID1:
 		case MII_PHYSID2:
-			devad = __ffs(phydev->c45_ids.devices_in_package);
+			devad = __ffs(phydev->c45_ids.mmds_present);
 			break;
 		case MII_ADVERTISE:
 		case MII_LPA:
-			if (!(phydev->c45_ids.devices_in_package & MDIO_DEVS_AN))
+			if (!(phydev->c45_ids.mmds_present & MDIO_DEVS_AN))
 				return -EINVAL;
 			devad = MDIO_MMD_AN;
 			if (reg == MII_ADVERTISE)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index abe318387331..19d9e040ad84 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -392,11 +392,13 @@ enum phy_state {
 
 /**
  * struct phy_c45_device_ids - 802.3-c45 Device Identifiers
- * @devices_in_package: Bit vector of devices present.
+ * @devices_in_package: IEEE 802.3 devices in package register value.
+ * @mmds_present: bit vector of MMDs present.
  * @device_ids: The device identifer for each present device.
  */
 struct phy_c45_device_ids {
 	u32 devices_in_package;
+	u32 mmds_present;
 	u32 device_ids[8];
 };
 
-- 
cgit v1.2.3


From 389a338999875b6e7b111096e8b6484434556449 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 18 Jun 2020 14:46:13 +0100
Subject: net: phy: read MMD ID from all present MMDs

Expand the device_ids[] array to allow all MMD IDs to be read rather
than just the first 8 MMDs, but only read the ID if the MDIO_STAT2
register reports that a device really is present here for these new
devices to maintain compatibility with our current behaviour.  Note
that only a limited number of devices have MDIO_STAT2.

88X3310 PHY vendor MMDs do are marked as present in the
devices_in_package, but do not contain IEE 802.3 compatible register
sets in their lower space.  This avoids reading incorrect values as MMD
identifiers.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 13 +++++++++++++
 include/linux/phy.h          |  2 +-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c1f81c4d0bb3..29ef4456ac25 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -774,6 +774,19 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr,
 		if (!(devs_in_pkg & (1 << i)))
 			continue;
 
+		if (i == MDIO_MMD_VEND1 || i == MDIO_MMD_VEND2) {
+			/* Probe the "Device Present" bits for the vendor MMDs
+			 * to ignore these if they do not contain IEEE 802.3
+			 * registers.
+			 */
+			ret = phy_c45_probe_present(bus, addr, i);
+			if (ret < 0)
+				return ret;
+
+			if (!ret)
+				continue;
+		}
+
 		phy_reg = mdiobus_c45_read(bus, addr, i, MII_PHYSID1);
 		if (phy_reg < 0)
 			return -EIO;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 19d9e040ad84..9248dd2ce4ca 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -399,7 +399,7 @@ enum phy_state {
 struct phy_c45_device_ids {
 	u32 devices_in_package;
 	u32 mmds_present;
-	u32 device_ids[8];
+	u32 device_ids[MDIO_MMD_NUM];
 };
 
 struct macsec_context;
-- 
cgit v1.2.3


From 775f43facfe89af605d77a9669aa311b5b95cd07 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Wed, 17 Jun 2020 18:46:42 +0200
Subject: Drivers: hv: vmbus: Remove the lock field from the vmbus_channel
 struct

The spinlock is (now) *not used to protect test-and-set accesses
to attributes of the structure or sc_list operations.

There is, AFAICT, a distinct lack of {WRITE,READ}_ONCE()s in the
handling of channel->state, but the changes below do not seem to
make things "worse".  ;-)

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200617164642.37393-9-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c      | 6 +-----
 drivers/hv/channel_mgmt.c | 1 -
 include/linux/hyperv.h    | 6 ------
 3 files changed, 1 insertion(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 8848d1548b3f..3ebda7707e46 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -129,12 +129,8 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	send_pages = newchannel->ringbuffer_send_offset;
 	recv_pages = newchannel->ringbuffer_pagecount - send_pages;
 
-	spin_lock_irqsave(&newchannel->lock, flags);
-	if (newchannel->state != CHANNEL_OPEN_STATE) {
-		spin_unlock_irqrestore(&newchannel->lock, flags);
+	if (newchannel->state != CHANNEL_OPEN_STATE)
 		return -EINVAL;
-	}
-	spin_unlock_irqrestore(&newchannel->lock, flags);
 
 	newchannel->state = CHANNEL_OPENING_STATE;
 	newchannel->onchannel_callback = onchannelcallback;
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 92f8bb2077a9..591106cf58fc 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -317,7 +317,6 @@ static struct vmbus_channel *alloc_channel(void)
 		return NULL;
 
 	spin_lock_init(&channel->sched_lock);
-	spin_lock_init(&channel->lock);
 	init_completion(&channel->rescind_event);
 
 	INIT_LIST_HEAD(&channel->sc_list);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 690394b79d72..38100e80360a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -840,12 +840,6 @@ struct vmbus_channel {
 	 */
 	void (*chn_rescind_callback)(struct vmbus_channel *channel);
 
-	/*
-	 * The spinlock to protect the structure. It is being used to protect
-	 * test-and-set access to various attributes of the structure as well
-	 * as all sc_list operations.
-	 */
-	spinlock_t lock;
 	/*
 	 * All Sub-channels of a primary channel are linked here.
 	 */
-- 
cgit v1.2.3


From 481e980a7c199c5a4634fd7ea308067dd4ba75fa Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Mon, 15 Jun 2020 12:57:58 +0000
Subject: mm: Allow arches to provide ptep_get()

Since commit 9e343b467c70 ("READ_ONCE: Enforce atomicity for
{READ,WRITE}_ONCE() memory accesses") it is not possible anymore to
use READ_ONCE() to access complex page table entries like the one
defined for powerpc 8xx with 16k size pages.

Define a ptep_get() helper that architectures can override instead
of performing a READ_ONCE() on the page table entry pointer.

Fixes: 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/087fa12b6e920e32315136b998aa834f99242695.1592225558.git.christophe.leroy@csgroup.eu
---
 include/asm-generic/hugetlb.h | 2 +-
 include/linux/pgtable.h       | 7 +++++++
 mm/gup.c                      | 2 +-
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 40f85decc2ee..8e1e6244a89d 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -122,7 +122,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
-	return READ_ONCE(*ptep);
+	return ptep_get(ptep);
 }
 #endif
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 32b6c52d41b9..56c1e8eb7bb0 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -249,6 +249,13 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTEP_GET
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	return READ_ONCE(*ptep);
+}
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
diff --git a/mm/gup.c b/mm/gup.c
index 761df4944ef5..6f47697f8fb0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2196,7 +2196,7 @@ static inline pte_t gup_get_pte(pte_t *ptep)
  */
 static inline pte_t gup_get_pte(pte_t *ptep)
 {
-	return READ_ONCE(*ptep);
+	return ptep_get(ptep);
 }
 #endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
 
-- 
cgit v1.2.3


From f11d59d87b8622d4cf9f856c0b8029fb030d8612 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 25 May 2020 14:38:53 +0300
Subject: iio: Move attach/detach of the poll func to the core

All devices using a triggered buffer need to attach and detach the trigger
to the device in order to properly work. Instead of doing this in each and
every driver by hand move this into the core.

At this point in time, all drivers should have been resolved to
attach/detach the poll-function in the same order.

This patch removes all explicit calls of iio_triggered_buffer_postenable()
& iio_triggered_buffer_predisable() in all drivers, since the core handles
now the pollfunc attach/detach.

The more peculiar change is for the 'at91-sama5d2_adc' driver, since it's
not immediately obvious that removing the hooks doesn't break anything.
Eugen was able to test on at91-sama5d2-adc driver, sama5d2-xplained board.
All seems to be fine.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Tested-by: Eugen Hristev <eugen.hristev@microchip.com> #for at91-sama5d2-adc
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl372.c                        | 20 +++--------
 drivers/iio/accel/bmc150-accel-core.c              |  4 +--
 drivers/iio/accel/kxcjk-1013.c                     |  2 --
 drivers/iio/accel/kxsd9.c                          |  2 --
 drivers/iio/accel/st_accel_buffer.c                | 22 +++---------
 drivers/iio/accel/stk8312.c                        |  2 --
 drivers/iio/accel/stk8ba50.c                       |  2 --
 drivers/iio/adc/ad7266.c                           |  2 --
 drivers/iio/adc/ad7606.c                           |  3 +-
 drivers/iio/adc/ad7766.c                           |  2 --
 drivers/iio/adc/ad7768-1.c                         |  8 +----
 drivers/iio/adc/ad7887.c                           |  2 --
 drivers/iio/adc/ad_sigma_delta.c                   |  5 ---
 drivers/iio/adc/at91-sama5d2_adc.c                 | 18 ----------
 drivers/iio/adc/dln2-adc.c                         | 12 +------
 drivers/iio/adc/mxs-lradc-adc.c                    |  2 --
 drivers/iio/adc/stm32-adc.c                        | 36 +++-----------------
 drivers/iio/adc/stm32-dfsdm-adc.c                  | 39 +++-------------------
 drivers/iio/adc/ti-adc084s021.c                    |  2 --
 drivers/iio/adc/ti-ads1015.c                       |  2 --
 drivers/iio/adc/vf610_adc.c                        |  7 +---
 drivers/iio/adc/xilinx-xadc-core.c                 |  2 --
 drivers/iio/buffer/industrialio-triggered-buffer.c | 10 +-----
 drivers/iio/chemical/atlas-sensor.c                |  6 +---
 drivers/iio/dummy/iio_simple_dummy_buffer.c        | 14 --------
 drivers/iio/gyro/bmg160_core.c                     |  2 --
 drivers/iio/gyro/mpu3050-core.c                    |  2 --
 drivers/iio/gyro/st_gyro_buffer.c                  | 21 +++---------
 drivers/iio/humidity/hdc100x.c                     | 12 +------
 drivers/iio/humidity/hts221_buffer.c               |  2 --
 drivers/iio/iio_core_trigger.h                     | 17 ++++++++++
 drivers/iio/industrialio-buffer.c                  | 13 ++++++++
 drivers/iio/industrialio-trigger.c                 | 22 +++---------
 drivers/iio/light/gp2ap020a00f.c                   | 10 ------
 drivers/iio/light/isl29125.c                       | 20 ++---------
 drivers/iio/light/rpr0521.c                        |  2 --
 drivers/iio/light/si1145.c                         |  2 --
 drivers/iio/light/st_uvis25_core.c                 |  2 --
 drivers/iio/light/tcs3414.c                        | 20 ++---------
 drivers/iio/light/vcnl4000.c                       | 35 ++++---------------
 drivers/iio/magnetometer/bmc150_magn.c             |  2 --
 drivers/iio/magnetometer/rm3100-core.c             |  2 --
 drivers/iio/magnetometer/st_magn_buffer.c          | 26 ++-------------
 drivers/iio/potentiostat/lmp91000.c                | 13 ++------
 drivers/iio/pressure/st_pressure_buffer.c          | 26 ++-------------
 drivers/iio/pressure/zpa2326.c                     | 27 ++++++---------
 drivers/iio/proximity/sx9310.c                     |  2 --
 drivers/iio/proximity/sx9500.c                     |  9 -----
 include/linux/iio/trigger_consumer.h               |  7 ----
 49 files changed, 93 insertions(+), 429 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index 26ca45073a56..e7e316b75e87 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -795,13 +795,9 @@ static int adxl372_buffer_postenable(struct iio_dev *indio_dev)
 	unsigned int mask;
 	int i, ret;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret < 0)
-		return ret;
-
 	ret = adxl372_set_interrupts(st, ADXL372_INT1_MAP_FIFO_FULL_MSK, 0);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	mask = *indio_dev->active_scan_mask;
 
@@ -810,10 +806,8 @@ static int adxl372_buffer_postenable(struct iio_dev *indio_dev)
 			break;
 	}
 
-	if (i == ARRAY_SIZE(adxl372_axis_lookup_table)) {
-		ret = -EINVAL;
-		goto err;
-	}
+	if (i == ARRAY_SIZE(adxl372_axis_lookup_table))
+		return -EINVAL;
 
 	st->fifo_format = adxl372_axis_lookup_table[i].fifo_format;
 	st->fifo_set_size = bitmap_weight(indio_dev->active_scan_mask,
@@ -833,14 +827,10 @@ static int adxl372_buffer_postenable(struct iio_dev *indio_dev)
 	if (ret < 0) {
 		st->fifo_mode = ADXL372_FIFO_BYPASSED;
 		adxl372_set_interrupts(st, 0, 0);
-		goto err;
+		return ret;
 	}
 
 	return 0;
-
-err:
-	iio_triggered_buffer_predisable(indio_dev);
-	return ret;
 }
 
 static int adxl372_buffer_predisable(struct iio_dev *indio_dev)
@@ -851,7 +841,7 @@ static int adxl372_buffer_predisable(struct iio_dev *indio_dev)
 	st->fifo_mode = ADXL372_FIFO_BYPASSED;
 	adxl372_configure_fifo(st);
 
-	return iio_triggered_buffer_predisable(indio_dev);
+	return 0;
 }
 
 static const struct iio_buffer_setup_ops adxl372_buffer_ops = {
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 8f60d0727ee8..24864d9dfab5 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -1411,7 +1411,7 @@ static int bmc150_accel_buffer_postenable(struct iio_dev *indio_dev)
 	int ret = 0;
 
 	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
-		return iio_triggered_buffer_postenable(indio_dev);
+		return 0;
 
 	mutex_lock(&data->mutex);
 
@@ -1443,7 +1443,7 @@ static int bmc150_accel_buffer_predisable(struct iio_dev *indio_dev)
 	struct bmc150_accel_data *data = iio_priv(indio_dev);
 
 	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
-		return iio_triggered_buffer_predisable(indio_dev);
+		return 0;
 
 	mutex_lock(&data->mutex);
 
diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c
index 6b93521c0e17..beb38d9d607d 100644
--- a/drivers/iio/accel/kxcjk-1013.c
+++ b/drivers/iio/accel/kxcjk-1013.c
@@ -1027,9 +1027,7 @@ static const struct iio_chan_spec kxcjk1013_channels[] = {
 
 static const struct iio_buffer_setup_ops kxcjk1013_buffer_setup_ops = {
 	.preenable		= kxcjk1013_buffer_preenable,
-	.postenable		= iio_triggered_buffer_postenable,
 	.postdisable		= kxcjk1013_buffer_postdisable,
-	.predisable		= iio_triggered_buffer_predisable,
 };
 
 static const struct iio_info kxcjk1013_info = {
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 63b1d8ee6c6f..66b2e4cf24cf 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -252,8 +252,6 @@ static int kxsd9_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops kxsd9_buffer_setup_ops = {
 	.preenable = kxsd9_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = kxsd9_buffer_postdisable,
 };
 
diff --git a/drivers/iio/accel/st_accel_buffer.c b/drivers/iio/accel/st_accel_buffer.c
index b5c814ef1637..492263589e04 100644
--- a/drivers/iio/accel/st_accel_buffer.c
+++ b/drivers/iio/accel/st_accel_buffer.c
@@ -33,13 +33,9 @@ static int st_accel_buffer_postenable(struct iio_dev *indio_dev)
 {
 	int err;
 
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err < 0)
-		return err;
-
 	err = st_sensors_set_axis_enable(indio_dev, indio_dev->active_scan_mask[0]);
 	if (err < 0)
-		goto st_accel_buffer_predisable;
+		return err;
 
 	err = st_sensors_set_enable(indio_dev, true);
 	if (err < 0)
@@ -49,27 +45,19 @@ static int st_accel_buffer_postenable(struct iio_dev *indio_dev)
 
 st_accel_buffer_enable_all_axis:
 	st_sensors_set_axis_enable(indio_dev, ST_SENSORS_ENABLE_ALL_AXIS);
-st_accel_buffer_predisable:
-	iio_triggered_buffer_predisable(indio_dev);
 	return err;
 }
 
 static int st_accel_buffer_predisable(struct iio_dev *indio_dev)
 {
-	int err, err2;
+	int err;
 
 	err = st_sensors_set_enable(indio_dev, false);
 	if (err < 0)
-		goto st_accel_buffer_predisable;
-
-	err = st_sensors_set_axis_enable(indio_dev, ST_SENSORS_ENABLE_ALL_AXIS);
-
-st_accel_buffer_predisable:
-	err2 = iio_triggered_buffer_predisable(indio_dev);
-	if (!err)
-		err = err2;
+		return err;
 
-	return err;
+	return st_sensors_set_axis_enable(indio_dev,
+					  ST_SENSORS_ENABLE_ALL_AXIS);
 }
 
 static const struct iio_buffer_setup_ops st_accel_buffer_setup_ops = {
diff --git a/drivers/iio/accel/stk8312.c b/drivers/iio/accel/stk8312.c
index 616d0b90dd92..3b59887a8581 100644
--- a/drivers/iio/accel/stk8312.c
+++ b/drivers/iio/accel/stk8312.c
@@ -492,8 +492,6 @@ static int stk8312_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops stk8312_buffer_setup_ops = {
 	.preenable   = stk8312_buffer_preenable,
-	.postenable  = iio_triggered_buffer_postenable,
-	.predisable  = iio_triggered_buffer_predisable,
 	.postdisable = stk8312_buffer_postdisable,
 };
 
diff --git a/drivers/iio/accel/stk8ba50.c b/drivers/iio/accel/stk8ba50.c
index 98fad8cd6fe7..3ead378b02c9 100644
--- a/drivers/iio/accel/stk8ba50.c
+++ b/drivers/iio/accel/stk8ba50.c
@@ -376,8 +376,6 @@ static int stk8ba50_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops stk8ba50_buffer_setup_ops = {
 	.preenable   = stk8ba50_buffer_preenable,
-	.postenable  = iio_triggered_buffer_postenable,
-	.predisable  = iio_triggered_buffer_predisable,
 	.postdisable = stk8ba50_buffer_postdisable,
 };
 
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 3dc15ec04f66..a8ec3efd659e 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -74,8 +74,6 @@ static int ad7266_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops iio_triggered_buffer_setup_ops = {
 	.preenable = &ad7266_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &ad7266_postdisable,
 };
 
diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index 23d8277086ee..ee7b108688b3 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -499,7 +499,6 @@ static int ad7606_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct ad7606_state *st = iio_priv(indio_dev);
 
-	iio_triggered_buffer_postenable(indio_dev);
 	gpiod_set_value(st->gpio_convst, 1);
 
 	return 0;
@@ -511,7 +510,7 @@ static int ad7606_buffer_predisable(struct iio_dev *indio_dev)
 
 	gpiod_set_value(st->gpio_convst, 0);
 
-	return iio_triggered_buffer_predisable(indio_dev);
+	return 0;
 }
 
 static const struct iio_buffer_setup_ops ad7606_buffer_ops = {
diff --git a/drivers/iio/adc/ad7766.c b/drivers/iio/adc/ad7766.c
index 4bcf8a34bc46..b6b6765be7b4 100644
--- a/drivers/iio/adc/ad7766.c
+++ b/drivers/iio/adc/ad7766.c
@@ -178,8 +178,6 @@ static const struct ad7766_chip_info ad7766_chip_info[] = {
 
 static const struct iio_buffer_setup_ops ad7766_buffer_setup_ops = {
 	.preenable = &ad7766_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &ad7766_postdisable,
 };
 
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index be2aed551324..0e93b0766eb4 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -490,7 +490,6 @@ static int ad7768_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct ad7768_state *st = iio_priv(indio_dev);
 
-	iio_triggered_buffer_postenable(indio_dev);
 	/*
 	 * Write a 1 to the LSB of the INTERFACE_FORMAT register to enter
 	 * continuous read mode. Subsequent data reads do not require an
@@ -502,17 +501,12 @@ static int ad7768_buffer_postenable(struct iio_dev *indio_dev)
 static int ad7768_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct ad7768_state *st = iio_priv(indio_dev);
-	int ret;
 
 	/*
 	 * To exit continuous read mode, perform a single read of the ADC_DATA
 	 * reg (0x2C), which allows further configuration of the device.
 	 */
-	ret = ad7768_spi_reg_read(st, AD7768_REG_ADC_DATA, 3);
-	if (ret < 0)
-		return ret;
-
-	return iio_triggered_buffer_predisable(indio_dev);
+	return ad7768_spi_reg_read(st, AD7768_REG_ADC_DATA, 3);
 }
 
 static const struct iio_buffer_setup_ops ad7768_buffer_ops = {
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index d1d43fb700ba..f8e6243457bb 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -136,8 +136,6 @@ done:
 
 static const struct iio_buffer_setup_ops ad7887_ring_setup_ops = {
 	.preenable = &ad7887_ring_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &ad7887_ring_postdisable,
 };
 
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index dd3d54b3bc8b..3554ee6ee099 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -345,10 +345,6 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	unsigned int channel;
 	int ret;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret < 0)
-		return ret;
-
 	channel = find_first_bit(indio_dev->active_scan_mask,
 				 indio_dev->masklength);
 	ret = ad_sigma_delta_set_channel(sigma_delta,
@@ -441,7 +437,6 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 
 static const struct iio_buffer_setup_ops ad_sd_buffer_setup_ops = {
 	.postenable = &ad_sd_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &ad_sd_buffer_postdisable,
 	.validate_scan_mask = &iio_validate_scan_mask_onehot,
 };
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 1b4340a6c6bb..6cc06f1566eb 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -937,14 +937,6 @@ static int at91_adc_buffer_preenable(struct iio_dev *indio_dev)
 	return 0;
 }
 
-static int at91_adc_buffer_postenable(struct iio_dev *indio_dev)
-{
-	if (at91_adc_current_chan_is_touch(indio_dev))
-		return 0;
-
-	return iio_triggered_buffer_postenable(indio_dev);
-}
-
 static int at91_adc_buffer_postdisable(struct iio_dev *indio_dev)
 {
 	struct at91_adc_state *st = iio_priv(indio_dev);
@@ -995,19 +987,9 @@ static int at91_adc_buffer_postdisable(struct iio_dev *indio_dev)
 	return 0;
 }
 
-static int at91_adc_buffer_predisable(struct iio_dev *indio_dev)
-{
-	if (at91_adc_current_chan_is_touch(indio_dev))
-		return 0;
-
-	return iio_triggered_buffer_predisable(indio_dev);
-}
-
 static const struct iio_buffer_setup_ops at91_buffer_setup_ops = {
 	.preenable = &at91_adc_buffer_preenable,
 	.postdisable = &at91_adc_buffer_postdisable,
-	.postenable = &at91_adc_buffer_postenable,
-	.predisable = &at91_adc_buffer_predisable,
 };
 
 static struct iio_trigger *at91_adc_allocate_trigger(struct iio_dev *indio,
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index 6689cb93c6a2..0d53ef18e045 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -524,10 +524,6 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev)
 	u16 conflict;
 	unsigned int trigger_chan;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	mutex_lock(&dln2->mutex);
 
 	/* Enable ADC */
@@ -541,7 +537,6 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev)
 				(int)conflict);
 			ret = -EBUSY;
 		}
-		iio_triggered_buffer_predisable(indio_dev);
 		return ret;
 	}
 
@@ -555,7 +550,6 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev)
 		mutex_unlock(&dln2->mutex);
 		if (ret < 0) {
 			dev_dbg(&dln2->pdev->dev, "Problem in %s\n", __func__);
-			iio_triggered_buffer_predisable(indio_dev);
 			return ret;
 		}
 	} else {
@@ -568,7 +562,7 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev)
 
 static int dln2_adc_triggered_buffer_predisable(struct iio_dev *indio_dev)
 {
-	int ret, ret2;
+	int ret;
 	struct dln2_adc *dln2 = iio_priv(indio_dev);
 
 	mutex_lock(&dln2->mutex);
@@ -586,10 +580,6 @@ static int dln2_adc_triggered_buffer_predisable(struct iio_dev *indio_dev)
 	if (ret < 0)
 		dev_dbg(&dln2->pdev->dev, "Problem in %s\n", __func__);
 
-	ret2 = iio_triggered_buffer_predisable(indio_dev);
-	if (ret == 0)
-		ret = ret2;
-
 	return ret;
 }
 
diff --git a/drivers/iio/adc/mxs-lradc-adc.c b/drivers/iio/adc/mxs-lradc-adc.c
index c371565374d1..30e29f44ebd2 100644
--- a/drivers/iio/adc/mxs-lradc-adc.c
+++ b/drivers/iio/adc/mxs-lradc-adc.c
@@ -568,8 +568,6 @@ static bool mxs_lradc_adc_validate_scan_mask(struct iio_dev *iio,
 
 static const struct iio_buffer_setup_ops mxs_lradc_adc_buffer_ops = {
 	.preenable = &mxs_lradc_adc_buffer_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &mxs_lradc_adc_buffer_postdisable,
 	.validate_scan_mask = &mxs_lradc_adc_validate_scan_mask,
 };
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index e5a2bfcb5681..3eb9ebe8372f 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1492,7 +1492,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev)
 	return 0;
 }
 
-static int __stm32_adc_buffer_postenable(struct iio_dev *indio_dev)
+static int stm32_adc_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct stm32_adc *adc = iio_priv(indio_dev);
 	struct device *dev = indio_dev->dev.parent;
@@ -1537,22 +1537,7 @@ err_pm_put:
 	return ret;
 }
 
-static int stm32_adc_buffer_postenable(struct iio_dev *indio_dev)
-{
-	int ret;
-
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret < 0)
-		return ret;
-
-	ret = __stm32_adc_buffer_postenable(indio_dev);
-	if (ret < 0)
-		iio_triggered_buffer_predisable(indio_dev);
-
-	return ret;
-}
-
-static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
+static int stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct stm32_adc *adc = iio_priv(indio_dev);
 	struct device *dev = indio_dev->dev.parent;
@@ -1571,19 +1556,8 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
 
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
-}
-
-static int stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
-{
-	int ret;
-
-	__stm32_adc_buffer_predisable(indio_dev);
-
-	ret = iio_triggered_buffer_predisable(indio_dev);
-	if (ret < 0)
-		dev_err(&indio_dev->dev, "predisable failed\n");
 
-	return ret;
+	return 0;
 }
 
 static const struct iio_buffer_setup_ops stm32_adc_buffer_setup_ops = {
@@ -2024,7 +1998,7 @@ static int stm32_adc_suspend(struct device *dev)
 	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 
 	if (iio_buffer_enabled(indio_dev))
-		__stm32_adc_buffer_predisable(indio_dev);
+		stm32_adc_buffer_predisable(indio_dev);
 
 	return pm_runtime_force_suspend(dev);
 }
@@ -2046,7 +2020,7 @@ static int stm32_adc_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	return __stm32_adc_buffer_postenable(indio_dev);
+	return stm32_adc_buffer_postenable(indio_dev);
 }
 #endif
 
diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c
index 017d1ba4c14e..5e10fb4f3704 100644
--- a/drivers/iio/adc/stm32-dfsdm-adc.c
+++ b/drivers/iio/adc/stm32-dfsdm-adc.c
@@ -995,7 +995,7 @@ static int stm32_dfsdm_update_scan_mode(struct iio_dev *indio_dev,
 	return 0;
 }
 
-static int __stm32_dfsdm_postenable(struct iio_dev *indio_dev)
+static int stm32_dfsdm_postenable(struct iio_dev *indio_dev)
 {
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
 	int ret;
@@ -1038,30 +1038,7 @@ err_stop_hwc:
 	return ret;
 }
 
-static int stm32_dfsdm_postenable(struct iio_dev *indio_dev)
-{
-	int ret;
-
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
-		ret = iio_triggered_buffer_postenable(indio_dev);
-		if (ret < 0)
-			return ret;
-	}
-
-	ret = __stm32_dfsdm_postenable(indio_dev);
-	if (ret < 0)
-		goto err_predisable;
-
-	return 0;
-
-err_predisable:
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
-		iio_triggered_buffer_predisable(indio_dev);
-
-	return ret;
-}
-
-static void __stm32_dfsdm_predisable(struct iio_dev *indio_dev)
+static int stm32_dfsdm_predisable(struct iio_dev *indio_dev)
 {
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
 
@@ -1073,14 +1050,6 @@ static void __stm32_dfsdm_predisable(struct iio_dev *indio_dev)
 
 	if (adc->hwc)
 		iio_hw_consumer_disable(adc->hwc);
-}
-
-static int stm32_dfsdm_predisable(struct iio_dev *indio_dev)
-{
-	__stm32_dfsdm_predisable(indio_dev);
-
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
-		iio_triggered_buffer_predisable(indio_dev);
 
 	return 0;
 }
@@ -1668,7 +1637,7 @@ static int __maybe_unused stm32_dfsdm_adc_suspend(struct device *dev)
 	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 
 	if (iio_buffer_enabled(indio_dev))
-		__stm32_dfsdm_predisable(indio_dev);
+		stm32_dfsdm_predisable(indio_dev);
 
 	return 0;
 }
@@ -1691,7 +1660,7 @@ static int __maybe_unused stm32_dfsdm_adc_resume(struct device *dev)
 	}
 
 	if (iio_buffer_enabled(indio_dev))
-		__stm32_dfsdm_postenable(indio_dev);
+		stm32_dfsdm_postenable(indio_dev);
 
 	return 0;
 }
diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c
index f22f004c1eb6..c2db2435f419 100644
--- a/drivers/iio/adc/ti-adc084s021.c
+++ b/drivers/iio/adc/ti-adc084s021.c
@@ -187,8 +187,6 @@ static const struct iio_info adc084s021_info = {
 
 static const struct iio_buffer_setup_ops adc084s021_buffer_setup_ops = {
 	.preenable = adc084s021_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = adc084s021_buffer_postdisable,
 };
 
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index 1a5f520080d2..f42ab112986e 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -788,8 +788,6 @@ static int ads1015_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops ads1015_buffer_setup_ops = {
 	.preenable	= ads1015_buffer_preenable,
-	.postenable	= iio_triggered_buffer_postenable,
-	.predisable	= iio_triggered_buffer_predisable,
 	.postdisable	= ads1015_buffer_postdisable,
 	.validate_scan_mask = &iio_validate_scan_mask_onehot,
 };
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index f5637bf38d37..1d794cf3e3f1 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -724,13 +724,8 @@ static int vf610_adc_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct vf610_adc *info = iio_priv(indio_dev);
 	unsigned int channel;
-	int ret;
 	int val;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	val = readl(info->regs + VF610_REG_ADC_GC);
 	val |= VF610_ADC_ADCON;
 	writel(val, info->regs + VF610_REG_ADC_GC);
@@ -761,7 +756,7 @@ static int vf610_adc_buffer_predisable(struct iio_dev *indio_dev)
 
 	writel(hc_cfg, info->regs + VF610_REG_ADC_HC0);
 
-	return iio_triggered_buffer_predisable(indio_dev);
+	return 0;
 }
 
 static const struct iio_buffer_setup_ops iio_triggered_buffer_setup_ops = {
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 69be9e82fe3e..d0b7ef296afb 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -839,8 +839,6 @@ err:
 
 static const struct iio_buffer_setup_ops xadc_buffer_ops = {
 	.preenable = &xadc_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
 	.postdisable = &xadc_postdisable,
 };
 
diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c
index e8046c1ecd6b..6c20a83f887e 100644
--- a/drivers/iio/buffer/industrialio-triggered-buffer.c
+++ b/drivers/iio/buffer/industrialio-triggered-buffer.c
@@ -13,11 +13,6 @@
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 
-static const struct iio_buffer_setup_ops iio_triggered_buffer_setup_ops = {
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
-};
-
 /**
  * iio_triggered_buffer_setup() - Setup triggered buffer and pollfunc
  * @indio_dev:		IIO device structure
@@ -67,10 +62,7 @@ int iio_triggered_buffer_setup(struct iio_dev *indio_dev,
 	}
 
 	/* Ring buffer functions - here trigger setup related */
-	if (setup_ops)
-		indio_dev->setup_ops = setup_ops;
-	else
-		indio_dev->setup_ops = &iio_triggered_buffer_setup_ops;
+	indio_dev->setup_ops = setup_ops;
 
 	/* Flag that polled ring buffering is possible */
 	indio_dev->modes |= INDIO_BUFFER_TRIGGERED;
diff --git a/drivers/iio/chemical/atlas-sensor.c b/drivers/iio/chemical/atlas-sensor.c
index 047f4b3f5a0e..43069636fcd5 100644
--- a/drivers/iio/chemical/atlas-sensor.c
+++ b/drivers/iio/chemical/atlas-sensor.c
@@ -410,10 +410,6 @@ static int atlas_buffer_postenable(struct iio_dev *indio_dev)
 	struct atlas_data *data = iio_priv(indio_dev);
 	int ret;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	ret = pm_runtime_get_sync(&data->client->dev);
 	if (ret < 0) {
 		pm_runtime_put_noidle(&data->client->dev);
@@ -437,7 +433,7 @@ static int atlas_buffer_predisable(struct iio_dev *indio_dev)
 	if (ret)
 		return ret;
 
-	return iio_triggered_buffer_predisable(indio_dev);
+	return 0;
 }
 
 static const struct iio_trigger_ops atlas_interrupt_trigger_ops = {
diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c
index 17606eca42b4..8e13c53d4360 100644
--- a/drivers/iio/dummy/iio_simple_dummy_buffer.c
+++ b/drivers/iio/dummy/iio_simple_dummy_buffer.c
@@ -99,20 +99,6 @@ done:
 }
 
 static const struct iio_buffer_setup_ops iio_simple_dummy_buffer_setup_ops = {
-	/*
-	 * iio_triggered_buffer_postenable:
-	 * Generic function that simply attaches the pollfunc to the trigger.
-	 * Replace this to mess with hardware state before we attach the
-	 * trigger.
-	 */
-	.postenable = &iio_triggered_buffer_postenable,
-	/*
-	 * iio_triggered_buffer_predisable:
-	 * Generic function that simple detaches the pollfunc from the trigger.
-	 * Replace this to put hardware state back again after the trigger is
-	 * detached but before userspace knows we have disabled the ring.
-	 */
-	.predisable = &iio_triggered_buffer_predisable,
 };
 
 int iio_simple_dummy_configure_buffer(struct iio_dev *indio_dev)
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index 933492b33189..8ddda96455fc 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -1051,8 +1051,6 @@ static int bmg160_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops bmg160_buffer_setup_ops = {
 	.preenable = bmg160_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = bmg160_buffer_postdisable,
 };
 
diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index 157330451e0a..00e58060968c 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -662,8 +662,6 @@ static int mpu3050_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops mpu3050_buffer_setup_ops = {
 	.preenable = mpu3050_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = mpu3050_buffer_postdisable,
 };
 
diff --git a/drivers/iio/gyro/st_gyro_buffer.c b/drivers/iio/gyro/st_gyro_buffer.c
index 9c92ff7a82be..4feb7ada7195 100644
--- a/drivers/iio/gyro/st_gyro_buffer.c
+++ b/drivers/iio/gyro/st_gyro_buffer.c
@@ -33,13 +33,9 @@ static int st_gyro_buffer_postenable(struct iio_dev *indio_dev)
 {
 	int err;
 
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err < 0)
-		return err;
-
 	err = st_sensors_set_axis_enable(indio_dev, indio_dev->active_scan_mask[0]);
 	if (err < 0)
-		goto st_gyro_buffer_predisable;
+		return err;
 
 	err = st_sensors_set_enable(indio_dev, true);
 	if (err < 0)
@@ -49,27 +45,18 @@ static int st_gyro_buffer_postenable(struct iio_dev *indio_dev)
 
 st_gyro_buffer_enable_all_axis:
 	st_sensors_set_axis_enable(indio_dev, ST_SENSORS_ENABLE_ALL_AXIS);
-st_gyro_buffer_predisable:
-	iio_triggered_buffer_predisable(indio_dev);
 	return err;
 }
 
 static int st_gyro_buffer_predisable(struct iio_dev *indio_dev)
 {
-	int err, err2;
+	int err;
 
 	err = st_sensors_set_enable(indio_dev, false);
 	if (err < 0)
-		goto st_gyro_buffer_predisable;
-
-	err = st_sensors_set_axis_enable(indio_dev, ST_SENSORS_ENABLE_ALL_AXIS);
-
-st_gyro_buffer_predisable:
-	err2 = iio_triggered_buffer_predisable(indio_dev);
-	if (!err)
-		err = err2;
+		return err;
 
-	return err;
+	return st_sensors_set_axis_enable(indio_dev, ST_SENSORS_ENABLE_ALL_AXIS);
 }
 
 static const struct iio_buffer_setup_ops st_gyro_buffer_setup_ops = {
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index 3331141734c8..413204cd9bbd 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -278,17 +278,11 @@ static int hdc100x_buffer_postenable(struct iio_dev *indio_dev)
 	struct hdc100x_data *data = iio_priv(indio_dev);
 	int ret;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	/* Buffer is enabled. First set ACQ Mode, then attach poll func */
 	mutex_lock(&data->lock);
 	ret = hdc100x_update_config(data, HDC100X_REG_CONFIG_ACQ_MODE,
 				    HDC100X_REG_CONFIG_ACQ_MODE);
 	mutex_unlock(&data->lock);
-	if (ret)
-		iio_triggered_buffer_predisable(indio_dev);
 
 	return ret;
 }
@@ -296,16 +290,12 @@ static int hdc100x_buffer_postenable(struct iio_dev *indio_dev)
 static int hdc100x_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct hdc100x_data *data = iio_priv(indio_dev);
-	int ret, ret2;
+	int ret;
 
 	mutex_lock(&data->lock);
 	ret = hdc100x_update_config(data, HDC100X_REG_CONFIG_ACQ_MODE, 0);
 	mutex_unlock(&data->lock);
 
-	ret2 = iio_triggered_buffer_predisable(indio_dev);
-	if (ret == 0)
-		ret = ret2;
-
 	return ret;
 }
 
diff --git a/drivers/iio/humidity/hts221_buffer.c b/drivers/iio/humidity/hts221_buffer.c
index 21c6c160462d..f75f0b218fea 100644
--- a/drivers/iio/humidity/hts221_buffer.c
+++ b/drivers/iio/humidity/hts221_buffer.c
@@ -153,8 +153,6 @@ static int hts221_buffer_postdisable(struct iio_dev *iio_dev)
 
 static const struct iio_buffer_setup_ops hts221_buffer_ops = {
 	.preenable = hts221_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = hts221_buffer_postdisable,
 };
 
diff --git a/drivers/iio/iio_core_trigger.h b/drivers/iio/iio_core_trigger.h
index e59fe2f36bbb..9d1a92cc6480 100644
--- a/drivers/iio/iio_core_trigger.h
+++ b/drivers/iio/iio_core_trigger.h
@@ -18,6 +18,12 @@ void iio_device_register_trigger_consumer(struct iio_dev *indio_dev);
  **/
 void iio_device_unregister_trigger_consumer(struct iio_dev *indio_dev);
 
+
+int iio_trigger_attach_poll_func(struct iio_trigger *trig,
+				 struct iio_poll_func *pf);
+int iio_trigger_detach_poll_func(struct iio_trigger *trig,
+				 struct iio_poll_func *pf);
+
 #else
 
 /**
@@ -37,4 +43,15 @@ static void iio_device_unregister_trigger_consumer(struct iio_dev *indio_dev)
 {
 }
 
+static inline int iio_trigger_attach_poll_func(struct iio_trigger *trig,
+					       struct iio_poll_func *pf)
+{
+	return 0;
+}
+static inline int iio_trigger_detach_poll_func(struct iio_trigger *trig,
+					       struct iio_poll_func *pf)
+{
+	return 0;
+}
+
 #endif /* CONFIG_TRIGGER_CONSUMER */
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 9fa238c0a7d4..329dd4d6757a 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -20,6 +20,7 @@
 
 #include <linux/iio/iio.h>
 #include "iio_core.h"
+#include "iio_core_trigger.h"
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
 #include <linux/iio/buffer_impl.h>
@@ -972,6 +973,13 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 		}
 	}
 
+	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+		ret = iio_trigger_attach_poll_func(indio_dev->trig,
+						   indio_dev->pollfunc);
+		if (ret)
+			goto err_disable_buffers;
+	}
+
 	return 0;
 
 err_disable_buffers:
@@ -998,6 +1006,11 @@ static int iio_disable_buffers(struct iio_dev *indio_dev)
 	if (list_empty(&indio_dev->buffer_list))
 		return 0;
 
+	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+		iio_trigger_detach_poll_func(indio_dev->trig,
+					     indio_dev->pollfunc);
+	}
+
 	/*
 	 * If things go wrong at some step in disable we still need to continue
 	 * to perform the other steps, otherwise we leave the device in a
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index 53d1931f6be8..6f16357fd732 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -239,8 +239,8 @@ static void iio_trigger_put_irq(struct iio_trigger *trig, int irq)
  * the relevant function is in there may be the best option.
  */
 /* Worth protecting against double additions? */
-static int iio_trigger_attach_poll_func(struct iio_trigger *trig,
-					struct iio_poll_func *pf)
+int iio_trigger_attach_poll_func(struct iio_trigger *trig,
+				 struct iio_poll_func *pf)
 {
 	int ret = 0;
 	bool notinuse
@@ -290,8 +290,8 @@ out_put_module:
 	return ret;
 }
 
-static int iio_trigger_detach_poll_func(struct iio_trigger *trig,
-					 struct iio_poll_func *pf)
+int iio_trigger_detach_poll_func(struct iio_trigger *trig,
+				 struct iio_poll_func *pf)
 {
 	int ret = 0;
 	bool no_other_users
@@ -705,17 +705,3 @@ void iio_device_unregister_trigger_consumer(struct iio_dev *indio_dev)
 	if (indio_dev->trig)
 		iio_trigger_put(indio_dev->trig);
 }
-
-int iio_triggered_buffer_postenable(struct iio_dev *indio_dev)
-{
-	return iio_trigger_attach_poll_func(indio_dev->trig,
-					    indio_dev->pollfunc);
-}
-EXPORT_SYMBOL(iio_triggered_buffer_postenable);
-
-int iio_triggered_buffer_predisable(struct iio_dev *indio_dev)
-{
-	return iio_trigger_detach_poll_func(indio_dev->trig,
-					     indio_dev->pollfunc);
-}
-EXPORT_SYMBOL(iio_triggered_buffer_predisable);
diff --git a/drivers/iio/light/gp2ap020a00f.c b/drivers/iio/light/gp2ap020a00f.c
index dd9ad880deca..e2850c1a7353 100644
--- a/drivers/iio/light/gp2ap020a00f.c
+++ b/drivers/iio/light/gp2ap020a00f.c
@@ -1390,12 +1390,6 @@ static int gp2ap020a00f_buffer_postenable(struct iio_dev *indio_dev)
 
 	mutex_lock(&data->lock);
 
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err < 0) {
-		mutex_unlock(&data->lock);
-		return err;
-	}
-
 	/*
 	 * Enable triggers according to the scan_mask. Enabling either
 	 * LIGHT_CLEAR or LIGHT_IR scan mode results in enabling ALS
@@ -1430,8 +1424,6 @@ static int gp2ap020a00f_buffer_postenable(struct iio_dev *indio_dev)
 		err = -ENOMEM;
 
 error_unlock:
-	if (err < 0)
-		iio_triggered_buffer_predisable(indio_dev);
 	mutex_unlock(&data->lock);
 
 	return err;
@@ -1465,8 +1457,6 @@ static int gp2ap020a00f_buffer_predisable(struct iio_dev *indio_dev)
 	if (err == 0)
 		kfree(data->buffer);
 
-	iio_triggered_buffer_predisable(indio_dev);
-
 	mutex_unlock(&data->lock);
 
 	return err;
diff --git a/drivers/iio/light/isl29125.c b/drivers/iio/light/isl29125.c
index 663c72610655..b93b85dbc3a6 100644
--- a/drivers/iio/light/isl29125.c
+++ b/drivers/iio/light/isl29125.c
@@ -216,36 +216,20 @@ static const struct iio_info isl29125_info = {
 static int isl29125_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct isl29125_data *data = iio_priv(indio_dev);
-	int err;
-
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err)
-		return err;
 
 	data->conf1 |= ISL29125_MODE_RGB;
-	err = i2c_smbus_write_byte_data(data->client, ISL29125_CONF1,
+	return i2c_smbus_write_byte_data(data->client, ISL29125_CONF1,
 		data->conf1);
-	if (err) {
-		iio_triggered_buffer_predisable(indio_dev);
-		return err;
-	}
-
-	return 0;
 }
 
 static int isl29125_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct isl29125_data *data = iio_priv(indio_dev);
-	int ret;
 
 	data->conf1 &= ~ISL29125_MODE_MASK;
 	data->conf1 |= ISL29125_MODE_PD;
-	ret = i2c_smbus_write_byte_data(data->client, ISL29125_CONF1,
+	return i2c_smbus_write_byte_data(data->client, ISL29125_CONF1,
 		data->conf1);
-
-	iio_triggered_buffer_predisable(indio_dev);
-
-	return ret;
 }
 
 static const struct iio_buffer_setup_ops isl29125_buffer_setup_ops = {
diff --git a/drivers/iio/light/rpr0521.c b/drivers/iio/light/rpr0521.c
index c20fbc730d65..aa2972b04833 100644
--- a/drivers/iio/light/rpr0521.c
+++ b/drivers/iio/light/rpr0521.c
@@ -570,8 +570,6 @@ static int rpr0521_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops rpr0521_buffer_setup_ops = {
 	.preenable = rpr0521_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = rpr0521_buffer_postdisable,
 };
 
diff --git a/drivers/iio/light/si1145.c b/drivers/iio/light/si1145.c
index e1f989dd3a3d..521e8adb93a7 100644
--- a/drivers/iio/light/si1145.c
+++ b/drivers/iio/light/si1145.c
@@ -1171,8 +1171,6 @@ static bool si1145_validate_scan_mask(struct iio_dev *indio_dev,
 
 static const struct iio_buffer_setup_ops si1145_buffer_setup_ops = {
 	.preenable = si1145_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.validate_scan_mask = si1145_validate_scan_mask,
 };
 
diff --git a/drivers/iio/light/st_uvis25_core.c b/drivers/iio/light/st_uvis25_core.c
index 4d001d50e775..a18a82e6bbf5 100644
--- a/drivers/iio/light/st_uvis25_core.c
+++ b/drivers/iio/light/st_uvis25_core.c
@@ -227,8 +227,6 @@ static int st_uvis25_buffer_postdisable(struct iio_dev *iio_dev)
 
 static const struct iio_buffer_setup_ops st_uvis25_buffer_ops = {
 	.preenable = st_uvis25_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = st_uvis25_buffer_postdisable,
 };
 
diff --git a/drivers/iio/light/tcs3414.c b/drivers/iio/light/tcs3414.c
index bd6d3e4a0c4d..6fe5d46f80d4 100644
--- a/drivers/iio/light/tcs3414.c
+++ b/drivers/iio/light/tcs3414.c
@@ -243,35 +243,19 @@ static const struct iio_info tcs3414_info = {
 static int tcs3414_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct tcs3414_data *data = iio_priv(indio_dev);
-	int ret;
-
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
 
 	data->control |= TCS3414_CONTROL_ADC_EN;
-	ret = i2c_smbus_write_byte_data(data->client, TCS3414_CONTROL,
+	return i2c_smbus_write_byte_data(data->client, TCS3414_CONTROL,
 		data->control);
-	if (ret)
-		iio_triggered_buffer_predisable(indio_dev);
-
-	return ret;
 }
 
 static int tcs3414_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct tcs3414_data *data = iio_priv(indio_dev);
-	int ret, ret2;
 
 	data->control &= ~TCS3414_CONTROL_ADC_EN;
-	ret = i2c_smbus_write_byte_data(data->client, TCS3414_CONTROL,
+	return i2c_smbus_write_byte_data(data->client, TCS3414_CONTROL,
 		data->control);
-
-	ret2 = iio_triggered_buffer_predisable(indio_dev);
-	if (!ret)
-		ret = ret2;
-
-	return ret;
 }
 
 static const struct iio_buffer_setup_ops tcs3414_buffer_setup_ops = {
diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index ac1ab715d4dd..fff4b36b8b58 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -957,50 +957,29 @@ static int vcnl4010_buffer_postenable(struct iio_dev *indio_dev)
 	int ret;
 	int cmd;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	/* Do not enable the buffer if we are already capturing events. */
-	if (vcnl4010_is_in_periodic_mode(data)) {
-		ret = -EBUSY;
-		goto end;
-	}
+	if (vcnl4010_is_in_periodic_mode(data))
+		return -EBUSY;
 
 	ret = i2c_smbus_write_byte_data(data->client, VCNL4010_INT_CTRL,
 					VCNL4010_INT_PROX_EN);
 	if (ret < 0)
-		goto end;
+		return ret;
 
 	cmd = VCNL4000_SELF_TIMED_EN | VCNL4000_PROX_EN;
-	ret = i2c_smbus_write_byte_data(data->client, VCNL4000_COMMAND, cmd);
-	if (ret < 0)
-		goto end;
-
-	return 0;
-end:
-	iio_triggered_buffer_predisable(indio_dev);
-
-	return ret;
+	return i2c_smbus_write_byte_data(data->client, VCNL4000_COMMAND, cmd);
 }
 
 static int vcnl4010_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct vcnl4000_data *data = iio_priv(indio_dev);
-	int ret, ret_disable;
+	int ret;
 
 	ret = i2c_smbus_write_byte_data(data->client, VCNL4010_INT_CTRL, 0);
 	if (ret < 0)
-		goto end;
-
-	ret = i2c_smbus_write_byte_data(data->client, VCNL4000_COMMAND, 0);
-
-end:
-	ret_disable = iio_triggered_buffer_predisable(indio_dev);
-	if (ret == 0)
-		ret = ret_disable;
+		return ret;
 
-	return ret;
+	return i2c_smbus_write_byte_data(data->client, VCNL4000_COMMAND, 0);
 }
 
 static const struct iio_buffer_setup_ops vcnl4010_buffer_ops = {
diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c
index 8fc52057837d..fc6840f9c1fa 100644
--- a/drivers/iio/magnetometer/bmc150_magn.c
+++ b/drivers/iio/magnetometer/bmc150_magn.c
@@ -836,8 +836,6 @@ static int bmc150_magn_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops bmc150_magn_buffer_setup_ops = {
 	.preenable = bmc150_magn_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = bmc150_magn_buffer_postdisable,
 };
 
diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c
index a3e754943456..7242897a05e9 100644
--- a/drivers/iio/magnetometer/rm3100-core.c
+++ b/drivers/iio/magnetometer/rm3100-core.c
@@ -463,8 +463,6 @@ static int rm3100_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops rm3100_buffer_ops = {
 	.preenable = rm3100_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = rm3100_buffer_postdisable,
 };
 
diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c
index bb425c167a96..4917721fa2e5 100644
--- a/drivers/iio/magnetometer/st_magn_buffer.c
+++ b/drivers/iio/magnetometer/st_magn_buffer.c
@@ -31,34 +31,12 @@ int st_magn_trig_set_state(struct iio_trigger *trig, bool state)
 
 static int st_magn_buffer_postenable(struct iio_dev *indio_dev)
 {
-	int err;
-
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err < 0)
-		return err;
-
-	err = st_sensors_set_enable(indio_dev, true);
-	if (err < 0)
-		goto st_magn_buffer_predisable;
-
-	return 0;
-
-st_magn_buffer_predisable:
-	iio_triggered_buffer_predisable(indio_dev);
-	return err;
+	return st_sensors_set_enable(indio_dev, true);
 }
 
 static int st_magn_buffer_predisable(struct iio_dev *indio_dev)
 {
-	int err, err2;
-
-	err = st_sensors_set_enable(indio_dev, false);
-
-	err2 = iio_triggered_buffer_predisable(indio_dev);
-	if (!err)
-		err = err2;
-
-	return err;
+	return st_sensors_set_enable(indio_dev, false);
 }
 
 static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = {
diff --git a/drivers/iio/potentiostat/lmp91000.c b/drivers/iio/potentiostat/lmp91000.c
index 2d601889c8c0..67ae635a05f3 100644
--- a/drivers/iio/potentiostat/lmp91000.c
+++ b/drivers/iio/potentiostat/lmp91000.c
@@ -278,17 +278,8 @@ static const struct iio_trigger_ops lmp91000_trigger_ops = {
 static int lmp91000_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct lmp91000_data *data = iio_priv(indio_dev);
-	int err;
 
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err)
-		return err;
-
-	err = iio_channel_start_all_cb(data->cb_buffer);
-	if (err)
-		iio_triggered_buffer_predisable(indio_dev);
-
-	return err;
+	return iio_channel_start_all_cb(data->cb_buffer);
 }
 
 static int lmp91000_buffer_predisable(struct iio_dev *indio_dev)
@@ -297,7 +288,7 @@ static int lmp91000_buffer_predisable(struct iio_dev *indio_dev)
 
 	iio_channel_stop_all_cb(data->cb_buffer);
 
-	return iio_triggered_buffer_predisable(indio_dev);
+	return 0;
 }
 
 static const struct iio_buffer_setup_ops lmp91000_buffer_setup_ops = {
diff --git a/drivers/iio/pressure/st_pressure_buffer.c b/drivers/iio/pressure/st_pressure_buffer.c
index 418dbf9e6e1e..7cf6f06797e1 100644
--- a/drivers/iio/pressure/st_pressure_buffer.c
+++ b/drivers/iio/pressure/st_pressure_buffer.c
@@ -31,34 +31,12 @@ int st_press_trig_set_state(struct iio_trigger *trig, bool state)
 
 static int st_press_buffer_postenable(struct iio_dev *indio_dev)
 {
-	int err;
-
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err < 0)
-		return err;
-
-	err = st_sensors_set_enable(indio_dev, true);
-	if (err < 0)
-		goto st_press_buffer_predisable;
-
-	return 0;
-
-st_press_buffer_predisable:
-	iio_triggered_buffer_predisable(indio_dev);
-	return err;
+	return st_sensors_set_enable(indio_dev, true);
 }
 
 static int st_press_buffer_predisable(struct iio_dev *indio_dev)
 {
-	int err, err2;
-
-	err = st_sensors_set_enable(indio_dev, false);
-
-	err2 = iio_triggered_buffer_predisable(indio_dev);
-	if (!err)
-		err = err2;
-
-	return err;
+	return st_sensors_set_enable(indio_dev, false);
 }
 
 static const struct iio_buffer_setup_ops st_press_buffer_setup_ops = {
diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c
index ef818f2aebd6..2b8796ef91ef 100644
--- a/drivers/iio/pressure/zpa2326.c
+++ b/drivers/iio/pressure/zpa2326.c
@@ -1242,19 +1242,17 @@ static int zpa2326_postenable_buffer(struct iio_dev *indio_dev)
 	const struct zpa2326_private *priv = iio_priv(indio_dev);
 	int                           err;
 
-	/* Plug our own trigger event handler. */
-	err = iio_triggered_buffer_postenable(indio_dev);
-	if (err)
-		goto err;
-
 	if (!priv->waken) {
 		/*
 		 * We were already power supplied. Just clear hardware FIFO to
 		 * get rid of samples acquired during previous rounds (if any).
 		 */
 		err = zpa2326_clear_fifo(indio_dev, 0);
-		if (err)
-			goto err_buffer_predisable;
+		if (err) {
+			zpa2326_err(indio_dev,
+				    "failed to enable buffering (%d)", err);
+			return err;
+		}
 	}
 
 	if (!iio_trigger_using_own(indio_dev) && priv->waken) {
@@ -1263,18 +1261,14 @@ static int zpa2326_postenable_buffer(struct iio_dev *indio_dev)
 		 * powered up: reconfigure one-shot mode.
 		 */
 		err = zpa2326_config_oneshot(indio_dev, priv->irq);
-		if (err)
-			goto err_buffer_predisable;
+		if (err) {
+			zpa2326_err(indio_dev,
+				    "failed to enable buffering (%d)", err);
+			return err;
+		}
 	}
 
 	return 0;
-
-err_buffer_predisable:
-	iio_triggered_buffer_predisable(indio_dev);
-err:
-	zpa2326_err(indio_dev, "failed to enable buffering (%d)", err);
-
-	return err;
 }
 
 static int zpa2326_postdisable_buffer(struct iio_dev *indio_dev)
@@ -1287,7 +1281,6 @@ static int zpa2326_postdisable_buffer(struct iio_dev *indio_dev)
 static const struct iio_buffer_setup_ops zpa2326_buffer_setup_ops = {
 	.preenable   = zpa2326_preenable_buffer,
 	.postenable  = zpa2326_postenable_buffer,
-	.predisable  = iio_triggered_buffer_predisable,
 	.postdisable = zpa2326_postdisable_buffer
 };
 
diff --git a/drivers/iio/proximity/sx9310.c b/drivers/iio/proximity/sx9310.c
index 08c6100e2c94..dc2e11b43431 100644
--- a/drivers/iio/proximity/sx9310.c
+++ b/drivers/iio/proximity/sx9310.c
@@ -736,8 +736,6 @@ static int sx9310_buffer_postdisable(struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops sx9310_buffer_setup_ops = {
 	.preenable = sx9310_buffer_preenable,
-	.postenable = iio_triggered_buffer_postenable,
-	.predisable = iio_triggered_buffer_predisable,
 	.postdisable = sx9310_buffer_postdisable,
 };
 
diff --git a/drivers/iio/proximity/sx9500.c b/drivers/iio/proximity/sx9500.c
index f6eec54faef4..acb821cbad46 100644
--- a/drivers/iio/proximity/sx9500.c
+++ b/drivers/iio/proximity/sx9500.c
@@ -680,10 +680,6 @@ static int sx9500_buffer_postenable(struct iio_dev *indio_dev)
 	struct sx9500_data *data = iio_priv(indio_dev);
 	int ret = 0, i;
 
-	ret = iio_triggered_buffer_postenable(indio_dev);
-	if (ret)
-		return ret;
-
 	mutex_lock(&data->mutex);
 
 	for (i = 0; i < SX9500_NUM_CHANNELS; i++)
@@ -700,9 +696,6 @@ static int sx9500_buffer_postenable(struct iio_dev *indio_dev)
 
 	mutex_unlock(&data->mutex);
 
-	if (ret)
-		iio_triggered_buffer_predisable(indio_dev);
-
 	return ret;
 }
 
@@ -727,8 +720,6 @@ static int sx9500_buffer_predisable(struct iio_dev *indio_dev)
 
 	mutex_unlock(&data->mutex);
 
-	iio_triggered_buffer_predisable(indio_dev);
-
 	return ret;
 }
 
diff --git a/include/linux/iio/trigger_consumer.h b/include/linux/iio/trigger_consumer.h
index c3c6ba5ec423..3aa2f132dd67 100644
--- a/include/linux/iio/trigger_consumer.h
+++ b/include/linux/iio/trigger_consumer.h
@@ -50,11 +50,4 @@ irqreturn_t iio_pollfunc_store_time(int irq, void *p);
 
 void iio_trigger_notify_done(struct iio_trigger *trig);
 
-/*
- * Two functions for common case where all that happens is a pollfunc
- * is attached and detached from a trigger
- */
-int iio_triggered_buffer_postenable(struct iio_dev *indio_dev);
-int iio_triggered_buffer_predisable(struct iio_dev *indio_dev);
-
 #endif
-- 
cgit v1.2.3


From b3337eb24831db058231ea87838f316d9eb86253 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 15 Jun 2020 18:05:41 +0300
Subject: gpiolib: Introduce for_each_requested_gpio_in_range() macro

Introduce for_each_requested_gpio_in_range() macro which helps
to iterate over requested GPIO in a range. There are already
potential users of it, which are going to be converted
by the following patches.

For most of them for_each_requested_gpio() shortcut has been added.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200615150545.87964-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/driver.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c4f272af7af5..11cdcb195635 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -474,6 +474,22 @@ struct gpio_chip {
 extern const char *gpiochip_is_requested(struct gpio_chip *gc,
 			unsigned int offset);
 
+/**
+ * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range
+ * @chip:	the chip to query
+ * @i:		loop variable
+ * @base:	first GPIO in the range
+ * @size:	amount of GPIOs to check starting from @base
+ * @label:	label of current GPIO
+ */
+#define for_each_requested_gpio_in_range(chip, i, base, size, label)			\
+	for (i = 0; i < size; i++)							\
+		if ((label = gpiochip_is_requested(chip, base + i)) == NULL) {} else
+
+/* Iterates over all requested GPIO of the given @chip */
+#define for_each_requested_gpio(chip, i, label)						\
+	for_each_requested_gpio_in_range(chip, i, 0, chip->ngpio, label)
+
 /* add/remove chips */
 extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 				      struct lock_class_key *lock_key,
-- 
cgit v1.2.3


From 5a473e8311b582a40c10409a0f4bb39f42aa8123 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 4 Jun 2020 11:23:39 -0600
Subject: block: provide plug based way of signaling forced no-wait semantics

Provide a way for the caller to specify that IO should be marked
with REQ_NOWAIT to avoid blocking on allocation.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 6 ++++++
 include/linux/blkdev.h | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 03252af8c82c..62a4904db921 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -958,6 +958,7 @@ generic_make_request_checks(struct bio *bio)
 	struct request_queue *q;
 	int nr_sectors = bio_sectors(bio);
 	blk_status_t status = BLK_STS_IOERR;
+	struct blk_plug *plug;
 	char b[BDEVNAME_SIZE];
 
 	might_sleep();
@@ -971,6 +972,10 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
+	plug = blk_mq_plug(q, bio);
+	if (plug && plug->nowait)
+		bio->bi_opf |= REQ_NOWAIT;
+
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
 	 * if queue is not a request based queue.
@@ -1800,6 +1805,7 @@ void blk_start_plug(struct blk_plug *plug)
 	INIT_LIST_HEAD(&plug->cb_list);
 	plug->rq_count = 0;
 	plug->multiple_queues = false;
+	plug->nowait = false;
 
 	/*
 	 * Store ordering should not be needed here, since a potential
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8fd900998b4e..6e067dca94cf 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1189,6 +1189,7 @@ struct blk_plug {
 	struct list_head cb_list; /* md requires an unplug callback */
 	unsigned short rq_count;
 	bool multiple_queues;
+	bool nowait;
 };
 #define BLK_MAX_REQUEST_COUNT 16
 #define BLK_PLUG_FLUSH_SIZE (128 * 1024)
-- 
cgit v1.2.3


From c7510ab2cf5ccd997fe7f194edfe09cc511abf99 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 23 May 2020 08:22:14 -0600
Subject: mm: abstract out wake_page_match() from wake_page_function()

No functional changes in this patch, just in preparation for allowing
more callers.

Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/pagemap.h | 37 +++++++++++++++++++++++++++++++++++++
 mm/filemap.c            | 35 ++++-------------------------------
 2 files changed, 41 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index cf2468da68e9..2f18221bb5c8 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -496,6 +496,43 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 	return pgoff;
 }
 
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
+struct wait_page_key {
+	struct page *page;
+	int bit_nr;
+	int page_match;
+};
+
+struct wait_page_queue {
+	struct page *page;
+	int bit_nr;
+	wait_queue_entry_t wait;
+};
+
+static inline int wake_page_match(struct wait_page_queue *wait_page,
+				  struct wait_page_key *key)
+{
+	if (wait_page->page != key->page)
+	       return 0;
+	key->page_match = 1;
+
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+
+	/*
+	 * Stop walking if it's locked.
+	 * Is this safe if put_and_wait_on_page_locked() is in use?
+	 * Yes: the waker must hold a reference to this page, and if PG_locked
+	 * has now already been set by another task, that task must also hold
+	 * a reference to the *same usage* of this page; so there is no need
+	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
+	 */
+	if (test_bit(key->bit_nr, &key->page->flags))
+		return -1;
+
+	return 1;
+}
+
 extern void __lock_page(struct page *page);
 extern int __lock_page_killable(struct page *page);
 extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
diff --git a/mm/filemap.c b/mm/filemap.c
index 3378d4fca883..c3175dbd8fba 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -987,43 +987,16 @@ void __init pagecache_init(void)
 	page_writeback_init();
 }
 
-/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
-struct wait_page_key {
-	struct page *page;
-	int bit_nr;
-	int page_match;
-};
-
-struct wait_page_queue {
-	struct page *page;
-	int bit_nr;
-	wait_queue_entry_t wait;
-};
-
 static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
+	int ret;
 
-	if (wait_page->page != key->page)
-	       return 0;
-	key->page_match = 1;
-
-	if (wait_page->bit_nr != key->bit_nr)
-		return 0;
-
-	/*
-	 * Stop walking if it's locked.
-	 * Is this safe if put_and_wait_on_page_locked() is in use?
-	 * Yes: the waker must hold a reference to this page, and if PG_locked
-	 * has now already been set by another task, that task must also hold
-	 * a reference to the *same usage* of this page; so there is no need
-	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
-	 */
-	if (test_bit(key->bit_nr, &key->page->flags))
-		return -1;
-
+	ret = wake_page_match(wait_page, key);
+	if (ret != 1)
+		return ret;
 	return autoremove_wake_function(wait, mode, sync, key);
 }
 
-- 
cgit v1.2.3


From dd3e6d5039de1cbff4e20e2b34390ff44cdb182f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 22 May 2020 09:12:09 -0600
Subject: mm: add support for async page locking

Normally waiting for a page to become unlocked, or locking the page,
requires waiting for IO to complete. Add support for lock_page_async()
and wait_on_page_locked_async(), which are callback based instead. This
allows a caller to get notified when a page becomes unlocked, rather
than wait for it.

We add a new iocb field, ki_waitq, to pass in the necessary data for this
to happen. We can unionize this with ki_cookie, since that is only used
for polled IO. Polled IO can never co-exist with async callbacks, as it is
(by definition) polled completions. struct wait_page_key is made public,
and we define struct wait_page_async as the interface between the caller
and the core.

Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h      |  7 ++++++-
 include/linux/pagemap.h | 17 +++++++++++++++++
 mm/filemap.c            | 45 ++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..2a5cf6080e68 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -315,6 +315,8 @@ enum rw_hint {
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
 #define IOCB_NOWAIT		(1 << 7)
+/* iocb->ki_waitq is valid */
+#define IOCB_WAITQ		(1 << 8)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -328,7 +330,10 @@ struct kiocb {
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	unsigned int		ki_cookie; /* for ->iopoll */
+	union {
+		unsigned int		ki_cookie; /* for ->iopoll */
+		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	};
 
 	randomized_struct_fields_end
 };
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2f18221bb5c8..e053e1d9a4d7 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -535,6 +535,7 @@ static inline int wake_page_match(struct wait_page_queue *wait_page,
 
 extern void __lock_page(struct page *page);
 extern int __lock_page_killable(struct page *page);
+extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
 extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
@@ -571,6 +572,22 @@ static inline int lock_page_killable(struct page *page)
 	return 0;
 }
 
+/*
+ * lock_page_async - Lock the page, unless this would block. If the page
+ * is already locked, then queue a callback when the page becomes unlocked.
+ * This callback can then retry the operation.
+ *
+ * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page
+ * was already locked and the callback defined in 'wait' was queued.
+ */
+static inline int lock_page_async(struct page *page,
+				  struct wait_page_queue *wait)
+{
+	if (!trylock_page(page))
+		return __lock_page_async(page, wait);
+	return 0;
+}
+
 /*
  * lock_page_or_retry - Lock the page, unless this would block and the
  * caller indicated that it can handle a retry.
diff --git a/mm/filemap.c b/mm/filemap.c
index c3175dbd8fba..e8aaf43bee9f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1180,6 +1180,36 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 }
 EXPORT_SYMBOL(wait_on_page_bit_killable);
 
+static int __wait_on_page_locked_async(struct page *page,
+				       struct wait_page_queue *wait, bool set)
+{
+	struct wait_queue_head *q = page_waitqueue(page);
+	int ret = 0;
+
+	wait->page = page;
+	wait->bit_nr = PG_locked;
+
+	spin_lock_irq(&q->lock);
+	__add_wait_queue_entry_tail(q, &wait->wait);
+	SetPageWaiters(page);
+	if (set)
+		ret = !trylock_page(page);
+	else
+		ret = PageLocked(page);
+	/*
+	 * If we were succesful now, we know we're still on the
+	 * waitqueue as we're still under the lock. This means it's
+	 * safe to remove and return success, we know the callback
+	 * isn't going to trigger.
+	 */
+	if (!ret)
+		__remove_wait_queue(q, &wait->wait);
+	else
+		ret = -EIOCBQUEUED;
+	spin_unlock_irq(&q->lock);
+	return ret;
+}
+
 /**
  * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
  * @page: The page to wait for.
@@ -1342,6 +1372,11 @@ int __lock_page_killable(struct page *__page)
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
+int __lock_page_async(struct page *page, struct wait_page_queue *wait)
+{
+	return __wait_on_page_locked_async(page, wait, true);
+}
+
 /*
  * Return values:
  * 1 - page is locked; mmap_lock is still held.
@@ -2131,6 +2166,11 @@ page_not_up_to_date_locked:
 		}
 
 readpage:
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			unlock_page(page);
+			put_page(page);
+			goto would_block;
+		}
 		/*
 		 * A previous I/O error may have been due to temporary
 		 * failures, eg. multipath errors.
@@ -2150,7 +2190,10 @@ readpage:
 		}
 
 		if (!PageUptodate(page)) {
-			error = lock_page_killable(page);
+			if (iocb->ki_flags & IOCB_WAITQ)
+				error = lock_page_async(page, iocb->ki_waitq);
+			else
+				error = lock_page_killable(page);
 			if (unlikely(error))
 				goto readpage_error;
 			if (!PageUptodate(page)) {
-- 
cgit v1.2.3


From c2a25ec0f1005dde004cd671484f578a9c8ca7de Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 22 May 2020 09:12:51 -0600
Subject: fs: add FMODE_BUF_RASYNC

If set, this indicates that the file system supports IOCB_WAITQ for
buffered reads.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2a5cf6080e68..4090320360f4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -175,6 +175,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File does not contribute to nr_files count */
 #define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
+/* File supports async buffered reads */
+#define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
-- 
cgit v1.2.3


From d1932dc3dc268f8dd5201c64971324d06ba977cc Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 22 May 2020 10:18:23 -0600
Subject: mm: add kiocb_wait_page_queue_init() helper

Checks if the file supports it, and initializes the values that we need.
Caller passes in 'data' pointer, if any, and the callback function to
be used.

Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/pagemap.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e053e1d9a4d7..7386bc67cc5a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -533,6 +533,27 @@ static inline int wake_page_match(struct wait_page_queue *wait_page,
 	return 1;
 }
 
+static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb,
+					     struct wait_page_queue *wait,
+					     wait_queue_func_t func,
+					     void *data)
+{
+	/* Can't support async wakeup with polled IO */
+	if (kiocb->ki_flags & IOCB_HIPRI)
+		return -EINVAL;
+	if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) {
+		wait->wait.func = func;
+		wait->wait.private = data;
+		wait->wait.flags = 0;
+		INIT_LIST_HEAD(&wait->wait.entry);
+		kiocb->ki_flags |= IOCB_WAITQ;
+		kiocb->ki_waitq = wait;
+		return 0;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 extern void __lock_page(struct page *page);
 extern int __lock_page_killable(struct page *page);
 extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
-- 
cgit v1.2.3


From 613c2e2c7e69e574411e2a3609459e18e91ae3fb Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Sun, 21 Jun 2020 22:18:26 +0800
Subject: soc: mediatek: cmdq: add assign function

Add assign function in cmdq helper which assign constant value into
internal register by index.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1592749115-24158-3-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 24 +++++++++++++++++++++++-
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 14 ++++++++++++++
 3 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 87ee9f767b7a..b9e5e4eea876 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -12,6 +12,7 @@
 #define CMDQ_WRITE_ENABLE_MASK	BIT(0)
 #define CMDQ_POLL_ENABLE_MASK	BIT(0)
 #define CMDQ_EOC_IRQ_EN		BIT(0)
+#define CMDQ_REG_TYPE		1
 
 struct cmdq_instruction {
 	union {
@@ -21,8 +22,17 @@ struct cmdq_instruction {
 	union {
 		u16 offset;
 		u16 event;
+		u16 reg_dst;
+	};
+	union {
+		u8 subsys;
+		struct {
+			u8 sop:5;
+			u8 arg_c_t:1;
+			u8 src_t:1;
+			u8 dst_t:1;
+		};
 	};
-	u8 subsys;
 	u8 op;
 };
 
@@ -278,6 +288,18 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
 }
 EXPORT_SYMBOL(cmdq_pkt_poll_mask);
 
+int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_LOGIC;
+	inst.dst_t = CMDQ_REG_TYPE;
+	inst.reg_dst = reg_idx;
+	inst.value = value;
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_assign);
+
 static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index a4dc45fbec0a..70b740a552c2 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -59,6 +59,7 @@ enum cmdq_code {
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
+	CMDQ_CODE_LOGIC = 0xa0,
 };
 
 enum cmdq_cb_status {
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index a74c1d5acdf3..83340211e1d3 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -152,6 +152,20 @@ int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
  */
 int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
 		       u16 offset, u32 value, u32 mask);
+
+/**
+ * cmdq_pkt_assign() - Append logic assign command to the CMDQ packet, ask GCE
+ *		       to execute an instruction that set a constant value into
+ *		       internal register and use as value, mask or address in
+ *		       read/write instruction.
+ * @pkt:	the CMDQ packet
+ * @reg_idx:	the CMDQ internal register ID
+ * @value:	the specified value
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value);
+
 /**
  * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ
  *                          packet and call back at the end of done packet
-- 
cgit v1.2.3


From 995818588b6deedbed6b2b9d4c67e59b9afd6c60 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Sun, 21 Jun 2020 22:18:32 +0800
Subject: soc: mediatek: cmdq: export finalize function

Export finalize function to client which helps append eoc and jump
command to pkt. Let client decide call finalize or not.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Acked-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Link: https://lore.kernel.org/r/1592749115-24158-9-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 1 +
 drivers/soc/mediatek/mtk-cmdq-helper.c  | 7 ++-----
 include/linux/soc/mediatek/mtk-cmdq.h   | 8 ++++++++
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index fe46c4bac64d..ec6c9ffbf35e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -492,6 +492,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
 		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
+		cmdq_pkt_finalize(cmdq_handle);
 		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
 	}
 #endif
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index b9e5e4eea876..2eda03fc7662 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -300,7 +300,7 @@ int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value)
 }
 EXPORT_SYMBOL(cmdq_pkt_assign);
 
-static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
+int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
 	struct cmdq_instruction inst = { {0} };
 	int err;
@@ -319,6 +319,7 @@ static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 
 	return err;
 }
+EXPORT_SYMBOL(cmdq_pkt_finalize);
 
 static void cmdq_pkt_flush_async_cb(struct cmdq_cb_data data)
 {
@@ -353,10 +354,6 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
 	unsigned long flags = 0;
 	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
 
-	err = cmdq_pkt_finalize(pkt);
-	if (err < 0)
-		return err;
-
 	pkt->cb.cb = cb;
 	pkt->cb.data = data;
 	pkt->async_cb.cb = cmdq_pkt_flush_async_cb;
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 83340211e1d3..c331255eacd1 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -166,6 +166,14 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
  */
 int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value);
 
+/**
+ * cmdq_pkt_finalize() - Append EOC and jump command to pkt.
+ * @pkt:	the CMDQ packet
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_finalize(struct cmdq_pkt *pkt);
+
 /**
  * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ
  *                          packet and call back at the end of done packet
-- 
cgit v1.2.3


From 7de796cac48c0f55974cfe9cff683dfb3b7c71b6 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Sun, 21 Jun 2020 22:18:35 +0800
Subject: soc: mediatek: cmdq: add set event function

Add set event function in cmdq helper functions to set specific event.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1592749115-24158-12-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 15 +++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    |  9 +++++++++
 3 files changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 2eda03fc7662..dc644cfb6419 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -253,6 +253,21 @@ int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event)
 }
 EXPORT_SYMBOL(cmdq_pkt_clear_event);
 
+int cmdq_pkt_set_event(struct cmdq_pkt *pkt, u16 event)
+{
+	struct cmdq_instruction inst = {};
+
+	if (event >= CMDQ_MAX_EVENT)
+		return -EINVAL;
+
+	inst.op = CMDQ_CODE_WFE;
+	inst.value = CMDQ_WFE_UPDATE | CMDQ_WFE_UPDATE_VALUE;
+	inst.event = event;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_set_event);
+
 int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
 		  u16 offset, u32 value)
 {
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 70b740a552c2..a96e8c252bac 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -17,6 +17,7 @@
 #define CMDQ_JUMP_PASS			CMDQ_INST_SIZE
 
 #define CMDQ_WFE_UPDATE			BIT(31)
+#define CMDQ_WFE_UPDATE_VALUE		BIT(16)
 #define CMDQ_WFE_WAIT			BIT(15)
 #define CMDQ_WFE_WAIT_VALUE		0x1
 
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index c331255eacd1..2249ecaf77e4 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -120,6 +120,15 @@ int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event);
  */
 int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event);
 
+/**
+ * cmdq_pkt_set_event() - append set event command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @event:	the desired event to be set
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_set_event(struct cmdq_pkt *pkt, u16 event);
+
 /**
  * cmdq_pkt_poll() - Append polling command to the CMDQ packet, ask GCE to
  *		     execute an instruction that wait for a specified
-- 
cgit v1.2.3


From 3af8588c77186bf08e55e7281da83d88373481d7 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Mon, 8 Jun 2020 17:28:50 +0200
Subject: fork: fold legacy_clone_args_valid() into _do_fork()

This separate helper only existed to guarantee the mutual exclusivity of
CLONE_PIDFD and CLONE_PARENT_SETTID for legacy clone since CLONE_PIDFD
abuses the parent_tid field to return the pidfd. But we can actually handle
this uniformely thus removing the helper. For legacy clone we can detect
that CLONE_PIDFD is specified in conjunction with CLONE_PARENT_SETTID
because they will share the same memory which is invalid and for clone3()
setting the separate pidfd and parent_tid fields to the same memory is
bogus as well. So fold that helper directly into _do_fork() by detecting
this case.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: linux-m68k@lists.linux-m68k.org
Cc: x86@kernel.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 arch/m68k/kernel/process.c |  3 ---
 arch/x86/kernel/sys_ia32.c |  3 ---
 include/linux/sched/task.h |  1 -
 kernel/fork.c              | 30 ++++++++++++++----------------
 4 files changed, 14 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 90ae376b7ab1..0608439ba452 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -125,9 +125,6 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
 		.tls		= regs->d5,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 
diff --git a/arch/x86/kernel/sys_ia32.c b/arch/x86/kernel/sys_ia32.c
index f8d65c99feb8..720cde885042 100644
--- a/arch/x86/kernel/sys_ia32.c
+++ b/arch/x86/kernel/sys_ia32.c
@@ -251,9 +251,6 @@ COMPAT_SYSCALL_DEFINE5(ia32_clone, unsigned long, clone_flags,
 		.tls		= tls_val,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 #endif /* CONFIG_IA32_EMULATION */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 38359071236a..ddce0ea515d1 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -96,7 +96,6 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern long _do_fork(struct kernel_clone_args *kargs);
-extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..9875aeb2ba41 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2422,6 +2422,20 @@ long _do_fork(struct kernel_clone_args *args)
 	int trace = 0;
 	long nr;
 
+	/*
+	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
+	 * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are
+	 * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate
+	 * field in struct clone_args and it still doesn't make sense to have
+	 * them both point at the same memory location. Performing this check
+	 * here has the advantage that we don't need to have a separate helper
+	 * to check for legacy clone().
+	 */
+	if ((args->flags & CLONE_PIDFD) &&
+	    (args->flags & CLONE_PARENT_SETTID) &&
+	    (args->pidfd == args->parent_tid))
+		return -EINVAL;
+
 	/*
 	 * Determine whether and which event to report to ptracer.  When
 	 * called from kernel_thread or CLONE_UNTRACED is explicitly
@@ -2479,16 +2493,6 @@ long _do_fork(struct kernel_clone_args *args)
 	return nr;
 }
 
-bool legacy_clone_args_valid(const struct kernel_clone_args *kargs)
-{
-	/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
-	if ((kargs->flags & CLONE_PIDFD) &&
-	    (kargs->flags & CLONE_PARENT_SETTID))
-		return false;
-
-	return true;
-}
-
 #ifndef CONFIG_HAVE_COPY_THREAD_TLS
 /* For compatibility with architectures that call do_fork directly rather than
  * using the syscall entry points below. */
@@ -2508,9 +2512,6 @@ long do_fork(unsigned long clone_flags,
 		.stack_size	= stack_size,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 #endif
@@ -2593,9 +2594,6 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 #endif
-- 
cgit v1.2.3


From 53f13319d13197dd1f4c8ce5fc1ef4c32509b4e2 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 9 Jun 2020 18:10:39 +0300
Subject: thunderbolt: Get rid of E2E workaround

The end-to-end (E2E) workaround is needed for Falcon Ridge (TBT 2)
controller when E2E is enabled for both ends of the host-to-host
connection. However, we never supported full E2E in the first place so
this code is not necessary at the moment. Further this allows us to use
all available rings for data except ring 0 which is reserved for the
control path.

The complete E2E flow control is explained in the USB4 spec so we may
add it back later if needed but at least the networking driver seems to
work fine without, and the higher level stack, like TCP will retransmit
lost packets anyway.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/net/thunderbolt.c   |  4 ++--
 drivers/thunderbolt/nhi.c   | 26 ++------------------------
 include/linux/thunderbolt.h |  2 --
 3 files changed, 4 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c
index dacb4f680fd4..a812726703a4 100644
--- a/drivers/net/thunderbolt.c
+++ b/drivers/net/thunderbolt.c
@@ -866,8 +866,8 @@ static int tbnet_open(struct net_device *dev)
 	eof_mask = BIT(TBIP_PDF_FRAME_END);
 
 	ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE,
-				RING_FLAG_FRAME | RING_FLAG_E2E, sof_mask,
-				eof_mask, tbnet_start_poll, net);
+				RING_FLAG_FRAME, sof_mask, eof_mask,
+				tbnet_start_poll, net);
 	if (!ring) {
 		netdev_err(dev, "failed to allocate Rx ring\n");
 		tb_ring_free(net->tx_ring.ring);
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index b617922b5b0a..5f7489fa1327 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -24,12 +24,7 @@
 
 #define RING_TYPE(ring) ((ring)->is_tx ? "TX ring" : "RX ring")
 
-/*
- * Used to enable end-to-end workaround for missing RX packets. Do not
- * use this ring for anything else.
- */
-#define RING_E2E_UNUSED_HOPID	2
-#define RING_FIRST_USABLE_HOPID	TB_PATH_MIN_HOPID
+#define RING_FIRST_USABLE_HOPID	1
 
 /*
  * Minimal number of vectors when we use MSI-X. Two for control channel
@@ -440,7 +435,7 @@ static int nhi_alloc_hop(struct tb_nhi *nhi, struct tb_ring *ring)
 
 		/*
 		 * Automatically allocate HopID from the non-reserved
-		 * range 8 .. hop_count - 1.
+		 * range 1 .. hop_count - 1.
 		 */
 		for (i = RING_FIRST_USABLE_HOPID; i < nhi->hop_count; i++) {
 			if (ring->is_tx) {
@@ -496,10 +491,6 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 	dev_dbg(&nhi->pdev->dev, "allocating %s ring %d of size %d\n",
 		transmit ? "TX" : "RX", hop, size);
 
-	/* Tx Ring 2 is reserved for E2E workaround */
-	if (transmit && hop == RING_E2E_UNUSED_HOPID)
-		return NULL;
-
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
 	if (!ring)
 		return NULL;
@@ -614,19 +605,6 @@ void tb_ring_start(struct tb_ring *ring)
 		flags = RING_FLAG_ENABLE | RING_FLAG_RAW;
 	}
 
-	if (ring->flags & RING_FLAG_E2E && !ring->is_tx) {
-		u32 hop;
-
-		/*
-		 * In order not to lose Rx packets we enable end-to-end
-		 * workaround which transfers Rx credits to an unused Tx
-		 * HopID.
-		 */
-		hop = RING_E2E_UNUSED_HOPID << REG_RX_OPTIONS_E2E_HOP_SHIFT;
-		hop &= REG_RX_OPTIONS_E2E_HOP_MASK;
-		flags |= hop | RING_FLAG_E2E_FLOW_CONTROL;
-	}
-
 	ring_iowrite64desc(ring, ring->descriptors_dma, 0);
 	if (ring->is_tx) {
 		ring_iowrite32desc(ring, ring->size, 12);
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index ff397c0d5c07..5db2b11ab085 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -504,8 +504,6 @@ struct tb_ring {
 #define RING_FLAG_NO_SUSPEND	BIT(0)
 /* Configure the ring to be in frame mode */
 #define RING_FLAG_FRAME		BIT(1)
-/* Enable end-to-end flow control */
-#define RING_FLAG_E2E		BIT(2)
 
 struct ring_frame;
 typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled);
-- 
cgit v1.2.3


From 4bc799dcb67066e0531004d5bdbe755bb02b5488 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 15 Jun 2020 11:12:32 -0700
Subject: security: fix the key_permission LSM hook function type

Commit 8c0637e950d6 ("keys: Make the KEY_NEED_* perms an enum rather than
a mask") changed the type of the key_permission callback functions, but
didn't change the type of the hook, which trips indirect call checking with
Control-Flow Integrity (CFI). This change fixes the issue by changing the
hook type to match the functions.

Fixes: 8c0637e950d6 ("keys: Make the KEY_NEED_* perms an enum rather than a mask")
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <jmorris@namei.org>
---
 include/linux/lsm_hook_defs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 6791813cd439..24f6683f1cfc 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -360,7 +360,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred,
 	 unsigned long flags)
 LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key)
 LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred,
-	 unsigned perm)
+	 enum key_need_perm need_perm)
 LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer)
 #endif /* CONFIG_KEYS */
 
-- 
cgit v1.2.3


From 41c48f3a98231738c5ce79f6f2aa6e40ba924d18 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 19 Jun 2020 14:11:43 -0700
Subject: bpf: Support access to bpf map fields

There are multiple use-cases when it's convenient to have access to bpf
map fields, both `struct bpf_map` and map type specific struct-s such as
`struct bpf_array`, `struct bpf_htab`, etc.

For example while working with sock arrays it can be necessary to
calculate the key based on map->max_entries (some_hash % max_entries).
Currently this is solved by communicating max_entries via "out-of-band"
channel, e.g. via additional map with known key to get info about target
map. That works, but is not very convenient and error-prone while
working with many maps.

In other cases necessary data is dynamic (i.e. unknown at loading time)
and it's impossible to get it at all. For example while working with a
hash table it can be convenient to know how much capacity is already
used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case).

At the same time kernel knows this info and can provide it to bpf
program.

Fill this gap by adding support to access bpf map fields from bpf
program for both `struct bpf_map` and map type specific fields.

Support is implemented via btf_struct_access() so that a user can define
their own `struct bpf_map` or map type specific struct in their program
with only necessary fields and preserve_access_index attribute, cast a
map to this struct and use a field.

For example:

	struct bpf_map {
		__u32 max_entries;
	} __attribute__((preserve_access_index));

	struct bpf_array {
		struct bpf_map map;
		__u32 elem_size;
	} __attribute__((preserve_access_index));

	struct {
		__uint(type, BPF_MAP_TYPE_ARRAY);
		__uint(max_entries, 4);
		__type(key, __u32);
		__type(value, __u32);
	} m_array SEC(".maps");

	SEC("cgroup_skb/egress")
	int cg_skb(void *ctx)
	{
		struct bpf_array *array = (struct bpf_array *)&m_array;
		struct bpf_map *map = (struct bpf_map *)&m_array;

		/* .. use map->max_entries or array->map.max_entries .. */
	}

Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock
in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of
corresponding struct. Only reading from map fields is supported.

For btf_struct_access() to work there should be a way to know btf id of
a struct that corresponds to a map type. To get btf id there should be a
way to get a stringified name of map-specific struct, such as
"bpf_array", "bpf_htab", etc for a map type. Two new fields are added to
`struct bpf_map_ops` to handle it:
* .map_btf_name keeps a btf name of a struct returned by map_alloc();
* .map_btf_id is used to cache btf id of that struct.

To make btf ids calculation cheaper they're calculated once while
preparing btf_vmlinux and cached same way as it's done for btf_id field
of `struct bpf_func_proto`

While calculating btf ids, struct names are NOT checked for collision.
Collisions will be checked as a part of the work to prepare btf ids used
in verifier in compile time that should land soon. The only known
collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs
net/core/sock_map.c) was fixed earlier.

Both new fields .map_btf_name and .map_btf_id must be set for a map type
for the feature to work. If neither is set for a map type, verifier will
return ENOTSUPP on a try to access map_ptr of corresponding type. If
just one of them set, it's verifier misconfiguration.

Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for
BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be
supported separately.

The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by
perfmon_capable() so that unpriv programs won't have access to bpf map
fields.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
---
 include/linux/bpf.h                                |  9 +++
 include/linux/bpf_verifier.h                       |  1 +
 kernel/bpf/arraymap.c                              |  3 +
 kernel/bpf/btf.c                                   | 40 +++++++++++
 kernel/bpf/hashtab.c                               |  3 +
 kernel/bpf/verifier.c                              | 82 +++++++++++++++++++---
 .../selftests/bpf/verifier/map_ptr_mixing.c        |  2 +-
 7 files changed, 131 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07052d44bca1..1e1501ee53ce 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -92,6 +92,10 @@ struct bpf_map_ops {
 	int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
 	__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
 			     struct poll_table_struct *pts);
+
+	/* BTF name and id of struct allocated by map_alloc */
+	const char * const map_btf_name;
+	int *map_btf_id;
 };
 
 struct bpf_map_memory {
@@ -1109,6 +1113,11 @@ static inline bool bpf_allow_ptr_leaks(void)
 	return perfmon_capable();
 }
 
+static inline bool bpf_allow_ptr_to_map_access(void)
+{
+	return perfmon_capable();
+}
+
 static inline bool bpf_bypass_spec_v1(void)
 {
 	return perfmon_capable();
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index ca08db4ffb5f..53c7bd568c5d 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -379,6 +379,7 @@ struct bpf_verifier_env {
 	u32 used_map_cnt;		/* number of used maps */
 	u32 id_gen;			/* used to generate unique reg IDs */
 	bool allow_ptr_leaks;
+	bool allow_ptr_to_map_access;
 	bool bpf_capable;
 	bool bypass_spec_v1;
 	bool bypass_spec_v4;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 11584618e861..e7caa48812fb 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -494,6 +494,7 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 				   vma->vm_pgoff + pgoff);
 }
 
+static int array_map_btf_id;
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -510,6 +511,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_check_btf = array_map_check_btf,
 	.map_lookup_batch = generic_map_lookup_batch,
 	.map_update_batch = generic_map_update_batch,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &array_map_btf_id,
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3eb804618a53..e377d1981730 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3571,6 +3571,41 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 	return ctx_type;
 }
 
+static const struct bpf_map_ops * const btf_vmlinux_map_ops[] = {
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
+#define BPF_LINK_TYPE(_id, _name)
+#define BPF_MAP_TYPE(_id, _ops) \
+	[_id] = &_ops,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_LINK_TYPE
+#undef BPF_MAP_TYPE
+};
+
+static int btf_vmlinux_map_ids_init(const struct btf *btf,
+				    struct bpf_verifier_log *log)
+{
+	const struct bpf_map_ops *ops;
+	int i, btf_id;
+
+	for (i = 0; i < ARRAY_SIZE(btf_vmlinux_map_ops); ++i) {
+		ops = btf_vmlinux_map_ops[i];
+		if (!ops || (!ops->map_btf_name && !ops->map_btf_id))
+			continue;
+		if (!ops->map_btf_name || !ops->map_btf_id) {
+			bpf_log(log, "map type %d is misconfigured\n", i);
+			return -EINVAL;
+		}
+		btf_id = btf_find_by_name_kind(btf, ops->map_btf_name,
+					       BTF_KIND_STRUCT);
+		if (btf_id < 0)
+			return btf_id;
+		*ops->map_btf_id = btf_id;
+	}
+
+	return 0;
+}
+
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     struct btf *btf,
 				     const struct btf_type *t,
@@ -3633,6 +3668,11 @@ struct btf *btf_parse_vmlinux(void)
 	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
 	bpf_ctx_convert.t = btf_type_by_id(btf, btf_id);
 
+	/* find bpf map structs for map_ptr access checking */
+	err = btf_vmlinux_map_ids_init(btf, log);
+	if (err < 0)
+		goto errout;
+
 	bpf_struct_ops_init(btf, log);
 
 	btf_verifier_env_free(env);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index b4b288a3c3c9..2c5999e02060 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1614,6 +1614,7 @@ htab_lru_map_lookup_and_delete_batch(struct bpf_map *map,
 						  true, false);
 }
 
+static int htab_map_btf_id;
 const struct bpf_map_ops htab_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1625,6 +1626,8 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_gen_lookup = htab_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	BATCH_OPS(htab),
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_map_btf_id,
 };
 
 const struct bpf_map_ops htab_lru_map_ops = {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a1857c4ffaaf..7460f967cb75 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1351,6 +1351,19 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, regs + regno);
 }
 
+static void mark_btf_ld_reg(struct bpf_verifier_env *env,
+			    struct bpf_reg_state *regs, u32 regno,
+			    enum bpf_reg_type reg_type, u32 btf_id)
+{
+	if (reg_type == SCALAR_VALUE) {
+		mark_reg_unknown(env, regs, regno);
+		return;
+	}
+	mark_reg_known_zero(env, regs, regno);
+	regs[regno].type = PTR_TO_BTF_ID;
+	regs[regno].btf_id = btf_id;
+}
+
 #define DEF_NOT_SUBREG	(0)
 static void init_reg_state(struct bpf_verifier_env *env,
 			   struct bpf_func_state *state)
@@ -3182,19 +3195,68 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
-	if (atype == BPF_READ && value_regno >= 0) {
-		if (ret == SCALAR_VALUE) {
-			mark_reg_unknown(env, regs, value_regno);
-			return 0;
-		}
-		mark_reg_known_zero(env, regs, value_regno);
-		regs[value_regno].type = PTR_TO_BTF_ID;
-		regs[value_regno].btf_id = btf_id;
+	if (atype == BPF_READ && value_regno >= 0)
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
+	return 0;
+}
+
+static int check_ptr_to_map_access(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs,
+				   int regno, int off, int size,
+				   enum bpf_access_type atype,
+				   int value_regno)
+{
+	struct bpf_reg_state *reg = regs + regno;
+	struct bpf_map *map = reg->map_ptr;
+	const struct btf_type *t;
+	const char *tname;
+	u32 btf_id;
+	int ret;
+
+	if (!btf_vmlinux) {
+		verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n");
+		return -ENOTSUPP;
+	}
+
+	if (!map->ops->map_btf_id || !*map->ops->map_btf_id) {
+		verbose(env, "map_ptr access not supported for map type %d\n",
+			map->map_type);
+		return -ENOTSUPP;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id);
+	tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+
+	if (!env->allow_ptr_to_map_access) {
+		verbose(env,
+			"%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+			tname);
+		return -EPERM;
 	}
 
+	if (off < 0) {
+		verbose(env, "R%d is %s invalid negative access: off=%d\n",
+			regno, tname, off);
+		return -EACCES;
+	}
+
+	if (atype != BPF_READ) {
+		verbose(env, "only read from %s is supported\n", tname);
+		return -EACCES;
+	}
+
+	ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+	if (ret < 0)
+		return ret;
+
+	if (value_regno >= 0)
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
 	return 0;
 }
 
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -3363,6 +3425,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (reg->type == PTR_TO_BTF_ID) {
 		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
 					      value_regno);
+	} else if (reg->type == CONST_PTR_TO_MAP) {
+		err = check_ptr_to_map_access(env, regs, regno, off, size, t,
+					      value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
@@ -10951,6 +11016,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		env->strict_alignment = false;
 
 	env->allow_ptr_leaks = bpf_allow_ptr_leaks();
+	env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access();
 	env->bypass_spec_v1 = bpf_bypass_spec_v1();
 	env->bypass_spec_v4 = bpf_bypass_spec_v4();
 	env->bpf_capable = bpf_capable();
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
index cd26ee6b7b1d..1f2b8c4cb26d 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
@@ -56,7 +56,7 @@
 	.fixup_map_in_map = { 16 },
 	.fixup_map_array_48b = { 13 },
 	.result = REJECT,
-	.errstr = "R0 invalid mem access 'map_ptr'",
+	.errstr = "only read from bpf_array is supported",
 },
 {
 	"cond: two branches returning different map pointers for lookup (tail, tail)",
-- 
cgit v1.2.3


From fa997825ebeca820f4001a9e6d285345d3a535ba Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 19 Jun 2020 03:32:50 +0000
Subject: net/mlx5: Constify mac address pointer

Since none of the functions need to modify the input mac address,
constify them.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/vport.c   | 2 +-
 include/linux/mlx5/vport.h                        | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1116ab9bea6c..d6a585a143dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1127,7 +1127,7 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 						  MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
 }
 
-static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
+static void node_guid_gen_from_mac(u64 *node_guid, const u8 *mac)
 {
 	((u8 *)node_guid)[7] = mac[0];
 	((u8 *)node_guid)[6] = mac[1];
@@ -1779,7 +1779,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 
 /* Vport Administration */
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
-			       u16 vport, u8 mac[ETH_ALEN])
+			       u16 vport, const u8 *mac)
 {
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	u64 node_guid;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a5175e98c0b3..165a23efc608 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -311,7 +311,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs);
 void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf);
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
-			       u16 vport, u8 mac[ETH_ALEN]);
+			       u16 vport, const u8 *mac);
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 				 u16 vport, int link_state);
 int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index c107d92dc118..88cdb9bb4c4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -173,7 +173,7 @@ int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr)
 EXPORT_SYMBOL_GPL(mlx5_query_mac_address);
 
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
-				      u16 vport, u8 *addr)
+				      u16 vport, const u8 *addr)
 {
 	void *in;
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 8170da1e9f70..4db87bcfce7b 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -75,7 +75,7 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline);
 int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 min_inline);
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
-				      u16 vport, u8 *addr);
+				      u16 vport, const u8 *addr);
 int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
-- 
cgit v1.2.3


From a602ea86e9f0d82f5c7ba1d3f7487d4097380b96 Mon Sep 17 00:00:00 2001
From: Maxim Kochetkov <fido_max@inbox.ru>
Date: Sun, 21 Jun 2020 10:59:51 +0300
Subject: net: phy: marvell: Add Marvell 88E1340S support

Add support for this new phy ID.

Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c   | 23 +++++++++++++++++++++++
 include/linux/marvell_phy.h |  1 +
 2 files changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index ee9c352f67ab..0842deb33085 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2943,6 +2943,28 @@ static struct phy_driver marvell_drivers[] = {
 		.cable_test_tdr_start = marvell_vct5_cable_test_tdr_start,
 		.cable_test_get_status = marvell_vct7_cable_test_get_status,
 	},
+	{
+		.phy_id = MARVELL_PHY_ID_88E1340S,
+		.phy_id_mask = MARVELL_PHY_ID_MASK,
+		.name = "Marvell 88E1340S",
+		.probe = m88e1510_probe,
+		/* PHY_GBIT_FEATURES */
+		.config_init = marvell_config_init,
+		.config_aneg = m88e1510_config_aneg,
+		.read_status = marvell_read_status,
+		.ack_interrupt = marvell_ack_interrupt,
+		.config_intr = marvell_config_intr,
+		.did_interrupt = m88e1121_did_interrupt,
+		.resume = genphy_resume,
+		.suspend = genphy_suspend,
+		.read_page = marvell_read_page,
+		.write_page = marvell_write_page,
+		.get_sset_count = marvell_get_sset_count,
+		.get_strings = marvell_get_strings,
+		.get_stats = marvell_get_stats,
+		.get_tunable = m88e1540_get_tunable,
+		.set_tunable = m88e1540_set_tunable,
+	},
 };
 
 module_phy_driver(marvell_drivers);
@@ -2963,6 +2985,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = {
 	{ MARVELL_PHY_ID_88E1545, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E6390, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E1340S, MARVELL_PHY_ID_MASK },
 	{ }
 };
 
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index af6b11d4d673..c4390e9cbf15 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -15,6 +15,7 @@
 #define MARVELL_PHY_ID_88E1149R		0x01410e50
 #define MARVELL_PHY_ID_88E1240		0x01410e30
 #define MARVELL_PHY_ID_88E1318S		0x01410e90
+#define MARVELL_PHY_ID_88E1340S		0x01410dc0
 #define MARVELL_PHY_ID_88E1116R		0x01410e40
 #define MARVELL_PHY_ID_88E1510		0x01410dd0
 #define MARVELL_PHY_ID_88E1540		0x01410eb0
-- 
cgit v1.2.3


From f59babf95ef969a18744082ee16e4dfd17743c0b Mon Sep 17 00:00:00 2001
From: Maxim Kochetkov <fido_max@inbox.ru>
Date: Sun, 21 Jun 2020 10:59:52 +0300
Subject: net: phy: marvell: Add Marvell 88E1548P support

Add support for this new phy ID.

Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c   | 23 +++++++++++++++++++++++
 include/linux/marvell_phy.h |  1 +
 2 files changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 0842deb33085..bb86ac0bd092 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2965,6 +2965,28 @@ static struct phy_driver marvell_drivers[] = {
 		.get_tunable = m88e1540_get_tunable,
 		.set_tunable = m88e1540_set_tunable,
 	},
+	{
+		.phy_id = MARVELL_PHY_ID_88E1548P,
+		.phy_id_mask = MARVELL_PHY_ID_MASK,
+		.name = "Marvell 88E1548P",
+		.probe = m88e1510_probe,
+		.features = PHY_GBIT_FIBRE_FEATURES,
+		.config_init = marvell_config_init,
+		.config_aneg = m88e1510_config_aneg,
+		.read_status = marvell_read_status,
+		.ack_interrupt = marvell_ack_interrupt,
+		.config_intr = marvell_config_intr,
+		.did_interrupt = m88e1121_did_interrupt,
+		.resume = genphy_resume,
+		.suspend = genphy_suspend,
+		.read_page = marvell_read_page,
+		.write_page = marvell_write_page,
+		.get_sset_count = marvell_get_sset_count,
+		.get_strings = marvell_get_strings,
+		.get_stats = marvell_get_stats,
+		.get_tunable = m88e1540_get_tunable,
+		.set_tunable = m88e1540_set_tunable,
+	},
 };
 
 module_phy_driver(marvell_drivers);
@@ -2986,6 +3008,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = {
 	{ MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E6390, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1340S, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E1548P, MARVELL_PHY_ID_MASK },
 	{ }
 };
 
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index c4390e9cbf15..ff7b7607c8cf 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -20,6 +20,7 @@
 #define MARVELL_PHY_ID_88E1510		0x01410dd0
 #define MARVELL_PHY_ID_88E1540		0x01410eb0
 #define MARVELL_PHY_ID_88E1545		0x01410ea0
+#define MARVELL_PHY_ID_88E1548P		0x01410ec0
 #define MARVELL_PHY_ID_88E3016		0x01410e60
 #define MARVELL_PHY_ID_88X3310		0x002b09a0
 #define MARVELL_PHY_ID_88E2110		0x002b09b0
-- 
cgit v1.2.3


From 169caf692567897da35382503a5caeb64ab4b8c7 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Fri, 5 Jun 2020 09:59:31 +0800
Subject: firmware: imx: add resource management api

Add resource management API, when we have multiple
partition running together, resources not owned to current
partition should not be used.

Reviewed-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/firmware/imx/Makefile       |  2 +-
 drivers/firmware/imx/rm.c           | 45 ++++++++++++++++++++++++
 include/linux/firmware/imx/sci.h    |  1 +
 include/linux/firmware/imx/svc/rm.h | 69 +++++++++++++++++++++++++++++++++++++
 4 files changed, 116 insertions(+), 1 deletion(-)
 create mode 100644 drivers/firmware/imx/rm.c
 create mode 100644 include/linux/firmware/imx/svc/rm.h

(limited to 'include/linux')

diff --git a/drivers/firmware/imx/Makefile b/drivers/firmware/imx/Makefile
index 08bc9ddfbdfb..17ea3613e142 100644
--- a/drivers/firmware/imx/Makefile
+++ b/drivers/firmware/imx/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_IMX_DSP)		+= imx-dsp.o
-obj-$(CONFIG_IMX_SCU)		+= imx-scu.o misc.o imx-scu-irq.o
+obj-$(CONFIG_IMX_SCU)		+= imx-scu.o misc.o imx-scu-irq.o rm.o
 obj-$(CONFIG_IMX_SCU_PD)	+= scu-pd.o
diff --git a/drivers/firmware/imx/rm.c b/drivers/firmware/imx/rm.c
new file mode 100644
index 000000000000..a12db6ff323b
--- /dev/null
+++ b/drivers/firmware/imx/rm.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2020 NXP
+ *
+ * File containing client-side RPC functions for the RM service. These
+ * function are ported to clients that communicate to the SC.
+ */
+
+#include <linux/firmware/imx/svc/rm.h>
+
+struct imx_sc_msg_rm_rsrc_owned {
+	struct imx_sc_rpc_msg hdr;
+	u16 resource;
+} __packed __aligned(4);
+
+/*
+ * This function check @resource is owned by current partition or not
+ *
+ * @param[in]     ipc         IPC handle
+ * @param[in]     resource    resource the control is associated with
+ *
+ * @return Returns 0 for not owned and 1 for owned.
+ */
+bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource)
+{
+	struct imx_sc_msg_rm_rsrc_owned msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_RM;
+	hdr->func = IMX_SC_RM_FUNC_IS_RESOURCE_OWNED;
+	hdr->size = 2;
+
+	msg.resource = resource;
+
+	/*
+	 * SCU firmware only returns value 0 or 1
+	 * for resource owned check which means not owned or owned.
+	 * So it is always successful.
+	 */
+	imx_scu_call_rpc(ipc, &msg, true);
+
+	return hdr->func;
+}
+EXPORT_SYMBOL(imx_sc_rm_is_resource_owned);
diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h
index 3fa418a4ca67..3c459f54a88f 100644
--- a/include/linux/firmware/imx/sci.h
+++ b/include/linux/firmware/imx/sci.h
@@ -14,6 +14,7 @@
 
 #include <linux/firmware/imx/svc/misc.h>
 #include <linux/firmware/imx/svc/pm.h>
+#include <linux/firmware/imx/svc/rm.h>
 
 int imx_scu_enable_general_irq_channel(struct device *dev);
 int imx_scu_irq_register_notifier(struct notifier_block *nb);
diff --git a/include/linux/firmware/imx/svc/rm.h b/include/linux/firmware/imx/svc/rm.h
new file mode 100644
index 000000000000..456b6a59d29b
--- /dev/null
+++ b/include/linux/firmware/imx/svc/rm.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017-2020 NXP
+ *
+ * Header file containing the public API for the System Controller (SC)
+ * Resource Management (RM) function. This includes functions for
+ * partitioning resources, pads, and memory regions.
+ *
+ * RM_SVC (SVC) Resource Management Service
+ *
+ * Module for the Resource Management (RM) service.
+ */
+
+#ifndef _SC_RM_API_H
+#define _SC_RM_API_H
+
+#include <linux/firmware/imx/sci.h>
+
+/*
+ * This type is used to indicate RPC RM function calls.
+ */
+enum imx_sc_rm_func {
+	IMX_SC_RM_FUNC_UNKNOWN = 0,
+	IMX_SC_RM_FUNC_PARTITION_ALLOC = 1,
+	IMX_SC_RM_FUNC_SET_CONFIDENTIAL = 31,
+	IMX_SC_RM_FUNC_PARTITION_FREE = 2,
+	IMX_SC_RM_FUNC_GET_DID = 26,
+	IMX_SC_RM_FUNC_PARTITION_STATIC = 3,
+	IMX_SC_RM_FUNC_PARTITION_LOCK = 4,
+	IMX_SC_RM_FUNC_GET_PARTITION = 5,
+	IMX_SC_RM_FUNC_SET_PARENT = 6,
+	IMX_SC_RM_FUNC_MOVE_ALL = 7,
+	IMX_SC_RM_FUNC_ASSIGN_RESOURCE = 8,
+	IMX_SC_RM_FUNC_SET_RESOURCE_MOVABLE = 9,
+	IMX_SC_RM_FUNC_SET_SUBSYS_RSRC_MOVABLE = 28,
+	IMX_SC_RM_FUNC_SET_MASTER_ATTRIBUTES = 10,
+	IMX_SC_RM_FUNC_SET_MASTER_SID = 11,
+	IMX_SC_RM_FUNC_SET_PERIPHERAL_PERMISSIONS = 12,
+	IMX_SC_RM_FUNC_IS_RESOURCE_OWNED = 13,
+	IMX_SC_RM_FUNC_GET_RESOURCE_OWNER = 33,
+	IMX_SC_RM_FUNC_IS_RESOURCE_MASTER = 14,
+	IMX_SC_RM_FUNC_IS_RESOURCE_PERIPHERAL = 15,
+	IMX_SC_RM_FUNC_GET_RESOURCE_INFO = 16,
+	IMX_SC_RM_FUNC_MEMREG_ALLOC = 17,
+	IMX_SC_RM_FUNC_MEMREG_SPLIT = 29,
+	IMX_SC_RM_FUNC_MEMREG_FRAG = 32,
+	IMX_SC_RM_FUNC_MEMREG_FREE = 18,
+	IMX_SC_RM_FUNC_FIND_MEMREG = 30,
+	IMX_SC_RM_FUNC_ASSIGN_MEMREG = 19,
+	IMX_SC_RM_FUNC_SET_MEMREG_PERMISSIONS = 20,
+	IMX_SC_RM_FUNC_IS_MEMREG_OWNED = 21,
+	IMX_SC_RM_FUNC_GET_MEMREG_INFO = 22,
+	IMX_SC_RM_FUNC_ASSIGN_PAD = 23,
+	IMX_SC_RM_FUNC_SET_PAD_MOVABLE = 24,
+	IMX_SC_RM_FUNC_IS_PAD_OWNED = 25,
+	IMX_SC_RM_FUNC_DUMP = 27,
+};
+
+#if IS_ENABLED(CONFIG_IMX_SCU)
+bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource);
+#else
+static inline bool
+imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource)
+{
+	return true;
+}
+#endif
+#endif
-- 
cgit v1.2.3


From 16ecf10e815d70d11d2300243f4a3b4c7c5acac7 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Tue, 23 Jun 2020 07:13:41 +0800
Subject: iommu/vt-d: Set U/S bit in first level page table by default

When using first-level translation for IOVA, currently the U/S bit in the
page table is cleared which implies DMA requests with user privilege are
blocked. As the result, following error messages might be observed when
passing through a device to user level:

DMAR: DRHD: handling fault status reg 3
DMAR: [DMA Read] Request device [41:00.0] PASID 1 fault addr 7ecdcd000
        [fault reason 129] SM: U/S set 0 for first-level translation
        with user privilege

This fixes it by setting U/S bit in the first level page table and makes
IOVA over first level compatible with previous second-level translation.

Fixes: b802d070a52a1 ("iommu/vt-d: Use iova over first level")
Reported-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200622231345.29722-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 5 ++---
 include/linux/intel-iommu.h | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 9129663a7406..0fa394f7bbf9 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -921,7 +921,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
 			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
 			if (domain_use_first_level(domain))
-				pteval |= DMA_FL_PTE_XD;
+				pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US;
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -1951,7 +1951,6 @@ static inline void
 context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
 {
 	context->hi |= pasid & ((1 << 20) - 1);
-	context->hi |= (1 << 20);
 }
 
 /*
@@ -2243,7 +2242,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 
 	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
 	if (domain_use_first_level(domain))
-		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
+		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US;
 
 	if (!sg) {
 		sg_res = nr_pages;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4100bd224f5c..3e8fa1c7a1e6 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -41,6 +41,7 @@
 #define DMA_PTE_SNP		BIT_ULL(11)
 
 #define DMA_FL_PTE_PRESENT	BIT_ULL(0)
+#define DMA_FL_PTE_US		BIT_ULL(2)
 #define DMA_FL_PTE_XD		BIT_ULL(63)
 
 #define ADDR_WIDTH_5LEVEL	(57)
-- 
cgit v1.2.3


From 809b1b04df898b6d182069146231a3cbf5f2d9cc Mon Sep 17 00:00:00 2001
From: Robin Gong <yibin.gong@nxp.com>
Date: Wed, 17 Jun 2020 06:42:08 +0800
Subject: spi: introduce fallback to pio

Add fallback to pio mode in case dma transfer failed with error status
SPI_TRANS_FAIL_NO_START.
If spi client driver want to enable this feature please set xfer->error in
the proper place such as dmaengine_prep_slave_sg() failure detect(but no
any data put into spi bus yet). Besides, add master->fallback checking in
its can_dma() so that spi core could switch to pio next time. Please refer
to spi-imx.c.

Signed-off-by: Robin Gong <yibin.gong@nxp.com>
Link: https://lore.kernel.org/r/1592347329-28363-2-git-send-email-yibin.gong@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 12 ++++++++++++
 include/linux/spi/spi.h |  7 +++++++
 2 files changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8158e281f354..6fa56590bba2 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -982,6 +982,8 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 		spi_unmap_buf(ctlr, tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 	}
 
+	ctlr->cur_msg_mapped = false;
+
 	return 0;
 }
 #else /* !CONFIG_HAS_DMA */
@@ -1234,8 +1236,17 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 		if (xfer->tx_buf || xfer->rx_buf) {
 			reinit_completion(&ctlr->xfer_completion);
 
+fallback_pio:
 			ret = ctlr->transfer_one(ctlr, msg->spi, xfer);
 			if (ret < 0) {
+				if (ctlr->cur_msg_mapped &&
+				   (xfer->error & SPI_TRANS_FAIL_NO_START)) {
+					__spi_unmap_msg(ctlr, msg);
+					ctlr->fallback = true;
+					xfer->error &= ~SPI_TRANS_FAIL_NO_START;
+					goto fallback_pio;
+				}
+
 				SPI_STATISTICS_INCREMENT_FIELD(statm,
 							       errors);
 				SPI_STATISTICS_INCREMENT_FIELD(stats,
@@ -1693,6 +1704,7 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 	spin_lock_irqsave(&ctlr->queue_lock, flags);
 	ctlr->cur_msg = NULL;
 	ctlr->cur_msg_prepared = false;
+	ctlr->fallback = false;
 	kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index aac57b5b7c21..b4917df79637 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -447,6 +447,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	If the driver does not set this, the SPI core takes the snapshot as
  *	close to the driver hand-over as possible.
  * @irq_flags: Interrupt enable state during PTP system timestamping
+ * @fallback: fallback to pio if dma transfer return failure with
+ *	SPI_TRANS_FAIL_NO_START.
  *
  * Each SPI controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -602,6 +604,7 @@ struct spi_controller {
 	bool				auto_runtime_pm;
 	bool                            cur_msg_prepared;
 	bool				cur_msg_mapped;
+	bool                            fallback;
 	struct completion               xfer_completion;
 	size_t				max_dma_len;
 
@@ -847,6 +850,7 @@ extern void spi_res_release(struct spi_controller *ctlr,
  *	back unset and they need the better resolution.
  * @timestamped_post: See above. The reason why both exist is that these
  *	booleans are also used to keep state in the core SPI logic.
+ * @error: Error status logged by spi controller driver.
  *
  * SPI transfers always write the same number of bytes as they read.
  * Protocol drivers should always provide @rx_buf and/or @tx_buf.
@@ -940,6 +944,9 @@ struct spi_transfer {
 	bool		timestamped;
 
 	struct list_head transfer_list;
+
+#define SPI_TRANS_FAIL_NO_START	BIT(0)
+	u16		error;
 };
 
 /**
-- 
cgit v1.2.3


From d63cc24933c774ea464090af1998a7b63f11c166 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Wed, 8 Apr 2020 12:42:09 +0300
Subject: net/mlx5: Export resource dump interface

Export some of the resource dump API. mlx5_ib driver will use
it in downstream patches.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/rsc_dump.c    |  3 ++
 .../ethernet/mellanox/mlx5/core/diag/rsc_dump.h    | 33 +--------------
 include/linux/mlx5/rsc_dump.h                      | 48 ++++++++++++++++++++++
 3 files changed, 52 insertions(+), 32 deletions(-)
 create mode 100644 include/linux/mlx5/rsc_dump.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
index 17ab7efe693d..10218c2324cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
@@ -130,11 +130,13 @@ struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev,
 	cmd->mem_size = key->size;
 	return cmd;
 }
+EXPORT_SYMBOL(mlx5_rsc_dump_cmd_create);
 
 void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd)
 {
 	kfree(cmd);
 }
+EXPORT_SYMBOL(mlx5_rsc_dump_cmd_destroy);
 
 int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd,
 		       struct page *page, int *size)
@@ -155,6 +157,7 @@ int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd,
 
 	return more_dump;
 }
+EXPORT_SYMBOL(mlx5_rsc_dump_next);
 
 #define MLX5_RSC_DUMP_MENU_SEGMENT 0xffff
 static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h
index 148270073e71..64c4956db6d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h
@@ -4,41 +4,10 @@
 #ifndef __MLX5_RSC_DUMP_H
 #define __MLX5_RSC_DUMP_H
 
+#include <linux/mlx5/rsc_dump.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
 
-enum mlx5_sgmt_type {
-	MLX5_SGMT_TYPE_HW_CQPC,
-	MLX5_SGMT_TYPE_HW_SQPC,
-	MLX5_SGMT_TYPE_HW_RQPC,
-	MLX5_SGMT_TYPE_FULL_SRQC,
-	MLX5_SGMT_TYPE_FULL_CQC,
-	MLX5_SGMT_TYPE_FULL_EQC,
-	MLX5_SGMT_TYPE_FULL_QPC,
-	MLX5_SGMT_TYPE_SND_BUFF,
-	MLX5_SGMT_TYPE_RCV_BUFF,
-	MLX5_SGMT_TYPE_SRQ_BUFF,
-	MLX5_SGMT_TYPE_CQ_BUFF,
-	MLX5_SGMT_TYPE_EQ_BUFF,
-	MLX5_SGMT_TYPE_SX_SLICE,
-	MLX5_SGMT_TYPE_SX_SLICE_ALL,
-	MLX5_SGMT_TYPE_RDB,
-	MLX5_SGMT_TYPE_RX_SLICE_ALL,
-	MLX5_SGMT_TYPE_MENU,
-	MLX5_SGMT_TYPE_TERMINATE,
-
-	MLX5_SGMT_TYPE_NUM, /* Keep last */
-};
-
-struct mlx5_rsc_key {
-	enum mlx5_sgmt_type rsc;
-	int index1;
-	int index2;
-	int num_of_obj1;
-	int num_of_obj2;
-	int size;
-};
-
 #define MLX5_RSC_DUMP_ALL 0xFFFF
 struct mlx5_rsc_dump_cmd;
 struct mlx5_rsc_dump;
diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h
new file mode 100644
index 000000000000..87415fa754fe
--- /dev/null
+++ b/include/linux/mlx5/rsc_dump.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies inc. */
+
+#include <linux/mlx5/driver.h>
+
+#ifndef __MLX5_RSC_DUMP
+#define __MLX5_RSC_DUMP
+
+enum mlx5_sgmt_type {
+	MLX5_SGMT_TYPE_HW_CQPC,
+	MLX5_SGMT_TYPE_HW_SQPC,
+	MLX5_SGMT_TYPE_HW_RQPC,
+	MLX5_SGMT_TYPE_FULL_SRQC,
+	MLX5_SGMT_TYPE_FULL_CQC,
+	MLX5_SGMT_TYPE_FULL_EQC,
+	MLX5_SGMT_TYPE_FULL_QPC,
+	MLX5_SGMT_TYPE_SND_BUFF,
+	MLX5_SGMT_TYPE_RCV_BUFF,
+	MLX5_SGMT_TYPE_SRQ_BUFF,
+	MLX5_SGMT_TYPE_CQ_BUFF,
+	MLX5_SGMT_TYPE_EQ_BUFF,
+	MLX5_SGMT_TYPE_SX_SLICE,
+	MLX5_SGMT_TYPE_SX_SLICE_ALL,
+	MLX5_SGMT_TYPE_RDB,
+	MLX5_SGMT_TYPE_RX_SLICE_ALL,
+	MLX5_SGMT_TYPE_MENU,
+	MLX5_SGMT_TYPE_TERMINATE,
+
+	MLX5_SGMT_TYPE_NUM, /* Keep last */
+};
+
+struct mlx5_rsc_key {
+	enum mlx5_sgmt_type rsc;
+	int index1;
+	int index2;
+	int num_of_obj1;
+	int num_of_obj2;
+	int size;
+};
+
+struct mlx5_rsc_dump_cmd;
+
+struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev,
+						   struct mlx5_rsc_key *key);
+void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd);
+int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd,
+		       struct page *page, int *size);
+#endif /* __MLX5_RSC_DUMP */
-- 
cgit v1.2.3


From 608ca553c9a2008908120e0e45b1cfc4aefcfd49 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Wed, 8 Apr 2020 12:36:20 +0300
Subject: net/mlx5: Add support in query QP, CQ and MKEY segments

Introduce new resource dump segments - PRM_QUERY_QP,
PRM_QUERY_CQ and PRM_QUERY_MKEY. These segments contains the resource
dump in PRM query format.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c | 3 +++
 include/linux/mlx5/rsc_dump.h                           | 3 +++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
index 10218c2324cc..4924a5658853 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
@@ -23,6 +23,9 @@ static const char *const mlx5_rsc_sgmt_name[] = {
 	MLX5_SGMT_STR_ASSING(SX_SLICE_ALL),
 	MLX5_SGMT_STR_ASSING(RDB),
 	MLX5_SGMT_STR_ASSING(RX_SLICE_ALL),
+	MLX5_SGMT_STR_ASSING(PRM_QUERY_QP),
+	MLX5_SGMT_STR_ASSING(PRM_QUERY_CQ),
+	MLX5_SGMT_STR_ASSING(PRM_QUERY_MKEY),
 };
 
 struct mlx5_rsc_dump {
diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h
index 87415fa754fe..d11c0b228620 100644
--- a/include/linux/mlx5/rsc_dump.h
+++ b/include/linux/mlx5/rsc_dump.h
@@ -23,6 +23,9 @@ enum mlx5_sgmt_type {
 	MLX5_SGMT_TYPE_SX_SLICE_ALL,
 	MLX5_SGMT_TYPE_RDB,
 	MLX5_SGMT_TYPE_RX_SLICE_ALL,
+	MLX5_SGMT_TYPE_PRM_QUERY_QP,
+	MLX5_SGMT_TYPE_PRM_QUERY_CQ,
+	MLX5_SGMT_TYPE_PRM_QUERY_MKEY,
 	MLX5_SGMT_TYPE_MENU,
 	MLX5_SGMT_TYPE_TERMINATE,
 
-- 
cgit v1.2.3


From 97dd1abd026ae4e6a82fa68645928404ad483409 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Tue, 23 Jun 2020 16:51:29 +0300
Subject: net: qed: fix left elements count calculation

qed_chain_get_element_left{,_u32} returned 0 when the difference
between producer and consumer page count was equal to the total
page count.
Fix this by conditional expanding of producer value (vs
unconditional). This allowed to eliminate normalizaton against
total page count, which was the cause of this bug.

Misc: replace open-coded constants with common defines.

Fixes: a91eb52abb50 ("qed: Revisit chain implementation")
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_chain.h | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 733fad7dfbed..6d15040c642c 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain)
 
 static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u32 prod = p_chain->u.chain16.prod_idx;
+	u32 cons = p_chain->u.chain16.cons_idx;
 	u16 used;
 
-	used = (u16) (((u32)0x10000 +
-		       (u32)p_chain->u.chain16.prod_idx) -
-		      (u32)p_chain->u.chain16.cons_idx);
+	if (prod < cons)
+		prod += (u32)U16_MAX + 1;
+
+	used = (u16)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain16.cons_idx / p_chain->elem_per_page;
+		used -= prod / elem_per_page - cons / elem_per_page;
 
 	return (u16)(p_chain->capacity - used);
 }
 
 static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u64 prod = p_chain->u.chain32.prod_idx;
+	u64 cons = p_chain->u.chain32.cons_idx;
 	u32 used;
 
-	used = (u32) (((u64)0x100000000ULL +
-		       (u64)p_chain->u.chain32.prod_idx) -
-		      (u64)p_chain->u.chain32.cons_idx);
+	if (prod < cons)
+		prod += (u64)U32_MAX + 1;
+
+	used = (u32)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain32.cons_idx / p_chain->elem_per_page;
+		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
 
 	return p_chain->capacity - used;
 }
-- 
cgit v1.2.3


From e678e9ddea96590888b034e2a7ad1128bf1ea1ea Mon Sep 17 00:00:00 2001
From: Brian Vazquez <brianvv@google.com>
Date: Tue, 23 Jun 2020 09:42:31 -0700
Subject: indirect_call_wrapper: extend indirect wrapper to support up to 4
 calls

There are many places where 2 annotations are not enough. This patch
adds INDIRECT_CALL_3 and INDIRECT_CALL_4 to cover such cases.

Signed-off-by: Brian Vazquez <brianvv@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/indirect_call_wrapper.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 00d7e8e919c6..54c02c84906a 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -23,6 +23,16 @@
 		likely(f == f2) ? f2(__VA_ARGS__) :			\
 				  INDIRECT_CALL_1(f, f1, __VA_ARGS__);	\
 	})
+#define INDIRECT_CALL_3(f, f3, f2, f1, ...)					\
+	({									\
+		likely(f == f3) ? f3(__VA_ARGS__) :				\
+				  INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__);	\
+	})
+#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...)					\
+	({									\
+		likely(f == f4) ? f4(__VA_ARGS__) :				\
+				  INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__);	\
+	})
 
 #define INDIRECT_CALLABLE_DECLARE(f)	f
 #define INDIRECT_CALLABLE_SCOPE
@@ -30,6 +40,8 @@
 #else
 #define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__)
 #define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_3(f, f3, f2, f1, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__)
 #define INDIRECT_CALLABLE_DECLARE(f)
 #define INDIRECT_CALLABLE_SCOPE		static
 #endif
-- 
cgit v1.2.3


From 23e390cdbe6f85827a43d38f9288dcd3066fa376 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Mon, 22 Jun 2020 00:21:35 +0200
Subject: security: Fix hook iteration and default value for
 inode_copy_up_xattr

inode_copy_up_xattr returns 0 to indicate the acceptance of the xattr
and 1 to reject it. If the LSM does not know about the xattr, it's
expected to return -EOPNOTSUPP, which is the correct default value for
this hook. BPF LSM, currently, uses 0 as the default value and thereby
falsely allows all overlay fs xattributes to be copied up.

The iteration logic is also updated from the "bail-on-fail"
call_int_hook to continue on the non-decisive -EOPNOTSUPP and bail out
on other values.

Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks")
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 include/linux/lsm_hook_defs.h |  2 +-
 security/security.c           | 17 ++++++++++++++++-
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 24f6683f1cfc..af998f93d256 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -150,7 +150,7 @@ LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer,
 	 size_t buffer_size)
 LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid)
 LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new)
-LSM_HOOK(int, 0, inode_copy_up_xattr, const char *name)
+LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name)
 LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir,
 	 struct kernfs_node *kn)
 LSM_HOOK(int, 0, file_permission, struct file *file, int mask)
diff --git a/security/security.c b/security/security.c
index 0ce3e73edd42..70a7ad357bc6 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1414,7 +1414,22 @@ EXPORT_SYMBOL(security_inode_copy_up);
 
 int security_inode_copy_up_xattr(const char *name)
 {
-	return call_int_hook(inode_copy_up_xattr, -EOPNOTSUPP, name);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * The implementation can return 0 (accept the xattr), 1 (discard the
+	 * xattr), -EOPNOTSUPP if it does not know anything about the xattr or
+	 * any other error code incase of an error.
+	 */
+	hlist_for_each_entry(hp,
+		&security_hook_heads.inode_copy_up_xattr, list) {
+		rc = hp->hook.inode_copy_up_xattr(name);
+		if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(inode_copy_up_xattr);
 }
 EXPORT_SYMBOL(security_inode_copy_up_xattr);
 
-- 
cgit v1.2.3


From 8e6cf365e1d5c70e275a77a3c5ad7e3dc685474c Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 4 Jun 2020 09:20:49 -0400
Subject: audit: log nftables configuration change events

iptables, ip6tables, arptables and ebtables table registration,
replacement and unregistration configuration events are logged for the
native (legacy) iptables setsockopt api, but not for the
nftables netlink api which is used by the nft-variant of iptables in
addition to nftables itself.

Add calls to log the configuration actions in the nftables netlink api.

This uses the same NETFILTER_CFG record format but overloads the table
field.

  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=?:0;?:0 family=unspecified entries=2 op=nft_register_gen pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
  ...
  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=firewalld:1;?:0 family=inet entries=0 op=nft_register_table pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
  ...
  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=8 op=nft_register_chain pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
  ...
  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=101 op=nft_register_rule pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
  ...
  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=87 op=nft_register_setelem pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
  ...
  type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=0 op=nft_register_set pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld

For further information please see issue
https://github.com/linux-audit/audit-kernel/issues/124

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h         |  18 ++++++++
 kernel/auditsc.c              |  24 ++++++++--
 net/netfilter/nf_tables_api.c | 103 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 142 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 3fcd9ee49734..604ede630580 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
+#include <uapi/linux/netfilter/nf_tables.h>
 
 #define AUDIT_INO_UNSET ((unsigned long)-1)
 #define AUDIT_DEV_UNSET ((dev_t)-1)
@@ -98,6 +99,23 @@ enum audit_nfcfgop {
 	AUDIT_XT_OP_REGISTER,
 	AUDIT_XT_OP_REPLACE,
 	AUDIT_XT_OP_UNREGISTER,
+	AUDIT_NFT_OP_TABLE_REGISTER,
+	AUDIT_NFT_OP_TABLE_UNREGISTER,
+	AUDIT_NFT_OP_CHAIN_REGISTER,
+	AUDIT_NFT_OP_CHAIN_UNREGISTER,
+	AUDIT_NFT_OP_RULE_REGISTER,
+	AUDIT_NFT_OP_RULE_UNREGISTER,
+	AUDIT_NFT_OP_SET_REGISTER,
+	AUDIT_NFT_OP_SET_UNREGISTER,
+	AUDIT_NFT_OP_SETELEM_REGISTER,
+	AUDIT_NFT_OP_SETELEM_UNREGISTER,
+	AUDIT_NFT_OP_GEN_REGISTER,
+	AUDIT_NFT_OP_OBJ_REGISTER,
+	AUDIT_NFT_OP_OBJ_UNREGISTER,
+	AUDIT_NFT_OP_OBJ_RESET,
+	AUDIT_NFT_OP_FLOWTABLE_REGISTER,
+	AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+	AUDIT_NFT_OP_INVALID,
 };
 
 extern int is_audit_feature_set(int which);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 468a23390457..3a9100e95fda 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -75,6 +75,7 @@
 #include <linux/uaccess.h>
 #include <linux/fsnotify_backend.h>
 #include <uapi/linux/limits.h>
+#include <uapi/linux/netfilter/nf_tables.h>
 
 #include "audit.h"
 
@@ -136,9 +137,26 @@ struct audit_nfcfgop_tab {
 };
 
 static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
-	{ AUDIT_XT_OP_REGISTER,		"register"	},
-	{ AUDIT_XT_OP_REPLACE,		"replace"	},
-	{ AUDIT_XT_OP_UNREGISTER,	"unregister"	},
+	{ AUDIT_XT_OP_REGISTER,			"xt_register"		   },
+	{ AUDIT_XT_OP_REPLACE,			"xt_replace"		   },
+	{ AUDIT_XT_OP_UNREGISTER,		"xt_unregister"		   },
+	{ AUDIT_NFT_OP_TABLE_REGISTER,		"nft_register_table"	   },
+	{ AUDIT_NFT_OP_TABLE_UNREGISTER,	"nft_unregister_table"	   },
+	{ AUDIT_NFT_OP_CHAIN_REGISTER,		"nft_register_chain"	   },
+	{ AUDIT_NFT_OP_CHAIN_UNREGISTER,	"nft_unregister_chain"	   },
+	{ AUDIT_NFT_OP_RULE_REGISTER,		"nft_register_rule"	   },
+	{ AUDIT_NFT_OP_RULE_UNREGISTER,		"nft_unregister_rule"	   },
+	{ AUDIT_NFT_OP_SET_REGISTER,		"nft_register_set"	   },
+	{ AUDIT_NFT_OP_SET_UNREGISTER,		"nft_unregister_set"	   },
+	{ AUDIT_NFT_OP_SETELEM_REGISTER,	"nft_register_setelem"	   },
+	{ AUDIT_NFT_OP_SETELEM_UNREGISTER,	"nft_unregister_setelem"   },
+	{ AUDIT_NFT_OP_GEN_REGISTER,		"nft_register_gen"	   },
+	{ AUDIT_NFT_OP_OBJ_REGISTER,		"nft_register_obj"	   },
+	{ AUDIT_NFT_OP_OBJ_UNREGISTER,		"nft_unregister_obj"	   },
+	{ AUDIT_NFT_OP_OBJ_RESET,		"nft_reset_obj"		   },
+	{ AUDIT_NFT_OP_FLOWTABLE_REGISTER,	"nft_register_flowtable"   },
+	{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,	"nft_unregister_flowtable" },
+	{ AUDIT_NFT_OP_INVALID,			"nft_invalid"		   },
 };
 
 static int audit_match_perm(struct audit_context *ctx, int mask)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 073aa1051d43..164700273947 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -12,6 +12,7 @@
 #include <linux/netlink.h>
 #include <linux/vmalloc.h>
 #include <linux/rhashtable.h>
+#include <linux/audit.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
@@ -693,6 +694,16 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+			      ctx->table->name, ctx->table->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			ctx->table->use,
+			event == NFT_MSG_NEWTABLE ?
+				AUDIT_NFT_OP_TABLE_REGISTER :
+				AUDIT_NFT_OP_TABLE_UNREGISTER);
+	kfree(buf);
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -1428,6 +1439,17 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+			      ctx->table->name, ctx->table->handle,
+			      ctx->chain->name, ctx->chain->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			ctx->chain->use,
+			event == NFT_MSG_NEWCHAIN ?
+				AUDIT_NFT_OP_CHAIN_REGISTER :
+				AUDIT_NFT_OP_CHAIN_UNREGISTER);
+	kfree(buf);
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -2693,6 +2715,17 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
 {
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+			      ctx->table->name, ctx->table->handle,
+			      ctx->chain->name, ctx->chain->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			rule->handle,
+			event == NFT_MSG_NEWRULE ?
+				AUDIT_NFT_OP_RULE_REGISTER :
+				AUDIT_NFT_OP_RULE_UNREGISTER);
+	kfree(buf);
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -3695,6 +3728,17 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx,
 	struct sk_buff *skb;
 	u32 portid = ctx->portid;
 	int err;
+	char *buf = kasprintf(gfp_flags, "%s:%llu;%s:%llu",
+			      ctx->table->name, ctx->table->handle,
+			      set->name, set->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			set->field_count,
+			event == NFT_MSG_NEWSET ?
+				AUDIT_NFT_OP_SET_REGISTER :
+				AUDIT_NFT_OP_SET_UNREGISTER);
+	kfree(buf);
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -4811,6 +4855,17 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
 	u32 portid = ctx->portid;
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+			      ctx->table->name, ctx->table->handle,
+			      set->name, set->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			set->handle,
+			event == NFT_MSG_NEWSETELEM ?
+				AUDIT_NFT_OP_SETELEM_REGISTER :
+				AUDIT_NFT_OP_SETELEM_UNREGISTER);
+	kfree(buf);
 
 	if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
 		return;
@@ -5892,6 +5947,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 			    obj->ops->type->type != filter->type)
 				goto cont;
 
+			if (reset) {
+				char *buf = kasprintf(GFP_KERNEL,
+						      "%s:%llu;?:0",
+						      table->name,
+						      table->handle);
+
+				audit_log_nfcfg(buf,
+						family,
+						obj->handle,
+						AUDIT_NFT_OP_OBJ_RESET);
+				kfree(buf);
+			}
+
 			if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NFT_MSG_NEWOBJ,
@@ -6002,6 +6070,17 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 	if (NFNL_MSG_TYPE(nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
 		reset = true;
 
+	if (reset) {
+		char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+				      table->name, table->handle);
+
+		audit_log_nfcfg(buf,
+				family,
+				obj->handle,
+				AUDIT_NFT_OP_OBJ_RESET);
+		kfree(buf);
+	}
+
 	err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
 				      nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
 				      family, table, obj, reset);
@@ -6077,6 +6156,16 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 {
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+			      table->name, table->handle);
+
+	audit_log_nfcfg(buf,
+			family,
+			obj->handle,
+			event == NFT_MSG_NEWOBJ ?
+				AUDIT_NFT_OP_OBJ_REGISTER :
+				AUDIT_NFT_OP_OBJ_UNREGISTER);
+	kfree(buf);
 
 	if (!report &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
@@ -6856,6 +6945,17 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 {
 	struct sk_buff *skb;
 	int err;
+	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+			      flowtable->table->name, flowtable->table->handle,
+			      flowtable->name, flowtable->handle);
+
+	audit_log_nfcfg(buf,
+			ctx->family,
+			flowtable->hooknum,
+			event == NFT_MSG_NEWFLOWTABLE ?
+				AUDIT_NFT_OP_FLOWTABLE_REGISTER :
+				AUDIT_NFT_OP_FLOWTABLE_UNREGISTER);
+	kfree(buf);
 
 	if (ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -6977,6 +7077,9 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
 	struct sk_buff *skb2;
 	int err;
 
+	audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
+			AUDIT_NFT_OP_GEN_REGISTER);
+
 	if (nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
 		return;
-- 
cgit v1.2.3


From 0cc8fecf041d3e5285380da62cc6662bdc942d8c Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Mon, 22 Jun 2020 20:35:32 +0530
Subject: net: phy: Allow mdio buses to auto-probe c45 devices

The mdiobus_scan logic is currently hardcoded to only
work with c22 devices. This works fairly well in most
cases, but its possible that a c45 device doesn't respond
despite being a standard phy. If the parent hardware
is capable, it makes sense to scan for c22 devices before
falling back to c45.

As we want this to reflect the capabilities of the STA,
lets add a field to the mii_bus structure to represent
the capability. That way devices can opt into the extended
scanning. Existing users should continue to default to c22
only scanning as long as they are zero'ing the structure
before use.

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Calvin Johnson <calvin.johnson@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 18 ++++++++++++++++--
 include/linux/phy.h        |  8 ++++++++
 2 files changed, 24 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 6ceee82b2839..ab9233c558d8 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -739,10 +739,24 @@ EXPORT_SYMBOL(mdiobus_free);
  */
 struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr)
 {
-	struct phy_device *phydev;
+	struct phy_device *phydev = ERR_PTR(-ENODEV);
 	int err;
 
-	phydev = get_phy_device(bus, addr, false);
+	switch (bus->probe_capabilities) {
+	case MDIOBUS_NO_CAP:
+	case MDIOBUS_C22:
+		phydev = get_phy_device(bus, addr, false);
+		break;
+	case MDIOBUS_C45:
+		phydev = get_phy_device(bus, addr, true);
+		break;
+	case MDIOBUS_C22_C45:
+		phydev = get_phy_device(bus, addr, false);
+		if (IS_ERR(phydev))
+			phydev = get_phy_device(bus, addr, true);
+		break;
+	}
+
 	if (IS_ERR(phydev))
 		return phydev;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 9248dd2ce4ca..7860d56c6bf5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -298,6 +298,14 @@ struct mii_bus {
 	/* RESET GPIO descriptor pointer */
 	struct gpio_desc *reset_gpiod;
 
+	/* bus capabilities, used for probing */
+	enum {
+		MDIOBUS_NO_CAP = 0,
+		MDIOBUS_C22,
+		MDIOBUS_C45,
+		MDIOBUS_C22_C45,
+	} probe_capabilities;
+
 	/* protect access to the shared element */
 	struct mutex shared_lock;
 
-- 
cgit v1.2.3


From aad4b4d15f30de087c5972cfb767fadb5dbc3c52 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:13:02 +0200
Subject: scsi: libata: Fix the ata_scsi_dma_need_drain stub

We not only need the stub when libata is disabled, but also if it is
modular and there are built-in SAS drivers (which can happen when
SCSI_SAS_ATA is disabled).

Link: https://lore.kernel.org/r/20200620071302.462974-2-hch@lst.de
Fixes: b8f1d1e05817 ("scsi: Wire up ata_scsi_dma_need_drain for SAS HBA drivers")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/libata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/libata.h b/include/linux/libata.h
index 042e584daca7..c57bf6749681 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1092,7 +1092,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 #define ATA_SCSI_COMPAT_IOCTL /* empty */
 #endif
 extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
-#if IS_ENABLED(CONFIG_ATA)
+#if IS_REACHABLE(CONFIG_ATA)
 bool ata_scsi_dma_need_drain(struct request *rq);
 #else
 #define ata_scsi_dma_need_drain NULL
-- 
cgit v1.2.3


From feee1b8c490821f29aae416a5422795f5a29263d Mon Sep 17 00:00:00 2001
From: Alexander Popov <alex.popov@linux.com>
Date: Wed, 24 Jun 2020 15:33:29 +0300
Subject: gcc-plugins/stackleak: Use asm instrumentation to avoid useless
 register saving

The kernel code instrumentation in stackleak gcc plugin works in two stages.
At first, stack tracking is added to GIMPLE representation of every function
(except some special cases). And later, when stack frame size info is
available, stack tracking is removed from the RTL representation of the
functions with small stack frame. There is an unwanted side-effect for these
functions: some of them do useless work with caller-saved registers.

As an example of such case, proc_sys_write without() instrumentation:
    55                      push   %rbp
    41 b8 01 00 00 00       mov    $0x1,%r8d
    48 89 e5                mov    %rsp,%rbp
    e8 11 ff ff ff          callq  ffffffff81284610 <proc_sys_call_handler>
    5d                      pop    %rbp
    c3                      retq
    0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
    66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
    00 00 00

proc_sys_write() with instrumentation:
    55                      push   %rbp
    48 89 e5                mov    %rsp,%rbp
    41 56                   push   %r14
    41 55                   push   %r13
    41 54                   push   %r12
    53                      push   %rbx
    49 89 f4                mov    %rsi,%r12
    48 89 fb                mov    %rdi,%rbx
    49 89 d5                mov    %rdx,%r13
    49 89 ce                mov    %rcx,%r14
    4c 89 f1                mov    %r14,%rcx
    4c 89 ea                mov    %r13,%rdx
    4c 89 e6                mov    %r12,%rsi
    48 89 df                mov    %rbx,%rdi
    41 b8 01 00 00 00       mov    $0x1,%r8d
    e8 f2 fe ff ff          callq  ffffffff81298e80 <proc_sys_call_handler>
    5b                      pop    %rbx
    41 5c                   pop    %r12
    41 5d                   pop    %r13
    41 5e                   pop    %r14
    5d                      pop    %rbp
    c3                      retq
    66 0f 1f 84 00 00 00    nopw   0x0(%rax,%rax,1)
    00 00

Let's improve the instrumentation to avoid this:

1. Make stackleak_track_stack() save all register that it works with.
Use no_caller_saved_registers attribute for that function. This attribute
is available for x86_64 and i386 starting from gcc-7.

2. Insert calling stackleak_track_stack() in asm:
  asm volatile("call stackleak_track_stack" :: "r" (current_stack_pointer))
Here we use ASM_CALL_CONSTRAINT trick from arch/x86/include/asm/asm.h.
The input constraint is taken into account during gcc shrink-wrapping
optimization. It is needed to be sure that stackleak_track_stack() call is
inserted after the prologue of the containing function, when the stack
frame is prepared.

This work is a deep reengineering of the idea described on grsecurity blog
  https://grsecurity.net/resolving_an_unfortunate_stackleak_interaction

Signed-off-by: Alexander Popov <alex.popov@linux.com>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Link: https://lore.kernel.org/r/20200624123330.83226-5-alex.popov@linux.com
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/compiler_attributes.h    |  13 +++
 kernel/stackleak.c                     |  16 +--
 scripts/Makefile.gcc-plugins           |   2 +
 scripts/gcc-plugins/stackleak_plugin.c | 205 ++++++++++++++++++++++++++++-----
 4 files changed, 196 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index cdf016596659..551ea8cb70b1 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -37,6 +37,7 @@
 # define __GCC4_has_attribute___copy__                0
 # define __GCC4_has_attribute___designated_init__     0
 # define __GCC4_has_attribute___externally_visible__  1
+# define __GCC4_has_attribute___no_caller_saved_registers__ 0
 # define __GCC4_has_attribute___noclone__             1
 # define __GCC4_has_attribute___nonstring__           0
 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8)
@@ -175,6 +176,18 @@
  */
 #define __mode(x)                       __attribute__((__mode__(x)))
 
+/*
+ * Optional: only supported since gcc >= 7
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/x86-Function-Attributes.html#index-no_005fcaller_005fsaved_005fregisters-function-attribute_002c-x86
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#no-caller-saved-registers
+ */
+#if __has_attribute(__no_caller_saved_registers__)
+# define __no_caller_saved_registers	__attribute__((__no_caller_saved_registers__))
+#else
+# define __no_caller_saved_registers
+#endif
+
 /*
  * Optional: not supported by clang
  *
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index b193a59fc05b..a8fc9ae1d03d 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -104,19 +104,9 @@ asmlinkage void notrace stackleak_erase(void)
 }
 NOKPROBE_SYMBOL(stackleak_erase);
 
-void __used notrace stackleak_track_stack(void)
+void __used __no_caller_saved_registers notrace stackleak_track_stack(void)
 {
-	/*
-	 * N.B. stackleak_erase() fills the kernel stack with the poison value,
-	 * which has the register width. That code assumes that the value
-	 * of 'lowest_stack' is aligned on the register width boundary.
-	 *
-	 * That is true for x86 and x86_64 because of the kernel stack
-	 * alignment on these platforms (for details, see 'cc_stack_align' in
-	 * arch/x86/Makefile). Take care of that when you port STACKLEAK to
-	 * new platforms.
-	 */
-	unsigned long sp = (unsigned long)&sp;
+	unsigned long sp = current_stack_pointer;
 
 	/*
 	 * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than
@@ -125,6 +115,8 @@ void __used notrace stackleak_track_stack(void)
 	 */
 	BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH);
 
+	/* 'lowest_stack' should be aligned on the register width boundary */
+	sp = ALIGN(sp, sizeof(unsigned long));
 	if (sp < current->lowest_stack &&
 	    sp >= (unsigned long)task_stack_page(current) +
 						sizeof(unsigned long)) {
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 5f7df50cfe7a..952e46876329 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -33,6 +33,8 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
 		+= -DSTACKLEAK_PLUGIN
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
 		+= -fplugin-arg-stackleak_plugin-track-min-size=$(CONFIG_STACKLEAK_TRACK_MIN_SIZE)
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
+		+= -fplugin-arg-stackleak_plugin-arch=$(SRCARCH)
 ifdef CONFIG_GCC_PLUGIN_STACKLEAK
     DISABLE_STACKLEAK_PLUGIN += -fplugin-arg-stackleak_plugin-disable
 endif
diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c
index cc75eeba0be1..a18b0d4af456 100644
--- a/scripts/gcc-plugins/stackleak_plugin.c
+++ b/scripts/gcc-plugins/stackleak_plugin.c
@@ -20,7 +20,7 @@
  *
  * Debugging:
  *  - use fprintf() to stderr, debug_generic_expr(), debug_gimple_stmt(),
- *     print_rtl() and print_simple_rtl();
+ *     print_rtl_single() and debug_rtx();
  *  - add "-fdump-tree-all -fdump-rtl-all" to the plugin CFLAGS in
  *     Makefile.gcc-plugins to see the verbose dumps of the gcc passes;
  *  - use gcc -E to understand the preprocessing shenanigans;
@@ -32,6 +32,7 @@
 __visible int plugin_is_GPL_compatible;
 
 static int track_frame_size = -1;
+static bool build_for_x86 = false;
 static const char track_function[] = "stackleak_track_stack";
 
 /*
@@ -43,32 +44,31 @@ static GTY(()) tree track_function_decl;
 static struct plugin_info stackleak_plugin_info = {
 	.version = "201707101337",
 	.help = "track-min-size=nn\ttrack stack for functions with a stack frame size >= nn bytes\n"
+		"arch=target_arch\tspecify target build arch\n"
 		"disable\t\tdo not activate the plugin\n"
 };
 
-static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after)
+static void add_stack_tracking_gcall(gimple_stmt_iterator *gsi, bool after)
 {
 	gimple stmt;
-	gcall *stackleak_track_stack;
+	gcall *gimple_call;
 	cgraph_node_ptr node;
 	basic_block bb;
 
-	/* Insert call to void stackleak_track_stack(void) */
+	/* Insert calling stackleak_track_stack() */
 	stmt = gimple_build_call(track_function_decl, 0);
-	stackleak_track_stack = as_a_gcall(stmt);
-	if (after) {
-		gsi_insert_after(gsi, stackleak_track_stack,
-						GSI_CONTINUE_LINKING);
-	} else {
-		gsi_insert_before(gsi, stackleak_track_stack, GSI_SAME_STMT);
-	}
+	gimple_call = as_a_gcall(stmt);
+	if (after)
+		gsi_insert_after(gsi, gimple_call, GSI_CONTINUE_LINKING);
+	else
+		gsi_insert_before(gsi, gimple_call, GSI_SAME_STMT);
 
 	/* Update the cgraph */
-	bb = gimple_bb(stackleak_track_stack);
+	bb = gimple_bb(gimple_call);
 	node = cgraph_get_create_node(track_function_decl);
 	gcc_assert(node);
 	cgraph_create_edge(cgraph_get_node(current_function_decl), node,
-			stackleak_track_stack, bb->count,
+			gimple_call, bb->count,
 			compute_call_stmt_bb_frequency(current_function_decl, bb));
 }
 
@@ -85,6 +85,79 @@ static bool is_alloca(gimple stmt)
 	return false;
 }
 
+static tree get_current_stack_pointer_decl(void)
+{
+	varpool_node_ptr node;
+
+	FOR_EACH_VARIABLE(node) {
+		tree var = NODE_DECL(node);
+		tree name = DECL_NAME(var);
+
+		if (DECL_NAME_LENGTH(var) != sizeof("current_stack_pointer") - 1)
+			continue;
+
+		if (strcmp(IDENTIFIER_POINTER(name), "current_stack_pointer"))
+			continue;
+
+		return var;
+	}
+
+	return NULL_TREE;
+}
+
+static void add_stack_tracking_gasm(gimple_stmt_iterator *gsi, bool after)
+{
+	gasm *asm_call = NULL;
+	tree sp_decl, input;
+	vec<tree, va_gc> *inputs = NULL;
+
+	/* 'no_caller_saved_registers' is currently supported only for x86 */
+	gcc_assert(build_for_x86);
+
+	/*
+	 * Insert calling stackleak_track_stack() in asm:
+	 *   asm volatile("call stackleak_track_stack"
+	 *		  :: "r" (current_stack_pointer))
+	 * Use ASM_CALL_CONSTRAINT trick from arch/x86/include/asm/asm.h.
+	 * This constraint is taken into account during gcc shrink-wrapping
+	 * optimization. It is needed to be sure that stackleak_track_stack()
+	 * call is inserted after the prologue of the containing function,
+	 * when the stack frame is prepared.
+	 */
+	sp_decl = get_current_stack_pointer_decl();
+	if (sp_decl == NULL_TREE) {
+		add_stack_tracking_gcall(gsi, after);
+		return;
+	}
+	input = build_tree_list(NULL_TREE, build_const_char_string(2, "r"));
+	input = chainon(NULL_TREE, build_tree_list(input, sp_decl));
+	vec_safe_push(inputs, input);
+	asm_call = gimple_build_asm_vec("call stackleak_track_stack",
+					inputs, NULL, NULL, NULL);
+	gimple_asm_set_volatile(asm_call, true);
+	if (after)
+		gsi_insert_after(gsi, asm_call, GSI_CONTINUE_LINKING);
+	else
+		gsi_insert_before(gsi, asm_call, GSI_SAME_STMT);
+	update_stmt(asm_call);
+}
+
+static void add_stack_tracking(gimple_stmt_iterator *gsi, bool after)
+{
+	/*
+	 * The 'no_caller_saved_registers' attribute is used for
+	 * stackleak_track_stack(). If the compiler supports this attribute for
+	 * the target arch, we can add calling stackleak_track_stack() in asm.
+	 * That improves performance: we avoid useless operations with the
+	 * caller-saved registers in the functions from which we will remove
+	 * stackleak_track_stack() call during the stackleak_cleanup pass.
+	 */
+	if (lookup_attribute_spec(get_identifier("no_caller_saved_registers")))
+		add_stack_tracking_gasm(gsi, after);
+	else
+		add_stack_tracking_gcall(gsi, after);
+}
+
 /*
  * Work with the GIMPLE representation of the code. Insert the
  * stackleak_track_stack() call after alloca() and into the beginning
@@ -94,7 +167,7 @@ static unsigned int stackleak_instrument_execute(void)
 {
 	basic_block bb, entry_bb;
 	bool prologue_instrumented = false, is_leaf = true;
-	gimple_stmt_iterator gsi;
+	gimple_stmt_iterator gsi = { 0 };
 
 	/*
 	 * ENTRY_BLOCK_PTR is a basic block which represents possible entry
@@ -123,7 +196,7 @@ static unsigned int stackleak_instrument_execute(void)
 				continue;
 
 			/* Insert stackleak_track_stack() call after alloca() */
-			stackleak_add_track_stack(&gsi, true);
+			add_stack_tracking(&gsi, true);
 			if (bb == entry_bb)
 				prologue_instrumented = true;
 		}
@@ -168,7 +241,7 @@ static unsigned int stackleak_instrument_execute(void)
 		bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun));
 	}
 	gsi = gsi_after_labels(bb);
-	stackleak_add_track_stack(&gsi, false);
+	add_stack_tracking(&gsi, false);
 
 	return 0;
 }
@@ -182,21 +255,10 @@ static bool large_stack_frame(void)
 #endif
 }
 
-/*
- * Work with the RTL representation of the code.
- * Remove the unneeded stackleak_track_stack() calls from the functions
- * which don't call alloca() and don't have a large enough stack frame size.
- */
-static unsigned int stackleak_cleanup_execute(void)
+static void remove_stack_tracking_gcall(void)
 {
 	rtx_insn *insn, *next;
 
-	if (cfun->calls_alloca)
-		return 0;
-
-	if (large_stack_frame())
-		return 0;
-
 	/*
 	 * Find stackleak_track_stack() calls. Loop through the chain of insns,
 	 * which is an RTL representation of the code for a function.
@@ -257,6 +319,84 @@ static unsigned int stackleak_cleanup_execute(void)
 		}
 #endif
 	}
+}
+
+static bool remove_stack_tracking_gasm(void)
+{
+	bool removed = false;
+	rtx_insn *insn, *next;
+
+	/* 'no_caller_saved_registers' is currently supported only for x86 */
+	gcc_assert(build_for_x86);
+
+	/*
+	 * Find stackleak_track_stack() asm calls. Loop through the chain of
+	 * insns, which is an RTL representation of the code for a function.
+	 *
+	 * The example of a matching insn:
+	 *  (insn 11 5 12 2 (parallel [ (asm_operands/v
+	 *  ("call stackleak_track_stack") ("") 0
+	 *  [ (reg/v:DI 7 sp [ current_stack_pointer ]) ]
+	 *  [ (asm_input:DI ("r")) ] [])
+	 *  (clobber (reg:CC 17 flags)) ]) -1 (nil))
+	 */
+	for (insn = get_insns(); insn; insn = next) {
+		rtx body;
+
+		next = NEXT_INSN(insn);
+
+		/* Check the expression code of the insn */
+		if (!NONJUMP_INSN_P(insn))
+			continue;
+
+		/*
+		 * Check the expression code of the insn body, which is an RTL
+		 * Expression (RTX) describing the side effect performed by
+		 * that insn.
+		 */
+		body = PATTERN(insn);
+
+		if (GET_CODE(body) != PARALLEL)
+			continue;
+
+		body = XVECEXP(body, 0, 0);
+
+		if (GET_CODE(body) != ASM_OPERANDS)
+			continue;
+
+		if (strcmp(ASM_OPERANDS_TEMPLATE(body),
+						"call stackleak_track_stack")) {
+			continue;
+		}
+
+		delete_insn_and_edges(insn);
+		gcc_assert(!removed);
+		removed = true;
+	}
+
+	return removed;
+}
+
+/*
+ * Work with the RTL representation of the code.
+ * Remove the unneeded stackleak_track_stack() calls from the functions
+ * which don't call alloca() and don't have a large enough stack frame size.
+ */
+static unsigned int stackleak_cleanup_execute(void)
+{
+	bool removed = false;
+
+	if (cfun->calls_alloca)
+		return 0;
+
+	if (large_stack_frame())
+		return 0;
+
+	if (lookup_attribute_spec(get_identifier("no_caller_saved_registers")))
+		removed = remove_stack_tracking_gasm();
+
+	if (!removed)
+		remove_stack_tracking_gcall();
 
 	return 0;
 }
@@ -392,6 +532,15 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
 					plugin_name, argv[i].key, argv[i].value);
 				return 1;
 			}
+		} else if (!strcmp(argv[i].key, "arch")) {
+			if (!argv[i].value) {
+				error(G_("no value supplied for option '-fplugin-arg-%s-%s'"),
+					plugin_name, argv[i].key);
+				return 1;
+			}
+
+			if (!strcmp(argv[i].value, "x86"))
+				build_for_x86 = true;
 		} else {
 			error(G_("unknown option '-fplugin-arg-%s-%s'"),
 					plugin_name, argv[i].key);
-- 
cgit v1.2.3


From 28bc24fc46f9c9f39ddefb424d6072041805b563 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:33 +0200
Subject: vc: separate state

There are two copies of some members of struct vc_data. This is because
we need to save them and restore later. Move these memebers to a
separate structure called vc_state. So now instead of members like:
  vc_x, vc_y and vc_saved_x, vc_saved_y
we have
  state and saved_state (of type: struct vc_state)
containing
  state.x, state.y and saved_state.x, saved_state.y

This change:
* makes clear what is saved & restored
* eases save & restore by using memcpy (see save_cur and restore_cur)

Finally, we document the newly added struct vc_state using kernel-doc.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-1-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/accessibility/braille/braille_console.c |  10 +-
 drivers/staging/speakup/main.c                  |  28 +-
 drivers/tty/vt/vt.c                             | 327 ++++++++++++------------
 drivers/video/console/mdacon.c                  |   2 +-
 drivers/video/console/sticon.c                  |   6 +-
 drivers/video/console/vgacon.c                  |  22 +-
 drivers/video/fbdev/core/bitblit.c              |   6 +-
 drivers/video/fbdev/core/fbcon.c                |   8 +-
 drivers/video/fbdev/core/fbcon_ccw.c            |   4 +-
 drivers/video/fbdev/core/fbcon_cw.c             |   4 +-
 drivers/video/fbdev/core/fbcon_ud.c             |   4 +-
 drivers/video/fbdev/core/tileblit.c             |   4 +-
 include/linux/console_struct.h                  |  54 ++--
 13 files changed, 239 insertions(+), 240 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c
index a8f7c278b691..c2b452af6806 100644
--- a/drivers/accessibility/braille/braille_console.c
+++ b/drivers/accessibility/braille/braille_console.c
@@ -109,16 +109,16 @@ static void braille_write(u16 *buf)
 /* Follow the VC cursor*/
 static void vc_follow_cursor(struct vc_data *vc)
 {
-	vc_x = vc->vc_x - (vc->vc_x % WIDTH);
-	vc_y = vc->vc_y;
-	lastvc_x = vc->vc_x;
-	lastvc_y = vc->vc_y;
+	vc_x = vc->state.x - (vc->state.x % WIDTH);
+	vc_y = vc->state.y;
+	lastvc_x = vc->state.x;
+	lastvc_y = vc->state.y;
 }
 
 /* Maybe the VC cursor moved, if so follow it */
 static void vc_maybe_cursor_moved(struct vc_data *vc)
 {
-	if (vc->vc_x != lastvc_x || vc->vc_y != lastvc_y)
+	if (vc->state.x != lastvc_x || vc->state.y != lastvc_y)
 		vc_follow_cursor(vc);
 }
 
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 02471d932d71..ddfd12afe3b9 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -263,8 +263,8 @@ static unsigned char get_attributes(struct vc_data *vc, u16 *pos)
 
 static void speakup_date(struct vc_data *vc)
 {
-	spk_x = spk_cx = vc->vc_x;
-	spk_y = spk_cy = vc->vc_y;
+	spk_x = spk_cx = vc->state.x;
+	spk_y = spk_cy = vc->state.y;
 	spk_pos = spk_cp = vc->vc_pos;
 	spk_old_attr = spk_attr;
 	spk_attr = get_attributes(vc, (u_short *)spk_pos);
@@ -1551,9 +1551,9 @@ static void do_handle_cursor(struct vc_data *vc, u_char value, char up_flag)
  */
 	is_cursor = value + 1;
 	old_cursor_pos = vc->vc_pos;
-	old_cursor_x = vc->vc_x;
-	old_cursor_y = vc->vc_y;
-	speakup_console[vc->vc_num]->ht.cy = vc->vc_y;
+	old_cursor_x = vc->state.x;
+	old_cursor_y = vc->state.y;
+	speakup_console[vc->vc_num]->ht.cy = vc->state.y;
 	cursor_con = vc->vc_num;
 	if (cursor_track == CT_Highlight)
 		reset_highlight_buffers(vc);
@@ -1574,8 +1574,8 @@ static void update_color_buffer(struct vc_data *vc, const u16 *ic, int len)
 	i = 0;
 	if (speakup_console[vc_num]->ht.highsize[bi] == 0) {
 		speakup_console[vc_num]->ht.rpos[bi] = vc->vc_pos;
-		speakup_console[vc_num]->ht.rx[bi] = vc->vc_x;
-		speakup_console[vc_num]->ht.ry[bi] = vc->vc_y;
+		speakup_console[vc_num]->ht.rx[bi] = vc->state.x;
+		speakup_console[vc_num]->ht.ry[bi] = vc->state.y;
 	}
 	while ((hi < COLOR_BUFFER_SIZE) && (i < len)) {
 		if (ic[i] > 32) {
@@ -1664,9 +1664,9 @@ static int speak_highlight(struct vc_data *vc)
 		return 0;
 	hc = get_highlight_color(vc);
 	if (hc != -1) {
-		d = vc->vc_y - speakup_console[vc_num]->ht.cy;
+		d = vc->state.y - speakup_console[vc_num]->ht.cy;
 		if ((d == 1) || (d == -1))
-			if (speakup_console[vc_num]->ht.ry[hc] != vc->vc_y)
+			if (speakup_console[vc_num]->ht.ry[hc] != vc->state.y)
 				return 0;
 		spk_parked |= 0x01;
 		spk_do_flush();
@@ -1693,8 +1693,8 @@ static void cursor_done(struct timer_list *unused)
 	}
 	speakup_date(vc);
 	if (win_enabled) {
-		if (vc->vc_x >= win_left && vc->vc_x <= win_right &&
-		    vc->vc_y >= win_top && vc->vc_y <= win_bottom) {
+		if (vc->state.x >= win_left && vc->state.x <= win_right &&
+		    vc->state.y >= win_top && vc->state.y <= win_bottom) {
 			spk_keydown = 0;
 			is_cursor = 0;
 			goto out;
@@ -1757,7 +1757,7 @@ static void speakup_con_write(struct vc_data *vc, u16 *str, int len)
 	if (!spin_trylock_irqsave(&speakup_info.spinlock, flags))
 		/* Speakup output, discard */
 		return;
-	if (spk_bell_pos && spk_keydown && (vc->vc_x == spk_bell_pos - 1))
+	if (spk_bell_pos && spk_keydown && (vc->state.x == spk_bell_pos - 1))
 		bleep(3);
 	if ((is_cursor) || (cursor_track == read_all_mode)) {
 		if (cursor_track == CT_Highlight)
@@ -1766,8 +1766,8 @@ static void speakup_con_write(struct vc_data *vc, u16 *str, int len)
 		return;
 	}
 	if (win_enabled) {
-		if (vc->vc_x >= win_left && vc->vc_x <= win_right &&
-		    vc->vc_y >= win_top && vc->vc_y <= win_bottom) {
+		if (vc->state.x >= win_left && vc->state.x <= win_right &&
+		    vc->state.y >= win_top && vc->state.y <= win_bottom) {
 			spin_unlock_irqrestore(&speakup_info.spinlock, flags);
 			return;
 		}
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 48a8199f7845..76f52935e0c8 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -381,7 +381,7 @@ static void vc_uniscr_putc(struct vc_data *vc, char32_t uc)
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
 
 	if (uniscr)
-		uniscr->lines[vc->vc_y][vc->vc_x] = uc;
+		uniscr->lines[vc->state.y][vc->state.x] = uc;
 }
 
 static void vc_uniscr_insert(struct vc_data *vc, unsigned int nr)
@@ -389,8 +389,8 @@ static void vc_uniscr_insert(struct vc_data *vc, unsigned int nr)
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
 
 	if (uniscr) {
-		char32_t *ln = uniscr->lines[vc->vc_y];
-		unsigned int x = vc->vc_x, cols = vc->vc_cols;
+		char32_t *ln = uniscr->lines[vc->state.y];
+		unsigned int x = vc->state.x, cols = vc->vc_cols;
 
 		memmove(&ln[x + nr], &ln[x], (cols - x - nr) * sizeof(*ln));
 		memset32(&ln[x], ' ', nr);
@@ -402,8 +402,8 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr)
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
 
 	if (uniscr) {
-		char32_t *ln = uniscr->lines[vc->vc_y];
-		unsigned int x = vc->vc_x, cols = vc->vc_cols;
+		char32_t *ln = uniscr->lines[vc->state.y];
+		unsigned int x = vc->state.x, cols = vc->vc_cols;
 
 		memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
 		memset32(&ln[cols - nr], ' ', nr);
@@ -416,7 +416,7 @@ static void vc_uniscr_clear_line(struct vc_data *vc, unsigned int x,
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
 
 	if (uniscr) {
-		char32_t *ln = uniscr->lines[vc->vc_y];
+		char32_t *ln = uniscr->lines[vc->state.y];
 
 		memset32(&ln[x], ' ', nr);
 	}
@@ -750,10 +750,11 @@ static u8 build_attr(struct vc_data *vc, u8 _color, u8 _intensity, u8 _blink,
 
 static void update_attr(struct vc_data *vc)
 {
-	vc->vc_attr = build_attr(vc, vc->vc_color, vc->vc_intensity,
-	              vc->vc_blink, vc->vc_underline,
-	              vc->vc_reverse ^ vc->vc_decscnm, vc->vc_italic);
-	vc->vc_video_erase_char = (build_attr(vc, vc->vc_color, 1, vc->vc_blink, 0, vc->vc_decscnm, 0) << 8) | ' ';
+	vc->vc_attr = build_attr(vc, vc->state.color, vc->state.intensity,
+	              vc->state.blink, vc->state.underline,
+	              vc->state.reverse ^ vc->vc_decscnm, vc->state.italic);
+	vc->vc_video_erase_char = ' ' | (build_attr(vc, vc->state.color, 1,
+				vc->state.blink, 0, vc->vc_decscnm, 0) << 8);
 }
 
 /* Note: inverting the screen twice should revert to the original state */
@@ -842,12 +843,12 @@ static void insert_char(struct vc_data *vc, unsigned int nr)
 	unsigned short *p = (unsigned short *) vc->vc_pos;
 
 	vc_uniscr_insert(vc, nr);
-	scr_memmovew(p + nr, p, (vc->vc_cols - vc->vc_x - nr) * 2);
+	scr_memmovew(p + nr, p, (vc->vc_cols - vc->state.x - nr) * 2);
 	scr_memsetw(p, vc->vc_video_erase_char, nr * 2);
 	vc->vc_need_wrap = 0;
 	if (con_should_update(vc))
 		do_update_region(vc, (unsigned long) p,
-			vc->vc_cols - vc->vc_x);
+			vc->vc_cols - vc->state.x);
 }
 
 static void delete_char(struct vc_data *vc, unsigned int nr)
@@ -855,13 +856,13 @@ static void delete_char(struct vc_data *vc, unsigned int nr)
 	unsigned short *p = (unsigned short *) vc->vc_pos;
 
 	vc_uniscr_delete(vc, nr);
-	scr_memcpyw(p, p + nr, (vc->vc_cols - vc->vc_x - nr) * 2);
-	scr_memsetw(p + vc->vc_cols - vc->vc_x - nr, vc->vc_video_erase_char,
+	scr_memcpyw(p, p + nr, (vc->vc_cols - vc->state.x - nr) * 2);
+	scr_memsetw(p + vc->vc_cols - vc->state.x - nr, vc->vc_video_erase_char,
 			nr * 2);
 	vc->vc_need_wrap = 0;
 	if (con_should_update(vc))
 		do_update_region(vc, (unsigned long) p,
-			vc->vc_cols - vc->vc_x);
+			vc->vc_cols - vc->state.x);
 }
 
 static int softcursor_original = -1;
@@ -880,7 +881,7 @@ static void add_softcursor(struct vc_data *vc)
 	if ((type & 0x40) && ((i & 0x700) == ((i & 0x7000) >> 4))) i ^= 0x0700;
 	scr_writew(i, (u16 *) vc->vc_pos);
 	if (con_should_update(vc))
-		vc->vc_sw->con_putc(vc, i, vc->vc_y, vc->vc_x);
+		vc->vc_sw->con_putc(vc, i, vc->state.y, vc->state.x);
 }
 
 static void hide_softcursor(struct vc_data *vc)
@@ -889,7 +890,7 @@ static void hide_softcursor(struct vc_data *vc)
 		scr_writew(softcursor_original, (u16 *)vc->vc_pos);
 		if (con_should_update(vc))
 			vc->vc_sw->con_putc(vc, softcursor_original,
-					vc->vc_y, vc->vc_x);
+					vc->state.y, vc->state.x);
 		softcursor_original = -1;
 	}
 }
@@ -927,7 +928,8 @@ static void set_origin(struct vc_data *vc)
 		vc->vc_origin = (unsigned long)vc->vc_screenbuf;
 	vc->vc_visible_origin = vc->vc_origin;
 	vc->vc_scr_end = vc->vc_origin + vc->vc_screenbuf_size;
-	vc->vc_pos = vc->vc_origin + vc->vc_size_row * vc->vc_y + 2 * vc->vc_x;
+	vc->vc_pos = vc->vc_origin + vc->vc_size_row * vc->state.y +
+		2 * vc->state.x;
 }
 
 static void save_screen(struct vc_data *vc)
@@ -1250,8 +1252,8 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	new_origin = (long) newscreen;
 	new_scr_end = new_origin + new_screen_size;
 
-	if (vc->vc_y > new_rows) {
-		if (old_rows - vc->vc_y < new_rows) {
+	if (vc->state.y > new_rows) {
+		if (old_rows - vc->state.y < new_rows) {
 			/*
 			 * Cursor near the bottom, copy contents from the
 			 * bottom of buffer
@@ -1262,7 +1264,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 			 * Cursor is in no man's land, copy 1/2 screenful
 			 * from the top and bottom of cursor position
 			 */
-			first_copied_row = (vc->vc_y - new_rows/2);
+			first_copied_row = (vc->state.y - new_rows/2);
 		}
 		old_origin += first_copied_row * old_row_size;
 	} else
@@ -1296,7 +1298,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	/* do part of a reset_terminal() */
 	vc->vc_top = 0;
 	vc->vc_bottom = vc->vc_rows;
-	gotoxy(vc, vc->vc_x, vc->vc_y);
+	gotoxy(vc, vc->state.x, vc->state.y);
 	save_cur(vc);
 
 	if (tty) {
@@ -1431,12 +1433,12 @@ static void gotoxy(struct vc_data *vc, int new_x, int new_y)
 	int min_y, max_y;
 
 	if (new_x < 0)
-		vc->vc_x = 0;
+		vc->state.x = 0;
 	else {
 		if (new_x >= vc->vc_cols)
-			vc->vc_x = vc->vc_cols - 1;
+			vc->state.x = vc->vc_cols - 1;
 		else
-			vc->vc_x = new_x;
+			vc->state.x = new_x;
 	}
 
  	if (vc->vc_decom) {
@@ -1447,12 +1449,13 @@ static void gotoxy(struct vc_data *vc, int new_x, int new_y)
 		max_y = vc->vc_rows;
 	}
 	if (new_y < min_y)
-		vc->vc_y = min_y;
+		vc->state.y = min_y;
 	else if (new_y >= max_y)
-		vc->vc_y = max_y - 1;
+		vc->state.y = max_y - 1;
 	else
-		vc->vc_y = new_y;
-	vc->vc_pos = vc->vc_origin + vc->vc_y * vc->vc_size_row + (vc->vc_x<<1);
+		vc->state.y = new_y;
+	vc->vc_pos = vc->vc_origin + vc->state.y * vc->vc_size_row +
+		(vc->state.x << 1);
 	vc->vc_need_wrap = 0;
 }
 
@@ -1479,10 +1482,10 @@ static void lf(struct vc_data *vc)
     	/* don't scroll if above bottom of scrolling region, or
 	 * if below scrolling region
 	 */
-    	if (vc->vc_y + 1 == vc->vc_bottom)
+	if (vc->state.y + 1 == vc->vc_bottom)
 		con_scroll(vc, vc->vc_top, vc->vc_bottom, SM_UP, 1);
-	else if (vc->vc_y < vc->vc_rows - 1) {
-	    	vc->vc_y++;
+	else if (vc->state.y < vc->vc_rows - 1) {
+		vc->state.y++;
 		vc->vc_pos += vc->vc_size_row;
 	}
 	vc->vc_need_wrap = 0;
@@ -1494,10 +1497,10 @@ static void ri(struct vc_data *vc)
     	/* don't scroll if below top of scrolling region, or
 	 * if above scrolling region
 	 */
-	if (vc->vc_y == vc->vc_top)
+	if (vc->state.y == vc->vc_top)
 		con_scroll(vc, vc->vc_top, vc->vc_bottom, SM_DOWN, 1);
-	else if (vc->vc_y > 0) {
-		vc->vc_y--;
+	else if (vc->state.y > 0) {
+		vc->state.y--;
 		vc->vc_pos -= vc->vc_size_row;
 	}
 	vc->vc_need_wrap = 0;
@@ -1505,16 +1508,16 @@ static void ri(struct vc_data *vc)
 
 static inline void cr(struct vc_data *vc)
 {
-	vc->vc_pos -= vc->vc_x << 1;
-	vc->vc_need_wrap = vc->vc_x = 0;
+	vc->vc_pos -= vc->state.x << 1;
+	vc->vc_need_wrap = vc->state.x = 0;
 	notify_write(vc, '\r');
 }
 
 static inline void bs(struct vc_data *vc)
 {
-	if (vc->vc_x) {
+	if (vc->state.x) {
 		vc->vc_pos -= 2;
-		vc->vc_x--;
+		vc->state.x--;
 		vc->vc_need_wrap = 0;
 		notify_write(vc, '\b');
 	}
@@ -1532,16 +1535,16 @@ static void csi_J(struct vc_data *vc, int vpar)
 
 	switch (vpar) {
 		case 0:	/* erase from cursor to end of display */
-			vc_uniscr_clear_line(vc, vc->vc_x,
-					     vc->vc_cols - vc->vc_x);
-			vc_uniscr_clear_lines(vc, vc->vc_y + 1,
-					      vc->vc_rows - vc->vc_y - 1);
+			vc_uniscr_clear_line(vc, vc->state.x,
+					     vc->vc_cols - vc->state.x);
+			vc_uniscr_clear_lines(vc, vc->state.y + 1,
+					      vc->vc_rows - vc->state.y - 1);
 			count = (vc->vc_scr_end - vc->vc_pos) >> 1;
 			start = (unsigned short *)vc->vc_pos;
 			break;
 		case 1:	/* erase from start to cursor */
-			vc_uniscr_clear_line(vc, 0, vc->vc_x + 1);
-			vc_uniscr_clear_lines(vc, 0, vc->vc_y);
+			vc_uniscr_clear_line(vc, 0, vc->state.x + 1);
+			vc_uniscr_clear_lines(vc, 0, vc->state.y);
 			count = ((vc->vc_pos - vc->vc_origin) >> 1) + 1;
 			start = (unsigned short *)vc->vc_origin;
 			break;
@@ -1571,20 +1574,20 @@ static void csi_K(struct vc_data *vc, int vpar)
 	switch (vpar) {
 		case 0:	/* erase from cursor to end of line */
 			offset = 0;
-			count = vc->vc_cols - vc->vc_x;
+			count = vc->vc_cols - vc->state.x;
 			break;
 		case 1:	/* erase from start of line to cursor */
-			offset = -vc->vc_x;
-			count = vc->vc_x + 1;
+			offset = -vc->state.x;
+			count = vc->state.x + 1;
 			break;
 		case 2: /* erase whole line */
-			offset = -vc->vc_x;
+			offset = -vc->state.x;
 			count = vc->vc_cols;
 			break;
 		default:
 			return;
 	}
-	vc_uniscr_clear_line(vc, vc->vc_x + offset, count);
+	vc_uniscr_clear_line(vc, vc->state.x + offset, count);
 	scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count);
 	vc->vc_need_wrap = 0;
 	if (con_should_update(vc))
@@ -1597,23 +1600,23 @@ static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar posi
 
 	if (!vpar)
 		vpar++;
-	count = (vpar > vc->vc_cols - vc->vc_x) ? (vc->vc_cols - vc->vc_x) : vpar;
+	count = (vpar > vc->vc_cols - vc->state.x) ? (vc->vc_cols - vc->state.x) : vpar;
 
-	vc_uniscr_clear_line(vc, vc->vc_x, count);
+	vc_uniscr_clear_line(vc, vc->state.x, count);
 	scr_memsetw((unsigned short *)vc->vc_pos, vc->vc_video_erase_char, 2 * count);
 	if (con_should_update(vc))
-		vc->vc_sw->con_clear(vc, vc->vc_y, vc->vc_x, 1, count);
+		vc->vc_sw->con_clear(vc, vc->state.y, vc->state.x, 1, count);
 	vc->vc_need_wrap = 0;
 }
 
 static void default_attr(struct vc_data *vc)
 {
-	vc->vc_intensity = 1;
-	vc->vc_italic = 0;
-	vc->vc_underline = 0;
-	vc->vc_reverse = 0;
-	vc->vc_blink = 0;
-	vc->vc_color = vc->vc_def_color;
+	vc->state.intensity = 1;
+	vc->state.italic = 0;
+	vc->state.underline = 0;
+	vc->state.reverse = 0;
+	vc->state.blink = 0;
+	vc->state.color = vc->vc_def_color;
 }
 
 struct rgb { u8 r; u8 g; u8 b; };
@@ -1649,19 +1652,19 @@ static void rgb_foreground(struct vc_data *vc, const struct rgb *c)
 
 	if (hue == 7 && max <= 0x55) {
 		hue = 0;
-		vc->vc_intensity = 2;
+		vc->state.intensity = 2;
 	} else if (max > 0xaa)
-		vc->vc_intensity = 2;
+		vc->state.intensity = 2;
 	else
-		vc->vc_intensity = 1;
+		vc->state.intensity = 1;
 
-	vc->vc_color = (vc->vc_color & 0xf0) | hue;
+	vc->state.color = (vc->state.color & 0xf0) | hue;
 }
 
 static void rgb_background(struct vc_data *vc, const struct rgb *c)
 {
 	/* For backgrounds, err on the dark side. */
-	vc->vc_color = (vc->vc_color & 0x0f)
+	vc->state.color = (vc->state.color & 0x0f)
 		| (c->r&0x80) >> 1 | (c->g&0x80) >> 2 | (c->b&0x80) >> 3;
 }
 
@@ -1712,13 +1715,13 @@ static void csi_m(struct vc_data *vc)
 			default_attr(vc);
 			break;
 		case 1:
-			vc->vc_intensity = 2;
+			vc->state.intensity = 2;
 			break;
 		case 2:
-			vc->vc_intensity = 0;
+			vc->state.intensity = 0;
 			break;
 		case 3:
-			vc->vc_italic = 1;
+			vc->state.italic = 1;
 			break;
 		case 21:
 			/*
@@ -1726,21 +1729,21 @@ static void csi_m(struct vc_data *vc)
 			 * convert it to a single underline.
 			 */
 		case 4:
-			vc->vc_underline = 1;
+			vc->state.underline = 1;
 			break;
 		case 5:
-			vc->vc_blink = 1;
+			vc->state.blink = 1;
 			break;
 		case 7:
-			vc->vc_reverse = 1;
+			vc->state.reverse = 1;
 			break;
 		case 10: /* ANSI X3.64-1979 (SCO-ish?)
 			  * Select primary font, don't display control chars if
 			  * defined, don't set bit 8 on output.
 			  */
-			vc->vc_translate = set_translate(vc->vc_charset == 0
-					? vc->vc_G0_charset
-					: vc->vc_G1_charset, vc);
+			vc->vc_translate = set_translate(vc->state.charset == 0
+					? vc->state.G0_charset
+					: vc->state.G1_charset, vc);
 			vc->vc_disp_ctrl = 0;
 			vc->vc_toggle_meta = 0;
 			break;
@@ -1761,19 +1764,19 @@ static void csi_m(struct vc_data *vc)
 			vc->vc_toggle_meta = 1;
 			break;
 		case 22:
-			vc->vc_intensity = 1;
+			vc->state.intensity = 1;
 			break;
 		case 23:
-			vc->vc_italic = 0;
+			vc->state.italic = 0;
 			break;
 		case 24:
-			vc->vc_underline = 0;
+			vc->state.underline = 0;
 			break;
 		case 25:
-			vc->vc_blink = 0;
+			vc->state.blink = 0;
 			break;
 		case 27:
-			vc->vc_reverse = 0;
+			vc->state.reverse = 0;
 			break;
 		case 38:
 			i = vc_t416_color(vc, i, rgb_foreground);
@@ -1782,25 +1785,25 @@ static void csi_m(struct vc_data *vc)
 			i = vc_t416_color(vc, i, rgb_background);
 			break;
 		case 39:
-			vc->vc_color = (vc->vc_def_color & 0x0f) |
-				(vc->vc_color & 0xf0);
+			vc->state.color = (vc->vc_def_color & 0x0f) |
+				(vc->state.color & 0xf0);
 			break;
 		case 49:
-			vc->vc_color = (vc->vc_def_color & 0xf0) |
-				(vc->vc_color & 0x0f);
+			vc->state.color = (vc->vc_def_color & 0xf0) |
+				(vc->state.color & 0x0f);
 			break;
 		default:
 			if (vc->vc_par[i] >= 90 && vc->vc_par[i] <= 107) {
 				if (vc->vc_par[i] < 100)
-					vc->vc_intensity = 2;
+					vc->state.intensity = 2;
 				vc->vc_par[i] -= 60;
 			}
 			if (vc->vc_par[i] >= 30 && vc->vc_par[i] <= 37)
-				vc->vc_color = color_table[vc->vc_par[i] - 30]
-					| (vc->vc_color & 0xf0);
+				vc->state.color = color_table[vc->vc_par[i] - 30]
+					| (vc->state.color & 0xf0);
 			else if (vc->vc_par[i] >= 40 && vc->vc_par[i] <= 47)
-				vc->vc_color = (color_table[vc->vc_par[i] - 40] << 4)
-					| (vc->vc_color & 0x0f);
+				vc->state.color = (color_table[vc->vc_par[i] - 40] << 4)
+					| (vc->state.color & 0x0f);
 			break;
 		}
 	update_attr(vc);
@@ -1819,7 +1822,7 @@ static void cursor_report(struct vc_data *vc, struct tty_struct *tty)
 {
 	char buf[40];
 
-	sprintf(buf, "\033[%d;%dR", vc->vc_y + (vc->vc_decom ? vc->vc_top + 1 : 1), vc->vc_x + 1);
+	sprintf(buf, "\033[%d;%dR", vc->state.y + (vc->vc_decom ? vc->vc_top + 1 : 1), vc->state.x + 1);
 	respond_string(buf, tty->port);
 }
 
@@ -1924,14 +1927,14 @@ static void setterm_command(struct vc_data *vc)
 	case 1:	/* set color for underline mode */
 		if (vc->vc_can_do_color && vc->vc_par[1] < 16) {
 			vc->vc_ulcolor = color_table[vc->vc_par[1]];
-			if (vc->vc_underline)
+			if (vc->state.underline)
 				update_attr(vc);
 		}
 		break;
 	case 2:	/* set color for half intensity mode */
 		if (vc->vc_can_do_color && vc->vc_par[1] < 16) {
 			vc->vc_halfcolor = color_table[vc->vc_par[1]];
-			if (vc->vc_intensity == 0)
+			if (vc->state.intensity == 0)
 				update_attr(vc);
 		}
 		break;
@@ -1985,8 +1988,8 @@ static void setterm_command(struct vc_data *vc)
 /* console_lock is held */
 static void csi_at(struct vc_data *vc, unsigned int nr)
 {
-	if (nr > vc->vc_cols - vc->vc_x)
-		nr = vc->vc_cols - vc->vc_x;
+	if (nr > vc->vc_cols - vc->state.x)
+		nr = vc->vc_cols - vc->state.x;
 	else if (!nr)
 		nr = 1;
 	insert_char(vc, nr);
@@ -1995,19 +1998,19 @@ static void csi_at(struct vc_data *vc, unsigned int nr)
 /* console_lock is held */
 static void csi_L(struct vc_data *vc, unsigned int nr)
 {
-	if (nr > vc->vc_rows - vc->vc_y)
-		nr = vc->vc_rows - vc->vc_y;
+	if (nr > vc->vc_rows - vc->state.y)
+		nr = vc->vc_rows - vc->state.y;
 	else if (!nr)
 		nr = 1;
-	con_scroll(vc, vc->vc_y, vc->vc_bottom, SM_DOWN, nr);
+	con_scroll(vc, vc->state.y, vc->vc_bottom, SM_DOWN, nr);
 	vc->vc_need_wrap = 0;
 }
 
 /* console_lock is held */
 static void csi_P(struct vc_data *vc, unsigned int nr)
 {
-	if (nr > vc->vc_cols - vc->vc_x)
-		nr = vc->vc_cols - vc->vc_x;
+	if (nr > vc->vc_cols - vc->state.x)
+		nr = vc->vc_cols - vc->state.x;
 	else if (!nr)
 		nr = 1;
 	delete_char(vc, nr);
@@ -2016,44 +2019,28 @@ static void csi_P(struct vc_data *vc, unsigned int nr)
 /* console_lock is held */
 static void csi_M(struct vc_data *vc, unsigned int nr)
 {
-	if (nr > vc->vc_rows - vc->vc_y)
-		nr = vc->vc_rows - vc->vc_y;
+	if (nr > vc->vc_rows - vc->state.y)
+		nr = vc->vc_rows - vc->state.y;
 	else if (!nr)
 		nr=1;
-	con_scroll(vc, vc->vc_y, vc->vc_bottom, SM_UP, nr);
+	con_scroll(vc, vc->state.y, vc->vc_bottom, SM_UP, nr);
 	vc->vc_need_wrap = 0;
 }
 
 /* console_lock is held (except via vc_init->reset_terminal */
 static void save_cur(struct vc_data *vc)
 {
-	vc->vc_saved_x		= vc->vc_x;
-	vc->vc_saved_y		= vc->vc_y;
-	vc->vc_s_intensity	= vc->vc_intensity;
-	vc->vc_s_italic         = vc->vc_italic;
-	vc->vc_s_underline	= vc->vc_underline;
-	vc->vc_s_blink		= vc->vc_blink;
-	vc->vc_s_reverse	= vc->vc_reverse;
-	vc->vc_s_charset	= vc->vc_charset;
-	vc->vc_s_color		= vc->vc_color;
-	vc->vc_saved_G0		= vc->vc_G0_charset;
-	vc->vc_saved_G1		= vc->vc_G1_charset;
+	memcpy(&vc->saved_state, &vc->state, sizeof(vc->state));
 }
 
 /* console_lock is held */
 static void restore_cur(struct vc_data *vc)
 {
-	gotoxy(vc, vc->vc_saved_x, vc->vc_saved_y);
-	vc->vc_intensity	= vc->vc_s_intensity;
-	vc->vc_italic		= vc->vc_s_italic;
-	vc->vc_underline	= vc->vc_s_underline;
-	vc->vc_blink		= vc->vc_s_blink;
-	vc->vc_reverse		= vc->vc_s_reverse;
-	vc->vc_charset		= vc->vc_s_charset;
-	vc->vc_color		= vc->vc_s_color;
-	vc->vc_G0_charset	= vc->vc_saved_G0;
-	vc->vc_G1_charset	= vc->vc_saved_G1;
-	vc->vc_translate	= set_translate(vc->vc_charset ? vc->vc_G1_charset : vc->vc_G0_charset, vc);
+	memcpy(&vc->state, &vc->saved_state, sizeof(vc->state));
+
+	gotoxy(vc, vc->state.x, vc->state.y);
+	vc->vc_translate = set_translate(vc->state.charset ? vc->state.G1_charset :
+			vc->state.G0_charset, vc);
 	update_attr(vc);
 	vc->vc_need_wrap = 0;
 }
@@ -2070,9 +2057,9 @@ static void reset_terminal(struct vc_data *vc, int do_clear)
 	vc->vc_state		= ESnormal;
 	vc->vc_priv		= EPecma;
 	vc->vc_translate	= set_translate(LAT1_MAP, vc);
-	vc->vc_G0_charset	= LAT1_MAP;
-	vc->vc_G1_charset	= GRAF_MAP;
-	vc->vc_charset		= 0;
+	vc->state.G0_charset	= LAT1_MAP;
+	vc->state.G1_charset	= GRAF_MAP;
+	vc->state.charset	= 0;
 	vc->vc_need_wrap	= 0;
 	vc->vc_report_mouse	= 0;
 	vc->vc_utf              = default_utf8;
@@ -2136,13 +2123,13 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		bs(vc);
 		return;
 	case 9:
-		vc->vc_pos -= (vc->vc_x << 1);
-		while (vc->vc_x < vc->vc_cols - 1) {
-			vc->vc_x++;
-			if (vc->vc_tab_stop[7 & (vc->vc_x >> 5)] & (1 << (vc->vc_x & 31)))
+		vc->vc_pos -= (vc->state.x << 1);
+		while (vc->state.x < vc->vc_cols - 1) {
+			vc->state.x++;
+			if (vc->vc_tab_stop[7 & (vc->state.x >> 5)] & (1 << (vc->state.x & 31)))
 				break;
 		}
-		vc->vc_pos += (vc->vc_x << 1);
+		vc->vc_pos += (vc->state.x << 1);
 		notify_write(vc, '\t');
 		return;
 	case 10: case 11: case 12:
@@ -2154,13 +2141,13 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		cr(vc);
 		return;
 	case 14:
-		vc->vc_charset = 1;
-		vc->vc_translate = set_translate(vc->vc_G1_charset, vc);
+		vc->state.charset = 1;
+		vc->vc_translate = set_translate(vc->state.G1_charset, vc);
 		vc->vc_disp_ctrl = 1;
 		return;
 	case 15:
-		vc->vc_charset = 0;
-		vc->vc_translate = set_translate(vc->vc_G0_charset, vc);
+		vc->state.charset = 0;
+		vc->vc_translate = set_translate(vc->state.G0_charset, vc);
 		vc->vc_disp_ctrl = 0;
 		return;
 	case 24: case 26:
@@ -2200,7 +2187,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 			lf(vc);
 			return;
 		case 'H':
-			vc->vc_tab_stop[7 & (vc->vc_x >> 5)] |= (1 << (vc->vc_x & 31));
+			vc->vc_tab_stop[7 & (vc->state.x >> 5)] |= (1 << (vc->state.x & 31));
 			return;
 		case 'Z':
 			respond_ID(tty);
@@ -2347,42 +2334,42 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		case 'G': case '`':
 			if (vc->vc_par[0])
 				vc->vc_par[0]--;
-			gotoxy(vc, vc->vc_par[0], vc->vc_y);
+			gotoxy(vc, vc->vc_par[0], vc->state.y);
 			return;
 		case 'A':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, vc->vc_x, vc->vc_y - vc->vc_par[0]);
+			gotoxy(vc, vc->state.x, vc->state.y - vc->vc_par[0]);
 			return;
 		case 'B': case 'e':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, vc->vc_x, vc->vc_y + vc->vc_par[0]);
+			gotoxy(vc, vc->state.x, vc->state.y + vc->vc_par[0]);
 			return;
 		case 'C': case 'a':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, vc->vc_x + vc->vc_par[0], vc->vc_y);
+			gotoxy(vc, vc->state.x + vc->vc_par[0], vc->state.y);
 			return;
 		case 'D':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, vc->vc_x - vc->vc_par[0], vc->vc_y);
+			gotoxy(vc, vc->state.x - vc->vc_par[0], vc->state.y);
 			return;
 		case 'E':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, 0, vc->vc_y + vc->vc_par[0]);
+			gotoxy(vc, 0, vc->state.y + vc->vc_par[0]);
 			return;
 		case 'F':
 			if (!vc->vc_par[0])
 				vc->vc_par[0]++;
-			gotoxy(vc, 0, vc->vc_y - vc->vc_par[0]);
+			gotoxy(vc, 0, vc->state.y - vc->vc_par[0]);
 			return;
 		case 'd':
 			if (vc->vc_par[0])
 				vc->vc_par[0]--;
-			gotoxay(vc, vc->vc_x ,vc->vc_par[0]);
+			gotoxay(vc, vc->state.x ,vc->vc_par[0]);
 			return;
 		case 'H': case 'f':
 			if (vc->vc_par[0])
@@ -2412,7 +2399,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 			return;
 		case 'g':
 			if (!vc->vc_par[0])
-				vc->vc_tab_stop[7 & (vc->vc_x >> 5)] &= ~(1 << (vc->vc_x & 31));
+				vc->vc_tab_stop[7 & (vc->state.x >> 5)] &= ~(1 << (vc->state.x & 31));
 			else if (vc->vc_par[0] == 3) {
 				vc->vc_tab_stop[0] =
 					vc->vc_tab_stop[1] =
@@ -2497,28 +2484,28 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		return;
 	case ESsetG0:
 		if (c == '0')
-			vc->vc_G0_charset = GRAF_MAP;
+			vc->state.G0_charset = GRAF_MAP;
 		else if (c == 'B')
-			vc->vc_G0_charset = LAT1_MAP;
+			vc->state.G0_charset = LAT1_MAP;
 		else if (c == 'U')
-			vc->vc_G0_charset = IBMPC_MAP;
+			vc->state.G0_charset = IBMPC_MAP;
 		else if (c == 'K')
-			vc->vc_G0_charset = USER_MAP;
-		if (vc->vc_charset == 0)
-			vc->vc_translate = set_translate(vc->vc_G0_charset, vc);
+			vc->state.G0_charset = USER_MAP;
+		if (vc->state.charset == 0)
+			vc->vc_translate = set_translate(vc->state.G0_charset, vc);
 		vc->vc_state = ESnormal;
 		return;
 	case ESsetG1:
 		if (c == '0')
-			vc->vc_G1_charset = GRAF_MAP;
+			vc->state.G1_charset = GRAF_MAP;
 		else if (c == 'B')
-			vc->vc_G1_charset = LAT1_MAP;
+			vc->state.G1_charset = LAT1_MAP;
 		else if (c == 'U')
-			vc->vc_G1_charset = IBMPC_MAP;
+			vc->state.G1_charset = IBMPC_MAP;
 		else if (c == 'K')
-			vc->vc_G1_charset = USER_MAP;
-		if (vc->vc_charset == 1)
-			vc->vc_translate = set_translate(vc->vc_G1_charset, vc);
+			vc->state.G1_charset = USER_MAP;
+		if (vc->state.charset == 1)
+			vc->vc_translate = set_translate(vc->state.G1_charset, vc);
 		vc->vc_state = ESnormal;
 		return;
 	case ESosc:
@@ -2572,7 +2559,7 @@ static void con_flush(struct vc_data *vc, unsigned long draw_from,
 		return;
 
 	vc->vc_sw->con_putcs(vc, (u16 *)draw_from,
-			(u16 *)draw_to - (u16 *)draw_from, vc->vc_y, *draw_x);
+			(u16 *)draw_to - (u16 *)draw_from, vc->state.y, *draw_x);
 	*draw_x = -1;
 }
 
@@ -2788,14 +2775,14 @@ rescan_last_byte:
 					     (vc_attr << 8) + tc,
 					   (u16 *) vc->vc_pos);
 				if (con_should_update(vc) && draw_x < 0) {
-					draw_x = vc->vc_x;
+					draw_x = vc->state.x;
 					draw_from = vc->vc_pos;
 				}
-				if (vc->vc_x == vc->vc_cols - 1) {
+				if (vc->state.x == vc->vc_cols - 1) {
 					vc->vc_need_wrap = vc->vc_decawm;
 					draw_to = vc->vc_pos + 2;
 				} else {
-					vc->vc_x++;
+					vc->state.x++;
 					draw_to = (vc->vc_pos += 2);
 				}
 
@@ -2972,25 +2959,25 @@ static void vt_console_print(struct console *co, const char *b, unsigned count)
 		hide_cursor(vc);
 
 	start = (ushort *)vc->vc_pos;
-	start_x = vc->vc_x;
+	start_x = vc->state.x;
 	cnt = 0;
 	while (count--) {
 		c = *b++;
 		if (c == 10 || c == 13 || c == 8 || vc->vc_need_wrap) {
 			if (cnt && con_is_visible(vc))
-				vc->vc_sw->con_putcs(vc, start, cnt, vc->vc_y, start_x);
+				vc->vc_sw->con_putcs(vc, start, cnt, vc->state.y, start_x);
 			cnt = 0;
 			if (c == 8) {		/* backspace */
 				bs(vc);
 				start = (ushort *)vc->vc_pos;
-				start_x = vc->vc_x;
+				start_x = vc->state.x;
 				continue;
 			}
 			if (c != 13)
 				lf(vc);
 			cr(vc);
 			start = (ushort *)vc->vc_pos;
-			start_x = vc->vc_x;
+			start_x = vc->state.x;
 			if (c == 10 || c == 13)
 				continue;
 		}
@@ -2998,15 +2985,15 @@ static void vt_console_print(struct console *co, const char *b, unsigned count)
 		scr_writew((vc->vc_attr << 8) + c, (unsigned short *)vc->vc_pos);
 		notify_write(vc, c);
 		cnt++;
-		if (vc->vc_x == vc->vc_cols - 1) {
+		if (vc->state.x == vc->vc_cols - 1) {
 			vc->vc_need_wrap = 1;
 		} else {
 			vc->vc_pos += 2;
-			vc->vc_x++;
+			vc->state.x++;
 		}
 	}
 	if (cnt && con_is_visible(vc))
-		vc->vc_sw->con_putcs(vc, start, cnt, vc->vc_y, start_x);
+		vc->vc_sw->con_putcs(vc, start, cnt, vc->state.y, start_x);
 	set_cursor(vc);
 	notify_update(vc);
 
@@ -3401,7 +3388,7 @@ static int __init con_init(void)
 	master_display_fg = vc = vc_cons[currcons].d;
 	set_origin(vc);
 	save_screen(vc);
-	gotoxy(vc, vc->vc_x, vc->vc_y);
+	gotoxy(vc, vc->state.x, vc->state.y);
 	csi_J(vc, 0);
 	update_screen(vc);
 	pr_info("Console: %s %s %dx%d\n",
@@ -4680,8 +4667,8 @@ EXPORT_SYMBOL_GPL(screen_pos);
 void getconsxy(struct vc_data *vc, unsigned char *p)
 {
 	/* clamp values if they don't fit */
-	p[0] = min(vc->vc_x, 0xFFu);
-	p[1] = min(vc->vc_y, 0xFFu);
+	p[0] = min(vc->state.x, 0xFFu);
+	p[1] = min(vc->state.y, 0xFFu);
 }
 
 void putconsxy(struct vc_data *vc, unsigned char *p)
diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c
index d0d427a2f1a3..d64c5ce84125 100644
--- a/drivers/video/console/mdacon.c
+++ b/drivers/video/console/mdacon.c
@@ -488,7 +488,7 @@ static void mdacon_cursor(struct vc_data *c, int mode)
 		return;
 	}
 
-	mda_set_cursor(c->vc_y*mda_num_columns*2 + c->vc_x*2);
+	mda_set_cursor(c->state.y * mda_num_columns * 2 + c->state.x * 2);
 
 	switch (c->vc_cursor_type & 0x0f) {
 
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index 79c9bd8d3025..90083eb80515 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -132,10 +132,10 @@ static void sticon_cursor(struct vc_data *conp, int mode)
 {
     unsigned short car1;
 
-    car1 = conp->vc_screenbuf[conp->vc_x + conp->vc_y * conp->vc_cols];
+    car1 = conp->vc_screenbuf[conp->state.x + conp->state.y * conp->vc_cols];
     switch (mode) {
     case CM_ERASE:
-	sti_putc(sticon_sti, car1, conp->vc_y, conp->vc_x);
+	sti_putc(sticon_sti, car1, conp->state.y, conp->state.x);
 	break;
     case CM_MOVE:
     case CM_DRAW:
@@ -146,7 +146,7 @@ static void sticon_cursor(struct vc_data *conp, int mode)
 	case CUR_TWO_THIRDS:
 	case CUR_BLOCK:
 	    sti_putc(sticon_sti, (car1 & 255) + (0 << 8) + (7 << 11),
-		     conp->vc_y, conp->vc_x);
+		     conp->state.y, conp->state.x);
 	    break;
 	}
 	break;
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 998b0de1812f..d073fa167e87 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -718,9 +718,9 @@ static void vgacon_cursor(struct vc_data *c, int mode)
 	case CM_ERASE:
 		write_vga(14, (c->vc_pos - vga_vram_base) / 2);
 	        if (vga_video_type >= VIDEO_TYPE_VGAC)
-			vgacon_set_cursor_size(c->vc_x, 31, 30);
+			vgacon_set_cursor_size(c->state.x, 31, 30);
 		else
-			vgacon_set_cursor_size(c->vc_x, 31, 31);
+			vgacon_set_cursor_size(c->state.x, 31, 31);
 		break;
 
 	case CM_MOVE:
@@ -728,7 +728,7 @@ static void vgacon_cursor(struct vc_data *c, int mode)
 		write_vga(14, (c->vc_pos - vga_vram_base) / 2);
 		switch (c->vc_cursor_type & 0x0f) {
 		case CUR_UNDERLINE:
-			vgacon_set_cursor_size(c->vc_x,
+			vgacon_set_cursor_size(c->state.x,
 					       c->vc_font.height -
 					       (c->vc_font.height <
 						10 ? 2 : 3),
@@ -737,21 +737,21 @@ static void vgacon_cursor(struct vc_data *c, int mode)
 						10 ? 1 : 2));
 			break;
 		case CUR_TWO_THIRDS:
-			vgacon_set_cursor_size(c->vc_x,
+			vgacon_set_cursor_size(c->state.x,
 					       c->vc_font.height / 3,
 					       c->vc_font.height -
 					       (c->vc_font.height <
 						10 ? 1 : 2));
 			break;
 		case CUR_LOWER_THIRD:
-			vgacon_set_cursor_size(c->vc_x,
+			vgacon_set_cursor_size(c->state.x,
 					       (c->vc_font.height * 2) / 3,
 					       c->vc_font.height -
 					       (c->vc_font.height <
 						10 ? 1 : 2));
 			break;
 		case CUR_LOWER_HALF:
-			vgacon_set_cursor_size(c->vc_x,
+			vgacon_set_cursor_size(c->state.x,
 					       c->vc_font.height / 2,
 					       c->vc_font.height -
 					       (c->vc_font.height <
@@ -759,12 +759,12 @@ static void vgacon_cursor(struct vc_data *c, int mode)
 			break;
 		case CUR_NONE:
 			if (vga_video_type >= VIDEO_TYPE_VGAC)
-				vgacon_set_cursor_size(c->vc_x, 31, 30);
+				vgacon_set_cursor_size(c->state.x, 31, 30);
 			else
-				vgacon_set_cursor_size(c->vc_x, 31, 31);
+				vgacon_set_cursor_size(c->state.x, 31, 31);
 			break;
 		default:
-			vgacon_set_cursor_size(c->vc_x, 1,
+			vgacon_set_cursor_size(c->state.x, 1,
 					       c->vc_font.height);
 			break;
 		}
@@ -1352,8 +1352,8 @@ static void vgacon_save_screen(struct vc_data *c)
 		 * console initialization routines.
 		 */
 		vga_bootup_console = 1;
-		c->vc_x = screen_info.orig_x;
-		c->vc_y = screen_info.orig_y;
+		c->state.x = screen_info.orig_x;
+		c->state.y = screen_info.orig_y;
 	}
 
 	/* We can't copy in more than the size of the video buffer,
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index ca935c09a261..c750470a31ec 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -240,7 +240,7 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	struct fbcon_ops *ops = info->fbcon_par;
 	unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff;
 	int w = DIV_ROUND_UP(vc->vc_font.width, 8), c;
-	int y = real_y(ops->p, vc->vc_y);
+	int y = real_y(ops->p, vc->state.y);
 	int attribute, use_sw = (vc->vc_cursor_type & 0x10);
 	int err = 1;
 	char *src;
@@ -286,10 +286,10 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 		cursor.set |= FB_CUR_SETCMAP;
 	}
 
-	if ((ops->cursor_state.image.dx != (vc->vc_font.width * vc->vc_x)) ||
+	if ((ops->cursor_state.image.dx != (vc->vc_font.width * vc->state.x)) ||
 	    (ops->cursor_state.image.dy != (vc->vc_font.height * y)) ||
 	    ops->cursor_reset) {
-		ops->cursor_state.image.dx = vc->vc_font.width * vc->vc_x;
+		ops->cursor_state.image.dx = vc->vc_font.width * vc->state.x;
 		ops->cursor_state.image.dy = vc->vc_font.height * y;
 		cursor.set |= FB_CUR_SETPOS;
 	}
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 9d28a8e3328f..38d2a00b0ccf 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -655,11 +655,11 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
 		}
 		if (!save) {
 			int lines;
-			if (vc->vc_y + logo_lines >= rows)
-				lines = rows - vc->vc_y - 1;
+			if (vc->state.y + logo_lines >= rows)
+				lines = rows - vc->state.y - 1;
 			else
 				lines = logo_lines;
-			vc->vc_y += lines;
+			vc->state.y += lines;
 			vc->vc_pos += lines * vc->vc_size_row;
 		}
 	}
@@ -677,7 +677,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
 					vc->vc_size_row *
 					rows);
 		scr_memcpyw(q, save, logo_lines * new_cols * 2);
-		vc->vc_y += logo_lines;
+		vc->state.y += logo_lines;
 		vc->vc_pos += logo_lines * vc->vc_size_row;
 		kfree(save);
 	}
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index dfa9a8aa4509..9d06446a1a3b 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -225,7 +225,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	struct fbcon_ops *ops = info->fbcon_par;
 	unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff;
 	int w = (vc->vc_font.height + 7) >> 3, c;
-	int y = real_y(ops->p, vc->vc_y);
+	int y = real_y(ops->p, vc->state.y);
 	int attribute, use_sw = (vc->vc_cursor_type & 0x10);
 	int err = 1, dx, dy;
 	char *src;
@@ -284,7 +284,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	}
 
 	dx = y * vc->vc_font.height;
-	dy = vyres - ((vc->vc_x + 1) * vc->vc_font.width);
+	dy = vyres - ((vc->state.x + 1) * vc->vc_font.width);
 
 	if (ops->cursor_state.image.dx != dx ||
 	    ops->cursor_state.image.dy != dy ||
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index ce08251bfd38..4b5f76bb01e5 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -208,7 +208,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	struct fbcon_ops *ops = info->fbcon_par;
 	unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff;
 	int w = (vc->vc_font.height + 7) >> 3, c;
-	int y = real_y(ops->p, vc->vc_y);
+	int y = real_y(ops->p, vc->state.y);
 	int attribute, use_sw = (vc->vc_cursor_type & 0x10);
 	int err = 1, dx, dy;
 	char *src;
@@ -267,7 +267,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	}
 
 	dx = vxres - ((y * vc->vc_font.height) + vc->vc_font.height);
-	dy = vc->vc_x * vc->vc_font.width;
+	dy = vc->state.x * vc->vc_font.width;
 
 	if (ops->cursor_state.image.dx != dx ||
 	    ops->cursor_state.image.dy != dy ||
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 1936afc78fec..7e0ae3549dc7 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -255,7 +255,7 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	struct fbcon_ops *ops = info->fbcon_par;
 	unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff;
 	int w = (vc->vc_font.width + 7) >> 3, c;
-	int y = real_y(ops->p, vc->vc_y);
+	int y = real_y(ops->p, vc->state.y);
 	int attribute, use_sw = (vc->vc_cursor_type & 0x10);
 	int err = 1, dx, dy;
 	char *src;
@@ -315,7 +315,7 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	}
 
 	dy = vyres - ((y * vc->vc_font.height) + vc->vc_font.height);
-	dx = vxres - ((vc->vc_x * vc->vc_font.width) + vc->vc_font.width);
+	dx = vxres - ((vc->state.x * vc->vc_font.width) + vc->vc_font.width);
 
 	if (ops->cursor_state.image.dx != dx ||
 	    ops->cursor_state.image.dy != dy ||
diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c
index 93390312957f..ac51425687e4 100644
--- a/drivers/video/fbdev/core/tileblit.c
+++ b/drivers/video/fbdev/core/tileblit.c
@@ -85,8 +85,8 @@ static void tile_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 	struct fb_tilecursor cursor;
 	int use_sw = (vc->vc_cursor_type & 0x10);
 
-	cursor.sx = vc->vc_x;
-	cursor.sy = vc->vc_y;
+	cursor.sx = vc->state.x;
+	cursor.sy = vc->state.y;
 	cursor.mode = (mode == CM_ERASE || use_sw) ? 0 : 1;
 	cursor.fg = fg;
 	cursor.bg = bg;
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 24d4c16e3ae0..162f4337c767 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -22,6 +22,37 @@ struct uni_screen;
 
 #define NPAR 16
 
+/**
+ * struct vc_state -- state of a VC
+ * @x: cursor's x-position
+ * @y: cursor's y-position
+ * @color: foreground & background colors
+ * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP)
+ * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP)
+ * @charset: what character set to use (0=G0 or 1=G1)
+ * @intensity: 0=half-bright, 1=normal, 2=bold
+ * @reverse: reversed foreground/background colors
+ *
+ * These members are defined separately from struct vc_data as we save &
+ * restore them at times.
+ */
+struct vc_state {
+	unsigned int	x, y;
+
+	unsigned char	color;
+
+	unsigned char	G0_charset;
+	unsigned char	G1_charset;
+	unsigned int	charset		: 1;
+
+	/* attribute flags */
+	unsigned int	intensity	: 2;
+	unsigned int	italic		: 1;
+	unsigned int	underline	: 1;
+	unsigned int	blink		: 1;
+	unsigned int	reverse		: 1;
+};
+
 /*
  * Example: vc_data of a console that was scrolled 3 lines down.
  *
@@ -57,6 +88,8 @@ struct uni_screen;
 struct vc_data {
 	struct tty_port port;			/* Upper level data */
 
+	struct vc_state state, saved_state;
+
 	unsigned short	vc_num;			/* Console number */
 	unsigned int	vc_cols;		/* [#] Console size */
 	unsigned int	vc_rows;
@@ -73,8 +106,6 @@ struct vc_data {
 	/* attributes for all characters on screen */
 	unsigned char	vc_attr;		/* Current attributes */
 	unsigned char	vc_def_color;		/* Default colors */
-	unsigned char	vc_color;		/* Foreground & background */
-	unsigned char	vc_s_color;		/* Saved foreground & background */
 	unsigned char	vc_ulcolor;		/* Color for underline mode */
 	unsigned char   vc_itcolor;
 	unsigned char	vc_halfcolor;		/* Color for half intensity mode */
@@ -82,8 +113,6 @@ struct vc_data {
 	unsigned int	vc_cursor_type;
 	unsigned short	vc_complement_mask;	/* [#] Xor mask for mouse pointer */
 	unsigned short	vc_s_complement_mask;	/* Saved mouse pointer mask */
-	unsigned int	vc_x, vc_y;		/* Cursor position */
-	unsigned int	vc_saved_x, vc_saved_y;
 	unsigned long	vc_pos;			/* Cursor address */
 	/* fonts */	
 	unsigned short	vc_hi_font_mask;	/* [#] Attribute set for upper 256 chars of font or 0 if not supported */
@@ -98,8 +127,6 @@ struct vc_data {
 	int		vt_newvt;
 	wait_queue_head_t paste_wait;
 	/* mode flags */
-	unsigned int	vc_charset	: 1;	/* Character set G0 / G1 */
-	unsigned int	vc_s_charset	: 1;	/* Saved character set */
 	unsigned int	vc_disp_ctrl	: 1;	/* Display chars < 32? */
 	unsigned int	vc_toggle_meta	: 1;	/* Toggle high bit? */
 	unsigned int	vc_decscnm	: 1;	/* Screen Mode */
@@ -107,17 +134,6 @@ struct vc_data {
 	unsigned int	vc_decawm	: 1;	/* Autowrap Mode */
 	unsigned int	vc_deccm	: 1;	/* Cursor Visible */
 	unsigned int	vc_decim	: 1;	/* Insert Mode */
-	/* attribute flags */
-	unsigned int	vc_intensity	: 2;	/* 0=half-bright, 1=normal, 2=bold */
-	unsigned int    vc_italic:1;
-	unsigned int	vc_underline	: 1;
-	unsigned int	vc_blink	: 1;
-	unsigned int	vc_reverse	: 1;
-	unsigned int	vc_s_intensity	: 2;	/* saved rendition */
-	unsigned int    vc_s_italic:1;
-	unsigned int	vc_s_underline	: 1;
-	unsigned int	vc_s_blink	: 1;
-	unsigned int	vc_s_reverse	: 1;
 	/* misc */
 	unsigned int	vc_priv		: 3;
 	unsigned int	vc_need_wrap	: 1;
@@ -129,10 +145,6 @@ struct vc_data {
 	unsigned int	vc_tab_stop[8];		/* Tab stops. 256 columns. */
 	unsigned char   vc_palette[16*3];       /* Colour palette for VGA+ */
 	unsigned short * vc_translate;
-	unsigned char 	vc_G0_charset;
-	unsigned char 	vc_G1_charset;
-	unsigned char 	vc_saved_G0;
-	unsigned char 	vc_saved_G1;
 	unsigned int    vc_resize_user;         /* resize request from user */
 	unsigned int	vc_bell_pitch;		/* Console bell pitch */
 	unsigned int	vc_bell_duration;	/* Console bell duration */
-- 
cgit v1.2.3


From b84ae3dc70fedf4bdee2dbfa487fd23b606fbb82 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:34 +0200
Subject: vt: introduce enum vc_intensity for intensity

Introduce names (en enum) for 0, 1, and 2 constants. We now have
VCI_HALF_BRIGHT, VCI_NORMAL, and VCI_BOLD instead.

Apart from the cleanup,
1) the enum allows for better type checking, and
2) this saves some code. No more fiddling with bits is needed in
   assembly now. (OTOH, the structure is larger.)

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-2-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c                     | 32 +++++++++++++++++---------------
 drivers/usb/misc/sisusbvga/sisusb_con.c |  6 +++---
 drivers/video/console/mdacon.c          |  5 +++--
 drivers/video/console/sticon.c          |  3 ++-
 drivers/video/console/vgacon.c          |  9 +++++----
 include/linux/console.h                 |  5 ++++-
 include/linux/console_struct.h          | 11 +++++++++--
 7 files changed, 43 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 76f52935e0c8..71bf483e5640 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -705,8 +705,9 @@ void update_region(struct vc_data *vc, unsigned long start, int count)
 
 /* Structure of attributes is hardware-dependent */
 
-static u8 build_attr(struct vc_data *vc, u8 _color, u8 _intensity, u8 _blink,
-    u8 _underline, u8 _reverse, u8 _italic)
+static u8 build_attr(struct vc_data *vc, u8 _color,
+		enum vc_intensity _intensity, u8 _blink, u8 _underline,
+		u8 _reverse, u8 _italic)
 {
 	if (vc->vc_sw->con_build_attr)
 		return vc->vc_sw->con_build_attr(vc, _color, _intensity,
@@ -734,13 +735,13 @@ static u8 build_attr(struct vc_data *vc, u8 _color, u8 _intensity, u8 _blink,
 		a = (a & 0xF0) | vc->vc_itcolor;
 	else if (_underline)
 		a = (a & 0xf0) | vc->vc_ulcolor;
-	else if (_intensity == 0)
+	else if (_intensity == VCI_HALF_BRIGHT)
 		a = (a & 0xf0) | vc->vc_halfcolor;
 	if (_reverse)
 		a = ((a) & 0x88) | ((((a) >> 4) | ((a) << 4)) & 0x77);
 	if (_blink)
 		a ^= 0x80;
-	if (_intensity == 2)
+	if (_intensity == VCI_BOLD)
 		a ^= 0x08;
 	if (vc->vc_hi_font_mask == 0x100)
 		a <<= 1;
@@ -753,8 +754,9 @@ static void update_attr(struct vc_data *vc)
 	vc->vc_attr = build_attr(vc, vc->state.color, vc->state.intensity,
 	              vc->state.blink, vc->state.underline,
 	              vc->state.reverse ^ vc->vc_decscnm, vc->state.italic);
-	vc->vc_video_erase_char = ' ' | (build_attr(vc, vc->state.color, 1,
-				vc->state.blink, 0, vc->vc_decscnm, 0) << 8);
+	vc->vc_video_erase_char = ' ' | (build_attr(vc, vc->state.color,
+				VCI_NORMAL, vc->state.blink, 0, vc->vc_decscnm,
+				0) << 8);
 }
 
 /* Note: inverting the screen twice should revert to the original state */
@@ -1611,7 +1613,7 @@ static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar posi
 
 static void default_attr(struct vc_data *vc)
 {
-	vc->state.intensity = 1;
+	vc->state.intensity = VCI_NORMAL;
 	vc->state.italic = 0;
 	vc->state.underline = 0;
 	vc->state.reverse = 0;
@@ -1652,11 +1654,11 @@ static void rgb_foreground(struct vc_data *vc, const struct rgb *c)
 
 	if (hue == 7 && max <= 0x55) {
 		hue = 0;
-		vc->state.intensity = 2;
+		vc->state.intensity = VCI_BOLD;
 	} else if (max > 0xaa)
-		vc->state.intensity = 2;
+		vc->state.intensity = VCI_BOLD;
 	else
-		vc->state.intensity = 1;
+		vc->state.intensity = VCI_NORMAL;
 
 	vc->state.color = (vc->state.color & 0xf0) | hue;
 }
@@ -1715,10 +1717,10 @@ static void csi_m(struct vc_data *vc)
 			default_attr(vc);
 			break;
 		case 1:
-			vc->state.intensity = 2;
+			vc->state.intensity = VCI_BOLD;
 			break;
 		case 2:
-			vc->state.intensity = 0;
+			vc->state.intensity = VCI_HALF_BRIGHT;
 			break;
 		case 3:
 			vc->state.italic = 1;
@@ -1764,7 +1766,7 @@ static void csi_m(struct vc_data *vc)
 			vc->vc_toggle_meta = 1;
 			break;
 		case 22:
-			vc->state.intensity = 1;
+			vc->state.intensity = VCI_NORMAL;
 			break;
 		case 23:
 			vc->state.italic = 0;
@@ -1795,7 +1797,7 @@ static void csi_m(struct vc_data *vc)
 		default:
 			if (vc->vc_par[i] >= 90 && vc->vc_par[i] <= 107) {
 				if (vc->vc_par[i] < 100)
-					vc->state.intensity = 2;
+					vc->state.intensity = VCI_BOLD;
 				vc->vc_par[i] -= 60;
 			}
 			if (vc->vc_par[i] >= 30 && vc->vc_par[i] <= 37)
@@ -1934,7 +1936,7 @@ static void setterm_command(struct vc_data *vc)
 	case 2:	/* set color for half intensity mode */
 		if (vc->vc_can_do_color && vc->vc_par[1] < 16) {
 			vc->vc_halfcolor = color_table[vc->vc_par[1]];
-			if (vc->state.intensity == 0)
+			if (vc->state.intensity == VCI_HALF_BRIGHT)
 				update_attr(vc);
 		}
 		break;
diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c
index cd0155310fea..c59fe641b8b5 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_con.c
+++ b/drivers/usb/misc/sisusbvga/sisusb_con.c
@@ -302,14 +302,14 @@ sisusbcon_deinit(struct vc_data *c)
 
 /* interface routine */
 static u8
-sisusbcon_build_attr(struct vc_data *c, u8 color, u8 intensity,
+sisusbcon_build_attr(struct vc_data *c, u8 color, enum vc_intensity intensity,
 			    u8 blink, u8 underline, u8 reverse, u8 unused)
 {
 	u8 attr = color;
 
 	if (underline)
 		attr = (attr & 0xf0) | c->vc_ulcolor;
-	else if (intensity == 0)
+	else if (intensity == VCI_HALF_BRIGHT)
 		attr = (attr & 0xf0) | c->vc_halfcolor;
 
 	if (reverse)
@@ -320,7 +320,7 @@ sisusbcon_build_attr(struct vc_data *c, u8 color, u8 intensity,
 	if (blink)
 		attr ^= 0x80;
 
-	if (intensity == 2)
+	if (intensity == VCI_BOLD)
 		attr ^= 0x08;
 
 	return attr;
diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c
index d64c5ce84125..e3da664df16c 100644
--- a/drivers/video/console/mdacon.c
+++ b/drivers/video/console/mdacon.c
@@ -394,7 +394,8 @@ static inline u16 mda_convert_attr(u16 ch)
 		(ch & 0x00ff) | attr;
 }
 
-static u8 mdacon_build_attr(struct vc_data *c, u8 color, u8 intensity, 
+static u8 mdacon_build_attr(struct vc_data *c, u8 color,
+			    enum vc_intensity intensity,
 			    u8 blink, u8 underline, u8 reverse, u8 italic)
 {
 	/* The attribute is just a bit vector:
@@ -405,7 +406,7 @@ static u8 mdacon_build_attr(struct vc_data *c, u8 color, u8 intensity,
 	 *	Bit 7    : blink
 	 */
 
-	return (intensity & 3) |
+	return (intensity & VCI_MASK) |
 		((underline & 1) << 2) |
 		((reverse   & 1) << 3) |
 		(!!italic << 4) |
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index 90083eb80515..a847067abbe5 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -288,7 +288,8 @@ static unsigned long sticon_getxy(struct vc_data *conp, unsigned long pos,
     return ret;
 }
 
-static u8 sticon_build_attr(struct vc_data *conp, u8 color, u8 intens,
+static u8 sticon_build_attr(struct vc_data *conp, u8 color,
+			    enum vc_intensity intens,
 			    u8 blink, u8 underline, u8 reverse, u8 italic)
 {
     u8 attr = ((color & 0x70) >> 1) | ((color & 7));
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index d073fa167e87..d0b26e2318d3 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -629,7 +629,8 @@ static void vgacon_deinit(struct vc_data *c)
 	con_set_default_unimap(c);
 }
 
-static u8 vgacon_build_attr(struct vc_data *c, u8 color, u8 intensity,
+static u8 vgacon_build_attr(struct vc_data *c, u8 color,
+			    enum vc_intensity intensity,
 			    u8 blink, u8 underline, u8 reverse, u8 italic)
 {
 	u8 attr = color;
@@ -639,7 +640,7 @@ static u8 vgacon_build_attr(struct vc_data *c, u8 color, u8 intensity,
 			attr = (attr & 0xF0) | c->vc_itcolor;
 		else if (underline)
 			attr = (attr & 0xf0) | c->vc_ulcolor;
-		else if (intensity == 0)
+		else if (intensity == VCI_HALF_BRIGHT)
 			attr = (attr & 0xf0) | c->vc_halfcolor;
 	}
 	if (reverse)
@@ -648,14 +649,14 @@ static u8 vgacon_build_attr(struct vc_data *c, u8 color, u8 intensity,
 				       0x77);
 	if (blink)
 		attr ^= 0x80;
-	if (intensity == 2)
+	if (intensity == VCI_BOLD)
 		attr ^= 0x08;
 	if (!vga_can_do_color) {
 		if (italic)
 			attr = (attr & 0xF8) | 0x02;
 		else if (underline)
 			attr = (attr & 0xf8) | 0x01;
-		else if (intensity == 0)
+		else if (intensity == VCI_HALF_BRIGHT)
 			attr = (attr & 0xf0) | 0x08;
 	}
 	return attr;
diff --git a/include/linux/console.h b/include/linux/console.h
index 75dd20650fbe..10c04779ae49 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -35,6 +35,8 @@ enum con_scroll {
 	SM_DOWN,
 };
 
+enum vc_intensity;
+
 /**
  * struct consw - callbacks for consoles
  *
@@ -74,7 +76,8 @@ struct consw {
 	void	(*con_scrolldelta)(struct vc_data *vc, int lines);
 	int	(*con_set_origin)(struct vc_data *vc);
 	void	(*con_save_screen)(struct vc_data *vc);
-	u8	(*con_build_attr)(struct vc_data *vc, u8 color, u8 intensity,
+	u8	(*con_build_attr)(struct vc_data *vc, u8 color,
+			enum vc_intensity intensity,
 			u8 blink, u8 underline, u8 reverse, u8 italic);
 	void	(*con_invert_region)(struct vc_data *vc, u16 *p, int count);
 	u16    *(*con_screen_pos)(struct vc_data *vc, int offset);
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 162f4337c767..e901d98790bf 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -22,6 +22,13 @@ struct uni_screen;
 
 #define NPAR 16
 
+enum vc_intensity {
+	VCI_HALF_BRIGHT,
+	VCI_NORMAL,
+	VCI_BOLD,
+	VCI_MASK = 0x3,
+};
+
 /**
  * struct vc_state -- state of a VC
  * @x: cursor's x-position
@@ -30,7 +37,7 @@ struct uni_screen;
  * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP)
  * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP)
  * @charset: what character set to use (0=G0 or 1=G1)
- * @intensity: 0=half-bright, 1=normal, 2=bold
+ * @intensity: see enum vc_intensity for values
  * @reverse: reversed foreground/background colors
  *
  * These members are defined separately from struct vc_data as we save &
@@ -46,7 +53,7 @@ struct vc_state {
 	unsigned int	charset		: 1;
 
 	/* attribute flags */
-	unsigned int	intensity	: 2;
+	enum vc_intensity intensity;
 	unsigned int	italic		: 1;
 	unsigned int	underline	: 1;
 	unsigned int	blink		: 1;
-- 
cgit v1.2.3


From 77bc14f273c2dfecbf87f41fdc00345d99597e13 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:35 +0200
Subject: vc: switch state to bool

The code currently uses bitfields to store true-false values. Switch all
of that to bools. Apart from the cleanup, it saves 20B of code as many
shifts, ANDs, and ORs became simple movzb's.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-3-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c                     | 32 ++++++++++++++++----------------
 drivers/usb/misc/sisusbvga/sisusb_con.c |  3 ++-
 drivers/video/console/mdacon.c          | 11 ++++++-----
 drivers/video/console/sticon.c          |  3 ++-
 drivers/video/console/vgacon.c          |  3 ++-
 include/linux/console.h                 |  2 +-
 include/linux/console_struct.h          |  8 ++++----
 7 files changed, 33 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 71bf483e5640..26cb1fc48b27 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -706,8 +706,8 @@ void update_region(struct vc_data *vc, unsigned long start, int count)
 /* Structure of attributes is hardware-dependent */
 
 static u8 build_attr(struct vc_data *vc, u8 _color,
-		enum vc_intensity _intensity, u8 _blink, u8 _underline,
-		u8 _reverse, u8 _italic)
+		enum vc_intensity _intensity, bool _blink, bool _underline,
+		bool _reverse, bool _italic)
 {
 	if (vc->vc_sw->con_build_attr)
 		return vc->vc_sw->con_build_attr(vc, _color, _intensity,
@@ -755,8 +755,8 @@ static void update_attr(struct vc_data *vc)
 	              vc->state.blink, vc->state.underline,
 	              vc->state.reverse ^ vc->vc_decscnm, vc->state.italic);
 	vc->vc_video_erase_char = ' ' | (build_attr(vc, vc->state.color,
-				VCI_NORMAL, vc->state.blink, 0, vc->vc_decscnm,
-				0) << 8);
+				VCI_NORMAL, vc->state.blink, false,
+				vc->vc_decscnm, false) << 8);
 }
 
 /* Note: inverting the screen twice should revert to the original state */
@@ -1614,10 +1614,10 @@ static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar posi
 static void default_attr(struct vc_data *vc)
 {
 	vc->state.intensity = VCI_NORMAL;
-	vc->state.italic = 0;
-	vc->state.underline = 0;
-	vc->state.reverse = 0;
-	vc->state.blink = 0;
+	vc->state.italic = false;
+	vc->state.underline = false;
+	vc->state.reverse = false;
+	vc->state.blink = false;
 	vc->state.color = vc->vc_def_color;
 }
 
@@ -1723,7 +1723,7 @@ static void csi_m(struct vc_data *vc)
 			vc->state.intensity = VCI_HALF_BRIGHT;
 			break;
 		case 3:
-			vc->state.italic = 1;
+			vc->state.italic = true;
 			break;
 		case 21:
 			/*
@@ -1731,13 +1731,13 @@ static void csi_m(struct vc_data *vc)
 			 * convert it to a single underline.
 			 */
 		case 4:
-			vc->state.underline = 1;
+			vc->state.underline = true;
 			break;
 		case 5:
-			vc->state.blink = 1;
+			vc->state.blink = true;
 			break;
 		case 7:
-			vc->state.reverse = 1;
+			vc->state.reverse = true;
 			break;
 		case 10: /* ANSI X3.64-1979 (SCO-ish?)
 			  * Select primary font, don't display control chars if
@@ -1769,16 +1769,16 @@ static void csi_m(struct vc_data *vc)
 			vc->state.intensity = VCI_NORMAL;
 			break;
 		case 23:
-			vc->state.italic = 0;
+			vc->state.italic = false;
 			break;
 		case 24:
-			vc->state.underline = 0;
+			vc->state.underline = false;
 			break;
 		case 25:
-			vc->state.blink = 0;
+			vc->state.blink = false;
 			break;
 		case 27:
-			vc->state.reverse = 0;
+			vc->state.reverse = false;
 			break;
 		case 38:
 			i = vc_t416_color(vc, i, rgb_foreground);
diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c
index c59fe641b8b5..80657c49310a 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_con.c
+++ b/drivers/usb/misc/sisusbvga/sisusb_con.c
@@ -303,7 +303,8 @@ sisusbcon_deinit(struct vc_data *c)
 /* interface routine */
 static u8
 sisusbcon_build_attr(struct vc_data *c, u8 color, enum vc_intensity intensity,
-			    u8 blink, u8 underline, u8 reverse, u8 unused)
+			    bool blink, bool underline, bool reverse,
+			    bool unused)
 {
 	u8 attr = color;
 
diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c
index e3da664df16c..00cb6245fbef 100644
--- a/drivers/video/console/mdacon.c
+++ b/drivers/video/console/mdacon.c
@@ -396,7 +396,8 @@ static inline u16 mda_convert_attr(u16 ch)
 
 static u8 mdacon_build_attr(struct vc_data *c, u8 color,
 			    enum vc_intensity intensity,
-			    u8 blink, u8 underline, u8 reverse, u8 italic)
+			    bool blink, bool underline, bool reverse,
+			    bool italic)
 {
 	/* The attribute is just a bit vector:
 	 *
@@ -407,10 +408,10 @@ static u8 mdacon_build_attr(struct vc_data *c, u8 color,
 	 */
 
 	return (intensity & VCI_MASK) |
-		((underline & 1) << 2) |
-		((reverse   & 1) << 3) |
-		(!!italic << 4) |
-		((blink     & 1) << 7);
+		(underline << 2) |
+		(reverse << 3) |
+		(italic << 4) |
+		(blink << 7);
 }
 
 static void mdacon_invert_region(struct vc_data *c, u16 *p, int count)
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index a847067abbe5..bbcdfd312c36 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -290,7 +290,8 @@ static unsigned long sticon_getxy(struct vc_data *conp, unsigned long pos,
 
 static u8 sticon_build_attr(struct vc_data *conp, u8 color,
 			    enum vc_intensity intens,
-			    u8 blink, u8 underline, u8 reverse, u8 italic)
+			    bool blink, bool underline, bool reverse,
+			    bool italic)
 {
     u8 attr = ((color & 0x70) >> 1) | ((color & 7));
 
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index d0b26e2318d3..c1c4ce28ac5e 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -631,7 +631,8 @@ static void vgacon_deinit(struct vc_data *c)
 
 static u8 vgacon_build_attr(struct vc_data *c, u8 color,
 			    enum vc_intensity intensity,
-			    u8 blink, u8 underline, u8 reverse, u8 italic)
+			    bool blink, bool underline, bool reverse,
+			    bool italic)
 {
 	u8 attr = color;
 
diff --git a/include/linux/console.h b/include/linux/console.h
index 10c04779ae49..964b67912b04 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -78,7 +78,7 @@ struct consw {
 	void	(*con_save_screen)(struct vc_data *vc);
 	u8	(*con_build_attr)(struct vc_data *vc, u8 color,
 			enum vc_intensity intensity,
-			u8 blink, u8 underline, u8 reverse, u8 italic);
+			bool blink, bool underline, bool reverse, bool italic);
 	void	(*con_invert_region)(struct vc_data *vc, u16 *p, int count);
 	u16    *(*con_screen_pos)(struct vc_data *vc, int offset);
 	unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position,
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index e901d98790bf..fa1abffe64be 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -54,10 +54,10 @@ struct vc_state {
 
 	/* attribute flags */
 	enum vc_intensity intensity;
-	unsigned int	italic		: 1;
-	unsigned int	underline	: 1;
-	unsigned int	blink		: 1;
-	unsigned int	reverse		: 1;
+	bool		italic;
+	bool		underline;
+	bool		blink;
+	bool		reverse;
 };
 
 /*
-- 
cgit v1.2.3


From b70ec4d97f4cc4f6f804ca57419d070b80a9874e Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:37 +0200
Subject: vt: switch G0/1_charset to an array

Declare Gx_charset[2] instead of G0_charset and G1_charset. It makes
the code simpler (without ternary operators).

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-5-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c            | 19 ++++++++-----------
 include/linux/console_struct.h |  6 ++----
 2 files changed, 10 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 729c7c8c682b..4e79cda0c2be 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1743,9 +1743,7 @@ static void csi_m(struct vc_data *vc)
 			  * Select primary font, don't display control chars if
 			  * defined, don't set bit 8 on output.
 			  */
-			vc->vc_translate = set_translate(vc->state.charset == 0
-					? vc->state.G0_charset
-					: vc->state.G1_charset, vc);
+			vc->vc_translate = set_translate(vc->state.Gx_charset[vc->state.charset], vc);
 			vc->vc_disp_ctrl = 0;
 			vc->vc_toggle_meta = 0;
 			break;
@@ -2041,8 +2039,8 @@ static void restore_cur(struct vc_data *vc)
 	memcpy(&vc->state, &vc->saved_state, sizeof(vc->state));
 
 	gotoxy(vc, vc->state.x, vc->state.y);
-	vc->vc_translate = set_translate(vc->state.charset ? vc->state.G1_charset :
-			vc->state.G0_charset, vc);
+	vc->vc_translate = set_translate(vc->state.Gx_charset[vc->state.charset],
+			vc);
 	update_attr(vc);
 	vc->vc_need_wrap = 0;
 }
@@ -2059,8 +2057,8 @@ static void reset_terminal(struct vc_data *vc, int do_clear)
 	vc->vc_state		= ESnormal;
 	vc->vc_priv		= EPecma;
 	vc->vc_translate	= set_translate(LAT1_MAP, vc);
-	vc->state.G0_charset	= LAT1_MAP;
-	vc->state.G1_charset	= GRAF_MAP;
+	vc->state.Gx_charset[0]	= LAT1_MAP;
+	vc->state.Gx_charset[1]	= GRAF_MAP;
 	vc->state.charset	= 0;
 	vc->vc_need_wrap	= 0;
 	vc->vc_report_mouse	= 0;
@@ -2105,8 +2103,7 @@ static void reset_terminal(struct vc_data *vc, int do_clear)
 
 static void vc_setGx(struct vc_data *vc, unsigned int which, int c)
 {
-	unsigned char *charset = which == 0 ? &vc->state.G0_charset :
-		&vc->state.G1_charset;
+	unsigned char *charset = &vc->state.Gx_charset[which];
 
 	switch (c) {
 	case '0':
@@ -2168,12 +2165,12 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		return;
 	case 14:
 		vc->state.charset = 1;
-		vc->vc_translate = set_translate(vc->state.G1_charset, vc);
+		vc->vc_translate = set_translate(vc->state.Gx_charset[1], vc);
 		vc->vc_disp_ctrl = 1;
 		return;
 	case 15:
 		vc->state.charset = 0;
-		vc->vc_translate = set_translate(vc->state.G0_charset, vc);
+		vc->vc_translate = set_translate(vc->state.Gx_charset[0], vc);
 		vc->vc_disp_ctrl = 0;
 		return;
 	case 24: case 26:
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index fa1abffe64be..623e86689c3a 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -34,8 +34,7 @@ enum vc_intensity {
  * @x: cursor's x-position
  * @y: cursor's y-position
  * @color: foreground & background colors
- * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP)
- * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP)
+ * @Gx_charset: what's G0/G1 slot set to (like GRAF_MAP, LAT1_MAP)
  * @charset: what character set to use (0=G0 or 1=G1)
  * @intensity: see enum vc_intensity for values
  * @reverse: reversed foreground/background colors
@@ -48,8 +47,7 @@ struct vc_state {
 
 	unsigned char	color;
 
-	unsigned char	G0_charset;
-	unsigned char	G1_charset;
+	unsigned char	Gx_charset[2];
 	unsigned int	charset		: 1;
 
 	/* attribute flags */
-- 
cgit v1.2.3


From dbee4cffa1bfe23263edde1d17cdbef0de3a6ac0 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:38 +0200
Subject: vt: convert vc_tab_stop to bitmap

vc_tab_stop is used as a bitmap, but defined as an unsigned int array.
Switch it to bitmap and convert all users to the bitmap interface.

Note the difference in behavior! We no longer mask the top 24 bits away
from x, hence we do not wrap tabs at 256th column. Instead, we silently
drop attempts to set a tab behind 256 columns. And we will also seek by
'\t' to the rightmost column, when behind that boundary. I do not think
the original behavior was desired and that someone relies on that. If
this turns out to be the case, we can change the added 'if's back to
masks here and there instead...

(Or we can increase the limit as fb consoles now have 240 chars here.
And they could have more with higher than my resolution, of course.)

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-6-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c            | 44 +++++++++++++++++-------------------------
 include/linux/console_struct.h |  3 ++-
 2 files changed, 20 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 4e79cda0c2be..3adb7f409524 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2052,6 +2052,8 @@ enum { ESnormal, ESesc, ESsquare, ESgetpars, ESfunckey,
 /* console_lock is held (except via vc_init()) */
 static void reset_terminal(struct vc_data *vc, int do_clear)
 {
+	unsigned int i;
+
 	vc->vc_top		= 0;
 	vc->vc_bottom		= vc->vc_rows;
 	vc->vc_state		= ESnormal;
@@ -2082,14 +2084,9 @@ static void reset_terminal(struct vc_data *vc, int do_clear)
 	default_attr(vc);
 	update_attr(vc);
 
-	vc->vc_tab_stop[0]	=
-	vc->vc_tab_stop[1]	=
-	vc->vc_tab_stop[2]	=
-	vc->vc_tab_stop[3]	=
-	vc->vc_tab_stop[4]	=
-	vc->vc_tab_stop[5]	=
-	vc->vc_tab_stop[6]	=
-	vc->vc_tab_stop[7]	= 0x01010101;
+	bitmap_zero(vc->vc_tab_stop, VC_TABSTOPS_COUNT);
+	for (i = 0; i < VC_TABSTOPS_COUNT; i += 8)
+		set_bit(i, vc->vc_tab_stop);
 
 	vc->vc_bell_pitch = DEFAULT_BELL_PITCH;
 	vc->vc_bell_duration = DEFAULT_BELL_DURATION;
@@ -2147,11 +2144,13 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 		return;
 	case 9:
 		vc->vc_pos -= (vc->state.x << 1);
-		while (vc->state.x < vc->vc_cols - 1) {
-			vc->state.x++;
-			if (vc->vc_tab_stop[7 & (vc->state.x >> 5)] & (1 << (vc->state.x & 31)))
-				break;
-		}
+
+		vc->state.x = find_next_bit(vc->vc_tab_stop,
+				min(vc->vc_cols - 1, VC_TABSTOPS_COUNT),
+				vc->state.x + 1);
+		if (vc->state.x >= VC_TABSTOPS_COUNT)
+			vc->state.x = vc->vc_cols - 1;
+
 		vc->vc_pos += (vc->state.x << 1);
 		notify_write(vc, '\t');
 		return;
@@ -2210,7 +2209,8 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 			lf(vc);
 			return;
 		case 'H':
-			vc->vc_tab_stop[7 & (vc->state.x >> 5)] |= (1 << (vc->state.x & 31));
+			if (vc->state.x < VC_TABSTOPS_COUNT)
+				set_bit(vc->state.x, vc->vc_tab_stop);
 			return;
 		case 'Z':
 			respond_ID(tty);
@@ -2421,18 +2421,10 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 				respond_ID(tty);
 			return;
 		case 'g':
-			if (!vc->vc_par[0])
-				vc->vc_tab_stop[7 & (vc->state.x >> 5)] &= ~(1 << (vc->state.x & 31));
-			else if (vc->vc_par[0] == 3) {
-				vc->vc_tab_stop[0] =
-					vc->vc_tab_stop[1] =
-					vc->vc_tab_stop[2] =
-					vc->vc_tab_stop[3] =
-					vc->vc_tab_stop[4] =
-					vc->vc_tab_stop[5] =
-					vc->vc_tab_stop[6] =
-					vc->vc_tab_stop[7] = 0;
-			}
+			if (!vc->vc_par[0] && vc->state.x < VC_TABSTOPS_COUNT)
+				set_bit(vc->state.x, vc->vc_tab_stop);
+			else if (vc->vc_par[0] == 3)
+				bitmap_zero(vc->vc_tab_stop, VC_TABSTOPS_COUNT);
 			return;
 		case 'm':
 			csi_m(vc);
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 623e86689c3a..81f7afcd061a 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -21,6 +21,7 @@ struct uni_pagedir;
 struct uni_screen;
 
 #define NPAR 16
+#define VC_TABSTOPS_COUNT	256U
 
 enum vc_intensity {
 	VCI_HALF_BRIGHT,
@@ -147,7 +148,7 @@ struct vc_data {
 	unsigned char	vc_utf		: 1;	/* Unicode UTF-8 encoding */
 	unsigned char	vc_utf_count;
 		 int	vc_utf_char;
-	unsigned int	vc_tab_stop[8];		/* Tab stops. 256 columns. */
+	DECLARE_BITMAP(vc_tab_stop, VC_TABSTOPS_COUNT);	/* Tab stops. 256 columns. */
 	unsigned char   vc_palette[16*3];       /* Colour palette for VGA+ */
 	unsigned short * vc_translate;
 	unsigned int    vc_resize_user;         /* resize request from user */
-- 
cgit v1.2.3


From 7d4a3112f07878ba9c6bffbcdb2dea2dcfc5c1f9 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:39 +0200
Subject: vt: remove 25 years stale comment

vc_cons was made global (non-static) in 1.3.38, almost 25 years ago.
Remove a comment which says that it would be a disadvantage to do so :P.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-7-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/console_struct.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 81f7afcd061a..40ed52f67bc5 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -167,8 +167,7 @@ struct vc {
 	struct work_struct SAK_work;
 
 	/* might add  scrmem, kbd  at some time,
-	   to have everything in one place - the disadvantage
-	   would be that vc_cons etc can no longer be static */
+	   to have everything in one place */
 };
 
 extern struct vc vc_cons [MAX_NR_CONSOLES];
-- 
cgit v1.2.3


From 9a6f72d9b6c121415bc2867329fe77b0d2a52dc1 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:41 +0200
Subject: vt: get rid of VT10.ID macros

VT100ID is unused, but defined twice. Kill it.

VT102ID is used only in respond_ID. Define there a variable with proper
type and use that instead. Then drop both defines of VT102ID too.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-9-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c     | 11 ++++-------
 include/linux/console.h |  6 ------
 2 files changed, 4 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 49c9d1e4067c..8d9e532f050a 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1397,12 +1397,6 @@ enum { EPecma = 0, EPdec, EPeq, EPgt, EPlt};
 #define kbdapplic	VC_APPLIC
 #define lnm		VC_CRLF
 
-/*
- * this is what the terminal answers to a ESC-Z or csi0c query.
- */
-#define VT100ID "\033[?1;2c"
-#define VT102ID "\033[?6c"
-
 const unsigned char color_table[] = { 0, 4, 2, 6, 1, 5, 3, 7,
 				       8,12,10,14, 9,13,11,15 };
 
@@ -1835,7 +1829,10 @@ static inline void status_report(struct tty_struct *tty)
 
 static inline void respond_ID(struct tty_struct *tty)
 {
-	respond_string(VT102ID, strlen(VT102ID), tty->port);
+	/* terminal answer to an ESC-Z or csi0c query. */
+	static const char vt102_id[] = "\033[?6c";
+
+	respond_string(vt102_id, strlen(vt102_id), tty->port);
 }
 
 void mouse_report(struct tty_struct *tty, int butt, int mrx, int mry)
diff --git a/include/linux/console.h b/include/linux/console.h
index 964b67912b04..0670d3491e0e 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -24,12 +24,6 @@ struct module;
 struct tty_struct;
 struct notifier_block;
 
-/*
- * this is what the terminal answers to a ESC-Z or csi0c query.
- */
-#define VT100ID "\033[?1;2c"
-#define VT102ID "\033[?6c"
-
 enum con_scroll {
 	SM_UP,
 	SM_DOWN,
-- 
cgit v1.2.3


From a018180cc3485e71f7912e36bf93caa635e0e4af Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:42 +0200
Subject: vt: move vc_translate to vt.c and rename it

vc_translate is used only in vt.c, so move the definition from a header
there. Also, it used to be a macro, so be modern and make a static
inline from it. This makes the code actually readable.

And as a preparation for next patches, rename it to vc_translate_ascii.
vc_translate will be a wrapper for both unicode and this one.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200615074910.19267-10-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c     | 14 +++++++++++++-
 include/linux/vt_kern.h |  3 ---
 2 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 8d9e532f050a..b86639351dd2 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2560,6 +2560,18 @@ static void con_flush(struct vc_data *vc, unsigned long draw_from,
 	*draw_x = -1;
 }
 
+static inline int vc_translate_ascii(const struct vc_data *vc, int c)
+{
+	if (IS_ENABLED(CONFIG_CONSOLE_TRANSLATIONS)) {
+		if (vc->vc_toggle_meta)
+			c |= 0x80;
+
+		return vc->vc_translate[c];
+	}
+
+	return c;
+}
+
 /* acquires console_lock */
 static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int count)
 {
@@ -2687,7 +2699,7 @@ rescan_last_byte:
 			c = 0xfffd;
 		    tc = c;
 		} else {	/* no utf or alternate charset mode */
-		    tc = vc_translate(vc, c);
+			tc = vc_translate_ascii(vc, c);
 		}
 
 		param.c = tc;
diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
index abf5bccf906a..349e39c3ab60 100644
--- a/include/linux/vt_kern.h
+++ b/include/linux/vt_kern.h
@@ -74,8 +74,6 @@ int con_set_default_unimap(struct vc_data *vc);
 void con_free_unimap(struct vc_data *vc);
 int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc);
 
-#define vc_translate(vc, c) ((vc)->vc_translate[(c) |			\
-					((vc)->vc_toggle_meta ? 0x80 : 0)])
 #else
 static inline int con_set_trans_old(unsigned char __user *table)
 {
@@ -124,7 +122,6 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc)
 	return 0;
 }
 
-#define vc_translate(vc, c) (c)
 #endif
 
 /* vt.c */
-- 
cgit v1.2.3


From 4dfa3c54f908d7ec20b88671329d6a3205d37d36 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 15 Jun 2020 09:48:57 +0200
Subject: vt: redefine world of cursor macros

The cursor code used to use magic constants, ANDs, ORs, and some macros.
Redefine all this to make some sense.

In particular:
* Drop CUR_DEFAULT, which is CUR_UNDERLINE. CUR_DEFAULT was used only
  for cur_default variable initialization, so use CUR_UNDERLINE there to
  make obvious what's the default.
* Drop CUR_HWMASK. Instead, define CUR_SIZE() which explains it more.
  And use it all over the places.
* Define few more masks and bits which will be used in next patches
  instead of magic constants.
* Define CUR_MAKE to build up cursor value.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-fbdev@vger.kernel.org
Link: https://lore.kernel.org/r/20200615074910.19267-25-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c                  |  2 +-
 drivers/video/fbdev/core/bitblit.c   |  2 +-
 drivers/video/fbdev/core/fbcon_ccw.c |  2 +-
 drivers/video/fbdev/core/fbcon_cw.c  |  2 +-
 drivers/video/fbdev/core/fbcon_ud.c  |  2 +-
 include/linux/console_struct.h       | 28 +++++++++++++++++-----------
 6 files changed, 22 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index f7d5a3c3845f..af1ef717f416 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -163,7 +163,7 @@ module_param(default_utf8, int, S_IRUGO | S_IWUSR);
 int global_cursor_default = -1;
 module_param(global_cursor_default, int, S_IRUGO | S_IWUSR);
 
-static int cur_default = CUR_DEFAULT;
+static int cur_default = CUR_UNDERLINE;
 module_param(cur_default, int, S_IRUGO | S_IWUSR);
 
 /*
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index c750470a31ec..3b002b365a5a 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -325,7 +325,7 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 		ops->p->cursor_shape = vc->vc_cursor_type;
 		cursor.set |= FB_CUR_SETSHAPE;
 
-		switch (ops->p->cursor_shape & CUR_HWMASK) {
+		switch (CUR_SIZE(ops->p->cursor_shape)) {
 		case CUR_NONE:
 			cur_height = 0;
 			break;
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index 9d06446a1a3b..5b67bcebe34c 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -325,7 +325,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 		ops->p->cursor_shape = vc->vc_cursor_type;
 		cursor.set |= FB_CUR_SETSHAPE;
 
-		switch (ops->p->cursor_shape & CUR_HWMASK) {
+		switch (CUR_SIZE(ops->p->cursor_shape)) {
 		case CUR_NONE:
 			cur_height = 0;
 			break;
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index 4b5f76bb01e5..f1aab3ae3bc9 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -308,7 +308,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 		ops->p->cursor_shape = vc->vc_cursor_type;
 		cursor.set |= FB_CUR_SETSHAPE;
 
-		switch (ops->p->cursor_shape & CUR_HWMASK) {
+		switch (CUR_SIZE(ops->p->cursor_shape)) {
 		case CUR_NONE:
 			cur_height = 0;
 			break;
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 7e0ae3549dc7..81ed6f6bed67 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -348,7 +348,7 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 		ops->p->cursor_shape = vc->vc_cursor_type;
 		cursor.set |= FB_CUR_SETSHAPE;
 
-		switch (ops->p->cursor_shape & CUR_HWMASK) {
+		switch (CUR_SIZE(ops->p->cursor_shape)) {
 		case CUR_NONE:
 			cur_height = 0;
 			break;
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 40ed52f67bc5..153734816b49 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -173,17 +173,23 @@ struct vc {
 extern struct vc vc_cons [MAX_NR_CONSOLES];
 extern void vc_SAK(struct work_struct *work);
 
-#define CUR_DEF		0
-#define CUR_NONE	1
-#define CUR_UNDERLINE	2
-#define CUR_LOWER_THIRD	3
-#define CUR_LOWER_HALF	4
-#define CUR_TWO_THIRDS	5
-#define CUR_BLOCK	6
-#define CUR_HWMASK	0x0f
-#define CUR_SWMASK	0xfff0
-
-#define CUR_DEFAULT CUR_UNDERLINE
+#define CUR_MAKE(size, change, set)	((size) | ((change) << 8) |	\
+		((set) << 16))
+#define CUR_SIZE(c)		 ((c) & 0x00000f)
+# define CUR_DEF			       0
+# define CUR_NONE			       1
+# define CUR_UNDERLINE			       2
+# define CUR_LOWER_THIRD		       3
+# define CUR_LOWER_HALF			       4
+# define CUR_TWO_THIRDS			       5
+# define CUR_BLOCK			       6
+#define CUR_SW				0x000010
+#define CUR_ALWAYS_BG			0x000020
+#define CUR_INVERT_FG_BG		0x000040
+#define CUR_FG				0x000700
+#define CUR_BG				0x007000
+#define CUR_CHANGE(c)		 ((c) & 0x00ff00)
+#define CUR_SET(c)		(((c) & 0xff0000) >> 8)
 
 bool con_is_visible(const struct vc_data *vc);
 
-- 
cgit v1.2.3


From 521b512b157a1315ff2bf11c11ab184c79515aea Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:47 +0100
Subject: PM / EM: change naming convention from 'capacity' to 'performance'

The Energy Model uses concept of performance domain and capacity states in
order to calculate power used by CPUs. Change naming convention from
capacity to performance state would enable wider usage in future, e.g.
upcoming support for other devices other than CPUs.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/cpufreq_cooling.c | 12 +++---
 include/linux/energy_model.h      | 86 +++++++++++++++++++++------------------
 kernel/power/energy_model.c       | 44 ++++++++++----------
 kernel/sched/topology.c           | 20 ++++-----
 4 files changed, 84 insertions(+), 78 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 9e124020519f..641995ebc107 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -333,18 +333,18 @@ static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev,
 		return false;
 
 	policy = cpufreq_cdev->policy;
-	if (!cpumask_equal(policy->related_cpus, to_cpumask(em->cpus))) {
+	if (!cpumask_equal(policy->related_cpus, em_span_cpus(em))) {
 		pr_err("The span of pd %*pbl is misaligned with cpufreq policy %*pbl\n",
-			cpumask_pr_args(to_cpumask(em->cpus)),
+			cpumask_pr_args(em_span_cpus(em)),
 			cpumask_pr_args(policy->related_cpus));
 		return false;
 	}
 
 	nr_levels = cpufreq_cdev->max_level + 1;
-	if (em->nr_cap_states != nr_levels) {
-		pr_err("The number of cap states in pd %*pbl (%u) doesn't match the number of cooling levels (%u)\n",
-			cpumask_pr_args(to_cpumask(em->cpus)),
-			em->nr_cap_states, nr_levels);
+	if (em_pd_nr_perf_states(em) != nr_levels) {
+		pr_err("The number of performance states in pd %*pbl (%u) doesn't match the number of cooling levels (%u)\n",
+			cpumask_pr_args(em_span_cpus(em)),
+			em_pd_nr_perf_states(em), nr_levels);
 		return false;
 	}
 
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index ade6486a3382..fe336a9eb5d4 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -10,13 +10,13 @@
 #include <linux/types.h>
 
 /**
- * em_cap_state - Capacity state of a performance domain
+ * em_perf_state - Performance state of a performance domain
  * @frequency:	The CPU frequency in KHz, for consistency with CPUFreq
  * @power:	The power consumed by 1 CPU at this level, in milli-watts
  * @cost:	The cost coefficient associated with this level, used during
  *		energy calculation. Equal to: power * max_frequency / frequency
  */
-struct em_cap_state {
+struct em_perf_state {
 	unsigned long frequency;
 	unsigned long power;
 	unsigned long cost;
@@ -24,8 +24,8 @@ struct em_cap_state {
 
 /**
  * em_perf_domain - Performance domain
- * @table:		List of capacity states, in ascending order
- * @nr_cap_states:	Number of capacity states
+ * @table:		List of performance states, in ascending order
+ * @nr_perf_states:	Number of performance states
  * @cpus:		Cpumask covering the CPUs of the domain
  *
  * A "performance domain" represents a group of CPUs whose performance is
@@ -34,22 +34,27 @@ struct em_cap_state {
  * CPUFreq policies.
  */
 struct em_perf_domain {
-	struct em_cap_state *table;
-	int nr_cap_states;
+	struct em_perf_state *table;
+	int nr_perf_states;
 	unsigned long cpus[];
 };
 
+#define em_span_cpus(em) (to_cpumask((em)->cpus))
+
 #ifdef CONFIG_ENERGY_MODEL
 #define EM_CPU_MAX_POWER 0xFFFF
 
 struct em_data_callback {
 	/**
-	 * active_power() - Provide power at the next capacity state of a CPU
-	 * @power	: Active power at the capacity state in mW (modified)
-	 * @freq	: Frequency at the capacity state in kHz (modified)
+	 * active_power() - Provide power at the next performance state of
+	 *		a CPU
+	 * @power	: Active power at the performance state in mW
+	 *		(modified)
+	 * @freq	: Frequency at the performance state in kHz
+	 *		(modified)
 	 * @cpu		: CPU for which we do this operation
 	 *
-	 * active_power() must find the lowest capacity state of 'cpu' above
+	 * active_power() must find the lowest performance state of 'cpu' above
 	 * 'freq' and update 'power' and 'freq' to the matching active power
 	 * and frequency.
 	 *
@@ -80,46 +85,46 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util)
 {
 	unsigned long freq, scale_cpu;
-	struct em_cap_state *cs;
+	struct em_perf_state *ps;
 	int i, cpu;
 
 	/*
-	 * In order to predict the capacity state, map the utilization of the
-	 * most utilized CPU of the performance domain to a requested frequency,
-	 * like schedutil.
+	 * In order to predict the performance state, map the utilization of
+	 * the most utilized CPU of the performance domain to a requested
+	 * frequency, like schedutil.
 	 */
 	cpu = cpumask_first(to_cpumask(pd->cpus));
 	scale_cpu = arch_scale_cpu_capacity(cpu);
-	cs = &pd->table[pd->nr_cap_states - 1];
-	freq = map_util_freq(max_util, cs->frequency, scale_cpu);
+	ps = &pd->table[pd->nr_perf_states - 1];
+	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
 
 	/*
-	 * Find the lowest capacity state of the Energy Model above the
+	 * Find the lowest performance state of the Energy Model above the
 	 * requested frequency.
 	 */
-	for (i = 0; i < pd->nr_cap_states; i++) {
-		cs = &pd->table[i];
-		if (cs->frequency >= freq)
+	for (i = 0; i < pd->nr_perf_states; i++) {
+		ps = &pd->table[i];
+		if (ps->frequency >= freq)
 			break;
 	}
 
 	/*
-	 * The capacity of a CPU in the domain at that capacity state (cs)
+	 * The capacity of a CPU in the domain at the performance state (ps)
 	 * can be computed as:
 	 *
-	 *             cs->freq * scale_cpu
-	 *   cs->cap = --------------------                          (1)
+	 *             ps->freq * scale_cpu
+	 *   ps->cap = --------------------                          (1)
 	 *                 cpu_max_freq
 	 *
 	 * So, ignoring the costs of idle states (which are not available in
-	 * the EM), the energy consumed by this CPU at that capacity state is
-	 * estimated as:
+	 * the EM), the energy consumed by this CPU at that performance state
+	 * is estimated as:
 	 *
-	 *             cs->power * cpu_util
+	 *             ps->power * cpu_util
 	 *   cpu_nrg = --------------------                          (2)
-	 *                   cs->cap
+	 *                   ps->cap
 	 *
-	 * since 'cpu_util / cs->cap' represents its percentage of busy time.
+	 * since 'cpu_util / ps->cap' represents its percentage of busy time.
 	 *
 	 *   NOTE: Although the result of this computation actually is in
 	 *         units of power, it can be manipulated as an energy value
@@ -129,34 +134,35 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
 	 * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product
 	 * of two terms:
 	 *
-	 *             cs->power * cpu_max_freq   cpu_util
+	 *             ps->power * cpu_max_freq   cpu_util
 	 *   cpu_nrg = ------------------------ * ---------          (3)
-	 *                    cs->freq            scale_cpu
+	 *                    ps->freq            scale_cpu
 	 *
-	 * The first term is static, and is stored in the em_cap_state struct
-	 * as 'cs->cost'.
+	 * The first term is static, and is stored in the em_perf_state struct
+	 * as 'ps->cost'.
 	 *
 	 * Since all CPUs of the domain have the same micro-architecture, they
-	 * share the same 'cs->cost', and the same CPU capacity. Hence, the
+	 * share the same 'ps->cost', and the same CPU capacity. Hence, the
 	 * total energy of the domain (which is the simple sum of the energy of
 	 * all of its CPUs) can be factorized as:
 	 *
-	 *            cs->cost * \Sum cpu_util
+	 *            ps->cost * \Sum cpu_util
 	 *   pd_nrg = ------------------------                       (4)
 	 *                  scale_cpu
 	 */
-	return cs->cost * sum_util / scale_cpu;
+	return ps->cost * sum_util / scale_cpu;
 }
 
 /**
- * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain
+ * em_pd_nr_perf_states() - Get the number of performance states of a perf.
+ *				domain
  * @pd		: performance domain for which this must be done
  *
- * Return: the number of capacity states in the performance domain table
+ * Return: the number of performance states in the performance domain table
  */
-static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
+static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 {
-	return pd->nr_cap_states;
+	return pd->nr_perf_states;
 }
 
 #else
@@ -177,7 +183,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
 {
 	return 0;
 }
-static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
+static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 {
 	return 0;
 }
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0a9326f5f421..9892d548a0fa 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -27,18 +27,18 @@ static DEFINE_MUTEX(em_pd_mutex);
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *rootdir;
 
-static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd)
+static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd)
 {
 	struct dentry *d;
 	char name[24];
 
-	snprintf(name, sizeof(name), "cs:%lu", cs->frequency);
+	snprintf(name, sizeof(name), "ps:%lu", ps->frequency);
 
-	/* Create per-cs directory */
+	/* Create per-ps directory */
 	d = debugfs_create_dir(name, pd);
-	debugfs_create_ulong("frequency", 0444, d, &cs->frequency);
-	debugfs_create_ulong("power", 0444, d, &cs->power);
-	debugfs_create_ulong("cost", 0444, d, &cs->cost);
+	debugfs_create_ulong("frequency", 0444, d, &ps->frequency);
+	debugfs_create_ulong("power", 0444, d, &ps->power);
+	debugfs_create_ulong("cost", 0444, d, &ps->cost);
 }
 
 static int em_debug_cpus_show(struct seq_file *s, void *unused)
@@ -62,9 +62,9 @@ static void em_debug_create_pd(struct em_perf_domain *pd, int cpu)
 
 	debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops);
 
-	/* Create a sub-directory for each capacity state */
-	for (i = 0; i < pd->nr_cap_states; i++)
-		em_debug_create_cs(&pd->table[i], d);
+	/* Create a sub-directory for each performance state */
+	for (i = 0; i < pd->nr_perf_states; i++)
+		em_debug_create_ps(&pd->table[i], d);
 }
 
 static int __init em_debug_init(void)
@@ -84,7 +84,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
 	unsigned long power, freq, prev_freq = 0;
 	int i, ret, cpu = cpumask_first(span);
-	struct em_cap_state *table;
+	struct em_perf_state *table;
 	struct em_perf_domain *pd;
 	u64 fmax;
 
@@ -99,26 +99,26 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 	if (!table)
 		goto free_pd;
 
-	/* Build the list of capacity states for this performance domain */
+	/* Build the list of performance states for this performance domain */
 	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
 		/*
 		 * active_power() is a driver callback which ceils 'freq' to
-		 * lowest capacity state of 'cpu' above 'freq' and updates
+		 * lowest performance state of 'cpu' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
 		ret = cb->active_power(&power, &freq, cpu);
 		if (ret) {
-			pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
-			goto free_cs_table;
+			pr_err("pd%d: invalid perf. state: %d\n", cpu, ret);
+			goto free_ps_table;
 		}
 
 		/*
 		 * We expect the driver callback to increase the frequency for
-		 * higher capacity states.
+		 * higher performance states.
 		 */
 		if (freq <= prev_freq) {
 			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
-			goto free_cs_table;
+			goto free_ps_table;
 		}
 
 		/*
@@ -127,7 +127,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 		 */
 		if (!power || power > EM_CPU_MAX_POWER) {
 			pr_err("pd%d: invalid power: %lu\n", cpu, power);
-			goto free_cs_table;
+			goto free_ps_table;
 		}
 
 		table[i].power = power;
@@ -141,12 +141,12 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 		 */
 		opp_eff = freq / power;
 		if (opp_eff >= prev_opp_eff)
-			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
+			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
 					cpu, i, i - 1);
 		prev_opp_eff = opp_eff;
 	}
 
-	/* Compute the cost of each capacity_state. */
+	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
 	for (i = 0; i < nr_states; i++) {
 		table[i].cost = div64_u64(fmax * table[i].power,
@@ -154,14 +154,14 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 	}
 
 	pd->table = table;
-	pd->nr_cap_states = nr_states;
+	pd->nr_perf_states = nr_states;
 	cpumask_copy(to_cpumask(pd->cpus), span);
 
 	em_debug_create_pd(pd, cpu);
 
 	return pd;
 
-free_cs_table:
+free_ps_table:
 	kfree(table);
 free_pd:
 	kfree(pd);
@@ -185,7 +185,7 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
 /**
  * em_register_perf_domain() - Register the Energy Model of a performance domain
  * @span	: Mask of CPUs in the performance domain
- * @nr_states	: Number of capacity states to register
+ * @nr_states	: Number of performance states to register
  * @cb		: Callback functions providing the data of the Energy Model
  *
  * Create Energy Model tables for a performance domain using the callbacks
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ba81187bb7af..2f91d3126365 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -272,10 +272,10 @@ static void perf_domain_debug(const struct cpumask *cpu_map,
 	printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
 
 	while (pd) {
-		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_pstate=%d }",
 				cpumask_first(perf_domain_span(pd)),
 				cpumask_pr_args(perf_domain_span(pd)),
-				em_pd_nr_cap_states(pd->em_pd));
+				em_pd_nr_perf_states(pd->em_pd));
 		pd = pd->next;
 	}
 
@@ -313,26 +313,26 @@ static void sched_energy_set(bool has_eas)
  *
  * The complexity of the Energy Model is defined as:
  *
- *              C = nr_pd * (nr_cpus + nr_cs)
+ *              C = nr_pd * (nr_cpus + nr_ps)
  *
  * with parameters defined as:
  *  - nr_pd:    the number of performance domains
  *  - nr_cpus:  the number of CPUs
- *  - nr_cs:    the sum of the number of capacity states of all performance
+ *  - nr_ps:    the sum of the number of performance states of all performance
  *              domains (for example, on a system with 2 performance domains,
- *              with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *              with 10 performance states each, nr_ps = 2 * 10 = 20).
  *
  * It is generally not a good idea to use such a model in the wake-up path on
  * very complex platforms because of the associated scheduling overheads. The
  * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
- * with per-CPU DVFS and less than 8 capacity states each, for example.
+ * with per-CPU DVFS and less than 8 performance states each, for example.
  */
 #define EM_MAX_COMPLEXITY 2048
 
 extern struct cpufreq_governor schedutil_gov;
 static bool build_perf_domains(const struct cpumask *cpu_map)
 {
-	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+	int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
@@ -384,15 +384,15 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		pd = tmp;
 
 		/*
-		 * Count performance domains and capacity states for the
+		 * Count performance domains and performance states for the
 		 * complexity check.
 		 */
 		nr_pd++;
-		nr_cs += em_pd_nr_cap_states(pd->em_pd);
+		nr_ps += em_pd_nr_perf_states(pd->em_pd);
 	}
 
 	/* Bail out if the Energy Model complexity is too high. */
-	if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+	if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) {
 		WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
 						cpumask_pr_args(cpu_map));
 		goto free;
-- 
cgit v1.2.3


From 7d9895c7fbfc9c70afce7029b7de0f3f974adb88 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:48 +0100
Subject: PM / EM: introduce em_dev_register_perf_domain function

Add now function in the Energy Model framework which is going to support
new devices. This function will help in transition and make it smoother.
For now it still checks if the cpumask is a valid pointer, which will be
removed later when the new structures and infrastructure will be ready.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 13 +++++++++++--
 kernel/power/energy_model.c  | 40 ++++++++++++++++++++++++++++++++++------
 2 files changed, 45 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index fe336a9eb5d4..7c048df98447 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_ENERGY_MODEL_H
 #define _LINUX_ENERGY_MODEL_H
 #include <linux/cpumask.h>
+#include <linux/device.h>
 #include <linux/jump_label.h>
 #include <linux/kobject.h>
 #include <linux/rcupdate.h>
@@ -42,7 +43,7 @@ struct em_perf_domain {
 #define em_span_cpus(em) (to_cpumask((em)->cpus))
 
 #ifdef CONFIG_ENERGY_MODEL
-#define EM_CPU_MAX_POWER 0xFFFF
+#define EM_MAX_POWER 0xFFFF
 
 struct em_data_callback {
 	/**
@@ -59,7 +60,7 @@ struct em_data_callback {
 	 * and frequency.
 	 *
 	 * The power is the one of a single CPU in the domain, expressed in
-	 * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER]
+	 * milli-watts. It is expected to fit in the [0, EM_MAX_POWER]
 	 * range.
 	 *
 	 * Return 0 on success.
@@ -71,6 +72,8 @@ struct em_data_callback {
 struct em_perf_domain *em_cpu_get(int cpu);
 int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 						struct em_data_callback *cb);
+int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
+				struct em_data_callback *cb, cpumask_t *span);
 
 /**
  * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain
@@ -174,6 +177,12 @@ static inline int em_register_perf_domain(cpumask_t *span,
 {
 	return -EINVAL;
 }
+static inline
+int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
+				struct em_data_callback *cb, cpumask_t *span)
+{
+	return -EINVAL;
+}
 static inline struct em_perf_domain *em_cpu_get(int cpu)
 {
 	return NULL;
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 9892d548a0fa..875b163e54ab 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -125,7 +125,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 		 * The power returned by active_state() is expected to be
 		 * positive, in milli-watts and to fit into 16 bits.
 		 */
-		if (!power || power > EM_CPU_MAX_POWER) {
+		if (!power || power > EM_MAX_POWER) {
 			pr_err("pd%d: invalid power: %lu\n", cpu, power);
 			goto free_ps_table;
 		}
@@ -183,10 +183,13 @@ struct em_perf_domain *em_cpu_get(int cpu)
 EXPORT_SYMBOL_GPL(em_cpu_get);
 
 /**
- * em_register_perf_domain() - Register the Energy Model of a performance domain
- * @span	: Mask of CPUs in the performance domain
+ * em_dev_register_perf_domain() - Register the Energy Model (EM) for a device
+ * @dev		: Device for which the EM is to register
  * @nr_states	: Number of performance states to register
  * @cb		: Callback functions providing the data of the Energy Model
+ * @span	: Pointer to cpumask_t, which in case of a CPU device is
+ *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
+ *		type of devices this should be set to NULL.
  *
  * Create Energy Model tables for a performance domain using the callbacks
  * defined in cb.
@@ -196,14 +199,14 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  *
  * Return 0 on success
  */
-int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
-						struct em_data_callback *cb)
+int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
+				struct em_data_callback *cb, cpumask_t *span)
 {
 	unsigned long cap, prev_cap = 0;
 	struct em_perf_domain *pd;
 	int cpu, ret = 0;
 
-	if (!span || !nr_states || !cb)
+	if (!dev || !span || !nr_states || !cb)
 		return -EINVAL;
 
 	/*
@@ -255,4 +258,29 @@ unlock:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+
+/**
+ * em_register_perf_domain() - Register the Energy Model of a performance domain
+ * @span	: Mask of CPUs in the performance domain
+ * @nr_states	: Number of capacity states to register
+ * @cb		: Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same performance domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb)
+{
+	struct device *cpu_dev;
+
+	cpu_dev = get_cpu_device(cpumask_first(span));
+
+	return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span);
+}
 EXPORT_SYMBOL_GPL(em_register_perf_domain);
-- 
cgit v1.2.3


From d0351cc3b0f57214d157e4d589564730af2aedae Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:49 +0100
Subject: PM / EM: update callback structure and add device pointer

The Energy Model framework is going to support devices other that CPUs. In
order to make this happen change the callback function and add pointer to
a device as an argument.

Update the related users to use new function and new callback from the
Energy Model.

Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/scmi-cpufreq.c | 11 +++--------
 drivers/opp/of.c               |  9 ++-------
 include/linux/energy_model.h   | 15 ++++++++-------
 kernel/power/energy_model.c    |  9 +++++----
 4 files changed, 18 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 61623e2ff149..11ee24e06d12 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -103,17 +103,12 @@ scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 }
 
 static int __maybe_unused
-scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, int cpu)
+scmi_get_cpu_power(unsigned long *power, unsigned long *KHz,
+		   struct device *cpu_dev)
 {
-	struct device *cpu_dev = get_cpu_device(cpu);
 	unsigned long Hz;
 	int ret, domain;
 
-	if (!cpu_dev) {
-		pr_err("failed to get cpu%d device\n", cpu);
-		return -ENODEV;
-	}
-
 	domain = handle->perf_ops->device_domain_id(cpu_dev);
 	if (domain < 0)
 		return domain;
@@ -200,7 +195,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->fast_switch_possible = true;
 
-	em_register_perf_domain(policy->cpus, nr_opp, &em_cb);
+	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus);
 
 	return 0;
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 9a5873591a40..e273f419a4bf 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1216,9 +1216,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
  * calculation failed because of missing parameters, 0 otherwise.
  */
 static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
-					 int cpu)
+					 struct device *cpu_dev)
 {
-	struct device *cpu_dev;
 	struct dev_pm_opp *opp;
 	struct device_node *np;
 	unsigned long mV, Hz;
@@ -1226,10 +1225,6 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
 	u64 tmp;
 	int ret;
 
-	cpu_dev = get_cpu_device(cpu);
-	if (!cpu_dev)
-		return -ENODEV;
-
 	np = of_node_get(cpu_dev->of_node);
 	if (!np)
 		return -EINVAL;
@@ -1297,6 +1292,6 @@ void dev_pm_opp_of_register_em(struct cpumask *cpus)
 	if (ret || !cap)
 		return;
 
-	em_register_perf_domain(cpus, nr_opp, &em_cb);
+	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, cpus);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em);
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 7c048df98447..7076cb22b247 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -48,24 +48,25 @@ struct em_perf_domain {
 struct em_data_callback {
 	/**
 	 * active_power() - Provide power at the next performance state of
-	 *		a CPU
+	 *		a device
 	 * @power	: Active power at the performance state in mW
 	 *		(modified)
 	 * @freq	: Frequency at the performance state in kHz
 	 *		(modified)
-	 * @cpu		: CPU for which we do this operation
+	 * @dev		: Device for which we do this operation (can be a CPU)
 	 *
-	 * active_power() must find the lowest performance state of 'cpu' above
+	 * active_power() must find the lowest performance state of 'dev' above
 	 * 'freq' and update 'power' and 'freq' to the matching active power
 	 * and frequency.
 	 *
-	 * The power is the one of a single CPU in the domain, expressed in
-	 * milli-watts. It is expected to fit in the [0, EM_MAX_POWER]
-	 * range.
+	 * In case of CPUs, the power is the one of a single CPU in the domain,
+	 * expressed in milli-watts. It is expected to fit in the
+	 * [0, EM_MAX_POWER] range.
 	 *
 	 * Return 0 on success.
 	 */
-	int (*active_power)(unsigned long *power, unsigned long *freq, int cpu);
+	int (*active_power)(unsigned long *power, unsigned long *freq,
+			    struct device *dev);
 };
 #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
 
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 875b163e54ab..5b8a1566526a 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -78,8 +78,9 @@ core_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
 static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {}
 #endif
-static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
-						struct em_data_callback *cb)
+static struct em_perf_domain *
+em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
+	     cpumask_t *span)
 {
 	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
 	unsigned long power, freq, prev_freq = 0;
@@ -106,7 +107,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 		 * lowest performance state of 'cpu' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, cpu);
+		ret = cb->active_power(&power, &freq, dev);
 		if (ret) {
 			pr_err("pd%d: invalid perf. state: %d\n", cpu, ret);
 			goto free_ps_table;
@@ -237,7 +238,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 	}
 
 	/* Create the performance domain and add it to the Energy Model. */
-	pd = em_create_pd(span, nr_states, cb);
+	pd = em_create_pd(dev, nr_states, cb, span);
 	if (!pd) {
 		ret = -EINVAL;
 		goto unlock;
-- 
cgit v1.2.3


From c3077b5d97a39223a2d4b95a21ccff660836170f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Jun 2020 08:44:41 +0200
Subject: blk-mq: merge blk-softirq.c into blk-mq.c

__blk_complete_request is only called from the blk-mq code, and
duplicates a lot of code from blk-mq.c.  Move it there to prepare
for better code sharing and simplifications.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Makefile         |   2 +-
 block/blk-mq.c         | 135 ++++++++++++++++++++++++++++++++++++++++++
 block/blk-softirq.c    | 156 -------------------------------------------------
 include/linux/blkdev.h |   1 -
 4 files changed, 136 insertions(+), 158 deletions(-)
 delete mode 100644 block/blk-softirq.c

(limited to 'include/linux')

diff --git a/block/Makefile b/block/Makefile
index 78719169fb2a..8d841f5f986f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 
 obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
-			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
+			blk-exec.o blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a9aa6d1e44cf..60febbf6f8d9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -41,6 +41,8 @@
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
 
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
@@ -574,6 +576,130 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
+/*
+ * Softirq action handler - move entries to local list and loop over them
+ * while passing them to the queue registered handler.
+ */
+static __latent_entropy void blk_done_softirq(struct softirq_action *h)
+{
+	struct list_head *cpu_list, local_list;
+
+	local_irq_disable();
+	cpu_list = this_cpu_ptr(&blk_cpu_done);
+	list_replace_init(cpu_list, &local_list);
+	local_irq_enable();
+
+	while (!list_empty(&local_list)) {
+		struct request *rq;
+
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
+		rq->q->mq_ops->complete(rq);
+	}
+}
+
+#ifdef CONFIG_SMP
+static void trigger_softirq(void *data)
+{
+	struct request *rq = data;
+	struct list_head *list;
+
+	list = this_cpu_ptr(&blk_cpu_done);
+	list_add_tail(&rq->ipi_list, list);
+
+	if (list->next == &rq->ipi_list)
+		raise_softirq_irqoff(BLOCK_SOFTIRQ);
+}
+
+/*
+ * Setup and invoke a run of 'trigger_softirq' on the given cpu.
+ */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	if (cpu_online(cpu)) {
+		call_single_data_t *data = &rq->csd;
+
+		data->func = trigger_softirq;
+		data->info = rq;
+		data->flags = 0;
+
+		smp_call_function_single_async(cpu, data);
+		return 0;
+	}
+
+	return 1;
+}
+#else /* CONFIG_SMP */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	return 1;
+}
+#endif
+
+static int blk_softirq_cpu_dead(unsigned int cpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	local_irq_disable();
+	list_splice_init(&per_cpu(blk_cpu_done, cpu),
+			 this_cpu_ptr(&blk_cpu_done));
+	raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void __blk_complete_request(struct request *req)
+{
+	struct request_queue *q = req->q;
+	int cpu, ccpu = req->mq_ctx->cpu;
+	unsigned long flags;
+	bool shared = false;
+
+	BUG_ON(!q->mq_ops->complete);
+
+	local_irq_save(flags);
+	cpu = smp_processor_id();
+
+	/*
+	 * Select completion CPU
+	 */
+	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) {
+		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
+			shared = cpus_share_cache(cpu, ccpu);
+	} else
+		ccpu = cpu;
+
+	/*
+	 * If current CPU and requested CPU share a cache, run the softirq on
+	 * the current CPU. One might concern this is just like
+	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
+	 * running in interrupt handler, and currently I/O controller doesn't
+	 * support multiple interrupts, so current CPU is unique actually. This
+	 * avoids IPI sending from current CPU to the first CPU of a group.
+	 */
+	if (ccpu == cpu || shared) {
+		struct list_head *list;
+do_local:
+		list = this_cpu_ptr(&blk_cpu_done);
+		list_add_tail(&req->ipi_list, list);
+
+		/*
+		 * if the list only contains our just added request,
+		 * signal a raise of the softirq. If there are already
+		 * entries there, someone already raised the irq but it
+		 * hasn't run yet.
+		 */
+		if (list->next == &req->ipi_list)
+			raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	} else if (raise_blk_irq(ccpu, req))
+		goto do_local;
+
+	local_irq_restore(flags);
+}
+
 static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
@@ -3760,6 +3886,15 @@ EXPORT_SYMBOL(blk_mq_rq_cpu);
 
 static int __init blk_mq_init(void)
 {
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
+
+	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
+				  "block/softirq:dead", NULL,
+				  blk_softirq_cpu_dead);
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 	cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
deleted file mode 100644
index 6e7ec87d49fa..000000000000
--- a/block/blk-softirq.c
+++ /dev/null
@@ -1,156 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Functions related to softirq rq completions
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/cpu.h>
-#include <linux/sched.h>
-#include <linux/sched/topology.h>
-
-#include "blk.h"
-
-static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
-
-/*
- * Softirq action handler - move entries to local list and loop over them
- * while passing them to the queue registered handler.
- */
-static __latent_entropy void blk_done_softirq(struct softirq_action *h)
-{
-	struct list_head *cpu_list, local_list;
-
-	local_irq_disable();
-	cpu_list = this_cpu_ptr(&blk_cpu_done);
-	list_replace_init(cpu_list, &local_list);
-	local_irq_enable();
-
-	while (!list_empty(&local_list)) {
-		struct request *rq;
-
-		rq = list_entry(local_list.next, struct request, ipi_list);
-		list_del_init(&rq->ipi_list);
-		rq->q->mq_ops->complete(rq);
-	}
-}
-
-#ifdef CONFIG_SMP
-static void trigger_softirq(void *data)
-{
-	struct request *rq = data;
-	struct list_head *list;
-
-	list = this_cpu_ptr(&blk_cpu_done);
-	list_add_tail(&rq->ipi_list, list);
-
-	if (list->next == &rq->ipi_list)
-		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-}
-
-/*
- * Setup and invoke a run of 'trigger_softirq' on the given cpu.
- */
-static int raise_blk_irq(int cpu, struct request *rq)
-{
-	if (cpu_online(cpu)) {
-		call_single_data_t *data = &rq->csd;
-
-		data->func = trigger_softirq;
-		data->info = rq;
-		data->flags = 0;
-
-		smp_call_function_single_async(cpu, data);
-		return 0;
-	}
-
-	return 1;
-}
-#else /* CONFIG_SMP */
-static int raise_blk_irq(int cpu, struct request *rq)
-{
-	return 1;
-}
-#endif
-
-static int blk_softirq_cpu_dead(unsigned int cpu)
-{
-	/*
-	 * If a CPU goes away, splice its entries to the current CPU
-	 * and trigger a run of the softirq
-	 */
-	local_irq_disable();
-	list_splice_init(&per_cpu(blk_cpu_done, cpu),
-			 this_cpu_ptr(&blk_cpu_done));
-	raise_softirq_irqoff(BLOCK_SOFTIRQ);
-	local_irq_enable();
-
-	return 0;
-}
-
-void __blk_complete_request(struct request *req)
-{
-	struct request_queue *q = req->q;
-	int cpu, ccpu = req->mq_ctx->cpu;
-	unsigned long flags;
-	bool shared = false;
-
-	BUG_ON(!q->mq_ops->complete);
-
-	local_irq_save(flags);
-	cpu = smp_processor_id();
-
-	/*
-	 * Select completion CPU
-	 */
-	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) {
-		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
-			shared = cpus_share_cache(cpu, ccpu);
-	} else
-		ccpu = cpu;
-
-	/*
-	 * If current CPU and requested CPU share a cache, run the softirq on
-	 * the current CPU. One might concern this is just like
-	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
-	 * running in interrupt handler, and currently I/O controller doesn't
-	 * support multiple interrupts, so current CPU is unique actually. This
-	 * avoids IPI sending from current CPU to the first CPU of a group.
-	 */
-	if (ccpu == cpu || shared) {
-		struct list_head *list;
-do_local:
-		list = this_cpu_ptr(&blk_cpu_done);
-		list_add_tail(&req->ipi_list, list);
-
-		/*
-		 * if the list only contains our just added request,
-		 * signal a raise of the softirq. If there are already
-		 * entries there, someone already raised the irq but it
-		 * hasn't run yet.
-		 */
-		if (list->next == &req->ipi_list)
-			raise_softirq_irqoff(BLOCK_SOFTIRQ);
-	} else if (raise_blk_irq(ccpu, req))
-		goto do_local;
-
-	local_irq_restore(flags);
-}
-
-static __init int blk_softirq_init(void)
-{
-	int i;
-
-	for_each_possible_cpu(i)
-		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
-
-	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
-				  "block/softirq:dead", NULL,
-				  blk_softirq_cpu_dead);
-	return 0;
-}
-subsys_initcall(blk_softirq_init);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8fd900998b4e..98712cfc7a34 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1078,7 +1078,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq);
 extern bool blk_update_request(struct request *rq, blk_status_t error,
 			       unsigned int nr_bytes);
 
-extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 
 /*
-- 
cgit v1.2.3


From 15f73f5b3e5958f2d169fe13c420eeeeae07bbf2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Jun 2020 08:44:47 +0200
Subject: blk-mq: move failure injection out of blk_mq_complete_request

Move the call to blk_should_fake_timeout out of blk_mq_complete_request
and into the drivers, skipping call sites that are obvious error
handlers, and remove the now superflous blk_mq_force_complete_rq helper.
This ensures we don't keep injecting errors into completions that just
terminate the Linux request after the hardware has been reset or the
command has been aborted.

Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c                    | 34 +++++++---------------------------
 block/blk-timeout.c               |  6 ++----
 block/blk.h                       |  9 ---------
 block/bsg-lib.c                   |  5 ++++-
 drivers/block/loop.c              |  6 ++++--
 drivers/block/mtip32xx/mtip32xx.c |  3 ++-
 drivers/block/nbd.c               |  5 ++++-
 drivers/block/null_blk_main.c     |  5 +++--
 drivers/block/skd_main.c          |  9 ++++++---
 drivers/block/virtio_blk.c        |  3 ++-
 drivers/block/xen-blkfront.c      |  3 ++-
 drivers/md/dm-rq.c                |  3 ++-
 drivers/mmc/core/block.c          |  8 ++++----
 drivers/nvme/host/core.c          |  2 +-
 drivers/nvme/host/nvme.h          |  3 ++-
 drivers/s390/block/dasd.c         |  2 +-
 drivers/s390/block/scm_blk.c      |  3 ++-
 drivers/scsi/scsi_lib.c           | 12 +++---------
 include/linux/blk-mq.h            | 12 ++++++++++--
 19 files changed, 61 insertions(+), 72 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ce772ab19188..3f4f227cf830 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -655,16 +655,13 @@ static void __blk_mq_complete_request_remote(void *data)
 }
 
 /**
- * blk_mq_force_complete_rq() - Force complete the request, bypassing any error
- * 				injection that could drop the completion.
- * @rq: Request to be force completed
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
  *
- * Drivers should use blk_mq_complete_request() to complete requests in their
- * normal IO path. For timeout error recovery, drivers may call this forced
- * completion routine after they've reclaimed timed out requests to bypass
- * potentially subsequent fake timeouts.
- */
-void blk_mq_force_complete_rq(struct request *rq)
+ * Description:
+ *	Complete a request by scheduling the ->complete_rq operation.
+ **/
+void blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
@@ -702,7 +699,7 @@ void blk_mq_force_complete_rq(struct request *rq)
 	}
 	put_cpu();
 }
-EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq);
+EXPORT_SYMBOL(blk_mq_complete_request);
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
 	__releases(hctx->srcu)
@@ -724,23 +721,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
 		*srcu_idx = srcu_read_lock(hctx->srcu);
 }
 
-/**
- * blk_mq_complete_request - end I/O on a request
- * @rq:		the request being processed
- *
- * Description:
- *	Ends all I/O on a request. It does not handle partial completions.
- *	The actual completion happens out-of-order, through a IPI handler.
- **/
-bool blk_mq_complete_request(struct request *rq)
-{
-	if (unlikely(blk_should_fake_timeout(rq->q)))
-		return false;
-	blk_mq_force_complete_rq(rq);
-	return true;
-}
-EXPORT_SYMBOL(blk_mq_complete_request);
-
 /**
  * blk_mq_start_request - Start processing a request
  * @rq: Pointer to request to be started
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 8aa68fae96ad..3a1ac6434758 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -20,13 +20,11 @@ static int __init setup_fail_io_timeout(char *str)
 }
 __setup("fail_io_timeout=", setup_fail_io_timeout);
 
-int blk_should_fake_timeout(struct request_queue *q)
+bool __blk_should_fake_timeout(struct request_queue *q)
 {
-	if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
-		return 0;
-
 	return should_fail(&fail_io_timeout, 1);
 }
+EXPORT_SYMBOL_GPL(__blk_should_fake_timeout);
 
 static int __init fail_io_timeout_debugfs(void)
 {
diff --git a/block/blk.h b/block/blk.h
index b5d1f0fc6547..8ba4a5e4fe07 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -223,18 +223,9 @@ ssize_t part_fail_show(struct device *dev, struct device_attribute *attr,
 		char *buf);
 ssize_t part_fail_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count);
-
-#ifdef CONFIG_FAIL_IO_TIMEOUT
-int blk_should_fake_timeout(struct request_queue *);
 ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
-#else
-static inline int blk_should_fake_timeout(struct request_queue *q)
-{
-	return 0;
-}
-#endif
 
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 6cbb7926534c..fb7b347f8010 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -181,9 +181,12 @@ EXPORT_SYMBOL_GPL(bsg_job_get);
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len)
 {
+	struct request *rq = blk_mq_rq_from_pdu(job);
+
 	job->result = result;
 	job->reply_payload_rcv_len = reply_payload_rcv_len;
-	blk_mq_complete_request(blk_mq_rq_from_pdu(job));
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 EXPORT_SYMBOL_GPL(bsg_job_done);
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 475e1a738560..4acae248790c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -509,7 +509,8 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
-	blk_mq_complete_request(rq);
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -2048,7 +2049,8 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 			cmd->ret = ret;
 		else
 			cmd->ret = ret ? -EIO : 0;
-		blk_mq_complete_request(rq);
+		if (likely(!blk_should_fake_timeout(rq->q)))
+			blk_mq_complete_request(rq);
 	}
 }
 
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index f6bafa9a68b9..153e2cdecb4d 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -492,7 +492,8 @@ static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status)
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 
 	cmd->status = status;
-	blk_mq_complete_request(req);
+	if (likely(!blk_should_fake_timeout(req->q)))
+		blk_mq_complete_request(req);
 }
 
 /*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 43cff01a5a67..01794cd2b6ca 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -784,6 +784,7 @@ static void recv_work(struct work_struct *work)
 	struct nbd_device *nbd = args->nbd;
 	struct nbd_config *config = nbd->config;
 	struct nbd_cmd *cmd;
+	struct request *rq;
 
 	while (1) {
 		cmd = nbd_read_stat(nbd, args->index);
@@ -796,7 +797,9 @@ static void recv_work(struct work_struct *work)
 			break;
 		}
 
-		blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
+		rq = blk_mq_rq_from_pdu(cmd);
+		if (likely(!blk_should_fake_timeout(rq->q)))
+			blk_mq_complete_request(rq);
 	}
 	atomic_dec(&config->recv_threads);
 	wake_up(&config->recv_wq);
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 87b31f9ca362..82259242b9b5 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -1283,7 +1283,8 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	case NULL_IRQ_SOFTIRQ:
 		switch (cmd->nq->dev->queue_mode) {
 		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
+			if (likely(!blk_should_fake_timeout(cmd->rq->q)))
+				blk_mq_complete_request(cmd->rq);
 			break;
 		case NULL_Q_BIO:
 			/*
@@ -1423,7 +1424,7 @@ static bool should_requeue_request(struct request *rq)
 static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
 {
 	pr_info("rq %p timed out\n", rq);
-	blk_mq_force_complete_rq(rq);
+	blk_mq_complete_request(rq);
 	return BLK_EH_DONE;
 }
 
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 51569c199a6c..3a476dc1d14f 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -1417,7 +1417,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 	case SKD_CHECK_STATUS_REPORT_GOOD:
 	case SKD_CHECK_STATUS_REPORT_SMART_ALERT:
 		skreq->status = BLK_STS_OK;
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 		break;
 
 	case SKD_CHECK_STATUS_BUSY_IMMINENT:
@@ -1440,7 +1441,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 	case SKD_CHECK_STATUS_REPORT_ERROR:
 	default:
 		skreq->status = BLK_STS_IOERR;
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 		break;
 	}
 }
@@ -1560,7 +1562,8 @@ static int skd_isr_completion_posted(struct skd_device *skdev,
 		 */
 		if (likely(cmp_status == SAM_STAT_GOOD)) {
 			skreq->status = BLK_STS_OK;
-			blk_mq_complete_request(rq);
+			if (likely(!blk_should_fake_timeout(rq->q)))
+				blk_mq_complete_request(rq);
 		} else {
 			skd_resolve_req_exception(skdev, skreq, rq);
 		}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 9d21bf0f155e..741804bd8a14 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -171,7 +171,8 @@ static void virtblk_done(struct virtqueue *vq)
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
 			struct request *req = blk_mq_rq_from_pdu(vbr);
 
-			blk_mq_complete_request(req);
+			if (likely(!blk_should_fake_timeout(req->q)))
+				blk_mq_complete_request(req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3b889ea950c2..3bb3dd8da9b0 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1655,7 +1655,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			BUG();
 		}
 
-		blk_mq_complete_request(req);
+		if (likely(!blk_should_fake_timeout(req->q)))
+			blk_mq_complete_request(req);
 	}
 
 	rinfo->ring.rsp_cons = i;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index f60c02512121..5aec1cd09348 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -288,7 +288,8 @@ static void dm_complete_request(struct request *rq, blk_status_t error)
 	struct dm_rq_target_io *tio = tio_from_request(rq);
 
 	tio->error = error;
-	blk_mq_complete_request(rq);
+	if (likely(!blk_should_fake_timeout(rq->q)))
+		blk_mq_complete_request(rq);
 }
 
 /*
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 7896952de1ac..4791c82f8f7c 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1446,7 +1446,7 @@ static void mmc_blk_cqe_req_done(struct mmc_request *mrq)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 }
 
@@ -1926,7 +1926,7 @@ static void mmc_blk_hsq_req_done(struct mmc_request *mrq)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 }
 
@@ -1936,7 +1936,7 @@ void mmc_blk_mq_complete(struct request *req)
 
 	if (mq->use_cqe)
 		mmc_blk_cqe_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		mmc_blk_mq_complete_rq(mq, req);
 }
 
@@ -1988,7 +1988,7 @@ static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req)
 	 */
 	if (mq->in_recovery)
 		mmc_blk_mq_complete_rq(mq, req);
-	else
+	else if (likely(!blk_should_fake_timeout(req->q)))
 		blk_mq_complete_request(req);
 
 	mmc_blk_mq_dec_in_flight(mq, req);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2c5bc4fb702..6810c8812aed 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -304,7 +304,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
-	blk_mq_force_complete_rq(req);
+	blk_mq_complete_request(req);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c0f4226d3299..034613205701 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -481,7 +481,8 @@ static inline void nvme_end_request(struct request *req, __le16 status,
 	rq->result = result;
 	/* inject error when permitted by fault injection framework */
 	nvme_should_fail(req);
-	blk_mq_complete_request(req);
+	if (likely(!blk_should_fake_timeout(req->q)))
+		blk_mq_complete_request(req);
 }
 
 static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index cf87eb27879f..eb17fea8075c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2802,7 +2802,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr)
 			blk_update_request(req, BLK_STS_OK,
 					   blk_rq_bytes(req) - proc_bytes);
 			blk_mq_requeue_request(req, true);
-		} else {
+		} else if (likely(!blk_should_fake_timeout(req->q))) {
 			blk_mq_complete_request(req);
 		}
 	}
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index e01889394c84..a4f6f2e62b1d 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -256,7 +256,8 @@ static void scm_request_finish(struct scm_request *scmrq)
 	for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
 		error = blk_mq_rq_to_pdu(scmrq->request[i]);
 		*error = scmrq->error;
-		blk_mq_complete_request(scmrq->request[i]);
+		if (likely(!blk_should_fake_timeout(scmrq->request[i]->q)))
+			blk_mq_complete_request(scmrq->request[i]);
 	}
 
 	atomic_dec(&bdev->queued_reqs);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0ba7a65e7c8d..6ca91d09eca1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1589,18 +1589,12 @@ static blk_status_t scsi_mq_prep_fn(struct request *req)
 
 static void scsi_mq_done(struct scsi_cmnd *cmd)
 {
+	if (unlikely(blk_should_fake_timeout(cmd->request->q)))
+		return;
 	if (unlikely(test_and_set_bit(SCMD_STATE_COMPLETE, &cmd->state)))
 		return;
 	trace_scsi_dispatch_cmd_done(cmd);
-
-	/*
-	 * If the block layer didn't complete the request due to a timeout
-	 * injection, scsi must clear its internal completed state so that the
-	 * timeout handler will see it needs to escalate its own error
-	 * recovery.
-	 */
-	if (unlikely(!blk_mq_complete_request(cmd->request)))
-		clear_bit(SCMD_STATE_COMPLETE, &cmd->state);
+	blk_mq_complete_request(cmd->request);
 }
 
 static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index d6fcae17da5a..8e6ab766aef7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -503,8 +503,7 @@ void __blk_mq_end_request(struct request *rq, blk_status_t error);
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
-bool blk_mq_complete_request(struct request *rq);
-void blk_mq_force_complete_rq(struct request *rq);
+void blk_mq_complete_request(struct request *rq);
 bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
 			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
@@ -537,6 +536,15 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
 unsigned int blk_mq_rq_cpu(struct request *rq);
 
+bool __blk_should_fake_timeout(struct request_queue *q);
+static inline bool blk_should_fake_timeout(struct request_queue *q)
+{
+	if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) &&
+	    test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
+		return __blk_should_fake_timeout(q);
+	return false;
+}
+
 /**
  * blk_mq_rq_from_pdu - cast a PDU to a request
  * @pdu: the PDU (Protocol Data Unit) to be casted
-- 
cgit v1.2.3


From 40d09b53bfc557af7481b9d80f060a7ac9c7d314 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Jun 2020 08:44:50 +0200
Subject: blk-mq: add a new blk_mq_complete_request_remote API

This is a variant of blk_mq_complete_request_remote that only completes
the request if it needs to be bounced to another CPU or a softirq.  If
the request can be completed locally the function returns false and lets
the driver complete it without requring and indirect function call.

Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         | 45 ++++++++++++++++++++++++++-------------------
 include/linux/blk-mq.h |  1 +
 2 files changed, 27 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 961635b40999..b8738b3c6d06 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -632,8 +632,11 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
 	return 0;
 }
 
-static void __blk_mq_complete_request(struct request *rq)
+
+static void __blk_mq_complete_request_remote(void *data)
 {
+	struct request *rq = data;
+
 	/*
 	 * For most of single queue controllers, there is only one irq vector
 	 * for handling I/O completion, and the only irq's affinity is set
@@ -649,11 +652,6 @@ static void __blk_mq_complete_request(struct request *rq)
 		rq->q->mq_ops->complete(rq);
 }
 
-static void __blk_mq_complete_request_remote(void *data)
-{
-	__blk_mq_complete_request(data);
-}
-
 static inline bool blk_mq_complete_need_ipi(struct request *rq)
 {
 	int cpu = raw_smp_processor_id();
@@ -672,14 +670,7 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	return cpu_online(rq->mq_ctx->cpu);
 }
 
-/**
- * blk_mq_complete_request - end I/O on a request
- * @rq:		the request being processed
- *
- * Description:
- *	Complete a request by scheduling the ->complete_rq operation.
- **/
-void blk_mq_complete_request(struct request *rq)
+bool blk_mq_complete_request_remote(struct request *rq)
 {
 	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 
@@ -687,10 +678,8 @@ void blk_mq_complete_request(struct request *rq)
 	 * For a polled request, always complete locallly, it's pointless
 	 * to redirect the completion.
 	 */
-	if (rq->cmd_flags & REQ_HIPRI) {
-		rq->q->mq_ops->complete(rq);
-		return;
-	}
+	if (rq->cmd_flags & REQ_HIPRI)
+		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
 		rq->csd.func = __blk_mq_complete_request_remote;
@@ -698,8 +687,26 @@ void blk_mq_complete_request(struct request *rq)
 		rq->csd.flags = 0;
 		smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd);
 	} else {
-		__blk_mq_complete_request(rq);
+		if (rq->q->nr_hw_queues > 1)
+			return false;
+		blk_mq_trigger_softirq(rq);
 	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);
+
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Complete a request by scheduling the ->complete_rq operation.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (!blk_mq_complete_request_remote(rq))
+		rq->q->mq_ops->complete(rq);
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8e6ab766aef7..1641ec6cd7e5 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -504,6 +504,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
+bool blk_mq_complete_request_remote(struct request *rq);
 bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
 			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
-- 
cgit v1.2.3


From e8c7d14ac6c37c173ec606907d38802b00302988 Mon Sep 17 00:00:00 2001
From: Luis Chamberlain <mcgrof@kernel.org>
Date: Fri, 19 Jun 2020 20:47:25 +0000
Subject: block: revert back to synchronous request_queue removal

Commit dc9edc44de6c ("block: Fix a blk_exit_rl() regression") merged on
v4.12 moved the work behind blk_release_queue() into a workqueue after a
splat floated around which indicated some work on blk_release_queue()
could sleep in blk_exit_rl(). This splat would be possible when a driver
called blk_put_queue() or blk_cleanup_queue() (which calls blk_put_queue()
as its final call) from an atomic context.

blk_put_queue() decrements the refcount for the request_queue kobject, and
upon reaching 0 blk_release_queue() is called. Although blk_exit_rl() is
now removed through commit db6d99523560 ("block: remove request_list code")
on v5.0, we reserve the right to be able to sleep within
blk_release_queue() context.

The last reference for the request_queue must not be called from atomic
context. *When* the last reference to the request_queue reaches 0 varies,
and so let's take the opportunity to document when that is expected to
happen and also document the context of the related calls as best as
possible so we can avoid future issues, and with the hopes that the
synchronous request_queue removal sticks.

We revert back to synchronous request_queue removal because asynchronous
removal creates a regression with expected userspace interaction with
several drivers. An example is when removing the loopback driver, one
uses ioctls from userspace to do so, but upon return and if successful,
one expects the device to be removed. Likewise if one races to add another
device the new one may not be added as it is still being removed. This was
expected behavior before and it now fails as the device is still present
and busy still. Moving to asynchronous request_queue removal could have
broken many scripts which relied on the removal to have been completed if
there was no error. Document this expectation as well so that this
doesn't regress userspace again.

Using asynchronous request_queue removal however has helped us find
other bugs. In the future we can test what could break with this
arrangement by enabling CONFIG_DEBUG_KOBJECT_RELEASE.

While at it, update the docs with the context expectations for the
request_queue / gendisk refcount decrement, and make these
expectations explicit by using might_sleep().

Fixes: dc9edc44de6c ("block: Fix a blk_exit_rl() regression")
Suggested-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Nicolai Stange <nstange@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: yu kuai <yukuai3@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       |  8 ++++++++
 block/blk-sysfs.c      | 43 ++++++++++++++++++++++---------------------
 block/genhd.c          | 17 +++++++++++++++++
 include/linux/blkdev.h |  2 --
 4 files changed, 47 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index f68398cb2ef6..a99b22fac38a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -327,6 +327,9 @@ EXPORT_SYMBOL_GPL(blk_clear_pm_only);
  *
  * Decrements the refcount of the request_queue kobject. When this reaches 0
  * we'll have blk_release_queue() called.
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void blk_put_queue(struct request_queue *q)
 {
@@ -359,9 +362,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  *
  * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
  * put it.  All future requests will be failed immediately with -ENODEV.
+ *
+ * Context: can sleep
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	/* cannot be called from atomic context */
+	might_sleep();
+
 	WARN_ON_ONCE(blk_queue_registered(q));
 
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 02643e149d5e..561624d4cc4e 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -873,22 +873,32 @@ static void blk_exit_queue(struct request_queue *q)
 	bdi_put(q->backing_dev_info);
 }
 
-
 /**
- * __blk_release_queue - release a request queue
- * @work: pointer to the release_work member of the request queue to be released
+ * blk_release_queue - releases all allocated resources of the request_queue
+ * @kobj: pointer to a kobject, whose container is a request_queue
+ *
+ * This function releases all allocated resources of the request queue.
+ *
+ * The struct request_queue refcount is incremented with blk_get_queue() and
+ * decremented with blk_put_queue(). Once the refcount reaches 0 this function
+ * is called.
+ *
+ * For drivers that have a request_queue on a gendisk and added with
+ * __device_add_disk() the refcount to request_queue will reach 0 with
+ * the last put_disk() called by the driver. For drivers which don't use
+ * __device_add_disk() this happens with blk_cleanup_queue().
  *
- * Description:
- *     This function is called when a block device is being unregistered. The
- *     process of releasing a request queue starts with blk_cleanup_queue, which
- *     set the appropriate flags and then calls blk_put_queue, that decrements
- *     the reference counter of the request queue. Once the reference counter
- *     of the request queue reaches zero, blk_release_queue is called to release
- *     all allocated resources of the request queue.
+ * Drivers exist which depend on the release of the request_queue to be
+ * synchronous, it should not be deferred.
+ *
+ * Context: can sleep
  */
-static void __blk_release_queue(struct work_struct *work)
+static void blk_release_queue(struct kobject *kobj)
 {
-	struct request_queue *q = container_of(work, typeof(*q), release_work);
+	struct request_queue *q =
+		container_of(kobj, struct request_queue, kobj);
+
+	might_sleep();
 
 	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
 		blk_stat_remove_callback(q, q->poll_cb);
@@ -917,15 +927,6 @@ static void __blk_release_queue(struct work_struct *work)
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
 }
 
-static void blk_release_queue(struct kobject *kobj)
-{
-	struct request_queue *q =
-		container_of(kobj, struct request_queue, kobj);
-
-	INIT_WORK(&q->release_work, __blk_release_queue);
-	schedule_work(&q->release_work);
-}
-
 static const struct sysfs_ops queue_sysfs_ops = {
 	.show	= queue_attr_show,
 	.store	= queue_attr_store,
diff --git a/block/genhd.c b/block/genhd.c
index 1be86b1f43ec..60ae4e1b4d38 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -889,12 +889,19 @@ static void invalidate_partition(struct gendisk *disk, int partno)
  * The final removal of the struct gendisk happens when its refcount reaches 0
  * with put_disk(), which should be called after del_gendisk(), if
  * __device_add_disk() was used.
+ *
+ * Drivers exist which depend on the release of the gendisk to be synchronous,
+ * it should not be deferred.
+ *
+ * Context: can sleep
  */
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
+	might_sleep();
+
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
@@ -1548,11 +1555,15 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
  * drivers we also call blk_put_queue() for them, and we expect the
  * request_queue refcount to reach 0 at this point, and so the request_queue
  * will also be freed prior to the disk.
+ *
+ * Context: can sleep
  */
 static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	might_sleep();
+
 	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
@@ -1797,6 +1808,9 @@ EXPORT_SYMBOL(get_disk_and_module);
  *
  * This decrements the refcount for the struct gendisk. When this reaches 0
  * we'll have disk_release() called.
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void put_disk(struct gendisk *disk)
 {
@@ -1811,6 +1825,9 @@ EXPORT_SYMBOL(put_disk);
  *
  * This is a counterpart of get_disk_and_module() and thus also of
  * get_gendisk().
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void put_disk_and_module(struct gendisk *disk)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 98712cfc7a34..e214e0e9f868 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -584,8 +584,6 @@ struct request_queue {
 
 	size_t			cmd_size;
 
-	struct work_struct	release_work;
-
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
-- 
cgit v1.2.3


From 85e0cbbb8a79537dbc465e9deb449a08b2b092a6 Mon Sep 17 00:00:00 2001
From: Luis Chamberlain <mcgrof@kernel.org>
Date: Fri, 19 Jun 2020 20:47:30 +0000
Subject: block: create the request_queue debugfs_dir on registration

We were only creating the request_queue debugfs_dir only
for make_request block drivers (multiqueue), but never for
request-based block drivers. We did this as we were only
creating non-blktrace additional debugfs files on that directory
for make_request drivers. However, since blktrace *always* creates
that directory anyway, we special-case the use of that directory
on blktrace. Other than this being an eye-sore, this exposes
request-based block drivers to the same debugfs fragile
race that used to exist with make_request block drivers
where if we start adding files onto that directory we can later
run a race with a double removal of dentries on the directory
if we don't deal with this carefully on blktrace.

Instead, just simplify things by always creating the request_queue
debugfs_dir on request_queue registration. Rename the mutex also to
reflect the fact that this is used outside of the blktrace context.

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c        |  8 +------
 block/blk-mq-debugfs.c  |  5 -----
 block/blk-sysfs.c       |  9 ++++++++
 block/blk.h             |  2 --
 include/linux/blkdev.h  |  5 +++--
 kernel/trace/blktrace.c | 58 ++++++++++++++++++++++---------------------------
 6 files changed, 39 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index a99b22fac38a..a9769c1a2875 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -51,9 +51,7 @@
 #include "blk-pm.h"
 #include "blk-rq-qos.h"
 
-#ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
-#endif
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
@@ -555,9 +553,7 @@ struct request_queue *__blk_alloc_queue(int node_id)
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
-#ifdef CONFIG_BLK_DEV_IO_TRACE
-	mutex_init(&q->blk_trace_mutex);
-#endif
+	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
 	spin_lock_init(&q->queue_lock);
@@ -1931,9 +1927,7 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
-#ifdef CONFIG_DEBUG_FS
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
-#endif
 
 	return 0;
 }
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 15df3a36e9fa..a2800bc56fb4 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -824,9 +824,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
 	/*
@@ -857,9 +854,7 @@ void blk_mq_debugfs_register(struct request_queue *q)
 
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
-	debugfs_remove_recursive(q->debugfs_dir);
 	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
 }
 
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 561624d4cc4e..be67952e7be2 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -11,6 +11,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -917,6 +918,9 @@ static void blk_release_queue(struct kobject *kobj)
 		blk_mq_release(q);
 
 	blk_trace_shutdown(q);
+	mutex_lock(&q->debugfs_mutex);
+	debugfs_remove_recursive(q->debugfs_dir);
+	mutex_unlock(&q->debugfs_mutex);
 
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
@@ -989,6 +993,11 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	mutex_lock(&q->debugfs_mutex);
+	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+					    blk_debugfs_root);
+	mutex_unlock(&q->debugfs_mutex);
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);
diff --git a/block/blk.h b/block/blk.h
index 8ba4a5e4fe07..3a120a070dac 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -14,9 +14,7 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
-#ifdef CONFIG_DEBUG_FS
 extern struct dentry *blk_debugfs_root;
-#endif
 
 struct blk_flush_queue {
 	unsigned int		flush_pending_idx:1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e214e0e9f868..c0701237116d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -528,9 +528,9 @@ struct request_queue {
 	unsigned int		sg_timeout;
 	unsigned int		sg_reserved_size;
 	int			node;
+	struct mutex		debugfs_mutex;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
-	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations
@@ -574,8 +574,9 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 46c273f4dec5..c086c38f4954 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -348,7 +348,7 @@ static int __blk_trace_remove(struct request_queue *q)
 	struct blk_trace *bt;
 
 	bt = rcu_replace_pointer(q->blk_trace, NULL,
-				 lockdep_is_held(&q->blk_trace_mutex));
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -362,9 +362,9 @@ int blk_trace_remove(struct request_queue *q)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_remove(q);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -483,14 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	struct dentry *dir = NULL;
 	int ret;
 
-	lockdep_assert_held(&q->blk_trace_mutex);
+	lockdep_assert_held(&q->debugfs_mutex);
 
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
-
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -505,7 +502,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 * we can be.
 	 */
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		pr_warn("Concurrent blktraces are not allowed on %s\n",
 			buts->name);
 		return -EBUSY;
@@ -524,18 +521,15 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	/*
-	 * When tracing whole make_request drivers (multiqueue) block devices,
-	 * reuse the existing debugfs directory created by the block layer on
-	 * init. For request-based block devices, all partitions block devices,
+	 * When tracing the whole disk reuse the existing debugfs directory
+	 * created by the block layer on init. For partitions block devices,
 	 * and scsi-generic block devices we create a temporary new debugfs
 	 * directory that will be removed once the trace ends.
 	 */
-	if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains)
+	if (bdev && bdev == bdev->bd_contains)
 		dir = q->debugfs_dir;
 	else
-#endif
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 
 	/*
@@ -617,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_setup(q, name, dev, bdev, arg);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -665,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -705,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_startstop(q, start);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -736,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -763,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 	return ret;
 }
 
@@ -774,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1662,7 +1656,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	struct blk_trace *bt;
 
 	bt = rcu_replace_pointer(q->blk_trace, NULL,
-				 lockdep_is_held(&q->blk_trace_mutex));
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -1837,10 +1831,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
@@ -1858,7 +1852,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1901,10 +1895,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		if (!!value == !!bt) {
 			ret = 0;
@@ -1921,7 +1915,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
 		bt = rcu_dereference_protected(q->blk_trace,
-				lockdep_is_held(&q->blk_trace_mutex));
+				lockdep_is_held(&q->debugfs_mutex));
 	}
 
 	if (ret == 0) {
@@ -1936,7 +1930,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
-- 
cgit v1.2.3


From b818f09e46f9f6a66471f81bf83094ff0a477d0c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:35 +0200
Subject: tty/sysrq: emergency_thaw_all does not depend on CONFIG_BLOCK

We can also thaw non-block file systems.  Remove the CONFIG_BLOCK in
sysrq.c after making the prototype available unconditionally.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/tty/sysrq.c | 2 --
 include/linux/fs.h  | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 7c95afa905a0..a8e39b2cdd55 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -403,7 +403,6 @@ static const struct sysrq_key_op sysrq_moom_op = {
 	.enable_mask	= SYSRQ_ENABLE_SIGNAL,
 };
 
-#ifdef CONFIG_BLOCK
 static void sysrq_handle_thaw(int key)
 {
 	emergency_thaw_all();
@@ -414,7 +413,6 @@ static const struct sysrq_key_op sysrq_thaw_op = {
 	.action_msg	= "Emergency Thaw of all frozen filesystems",
 	.enable_mask	= SYSRQ_ENABLE_SIGNAL,
 };
-#endif
 
 static void sysrq_handle_kill(int key)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..7f40dbafbf6d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2593,7 +2593,6 @@ extern void invalidate_bdev(struct block_device *);
 extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 extern int sync_blockdev(struct block_device *bdev);
 extern struct super_block *freeze_bdev(struct block_device *);
-extern void emergency_thaw_all(void);
 extern void emergency_thaw_bdev(struct super_block *sb);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
@@ -2633,6 +2632,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb)
 	return false;
 }
 #endif
+void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-- 
cgit v1.2.3


From 764b23bd9af8ff8ecc664816e39d4791b6a72bfd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:36 +0200
Subject: block: mark bd_finish_claiming static

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c     | 5 ++---
 include/linux/fs.h | 2 --
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0ae656e022fd..0e0d43dc27d3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1187,8 +1187,8 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
  * Finish exclusive open of a block device. Mark the device as exlusively
  * open by the holder and wake up all waiters for exclusive open to finish.
  */
-void bd_finish_claiming(struct block_device *bdev, struct block_device *whole,
-			void *holder)
+static void bd_finish_claiming(struct block_device *bdev,
+		struct block_device *whole, void *holder)
 {
 	spin_lock(&bdev_lock);
 	BUG_ON(!bd_may_claim(bdev, whole, holder));
@@ -1203,7 +1203,6 @@ void bd_finish_claiming(struct block_device *bdev, struct block_device *whole,
 	bd_clear_claiming(whole, holder);
 	spin_unlock(&bdev_lock);
 }
-EXPORT_SYMBOL(bd_finish_claiming);
 
 /**
  * bd_abort_claiming - abort claiming of a block device
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7f40dbafbf6d..b1c960e9b84e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2646,8 +2646,6 @@ extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
 					      void *holder);
 extern struct block_device *bd_start_claiming(struct block_device *bdev,
 					      void *holder);
-extern void bd_finish_claiming(struct block_device *bdev,
-			       struct block_device *whole, void *holder);
 extern void bd_abort_claiming(struct block_device *bdev,
 			      struct block_device *whole, void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-- 
cgit v1.2.3


From 7dbac5baa887facf80373825b8f66c626703621f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:37 +0200
Subject: fs: remove an unused block_device_operations forward declaration

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b1c960e9b84e..0d282c853691 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1774,8 +1774,6 @@ struct dir_context {
 	loff_t pos;
 };
 
-struct block_device_operations;
-
 /* These macros are for out of kernel modules to test that
  * the kernel supports the unlocked_ioctl and compat_ioctl
  * fields in struct file_operations. */
-- 
cgit v1.2.3


From 4e24566a134ea167441a1ffa3d439a27cf400880 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:38 +0200
Subject: fs: remove the HAVE_UNLOCKED_IOCTL and HAVE_COMPAT_IOCTL defines

These are not defined anywhere, and contrary to the comments we really
do not care about out of tree code at all.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0d282c853691..224edcc5b56e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1774,12 +1774,6 @@ struct dir_context {
 	loff_t pos;
 };
 
-/* These macros are for out of kernel modules to test that
- * the kernel supports the unlocked_ioctl and compat_ioctl
- * fields in struct file_operations. */
-#define HAVE_COMPAT_IOCTL 1
-#define HAVE_UNLOCKED_IOCTL 1
-
 /*
  * These flags let !MMU mmap() govern direct device mapping vs immediate
  * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
-- 
cgit v1.2.3


From 75362a1792d16a61f0277d3610dea2f50a16bf3e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:39 +0200
Subject: fs: remove the mount_bdev and kill_block_super stubs

No one calls these functions without CONFIG_BLOCK, so don't bother
stubbing them out.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 16 ----------------
 1 file changed, 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 224edcc5b56e..9ee09e2b5a97 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2256,18 +2256,9 @@ struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
-#ifdef CONFIG_BLOCK
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-#else
-static inline struct dentry *mount_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
-{
-	return ERR_PTR(-ENODEV);
-}
-#endif
 extern struct dentry *mount_single(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
@@ -2276,14 +2267,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type,
 	int (*fill_super)(struct super_block *, void *, int));
 extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
 void generic_shutdown_super(struct super_block *sb);
-#ifdef CONFIG_BLOCK
 void kill_block_super(struct super_block *sb);
-#else
-static inline void kill_block_super(struct super_block *sb)
-{
-	BUG();
-}
-#endif
 void kill_anon_super(struct super_block *sb);
 void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
-- 
cgit v1.2.3


From dd0dca223e091bbacdd3c7ce9cf06b373da59816 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:40 +0200
Subject: block: simplify sb_is_blkdev_sb

Just use IS_ENABLED instead of providing a stub for !CONFIG_BLOCK.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ee09e2b5a97..7f3ae38335d4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2557,6 +2557,12 @@ extern struct kmem_cache *names_cachep;
 #define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
 
+extern struct super_block *blockdev_superblock;
+static inline bool sb_is_blkdev_sb(struct super_block *sb)
+{
+	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
+}
+
 #ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
@@ -2572,13 +2578,6 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_bdev(struct super_block *sb);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-
-extern struct super_block *blockdev_superblock;
-
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return sb == blockdev_superblock;
-}
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }
@@ -2602,11 +2601,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb)
 static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
 {
 }
-
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return false;
-}
 #endif
 void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
-- 
cgit v1.2.3


From 3f1266f1f82d7b8c72472a8921e80aa3e611fb62 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:41 +0200
Subject: block: move block-related definitions out of fs.h

Move most of the block related definition out of fs.h into more suitable
headers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/affs/file.c             |  1 +
 fs/hfs/inode.c             |  1 +
 fs/internal.h              | 17 ++++++++-
 fs/ntfs/dir.c              |  1 +
 fs/proc/devices.c          |  1 +
 fs/quota/dquot.c           |  1 +
 fs/reiserfs/procfs.c       |  1 +
 include/linux/blkdev.h     | 46 +++++++++++++++++++++++
 include/linux/fs.h         | 92 ----------------------------------------------
 include/linux/genhd.h      | 27 ++++++++++++++
 include/linux/jbd2.h       |  1 +
 security/loadpin/loadpin.c |  1 +
 12 files changed, 96 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/fs/affs/file.c b/fs/affs/file.c
index a85817f54483..a26a0f96c119 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/uio.h>
+#include <linux/blkdev.h>
 #include "affs.h"
 
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2f224b98ee94..f35a37c65e5f 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -17,6 +17,7 @@
 #include <linux/cred.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
+#include <linux/blkdev.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/internal.h b/fs/internal.h
index 9b863a7bd708..969988d3d397 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -23,7 +23,9 @@ struct user_namespace;
 extern void __init bdev_cache_init(void);
 
 extern int __sync_blockdev(struct block_device *bdev, int wait);
-
+void iterate_bdevs(void (*)(struct block_device *, void *), void *);
+void emergency_thaw_bdev(struct super_block *sb);
+void bd_forget(struct inode *inode);
 #else
 static inline void bdev_cache_init(void)
 {
@@ -33,7 +35,18 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 {
 	return 0;
 }
-#endif
+static inline void iterate_bdevs(void (*f)(struct block_device *, void *),
+		void *arg)
+{
+}
+static inline int emergency_thaw_bdev(struct super_block *sb)
+{
+	return 0;
+}
+static inline void bd_forget(struct inode *inode)
+{
+}
+#endif /* CONFIG_BLOCK */
 
 /*
  * buffer.c
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 3c4811469ae8..a87d4391e6b5 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -8,6 +8,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 
 #include "dir.h"
 #include "aops.h"
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
index 37d38697eaf8..837971e74109 100644
--- a/fs/proc/devices.c
+++ b/fs/proc/devices.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/blkdev.h>
 
 static int devinfo_show(struct seq_file *f, void *v)
 {
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 7b4bac91146b..bb02989d92b6 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -78,6 +78,7 @@
 #include <linux/namei.h>
 #include <linux/capability.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 #include "../internal.h" /* ugh */
 
 #include <linux/uaccess.h>
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index ff336513c254..155b82870333 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -15,6 +15,7 @@
 #include "reiserfs.h"
 #include <linux/init.h>
 #include <linux/proc_fs.h>
+#include <linux/blkdev.h>
 
 /*
  * LOCKING:
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0701237116d..cf8f692f62a9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1918,4 +1918,50 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 }
 #endif /* CONFIG_BLOCK */
 
+int bdev_read_only(struct block_device *bdev);
+int set_blocksize(struct block_device *bdev, int size);
+
+const char *bdevname(struct block_device *bdev, char *buffer);
+struct block_device *lookup_bdev(const char *);
+
+void blkdev_show(struct seq_file *seqf, off_t offset);
+
+#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_MAX	512
+#else
+#define BLKDEV_MAJOR_MAX	0
+#endif
+
+int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
+struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+		void *holder);
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
+struct block_device *bd_start_claiming(struct block_device *bdev, void *holder);
+void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
+		void *holder);
+void blkdev_put(struct block_device *bdev, fmode_t mode);
+
+struct block_device *bdget(dev_t);
+struct block_device *bdgrab(struct block_device *bdev);
+void bdput(struct block_device *);
+
+#ifdef CONFIG_BLOCK
+void invalidate_bdev(struct block_device *bdev);
+int sync_blockdev(struct block_device *bdev);
+#else
+static inline void invalidate_bdev(struct block_device *bdev)
+{
+}
+static inline int sync_blockdev(struct block_device *bdev)
+{
+	return 0;
+}
 #endif
+int fsync_bdev(struct block_device *bdev);
+
+struct super_block *freeze_bdev(struct block_device *bdev);
+int thaw_bdev(struct block_device *bdev, struct super_block *sb);
+
+#endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7f3ae38335d4..add30c3bdf9a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2563,79 +2563,10 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb)
 	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
 }
 
-#ifdef CONFIG_BLOCK
-extern int register_blkdev(unsigned int, const char *);
-extern void unregister_blkdev(unsigned int, const char *);
-extern struct block_device *bdget(dev_t);
-extern struct block_device *bdgrab(struct block_device *bdev);
-extern void bd_set_size(struct block_device *, loff_t size);
-extern void bd_forget(struct inode *inode);
-extern void bdput(struct block_device *);
-extern void invalidate_bdev(struct block_device *);
-extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
-extern int sync_blockdev(struct block_device *bdev);
-extern struct super_block *freeze_bdev(struct block_device *);
-extern void emergency_thaw_bdev(struct super_block *sb);
-extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
-extern int fsync_bdev(struct block_device *);
-#else
-static inline void bd_forget(struct inode *inode) {}
-static inline int sync_blockdev(struct block_device *bdev) { return 0; }
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
-	return NULL;
-}
-
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-	return 0;
-}
-
-static inline int emergency_thaw_bdev(struct super_block *sb)
-{
-	return 0;
-}
-
-static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
-{
-}
-#endif
 void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-#ifdef CONFIG_BLOCK
-extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
-extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-					       void *holder);
-extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
-					      void *holder);
-extern struct block_device *bd_start_claiming(struct block_device *bdev,
-					      void *holder);
-extern void bd_abort_claiming(struct block_device *bdev,
-			      struct block_device *whole, void *holder);
-extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-
-#ifdef CONFIG_SYSFS
-extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
-extern void bd_unlink_disk_holder(struct block_device *bdev,
-				  struct gendisk *disk);
-#else
-static inline int bd_link_disk_holder(struct block_device *bdev,
-				      struct gendisk *disk)
-{
-	return 0;
-}
-static inline void bd_unlink_disk_holder(struct block_device *bdev,
-					 struct gendisk *disk)
-{
-}
-#endif
-#endif
 
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_MAX 512
@@ -2666,31 +2597,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name)
 	__unregister_chrdev(major, 0, 256, name);
 }
 
-/* fs/block_dev.c */
-#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
-#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
-
-#ifdef CONFIG_BLOCK
-#define BLKDEV_MAJOR_MAX	512
-extern const char *bdevname(struct block_device *bdev, char *buffer);
-extern struct block_device *lookup_bdev(const char *);
-extern void blkdev_show(struct seq_file *,off_t);
-
-#else
-#define BLKDEV_MAJOR_MAX	0
-#endif
-
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 
 /* Invalid inode operations -- fs/bad_inode.c */
 extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
-#ifdef CONFIG_BLOCK
-extern int revalidate_disk(struct gendisk *);
-extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *, bool);
-#endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 
@@ -3090,10 +3002,6 @@ static inline void remove_inode_hash(struct inode *inode)
 
 extern void inode_sb_list_add(struct inode *inode);
 
-#ifdef CONFIG_BLOCK
-extern int bdev_read_only(struct block_device *);
-#endif
-extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 392aad5e29a2..83f8e0d83228 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -373,6 +373,33 @@ extern void blk_unregister_region(dev_t devt, unsigned long range);
 
 #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
 
+int register_blkdev(unsigned int major, const char *name);
+void unregister_blkdev(unsigned int major, const char *name);
+
+int revalidate_disk(struct gendisk *disk);
+int check_disk_change(struct block_device *bdev);
+int __invalidate_device(struct block_device *bdev, bool kill_dirty);
+void bd_set_size(struct block_device *bdev, loff_t size);
+
+/* for drivers/char/raw.c: */
+int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
+long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
+
+#ifdef CONFIG_SYSFS
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
+void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
+#else
+static inline int bd_link_disk_holder(struct block_device *bdev,
+				      struct gendisk *disk)
+{
+	return 0;
+}
+static inline void bd_unlink_disk_holder(struct block_device *bdev,
+					 struct gendisk *disk)
+{
+}
+#endif /* CONFIG_SYSFS */
+
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d56128df2aff..4aaa29772bb0 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -27,6 +27,7 @@
 #include <linux/timer.h>
 #include <linux/slab.h>
 #include <linux/bit_spinlock.h>
+#include <linux/blkdev.h>
 #include <crypto/hash.h>
 #endif
 
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index ee5cb944f4ad..670a1aebb8a1 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -13,6 +13,7 @@
 #include <linux/fs.h>
 #include <linux/lsm_hooks.h>
 #include <linux/mount.h>
+#include <linux/blkdev.h>
 #include <linux/path.h>
 #include <linux/sched.h>	/* current */
 #include <linux/string_helpers.h>
-- 
cgit v1.2.3


From d2de7ea48d83195ef1310555f1fdd9e8e1bab0d3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:42 +0200
Subject: fs: move the buffer_heads_over_limit stub to buffer_head.h

Move the !CONFIG_BLOCK stub to the same place as the non-stub
declaration.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h      | 1 -
 include/linux/buffer_head.h | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cf8f692f62a9..c824c6fee35d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1838,7 +1838,6 @@ struct block_device;
 /*
  * stubs for when the block layer is configured out
  */
-#define buffer_heads_over_limit 0
 
 static inline long nr_blockdev_pages(void)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 22fb11e2d2e0..6b47f94378c5 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -406,6 +406,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+#define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
-- 
cgit v1.2.3


From 1a4dcfa8bc10d6bf4f94ac20adc2b30a1da72cfd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:43 +0200
Subject: block: reduce ifdef CONFIG_BLOCK madness in headers

Large part of bio.h, blkdev.h and genhd.h are under ifdef CONFIG_BLOCK
for no good reason.  Only stub out function that are called from
code that is not dependent on CONFIG_BLOCK and leave the harmless
other declarations around.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h    |  3 --
 include/linux/blkdev.h | 92 ++++++++++++++++++++++----------------------------
 include/linux/genhd.h  | 14 ++++----
 3 files changed, 46 insertions(+), 63 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 91676d4b2dfe..0282f8aa8593 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -8,8 +8,6 @@
 #include <linux/highmem.h>
 #include <linux/mempool.h>
 #include <linux/ioprio.h>
-
-#ifdef CONFIG_BLOCK
 /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
 #include <linux/blk_types.h>
 
@@ -824,5 +822,4 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
-#endif /* CONFIG_BLOCK */
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c824c6fee35d..f788bddc9219 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -4,9 +4,6 @@
 
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
-
-#ifdef CONFIG_BLOCK
-
 #include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
@@ -1163,13 +1160,13 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
 }
 extern void blk_dump_rq_flags(struct request *, char *);
-extern long nr_blockdev_pages(void);
 
 bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
+#ifdef CONFIG_BLOCK
 /*
  * blk_plug permits building a queue of related requests by holding the I/O
  * fragments for a short period. This allows merging of sequential requests
@@ -1229,9 +1226,47 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 		 !list_empty(&plug->cb_list));
 }
 
+int blkdev_issue_flush(struct block_device *, gfp_t);
+long nr_blockdev_pages(void);
+#else /* CONFIG_BLOCK */
+struct blk_plug {
+};
+
+static inline void blk_start_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_finish_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_flush_plug(struct task_struct *task)
+{
+}
+
+static inline void blk_schedule_flush_plug(struct task_struct *task)
+{
+}
+
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	return false;
+}
+
+static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+{
+	return 0;
+}
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK */
+
 extern void blk_io_schedule(void);
 
-int blkdev_issue_flush(struct block_device *, gfp_t);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 
@@ -1831,51 +1866,6 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-#else /* CONFIG_BLOCK */
-
-struct block_device;
-
-/*
- * stubs for when the block layer is configured out
- */
-
-static inline long nr_blockdev_pages(void)
-{
-	return 0;
-}
-
-struct blk_plug {
-};
-
-static inline void blk_start_plug(struct blk_plug *plug)
-{
-}
-
-static inline void blk_finish_plug(struct blk_plug *plug)
-{
-}
-
-static inline void blk_flush_plug(struct task_struct *task)
-{
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *task)
-{
-}
-
-
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
-{
-	return false;
-}
-
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
-{
-	return 0;
-}
-
-#endif /* CONFIG_BLOCK */
-
 static inline void blk_wake_io_task(struct task_struct *waiter)
 {
 	/*
@@ -1889,7 +1879,6 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 		wake_up_process(waiter);
 }
 
-#ifdef CONFIG_BLOCK
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 		unsigned int op);
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
@@ -1915,7 +1904,6 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 {
 	return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time);
 }
-#endif /* CONFIG_BLOCK */
 
 int bdev_read_only(struct block_device *bdev);
 int set_blocksize(struct block_device *bdev, int size);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 83f8e0d83228..31a54072ffd6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -19,8 +19,6 @@
 #include <linux/blk_types.h>
 #include <asm/local.h>
 
-#ifdef CONFIG_BLOCK
-
 #define dev_to_disk(device)	container_of((device), struct gendisk, part0.__dev)
 #define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
 #define disk_to_dev(disk)	(&(disk)->part0.__dev)
@@ -337,12 +335,9 @@ static inline void set_capacity(struct gendisk *disk, sector_t size)
 	disk->part0.nr_sects = size;
 }
 
-extern dev_t blk_lookup_devt(const char *name, int partno);
-
 int bdev_disk_changed(struct block_device *bdev, bool invalidate);
 int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
 int blk_drop_partitions(struct block_device *bdev);
-extern void printk_all_partitions(void);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
 extern struct kobject *get_disk_and_module(struct gendisk *disk);
@@ -400,10 +395,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 }
 #endif /* CONFIG_SYSFS */
 
+#ifdef CONFIG_BLOCK
+void printk_all_partitions(void);
+dev_t blk_lookup_devt(const char *name, int partno);
 #else /* CONFIG_BLOCK */
-
-static inline void printk_all_partitions(void) { }
-
+static inline void printk_all_partitions(void)
+{
+}
 static inline dev_t blk_lookup_devt(const char *name, int partno)
 {
 	dev_t devt = MKDEV(0, 0);
-- 
cgit v1.2.3


From 621c1f42945e76015c3a585e7a9fe6e71665eba0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 20 Jun 2020 09:16:44 +0200
Subject: block: move struct block_device to blk_types.h

Move the struct block_device definition together with most of the
block layer definitions, as it has nothing to do with the rest of fs.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/adfs/super.c           |  1 +
 fs/befs/linuxvfs.c        |  1 +
 fs/efs/super.c            |  1 +
 fs/jfs/jfs_mount.c        |  1 +
 fs/jfs/resize.c           |  1 +
 include/linux/blk_types.h | 39 ++++++++++++++++++++++++++++++++++++++-
 include/linux/blkdev.h    |  1 +
 include/linux/dasd_mod.h  |  2 ++
 include/linux/fs.h        | 41 -----------------------------------------
 9 files changed, 46 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index a3cc8ecb50da..d553bb5bc17a 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/user_namespace.h>
+#include <linux/blkdev.h>
 #include "adfs.h"
 #include "dir_f.h"
 #include "dir_fplus.h"
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 64cdf4d8e424..2482032021ca 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -22,6 +22,7 @@
 #include <linux/cred.h>
 #include <linux/exportfs.h>
 #include <linux/seq_file.h>
+#include <linux/blkdev.h>
 
 #include "befs.h"
 #include "btree.h"
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 4a6ebff2af76..a4a945d0ac6a 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
+#include <linux/blkdev.h>
 
 #include "efs.h"
 #include <linux/efs_vh.h>
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index eb8b9e233d73..2935d4c776ec 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -36,6 +36,7 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 66acea9d878b..bde787c354fc 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -6,6 +6,7 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
 #include "jfs_metapage.h"
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ccb895f911b1..a602132cbe32 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -14,12 +14,49 @@ struct bio_set;
 struct bio;
 struct bio_integrity_payload;
 struct page;
-struct block_device;
 struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
+struct block_device {
+	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
+	int			bd_openers;
+	struct inode *		bd_inode;	/* will die */
+	struct super_block *	bd_super;
+	struct mutex		bd_mutex;	/* open/close mutex */
+	void *			bd_claiming;
+	void *			bd_holder;
+	int			bd_holders;
+	bool			bd_write_holder;
+#ifdef CONFIG_SYSFS
+	struct list_head	bd_holder_disks;
+#endif
+	struct block_device *	bd_contains;
+	unsigned		bd_block_size;
+	u8			bd_partno;
+	struct hd_struct *	bd_part;
+	/* number of times partitions within this device have been opened. */
+	unsigned		bd_part_count;
+	int			bd_invalidated;
+	struct gendisk *	bd_disk;
+	struct request_queue *  bd_queue;
+	struct backing_dev_info *bd_bdi;
+	struct list_head	bd_list;
+	/*
+	 * Private data.  You must have bd_claim'ed the block_device
+	 * to use this.  NOTE:  bd_claim allows an owner to claim
+	 * the same device multiple times, the owner must take special
+	 * care to not mess up bd_private for that case.
+	 */
+	unsigned long		bd_private;
+
+	/* The counter of freeze processes */
+	int			bd_fsfreeze_count;
+	/* Mutex for freeze */
+	struct mutex		bd_fsfreeze_mutex;
+} __randomize_layout;
+
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
  * Alpha cannot write a byte atomically, so we need to use 32-bit value.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f788bddc9219..15497782c176 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1930,6 +1930,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 		void *holder);
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
+struct block_device *I_BDEV(struct inode *inode);
 struct block_device *bdget(dev_t);
 struct block_device *bdgrab(struct block_device *bdev);
 void bdput(struct block_device *);
diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h
index d39abad2ff6e..14e6cf8c6267 100644
--- a/include/linux/dasd_mod.h
+++ b/include/linux/dasd_mod.h
@@ -4,6 +4,8 @@
 
 #include <asm/dasd.h>
 
+struct gendisk;
+
 extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info);
 
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index add30c3bdf9a..1d7c4f7465d2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -470,45 +470,6 @@ struct address_space {
 	 * must be enforced here for CRIS, to let the least significant bit
 	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
 	 */
-struct request_queue;
-
-struct block_device {
-	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
-	int			bd_openers;
-	struct inode *		bd_inode;	/* will die */
-	struct super_block *	bd_super;
-	struct mutex		bd_mutex;	/* open/close mutex */
-	void *			bd_claiming;
-	void *			bd_holder;
-	int			bd_holders;
-	bool			bd_write_holder;
-#ifdef CONFIG_SYSFS
-	struct list_head	bd_holder_disks;
-#endif
-	struct block_device *	bd_contains;
-	unsigned		bd_block_size;
-	u8			bd_partno;
-	struct hd_struct *	bd_part;
-	/* number of times partitions within this device have been opened. */
-	unsigned		bd_part_count;
-	int			bd_invalidated;
-	struct gendisk *	bd_disk;
-	struct request_queue *  bd_queue;
-	struct backing_dev_info *bd_bdi;
-	struct list_head	bd_list;
-	/*
-	 * Private data.  You must have bd_claim'ed the block_device
-	 * to use this.  NOTE:  bd_claim allows an owner to claim
-	 * the same device multiple times, the owner must take special
-	 * care to not mess up bd_private for that case.
-	 */
-	unsigned long		bd_private;
-
-	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-} __randomize_layout;
 
 /* XArray tags, for tagging dirty and writeback pages in the pagecache. */
 #define PAGECACHE_TAG_DIRTY	XA_MARK_0
@@ -907,8 +868,6 @@ static inline unsigned imajor(const struct inode *inode)
 	return MAJOR(inode->i_rdev);
 }
 
-extern struct block_device *I_BDEV(struct inode *inode);
-
 struct fown_struct {
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
-- 
cgit v1.2.3


From 1bc138c622959979eb547be2d3bbc6442a5c80b0 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 10 Jun 2020 11:12:23 +0100
Subject: PM / EM: add support for other devices than CPUs in Energy Model

Add support for other devices than CPUs. The registration function
does not require a valid cpumask pointer and is ready to handle new
devices. Some of the internal structures has been reorganized in order to
keep consistent view (like removing per_cpu pd pointers).

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/device.h       |   5 +
 include/linux/energy_model.h |  29 +++--
 kernel/power/energy_model.c  | 244 +++++++++++++++++++++++++++++--------------
 3 files changed, 194 insertions(+), 84 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..b72e6f9ad845 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -13,6 +13,7 @@
 #define _DEVICE_H_
 
 #include <linux/dev_printk.h>
+#include <linux/energy_model.h>
 #include <linux/ioport.h>
 #include <linux/kobject.h>
 #include <linux/klist.h>
@@ -559,6 +560,10 @@ struct device {
 	struct dev_pm_info	power;
 	struct dev_pm_domain	*pm_domain;
 
+#ifdef CONFIG_ENERGY_MODEL
+	struct em_perf_domain	*em_pd;
+#endif
+
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 	struct irq_domain	*msi_domain;
 #endif
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 7076cb22b247..2d4689964029 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -12,8 +12,10 @@
 
 /**
  * em_perf_state - Performance state of a performance domain
- * @frequency:	The CPU frequency in KHz, for consistency with CPUFreq
- * @power:	The power consumed by 1 CPU at this level, in milli-watts
+ * @frequency:	The frequency in KHz, for consistency with CPUFreq
+ * @power:	The power consumed at this level, in milli-watts (by 1 CPU or
+		by a registered device). It can be a total power: static and
+		dynamic.
  * @cost:	The cost coefficient associated with this level, used during
  *		energy calculation. Equal to: power * max_frequency / frequency
  */
@@ -27,12 +29,16 @@ struct em_perf_state {
  * em_perf_domain - Performance domain
  * @table:		List of performance states, in ascending order
  * @nr_perf_states:	Number of performance states
- * @cpus:		Cpumask covering the CPUs of the domain
+ * @cpus:		Cpumask covering the CPUs of the domain. It's here
+ *			for performance reasons to avoid potential cache
+ *			misses during energy calculations in the scheduler
+ *			and simplifies allocating/freeing that memory region.
  *
- * A "performance domain" represents a group of CPUs whose performance is
- * scaled together. All CPUs of a performance domain must have the same
- * micro-architecture. Performance domains often have a 1-to-1 mapping with
- * CPUFreq policies.
+ * In case of CPU device, a "performance domain" represents a group of CPUs
+ * whose performance is scaled together. All CPUs of a performance domain
+ * must have the same micro-architecture. Performance domains often have
+ * a 1-to-1 mapping with CPUFreq policies. In case of other devices the @cpus
+ * field is unused.
  */
 struct em_perf_domain {
 	struct em_perf_state *table;
@@ -71,10 +77,12 @@ struct em_data_callback {
 #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
 
 struct em_perf_domain *em_cpu_get(int cpu);
+struct em_perf_domain *em_pd_get(struct device *dev);
 int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 						struct em_data_callback *cb);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				struct em_data_callback *cb, cpumask_t *span);
+void em_dev_unregister_perf_domain(struct device *dev);
 
 /**
  * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain
@@ -184,10 +192,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 {
 	return -EINVAL;
 }
+static inline void em_dev_unregister_perf_domain(struct device *dev)
+{
+}
 static inline struct em_perf_domain *em_cpu_get(int cpu)
 {
 	return NULL;
 }
+static inline struct em_perf_domain *em_pd_get(struct device *dev)
+{
+	return NULL;
+}
 static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
 			unsigned long max_util, unsigned long sum_util)
 {
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 5b8a1566526a..32d76e78f992 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Energy Model of CPUs
+ * Energy Model of devices
  *
- * Copyright (c) 2018, Arm ltd.
+ * Copyright (c) 2018-2020, Arm ltd.
  * Written by: Quentin Perret, Arm ltd.
+ * Improvements provided by: Lukasz Luba, Arm ltd.
  */
 
 #define pr_fmt(fmt) "energy_model: " fmt
@@ -15,15 +16,17 @@
 #include <linux/sched/topology.h>
 #include <linux/slab.h>
 
-/* Mapping of each CPU to the performance domain to which it belongs. */
-static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
-
 /*
  * Mutex serializing the registrations of performance domains and letting
  * callbacks defined by drivers sleep.
  */
 static DEFINE_MUTEX(em_pd_mutex);
 
+static bool _is_cpu_device(struct device *dev)
+{
+	return (dev->bus == &cpu_subsys);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *rootdir;
 
@@ -49,22 +52,30 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu)
+static void em_debug_create_pd(struct device *dev)
 {
 	struct dentry *d;
-	char name[8];
 	int i;
 
-	snprintf(name, sizeof(name), "pd%d", cpu);
-
 	/* Create the directory of the performance domain */
-	d = debugfs_create_dir(name, rootdir);
+	d = debugfs_create_dir(dev_name(dev), rootdir);
 
-	debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops);
+	if (_is_cpu_device(dev))
+		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
+				    &em_debug_cpus_fops);
 
 	/* Create a sub-directory for each performance state */
-	for (i = 0; i < pd->nr_perf_states; i++)
-		em_debug_create_ps(&pd->table[i], d);
+	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
+		em_debug_create_ps(&dev->em_pd->table[i], d);
+
+}
+
+static void em_debug_remove_pd(struct device *dev)
+{
+	struct dentry *debug_dir;
+
+	debug_dir = debugfs_lookup(dev_name(dev), rootdir);
+	debugfs_remove_recursive(debug_dir);
 }
 
 static int __init em_debug_init(void)
@@ -76,40 +87,34 @@ static int __init em_debug_init(void)
 }
 core_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {}
+static void em_debug_create_pd(struct device *dev) {}
+static void em_debug_remove_pd(struct device *dev) {}
 #endif
-static struct em_perf_domain *
-em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
-	     cpumask_t *span)
+
+static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
+				int nr_states, struct em_data_callback *cb)
 {
 	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
 	unsigned long power, freq, prev_freq = 0;
-	int i, ret, cpu = cpumask_first(span);
 	struct em_perf_state *table;
-	struct em_perf_domain *pd;
+	int i, ret;
 	u64 fmax;
 
-	if (!cb->active_power)
-		return NULL;
-
-	pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
-	if (!pd)
-		return NULL;
-
 	table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
 	if (!table)
-		goto free_pd;
+		return -ENOMEM;
 
 	/* Build the list of performance states for this performance domain */
 	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
 		/*
 		 * active_power() is a driver callback which ceils 'freq' to
-		 * lowest performance state of 'cpu' above 'freq' and updates
+		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
 		ret = cb->active_power(&power, &freq, dev);
 		if (ret) {
-			pr_err("pd%d: invalid perf. state: %d\n", cpu, ret);
+			dev_err(dev, "EM: invalid perf. state: %d\n",
+				ret);
 			goto free_ps_table;
 		}
 
@@ -118,7 +123,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
 		 * higher performance states.
 		 */
 		if (freq <= prev_freq) {
-			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
+			dev_err(dev, "EM: non-increasing freq: %lu\n",
+				freq);
 			goto free_ps_table;
 		}
 
@@ -127,7 +133,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
 		 * positive, in milli-watts and to fit into 16 bits.
 		 */
 		if (!power || power > EM_MAX_POWER) {
-			pr_err("pd%d: invalid power: %lu\n", cpu, power);
+			dev_err(dev, "EM: invalid power: %lu\n",
+				power);
 			goto free_ps_table;
 		}
 
@@ -142,8 +149,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
 		 */
 		opp_eff = freq / power;
 		if (opp_eff >= prev_opp_eff)
-			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
-					cpu, i, i - 1);
+			dev_dbg(dev, "EM: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
+					i, i - 1);
 		prev_opp_eff = opp_eff;
 	}
 
@@ -156,30 +163,82 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb,
 
 	pd->table = table;
 	pd->nr_perf_states = nr_states;
-	cpumask_copy(to_cpumask(pd->cpus), span);
 
-	em_debug_create_pd(pd, cpu);
-
-	return pd;
+	return 0;
 
 free_ps_table:
 	kfree(table);
-free_pd:
-	kfree(pd);
+	return -EINVAL;
+}
+
+static int em_create_pd(struct device *dev, int nr_states,
+			struct em_data_callback *cb, cpumask_t *cpus)
+{
+	struct em_perf_domain *pd;
+	struct device *cpu_dev;
+	int cpu, ret;
+
+	if (_is_cpu_device(dev)) {
+		pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+
+		cpumask_copy(em_span_cpus(pd), cpus);
+	} else {
+		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+	}
+
+	ret = em_create_perf_table(dev, pd, nr_states, cb);
+	if (ret) {
+		kfree(pd);
+		return ret;
+	}
+
+	if (_is_cpu_device(dev))
+		for_each_cpu(cpu, cpus) {
+			cpu_dev = get_cpu_device(cpu);
+			cpu_dev->em_pd = pd;
+		}
+
+	dev->em_pd = pd;
+
+	return 0;
+}
+
+/**
+ * em_pd_get() - Return the performance domain for a device
+ * @dev : Device to find the performance domain for
+ *
+ * Returns the performance domain to which @dev belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_pd_get(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev))
+		return NULL;
 
-	return NULL;
+	return dev->em_pd;
 }
+EXPORT_SYMBOL_GPL(em_pd_get);
 
 /**
  * em_cpu_get() - Return the performance domain for a CPU
  * @cpu : CPU to find the performance domain for
  *
- * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * Returns the performance domain to which @cpu belongs, or NULL if it doesn't
  * exist.
  */
 struct em_perf_domain *em_cpu_get(int cpu)
 {
-	return READ_ONCE(per_cpu(em_data, cpu));
+	struct device *cpu_dev;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return NULL;
+
+	return em_pd_get(cpu_dev);
 }
 EXPORT_SYMBOL_GPL(em_cpu_get);
 
@@ -188,7 +247,7 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  * @dev		: Device for which the EM is to register
  * @nr_states	: Number of performance states to register
  * @cb		: Callback functions providing the data of the Energy Model
- * @span	: Pointer to cpumask_t, which in case of a CPU device is
+ * @cpus	: Pointer to cpumask_t, which in case of a CPU device is
  *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
  *		type of devices this should be set to NULL.
  *
@@ -201,13 +260,12 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  * Return 0 on success
  */
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *span)
+				struct em_data_callback *cb, cpumask_t *cpus)
 {
 	unsigned long cap, prev_cap = 0;
-	struct em_perf_domain *pd;
-	int cpu, ret = 0;
+	int cpu, ret;
 
-	if (!dev || !span || !nr_states || !cb)
+	if (!dev || !nr_states || !cb)
 		return -EINVAL;
 
 	/*
@@ -216,47 +274,50 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 	 */
 	mutex_lock(&em_pd_mutex);
 
-	for_each_cpu(cpu, span) {
-		/* Make sure we don't register again an existing domain. */
-		if (READ_ONCE(per_cpu(em_data, cpu))) {
-			ret = -EEXIST;
-			goto unlock;
-		}
+	if (dev->em_pd) {
+		ret = -EEXIST;
+		goto unlock;
+	}
 
-		/*
-		 * All CPUs of a domain must have the same micro-architecture
-		 * since they all share the same table.
-		 */
-		cap = arch_scale_cpu_capacity(cpu);
-		if (prev_cap && prev_cap != cap) {
-			pr_err("CPUs of %*pbl must have the same capacity\n",
-							cpumask_pr_args(span));
+	if (_is_cpu_device(dev)) {
+		if (!cpus) {
+			dev_err(dev, "EM: invalid CPU mask\n");
 			ret = -EINVAL;
 			goto unlock;
 		}
-		prev_cap = cap;
+
+		for_each_cpu(cpu, cpus) {
+			if (em_cpu_get(cpu)) {
+				dev_err(dev, "EM: exists for CPU%d\n", cpu);
+				ret = -EEXIST;
+				goto unlock;
+			}
+			/*
+			 * All CPUs of a domain must have the same
+			 * micro-architecture since they all share the same
+			 * table.
+			 */
+			cap = arch_scale_cpu_capacity(cpu);
+			if (prev_cap && prev_cap != cap) {
+				dev_err(dev, "EM: CPUs of %*pbl must have the same capacity\n",
+					cpumask_pr_args(cpus));
+
+				ret = -EINVAL;
+				goto unlock;
+			}
+			prev_cap = cap;
+		}
 	}
 
-	/* Create the performance domain and add it to the Energy Model. */
-	pd = em_create_pd(dev, nr_states, cb, span);
-	if (!pd) {
-		ret = -EINVAL;
+	ret = em_create_pd(dev, nr_states, cb, cpus);
+	if (ret)
 		goto unlock;
-	}
 
-	for_each_cpu(cpu, span) {
-		/*
-		 * The per-cpu array can be read concurrently from em_cpu_get().
-		 * The barrier enforces the ordering needed to make sure readers
-		 * can only access well formed em_perf_domain structs.
-		 */
-		smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
-	}
+	em_debug_create_pd(dev);
+	dev_info(dev, "EM: created perf domain\n");
 
-	pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
 unlock:
 	mutex_unlock(&em_pd_mutex);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
@@ -285,3 +346,32 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 	return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span);
 }
 EXPORT_SYMBOL_GPL(em_register_perf_domain);
+
+/**
+ * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device
+ * @dev		: Device for which the EM is registered
+ *
+ * Unregister the EM for the specified @dev (but not a CPU device).
+ */
+void em_dev_unregister_perf_domain(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev) || !dev->em_pd)
+		return;
+
+	if (_is_cpu_device(dev))
+		return;
+
+	/*
+	 * The mutex separates all register/unregister requests and protects
+	 * from potential clean-up/setup issues in the debugfs directories.
+	 * The debugfs directory name is the same as device's name.
+	 */
+	mutex_lock(&em_pd_mutex);
+	em_debug_remove_pd(dev);
+
+	kfree(dev->em_pd->table);
+	kfree(dev->em_pd);
+	dev->em_pd = NULL;
+	mutex_unlock(&em_pd_mutex);
+}
+EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain);
-- 
cgit v1.2.3


From 07891f15d91317b2220a0b610a2d7e324a88105d Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:51 +0100
Subject: PM / EM: remove em_register_perf_domain

Remove old function em_register_perf_domain which is no longer needed.
There is em_dev_register_perf_domain that covers old use cases and new as
well.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h |  7 -------
 kernel/power/energy_model.c  | 25 -------------------------
 2 files changed, 32 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 2d4689964029..0f94e871a202 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -78,8 +78,6 @@ struct em_data_callback {
 
 struct em_perf_domain *em_cpu_get(int cpu);
 struct em_perf_domain *em_pd_get(struct device *dev);
-int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
-						struct em_data_callback *cb);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				struct em_data_callback *cb, cpumask_t *span);
 void em_dev_unregister_perf_domain(struct device *dev);
@@ -181,11 +179,6 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 struct em_data_callback {};
 #define EM_DATA_CB(_active_power_cb) { }
 
-static inline int em_register_perf_domain(cpumask_t *span,
-			unsigned int nr_states, struct em_data_callback *cb)
-{
-	return -EINVAL;
-}
 static inline
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				struct em_data_callback *cb, cpumask_t *span)
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 32d76e78f992..c1ff7fa030ab 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -322,31 +322,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
 
-/**
- * em_register_perf_domain() - Register the Energy Model of a performance domain
- * @span	: Mask of CPUs in the performance domain
- * @nr_states	: Number of capacity states to register
- * @cb		: Callback functions providing the data of the Energy Model
- *
- * Create Energy Model tables for a performance domain using the callbacks
- * defined in cb.
- *
- * If multiple clients register the same performance domain, all but the first
- * registration will be ignored.
- *
- * Return 0 on success
- */
-int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
-						struct em_data_callback *cb)
-{
-	struct device *cpu_dev;
-
-	cpu_dev = get_cpu_device(cpumask_first(span));
-
-	return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span);
-}
-EXPORT_SYMBOL_GPL(em_register_perf_domain);
-
 /**
  * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device
  * @dev		: Device for which the EM is registered
-- 
cgit v1.2.3


From f0b5694791ce70dba16758c3b838d5ddc7731b02 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:52 +0100
Subject: PM / EM: change name of em_pd_energy to em_cpu_energy

Energy Model framework now supports other devices than CPUs. Refactor some
of the functions in order to prevent wrong usage. The old function
em_pd_energy has to generic name. It must not be used without proper
cpumask pointer, which is possible only for CPU devices. Thus, rename it
and add proper description to warn of potential wrong usage for other
devices.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 11 ++++++++---
 kernel/sched/fair.c          |  2 +-
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 0f94e871a202..b67a51c574b9 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -83,15 +83,20 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 void em_dev_unregister_perf_domain(struct device *dev);
 
 /**
- * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain
+ * em_cpu_energy() - Estimates the energy consumed by the CPUs of a
+		performance domain
  * @pd		: performance domain for which energy has to be estimated
  * @max_util	: highest utilization among CPUs of the domain
  * @sum_util	: sum of the utilization of all CPUs in the domain
  *
+ * This function must be used only for CPU devices. There is no validation,
+ * i.e. if the EM is a CPU type and has cpumask allocated. It is called from
+ * the scheduler code quite frequently and that is why there is not checks.
+ *
  * Return: the sum of the energy consumed by the CPUs of the domain assuming
  * a capacity state satisfying the max utilization of the domain.
  */
-static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
+static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util)
 {
 	unsigned long freq, scale_cpu;
@@ -196,7 +201,7 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev)
 {
 	return NULL;
 }
-static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
+static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 			unsigned long max_util, unsigned long sum_util)
 {
 	return 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cbcb2f71599b..6da601c8d383 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6497,7 +6497,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		max_util = max(max_util, cpu_util);
 	}
 
-	return em_pd_energy(pd->em_pd, max_util, sum_util);
+	return em_cpu_energy(pd->em_pd, max_util, sum_util);
 }
 
 /*
-- 
cgit v1.2.3


From 0e0ffa855d1590e54ec0033404a49e2e57e294fe Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 27 May 2020 10:58:54 +0100
Subject: OPP: refactor dev_pm_opp_of_register_em() and update related drivers

The Energy Model framework supports not only CPU devices. Drop the CPU
specific interface with cpumask and add struct device. Add also a return
value, user might use it. This new interface provides easy way to create
a simple Energy Model, which then might be used by e.g. thermal subsystem.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq-dt.c           |  2 +-
 drivers/cpufreq/imx6q-cpufreq.c        |  2 +-
 drivers/cpufreq/mediatek-cpufreq.c     |  2 +-
 drivers/cpufreq/omap-cpufreq.c         |  2 +-
 drivers/cpufreq/qcom-cpufreq-hw.c      |  2 +-
 drivers/cpufreq/scpi-cpufreq.c         |  2 +-
 drivers/cpufreq/vexpress-spc-cpufreq.c |  2 +-
 drivers/opp/of.c                       | 71 +++++++++++++++++++++-------------
 include/linux/pm_opp.h                 | 15 ++++++-
 9 files changed, 65 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 79742bbd221f..944d7b45afe9 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -279,7 +279,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = transition_latency;
 	policy->dvfs_possible_from_any_cpu = true;
 
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index fdb2ffffbd15..ef7b34c1fd2b 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -193,7 +193,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	policy->clk = clks[ARM].clk;
 	cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index 0c98dd08273d..7d1212c9b7c8 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -448,7 +448,7 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(info->cpu_dev, policy->cpus);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 8d14b42a8c6f..3694bb030df3 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -131,7 +131,7 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 
 	/* FIXME: what's the actual transition time? */
 	cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(mpu_dev, policy->cpus);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index fc92a8842e25..0a04b6f03b9a 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -238,7 +238,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 		goto error;
 	}
 
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	policy->fast_switch_possible = true;
 
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 20d1f85d5f5a..b0f5388b8854 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -167,7 +167,7 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->fast_switch_possible = false;
 
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 83c85d3d67e3..4e8b1dee7c9a 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -450,7 +450,7 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
 	policy->freq_table = freq_table[cur_cluster];
 	policy->cpuinfo.transition_latency = 1000000; /* 1 ms */
 
-	dev_pm_opp_of_register_em(policy->cpus);
+	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) =
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index e273f419a4bf..4aa42739599e 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1205,18 +1205,18 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
 
 /*
  * Callback function provided to the Energy Model framework upon registration.
- * This computes the power estimated by @CPU at @kHz if it is the frequency
+ * This computes the power estimated by @dev at @kHz if it is the frequency
  * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise
  * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled
  * frequency and @mW to the associated power. The power is estimated as
- * P = C * V^2 * f with C being the CPU's capacitance and V and f respectively
- * the voltage and frequency of the OPP.
+ * P = C * V^2 * f with C being the device's capacitance and V and f
+ * respectively the voltage and frequency of the OPP.
  *
- * Returns -ENODEV if the CPU device cannot be found, -EINVAL if the power
- * calculation failed because of missing parameters, 0 otherwise.
+ * Returns -EINVAL if the power calculation failed because of missing
+ * parameters, 0 otherwise.
  */
-static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
-					 struct device *cpu_dev)
+static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz,
+				     struct device *dev)
 {
 	struct dev_pm_opp *opp;
 	struct device_node *np;
@@ -1225,7 +1225,7 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
 	u64 tmp;
 	int ret;
 
-	np = of_node_get(cpu_dev->of_node);
+	np = of_node_get(dev->of_node);
 	if (!np)
 		return -EINVAL;
 
@@ -1235,7 +1235,7 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
 		return -EINVAL;
 
 	Hz = *kHz * 1000;
-	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &Hz);
+	opp = dev_pm_opp_find_freq_ceil(dev, &Hz);
 	if (IS_ERR(opp))
 		return -EINVAL;
 
@@ -1255,30 +1255,38 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
 
 /**
  * dev_pm_opp_of_register_em() - Attempt to register an Energy Model
- * @cpus	: CPUs for which an Energy Model has to be registered
+ * @dev		: Device for which an Energy Model has to be registered
+ * @cpus	: CPUs for which an Energy Model has to be registered. For
+ *		other type of devices it should be set to NULL.
  *
  * This checks whether the "dynamic-power-coefficient" devicetree property has
  * been specified, and tries to register an Energy Model with it if it has.
+ * Having this property means the voltages are known for OPPs and the EM
+ * might be calculated.
  */
-void dev_pm_opp_of_register_em(struct cpumask *cpus)
+int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus)
 {
-	struct em_data_callback em_cb = EM_DATA_CB(_get_cpu_power);
-	int ret, nr_opp, cpu = cpumask_first(cpus);
-	struct device *cpu_dev;
+	struct em_data_callback em_cb = EM_DATA_CB(_get_power);
 	struct device_node *np;
+	int ret, nr_opp;
 	u32 cap;
 
-	cpu_dev = get_cpu_device(cpu);
-	if (!cpu_dev)
-		return;
+	if (IS_ERR_OR_NULL(dev)) {
+		ret = -EINVAL;
+		goto failed;
+	}
 
-	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
-	if (nr_opp <= 0)
-		return;
+	nr_opp = dev_pm_opp_get_opp_count(dev);
+	if (nr_opp <= 0) {
+		ret = -EINVAL;
+		goto failed;
+	}
 
-	np = of_node_get(cpu_dev->of_node);
-	if (!np)
-		return;
+	np = of_node_get(dev->of_node);
+	if (!np) {
+		ret = -EINVAL;
+		goto failed;
+	}
 
 	/*
 	 * Register an EM only if the 'dynamic-power-coefficient' property is
@@ -1289,9 +1297,20 @@ void dev_pm_opp_of_register_em(struct cpumask *cpus)
 	 */
 	ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap);
 	of_node_put(np);
-	if (ret || !cap)
-		return;
+	if (ret || !cap) {
+		dev_dbg(dev, "Couldn't find proper 'dynamic-power-coefficient' in DT\n");
+		ret = -EINVAL;
+		goto failed;
+	}
 
-	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, cpus);
+	ret = em_dev_register_perf_domain(dev, nr_opp, &em_cb, cpus);
+	if (ret)
+		goto failed;
+
+	return 0;
+
+failed:
+	dev_dbg(dev, "Couldn't register Energy Model %d\n", ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index d5c4a329321d..ee34c553f6bf 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -11,6 +11,7 @@
 #ifndef __LINUX_OPP_H__
 #define __LINUX_OPP_H__
 
+#include <linux/energy_model.h>
 #include <linux/err.h>
 #include <linux/notifier.h>
 
@@ -373,7 +374,11 @@ struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
 struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp);
 int of_get_required_opp_performance_state(struct device_node *np, int index);
 int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table);
-void dev_pm_opp_of_register_em(struct cpumask *cpus);
+int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus);
+static inline void dev_pm_opp_of_unregister_em(struct device *dev)
+{
+	em_dev_unregister_perf_domain(dev);
+}
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
 {
@@ -413,7 +418,13 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
 	return NULL;
 }
 
-static inline void dev_pm_opp_of_register_em(struct cpumask *cpus)
+static inline int dev_pm_opp_of_register_em(struct device *dev,
+					    struct cpumask *cpus)
+{
+	return -ENOTSUPP;
+}
+
+static inline void dev_pm_opp_of_unregister_em(struct device *dev)
 {
 }
 
-- 
cgit v1.2.3


From aad4a0a9513af962137c4842463d11ed491eec37 Mon Sep 17 00:00:00 2001
From: Dmitry Yakunin <zeil@yandex-team.ru>
Date: Sat, 20 Jun 2020 18:30:51 +0300
Subject: tcp: Expose tcp_sock_set_keepidle_locked

This is preparation for usage in bpf_setsockopt.

v2:
  - remove redundant EXPORT_SYMBOL (Alexei Starovoitov)

Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200620153052.9439-2-zeil@yandex-team.ru
---
 include/linux/tcp.h | 1 +
 net/ipv4/tcp.c      | 6 +++---
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 9aac824c523c..3bdec31ce8f4 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 
 void tcp_sock_set_cork(struct sock *sk, bool on);
 int tcp_sock_set_keepcnt(struct sock *sk, int val);
+int tcp_sock_set_keepidle_locked(struct sock *sk, int val);
 int tcp_sock_set_keepidle(struct sock *sk, int val);
 int tcp_sock_set_keepintvl(struct sock *sk, int val);
 void tcp_sock_set_nodelay(struct sock *sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 810cc164f795..de36c91d32ea 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2957,7 +2957,7 @@ void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
 }
 EXPORT_SYMBOL(tcp_sock_set_user_timeout);
 
-static int __tcp_sock_set_keepidle(struct sock *sk, int val)
+int tcp_sock_set_keepidle_locked(struct sock *sk, int val)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2984,7 +2984,7 @@ int tcp_sock_set_keepidle(struct sock *sk, int val)
 	int err;
 
 	lock_sock(sk);
-	err = __tcp_sock_set_keepidle(sk, val);
+	err = tcp_sock_set_keepidle_locked(sk, val);
 	release_sock(sk);
 	return err;
 }
@@ -3183,7 +3183,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_KEEPIDLE:
-		err = __tcp_sock_set_keepidle(sk, val);
+		err = tcp_sock_set_keepidle_locked(sk, val);
 		break;
 	case TCP_KEEPINTVL:
 		if (val < 1 || val > MAX_TCP_KEEPINTVL)
-- 
cgit v1.2.3


From 0ef44e5cab8dbf0a0327871b48fe7c8425d0d885 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 23 Jun 2020 16:30:07 +0200
Subject: net: phy: add support for a common probe between shared PHYs

Shared PHYs (PHYs in the same hardware package) may have shared
registers and their drivers would usually need to share information.
There is currently a way to have a shared (part of the) init, by using
phy_package_init_once(). This patch extends the logic to share parts of
the probe to allow sharing the initialization of locks or resources
retrieval.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7860d56c6bf5..6fb8f302978d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -244,7 +244,8 @@ struct phy_package_shared {
 };
 
 /* used as bit number in atomic bitops */
-#define PHY_SHARED_F_INIT_DONE 0
+#define PHY_SHARED_F_INIT_DONE  0
+#define PHY_SHARED_F_PROBE_DONE 1
 
 /*
  * The Bus class for PHYs.  Devices which provide access to
@@ -1566,14 +1567,25 @@ static inline int __phy_package_write(struct phy_device *phydev,
 	return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
 }
 
-static inline bool phy_package_init_once(struct phy_device *phydev)
+static inline bool __phy_package_set_once(struct phy_device *phydev,
+					  unsigned int b)
 {
 	struct phy_package_shared *shared = phydev->shared;
 
 	if (!shared)
 		return false;
 
-	return !test_and_set_bit(PHY_SHARED_F_INIT_DONE, &shared->flags);
+	return !test_and_set_bit(b, &shared->flags);
+}
+
+static inline bool phy_package_init_once(struct phy_device *phydev)
+{
+	return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE);
+}
+
+static inline bool phy_package_probe_once(struct phy_device *phydev)
+{
+	return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE);
 }
 
 extern struct bus_type mdio_bus_type;
-- 
cgit v1.2.3


From 3dd4ef1bdbac959bb20faec93937720ddd9917c6 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Wed, 24 Jun 2020 15:58:24 +0800
Subject: net: phy: make phy_disable_interrupts() non-static

We face an issue with rtl8211f, a pin is shared between INTB and PMEB,
and the PHY Register Accessible Interrupt is enabled by default, so
the INTB/PMEB pin is always active in polling mode case.

As Heiner pointed out "I was thinking about calling
phy_disable_interrupts() in phy_init_hw(), to have a defined init
state as we don't know in which state the PHY is if the PHY driver is
loaded. We shouldn't assume that it's the chip power-on defaults, BIOS
or boot loader could have changed this. Or in case of dual-boot
systems the other OS could leave the PHY in whatever state."

Make phy_disable_interrupts() non-static so that it could be used in
phy_init_hw() to have a defined init state.

Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 include/linux/phy.h   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1de3938628f4..56cfae950472 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -840,7 +840,7 @@ static void phy_error(struct phy_device *phydev)
  * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
  * @phydev: target phy_device struct
  */
-static int phy_disable_interrupts(struct phy_device *phydev)
+int phy_disable_interrupts(struct phy_device *phydev)
 {
 	int err;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8c05d0fb5c00..b693b609b2f5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1416,6 +1416,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd);
 int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
 int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd);
+int phy_disable_interrupts(struct phy_device *phydev);
 void phy_request_interrupt(struct phy_device *phydev);
 void phy_free_interrupt(struct phy_device *phydev);
 void phy_print_status(struct phy_device *phydev);
-- 
cgit v1.2.3


From 1cbf90985f7448f1b0dd630e17ee1070f7d58665 Mon Sep 17 00:00:00 2001
From: David Wilder <dwilder@us.ibm.com>
Date: Mon, 22 Jun 2020 10:10:11 -0700
Subject: netfilter: iptables: Split ipt_unregister_table() into pre_exit and
 exit helpers.

The pre_exit will un-register the underlying hook and .exit will do the
table freeing. The netns core does an unconditional synchronize_rcu after
the pre_exit hooks insuring no packets are in flight that have picked up
the pointer before completing the un-register.

Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default")
Signed-off-by: David Wilder <dwilder@us.ibm.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv4/ip_tables.h |  6 ++++++
 net/ipv4/netfilter/ip_tables.c           | 15 ++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h
index b394bd4f68a3..c4676d6feeff 100644
--- a/include/linux/netfilter_ipv4/ip_tables.h
+++ b/include/linux/netfilter_ipv4/ip_tables.h
@@ -25,6 +25,12 @@
 int ipt_register_table(struct net *net, const struct xt_table *table,
 		       const struct ipt_replace *repl,
 		       const struct nf_hook_ops *ops, struct xt_table **res);
+
+void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+		       const struct nf_hook_ops *ops);
+
+void ipt_unregister_table_exit(struct net *net, struct xt_table *table);
+
 void ipt_unregister_table(struct net *net, struct xt_table *table,
 			  const struct nf_hook_ops *ops);
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c2670eaa74e6..5bf9fa06aee0 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1797,11 +1797,22 @@ out_free:
 	return ret;
 }
 
+void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+				   const struct nf_hook_ops *ops)
+{
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+
+void ipt_unregister_table_exit(struct net *net, struct xt_table *table)
+{
+	__ipt_unregister_table(net, table);
+}
+
 void ipt_unregister_table(struct net *net, struct xt_table *table,
 			  const struct nf_hook_ops *ops)
 {
 	if (ops)
-		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+		ipt_unregister_table_pre_exit(net, table, ops);
 	__ipt_unregister_table(net, table);
 }
 
@@ -1958,6 +1969,8 @@ static void __exit ip_tables_fini(void)
 
 EXPORT_SYMBOL(ipt_register_table);
 EXPORT_SYMBOL(ipt_unregister_table);
+EXPORT_SYMBOL(ipt_unregister_table_pre_exit);
+EXPORT_SYMBOL(ipt_unregister_table_exit);
 EXPORT_SYMBOL(ipt_do_table);
 module_init(ip_tables_init);
 module_exit(ip_tables_fini);
-- 
cgit v1.2.3


From 57ea5f18882a3d7cf6135fa8c949a37c89395837 Mon Sep 17 00:00:00 2001
From: David Wilder <dwilder@us.ibm.com>
Date: Mon, 22 Jun 2020 10:10:13 -0700
Subject: netfilter: ip6tables: Split ip6t_unregister_table() into pre_exit and
 exit helpers.

The pre_exit will un-register the underlying hook and .exit will do
the table freeing. The netns core does an unconditional synchronize_rcu
after the pre_exit hooks insuring no packets are in flight that have
picked up the pointer before completing the un-register.

Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default")
Signed-off-by: David Wilder <dwilder@us.ibm.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv6/ip6_tables.h |  3 +++
 net/ipv6/netfilter/ip6_tables.c           | 15 ++++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index 8225f7821a29..1547d5f9ae06 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -29,6 +29,9 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 			const struct nf_hook_ops *ops, struct xt_table **res);
 void ip6t_unregister_table(struct net *net, struct xt_table *table,
 			   const struct nf_hook_ops *ops);
+void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+				    const struct nf_hook_ops *ops);
+void ip6t_unregister_table_exit(struct net *net, struct xt_table *table);
 extern unsigned int ip6t_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e27393498ecb..e96a431549bc 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1807,11 +1807,22 @@ out_free:
 	return ret;
 }
 
+void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+				    const struct nf_hook_ops *ops)
+{
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+
+void ip6t_unregister_table_exit(struct net *net, struct xt_table *table)
+{
+	__ip6t_unregister_table(net, table);
+}
+
 void ip6t_unregister_table(struct net *net, struct xt_table *table,
 			   const struct nf_hook_ops *ops)
 {
 	if (ops)
-		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+		ip6t_unregister_table_pre_exit(net, table, ops);
 	__ip6t_unregister_table(net, table);
 }
 
@@ -1969,6 +1980,8 @@ static void __exit ip6_tables_fini(void)
 
 EXPORT_SYMBOL(ip6t_register_table);
 EXPORT_SYMBOL(ip6t_unregister_table);
+EXPORT_SYMBOL(ip6t_unregister_table_pre_exit);
+EXPORT_SYMBOL(ip6t_unregister_table_exit);
 EXPORT_SYMBOL(ip6t_do_table);
 
 module_init(ip6_tables_init);
-- 
cgit v1.2.3


From af7ec13833619e17f03aa73a785a2f871da6d66b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:09 -0700
Subject: bpf: Add bpf_skc_to_tcp6_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a tcp6_sock pointer.
The return value could be NULL if the casting is illegal.

A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added
so the verifier is able to deduce proper return types for the helper.

Different from the previous BTF_ID based helpers,
the bpf_skc_to_tcp6_sock() argument can be several possible
btf_ids. More specifically, all possible socket data structures
with sock_common appearing in the first in the memory layout.
This patch only added socket types related to tcp and udp.

All possible argument btf_id and return value btf_id
for helper bpf_skc_to_tcp6_sock() are pre-calculcated and
cached. In the future, it is even possible to precompute
these btf_id's at kernel build time.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com
---
 include/linux/bpf.h            | 12 +++++++
 include/uapi/linux/bpf.h       |  9 ++++-
 kernel/bpf/btf.c               |  1 +
 kernel/bpf/verifier.c          | 43 ++++++++++++++++------
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 82 ++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h |  9 ++++-
 8 files changed, 148 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1e1501ee53ce..c0e38ad07848 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -265,6 +265,7 @@ enum bpf_return_type {
 	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
+	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -287,6 +288,12 @@ struct bpf_func_proto {
 		enum bpf_arg_type arg_type[5];
 	};
 	int *btf_id; /* BTF ids of arguments */
+	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
+						    * valid. Often used if more
+						    * than one btf id is permitted
+						    * for this argument.
+						    */
+	int *ret_btf_id; /* return value btf_id */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -1524,6 +1531,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
+void init_btf_sock_ids(struct btf *btf);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1549,6 +1557,9 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
+static inline void init_btf_sock_ids(struct btf *btf)
+{
+}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
@@ -1638,6 +1649,7 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
 extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d9737d51dd19..e90ad07b291a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e377d1981730..4c3007f428b1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3674,6 +3674,7 @@ struct btf *btf_parse_vmlinux(void)
 		goto errout;
 
 	bpf_struct_ops_init(btf, log);
+	init_btf_sock_ids(btf);
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7460f967cb75..7de98906ddf4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3800,12 +3800,14 @@ static int int_ptr_type_to_size(enum bpf_arg_type type)
 	return -EINVAL;
 }
 
-static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
-			  enum bpf_arg_type arg_type,
-			  struct bpf_call_arg_meta *meta)
+static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+			  struct bpf_call_arg_meta *meta,
+			  const struct bpf_func_proto *fn)
 {
+	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected_type, type = reg->type;
+	enum bpf_arg_type arg_type = fn->arg_type[arg];
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -3885,9 +3887,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
-		if (reg->btf_id != meta->btf_id) {
-			verbose(env, "Helper has type %s got %s in R%d\n",
-				kernel_type_name(meta->btf_id),
+		if (!fn->check_btf_id) {
+			if (reg->btf_id != meta->btf_id) {
+				verbose(env, "Helper has type %s got %s in R%d\n",
+					kernel_type_name(meta->btf_id),
+					kernel_type_name(reg->btf_id), regno);
+
+				return -EACCES;
+			}
+		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
+			verbose(env, "Helper does not support %s in R%d\n",
 				kernel_type_name(reg->btf_id), regno);
 
 			return -EACCES;
@@ -4709,10 +4718,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		err = btf_resolve_helper_id(&env->log, fn, i);
-		if (err > 0)
-			meta.btf_id = err;
-		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (!fn->check_btf_id) {
+			err = btf_resolve_helper_id(&env->log, fn, i);
+			if (err > 0)
+				meta.btf_id = err;
+		}
+		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
 	}
@@ -4815,6 +4826,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+		int ret_btf_id;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+		ret_btf_id = *fn->ret_btf_id;
+		if (ret_btf_id == 0) {
+			verbose(env, "invalid return type %d of func %s#%d\n",
+				fn->ret_type, func_id_name(func_id), func_id);
+			return -EINVAL;
+		}
+		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0159f12d2af5..2a97a268f533 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1515,6 +1515,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_output_proto;
 	case BPF_FUNC_xdp_output:
 		return &bpf_xdp_output_proto;
+	case BPF_FUNC_skc_to_tcp6_sock:
+		return &bpf_skc_to_tcp6_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index c713b6b8938f..176e27d75c51 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -47,6 +47,7 @@
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <net/sch_generic.h>
 #include <net/cls_cgroup.h>
 #include <net/dst_metadata.h>
@@ -9225,3 +9226,84 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog)
 {
 	bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog);
 }
+
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, "inet_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, "inet_connection_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, "inet_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, "inet_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, "request_sock")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, "sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, "sock_common")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, "tcp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, "tcp_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, "tcp_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, "tcp6_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, "udp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, "udp6_sock")
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+static int btf_sock_ids[MAX_BTF_SOCK_TYPE];
+
+#ifdef CONFIG_BPF_SYSCALL
+static const char *bpf_sock_types[] = {
+#define BTF_SOCK_TYPE(name, str) str,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+};
+
+void init_btf_sock_ids(struct btf *btf)
+{
+	int i, btf_id;
+
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) {
+		btf_id = btf_find_by_name_kind(btf, bpf_sock_types[i],
+					       BTF_KIND_STRUCT);
+		if (btf_id > 0)
+			btf_sock_ids[i] = btf_id;
+	}
+}
+#endif
+
+static bool check_arg_btf_id(u32 btf_id, u32 arg)
+{
+	int i;
+
+	/* only one argument, no need to check arg */
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
+		if (btf_sock_ids[i] == btf_id)
+			return true;
+	return false;
+}
+
+BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
+{
+	/* tcp6_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct tcp6_sock);
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP &&
+	    sk->sk_family == AF_INET6)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
+	.func			= bpf_skc_to_tcp6_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 91fa668fa860..6c2f64118651 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -421,6 +421,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -458,6 +459,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d9737d51dd19..e90ad07b291a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 478cfbdf5f13dfe09cfd0b1cbac821f5e27f6108 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:11 -0700
Subject: bpf: Add bpf_skc_to_{tcp, tcp_timewait, tcp_request}_sock() helpers

Three more helpers are added to cast a sock_common pointer to
an tcp_sock, tcp_timewait_sock or a tcp_request_sock for
tracing programs.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com
---
 include/linux/bpf.h            |  3 ++
 include/uapi/linux/bpf.h       | 23 +++++++++++++++-
 kernel/trace/bpf_trace.c       |  6 ++++
 net/core/filter.c              | 62 ++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  6 ++++
 tools/include/uapi/linux/bpf.h | 23 +++++++++++++++-
 6 files changed, 121 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c0e38ad07848..c23998cf6699 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1650,6 +1650,9 @@ extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e90ad07b291a..b9412ab275f3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3261,6 +3261,24 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3399,7 +3417,10 @@ union bpf_attr {
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
 	FN(csum_level),			\
-	FN(skc_to_tcp6_sock),
+	FN(skc_to_tcp6_sock),		\
+	FN(skc_to_tcp_sock),		\
+	FN(skc_to_tcp_timewait_sock),	\
+	FN(skc_to_tcp_request_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2a97a268f533..48d935b0d87c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1517,6 +1517,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_output_proto;
 	case BPF_FUNC_skc_to_tcp6_sock:
 		return &bpf_skc_to_tcp6_sock_proto;
+	case BPF_FUNC_skc_to_tcp_sock:
+		return &bpf_skc_to_tcp_sock_proto;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		return &bpf_skc_to_tcp_timewait_sock_proto;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		return &bpf_skc_to_tcp_request_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index 176e27d75c51..0b4e5aed7e20 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -74,6 +74,7 @@
 #include <net/lwtunnel.h>
 #include <net/ipv6_stubs.h>
 #include <net/bpf_sk_storage.h>
+#include <net/transp_v6.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -9307,3 +9308,64 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.check_btf_id		= check_arg_btf_id,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
+
+BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk)
+{
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
+	.func			= bpf_skc_to_tcp_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+};
+
+BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk)
+{
+	if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
+		return (unsigned long)sk;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT)
+		return (unsigned long)sk;
+#endif
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
+	.func			= bpf_skc_to_tcp_timewait_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
+};
+
+BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk)
+{
+	if (sk->sk_prot == &tcp_prot  && sk->sk_state == TCP_NEW_SYN_RECV)
+		return (unsigned long)sk;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV)
+		return (unsigned long)sk;
+#endif
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
+	.func			= bpf_skc_to_tcp_request_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6c2f64118651..d886657c6aaa 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -422,6 +422,9 @@ class PrinterHelpers(Printer):
             'struct tcphdr',
             'struct seq_file',
             'struct tcp6_sock',
+            'struct tcp_sock',
+            'struct tcp_timewait_sock',
+            'struct tcp_request_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -460,6 +463,9 @@ class PrinterHelpers(Printer):
             'struct tcphdr',
             'struct seq_file',
             'struct tcp6_sock',
+            'struct tcp_sock',
+            'struct tcp_timewait_sock',
+            'struct tcp_request_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e90ad07b291a..b9412ab275f3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3261,6 +3261,24 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3399,7 +3417,10 @@ union bpf_attr {
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
 	FN(csum_level),			\
-	FN(skc_to_tcp6_sock),
+	FN(skc_to_tcp6_sock),		\
+	FN(skc_to_tcp_sock),		\
+	FN(skc_to_tcp_timewait_sock),	\
+	FN(skc_to_tcp_request_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 0d4fad3e57df2bf61e8ffc8d12a34b1caf9b8835 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:15 -0700
Subject: bpf: Add bpf_skc_to_udp6_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a udp6_sock pointer.
The return value could be NULL if the casting is illegal.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  9 ++++++++-
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 22 ++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h |  9 ++++++++-
 6 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c23998cf6699..3d2ade703a35 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1653,6 +1653,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b9412ab275f3..0cb8ec948816 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3279,6 +3279,12 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3420,7 +3426,8 @@ union bpf_attr {
 	FN(skc_to_tcp6_sock),		\
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
-	FN(skc_to_tcp_request_sock),
+	FN(skc_to_tcp_request_sock),	\
+	FN(skc_to_udp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 48d935b0d87c..5d59dda5f661 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1523,6 +1523,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_tcp_timewait_sock_proto;
 	case BPF_FUNC_skc_to_tcp_request_sock:
 		return &bpf_skc_to_tcp_request_sock_proto;
+	case BPF_FUNC_skc_to_udp6_sock:
+		return &bpf_skc_to_udp6_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index 0b4e5aed7e20..c796e141ea8e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9369,3 +9369,25 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.check_btf_id		= check_arg_btf_id,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
+
+BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk)
+{
+	/* udp6_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct udp6_sock);
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP &&
+	    sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
+	.func			= bpf_skc_to_udp6_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index d886657c6aaa..6bab40ff442e 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -425,6 +425,7 @@ class PrinterHelpers(Printer):
             'struct tcp_sock',
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
+            'struct udp6_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -466,6 +467,7 @@ class PrinterHelpers(Printer):
             'struct tcp_sock',
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
+            'struct udp6_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b9412ab275f3..0cb8ec948816 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3279,6 +3279,12 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3420,7 +3426,8 @@ union bpf_attr {
 	FN(skc_to_tcp6_sock),		\
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
-	FN(skc_to_tcp_request_sock),
+	FN(skc_to_tcp_request_sock),	\
+	FN(skc_to_udp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 58ffbba6a39979baa22d2f7e69faeffa2d9c0641 Mon Sep 17 00:00:00 2001
From: Akash Asthana <akashast@codeaurora.org>
Date: Tue, 23 Jun 2020 16:08:50 +0530
Subject: soc: qcom: geni: Support for ICC voting

Add necessary macros and structure variables to support ICC BW
voting from individual SE drivers.

Signed-off-by: Akash Asthana <akashast@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/1592908737-7068-2-git-send-email-akashast@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/soc/qcom/qcom-geni-se.c | 82 +++++++++++++++++++++++++++++++++++++++++
 include/linux/qcom-geni-se.h    | 38 +++++++++++++++++++
 2 files changed, 120 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index 7d622ea1274e..950e3470c498 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -92,6 +92,9 @@ struct geni_wrapper {
 	struct clk_bulk_data ahb_clks[NUM_AHB_CLKS];
 };
 
+static const char * const icc_path_names[] = {"qup-core", "qup-config",
+						"qup-memory"};
+
 #define QUP_HW_VER_REG			0x4
 
 /* Common SE registers */
@@ -720,6 +723,85 @@ void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len)
 }
 EXPORT_SYMBOL(geni_se_rx_dma_unprep);
 
+int geni_icc_get(struct geni_se *se, const char *icc_ddr)
+{
+	int i, err;
+	const char *icc_names[] = {"qup-core", "qup-config", icc_ddr};
+
+	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
+		if (!icc_names[i])
+			continue;
+
+		se->icc_paths[i].path = devm_of_icc_get(se->dev, icc_names[i]);
+		if (IS_ERR(se->icc_paths[i].path))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	err = PTR_ERR(se->icc_paths[i].path);
+	if (err != -EPROBE_DEFER)
+		dev_err_ratelimited(se->dev, "Failed to get ICC path '%s': %d\n",
+					icc_names[i], err);
+	return err;
+
+}
+EXPORT_SYMBOL(geni_icc_get);
+
+int geni_icc_set_bw(struct geni_se *se)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
+		ret = icc_set_bw(se->icc_paths[i].path,
+			se->icc_paths[i].avg_bw, se->icc_paths[i].avg_bw);
+		if (ret) {
+			dev_err_ratelimited(se->dev, "ICC BW voting failed on path '%s': %d\n",
+					icc_path_names[i], ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(geni_icc_set_bw);
+
+/* To do: Replace this by icc_bulk_enable once it's implemented in ICC core */
+int geni_icc_enable(struct geni_se *se)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
+		ret = icc_enable(se->icc_paths[i].path);
+		if (ret) {
+			dev_err_ratelimited(se->dev, "ICC enable failed on path '%s': %d\n",
+					icc_path_names[i], ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(geni_icc_enable);
+
+int geni_icc_disable(struct geni_se *se)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
+		ret = icc_disable(se->icc_paths[i].path);
+		if (ret) {
+			dev_err_ratelimited(se->dev, "ICC disable failed on path '%s': %d\n",
+					icc_path_names[i], ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(geni_icc_disable);
+
 static int geni_se_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index dd464943f717..80dbc01904d6 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -6,6 +6,8 @@
 #ifndef _LINUX_QCOM_GENI_SE
 #define _LINUX_QCOM_GENI_SE
 
+#include <linux/interconnect.h>
+
 /* Transfer mode supported by GENI Serial Engines */
 enum geni_se_xfer_mode {
 	GENI_SE_INVALID,
@@ -25,6 +27,17 @@ enum geni_se_protocol_type {
 struct geni_wrapper;
 struct clk;
 
+enum geni_icc_path_index {
+	GENI_TO_CORE,
+	CPU_TO_GENI,
+	GENI_TO_DDR
+};
+
+struct geni_icc_path {
+	struct icc_path *path;
+	unsigned int avg_bw;
+};
+
 /**
  * struct geni_se - GENI Serial Engine
  * @base:		Base Address of the Serial Engine's register block
@@ -33,6 +46,7 @@ struct clk;
  * @clk:		Handle to the core serial engine clock
  * @num_clk_levels:	Number of valid clock levels in clk_perf_tbl
  * @clk_perf_tbl:	Table of clock frequency input to serial engine clock
+ * @icc_paths:		Array of ICC paths for SE
  */
 struct geni_se {
 	void __iomem *base;
@@ -41,6 +55,7 @@ struct geni_se {
 	struct clk *clk;
 	unsigned int num_clk_levels;
 	unsigned long *clk_perf_tbl;
+	struct geni_icc_path icc_paths[3];
 };
 
 /* Common SE registers */
@@ -229,6 +244,21 @@ struct geni_se {
 #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT)
 #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK)
 
+/*
+ * Define bandwidth thresholds that cause the underlying Core 2X interconnect
+ * clock to run at the named frequency. These baseline values are recommended
+ * by the hardware team, and are not dynamically scaled with GENI bandwidth
+ * beyond basic on/off.
+ */
+#define CORE_2X_19_2_MHZ		960
+#define CORE_2X_50_MHZ			2500
+#define CORE_2X_100_MHZ			5000
+#define CORE_2X_150_MHZ			7500
+#define CORE_2X_200_MHZ			10000
+#define CORE_2X_236_MHZ			16383
+
+#define GENI_DEFAULT_BW			Bps_to_icc(1000)
+
 #if IS_ENABLED(CONFIG_QCOM_GENI_SE)
 
 u32 geni_se_get_qup_hw_version(struct geni_se *se);
@@ -416,5 +446,13 @@ int geni_se_rx_dma_prep(struct geni_se *se, void *buf, size_t len,
 void geni_se_tx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len);
 
 void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len);
+
+int geni_icc_get(struct geni_se *se, const char *icc_ddr);
+
+int geni_icc_set_bw(struct geni_se *se);
+
+int geni_icc_enable(struct geni_se *se);
+
+int geni_icc_disable(struct geni_se *se);
 #endif
 #endif
-- 
cgit v1.2.3


From 048eb908a1f276ca0346f20a3e6e7d707dcd81f3 Mon Sep 17 00:00:00 2001
From: Akash Asthana <akashast@codeaurora.org>
Date: Tue, 23 Jun 2020 16:08:51 +0530
Subject: soc: qcom-geni-se: Add interconnect support to fix earlycon crash

QUP core clock is shared among all the SE drivers present on particular
QUP wrapper, the system will reset(unclocked access) if earlycon used after
QUP core clock is put to 0 from other SE drivers before real console comes
up.

As earlycon can't vote for it's QUP core need, to fix this add ICC
support to common/QUP wrapper driver and put vote for QUP core from
probe on behalf of earlycon and remove vote during earlycon exit call.

Signed-off-by: Akash Asthana <akashast@codeaurora.org>
Reported-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/1592908737-7068-3-git-send-email-akashast@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/soc/qcom/qcom-geni-se.c       | 68 +++++++++++++++++++++++++++++++++++
 drivers/tty/serial/qcom_geni_serial.c |  7 ++++
 include/linux/qcom-geni-se.h          |  2 ++
 3 files changed, 77 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index 950e3470c498..e2a0ba278b6b 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -3,6 +3,7 @@
 
 #include <linux/acpi.h>
 #include <linux/clk.h>
+#include <linux/console.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
@@ -90,11 +91,14 @@ struct geni_wrapper {
 	struct device *dev;
 	void __iomem *base;
 	struct clk_bulk_data ahb_clks[NUM_AHB_CLKS];
+	struct geni_icc_path to_core;
 };
 
 static const char * const icc_path_names[] = {"qup-core", "qup-config",
 						"qup-memory"};
 
+static struct geni_wrapper *earlycon_wrapper;
+
 #define QUP_HW_VER_REG			0x4
 
 /* Common SE registers */
@@ -802,11 +806,38 @@ int geni_icc_disable(struct geni_se *se)
 }
 EXPORT_SYMBOL(geni_icc_disable);
 
+void geni_remove_earlycon_icc_vote(void)
+{
+	struct geni_wrapper *wrapper;
+	struct device_node *parent;
+	struct device_node *child;
+
+	if (!earlycon_wrapper)
+		return;
+
+	wrapper = earlycon_wrapper;
+	parent = of_get_next_parent(wrapper->dev->of_node);
+	for_each_child_of_node(parent, child) {
+		if (!of_device_is_compatible(child, "qcom,geni-se-qup"))
+			continue;
+		wrapper = platform_get_drvdata(of_find_device_by_node(child));
+		icc_put(wrapper->to_core.path);
+		wrapper->to_core.path = NULL;
+
+	}
+	of_node_put(parent);
+
+	earlycon_wrapper = NULL;
+}
+EXPORT_SYMBOL(geni_remove_earlycon_icc_vote);
+
 static int geni_se_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct geni_wrapper *wrapper;
+	struct console __maybe_unused *bcon;
+	bool __maybe_unused has_earlycon = false;
 	int ret;
 
 	wrapper = devm_kzalloc(dev, sizeof(*wrapper), GFP_KERNEL);
@@ -829,6 +860,43 @@ static int geni_se_probe(struct platform_device *pdev)
 		}
 	}
 
+#ifdef CONFIG_SERIAL_EARLYCON
+	for_each_console(bcon) {
+		if (!strcmp(bcon->name, "qcom_geni")) {
+			has_earlycon = true;
+			break;
+		}
+	}
+	if (!has_earlycon)
+		goto exit;
+
+	wrapper->to_core.path = devm_of_icc_get(dev, "qup-core");
+	if (IS_ERR(wrapper->to_core.path))
+		return PTR_ERR(wrapper->to_core.path);
+	/*
+	 * Put minmal BW request on core clocks on behalf of early console.
+	 * The vote will be removed earlycon exit function.
+	 *
+	 * Note: We are putting vote on each QUP wrapper instead only to which
+	 * earlycon is connected because QUP core clock of different wrapper
+	 * share same voltage domain. If core1 is put to 0, then core2 will
+	 * also run at 0, if not voted. Default ICC vote will be removed ASA
+	 * we touch any of the core clock.
+	 * core1 = core2 = max(core1, core2)
+	 */
+	ret = icc_set_bw(wrapper->to_core.path, GENI_DEFAULT_BW,
+				GENI_DEFAULT_BW);
+	if (ret) {
+		dev_err(&pdev->dev, "%s: ICC BW voting failed for core: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	if (of_get_compatible_child(pdev->dev.of_node, "qcom,geni-debug-uart"))
+		earlycon_wrapper = wrapper;
+	of_node_put(pdev->dev.of_node);
+#endif
+exit:
 	dev_set_drvdata(dev, wrapper);
 	dev_dbg(dev, "GENI SE Driver probed\n");
 	return devm_of_platform_populate(dev);
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 457c0bf8cbf8..a4468db3b734 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1121,6 +1121,12 @@ static inline void qcom_geni_serial_enable_early_read(struct geni_se *se,
 						      struct console *con) { }
 #endif
 
+static int qcom_geni_serial_earlycon_exit(struct console *con)
+{
+	geni_remove_earlycon_icc_vote();
+	return 0;
+}
+
 static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
 								const char *opt)
 {
@@ -1166,6 +1172,7 @@ static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
 	writel(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN);
 
 	dev->con->write = qcom_geni_serial_earlycon_write;
+	dev->con->exit = qcom_geni_serial_earlycon_exit;
 	dev->con->setup = NULL;
 	qcom_geni_serial_enable_early_read(&se, dev->con);
 
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 80dbc01904d6..743dd975d1cd 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -454,5 +454,7 @@ int geni_icc_set_bw(struct geni_se *se);
 int geni_icc_enable(struct geni_se *se);
 
 int geni_icc_disable(struct geni_se *se);
+
+void geni_remove_earlycon_icc_vote(void);
 #endif
 #endif
-- 
cgit v1.2.3


From a5819b548af0cc0fd0b84fa3e35723c4c36f157c Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <rnayak@codeaurora.org>
Date: Mon, 15 Jun 2020 17:32:39 +0530
Subject: tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state

geni serial needs to express a perforamnce state requirement on CX
powerdomain depending on the frequency of the clock rates.
Use OPP table from DT to register with OPP framework and use
dev_pm_opp_set_rate() to set the clk/perf state.

Signed-off-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Akash Asthana <akashast@codeaurora.org>
Cc: linux-serial@vger.kernel.org
Link: https://lore.kernel.org/r/1592222564-13556-2-git-send-email-rnayak@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/tty/serial/qcom_geni_serial.c | 29 +++++++++++++++++++++++++----
 include/linux/qcom-geni-se.h          |  4 ++++
 2 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index f701c7e9b89d..0300867eab7a 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_wakeirq.h>
@@ -963,7 +964,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport,
 		goto out_restart_rx;
 
 	uport->uartclk = clk_rate;
-	clk_set_rate(port->se.clk, clk_rate);
+	dev_pm_opp_set_rate(uport->dev, clk_rate);
 	ser_clk_cfg = SER_CLK_EN;
 	ser_clk_cfg |= clk_div << CLK_DIV_SHFT;
 
@@ -1383,13 +1384,25 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	if (of_property_read_bool(pdev->dev.of_node, "cts-rts-swap"))
 		port->cts_rts_swap = true;
 
+	port->se.opp_table = dev_pm_opp_set_clkname(&pdev->dev, "se");
+	if (IS_ERR(port->se.opp_table))
+		return PTR_ERR(port->se.opp_table);
+	/* OPP table is optional */
+	ret = dev_pm_opp_of_add_table(&pdev->dev);
+	if (!ret) {
+		port->se.has_opp_table = true;
+	} else if (ret != -ENODEV) {
+		dev_err(&pdev->dev, "invalid OPP table in device tree\n");
+		return ret;
+	}
+
 	uport->private_data = drv;
 	platform_set_drvdata(pdev, port);
 	port->handle_rx = console ? handle_rx_console : handle_rx_uart;
 
 	ret = uart_add_one_port(drv, uport);
 	if (ret)
-		return ret;
+		goto err;
 
 	irq_set_status_flags(uport->irq, IRQ_NOAUTOEN);
 	ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr,
@@ -1397,7 +1410,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret);
 		uart_remove_one_port(drv, uport);
-		return ret;
+		goto err;
 	}
 
 	/*
@@ -1414,11 +1427,16 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 		if (ret) {
 			device_init_wakeup(&pdev->dev, false);
 			uart_remove_one_port(drv, uport);
-			return ret;
+			goto err;
 		}
 	}
 
 	return 0;
+err:
+	if (port->se.has_opp_table)
+		dev_pm_opp_of_remove_table(&pdev->dev);
+	dev_pm_opp_put_clkname(port->se.opp_table);
+	return ret;
 }
 
 static int qcom_geni_serial_remove(struct platform_device *pdev)
@@ -1426,6 +1444,9 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
 	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
 	struct uart_driver *drv = port->uport.private_data;
 
+	if (port->se.has_opp_table)
+		dev_pm_opp_of_remove_table(&pdev->dev);
+	dev_pm_opp_put_clkname(port->se.opp_table);
 	dev_pm_clear_wake_irq(&pdev->dev);
 	device_init_wakeup(&pdev->dev, false);
 	uart_remove_one_port(drv, &port->uport);
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 743dd975d1cd..afa511ef1457 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -47,6 +47,8 @@ struct geni_icc_path {
  * @num_clk_levels:	Number of valid clock levels in clk_perf_tbl
  * @clk_perf_tbl:	Table of clock frequency input to serial engine clock
  * @icc_paths:		Array of ICC paths for SE
+ * @opp_table:		Pointer to the OPP table
+ * @has_opp_table:	Specifies if the SE has an OPP table
  */
 struct geni_se {
 	void __iomem *base;
@@ -56,6 +58,8 @@ struct geni_se {
 	unsigned int num_clk_levels;
 	unsigned long *clk_perf_tbl;
 	struct geni_icc_path icc_paths[3];
+	struct opp_table *opp_table;
+	bool has_opp_table;
 };
 
 /* Common SE registers */
-- 
cgit v1.2.3


From 5e48a03bb9bff1728164040d71aa03cdb3cdfca2 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Wed, 24 Jun 2020 01:09:23 -0700
Subject: platform/chrome: cros_ec: Add TBT pd_ctrl fields

To support Thunderbolt compatibility mode, synchronize
ec_response_usb_pd_control_v2 with the Chrome EC version, so that
we get the Thunderbolt related control fields and macros.

Signed-off-by: Prashant Malani <pmalani@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
---
 include/linux/platform_data/cros_ec_commands.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index a7b0fc440c35..b808570bdd04 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -4917,15 +4917,26 @@ struct ec_response_usb_pd_control_v1 {
 #define USBC_PD_CC_UFP_ATTACHED	4 /* UFP attached to usbc */
 #define USBC_PD_CC_DFP_ATTACHED	5 /* DPF attached to usbc */
 
+/* Active/Passive Cable */
+#define USB_PD_CTRL_ACTIVE_CABLE        BIT(0)
+/* Optical/Non-optical cable */
+#define USB_PD_CTRL_OPTICAL_CABLE       BIT(1)
+/* 3rd Gen TBT device (or AMA)/2nd gen tbt Adapter */
+#define USB_PD_CTRL_TBT_LEGACY_ADAPTER  BIT(2)
+/* Active Link Uni-Direction */
+#define USB_PD_CTRL_ACTIVE_LINK_UNIDIR  BIT(3)
+
 struct ec_response_usb_pd_control_v2 {
 	uint8_t enabled;
 	uint8_t role;
 	uint8_t polarity;
 	char state[32];
-	uint8_t cc_state; /* USBC_PD_CC_*Encoded cc state */
-	uint8_t dp_mode;  /* Current DP pin mode (MODE_DP_PIN_[A-E]) */
-	/* CL:1500994 Current cable type */
-	uint8_t reserved_cable_type;
+	uint8_t cc_state;	/* enum pd_cc_states representing cc state */
+	uint8_t dp_mode;	/* Current DP pin mode (MODE_DP_PIN_[A-E]) */
+	uint8_t reserved;	/* Reserved for future use */
+	uint8_t control_flags;	/* USB_PD_CTRL_*flags */
+	uint8_t cable_speed;	/* TBT_SS_* cable speed */
+	uint8_t cable_gen;	/* TBT_GEN3_* cable rounded support */
 } __ec_align1;
 
 #define EC_CMD_USB_PD_PORTS 0x0102
-- 
cgit v1.2.3


From 0c1a7f13c9ec1ceb18d97ef4b1dd20ec71ffba31 Mon Sep 17 00:00:00 2001
From: Veerendranath Jakkam <vjakkam@codeaurora.org>
Date: Wed, 17 Jun 2020 17:01:32 +0530
Subject: ieee80211: Add missing and new AKM suite selector definitions

Add the definitions for missing AKM selectors defined in
IEEE P802.11-REVmd/D3.0, table 9-151. These definitions will
be used by various drivers that support these new AKM suites.

Signed-off-by: Veerendranath Jakkam <vjakkam@codeaurora.org>
Link: https://lore.kernel.org/r/20200617113132.13477-1-vjakkam@codeaurora.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index fe15f831841b..9f732499ea88 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3333,13 +3333,17 @@ struct ieee80211_multiple_bssid_configuration {
 #define WLAN_AKM_SUITE_TDLS			SUITE(0x000FAC, 7)
 #define WLAN_AKM_SUITE_SAE			SUITE(0x000FAC, 8)
 #define WLAN_AKM_SUITE_FT_OVER_SAE		SUITE(0x000FAC, 9)
+#define WLAN_AKM_SUITE_AP_PEER_KEY		SUITE(0x000FAC, 10)
 #define WLAN_AKM_SUITE_8021X_SUITE_B		SUITE(0x000FAC, 11)
 #define WLAN_AKM_SUITE_8021X_SUITE_B_192	SUITE(0x000FAC, 12)
+#define WLAN_AKM_SUITE_FT_8021X_SHA384		SUITE(0x000FAC, 13)
 #define WLAN_AKM_SUITE_FILS_SHA256		SUITE(0x000FAC, 14)
 #define WLAN_AKM_SUITE_FILS_SHA384		SUITE(0x000FAC, 15)
 #define WLAN_AKM_SUITE_FT_FILS_SHA256		SUITE(0x000FAC, 16)
 #define WLAN_AKM_SUITE_FT_FILS_SHA384		SUITE(0x000FAC, 17)
 #define WLAN_AKM_SUITE_OWE			SUITE(0x000FAC, 18)
+#define WLAN_AKM_SUITE_FT_PSK_SHA384		SUITE(0x000FAC, 19)
+#define WLAN_AKM_SUITE_PSK_SHA384		SUITE(0x000FAC, 20)
 
 #define WLAN_MAX_KEY_LEN		32
 
-- 
cgit v1.2.3


From 01e377c539ca52a6c753d0fdbe93b3b8fcd66a1c Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 18 Jun 2020 21:08:10 +0200
Subject: sched/core: Remove mmdrop() definition

Commit
   bf2c59fce4074 ("sched/core: Fix illegal RCU from offline CPUs")

introduced a definition for mmdrop() but a a few lines above there is
already mmdrop() defined as static inline.

Remove the newly introduced mmdrop() definition.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200618190810.790211-1-bigeasy@linutronix.de
---
 include/linux/sched/mm.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 480a4d1b7dd8..a98604ea76f1 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,8 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-void mmdrop(struct mm_struct *mm);
-
 /*
  * This has to be called after a get_task_mm()/mmget_not_zero()
  * followed by taking the mmap_lock for writing before modifying the
-- 
cgit v1.2.3


From a9b59159d338d414acaa8e2f569d129d51c76452 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Wed, 24 Jun 2020 15:20:39 -0700
Subject: bpf: Do not allow btf_ctx_access with __int128 types

To ensure btf_ctx_access() is safe the verifier checks that the BTF
arg type is an int, enum, or pointer. When the function does the
BTF arg lookup it uses the calculation 'arg = off / 8'  using the
fact that registers are 8B. This requires that the first arg is
in the first reg, the second in the second, and so on. However,
for __int128 the arg will consume two registers by default LLVM
implementation. So this will cause the arg layout assumed by the
'arg = off / 8' calculation to be incorrect.

Because __int128 is uncommon this patch applies the easiest fix and
will force int types to be sizeof(u64) or smaller so that they will
fit in a single register.

v2: remove unneeded parens per Andrii's feedback

Fixes: 9e15db66136a1 ("bpf: Implement accurate raw_tp context access via BTF")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/159303723962.11287.13309537171132420717.stgit@john-Precision-5820-Tower
---
 include/linux/btf.h | 5 +++++
 kernel/bpf/btf.c    | 4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 5c1ea99b480f..8b81fbb4497c 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
 }
 
+static inline bool btf_type_is_small_int(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && t->size <= sizeof(u64);
+}
+
 static inline bool btf_type_is_enum(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 58c9af1d4808..9a1a98dd9e97 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3746,7 +3746,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 				return false;
 
 			t = btf_type_skip_modifiers(btf, t->type, NULL);
-			if (!btf_type_is_int(t)) {
+			if (!btf_type_is_small_int(t)) {
 				bpf_log(log,
 					"ret type %s not allowed for fmod_ret\n",
 					btf_kind_str[BTF_INFO_KIND(t->info)]);
@@ -3768,7 +3768,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
-	if (btf_type_is_int(t) || btf_type_is_enum(t))
+	if (btf_type_is_small_int(t) || btf_type_is_enum(t))
 		/* accessing a scalar */
 		return true;
 	if (!btf_type_is_ptr(t)) {
-- 
cgit v1.2.3


From 5faafd5685764e4d75376aceac91fdf75b3b16f8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 25 Jun 2020 15:55:14 +0200
Subject: locking/atomics: Provide the arch_atomic_ interface to generic code

Architectures with instrumented (KASAN/KCSAN) atomic operations
natively provide arch_atomic_ variants that are not instrumented.

It turns out that some generic code also requires arch_atomic_ in
order to avoid instrumentation, so provide the arch_atomic_ interface
as a direct map into the regular atomic_ interface for
non-instrumented architectures.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/atomic-fallback.h       | 236 +++++++++++++++++++++++++++++++++-
 scripts/atomic/gen-atomic-fallback.sh |  31 +++++
 2 files changed, 266 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h
index 2c4927bf7b8d..fd525c71d676 100644
--- a/include/linux/atomic-fallback.h
+++ b/include/linux/atomic-fallback.h
@@ -77,6 +77,9 @@
 
 #endif /* cmpxchg64_relaxed */
 
+#define arch_atomic_read atomic_read
+#define arch_atomic_read_acquire atomic_read_acquire
+
 #ifndef atomic_read_acquire
 static __always_inline int
 atomic_read_acquire(const atomic_t *v)
@@ -86,6 +89,9 @@ atomic_read_acquire(const atomic_t *v)
 #define atomic_read_acquire atomic_read_acquire
 #endif
 
+#define arch_atomic_set atomic_set
+#define arch_atomic_set_release atomic_set_release
+
 #ifndef atomic_set_release
 static __always_inline void
 atomic_set_release(atomic_t *v, int i)
@@ -95,6 +101,13 @@ atomic_set_release(atomic_t *v, int i)
 #define atomic_set_release atomic_set_release
 #endif
 
+#define arch_atomic_add atomic_add
+
+#define arch_atomic_add_return atomic_add_return
+#define arch_atomic_add_return_acquire atomic_add_return_acquire
+#define arch_atomic_add_return_release atomic_add_return_release
+#define arch_atomic_add_return_relaxed atomic_add_return_relaxed
+
 #ifndef atomic_add_return_relaxed
 #define atomic_add_return_acquire atomic_add_return
 #define atomic_add_return_release atomic_add_return
@@ -137,6 +150,11 @@ atomic_add_return(int i, atomic_t *v)
 
 #endif /* atomic_add_return_relaxed */
 
+#define arch_atomic_fetch_add atomic_fetch_add
+#define arch_atomic_fetch_add_acquire atomic_fetch_add_acquire
+#define arch_atomic_fetch_add_release atomic_fetch_add_release
+#define arch_atomic_fetch_add_relaxed atomic_fetch_add_relaxed
+
 #ifndef atomic_fetch_add_relaxed
 #define atomic_fetch_add_acquire atomic_fetch_add
 #define atomic_fetch_add_release atomic_fetch_add
@@ -179,6 +197,13 @@ atomic_fetch_add(int i, atomic_t *v)
 
 #endif /* atomic_fetch_add_relaxed */
 
+#define arch_atomic_sub atomic_sub
+
+#define arch_atomic_sub_return atomic_sub_return
+#define arch_atomic_sub_return_acquire atomic_sub_return_acquire
+#define arch_atomic_sub_return_release atomic_sub_return_release
+#define arch_atomic_sub_return_relaxed atomic_sub_return_relaxed
+
 #ifndef atomic_sub_return_relaxed
 #define atomic_sub_return_acquire atomic_sub_return
 #define atomic_sub_return_release atomic_sub_return
@@ -221,6 +246,11 @@ atomic_sub_return(int i, atomic_t *v)
 
 #endif /* atomic_sub_return_relaxed */
 
+#define arch_atomic_fetch_sub atomic_fetch_sub
+#define arch_atomic_fetch_sub_acquire atomic_fetch_sub_acquire
+#define arch_atomic_fetch_sub_release atomic_fetch_sub_release
+#define arch_atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
+
 #ifndef atomic_fetch_sub_relaxed
 #define atomic_fetch_sub_acquire atomic_fetch_sub
 #define atomic_fetch_sub_release atomic_fetch_sub
@@ -263,6 +293,8 @@ atomic_fetch_sub(int i, atomic_t *v)
 
 #endif /* atomic_fetch_sub_relaxed */
 
+#define arch_atomic_inc atomic_inc
+
 #ifndef atomic_inc
 static __always_inline void
 atomic_inc(atomic_t *v)
@@ -272,6 +304,11 @@ atomic_inc(atomic_t *v)
 #define atomic_inc atomic_inc
 #endif
 
+#define arch_atomic_inc_return atomic_inc_return
+#define arch_atomic_inc_return_acquire atomic_inc_return_acquire
+#define arch_atomic_inc_return_release atomic_inc_return_release
+#define arch_atomic_inc_return_relaxed atomic_inc_return_relaxed
+
 #ifndef atomic_inc_return_relaxed
 #ifdef atomic_inc_return
 #define atomic_inc_return_acquire atomic_inc_return
@@ -353,6 +390,11 @@ atomic_inc_return(atomic_t *v)
 
 #endif /* atomic_inc_return_relaxed */
 
+#define arch_atomic_fetch_inc atomic_fetch_inc
+#define arch_atomic_fetch_inc_acquire atomic_fetch_inc_acquire
+#define arch_atomic_fetch_inc_release atomic_fetch_inc_release
+#define arch_atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed
+
 #ifndef atomic_fetch_inc_relaxed
 #ifdef atomic_fetch_inc
 #define atomic_fetch_inc_acquire atomic_fetch_inc
@@ -434,6 +476,8 @@ atomic_fetch_inc(atomic_t *v)
 
 #endif /* atomic_fetch_inc_relaxed */
 
+#define arch_atomic_dec atomic_dec
+
 #ifndef atomic_dec
 static __always_inline void
 atomic_dec(atomic_t *v)
@@ -443,6 +487,11 @@ atomic_dec(atomic_t *v)
 #define atomic_dec atomic_dec
 #endif
 
+#define arch_atomic_dec_return atomic_dec_return
+#define arch_atomic_dec_return_acquire atomic_dec_return_acquire
+#define arch_atomic_dec_return_release atomic_dec_return_release
+#define arch_atomic_dec_return_relaxed atomic_dec_return_relaxed
+
 #ifndef atomic_dec_return_relaxed
 #ifdef atomic_dec_return
 #define atomic_dec_return_acquire atomic_dec_return
@@ -524,6 +573,11 @@ atomic_dec_return(atomic_t *v)
 
 #endif /* atomic_dec_return_relaxed */
 
+#define arch_atomic_fetch_dec atomic_fetch_dec
+#define arch_atomic_fetch_dec_acquire atomic_fetch_dec_acquire
+#define arch_atomic_fetch_dec_release atomic_fetch_dec_release
+#define arch_atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed
+
 #ifndef atomic_fetch_dec_relaxed
 #ifdef atomic_fetch_dec
 #define atomic_fetch_dec_acquire atomic_fetch_dec
@@ -605,6 +659,13 @@ atomic_fetch_dec(atomic_t *v)
 
 #endif /* atomic_fetch_dec_relaxed */
 
+#define arch_atomic_and atomic_and
+
+#define arch_atomic_fetch_and atomic_fetch_and
+#define arch_atomic_fetch_and_acquire atomic_fetch_and_acquire
+#define arch_atomic_fetch_and_release atomic_fetch_and_release
+#define arch_atomic_fetch_and_relaxed atomic_fetch_and_relaxed
+
 #ifndef atomic_fetch_and_relaxed
 #define atomic_fetch_and_acquire atomic_fetch_and
 #define atomic_fetch_and_release atomic_fetch_and
@@ -647,6 +708,8 @@ atomic_fetch_and(int i, atomic_t *v)
 
 #endif /* atomic_fetch_and_relaxed */
 
+#define arch_atomic_andnot atomic_andnot
+
 #ifndef atomic_andnot
 static __always_inline void
 atomic_andnot(int i, atomic_t *v)
@@ -656,6 +719,11 @@ atomic_andnot(int i, atomic_t *v)
 #define atomic_andnot atomic_andnot
 #endif
 
+#define arch_atomic_fetch_andnot atomic_fetch_andnot
+#define arch_atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire
+#define arch_atomic_fetch_andnot_release atomic_fetch_andnot_release
+#define arch_atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed
+
 #ifndef atomic_fetch_andnot_relaxed
 #ifdef atomic_fetch_andnot
 #define atomic_fetch_andnot_acquire atomic_fetch_andnot
@@ -737,6 +805,13 @@ atomic_fetch_andnot(int i, atomic_t *v)
 
 #endif /* atomic_fetch_andnot_relaxed */
 
+#define arch_atomic_or atomic_or
+
+#define arch_atomic_fetch_or atomic_fetch_or
+#define arch_atomic_fetch_or_acquire atomic_fetch_or_acquire
+#define arch_atomic_fetch_or_release atomic_fetch_or_release
+#define arch_atomic_fetch_or_relaxed atomic_fetch_or_relaxed
+
 #ifndef atomic_fetch_or_relaxed
 #define atomic_fetch_or_acquire atomic_fetch_or
 #define atomic_fetch_or_release atomic_fetch_or
@@ -779,6 +854,13 @@ atomic_fetch_or(int i, atomic_t *v)
 
 #endif /* atomic_fetch_or_relaxed */
 
+#define arch_atomic_xor atomic_xor
+
+#define arch_atomic_fetch_xor atomic_fetch_xor
+#define arch_atomic_fetch_xor_acquire atomic_fetch_xor_acquire
+#define arch_atomic_fetch_xor_release atomic_fetch_xor_release
+#define arch_atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
+
 #ifndef atomic_fetch_xor_relaxed
 #define atomic_fetch_xor_acquire atomic_fetch_xor
 #define atomic_fetch_xor_release atomic_fetch_xor
@@ -821,6 +903,11 @@ atomic_fetch_xor(int i, atomic_t *v)
 
 #endif /* atomic_fetch_xor_relaxed */
 
+#define arch_atomic_xchg atomic_xchg
+#define arch_atomic_xchg_acquire atomic_xchg_acquire
+#define arch_atomic_xchg_release atomic_xchg_release
+#define arch_atomic_xchg_relaxed atomic_xchg_relaxed
+
 #ifndef atomic_xchg_relaxed
 #define atomic_xchg_acquire atomic_xchg
 #define atomic_xchg_release atomic_xchg
@@ -863,6 +950,11 @@ atomic_xchg(atomic_t *v, int i)
 
 #endif /* atomic_xchg_relaxed */
 
+#define arch_atomic_cmpxchg atomic_cmpxchg
+#define arch_atomic_cmpxchg_acquire atomic_cmpxchg_acquire
+#define arch_atomic_cmpxchg_release atomic_cmpxchg_release
+#define arch_atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed
+
 #ifndef atomic_cmpxchg_relaxed
 #define atomic_cmpxchg_acquire atomic_cmpxchg
 #define atomic_cmpxchg_release atomic_cmpxchg
@@ -905,6 +997,11 @@ atomic_cmpxchg(atomic_t *v, int old, int new)
 
 #endif /* atomic_cmpxchg_relaxed */
 
+#define arch_atomic_try_cmpxchg atomic_try_cmpxchg
+#define arch_atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire
+#define arch_atomic_try_cmpxchg_release atomic_try_cmpxchg_release
+#define arch_atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed
+
 #ifndef atomic_try_cmpxchg_relaxed
 #ifdef atomic_try_cmpxchg
 #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg
@@ -1002,6 +1099,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 
 #endif /* atomic_try_cmpxchg_relaxed */
 
+#define arch_atomic_sub_and_test atomic_sub_and_test
+
 #ifndef atomic_sub_and_test
 /**
  * atomic_sub_and_test - subtract value from variable and test result
@@ -1020,6 +1119,8 @@ atomic_sub_and_test(int i, atomic_t *v)
 #define atomic_sub_and_test atomic_sub_and_test
 #endif
 
+#define arch_atomic_dec_and_test atomic_dec_and_test
+
 #ifndef atomic_dec_and_test
 /**
  * atomic_dec_and_test - decrement and test
@@ -1037,6 +1138,8 @@ atomic_dec_and_test(atomic_t *v)
 #define atomic_dec_and_test atomic_dec_and_test
 #endif
 
+#define arch_atomic_inc_and_test atomic_inc_and_test
+
 #ifndef atomic_inc_and_test
 /**
  * atomic_inc_and_test - increment and test
@@ -1054,6 +1157,8 @@ atomic_inc_and_test(atomic_t *v)
 #define atomic_inc_and_test atomic_inc_and_test
 #endif
 
+#define arch_atomic_add_negative atomic_add_negative
+
 #ifndef atomic_add_negative
 /**
  * atomic_add_negative - add and test if negative
@@ -1072,6 +1177,8 @@ atomic_add_negative(int i, atomic_t *v)
 #define atomic_add_negative atomic_add_negative
 #endif
 
+#define arch_atomic_fetch_add_unless atomic_fetch_add_unless
+
 #ifndef atomic_fetch_add_unless
 /**
  * atomic_fetch_add_unless - add unless the number is already a given value
@@ -1097,6 +1204,8 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 #endif
 
+#define arch_atomic_add_unless atomic_add_unless
+
 #ifndef atomic_add_unless
 /**
  * atomic_add_unless - add unless the number is already a given value
@@ -1115,6 +1224,8 @@ atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_add_unless atomic_add_unless
 #endif
 
+#define arch_atomic_inc_not_zero atomic_inc_not_zero
+
 #ifndef atomic_inc_not_zero
 /**
  * atomic_inc_not_zero - increment unless the number is zero
@@ -1131,6 +1242,8 @@ atomic_inc_not_zero(atomic_t *v)
 #define atomic_inc_not_zero atomic_inc_not_zero
 #endif
 
+#define arch_atomic_inc_unless_negative atomic_inc_unless_negative
+
 #ifndef atomic_inc_unless_negative
 static __always_inline bool
 atomic_inc_unless_negative(atomic_t *v)
@@ -1147,6 +1260,8 @@ atomic_inc_unless_negative(atomic_t *v)
 #define atomic_inc_unless_negative atomic_inc_unless_negative
 #endif
 
+#define arch_atomic_dec_unless_positive atomic_dec_unless_positive
+
 #ifndef atomic_dec_unless_positive
 static __always_inline bool
 atomic_dec_unless_positive(atomic_t *v)
@@ -1163,6 +1278,8 @@ atomic_dec_unless_positive(atomic_t *v)
 #define atomic_dec_unless_positive atomic_dec_unless_positive
 #endif
 
+#define arch_atomic_dec_if_positive atomic_dec_if_positive
+
 #ifndef atomic_dec_if_positive
 static __always_inline int
 atomic_dec_if_positive(atomic_t *v)
@@ -1184,6 +1301,9 @@ atomic_dec_if_positive(atomic_t *v)
 #include <asm-generic/atomic64.h>
 #endif
 
+#define arch_atomic64_read atomic64_read
+#define arch_atomic64_read_acquire atomic64_read_acquire
+
 #ifndef atomic64_read_acquire
 static __always_inline s64
 atomic64_read_acquire(const atomic64_t *v)
@@ -1193,6 +1313,9 @@ atomic64_read_acquire(const atomic64_t *v)
 #define atomic64_read_acquire atomic64_read_acquire
 #endif
 
+#define arch_atomic64_set atomic64_set
+#define arch_atomic64_set_release atomic64_set_release
+
 #ifndef atomic64_set_release
 static __always_inline void
 atomic64_set_release(atomic64_t *v, s64 i)
@@ -1202,6 +1325,13 @@ atomic64_set_release(atomic64_t *v, s64 i)
 #define atomic64_set_release atomic64_set_release
 #endif
 
+#define arch_atomic64_add atomic64_add
+
+#define arch_atomic64_add_return atomic64_add_return
+#define arch_atomic64_add_return_acquire atomic64_add_return_acquire
+#define arch_atomic64_add_return_release atomic64_add_return_release
+#define arch_atomic64_add_return_relaxed atomic64_add_return_relaxed
+
 #ifndef atomic64_add_return_relaxed
 #define atomic64_add_return_acquire atomic64_add_return
 #define atomic64_add_return_release atomic64_add_return
@@ -1244,6 +1374,11 @@ atomic64_add_return(s64 i, atomic64_t *v)
 
 #endif /* atomic64_add_return_relaxed */
 
+#define arch_atomic64_fetch_add atomic64_fetch_add
+#define arch_atomic64_fetch_add_acquire atomic64_fetch_add_acquire
+#define arch_atomic64_fetch_add_release atomic64_fetch_add_release
+#define arch_atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
+
 #ifndef atomic64_fetch_add_relaxed
 #define atomic64_fetch_add_acquire atomic64_fetch_add
 #define atomic64_fetch_add_release atomic64_fetch_add
@@ -1286,6 +1421,13 @@ atomic64_fetch_add(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_add_relaxed */
 
+#define arch_atomic64_sub atomic64_sub
+
+#define arch_atomic64_sub_return atomic64_sub_return
+#define arch_atomic64_sub_return_acquire atomic64_sub_return_acquire
+#define arch_atomic64_sub_return_release atomic64_sub_return_release
+#define arch_atomic64_sub_return_relaxed atomic64_sub_return_relaxed
+
 #ifndef atomic64_sub_return_relaxed
 #define atomic64_sub_return_acquire atomic64_sub_return
 #define atomic64_sub_return_release atomic64_sub_return
@@ -1328,6 +1470,11 @@ atomic64_sub_return(s64 i, atomic64_t *v)
 
 #endif /* atomic64_sub_return_relaxed */
 
+#define arch_atomic64_fetch_sub atomic64_fetch_sub
+#define arch_atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire
+#define arch_atomic64_fetch_sub_release atomic64_fetch_sub_release
+#define arch_atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
+
 #ifndef atomic64_fetch_sub_relaxed
 #define atomic64_fetch_sub_acquire atomic64_fetch_sub
 #define atomic64_fetch_sub_release atomic64_fetch_sub
@@ -1370,6 +1517,8 @@ atomic64_fetch_sub(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_sub_relaxed */
 
+#define arch_atomic64_inc atomic64_inc
+
 #ifndef atomic64_inc
 static __always_inline void
 atomic64_inc(atomic64_t *v)
@@ -1379,6 +1528,11 @@ atomic64_inc(atomic64_t *v)
 #define atomic64_inc atomic64_inc
 #endif
 
+#define arch_atomic64_inc_return atomic64_inc_return
+#define arch_atomic64_inc_return_acquire atomic64_inc_return_acquire
+#define arch_atomic64_inc_return_release atomic64_inc_return_release
+#define arch_atomic64_inc_return_relaxed atomic64_inc_return_relaxed
+
 #ifndef atomic64_inc_return_relaxed
 #ifdef atomic64_inc_return
 #define atomic64_inc_return_acquire atomic64_inc_return
@@ -1460,6 +1614,11 @@ atomic64_inc_return(atomic64_t *v)
 
 #endif /* atomic64_inc_return_relaxed */
 
+#define arch_atomic64_fetch_inc atomic64_fetch_inc
+#define arch_atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire
+#define arch_atomic64_fetch_inc_release atomic64_fetch_inc_release
+#define arch_atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed
+
 #ifndef atomic64_fetch_inc_relaxed
 #ifdef atomic64_fetch_inc
 #define atomic64_fetch_inc_acquire atomic64_fetch_inc
@@ -1541,6 +1700,8 @@ atomic64_fetch_inc(atomic64_t *v)
 
 #endif /* atomic64_fetch_inc_relaxed */
 
+#define arch_atomic64_dec atomic64_dec
+
 #ifndef atomic64_dec
 static __always_inline void
 atomic64_dec(atomic64_t *v)
@@ -1550,6 +1711,11 @@ atomic64_dec(atomic64_t *v)
 #define atomic64_dec atomic64_dec
 #endif
 
+#define arch_atomic64_dec_return atomic64_dec_return
+#define arch_atomic64_dec_return_acquire atomic64_dec_return_acquire
+#define arch_atomic64_dec_return_release atomic64_dec_return_release
+#define arch_atomic64_dec_return_relaxed atomic64_dec_return_relaxed
+
 #ifndef atomic64_dec_return_relaxed
 #ifdef atomic64_dec_return
 #define atomic64_dec_return_acquire atomic64_dec_return
@@ -1631,6 +1797,11 @@ atomic64_dec_return(atomic64_t *v)
 
 #endif /* atomic64_dec_return_relaxed */
 
+#define arch_atomic64_fetch_dec atomic64_fetch_dec
+#define arch_atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire
+#define arch_atomic64_fetch_dec_release atomic64_fetch_dec_release
+#define arch_atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed
+
 #ifndef atomic64_fetch_dec_relaxed
 #ifdef atomic64_fetch_dec
 #define atomic64_fetch_dec_acquire atomic64_fetch_dec
@@ -1712,6 +1883,13 @@ atomic64_fetch_dec(atomic64_t *v)
 
 #endif /* atomic64_fetch_dec_relaxed */
 
+#define arch_atomic64_and atomic64_and
+
+#define arch_atomic64_fetch_and atomic64_fetch_and
+#define arch_atomic64_fetch_and_acquire atomic64_fetch_and_acquire
+#define arch_atomic64_fetch_and_release atomic64_fetch_and_release
+#define arch_atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
+
 #ifndef atomic64_fetch_and_relaxed
 #define atomic64_fetch_and_acquire atomic64_fetch_and
 #define atomic64_fetch_and_release atomic64_fetch_and
@@ -1754,6 +1932,8 @@ atomic64_fetch_and(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_and_relaxed */
 
+#define arch_atomic64_andnot atomic64_andnot
+
 #ifndef atomic64_andnot
 static __always_inline void
 atomic64_andnot(s64 i, atomic64_t *v)
@@ -1763,6 +1943,11 @@ atomic64_andnot(s64 i, atomic64_t *v)
 #define atomic64_andnot atomic64_andnot
 #endif
 
+#define arch_atomic64_fetch_andnot atomic64_fetch_andnot
+#define arch_atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire
+#define arch_atomic64_fetch_andnot_release atomic64_fetch_andnot_release
+#define arch_atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed
+
 #ifndef atomic64_fetch_andnot_relaxed
 #ifdef atomic64_fetch_andnot
 #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot
@@ -1844,6 +2029,13 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_andnot_relaxed */
 
+#define arch_atomic64_or atomic64_or
+
+#define arch_atomic64_fetch_or atomic64_fetch_or
+#define arch_atomic64_fetch_or_acquire atomic64_fetch_or_acquire
+#define arch_atomic64_fetch_or_release atomic64_fetch_or_release
+#define arch_atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
+
 #ifndef atomic64_fetch_or_relaxed
 #define atomic64_fetch_or_acquire atomic64_fetch_or
 #define atomic64_fetch_or_release atomic64_fetch_or
@@ -1886,6 +2078,13 @@ atomic64_fetch_or(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_or_relaxed */
 
+#define arch_atomic64_xor atomic64_xor
+
+#define arch_atomic64_fetch_xor atomic64_fetch_xor
+#define arch_atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire
+#define arch_atomic64_fetch_xor_release atomic64_fetch_xor_release
+#define arch_atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
+
 #ifndef atomic64_fetch_xor_relaxed
 #define atomic64_fetch_xor_acquire atomic64_fetch_xor
 #define atomic64_fetch_xor_release atomic64_fetch_xor
@@ -1928,6 +2127,11 @@ atomic64_fetch_xor(s64 i, atomic64_t *v)
 
 #endif /* atomic64_fetch_xor_relaxed */
 
+#define arch_atomic64_xchg atomic64_xchg
+#define arch_atomic64_xchg_acquire atomic64_xchg_acquire
+#define arch_atomic64_xchg_release atomic64_xchg_release
+#define arch_atomic64_xchg_relaxed atomic64_xchg_relaxed
+
 #ifndef atomic64_xchg_relaxed
 #define atomic64_xchg_acquire atomic64_xchg
 #define atomic64_xchg_release atomic64_xchg
@@ -1970,6 +2174,11 @@ atomic64_xchg(atomic64_t *v, s64 i)
 
 #endif /* atomic64_xchg_relaxed */
 
+#define arch_atomic64_cmpxchg atomic64_cmpxchg
+#define arch_atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire
+#define arch_atomic64_cmpxchg_release atomic64_cmpxchg_release
+#define arch_atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed
+
 #ifndef atomic64_cmpxchg_relaxed
 #define atomic64_cmpxchg_acquire atomic64_cmpxchg
 #define atomic64_cmpxchg_release atomic64_cmpxchg
@@ -2012,6 +2221,11 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 
 #endif /* atomic64_cmpxchg_relaxed */
 
+#define arch_atomic64_try_cmpxchg atomic64_try_cmpxchg
+#define arch_atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire
+#define arch_atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release
+#define arch_atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed
+
 #ifndef atomic64_try_cmpxchg_relaxed
 #ifdef atomic64_try_cmpxchg
 #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg
@@ -2109,6 +2323,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 
 #endif /* atomic64_try_cmpxchg_relaxed */
 
+#define arch_atomic64_sub_and_test atomic64_sub_and_test
+
 #ifndef atomic64_sub_and_test
 /**
  * atomic64_sub_and_test - subtract value from variable and test result
@@ -2127,6 +2343,8 @@ atomic64_sub_and_test(s64 i, atomic64_t *v)
 #define atomic64_sub_and_test atomic64_sub_and_test
 #endif
 
+#define arch_atomic64_dec_and_test atomic64_dec_and_test
+
 #ifndef atomic64_dec_and_test
 /**
  * atomic64_dec_and_test - decrement and test
@@ -2144,6 +2362,8 @@ atomic64_dec_and_test(atomic64_t *v)
 #define atomic64_dec_and_test atomic64_dec_and_test
 #endif
 
+#define arch_atomic64_inc_and_test atomic64_inc_and_test
+
 #ifndef atomic64_inc_and_test
 /**
  * atomic64_inc_and_test - increment and test
@@ -2161,6 +2381,8 @@ atomic64_inc_and_test(atomic64_t *v)
 #define atomic64_inc_and_test atomic64_inc_and_test
 #endif
 
+#define arch_atomic64_add_negative atomic64_add_negative
+
 #ifndef atomic64_add_negative
 /**
  * atomic64_add_negative - add and test if negative
@@ -2179,6 +2401,8 @@ atomic64_add_negative(s64 i, atomic64_t *v)
 #define atomic64_add_negative atomic64_add_negative
 #endif
 
+#define arch_atomic64_fetch_add_unless atomic64_fetch_add_unless
+
 #ifndef atomic64_fetch_add_unless
 /**
  * atomic64_fetch_add_unless - add unless the number is already a given value
@@ -2204,6 +2428,8 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
+#define arch_atomic64_add_unless atomic64_add_unless
+
 #ifndef atomic64_add_unless
 /**
  * atomic64_add_unless - add unless the number is already a given value
@@ -2222,6 +2448,8 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 #define atomic64_add_unless atomic64_add_unless
 #endif
 
+#define arch_atomic64_inc_not_zero atomic64_inc_not_zero
+
 #ifndef atomic64_inc_not_zero
 /**
  * atomic64_inc_not_zero - increment unless the number is zero
@@ -2238,6 +2466,8 @@ atomic64_inc_not_zero(atomic64_t *v)
 #define atomic64_inc_not_zero atomic64_inc_not_zero
 #endif
 
+#define arch_atomic64_inc_unless_negative atomic64_inc_unless_negative
+
 #ifndef atomic64_inc_unless_negative
 static __always_inline bool
 atomic64_inc_unless_negative(atomic64_t *v)
@@ -2254,6 +2484,8 @@ atomic64_inc_unless_negative(atomic64_t *v)
 #define atomic64_inc_unless_negative atomic64_inc_unless_negative
 #endif
 
+#define arch_atomic64_dec_unless_positive atomic64_dec_unless_positive
+
 #ifndef atomic64_dec_unless_positive
 static __always_inline bool
 atomic64_dec_unless_positive(atomic64_t *v)
@@ -2270,6 +2502,8 @@ atomic64_dec_unless_positive(atomic64_t *v)
 #define atomic64_dec_unless_positive atomic64_dec_unless_positive
 #endif
 
+#define arch_atomic64_dec_if_positive atomic64_dec_if_positive
+
 #ifndef atomic64_dec_if_positive
 static __always_inline s64
 atomic64_dec_if_positive(atomic64_t *v)
@@ -2288,4 +2522,4 @@ atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// 1fac0941c79bf0ae100723cc2ac9b94061f0b67a
+// 9d95b56f98d82a2a26c7b79ccdd0c47572d50a6f
diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh
index 0fd1cf0c2b94..693dfa1de430 100755
--- a/scripts/atomic/gen-atomic-fallback.sh
+++ b/scripts/atomic/gen-atomic-fallback.sh
@@ -58,6 +58,21 @@ cat << EOF
 EOF
 }
 
+gen_proto_order_variant()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+	local arch="$1"
+	local atomic="$2"
+
+	local basename="${arch}${atomic}_${pfx}${name}${sfx}"
+
+	printf "#define arch_${basename}${order} ${basename}${order}\n"
+}
+
 #gen_proto_order_variants(meta, pfx, name, sfx, arch, atomic, int, args...)
 gen_proto_order_variants()
 {
@@ -72,6 +87,22 @@ gen_proto_order_variants()
 
 	local template="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")"
 
+	if [ -z "$arch" ]; then
+		gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "" "$@"
+
+		if meta_has_acquire "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_acquire" "$@"
+		fi
+		if meta_has_release "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_release" "$@"
+		fi
+		if meta_has_relaxed "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_relaxed" "$@"
+		fi
+
+		echo ""
+	fi
+
 	# If we don't have relaxed atomics, then we don't bother with ordering fallbacks
 	# read_acquire and set_release need to be templated, though
 	if ! meta_has_relaxed "${meta}"; then
-- 
cgit v1.2.3


From b58e733fd774f3f4b49d9e7640d172a57e35200e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 15 Jun 2020 18:24:27 +0200
Subject: rcu: Fixup noinstr warnings

A KCSAN build revealed we have explicit annoations through atomic_*()
usage, switch to arch_atomic_*() for the respective functions.

vmlinux.o: warning: objtool: rcu_nmi_exit()+0x4d: call to __kcsan_check_access() leaves .noinstr.text section
vmlinux.o: warning: objtool: rcu_dynticks_eqs_enter()+0x25: call to __kcsan_check_access() leaves .noinstr.text section
vmlinux.o: warning: objtool: rcu_nmi_enter()+0x4f: call to __kcsan_check_access() leaves .noinstr.text section
vmlinux.o: warning: objtool: rcu_dynticks_eqs_exit()+0x2a: call to __kcsan_check_access() leaves .noinstr.text section
vmlinux.o: warning: objtool: __rcu_is_watching()+0x25: call to __kcsan_check_access() leaves .noinstr.text section

Additionally, without the NOP in instrumentation_begin(), objtool would
not detect the lack of the 'else instrumentation_begin();' branch in
rcu_nmi_enter().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/compiler.h |  2 +-
 kernel/rcu/tree.c        | 32 +++++++++++++++++++++++++-------
 2 files changed, 26 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 30827f82ad62..204e76856435 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -123,7 +123,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #ifdef CONFIG_DEBUG_ENTRY
 /* Begin/end of an instrumentation safe region */
 #define instrumentation_begin() ({					\
-	asm volatile("%c0:\n\t"						\
+	asm volatile("%c0: nop\n\t"						\
 		     ".pushsection .discard.instr_begin\n\t"		\
 		     ".long %c0b - .\n\t"				\
 		     ".popsection\n\t" : : "i" (__COUNTER__));		\
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c716eadc7617..6c6569e0586c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -250,7 +250,7 @@ static noinstr void rcu_dynticks_eqs_enter(void)
 	 * next idle sojourn.
 	 */
 	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
@@ -274,13 +274,13 @@ static noinstr void rcu_dynticks_eqs_exit(void)
 	 * and we also must force ordering with the next RCU read-side
 	 * critical section.
 	 */
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is now watching.  Better not be in an extended quiescent state!
 	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
-		atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
+		arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
 		smp_mb__after_atomic(); /* _exit after clearing mask. */
 	}
 }
@@ -313,7 +313,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+	return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
 }
 
 /*
@@ -633,6 +633,10 @@ static noinstr void rcu_eqs_enter(bool user)
 	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
 	// RCU is watching here ...
@@ -692,6 +696,7 @@ noinstr void rcu_nmi_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
+	instrumentation_begin();
 	/*
 	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
 	 * (We are exiting an NMI handler, so RCU better be paying attention
@@ -705,7 +710,6 @@ noinstr void rcu_nmi_exit(void)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		instrumentation_begin();
 		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
 				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
@@ -714,13 +718,15 @@ noinstr void rcu_nmi_exit(void)
 		return;
 	}
 
-	instrumentation_begin();
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (!in_nmi())
 		rcu_prepare_for_idle();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
 
 	// RCU is watching here ...
@@ -838,6 +844,10 @@ static void noinstr rcu_eqs_exit(bool user)
 	rcu_dynticks_eqs_exit();
 	// ... but is watching here.
 	instrumentation_begin();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
@@ -983,13 +993,21 @@ noinstr void rcu_nmi_enter(void)
 		if (!in_nmi())
 			rcu_cleanup_after_idle();
 
+		instrumentation_begin();
+		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+		// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+		instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 		incby = 1;
 	} else if (!in_nmi()) {
 		instrumentation_begin();
 		rcu_irq_enter_check_tick();
 		instrumentation_end();
+	} else  {
+		instrumentation_begin();
 	}
-	instrumentation_begin();
+
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
 			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
-- 
cgit v1.2.3


From c6d5d843d9b6e8dca3768250970f0d0a1e3d4fb0 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 24 Jun 2020 11:06:54 +0100
Subject: net: phylink: add phylink_speed_(up|down) interface

Add an interface for the phy_speed_(up|down) functions when a driver
makes use of phylink. These pass the call through to phylib when we
have a normal PHY attached (i.o.w., not a PHY on a SFP module.)

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  2 ++
 2 files changed, 50 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 7ce787c227b3..7cda1646bbf7 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1826,6 +1826,54 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL_GPL(phylink_mii_ioctl);
 
+/**
+ * phylink_speed_down() - set the non-SFP PHY to lowest speed supported by both
+ *   link partners
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ * @sync: perform action synchronously
+ *
+ * If we have a PHY that is not part of a SFP module, then set the speed
+ * as described in the phy_speed_down() function. Please see this function
+ * for a description of the @sync parameter.
+ *
+ * Returns zero if there is no PHY, otherwise as per phy_speed_down().
+ */
+int phylink_speed_down(struct phylink *pl, bool sync)
+{
+	int ret = 0;
+
+	ASSERT_RTNL();
+
+	if (!pl->sfp_bus && pl->phydev)
+		ret = phy_speed_down(pl->phydev, sync);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phylink_speed_down);
+
+/**
+ * phylink_speed_up() - restore the advertised speeds prior to the call to
+ *   phylink_speed_down()
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ *
+ * If we have a PHY that is not part of a SFP module, then restore the
+ * PHY speeds as per phy_speed_up().
+ *
+ * Returns zero if there is no PHY, otherwise as per phy_speed_up().
+ */
+int phylink_speed_up(struct phylink *pl)
+{
+	int ret = 0;
+
+	ASSERT_RTNL();
+
+	if (!pl->sfp_bus && pl->phydev)
+		ret = phy_speed_up(pl->phydev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phylink_speed_up);
+
 static void phylink_sfp_attach(void *upstream, struct sfp_bus *bus)
 {
 	struct phylink *pl = upstream;
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index cc5b452a184e..b32b8b45421b 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -392,6 +392,8 @@ int phylink_init_eee(struct phylink *, bool);
 int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *);
 int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *);
 int phylink_mii_ioctl(struct phylink *, struct ifreq *, int);
+int phylink_speed_down(struct phylink *pl, bool sync);
+int phylink_speed_up(struct phylink *pl);
 
 #define phylink_zero(bm) \
 	bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS)
-- 
cgit v1.2.3


From 92252eec913b2dd5e7b5de11ea3efa2e64d65cf4 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Wed, 24 Jun 2020 07:16:02 -0500
Subject: net: phy: Add a helper to return the index for of the internal delay

Add a helper function that will return the index in the array for the
passed in internal delay value.  The helper requires the array, size and
delay value.

The helper will then return the index for the exact match or return the
index for the index to the closest smaller value.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 99 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h          |  4 ++
 2 files changed, 103 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 29ef4456ac25..6d47485e68f9 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -31,6 +31,7 @@
 #include <linux/mdio.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
+#include <linux/property.h>
 
 MODULE_DESCRIPTION("PHY library");
 MODULE_AUTHOR("Andy Fleming");
@@ -2708,6 +2709,104 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause)
 }
 EXPORT_SYMBOL(phy_get_pause);
 
+#if IS_ENABLED(CONFIG_OF_MDIO)
+static int phy_get_int_delay_property(struct device *dev, const char *name)
+{
+	s32 int_delay;
+	int ret;
+
+	ret = device_property_read_u32(dev, name, &int_delay);
+	if (ret)
+		return ret;
+
+	return int_delay;
+}
+#else
+static int phy_get_int_delay_property(struct device *dev, const char *name)
+{
+	return -EINVAL;
+}
+#endif
+
+/**
+ * phy_get_delay_index - returns the index of the internal delay
+ * @phydev: phy_device struct
+ * @dev: pointer to the devices device struct
+ * @delay_values: array of delays the PHY supports
+ * @size: the size of the delay array
+ * @is_rx: boolean to indicate to get the rx internal delay
+ *
+ * Returns the index within the array of internal delay passed in.
+ * If the device property is not present then the interface type is checked
+ * if the interface defines use of internal delay then a 1 is returned otherwise
+ * a 0 is returned.
+ * The array must be in ascending order. If PHY does not have an ascending order
+ * array then size = 0 and the value of the delay property is returned.
+ * Return -EINVAL if the delay is invalid or cannot be found.
+ */
+s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
+			   const int *delay_values, int size, bool is_rx)
+{
+	s32 delay;
+	int i;
+
+	if (is_rx) {
+		delay = phy_get_int_delay_property(dev, "rx-internal-delay-ps");
+		if (delay < 0 && size == 0) {
+			if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+				return 1;
+			else
+				return 0;
+		}
+
+	} else {
+		delay = phy_get_int_delay_property(dev, "tx-internal-delay-ps");
+		if (delay < 0 && size == 0) {
+			if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+				return 1;
+			else
+				return 0;
+		}
+	}
+
+	if (delay < 0)
+		return delay;
+
+	if (delay && size == 0)
+		return delay;
+
+	if (delay < delay_values[0] || delay > delay_values[size - 1]) {
+		phydev_err(phydev, "Delay %d is out of range\n", delay);
+		return -EINVAL;
+	}
+
+	if (delay == delay_values[0])
+		return 0;
+
+	for (i = 1; i < size; i++) {
+		if (delay == delay_values[i])
+			return i;
+
+		/* Find an approximate index by looking up the table */
+		if (delay > delay_values[i - 1] &&
+		    delay < delay_values[i]) {
+			if (delay - delay_values[i - 1] <
+			    delay_values[i] - delay)
+				return i - 1;
+			else
+				return i;
+		}
+	}
+
+	phydev_err(phydev, "error finding internal delay index for %d\n",
+		   delay);
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(phy_get_internal_delay);
+
 static bool phy_drv_supports_irq(struct phy_driver *phydrv)
 {
 	return phydrv->config_intr && phydrv->ack_interrupt;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6fb8f302978d..2c00374dc996 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1443,6 +1443,10 @@ void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx);
 bool phy_validate_pause(struct phy_device *phydev,
 			struct ethtool_pauseparam *pp);
 void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause);
+
+s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
+			   const int *delay_values, int size, bool is_rx);
+
 void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv,
 		       bool *tx_pause, bool *rx_pause);
 
-- 
cgit v1.2.3


From d037cb4ae20407df89491f9c2d521ac0723aa15d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 18 Jun 2020 17:00:22 +1000
Subject: crypto: api - Prune inclusions in crypto.h

We haven't used string.h since the memcpy calls were removed so
this patch removes its inclusion.  The file uaccess.h isn't needed
at all.  However, removing it reveals that we do need to add an
inclusion for refcount.h.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 763863dbc079..bc5d2d4bfc3d 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -16,9 +16,8 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/bug.h>
+#include <linux/refcount.h>
 #include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/uaccess.h>
 #include <linux/completion.h>
 
 /*
-- 
cgit v1.2.3


From fe21b6c3a65ca74cc4d0909635649bea48b115b3 Mon Sep 17 00:00:00 2001
From: Shiraz Saleem <shiraz.saleem@intel.com>
Date: Mon, 4 May 2020 09:43:48 -0700
Subject: i40e: Move client header location

Move i40e_client.h to include/linux/net/intel/*
since its shared between i40iw and i40e.

Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/infiniband/hw/i40iw/Makefile          |   1 -
 drivers/infiniband/hw/i40iw/i40iw.h           |   2 +-
 drivers/net/ethernet/intel/i40e/i40e.h        |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_client.c |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_client.h | 203 --------------------------
 include/linux/net/intel/i40e_client.h         | 203 ++++++++++++++++++++++++++
 6 files changed, 206 insertions(+), 207 deletions(-)
 delete mode 100644 drivers/net/ethernet/intel/i40e/i40e_client.h
 create mode 100644 include/linux/net/intel/i40e_client.h

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/i40iw/Makefile b/drivers/infiniband/hw/i40iw/Makefile
index 8942f8229945..34da9eba8a7c 100644
--- a/drivers/infiniband/hw/i40iw/Makefile
+++ b/drivers/infiniband/hw/i40iw/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ccflags-y :=  -I $(srctree)/drivers/net/ethernet/intel/i40e
 
 obj-$(CONFIG_INFINIBAND_I40IW) += i40iw.o
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 49d92638e0db..25747b85a79c 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -45,6 +45,7 @@
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/crc32c.h>
+#include <linux/net/intel/i40e_client.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
@@ -57,7 +58,6 @@
 #include "i40iw_d.h"
 #include "i40iw_hmc.h"
 
-#include <i40e_client.h>
 #include "i40iw_type.h"
 #include "i40iw_p.h"
 #include <rdma/i40iw-abi.h>
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index e95b8da45e07..5ff0828a6f50 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -38,7 +38,7 @@
 #include <net/xdp_sock.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
-#include "i40e_client.h"
+#include <linux/net/intel/i40e_client.h>
 #include <linux/avf/virtchnl.h>
 #include "i40e_virtchnl_pf.h"
 #include "i40e_txrx.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index e81530ca08d0..befd3018183f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -3,10 +3,10 @@
 
 #include <linux/list.h>
 #include <linux/errno.h>
+#include <linux/net/intel/i40e_client.h>
 
 #include "i40e.h"
 #include "i40e_prototype.h"
-#include "i40e_client.h"
 
 static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR;
 static struct i40e_client *registered_client;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h
deleted file mode 100644
index 72994baf4941..000000000000
--- a/drivers/net/ethernet/intel/i40e/i40e_client.h
+++ /dev/null
@@ -1,203 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_CLIENT_H_
-#define _I40E_CLIENT_H_
-
-#define I40E_CLIENT_STR_LENGTH 10
-
-/* Client interface version should be updated anytime there is a change in the
- * existing APIs or data structures.
- */
-#define I40E_CLIENT_VERSION_MAJOR 0
-#define I40E_CLIENT_VERSION_MINOR 01
-#define I40E_CLIENT_VERSION_BUILD 00
-#define I40E_CLIENT_VERSION_STR     \
-	__stringify(I40E_CLIENT_VERSION_MAJOR) "." \
-	__stringify(I40E_CLIENT_VERSION_MINOR) "." \
-	__stringify(I40E_CLIENT_VERSION_BUILD)
-
-struct i40e_client_version {
-	u8 major;
-	u8 minor;
-	u8 build;
-	u8 rsvd;
-};
-
-enum i40e_client_state {
-	__I40E_CLIENT_NULL,
-	__I40E_CLIENT_REGISTERED
-};
-
-enum i40e_client_instance_state {
-	__I40E_CLIENT_INSTANCE_NONE,
-	__I40E_CLIENT_INSTANCE_OPENED,
-};
-
-struct i40e_ops;
-struct i40e_client;
-
-/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
- * In order for us to keep the interface simple, SW will define a
- * unique type value for AEQ.
- */
-#define I40E_QUEUE_TYPE_PE_AEQ  0x80
-#define I40E_QUEUE_INVALID_IDX	0xFFFF
-
-struct i40e_qv_info {
-	u32 v_idx; /* msix_vector */
-	u16 ceq_idx;
-	u16 aeq_idx;
-	u8 itr_idx;
-};
-
-struct i40e_qvlist_info {
-	u32 num_vectors;
-	struct i40e_qv_info qv_info[1];
-};
-
-#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
-
-/* set of LAN parameters useful for clients managed by LAN */
-
-/* Struct to hold per priority info */
-struct i40e_prio_qos_params {
-	u16 qs_handle; /* qs handle for prio */
-	u8 tc; /* TC mapped to prio */
-	u8 reserved;
-};
-
-#define I40E_CLIENT_MAX_USER_PRIORITY        8
-/* Struct to hold Client QoS */
-struct i40e_qos_params {
-	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
-};
-
-struct i40e_params {
-	struct i40e_qos_params qos;
-	u16 mtu;
-};
-
-/* Structure to hold Lan device info for a client device */
-struct i40e_info {
-	struct i40e_client_version version;
-	u8 lanmac[6];
-	struct net_device *netdev;
-	struct pci_dev *pcidev;
-	u8 __iomem *hw_addr;
-	u8 fid;	/* function id, PF id or VF id */
-#define I40E_CLIENT_FTYPE_PF 0
-#define I40E_CLIENT_FTYPE_VF 1
-	u8 ftype; /* function type, PF or VF */
-	void *pf;
-
-	/* All L2 params that could change during the life span of the PF
-	 * and needs to be communicated to the client when they change
-	 */
-	struct i40e_qvlist_info *qvlist_info;
-	struct i40e_params params;
-	struct i40e_ops *ops;
-
-	u16 msix_count;	 /* number of msix vectors*/
-	/* Array down below will be dynamically allocated based on msix_count */
-	struct msix_entry *msix_entries;
-	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
-	u16 fw_maj_ver;                 /* firmware major version */
-	u16 fw_min_ver;                 /* firmware minor version */
-	u32 fw_build;                   /* firmware build number */
-};
-
-#define I40E_CLIENT_RESET_LEVEL_PF   1
-#define I40E_CLIENT_RESET_LEVEL_CORE 2
-#define I40E_CLIENT_VSI_FLAG_TCP_ENABLE  BIT(1)
-
-struct i40e_ops {
-	/* setup_q_vector_list enables queues with a particular vector */
-	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
-			    struct i40e_qvlist_info *qv_info);
-
-	int (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
-			     u32 vf_id, u8 *msg, u16 len);
-
-	/* If the PE Engine is unresponsive, RDMA driver can request a reset.
-	 * The level helps determine the level of reset being requested.
-	 */
-	void (*request_reset)(struct i40e_info *ldev,
-			      struct i40e_client *client, u32 level);
-
-	/* API for the RDMA driver to set certain VSI flags that control
-	 * PE Engine.
-	 */
-	int (*update_vsi_ctxt)(struct i40e_info *ldev,
-			       struct i40e_client *client,
-			       bool is_vf, u32 vf_id,
-			       u32 flag, u32 valid_flag);
-};
-
-struct i40e_client_ops {
-	/* Should be called from register_client() or whenever PF is ready
-	 * to create a specific client instance.
-	 */
-	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
-
-	/* Should be called when netdev is unavailable or when unregister
-	 * call comes in. If the close is happenening due to a reset being
-	 * triggered set the reset bit to true.
-	 */
-	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
-		      bool reset);
-
-	/* called when some l2 managed parameters changes - mtu */
-	void (*l2_param_change)(struct i40e_info *ldev,
-				struct i40e_client *client,
-				struct i40e_params *params);
-
-	int (*virtchnl_receive)(struct i40e_info *ldev,
-				struct i40e_client *client, u32 vf_id,
-				u8 *msg, u16 len);
-
-	/* called when a VF is reset by the PF */
-	void (*vf_reset)(struct i40e_info *ldev,
-			 struct i40e_client *client, u32 vf_id);
-
-	/* called when the number of VFs changes */
-	void (*vf_enable)(struct i40e_info *ldev,
-			  struct i40e_client *client, u32 num_vfs);
-
-	/* returns true if VF is capable of specified offload */
-	int (*vf_capable)(struct i40e_info *ldev,
-			  struct i40e_client *client, u32 vf_id);
-};
-
-/* Client device */
-struct i40e_client_instance {
-	struct list_head list;
-	struct i40e_info lan_info;
-	struct i40e_client *client;
-	unsigned long  state;
-};
-
-struct i40e_client {
-	struct list_head list;		/* list of registered clients */
-	char name[I40E_CLIENT_STR_LENGTH];
-	struct i40e_client_version version;
-	unsigned long state;		/* client state */
-	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
-	u32 flags;
-#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
-#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
-	u8 type;
-#define I40E_CLIENT_IWARP 0
-	const struct i40e_client_ops *ops; /* client ops provided by the client */
-};
-
-static inline bool i40e_client_is_registered(struct i40e_client *client)
-{
-	return test_bit(__I40E_CLIENT_REGISTERED, &client->state);
-}
-
-/* used by clients */
-int i40e_register_client(struct i40e_client *client);
-int i40e_unregister_client(struct i40e_client *client);
-
-#endif /* _I40E_CLIENT_H_ */
diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
new file mode 100644
index 000000000000..72994baf4941
--- /dev/null
+++ b/include/linux/net/intel/i40e_client.h
@@ -0,0 +1,203 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _I40E_CLIENT_H_
+#define _I40E_CLIENT_H_
+
+#define I40E_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define I40E_CLIENT_VERSION_MAJOR 0
+#define I40E_CLIENT_VERSION_MINOR 01
+#define I40E_CLIENT_VERSION_BUILD 00
+#define I40E_CLIENT_VERSION_STR     \
+	__stringify(I40E_CLIENT_VERSION_MAJOR) "." \
+	__stringify(I40E_CLIENT_VERSION_MINOR) "." \
+	__stringify(I40E_CLIENT_VERSION_BUILD)
+
+struct i40e_client_version {
+	u8 major;
+	u8 minor;
+	u8 build;
+	u8 rsvd;
+};
+
+enum i40e_client_state {
+	__I40E_CLIENT_NULL,
+	__I40E_CLIENT_REGISTERED
+};
+
+enum i40e_client_instance_state {
+	__I40E_CLIENT_INSTANCE_NONE,
+	__I40E_CLIENT_INSTANCE_OPENED,
+};
+
+struct i40e_ops;
+struct i40e_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX	0xFFFF
+
+struct i40e_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_qvlist_info {
+	u32 num_vectors;
+	struct i40e_qv_info qv_info[1];
+};
+
+#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct i40e_prio_qos_params {
+	u16 qs_handle; /* qs handle for prio */
+	u8 tc; /* TC mapped to prio */
+	u8 reserved;
+};
+
+#define I40E_CLIENT_MAX_USER_PRIORITY        8
+/* Struct to hold Client QoS */
+struct i40e_qos_params {
+	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct i40e_params {
+	struct i40e_qos_params qos;
+	u16 mtu;
+};
+
+/* Structure to hold Lan device info for a client device */
+struct i40e_info {
+	struct i40e_client_version version;
+	u8 lanmac[6];
+	struct net_device *netdev;
+	struct pci_dev *pcidev;
+	u8 __iomem *hw_addr;
+	u8 fid;	/* function id, PF id or VF id */
+#define I40E_CLIENT_FTYPE_PF 0
+#define I40E_CLIENT_FTYPE_VF 1
+	u8 ftype; /* function type, PF or VF */
+	void *pf;
+
+	/* All L2 params that could change during the life span of the PF
+	 * and needs to be communicated to the client when they change
+	 */
+	struct i40e_qvlist_info *qvlist_info;
+	struct i40e_params params;
+	struct i40e_ops *ops;
+
+	u16 msix_count;	 /* number of msix vectors*/
+	/* Array down below will be dynamically allocated based on msix_count */
+	struct msix_entry *msix_entries;
+	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+	u16 fw_maj_ver;                 /* firmware major version */
+	u16 fw_min_ver;                 /* firmware minor version */
+	u32 fw_build;                   /* firmware build number */
+};
+
+#define I40E_CLIENT_RESET_LEVEL_PF   1
+#define I40E_CLIENT_RESET_LEVEL_CORE 2
+#define I40E_CLIENT_VSI_FLAG_TCP_ENABLE  BIT(1)
+
+struct i40e_ops {
+	/* setup_q_vector_list enables queues with a particular vector */
+	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
+			    struct i40e_qvlist_info *qv_info);
+
+	int (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+			     u32 vf_id, u8 *msg, u16 len);
+
+	/* If the PE Engine is unresponsive, RDMA driver can request a reset.
+	 * The level helps determine the level of reset being requested.
+	 */
+	void (*request_reset)(struct i40e_info *ldev,
+			      struct i40e_client *client, u32 level);
+
+	/* API for the RDMA driver to set certain VSI flags that control
+	 * PE Engine.
+	 */
+	int (*update_vsi_ctxt)(struct i40e_info *ldev,
+			       struct i40e_client *client,
+			       bool is_vf, u32 vf_id,
+			       u32 flag, u32 valid_flag);
+};
+
+struct i40e_client_ops {
+	/* Should be called from register_client() or whenever PF is ready
+	 * to create a specific client instance.
+	 */
+	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+
+	/* Should be called when netdev is unavailable or when unregister
+	 * call comes in. If the close is happenening due to a reset being
+	 * triggered set the reset bit to true.
+	 */
+	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+		      bool reset);
+
+	/* called when some l2 managed parameters changes - mtu */
+	void (*l2_param_change)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				struct i40e_params *params);
+
+	int (*virtchnl_receive)(struct i40e_info *ldev,
+				struct i40e_client *client, u32 vf_id,
+				u8 *msg, u16 len);
+
+	/* called when a VF is reset by the PF */
+	void (*vf_reset)(struct i40e_info *ldev,
+			 struct i40e_client *client, u32 vf_id);
+
+	/* called when the number of VFs changes */
+	void (*vf_enable)(struct i40e_info *ldev,
+			  struct i40e_client *client, u32 num_vfs);
+
+	/* returns true if VF is capable of specified offload */
+	int (*vf_capable)(struct i40e_info *ldev,
+			  struct i40e_client *client, u32 vf_id);
+};
+
+/* Client device */
+struct i40e_client_instance {
+	struct list_head list;
+	struct i40e_info lan_info;
+	struct i40e_client *client;
+	unsigned long  state;
+};
+
+struct i40e_client {
+	struct list_head list;		/* list of registered clients */
+	char name[I40E_CLIENT_STR_LENGTH];
+	struct i40e_client_version version;
+	unsigned long state;		/* client state */
+	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
+	u32 flags;
+#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
+#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
+	u8 type;
+#define I40E_CLIENT_IWARP 0
+	const struct i40e_client_ops *ops; /* client ops provided by the client */
+};
+
+static inline bool i40e_client_is_registered(struct i40e_client *client)
+{
+	return test_bit(__I40E_CLIENT_REGISTERED, &client->state);
+}
+
+/* used by clients */
+int i40e_register_client(struct i40e_client *client);
+int i40e_unregister_client(struct i40e_client *client);
+
+#endif /* _I40E_CLIENT_H_ */
-- 
cgit v1.2.3


From 3c98f9ee6bc280499cbcb6f8e42c001c3bd7caa1 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 6 Jan 2020 16:09:33 -0800
Subject: i40e: remove unused defines

Remove all the unused defines as they are just dead weight.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h             |   24 -
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h  |  497 +--
 drivers/net/ethernet/intel/i40e/i40e_common.c      |    4 -
 drivers/net/ethernet/intel/i40e/i40e_dcb.h         |    5 -
 drivers/net/ethernet/intel/i40e/i40e_debugfs.c     |    1 -
 drivers/net/ethernet/intel/i40e/i40e_devids.h      |    3 -
 drivers/net/ethernet/intel/i40e/i40e_hmc.h         |    1 -
 drivers/net/ethernet/intel/i40e/i40e_main.c        |   10 +-
 drivers/net/ethernet/intel/i40e/i40e_osdep.h       |    1 -
 drivers/net/ethernet/intel/i40e/i40e_register.h    | 4656 --------------------
 drivers/net/ethernet/intel/i40e/i40e_txrx.h        |   25 -
 drivers/net/ethernet/intel/i40e/i40e_type.h        |   82 -
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h |    1 -
 include/linux/net/intel/i40e_client.h              |    9 -
 14 files changed, 2 insertions(+), 5317 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 5ff0828a6f50..8151671e5e0e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -60,17 +60,14 @@
 		(((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1)
 #define I40E_DEFAULT_QUEUES_PER_VF	4
 #define I40E_MAX_VF_QUEUES		16
-#define I40E_DEFAULT_QUEUES_PER_TC	1 /* should be a power of 2 */
 #define i40e_pf_get_max_q_per_tc(pf) \
 		(((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64)
-#define I40E_FDIR_RING			0
 #define I40E_FDIR_RING_COUNT		32
 #define I40E_MAX_AQ_BUF_SIZE		4096
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
 #define I40E_MAX_USER_PRIORITY		8
 #define I40E_DEFAULT_TRAFFIC_CLASS	BIT(0)
-#define I40E_DEFAULT_MSG_ENABLE		4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10
 #define I40E_INT_NAME_STR_LEN		(IFNAMSIZ + 16)
 
@@ -92,10 +89,6 @@
 #define I40E_OEM_SNAP_SHIFT		16
 #define I40E_OEM_RELEASE_MASK		0x0000ffff
 
-/* The values in here are decimal coded as hex as is the case in the NVM map*/
-#define I40E_CURRENT_NVM_VERSION_HI	0x2
-#define I40E_CURRENT_NVM_VERSION_LO	0x40
-
 #define I40E_RX_DESC(R, i)	\
 	(&(((union i40e_32byte_rx_desc *)((R)->desc))[i]))
 #define I40E_TX_DESC(R, i)	\
@@ -105,9 +98,6 @@
 #define I40E_TX_FDIRDESC(R, i)	\
 	(&(((struct i40e_filter_program_desc *)((R)->desc))[i]))
 
-/* default to trying for four seconds */
-#define I40E_TRY_LINK_TIMEOUT	(4 * HZ)
-
 /* BW rate limiting */
 #define I40E_BW_CREDIT_DIVISOR		50 /* 50Mbps per BW credit */
 #define I40E_BW_MBPS_DIVISOR		125000 /* rate / (1000000 / 8) Mbps */
@@ -295,9 +285,6 @@ struct i40e_cloud_filter {
 	u8 tunnel_type;
 };
 
-#define I40E_DCB_PRIO_TYPE_STRICT	0
-#define I40E_DCB_PRIO_TYPE_ETS		1
-#define I40E_DCB_STRICT_PRIO_CREDITS	127
 /* DCB per TC information data structure */
 struct i40e_tc_info {
 	u16	qoffset;	/* Queue offset from base queue */
@@ -357,15 +344,6 @@ struct i40e_ddp_old_profile_list {
 					     I40E_FLEX_SET_FSIZE(fsize) | \
 					     I40E_FLEX_SET_SRC_WORD(src))
 
-#define I40E_FLEX_PIT_GET_SRC(flex) (((flex) & \
-				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) >> \
-				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
-#define I40E_FLEX_PIT_GET_DST(flex) (((flex) & \
-				     I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) >> \
-				     I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
-#define I40E_FLEX_PIT_GET_FSIZE(flex) (((flex) & \
-				       I40E_PRTQF_FLX_PIT_FSIZE_MASK) >> \
-				       I40E_PRTQF_FLX_PIT_FSIZE_SHIFT)
 
 #define I40E_MAX_FLEX_SRC_OFFSET 0x1F
 
@@ -390,7 +368,6 @@ struct i40e_ddp_old_profile_list {
 #define I40E_L4_GLQF_ORT_IDX		35
 
 /* Flex PIT register index */
-#define I40E_FLEX_PIT_IDX_START_L2	0
 #define I40E_FLEX_PIT_IDX_START_L3	3
 #define I40E_FLEX_PIT_IDX_START_L4	6
 
@@ -531,7 +508,6 @@ struct i40e_pf {
 #define I40E_HW_GENEVE_OFFLOAD_CAPABLE		BIT(9)
 #define I40E_HW_PTP_L4_CAPABLE			BIT(10)
 #define I40E_HW_WOL_MC_MAGIC_PKT_WAKE		BIT(11)
-#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE	BIT(12)
 #define I40E_HW_HAVE_CRT_RETIMER		BIT(13)
 #define I40E_HW_OUTER_UDP_CSUM_CAPABLE		BIT(14)
 #define I40E_HW_PHY_CONTROLS_LEDS		BIT(15)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index aa5f1c0aa721..c52910f03cfb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -55,29 +55,17 @@ struct i40e_aq_desc {
  */
 
 /* command flags and offsets*/
-#define I40E_AQ_FLAG_DD_SHIFT	0
-#define I40E_AQ_FLAG_CMP_SHIFT	1
 #define I40E_AQ_FLAG_ERR_SHIFT	2
-#define I40E_AQ_FLAG_VFE_SHIFT	3
 #define I40E_AQ_FLAG_LB_SHIFT	9
 #define I40E_AQ_FLAG_RD_SHIFT	10
-#define I40E_AQ_FLAG_VFC_SHIFT	11
 #define I40E_AQ_FLAG_BUF_SHIFT	12
 #define I40E_AQ_FLAG_SI_SHIFT	13
-#define I40E_AQ_FLAG_EI_SHIFT	14
-#define I40E_AQ_FLAG_FE_SHIFT	15
 
-#define I40E_AQ_FLAG_DD		BIT(I40E_AQ_FLAG_DD_SHIFT)  /* 0x1    */
-#define I40E_AQ_FLAG_CMP	BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2    */
 #define I40E_AQ_FLAG_ERR	BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4    */
-#define I40E_AQ_FLAG_VFE	BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8    */
 #define I40E_AQ_FLAG_LB		BIT(I40E_AQ_FLAG_LB_SHIFT)  /* 0x200  */
 #define I40E_AQ_FLAG_RD		BIT(I40E_AQ_FLAG_RD_SHIFT)  /* 0x400  */
-#define I40E_AQ_FLAG_VFC	BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800  */
 #define I40E_AQ_FLAG_BUF	BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
 #define I40E_AQ_FLAG_SI		BIT(I40E_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
-#define I40E_AQ_FLAG_EI		BIT(I40E_AQ_FLAG_EI_SHIFT)  /* 0x4000 */
-#define I40E_AQ_FLAG_FE		BIT(I40E_AQ_FLAG_FE_SHIFT)  /* 0x8000 */
 
 /* error codes */
 enum i40e_admin_queue_err {
@@ -362,13 +350,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
 /* Request resource ownership (direct 0x0008)
  * Release resource ownership (direct 0x0009)
  */
-#define I40E_AQ_RESOURCE_NVM			1
-#define I40E_AQ_RESOURCE_SDP			2
-#define I40E_AQ_RESOURCE_ACCESS_READ		1
-#define I40E_AQ_RESOURCE_ACCESS_WRITE		2
-#define I40E_AQ_RESOURCE_NVM_READ_TIMEOUT	3000
-#define I40E_AQ_RESOURCE_NVM_WRITE_TIMEOUT	180000
-
 struct i40e_aqc_request_resource {
 	__le16	resource_id;
 	__le16	access_type;
@@ -384,7 +365,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource);
  */
 struct i40e_aqc_list_capabilites {
 	u8 command_flags;
-#define I40E_AQ_LIST_CAP_PF_INDEX_EN	1
 	u8 pf_index;
 	u8 reserved[2];
 	__le32 count;
@@ -411,8 +391,6 @@ struct i40e_aqc_list_capabilities_element_resp {
 #define I40E_AQ_CAP_ID_NPAR_ACTIVE	0x0003
 #define I40E_AQ_CAP_ID_OS2BMC_CAP	0x0004
 #define I40E_AQ_CAP_ID_FUNCTIONS_VALID	0x0005
-#define I40E_AQ_CAP_ID_ALTERNATE_RAM	0x0006
-#define I40E_AQ_CAP_ID_WOL_AND_PROXY	0x0008
 #define I40E_AQ_CAP_ID_SRIOV		0x0012
 #define I40E_AQ_CAP_ID_VF		0x0013
 #define I40E_AQ_CAP_ID_VMDQ		0x0014
@@ -441,11 +419,6 @@ struct i40e_aqc_list_capabilities_element_resp {
 /* Set CPPM Configuration (direct 0x0103) */
 struct i40e_aqc_cppm_configuration {
 	__le16	command_flags;
-#define I40E_AQ_CPPM_EN_LTRC	0x0800
-#define I40E_AQ_CPPM_EN_DMCTH	0x1000
-#define I40E_AQ_CPPM_EN_DMCTLX	0x2000
-#define I40E_AQ_CPPM_EN_HPTC	0x4000
-#define I40E_AQ_CPPM_EN_DMARC	0x8000
 	__le16	ttlx;
 	__le32	dmacr;
 	__le16	dmcth;
@@ -459,15 +432,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_cppm_configuration);
 /* Set ARP Proxy command / response (indirect 0x0104) */
 struct i40e_aqc_arp_proxy_data {
 	__le16	command_flags;
-#define I40E_AQ_ARP_INIT_IPV4	0x0800
-#define I40E_AQ_ARP_UNSUP_CTL	0x1000
-#define I40E_AQ_ARP_ENA		0x2000
-#define I40E_AQ_ARP_ADD_IPV4	0x4000
-#define I40E_AQ_ARP_DEL_IPV4	0x8000
 	__le16	table_id;
 	__le32	enabled_offloads;
-#define I40E_AQ_ARP_DIRECTED_OFFLOAD_ENABLE	0x00000020
-#define I40E_AQ_ARP_OFFLOAD_ENABLE		0x00000800
 	__le32	ip_addr;
 	u8	mac_addr[6];
 	u8	reserved[2];
@@ -482,19 +448,6 @@ struct i40e_aqc_ns_proxy_data {
 	__le16	table_idx_ipv6_0;
 	__le16	table_idx_ipv6_1;
 	__le16	control;
-#define I40E_AQ_NS_PROXY_ADD_0		0x0001
-#define I40E_AQ_NS_PROXY_DEL_0		0x0002
-#define I40E_AQ_NS_PROXY_ADD_1		0x0004
-#define I40E_AQ_NS_PROXY_DEL_1		0x0008
-#define I40E_AQ_NS_PROXY_ADD_IPV6_0	0x0010
-#define I40E_AQ_NS_PROXY_DEL_IPV6_0	0x0020
-#define I40E_AQ_NS_PROXY_ADD_IPV6_1	0x0040
-#define I40E_AQ_NS_PROXY_DEL_IPV6_1	0x0080
-#define I40E_AQ_NS_PROXY_COMMAND_SEQ	0x0100
-#define I40E_AQ_NS_PROXY_INIT_IPV6_TBL	0x0200
-#define I40E_AQ_NS_PROXY_INIT_MAC_TBL	0x0400
-#define I40E_AQ_NS_PROXY_OFFLOAD_ENABLE	0x0800
-#define I40E_AQ_NS_PROXY_DIRECTED_OFFLOAD_ENABLE	0x1000
 	u8	mac_addr_0[6];
 	u8	mac_addr_1[6];
 	u8	local_mac_addr[6];
@@ -507,7 +460,6 @@ I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data);
 /* Manage LAA Command (0x0106) - obsolete */
 struct i40e_aqc_mng_laa {
 	__le16	command_flags;
-#define I40E_AQ_LAA_FLAG_WR	0x8000
 	u8	reserved[2];
 	__le32	sal;
 	__le16	sah;
@@ -520,11 +472,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa);
 struct i40e_aqc_mac_address_read {
 	__le16	command_flags;
 #define I40E_AQC_LAN_ADDR_VALID		0x10
-#define I40E_AQC_SAN_ADDR_VALID		0x20
 #define I40E_AQC_PORT_ADDR_VALID	0x40
-#define I40E_AQC_WOL_ADDR_VALID		0x80
-#define I40E_AQC_MC_MAG_EN_VALID	0x100
-#define I40E_AQC_ADDR_VALID_MASK	0x3F0
 	u8	reserved[6];
 	__le32	addr_high;
 	__le32	addr_low;
@@ -548,9 +496,7 @@ struct i40e_aqc_mac_address_write {
 #define I40E_AQC_WOL_PRESERVE_ON_PFR	0x0200
 #define I40E_AQC_WRITE_TYPE_LAA_ONLY	0x0000
 #define I40E_AQC_WRITE_TYPE_LAA_WOL	0x4000
-#define I40E_AQC_WRITE_TYPE_PORT	0x8000
 #define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG	0xC000
-#define I40E_AQC_WRITE_TYPE_MASK	0xC000
 
 	__le16	mac_sah;
 	__le32	mac_sal;
@@ -573,22 +519,9 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
 struct i40e_aqc_set_wol_filter {
 	__le16 filter_index;
-#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
-#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
-#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
-		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
-
-#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
-#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
-		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+
 	__le16 cmd_flags;
-#define I40E_AQC_SET_WOL_FILTER				0x8000
-#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
-#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
-#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
 	__le16 valid_flags;
-#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
-#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
 	u8 reserved[2];
 	__le32	address_high;
 	__le32	address_low;
@@ -608,12 +541,6 @@ I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
 struct i40e_aqc_get_wake_reason_completion {
 	u8 reserved_1[2];
 	__le16 wake_reason;
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
-		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
-		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
 	u8 reserved_2[12];
 };
 
@@ -646,25 +573,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp);
 
 struct i40e_aqc_switch_config_element_resp {
 	u8	element_type;
-#define I40E_AQ_SW_ELEM_TYPE_MAC	1
-#define I40E_AQ_SW_ELEM_TYPE_PF		2
-#define I40E_AQ_SW_ELEM_TYPE_VF		3
-#define I40E_AQ_SW_ELEM_TYPE_EMP	4
-#define I40E_AQ_SW_ELEM_TYPE_BMC	5
-#define I40E_AQ_SW_ELEM_TYPE_PV		16
-#define I40E_AQ_SW_ELEM_TYPE_VEB	17
-#define I40E_AQ_SW_ELEM_TYPE_PA		18
-#define I40E_AQ_SW_ELEM_TYPE_VSI	19
 	u8	revision;
-#define I40E_AQ_SW_ELEM_REV_1		1
 	__le16	seid;
 	__le16	uplink_seid;
 	__le16	downlink_seid;
 	u8	reserved[3];
 	u8	connection_type;
-#define I40E_AQ_CONN_TYPE_REGULAR	0x1
-#define I40E_AQ_CONN_TYPE_DEFAULT	0x2
-#define I40E_AQ_CONN_TYPE_CASCADED	0x3
 	__le16	scheduler_id;
 	__le16	element_info;
 };
@@ -697,12 +611,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_statistics);
 /* Set Port Parameters command (direct 0x0203) */
 struct i40e_aqc_set_port_parameters {
 	__le16	command_flags;
-#define I40E_AQ_SET_P_PARAMS_SAVE_BAD_PACKETS	1
-#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
-#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
-#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
-#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -722,25 +631,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_resource_alloc);
 /* expect an array of these structs in the response buffer */
 struct i40e_aqc_switch_resource_alloc_element_resp {
 	u8	resource_type;
-#define I40E_AQ_RESOURCE_TYPE_VEB		0x0
-#define I40E_AQ_RESOURCE_TYPE_VSI		0x1
-#define I40E_AQ_RESOURCE_TYPE_MACADDR		0x2
-#define I40E_AQ_RESOURCE_TYPE_STAG		0x3
-#define I40E_AQ_RESOURCE_TYPE_ETAG		0x4
-#define I40E_AQ_RESOURCE_TYPE_MULTICAST_HASH	0x5
-#define I40E_AQ_RESOURCE_TYPE_UNICAST_HASH	0x6
-#define I40E_AQ_RESOURCE_TYPE_VLAN		0x7
-#define I40E_AQ_RESOURCE_TYPE_VSI_LIST_ENTRY	0x8
-#define I40E_AQ_RESOURCE_TYPE_ETAG_LIST_ENTRY	0x9
-#define I40E_AQ_RESOURCE_TYPE_VLAN_STAT_POOL	0xA
-#define I40E_AQ_RESOURCE_TYPE_MIRROR_RULE	0xB
-#define I40E_AQ_RESOURCE_TYPE_QUEUE_SETS	0xC
-#define I40E_AQ_RESOURCE_TYPE_VLAN_FILTERS	0xD
-#define I40E_AQ_RESOURCE_TYPE_INNER_MAC_FILTERS	0xF
-#define I40E_AQ_RESOURCE_TYPE_IP_FILTERS	0x10
-#define I40E_AQ_RESOURCE_TYPE_GRE_VN_KEYS	0x11
-#define I40E_AQ_RESOURCE_TYPE_VN2_KEYS		0x12
-#define I40E_AQ_RESOURCE_TYPE_TUNNEL_PORTS	0x13
 	u8	reserved1;
 	__le16	guaranteed;
 	__le16	total;
@@ -756,7 +646,6 @@ struct i40e_aqc_set_switch_config {
 	__le16	flags;
 /* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
-#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
 	/* The ethertype in switch_tag is dropped on ingress and used
 	 * internally by the switch. Set this to zero for the default
@@ -789,17 +678,10 @@ struct i40e_aqc_set_switch_config {
 	 */
 #define I40E_AQ_SET_SWITCH_BIT7_VALID		0x80
 
-#define I40E_AQ_SET_SWITCH_L4_SRC_PORT		0x40
 
-#define I40E_AQ_SET_SWITCH_L4_TYPE_RSVD		0x00
 #define I40E_AQ_SET_SWITCH_L4_TYPE_TCP		0x10
-#define I40E_AQ_SET_SWITCH_L4_TYPE_UDP		0x20
-#define I40E_AQ_SET_SWITCH_L4_TYPE_BOTH		0x30
 
-#define I40E_AQ_SET_SWITCH_MODE_DEFAULT		0x00
-#define I40E_AQ_SET_SWITCH_MODE_L4_PORT		0x01
 #define I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL	0x02
-#define I40E_AQ_SET_SWITCH_MODE_TUNNEL		0x03
 	u8	mode;
 	u8	rsvd5[5];
 };
@@ -834,19 +716,13 @@ struct i40e_aqc_add_get_update_vsi {
 	__le16	uplink_seid;
 	u8	connection_type;
 #define I40E_AQ_VSI_CONN_TYPE_NORMAL	0x1
-#define I40E_AQ_VSI_CONN_TYPE_DEFAULT	0x2
-#define I40E_AQ_VSI_CONN_TYPE_CASCADED	0x3
 	u8	reserved1;
 	u8	vf_id;
 	u8	reserved2;
 	__le16	vsi_flags;
-#define I40E_AQ_VSI_TYPE_SHIFT		0x0
-#define I40E_AQ_VSI_TYPE_MASK		(0x3 << I40E_AQ_VSI_TYPE_SHIFT)
 #define I40E_AQ_VSI_TYPE_VF		0x0
 #define I40E_AQ_VSI_TYPE_VMDQ2		0x1
 #define I40E_AQ_VSI_TYPE_PF		0x2
-#define I40E_AQ_VSI_TYPE_EMP_MNG	0x3
-#define I40E_AQ_VSI_FLAG_CASCADED_PV	0x4
 	__le32	addr_high;
 	__le32	addr_low;
 };
@@ -870,24 +746,18 @@ struct i40e_aqc_vsi_properties_data {
 #define I40E_AQ_VSI_PROP_SWITCH_VALID		0x0001
 #define I40E_AQ_VSI_PROP_SECURITY_VALID		0x0002
 #define I40E_AQ_VSI_PROP_VLAN_VALID		0x0004
-#define I40E_AQ_VSI_PROP_CAS_PV_VALID		0x0008
-#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID	0x0010
-#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID	0x0020
 #define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID	0x0040
 #define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID	0x0080
-#define I40E_AQ_VSI_PROP_OUTER_UP_VALID		0x0100
 #define I40E_AQ_VSI_PROP_SCHED_VALID		0x0200
 	/* switch section */
 	__le16	switch_id; /* 12bit id combined with flags below */
 #define I40E_AQ_VSI_SW_ID_SHIFT		0x0000
 #define I40E_AQ_VSI_SW_ID_MASK		(0xFFF << I40E_AQ_VSI_SW_ID_SHIFT)
-#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG	0x1000
 #define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB	0x2000
 #define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB	0x4000
 	u8	sw_reserved[2];
 	/* security section */
 	u8	sec_flags;
-#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD	0x01
 #define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK	0x02
 #define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK	0x04
 	u8	sec_reserved;
@@ -899,78 +769,33 @@ struct i40e_aqc_vsi_properties_data {
 #define I40E_AQ_VSI_PVLAN_MODE_MASK	(0x03 << \
 					 I40E_AQ_VSI_PVLAN_MODE_SHIFT)
 #define I40E_AQ_VSI_PVLAN_MODE_TAGGED	0x01
-#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED	0x02
 #define I40E_AQ_VSI_PVLAN_MODE_ALL	0x03
 #define I40E_AQ_VSI_PVLAN_INSERT_PVID	0x04
 #define I40E_AQ_VSI_PVLAN_EMOD_SHIFT	0x03
 #define I40E_AQ_VSI_PVLAN_EMOD_MASK	(0x3 << \
 					 I40E_AQ_VSI_PVLAN_EMOD_SHIFT)
 #define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH	0x0
-#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP	0x08
 #define I40E_AQ_VSI_PVLAN_EMOD_STR	0x10
 #define I40E_AQ_VSI_PVLAN_EMOD_NOTHING	0x18
 	u8	pvlan_reserved[3];
 	/* ingress egress up sections */
 	__le32	ingress_table; /* bitmap, 3 bits per up */
-#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT	0
-#define I40E_AQ_VSI_UP_TABLE_UP0_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP0_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT	3
-#define I40E_AQ_VSI_UP_TABLE_UP1_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP1_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT	6
-#define I40E_AQ_VSI_UP_TABLE_UP2_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP2_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT	9
-#define I40E_AQ_VSI_UP_TABLE_UP3_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP3_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT	12
-#define I40E_AQ_VSI_UP_TABLE_UP4_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP4_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT	15
-#define I40E_AQ_VSI_UP_TABLE_UP5_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP5_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT	18
-#define I40E_AQ_VSI_UP_TABLE_UP6_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP6_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT	21
-#define I40E_AQ_VSI_UP_TABLE_UP7_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP7_SHIFT)
 	__le32	egress_table;   /* same defines as for ingress table */
 	/* cascaded PV section */
 	__le16	cas_pv_tag;
 	u8	cas_pv_flags;
-#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT		0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_MASK		(0x03 << \
-						 I40E_AQ_VSI_CAS_PV_TAGX_SHIFT)
-#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE		0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE		0x01
-#define I40E_AQ_VSI_CAS_PV_TAGX_COPY		0x02
-#define I40E_AQ_VSI_CAS_PV_INSERT_TAG		0x10
-#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE		0x20
-#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG	0x40
 	u8	cas_pv_reserved;
 	/* queue mapping section */
 	__le16	mapping_flags;
 #define I40E_AQ_VSI_QUE_MAP_CONTIG	0x0
 #define I40E_AQ_VSI_QUE_MAP_NONCONTIG	0x1
 	__le16	queue_mapping[16];
-#define I40E_AQ_VSI_QUEUE_SHIFT		0x0
-#define I40E_AQ_VSI_QUEUE_MASK		(0x7FF << I40E_AQ_VSI_QUEUE_SHIFT)
 	__le16	tc_mapping[8];
 #define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT	0
-#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK	(0x1FF << \
-					 I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT)
 #define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT	9
-#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK	(0x7 << \
-					 I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT)
 	/* queueing option section */
 	u8	queueing_opt_flags;
-#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA	0x04
-#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA	0x08
 #define I40E_AQ_VSI_QUE_OPT_TCP_ENA	0x10
-#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA	0x20
-#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF	0x00
 #define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI	0x40
 	u8	queueing_opt_reserved[3];
 	/* scheduler section */
@@ -995,10 +820,6 @@ I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data);
  */
 struct i40e_aqc_add_update_pv {
 	__le16	command_flags;
-#define I40E_AQC_PV_FLAG_PV_TYPE		0x1
-#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_STAG_EN	0x2
-#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_ETAG_EN	0x4
-#define I40E_AQC_PV_FLAG_IS_CTRL_PORT		0x8
 	__le16	uplink_seid;
 	__le16	connected_seid;
 	u8	reserved[10];
@@ -1009,10 +830,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv);
 struct i40e_aqc_add_update_pv_completion {
 	/* reserved for update; for add also encodes error if rc == ENOSPC */
 	__le16	pv_seid;
-#define I40E_AQC_PV_ERR_FLAG_NO_PV	0x1
-#define I40E_AQC_PV_ERR_FLAG_NO_SCHED	0x2
-#define I40E_AQC_PV_ERR_FLAG_NO_COUNTER	0x4
-#define I40E_AQC_PV_ERR_FLAG_NO_ENTRY	0x8
 	u8	reserved[14];
 };
 
@@ -1026,9 +843,6 @@ struct i40e_aqc_get_pv_params_completion {
 	__le16	seid;
 	__le16	default_stag;
 	__le16	pv_flags; /* same flags as add_pv */
-#define I40E_AQC_GET_PV_PV_TYPE			0x1
-#define I40E_AQC_GET_PV_FRWD_UNKNOWN_STAG	0x2
-#define I40E_AQC_GET_PV_FRWD_UNKNOWN_ETAG	0x4
 	u8	reserved[8];
 	__le16	default_port_seid;
 };
@@ -1041,12 +855,8 @@ struct i40e_aqc_add_veb {
 	__le16	downlink_seid;
 	__le16	veb_flags;
 #define I40E_AQC_ADD_VEB_FLOATING		0x1
-#define I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT	1
-#define I40E_AQC_ADD_VEB_PORT_TYPE_MASK		(0x3 << \
-					I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT)
 #define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT	0x2
 #define I40E_AQC_ADD_VEB_PORT_TYPE_DATA		0x4
-#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER	0x8     /* deprecated */
 #define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS	0x10
 	u8	enable_tcs;
 	u8	reserved[9];
@@ -1059,10 +869,6 @@ struct i40e_aqc_add_veb_completion {
 	__le16	switch_seid;
 	/* also encodes error if rc == ENOSPC; codes are the same as add_pv */
 	__le16	veb_seid;
-#define I40E_AQC_VEB_ERR_FLAG_NO_VEB		0x1
-#define I40E_AQC_VEB_ERR_FLAG_NO_SCHED		0x2
-#define I40E_AQC_VEB_ERR_FLAG_NO_COUNTER	0x4
-#define I40E_AQC_VEB_ERR_FLAG_NO_ENTRY		0x8
 	__le16	statistic_index;
 	__le16	vebs_used;
 	__le16	vebs_free;
@@ -1095,9 +901,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion);
 struct i40e_aqc_macvlan {
 	__le16	num_addresses;
 	__le16	seid[3];
-#define I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_MACVLAN_CMD_SEID_NUM_MASK	(0x3FF << \
-					I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
 #define I40E_AQC_MACVLAN_CMD_SEID_VALID		0x8000
 	__le32	addr_high;
 	__le32	addr_low;
@@ -1111,18 +914,11 @@ struct i40e_aqc_add_macvlan_element_data {
 	__le16	vlan_tag;
 	__le16	flags;
 #define I40E_AQC_MACVLAN_ADD_PERFECT_MATCH	0x0001
-#define I40E_AQC_MACVLAN_ADD_HASH_MATCH		0x0002
 #define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN	0x0004
-#define I40E_AQC_MACVLAN_ADD_TO_QUEUE		0x0008
 #define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC	0x0010
 	__le16	queue_number;
-#define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT	0
-#define I40E_AQC_MACVLAN_CMD_QUEUE_MASK		(0x7FF << \
-					I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
 	/* response section */
 	u8	match_method;
-#define I40E_AQC_MM_PERFECT_MATCH	0x01
-#define I40E_AQC_MM_HASH_MATCH		0x02
 #define I40E_AQC_MM_ERR_NO_RES		0xFF
 	u8	reserved1[3];
 };
@@ -1148,14 +944,10 @@ struct i40e_aqc_remove_macvlan_element_data {
 	__le16	vlan_tag;
 	u8	flags;
 #define I40E_AQC_MACVLAN_DEL_PERFECT_MATCH	0x01
-#define I40E_AQC_MACVLAN_DEL_HASH_MATCH		0x02
 #define I40E_AQC_MACVLAN_DEL_IGNORE_VLAN	0x08
-#define I40E_AQC_MACVLAN_DEL_ALL_VSIS		0x10
 	u8	reserved[3];
 	/* reply section */
 	u8	error_code;
-#define I40E_AQC_REMOVE_MACVLAN_SUCCESS		0x0
-#define I40E_AQC_REMOVE_MACVLAN_FAIL		0xFF
 	u8	reply_reserved[3];
 };
 
@@ -1166,30 +958,8 @@ struct i40e_aqc_remove_macvlan_element_data {
 struct i40e_aqc_add_remove_vlan_element_data {
 	__le16	vlan_tag;
 	u8	vlan_flags;
-/* flags for add VLAN */
-#define I40E_AQC_ADD_VLAN_LOCAL			0x1
-#define I40E_AQC_ADD_PVLAN_TYPE_SHIFT		1
-#define I40E_AQC_ADD_PVLAN_TYPE_MASK	(0x3 << I40E_AQC_ADD_PVLAN_TYPE_SHIFT)
-#define I40E_AQC_ADD_PVLAN_TYPE_REGULAR		0x0
-#define I40E_AQC_ADD_PVLAN_TYPE_PRIMARY		0x2
-#define I40E_AQC_ADD_PVLAN_TYPE_SECONDARY	0x4
-#define I40E_AQC_VLAN_PTYPE_SHIFT		3
-#define I40E_AQC_VLAN_PTYPE_MASK	(0x3 << I40E_AQC_VLAN_PTYPE_SHIFT)
-#define I40E_AQC_VLAN_PTYPE_REGULAR_VSI		0x0
-#define I40E_AQC_VLAN_PTYPE_PROMISC_VSI		0x8
-#define I40E_AQC_VLAN_PTYPE_COMMUNITY_VSI	0x10
-#define I40E_AQC_VLAN_PTYPE_ISOLATED_VSI	0x18
-/* flags for remove VLAN */
-#define I40E_AQC_REMOVE_VLAN_ALL	0x1
 	u8	reserved;
 	u8	result;
-/* flags for add VLAN */
-#define I40E_AQC_ADD_VLAN_SUCCESS	0x0
-#define I40E_AQC_ADD_VLAN_FAIL_REQUEST	0xFE
-#define I40E_AQC_ADD_VLAN_FAIL_RESOURCE	0xFF
-/* flags for remove VLAN */
-#define I40E_AQC_REMOVE_VLAN_SUCCESS	0x0
-#define I40E_AQC_REMOVE_VLAN_FAIL	0xFF
 	u8	reserved1[3];
 };
 
@@ -1213,9 +983,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes {
 #define I40E_AQC_SET_VSI_PROMISC_VLAN		0x10
 #define I40E_AQC_SET_VSI_PROMISC_TX		0x8000
 	__le16	seid;
-#define I40E_AQC_VSI_PROM_CMD_SEID_MASK		0x3FF
 	__le16	vlan_tag;
-#define I40E_AQC_SET_VSI_VLAN_MASK		0x0FFF
 #define I40E_AQC_SET_VSI_VLAN_VALID		0x8000
 	u8	reserved[8];
 };
@@ -1227,11 +995,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes);
  */
 struct i40e_aqc_add_tag {
 	__le16	flags;
-#define I40E_AQC_ADD_TAG_FLAG_TO_QUEUE		0x0001
 	__le16	seid;
-#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_MASK	(0x3FF << \
-					I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT)
 	__le16	tag;
 	__le16	queue_number;
 	u8	reserved[8];
@@ -1252,9 +1016,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_tag_completion);
  */
 struct i40e_aqc_remove_tag {
 	__le16	seid;
-#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_MASK	(0x3FF << \
-					I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT)
 	__le16	tag;
 	u8	reserved[12];
 };
@@ -1290,9 +1051,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag_completion);
 /* Update S/E-Tag (direct 0x0259) */
 struct i40e_aqc_update_tag {
 	__le16	seid;
-#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_MASK	(0x3FF << \
-					I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT)
 	__le16	old_tag;
 	__le16	new_tag;
 	u8	reserved[10];
@@ -1319,13 +1077,8 @@ struct i40e_aqc_add_remove_control_packet_filter {
 	__le16	flags;
 #define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC	0x0001
 #define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP		0x0002
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TO_QUEUE	0x0004
 #define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX		0x0008
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_RX		0x0000
 	__le16	seid;
-#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_MASK	(0x3FF << \
-				I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT)
 	__le16	queue;
 	u8	reserved[2];
 };
@@ -1351,9 +1104,6 @@ struct i40e_aqc_add_remove_cloud_filters {
 	u8	num_filters;
 	u8	reserved;
 	__le16	seid;
-#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT	0
-#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK	(0x3FF << \
-					I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT)
 	u8	big_buffer_flag;
 #define I40E_AQC_ADD_CLOUD_CMD_BB	1
 	u8	reserved2[3];
@@ -1380,9 +1130,6 @@ struct i40e_aqc_cloud_filters_element_data {
 		} raw_v6;
 	} ipaddr;
 	__le16	flags;
-#define I40E_AQC_ADD_CLOUD_FILTER_SHIFT			0
-#define I40E_AQC_ADD_CLOUD_FILTER_MASK	(0x3F << \
-					I40E_AQC_ADD_CLOUD_FILTER_SHIFT)
 /* 0x0000 reserved */
 /* 0x0001 reserved */
 /* 0x0002 reserved */
@@ -1404,36 +1151,20 @@ struct i40e_aqc_cloud_filters_element_data {
 #define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT		0x0011 /* Dest MAC + L4 Port */
 #define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT		0x0012 /* Dest MAC + VLAN + L4 Port */
 
-#define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE		0x0080
-#define I40E_AQC_ADD_CLOUD_VNK_SHIFT			6
-#define I40E_AQC_ADD_CLOUD_VNK_MASK			0x00C0
 #define I40E_AQC_ADD_CLOUD_FLAGS_IPV4			0
 #define I40E_AQC_ADD_CLOUD_FLAGS_IPV6			0x0100
 
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT		9
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK		0x1E00
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN		0
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC		1
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE		2
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP			3
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED		4
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE		5
 
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC	0x2000
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC	0x4000
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP	0x8000
 
 	__le32	tenant_id;
 	u8	reserved[4];
 	__le16	queue_number;
-#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT		0
-#define I40E_AQC_ADD_CLOUD_QUEUE_MASK		(0x7FF << \
-						 I40E_AQC_ADD_CLOUD_QUEUE_SHIFT)
 	u8	reserved2[14];
 	/* response section */
 	u8	allocation_result;
-#define I40E_AQC_ADD_CLOUD_FILTER_SUCCESS	0x0
-#define I40E_AQC_ADD_CLOUD_FILTER_FAIL		0xFF
 	u8	response_reserved[7];
 };
 
@@ -1445,37 +1176,7 @@ I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data);
 struct i40e_aqc_cloud_filters_element_bb {
 	struct i40e_aqc_cloud_filters_element_data element;
 	u16     general_fields[32];
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0	0
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1	1
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2	2
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0	3
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1	4
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2	5
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0	6
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1	7
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2	8
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0	9
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1	10
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2	11
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0	12
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1	13
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2	14
 #define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0	15
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1	16
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2	17
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3	18
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4	19
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5	20
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6	21
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7	22
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0	23
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1	24
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2	25
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3	26
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4	27
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5	28
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6	29
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7	30
 };
 
 I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb);
@@ -1504,11 +1205,6 @@ I40E_CHECK_STRUCT_LEN(4, i40e_filter_data);
 
 struct i40e_aqc_replace_cloud_filters_cmd {
 	u8      valid_flags;
-#define I40E_AQC_REPLACE_L1_FILTER		0x0
-#define I40E_AQC_REPLACE_CLOUD_FILTER		0x1
-#define I40E_AQC_GET_CLOUD_FILTERS		0x2
-#define I40E_AQC_MIRROR_CLOUD_FILTER		0x4
-#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER	0x8
 	u8      old_filter_type;
 	u8      new_filter_type;
 	u8      tr_bit;
@@ -1521,25 +1217,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd);
 
 struct i40e_aqc_replace_cloud_filters_cmd_buf {
 	u8      data[32];
-/* Filter type INPUT codes*/
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX	3
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED	BIT(7)
-
-/* Field Vector offsets */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA	0
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH	6
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG	7
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN	8
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN	9
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN	10
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY	11
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC	12
-/* big FLU */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA	14
-/* big FLU */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA	15
-
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN	37
 	struct i40e_filter_data filters[8];
 };
 
@@ -1556,8 +1233,6 @@ struct i40e_aqc_add_delete_mirror_rule {
 #define I40E_AQC_MIRROR_RULE_TYPE_SHIFT		0
 #define I40E_AQC_MIRROR_RULE_TYPE_MASK		(0x7 << \
 						I40E_AQC_MIRROR_RULE_TYPE_SHIFT)
-#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_INGRESS	1
-#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_EGRESS	2
 #define I40E_AQC_MIRROR_RULE_TYPE_VLAN		3
 #define I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS	4
 #define I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS	5
@@ -1600,8 +1275,6 @@ struct i40e_aqc_write_ddp_resp {
 
 struct i40e_aqc_get_applied_profiles {
 	u8      flags;
-#define I40E_AQC_GET_DDP_GET_CONF	0x1
-#define I40E_AQC_GET_DDP_GET_RDPU_CONF	0x2
 	u8      rsv[3];
 	__le32  reserved;
 	__le32  addr_high;
@@ -1618,8 +1291,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles);
 struct i40e_aqc_pfc_ignore {
 	u8	tc_bitmap;
 	u8	command_flags; /* unused on response */
-#define I40E_AQC_PFC_IGNORE_SET		0x80
-#define I40E_AQC_PFC_IGNORE_CLEAR	0x0
 	u8	reserved[14];
 };
 
@@ -1736,7 +1407,6 @@ struct i40e_aqc_configure_switching_comp_ets_data {
 	u8	reserved[4];
 	u8	tc_valid_bits;
 	u8	seepage;
-#define I40E_AQ_ETS_SEEPAGE_EN_MASK	0x1
 	u8	tc_strict_priority_flags;
 	u8	reserved1[17];
 	u8	tc_bw_share_credits[8];
@@ -1977,40 +1647,18 @@ struct i40e_aq_get_phy_abilities_resp {
 	u8	abilities;
 #define I40E_AQ_PHY_FLAG_PAUSE_TX	0x01
 #define I40E_AQ_PHY_FLAG_PAUSE_RX	0x02
-#define I40E_AQ_PHY_FLAG_LOW_POWER	0x04
-#define I40E_AQ_PHY_LINK_ENABLED	0x08
-#define I40E_AQ_PHY_AN_ENABLED		0x10
-#define I40E_AQ_PHY_FLAG_MODULE_QUAL	0x20
-#define I40E_AQ_PHY_FEC_ABILITY_KR	0x40
-#define I40E_AQ_PHY_FEC_ABILITY_RS	0x80
 	__le16	eee_capability;
-#define I40E_AQ_EEE_100BASE_TX		0x0002
-#define I40E_AQ_EEE_1000BASE_T		0x0004
-#define I40E_AQ_EEE_10GBASE_T		0x0008
-#define I40E_AQ_EEE_1000BASE_KX		0x0010
-#define I40E_AQ_EEE_10GBASE_KX4		0x0020
-#define I40E_AQ_EEE_10GBASE_KR		0x0040
 	__le32	eeer_val;
 	u8	d3_lpan;
-#define I40E_AQ_SET_PHY_D3_LPAN_ENA	0x01
 	u8	phy_type_ext;
 #define I40E_AQ_PHY_TYPE_EXT_25G_KR	0X01
 #define I40E_AQ_PHY_TYPE_EXT_25G_CR	0X02
 #define I40E_AQ_PHY_TYPE_EXT_25G_SR	0x04
 #define I40E_AQ_PHY_TYPE_EXT_25G_LR	0x08
-#define I40E_AQ_PHY_TYPE_EXT_25G_AOC	0x10
-#define I40E_AQ_PHY_TYPE_EXT_25G_ACC	0x20
-#define I40E_AQ_PHY_TYPE_EXT_2_5GBASE_T	0x40
-#define I40E_AQ_PHY_TYPE_EXT_5GBASE_T	0x80
 	u8	fec_cfg_curr_mod_ext_info;
-#define I40E_AQ_ENABLE_FEC_KR		0x01
-#define I40E_AQ_ENABLE_FEC_RS		0x02
 #define I40E_AQ_REQUEST_FEC_KR		0x04
 #define I40E_AQ_REQUEST_FEC_RS		0x08
 #define I40E_AQ_ENABLE_FEC_AUTO		0x10
-#define I40E_AQ_FEC
-#define I40E_AQ_MODULE_TYPE_EXT_MASK	0xE0
-#define I40E_AQ_MODULE_TYPE_EXT_SHIFT	5
 
 	u8	ext_comp_code;
 	u8	phy_id[4];
@@ -2028,7 +1676,6 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */
 	u8	link_speed;
 	u8	abilities;
 /* bits 0-2 use the values from get_phy_abilities_resp */
-#define I40E_AQ_PHY_ENABLE_LINK		0x08
 #define I40E_AQ_PHY_ENABLE_AN		0x10
 #define I40E_AQ_PHY_ENABLE_ATOMIC_LINK	0x20
 	__le16	eee_capability;
@@ -2056,21 +1703,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
 struct i40e_aq_set_mac_config {
 	__le16	max_frame_size;
 	u8	params;
-#define I40E_AQ_SET_MAC_CONFIG_CRC_EN			0x04
-#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK		0x78
-#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT		3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE		0x0
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX		0xF
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX		0x9
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX		0x8
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX		0x7
-#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX		0x6
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX		0x5
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX		0x4
-#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX		0x3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX		0x2
-#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX		0x1
-#define I40E_AQ_SET_MAC_CONFIG_DROP_BLOCKING_PACKET_EN	0x80
 	u8	tx_timer_priority; /* bitmap */
 	__le16	tx_timer_value;
 	__le16	fc_refresh_threshold;
@@ -2092,8 +1724,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_set_link_restart_an);
 /* Get Link Status cmd & response data structure (direct 0x0607) */
 struct i40e_aqc_get_link_status {
 	__le16	command_flags; /* only field set on command */
-#define I40E_AQ_LSE_MASK		0x3
-#define I40E_AQ_LSE_NOP			0x0
 #define I40E_AQ_LSE_DISABLE		0x2
 #define I40E_AQ_LSE_ENABLE		0x3
 /* only response uses this flag */
@@ -2102,44 +1732,16 @@ struct i40e_aqc_get_link_status {
 	u8	link_speed;  /* i40e_aq_link_speed */
 	u8	link_info;
 #define I40E_AQ_LINK_UP			0x01    /* obsolete */
-#define I40E_AQ_LINK_UP_FUNCTION	0x01
-#define I40E_AQ_LINK_FAULT		0x02
-#define I40E_AQ_LINK_FAULT_TX		0x04
-#define I40E_AQ_LINK_FAULT_RX		0x08
-#define I40E_AQ_LINK_FAULT_REMOTE	0x10
-#define I40E_AQ_LINK_UP_PORT		0x20
 #define I40E_AQ_MEDIA_AVAILABLE		0x40
-#define I40E_AQ_SIGNAL_DETECT		0x80
 	u8	an_info;
 #define I40E_AQ_AN_COMPLETED		0x01
-#define I40E_AQ_LP_AN_ABILITY		0x02
-#define I40E_AQ_PD_FAULT		0x04
-#define I40E_AQ_FEC_EN			0x08
-#define I40E_AQ_PHY_LOW_POWER		0x10
 #define I40E_AQ_LINK_PAUSE_TX		0x20
 #define I40E_AQ_LINK_PAUSE_RX		0x40
 #define I40E_AQ_QUALIFIED_MODULE	0x80
 	u8	ext_info;
-#define I40E_AQ_LINK_PHY_TEMP_ALARM	0x01
-#define I40E_AQ_LINK_XCESSIVE_ERRORS	0x02
-#define I40E_AQ_LINK_TX_SHIFT		0x02
-#define I40E_AQ_LINK_TX_MASK		(0x03 << I40E_AQ_LINK_TX_SHIFT)
-#define I40E_AQ_LINK_TX_ACTIVE		0x00
-#define I40E_AQ_LINK_TX_DRAINED		0x01
-#define I40E_AQ_LINK_TX_FLUSHED		0x03
-#define I40E_AQ_LINK_FORCED_40G		0x10
-/* 25G Error Codes */
-#define I40E_AQ_25G_NO_ERR		0X00
-#define I40E_AQ_25G_NOT_PRESENT		0X01
-#define I40E_AQ_25G_NVM_CRC_ERR		0X02
-#define I40E_AQ_25G_SBUS_UCODE_ERR	0X03
-#define I40E_AQ_25G_SERDES_UCODE_ERR	0X04
-#define I40E_AQ_25G_NIMB_UCODE_ERR	0X05
 	u8	loopback; /* use defines from i40e_aqc_set_lb_mode */
 /* Since firmware API 1.7 loopback field keeps power class info as well */
 #define I40E_AQ_LOOPBACK_MASK		0x07
-#define I40E_AQ_PWR_CLASS_SHIFT_LB	6
-#define I40E_AQ_PWR_CLASS_MASK_LB	(0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
 	__le16	max_frame_size;
 	u8	config;
 #define I40E_AQ_CONFIG_FEC_KR_ENA	0x01
@@ -2149,11 +1751,6 @@ struct i40e_aqc_get_link_status {
 	union {
 		struct {
 			u8	power_desc;
-#define I40E_AQ_LINK_POWER_CLASS_1	0x00
-#define I40E_AQ_LINK_POWER_CLASS_2	0x01
-#define I40E_AQ_LINK_POWER_CLASS_3	0x02
-#define I40E_AQ_LINK_POWER_CLASS_4	0x03
-#define I40E_AQ_PWR_CLASS_MASK		0x03
 			u8	reserved[4];
 		};
 		struct {
@@ -2171,13 +1768,7 @@ struct i40e_aqc_set_phy_int_mask {
 	__le16	event_mask;
 #define I40E_AQ_EVENT_LINK_UPDOWN	0x0002
 #define I40E_AQ_EVENT_MEDIA_NA		0x0004
-#define I40E_AQ_EVENT_LINK_FAULT	0x0008
-#define I40E_AQ_EVENT_PHY_TEMP_ALARM	0x0010
-#define I40E_AQ_EVENT_EXCESSIVE_ERRORS	0x0020
-#define I40E_AQ_EVENT_SIGNAL_DETECT	0x0040
-#define I40E_AQ_EVENT_AN_COMPLETED	0x0080
 #define I40E_AQ_EVENT_MODULE_QUAL_FAIL	0x0100
-#define I40E_AQ_EVENT_PORT_TX_SUSPENDED	0x0200
 	u8	reserved1[6];
 };
 
@@ -2209,13 +1800,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode);
 /* Set PHY Debug command (0x0622) */
 struct i40e_aqc_set_phy_debug {
 	u8	command_flags;
-#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL	0x02
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT	2
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK	(0x03 << \
-					I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT)
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE	0x00
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD	0x01
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT	0x02
 /* Disable link manageability on a single port */
 #define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW	0x10
 /* Disable link manageability on all ports */
@@ -2247,7 +1831,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
 /* Get PHY Register command (0x0629) */
 struct i40e_aqc_phy_register_access {
 	u8	phy_interface;
-#define I40E_AQ_PHY_REG_ACCESS_INTERNAL	0
 #define I40E_AQ_PHY_REG_ACCESS_EXTERNAL	1
 #define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE	2
 	u8	dev_address;
@@ -2274,9 +1857,7 @@ struct i40e_aqc_nvm_update {
 #define I40E_AQ_NVM_LAST_CMD			0x01
 #define I40E_AQ_NVM_REARRANGE_TO_FLAT		0x20
 #define I40E_AQ_NVM_REARRANGE_TO_STRUCT		0x40
-#define I40E_AQ_NVM_FLASH_ONLY			0x80
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT	1
-#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK	0x03
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED	0x03
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL	0x01
 	u8	module_pointer;
@@ -2291,9 +1872,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
 /* NVM Config Read (indirect 0x0704) */
 struct i40e_aqc_nvm_config_read {
 	__le16	cmd_flags;
-#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK	1 
-#define I40E_AQ_ANVM_READ_SINGLE_FEATURE		0 
-#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES		1
 	__le16	element_count;
 	__le16	element_id;	/* Feature/field ID */
 	__le16	element_id_msw;	/* MSWord of field ID */
@@ -2315,16 +1893,8 @@ struct i40e_aqc_nvm_config_write {
 I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write);
 
 /* Used for 0x0704 as well as for 0x0705 commands */
-#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT		1
-#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \
-				BIT(I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT)
-#define I40E_AQ_ANVM_FEATURE		0
-#define I40E_AQ_ANVM_IMMEDIATE_FIELD	BIT(FEATURE_OR_IMMEDIATE_SHIFT)
 struct i40e_aqc_nvm_config_data_feature {
 	__le16 feature_id;
-#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY		0x01
-#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP		0x08
-#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR		0x10
 	__le16 feature_options;
 	__le16 feature_selection;
 };
@@ -2344,7 +1914,6 @@ I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field);
  * no command data struct used
  */
 struct i40e_aqc_nvm_oem_post_update {
-#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA	0x01
 	u8 sel_data;
 	u8 reserved[7];
 };
@@ -2366,9 +1935,6 @@ I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer);
  */
 struct i40e_aqc_thermal_sensor {
 	u8 sensor_action;
-#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG	0
-#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG	1
-#define I40E_AQ_THERMAL_SENSOR_READ_TEMP	2
 	u8 reserved[7];
 	__le32	addr_high;
 	__le32	addr_low;
@@ -2421,10 +1987,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_ind_write);
  */
 struct i40e_aqc_alternate_write_done {
 	__le16	cmd_flags;
-#define I40E_AQ_ALTERNATE_MODE_BIOS_MASK	1
-#define I40E_AQ_ALTERNATE_MODE_BIOS_LEGACY	0
-#define I40E_AQ_ALTERNATE_MODE_BIOS_UEFI	1
-#define I40E_AQ_ALTERNATE_RESET_NEEDED		2
 	u8	reserved[14];
 };
 
@@ -2433,8 +1995,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write_done);
 /* Set OEM mode (direct 0x0905) */
 struct i40e_aqc_alternate_set_mode {
 	__le32	mode;
-#define I40E_AQ_ALTERNATE_MODE_NONE	0
-#define I40E_AQ_ALTERNATE_MODE_OEM	1
 	u8	reserved[12];
 };
 
@@ -2460,13 +2020,9 @@ struct i40e_aqc_lldp_get_mib {
 #define I40E_AQ_LLDP_MIB_TYPE_MASK		0x3
 #define I40E_AQ_LLDP_MIB_LOCAL			0x0
 #define I40E_AQ_LLDP_MIB_REMOTE			0x1
-#define I40E_AQ_LLDP_MIB_LOCAL_AND_REMOTE	0x2
 #define I40E_AQ_LLDP_BRIDGE_TYPE_MASK		0xC
 #define I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT		0x2
 #define I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE	0x0
-#define I40E_AQ_LLDP_BRIDGE_TYPE_NON_TPMR	0x1
-#define I40E_AQ_LLDP_TX_SHIFT			0x4
-#define I40E_AQ_LLDP_TX_MASK			(0x03 << I40E_AQ_LLDP_TX_SHIFT)
 /* TX pause flags use I40E_AQ_LINK_TX_* above */
 	__le16	local_len;
 	__le16	remote_len;
@@ -2482,7 +2038,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_get_mib);
  */
 struct i40e_aqc_lldp_update_mib {
 	u8	command;
-#define I40E_AQ_LLDP_MIB_UPDATE_ENABLE	0x0
 #define I40E_AQ_LLDP_MIB_UPDATE_DISABLE	0x1
 	u8	reserved[7];
 	__le32	addr_high;
@@ -2521,7 +2076,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv);
 /* Stop LLDP (direct 0x0A05) */
 struct i40e_aqc_lldp_stop {
 	u8	command;
-#define I40E_AQ_LLDP_AGENT_STOP			0x0
 #define I40E_AQ_LLDP_AGENT_SHUTDOWN		0x1
 #define I40E_AQ_LLDP_AGENT_STOP_PERSIST		0x2
 	u8	reserved[15];
@@ -2627,13 +2181,6 @@ I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_cee_dcb_cfg_resp);
  *	Used to replace the local MIB of a given LLDP agent. e.g. DCBx
  */
 struct i40e_aqc_lldp_set_local_mib {
-#define SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT	0
-#define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK	BIT(SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT)
-#define SET_LOCAL_MIB_AC_TYPE_LOCAL_MIB	0x0
-#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT	(1)
-#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_MASK \
-			BIT(SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT)
-#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS		0x1
 	u8	type;
 	u8	reserved0;
 	__le16	length;
@@ -2648,9 +2195,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_set_local_mib);
  *	Used for stopping/starting specific LLDP agent. e.g. DCBx
  */
 struct i40e_aqc_lldp_stop_start_specific_agent {
-#define I40E_AQC_START_SPECIFIC_AGENT_SHIFT	0
-#define I40E_AQC_START_SPECIFIC_AGENT_MASK \
-				BIT(I40E_AQC_START_SPECIFIC_AGENT_SHIFT)
 	u8	command;
 	u8	reserved[15];
 };
@@ -2660,7 +2204,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop_start_specific_agent);
 /* Restore LLDP Agent factory settings (direct 0x0A0A) */
 struct i40e_aqc_lldp_restore {
 	u8	command;
-#define I40E_AQ_LLDP_AGENT_RESTORE_NOT		0x0
 #define I40E_AQ_LLDP_AGENT_RESTORE		0x1
 	u8	reserved[15];
 };
@@ -2674,8 +2217,6 @@ struct i40e_aqc_add_udp_tunnel {
 	u8	protocol_type;
 #define I40E_AQC_TUNNEL_TYPE_VXLAN	0x00
 #define I40E_AQC_TUNNEL_TYPE_NGE	0x01
-#define I40E_AQC_TUNNEL_TYPE_TEREDO	0x10
-#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE	0x11
 	u8	reserved1[10];
 };
 
@@ -2685,8 +2226,6 @@ struct i40e_aqc_add_udp_tunnel_completion {
 	__le16	udp_port;
 	u8	filter_entry_index;
 	u8	multiple_pfs;
-#define I40E_AQC_SINGLE_PF		0x0
-#define I40E_AQC_MULTIPLE_PFS		0x1
 	u8	total_filters;
 	u8	reserved[11];
 };
@@ -2759,16 +2298,7 @@ struct i40e_aqc_tunnel_key_structure {
 	u8	key1_len;  /* 0 to 15 */
 	u8	key2_len;  /* 0 to 15 */
 	u8	flags;
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE	0x01
-/* response flags */
-#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS	0x01
-#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED	0x02
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN	0x03
 	u8	network_key_index;
-#define I40E_AQC_NETWORK_KEY_INDEX_VXLAN		0x0
-#define I40E_AQC_NETWORK_KEY_INDEX_NGE			0x1
-#define I40E_AQC_NETWORK_KEY_INDEX_FLEX_MAC_IN_UDP	0x2
-#define I40E_AQC_NETWORK_KEY_INDEX_GRE			0x3
 	u8	reserved[10];
 };
 
@@ -2777,9 +2307,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure);
 /* OEM mode commands (direct 0xFE0x) */
 struct i40e_aqc_oem_param_change {
 	__le32	param_type;
-#define I40E_AQ_OEM_PARAM_TYPE_PF_CTL	0
-#define I40E_AQ_OEM_PARAM_TYPE_BW_CTL	1
-#define I40E_AQ_OEM_PARAM_MAC		2
 	__le32	param_value1;
 	__le16	param_value2;
 	u8	reserved[6];
@@ -2789,8 +2316,6 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change);
 
 struct i40e_aqc_oem_state_change {
 	__le32	state;
-#define I40E_AQ_OEM_STATE_LINK_DOWN	0x0
-#define I40E_AQ_OEM_STATE_LINK_UP	0x1
 	u8	reserved[12];
 };
 
@@ -2826,14 +2351,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize);
 
 struct i40e_acq_set_test_mode {
 	u8	mode;
-#define I40E_AQ_TEST_PARTIAL	0
-#define I40E_AQ_TEST_FULL	1
-#define I40E_AQ_TEST_NVM	2
 	u8	reserved[3];
 	u8	command;
-#define I40E_AQ_TEST_OPEN	0
-#define I40E_AQ_TEST_CLOSE	1
-#define I40E_AQ_TEST_INC	2
 	u8	reserved2[3];
 	__le32	address_high;
 	__le32	address_low;
@@ -2874,20 +2393,6 @@ struct i40e_aqc_debug_modify_reg {
 I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_reg);
 
 /* dump internal data (0xFF08, indirect) */
-
-#define I40E_AQ_CLUSTER_ID_AUX		0
-#define I40E_AQ_CLUSTER_ID_SWITCH_FLU	1
-#define I40E_AQ_CLUSTER_ID_TXSCHED	2
-#define I40E_AQ_CLUSTER_ID_HMC		3
-#define I40E_AQ_CLUSTER_ID_MAC0		4
-#define I40E_AQ_CLUSTER_ID_MAC1		5
-#define I40E_AQ_CLUSTER_ID_MAC2		6
-#define I40E_AQ_CLUSTER_ID_MAC3		7
-#define I40E_AQ_CLUSTER_ID_DCB		8
-#define I40E_AQ_CLUSTER_ID_EMP_MEM	9
-#define I40E_AQ_CLUSTER_ID_PKT_BUF	10
-#define I40E_AQ_CLUSTER_ID_ALTRAM	11
-
 struct i40e_aqc_debug_dump_internals {
 	u8	cluster_id;
 	u8	table_id;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 45b90eb11adb..4ab081953e19 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1455,10 +1455,6 @@ static u32 i40e_led_is_mine(struct i40e_hw *hw, int idx)
 	return gpio_val;
 }
 
-#define I40E_COMBINED_ACTIVITY 0xA
-#define I40E_FILTER_ACTIVITY 0xE
-#define I40E_LINK_ACTIVITY 0xC
-#define I40E_MAC_ACTIVITY 0xD
 #define I40E_FW_LED BIT(4)
 #define I40E_LED_MODE_VALID (I40E_GLGEN_GPIO_CTL_LED_MODE_MASK >> \
 			     I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index ba86ad833bee..2b1a2e81ac73 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -6,10 +6,8 @@
 
 #include "i40e_type.h"
 
-#define I40E_DCBX_STATUS_NOT_STARTED	0
 #define I40E_DCBX_STATUS_IN_PROGRESS	1
 #define I40E_DCBX_STATUS_DONE		2
-#define I40E_DCBX_STATUS_MULTIPLE_PEERS	3
 #define I40E_DCBX_STATUS_DISABLED	7
 
 #define I40E_TLV_TYPE_END		0
@@ -24,7 +22,6 @@
 #define I40E_CEE_DCBX_OUI		0x001b21
 #define I40E_CEE_DCBX_TYPE		2
 
-#define I40E_CEE_SUBTYPE_CTRL		1
 #define I40E_CEE_SUBTYPE_PG_CFG		2
 #define I40E_CEE_SUBTYPE_PFC_CFG	3
 #define I40E_CEE_SUBTYPE_APP_PRI	4
@@ -105,9 +102,7 @@ struct i40e_cee_ctrl_tlv {
 struct i40e_cee_feat_tlv {
 	struct i40e_cee_tlv_hdr hdr;
 	u8 en_will_err; /* Bits: |En|Will|Err|Reserved(5)| */
-#define I40E_CEE_FEAT_TLV_ENABLE_MASK	0x80
 #define I40E_CEE_FEAT_TLV_WILLING_MASK	0x40
-#define I40E_CEE_FEAT_TLV_ERR_MASK	0x20
 	u8 subtype;
 	u8 tlvinfo[1];
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 99ea543dd245..9cb9b781451c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -688,7 +688,6 @@ static void i40e_dbg_dump_vf_all(struct i40e_pf *pf)
 			i40e_dbg_dump_vf(pf, i);
 }
 
-#define I40E_MAX_DEBUG_OUT_BUFFER (4096*4)
 /**
  * i40e_dbg_command_write - write into command datum
  * @filp: the opened file
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h
index bf15a868292f..33df3bf2f73b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h
@@ -32,8 +32,5 @@
 #define I40E_DEV_ID_10G_BASE_T_X722	0x37D2
 #define I40E_DEV_ID_SFP_I_X722		0x37D3
 
-#define i40e_is_40G_device(d)		((d) == I40E_DEV_ID_QSFP_A  || \
-					 (d) == I40E_DEV_ID_QSFP_B  || \
-					 (d) == I40E_DEV_ID_QSFP_C)
 
 #endif /* _I40E_DEVIDS_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
index 1c78de838857..3113792afaff 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
@@ -14,7 +14,6 @@ struct i40e_hw;
 #define I40E_HMC_DIRECT_BP_SIZE		0x200000 /* 2M */
 #define I40E_HMC_PAGED_BP_SIZE		4096
 #define I40E_HMC_PD_BP_BUF_ALIGNMENT	4096
-#define I40E_FIRST_VF_FPM_ID		16
 
 struct i40e_hmc_obj_info {
 	u64 base;	/* base addr in FPM */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5d807c8004f8..5f7f5147f9a7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6492,8 +6492,7 @@ out:
 	return err;
 }
 #endif /* CONFIG_I40E_DCB */
-#define SPEED_SIZE 14
-#define FC_SIZE 8
+
 /**
  * i40e_print_link_message - print link up or down
  * @vsi: the VSI for which link needs a message
@@ -8950,13 +8949,6 @@ u32 i40e_get_current_atr_cnt(struct i40e_pf *pf)
 	return i40e_get_current_fd_count(pf) - pf->fdir_pf_active_filters;
 }
 
-/* We can see up to 256 filter programming desc in transit if the filters are
- * being applied really fast; before we see the first
- * filter miss error on Rx queue 0. Accumulating enough error messages before
- * reacting will make sure we don't cause flush too often.
- */
-#define I40E_MAX_FD_PROGRAM_ERROR 256
-
 /**
  * i40e_fdir_reinit_subtask - Worker thread to reinit FDIR filter table
  * @pf: board private structure
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index c302ef2524f8..2f6815b2f8df 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -26,7 +26,6 @@ do {										\
 #define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
 #define rd32(a, reg)		readl((a)->hw_addr + (reg))
 
-#define wr64(a, reg, value)	writeq((value), ((a)->hw_addr + (reg)))
 #define rd64(a, reg)		readq((a)->hw_addr + (reg))
 #define i40e_flush(a)		readl((a)->hw_addr + I40E_GLGEN_STAT)
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index d35d690ca10f..7cd3a08a1891 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -4,53 +4,14 @@
 #ifndef _I40E_REGISTER_H_
 #define _I40E_REGISTER_H_
 
-#define I40E_GL_ARQBAH 0x000801C0 /* Reset: EMPR */
-#define I40E_GL_ARQBAH_ARQBAH_SHIFT 0
-#define I40E_GL_ARQBAH_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_ARQBAH_ARQBAH_SHIFT)
-#define I40E_GL_ARQBAL 0x000800C0 /* Reset: EMPR */
-#define I40E_GL_ARQBAL_ARQBAL_SHIFT 0
-#define I40E_GL_ARQBAL_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_ARQBAL_ARQBAL_SHIFT)
-#define I40E_GL_ARQH 0x000803C0 /* Reset: EMPR */
-#define I40E_GL_ARQH_ARQH_SHIFT 0
-#define I40E_GL_ARQH_ARQH_MASK I40E_MASK(0x3FF, I40E_GL_ARQH_ARQH_SHIFT)
-#define I40E_GL_ARQT 0x000804C0 /* Reset: EMPR */
-#define I40E_GL_ARQT_ARQT_SHIFT 0
-#define I40E_GL_ARQT_ARQT_MASK I40E_MASK(0x3FF, I40E_GL_ARQT_ARQT_SHIFT)
-#define I40E_GL_ATQBAH 0x00080140 /* Reset: EMPR */
-#define I40E_GL_ATQBAH_ATQBAH_SHIFT 0
-#define I40E_GL_ATQBAH_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_ATQBAH_ATQBAH_SHIFT)
-#define I40E_GL_ATQBAL 0x00080040 /* Reset: EMPR */
-#define I40E_GL_ATQBAL_ATQBAL_SHIFT 0
-#define I40E_GL_ATQBAL_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_ATQBAL_ATQBAL_SHIFT)
-#define I40E_GL_ATQH 0x00080340 /* Reset: EMPR */
-#define I40E_GL_ATQH_ATQH_SHIFT 0
-#define I40E_GL_ATQH_ATQH_MASK I40E_MASK(0x3FF, I40E_GL_ATQH_ATQH_SHIFT)
-#define I40E_GL_ATQLEN 0x00080240 /* Reset: EMPR */
-#define I40E_GL_ATQLEN_ATQLEN_SHIFT 0
-#define I40E_GL_ATQLEN_ATQLEN_MASK I40E_MASK(0x3FF, I40E_GL_ATQLEN_ATQLEN_SHIFT)
-#define I40E_GL_ATQLEN_ATQVFE_SHIFT 28
-#define I40E_GL_ATQLEN_ATQVFE_MASK I40E_MASK(0x1, I40E_GL_ATQLEN_ATQVFE_SHIFT)
-#define I40E_GL_ATQLEN_ATQOVFL_SHIFT 29
-#define I40E_GL_ATQLEN_ATQOVFL_MASK I40E_MASK(0x1, I40E_GL_ATQLEN_ATQOVFL_SHIFT)
 #define I40E_GL_ATQLEN_ATQCRIT_SHIFT 30
 #define I40E_GL_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_GL_ATQLEN_ATQCRIT_SHIFT)
-#define I40E_GL_ATQLEN_ATQENABLE_SHIFT 31
-#define I40E_GL_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1, I40E_GL_ATQLEN_ATQENABLE_SHIFT)
-#define I40E_GL_ATQT 0x00080440 /* Reset: EMPR */
-#define I40E_GL_ATQT_ATQT_SHIFT 0
-#define I40E_GL_ATQT_ATQT_MASK I40E_MASK(0x3FF, I40E_GL_ATQT_ATQT_SHIFT)
 #define I40E_PF_ARQBAH 0x00080180 /* Reset: EMPR */
-#define I40E_PF_ARQBAH_ARQBAH_SHIFT 0
-#define I40E_PF_ARQBAH_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_PF_ARQBAH_ARQBAH_SHIFT)
 #define I40E_PF_ARQBAL 0x00080080 /* Reset: EMPR */
-#define I40E_PF_ARQBAL_ARQBAL_SHIFT 0
-#define I40E_PF_ARQBAL_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_PF_ARQBAL_ARQBAL_SHIFT)
 #define I40E_PF_ARQH 0x00080380 /* Reset: EMPR */
 #define I40E_PF_ARQH_ARQH_SHIFT 0
 #define I40E_PF_ARQH_ARQH_MASK I40E_MASK(0x3FF, I40E_PF_ARQH_ARQH_SHIFT)
 #define I40E_PF_ARQLEN 0x00080280 /* Reset: EMPR */
-#define I40E_PF_ARQLEN_ARQLEN_SHIFT 0
-#define I40E_PF_ARQLEN_ARQLEN_MASK I40E_MASK(0x3FF, I40E_PF_ARQLEN_ARQLEN_SHIFT)
 #define I40E_PF_ARQLEN_ARQVFE_SHIFT 28
 #define I40E_PF_ARQLEN_ARQVFE_MASK I40E_MASK(0x1, I40E_PF_ARQLEN_ARQVFE_SHIFT)
 #define I40E_PF_ARQLEN_ARQOVFL_SHIFT 29
@@ -60,20 +21,10 @@
 #define I40E_PF_ARQLEN_ARQENABLE_SHIFT 31
 #define I40E_PF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ARQLEN_ARQENABLE_SHIFT)
 #define I40E_PF_ARQT 0x00080480 /* Reset: EMPR */
-#define I40E_PF_ARQT_ARQT_SHIFT 0
-#define I40E_PF_ARQT_ARQT_MASK I40E_MASK(0x3FF, I40E_PF_ARQT_ARQT_SHIFT)
 #define I40E_PF_ATQBAH 0x00080100 /* Reset: EMPR */
-#define I40E_PF_ATQBAH_ATQBAH_SHIFT 0
-#define I40E_PF_ATQBAH_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_PF_ATQBAH_ATQBAH_SHIFT)
 #define I40E_PF_ATQBAL 0x00080000 /* Reset: EMPR */
-#define I40E_PF_ATQBAL_ATQBAL_SHIFT 0
-#define I40E_PF_ATQBAL_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_PF_ATQBAL_ATQBAL_SHIFT)
 #define I40E_PF_ATQH 0x00080300 /* Reset: EMPR */
-#define I40E_PF_ATQH_ATQH_SHIFT 0
-#define I40E_PF_ATQH_ATQH_MASK I40E_MASK(0x3FF, I40E_PF_ATQH_ATQH_SHIFT)
 #define I40E_PF_ATQLEN 0x00080200 /* Reset: EMPR */
-#define I40E_PF_ATQLEN_ATQLEN_SHIFT 0
-#define I40E_PF_ATQLEN_ATQLEN_MASK I40E_MASK(0x3FF, I40E_PF_ATQLEN_ATQLEN_SHIFT)
 #define I40E_PF_ATQLEN_ATQVFE_SHIFT 28
 #define I40E_PF_ATQLEN_ATQVFE_MASK I40E_MASK(0x1, I40E_PF_ATQLEN_ATQVFE_SHIFT)
 #define I40E_PF_ATQLEN_ATQOVFL_SHIFT 29
@@ -83,284 +34,13 @@
 #define I40E_PF_ATQLEN_ATQENABLE_SHIFT 31
 #define I40E_PF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ATQLEN_ATQENABLE_SHIFT)
 #define I40E_PF_ATQT 0x00080400 /* Reset: EMPR */
-#define I40E_PF_ATQT_ATQT_SHIFT 0
-#define I40E_PF_ATQT_ATQT_MASK I40E_MASK(0x3FF, I40E_PF_ATQT_ATQT_SHIFT)
-#define I40E_VF_ARQBAH(_VF) (0x00081400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ARQBAH_MAX_INDEX 127
-#define I40E_VF_ARQBAH_ARQBAH_SHIFT 0
-#define I40E_VF_ARQBAH_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAH_ARQBAH_SHIFT)
-#define I40E_VF_ARQBAL(_VF) (0x00080C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ARQBAL_MAX_INDEX 127
-#define I40E_VF_ARQBAL_ARQBAL_SHIFT 0
-#define I40E_VF_ARQBAL_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAL_ARQBAL_SHIFT)
-#define I40E_VF_ARQH(_VF) (0x00082400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ARQH_MAX_INDEX 127
-#define I40E_VF_ARQH_ARQH_SHIFT 0
-#define I40E_VF_ARQH_ARQH_MASK I40E_MASK(0x3FF, I40E_VF_ARQH_ARQH_SHIFT)
-#define I40E_VF_ARQLEN(_VF) (0x00081C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ARQLEN_MAX_INDEX 127
-#define I40E_VF_ARQLEN_ARQLEN_SHIFT 0
-#define I40E_VF_ARQLEN_ARQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ARQLEN_ARQLEN_SHIFT)
-#define I40E_VF_ARQLEN_ARQVFE_SHIFT 28
-#define I40E_VF_ARQLEN_ARQVFE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQVFE_SHIFT)
-#define I40E_VF_ARQLEN_ARQOVFL_SHIFT 29
-#define I40E_VF_ARQLEN_ARQOVFL_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQOVFL_SHIFT)
-#define I40E_VF_ARQLEN_ARQCRIT_SHIFT 30
-#define I40E_VF_ARQLEN_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQCRIT_SHIFT)
-#define I40E_VF_ARQLEN_ARQENABLE_SHIFT 31
-#define I40E_VF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN_ARQENABLE_SHIFT)
-#define I40E_VF_ARQT(_VF) (0x00082C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ARQT_MAX_INDEX 127
-#define I40E_VF_ARQT_ARQT_SHIFT 0
-#define I40E_VF_ARQT_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT_ARQT_SHIFT)
-#define I40E_VF_ATQBAH(_VF) (0x00081000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ATQBAH_MAX_INDEX 127
-#define I40E_VF_ATQBAH_ATQBAH_SHIFT 0
-#define I40E_VF_ATQBAH_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAH_ATQBAH_SHIFT)
-#define I40E_VF_ATQBAL(_VF) (0x00080800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ATQBAL_MAX_INDEX 127
-#define I40E_VF_ATQBAL_ATQBAL_SHIFT 0
-#define I40E_VF_ATQBAL_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAL_ATQBAL_SHIFT)
-#define I40E_VF_ATQH(_VF) (0x00082000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ATQH_MAX_INDEX 127
-#define I40E_VF_ATQH_ATQH_SHIFT 0
-#define I40E_VF_ATQH_ATQH_MASK I40E_MASK(0x3FF, I40E_VF_ATQH_ATQH_SHIFT)
-#define I40E_VF_ATQLEN(_VF) (0x00081800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ATQLEN_MAX_INDEX 127
-#define I40E_VF_ATQLEN_ATQLEN_SHIFT 0
-#define I40E_VF_ATQLEN_ATQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ATQLEN_ATQLEN_SHIFT)
-#define I40E_VF_ATQLEN_ATQVFE_SHIFT 28
-#define I40E_VF_ATQLEN_ATQVFE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQVFE_SHIFT)
-#define I40E_VF_ATQLEN_ATQOVFL_SHIFT 29
-#define I40E_VF_ATQLEN_ATQOVFL_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQOVFL_SHIFT)
-#define I40E_VF_ATQLEN_ATQCRIT_SHIFT 30
-#define I40E_VF_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQCRIT_SHIFT)
-#define I40E_VF_ATQLEN_ATQENABLE_SHIFT 31
-#define I40E_VF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN_ATQENABLE_SHIFT)
-#define I40E_VF_ATQT(_VF) (0x00082800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_VF_ATQT_MAX_INDEX 127
-#define I40E_VF_ATQT_ATQT_SHIFT 0
-#define I40E_VF_ATQT_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT_ATQT_SHIFT)
-#define I40E_PRT_L2TAGSEN 0x001C0B20 /* Reset: CORER */
-#define I40E_PRT_L2TAGSEN_ENABLE_SHIFT 0
-#define I40E_PRT_L2TAGSEN_ENABLE_MASK I40E_MASK(0xFF, I40E_PRT_L2TAGSEN_ENABLE_SHIFT)
-#define I40E_PFCM_LAN_ERRDATA 0x0010C080 /* Reset: PFR */
-#define I40E_PFCM_LAN_ERRDATA_ERROR_CODE_SHIFT 0
-#define I40E_PFCM_LAN_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_PFCM_LAN_ERRDATA_ERROR_CODE_SHIFT)
-#define I40E_PFCM_LAN_ERRDATA_Q_TYPE_SHIFT 4
-#define I40E_PFCM_LAN_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_PFCM_LAN_ERRDATA_Q_TYPE_SHIFT)
-#define I40E_PFCM_LAN_ERRDATA_Q_NUM_SHIFT 8
-#define I40E_PFCM_LAN_ERRDATA_Q_NUM_MASK I40E_MASK(0xFFF, I40E_PFCM_LAN_ERRDATA_Q_NUM_SHIFT)
-#define I40E_PFCM_LAN_ERRINFO 0x0010C000 /* Reset: PFR */
-#define I40E_PFCM_LAN_ERRINFO_ERROR_VALID_SHIFT 0
-#define I40E_PFCM_LAN_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_PFCM_LAN_ERRINFO_ERROR_VALID_SHIFT)
-#define I40E_PFCM_LAN_ERRINFO_ERROR_INST_SHIFT 4
-#define I40E_PFCM_LAN_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_PFCM_LAN_ERRINFO_ERROR_INST_SHIFT)
-#define I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_SHIFT 8
-#define I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_SHIFT)
-#define I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_SHIFT 16
-#define I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_SHIFT)
-#define I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_SHIFT 24
-#define I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_SHIFT)
-#define I40E_PFCM_LANCTXCTL 0x0010C300 /* Reset: CORER */
-#define I40E_PFCM_LANCTXCTL_QUEUE_NUM_SHIFT 0
-#define I40E_PFCM_LANCTXCTL_QUEUE_NUM_MASK I40E_MASK(0xFFF, I40E_PFCM_LANCTXCTL_QUEUE_NUM_SHIFT)
-#define I40E_PFCM_LANCTXCTL_SUB_LINE_SHIFT 12
-#define I40E_PFCM_LANCTXCTL_SUB_LINE_MASK I40E_MASK(0x7, I40E_PFCM_LANCTXCTL_SUB_LINE_SHIFT)
-#define I40E_PFCM_LANCTXCTL_QUEUE_TYPE_SHIFT 15
-#define I40E_PFCM_LANCTXCTL_QUEUE_TYPE_MASK I40E_MASK(0x3, I40E_PFCM_LANCTXCTL_QUEUE_TYPE_SHIFT)
-#define I40E_PFCM_LANCTXCTL_OP_CODE_SHIFT 17
-#define I40E_PFCM_LANCTXCTL_OP_CODE_MASK I40E_MASK(0x3, I40E_PFCM_LANCTXCTL_OP_CODE_SHIFT)
-#define I40E_PFCM_LANCTXDATA(_i) (0x0010C100 + ((_i) * 128)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_PFCM_LANCTXDATA_MAX_INDEX 3
-#define I40E_PFCM_LANCTXDATA_DATA_SHIFT 0
-#define I40E_PFCM_LANCTXDATA_DATA_MASK I40E_MASK(0xFFFFFFFF, I40E_PFCM_LANCTXDATA_DATA_SHIFT)
-#define I40E_PFCM_LANCTXSTAT 0x0010C380 /* Reset: CORER */
-#define I40E_PFCM_LANCTXSTAT_CTX_DONE_SHIFT 0
-#define I40E_PFCM_LANCTXSTAT_CTX_DONE_MASK I40E_MASK(0x1, I40E_PFCM_LANCTXSTAT_CTX_DONE_SHIFT)
-#define I40E_PFCM_LANCTXSTAT_CTX_MISS_SHIFT 1
-#define I40E_PFCM_LANCTXSTAT_CTX_MISS_MASK I40E_MASK(0x1, I40E_PFCM_LANCTXSTAT_CTX_MISS_SHIFT)
-#define I40E_VFCM_PE_ERRDATA1(_VF) (0x00138800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFCM_PE_ERRDATA1_MAX_INDEX 127
-#define I40E_VFCM_PE_ERRDATA1_ERROR_CODE_SHIFT 0
-#define I40E_VFCM_PE_ERRDATA1_ERROR_CODE_MASK I40E_MASK(0xF, I40E_VFCM_PE_ERRDATA1_ERROR_CODE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA1_Q_TYPE_SHIFT 4
-#define I40E_VFCM_PE_ERRDATA1_Q_TYPE_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRDATA1_Q_TYPE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA1_Q_NUM_SHIFT 8
-#define I40E_VFCM_PE_ERRDATA1_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_VFCM_PE_ERRDATA1_Q_NUM_SHIFT)
-#define I40E_VFCM_PE_ERRINFO1(_VF) (0x00138400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFCM_PE_ERRINFO1_MAX_INDEX 127
-#define I40E_VFCM_PE_ERRINFO1_ERROR_VALID_SHIFT 0
-#define I40E_VFCM_PE_ERRINFO1_ERROR_VALID_MASK I40E_MASK(0x1, I40E_VFCM_PE_ERRINFO1_ERROR_VALID_SHIFT)
-#define I40E_VFCM_PE_ERRINFO1_ERROR_INST_SHIFT 4
-#define I40E_VFCM_PE_ERRINFO1_ERROR_INST_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRINFO1_ERROR_INST_SHIFT)
-#define I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_SHIFT 8
-#define I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_SHIFT 16
-#define I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_SHIFT 24
-#define I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_SHIFT)
-#define I40E_GLDCB_GENC 0x00083044 /* Reset: CORER */
-#define I40E_GLDCB_GENC_PCIRTT_SHIFT 0
-#define I40E_GLDCB_GENC_PCIRTT_MASK I40E_MASK(0xFFFF, I40E_GLDCB_GENC_PCIRTT_SHIFT)
-#define I40E_GLDCB_RUPTI 0x00122618 /* Reset: CORER */
-#define I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_SHIFT 0
-#define I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_SHIFT)
-#define I40E_PRTDCB_FCCFG 0x001E4640 /* Reset: GLOBR */
-#define I40E_PRTDCB_FCCFG_TFCE_SHIFT 3
-#define I40E_PRTDCB_FCCFG_TFCE_MASK I40E_MASK(0x3, I40E_PRTDCB_FCCFG_TFCE_SHIFT)
-#define I40E_PRTDCB_FCRTV 0x001E4600 /* Reset: GLOBR */
-#define I40E_PRTDCB_FCRTV_FC_REFRESH_TH_SHIFT 0
-#define I40E_PRTDCB_FCRTV_FC_REFRESH_TH_MASK I40E_MASK(0xFFFF, I40E_PRTDCB_FCRTV_FC_REFRESH_TH_SHIFT)
-#define I40E_PRTDCB_FCTTVN(_i) (0x001E4580 + ((_i) * 32)) /* _i=0...3 */ /* Reset: GLOBR */
-#define I40E_PRTDCB_FCTTVN_MAX_INDEX 3
-#define I40E_PRTDCB_FCTTVN_TTV_2N_SHIFT 0
-#define I40E_PRTDCB_FCTTVN_TTV_2N_MASK I40E_MASK(0xFFFF, I40E_PRTDCB_FCTTVN_TTV_2N_SHIFT)
-#define I40E_PRTDCB_FCTTVN_TTV_2N_P1_SHIFT 16
-#define I40E_PRTDCB_FCTTVN_TTV_2N_P1_MASK I40E_MASK(0xFFFF, I40E_PRTDCB_FCTTVN_TTV_2N_P1_SHIFT)
 #define I40E_PRTDCB_GENC 0x00083000 /* Reset: CORER */
-#define I40E_PRTDCB_GENC_RESERVED_1_SHIFT 0
-#define I40E_PRTDCB_GENC_RESERVED_1_MASK I40E_MASK(0x3, I40E_PRTDCB_GENC_RESERVED_1_SHIFT)
-#define I40E_PRTDCB_GENC_NUMTC_SHIFT 2
-#define I40E_PRTDCB_GENC_NUMTC_MASK I40E_MASK(0xF, I40E_PRTDCB_GENC_NUMTC_SHIFT)
-#define I40E_PRTDCB_GENC_FCOEUP_SHIFT 6
-#define I40E_PRTDCB_GENC_FCOEUP_MASK I40E_MASK(0x7, I40E_PRTDCB_GENC_FCOEUP_SHIFT)
-#define I40E_PRTDCB_GENC_FCOEUP_VALID_SHIFT 9
-#define I40E_PRTDCB_GENC_FCOEUP_VALID_MASK I40E_MASK(0x1, I40E_PRTDCB_GENC_FCOEUP_VALID_SHIFT)
 #define I40E_PRTDCB_GENC_PFCLDA_SHIFT 16
 #define I40E_PRTDCB_GENC_PFCLDA_MASK I40E_MASK(0xFFFF, I40E_PRTDCB_GENC_PFCLDA_SHIFT)
 #define I40E_PRTDCB_GENS 0x00083020 /* Reset: CORER */
 #define I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT 0
 #define I40E_PRTDCB_GENS_DCBX_STATUS_MASK I40E_MASK(0x7, I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT)
-#define I40E_PRTDCB_MFLCN 0x001E2400 /* Reset: GLOBR */
-#define I40E_PRTDCB_MFLCN_PMCF_SHIFT 0
-#define I40E_PRTDCB_MFLCN_PMCF_MASK I40E_MASK(0x1, I40E_PRTDCB_MFLCN_PMCF_SHIFT)
-#define I40E_PRTDCB_MFLCN_DPF_SHIFT 1
-#define I40E_PRTDCB_MFLCN_DPF_MASK I40E_MASK(0x1, I40E_PRTDCB_MFLCN_DPF_SHIFT)
-#define I40E_PRTDCB_MFLCN_RPFCM_SHIFT 2
-#define I40E_PRTDCB_MFLCN_RPFCM_MASK I40E_MASK(0x1, I40E_PRTDCB_MFLCN_RPFCM_SHIFT)
-#define I40E_PRTDCB_MFLCN_RFCE_SHIFT 3
-#define I40E_PRTDCB_MFLCN_RFCE_MASK I40E_MASK(0x1, I40E_PRTDCB_MFLCN_RFCE_SHIFT)
-#define I40E_PRTDCB_MFLCN_RPFCE_SHIFT 4
-#define I40E_PRTDCB_MFLCN_RPFCE_MASK I40E_MASK(0xFF, I40E_PRTDCB_MFLCN_RPFCE_SHIFT)
-#define I40E_PRTDCB_RETSC 0x001223E0 /* Reset: CORER */
-#define I40E_PRTDCB_RETSC_ETS_MODE_SHIFT 0
-#define I40E_PRTDCB_RETSC_ETS_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSC_ETS_MODE_SHIFT)
-#define I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT 1
-#define I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT)
-#define I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT 2
-#define I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK I40E_MASK(0xF, I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT)
-#define I40E_PRTDCB_RETSC_LLTC_SHIFT 8
-#define I40E_PRTDCB_RETSC_LLTC_MASK I40E_MASK(0xFF, I40E_PRTDCB_RETSC_LLTC_SHIFT)
-#define I40E_PRTDCB_RETSTCC(_i) (0x00122180 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTDCB_RETSTCC_MAX_INDEX 7
-#define I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT 0
-#define I40E_PRTDCB_RETSTCC_BWSHARE_MASK I40E_MASK(0x7F, I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT)
-#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT 30
-#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT)
-#define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT 31
-#define I40E_PRTDCB_RETSTCC_ETSTC_MASK I40E_MASK(0x1u, I40E_PRTDCB_RETSTCC_ETSTC_SHIFT)
-#define I40E_PRTDCB_RPPMC 0x001223A0 /* Reset: CORER */
-#define I40E_PRTDCB_RPPMC_LANRPPM_SHIFT 0
-#define I40E_PRTDCB_RPPMC_LANRPPM_MASK I40E_MASK(0xFF, I40E_PRTDCB_RPPMC_LANRPPM_SHIFT)
-#define I40E_PRTDCB_RPPMC_RDMARPPM_SHIFT 8
-#define I40E_PRTDCB_RPPMC_RDMARPPM_MASK I40E_MASK(0xFF, I40E_PRTDCB_RPPMC_RDMARPPM_SHIFT)
-#define I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT 16
-#define I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK I40E_MASK(0xFF, I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT)
-#define I40E_PRTDCB_RUP 0x001C0B00 /* Reset: CORER */
-#define I40E_PRTDCB_RUP_NOVLANUP_SHIFT 0
-#define I40E_PRTDCB_RUP_NOVLANUP_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP_NOVLANUP_SHIFT)
-#define I40E_PRTDCB_RUP2TC 0x001C09A0 /* Reset: CORER */
-#define I40E_PRTDCB_RUP2TC_UP0TC_SHIFT 0
-#define I40E_PRTDCB_RUP2TC_UP0TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP0TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP1TC_SHIFT 3
-#define I40E_PRTDCB_RUP2TC_UP1TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP1TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP2TC_SHIFT 6
-#define I40E_PRTDCB_RUP2TC_UP2TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP2TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP3TC_SHIFT 9
-#define I40E_PRTDCB_RUP2TC_UP3TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP3TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP4TC_SHIFT 12
-#define I40E_PRTDCB_RUP2TC_UP4TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP4TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP5TC_SHIFT 15
-#define I40E_PRTDCB_RUP2TC_UP5TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP5TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP6TC_SHIFT 18
-#define I40E_PRTDCB_RUP2TC_UP6TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP6TC_SHIFT)
-#define I40E_PRTDCB_RUP2TC_UP7TC_SHIFT 21
-#define I40E_PRTDCB_RUP2TC_UP7TC_MASK I40E_MASK(0x7, I40E_PRTDCB_RUP2TC_UP7TC_SHIFT)
-#define I40E_PRTDCB_RUPTQ(_i) (0x00122400 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTDCB_RUPTQ_MAX_INDEX 7
-#define I40E_PRTDCB_RUPTQ_RXQNUM_SHIFT 0
-#define I40E_PRTDCB_RUPTQ_RXQNUM_MASK I40E_MASK(0x3FFF, I40E_PRTDCB_RUPTQ_RXQNUM_SHIFT)
-#define I40E_PRTDCB_TC2PFC 0x001C0980 /* Reset: CORER */
-#define I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT 0
-#define I40E_PRTDCB_TC2PFC_TC2PFC_MASK I40E_MASK(0xFF, I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT)
-#define I40E_PRTDCB_TCMSTC(_i) (0x000A0040 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTDCB_TCMSTC_MAX_INDEX 7
-#define I40E_PRTDCB_TCMSTC_MSTC_SHIFT 0
-#define I40E_PRTDCB_TCMSTC_MSTC_MASK I40E_MASK(0xFFFFF, I40E_PRTDCB_TCMSTC_MSTC_SHIFT)
-#define I40E_PRTDCB_TCPMC 0x000A21A0 /* Reset: CORER */
-#define I40E_PRTDCB_TCPMC_CPM_SHIFT 0
-#define I40E_PRTDCB_TCPMC_CPM_MASK I40E_MASK(0x1FFF, I40E_PRTDCB_TCPMC_CPM_SHIFT)
-#define I40E_PRTDCB_TCPMC_LLTC_SHIFT 13
-#define I40E_PRTDCB_TCPMC_LLTC_MASK I40E_MASK(0xFF, I40E_PRTDCB_TCPMC_LLTC_SHIFT)
-#define I40E_PRTDCB_TCPMC_TCPM_MODE_SHIFT 30
-#define I40E_PRTDCB_TCPMC_TCPM_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_TCPMC_TCPM_MODE_SHIFT)
-#define I40E_PRTDCB_TCWSTC(_i) (0x000A2040 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTDCB_TCWSTC_MAX_INDEX 7
-#define I40E_PRTDCB_TCWSTC_MSTC_SHIFT 0
-#define I40E_PRTDCB_TCWSTC_MSTC_MASK I40E_MASK(0xFFFFF, I40E_PRTDCB_TCWSTC_MSTC_SHIFT)
-#define I40E_PRTDCB_TDPMC 0x000A0180 /* Reset: CORER */
-#define I40E_PRTDCB_TDPMC_DPM_SHIFT 0
-#define I40E_PRTDCB_TDPMC_DPM_MASK I40E_MASK(0xFF, I40E_PRTDCB_TDPMC_DPM_SHIFT)
-#define I40E_PRTDCB_TDPMC_TCPM_MODE_SHIFT 30
-#define I40E_PRTDCB_TDPMC_TCPM_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_TDPMC_TCPM_MODE_SHIFT)
-#define I40E_PRTDCB_TETSC_TCB 0x000AE060 /* Reset: CORER */
-#define I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_SHIFT 0
-#define I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_MASK I40E_MASK(0x1, I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_SHIFT)
-#define I40E_PRTDCB_TETSC_TCB_LLTC_SHIFT 8
-#define I40E_PRTDCB_TETSC_TCB_LLTC_MASK I40E_MASK(0xFF, I40E_PRTDCB_TETSC_TCB_LLTC_SHIFT)
-#define I40E_PRTDCB_TETSC_TPB 0x00098060 /* Reset: CORER */
-#define I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_SHIFT 0
-#define I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_MASK I40E_MASK(0x1, I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_SHIFT)
-#define I40E_PRTDCB_TETSC_TPB_LLTC_SHIFT 8
-#define I40E_PRTDCB_TETSC_TPB_LLTC_MASK I40E_MASK(0xFF, I40E_PRTDCB_TETSC_TPB_LLTC_SHIFT)
-#define I40E_PRTDCB_TFCS 0x001E4560 /* Reset: GLOBR */
-#define I40E_PRTDCB_TFCS_TXOFF_SHIFT 0
-#define I40E_PRTDCB_TFCS_TXOFF_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF0_SHIFT 8
-#define I40E_PRTDCB_TFCS_TXOFF0_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF0_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF1_SHIFT 9
-#define I40E_PRTDCB_TFCS_TXOFF1_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF1_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF2_SHIFT 10
-#define I40E_PRTDCB_TFCS_TXOFF2_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF2_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF3_SHIFT 11
-#define I40E_PRTDCB_TFCS_TXOFF3_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF3_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF4_SHIFT 12
-#define I40E_PRTDCB_TFCS_TXOFF4_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF4_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF5_SHIFT 13
-#define I40E_PRTDCB_TFCS_TXOFF5_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF5_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF6_SHIFT 14
-#define I40E_PRTDCB_TFCS_TXOFF6_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF6_SHIFT)
-#define I40E_PRTDCB_TFCS_TXOFF7_SHIFT 15
-#define I40E_PRTDCB_TFCS_TXOFF7_MASK I40E_MASK(0x1, I40E_PRTDCB_TFCS_TXOFF7_SHIFT)
-#define I40E_PRTDCB_TPFCTS(_i) (0x001E4660 + ((_i) * 32)) /* _i=0...7 */ /* Reset: GLOBR */
-#define I40E_PRTDCB_TPFCTS_MAX_INDEX 7
-#define I40E_PRTDCB_TPFCTS_PFCTIMER_SHIFT 0
-#define I40E_PRTDCB_TPFCTS_PFCTIMER_MASK I40E_MASK(0x3FFF, I40E_PRTDCB_TPFCTS_PFCTIMER_SHIFT)
-#define I40E_GLFCOE_RCTL 0x00269B94 /* Reset: CORER */
-#define I40E_GLFCOE_RCTL_FCOEVER_SHIFT 0
-#define I40E_GLFCOE_RCTL_FCOEVER_MASK I40E_MASK(0xF, I40E_GLFCOE_RCTL_FCOEVER_SHIFT)
-#define I40E_GLFCOE_RCTL_SAVBAD_SHIFT 4
-#define I40E_GLFCOE_RCTL_SAVBAD_MASK I40E_MASK(0x1, I40E_GLFCOE_RCTL_SAVBAD_SHIFT)
-#define I40E_GLFCOE_RCTL_ICRC_SHIFT 5
-#define I40E_GLFCOE_RCTL_ICRC_MASK I40E_MASK(0x1, I40E_GLFCOE_RCTL_ICRC_SHIFT)
-#define I40E_GLFCOE_RCTL_MAX_SIZE_SHIFT 16
-#define I40E_GLFCOE_RCTL_MAX_SIZE_MASK I40E_MASK(0x3FFF, I40E_GLFCOE_RCTL_MAX_SIZE_SHIFT)
 #define I40E_GL_FWSTS 0x00083048 /* Reset: POR */
-#define I40E_GL_FWSTS_FWS0B_SHIFT 0
-#define I40E_GL_FWSTS_FWS0B_MASK I40E_MASK(0xFF, I40E_GL_FWSTS_FWS0B_SHIFT)
-#define I40E_GL_FWSTS_FWRI_SHIFT 9
-#define I40E_GL_FWSTS_FWRI_MASK I40E_MASK(0x1, I40E_GL_FWSTS_FWRI_SHIFT)
 #define I40E_GL_FWSTS_FWS1B_SHIFT 16
 #define I40E_GL_FWSTS_FWS1B_MASK I40E_MASK(0xFF, I40E_GL_FWSTS_FWS1B_SHIFT)
 #define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0x30, I40E_GL_FWSTS_FWS1B_SHIFT)
@@ -369,500 +49,119 @@
 #define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK I40E_MASK(0x33, I40E_GL_FWSTS_FWS1B_SHIFT)
 #define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0xB, I40E_GL_FWSTS_FWS1B_SHIFT)
 #define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK I40E_MASK(0xC, I40E_GL_FWSTS_FWS1B_SHIFT)
-#define I40E_GLGEN_CLKSTAT 0x000B8184 /* Reset: POR */
-#define I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT 0
-#define I40E_GLGEN_CLKSTAT_CLKMODE_MASK I40E_MASK(0x1, I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT)
-#define I40E_GLGEN_CLKSTAT_U_CLK_SPEED_SHIFT 4
-#define I40E_GLGEN_CLKSTAT_U_CLK_SPEED_MASK I40E_MASK(0x3, I40E_GLGEN_CLKSTAT_U_CLK_SPEED_SHIFT)
-#define I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_SHIFT 8
-#define I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_MASK I40E_MASK(0x7, I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_SHIFT)
-#define I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_SHIFT 12
-#define I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_MASK I40E_MASK(0x7, I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_SHIFT)
-#define I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_SHIFT 16
-#define I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_MASK I40E_MASK(0x7, I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_SHIFT)
-#define I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_SHIFT 20
-#define I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_MASK I40E_MASK(0x7, I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_SHIFT)
 #define I40E_GLGEN_GPIO_CTL(_i) (0x00088100 + ((_i) * 4)) /* _i=0...29 */ /* Reset: POR */
 #define I40E_GLGEN_GPIO_CTL_MAX_INDEX 29
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT 0
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK I40E_MASK(0x3, I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT 3
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT 4
-#define I40E_GLGEN_GPIO_CTL_PIN_DIR_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT 5
-#define I40E_GLGEN_GPIO_CTL_TRI_CTL_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT 6
-#define I40E_GLGEN_GPIO_CTL_OUT_CTL_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT 7
 #define I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK I40E_MASK(0x7, I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_LED_INVRT_SHIFT 10
-#define I40E_GLGEN_GPIO_CTL_LED_INVRT_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_LED_INVRT_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT 11
-#define I40E_GLGEN_GPIO_CTL_LED_BLINK_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT 12
 #define I40E_GLGEN_GPIO_CTL_LED_MODE_MASK I40E_MASK(0x1F, I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_INT_MODE_SHIFT 17
-#define I40E_GLGEN_GPIO_CTL_INT_MODE_MASK I40E_MASK(0x3, I40E_GLGEN_GPIO_CTL_INT_MODE_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT 19
-#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT 20
-#define I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_MASK I40E_MASK(0x3F, I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT)
-#define I40E_GLGEN_GPIO_CTL_PRT_BIT_MAP_SHIFT 26
-#define I40E_GLGEN_GPIO_CTL_PRT_BIT_MAP_MASK I40E_MASK(0xF, I40E_GLGEN_GPIO_CTL_PRT_BIT_MAP_SHIFT)
-#define I40E_GLGEN_GPIO_SET 0x00088184 /* Reset: POR */
-#define I40E_GLGEN_GPIO_SET_GPIO_INDX_SHIFT 0
-#define I40E_GLGEN_GPIO_SET_GPIO_INDX_MASK I40E_MASK(0x1F, I40E_GLGEN_GPIO_SET_GPIO_INDX_SHIFT)
-#define I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT 5
-#define I40E_GLGEN_GPIO_SET_SDP_DATA_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT)
-#define I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT 6
-#define I40E_GLGEN_GPIO_SET_DRIVE_SDP_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT)
-#define I40E_GLGEN_GPIO_STAT 0x0008817C /* Reset: POR */
-#define I40E_GLGEN_GPIO_STAT_GPIO_VALUE_SHIFT 0
-#define I40E_GLGEN_GPIO_STAT_GPIO_VALUE_MASK I40E_MASK(0x3FFFFFFF, I40E_GLGEN_GPIO_STAT_GPIO_VALUE_SHIFT)
-#define I40E_GLGEN_GPIO_TRANSIT 0x00088180 /* Reset: POR */
-#define I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_SHIFT 0
-#define I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_MASK I40E_MASK(0x3FFFFFFF, I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_SHIFT)
-#define I40E_GLGEN_I2CCMD(_i) (0x000881E0 + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_I2CCMD_MAX_INDEX 3
-#define I40E_GLGEN_I2CCMD_DATA_SHIFT 0
-#define I40E_GLGEN_I2CCMD_DATA_MASK I40E_MASK(0xFFFF, I40E_GLGEN_I2CCMD_DATA_SHIFT)
-#define I40E_GLGEN_I2CCMD_REGADD_SHIFT 16
-#define I40E_GLGEN_I2CCMD_REGADD_MASK I40E_MASK(0xFF, I40E_GLGEN_I2CCMD_REGADD_SHIFT)
-#define I40E_GLGEN_I2CCMD_PHYADD_SHIFT 24
-#define I40E_GLGEN_I2CCMD_PHYADD_MASK I40E_MASK(0x7, I40E_GLGEN_I2CCMD_PHYADD_SHIFT)
-#define I40E_GLGEN_I2CCMD_OP_SHIFT 27
-#define I40E_GLGEN_I2CCMD_OP_MASK I40E_MASK(0x1, I40E_GLGEN_I2CCMD_OP_SHIFT)
-#define I40E_GLGEN_I2CCMD_RESET_SHIFT 28
-#define I40E_GLGEN_I2CCMD_RESET_MASK I40E_MASK(0x1, I40E_GLGEN_I2CCMD_RESET_SHIFT)
-#define I40E_GLGEN_I2CCMD_R_SHIFT 29
-#define I40E_GLGEN_I2CCMD_R_MASK I40E_MASK(0x1, I40E_GLGEN_I2CCMD_R_SHIFT)
-#define I40E_GLGEN_I2CCMD_E_SHIFT 31
-#define I40E_GLGEN_I2CCMD_E_MASK I40E_MASK(0x1, I40E_GLGEN_I2CCMD_E_SHIFT)
-#define I40E_GLGEN_I2CPARAMS(_i) (0x000881AC + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_I2CPARAMS_MAX_INDEX 3
-#define I40E_GLGEN_I2CPARAMS_WRITE_TIME_SHIFT 0
-#define I40E_GLGEN_I2CPARAMS_WRITE_TIME_MASK I40E_MASK(0x1F, I40E_GLGEN_I2CPARAMS_WRITE_TIME_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_READ_TIME_SHIFT 5
-#define I40E_GLGEN_I2CPARAMS_READ_TIME_MASK I40E_MASK(0x7, I40E_GLGEN_I2CPARAMS_READ_TIME_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_I2CBB_EN_SHIFT 8
-#define I40E_GLGEN_I2CPARAMS_I2CBB_EN_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_I2CBB_EN_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_CLK_SHIFT 9
-#define I40E_GLGEN_I2CPARAMS_CLK_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_CLK_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_DATA_OUT_SHIFT 10
-#define I40E_GLGEN_I2CPARAMS_DATA_OUT_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_DATA_OUT_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_DATA_OE_N_SHIFT 11
-#define I40E_GLGEN_I2CPARAMS_DATA_OE_N_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_DATA_OE_N_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_DATA_IN_SHIFT 12
-#define I40E_GLGEN_I2CPARAMS_DATA_IN_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_DATA_IN_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_CLK_OE_N_SHIFT 13
-#define I40E_GLGEN_I2CPARAMS_CLK_OE_N_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_CLK_OE_N_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_CLK_IN_SHIFT 14
-#define I40E_GLGEN_I2CPARAMS_CLK_IN_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_CLK_IN_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_SHIFT 15
-#define I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_SHIFT)
-#define I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_SHIFT 31
-#define I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_MASK I40E_MASK(0x1, I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_SHIFT)
-#define I40E_GLGEN_LED_CTL 0x00088178 /* Reset: POR */
-#define I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_SHIFT 0
-#define I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_MASK I40E_MASK(0x1, I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_SHIFT)
-#define I40E_GLGEN_MDIO_CTRL(_i) (0x000881D0 + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_MDIO_CTRL_MAX_INDEX 3
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_SHIFT 0
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_MASK I40E_MASK(0x1FFFF, I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_SHIFT)
-#define I40E_GLGEN_MDIO_CTRL_CONTMDC_SHIFT 17
-#define I40E_GLGEN_MDIO_CTRL_CONTMDC_MASK I40E_MASK(0x1, I40E_GLGEN_MDIO_CTRL_CONTMDC_SHIFT)
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_SHIFT 18
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_MASK I40E_MASK(0x7FF, I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_SHIFT)
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD0_SHIFT 29
-#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD0_MASK I40E_MASK(0x7, I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD0_SHIFT)
 #define I40E_GLGEN_MDIO_I2C_SEL(_i) (0x000881C0 + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_MDIO_I2C_SEL_MAX_INDEX 3
-#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_SHIFT 0
-#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_MASK I40E_MASK(0x1, I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_SHIFT 1
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_MASK I40E_MASK(0xF, I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_SHIFT 5
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_MASK I40E_MASK(0x1F, I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_SHIFT 10
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_MASK I40E_MASK(0x1F, I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_SHIFT 15
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_MASK I40E_MASK(0x1F, I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_SHIFT 20
-#define I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_MASK I40E_MASK(0x1F, I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_SHIFT 25
-#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_MASK I40E_MASK(0xF, I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_SHIFT)
-#define I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_SHIFT 31
-#define I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_MASK I40E_MASK(0x1, I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_SHIFT)
 #define I40E_GLGEN_MSCA(_i) (0x0008818C + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_MSCA_MAX_INDEX 3
 #define I40E_GLGEN_MSCA_MDIADD_SHIFT 0
-#define I40E_GLGEN_MSCA_MDIADD_MASK I40E_MASK(0xFFFF, I40E_GLGEN_MSCA_MDIADD_SHIFT)
 #define I40E_GLGEN_MSCA_DEVADD_SHIFT 16
-#define I40E_GLGEN_MSCA_DEVADD_MASK I40E_MASK(0x1F, I40E_GLGEN_MSCA_DEVADD_SHIFT)
 #define I40E_GLGEN_MSCA_PHYADD_SHIFT 21
-#define I40E_GLGEN_MSCA_PHYADD_MASK I40E_MASK(0x1F, I40E_GLGEN_MSCA_PHYADD_SHIFT)
 #define I40E_GLGEN_MSCA_OPCODE_SHIFT 26
-#define I40E_GLGEN_MSCA_OPCODE_MASK I40E_MASK(0x3, I40E_GLGEN_MSCA_OPCODE_SHIFT)
 #define I40E_GLGEN_MSCA_STCODE_SHIFT 28
-#define I40E_GLGEN_MSCA_STCODE_MASK I40E_MASK(0x3, I40E_GLGEN_MSCA_STCODE_SHIFT)
 #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30
 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT)
 #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31
 #define I40E_GLGEN_MSCA_MDIINPROGEN_MASK I40E_MASK(0x1u, I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT)
 #define I40E_GLGEN_MSRWD(_i) (0x0008819C + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_GLGEN_MSRWD_MAX_INDEX 3
 #define I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT 0
-#define I40E_GLGEN_MSRWD_MDIWRDATA_MASK I40E_MASK(0xFFFF, I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT)
 #define I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT 16
 #define I40E_GLGEN_MSRWD_MDIRDDATA_MASK I40E_MASK(0xFFFF, I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT)
-#define I40E_GLGEN_PCIFCNCNT 0x001C0AB4 /* Reset: PCIR */
-#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT 0
-#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_MASK I40E_MASK(0x1F, I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT)
-#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT 16
-#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_MASK I40E_MASK(0xFF, I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT)
 #define I40E_GLGEN_RSTAT 0x000B8188 /* Reset: POR */
 #define I40E_GLGEN_RSTAT_DEVSTATE_SHIFT 0
 #define I40E_GLGEN_RSTAT_DEVSTATE_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_DEVSTATE_SHIFT)
 #define I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT 2
 #define I40E_GLGEN_RSTAT_RESET_TYPE_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT)
-#define I40E_GLGEN_RSTAT_CORERCNT_SHIFT 4
-#define I40E_GLGEN_RSTAT_CORERCNT_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_CORERCNT_SHIFT)
-#define I40E_GLGEN_RSTAT_GLOBRCNT_SHIFT 6
-#define I40E_GLGEN_RSTAT_GLOBRCNT_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_GLOBRCNT_SHIFT)
-#define I40E_GLGEN_RSTAT_EMPRCNT_SHIFT 8
-#define I40E_GLGEN_RSTAT_EMPRCNT_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_EMPRCNT_SHIFT)
-#define I40E_GLGEN_RSTAT_TIME_TO_RST_SHIFT 10
-#define I40E_GLGEN_RSTAT_TIME_TO_RST_MASK I40E_MASK(0x3F, I40E_GLGEN_RSTAT_TIME_TO_RST_SHIFT)
 #define I40E_GLGEN_RSTCTL 0x000B8180 /* Reset: POR */
 #define I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT 0
 #define I40E_GLGEN_RSTCTL_GRSTDEL_MASK I40E_MASK(0x3F, I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT)
-#define I40E_GLGEN_RSTCTL_ECC_RST_ENA_SHIFT 8
-#define I40E_GLGEN_RSTCTL_ECC_RST_ENA_MASK I40E_MASK(0x1, I40E_GLGEN_RSTCTL_ECC_RST_ENA_SHIFT)
 #define I40E_GLGEN_RTRIG 0x000B8190 /* Reset: CORER */
 #define I40E_GLGEN_RTRIG_CORER_SHIFT 0
 #define I40E_GLGEN_RTRIG_CORER_MASK I40E_MASK(0x1, I40E_GLGEN_RTRIG_CORER_SHIFT)
 #define I40E_GLGEN_RTRIG_GLOBR_SHIFT 1
 #define I40E_GLGEN_RTRIG_GLOBR_MASK I40E_MASK(0x1, I40E_GLGEN_RTRIG_GLOBR_SHIFT)
-#define I40E_GLGEN_RTRIG_EMPFWR_SHIFT 2
-#define I40E_GLGEN_RTRIG_EMPFWR_MASK I40E_MASK(0x1, I40E_GLGEN_RTRIG_EMPFWR_SHIFT)
 #define I40E_GLGEN_STAT 0x000B612C /* Reset: POR */
-#define I40E_GLGEN_STAT_HWRSVD0_SHIFT 0
-#define I40E_GLGEN_STAT_HWRSVD0_MASK I40E_MASK(0x3, I40E_GLGEN_STAT_HWRSVD0_SHIFT)
-#define I40E_GLGEN_STAT_DCBEN_SHIFT 2
-#define I40E_GLGEN_STAT_DCBEN_MASK I40E_MASK(0x1, I40E_GLGEN_STAT_DCBEN_SHIFT)
-#define I40E_GLGEN_STAT_VTEN_SHIFT 3
-#define I40E_GLGEN_STAT_VTEN_MASK I40E_MASK(0x1, I40E_GLGEN_STAT_VTEN_SHIFT)
-#define I40E_GLGEN_STAT_FCOEN_SHIFT 4
-#define I40E_GLGEN_STAT_FCOEN_MASK I40E_MASK(0x1, I40E_GLGEN_STAT_FCOEN_SHIFT)
-#define I40E_GLGEN_STAT_EVBEN_SHIFT 5
-#define I40E_GLGEN_STAT_EVBEN_MASK I40E_MASK(0x1, I40E_GLGEN_STAT_EVBEN_SHIFT)
-#define I40E_GLGEN_STAT_HWRSVD1_SHIFT 6
-#define I40E_GLGEN_STAT_HWRSVD1_MASK I40E_MASK(0x3, I40E_GLGEN_STAT_HWRSVD1_SHIFT)
 #define I40E_GLGEN_VFLRSTAT(_i) (0x00092600 + ((_i) * 4)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLGEN_VFLRSTAT_MAX_INDEX 3
-#define I40E_GLGEN_VFLRSTAT_VFLRE_SHIFT 0
-#define I40E_GLGEN_VFLRSTAT_VFLRE_MASK I40E_MASK(0xFFFFFFFF, I40E_GLGEN_VFLRSTAT_VFLRE_SHIFT)
 #define I40E_GLVFGEN_TIMER 0x000881BC /* Reset: CORER */
-#define I40E_GLVFGEN_TIMER_GTIME_SHIFT 0
-#define I40E_GLVFGEN_TIMER_GTIME_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVFGEN_TIMER_GTIME_SHIFT)
 #define I40E_PFGEN_CTRL 0x00092400 /* Reset: PFR */
 #define I40E_PFGEN_CTRL_PFSWR_SHIFT 0
 #define I40E_PFGEN_CTRL_PFSWR_MASK I40E_MASK(0x1, I40E_PFGEN_CTRL_PFSWR_SHIFT)
-#define I40E_PFGEN_DRUN 0x00092500 /* Reset: CORER */
-#define I40E_PFGEN_DRUN_DRVUNLD_SHIFT 0
-#define I40E_PFGEN_DRUN_DRVUNLD_MASK I40E_MASK(0x1, I40E_PFGEN_DRUN_DRVUNLD_SHIFT)
 #define I40E_PFGEN_PORTNUM 0x001C0480 /* Reset: CORER */
 #define I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT 0
 #define I40E_PFGEN_PORTNUM_PORT_NUM_MASK I40E_MASK(0x3, I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT)
-#define I40E_PFGEN_STATE 0x00088000 /* Reset: CORER */
-#define I40E_PFGEN_STATE_RESERVED_0_SHIFT 0
-#define I40E_PFGEN_STATE_RESERVED_0_MASK I40E_MASK(0x1, I40E_PFGEN_STATE_RESERVED_0_SHIFT)
-#define I40E_PFGEN_STATE_PFFCEN_SHIFT 1
-#define I40E_PFGEN_STATE_PFFCEN_MASK I40E_MASK(0x1, I40E_PFGEN_STATE_PFFCEN_SHIFT)
-#define I40E_PFGEN_STATE_PFLINKEN_SHIFT 2
-#define I40E_PFGEN_STATE_PFLINKEN_MASK I40E_MASK(0x1, I40E_PFGEN_STATE_PFLINKEN_SHIFT)
-#define I40E_PFGEN_STATE_PFSCEN_SHIFT 3
-#define I40E_PFGEN_STATE_PFSCEN_MASK I40E_MASK(0x1, I40E_PFGEN_STATE_PFSCEN_SHIFT)
 #define I40E_PRTGEN_CNF 0x000B8120 /* Reset: POR */
 #define I40E_PRTGEN_CNF_PORT_DIS_SHIFT 0
 #define I40E_PRTGEN_CNF_PORT_DIS_MASK I40E_MASK(0x1, I40E_PRTGEN_CNF_PORT_DIS_SHIFT)
-#define I40E_PRTGEN_CNF_ALLOW_PORT_DIS_SHIFT 1
-#define I40E_PRTGEN_CNF_ALLOW_PORT_DIS_MASK I40E_MASK(0x1, I40E_PRTGEN_CNF_ALLOW_PORT_DIS_SHIFT)
-#define I40E_PRTGEN_CNF_EMP_PORT_DIS_SHIFT 2
-#define I40E_PRTGEN_CNF_EMP_PORT_DIS_MASK I40E_MASK(0x1, I40E_PRTGEN_CNF_EMP_PORT_DIS_SHIFT)
-#define I40E_PRTGEN_CNF2 0x000B8160 /* Reset: POR */
-#define I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_SHIFT 0
-#define I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_MASK I40E_MASK(0x1, I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_SHIFT)
 #define I40E_PRTGEN_STATUS 0x000B8100 /* Reset: POR */
-#define I40E_PRTGEN_STATUS_PORT_VALID_SHIFT 0
-#define I40E_PRTGEN_STATUS_PORT_VALID_MASK I40E_MASK(0x1, I40E_PRTGEN_STATUS_PORT_VALID_SHIFT)
-#define I40E_PRTGEN_STATUS_PORT_ACTIVE_SHIFT 1
-#define I40E_PRTGEN_STATUS_PORT_ACTIVE_MASK I40E_MASK(0x1, I40E_PRTGEN_STATUS_PORT_ACTIVE_SHIFT)
 #define I40E_VFGEN_RSTAT1(_VF) (0x00074400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFGEN_RSTAT1_MAX_INDEX 127
-#define I40E_VFGEN_RSTAT1_VFR_STATE_SHIFT 0
-#define I40E_VFGEN_RSTAT1_VFR_STATE_MASK I40E_MASK(0x3, I40E_VFGEN_RSTAT1_VFR_STATE_SHIFT)
 #define I40E_VPGEN_VFRSTAT(_VF) (0x00091C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VPGEN_VFRSTAT_MAX_INDEX 127
 #define I40E_VPGEN_VFRSTAT_VFRD_SHIFT 0
 #define I40E_VPGEN_VFRSTAT_VFRD_MASK I40E_MASK(0x1, I40E_VPGEN_VFRSTAT_VFRD_SHIFT)
 #define I40E_VPGEN_VFRTRIG(_VF) (0x00091800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VPGEN_VFRTRIG_MAX_INDEX 127
 #define I40E_VPGEN_VFRTRIG_VFSWR_SHIFT 0
 #define I40E_VPGEN_VFRTRIG_VFSWR_MASK I40E_MASK(0x1, I40E_VPGEN_VFRTRIG_VFSWR_SHIFT)
-#define I40E_VSIGEN_RSTAT(_VSI) (0x00090800 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_VSIGEN_RSTAT_MAX_INDEX 383
-#define I40E_VSIGEN_RSTAT_VMRD_SHIFT 0
-#define I40E_VSIGEN_RSTAT_VMRD_MASK I40E_MASK(0x1, I40E_VSIGEN_RSTAT_VMRD_SHIFT)
-#define I40E_VSIGEN_RTRIG(_VSI) (0x00090000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_VSIGEN_RTRIG_MAX_INDEX 383
-#define I40E_VSIGEN_RTRIG_VMSWR_SHIFT 0
-#define I40E_VSIGEN_RTRIG_VMSWR_MASK I40E_MASK(0x1, I40E_VSIGEN_RTRIG_VMSWR_SHIFT)
 #define I40E_GLHMC_FCOEDDPBASE(_i) (0x000C6600 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FCOEDDPBASE_MAX_INDEX 15
 #define I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_SHIFT 0
 #define I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_SHIFT)
 #define I40E_GLHMC_FCOEDDPCNT(_i) (0x000C6700 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FCOEDDPCNT_MAX_INDEX 15
-#define I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_SHIFT 0
-#define I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_MASK I40E_MASK(0xFFFFF, I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_SHIFT)
 #define I40E_GLHMC_FCOEDDPOBJSZ 0x000C2010 /* Reset: CORER */
-#define I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_SHIFT 0
-#define I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_SHIFT)
 #define I40E_GLHMC_FCOEFBASE(_i) (0x000C6800 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FCOEFBASE_MAX_INDEX 15
 #define I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_SHIFT 0
 #define I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_SHIFT)
 #define I40E_GLHMC_FCOEFCNT(_i) (0x000C6900 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FCOEFCNT_MAX_INDEX 15
-#define I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_SHIFT 0
-#define I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_MASK I40E_MASK(0x7FFFFF, I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_SHIFT)
 #define I40E_GLHMC_FCOEFMAX 0x000C20D0 /* Reset: CORER */
 #define I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT 0
 #define I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK I40E_MASK(0xFFFF, I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT)
 #define I40E_GLHMC_FCOEFOBJSZ 0x000C2018 /* Reset: CORER */
-#define I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_SHIFT 0
-#define I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_SHIFT)
 #define I40E_GLHMC_FCOEMAX 0x000C2014 /* Reset: CORER */
-#define I40E_GLHMC_FCOEMAX_PMFCOEMAX_SHIFT 0
-#define I40E_GLHMC_FCOEMAX_PMFCOEMAX_MASK I40E_MASK(0x1FFF, I40E_GLHMC_FCOEMAX_PMFCOEMAX_SHIFT)
-#define I40E_GLHMC_FSIAVBASE(_i) (0x000C5600 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FSIAVBASE_MAX_INDEX 15
-#define I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_SHIFT 0
-#define I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_SHIFT)
-#define I40E_GLHMC_FSIAVCNT(_i) (0x000C5700 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FSIAVCNT_MAX_INDEX 15
-#define I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_SHIFT 0
-#define I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_SHIFT)
-#define I40E_GLHMC_FSIAVCNT_RSVD_SHIFT 29
-#define I40E_GLHMC_FSIAVCNT_RSVD_MASK I40E_MASK(0x7, I40E_GLHMC_FSIAVCNT_RSVD_SHIFT)
-#define I40E_GLHMC_FSIAVMAX 0x000C2068 /* Reset: CORER */
-#define I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_SHIFT 0
-#define I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_MASK I40E_MASK(0x1FFFF, I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_SHIFT)
-#define I40E_GLHMC_FSIAVOBJSZ 0x000C2064 /* Reset: CORER */
-#define I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_SHIFT 0
-#define I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_SHIFT)
-#define I40E_GLHMC_FSIMCBASE(_i) (0x000C6000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FSIMCBASE_MAX_INDEX 15
-#define I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_SHIFT 0
-#define I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_SHIFT)
-#define I40E_GLHMC_FSIMCCNT(_i) (0x000C6100 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_FSIMCCNT_MAX_INDEX 15
-#define I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_SHIFT 0
-#define I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_SHIFT)
-#define I40E_GLHMC_FSIMCMAX 0x000C2060 /* Reset: CORER */
-#define I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_SHIFT 0
-#define I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_MASK I40E_MASK(0x3FFF, I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_SHIFT)
-#define I40E_GLHMC_FSIMCOBJSZ 0x000C205c /* Reset: CORER */
-#define I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_SHIFT 0
-#define I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_SHIFT)
 #define I40E_GLHMC_LANQMAX 0x000C2008 /* Reset: CORER */
-#define I40E_GLHMC_LANQMAX_PMLANQMAX_SHIFT 0
-#define I40E_GLHMC_LANQMAX_PMLANQMAX_MASK I40E_MASK(0x7FF, I40E_GLHMC_LANQMAX_PMLANQMAX_SHIFT)
 #define I40E_GLHMC_LANRXBASE(_i) (0x000C6400 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_LANRXBASE_MAX_INDEX 15
 #define I40E_GLHMC_LANRXBASE_FPMLANRXBASE_SHIFT 0
 #define I40E_GLHMC_LANRXBASE_FPMLANRXBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_LANRXBASE_FPMLANRXBASE_SHIFT)
 #define I40E_GLHMC_LANRXCNT(_i) (0x000C6500 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_LANRXCNT_MAX_INDEX 15
-#define I40E_GLHMC_LANRXCNT_FPMLANRXCNT_SHIFT 0
-#define I40E_GLHMC_LANRXCNT_FPMLANRXCNT_MASK I40E_MASK(0x7FF, I40E_GLHMC_LANRXCNT_FPMLANRXCNT_SHIFT)
 #define I40E_GLHMC_LANRXOBJSZ 0x000C200c /* Reset: CORER */
-#define I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_SHIFT 0
-#define I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_SHIFT)
 #define I40E_GLHMC_LANTXBASE(_i) (0x000C6200 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_LANTXBASE_MAX_INDEX 15
 #define I40E_GLHMC_LANTXBASE_FPMLANTXBASE_SHIFT 0
 #define I40E_GLHMC_LANTXBASE_FPMLANTXBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_LANTXBASE_FPMLANTXBASE_SHIFT)
-#define I40E_GLHMC_LANTXBASE_RSVD_SHIFT 24
-#define I40E_GLHMC_LANTXBASE_RSVD_MASK I40E_MASK(0xFF, I40E_GLHMC_LANTXBASE_RSVD_SHIFT)
 #define I40E_GLHMC_LANTXCNT(_i) (0x000C6300 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_LANTXCNT_MAX_INDEX 15
-#define I40E_GLHMC_LANTXCNT_FPMLANTXCNT_SHIFT 0
-#define I40E_GLHMC_LANTXCNT_FPMLANTXCNT_MASK I40E_MASK(0x7FF, I40E_GLHMC_LANTXCNT_FPMLANTXCNT_SHIFT)
 #define I40E_GLHMC_LANTXOBJSZ 0x000C2004 /* Reset: CORER */
-#define I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_SHIFT 0
-#define I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_SHIFT)
-#define I40E_GLHMC_PFASSIGN(_i) (0x000C0c00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PFASSIGN_MAX_INDEX 15
-#define I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_SHIFT 0
-#define I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_MASK I40E_MASK(0xF, I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_SHIFT)
-#define I40E_GLHMC_SDPART(_i) (0x000C0800 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_SDPART_MAX_INDEX 15
-#define I40E_GLHMC_SDPART_PMSDBASE_SHIFT 0
-#define I40E_GLHMC_SDPART_PMSDBASE_MASK I40E_MASK(0xFFF, I40E_GLHMC_SDPART_PMSDBASE_SHIFT)
-#define I40E_GLHMC_SDPART_PMSDSIZE_SHIFT 16
-#define I40E_GLHMC_SDPART_PMSDSIZE_MASK I40E_MASK(0x1FFF, I40E_GLHMC_SDPART_PMSDSIZE_SHIFT)
 #define I40E_PFHMC_ERRORDATA 0x000C0500 /* Reset: PFR */
-#define I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_SHIFT 0
-#define I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_MASK I40E_MASK(0x3FFFFFFF, I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_SHIFT)
 #define I40E_PFHMC_ERRORINFO 0x000C0400 /* Reset: PFR */
-#define I40E_PFHMC_ERRORINFO_PMF_INDEX_SHIFT 0
-#define I40E_PFHMC_ERRORINFO_PMF_INDEX_MASK I40E_MASK(0x1F, I40E_PFHMC_ERRORINFO_PMF_INDEX_SHIFT)
-#define I40E_PFHMC_ERRORINFO_PMF_ISVF_SHIFT 7
-#define I40E_PFHMC_ERRORINFO_PMF_ISVF_MASK I40E_MASK(0x1, I40E_PFHMC_ERRORINFO_PMF_ISVF_SHIFT)
-#define I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_SHIFT 8
-#define I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_MASK I40E_MASK(0xF, I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_SHIFT)
-#define I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_SHIFT 16
-#define I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_MASK I40E_MASK(0x1F, I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_SHIFT)
-#define I40E_PFHMC_ERRORINFO_ERROR_DETECTED_SHIFT 31
-#define I40E_PFHMC_ERRORINFO_ERROR_DETECTED_MASK I40E_MASK(0x1, I40E_PFHMC_ERRORINFO_ERROR_DETECTED_SHIFT)
 #define I40E_PFHMC_PDINV 0x000C0300 /* Reset: PFR */
 #define I40E_PFHMC_PDINV_PMSDIDX_SHIFT 0
-#define I40E_PFHMC_PDINV_PMSDIDX_MASK I40E_MASK(0xFFF, I40E_PFHMC_PDINV_PMSDIDX_SHIFT)
 #define I40E_PFHMC_PDINV_PMPDIDX_SHIFT 16
-#define I40E_PFHMC_PDINV_PMPDIDX_MASK I40E_MASK(0x1FF, I40E_PFHMC_PDINV_PMPDIDX_SHIFT)
 #define I40E_PFHMC_SDCMD 0x000C0000 /* Reset: PFR */
-#define I40E_PFHMC_SDCMD_PMSDIDX_SHIFT 0
-#define I40E_PFHMC_SDCMD_PMSDIDX_MASK I40E_MASK(0xFFF, I40E_PFHMC_SDCMD_PMSDIDX_SHIFT)
 #define I40E_PFHMC_SDCMD_PMSDWR_SHIFT 31
-#define I40E_PFHMC_SDCMD_PMSDWR_MASK I40E_MASK(0x1, I40E_PFHMC_SDCMD_PMSDWR_SHIFT)
 #define I40E_PFHMC_SDDATAHIGH 0x000C0200 /* Reset: PFR */
-#define I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_SHIFT 0
-#define I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_SHIFT)
 #define I40E_PFHMC_SDDATALOW 0x000C0100 /* Reset: PFR */
 #define I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT 0
-#define I40E_PFHMC_SDDATALOW_PMSDVALID_MASK I40E_MASK(0x1, I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT)
 #define I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT 1
-#define I40E_PFHMC_SDDATALOW_PMSDTYPE_MASK I40E_MASK(0x1, I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT)
 #define I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT 2
-#define I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_MASK I40E_MASK(0x3FF, I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT)
-#define I40E_PFHMC_SDDATALOW_PMSDDATALOW_SHIFT 12
-#define I40E_PFHMC_SDDATALOW_PMSDDATALOW_MASK I40E_MASK(0xFFFFF, I40E_PFHMC_SDDATALOW_PMSDDATALOW_SHIFT)
-#define I40E_GL_GP_FUSE(_i) (0x0009400C + ((_i) * 4)) /* _i=0...28 */ /* Reset: POR */
-#define I40E_GL_GP_FUSE_MAX_INDEX 28
-#define I40E_GL_GP_FUSE_GL_GP_FUSE_SHIFT 0
-#define I40E_GL_GP_FUSE_GL_GP_FUSE_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_GP_FUSE_GL_GP_FUSE_SHIFT)
-#define I40E_GL_UFUSE 0x00094008 /* Reset: POR */
-#define I40E_GL_UFUSE_FOUR_PORT_ENABLE_SHIFT 1
-#define I40E_GL_UFUSE_FOUR_PORT_ENABLE_MASK I40E_MASK(0x1, I40E_GL_UFUSE_FOUR_PORT_ENABLE_SHIFT)
-#define I40E_GL_UFUSE_NIC_ID_SHIFT 2
-#define I40E_GL_UFUSE_NIC_ID_MASK I40E_MASK(0x1, I40E_GL_UFUSE_NIC_ID_SHIFT)
-#define I40E_GL_UFUSE_ULT_LOCKOUT_SHIFT 10
-#define I40E_GL_UFUSE_ULT_LOCKOUT_MASK I40E_MASK(0x1, I40E_GL_UFUSE_ULT_LOCKOUT_SHIFT)
-#define I40E_GL_UFUSE_CLS_LOCKOUT_SHIFT 11
-#define I40E_GL_UFUSE_CLS_LOCKOUT_MASK I40E_MASK(0x1, I40E_GL_UFUSE_CLS_LOCKOUT_SHIFT)
-#define I40E_EMPINT_GPIO_ENA 0x00088188 /* Reset: POR */
-#define I40E_EMPINT_GPIO_ENA_GPIO0_ENA_SHIFT 0
-#define I40E_EMPINT_GPIO_ENA_GPIO0_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO0_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO1_ENA_SHIFT 1
-#define I40E_EMPINT_GPIO_ENA_GPIO1_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO1_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO2_ENA_SHIFT 2
-#define I40E_EMPINT_GPIO_ENA_GPIO2_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO2_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO3_ENA_SHIFT 3
-#define I40E_EMPINT_GPIO_ENA_GPIO3_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO3_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO4_ENA_SHIFT 4
-#define I40E_EMPINT_GPIO_ENA_GPIO4_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO4_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO5_ENA_SHIFT 5
-#define I40E_EMPINT_GPIO_ENA_GPIO5_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO5_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO6_ENA_SHIFT 6
-#define I40E_EMPINT_GPIO_ENA_GPIO6_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO6_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO7_ENA_SHIFT 7
-#define I40E_EMPINT_GPIO_ENA_GPIO7_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO7_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO8_ENA_SHIFT 8
-#define I40E_EMPINT_GPIO_ENA_GPIO8_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO8_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO9_ENA_SHIFT 9
-#define I40E_EMPINT_GPIO_ENA_GPIO9_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO9_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO10_ENA_SHIFT 10
-#define I40E_EMPINT_GPIO_ENA_GPIO10_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO10_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO11_ENA_SHIFT 11
-#define I40E_EMPINT_GPIO_ENA_GPIO11_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO11_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO12_ENA_SHIFT 12
-#define I40E_EMPINT_GPIO_ENA_GPIO12_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO12_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO13_ENA_SHIFT 13
-#define I40E_EMPINT_GPIO_ENA_GPIO13_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO13_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO14_ENA_SHIFT 14
-#define I40E_EMPINT_GPIO_ENA_GPIO14_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO14_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO15_ENA_SHIFT 15
-#define I40E_EMPINT_GPIO_ENA_GPIO15_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO15_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO16_ENA_SHIFT 16
-#define I40E_EMPINT_GPIO_ENA_GPIO16_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO16_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO17_ENA_SHIFT 17
-#define I40E_EMPINT_GPIO_ENA_GPIO17_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO17_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO18_ENA_SHIFT 18
-#define I40E_EMPINT_GPIO_ENA_GPIO18_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO18_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO19_ENA_SHIFT 19
-#define I40E_EMPINT_GPIO_ENA_GPIO19_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO19_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO20_ENA_SHIFT 20
-#define I40E_EMPINT_GPIO_ENA_GPIO20_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO20_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO21_ENA_SHIFT 21
-#define I40E_EMPINT_GPIO_ENA_GPIO21_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO21_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO22_ENA_SHIFT 22
-#define I40E_EMPINT_GPIO_ENA_GPIO22_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO22_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO23_ENA_SHIFT 23
-#define I40E_EMPINT_GPIO_ENA_GPIO23_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO23_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO24_ENA_SHIFT 24
-#define I40E_EMPINT_GPIO_ENA_GPIO24_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO24_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO25_ENA_SHIFT 25
-#define I40E_EMPINT_GPIO_ENA_GPIO25_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO25_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO26_ENA_SHIFT 26
-#define I40E_EMPINT_GPIO_ENA_GPIO26_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO26_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO27_ENA_SHIFT 27
-#define I40E_EMPINT_GPIO_ENA_GPIO27_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO27_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO28_ENA_SHIFT 28
-#define I40E_EMPINT_GPIO_ENA_GPIO28_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO28_ENA_SHIFT)
-#define I40E_EMPINT_GPIO_ENA_GPIO29_ENA_SHIFT 29
-#define I40E_EMPINT_GPIO_ENA_GPIO29_ENA_MASK I40E_MASK(0x1, I40E_EMPINT_GPIO_ENA_GPIO29_ENA_SHIFT)
 #define I40E_PFGEN_PORTMDIO_NUM 0x0003F100 /* Reset: CORER */
-#define I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_SHIFT 0
-#define I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_MASK I40E_MASK(0x3, I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_SHIFT)
 #define I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_SHIFT 4
 #define I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK I40E_MASK(0x1, I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_SHIFT)
 #define I40E_PFINT_AEQCTL 0x00038700 /* Reset: CORER */
 #define I40E_PFINT_AEQCTL_MSIX_INDX_SHIFT 0
-#define I40E_PFINT_AEQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_PFINT_AEQCTL_MSIX_INDX_SHIFT)
 #define I40E_PFINT_AEQCTL_ITR_INDX_SHIFT 11
-#define I40E_PFINT_AEQCTL_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_AEQCTL_ITR_INDX_SHIFT)
-#define I40E_PFINT_AEQCTL_MSIX0_INDX_SHIFT 13
-#define I40E_PFINT_AEQCTL_MSIX0_INDX_MASK I40E_MASK(0x7, I40E_PFINT_AEQCTL_MSIX0_INDX_SHIFT)
 #define I40E_PFINT_AEQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_PFINT_AEQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_PFINT_AEQCTL_CAUSE_ENA_SHIFT)
-#define I40E_PFINT_AEQCTL_INTEVENT_SHIFT 31
-#define I40E_PFINT_AEQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_AEQCTL_INTEVENT_SHIFT)
 #define I40E_PFINT_CEQCTL(_INTPF) (0x00036800 + ((_INTPF) * 4)) /* _i=0...511 */ /* Reset: CORER */
-#define I40E_PFINT_CEQCTL_MAX_INDEX 511
 #define I40E_PFINT_CEQCTL_MSIX_INDX_SHIFT 0
-#define I40E_PFINT_CEQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_PFINT_CEQCTL_MSIX_INDX_SHIFT)
 #define I40E_PFINT_CEQCTL_ITR_INDX_SHIFT 11
-#define I40E_PFINT_CEQCTL_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_CEQCTL_ITR_INDX_SHIFT)
-#define I40E_PFINT_CEQCTL_MSIX0_INDX_SHIFT 13
-#define I40E_PFINT_CEQCTL_MSIX0_INDX_MASK I40E_MASK(0x7, I40E_PFINT_CEQCTL_MSIX0_INDX_SHIFT)
 #define I40E_PFINT_CEQCTL_NEXTQ_INDX_SHIFT 16
-#define I40E_PFINT_CEQCTL_NEXTQ_INDX_MASK I40E_MASK(0x7FF, I40E_PFINT_CEQCTL_NEXTQ_INDX_SHIFT)
-#define I40E_PFINT_CEQCTL_NEXTQ_TYPE_SHIFT 27
-#define I40E_PFINT_CEQCTL_NEXTQ_TYPE_MASK I40E_MASK(0x3, I40E_PFINT_CEQCTL_NEXTQ_TYPE_SHIFT)
 #define I40E_PFINT_CEQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_PFINT_CEQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_PFINT_CEQCTL_CAUSE_ENA_SHIFT)
-#define I40E_PFINT_CEQCTL_INTEVENT_SHIFT 31
-#define I40E_PFINT_CEQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_CEQCTL_INTEVENT_SHIFT)
 #define I40E_GLINT_CTL 0x0003F800 /* Reset: CORER */
-#define I40E_GLINT_CTL_DIS_AUTOMASK_PF0_SHIFT 0
-#define I40E_GLINT_CTL_DIS_AUTOMASK_PF0_MASK I40E_MASK(0x1, I40E_GLINT_CTL_DIS_AUTOMASK_PF0_SHIFT)
 #define I40E_GLINT_CTL_DIS_AUTOMASK_VF0_SHIFT 1
 #define I40E_GLINT_CTL_DIS_AUTOMASK_VF0_MASK I40E_MASK(0x1, I40E_GLINT_CTL_DIS_AUTOMASK_VF0_SHIFT)
-#define I40E_GLINT_CTL_DIS_AUTOMASK_N_SHIFT 2
-#define I40E_GLINT_CTL_DIS_AUTOMASK_N_MASK I40E_MASK(0x1, I40E_GLINT_CTL_DIS_AUTOMASK_N_SHIFT)
 #define I40E_PFINT_DYN_CTL0 0x00038480 /* Reset: PFR */
 #define I40E_PFINT_DYN_CTL0_INTENA_SHIFT 0
 #define I40E_PFINT_DYN_CTL0_INTENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTL0_INTENA_SHIFT)
@@ -872,8 +171,6 @@
 #define I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTL0_SWINT_TRIG_SHIFT)
 #define I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT 3
 #define I40E_PFINT_DYN_CTL0_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT)
-#define I40E_PFINT_DYN_CTL0_INTERVAL_SHIFT 5
-#define I40E_PFINT_DYN_CTL0_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTL0_INTERVAL_SHIFT)
 #define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT 24
 #define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT)
 #define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_SHIFT 25
@@ -881,7 +178,6 @@
 #define I40E_PFINT_DYN_CTL0_INTENA_MSK_SHIFT 31
 #define I40E_PFINT_DYN_CTL0_INTENA_MSK_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTL0_INTENA_MSK_SHIFT)
 #define I40E_PFINT_DYN_CTLN(_INTPF) (0x00034800 + ((_INTPF) * 4)) /* _i=0...511 */ /* Reset: PFR */
-#define I40E_PFINT_DYN_CTLN_MAX_INDEX 511
 #define I40E_PFINT_DYN_CTLN_INTENA_SHIFT 0
 #define I40E_PFINT_DYN_CTLN_INTENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_INTENA_SHIFT)
 #define I40E_PFINT_DYN_CTLN_CLEARPBA_SHIFT 1
@@ -891,93 +187,13 @@
 #define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
 #define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
 #define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
-#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
-#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
-#define I40E_PFINT_DYN_CTLN_INTENA_MSK_SHIFT 31
-#define I40E_PFINT_DYN_CTLN_INTENA_MSK_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_INTENA_MSK_SHIFT)
-#define I40E_PFINT_GPIO_ENA 0x00088080 /* Reset: CORER */
-#define I40E_PFINT_GPIO_ENA_GPIO0_ENA_SHIFT 0
-#define I40E_PFINT_GPIO_ENA_GPIO0_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO0_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO1_ENA_SHIFT 1
-#define I40E_PFINT_GPIO_ENA_GPIO1_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO1_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO2_ENA_SHIFT 2
-#define I40E_PFINT_GPIO_ENA_GPIO2_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO2_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO3_ENA_SHIFT 3
-#define I40E_PFINT_GPIO_ENA_GPIO3_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO3_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO4_ENA_SHIFT 4
-#define I40E_PFINT_GPIO_ENA_GPIO4_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO4_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO5_ENA_SHIFT 5
-#define I40E_PFINT_GPIO_ENA_GPIO5_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO5_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO6_ENA_SHIFT 6
-#define I40E_PFINT_GPIO_ENA_GPIO6_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO6_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO7_ENA_SHIFT 7
-#define I40E_PFINT_GPIO_ENA_GPIO7_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO7_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO8_ENA_SHIFT 8
-#define I40E_PFINT_GPIO_ENA_GPIO8_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO8_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO9_ENA_SHIFT 9
-#define I40E_PFINT_GPIO_ENA_GPIO9_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO9_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO10_ENA_SHIFT 10
-#define I40E_PFINT_GPIO_ENA_GPIO10_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO10_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO11_ENA_SHIFT 11
-#define I40E_PFINT_GPIO_ENA_GPIO11_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO11_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO12_ENA_SHIFT 12
-#define I40E_PFINT_GPIO_ENA_GPIO12_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO12_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO13_ENA_SHIFT 13
-#define I40E_PFINT_GPIO_ENA_GPIO13_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO13_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO14_ENA_SHIFT 14
-#define I40E_PFINT_GPIO_ENA_GPIO14_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO14_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO15_ENA_SHIFT 15
-#define I40E_PFINT_GPIO_ENA_GPIO15_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO15_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO16_ENA_SHIFT 16
-#define I40E_PFINT_GPIO_ENA_GPIO16_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO16_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO17_ENA_SHIFT 17
-#define I40E_PFINT_GPIO_ENA_GPIO17_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO17_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO18_ENA_SHIFT 18
-#define I40E_PFINT_GPIO_ENA_GPIO18_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO18_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO19_ENA_SHIFT 19
-#define I40E_PFINT_GPIO_ENA_GPIO19_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO19_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO20_ENA_SHIFT 20
-#define I40E_PFINT_GPIO_ENA_GPIO20_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO20_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO21_ENA_SHIFT 21
-#define I40E_PFINT_GPIO_ENA_GPIO21_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO21_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO22_ENA_SHIFT 22
-#define I40E_PFINT_GPIO_ENA_GPIO22_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO22_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO23_ENA_SHIFT 23
-#define I40E_PFINT_GPIO_ENA_GPIO23_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO23_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO24_ENA_SHIFT 24
-#define I40E_PFINT_GPIO_ENA_GPIO24_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO24_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO25_ENA_SHIFT 25
-#define I40E_PFINT_GPIO_ENA_GPIO25_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO25_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO26_ENA_SHIFT 26
-#define I40E_PFINT_GPIO_ENA_GPIO26_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO26_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO27_ENA_SHIFT 27
-#define I40E_PFINT_GPIO_ENA_GPIO27_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO27_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO28_ENA_SHIFT 28
-#define I40E_PFINT_GPIO_ENA_GPIO28_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO28_ENA_SHIFT)
-#define I40E_PFINT_GPIO_ENA_GPIO29_ENA_SHIFT 29
-#define I40E_PFINT_GPIO_ENA_GPIO29_ENA_MASK I40E_MASK(0x1, I40E_PFINT_GPIO_ENA_GPIO29_ENA_SHIFT)
 #define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
 #define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
 #define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
 #define I40E_PFINT_ICR0_QUEUE_0_SHIFT 1
 #define I40E_PFINT_ICR0_QUEUE_0_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_0_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_1_SHIFT 2
-#define I40E_PFINT_ICR0_QUEUE_1_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_1_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_2_SHIFT 3
-#define I40E_PFINT_ICR0_QUEUE_2_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_2_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_3_SHIFT 4
-#define I40E_PFINT_ICR0_QUEUE_3_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_3_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_4_SHIFT 5
-#define I40E_PFINT_ICR0_QUEUE_4_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_4_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_5_SHIFT 6
-#define I40E_PFINT_ICR0_QUEUE_5_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_5_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_6_SHIFT 7
-#define I40E_PFINT_ICR0_QUEUE_6_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_6_SHIFT)
-#define I40E_PFINT_ICR0_QUEUE_7_SHIFT 8
-#define I40E_PFINT_ICR0_QUEUE_7_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_QUEUE_7_SHIFT)
 #define I40E_PFINT_ICR0_ECC_ERR_SHIFT 16
 #define I40E_PFINT_ICR0_ECC_ERR_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ECC_ERR_SHIFT)
 #define I40E_PFINT_ICR0_MAL_DETECT_SHIFT 19
@@ -986,14 +202,8 @@
 #define I40E_PFINT_ICR0_GRST_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_GRST_SHIFT)
 #define I40E_PFINT_ICR0_PCI_EXCEPTION_SHIFT 21
 #define I40E_PFINT_ICR0_PCI_EXCEPTION_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_PCI_EXCEPTION_SHIFT)
-#define I40E_PFINT_ICR0_GPIO_SHIFT 22
-#define I40E_PFINT_ICR0_GPIO_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_TIMESYNC_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_STORM_DETECT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_STORM_DETECT_SHIFT)
-#define I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_PFINT_ICR0_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_HMC_ERR_SHIFT 26
 #define I40E_PFINT_ICR0_HMC_ERR_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_HMC_ERR_SHIFT)
 #define I40E_PFINT_ICR0_PE_CRITERR_SHIFT 28
@@ -1017,10 +227,6 @@
 #define I40E_PFINT_ICR0_ENA_GPIO_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT)
-#define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT 26
 #define I40E_PFINT_ICR0_ENA_HMC_ERR_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT)
 #define I40E_PFINT_ICR0_ENA_PE_CRITERR_SHIFT 28
@@ -1029,43 +235,17 @@
 #define I40E_PFINT_ICR0_ENA_VFLR_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_VFLR_SHIFT)
 #define I40E_PFINT_ICR0_ENA_ADMINQ_SHIFT 30
 #define I40E_PFINT_ICR0_ENA_ADMINQ_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_ADMINQ_SHIFT)
-#define I40E_PFINT_ICR0_ENA_RSVD_SHIFT 31
-#define I40E_PFINT_ICR0_ENA_RSVD_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_ENA_RSVD_SHIFT)
 #define I40E_PFINT_ITR0(_i) (0x00038000 + ((_i) * 128)) /* _i=0...2 */ /* Reset: PFR */
-#define I40E_PFINT_ITR0_MAX_INDEX 2
-#define I40E_PFINT_ITR0_INTERVAL_SHIFT 0
-#define I40E_PFINT_ITR0_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_ITR0_INTERVAL_SHIFT)
 #define I40E_PFINT_ITRN(_i, _INTPF) (0x00030000 + ((_i) * 2048 + (_INTPF) * 4)) /* _i=0...2, _INTPF=0...511 */ /* Reset: PFR */
-#define I40E_PFINT_ITRN_MAX_INDEX 2
-#define I40E_PFINT_ITRN_INTERVAL_SHIFT 0
-#define I40E_PFINT_ITRN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_ITRN_INTERVAL_SHIFT)
 #define I40E_PFINT_LNKLST0 0x00038500 /* Reset: PFR */
 #define I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT 0
-#define I40E_PFINT_LNKLST0_FIRSTQ_INDX_MASK I40E_MASK(0x7FF, I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT)
-#define I40E_PFINT_LNKLST0_FIRSTQ_TYPE_SHIFT 11
-#define I40E_PFINT_LNKLST0_FIRSTQ_TYPE_MASK I40E_MASK(0x3, I40E_PFINT_LNKLST0_FIRSTQ_TYPE_SHIFT)
 #define I40E_PFINT_LNKLSTN(_INTPF) (0x00035000 + ((_INTPF) * 4)) /* _i=0...511 */ /* Reset: PFR */
-#define I40E_PFINT_LNKLSTN_MAX_INDEX 511
 #define I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT 0
 #define I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK I40E_MASK(0x7FF, I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT)
 #define I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_SHIFT 11
-#define I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_MASK I40E_MASK(0x3, I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_SHIFT)
-#define I40E_PFINT_RATE0 0x00038580 /* Reset: PFR */
-#define I40E_PFINT_RATE0_INTERVAL_SHIFT 0
-#define I40E_PFINT_RATE0_INTERVAL_MASK I40E_MASK(0x3F, I40E_PFINT_RATE0_INTERVAL_SHIFT)
-#define I40E_PFINT_RATE0_INTRL_ENA_SHIFT 6
-#define I40E_PFINT_RATE0_INTRL_ENA_MASK I40E_MASK(0x1, I40E_PFINT_RATE0_INTRL_ENA_SHIFT)
 #define I40E_PFINT_RATEN(_INTPF) (0x00035800 + ((_INTPF) * 4)) /* _i=0...511 */ /* Reset: PFR */
-#define I40E_PFINT_RATEN_MAX_INDEX 511
-#define I40E_PFINT_RATEN_INTERVAL_SHIFT 0
-#define I40E_PFINT_RATEN_INTERVAL_MASK I40E_MASK(0x3F, I40E_PFINT_RATEN_INTERVAL_SHIFT)
-#define I40E_PFINT_RATEN_INTRL_ENA_SHIFT 6
-#define I40E_PFINT_RATEN_INTRL_ENA_MASK I40E_MASK(0x1, I40E_PFINT_RATEN_INTRL_ENA_SHIFT)
 #define I40E_PFINT_STAT_CTL0 0x00038400 /* Reset: CORER */
-#define I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT 2
-#define I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT)
 #define I40E_QINT_RQCTL(_Q) (0x0003A000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: CORER */
-#define I40E_QINT_RQCTL_MAX_INDEX 1535
 #define I40E_QINT_RQCTL_MSIX_INDX_SHIFT 0
 #define I40E_QINT_RQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_QINT_RQCTL_MSIX_INDX_SHIFT)
 #define I40E_QINT_RQCTL_ITR_INDX_SHIFT 11
@@ -1075,13 +255,11 @@
 #define I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT 16
 #define I40E_QINT_RQCTL_NEXTQ_INDX_MASK I40E_MASK(0x7FF, I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)
 #define I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT 27
-#define I40E_QINT_RQCTL_NEXTQ_TYPE_MASK I40E_MASK(0x3, I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT)
 #define I40E_QINT_RQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_QINT_RQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_QINT_RQCTL_CAUSE_ENA_SHIFT)
 #define I40E_QINT_RQCTL_INTEVENT_SHIFT 31
 #define I40E_QINT_RQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_QINT_RQCTL_INTEVENT_SHIFT)
 #define I40E_QINT_TQCTL(_Q) (0x0003C000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: CORER */
-#define I40E_QINT_TQCTL_MAX_INDEX 1535
 #define I40E_QINT_TQCTL_MSIX_INDX_SHIFT 0
 #define I40E_QINT_TQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_QINT_TQCTL_MSIX_INDX_SHIFT)
 #define I40E_QINT_TQCTL_ITR_INDX_SHIFT 11
@@ -1091,160 +269,45 @@
 #define I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT 16
 #define I40E_QINT_TQCTL_NEXTQ_INDX_MASK I40E_MASK(0x7FF, I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT)
 #define I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT 27
-#define I40E_QINT_TQCTL_NEXTQ_TYPE_MASK I40E_MASK(0x3, I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT)
 #define I40E_QINT_TQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_QINT_TQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_QINT_TQCTL_CAUSE_ENA_SHIFT)
 #define I40E_QINT_TQCTL_INTEVENT_SHIFT 31
 #define I40E_QINT_TQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_QINT_TQCTL_INTEVENT_SHIFT)
 #define I40E_VFINT_DYN_CTL0(_VF) (0x0002A400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFINT_DYN_CTL0_MAX_INDEX 127
-#define I40E_VFINT_DYN_CTL0_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTL0_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_INTENA_SHIFT)
-#define I40E_VFINT_DYN_CTL0_CLEARPBA_SHIFT 1
-#define I40E_VFINT_DYN_CTL0_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTL0_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTL0_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTL0_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTL0_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL0_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL0_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTL0_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTL0_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL0_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL0_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTL0_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_INTENA_MSK_SHIFT)
 #define I40E_VFINT_DYN_CTLN(_INTVF) (0x00024800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */
-#define I40E_VFINT_DYN_CTLN_MAX_INDEX 511
-#define I40E_VFINT_DYN_CTLN_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTLN_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_INTENA_SHIFT)
 #define I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT 1
 #define I40E_VFINT_DYN_CTLN_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTLN_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTLN_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTLN_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTLN_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_INTENA_MSK_SHIFT)
-#define I40E_VFINT_ICR0(_VF) (0x0002BC00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VFINT_ICR0_MAX_INDEX 127
-#define I40E_VFINT_ICR0_INTEVENT_SHIFT 0
-#define I40E_VFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_INTEVENT_SHIFT)
-#define I40E_VFINT_ICR0_QUEUE_0_SHIFT 1
-#define I40E_VFINT_ICR0_QUEUE_0_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_QUEUE_0_SHIFT)
-#define I40E_VFINT_ICR0_QUEUE_1_SHIFT 2
-#define I40E_VFINT_ICR0_QUEUE_1_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_QUEUE_1_SHIFT)
-#define I40E_VFINT_ICR0_QUEUE_2_SHIFT 3
-#define I40E_VFINT_ICR0_QUEUE_2_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_QUEUE_2_SHIFT)
-#define I40E_VFINT_ICR0_QUEUE_3_SHIFT 4
-#define I40E_VFINT_ICR0_QUEUE_3_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_QUEUE_3_SHIFT)
-#define I40E_VFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR0_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR0_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR0_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR0_SWINT_SHIFT 31
-#define I40E_VFINT_ICR0_SWINT_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_SWINT_SHIFT)
-#define I40E_VFINT_ICR0_ENA(_VF) (0x0002C000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VFINT_ICR0_ENA_MAX_INDEX 127
-#define I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR0_ENA_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR0_ENA_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR0_ENA_RSVD_SHIFT 31
-#define I40E_VFINT_ICR0_ENA_RSVD_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA_RSVD_SHIFT)
-#define I40E_VFINT_ITR0(_i, _VF) (0x00028000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...2, _VF=0...127 */ /* Reset: VFR */
-#define I40E_VFINT_ITR0_MAX_INDEX 2
-#define I40E_VFINT_ITR0_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITR0_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITR0_INTERVAL_SHIFT)
-#define I40E_VFINT_ITRN(_i, _INTVF) (0x00020000 + ((_i) * 2048 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...511 */ /* Reset: VFR */
-#define I40E_VFINT_ITRN_MAX_INDEX 2
-#define I40E_VFINT_ITRN_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITRN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITRN_INTERVAL_SHIFT)
-#define I40E_VFINT_STAT_CTL0(_VF) (0x0002A000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VFINT_STAT_CTL0_MAX_INDEX 127
-#define I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT 2
-#define I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT)
 #define I40E_VPINT_AEQCTL(_VF) (0x0002B800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VPINT_AEQCTL_MAX_INDEX 127
 #define I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT 0
-#define I40E_VPINT_AEQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT)
 #define I40E_VPINT_AEQCTL_ITR_INDX_SHIFT 11
-#define I40E_VPINT_AEQCTL_ITR_INDX_MASK I40E_MASK(0x3, I40E_VPINT_AEQCTL_ITR_INDX_SHIFT)
-#define I40E_VPINT_AEQCTL_MSIX0_INDX_SHIFT 13
-#define I40E_VPINT_AEQCTL_MSIX0_INDX_MASK I40E_MASK(0x7, I40E_VPINT_AEQCTL_MSIX0_INDX_SHIFT)
 #define I40E_VPINT_AEQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_VPINT_AEQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_VPINT_AEQCTL_CAUSE_ENA_SHIFT)
-#define I40E_VPINT_AEQCTL_INTEVENT_SHIFT 31
-#define I40E_VPINT_AEQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_VPINT_AEQCTL_INTEVENT_SHIFT)
 #define I40E_VPINT_CEQCTL(_INTVF) (0x00026800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: CORER */
-#define I40E_VPINT_CEQCTL_MAX_INDEX 511
 #define I40E_VPINT_CEQCTL_MSIX_INDX_SHIFT 0
-#define I40E_VPINT_CEQCTL_MSIX_INDX_MASK I40E_MASK(0xFF, I40E_VPINT_CEQCTL_MSIX_INDX_SHIFT)
 #define I40E_VPINT_CEQCTL_ITR_INDX_SHIFT 11
-#define I40E_VPINT_CEQCTL_ITR_INDX_MASK I40E_MASK(0x3, I40E_VPINT_CEQCTL_ITR_INDX_SHIFT)
-#define I40E_VPINT_CEQCTL_MSIX0_INDX_SHIFT 13
-#define I40E_VPINT_CEQCTL_MSIX0_INDX_MASK I40E_MASK(0x7, I40E_VPINT_CEQCTL_MSIX0_INDX_SHIFT)
 #define I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT 16
 #define I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK I40E_MASK(0x7FF, I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT)
 #define I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT 27
 #define I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK I40E_MASK(0x3, I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT)
 #define I40E_VPINT_CEQCTL_CAUSE_ENA_SHIFT 30
 #define I40E_VPINT_CEQCTL_CAUSE_ENA_MASK I40E_MASK(0x1, I40E_VPINT_CEQCTL_CAUSE_ENA_SHIFT)
-#define I40E_VPINT_CEQCTL_INTEVENT_SHIFT 31
-#define I40E_VPINT_CEQCTL_INTEVENT_MASK I40E_MASK(0x1, I40E_VPINT_CEQCTL_INTEVENT_SHIFT)
 #define I40E_VPINT_LNKLST0(_VF) (0x0002A800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VPINT_LNKLST0_MAX_INDEX 127
 #define I40E_VPINT_LNKLST0_FIRSTQ_INDX_SHIFT 0
 #define I40E_VPINT_LNKLST0_FIRSTQ_INDX_MASK I40E_MASK(0x7FF, I40E_VPINT_LNKLST0_FIRSTQ_INDX_SHIFT)
-#define I40E_VPINT_LNKLST0_FIRSTQ_TYPE_SHIFT 11
-#define I40E_VPINT_LNKLST0_FIRSTQ_TYPE_MASK I40E_MASK(0x3, I40E_VPINT_LNKLST0_FIRSTQ_TYPE_SHIFT)
 #define I40E_VPINT_LNKLSTN(_INTVF) (0x00025000 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */
-#define I40E_VPINT_LNKLSTN_MAX_INDEX 511
 #define I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT 0
 #define I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK I40E_MASK(0x7FF, I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT)
 #define I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT 11
 #define I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK I40E_MASK(0x3, I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT)
-#define I40E_VPINT_RATE0(_VF) (0x0002AC00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VPINT_RATE0_MAX_INDEX 127
-#define I40E_VPINT_RATE0_INTERVAL_SHIFT 0
-#define I40E_VPINT_RATE0_INTERVAL_MASK I40E_MASK(0x3F, I40E_VPINT_RATE0_INTERVAL_SHIFT)
-#define I40E_VPINT_RATE0_INTRL_ENA_SHIFT 6
-#define I40E_VPINT_RATE0_INTRL_ENA_MASK I40E_MASK(0x1, I40E_VPINT_RATE0_INTRL_ENA_SHIFT)
-#define I40E_VPINT_RATEN(_INTVF) (0x00025800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */
-#define I40E_VPINT_RATEN_MAX_INDEX 511
-#define I40E_VPINT_RATEN_INTERVAL_SHIFT 0
-#define I40E_VPINT_RATEN_INTERVAL_MASK I40E_MASK(0x3F, I40E_VPINT_RATEN_INTERVAL_SHIFT)
-#define I40E_VPINT_RATEN_INTRL_ENA_SHIFT 6
-#define I40E_VPINT_RATEN_INTRL_ENA_MASK I40E_MASK(0x1, I40E_VPINT_RATEN_INTRL_ENA_SHIFT)
-#define I40E_GL_RDPU_CNTRL 0x00051060 /* Reset: CORER */
-#define I40E_GL_RDPU_CNTRL_RX_PAD_EN_SHIFT 0
-#define I40E_GL_RDPU_CNTRL_RX_PAD_EN_MASK I40E_MASK(0x1, I40E_GL_RDPU_CNTRL_RX_PAD_EN_SHIFT)
-#define I40E_GL_RDPU_CNTRL_ECO_SHIFT 1
-#define I40E_GL_RDPU_CNTRL_ECO_MASK I40E_MASK(0x7FFFFFFF, I40E_GL_RDPU_CNTRL_ECO_SHIFT)
 #define I40E_GLLAN_RCTL_0 0x0012A500 /* Reset: CORER */
 #define I40E_GLLAN_RCTL_0_PXE_MODE_SHIFT 0
 #define I40E_GLLAN_RCTL_0_PXE_MODE_MASK I40E_MASK(0x1, I40E_GLLAN_RCTL_0_PXE_MODE_SHIFT)
 #define I40E_GLLAN_TSOMSK_F 0x000442D8 /* Reset: CORER */
-#define I40E_GLLAN_TSOMSK_F_TCPMSKF_SHIFT 0
-#define I40E_GLLAN_TSOMSK_F_TCPMSKF_MASK I40E_MASK(0xFFF, I40E_GLLAN_TSOMSK_F_TCPMSKF_SHIFT)
 #define I40E_GLLAN_TSOMSK_L 0x000442E0 /* Reset: CORER */
-#define I40E_GLLAN_TSOMSK_L_TCPMSKL_SHIFT 0
-#define I40E_GLLAN_TSOMSK_L_TCPMSKL_MASK I40E_MASK(0xFFF, I40E_GLLAN_TSOMSK_L_TCPMSKL_SHIFT)
 #define I40E_GLLAN_TSOMSK_M 0x000442DC /* Reset: CORER */
-#define I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT 0
-#define I40E_GLLAN_TSOMSK_M_TCPMSKM_MASK I40E_MASK(0xFFF, I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT)
 #define I40E_GLLAN_TXPRE_QDIS(_i) (0x000e6500 + ((_i) * 4)) /* _i=0...11 */ /* Reset: CORER */
-#define I40E_GLLAN_TXPRE_QDIS_MAX_INDEX 11
 #define I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT 0
 #define I40E_GLLAN_TXPRE_QDIS_QINDX_MASK I40E_MASK(0x7FF, I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT)
-#define I40E_GLLAN_TXPRE_QDIS_QDIS_STAT_SHIFT 16
-#define I40E_GLLAN_TXPRE_QDIS_QDIS_STAT_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_QDIS_STAT_SHIFT)
 #define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT 30
 #define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT)
 #define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT 31
@@ -1257,19 +320,12 @@
 #define I40E_PFLAN_QALLOC_VALID_SHIFT 31
 #define I40E_PFLAN_QALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PFLAN_QALLOC_VALID_SHIFT)
 #define I40E_QRX_ENA(_Q) (0x00120000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: PFR */
-#define I40E_QRX_ENA_MAX_INDEX 1535
 #define I40E_QRX_ENA_QENA_REQ_SHIFT 0
 #define I40E_QRX_ENA_QENA_REQ_MASK I40E_MASK(0x1, I40E_QRX_ENA_QENA_REQ_SHIFT)
-#define I40E_QRX_ENA_FAST_QDIS_SHIFT 1
-#define I40E_QRX_ENA_FAST_QDIS_MASK I40E_MASK(0x1, I40E_QRX_ENA_FAST_QDIS_SHIFT)
 #define I40E_QRX_ENA_QENA_STAT_SHIFT 2
 #define I40E_QRX_ENA_QENA_STAT_MASK I40E_MASK(0x1, I40E_QRX_ENA_QENA_STAT_SHIFT)
 #define I40E_QRX_TAIL(_Q) (0x00128000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: CORER */
-#define I40E_QRX_TAIL_MAX_INDEX 1535
-#define I40E_QRX_TAIL_TAIL_SHIFT 0
-#define I40E_QRX_TAIL_TAIL_MASK I40E_MASK(0x1FFF, I40E_QRX_TAIL_TAIL_SHIFT)
 #define I40E_QTX_CTL(_Q) (0x00104000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: CORER */
-#define I40E_QTX_CTL_MAX_INDEX 1535
 #define I40E_QTX_CTL_PFVF_Q_SHIFT 0
 #define I40E_QTX_CTL_PFVF_Q_MASK I40E_MASK(0x3, I40E_QTX_CTL_PFVF_Q_SHIFT)
 #define I40E_QTX_CTL_PF_INDX_SHIFT 2
@@ -1277,43 +333,22 @@
 #define I40E_QTX_CTL_VFVM_INDX_SHIFT 7
 #define I40E_QTX_CTL_VFVM_INDX_MASK I40E_MASK(0x1FF, I40E_QTX_CTL_VFVM_INDX_SHIFT)
 #define I40E_QTX_ENA(_Q) (0x00100000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: PFR */
-#define I40E_QTX_ENA_MAX_INDEX 1535
 #define I40E_QTX_ENA_QENA_REQ_SHIFT 0
 #define I40E_QTX_ENA_QENA_REQ_MASK I40E_MASK(0x1, I40E_QTX_ENA_QENA_REQ_SHIFT)
-#define I40E_QTX_ENA_FAST_QDIS_SHIFT 1
-#define I40E_QTX_ENA_FAST_QDIS_MASK I40E_MASK(0x1, I40E_QTX_ENA_FAST_QDIS_SHIFT)
 #define I40E_QTX_ENA_QENA_STAT_SHIFT 2
 #define I40E_QTX_ENA_QENA_STAT_MASK I40E_MASK(0x1, I40E_QTX_ENA_QENA_STAT_SHIFT)
 #define I40E_QTX_HEAD(_Q) (0x000E4000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: CORER */
-#define I40E_QTX_HEAD_MAX_INDEX 1535
-#define I40E_QTX_HEAD_HEAD_SHIFT 0
-#define I40E_QTX_HEAD_HEAD_MASK I40E_MASK(0x1FFF, I40E_QTX_HEAD_HEAD_SHIFT)
-#define I40E_QTX_HEAD_RS_PENDING_SHIFT 16
-#define I40E_QTX_HEAD_RS_PENDING_MASK I40E_MASK(0x1, I40E_QTX_HEAD_RS_PENDING_SHIFT)
 #define I40E_QTX_TAIL(_Q) (0x00108000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: PFR */
-#define I40E_QTX_TAIL_MAX_INDEX 1535
-#define I40E_QTX_TAIL_TAIL_SHIFT 0
-#define I40E_QTX_TAIL_TAIL_MASK I40E_MASK(0x1FFF, I40E_QTX_TAIL_TAIL_SHIFT)
 #define I40E_VPLAN_MAPENA(_VF) (0x00074000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VPLAN_MAPENA_MAX_INDEX 127
 #define I40E_VPLAN_MAPENA_TXRX_ENA_SHIFT 0
 #define I40E_VPLAN_MAPENA_TXRX_ENA_MASK I40E_MASK(0x1, I40E_VPLAN_MAPENA_TXRX_ENA_SHIFT)
 #define I40E_VPLAN_QTABLE(_i, _VF) (0x00070000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...15, _VF=0...127 */ /* Reset: VFR */
-#define I40E_VPLAN_QTABLE_MAX_INDEX 15
 #define I40E_VPLAN_QTABLE_QINDEX_SHIFT 0
 #define I40E_VPLAN_QTABLE_QINDEX_MASK I40E_MASK(0x7FF, I40E_VPLAN_QTABLE_QINDEX_SHIFT)
 #define I40E_VSILAN_QBASE(_VSI) (0x0020C800 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: PFR */
-#define I40E_VSILAN_QBASE_MAX_INDEX 383
-#define I40E_VSILAN_QBASE_VSIBASE_SHIFT 0
-#define I40E_VSILAN_QBASE_VSIBASE_MASK I40E_MASK(0x7FF, I40E_VSILAN_QBASE_VSIBASE_SHIFT)
 #define I40E_VSILAN_QBASE_VSIQTABLE_ENA_SHIFT 11
 #define I40E_VSILAN_QBASE_VSIQTABLE_ENA_MASK I40E_MASK(0x1, I40E_VSILAN_QBASE_VSIQTABLE_ENA_SHIFT)
 #define I40E_VSILAN_QTABLE(_i, _VSI) (0x00200000 + ((_i) * 2048 + (_VSI) * 4)) /* _i=0...7, _VSI=0...383 */ /* Reset: PFR */
-#define I40E_VSILAN_QTABLE_MAX_INDEX 7
-#define I40E_VSILAN_QTABLE_QINDEX_0_SHIFT 0
-#define I40E_VSILAN_QTABLE_QINDEX_0_MASK I40E_MASK(0x7FF, I40E_VSILAN_QTABLE_QINDEX_0_SHIFT)
-#define I40E_VSILAN_QTABLE_QINDEX_1_SHIFT 16
-#define I40E_VSILAN_QTABLE_QINDEX_1_MASK I40E_MASK(0x7FF, I40E_VSILAN_QTABLE_QINDEX_1_SHIFT)
 #define I40E_PRTGL_SAH 0x001E2140 /* Reset: GLOBR */
 #define I40E_PRTGL_SAH_FC_SAH_SHIFT 0
 #define I40E_PRTGL_SAH_FC_SAH_MASK I40E_MASK(0xFFFF, I40E_PRTGL_SAH_FC_SAH_SHIFT)
@@ -1322,789 +357,47 @@
 #define I40E_PRTGL_SAL 0x001E2120 /* Reset: GLOBR */
 #define I40E_PRTGL_SAL_FC_SAL_SHIFT 0
 #define I40E_PRTGL_SAL_FC_SAL_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTGL_SAL_FC_SAL_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP 0x001E30E0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_MASK I40E_MASK(0x1, I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP 0x001E3260 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_MASK I40E_MASK(0x1, I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP 0x001E32E0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_MASK I40E_MASK(0x1, I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL 0x001E3360 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_MASK I40E_MASK(0x1, I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1 0x001E3110 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2 0x001E3120 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE 0x001E30C0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_MASK I40E_MASK(0x1FF, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1 0x001E3140 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2 0x001E3150 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE 0x001E30D0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_MASK I40E_MASK(0x1FF, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i) (0x001E3370 + ((_i) * 16)) /* _i=0...8 */ /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3400 + ((_i) * 16)) /* _i=0...8 */ /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MAX_INDEX 8
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1 0x001E34B0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_SHIFT)
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2 0x001E34C0 /* Reset: GLOBR */
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_SHIFT 0
-#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A 0x0008C480 /* Reset: GLOBR */
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_SHIFT 0
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_SHIFT 2
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_SHIFT 4
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_SHIFT 6
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_SHIFT 8
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_SHIFT 10
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_SHIFT 12
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_SHIFT 14
-#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B 0x0008C484 /* Reset: GLOBR */
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_SHIFT 0
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_SHIFT 2
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_SHIFT 4
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_SHIFT 6
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_SHIFT 8
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_SHIFT 10
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_SHIFT 12
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_SHIFT)
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_SHIFT 14
-#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_MASK I40E_MASK(0x3, I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_SHIFT)
-#define I40E_GL_FWRESETCNT 0x00083100 /* Reset: POR */
-#define I40E_GL_FWRESETCNT_FWRESETCNT_SHIFT 0
-#define I40E_GL_FWRESETCNT_FWRESETCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FWRESETCNT_FWRESETCNT_SHIFT)
-#define I40E_GL_MNG_FWSM 0x000B6134 /* Reset: POR */
-#define I40E_GL_MNG_FWSM_FW_MODES_SHIFT 0
-#define I40E_GL_MNG_FWSM_FW_MODES_MASK I40E_MASK(0x3, I40E_GL_MNG_FWSM_FW_MODES_SHIFT)
-#define I40E_GL_MNG_FWSM_EEP_RELOAD_IND_SHIFT 10
-#define I40E_GL_MNG_FWSM_EEP_RELOAD_IND_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_EEP_RELOAD_IND_SHIFT)
-#define I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_SHIFT 11
-#define I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_MASK I40E_MASK(0xF, I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_SHIFT)
-#define I40E_GL_MNG_FWSM_FW_STATUS_VALID_SHIFT 15
-#define I40E_GL_MNG_FWSM_FW_STATUS_VALID_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_FW_STATUS_VALID_SHIFT)
-#define I40E_GL_MNG_FWSM_RESET_CNT_SHIFT 16
-#define I40E_GL_MNG_FWSM_RESET_CNT_MASK I40E_MASK(0x7, I40E_GL_MNG_FWSM_RESET_CNT_SHIFT)
-#define I40E_GL_MNG_FWSM_EXT_ERR_IND_SHIFT 19
-#define I40E_GL_MNG_FWSM_EXT_ERR_IND_MASK I40E_MASK(0x3F, I40E_GL_MNG_FWSM_EXT_ERR_IND_SHIFT)
-#define I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_SHIFT 26
-#define I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_SHIFT)
-#define I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_SHIFT 27
-#define I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_SHIFT)
-#define I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_SHIFT 28
-#define I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_SHIFT)
-#define I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_SHIFT 29
-#define I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_MASK I40E_MASK(0x1, I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_SHIFT)
-#define I40E_GL_MNG_HWARB_CTRL 0x000B6130 /* Reset: POR */
-#define I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_SHIFT 0
-#define I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_MASK I40E_MASK(0x1, I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_SHIFT)
-#define I40E_PRT_MNG_FTFT_DATA(_i) (0x000852A0 + ((_i) * 32)) /* _i=0...31 */ /* Reset: POR */
-#define I40E_PRT_MNG_FTFT_DATA_MAX_INDEX 31
-#define I40E_PRT_MNG_FTFT_DATA_DWORD_SHIFT 0
-#define I40E_PRT_MNG_FTFT_DATA_DWORD_MASK I40E_MASK(0xFFFFFFFF, I40E_PRT_MNG_FTFT_DATA_DWORD_SHIFT)
-#define I40E_PRT_MNG_FTFT_LENGTH 0x00085260 /* Reset: POR */
-#define I40E_PRT_MNG_FTFT_LENGTH_LENGTH_SHIFT 0
-#define I40E_PRT_MNG_FTFT_LENGTH_LENGTH_MASK I40E_MASK(0xFF, I40E_PRT_MNG_FTFT_LENGTH_LENGTH_SHIFT)
-#define I40E_PRT_MNG_FTFT_MASK(_i) (0x00085160 + ((_i) * 32)) /* _i=0...7 */ /* Reset: POR */
-#define I40E_PRT_MNG_FTFT_MASK_MAX_INDEX 7
-#define I40E_PRT_MNG_FTFT_MASK_MASK_SHIFT 0
-#define I40E_PRT_MNG_FTFT_MASK_MASK_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_FTFT_MASK_MASK_SHIFT)
-#define I40E_PRT_MNG_MANC 0x00256A20 /* Reset: POR */
-#define I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_SHIFT 0
-#define I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_SHIFT)
-#define I40E_PRT_MNG_MANC_NCSI_DISCARD_SHIFT 1
-#define I40E_PRT_MNG_MANC_NCSI_DISCARD_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_NCSI_DISCARD_SHIFT)
-#define I40E_PRT_MNG_MANC_RCV_TCO_EN_SHIFT 17
-#define I40E_PRT_MNG_MANC_RCV_TCO_EN_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_RCV_TCO_EN_SHIFT)
-#define I40E_PRT_MNG_MANC_RCV_ALL_SHIFT 19
-#define I40E_PRT_MNG_MANC_RCV_ALL_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_RCV_ALL_SHIFT)
-#define I40E_PRT_MNG_MANC_FIXED_NET_TYPE_SHIFT 25
-#define I40E_PRT_MNG_MANC_FIXED_NET_TYPE_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_FIXED_NET_TYPE_SHIFT)
-#define I40E_PRT_MNG_MANC_NET_TYPE_SHIFT 26
-#define I40E_PRT_MNG_MANC_NET_TYPE_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_NET_TYPE_SHIFT)
-#define I40E_PRT_MNG_MANC_EN_BMC2OS_SHIFT 28
-#define I40E_PRT_MNG_MANC_EN_BMC2OS_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_EN_BMC2OS_SHIFT)
-#define I40E_PRT_MNG_MANC_EN_BMC2NET_SHIFT 29
-#define I40E_PRT_MNG_MANC_EN_BMC2NET_MASK I40E_MASK(0x1, I40E_PRT_MNG_MANC_EN_BMC2NET_SHIFT)
-#define I40E_PRT_MNG_MAVTV(_i) (0x00255900 + ((_i) * 32)) /* _i=0...7 */ /* Reset: POR */
-#define I40E_PRT_MNG_MAVTV_MAX_INDEX 7
-#define I40E_PRT_MNG_MAVTV_VID_SHIFT 0
-#define I40E_PRT_MNG_MAVTV_VID_MASK I40E_MASK(0xFFF, I40E_PRT_MNG_MAVTV_VID_SHIFT)
-#define I40E_PRT_MNG_MDEF(_i) (0x00255D00 + ((_i) * 32)) /* _i=0...7 */ /* Reset: POR */
-#define I40E_PRT_MNG_MDEF_MAX_INDEX 7
-#define I40E_PRT_MNG_MDEF_MAC_EXACT_AND_SHIFT 0
-#define I40E_PRT_MNG_MDEF_MAC_EXACT_AND_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_MAC_EXACT_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_BROADCAST_AND_SHIFT 4
-#define I40E_PRT_MNG_MDEF_BROADCAST_AND_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_BROADCAST_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_VLAN_AND_SHIFT 5
-#define I40E_PRT_MNG_MDEF_VLAN_AND_MASK I40E_MASK(0xFF, I40E_PRT_MNG_MDEF_VLAN_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_SHIFT 13
-#define I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_SHIFT 17
-#define I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_MAC_EXACT_OR_SHIFT 21
-#define I40E_PRT_MNG_MDEF_MAC_EXACT_OR_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_MAC_EXACT_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_BROADCAST_OR_SHIFT 25
-#define I40E_PRT_MNG_MDEF_BROADCAST_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_BROADCAST_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_MULTICAST_AND_SHIFT 26
-#define I40E_PRT_MNG_MDEF_MULTICAST_AND_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_MULTICAST_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_SHIFT 27
-#define I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_SHIFT 28
-#define I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_SHIFT 29
-#define I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_PORT_0X298_OR_SHIFT 30
-#define I40E_PRT_MNG_MDEF_PORT_0X298_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_PORT_0X298_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_PORT_0X26F_OR_SHIFT 31
-#define I40E_PRT_MNG_MDEF_PORT_0X26F_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_PORT_0X26F_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT(_i) (0x00255F00 + ((_i) * 32)) /* _i=0...7 */ /* Reset: POR */
-#define I40E_PRT_MNG_MDEF_EXT_MAX_INDEX 7
-#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_SHIFT 0
-#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_SHIFT 4
-#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_MASK I40E_MASK(0xF, I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_SHIFT 8
-#define I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_SHIFT 24
-#define I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_SHIFT 25
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_SHIFT 26
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_SHIFT 27
-#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_ICMP_OR_SHIFT 28
-#define I40E_PRT_MNG_MDEF_EXT_ICMP_OR_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_ICMP_OR_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_MLD_SHIFT 29
-#define I40E_PRT_MNG_MDEF_EXT_MLD_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_MLD_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_SHIFT 30
-#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_SHIFT)
-#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_SHIFT 31
-#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_MASK I40E_MASK(0x1, I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_SHIFT)
-#define I40E_PRT_MNG_MDEFVSI(_i) (0x00256580 + ((_i) * 32)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_PRT_MNG_MDEFVSI_MAX_INDEX 3
-#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_SHIFT 0
-#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_SHIFT)
-#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_SHIFT 16
-#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_SHIFT)
-#define I40E_PRT_MNG_METF(_i) (0x00256780 + ((_i) * 32)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_PRT_MNG_METF_MAX_INDEX 3
-#define I40E_PRT_MNG_METF_ETYPE_SHIFT 0
-#define I40E_PRT_MNG_METF_ETYPE_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_METF_ETYPE_SHIFT)
-#define I40E_PRT_MNG_METF_POLARITY_SHIFT 30
-#define I40E_PRT_MNG_METF_POLARITY_MASK I40E_MASK(0x1, I40E_PRT_MNG_METF_POLARITY_SHIFT)
-#define I40E_PRT_MNG_MFUTP(_i) (0x00254E00 + ((_i) * 32)) /* _i=0...15 */ /* Reset: POR */
-#define I40E_PRT_MNG_MFUTP_MAX_INDEX 15
-#define I40E_PRT_MNG_MFUTP_MFUTP_N_SHIFT 0
-#define I40E_PRT_MNG_MFUTP_MFUTP_N_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_MFUTP_MFUTP_N_SHIFT)
-#define I40E_PRT_MNG_MFUTP_UDP_SHIFT 16
-#define I40E_PRT_MNG_MFUTP_UDP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MFUTP_UDP_SHIFT)
-#define I40E_PRT_MNG_MFUTP_TCP_SHIFT 17
-#define I40E_PRT_MNG_MFUTP_TCP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MFUTP_TCP_SHIFT)
-#define I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_SHIFT 18
-#define I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_MASK I40E_MASK(0x1, I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_SHIFT)
-#define I40E_PRT_MNG_MIPAF4(_i) (0x00256280 + ((_i) * 32)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_PRT_MNG_MIPAF4_MAX_INDEX 3
-#define I40E_PRT_MNG_MIPAF4_MIPAF_SHIFT 0
-#define I40E_PRT_MNG_MIPAF4_MIPAF_MASK I40E_MASK(0xFFFFFFFF, I40E_PRT_MNG_MIPAF4_MIPAF_SHIFT)
-#define I40E_PRT_MNG_MIPAF6(_i) (0x00254200 + ((_i) * 32)) /* _i=0...15 */ /* Reset: POR */
-#define I40E_PRT_MNG_MIPAF6_MAX_INDEX 15
-#define I40E_PRT_MNG_MIPAF6_MIPAF_SHIFT 0
-#define I40E_PRT_MNG_MIPAF6_MIPAF_MASK I40E_MASK(0xFFFFFFFF, I40E_PRT_MNG_MIPAF6_MIPAF_SHIFT)
-#define I40E_PRT_MNG_MMAH(_i) (0x00256380 + ((_i) * 32)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_PRT_MNG_MMAH_MAX_INDEX 3
-#define I40E_PRT_MNG_MMAH_MMAH_SHIFT 0
-#define I40E_PRT_MNG_MMAH_MMAH_MASK I40E_MASK(0xFFFF, I40E_PRT_MNG_MMAH_MMAH_SHIFT)
-#define I40E_PRT_MNG_MMAL(_i) (0x00256480 + ((_i) * 32)) /* _i=0...3 */ /* Reset: POR */
-#define I40E_PRT_MNG_MMAL_MAX_INDEX 3
-#define I40E_PRT_MNG_MMAL_MMAL_SHIFT 0
-#define I40E_PRT_MNG_MMAL_MMAL_MASK I40E_MASK(0xFFFFFFFF, I40E_PRT_MNG_MMAL_MMAL_SHIFT)
-#define I40E_PRT_MNG_MNGONLY 0x00256A60 /* Reset: POR */
-#define I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_SHIFT 0
-#define I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_MASK I40E_MASK(0xFF, I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_SHIFT)
-#define I40E_PRT_MNG_MSFM 0x00256AA0 /* Reset: POR */
-#define I40E_PRT_MNG_MSFM_PORT_26F_UDP_SHIFT 0
-#define I40E_PRT_MNG_MSFM_PORT_26F_UDP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_PORT_26F_UDP_SHIFT)
-#define I40E_PRT_MNG_MSFM_PORT_26F_TCP_SHIFT 1
-#define I40E_PRT_MNG_MSFM_PORT_26F_TCP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_PORT_26F_TCP_SHIFT)
-#define I40E_PRT_MNG_MSFM_PORT_298_UDP_SHIFT 2
-#define I40E_PRT_MNG_MSFM_PORT_298_UDP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_PORT_298_UDP_SHIFT)
-#define I40E_PRT_MNG_MSFM_PORT_298_TCP_SHIFT 3
-#define I40E_PRT_MNG_MSFM_PORT_298_TCP_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_PORT_298_TCP_SHIFT)
-#define I40E_PRT_MNG_MSFM_IPV6_0_MASK_SHIFT 4
-#define I40E_PRT_MNG_MSFM_IPV6_0_MASK_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_IPV6_0_MASK_SHIFT)
-#define I40E_PRT_MNG_MSFM_IPV6_1_MASK_SHIFT 5
-#define I40E_PRT_MNG_MSFM_IPV6_1_MASK_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_IPV6_1_MASK_SHIFT)
-#define I40E_PRT_MNG_MSFM_IPV6_2_MASK_SHIFT 6
-#define I40E_PRT_MNG_MSFM_IPV6_2_MASK_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_IPV6_2_MASK_SHIFT)
-#define I40E_PRT_MNG_MSFM_IPV6_3_MASK_SHIFT 7
-#define I40E_PRT_MNG_MSFM_IPV6_3_MASK_MASK I40E_MASK(0x1, I40E_PRT_MNG_MSFM_IPV6_3_MASK_SHIFT)
-#define I40E_MSIX_PBA(_i) (0x00001000 + ((_i) * 4)) /* _i=0...5 */ /* Reset: FLR */
-#define I40E_MSIX_PBA_MAX_INDEX 5
-#define I40E_MSIX_PBA_PENBIT_SHIFT 0
-#define I40E_MSIX_PBA_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_MSIX_PBA_PENBIT_SHIFT)
-#define I40E_MSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...128 */ /* Reset: FLR */
-#define I40E_MSIX_TADD_MAX_INDEX 128
-#define I40E_MSIX_TADD_MSIXTADD10_SHIFT 0
-#define I40E_MSIX_TADD_MSIXTADD10_MASK I40E_MASK(0x3, I40E_MSIX_TADD_MSIXTADD10_SHIFT)
-#define I40E_MSIX_TADD_MSIXTADD_SHIFT 2
-#define I40E_MSIX_TADD_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_MSIX_TADD_MSIXTADD_SHIFT)
-#define I40E_MSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...128 */ /* Reset: FLR */
-#define I40E_MSIX_TMSG_MAX_INDEX 128
-#define I40E_MSIX_TMSG_MSIXTMSG_SHIFT 0
-#define I40E_MSIX_TMSG_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_MSIX_TMSG_MSIXTMSG_SHIFT)
-#define I40E_MSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...128 */ /* Reset: FLR */
-#define I40E_MSIX_TUADD_MAX_INDEX 128
-#define I40E_MSIX_TUADD_MSIXTUADD_SHIFT 0
-#define I40E_MSIX_TUADD_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_MSIX_TUADD_MSIXTUADD_SHIFT)
-#define I40E_MSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...128 */ /* Reset: FLR */
-#define I40E_MSIX_TVCTRL_MAX_INDEX 128
-#define I40E_MSIX_TVCTRL_MASK_SHIFT 0
-#define I40E_MSIX_TVCTRL_MASK_MASK I40E_MASK(0x1, I40E_MSIX_TVCTRL_MASK_SHIFT)
-#define I40E_VFMSIX_PBA1(_i) (0x00002000 + ((_i) * 4)) /* _i=0...19 */ /* Reset: VFLR */
-#define I40E_VFMSIX_PBA1_MAX_INDEX 19
-#define I40E_VFMSIX_PBA1_PENBIT_SHIFT 0
-#define I40E_VFMSIX_PBA1_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA1_PENBIT_SHIFT)
-#define I40E_VFMSIX_TADD1(_i) (0x00002100 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TADD1_MAX_INDEX 639
-#define I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT 0
-#define I40E_VFMSIX_TADD1_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT)
-#define I40E_VFMSIX_TADD1_MSIXTADD_SHIFT 2
-#define I40E_VFMSIX_TADD1_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD1_MSIXTADD_SHIFT)
-#define I40E_VFMSIX_TMSG1(_i) (0x00002108 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TMSG1_MAX_INDEX 639
-#define I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT 0
-#define I40E_VFMSIX_TMSG1_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT)
-#define I40E_VFMSIX_TUADD1(_i) (0x00002104 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TUADD1_MAX_INDEX 639
-#define I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT 0
-#define I40E_VFMSIX_TUADD1_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT)
-#define I40E_VFMSIX_TVCTRL1(_i) (0x0000210C + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TVCTRL1_MAX_INDEX 639
-#define I40E_VFMSIX_TVCTRL1_MASK_SHIFT 0
-#define I40E_VFMSIX_TVCTRL1_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL1_MASK_SHIFT)
 #define I40E_GLNVM_FLA 0x000B6108 /* Reset: POR */
-#define I40E_GLNVM_FLA_FL_SCK_SHIFT 0
-#define I40E_GLNVM_FLA_FL_SCK_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_SCK_SHIFT)
-#define I40E_GLNVM_FLA_FL_CE_SHIFT 1
-#define I40E_GLNVM_FLA_FL_CE_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_CE_SHIFT)
-#define I40E_GLNVM_FLA_FL_SI_SHIFT 2
-#define I40E_GLNVM_FLA_FL_SI_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_SI_SHIFT)
-#define I40E_GLNVM_FLA_FL_SO_SHIFT 3
-#define I40E_GLNVM_FLA_FL_SO_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_SO_SHIFT)
-#define I40E_GLNVM_FLA_FL_REQ_SHIFT 4
-#define I40E_GLNVM_FLA_FL_REQ_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_REQ_SHIFT)
-#define I40E_GLNVM_FLA_FL_GNT_SHIFT 5
-#define I40E_GLNVM_FLA_FL_GNT_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_GNT_SHIFT)
 #define I40E_GLNVM_FLA_LOCKED_SHIFT 6
 #define I40E_GLNVM_FLA_LOCKED_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_LOCKED_SHIFT)
-#define I40E_GLNVM_FLA_FL_SADDR_SHIFT 18
-#define I40E_GLNVM_FLA_FL_SADDR_MASK I40E_MASK(0x7FF, I40E_GLNVM_FLA_FL_SADDR_SHIFT)
-#define I40E_GLNVM_FLA_FL_BUSY_SHIFT 30
-#define I40E_GLNVM_FLA_FL_BUSY_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_BUSY_SHIFT)
-#define I40E_GLNVM_FLA_FL_DER_SHIFT 31
-#define I40E_GLNVM_FLA_FL_DER_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_FL_DER_SHIFT)
-#define I40E_GLNVM_FLASHID 0x000B6104 /* Reset: POR */
-#define I40E_GLNVM_FLASHID_FLASHID_SHIFT 0
-#define I40E_GLNVM_FLASHID_FLASHID_MASK I40E_MASK(0xFFFFFF, I40E_GLNVM_FLASHID_FLASHID_SHIFT)
-#define I40E_GLNVM_FLASHID_FLEEP_PERF_SHIFT 31
-#define I40E_GLNVM_FLASHID_FLEEP_PERF_MASK I40E_MASK(0x1, I40E_GLNVM_FLASHID_FLEEP_PERF_SHIFT)
 #define I40E_GLNVM_GENS 0x000B6100 /* Reset: POR */
-#define I40E_GLNVM_GENS_NVM_PRES_SHIFT 0
-#define I40E_GLNVM_GENS_NVM_PRES_MASK I40E_MASK(0x1, I40E_GLNVM_GENS_NVM_PRES_SHIFT)
 #define I40E_GLNVM_GENS_SR_SIZE_SHIFT 5
 #define I40E_GLNVM_GENS_SR_SIZE_MASK I40E_MASK(0x7, I40E_GLNVM_GENS_SR_SIZE_SHIFT)
-#define I40E_GLNVM_GENS_BANK1VAL_SHIFT 8
-#define I40E_GLNVM_GENS_BANK1VAL_MASK I40E_MASK(0x1, I40E_GLNVM_GENS_BANK1VAL_SHIFT)
-#define I40E_GLNVM_GENS_ALT_PRST_SHIFT 23
-#define I40E_GLNVM_GENS_ALT_PRST_MASK I40E_MASK(0x1, I40E_GLNVM_GENS_ALT_PRST_SHIFT)
-#define I40E_GLNVM_GENS_FL_AUTO_RD_SHIFT 25
-#define I40E_GLNVM_GENS_FL_AUTO_RD_MASK I40E_MASK(0x1, I40E_GLNVM_GENS_FL_AUTO_RD_SHIFT)
-#define I40E_GLNVM_PROTCSR(_i) (0x000B6010 + ((_i) * 4)) /* _i=0...59 */ /* Reset: POR */
-#define I40E_GLNVM_PROTCSR_MAX_INDEX 59
-#define I40E_GLNVM_PROTCSR_ADDR_BLOCK_SHIFT 0
-#define I40E_GLNVM_PROTCSR_ADDR_BLOCK_MASK I40E_MASK(0xFFFFFF, I40E_GLNVM_PROTCSR_ADDR_BLOCK_SHIFT)
 #define I40E_GLNVM_SRCTL 0x000B6110 /* Reset: POR */
-#define I40E_GLNVM_SRCTL_SRBUSY_SHIFT 0
-#define I40E_GLNVM_SRCTL_SRBUSY_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_SRBUSY_SHIFT)
 #define I40E_GLNVM_SRCTL_ADDR_SHIFT 14
-#define I40E_GLNVM_SRCTL_ADDR_MASK I40E_MASK(0x7FFF, I40E_GLNVM_SRCTL_ADDR_SHIFT)
-#define I40E_GLNVM_SRCTL_WRITE_SHIFT 29
-#define I40E_GLNVM_SRCTL_WRITE_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_WRITE_SHIFT)
 #define I40E_GLNVM_SRCTL_START_SHIFT 30
-#define I40E_GLNVM_SRCTL_START_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_START_SHIFT)
 #define I40E_GLNVM_SRCTL_DONE_SHIFT 31
 #define I40E_GLNVM_SRCTL_DONE_MASK I40E_MASK(0x1u, I40E_GLNVM_SRCTL_DONE_SHIFT)
 #define I40E_GLNVM_SRDATA 0x000B6114 /* Reset: POR */
-#define I40E_GLNVM_SRDATA_WRDATA_SHIFT 0
-#define I40E_GLNVM_SRDATA_WRDATA_MASK I40E_MASK(0xFFFF, I40E_GLNVM_SRDATA_WRDATA_SHIFT)
 #define I40E_GLNVM_SRDATA_RDDATA_SHIFT 16
 #define I40E_GLNVM_SRDATA_RDDATA_MASK I40E_MASK(0xFFFF, I40E_GLNVM_SRDATA_RDDATA_SHIFT)
 #define I40E_GLNVM_ULD 0x000B6008 /* Reset: POR */
-#define I40E_GLNVM_ULD_CONF_PCIR_DONE_SHIFT 0
-#define I40E_GLNVM_ULD_CONF_PCIR_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_PCIR_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_PCIRTL_DONE_SHIFT 1
-#define I40E_GLNVM_ULD_CONF_PCIRTL_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_PCIRTL_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_LCB_DONE_SHIFT 2
-#define I40E_GLNVM_ULD_CONF_LCB_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_LCB_DONE_SHIFT)
 #define I40E_GLNVM_ULD_CONF_CORE_DONE_SHIFT 3
 #define I40E_GLNVM_ULD_CONF_CORE_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_CORE_DONE_SHIFT)
 #define I40E_GLNVM_ULD_CONF_GLOBAL_DONE_SHIFT 4
 #define I40E_GLNVM_ULD_CONF_GLOBAL_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_GLOBAL_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_POR_DONE_SHIFT 5
-#define I40E_GLNVM_ULD_CONF_POR_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_POR_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_PCIE_ANA_DONE_SHIFT 6
-#define I40E_GLNVM_ULD_CONF_PCIE_ANA_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_PCIE_ANA_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_PHY_ANA_DONE_SHIFT 7
-#define I40E_GLNVM_ULD_CONF_PHY_ANA_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_PHY_ANA_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_EMP_DONE_SHIFT 8
-#define I40E_GLNVM_ULD_CONF_EMP_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_EMP_DONE_SHIFT)
-#define I40E_GLNVM_ULD_CONF_PCIALT_DONE_SHIFT 9
-#define I40E_GLNVM_ULD_CONF_PCIALT_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CONF_PCIALT_DONE_SHIFT)
-#define I40E_GLPCI_BYTCTH 0x0009C484 /* Reset: PCIR */
-#define I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_SHIFT 0
-#define I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_SHIFT)
-#define I40E_GLPCI_BYTCTL 0x0009C488 /* Reset: PCIR */
-#define I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_SHIFT 0
-#define I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_SHIFT)
-#define I40E_GLPCI_CAPCTRL 0x000BE4A4 /* Reset: PCIR */
-#define I40E_GLPCI_CAPCTRL_VPD_EN_SHIFT 0
-#define I40E_GLPCI_CAPCTRL_VPD_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPCTRL_VPD_EN_SHIFT)
 #define I40E_GLPCI_CAPSUP 0x000BE4A8 /* Reset: PCIR */
-#define I40E_GLPCI_CAPSUP_PCIE_VER_SHIFT 0
-#define I40E_GLPCI_CAPSUP_PCIE_VER_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_PCIE_VER_SHIFT)
-#define I40E_GLPCI_CAPSUP_LTR_EN_SHIFT 2
-#define I40E_GLPCI_CAPSUP_LTR_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_LTR_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_TPH_EN_SHIFT 3
-#define I40E_GLPCI_CAPSUP_TPH_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_TPH_EN_SHIFT)
 #define I40E_GLPCI_CAPSUP_ARI_EN_SHIFT 4
 #define I40E_GLPCI_CAPSUP_ARI_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_ARI_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_IOV_EN_SHIFT 5
-#define I40E_GLPCI_CAPSUP_IOV_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_IOV_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_ACS_EN_SHIFT 6
-#define I40E_GLPCI_CAPSUP_ACS_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_ACS_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_SEC_EN_SHIFT 7
-#define I40E_GLPCI_CAPSUP_SEC_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_SEC_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_ECRC_GEN_EN_SHIFT 16
-#define I40E_GLPCI_CAPSUP_ECRC_GEN_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_ECRC_GEN_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_ECRC_CHK_EN_SHIFT 17
-#define I40E_GLPCI_CAPSUP_ECRC_CHK_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_ECRC_CHK_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_IDO_EN_SHIFT 18
-#define I40E_GLPCI_CAPSUP_IDO_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_IDO_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_MSI_MASK_SHIFT 19
-#define I40E_GLPCI_CAPSUP_MSI_MASK_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_MSI_MASK_SHIFT)
-#define I40E_GLPCI_CAPSUP_CSR_CONF_EN_SHIFT 20
-#define I40E_GLPCI_CAPSUP_CSR_CONF_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_CSR_CONF_EN_SHIFT)
-#define I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_SHIFT 30
-#define I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_SHIFT)
-#define I40E_GLPCI_CAPSUP_LOAD_DEV_ID_SHIFT 31
-#define I40E_GLPCI_CAPSUP_LOAD_DEV_ID_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_LOAD_DEV_ID_SHIFT)
-#define I40E_GLPCI_CNF 0x000BE4C0 /* Reset: POR */
-#define I40E_GLPCI_CNF_FLEX10_SHIFT 1
-#define I40E_GLPCI_CNF_FLEX10_MASK I40E_MASK(0x1, I40E_GLPCI_CNF_FLEX10_SHIFT)
-#define I40E_GLPCI_CNF_WAKE_PIN_EN_SHIFT 2
-#define I40E_GLPCI_CNF_WAKE_PIN_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CNF_WAKE_PIN_EN_SHIFT)
 #define I40E_GLPCI_CNF2 0x000BE494 /* Reset: PCIR */
-#define I40E_GLPCI_CNF2_RO_DIS_SHIFT 0
-#define I40E_GLPCI_CNF2_RO_DIS_MASK I40E_MASK(0x1, I40E_GLPCI_CNF2_RO_DIS_SHIFT)
-#define I40E_GLPCI_CNF2_CACHELINE_SIZE_SHIFT 1
-#define I40E_GLPCI_CNF2_CACHELINE_SIZE_MASK I40E_MASK(0x1, I40E_GLPCI_CNF2_CACHELINE_SIZE_SHIFT)
 #define I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT 2
 #define I40E_GLPCI_CNF2_MSI_X_PF_N_MASK I40E_MASK(0x7FF, I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT)
 #define I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT 13
 #define I40E_GLPCI_CNF2_MSI_X_VF_N_MASK I40E_MASK(0x7FF, I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT)
-#define I40E_GLPCI_DREVID 0x0009C480 /* Reset: PCIR */
-#define I40E_GLPCI_DREVID_DEFAULT_REVID_SHIFT 0
-#define I40E_GLPCI_DREVID_DEFAULT_REVID_MASK I40E_MASK(0xFF, I40E_GLPCI_DREVID_DEFAULT_REVID_SHIFT)
-#define I40E_GLPCI_GSCL_1 0x0009C48C /* Reset: PCIR */
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_SHIFT 0
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_SHIFT 1
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_SHIFT 2
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_SHIFT 3
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_SHIFT)
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_0_SHIFT 4
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_0_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_LBC_ENABLE_0_SHIFT)
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_1_SHIFT 5
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_1_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_LBC_ENABLE_1_SHIFT)
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_2_SHIFT 6
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_2_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_LBC_ENABLE_2_SHIFT)
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_3_SHIFT 7
-#define I40E_GLPCI_GSCL_1_LBC_ENABLE_3_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_LBC_ENABLE_3_SHIFT)
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_SHIFT 8
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_SHIFT)
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_SHIFT 9
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_MASK I40E_MASK(0x1F, I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_SHIFT)
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_SHIFT 14
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_SHIFT)
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_SHIFT 15
-#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_MASK I40E_MASK(0x1F, I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_SHIFT 28
-#define I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_SHIFT 29
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_SHIFT 30
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_SHIFT)
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_START_SHIFT 31
-#define I40E_GLPCI_GSCL_1_GIO_COUNT_START_MASK I40E_MASK(0x1, I40E_GLPCI_GSCL_1_GIO_COUNT_START_SHIFT)
-#define I40E_GLPCI_GSCL_2 0x0009C490 /* Reset: PCIR */
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_SHIFT 0
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_MASK I40E_MASK(0xFF, I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_SHIFT)
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_SHIFT 8
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_MASK I40E_MASK(0xFF, I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_SHIFT)
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_SHIFT 16
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_MASK I40E_MASK(0xFF, I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_SHIFT)
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_SHIFT 24
-#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_MASK I40E_MASK(0xFF, I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_SHIFT)
-#define I40E_GLPCI_GSCL_5_8(_i) (0x0009C494 + ((_i) * 4)) /* _i=0...3 */ /* Reset: PCIR */
-#define I40E_GLPCI_GSCL_5_8_MAX_INDEX 3
-#define I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_SHIFT 0
-#define I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_MASK I40E_MASK(0xFFFF, I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_SHIFT)
-#define I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_SHIFT 16
-#define I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_MASK I40E_MASK(0xFFFF, I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_SHIFT)
-#define I40E_GLPCI_GSCN_0_3(_i) (0x0009C4A4 + ((_i) * 4)) /* _i=0...3 */ /* Reset: PCIR */
-#define I40E_GLPCI_GSCN_0_3_MAX_INDEX 3
-#define I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_SHIFT 0
-#define I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_SHIFT)
 #define I40E_GLPCI_LBARCTRL 0x000BE484 /* Reset: POR */
-#define I40E_GLPCI_LBARCTRL_PREFBAR_SHIFT 0
-#define I40E_GLPCI_LBARCTRL_PREFBAR_MASK I40E_MASK(0x1, I40E_GLPCI_LBARCTRL_PREFBAR_SHIFT)
-#define I40E_GLPCI_LBARCTRL_BAR32_SHIFT 1
-#define I40E_GLPCI_LBARCTRL_BAR32_MASK I40E_MASK(0x1, I40E_GLPCI_LBARCTRL_BAR32_SHIFT)
-#define I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_SHIFT 3
-#define I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_MASK I40E_MASK(0x1, I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_SHIFT)
-#define I40E_GLPCI_LBARCTRL_RSVD_4_SHIFT 4
-#define I40E_GLPCI_LBARCTRL_RSVD_4_MASK I40E_MASK(0x3, I40E_GLPCI_LBARCTRL_RSVD_4_SHIFT)
 #define I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT 6
 #define I40E_GLPCI_LBARCTRL_FL_SIZE_MASK I40E_MASK(0x7, I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT)
-#define I40E_GLPCI_LBARCTRL_RSVD_10_SHIFT 10
-#define I40E_GLPCI_LBARCTRL_RSVD_10_MASK I40E_MASK(0x1, I40E_GLPCI_LBARCTRL_RSVD_10_SHIFT)
-#define I40E_GLPCI_LBARCTRL_EXROM_SIZE_SHIFT 11
-#define I40E_GLPCI_LBARCTRL_EXROM_SIZE_MASK I40E_MASK(0x7, I40E_GLPCI_LBARCTRL_EXROM_SIZE_SHIFT)
-#define I40E_GLPCI_LINKCAP 0x000BE4AC /* Reset: PCIR */
-#define I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_SHIFT 0
-#define I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_MASK I40E_MASK(0x3F, I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_SHIFT)
-#define I40E_GLPCI_LINKCAP_MAX_PAYLOAD_SHIFT 6
-#define I40E_GLPCI_LINKCAP_MAX_PAYLOAD_MASK I40E_MASK(0x7, I40E_GLPCI_LINKCAP_MAX_PAYLOAD_SHIFT)
-#define I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_SHIFT 9
-#define I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_MASK I40E_MASK(0xF, I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_SHIFT)
-#define I40E_GLPCI_PCIERR 0x000BE4FC /* Reset: PCIR */
-#define I40E_GLPCI_PCIERR_PCIE_ERR_REP_SHIFT 0
-#define I40E_GLPCI_PCIERR_PCIE_ERR_REP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_PCIERR_PCIE_ERR_REP_SHIFT)
-#define I40E_GLPCI_PKTCT 0x0009C4BC /* Reset: PCIR */
-#define I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_SHIFT 0
-#define I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_SHIFT)
-#define I40E_GLPCI_PM_MUX_NPQ 0x0009C4F4 /* Reset: PCIR */
-#define I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_SHIFT 0
-#define I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_MASK I40E_MASK(0x7, I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_SHIFT)
-#define I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_SHIFT 16
-#define I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_MASK I40E_MASK(0x1F, I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_SHIFT)
-#define I40E_GLPCI_PM_MUX_PFB 0x0009C4F0 /* Reset: PCIR */
-#define I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_SHIFT 0
-#define I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_MASK I40E_MASK(0x1F, I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_SHIFT)
-#define I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_SHIFT 16
-#define I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_MASK I40E_MASK(0x7, I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_SHIFT)
-#define I40E_GLPCI_PMSUP 0x000BE4B0 /* Reset: PCIR */
-#define I40E_GLPCI_PMSUP_ASPM_SUP_SHIFT 0
-#define I40E_GLPCI_PMSUP_ASPM_SUP_MASK I40E_MASK(0x3, I40E_GLPCI_PMSUP_ASPM_SUP_SHIFT)
-#define I40E_GLPCI_PMSUP_L0S_EXIT_LAT_SHIFT 2
-#define I40E_GLPCI_PMSUP_L0S_EXIT_LAT_MASK I40E_MASK(0x7, I40E_GLPCI_PMSUP_L0S_EXIT_LAT_SHIFT)
-#define I40E_GLPCI_PMSUP_L1_EXIT_LAT_SHIFT 5
-#define I40E_GLPCI_PMSUP_L1_EXIT_LAT_MASK I40E_MASK(0x7, I40E_GLPCI_PMSUP_L1_EXIT_LAT_SHIFT)
-#define I40E_GLPCI_PMSUP_L0S_ACC_LAT_SHIFT 8
-#define I40E_GLPCI_PMSUP_L0S_ACC_LAT_MASK I40E_MASK(0x7, I40E_GLPCI_PMSUP_L0S_ACC_LAT_SHIFT)
-#define I40E_GLPCI_PMSUP_L1_ACC_LAT_SHIFT 11
-#define I40E_GLPCI_PMSUP_L1_ACC_LAT_MASK I40E_MASK(0x7, I40E_GLPCI_PMSUP_L1_ACC_LAT_SHIFT)
-#define I40E_GLPCI_PMSUP_SLOT_CLK_SHIFT 14
-#define I40E_GLPCI_PMSUP_SLOT_CLK_MASK I40E_MASK(0x1, I40E_GLPCI_PMSUP_SLOT_CLK_SHIFT)
-#define I40E_GLPCI_PMSUP_OBFF_SUP_SHIFT 15
-#define I40E_GLPCI_PMSUP_OBFF_SUP_MASK I40E_MASK(0x3, I40E_GLPCI_PMSUP_OBFF_SUP_SHIFT)
-#define I40E_GLPCI_PQ_MAX_USED_SPC 0x0009C4EC /* Reset: PCIR */
-#define I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_12_SHIFT 0
-#define I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_12_MASK I40E_MASK(0xFF, I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_12_SHIFT)
-#define I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_13_SHIFT 8
-#define I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_13_MASK I40E_MASK(0xFF, I40E_GLPCI_PQ_MAX_USED_SPC_GLPCI_PQ_MAX_USED_SPC_13_SHIFT)
-#define I40E_GLPCI_PWRDATA 0x000BE490 /* Reset: PCIR */
-#define I40E_GLPCI_PWRDATA_D0_POWER_SHIFT 0
-#define I40E_GLPCI_PWRDATA_D0_POWER_MASK I40E_MASK(0xFF, I40E_GLPCI_PWRDATA_D0_POWER_SHIFT)
-#define I40E_GLPCI_PWRDATA_COMM_POWER_SHIFT 8
-#define I40E_GLPCI_PWRDATA_COMM_POWER_MASK I40E_MASK(0xFF, I40E_GLPCI_PWRDATA_COMM_POWER_SHIFT)
-#define I40E_GLPCI_PWRDATA_D3_POWER_SHIFT 16
-#define I40E_GLPCI_PWRDATA_D3_POWER_MASK I40E_MASK(0xFF, I40E_GLPCI_PWRDATA_D3_POWER_SHIFT)
-#define I40E_GLPCI_PWRDATA_DATA_SCALE_SHIFT 24
-#define I40E_GLPCI_PWRDATA_DATA_SCALE_MASK I40E_MASK(0x3, I40E_GLPCI_PWRDATA_DATA_SCALE_SHIFT)
-#define I40E_GLPCI_REVID 0x000BE4B4 /* Reset: PCIR */
-#define I40E_GLPCI_REVID_NVM_REVID_SHIFT 0
-#define I40E_GLPCI_REVID_NVM_REVID_MASK I40E_MASK(0xFF, I40E_GLPCI_REVID_NVM_REVID_SHIFT)
-#define I40E_GLPCI_SERH 0x000BE49C /* Reset: PCIR */
-#define I40E_GLPCI_SERH_SER_NUM_H_SHIFT 0
-#define I40E_GLPCI_SERH_SER_NUM_H_MASK I40E_MASK(0xFFFF, I40E_GLPCI_SERH_SER_NUM_H_SHIFT)
-#define I40E_GLPCI_SERL 0x000BE498 /* Reset: PCIR */
-#define I40E_GLPCI_SERL_SER_NUM_L_SHIFT 0
-#define I40E_GLPCI_SERL_SER_NUM_L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_SERL_SER_NUM_L_SHIFT)
-#define I40E_GLPCI_SPARE_BITS_0 0x0009C4F8 /* Reset: PCIR */
-#define I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_SHIFT 0
-#define I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_SHIFT)
-#define I40E_GLPCI_SPARE_BITS_1 0x0009C4FC /* Reset: PCIR */
-#define I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_SHIFT 0
-#define I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_SHIFT)
-#define I40E_GLPCI_SUBVENID 0x000BE48C /* Reset: PCIR */
-#define I40E_GLPCI_SUBVENID_SUB_VEN_ID_SHIFT 0
-#define I40E_GLPCI_SUBVENID_SUB_VEN_ID_MASK I40E_MASK(0xFFFF, I40E_GLPCI_SUBVENID_SUB_VEN_ID_SHIFT)
-#define I40E_GLPCI_UPADD 0x000BE4F8 /* Reset: PCIR */
-#define I40E_GLPCI_UPADD_ADDRESS_SHIFT 1
-#define I40E_GLPCI_UPADD_ADDRESS_MASK I40E_MASK(0x7FFFFFFF, I40E_GLPCI_UPADD_ADDRESS_SHIFT)
-#define I40E_GLPCI_VENDORID 0x000BE518 /* Reset: PCIR */
-#define I40E_GLPCI_VENDORID_VENDORID_SHIFT 0
-#define I40E_GLPCI_VENDORID_VENDORID_MASK I40E_MASK(0xFFFF, I40E_GLPCI_VENDORID_VENDORID_SHIFT)
-#define I40E_GLPCI_VFSUP 0x000BE4B8 /* Reset: PCIR */
-#define I40E_GLPCI_VFSUP_VF_PREFETCH_SHIFT 0
-#define I40E_GLPCI_VFSUP_VF_PREFETCH_MASK I40E_MASK(0x1, I40E_GLPCI_VFSUP_VF_PREFETCH_SHIFT)
-#define I40E_GLPCI_VFSUP_VR_BAR_TYPE_SHIFT 1
-#define I40E_GLPCI_VFSUP_VR_BAR_TYPE_MASK I40E_MASK(0x1, I40E_GLPCI_VFSUP_VR_BAR_TYPE_SHIFT)
-#define I40E_GLTPH_CTRL 0x000BE480 /* Reset: PCIR */
-#define I40E_GLTPH_CTRL_DESC_PH_SHIFT 9
-#define I40E_GLTPH_CTRL_DESC_PH_MASK I40E_MASK(0x3, I40E_GLTPH_CTRL_DESC_PH_SHIFT)
-#define I40E_GLTPH_CTRL_DATA_PH_SHIFT 11
-#define I40E_GLTPH_CTRL_DATA_PH_MASK I40E_MASK(0x3, I40E_GLTPH_CTRL_DATA_PH_SHIFT)
 #define I40E_PF_FUNC_RID 0x0009C000 /* Reset: PCIR */
-#define I40E_PF_FUNC_RID_FUNCTION_NUMBER_SHIFT 0
-#define I40E_PF_FUNC_RID_FUNCTION_NUMBER_MASK I40E_MASK(0x7, I40E_PF_FUNC_RID_FUNCTION_NUMBER_SHIFT)
-#define I40E_PF_FUNC_RID_DEVICE_NUMBER_SHIFT 3
-#define I40E_PF_FUNC_RID_DEVICE_NUMBER_MASK I40E_MASK(0x1F, I40E_PF_FUNC_RID_DEVICE_NUMBER_SHIFT)
-#define I40E_PF_FUNC_RID_BUS_NUMBER_SHIFT 8
-#define I40E_PF_FUNC_RID_BUS_NUMBER_MASK I40E_MASK(0xFF, I40E_PF_FUNC_RID_BUS_NUMBER_SHIFT)
 #define I40E_PF_PCI_CIAA 0x0009C080 /* Reset: FLR */
-#define I40E_PF_PCI_CIAA_ADDRESS_SHIFT 0
-#define I40E_PF_PCI_CIAA_ADDRESS_MASK I40E_MASK(0xFFF, I40E_PF_PCI_CIAA_ADDRESS_SHIFT)
 #define I40E_PF_PCI_CIAA_VF_NUM_SHIFT 12
-#define I40E_PF_PCI_CIAA_VF_NUM_MASK I40E_MASK(0x7F, I40E_PF_PCI_CIAA_VF_NUM_SHIFT)
 #define I40E_PF_PCI_CIAD 0x0009C100 /* Reset: FLR */
-#define I40E_PF_PCI_CIAD_DATA_SHIFT 0
-#define I40E_PF_PCI_CIAD_DATA_MASK I40E_MASK(0xFFFFFFFF, I40E_PF_PCI_CIAD_DATA_SHIFT)
-#define I40E_PFPCI_CLASS 0x000BE400 /* Reset: PCIR */
-#define I40E_PFPCI_CLASS_STORAGE_CLASS_SHIFT 0
-#define I40E_PFPCI_CLASS_STORAGE_CLASS_MASK I40E_MASK(0x1, I40E_PFPCI_CLASS_STORAGE_CLASS_SHIFT)
-#define I40E_PFPCI_CLASS_RESERVED_1_SHIFT 1
-#define I40E_PFPCI_CLASS_RESERVED_1_MASK I40E_MASK(0x1, I40E_PFPCI_CLASS_RESERVED_1_SHIFT)
-#define I40E_PFPCI_CLASS_PF_IS_LAN_SHIFT 2
-#define I40E_PFPCI_CLASS_PF_IS_LAN_MASK I40E_MASK(0x1, I40E_PFPCI_CLASS_PF_IS_LAN_SHIFT)
-#define I40E_PFPCI_CNF 0x000BE000 /* Reset: PCIR */
-#define I40E_PFPCI_CNF_MSI_EN_SHIFT 2
-#define I40E_PFPCI_CNF_MSI_EN_MASK I40E_MASK(0x1, I40E_PFPCI_CNF_MSI_EN_SHIFT)
-#define I40E_PFPCI_CNF_EXROM_DIS_SHIFT 3
-#define I40E_PFPCI_CNF_EXROM_DIS_MASK I40E_MASK(0x1, I40E_PFPCI_CNF_EXROM_DIS_SHIFT)
-#define I40E_PFPCI_CNF_IO_BAR_SHIFT 4
-#define I40E_PFPCI_CNF_IO_BAR_MASK I40E_MASK(0x1, I40E_PFPCI_CNF_IO_BAR_SHIFT)
-#define I40E_PFPCI_CNF_INT_PIN_SHIFT 5
-#define I40E_PFPCI_CNF_INT_PIN_MASK I40E_MASK(0x3, I40E_PFPCI_CNF_INT_PIN_SHIFT)
-#define I40E_PFPCI_DEVID 0x000BE080 /* Reset: PCIR */
-#define I40E_PFPCI_DEVID_PF_DEV_ID_SHIFT 0
-#define I40E_PFPCI_DEVID_PF_DEV_ID_MASK I40E_MASK(0xFFFF, I40E_PFPCI_DEVID_PF_DEV_ID_SHIFT)
-#define I40E_PFPCI_DEVID_VF_DEV_ID_SHIFT 16
-#define I40E_PFPCI_DEVID_VF_DEV_ID_MASK I40E_MASK(0xFFFF, I40E_PFPCI_DEVID_VF_DEV_ID_SHIFT)
-#define I40E_PFPCI_FACTPS 0x0009C180 /* Reset: FLR */
-#define I40E_PFPCI_FACTPS_FUNC_POWER_STATE_SHIFT 0
-#define I40E_PFPCI_FACTPS_FUNC_POWER_STATE_MASK I40E_MASK(0x3, I40E_PFPCI_FACTPS_FUNC_POWER_STATE_SHIFT)
-#define I40E_PFPCI_FACTPS_FUNC_AUX_EN_SHIFT 3
-#define I40E_PFPCI_FACTPS_FUNC_AUX_EN_MASK I40E_MASK(0x1, I40E_PFPCI_FACTPS_FUNC_AUX_EN_SHIFT)
-#define I40E_PFPCI_FUNC 0x000BE200 /* Reset: POR */
-#define I40E_PFPCI_FUNC_FUNC_DIS_SHIFT 0
-#define I40E_PFPCI_FUNC_FUNC_DIS_MASK I40E_MASK(0x1, I40E_PFPCI_FUNC_FUNC_DIS_SHIFT)
-#define I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_SHIFT 1
-#define I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_MASK I40E_MASK(0x1, I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_SHIFT)
-#define I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_SHIFT 2
-#define I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_MASK I40E_MASK(0x1, I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_SHIFT)
-#define I40E_PFPCI_FUNC2 0x000BE180 /* Reset: PCIR */
-#define I40E_PFPCI_FUNC2_EMP_FUNC_DIS_SHIFT 0
-#define I40E_PFPCI_FUNC2_EMP_FUNC_DIS_MASK I40E_MASK(0x1, I40E_PFPCI_FUNC2_EMP_FUNC_DIS_SHIFT)
-#define I40E_PFPCI_ICAUSE 0x0009C200 /* Reset: PFR */
-#define I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_SHIFT 0
-#define I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_SHIFT)
-#define I40E_PFPCI_IENA 0x0009C280 /* Reset: PFR */
-#define I40E_PFPCI_IENA_PCIE_ERR_EN_SHIFT 0
-#define I40E_PFPCI_IENA_PCIE_ERR_EN_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPCI_IENA_PCIE_ERR_EN_SHIFT)
-#define I40E_PFPCI_PF_FLUSH_DONE 0x0009C800 /* Reset: PCIR */
-#define I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_SHIFT 0
-#define I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_MASK I40E_MASK(0x1, I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_SHIFT)
-#define I40E_PFPCI_PM 0x000BE300 /* Reset: POR */
-#define I40E_PFPCI_PM_PME_EN_SHIFT 0
-#define I40E_PFPCI_PM_PME_EN_MASK I40E_MASK(0x1, I40E_PFPCI_PM_PME_EN_SHIFT)
-#define I40E_PFPCI_STATUS1 0x000BE280 /* Reset: POR */
-#define I40E_PFPCI_STATUS1_FUNC_VALID_SHIFT 0
-#define I40E_PFPCI_STATUS1_FUNC_VALID_MASK I40E_MASK(0x1, I40E_PFPCI_STATUS1_FUNC_VALID_SHIFT)
-#define I40E_PFPCI_SUBSYSID 0x000BE100 /* Reset: PCIR */
-#define I40E_PFPCI_SUBSYSID_PF_SUBSYS_ID_SHIFT 0
-#define I40E_PFPCI_SUBSYSID_PF_SUBSYS_ID_MASK I40E_MASK(0xFFFF, I40E_PFPCI_SUBSYSID_PF_SUBSYS_ID_SHIFT)
-#define I40E_PFPCI_SUBSYSID_VF_SUBSYS_ID_SHIFT 16
-#define I40E_PFPCI_SUBSYSID_VF_SUBSYS_ID_MASK I40E_MASK(0xFFFF, I40E_PFPCI_SUBSYSID_VF_SUBSYS_ID_SHIFT)
-#define I40E_PFPCI_VF_FLUSH_DONE 0x0000E400 /* Reset: PCIR */
-#define I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_SHIFT 0
-#define I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_MASK I40E_MASK(0x1, I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_SHIFT)
-#define I40E_PFPCI_VF_FLUSH_DONE1(_VF) (0x0009C600 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: PCIR */
-#define I40E_PFPCI_VF_FLUSH_DONE1_MAX_INDEX 127
-#define I40E_PFPCI_VF_FLUSH_DONE1_FLUSH_DONE_SHIFT 0
-#define I40E_PFPCI_VF_FLUSH_DONE1_FLUSH_DONE_MASK I40E_MASK(0x1, I40E_PFPCI_VF_FLUSH_DONE1_FLUSH_DONE_SHIFT)
-#define I40E_PFPCI_VM_FLUSH_DONE 0x0009C880 /* Reset: PCIR */
-#define I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_SHIFT 0
-#define I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_MASK I40E_MASK(0x1, I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_SHIFT)
-#define I40E_PFPCI_VMINDEX 0x0009C300 /* Reset: PCIR */
-#define I40E_PFPCI_VMINDEX_VMINDEX_SHIFT 0
-#define I40E_PFPCI_VMINDEX_VMINDEX_MASK I40E_MASK(0x1FF, I40E_PFPCI_VMINDEX_VMINDEX_SHIFT)
-#define I40E_PFPCI_VMPEND 0x0009C380 /* Reset: PCIR */
-#define I40E_PFPCI_VMPEND_PENDING_SHIFT 0
-#define I40E_PFPCI_VMPEND_PENDING_MASK I40E_MASK(0x1, I40E_PFPCI_VMPEND_PENDING_SHIFT)
 #define I40E_PRTPM_EEE_STAT 0x001E4320 /* Reset: GLOBR */
-#define I40E_PRTPM_EEE_STAT_EEE_NEG_SHIFT 29
-#define I40E_PRTPM_EEE_STAT_EEE_NEG_MASK I40E_MASK(0x1, I40E_PRTPM_EEE_STAT_EEE_NEG_SHIFT)
 #define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT 30
 #define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK I40E_MASK(0x1, I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT)
 #define I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT 31
 #define I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK I40E_MASK(0x1, I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT)
-#define I40E_PRTPM_EEEC 0x001E4380 /* Reset: GLOBR */
-#define I40E_PRTPM_EEEC_TW_WAKE_MIN_SHIFT 16
-#define I40E_PRTPM_EEEC_TW_WAKE_MIN_MASK I40E_MASK(0x3F, I40E_PRTPM_EEEC_TW_WAKE_MIN_SHIFT)
-#define I40E_PRTPM_EEEC_TX_LU_LPI_DLY_SHIFT 24
-#define I40E_PRTPM_EEEC_TX_LU_LPI_DLY_MASK I40E_MASK(0x3, I40E_PRTPM_EEEC_TX_LU_LPI_DLY_SHIFT)
-#define I40E_PRTPM_EEEC_TEEE_DLY_SHIFT 26
-#define I40E_PRTPM_EEEC_TEEE_DLY_MASK I40E_MASK(0x3F, I40E_PRTPM_EEEC_TEEE_DLY_SHIFT)
-#define I40E_PRTPM_EEEFWD 0x001E4400 /* Reset: GLOBR */
-#define I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_SHIFT 31
-#define I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_MASK I40E_MASK(0x1, I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_SHIFT)
-#define I40E_PRTPM_EEER 0x001E4360 /* Reset: GLOBR */
-#define I40E_PRTPM_EEER_TW_SYSTEM_SHIFT 0
-#define I40E_PRTPM_EEER_TW_SYSTEM_MASK I40E_MASK(0xFFFF, I40E_PRTPM_EEER_TW_SYSTEM_SHIFT)
-#define I40E_PRTPM_EEER_TX_LPI_EN_SHIFT 16
-#define I40E_PRTPM_EEER_TX_LPI_EN_MASK I40E_MASK(0x1, I40E_PRTPM_EEER_TX_LPI_EN_SHIFT)
-#define I40E_PRTPM_EEETXC 0x001E43E0 /* Reset: GLOBR */
-#define I40E_PRTPM_EEETXC_TW_PHY_SHIFT 0
-#define I40E_PRTPM_EEETXC_TW_PHY_MASK I40E_MASK(0xFFFF, I40E_PRTPM_EEETXC_TW_PHY_SHIFT)
-#define I40E_PRTPM_GC 0x000B8140 /* Reset: POR */
-#define I40E_PRTPM_GC_EMP_LINK_ON_SHIFT 0
-#define I40E_PRTPM_GC_EMP_LINK_ON_MASK I40E_MASK(0x1, I40E_PRTPM_GC_EMP_LINK_ON_SHIFT)
-#define I40E_PRTPM_GC_MNG_VETO_SHIFT 1
-#define I40E_PRTPM_GC_MNG_VETO_MASK I40E_MASK(0x1, I40E_PRTPM_GC_MNG_VETO_SHIFT)
-#define I40E_PRTPM_GC_RATD_SHIFT 2
-#define I40E_PRTPM_GC_RATD_MASK I40E_MASK(0x1, I40E_PRTPM_GC_RATD_SHIFT)
-#define I40E_PRTPM_GC_LCDMP_SHIFT 3
-#define I40E_PRTPM_GC_LCDMP_MASK I40E_MASK(0x1, I40E_PRTPM_GC_LCDMP_SHIFT)
-#define I40E_PRTPM_GC_LPLU_ASSERTED_SHIFT 31
-#define I40E_PRTPM_GC_LPLU_ASSERTED_MASK I40E_MASK(0x1, I40E_PRTPM_GC_LPLU_ASSERTED_SHIFT)
 #define I40E_PRTPM_RLPIC 0x001E43A0 /* Reset: GLOBR */
-#define I40E_PRTPM_RLPIC_ERLPIC_SHIFT 0
-#define I40E_PRTPM_RLPIC_ERLPIC_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTPM_RLPIC_ERLPIC_SHIFT)
 #define I40E_PRTPM_TLPIC 0x001E43C0 /* Reset: GLOBR */
-#define I40E_PRTPM_TLPIC_ETLPIC_SHIFT 0
-#define I40E_PRTPM_TLPIC_ETLPIC_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTPM_TLPIC_ETLPIC_SHIFT)
-#define I40E_GL_PRS_FVBM(_i) (0x00269760 + ((_i) * 4)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GL_PRS_FVBM_MAX_INDEX 3
-#define I40E_GL_PRS_FVBM_FV_BYTE_INDX_SHIFT 0
-#define I40E_GL_PRS_FVBM_FV_BYTE_INDX_MASK I40E_MASK(0x7F, I40E_GL_PRS_FVBM_FV_BYTE_INDX_SHIFT)
-#define I40E_GL_PRS_FVBM_RULE_BUS_INDX_SHIFT 8
-#define I40E_GL_PRS_FVBM_RULE_BUS_INDX_MASK I40E_MASK(0x3F, I40E_GL_PRS_FVBM_RULE_BUS_INDX_SHIFT)
-#define I40E_GL_PRS_FVBM_MSK_ENA_SHIFT 31
-#define I40E_GL_PRS_FVBM_MSK_ENA_MASK I40E_MASK(0x1, I40E_GL_PRS_FVBM_MSK_ENA_SHIFT)
-#define I40E_GLRPB_DPSS 0x000AC828 /* Reset: CORER */
-#define I40E_GLRPB_DPSS_DPS_TCN_SHIFT 0
-#define I40E_GLRPB_DPSS_DPS_TCN_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_DPSS_DPS_TCN_SHIFT)
-#define I40E_GLRPB_GHW 0x000AC830 /* Reset: CORER */
-#define I40E_GLRPB_GHW_GHW_SHIFT 0
-#define I40E_GLRPB_GHW_GHW_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_GHW_GHW_SHIFT)
-#define I40E_GLRPB_GLW 0x000AC834 /* Reset: CORER */
-#define I40E_GLRPB_GLW_GLW_SHIFT 0
-#define I40E_GLRPB_GLW_GLW_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_GLW_GLW_SHIFT)
-#define I40E_GLRPB_PHW 0x000AC844 /* Reset: CORER */
-#define I40E_GLRPB_PHW_PHW_SHIFT 0
-#define I40E_GLRPB_PHW_PHW_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_PHW_PHW_SHIFT)
-#define I40E_GLRPB_PLW 0x000AC848 /* Reset: CORER */
-#define I40E_GLRPB_PLW_PLW_SHIFT 0
-#define I40E_GLRPB_PLW_PLW_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_PLW_PLW_SHIFT)
-#define I40E_PRTRPB_DHW(_i) (0x000AC100 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTRPB_DHW_MAX_INDEX 7
-#define I40E_PRTRPB_DHW_DHW_TCN_SHIFT 0
-#define I40E_PRTRPB_DHW_DHW_TCN_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_DHW_DHW_TCN_SHIFT)
-#define I40E_PRTRPB_DLW(_i) (0x000AC220 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTRPB_DLW_MAX_INDEX 7
-#define I40E_PRTRPB_DLW_DLW_TCN_SHIFT 0
-#define I40E_PRTRPB_DLW_DLW_TCN_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_DLW_DLW_TCN_SHIFT)
-#define I40E_PRTRPB_DPS(_i) (0x000AC320 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTRPB_DPS_MAX_INDEX 7
-#define I40E_PRTRPB_DPS_DPS_TCN_SHIFT 0
-#define I40E_PRTRPB_DPS_DPS_TCN_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_DPS_DPS_TCN_SHIFT)
-#define I40E_PRTRPB_SHT(_i) (0x000AC480 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTRPB_SHT_MAX_INDEX 7
-#define I40E_PRTRPB_SHT_SHT_TCN_SHIFT 0
-#define I40E_PRTRPB_SHT_SHT_TCN_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_SHT_SHT_TCN_SHIFT)
-#define I40E_PRTRPB_SHW 0x000AC580 /* Reset: CORER */
-#define I40E_PRTRPB_SHW_SHW_SHIFT 0
-#define I40E_PRTRPB_SHW_SHW_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_SHW_SHW_SHIFT)
-#define I40E_PRTRPB_SLT(_i) (0x000AC5A0 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTRPB_SLT_MAX_INDEX 7
-#define I40E_PRTRPB_SLT_SLT_TCN_SHIFT 0
-#define I40E_PRTRPB_SLT_SLT_TCN_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_SLT_SLT_TCN_SHIFT)
-#define I40E_PRTRPB_SLW 0x000AC6A0 /* Reset: CORER */
-#define I40E_PRTRPB_SLW_SLW_SHIFT 0
-#define I40E_PRTRPB_SLW_SLW_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_SLW_SLW_SHIFT)
-#define I40E_PRTRPB_SPS 0x000AC7C0 /* Reset: CORER */
-#define I40E_PRTRPB_SPS_SPS_SHIFT 0
-#define I40E_PRTRPB_SPS_SPS_MASK I40E_MASK(0xFFFFF, I40E_PRTRPB_SPS_SPS_SHIFT)
-#define I40E_GLQF_CTL 0x00269BA4 /* Reset: CORER */
-#define I40E_GLQF_CTL_HTOEP_SHIFT 1
-#define I40E_GLQF_CTL_HTOEP_MASK I40E_MASK(0x1, I40E_GLQF_CTL_HTOEP_SHIFT)
-#define I40E_GLQF_CTL_HTOEP_FCOE_SHIFT 2
-#define I40E_GLQF_CTL_HTOEP_FCOE_MASK I40E_MASK(0x1, I40E_GLQF_CTL_HTOEP_FCOE_SHIFT)
-#define I40E_GLQF_CTL_PCNT_ALLOC_SHIFT 3
-#define I40E_GLQF_CTL_PCNT_ALLOC_MASK I40E_MASK(0x7, I40E_GLQF_CTL_PCNT_ALLOC_SHIFT)
-#define I40E_GLQF_CTL_FD_AUTO_PCTYPE_SHIFT 6
-#define I40E_GLQF_CTL_FD_AUTO_PCTYPE_MASK I40E_MASK(0x1, I40E_GLQF_CTL_FD_AUTO_PCTYPE_SHIFT)
-#define I40E_GLQF_CTL_RSVD_SHIFT 7
-#define I40E_GLQF_CTL_RSVD_MASK I40E_MASK(0x1, I40E_GLQF_CTL_RSVD_SHIFT)
-#define I40E_GLQF_CTL_MAXPEBLEN_SHIFT 8
-#define I40E_GLQF_CTL_MAXPEBLEN_MASK I40E_MASK(0x7, I40E_GLQF_CTL_MAXPEBLEN_SHIFT)
-#define I40E_GLQF_CTL_MAXFCBLEN_SHIFT 11
-#define I40E_GLQF_CTL_MAXFCBLEN_MASK I40E_MASK(0x7, I40E_GLQF_CTL_MAXFCBLEN_SHIFT)
-#define I40E_GLQF_CTL_MAXFDBLEN_SHIFT 14
-#define I40E_GLQF_CTL_MAXFDBLEN_MASK I40E_MASK(0x7, I40E_GLQF_CTL_MAXFDBLEN_SHIFT)
-#define I40E_GLQF_CTL_FDBEST_SHIFT 17
-#define I40E_GLQF_CTL_FDBEST_MASK I40E_MASK(0xFF, I40E_GLQF_CTL_FDBEST_SHIFT)
-#define I40E_GLQF_CTL_PROGPRIO_SHIFT 25
-#define I40E_GLQF_CTL_PROGPRIO_MASK I40E_MASK(0x1, I40E_GLQF_CTL_PROGPRIO_SHIFT)
-#define I40E_GLQF_CTL_INVALPRIO_SHIFT 26
-#define I40E_GLQF_CTL_INVALPRIO_MASK I40E_MASK(0x1, I40E_GLQF_CTL_INVALPRIO_SHIFT)
-#define I40E_GLQF_CTL_IGNORE_IP_SHIFT 27
-#define I40E_GLQF_CTL_IGNORE_IP_MASK I40E_MASK(0x1, I40E_GLQF_CTL_IGNORE_IP_SHIFT)
 #define I40E_GLQF_FDCNT_0 0x00269BAC /* Reset: CORER */
 #define I40E_GLQF_FDCNT_0_GUARANT_CNT_SHIFT 0
 #define I40E_GLQF_FDCNT_0_GUARANT_CNT_MASK I40E_MASK(0x1FFF, I40E_GLQF_FDCNT_0_GUARANT_CNT_SHIFT)
@@ -2112,36 +405,7 @@
 #define I40E_GLQF_FDCNT_0_BESTCNT_MASK I40E_MASK(0x1FFF, I40E_GLQF_FDCNT_0_BESTCNT_SHIFT)
 #define I40E_GLQF_HKEY(_i) (0x00270140 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */
 #define I40E_GLQF_HKEY_MAX_INDEX 12
-#define I40E_GLQF_HKEY_KEY_0_SHIFT 0
-#define I40E_GLQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_GLQF_HKEY_KEY_0_SHIFT)
-#define I40E_GLQF_HKEY_KEY_1_SHIFT 8
-#define I40E_GLQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_GLQF_HKEY_KEY_1_SHIFT)
-#define I40E_GLQF_HKEY_KEY_2_SHIFT 16
-#define I40E_GLQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_GLQF_HKEY_KEY_2_SHIFT)
-#define I40E_GLQF_HKEY_KEY_3_SHIFT 24
-#define I40E_GLQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_GLQF_HKEY_KEY_3_SHIFT)
-#define I40E_GLQF_HSYM(_i) (0x00269D00 + ((_i) * 4)) /* _i=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_HSYM_MAX_INDEX 63
-#define I40E_GLQF_HSYM_SYMH_ENA_SHIFT 0
-#define I40E_GLQF_HSYM_SYMH_ENA_MASK I40E_MASK(0x1, I40E_GLQF_HSYM_SYMH_ENA_SHIFT)
 #define I40E_GLQF_PCNT(_i) (0x00266800 + ((_i) * 4)) /* _i=0...511 */ /* Reset: CORER */
-#define I40E_GLQF_PCNT_MAX_INDEX 511
-#define I40E_GLQF_PCNT_PCNT_SHIFT 0
-#define I40E_GLQF_PCNT_PCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLQF_PCNT_PCNT_SHIFT)
-#define I40E_GLQF_SWAP(_i, _j) (0x00267E00 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_SWAP_MAX_INDEX 1
-#define I40E_GLQF_SWAP_OFF0_SRC0_SHIFT 0
-#define I40E_GLQF_SWAP_OFF0_SRC0_MASK I40E_MASK(0x3F, I40E_GLQF_SWAP_OFF0_SRC0_SHIFT)
-#define I40E_GLQF_SWAP_OFF0_SRC1_SHIFT 6
-#define I40E_GLQF_SWAP_OFF0_SRC1_MASK I40E_MASK(0x3F, I40E_GLQF_SWAP_OFF0_SRC1_SHIFT)
-#define I40E_GLQF_SWAP_FLEN0_SHIFT 12
-#define I40E_GLQF_SWAP_FLEN0_MASK I40E_MASK(0xF, I40E_GLQF_SWAP_FLEN0_SHIFT)
-#define I40E_GLQF_SWAP_OFF1_SRC0_SHIFT 16
-#define I40E_GLQF_SWAP_OFF1_SRC0_MASK I40E_MASK(0x3F, I40E_GLQF_SWAP_OFF1_SRC0_SHIFT)
-#define I40E_GLQF_SWAP_OFF1_SRC1_SHIFT 22
-#define I40E_GLQF_SWAP_OFF1_SRC1_MASK I40E_MASK(0x3F, I40E_GLQF_SWAP_OFF1_SRC1_SHIFT)
-#define I40E_GLQF_SWAP_FLEN1_SHIFT 28
-#define I40E_GLQF_SWAP_FLEN1_MASK I40E_MASK(0xF, I40E_GLQF_SWAP_FLEN1_SHIFT)
 #define I40E_PFQF_CTL_0 0x001C0AC0 /* Reset: CORER */
 #define I40E_PFQF_CTL_0_PEHSIZE_SHIFT 0
 #define I40E_PFQF_CTL_0_PEHSIZE_MASK I40E_MASK(0x1F, I40E_PFQF_CTL_0_PEHSIZE_SHIFT)
@@ -2159,54 +423,19 @@
 #define I40E_PFQF_CTL_0_ETYPE_ENA_MASK I40E_MASK(0x1, I40E_PFQF_CTL_0_ETYPE_ENA_SHIFT)
 #define I40E_PFQF_CTL_0_MACVLAN_ENA_SHIFT 19
 #define I40E_PFQF_CTL_0_MACVLAN_ENA_MASK I40E_MASK(0x1, I40E_PFQF_CTL_0_MACVLAN_ENA_SHIFT)
-#define I40E_PFQF_CTL_0_VFFCHSIZE_SHIFT 20
-#define I40E_PFQF_CTL_0_VFFCHSIZE_MASK I40E_MASK(0xF, I40E_PFQF_CTL_0_VFFCHSIZE_SHIFT)
-#define I40E_PFQF_CTL_0_VFFCDSIZE_SHIFT 24
-#define I40E_PFQF_CTL_0_VFFCDSIZE_MASK I40E_MASK(0x3, I40E_PFQF_CTL_0_VFFCDSIZE_SHIFT)
 #define I40E_PFQF_CTL_1 0x00245D80 /* Reset: CORER */
 #define I40E_PFQF_CTL_1_CLEARFDTABLE_SHIFT 0
 #define I40E_PFQF_CTL_1_CLEARFDTABLE_MASK I40E_MASK(0x1, I40E_PFQF_CTL_1_CLEARFDTABLE_SHIFT)
-#define I40E_PFQF_FDALLOC 0x00246280 /* Reset: CORER */
-#define I40E_PFQF_FDALLOC_FDALLOC_SHIFT 0
-#define I40E_PFQF_FDALLOC_FDALLOC_MASK I40E_MASK(0xFF, I40E_PFQF_FDALLOC_FDALLOC_SHIFT)
-#define I40E_PFQF_FDALLOC_FDBEST_SHIFT 8
-#define I40E_PFQF_FDALLOC_FDBEST_MASK I40E_MASK(0xFF, I40E_PFQF_FDALLOC_FDBEST_SHIFT)
 #define I40E_PFQF_FDSTAT 0x00246380 /* Reset: CORER */
 #define I40E_PFQF_FDSTAT_GUARANT_CNT_SHIFT 0
 #define I40E_PFQF_FDSTAT_GUARANT_CNT_MASK I40E_MASK(0x1FFF, I40E_PFQF_FDSTAT_GUARANT_CNT_SHIFT)
 #define I40E_PFQF_FDSTAT_BEST_CNT_SHIFT 16
 #define I40E_PFQF_FDSTAT_BEST_CNT_MASK I40E_MASK(0x1FFF, I40E_PFQF_FDSTAT_BEST_CNT_SHIFT)
 #define I40E_PFQF_HENA(_i) (0x00245900 + ((_i) * 128)) /* _i=0...1 */ /* Reset: CORER */
-#define I40E_PFQF_HENA_MAX_INDEX 1
-#define I40E_PFQF_HENA_PTYPE_ENA_SHIFT 0
-#define I40E_PFQF_HENA_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_PFQF_HENA_PTYPE_ENA_SHIFT)
 #define I40E_PFQF_HKEY(_i) (0x00244800 + ((_i) * 128)) /* _i=0...12 */ /* Reset: CORER */
 #define I40E_PFQF_HKEY_MAX_INDEX 12
-#define I40E_PFQF_HKEY_KEY_0_SHIFT 0
-#define I40E_PFQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_PFQF_HKEY_KEY_0_SHIFT)
-#define I40E_PFQF_HKEY_KEY_1_SHIFT 8
-#define I40E_PFQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_PFQF_HKEY_KEY_1_SHIFT)
-#define I40E_PFQF_HKEY_KEY_2_SHIFT 16
-#define I40E_PFQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_PFQF_HKEY_KEY_2_SHIFT)
-#define I40E_PFQF_HKEY_KEY_3_SHIFT 24
-#define I40E_PFQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_PFQF_HKEY_KEY_3_SHIFT)
 #define I40E_PFQF_HLUT(_i) (0x00240000 + ((_i) * 128)) /* _i=0...127 */ /* Reset: CORER */
 #define I40E_PFQF_HLUT_MAX_INDEX 127
-#define I40E_PFQF_HLUT_LUT0_SHIFT 0
-#define I40E_PFQF_HLUT_LUT0_MASK I40E_MASK(0x3F, I40E_PFQF_HLUT_LUT0_SHIFT)
-#define I40E_PFQF_HLUT_LUT1_SHIFT 8
-#define I40E_PFQF_HLUT_LUT1_MASK I40E_MASK(0x3F, I40E_PFQF_HLUT_LUT1_SHIFT)
-#define I40E_PFQF_HLUT_LUT2_SHIFT 16
-#define I40E_PFQF_HLUT_LUT2_MASK I40E_MASK(0x3F, I40E_PFQF_HLUT_LUT2_SHIFT)
-#define I40E_PFQF_HLUT_LUT3_SHIFT 24
-#define I40E_PFQF_HLUT_LUT3_MASK I40E_MASK(0x3F, I40E_PFQF_HLUT_LUT3_SHIFT)
-#define I40E_PRTQF_CTL_0 0x00256E60 /* Reset: CORER */
-#define I40E_PRTQF_CTL_0_HSYM_ENA_SHIFT 0
-#define I40E_PRTQF_CTL_0_HSYM_ENA_MASK I40E_MASK(0x1, I40E_PRTQF_CTL_0_HSYM_ENA_SHIFT)
-#define I40E_PRTQF_FD_FLXINSET(_i) (0x00253800 + ((_i) * 32)) /* _i=0...63 */ /* Reset: CORER */
-#define I40E_PRTQF_FD_FLXINSET_MAX_INDEX 63
-#define I40E_PRTQF_FD_FLXINSET_INSET_SHIFT 0
-#define I40E_PRTQF_FD_FLXINSET_INSET_MASK I40E_MASK(0xFF, I40E_PRTQF_FD_FLXINSET_INSET_SHIFT)
 #define I40E_PRTQF_FD_INSET(_i, _j) (0x00250000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */ /* Reset: CORER */
 #define I40E_PRTQF_FD_INSET_MAX_INDEX 63
 #define I40E_PRTQF_FD_INSET_INSET_SHIFT 0
@@ -2215,14 +444,7 @@
 #define I40E_PRTQF_FD_INSET_MAX_INDEX 63
 #define I40E_PRTQF_FD_INSET_INSET_SHIFT 0
 #define I40E_PRTQF_FD_INSET_INSET_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTQF_FD_INSET_INSET_SHIFT)
-#define I40E_PRTQF_FD_MSK(_i, _j) (0x00252000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */ /* Reset: CORER */
-#define I40E_PRTQF_FD_MSK_MAX_INDEX 63
-#define I40E_PRTQF_FD_MSK_MASK_SHIFT 0
-#define I40E_PRTQF_FD_MSK_MASK_MASK I40E_MASK(0xFFFF, I40E_PRTQF_FD_MSK_MASK_SHIFT)
-#define I40E_PRTQF_FD_MSK_OFFSET_SHIFT 16
-#define I40E_PRTQF_FD_MSK_OFFSET_MASK I40E_MASK(0x3F, I40E_PRTQF_FD_MSK_OFFSET_SHIFT)
 #define I40E_PRTQF_FLX_PIT(_i) (0x00255200 + ((_i) * 32)) /* _i=0...8 */ /* Reset: CORER */
-#define I40E_PRTQF_FLX_PIT_MAX_INDEX 8
 #define I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT 0
 #define I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK I40E_MASK(0x1F, I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
 #define I40E_PRTQF_FLX_PIT_FSIZE_SHIFT 5
@@ -2230,775 +452,148 @@
 #define I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT 10
 #define I40E_PRTQF_FLX_PIT_DEST_OFF_MASK I40E_MASK(0x3F, I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
 #define I40E_VFQF_HENA1(_i, _VF) (0x00230800 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...1, _VF=0...127 */ /* Reset: CORER */
-#define I40E_VFQF_HENA1_MAX_INDEX 1
-#define I40E_VFQF_HENA1_PTYPE_ENA_SHIFT 0
-#define I40E_VFQF_HENA1_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_VFQF_HENA1_PTYPE_ENA_SHIFT)
 #define I40E_VFQF_HKEY1(_i, _VF) (0x00228000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...12, _VF=0...127 */ /* Reset: CORER */
 #define I40E_VFQF_HKEY1_MAX_INDEX 12
-#define I40E_VFQF_HKEY1_KEY_0_SHIFT 0
-#define I40E_VFQF_HKEY1_KEY_0_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY1_KEY_0_SHIFT)
-#define I40E_VFQF_HKEY1_KEY_1_SHIFT 8
-#define I40E_VFQF_HKEY1_KEY_1_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY1_KEY_1_SHIFT)
-#define I40E_VFQF_HKEY1_KEY_2_SHIFT 16
-#define I40E_VFQF_HKEY1_KEY_2_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY1_KEY_2_SHIFT)
-#define I40E_VFQF_HKEY1_KEY_3_SHIFT 24
-#define I40E_VFQF_HKEY1_KEY_3_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY1_KEY_3_SHIFT)
 #define I40E_VFQF_HLUT1(_i, _VF) (0x00220000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...15, _VF=0...127 */ /* Reset: CORER */
 #define I40E_VFQF_HLUT1_MAX_INDEX 15
-#define I40E_VFQF_HLUT1_LUT0_SHIFT 0
-#define I40E_VFQF_HLUT1_LUT0_MASK I40E_MASK(0xF, I40E_VFQF_HLUT1_LUT0_SHIFT)
-#define I40E_VFQF_HLUT1_LUT1_SHIFT 8
-#define I40E_VFQF_HLUT1_LUT1_MASK I40E_MASK(0xF, I40E_VFQF_HLUT1_LUT1_SHIFT)
-#define I40E_VFQF_HLUT1_LUT2_SHIFT 16
-#define I40E_VFQF_HLUT1_LUT2_MASK I40E_MASK(0xF, I40E_VFQF_HLUT1_LUT2_SHIFT)
-#define I40E_VFQF_HLUT1_LUT3_SHIFT 24
-#define I40E_VFQF_HLUT1_LUT3_MASK I40E_MASK(0xF, I40E_VFQF_HLUT1_LUT3_SHIFT)
-#define I40E_VFQF_HREGION1(_i, _VF) (0x0022E000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...7, _VF=0...127 */ /* Reset: CORER */
-#define I40E_VFQF_HREGION1_MAX_INDEX 7
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_0_SHIFT 0
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_0_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_0_SHIFT 1
-#define I40E_VFQF_HREGION1_REGION_0_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_0_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_1_SHIFT 4
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_1_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_1_SHIFT 5
-#define I40E_VFQF_HREGION1_REGION_1_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_1_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_2_SHIFT 8
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_2_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_2_SHIFT 9
-#define I40E_VFQF_HREGION1_REGION_2_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_2_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_3_SHIFT 12
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_3_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_3_SHIFT 13
-#define I40E_VFQF_HREGION1_REGION_3_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_3_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_4_SHIFT 16
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_4_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_4_SHIFT 17
-#define I40E_VFQF_HREGION1_REGION_4_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_4_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_5_SHIFT 20
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_5_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_5_SHIFT 21
-#define I40E_VFQF_HREGION1_REGION_5_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_5_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_6_SHIFT 24
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_6_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_6_SHIFT 25
-#define I40E_VFQF_HREGION1_REGION_6_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_6_SHIFT)
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_7_SHIFT 28
-#define I40E_VFQF_HREGION1_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_VFQF_HREGION1_OVERRIDE_ENA_7_SHIFT)
-#define I40E_VFQF_HREGION1_REGION_7_SHIFT 29
-#define I40E_VFQF_HREGION1_REGION_7_MASK I40E_MASK(0x7, I40E_VFQF_HREGION1_REGION_7_SHIFT)
-#define I40E_VPQF_CTL(_VF) (0x001C0000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VPQF_CTL_MAX_INDEX 127
-#define I40E_VPQF_CTL_PEHSIZE_SHIFT 0
-#define I40E_VPQF_CTL_PEHSIZE_MASK I40E_MASK(0x1F, I40E_VPQF_CTL_PEHSIZE_SHIFT)
-#define I40E_VPQF_CTL_PEDSIZE_SHIFT 5
-#define I40E_VPQF_CTL_PEDSIZE_MASK I40E_MASK(0x1F, I40E_VPQF_CTL_PEDSIZE_SHIFT)
-#define I40E_VPQF_CTL_FCHSIZE_SHIFT 10
-#define I40E_VPQF_CTL_FCHSIZE_MASK I40E_MASK(0xF, I40E_VPQF_CTL_FCHSIZE_SHIFT)
-#define I40E_VPQF_CTL_FCDSIZE_SHIFT 14
-#define I40E_VPQF_CTL_FCDSIZE_MASK I40E_MASK(0x3, I40E_VPQF_CTL_FCDSIZE_SHIFT)
-#define I40E_VSIQF_CTL(_VSI) (0x0020D800 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: PFR */
-#define I40E_VSIQF_CTL_MAX_INDEX 383
-#define I40E_VSIQF_CTL_FCOE_ENA_SHIFT 0
-#define I40E_VSIQF_CTL_FCOE_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_FCOE_ENA_SHIFT)
-#define I40E_VSIQF_CTL_PETCP_ENA_SHIFT 1
-#define I40E_VSIQF_CTL_PETCP_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_PETCP_ENA_SHIFT)
-#define I40E_VSIQF_CTL_PEUUDP_ENA_SHIFT 2
-#define I40E_VSIQF_CTL_PEUUDP_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_PEUUDP_ENA_SHIFT)
-#define I40E_VSIQF_CTL_PEMUDP_ENA_SHIFT 3
-#define I40E_VSIQF_CTL_PEMUDP_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_PEMUDP_ENA_SHIFT)
-#define I40E_VSIQF_CTL_PEUFRAG_ENA_SHIFT 4
-#define I40E_VSIQF_CTL_PEUFRAG_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_PEUFRAG_ENA_SHIFT)
-#define I40E_VSIQF_CTL_PEMFRAG_ENA_SHIFT 5
-#define I40E_VSIQF_CTL_PEMFRAG_ENA_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_PEMFRAG_ENA_SHIFT)
-#define I40E_VSIQF_TCREGION(_i, _VSI) (0x00206000 + ((_i) * 2048 + (_VSI) * 4)) /* _i=0...3, _VSI=0...383 */ /* Reset: PFR */
-#define I40E_VSIQF_TCREGION_MAX_INDEX 3
-#define I40E_VSIQF_TCREGION_TC_OFFSET_SHIFT 0
-#define I40E_VSIQF_TCREGION_TC_OFFSET_MASK I40E_MASK(0x1FF, I40E_VSIQF_TCREGION_TC_OFFSET_SHIFT)
-#define I40E_VSIQF_TCREGION_TC_SIZE_SHIFT 9
-#define I40E_VSIQF_TCREGION_TC_SIZE_MASK I40E_MASK(0x7, I40E_VSIQF_TCREGION_TC_SIZE_SHIFT)
-#define I40E_VSIQF_TCREGION_TC_OFFSET2_SHIFT 16
-#define I40E_VSIQF_TCREGION_TC_OFFSET2_MASK I40E_MASK(0x1FF, I40E_VSIQF_TCREGION_TC_OFFSET2_SHIFT)
-#define I40E_VSIQF_TCREGION_TC_SIZE2_SHIFT 25
-#define I40E_VSIQF_TCREGION_TC_SIZE2_MASK I40E_MASK(0x7, I40E_VSIQF_TCREGION_TC_SIZE2_SHIFT)
-#define I40E_GL_FCOECRC(_i) (0x00314d80 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOECRC_MAX_INDEX 143
-#define I40E_GL_FCOECRC_FCOECRC_SHIFT 0
-#define I40E_GL_FCOECRC_FCOECRC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOECRC_FCOECRC_SHIFT)
-#define I40E_GL_FCOEDDPC(_i) (0x00314480 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDDPC_MAX_INDEX 143
-#define I40E_GL_FCOEDDPC_FCOEDDPC_SHIFT 0
-#define I40E_GL_FCOEDDPC_FCOEDDPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDDPC_FCOEDDPC_SHIFT)
-#define I40E_GL_FCOEDIFEC(_i) (0x00318480 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDIFEC_MAX_INDEX 143
-#define I40E_GL_FCOEDIFEC_FCOEDIFRC_SHIFT 0
-#define I40E_GL_FCOEDIFEC_FCOEDIFRC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDIFEC_FCOEDIFRC_SHIFT)
-#define I40E_GL_FCOEDIFTCL(_i) (0x00354000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDIFTCL_MAX_INDEX 143
-#define I40E_GL_FCOEDIFTCL_FCOEDIFTC_SHIFT 0
-#define I40E_GL_FCOEDIFTCL_FCOEDIFTC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDIFTCL_FCOEDIFTC_SHIFT)
-#define I40E_GL_FCOEDIXEC(_i) (0x0034c000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDIXEC_MAX_INDEX 143
-#define I40E_GL_FCOEDIXEC_FCOEDIXEC_SHIFT 0
-#define I40E_GL_FCOEDIXEC_FCOEDIXEC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDIXEC_FCOEDIXEC_SHIFT)
-#define I40E_GL_FCOEDIXVC(_i) (0x00350000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDIXVC_MAX_INDEX 143
-#define I40E_GL_FCOEDIXVC_FCOEDIXVC_SHIFT 0
-#define I40E_GL_FCOEDIXVC_FCOEDIXVC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDIXVC_FCOEDIXVC_SHIFT)
-#define I40E_GL_FCOEDWRCH(_i) (0x00320004 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDWRCH_MAX_INDEX 143
-#define I40E_GL_FCOEDWRCH_FCOEDWRCH_SHIFT 0
-#define I40E_GL_FCOEDWRCH_FCOEDWRCH_MASK I40E_MASK(0xFFFF, I40E_GL_FCOEDWRCH_FCOEDWRCH_SHIFT)
-#define I40E_GL_FCOEDWRCL(_i) (0x00320000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDWRCL_MAX_INDEX 143
-#define I40E_GL_FCOEDWRCL_FCOEDWRCL_SHIFT 0
-#define I40E_GL_FCOEDWRCL_FCOEDWRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDWRCL_FCOEDWRCL_SHIFT)
-#define I40E_GL_FCOEDWTCH(_i) (0x00348084 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDWTCH_MAX_INDEX 143
-#define I40E_GL_FCOEDWTCH_FCOEDWTCH_SHIFT 0
-#define I40E_GL_FCOEDWTCH_FCOEDWTCH_MASK I40E_MASK(0xFFFF, I40E_GL_FCOEDWTCH_FCOEDWTCH_SHIFT)
-#define I40E_GL_FCOEDWTCL(_i) (0x00348080 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEDWTCL_MAX_INDEX 143
-#define I40E_GL_FCOEDWTCL_FCOEDWTCL_SHIFT 0
-#define I40E_GL_FCOEDWTCL_FCOEDWTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEDWTCL_FCOEDWTCL_SHIFT)
-#define I40E_GL_FCOELAST(_i) (0x00314000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOELAST_MAX_INDEX 143
-#define I40E_GL_FCOELAST_FCOELAST_SHIFT 0
-#define I40E_GL_FCOELAST_FCOELAST_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOELAST_FCOELAST_SHIFT)
-#define I40E_GL_FCOEPRC(_i) (0x00315200 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEPRC_MAX_INDEX 143
-#define I40E_GL_FCOEPRC_FCOEPRC_SHIFT 0
-#define I40E_GL_FCOEPRC_FCOEPRC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEPRC_FCOEPRC_SHIFT)
-#define I40E_GL_FCOEPTC(_i) (0x00344C00 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOEPTC_MAX_INDEX 143
-#define I40E_GL_FCOEPTC_FCOEPTC_SHIFT 0
-#define I40E_GL_FCOEPTC_FCOEPTC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOEPTC_FCOEPTC_SHIFT)
-#define I40E_GL_FCOERPDC(_i) (0x00324000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_FCOERPDC_MAX_INDEX 143
-#define I40E_GL_FCOERPDC_FCOERPDC_SHIFT 0
-#define I40E_GL_FCOERPDC_FCOERPDC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_FCOERPDC_FCOERPDC_SHIFT)
-#define I40E_GL_RXERR1_L(_i) (0x00318000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_RXERR1_L_MAX_INDEX 143
-#define I40E_GL_RXERR1_L_FCOEDIFRC_SHIFT 0
-#define I40E_GL_RXERR1_L_FCOEDIFRC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_RXERR1_L_FCOEDIFRC_SHIFT)
-#define I40E_GL_RXERR2_L(_i) (0x0031c000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
-#define I40E_GL_RXERR2_L_MAX_INDEX 143
-#define I40E_GL_RXERR2_L_FCOEDIXAC_SHIFT 0
-#define I40E_GL_RXERR2_L_FCOEDIXAC_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_RXERR2_L_FCOEDIXAC_SHIFT)
 #define I40E_GLPRT_BPRCH(_i) (0x003005E4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_BPRCH_MAX_INDEX 3
-#define I40E_GLPRT_BPRCH_BPRCH_SHIFT 0
-#define I40E_GLPRT_BPRCH_BPRCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_BPRCH_BPRCH_SHIFT)
 #define I40E_GLPRT_BPRCL(_i) (0x003005E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_BPRCL_MAX_INDEX 3
-#define I40E_GLPRT_BPRCL_BPRCL_SHIFT 0
-#define I40E_GLPRT_BPRCL_BPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_BPRCL_BPRCL_SHIFT)
 #define I40E_GLPRT_BPTCH(_i) (0x00300A04 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_BPTCH_MAX_INDEX 3
-#define I40E_GLPRT_BPTCH_BPTCH_SHIFT 0
-#define I40E_GLPRT_BPTCH_BPTCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_BPTCH_BPTCH_SHIFT)
 #define I40E_GLPRT_BPTCL(_i) (0x00300A00 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_BPTCL_MAX_INDEX 3
-#define I40E_GLPRT_BPTCL_BPTCL_SHIFT 0
-#define I40E_GLPRT_BPTCL_BPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_BPTCL_BPTCL_SHIFT)
 #define I40E_GLPRT_CRCERRS(_i) (0x00300080 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_CRCERRS_MAX_INDEX 3
-#define I40E_GLPRT_CRCERRS_CRCERRS_SHIFT 0
-#define I40E_GLPRT_CRCERRS_CRCERRS_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_CRCERRS_CRCERRS_SHIFT)
 #define I40E_GLPRT_GORCH(_i) (0x00300004 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_GORCH_MAX_INDEX 3
-#define I40E_GLPRT_GORCH_GORCH_SHIFT 0
-#define I40E_GLPRT_GORCH_GORCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_GORCH_GORCH_SHIFT)
 #define I40E_GLPRT_GORCL(_i) (0x00300000 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_GORCL_MAX_INDEX 3
-#define I40E_GLPRT_GORCL_GORCL_SHIFT 0
-#define I40E_GLPRT_GORCL_GORCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_GORCL_GORCL_SHIFT)
 #define I40E_GLPRT_GOTCH(_i) (0x00300684 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_GOTCH_MAX_INDEX 3
-#define I40E_GLPRT_GOTCH_GOTCH_SHIFT 0
-#define I40E_GLPRT_GOTCH_GOTCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_GOTCH_GOTCH_SHIFT)
 #define I40E_GLPRT_GOTCL(_i) (0x00300680 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_GOTCL_MAX_INDEX 3
-#define I40E_GLPRT_GOTCL_GOTCL_SHIFT 0
-#define I40E_GLPRT_GOTCL_GOTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_GOTCL_GOTCL_SHIFT)
 #define I40E_GLPRT_ILLERRC(_i) (0x003000E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_ILLERRC_MAX_INDEX 3
-#define I40E_GLPRT_ILLERRC_ILLERRC_SHIFT 0
-#define I40E_GLPRT_ILLERRC_ILLERRC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_ILLERRC_ILLERRC_SHIFT)
-#define I40E_GLPRT_LDPC(_i) (0x00300620 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_LDPC_MAX_INDEX 3
-#define I40E_GLPRT_LDPC_LDPC_SHIFT 0
-#define I40E_GLPRT_LDPC_LDPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_LDPC_LDPC_SHIFT)
 #define I40E_GLPRT_LXOFFRXC(_i) (0x00300160 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_LXOFFRXC_MAX_INDEX 3
-#define I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_SHIFT 0
-#define I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_SHIFT)
 #define I40E_GLPRT_LXOFFTXC(_i) (0x003009A0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_LXOFFTXC_MAX_INDEX 3
-#define I40E_GLPRT_LXOFFTXC_LXOFFTXC_SHIFT 0
-#define I40E_GLPRT_LXOFFTXC_LXOFFTXC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_LXOFFTXC_LXOFFTXC_SHIFT)
 #define I40E_GLPRT_LXONRXC(_i) (0x00300140 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_LXONRXC_MAX_INDEX 3
-#define I40E_GLPRT_LXONRXC_LXONRXCNT_SHIFT 0
-#define I40E_GLPRT_LXONRXC_LXONRXCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_LXONRXC_LXONRXCNT_SHIFT)
 #define I40E_GLPRT_LXONTXC(_i) (0x00300980 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_LXONTXC_MAX_INDEX 3
-#define I40E_GLPRT_LXONTXC_LXONTXC_SHIFT 0
-#define I40E_GLPRT_LXONTXC_LXONTXC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_LXONTXC_LXONTXC_SHIFT)
 #define I40E_GLPRT_MLFC(_i) (0x00300020 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MLFC_MAX_INDEX 3
-#define I40E_GLPRT_MLFC_MLFC_SHIFT 0
-#define I40E_GLPRT_MLFC_MLFC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_MLFC_MLFC_SHIFT)
 #define I40E_GLPRT_MPRCH(_i) (0x003005C4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MPRCH_MAX_INDEX 3
-#define I40E_GLPRT_MPRCH_MPRCH_SHIFT 0
-#define I40E_GLPRT_MPRCH_MPRCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_MPRCH_MPRCH_SHIFT)
 #define I40E_GLPRT_MPRCL(_i) (0x003005C0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MPRCL_MAX_INDEX 3
-#define I40E_GLPRT_MPRCL_MPRCL_SHIFT 0
-#define I40E_GLPRT_MPRCL_MPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_MPRCL_MPRCL_SHIFT)
 #define I40E_GLPRT_MPTCH(_i) (0x003009E4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MPTCH_MAX_INDEX 3
-#define I40E_GLPRT_MPTCH_MPTCH_SHIFT 0
-#define I40E_GLPRT_MPTCH_MPTCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_MPTCH_MPTCH_SHIFT)
 #define I40E_GLPRT_MPTCL(_i) (0x003009E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MPTCL_MAX_INDEX 3
-#define I40E_GLPRT_MPTCL_MPTCL_SHIFT 0
-#define I40E_GLPRT_MPTCL_MPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_MPTCL_MPTCL_SHIFT)
 #define I40E_GLPRT_MRFC(_i) (0x00300040 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_MRFC_MAX_INDEX 3
-#define I40E_GLPRT_MRFC_MRFC_SHIFT 0
-#define I40E_GLPRT_MRFC_MRFC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_MRFC_MRFC_SHIFT)
 #define I40E_GLPRT_PRC1023H(_i) (0x00300504 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC1023H_MAX_INDEX 3
-#define I40E_GLPRT_PRC1023H_PRC1023H_SHIFT 0
-#define I40E_GLPRT_PRC1023H_PRC1023H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC1023H_PRC1023H_SHIFT)
 #define I40E_GLPRT_PRC1023L(_i) (0x00300500 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC1023L_MAX_INDEX 3
-#define I40E_GLPRT_PRC1023L_PRC1023L_SHIFT 0
-#define I40E_GLPRT_PRC1023L_PRC1023L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC1023L_PRC1023L_SHIFT)
 #define I40E_GLPRT_PRC127H(_i) (0x003004A4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC127H_MAX_INDEX 3
-#define I40E_GLPRT_PRC127H_PRC127H_SHIFT 0
-#define I40E_GLPRT_PRC127H_PRC127H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC127H_PRC127H_SHIFT)
 #define I40E_GLPRT_PRC127L(_i) (0x003004A0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC127L_MAX_INDEX 3
-#define I40E_GLPRT_PRC127L_PRC127L_SHIFT 0
-#define I40E_GLPRT_PRC127L_PRC127L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC127L_PRC127L_SHIFT)
 #define I40E_GLPRT_PRC1522H(_i) (0x00300524 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC1522H_MAX_INDEX 3
-#define I40E_GLPRT_PRC1522H_PRC1522H_SHIFT 0
-#define I40E_GLPRT_PRC1522H_PRC1522H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC1522H_PRC1522H_SHIFT)
 #define I40E_GLPRT_PRC1522L(_i) (0x00300520 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC1522L_MAX_INDEX 3
-#define I40E_GLPRT_PRC1522L_PRC1522L_SHIFT 0
-#define I40E_GLPRT_PRC1522L_PRC1522L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC1522L_PRC1522L_SHIFT)
 #define I40E_GLPRT_PRC255H(_i) (0x003004C4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC255H_MAX_INDEX 3
-#define I40E_GLPRT_PRC255H_PRTPRC255H_SHIFT 0
-#define I40E_GLPRT_PRC255H_PRTPRC255H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC255H_PRTPRC255H_SHIFT)
 #define I40E_GLPRT_PRC255L(_i) (0x003004C0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC255L_MAX_INDEX 3
-#define I40E_GLPRT_PRC255L_PRC255L_SHIFT 0
-#define I40E_GLPRT_PRC255L_PRC255L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC255L_PRC255L_SHIFT)
 #define I40E_GLPRT_PRC511H(_i) (0x003004E4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC511H_MAX_INDEX 3
-#define I40E_GLPRT_PRC511H_PRC511H_SHIFT 0
-#define I40E_GLPRT_PRC511H_PRC511H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC511H_PRC511H_SHIFT)
 #define I40E_GLPRT_PRC511L(_i) (0x003004E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC511L_MAX_INDEX 3
-#define I40E_GLPRT_PRC511L_PRC511L_SHIFT 0
-#define I40E_GLPRT_PRC511L_PRC511L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC511L_PRC511L_SHIFT)
 #define I40E_GLPRT_PRC64H(_i) (0x00300484 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC64H_MAX_INDEX 3
-#define I40E_GLPRT_PRC64H_PRC64H_SHIFT 0
-#define I40E_GLPRT_PRC64H_PRC64H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC64H_PRC64H_SHIFT)
 #define I40E_GLPRT_PRC64L(_i) (0x00300480 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC64L_MAX_INDEX 3
-#define I40E_GLPRT_PRC64L_PRC64L_SHIFT 0
-#define I40E_GLPRT_PRC64L_PRC64L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC64L_PRC64L_SHIFT)
 #define I40E_GLPRT_PRC9522H(_i) (0x00300544 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC9522H_MAX_INDEX 3
-#define I40E_GLPRT_PRC9522H_PRC1522H_SHIFT 0
-#define I40E_GLPRT_PRC9522H_PRC1522H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PRC9522H_PRC1522H_SHIFT)
 #define I40E_GLPRT_PRC9522L(_i) (0x00300540 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PRC9522L_MAX_INDEX 3
-#define I40E_GLPRT_PRC9522L_PRC1522L_SHIFT 0
-#define I40E_GLPRT_PRC9522L_PRC1522L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PRC9522L_PRC1522L_SHIFT)
 #define I40E_GLPRT_PTC1023H(_i) (0x00300724 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC1023H_MAX_INDEX 3
-#define I40E_GLPRT_PTC1023H_PTC1023H_SHIFT 0
-#define I40E_GLPRT_PTC1023H_PTC1023H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC1023H_PTC1023H_SHIFT)
 #define I40E_GLPRT_PTC1023L(_i) (0x00300720 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC1023L_MAX_INDEX 3
-#define I40E_GLPRT_PTC1023L_PTC1023L_SHIFT 0
-#define I40E_GLPRT_PTC1023L_PTC1023L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC1023L_PTC1023L_SHIFT)
 #define I40E_GLPRT_PTC127H(_i) (0x003006C4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC127H_MAX_INDEX 3
-#define I40E_GLPRT_PTC127H_PTC127H_SHIFT 0
-#define I40E_GLPRT_PTC127H_PTC127H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC127H_PTC127H_SHIFT)
 #define I40E_GLPRT_PTC127L(_i) (0x003006C0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC127L_MAX_INDEX 3
-#define I40E_GLPRT_PTC127L_PTC127L_SHIFT 0
-#define I40E_GLPRT_PTC127L_PTC127L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC127L_PTC127L_SHIFT)
 #define I40E_GLPRT_PTC1522H(_i) (0x00300744 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC1522H_MAX_INDEX 3
-#define I40E_GLPRT_PTC1522H_PTC1522H_SHIFT 0
-#define I40E_GLPRT_PTC1522H_PTC1522H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC1522H_PTC1522H_SHIFT)
 #define I40E_GLPRT_PTC1522L(_i) (0x00300740 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC1522L_MAX_INDEX 3
-#define I40E_GLPRT_PTC1522L_PTC1522L_SHIFT 0
-#define I40E_GLPRT_PTC1522L_PTC1522L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC1522L_PTC1522L_SHIFT)
 #define I40E_GLPRT_PTC255H(_i) (0x003006E4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC255H_MAX_INDEX 3
-#define I40E_GLPRT_PTC255H_PTC255H_SHIFT 0
-#define I40E_GLPRT_PTC255H_PTC255H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC255H_PTC255H_SHIFT)
 #define I40E_GLPRT_PTC255L(_i) (0x003006E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC255L_MAX_INDEX 3
-#define I40E_GLPRT_PTC255L_PTC255L_SHIFT 0
-#define I40E_GLPRT_PTC255L_PTC255L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC255L_PTC255L_SHIFT)
 #define I40E_GLPRT_PTC511H(_i) (0x00300704 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC511H_MAX_INDEX 3
-#define I40E_GLPRT_PTC511H_PTC511H_SHIFT 0
-#define I40E_GLPRT_PTC511H_PTC511H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC511H_PTC511H_SHIFT)
 #define I40E_GLPRT_PTC511L(_i) (0x00300700 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC511L_MAX_INDEX 3
-#define I40E_GLPRT_PTC511L_PTC511L_SHIFT 0
-#define I40E_GLPRT_PTC511L_PTC511L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC511L_PTC511L_SHIFT)
 #define I40E_GLPRT_PTC64H(_i) (0x003006A4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC64H_MAX_INDEX 3
-#define I40E_GLPRT_PTC64H_PTC64H_SHIFT 0
-#define I40E_GLPRT_PTC64H_PTC64H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC64H_PTC64H_SHIFT)
 #define I40E_GLPRT_PTC64L(_i) (0x003006A0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC64L_MAX_INDEX 3
-#define I40E_GLPRT_PTC64L_PTC64L_SHIFT 0
-#define I40E_GLPRT_PTC64L_PTC64L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC64L_PTC64L_SHIFT)
 #define I40E_GLPRT_PTC9522H(_i) (0x00300764 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC9522H_MAX_INDEX 3
-#define I40E_GLPRT_PTC9522H_PTC9522H_SHIFT 0
-#define I40E_GLPRT_PTC9522H_PTC9522H_MASK I40E_MASK(0xFFFF, I40E_GLPRT_PTC9522H_PTC9522H_SHIFT)
 #define I40E_GLPRT_PTC9522L(_i) (0x00300760 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_PTC9522L_MAX_INDEX 3
-#define I40E_GLPRT_PTC9522L_PTC9522L_SHIFT 0
-#define I40E_GLPRT_PTC9522L_PTC9522L_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PTC9522L_PTC9522L_SHIFT)
 #define I40E_GLPRT_PXOFFRXC(_i, _j) (0x00300280 + ((_i) * 8 + (_j) * 32)) /* _i=0...3, _j=0...7 */ /* Reset: CORER */
-#define I40E_GLPRT_PXOFFRXC_MAX_INDEX 3
-#define I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_SHIFT 0
-#define I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_SHIFT)
 #define I40E_GLPRT_PXOFFTXC(_i, _j) (0x00300880 + ((_i) * 8 + (_j) * 32)) /* _i=0...3, _j=0...7 */ /* Reset: CORER */
-#define I40E_GLPRT_PXOFFTXC_MAX_INDEX 3
-#define I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_SHIFT 0
-#define I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_SHIFT)
 #define I40E_GLPRT_PXONRXC(_i, _j) (0x00300180 + ((_i) * 8 + (_j) * 32)) /* _i=0...3, _j=0...7 */ /* Reset: CORER */
-#define I40E_GLPRT_PXONRXC_MAX_INDEX 3
-#define I40E_GLPRT_PXONRXC_PRPXONRXCNT_SHIFT 0
-#define I40E_GLPRT_PXONRXC_PRPXONRXCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PXONRXC_PRPXONRXCNT_SHIFT)
 #define I40E_GLPRT_PXONTXC(_i, _j) (0x00300780 + ((_i) * 8 + (_j) * 32)) /* _i=0...3, _j=0...7 */ /* Reset: CORER */
-#define I40E_GLPRT_PXONTXC_MAX_INDEX 3
-#define I40E_GLPRT_PXONTXC_PRPXONTXC_SHIFT 0
-#define I40E_GLPRT_PXONTXC_PRPXONTXC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_PXONTXC_PRPXONTXC_SHIFT)
 #define I40E_GLPRT_RDPC(_i) (0x00300600 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RDPC_MAX_INDEX 3
-#define I40E_GLPRT_RDPC_RDPC_SHIFT 0
-#define I40E_GLPRT_RDPC_RDPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RDPC_RDPC_SHIFT)
 #define I40E_GLPRT_RFC(_i) (0x00300560 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RFC_MAX_INDEX 3
-#define I40E_GLPRT_RFC_RFC_SHIFT 0
-#define I40E_GLPRT_RFC_RFC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RFC_RFC_SHIFT)
 #define I40E_GLPRT_RJC(_i) (0x00300580 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RJC_MAX_INDEX 3
-#define I40E_GLPRT_RJC_RJC_SHIFT 0
-#define I40E_GLPRT_RJC_RJC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RJC_RJC_SHIFT)
 #define I40E_GLPRT_RLEC(_i) (0x003000A0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RLEC_MAX_INDEX 3
-#define I40E_GLPRT_RLEC_RLEC_SHIFT 0
-#define I40E_GLPRT_RLEC_RLEC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RLEC_RLEC_SHIFT)
 #define I40E_GLPRT_ROC(_i) (0x00300120 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_ROC_MAX_INDEX 3
-#define I40E_GLPRT_ROC_ROC_SHIFT 0
-#define I40E_GLPRT_ROC_ROC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_ROC_ROC_SHIFT)
 #define I40E_GLPRT_RUC(_i) (0x00300100 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RUC_MAX_INDEX 3
-#define I40E_GLPRT_RUC_RUC_SHIFT 0
-#define I40E_GLPRT_RUC_RUC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RUC_RUC_SHIFT)
-#define I40E_GLPRT_RUPP(_i) (0x00300660 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_RUPP_MAX_INDEX 3
-#define I40E_GLPRT_RUPP_RUPP_SHIFT 0
-#define I40E_GLPRT_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RUPP_RUPP_SHIFT)
 #define I40E_GLPRT_RXON2OFFCNT(_i, _j) (0x00300380 + ((_i) * 8 + (_j) * 32)) /* _i=0...3, _j=0...7 */ /* Reset: CORER */
-#define I40E_GLPRT_RXON2OFFCNT_MAX_INDEX 3
-#define I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_SHIFT 0
-#define I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_SHIFT)
 #define I40E_GLPRT_TDOLD(_i) (0x00300A20 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_TDOLD_MAX_INDEX 3
-#define I40E_GLPRT_TDOLD_GLPRT_TDOLD_SHIFT 0
-#define I40E_GLPRT_TDOLD_GLPRT_TDOLD_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_TDOLD_GLPRT_TDOLD_SHIFT)
 #define I40E_GLPRT_UPRCH(_i) (0x003005A4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_UPRCH_MAX_INDEX 3
-#define I40E_GLPRT_UPRCH_UPRCH_SHIFT 0
-#define I40E_GLPRT_UPRCH_UPRCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_UPRCH_UPRCH_SHIFT)
 #define I40E_GLPRT_UPRCL(_i) (0x003005A0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_UPRCL_MAX_INDEX 3
-#define I40E_GLPRT_UPRCL_UPRCL_SHIFT 0
-#define I40E_GLPRT_UPRCL_UPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_UPRCL_UPRCL_SHIFT)
 #define I40E_GLPRT_UPTCH(_i) (0x003009C4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_UPTCH_MAX_INDEX 3
-#define I40E_GLPRT_UPTCH_UPTCH_SHIFT 0
-#define I40E_GLPRT_UPTCH_UPTCH_MASK I40E_MASK(0xFFFF, I40E_GLPRT_UPTCH_UPTCH_SHIFT)
 #define I40E_GLPRT_UPTCL(_i) (0x003009C0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_GLPRT_UPTCL_MAX_INDEX 3
-#define I40E_GLPRT_UPTCL_VUPTCH_SHIFT 0
-#define I40E_GLPRT_UPTCL_VUPTCH_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPRT_UPTCL_VUPTCH_SHIFT)
 #define I40E_GLSW_BPRCH(_i) (0x00370104 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_BPRCH_MAX_INDEX 15
-#define I40E_GLSW_BPRCH_BPRCH_SHIFT 0
-#define I40E_GLSW_BPRCH_BPRCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_BPRCH_BPRCH_SHIFT)
 #define I40E_GLSW_BPRCL(_i) (0x00370100 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_BPRCL_MAX_INDEX 15
-#define I40E_GLSW_BPRCL_BPRCL_SHIFT 0
-#define I40E_GLSW_BPRCL_BPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_BPRCL_BPRCL_SHIFT)
 #define I40E_GLSW_BPTCH(_i) (0x00340104 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_BPTCH_MAX_INDEX 15
-#define I40E_GLSW_BPTCH_BPTCH_SHIFT 0
-#define I40E_GLSW_BPTCH_BPTCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_BPTCH_BPTCH_SHIFT)
 #define I40E_GLSW_BPTCL(_i) (0x00340100 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_BPTCL_MAX_INDEX 15
-#define I40E_GLSW_BPTCL_BPTCL_SHIFT 0
-#define I40E_GLSW_BPTCL_BPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_BPTCL_BPTCL_SHIFT)
 #define I40E_GLSW_GORCH(_i) (0x0035C004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_GORCH_MAX_INDEX 15
-#define I40E_GLSW_GORCH_GORCH_SHIFT 0
-#define I40E_GLSW_GORCH_GORCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_GORCH_GORCH_SHIFT)
 #define I40E_GLSW_GORCL(_i) (0x0035c000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_GORCL_MAX_INDEX 15
-#define I40E_GLSW_GORCL_GORCL_SHIFT 0
-#define I40E_GLSW_GORCL_GORCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_GORCL_GORCL_SHIFT)
 #define I40E_GLSW_GOTCH(_i) (0x0032C004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_GOTCH_MAX_INDEX 15
-#define I40E_GLSW_GOTCH_GOTCH_SHIFT 0
-#define I40E_GLSW_GOTCH_GOTCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_GOTCH_GOTCH_SHIFT)
 #define I40E_GLSW_GOTCL(_i) (0x0032c000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_GOTCL_MAX_INDEX 15
-#define I40E_GLSW_GOTCL_GOTCL_SHIFT 0
-#define I40E_GLSW_GOTCL_GOTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_GOTCL_GOTCL_SHIFT)
 #define I40E_GLSW_MPRCH(_i) (0x00370084 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_MPRCH_MAX_INDEX 15
-#define I40E_GLSW_MPRCH_MPRCH_SHIFT 0
-#define I40E_GLSW_MPRCH_MPRCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_MPRCH_MPRCH_SHIFT)
 #define I40E_GLSW_MPRCL(_i) (0x00370080 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_MPRCL_MAX_INDEX 15
-#define I40E_GLSW_MPRCL_MPRCL_SHIFT 0
-#define I40E_GLSW_MPRCL_MPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_MPRCL_MPRCL_SHIFT)
 #define I40E_GLSW_MPTCH(_i) (0x00340084 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_MPTCH_MAX_INDEX 15
-#define I40E_GLSW_MPTCH_MPTCH_SHIFT 0
-#define I40E_GLSW_MPTCH_MPTCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_MPTCH_MPTCH_SHIFT)
 #define I40E_GLSW_MPTCL(_i) (0x00340080 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_MPTCL_MAX_INDEX 15
-#define I40E_GLSW_MPTCL_MPTCL_SHIFT 0
-#define I40E_GLSW_MPTCL_MPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_MPTCL_MPTCL_SHIFT)
 #define I40E_GLSW_RUPP(_i) (0x00370180 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_RUPP_MAX_INDEX 15
-#define I40E_GLSW_RUPP_RUPP_SHIFT 0
-#define I40E_GLSW_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_RUPP_RUPP_SHIFT)
 #define I40E_GLSW_TDPC(_i) (0x00348000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_TDPC_MAX_INDEX 15
-#define I40E_GLSW_TDPC_TDPC_SHIFT 0
-#define I40E_GLSW_TDPC_TDPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_TDPC_TDPC_SHIFT)
 #define I40E_GLSW_UPRCH(_i) (0x00370004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_UPRCH_MAX_INDEX 15
-#define I40E_GLSW_UPRCH_UPRCH_SHIFT 0
-#define I40E_GLSW_UPRCH_UPRCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_UPRCH_UPRCH_SHIFT)
 #define I40E_GLSW_UPRCL(_i) (0x00370000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_UPRCL_MAX_INDEX 15
-#define I40E_GLSW_UPRCL_UPRCL_SHIFT 0
-#define I40E_GLSW_UPRCL_UPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_UPRCL_UPRCL_SHIFT)
 #define I40E_GLSW_UPTCH(_i) (0x00340004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_UPTCH_MAX_INDEX 15
-#define I40E_GLSW_UPTCH_UPTCH_SHIFT 0
-#define I40E_GLSW_UPTCH_UPTCH_MASK I40E_MASK(0xFFFF, I40E_GLSW_UPTCH_UPTCH_SHIFT)
 #define I40E_GLSW_UPTCL(_i) (0x00340000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLSW_UPTCL_MAX_INDEX 15
-#define I40E_GLSW_UPTCL_UPTCL_SHIFT 0
-#define I40E_GLSW_UPTCL_UPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLSW_UPTCL_UPTCL_SHIFT)
 #define I40E_GLV_BPRCH(_i) (0x0036D804 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_BPRCH_MAX_INDEX 383
-#define I40E_GLV_BPRCH_BPRCH_SHIFT 0
-#define I40E_GLV_BPRCH_BPRCH_MASK I40E_MASK(0xFFFF, I40E_GLV_BPRCH_BPRCH_SHIFT)
 #define I40E_GLV_BPRCL(_i) (0x0036d800 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_BPRCL_MAX_INDEX 383
-#define I40E_GLV_BPRCL_BPRCL_SHIFT 0
-#define I40E_GLV_BPRCL_BPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_BPRCL_BPRCL_SHIFT)
 #define I40E_GLV_BPTCH(_i) (0x0033D804 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_BPTCH_MAX_INDEX 383
-#define I40E_GLV_BPTCH_BPTCH_SHIFT 0
-#define I40E_GLV_BPTCH_BPTCH_MASK I40E_MASK(0xFFFF, I40E_GLV_BPTCH_BPTCH_SHIFT)
 #define I40E_GLV_BPTCL(_i) (0x0033d800 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_BPTCL_MAX_INDEX 383
-#define I40E_GLV_BPTCL_BPTCL_SHIFT 0
-#define I40E_GLV_BPTCL_BPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_BPTCL_BPTCL_SHIFT)
 #define I40E_GLV_GORCH(_i) (0x00358004 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_GORCH_MAX_INDEX 383
-#define I40E_GLV_GORCH_GORCH_SHIFT 0
-#define I40E_GLV_GORCH_GORCH_MASK I40E_MASK(0xFFFF, I40E_GLV_GORCH_GORCH_SHIFT)
 #define I40E_GLV_GORCL(_i) (0x00358000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_GORCL_MAX_INDEX 383
-#define I40E_GLV_GORCL_GORCL_SHIFT 0
-#define I40E_GLV_GORCL_GORCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_GORCL_GORCL_SHIFT)
 #define I40E_GLV_GOTCH(_i) (0x00328004 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_GOTCH_MAX_INDEX 383
-#define I40E_GLV_GOTCH_GOTCH_SHIFT 0
-#define I40E_GLV_GOTCH_GOTCH_MASK I40E_MASK(0xFFFF, I40E_GLV_GOTCH_GOTCH_SHIFT)
 #define I40E_GLV_GOTCL(_i) (0x00328000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_GOTCL_MAX_INDEX 383
-#define I40E_GLV_GOTCL_GOTCL_SHIFT 0
-#define I40E_GLV_GOTCL_GOTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_GOTCL_GOTCL_SHIFT)
 #define I40E_GLV_MPRCH(_i) (0x0036CC04 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_MPRCH_MAX_INDEX 383
-#define I40E_GLV_MPRCH_MPRCH_SHIFT 0
-#define I40E_GLV_MPRCH_MPRCH_MASK I40E_MASK(0xFFFF, I40E_GLV_MPRCH_MPRCH_SHIFT)
 #define I40E_GLV_MPRCL(_i) (0x0036cc00 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_MPRCL_MAX_INDEX 383
-#define I40E_GLV_MPRCL_MPRCL_SHIFT 0
-#define I40E_GLV_MPRCL_MPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_MPRCL_MPRCL_SHIFT)
 #define I40E_GLV_MPTCH(_i) (0x0033CC04 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_MPTCH_MAX_INDEX 383
-#define I40E_GLV_MPTCH_MPTCH_SHIFT 0
-#define I40E_GLV_MPTCH_MPTCH_MASK I40E_MASK(0xFFFF, I40E_GLV_MPTCH_MPTCH_SHIFT)
 #define I40E_GLV_MPTCL(_i) (0x0033cc00 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_MPTCL_MAX_INDEX 383
-#define I40E_GLV_MPTCL_MPTCL_SHIFT 0
-#define I40E_GLV_MPTCL_MPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_MPTCL_MPTCL_SHIFT)
 #define I40E_GLV_RDPC(_i) (0x00310000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_RDPC_MAX_INDEX 383
-#define I40E_GLV_RDPC_RDPC_SHIFT 0
-#define I40E_GLV_RDPC_RDPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RDPC_RDPC_SHIFT)
 #define I40E_GLV_RUPP(_i) (0x0036E400 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_RUPP_MAX_INDEX 383
-#define I40E_GLV_RUPP_RUPP_SHIFT 0
-#define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT)
 #define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_TEPC_MAX_INDEX 383
-#define I40E_GLV_TEPC_TEPC_SHIFT 0
-#define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT)
 #define I40E_GLV_UPRCH(_i) (0x0036C004 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_UPRCH_MAX_INDEX 383
-#define I40E_GLV_UPRCH_UPRCH_SHIFT 0
-#define I40E_GLV_UPRCH_UPRCH_MASK I40E_MASK(0xFFFF, I40E_GLV_UPRCH_UPRCH_SHIFT)
 #define I40E_GLV_UPRCL(_i) (0x0036c000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_UPRCL_MAX_INDEX 383
-#define I40E_GLV_UPRCL_UPRCL_SHIFT 0
-#define I40E_GLV_UPRCL_UPRCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_UPRCL_UPRCL_SHIFT)
 #define I40E_GLV_UPTCH(_i) (0x0033C004 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_UPTCH_MAX_INDEX 383
-#define I40E_GLV_UPTCH_GLVUPTCH_SHIFT 0
-#define I40E_GLV_UPTCH_GLVUPTCH_MASK I40E_MASK(0xFFFF, I40E_GLV_UPTCH_GLVUPTCH_SHIFT)
 #define I40E_GLV_UPTCL(_i) (0x0033c000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
-#define I40E_GLV_UPTCL_MAX_INDEX 383
-#define I40E_GLV_UPTCL_UPTCL_SHIFT 0
-#define I40E_GLV_UPTCL_UPTCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_UPTCL_UPTCL_SHIFT)
 #define I40E_GLVEBTC_RBCH(_i, _j) (0x00364004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_RBCH_MAX_INDEX 7
-#define I40E_GLVEBTC_RBCH_TCBCH_SHIFT 0
-#define I40E_GLVEBTC_RBCH_TCBCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBTC_RBCH_TCBCH_SHIFT)
 #define I40E_GLVEBTC_RBCL(_i, _j) (0x00364000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_RBCL_MAX_INDEX 7
-#define I40E_GLVEBTC_RBCL_TCBCL_SHIFT 0
-#define I40E_GLVEBTC_RBCL_TCBCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBTC_RBCL_TCBCL_SHIFT)
 #define I40E_GLVEBTC_RPCH(_i, _j) (0x00368004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_RPCH_MAX_INDEX 7
-#define I40E_GLVEBTC_RPCH_TCPCH_SHIFT 0
-#define I40E_GLVEBTC_RPCH_TCPCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBTC_RPCH_TCPCH_SHIFT)
 #define I40E_GLVEBTC_RPCL(_i, _j) (0x00368000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_RPCL_MAX_INDEX 7
-#define I40E_GLVEBTC_RPCL_TCPCL_SHIFT 0
-#define I40E_GLVEBTC_RPCL_TCPCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBTC_RPCL_TCPCL_SHIFT)
 #define I40E_GLVEBTC_TBCH(_i, _j) (0x00334004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_TBCH_MAX_INDEX 7
-#define I40E_GLVEBTC_TBCH_TCBCH_SHIFT 0
-#define I40E_GLVEBTC_TBCH_TCBCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBTC_TBCH_TCBCH_SHIFT)
 #define I40E_GLVEBTC_TBCL(_i, _j) (0x00334000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_TBCL_MAX_INDEX 7
-#define I40E_GLVEBTC_TBCL_TCBCL_SHIFT 0
-#define I40E_GLVEBTC_TBCL_TCBCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBTC_TBCL_TCBCL_SHIFT)
 #define I40E_GLVEBTC_TPCH(_i, _j) (0x00338004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_TPCH_MAX_INDEX 7
-#define I40E_GLVEBTC_TPCH_TCPCH_SHIFT 0
-#define I40E_GLVEBTC_TPCH_TCPCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBTC_TPCH_TCPCH_SHIFT)
 #define I40E_GLVEBTC_TPCL(_i, _j) (0x00338000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */ /* Reset: CORER */
-#define I40E_GLVEBTC_TPCL_MAX_INDEX 7
-#define I40E_GLVEBTC_TPCL_TCPCL_SHIFT 0
-#define I40E_GLVEBTC_TPCL_TCPCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBTC_TPCL_TCPCL_SHIFT)
-#define I40E_GLVEBVL_BPCH(_i) (0x00374804 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_BPCH_MAX_INDEX 127
-#define I40E_GLVEBVL_BPCH_VLBPCH_SHIFT 0
-#define I40E_GLVEBVL_BPCH_VLBPCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBVL_BPCH_VLBPCH_SHIFT)
-#define I40E_GLVEBVL_BPCL(_i) (0x00374800 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_BPCL_MAX_INDEX 127
-#define I40E_GLVEBVL_BPCL_VLBPCL_SHIFT 0
-#define I40E_GLVEBVL_BPCL_VLBPCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBVL_BPCL_VLBPCL_SHIFT)
-#define I40E_GLVEBVL_GORCH(_i) (0x00360004 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_GORCH_MAX_INDEX 127
-#define I40E_GLVEBVL_GORCH_VLBCH_SHIFT 0
-#define I40E_GLVEBVL_GORCH_VLBCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBVL_GORCH_VLBCH_SHIFT)
-#define I40E_GLVEBVL_GORCL(_i) (0x00360000 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_GORCL_MAX_INDEX 127
-#define I40E_GLVEBVL_GORCL_VLBCL_SHIFT 0
-#define I40E_GLVEBVL_GORCL_VLBCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBVL_GORCL_VLBCL_SHIFT)
-#define I40E_GLVEBVL_GOTCH(_i) (0x00330004 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_GOTCH_MAX_INDEX 127
-#define I40E_GLVEBVL_GOTCH_VLBCH_SHIFT 0
-#define I40E_GLVEBVL_GOTCH_VLBCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBVL_GOTCH_VLBCH_SHIFT)
-#define I40E_GLVEBVL_GOTCL(_i) (0x00330000 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_GOTCL_MAX_INDEX 127
-#define I40E_GLVEBVL_GOTCL_VLBCL_SHIFT 0
-#define I40E_GLVEBVL_GOTCL_VLBCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBVL_GOTCL_VLBCL_SHIFT)
-#define I40E_GLVEBVL_MPCH(_i) (0x00374404 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_MPCH_MAX_INDEX 127
-#define I40E_GLVEBVL_MPCH_VLMPCH_SHIFT 0
-#define I40E_GLVEBVL_MPCH_VLMPCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBVL_MPCH_VLMPCH_SHIFT)
-#define I40E_GLVEBVL_MPCL(_i) (0x00374400 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_MPCL_MAX_INDEX 127
-#define I40E_GLVEBVL_MPCL_VLMPCL_SHIFT 0
-#define I40E_GLVEBVL_MPCL_VLMPCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBVL_MPCL_VLMPCL_SHIFT)
-#define I40E_GLVEBVL_UPCH(_i) (0x00374004 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_UPCH_MAX_INDEX 127
-#define I40E_GLVEBVL_UPCH_VLUPCH_SHIFT 0
-#define I40E_GLVEBVL_UPCH_VLUPCH_MASK I40E_MASK(0xFFFF, I40E_GLVEBVL_UPCH_VLUPCH_SHIFT)
-#define I40E_GLVEBVL_UPCL(_i) (0x00374000 + ((_i) * 8)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_GLVEBVL_UPCL_MAX_INDEX 127
-#define I40E_GLVEBVL_UPCL_VLUPCL_SHIFT 0
-#define I40E_GLVEBVL_UPCL_VLUPCL_MASK I40E_MASK(0xFFFFFFFF, I40E_GLVEBVL_UPCL_VLUPCL_SHIFT)
-#define I40E_GL_MTG_FLU_MSK_H 0x00269F4C /* Reset: CORER */
-#define I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_SHIFT 0
-#define I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_MASK I40E_MASK(0xFFFF, I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_SHIFT)
-#define I40E_GL_SWR_DEF_ACT(_i) (0x00270200 + ((_i) * 4)) /* _i=0...35 */ /* Reset: CORER */
-#define I40E_GL_SWR_DEF_ACT_MAX_INDEX 35
-#define I40E_GL_SWR_DEF_ACT_DEF_ACTION_SHIFT 0
-#define I40E_GL_SWR_DEF_ACT_DEF_ACTION_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_SWR_DEF_ACT_DEF_ACTION_SHIFT)
-#define I40E_GL_SWR_DEF_ACT_EN(_i) (0x0026CFB8 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
-#define I40E_GL_SWR_DEF_ACT_EN_MAX_INDEX 1
-#define I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_SHIFT 0
-#define I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_SHIFT)
-#define I40E_PRTTSYN_ADJ 0x001E4280 /* Reset: GLOBR */
-#define I40E_PRTTSYN_ADJ_TSYNADJ_SHIFT 0
-#define I40E_PRTTSYN_ADJ_TSYNADJ_MASK I40E_MASK(0x7FFFFFFF, I40E_PRTTSYN_ADJ_TSYNADJ_SHIFT)
-#define I40E_PRTTSYN_ADJ_SIGN_SHIFT 31
-#define I40E_PRTTSYN_ADJ_SIGN_MASK I40E_MASK(0x1, I40E_PRTTSYN_ADJ_SIGN_SHIFT)
-#define I40E_PRTTSYN_AUX_0(_i) (0x001E42A0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_AUX_0_MAX_INDEX 1
-#define I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT 0
-#define I40E_PRTTSYN_AUX_0_OUT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT)
-#define I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT 1
-#define I40E_PRTTSYN_AUX_0_OUTMOD_MASK I40E_MASK(0x3, I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT)
-#define I40E_PRTTSYN_AUX_0_OUTLVL_SHIFT 3
-#define I40E_PRTTSYN_AUX_0_OUTLVL_MASK I40E_MASK(0x1, I40E_PRTTSYN_AUX_0_OUTLVL_SHIFT)
-#define I40E_PRTTSYN_AUX_0_PULSEW_SHIFT 8
-#define I40E_PRTTSYN_AUX_0_PULSEW_MASK I40E_MASK(0xF, I40E_PRTTSYN_AUX_0_PULSEW_SHIFT)
-#define I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT 16
-#define I40E_PRTTSYN_AUX_0_EVNTLVL_MASK I40E_MASK(0x3, I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT)
-#define I40E_PRTTSYN_AUX_1(_i) (0x001E42E0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_AUX_1_MAX_INDEX 1
-#define I40E_PRTTSYN_AUX_1_INSTNT_SHIFT 0
-#define I40E_PRTTSYN_AUX_1_INSTNT_MASK I40E_MASK(0x1, I40E_PRTTSYN_AUX_1_INSTNT_SHIFT)
-#define I40E_PRTTSYN_AUX_1_SAMPLE_TIME_SHIFT 1
-#define I40E_PRTTSYN_AUX_1_SAMPLE_TIME_MASK I40E_MASK(0x1, I40E_PRTTSYN_AUX_1_SAMPLE_TIME_SHIFT)
-#define I40E_PRTTSYN_CLKO(_i) (0x001E4240 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_CLKO_MAX_INDEX 1
-#define I40E_PRTTSYN_CLKO_TSYNCLKO_SHIFT 0
-#define I40E_PRTTSYN_CLKO_TSYNCLKO_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_CLKO_TSYNCLKO_SHIFT)
 #define I40E_PRTTSYN_CTL0 0x001E4200 /* Reset: GLOBR */
-#define I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_SHIFT 0
-#define I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_SHIFT)
 #define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT 1
 #define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT)
-#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT 2
-#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT)
-#define I40E_PRTTSYN_CTL0_TGT_INT_ENA_SHIFT 3
-#define I40E_PRTTSYN_CTL0_TGT_INT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_TGT_INT_ENA_SHIFT)
 #define I40E_PRTTSYN_CTL0_PF_ID_SHIFT 8
 #define I40E_PRTTSYN_CTL0_PF_ID_MASK I40E_MASK(0xF, I40E_PRTTSYN_CTL0_PF_ID_SHIFT)
-#define I40E_PRTTSYN_CTL0_TSYNACT_SHIFT 12
-#define I40E_PRTTSYN_CTL0_TSYNACT_MASK I40E_MASK(0x3, I40E_PRTTSYN_CTL0_TSYNACT_SHIFT)
 #define I40E_PRTTSYN_CTL0_TSYNENA_SHIFT 31
 #define I40E_PRTTSYN_CTL0_TSYNENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_TSYNENA_SHIFT)
 #define I40E_PRTTSYN_CTL1 0x00085020 /* Reset: CORER */
 #define I40E_PRTTSYN_CTL1_V1MESSTYPE0_SHIFT 0
 #define I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK I40E_MASK(0xFF, I40E_PRTTSYN_CTL1_V1MESSTYPE0_SHIFT)
-#define I40E_PRTTSYN_CTL1_V1MESSTYPE1_SHIFT 8
-#define I40E_PRTTSYN_CTL1_V1MESSTYPE1_MASK I40E_MASK(0xFF, I40E_PRTTSYN_CTL1_V1MESSTYPE1_SHIFT)
 #define I40E_PRTTSYN_CTL1_V2MESSTYPE0_SHIFT 16
 #define I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK I40E_MASK(0xF, I40E_PRTTSYN_CTL1_V2MESSTYPE0_SHIFT)
-#define I40E_PRTTSYN_CTL1_V2MESSTYPE1_SHIFT 20
-#define I40E_PRTTSYN_CTL1_V2MESSTYPE1_MASK I40E_MASK(0xF, I40E_PRTTSYN_CTL1_V2MESSTYPE1_SHIFT)
 #define I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT 24
-#define I40E_PRTTSYN_CTL1_TSYNTYPE_MASK I40E_MASK(0x3, I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
 #define I40E_PRTTSYN_CTL1_UDP_ENA_SHIFT 26
 #define I40E_PRTTSYN_CTL1_UDP_ENA_MASK I40E_MASK(0x3, I40E_PRTTSYN_CTL1_UDP_ENA_SHIFT)
 #define I40E_PRTTSYN_CTL1_TSYNENA_SHIFT 31
 #define I40E_PRTTSYN_CTL1_TSYNENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL1_TSYNENA_SHIFT)
-#define I40E_PRTTSYN_EVNT_H(_i) (0x001E40C0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_EVNT_H_MAX_INDEX 1
-#define I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_SHIFT 0
-#define I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_SHIFT)
-#define I40E_PRTTSYN_EVNT_L(_i) (0x001E4080 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_EVNT_L_MAX_INDEX 1
-#define I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_SHIFT 0
-#define I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_SHIFT)
 #define I40E_PRTTSYN_INC_H 0x001E4060 /* Reset: GLOBR */
-#define I40E_PRTTSYN_INC_H_TSYNINC_H_SHIFT 0
-#define I40E_PRTTSYN_INC_H_TSYNINC_H_MASK I40E_MASK(0x3F, I40E_PRTTSYN_INC_H_TSYNINC_H_SHIFT)
 #define I40E_PRTTSYN_INC_L 0x001E4040 /* Reset: GLOBR */
-#define I40E_PRTTSYN_INC_L_TSYNINC_L_SHIFT 0
-#define I40E_PRTTSYN_INC_L_TSYNINC_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_INC_L_TSYNINC_L_SHIFT)
 #define I40E_PRTTSYN_RXTIME_H(_i) (0x00085040 + ((_i) * 32)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_PRTTSYN_RXTIME_H_MAX_INDEX 3
-#define I40E_PRTTSYN_RXTIME_H_RXTIEM_H_SHIFT 0
-#define I40E_PRTTSYN_RXTIME_H_RXTIEM_H_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_RXTIME_H_RXTIEM_H_SHIFT)
 #define I40E_PRTTSYN_RXTIME_L(_i) (0x000850C0 + ((_i) * 32)) /* _i=0...3 */ /* Reset: CORER */
-#define I40E_PRTTSYN_RXTIME_L_MAX_INDEX 3
-#define I40E_PRTTSYN_RXTIME_L_RXTIEM_L_SHIFT 0
-#define I40E_PRTTSYN_RXTIME_L_RXTIEM_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_RXTIME_L_RXTIEM_L_SHIFT)
 #define I40E_PRTTSYN_STAT_0 0x001E4220 /* Reset: GLOBR */
-#define I40E_PRTTSYN_STAT_0_EVENT0_SHIFT 0
-#define I40E_PRTTSYN_STAT_0_EVENT0_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_EVENT0_SHIFT)
-#define I40E_PRTTSYN_STAT_0_EVENT1_SHIFT 1
-#define I40E_PRTTSYN_STAT_0_EVENT1_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_EVENT1_SHIFT)
-#define I40E_PRTTSYN_STAT_0_TGT0_SHIFT 2
-#define I40E_PRTTSYN_STAT_0_TGT0_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_TGT0_SHIFT)
-#define I40E_PRTTSYN_STAT_0_TGT1_SHIFT 3
-#define I40E_PRTTSYN_STAT_0_TGT1_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_TGT1_SHIFT)
 #define I40E_PRTTSYN_STAT_0_TXTIME_SHIFT 4
 #define I40E_PRTTSYN_STAT_0_TXTIME_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_TXTIME_SHIFT)
 #define I40E_PRTTSYN_STAT_1 0x00085140 /* Reset: CORER */
-#define I40E_PRTTSYN_STAT_1_RXT0_SHIFT 0
-#define I40E_PRTTSYN_STAT_1_RXT0_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_1_RXT0_SHIFT)
-#define I40E_PRTTSYN_STAT_1_RXT1_SHIFT 1
-#define I40E_PRTTSYN_STAT_1_RXT1_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_1_RXT1_SHIFT)
-#define I40E_PRTTSYN_STAT_1_RXT2_SHIFT 2
-#define I40E_PRTTSYN_STAT_1_RXT2_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_1_RXT2_SHIFT)
-#define I40E_PRTTSYN_STAT_1_RXT3_SHIFT 3
-#define I40E_PRTTSYN_STAT_1_RXT3_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_1_RXT3_SHIFT)
-#define I40E_PRTTSYN_TGT_H(_i) (0x001E4180 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_TGT_H_MAX_INDEX 1
-#define I40E_PRTTSYN_TGT_H_TSYNTGTT_H_SHIFT 0
-#define I40E_PRTTSYN_TGT_H_TSYNTGTT_H_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TGT_H_TSYNTGTT_H_SHIFT)
-#define I40E_PRTTSYN_TGT_L(_i) (0x001E4140 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
-#define I40E_PRTTSYN_TGT_L_MAX_INDEX 1
-#define I40E_PRTTSYN_TGT_L_TSYNTGTT_L_SHIFT 0
-#define I40E_PRTTSYN_TGT_L_TSYNTGTT_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TGT_L_TSYNTGTT_L_SHIFT)
 #define I40E_PRTTSYN_TIME_H 0x001E4120 /* Reset: GLOBR */
-#define I40E_PRTTSYN_TIME_H_TSYNTIME_H_SHIFT 0
-#define I40E_PRTTSYN_TIME_H_TSYNTIME_H_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TIME_H_TSYNTIME_H_SHIFT)
 #define I40E_PRTTSYN_TIME_L 0x001E4100 /* Reset: GLOBR */
-#define I40E_PRTTSYN_TIME_L_TSYNTIME_L_SHIFT 0
-#define I40E_PRTTSYN_TIME_L_TSYNTIME_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TIME_L_TSYNTIME_L_SHIFT)
 #define I40E_PRTTSYN_TXTIME_H 0x001E41E0 /* Reset: GLOBR */
-#define I40E_PRTTSYN_TXTIME_H_TXTIEM_H_SHIFT 0
-#define I40E_PRTTSYN_TXTIME_H_TXTIEM_H_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TXTIME_H_TXTIEM_H_SHIFT)
 #define I40E_PRTTSYN_TXTIME_L 0x001E41C0 /* Reset: GLOBR */
-#define I40E_PRTTSYN_TXTIME_L_TXTIEM_L_SHIFT 0
-#define I40E_PRTTSYN_TXTIME_L_TXTIEM_L_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTTSYN_TXTIME_L_TXTIEM_L_SHIFT)
 #define I40E_GL_MDET_RX 0x0012A510 /* Reset: CORER */
 #define I40E_GL_MDET_RX_FUNCTION_SHIFT 0
 #define I40E_GL_MDET_RX_FUNCTION_MASK I40E_MASK(0xFF, I40E_GL_MDET_RX_FUNCTION_SHIFT)
@@ -3033,2304 +628,53 @@
 #define I40E_PF_VT_PFALLOC_VALID_SHIFT 31
 #define I40E_PF_VT_PFALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PF_VT_PFALLOC_VALID_SHIFT)
 #define I40E_VP_MDET_RX(_VF) (0x0012A000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VP_MDET_RX_MAX_INDEX 127
 #define I40E_VP_MDET_RX_VALID_SHIFT 0
 #define I40E_VP_MDET_RX_VALID_MASK I40E_MASK(0x1, I40E_VP_MDET_RX_VALID_SHIFT)
 #define I40E_VP_MDET_TX(_VF) (0x000E6000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_VP_MDET_TX_MAX_INDEX 127
 #define I40E_VP_MDET_TX_VALID_SHIFT 0
 #define I40E_VP_MDET_TX_VALID_MASK I40E_MASK(0x1, I40E_VP_MDET_TX_VALID_SHIFT)
-#define I40E_GLPM_WUMC 0x0006C800 /* Reset: POR */
-#define I40E_GLPM_WUMC_NOTCO_SHIFT 0
-#define I40E_GLPM_WUMC_NOTCO_MASK I40E_MASK(0x1, I40E_GLPM_WUMC_NOTCO_SHIFT)
-#define I40E_GLPM_WUMC_SRST_PIN_VAL_SHIFT 1
-#define I40E_GLPM_WUMC_SRST_PIN_VAL_MASK I40E_MASK(0x1, I40E_GLPM_WUMC_SRST_PIN_VAL_SHIFT)
-#define I40E_GLPM_WUMC_ROL_MODE_SHIFT 2
-#define I40E_GLPM_WUMC_ROL_MODE_MASK I40E_MASK(0x1, I40E_GLPM_WUMC_ROL_MODE_SHIFT)
-#define I40E_GLPM_WUMC_RESERVED_4_SHIFT 3
-#define I40E_GLPM_WUMC_RESERVED_4_MASK I40E_MASK(0x1FFF, I40E_GLPM_WUMC_RESERVED_4_SHIFT)
-#define I40E_GLPM_WUMC_MNG_WU_PF_SHIFT 16
-#define I40E_GLPM_WUMC_MNG_WU_PF_MASK I40E_MASK(0xFFFF, I40E_GLPM_WUMC_MNG_WU_PF_SHIFT)
 #define I40E_PFPM_APM 0x000B8080 /* Reset: POR */
 #define I40E_PFPM_APM_APME_SHIFT 0
 #define I40E_PFPM_APM_APME_MASK I40E_MASK(0x1, I40E_PFPM_APM_APME_SHIFT)
-#define I40E_PFPM_FHFT_LENGTH(_i) (0x0006A000 + ((_i) * 128)) /* _i=0...7 */ /* Reset: POR */
-#define I40E_PFPM_FHFT_LENGTH_MAX_INDEX 7
-#define I40E_PFPM_FHFT_LENGTH_LENGTH_SHIFT 0
-#define I40E_PFPM_FHFT_LENGTH_LENGTH_MASK I40E_MASK(0xFF, I40E_PFPM_FHFT_LENGTH_LENGTH_SHIFT)
-#define I40E_PFPM_WUC 0x0006B200 /* Reset: POR */
-#define I40E_PFPM_WUC_EN_APM_D0_SHIFT 5
-#define I40E_PFPM_WUC_EN_APM_D0_MASK I40E_MASK(0x1, I40E_PFPM_WUC_EN_APM_D0_SHIFT)
 #define I40E_PFPM_WUFC 0x0006B400 /* Reset: POR */
-#define I40E_PFPM_WUFC_LNKC_SHIFT 0
-#define I40E_PFPM_WUFC_LNKC_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_LNKC_SHIFT)
 #define I40E_PFPM_WUFC_MAG_SHIFT 1
 #define I40E_PFPM_WUFC_MAG_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_MAG_SHIFT)
-#define I40E_PFPM_WUFC_MNG_SHIFT 3
-#define I40E_PFPM_WUFC_MNG_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_MNG_SHIFT)
-#define I40E_PFPM_WUFC_FLX0_ACT_SHIFT 4
-#define I40E_PFPM_WUFC_FLX0_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX0_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX1_ACT_SHIFT 5
-#define I40E_PFPM_WUFC_FLX1_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX1_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX2_ACT_SHIFT 6
-#define I40E_PFPM_WUFC_FLX2_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX2_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX3_ACT_SHIFT 7
-#define I40E_PFPM_WUFC_FLX3_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX3_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX4_ACT_SHIFT 8
-#define I40E_PFPM_WUFC_FLX4_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX4_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX5_ACT_SHIFT 9
-#define I40E_PFPM_WUFC_FLX5_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX5_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX6_ACT_SHIFT 10
-#define I40E_PFPM_WUFC_FLX6_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX6_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX7_ACT_SHIFT 11
-#define I40E_PFPM_WUFC_FLX7_ACT_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX7_ACT_SHIFT)
-#define I40E_PFPM_WUFC_FLX0_SHIFT 16
-#define I40E_PFPM_WUFC_FLX0_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX0_SHIFT)
-#define I40E_PFPM_WUFC_FLX1_SHIFT 17
-#define I40E_PFPM_WUFC_FLX1_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX1_SHIFT)
-#define I40E_PFPM_WUFC_FLX2_SHIFT 18
-#define I40E_PFPM_WUFC_FLX2_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX2_SHIFT)
-#define I40E_PFPM_WUFC_FLX3_SHIFT 19
-#define I40E_PFPM_WUFC_FLX3_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX3_SHIFT)
-#define I40E_PFPM_WUFC_FLX4_SHIFT 20
-#define I40E_PFPM_WUFC_FLX4_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX4_SHIFT)
-#define I40E_PFPM_WUFC_FLX5_SHIFT 21
-#define I40E_PFPM_WUFC_FLX5_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX5_SHIFT)
-#define I40E_PFPM_WUFC_FLX6_SHIFT 22
-#define I40E_PFPM_WUFC_FLX6_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX6_SHIFT)
-#define I40E_PFPM_WUFC_FLX7_SHIFT 23
-#define I40E_PFPM_WUFC_FLX7_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FLX7_SHIFT)
-#define I40E_PFPM_WUFC_FW_RST_WK_SHIFT 31
-#define I40E_PFPM_WUFC_FW_RST_WK_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_FW_RST_WK_SHIFT)
-#define I40E_PFPM_WUS 0x0006B600 /* Reset: POR */
-#define I40E_PFPM_WUS_LNKC_SHIFT 0
-#define I40E_PFPM_WUS_LNKC_MASK I40E_MASK(0x1, I40E_PFPM_WUS_LNKC_SHIFT)
-#define I40E_PFPM_WUS_MAG_SHIFT 1
-#define I40E_PFPM_WUS_MAG_MASK I40E_MASK(0x1, I40E_PFPM_WUS_MAG_SHIFT)
-#define I40E_PFPM_WUS_PME_STATUS_SHIFT 2
-#define I40E_PFPM_WUS_PME_STATUS_MASK I40E_MASK(0x1, I40E_PFPM_WUS_PME_STATUS_SHIFT)
-#define I40E_PFPM_WUS_MNG_SHIFT 3
-#define I40E_PFPM_WUS_MNG_MASK I40E_MASK(0x1, I40E_PFPM_WUS_MNG_SHIFT)
-#define I40E_PFPM_WUS_FLX0_SHIFT 16
-#define I40E_PFPM_WUS_FLX0_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX0_SHIFT)
-#define I40E_PFPM_WUS_FLX1_SHIFT 17
-#define I40E_PFPM_WUS_FLX1_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX1_SHIFT)
-#define I40E_PFPM_WUS_FLX2_SHIFT 18
-#define I40E_PFPM_WUS_FLX2_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX2_SHIFT)
-#define I40E_PFPM_WUS_FLX3_SHIFT 19
-#define I40E_PFPM_WUS_FLX3_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX3_SHIFT)
-#define I40E_PFPM_WUS_FLX4_SHIFT 20
-#define I40E_PFPM_WUS_FLX4_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX4_SHIFT)
-#define I40E_PFPM_WUS_FLX5_SHIFT 21
-#define I40E_PFPM_WUS_FLX5_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX5_SHIFT)
-#define I40E_PFPM_WUS_FLX6_SHIFT 22
-#define I40E_PFPM_WUS_FLX6_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX6_SHIFT)
-#define I40E_PFPM_WUS_FLX7_SHIFT 23
-#define I40E_PFPM_WUS_FLX7_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FLX7_SHIFT)
-#define I40E_PFPM_WUS_FW_RST_WK_SHIFT 31
-#define I40E_PFPM_WUS_FW_RST_WK_MASK I40E_MASK(0x1, I40E_PFPM_WUS_FW_RST_WK_SHIFT)
-#define I40E_PRTPM_FHFHR 0x0006C000 /* Reset: POR */
-#define I40E_PRTPM_FHFHR_UNICAST_SHIFT 0
-#define I40E_PRTPM_FHFHR_UNICAST_MASK I40E_MASK(0x1, I40E_PRTPM_FHFHR_UNICAST_SHIFT)
-#define I40E_PRTPM_FHFHR_MULTICAST_SHIFT 1
-#define I40E_PRTPM_FHFHR_MULTICAST_MASK I40E_MASK(0x1, I40E_PRTPM_FHFHR_MULTICAST_SHIFT)
-#define I40E_PRTPM_SAH(_i) (0x001E44C0 + ((_i) * 32)) /* _i=0...3 */ /* Reset: PFR */
-#define I40E_PRTPM_SAH_MAX_INDEX 3
-#define I40E_PRTPM_SAH_PFPM_SAH_SHIFT 0
-#define I40E_PRTPM_SAH_PFPM_SAH_MASK I40E_MASK(0xFFFF, I40E_PRTPM_SAH_PFPM_SAH_SHIFT)
-#define I40E_PRTPM_SAH_PF_NUM_SHIFT 26
-#define I40E_PRTPM_SAH_PF_NUM_MASK I40E_MASK(0xF, I40E_PRTPM_SAH_PF_NUM_SHIFT)
-#define I40E_PRTPM_SAH_MC_MAG_EN_SHIFT 30
-#define I40E_PRTPM_SAH_MC_MAG_EN_MASK I40E_MASK(0x1, I40E_PRTPM_SAH_MC_MAG_EN_SHIFT)
-#define I40E_PRTPM_SAH_AV_SHIFT 31
-#define I40E_PRTPM_SAH_AV_MASK I40E_MASK(0x1, I40E_PRTPM_SAH_AV_SHIFT)
-#define I40E_PRTPM_SAL(_i) (0x001E4440 + ((_i) * 32)) /* _i=0...3 */ /* Reset: PFR */
-#define I40E_PRTPM_SAL_MAX_INDEX 3
-#define I40E_PRTPM_SAL_PFPM_SAL_SHIFT 0
-#define I40E_PRTPM_SAL_PFPM_SAL_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTPM_SAL_PFPM_SAL_SHIFT)
 #define I40E_VF_ARQBAH1 0x00006000 /* Reset: EMPR */
-#define I40E_VF_ARQBAH1_ARQBAH_SHIFT 0
-#define I40E_VF_ARQBAH1_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAH1_ARQBAH_SHIFT)
 #define I40E_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */
-#define I40E_VF_ARQBAL1_ARQBAL_SHIFT 0
-#define I40E_VF_ARQBAL1_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAL1_ARQBAL_SHIFT)
 #define I40E_VF_ARQH1 0x00007400 /* Reset: EMPR */
-#define I40E_VF_ARQH1_ARQH_SHIFT 0
-#define I40E_VF_ARQH1_ARQH_MASK I40E_MASK(0x3FF, I40E_VF_ARQH1_ARQH_SHIFT)
 #define I40E_VF_ARQLEN1 0x00008000 /* Reset: EMPR */
-#define I40E_VF_ARQLEN1_ARQLEN_SHIFT 0
-#define I40E_VF_ARQLEN1_ARQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ARQLEN1_ARQLEN_SHIFT)
-#define I40E_VF_ARQLEN1_ARQVFE_SHIFT 28
-#define I40E_VF_ARQLEN1_ARQVFE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQVFE_SHIFT)
-#define I40E_VF_ARQLEN1_ARQOVFL_SHIFT 29
-#define I40E_VF_ARQLEN1_ARQOVFL_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQOVFL_SHIFT)
-#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30
-#define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT)
-#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31
-#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN1_ARQENABLE_SHIFT)
 #define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */
-#define I40E_VF_ARQT1_ARQT_SHIFT 0
-#define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT)
 #define I40E_VF_ATQBAH1 0x00007800 /* Reset: EMPR */
-#define I40E_VF_ATQBAH1_ATQBAH_SHIFT 0
-#define I40E_VF_ATQBAH1_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAH1_ATQBAH_SHIFT)
 #define I40E_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */
-#define I40E_VF_ATQBAL1_ATQBAL_SHIFT 0
-#define I40E_VF_ATQBAL1_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAL1_ATQBAL_SHIFT)
 #define I40E_VF_ATQH1 0x00006400 /* Reset: EMPR */
-#define I40E_VF_ATQH1_ATQH_SHIFT 0
-#define I40E_VF_ATQH1_ATQH_MASK I40E_MASK(0x3FF, I40E_VF_ATQH1_ATQH_SHIFT)
 #define I40E_VF_ATQLEN1 0x00006800 /* Reset: EMPR */
-#define I40E_VF_ATQLEN1_ATQLEN_SHIFT 0
-#define I40E_VF_ATQLEN1_ATQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ATQLEN1_ATQLEN_SHIFT)
-#define I40E_VF_ATQLEN1_ATQVFE_SHIFT 28
-#define I40E_VF_ATQLEN1_ATQVFE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQVFE_SHIFT)
-#define I40E_VF_ATQLEN1_ATQOVFL_SHIFT 29
-#define I40E_VF_ATQLEN1_ATQOVFL_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQOVFL_SHIFT)
-#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30
-#define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT)
-#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31
-#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN1_ATQENABLE_SHIFT)
 #define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */
-#define I40E_VF_ATQT1_ATQT_SHIFT 0
-#define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT)
-#define I40E_VFGEN_RSTAT 0x00008800 /* Reset: VFR */
-#define I40E_VFGEN_RSTAT_VFR_STATE_SHIFT 0
-#define I40E_VFGEN_RSTAT_VFR_STATE_MASK I40E_MASK(0x3, I40E_VFGEN_RSTAT_VFR_STATE_SHIFT)
-#define I40E_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */
-#define I40E_VFINT_DYN_CTL01_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTL01_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT 1
-#define I40E_VFINT_DYN_CTL01_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTL01_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTL01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTL01_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT)
-#define I40E_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */
-#define I40E_VFINT_DYN_CTLN1_MAX_INDEX 15
-#define I40E_VFINT_DYN_CTLN1_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTLN1_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT 1
-#define I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTLN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT)
-#define I40E_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */
-#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR0_ENA1_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR0_ENA1_RSVD_SHIFT 31
-#define I40E_VFINT_ICR0_ENA1_RSVD_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_RSVD_SHIFT)
-#define I40E_VFINT_ICR01 0x00004800 /* Reset: CORER */
-#define I40E_VFINT_ICR01_INTEVENT_SHIFT 0
-#define I40E_VFINT_ICR01_INTEVENT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_INTEVENT_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_0_SHIFT 1
-#define I40E_VFINT_ICR01_QUEUE_0_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_0_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_1_SHIFT 2
-#define I40E_VFINT_ICR01_QUEUE_1_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_1_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_2_SHIFT 3
-#define I40E_VFINT_ICR01_QUEUE_2_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_2_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_3_SHIFT 4
-#define I40E_VFINT_ICR01_QUEUE_3_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_3_SHIFT)
-#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR01_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR01_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR01_SWINT_SHIFT 31
-#define I40E_VFINT_ICR01_SWINT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_SWINT_SHIFT)
-#define I40E_VFINT_ITR01(_i) (0x00004C00 + ((_i) * 4)) /* _i=0...2 */ /* Reset: VFR */
-#define I40E_VFINT_ITR01_MAX_INDEX 2
-#define I40E_VFINT_ITR01_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITR01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITR01_INTERVAL_SHIFT)
-#define I40E_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */
-#define I40E_VFINT_ITRN1_MAX_INDEX 2
-#define I40E_VFINT_ITRN1_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITRN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITRN1_INTERVAL_SHIFT)
-#define I40E_VFINT_STAT_CTL01 0x00005400 /* Reset: CORER */
-#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT 2
-#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT)
-#define I40E_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_QRX_TAIL1_MAX_INDEX 15
-#define I40E_QRX_TAIL1_TAIL_SHIFT 0
-#define I40E_QRX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QRX_TAIL1_TAIL_SHIFT)
-#define I40E_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */
-#define I40E_QTX_TAIL1_MAX_INDEX 15
-#define I40E_QTX_TAIL1_TAIL_SHIFT 0
-#define I40E_QTX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QTX_TAIL1_TAIL_SHIFT)
-#define I40E_VFMSIX_PBA 0x00002000 /* Reset: VFLR */
-#define I40E_VFMSIX_PBA_PENBIT_SHIFT 0
-#define I40E_VFMSIX_PBA_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA_PENBIT_SHIFT)
-#define I40E_VFMSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TADD_MAX_INDEX 16
-#define I40E_VFMSIX_TADD_MSIXTADD10_SHIFT 0
-#define I40E_VFMSIX_TADD_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD_MSIXTADD10_SHIFT)
-#define I40E_VFMSIX_TADD_MSIXTADD_SHIFT 2
-#define I40E_VFMSIX_TADD_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD_MSIXTADD_SHIFT)
-#define I40E_VFMSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TMSG_MAX_INDEX 16
-#define I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT 0
-#define I40E_VFMSIX_TMSG_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT)
-#define I40E_VFMSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TUADD_MAX_INDEX 16
-#define I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT 0
-#define I40E_VFMSIX_TUADD_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT)
-#define I40E_VFMSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TVCTRL_MAX_INDEX 16
-#define I40E_VFMSIX_TVCTRL_MASK_SHIFT 0
-#define I40E_VFMSIX_TVCTRL_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL_MASK_SHIFT)
-#define I40E_VFCM_PE_ERRDATA 0x0000DC00 /* Reset: VFR */
-#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0
-#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT 4
-#define I40E_VFCM_PE_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT 8
-#define I40E_VFCM_PE_ERRDATA_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT)
-#define I40E_VFCM_PE_ERRINFO 0x0000D800 /* Reset: VFR */
-#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0
-#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT 4
-#define I40E_VFCM_PE_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8
-#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16
-#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24
-#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT)
-#define I40E_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
-#define I40E_VFQF_HENA_MAX_INDEX 1
-#define I40E_VFQF_HENA_PTYPE_ENA_SHIFT 0
-#define I40E_VFQF_HENA_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_VFQF_HENA_PTYPE_ENA_SHIFT)
-#define I40E_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */
-#define I40E_VFQF_HKEY_MAX_INDEX 12
-#define I40E_VFQF_HKEY_KEY_0_SHIFT 0
-#define I40E_VFQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_0_SHIFT)
-#define I40E_VFQF_HKEY_KEY_1_SHIFT 8
-#define I40E_VFQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_1_SHIFT)
-#define I40E_VFQF_HKEY_KEY_2_SHIFT 16
-#define I40E_VFQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_2_SHIFT)
-#define I40E_VFQF_HKEY_KEY_3_SHIFT 24
-#define I40E_VFQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_3_SHIFT)
-#define I40E_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
 #define I40E_VFQF_HLUT_MAX_INDEX 15
-#define I40E_VFQF_HLUT_LUT0_SHIFT 0
-#define I40E_VFQF_HLUT_LUT0_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT0_SHIFT)
-#define I40E_VFQF_HLUT_LUT1_SHIFT 8
-#define I40E_VFQF_HLUT_LUT1_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT1_SHIFT)
-#define I40E_VFQF_HLUT_LUT2_SHIFT 16
-#define I40E_VFQF_HLUT_LUT2_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT2_SHIFT)
-#define I40E_VFQF_HLUT_LUT3_SHIFT 24
-#define I40E_VFQF_HLUT_LUT3_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT3_SHIFT)
-#define I40E_VFQF_HREGION(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_VFQF_HREGION_MAX_INDEX 7
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT)
-#define I40E_VFQF_HREGION_REGION_0_SHIFT 1
-#define I40E_VFQF_HREGION_REGION_0_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_0_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT)
-#define I40E_VFQF_HREGION_REGION_1_SHIFT 5
-#define I40E_VFQF_HREGION_REGION_1_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_1_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT)
-#define I40E_VFQF_HREGION_REGION_2_SHIFT 9
-#define I40E_VFQF_HREGION_REGION_2_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_2_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT)
-#define I40E_VFQF_HREGION_REGION_3_SHIFT 13
-#define I40E_VFQF_HREGION_REGION_3_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_3_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT)
-#define I40E_VFQF_HREGION_REGION_4_SHIFT 17
-#define I40E_VFQF_HREGION_REGION_4_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_4_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT)
-#define I40E_VFQF_HREGION_REGION_5_SHIFT 21
-#define I40E_VFQF_HREGION_REGION_5_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_5_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT)
-#define I40E_VFQF_HREGION_REGION_6_SHIFT 25
-#define I40E_VFQF_HREGION_REGION_6_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_6_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT)
-#define I40E_VFQF_HREGION_REGION_7_SHIFT 29
-#define I40E_VFQF_HREGION_REGION_7_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_7_SHIFT)
 
-#define I40E_MNGSB_FDCRC 0x000B7050 /* Reset: POR */
-#define I40E_MNGSB_FDCRC_CRC_RES_SHIFT 0
-#define I40E_MNGSB_FDCRC_CRC_RES_MASK I40E_MASK(0xFF, I40E_MNGSB_FDCRC_CRC_RES_SHIFT)
-#define I40E_MNGSB_FDCS 0x000B7040 /* Reset: POR */
-#define I40E_MNGSB_FDCS_CRC_CONT_SHIFT 2
-#define I40E_MNGSB_FDCS_CRC_CONT_MASK I40E_MASK(0x1, I40E_MNGSB_FDCS_CRC_CONT_SHIFT)
-#define I40E_MNGSB_FDCS_CRC_SEED_EN_SHIFT 3
-#define I40E_MNGSB_FDCS_CRC_SEED_EN_MASK I40E_MASK(0x1, I40E_MNGSB_FDCS_CRC_SEED_EN_SHIFT)
-#define I40E_MNGSB_FDCS_CRC_WR_INH_SHIFT 4
-#define I40E_MNGSB_FDCS_CRC_WR_INH_MASK I40E_MASK(0x1, I40E_MNGSB_FDCS_CRC_WR_INH_SHIFT)
-#define I40E_MNGSB_FDCS_CRC_SEED_SHIFT 8
-#define I40E_MNGSB_FDCS_CRC_SEED_MASK I40E_MASK(0xFF, I40E_MNGSB_FDCS_CRC_SEED_SHIFT)
-#define I40E_MNGSB_FDS 0x000B7048 /* Reset: POR */
-#define I40E_MNGSB_FDS_START_BC_SHIFT 0
-#define I40E_MNGSB_FDS_START_BC_MASK I40E_MASK(0xFFF, I40E_MNGSB_FDS_START_BC_SHIFT)
-#define I40E_MNGSB_FDS_LAST_BC_SHIFT 16
-#define I40E_MNGSB_FDS_LAST_BC_MASK I40E_MASK(0xFFF, I40E_MNGSB_FDS_LAST_BC_SHIFT)
 
-#define I40E_GL_VF_CTRL_RX(_VF) (0x00083600 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_GL_VF_CTRL_RX_MAX_INDEX 127
-#define I40E_GL_VF_CTRL_RX_AQ_RX_EN_SHIFT 0
-#define I40E_GL_VF_CTRL_RX_AQ_RX_EN_MASK I40E_MASK(0x1, I40E_GL_VF_CTRL_RX_AQ_RX_EN_SHIFT)
-#define I40E_GL_VF_CTRL_TX(_VF) (0x00083400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
-#define I40E_GL_VF_CTRL_TX_MAX_INDEX 127
-#define I40E_GL_VF_CTRL_TX_AQ_TX_EN_SHIFT 0
-#define I40E_GL_VF_CTRL_TX_AQ_TX_EN_MASK I40E_MASK(0x1, I40E_GL_VF_CTRL_TX_AQ_TX_EN_SHIFT)
 
-#define I40E_GLCM_LAN_CACHESIZE 0x0010C4D8 /* Reset: CORER */
-#define I40E_GLCM_LAN_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLCM_LAN_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFFF, I40E_GLCM_LAN_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLCM_LAN_CACHESIZE_SETS_SHIFT 12
-#define I40E_GLCM_LAN_CACHESIZE_SETS_MASK I40E_MASK(0xF, I40E_GLCM_LAN_CACHESIZE_SETS_SHIFT)
-#define I40E_GLCM_LAN_CACHESIZE_WAYS_SHIFT 16
-#define I40E_GLCM_LAN_CACHESIZE_WAYS_MASK I40E_MASK(0x3FF, I40E_GLCM_LAN_CACHESIZE_WAYS_SHIFT)
-#define I40E_GLCM_PE_CACHESIZE 0x00138FE4 /* Reset: CORER */
-#define I40E_GLCM_PE_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLCM_PE_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFFF, I40E_GLCM_PE_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLCM_PE_CACHESIZE_SETS_SHIFT 12
-#define I40E_GLCM_PE_CACHESIZE_SETS_MASK I40E_MASK(0xF, I40E_GLCM_PE_CACHESIZE_SETS_SHIFT)
-#define I40E_GLCM_PE_CACHESIZE_WAYS_SHIFT 16
-#define I40E_GLCM_PE_CACHESIZE_WAYS_MASK I40E_MASK(0x1FF, I40E_GLCM_PE_CACHESIZE_WAYS_SHIFT)
-#define I40E_PFCM_PE_ERRDATA 0x00138D00 /* Reset: PFR */
-#define I40E_PFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0
-#define I40E_PFCM_PE_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_PFCM_PE_ERRDATA_ERROR_CODE_SHIFT)
-#define I40E_PFCM_PE_ERRDATA_Q_TYPE_SHIFT 4
-#define I40E_PFCM_PE_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_PFCM_PE_ERRDATA_Q_TYPE_SHIFT)
-#define I40E_PFCM_PE_ERRDATA_Q_NUM_SHIFT 8
-#define I40E_PFCM_PE_ERRDATA_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_PFCM_PE_ERRDATA_Q_NUM_SHIFT)
-#define I40E_PFCM_PE_ERRINFO 0x00138C80 /* Reset: PFR */
-#define I40E_PFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0
-#define I40E_PFCM_PE_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_PFCM_PE_ERRINFO_ERROR_VALID_SHIFT)
-#define I40E_PFCM_PE_ERRINFO_ERROR_INST_SHIFT 4
-#define I40E_PFCM_PE_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_PFCM_PE_ERRINFO_ERROR_INST_SHIFT)
-#define I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8
-#define I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT)
-#define I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16
-#define I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT)
-#define I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24
-#define I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT)
 
-#define I40E_PRTDCB_TFMSTC(_i) (0x000A0040 + ((_i) * 32)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PRTDCB_TFMSTC_MAX_INDEX 7
-#define I40E_PRTDCB_TFMSTC_MSTC_SHIFT 0
-#define I40E_PRTDCB_TFMSTC_MSTC_MASK I40E_MASK(0xFFFFF, I40E_PRTDCB_TFMSTC_MSTC_SHIFT)
-#define I40E_GL_FWSTS_FWROWD_SHIFT 8
-#define I40E_GL_FWSTS_FWROWD_MASK I40E_MASK(0x1, I40E_GL_FWSTS_FWROWD_SHIFT)
-#define I40E_GLFOC_CACHESIZE 0x000AA0DC /* Reset: CORER */
-#define I40E_GLFOC_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLFOC_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFF, I40E_GLFOC_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLFOC_CACHESIZE_SETS_SHIFT 8
-#define I40E_GLFOC_CACHESIZE_SETS_MASK I40E_MASK(0xFFF, I40E_GLFOC_CACHESIZE_SETS_SHIFT)
-#define I40E_GLFOC_CACHESIZE_WAYS_SHIFT 20
-#define I40E_GLFOC_CACHESIZE_WAYS_MASK I40E_MASK(0xF, I40E_GLFOC_CACHESIZE_WAYS_SHIFT)
-#define I40E_GLHMC_APBVTINUSEBASE(_i) (0x000C4a00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_APBVTINUSEBASE_MAX_INDEX 15
-#define I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT 0
-#define I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT)
-#define I40E_GLHMC_CEQPART(_i) (0x001312C0 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_CEQPART_MAX_INDEX 15
-#define I40E_GLHMC_CEQPART_PMCEQBASE_SHIFT 0
-#define I40E_GLHMC_CEQPART_PMCEQBASE_MASK I40E_MASK(0xFF, I40E_GLHMC_CEQPART_PMCEQBASE_SHIFT)
-#define I40E_GLHMC_CEQPART_PMCEQSIZE_SHIFT 16
-#define I40E_GLHMC_CEQPART_PMCEQSIZE_MASK I40E_MASK(0x1FF, I40E_GLHMC_CEQPART_PMCEQSIZE_SHIFT)
-#define I40E_GLHMC_DBCQMAX 0x000C20F0 /* Reset: CORER */
-#define I40E_GLHMC_DBCQMAX_GLHMC_DBCQMAX_SHIFT 0
-#define I40E_GLHMC_DBCQMAX_GLHMC_DBCQMAX_MASK I40E_MASK(0x3FFFF, I40E_GLHMC_DBCQMAX_GLHMC_DBCQMAX_SHIFT)
-#define I40E_GLHMC_DBCQPART(_i) (0x00131240 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_DBCQPART_MAX_INDEX 15
-#define I40E_GLHMC_DBCQPART_PMDBCQBASE_SHIFT 0
-#define I40E_GLHMC_DBCQPART_PMDBCQBASE_MASK I40E_MASK(0x3FFF, I40E_GLHMC_DBCQPART_PMDBCQBASE_SHIFT)
-#define I40E_GLHMC_DBCQPART_PMDBCQSIZE_SHIFT 16
-#define I40E_GLHMC_DBCQPART_PMDBCQSIZE_MASK I40E_MASK(0x7FFF, I40E_GLHMC_DBCQPART_PMDBCQSIZE_SHIFT)
-#define I40E_GLHMC_DBQPMAX 0x000C20EC /* Reset: CORER */
-#define I40E_GLHMC_DBQPMAX_GLHMC_DBQPMAX_SHIFT 0
-#define I40E_GLHMC_DBQPMAX_GLHMC_DBQPMAX_MASK I40E_MASK(0x7FFFF, I40E_GLHMC_DBQPMAX_GLHMC_DBQPMAX_SHIFT)
-#define I40E_GLHMC_DBQPPART(_i) (0x00138D80 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_DBQPPART_MAX_INDEX 15
-#define I40E_GLHMC_DBQPPART_PMDBQPBASE_SHIFT 0
-#define I40E_GLHMC_DBQPPART_PMDBQPBASE_MASK I40E_MASK(0x3FFF, I40E_GLHMC_DBQPPART_PMDBQPBASE_SHIFT)
-#define I40E_GLHMC_DBQPPART_PMDBQPSIZE_SHIFT 16
-#define I40E_GLHMC_DBQPPART_PMDBQPSIZE_MASK I40E_MASK(0x7FFF, I40E_GLHMC_DBQPPART_PMDBQPSIZE_SHIFT)
-#define I40E_GLHMC_PEARPBASE(_i) (0x000C4800 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEARPBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEARPBASE_FPMPEARPBASE_SHIFT 0
-#define I40E_GLHMC_PEARPBASE_FPMPEARPBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEARPBASE_FPMPEARPBASE_SHIFT)
-#define I40E_GLHMC_PEARPCNT(_i) (0x000C4900 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEARPCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEARPCNT_FPMPEARPCNT_SHIFT 0
-#define I40E_GLHMC_PEARPCNT_FPMPEARPCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEARPCNT_FPMPEARPCNT_SHIFT)
-#define I40E_GLHMC_PEARPMAX 0x000C2038 /* Reset: CORER */
-#define I40E_GLHMC_PEARPMAX_PMPEARPMAX_SHIFT 0
-#define I40E_GLHMC_PEARPMAX_PMPEARPMAX_MASK I40E_MASK(0x1FFFF, I40E_GLHMC_PEARPMAX_PMPEARPMAX_SHIFT)
-#define I40E_GLHMC_PEARPOBJSZ 0x000C2034 /* Reset: CORER */
-#define I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_SHIFT 0
-#define I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_MASK I40E_MASK(0x7, I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_SHIFT)
-#define I40E_GLHMC_PECQBASE(_i) (0x000C4200 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PECQBASE_MAX_INDEX 15
-#define I40E_GLHMC_PECQBASE_FPMPECQBASE_SHIFT 0
-#define I40E_GLHMC_PECQBASE_FPMPECQBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PECQBASE_FPMPECQBASE_SHIFT)
-#define I40E_GLHMC_PECQCNT(_i) (0x000C4300 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PECQCNT_MAX_INDEX 15
-#define I40E_GLHMC_PECQCNT_FPMPECQCNT_SHIFT 0
-#define I40E_GLHMC_PECQCNT_FPMPECQCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PECQCNT_FPMPECQCNT_SHIFT)
-#define I40E_GLHMC_PECQOBJSZ 0x000C2020 /* Reset: CORER */
-#define I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_SHIFT 0
-#define I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_SHIFT)
-#define I40E_GLHMC_PEHTCNT(_i) (0x000C4700 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEHTCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEHTCNT_FPMPEHTCNT_SHIFT 0
-#define I40E_GLHMC_PEHTCNT_FPMPEHTCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEHTCNT_FPMPEHTCNT_SHIFT)
-#define I40E_GLHMC_PEHTEBASE(_i) (0x000C4600 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEHTEBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_SHIFT 0
-#define I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_SHIFT)
-#define I40E_GLHMC_PEHTEOBJSZ 0x000C202c /* Reset: CORER */
-#define I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_SHIFT 0
-#define I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_SHIFT)
-#define I40E_GLHMC_PEHTMAX 0x000C2030 /* Reset: CORER */
-#define I40E_GLHMC_PEHTMAX_PMPEHTMAX_SHIFT 0
-#define I40E_GLHMC_PEHTMAX_PMPEHTMAX_MASK I40E_MASK(0x1FFFFF, I40E_GLHMC_PEHTMAX_PMPEHTMAX_SHIFT)
-#define I40E_GLHMC_PEMRBASE(_i) (0x000C4c00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEMRBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEMRBASE_FPMPEMRBASE_SHIFT 0
-#define I40E_GLHMC_PEMRBASE_FPMPEMRBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEMRBASE_FPMPEMRBASE_SHIFT)
-#define I40E_GLHMC_PEMRCNT(_i) (0x000C4d00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEMRCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEMRCNT_FPMPEMRSZ_SHIFT 0
-#define I40E_GLHMC_PEMRCNT_FPMPEMRSZ_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEMRCNT_FPMPEMRSZ_SHIFT)
-#define I40E_GLHMC_PEMRMAX 0x000C2040 /* Reset: CORER */
-#define I40E_GLHMC_PEMRMAX_PMPEMRMAX_SHIFT 0
-#define I40E_GLHMC_PEMRMAX_PMPEMRMAX_MASK I40E_MASK(0x7FFFFF, I40E_GLHMC_PEMRMAX_PMPEMRMAX_SHIFT)
-#define I40E_GLHMC_PEMROBJSZ 0x000C203c /* Reset: CORER */
-#define I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_SHIFT 0
-#define I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_SHIFT)
-#define I40E_GLHMC_PEPBLBASE(_i) (0x000C5800 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEPBLBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_SHIFT 0
-#define I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_SHIFT)
-#define I40E_GLHMC_PEPBLCNT(_i) (0x000C5900 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEPBLCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_SHIFT 0
-#define I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_SHIFT)
-#define I40E_GLHMC_PEPBLMAX 0x000C206c /* Reset: CORER */
-#define I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_SHIFT 0
-#define I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_SHIFT)
-#define I40E_GLHMC_PEPFFIRSTSD 0x000C20E4 /* Reset: CORER */
-#define I40E_GLHMC_PEPFFIRSTSD_GLHMC_PEPFFIRSTSD_SHIFT 0
-#define I40E_GLHMC_PEPFFIRSTSD_GLHMC_PEPFFIRSTSD_MASK I40E_MASK(0xFFF, I40E_GLHMC_PEPFFIRSTSD_GLHMC_PEPFFIRSTSD_SHIFT)
-#define I40E_GLHMC_PEQ1BASE(_i) (0x000C5200 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEQ1BASE_MAX_INDEX 15
-#define I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_SHIFT 0
-#define I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_SHIFT)
-#define I40E_GLHMC_PEQ1CNT(_i) (0x000C5300 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEQ1CNT_MAX_INDEX 15
-#define I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_SHIFT 0
-#define I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_SHIFT)
-#define I40E_GLHMC_PEQ1FLBASE(_i) (0x000C5400 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEQ1FLBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_SHIFT 0
-#define I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_SHIFT)
-#define I40E_GLHMC_PEQ1FLMAX 0x000C2058 /* Reset: CORER */
-#define I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_SHIFT 0
-#define I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_MASK I40E_MASK(0x3FFFFFF, I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_SHIFT)
-#define I40E_GLHMC_PEQ1MAX 0x000C2054 /* Reset: CORER */
-#define I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_SHIFT 0
-#define I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_MASK I40E_MASK(0x3FFFFFF, I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_SHIFT)
-#define I40E_GLHMC_PEQ1OBJSZ 0x000C2050 /* Reset: CORER */
-#define I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_SHIFT 0
-#define I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_SHIFT)
-#define I40E_GLHMC_PEQPBASE(_i) (0x000C4000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEQPBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEQPBASE_FPMPEQPBASE_SHIFT 0
-#define I40E_GLHMC_PEQPBASE_FPMPEQPBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEQPBASE_FPMPEQPBASE_SHIFT)
-#define I40E_GLHMC_PEQPCNT(_i) (0x000C4100 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEQPCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEQPCNT_FPMPEQPCNT_SHIFT 0
-#define I40E_GLHMC_PEQPCNT_FPMPEQPCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEQPCNT_FPMPEQPCNT_SHIFT)
-#define I40E_GLHMC_PEQPOBJSZ 0x000C201c /* Reset: CORER */
-#define I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_SHIFT 0
-#define I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_SHIFT)
-#define I40E_GLHMC_PESRQBASE(_i) (0x000C4400 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PESRQBASE_MAX_INDEX 15
-#define I40E_GLHMC_PESRQBASE_FPMPESRQBASE_SHIFT 0
-#define I40E_GLHMC_PESRQBASE_FPMPESRQBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PESRQBASE_FPMPESRQBASE_SHIFT)
-#define I40E_GLHMC_PESRQCNT(_i) (0x000C4500 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PESRQCNT_MAX_INDEX 15
-#define I40E_GLHMC_PESRQCNT_FPMPESRQCNT_SHIFT 0
-#define I40E_GLHMC_PESRQCNT_FPMPESRQCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PESRQCNT_FPMPESRQCNT_SHIFT)
-#define I40E_GLHMC_PESRQMAX 0x000C2028 /* Reset: CORER */
-#define I40E_GLHMC_PESRQMAX_PMPESRQMAX_SHIFT 0
-#define I40E_GLHMC_PESRQMAX_PMPESRQMAX_MASK I40E_MASK(0xFFFF, I40E_GLHMC_PESRQMAX_PMPESRQMAX_SHIFT)
-#define I40E_GLHMC_PESRQOBJSZ 0x000C2024 /* Reset: CORER */
-#define I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_SHIFT 0
-#define I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_SHIFT)
-#define I40E_GLHMC_PETIMERBASE(_i) (0x000C5A00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PETIMERBASE_MAX_INDEX 15
-#define I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_SHIFT 0
-#define I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_SHIFT)
-#define I40E_GLHMC_PETIMERCNT(_i) (0x000C5B00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PETIMERCNT_MAX_INDEX 15
-#define I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_SHIFT 0
-#define I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_SHIFT)
-#define I40E_GLHMC_PETIMERMAX 0x000C2084 /* Reset: CORER */
-#define I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_SHIFT 0
-#define I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_SHIFT)
-#define I40E_GLHMC_PETIMEROBJSZ 0x000C2080 /* Reset: CORER */
-#define I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_SHIFT 0
-#define I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_SHIFT)
-#define I40E_GLHMC_PEXFBASE(_i) (0x000C4e00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEXFBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEXFBASE_FPMPEXFBASE_SHIFT 0
-#define I40E_GLHMC_PEXFBASE_FPMPEXFBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEXFBASE_FPMPEXFBASE_SHIFT)
-#define I40E_GLHMC_PEXFCNT(_i) (0x000C4f00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEXFCNT_MAX_INDEX 15
-#define I40E_GLHMC_PEXFCNT_FPMPEXFCNT_SHIFT 0
-#define I40E_GLHMC_PEXFCNT_FPMPEXFCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_PEXFCNT_FPMPEXFCNT_SHIFT)
-#define I40E_GLHMC_PEXFFLBASE(_i) (0x000C5000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PEXFFLBASE_MAX_INDEX 15
-#define I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_SHIFT 0
-#define I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_SHIFT)
-#define I40E_GLHMC_PEXFFLMAX 0x000C204c /* Reset: CORER */
-#define I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_SHIFT 0
-#define I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_MASK I40E_MASK(0x1FFFFFF, I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_SHIFT)
-#define I40E_GLHMC_PEXFMAX 0x000C2048 /* Reset: CORER */
-#define I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT 0
-#define I40E_GLHMC_PEXFMAX_PMPEXFMAX_MASK I40E_MASK(0x3FFFFFF, I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT)
-#define I40E_GLHMC_PEXFOBJSZ 0x000C2044 /* Reset: CORER */
-#define I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_SHIFT 0
-#define I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_MASK I40E_MASK(0xF, I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_SHIFT)
-#define I40E_GLHMC_PFPESDPART(_i) (0x000C0880 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLHMC_PFPESDPART_MAX_INDEX 15
-#define I40E_GLHMC_PFPESDPART_PMSDBASE_SHIFT 0
-#define I40E_GLHMC_PFPESDPART_PMSDBASE_MASK I40E_MASK(0xFFF, I40E_GLHMC_PFPESDPART_PMSDBASE_SHIFT)
-#define I40E_GLHMC_PFPESDPART_PMSDSIZE_SHIFT 16
-#define I40E_GLHMC_PFPESDPART_PMSDSIZE_MASK I40E_MASK(0x1FFF, I40E_GLHMC_PFPESDPART_PMSDSIZE_SHIFT)
-#define I40E_GLHMC_VFAPBVTINUSEBASE(_i) (0x000Cca00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFAPBVTINUSEBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT 0
-#define I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT)
-#define I40E_GLHMC_VFCEQPART(_i) (0x00132240 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFCEQPART_MAX_INDEX 31
-#define I40E_GLHMC_VFCEQPART_PMCEQBASE_SHIFT 0
-#define I40E_GLHMC_VFCEQPART_PMCEQBASE_MASK I40E_MASK(0xFF, I40E_GLHMC_VFCEQPART_PMCEQBASE_SHIFT)
-#define I40E_GLHMC_VFCEQPART_PMCEQSIZE_SHIFT 16
-#define I40E_GLHMC_VFCEQPART_PMCEQSIZE_MASK I40E_MASK(0x1FF, I40E_GLHMC_VFCEQPART_PMCEQSIZE_SHIFT)
-#define I40E_GLHMC_VFDBCQPART(_i) (0x00132140 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFDBCQPART_MAX_INDEX 31
-#define I40E_GLHMC_VFDBCQPART_PMDBCQBASE_SHIFT 0
-#define I40E_GLHMC_VFDBCQPART_PMDBCQBASE_MASK I40E_MASK(0x3FFF, I40E_GLHMC_VFDBCQPART_PMDBCQBASE_SHIFT)
-#define I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_SHIFT 16
-#define I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_MASK I40E_MASK(0x7FFF, I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_SHIFT)
-#define I40E_GLHMC_VFDBQPPART(_i) (0x00138E00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFDBQPPART_MAX_INDEX 31
-#define I40E_GLHMC_VFDBQPPART_PMDBQPBASE_SHIFT 0
-#define I40E_GLHMC_VFDBQPPART_PMDBQPBASE_MASK I40E_MASK(0x3FFF, I40E_GLHMC_VFDBQPPART_PMDBQPBASE_SHIFT)
-#define I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_SHIFT 16
-#define I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_MASK I40E_MASK(0x7FFF, I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_SHIFT)
-#define I40E_GLHMC_VFFSIAVBASE(_i) (0x000Cd600 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFFSIAVBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_SHIFT 0
-#define I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_SHIFT)
-#define I40E_GLHMC_VFFSIAVCNT(_i) (0x000Cd700 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFFSIAVCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_SHIFT 0
-#define I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_SHIFT)
-#define I40E_GLHMC_VFPDINV(_i) (0x000C8300 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPDINV_MAX_INDEX 31
-#define I40E_GLHMC_VFPDINV_PMSDIDX_SHIFT 0
-#define I40E_GLHMC_VFPDINV_PMSDIDX_MASK I40E_MASK(0xFFF, I40E_GLHMC_VFPDINV_PMSDIDX_SHIFT)
-#define I40E_GLHMC_VFPDINV_PMSDPARTSEL_SHIFT 15
-#define I40E_GLHMC_VFPDINV_PMSDPARTSEL_MASK I40E_MASK(0x1, I40E_GLHMC_VFPDINV_PMSDPARTSEL_SHIFT)
-#define I40E_GLHMC_VFPDINV_PMPDIDX_SHIFT 16
-#define I40E_GLHMC_VFPDINV_PMPDIDX_MASK I40E_MASK(0x1FF, I40E_GLHMC_VFPDINV_PMPDIDX_SHIFT)
-#define I40E_GLHMC_VFPEARPBASE(_i) (0x000Cc800 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEARPBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_SHIFT 0
-#define I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_SHIFT)
-#define I40E_GLHMC_VFPEARPCNT(_i) (0x000Cc900 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEARPCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_SHIFT 0
-#define I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_SHIFT)
-#define I40E_GLHMC_VFPECQBASE(_i) (0x000Cc200 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPECQBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPECQBASE_FPMPECQBASE_SHIFT 0
-#define I40E_GLHMC_VFPECQBASE_FPMPECQBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPECQBASE_FPMPECQBASE_SHIFT)
-#define I40E_GLHMC_VFPECQCNT(_i) (0x000Cc300 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPECQCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPECQCNT_FPMPECQCNT_SHIFT 0
-#define I40E_GLHMC_VFPECQCNT_FPMPECQCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPECQCNT_FPMPECQCNT_SHIFT)
-#define I40E_GLHMC_VFPEHTCNT(_i) (0x000Cc700 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEHTCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_SHIFT 0
-#define I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_SHIFT)
-#define I40E_GLHMC_VFPEHTEBASE(_i) (0x000Cc600 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEHTEBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_SHIFT 0
-#define I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_SHIFT)
-#define I40E_GLHMC_VFPEMRBASE(_i) (0x000Ccc00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEMRBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_SHIFT 0
-#define I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_SHIFT)
-#define I40E_GLHMC_VFPEMRCNT(_i) (0x000Ccd00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEMRCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_SHIFT 0
-#define I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_SHIFT)
-#define I40E_GLHMC_VFPEPBLBASE(_i) (0x000Cd800 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEPBLBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_SHIFT 0
-#define I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_SHIFT)
-#define I40E_GLHMC_VFPEPBLCNT(_i) (0x000Cd900 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEPBLCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_SHIFT 0
-#define I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_SHIFT)
-#define I40E_GLHMC_VFPEQ1BASE(_i) (0x000Cd200 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEQ1BASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_SHIFT 0
-#define I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_SHIFT)
-#define I40E_GLHMC_VFPEQ1CNT(_i) (0x000Cd300 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEQ1CNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_SHIFT 0
-#define I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_SHIFT)
-#define I40E_GLHMC_VFPEQ1FLBASE(_i) (0x000Cd400 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEQ1FLBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_SHIFT 0
-#define I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_SHIFT)
-#define I40E_GLHMC_VFPEQPBASE(_i) (0x000Cc000 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEQPBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_SHIFT 0
-#define I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_SHIFT)
-#define I40E_GLHMC_VFPEQPCNT(_i) (0x000Cc100 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEQPCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_SHIFT 0
-#define I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_SHIFT)
-#define I40E_GLHMC_VFPESRQBASE(_i) (0x000Cc400 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPESRQBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_SHIFT 0
-#define I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_SHIFT)
-#define I40E_GLHMC_VFPESRQCNT(_i) (0x000Cc500 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPESRQCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_SHIFT 0
-#define I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_SHIFT)
-#define I40E_GLHMC_VFPETIMERBASE(_i) (0x000CDA00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPETIMERBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_SHIFT 0
-#define I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_SHIFT)
-#define I40E_GLHMC_VFPETIMERCNT(_i) (0x000CDB00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPETIMERCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_SHIFT 0
-#define I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_SHIFT)
-#define I40E_GLHMC_VFPEXFBASE(_i) (0x000Cce00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEXFBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_SHIFT 0
-#define I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_SHIFT)
-#define I40E_GLHMC_VFPEXFCNT(_i) (0x000Ccf00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEXFCNT_MAX_INDEX 31
-#define I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_SHIFT 0
-#define I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_MASK I40E_MASK(0x1FFFFFFF, I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_SHIFT)
-#define I40E_GLHMC_VFPEXFFLBASE(_i) (0x000Cd000 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFPEXFFLBASE_MAX_INDEX 31
-#define I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_SHIFT 0
-#define I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_MASK I40E_MASK(0xFFFFFF, I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_SHIFT)
-#define I40E_GLHMC_VFSDPART(_i) (0x000C8800 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLHMC_VFSDPART_MAX_INDEX 31
-#define I40E_GLHMC_VFSDPART_PMSDBASE_SHIFT 0
-#define I40E_GLHMC_VFSDPART_PMSDBASE_MASK I40E_MASK(0xFFF, I40E_GLHMC_VFSDPART_PMSDBASE_SHIFT)
-#define I40E_GLHMC_VFSDPART_PMSDSIZE_SHIFT 16
-#define I40E_GLHMC_VFSDPART_PMSDSIZE_MASK I40E_MASK(0x1FFF, I40E_GLHMC_VFSDPART_PMSDSIZE_SHIFT)
-#define I40E_GLPBLOC_CACHESIZE 0x000A80BC /* Reset: CORER */
-#define I40E_GLPBLOC_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLPBLOC_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFF, I40E_GLPBLOC_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLPBLOC_CACHESIZE_SETS_SHIFT 8
-#define I40E_GLPBLOC_CACHESIZE_SETS_MASK I40E_MASK(0xFFF, I40E_GLPBLOC_CACHESIZE_SETS_SHIFT)
-#define I40E_GLPBLOC_CACHESIZE_WAYS_SHIFT 20
-#define I40E_GLPBLOC_CACHESIZE_WAYS_MASK I40E_MASK(0xF, I40E_GLPBLOC_CACHESIZE_WAYS_SHIFT)
-#define I40E_GLPDOC_CACHESIZE 0x000D0088 /* Reset: CORER */
-#define I40E_GLPDOC_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLPDOC_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFF, I40E_GLPDOC_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLPDOC_CACHESIZE_SETS_SHIFT 8
-#define I40E_GLPDOC_CACHESIZE_SETS_MASK I40E_MASK(0xFFF, I40E_GLPDOC_CACHESIZE_SETS_SHIFT)
-#define I40E_GLPDOC_CACHESIZE_WAYS_SHIFT 20
-#define I40E_GLPDOC_CACHESIZE_WAYS_MASK I40E_MASK(0xF, I40E_GLPDOC_CACHESIZE_WAYS_SHIFT)
-#define I40E_GLPEOC_CACHESIZE 0x000A60E8 /* Reset: CORER */
-#define I40E_GLPEOC_CACHESIZE_WORD_SIZE_SHIFT 0
-#define I40E_GLPEOC_CACHESIZE_WORD_SIZE_MASK I40E_MASK(0xFF, I40E_GLPEOC_CACHESIZE_WORD_SIZE_SHIFT)
-#define I40E_GLPEOC_CACHESIZE_SETS_SHIFT 8
-#define I40E_GLPEOC_CACHESIZE_SETS_MASK I40E_MASK(0xFFF, I40E_GLPEOC_CACHESIZE_SETS_SHIFT)
-#define I40E_GLPEOC_CACHESIZE_WAYS_SHIFT 20
-#define I40E_GLPEOC_CACHESIZE_WAYS_MASK I40E_MASK(0xF, I40E_GLPEOC_CACHESIZE_WAYS_SHIFT)
-#define I40E_PFHMC_PDINV_PMSDPARTSEL_SHIFT 15
-#define I40E_PFHMC_PDINV_PMSDPARTSEL_MASK I40E_MASK(0x1, I40E_PFHMC_PDINV_PMSDPARTSEL_SHIFT)
-#define I40E_PFHMC_SDCMD_PMSDPARTSEL_SHIFT 15
-#define I40E_PFHMC_SDCMD_PMSDPARTSEL_MASK I40E_MASK(0x1, I40E_PFHMC_SDCMD_PMSDPARTSEL_SHIFT)
-#define I40E_GL_PPRS_SPARE 0x000856E0 /* Reset: CORER */
-#define I40E_GL_PPRS_SPARE_GL_PPRS_SPARE_SHIFT 0
-#define I40E_GL_PPRS_SPARE_GL_PPRS_SPARE_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_PPRS_SPARE_GL_PPRS_SPARE_SHIFT)
-#define I40E_GL_TLAN_SPARE 0x000E64E0 /* Reset: CORER */
-#define I40E_GL_TLAN_SPARE_GL_TLAN_SPARE_SHIFT 0
-#define I40E_GL_TLAN_SPARE_GL_TLAN_SPARE_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_TLAN_SPARE_GL_TLAN_SPARE_SHIFT)
-#define I40E_GL_TUPM_SPARE 0x000a2230 /* Reset: CORER */
-#define I40E_GL_TUPM_SPARE_GL_TUPM_SPARE_SHIFT 0
-#define I40E_GL_TUPM_SPARE_GL_TUPM_SPARE_MASK I40E_MASK(0xFFFFFFFF, I40E_GL_TUPM_SPARE_GL_TUPM_SPARE_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG 0x000B81C0 /* Reset: POR */
-#define I40E_GLGEN_CAR_DEBUG_CAR_UPPER_CORE_CLK_EN_SHIFT 0
-#define I40E_GLGEN_CAR_DEBUG_CAR_UPPER_CORE_CLK_EN_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_UPPER_CORE_CLK_EN_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_HIU_CLK_EN_SHIFT 1
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_HIU_CLK_EN_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_HIU_CLK_EN_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PE_CLK_EN_SHIFT 2
-#define I40E_GLGEN_CAR_DEBUG_CAR_PE_CLK_EN_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PE_CLK_EN_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_PRIM_CLK_ACTIVE_SHIFT 3
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_PRIM_CLK_ACTIVE_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_PRIM_CLK_ACTIVE_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CDC_PE_ACTIVE_SHIFT 4
-#define I40E_GLGEN_CAR_DEBUG_CDC_PE_ACTIVE_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CDC_PE_ACTIVE_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_PRST_RESET_N_SHIFT 5
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_PRST_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_PRST_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_SCLR_RESET_N_SHIFT 6
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_SCLR_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_SCLR_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IB_RESET_N_SHIFT 7
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IB_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IB_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IMIB_RESET_N_SHIFT 8
-#define I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IMIB_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_PCIE_RAW_IMIB_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_EMP_RESET_N_SHIFT 9
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_EMP_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_RAW_EMP_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_GLOBAL_RESET_N_SHIFT 10
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_GLOBAL_RESET_N_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_RAW_GLOBAL_RESET_N_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_LAN_POWER_GOOD_SHIFT 11
-#define I40E_GLGEN_CAR_DEBUG_CAR_RAW_LAN_POWER_GOOD_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CAR_RAW_LAN_POWER_GOOD_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_CDC_IOSF_PRIMERY_RST_B_SHIFT 12
-#define I40E_GLGEN_CAR_DEBUG_CDC_IOSF_PRIMERY_RST_B_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_CDC_IOSF_PRIMERY_RST_B_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_GBE_GLOBALRST_B_SHIFT 13
-#define I40E_GLGEN_CAR_DEBUG_GBE_GLOBALRST_B_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_GBE_GLOBALRST_B_SHIFT)
-#define I40E_GLGEN_CAR_DEBUG_FLEEP_AL_GLOBR_DONE_SHIFT 14
-#define I40E_GLGEN_CAR_DEBUG_FLEEP_AL_GLOBR_DONE_MASK I40E_MASK(0x1, I40E_GLGEN_CAR_DEBUG_FLEEP_AL_GLOBR_DONE_SHIFT)
-#define I40E_GLGEN_MISC_SPARE 0x000880E0 /* Reset: POR */
-#define I40E_GLGEN_MISC_SPARE_GLGEN_MISC_SPARE_SHIFT 0
-#define I40E_GLGEN_MISC_SPARE_GLGEN_MISC_SPARE_MASK I40E_MASK(0xFFFFFFFF, I40E_GLGEN_MISC_SPARE_GLGEN_MISC_SPARE_SHIFT)
-#define I40E_GL_UFUSE_SOC 0x000BE550 /* Reset: POR */
-#define I40E_GL_UFUSE_SOC_PORT_MODE_SHIFT 0
-#define I40E_GL_UFUSE_SOC_PORT_MODE_MASK I40E_MASK(0x3, I40E_GL_UFUSE_SOC_PORT_MODE_SHIFT)
-#define I40E_GL_UFUSE_SOC_NIC_ID_SHIFT 2
-#define I40E_GL_UFUSE_SOC_NIC_ID_MASK I40E_MASK(0x1, I40E_GL_UFUSE_SOC_NIC_ID_SHIFT)
-#define I40E_GL_UFUSE_SOC_SPARE_FUSES_SHIFT 3
-#define I40E_GL_UFUSE_SOC_SPARE_FUSES_MASK I40E_MASK(0x1FFF, I40E_GL_UFUSE_SOC_SPARE_FUSES_SHIFT)
 #define I40E_PFINT_DYN_CTL0_WB_ON_ITR_SHIFT 30
 #define I40E_PFINT_DYN_CTL0_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTL0_WB_ON_ITR_SHIFT)
 #define I40E_PFINT_DYN_CTLN_WB_ON_ITR_SHIFT 30
 #define I40E_PFINT_DYN_CTLN_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_WB_ON_ITR_SHIFT)
-#define I40E_VFINT_DYN_CTL0_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTL0_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL0_WB_ON_ITR_SHIFT)
-#define I40E_VFINT_DYN_CTLN_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTLN_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_WB_ON_ITR_SHIFT)
-#define I40E_VPLAN_QBASE(_VF) (0x00074800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VPLAN_QBASE_MAX_INDEX 127
-#define I40E_VPLAN_QBASE_VFFIRSTQ_SHIFT 0
-#define I40E_VPLAN_QBASE_VFFIRSTQ_MASK I40E_MASK(0x7FF, I40E_VPLAN_QBASE_VFFIRSTQ_SHIFT)
-#define I40E_VPLAN_QBASE_VFNUMQ_SHIFT 11
-#define I40E_VPLAN_QBASE_VFNUMQ_MASK I40E_MASK(0xFF, I40E_VPLAN_QBASE_VFNUMQ_SHIFT)
-#define I40E_VPLAN_QBASE_VFQTABLE_ENA_SHIFT 31
-#define I40E_VPLAN_QBASE_VFQTABLE_ENA_MASK I40E_MASK(0x1, I40E_VPLAN_QBASE_VFQTABLE_ENA_SHIFT)
-#define I40E_PRTMAC_LINK_DOWN_COUNTER 0x001E2440 /* Reset: GLOBR */
-#define I40E_PRTMAC_LINK_DOWN_COUNTER_LINK_DOWN_COUNTER_SHIFT 0
-#define I40E_PRTMAC_LINK_DOWN_COUNTER_LINK_DOWN_COUNTER_MASK I40E_MASK(0xFFFF, I40E_PRTMAC_LINK_DOWN_COUNTER_LINK_DOWN_COUNTER_SHIFT)
-#define I40E_GLNVM_AL_REQ 0x000B6164 /* Reset: POR */
-#define I40E_GLNVM_AL_REQ_POR_SHIFT 0
-#define I40E_GLNVM_AL_REQ_POR_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_POR_SHIFT)
-#define I40E_GLNVM_AL_REQ_PCIE_IMIB_SHIFT 1
-#define I40E_GLNVM_AL_REQ_PCIE_IMIB_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_PCIE_IMIB_SHIFT)
-#define I40E_GLNVM_AL_REQ_GLOBR_SHIFT 2
-#define I40E_GLNVM_AL_REQ_GLOBR_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_GLOBR_SHIFT)
-#define I40E_GLNVM_AL_REQ_CORER_SHIFT 3
-#define I40E_GLNVM_AL_REQ_CORER_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_CORER_SHIFT)
-#define I40E_GLNVM_AL_REQ_PE_SHIFT 4
-#define I40E_GLNVM_AL_REQ_PE_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_PE_SHIFT)
-#define I40E_GLNVM_AL_REQ_PCIE_IMIB_ASSERT_SHIFT 5
-#define I40E_GLNVM_AL_REQ_PCIE_IMIB_ASSERT_MASK I40E_MASK(0x1, I40E_GLNVM_AL_REQ_PCIE_IMIB_ASSERT_SHIFT)
-#define I40E_GLNVM_ALTIMERS 0x000B6140 /* Reset: POR */
-#define I40E_GLNVM_ALTIMERS_PCI_ALTIMER_SHIFT 0
-#define I40E_GLNVM_ALTIMERS_PCI_ALTIMER_MASK I40E_MASK(0xFFF, I40E_GLNVM_ALTIMERS_PCI_ALTIMER_SHIFT)
-#define I40E_GLNVM_ALTIMERS_GEN_ALTIMER_SHIFT 12
-#define I40E_GLNVM_ALTIMERS_GEN_ALTIMER_MASK I40E_MASK(0xFFFFF, I40E_GLNVM_ALTIMERS_GEN_ALTIMER_SHIFT)
 #define I40E_GLNVM_FLA 0x000B6108 /* Reset: POR */
 #define I40E_GLNVM_FLA_LOCKED_SHIFT 6
 #define I40E_GLNVM_FLA_LOCKED_MASK I40E_MASK(0x1, I40E_GLNVM_FLA_LOCKED_SHIFT)
 
 #define I40E_GLNVM_ULD 0x000B6008 /* Reset: POR */
-#define I40E_GLNVM_ULD_PCIER_DONE_SHIFT 0
-#define I40E_GLNVM_ULD_PCIER_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_PCIER_DONE_SHIFT)
-#define I40E_GLNVM_ULD_PCIER_DONE_1_SHIFT 1
-#define I40E_GLNVM_ULD_PCIER_DONE_1_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_PCIER_DONE_1_SHIFT)
-#define I40E_GLNVM_ULD_CORER_DONE_SHIFT 3
-#define I40E_GLNVM_ULD_CORER_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_CORER_DONE_SHIFT)
-#define I40E_GLNVM_ULD_GLOBR_DONE_SHIFT 4
-#define I40E_GLNVM_ULD_GLOBR_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_GLOBR_DONE_SHIFT)
-#define I40E_GLNVM_ULD_POR_DONE_SHIFT 5
-#define I40E_GLNVM_ULD_POR_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_POR_DONE_SHIFT)
-#define I40E_GLNVM_ULD_POR_DONE_1_SHIFT 8
-#define I40E_GLNVM_ULD_POR_DONE_1_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_POR_DONE_1_SHIFT)
-#define I40E_GLNVM_ULD_PCIER_DONE_2_SHIFT 9
-#define I40E_GLNVM_ULD_PCIER_DONE_2_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_PCIER_DONE_2_SHIFT)
-#define I40E_GLNVM_ULD_PE_DONE_SHIFT 10
-#define I40E_GLNVM_ULD_PE_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_ULD_PE_DONE_SHIFT)
-#define I40E_GLNVM_ULT 0x000B6154 /* Reset: POR */
-#define I40E_GLNVM_ULT_CONF_PCIR_AE_SHIFT 0
-#define I40E_GLNVM_ULT_CONF_PCIR_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_PCIR_AE_SHIFT)
-#define I40E_GLNVM_ULT_CONF_PCIRTL_AE_SHIFT 1
-#define I40E_GLNVM_ULT_CONF_PCIRTL_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_PCIRTL_AE_SHIFT)
-#define I40E_GLNVM_ULT_RESERVED_1_SHIFT 2
-#define I40E_GLNVM_ULT_RESERVED_1_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_RESERVED_1_SHIFT)
-#define I40E_GLNVM_ULT_CONF_CORE_AE_SHIFT 3
-#define I40E_GLNVM_ULT_CONF_CORE_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_CORE_AE_SHIFT)
-#define I40E_GLNVM_ULT_CONF_GLOBAL_AE_SHIFT 4
-#define I40E_GLNVM_ULT_CONF_GLOBAL_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_GLOBAL_AE_SHIFT)
-#define I40E_GLNVM_ULT_CONF_POR_AE_SHIFT 5
-#define I40E_GLNVM_ULT_CONF_POR_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_POR_AE_SHIFT)
-#define I40E_GLNVM_ULT_RESERVED_2_SHIFT 6
-#define I40E_GLNVM_ULT_RESERVED_2_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_RESERVED_2_SHIFT)
-#define I40E_GLNVM_ULT_RESERVED_3_SHIFT 7
-#define I40E_GLNVM_ULT_RESERVED_3_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_RESERVED_3_SHIFT)
-#define I40E_GLNVM_ULT_CONF_EMP_AE_SHIFT 8
-#define I40E_GLNVM_ULT_CONF_EMP_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_EMP_AE_SHIFT)
-#define I40E_GLNVM_ULT_CONF_PCIALT_AE_SHIFT 9
-#define I40E_GLNVM_ULT_CONF_PCIALT_AE_MASK I40E_MASK(0x1, I40E_GLNVM_ULT_CONF_PCIALT_AE_SHIFT)
-#define I40E_GLNVM_ULT_RESERVED_4_SHIFT 10
-#define I40E_GLNVM_ULT_RESERVED_4_MASK I40E_MASK(0x3FFFFF, I40E_GLNVM_ULT_RESERVED_4_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT 0x000B615C /* Reset: POR */
-#define I40E_MEM_INIT_DONE_STAT_CMLAN_MEM_INIT_DONE_SHIFT 0
-#define I40E_MEM_INIT_DONE_STAT_CMLAN_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_CMLAN_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_PMAT_MEM_INIT_DONE_SHIFT 1
-#define I40E_MEM_INIT_DONE_STAT_PMAT_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_PMAT_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_RCU_MEM_INIT_DONE_SHIFT 2
-#define I40E_MEM_INIT_DONE_STAT_RCU_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_RCU_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_TDPU_MEM_INIT_DONE_SHIFT 3
-#define I40E_MEM_INIT_DONE_STAT_TDPU_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_TDPU_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_TLAN_MEM_INIT_DONE_SHIFT 4
-#define I40E_MEM_INIT_DONE_STAT_TLAN_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_TLAN_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_RLAN_MEM_INIT_DONE_SHIFT 5
-#define I40E_MEM_INIT_DONE_STAT_RLAN_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_RLAN_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_RDPU_MEM_INIT_DONE_SHIFT 6
-#define I40E_MEM_INIT_DONE_STAT_RDPU_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_RDPU_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_PPRS_MEM_INIT_DONE_SHIFT 7
-#define I40E_MEM_INIT_DONE_STAT_PPRS_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_PPRS_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_RPB_MEM_INIT_DONE_SHIFT 8
-#define I40E_MEM_INIT_DONE_STAT_RPB_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_RPB_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_TPB_MEM_INIT_DONE_SHIFT 9
-#define I40E_MEM_INIT_DONE_STAT_TPB_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_TPB_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_FOC_MEM_INIT_DONE_SHIFT 10
-#define I40E_MEM_INIT_DONE_STAT_FOC_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_FOC_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_TSCD_MEM_INIT_DONE_SHIFT 11
-#define I40E_MEM_INIT_DONE_STAT_TSCD_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_TSCD_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_TCB_MEM_INIT_DONE_SHIFT 12
-#define I40E_MEM_INIT_DONE_STAT_TCB_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_TCB_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_RCB_MEM_INIT_DONE_SHIFT 13
-#define I40E_MEM_INIT_DONE_STAT_RCB_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_RCB_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_WUC_MEM_INIT_DONE_SHIFT 14
-#define I40E_MEM_INIT_DONE_STAT_WUC_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_WUC_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_STAT_MEM_INIT_DONE_SHIFT 15
-#define I40E_MEM_INIT_DONE_STAT_STAT_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_STAT_MEM_INIT_DONE_SHIFT)
-#define I40E_MEM_INIT_DONE_STAT_ITR_MEM_INIT_DONE_SHIFT 16
-#define I40E_MEM_INIT_DONE_STAT_ITR_MEM_INIT_DONE_MASK I40E_MASK(0x1, I40E_MEM_INIT_DONE_STAT_ITR_MEM_INIT_DONE_SHIFT)
-#define I40E_MNGSB_DADD 0x000B7030 /* Reset: POR */
-#define I40E_MNGSB_DADD_ADDR_SHIFT 0
-#define I40E_MNGSB_DADD_ADDR_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_DADD_ADDR_SHIFT)
-#define I40E_MNGSB_DCNT 0x000B7034 /* Reset: POR */
-#define I40E_MNGSB_DCNT_BYTE_CNT_SHIFT 0
-#define I40E_MNGSB_DCNT_BYTE_CNT_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_DCNT_BYTE_CNT_SHIFT)
-#define I40E_MNGSB_MSGCTL 0x000B7020 /* Reset: POR */
-#define I40E_MNGSB_MSGCTL_HDR_DWS_SHIFT 0
-#define I40E_MNGSB_MSGCTL_HDR_DWS_MASK I40E_MASK(0x3, I40E_MNGSB_MSGCTL_HDR_DWS_SHIFT)
-#define I40E_MNGSB_MSGCTL_EXP_RDW_SHIFT 8
-#define I40E_MNGSB_MSGCTL_EXP_RDW_MASK I40E_MASK(0x1FF, I40E_MNGSB_MSGCTL_EXP_RDW_SHIFT)
-#define I40E_MNGSB_MSGCTL_MSG_MODE_SHIFT 26
-#define I40E_MNGSB_MSGCTL_MSG_MODE_MASK I40E_MASK(0x3, I40E_MNGSB_MSGCTL_MSG_MODE_SHIFT)
-#define I40E_MNGSB_MSGCTL_TOKEN_MODE_SHIFT 28
-#define I40E_MNGSB_MSGCTL_TOKEN_MODE_MASK I40E_MASK(0x3, I40E_MNGSB_MSGCTL_TOKEN_MODE_SHIFT)
-#define I40E_MNGSB_MSGCTL_BARCLR_SHIFT 30
-#define I40E_MNGSB_MSGCTL_BARCLR_MASK I40E_MASK(0x1, I40E_MNGSB_MSGCTL_BARCLR_SHIFT)
-#define I40E_MNGSB_MSGCTL_CMDV_SHIFT 31
-#define I40E_MNGSB_MSGCTL_CMDV_MASK I40E_MASK(0x1, I40E_MNGSB_MSGCTL_CMDV_SHIFT)
-#define I40E_MNGSB_RDATA 0x000B7300 /* Reset: POR */
-#define I40E_MNGSB_RDATA_DATA_SHIFT 0
-#define I40E_MNGSB_RDATA_DATA_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_RDATA_DATA_SHIFT)
-#define I40E_MNGSB_RHDR0 0x000B72FC /* Reset: POR */
-#define I40E_MNGSB_RHDR0_DESTINATION_SHIFT 0
-#define I40E_MNGSB_RHDR0_DESTINATION_MASK I40E_MASK(0xFF, I40E_MNGSB_RHDR0_DESTINATION_SHIFT)
-#define I40E_MNGSB_RHDR0_SOURCE_SHIFT 8
-#define I40E_MNGSB_RHDR0_SOURCE_MASK I40E_MASK(0xFF, I40E_MNGSB_RHDR0_SOURCE_SHIFT)
-#define I40E_MNGSB_RHDR0_OPCODE_SHIFT 16
-#define I40E_MNGSB_RHDR0_OPCODE_MASK I40E_MASK(0xFF, I40E_MNGSB_RHDR0_OPCODE_SHIFT)
-#define I40E_MNGSB_RHDR0_TAG_SHIFT 24
-#define I40E_MNGSB_RHDR0_TAG_MASK I40E_MASK(0x7, I40E_MNGSB_RHDR0_TAG_SHIFT)
-#define I40E_MNGSB_RHDR0_RESPONSE_SHIFT 27
-#define I40E_MNGSB_RHDR0_RESPONSE_MASK I40E_MASK(0x7, I40E_MNGSB_RHDR0_RESPONSE_SHIFT)
-#define I40E_MNGSB_RHDR0_EH_SHIFT 31
-#define I40E_MNGSB_RHDR0_EH_MASK I40E_MASK(0x1, I40E_MNGSB_RHDR0_EH_SHIFT)
-#define I40E_MNGSB_RSPCTL 0x000B7024 /* Reset: POR */
-#define I40E_MNGSB_RSPCTL_DMA_MSG_DWORDS_SHIFT 0
-#define I40E_MNGSB_RSPCTL_DMA_MSG_DWORDS_MASK I40E_MASK(0x1FF, I40E_MNGSB_RSPCTL_DMA_MSG_DWORDS_SHIFT)
-#define I40E_MNGSB_RSPCTL_RSP_MODE_SHIFT 26
-#define I40E_MNGSB_RSPCTL_RSP_MODE_MASK I40E_MASK(0x3, I40E_MNGSB_RSPCTL_RSP_MODE_SHIFT)
-#define I40E_MNGSB_RSPCTL_RSP_BAD_LEN_SHIFT 30
-#define I40E_MNGSB_RSPCTL_RSP_BAD_LEN_MASK I40E_MASK(0x1, I40E_MNGSB_RSPCTL_RSP_BAD_LEN_SHIFT)
-#define I40E_MNGSB_RSPCTL_RSP_ERR_SHIFT 31
-#define I40E_MNGSB_RSPCTL_RSP_ERR_MASK I40E_MASK(0x1, I40E_MNGSB_RSPCTL_RSP_ERR_SHIFT)
-#define I40E_MNGSB_WDATA 0x000B7100 /* Reset: POR */
-#define I40E_MNGSB_WDATA_DATA_SHIFT 0
-#define I40E_MNGSB_WDATA_DATA_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_WDATA_DATA_SHIFT)
-#define I40E_MNGSB_WHDR0 0x000B70F4 /* Reset: POR */
-#define I40E_MNGSB_WHDR0_RAW_DEST_SHIFT 0
-#define I40E_MNGSB_WHDR0_RAW_DEST_MASK I40E_MASK(0xFF, I40E_MNGSB_WHDR0_RAW_DEST_SHIFT)
-#define I40E_MNGSB_WHDR0_DEST_SEL_SHIFT 12
-#define I40E_MNGSB_WHDR0_DEST_SEL_MASK I40E_MASK(0xF, I40E_MNGSB_WHDR0_DEST_SEL_SHIFT)
-#define I40E_MNGSB_WHDR0_OPCODE_SEL_SHIFT 16
-#define I40E_MNGSB_WHDR0_OPCODE_SEL_MASK I40E_MASK(0xFF, I40E_MNGSB_WHDR0_OPCODE_SEL_SHIFT)
-#define I40E_MNGSB_WHDR0_TAG_SHIFT 24
-#define I40E_MNGSB_WHDR0_TAG_MASK I40E_MASK(0x7F, I40E_MNGSB_WHDR0_TAG_SHIFT)
-#define I40E_MNGSB_WHDR1 0x000B70F8 /* Reset: POR */
-#define I40E_MNGSB_WHDR1_ADDR_SHIFT 0
-#define I40E_MNGSB_WHDR1_ADDR_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_WHDR1_ADDR_SHIFT)
-#define I40E_MNGSB_WHDR2 0x000B70FC /* Reset: POR */
-#define I40E_MNGSB_WHDR2_LENGTH_SHIFT 0
-#define I40E_MNGSB_WHDR2_LENGTH_MASK I40E_MASK(0xFFFFFFFF, I40E_MNGSB_WHDR2_LENGTH_SHIFT)
 
-#define I40E_GLPCI_CAPSUP_WAKUP_EN_SHIFT 21
-#define I40E_GLPCI_CAPSUP_WAKUP_EN_MASK I40E_MASK(0x1, I40E_GLPCI_CAPSUP_WAKUP_EN_SHIFT)
 
-#define I40E_GLPCI_CUR_CLNT_COMMON 0x0009CA18 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_CLNT_COMMON_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_CLNT_COMMON_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_CLNT_COMMON_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_CLNT_COMMON_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_CLNT_COMMON_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_CLNT_COMMON_OSR_SHIFT)
-#define I40E_GLPCI_CUR_CLNT_PIPEMON 0x0009CA20 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_CLNT_PIPEMON_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_CLNT_PIPEMON_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_CLNT_PIPEMON_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_MNG_ALWD 0x0009c514 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_MNG_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_MNG_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_MNG_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_MNG_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_MNG_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_MNG_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_MNG_RSVD 0x0009c594 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_MNG_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_MNG_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_MNG_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_MNG_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_MNG_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_MNG_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_PMAT_ALWD 0x0009c510 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_PMAT_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_PMAT_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_PMAT_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_PMAT_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_PMAT_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_PMAT_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_PMAT_RSVD 0x0009c590 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_PMAT_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_PMAT_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_PMAT_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_PMAT_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_PMAT_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_PMAT_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_RLAN_ALWD 0x0009c500 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_RLAN_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_RLAN_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RLAN_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_RLAN_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_RLAN_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RLAN_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_RLAN_RSVD 0x0009c580 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_RLAN_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_RLAN_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RLAN_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_RLAN_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_RLAN_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RLAN_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_RXPE_ALWD 0x0009c508 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_RXPE_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_RXPE_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RXPE_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_RXPE_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_RXPE_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RXPE_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_RXPE_RSVD 0x0009c588 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_RXPE_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_RXPE_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RXPE_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_RXPE_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_RXPE_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_RXPE_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TDPU_ALWD 0x0009c518 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TDPU_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TDPU_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TDPU_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TDPU_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TDPU_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TDPU_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TDPU_RSVD 0x0009c598 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TDPU_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TDPU_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TDPU_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TDPU_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TDPU_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TDPU_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TLAN_ALWD 0x0009c504 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TLAN_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TLAN_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TLAN_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TLAN_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TLAN_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TLAN_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TLAN_RSVD 0x0009c584 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TLAN_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TLAN_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TLAN_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TLAN_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TLAN_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TLAN_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TXPE_ALWD 0x0009c50C /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TXPE_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TXPE_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TXPE_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TXPE_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TXPE_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TXPE_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_TXPE_RSVD 0x0009c58c /* Reset: PCIR */
-#define I40E_GLPCI_CUR_TXPE_RSVD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_TXPE_RSVD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TXPE_RSVD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_TXPE_RSVD_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_TXPE_RSVD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_TXPE_RSVD_OSR_SHIFT)
-#define I40E_GLPCI_CUR_WATMK_CLNT_COMMON 0x0009CA28 /* Reset: PCIR */
-#define I40E_GLPCI_CUR_WATMK_CLNT_COMMON_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_CUR_WATMK_CLNT_COMMON_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_WATMK_CLNT_COMMON_DATA_LINES_SHIFT)
-#define I40E_GLPCI_CUR_WATMK_CLNT_COMMON_OSR_SHIFT 16
-#define I40E_GLPCI_CUR_WATMK_CLNT_COMMON_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_CUR_WATMK_CLNT_COMMON_OSR_SHIFT)
 
-#define I40E_GLPCI_LBARCTRL_PE_DB_SIZE_SHIFT 4
-#define I40E_GLPCI_LBARCTRL_PE_DB_SIZE_MASK I40E_MASK(0x3, I40E_GLPCI_LBARCTRL_PE_DB_SIZE_SHIFT)
-#define I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_SHIFT 10
-#define I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_MASK I40E_MASK(0x1, I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_SHIFT)
-#define I40E_GLPCI_NPQ_CFG 0x0009CA00 /* Reset: PCIR */
-#define I40E_GLPCI_NPQ_CFG_EXTEND_TO_SHIFT 0
-#define I40E_GLPCI_NPQ_CFG_EXTEND_TO_MASK I40E_MASK(0x1, I40E_GLPCI_NPQ_CFG_EXTEND_TO_SHIFT)
-#define I40E_GLPCI_NPQ_CFG_SMALL_TO_SHIFT 1
-#define I40E_GLPCI_NPQ_CFG_SMALL_TO_MASK I40E_MASK(0x1, I40E_GLPCI_NPQ_CFG_SMALL_TO_SHIFT)
-#define I40E_GLPCI_NPQ_CFG_WEIGHT_AVG_SHIFT 2
-#define I40E_GLPCI_NPQ_CFG_WEIGHT_AVG_MASK I40E_MASK(0xF, I40E_GLPCI_NPQ_CFG_WEIGHT_AVG_SHIFT)
-#define I40E_GLPCI_NPQ_CFG_NPQ_SPARE_SHIFT 6
-#define I40E_GLPCI_NPQ_CFG_NPQ_SPARE_MASK I40E_MASK(0x3FF, I40E_GLPCI_NPQ_CFG_NPQ_SPARE_SHIFT)
-#define I40E_GLPCI_NPQ_CFG_NPQ_ERR_STAT_SHIFT 16
-#define I40E_GLPCI_NPQ_CFG_NPQ_ERR_STAT_MASK I40E_MASK(0xF, I40E_GLPCI_NPQ_CFG_NPQ_ERR_STAT_SHIFT)
-#define I40E_GLPCI_WATMK_CLNT_PIPEMON 0x0009CA30 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_CLNT_PIPEMON_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_CLNT_PIPEMON_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_CLNT_PIPEMON_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_MNG_ALWD 0x0009CB14 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_MNG_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_MNG_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_MNG_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_MNG_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_MNG_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_MNG_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_PMAT_ALWD 0x0009CB10 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_PMAT_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_PMAT_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_PMAT_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_PMAT_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_PMAT_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_PMAT_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_RLAN_ALWD 0x0009CB00 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_RLAN_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_RLAN_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_RLAN_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_RLAN_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_RLAN_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_RLAN_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_RXPE_ALWD 0x0009CB08 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_RXPE_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_RXPE_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_RXPE_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_RXPE_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_RXPE_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_RXPE_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_TLAN_ALWD 0x0009CB04 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_TLAN_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_TLAN_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TLAN_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_TLAN_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_TLAN_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TLAN_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_TPDU_ALWD 0x0009CB18 /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_TPDU_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_TPDU_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TPDU_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_TPDU_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_TPDU_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TPDU_ALWD_OSR_SHIFT)
-#define I40E_GLPCI_WATMK_TXPE_ALWD 0x0009CB0c /* Reset: PCIR */
-#define I40E_GLPCI_WATMK_TXPE_ALWD_DATA_LINES_SHIFT 0
-#define I40E_GLPCI_WATMK_TXPE_ALWD_DATA_LINES_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TXPE_ALWD_DATA_LINES_SHIFT)
-#define I40E_GLPCI_WATMK_TXPE_ALWD_OSR_SHIFT 16
-#define I40E_GLPCI_WATMK_TXPE_ALWD_OSR_MASK I40E_MASK(0xFFFF, I40E_GLPCI_WATMK_TXPE_ALWD_OSR_SHIFT)
-#define I40E_GLPE_CPUSTATUS0 0x0000D040 /* Reset: PE_CORER */
-#define I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_SHIFT 0
-#define I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_SHIFT)
-#define I40E_GLPE_CPUSTATUS1 0x0000D044 /* Reset: PE_CORER */
-#define I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_SHIFT 0
-#define I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_SHIFT)
-#define I40E_GLPE_CPUSTATUS2 0x0000D048 /* Reset: PE_CORER */
-#define I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_SHIFT 0
-#define I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_SHIFT)
-#define I40E_GLPE_CPUTRIG0 0x0000D060 /* Reset: PE_CORER */
-#define I40E_GLPE_CPUTRIG0_PECPUTRIG0_SHIFT 0
-#define I40E_GLPE_CPUTRIG0_PECPUTRIG0_MASK I40E_MASK(0xFFFF, I40E_GLPE_CPUTRIG0_PECPUTRIG0_SHIFT)
-#define I40E_GLPE_CPUTRIG0_TEPREQUEST0_SHIFT 17
-#define I40E_GLPE_CPUTRIG0_TEPREQUEST0_MASK I40E_MASK(0x1, I40E_GLPE_CPUTRIG0_TEPREQUEST0_SHIFT)
-#define I40E_GLPE_CPUTRIG0_OOPREQUEST0_SHIFT 18
-#define I40E_GLPE_CPUTRIG0_OOPREQUEST0_MASK I40E_MASK(0x1, I40E_GLPE_CPUTRIG0_OOPREQUEST0_SHIFT)
-#define I40E_GLPE_DUAL40_RUPM 0x0000DA04 /* Reset: PE_CORER */
-#define I40E_GLPE_DUAL40_RUPM_DUAL_40G_MODE_SHIFT 0
-#define I40E_GLPE_DUAL40_RUPM_DUAL_40G_MODE_MASK I40E_MASK(0x1, I40E_GLPE_DUAL40_RUPM_DUAL_40G_MODE_SHIFT)
-#define I40E_GLPE_PFAEQEDROPCNT(_i) (0x00131440 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLPE_PFAEQEDROPCNT_MAX_INDEX 15
-#define I40E_GLPE_PFAEQEDROPCNT_AEQEDROPCNT_SHIFT 0
-#define I40E_GLPE_PFAEQEDROPCNT_AEQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_PFAEQEDROPCNT_AEQEDROPCNT_SHIFT)
-#define I40E_GLPE_PFCEQEDROPCNT(_i) (0x001313C0 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLPE_PFCEQEDROPCNT_MAX_INDEX 15
-#define I40E_GLPE_PFCEQEDROPCNT_CEQEDROPCNT_SHIFT 0
-#define I40E_GLPE_PFCEQEDROPCNT_CEQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_PFCEQEDROPCNT_CEQEDROPCNT_SHIFT)
-#define I40E_GLPE_PFCQEDROPCNT(_i) (0x00131340 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_GLPE_PFCQEDROPCNT_MAX_INDEX 15
-#define I40E_GLPE_PFCQEDROPCNT_CQEDROPCNT_SHIFT 0
-#define I40E_GLPE_PFCQEDROPCNT_CQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_PFCQEDROPCNT_CQEDROPCNT_SHIFT)
-#define I40E_GLPE_RUPM_CQPPOOL 0x0000DACC /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_CQPPOOL_CQPSPADS_SHIFT 0
-#define I40E_GLPE_RUPM_CQPPOOL_CQPSPADS_MASK I40E_MASK(0xFF, I40E_GLPE_RUPM_CQPPOOL_CQPSPADS_SHIFT)
-#define I40E_GLPE_RUPM_FLRPOOL 0x0000DAC4 /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_FLRPOOL_FLRSPADS_SHIFT 0
-#define I40E_GLPE_RUPM_FLRPOOL_FLRSPADS_MASK I40E_MASK(0xFF, I40E_GLPE_RUPM_FLRPOOL_FLRSPADS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL 0x0000DA00 /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_GCTL_ALLOFFTH_SHIFT 0
-#define I40E_GLPE_RUPM_GCTL_ALLOFFTH_MASK I40E_MASK(0xFF, I40E_GLPE_RUPM_GCTL_ALLOFFTH_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_RUPM_P0_DIS_SHIFT 26
-#define I40E_GLPE_RUPM_GCTL_RUPM_P0_DIS_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_RUPM_P0_DIS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_RUPM_P1_DIS_SHIFT 27
-#define I40E_GLPE_RUPM_GCTL_RUPM_P1_DIS_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_RUPM_P1_DIS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_RUPM_P2_DIS_SHIFT 28
-#define I40E_GLPE_RUPM_GCTL_RUPM_P2_DIS_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_RUPM_P2_DIS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_RUPM_P3_DIS_SHIFT 29
-#define I40E_GLPE_RUPM_GCTL_RUPM_P3_DIS_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_RUPM_P3_DIS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_RUPM_DIS_SHIFT 30
-#define I40E_GLPE_RUPM_GCTL_RUPM_DIS_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_RUPM_DIS_SHIFT)
-#define I40E_GLPE_RUPM_GCTL_SWLB_MODE_SHIFT 31
-#define I40E_GLPE_RUPM_GCTL_SWLB_MODE_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_GCTL_SWLB_MODE_SHIFT)
-#define I40E_GLPE_RUPM_PTXPOOL 0x0000DAC8 /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_PTXPOOL_PTXSPADS_SHIFT 0
-#define I40E_GLPE_RUPM_PTXPOOL_PTXSPADS_MASK I40E_MASK(0xFF, I40E_GLPE_RUPM_PTXPOOL_PTXSPADS_SHIFT)
-#define I40E_GLPE_RUPM_PUSHPOOL 0x0000DAC0 /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_PUSHPOOL_PUSHSPADS_SHIFT 0
-#define I40E_GLPE_RUPM_PUSHPOOL_PUSHSPADS_MASK I40E_MASK(0xFF, I40E_GLPE_RUPM_PUSHPOOL_PUSHSPADS_SHIFT)
-#define I40E_GLPE_RUPM_TXHOST_EN 0x0000DA08 /* Reset: PE_CORER */
-#define I40E_GLPE_RUPM_TXHOST_EN_TXHOST_EN_SHIFT 0
-#define I40E_GLPE_RUPM_TXHOST_EN_TXHOST_EN_MASK I40E_MASK(0x1, I40E_GLPE_RUPM_TXHOST_EN_TXHOST_EN_SHIFT)
-#define I40E_GLPE_VFAEQEDROPCNT(_i) (0x00132540 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLPE_VFAEQEDROPCNT_MAX_INDEX 31
-#define I40E_GLPE_VFAEQEDROPCNT_AEQEDROPCNT_SHIFT 0
-#define I40E_GLPE_VFAEQEDROPCNT_AEQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_VFAEQEDROPCNT_AEQEDROPCNT_SHIFT)
-#define I40E_GLPE_VFCEQEDROPCNT(_i) (0x00132440 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLPE_VFCEQEDROPCNT_MAX_INDEX 31
-#define I40E_GLPE_VFCEQEDROPCNT_CEQEDROPCNT_SHIFT 0
-#define I40E_GLPE_VFCEQEDROPCNT_CEQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_VFCEQEDROPCNT_CEQEDROPCNT_SHIFT)
-#define I40E_GLPE_VFCQEDROPCNT(_i) (0x00132340 + ((_i) * 4)) /* _i=0...31 */ /* Reset: CORER */
-#define I40E_GLPE_VFCQEDROPCNT_MAX_INDEX 31
-#define I40E_GLPE_VFCQEDROPCNT_CQEDROPCNT_SHIFT 0
-#define I40E_GLPE_VFCQEDROPCNT_CQEDROPCNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_VFCQEDROPCNT_CQEDROPCNT_SHIFT)
-#define I40E_GLPE_VFFLMOBJCTRL(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPE_VFFLMOBJCTRL_MAX_INDEX 31
-#define I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT 0
-#define I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_MASK I40E_MASK(0x7, I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT)
-#define I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT 8
-#define I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_MASK I40E_MASK(0x7, I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT)
-#define I40E_GLPE_VFFLMQ1ALLOCERR(_i) (0x0000C700 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPE_VFFLMQ1ALLOCERR_MAX_INDEX 31
-#define I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_SHIFT 0
-#define I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_SHIFT)
-#define I40E_GLPE_VFFLMXMITALLOCERR(_i) (0x0000C600 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPE_VFFLMXMITALLOCERR_MAX_INDEX 31
-#define I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_SHIFT 0
-#define I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_MASK I40E_MASK(0xFFFF, I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_SHIFT)
-#define I40E_GLPE_VFUDACTRL(_i) (0x0000C000 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPE_VFUDACTRL_MAX_INDEX 31
-#define I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_SHIFT 0
-#define I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_MASK I40E_MASK(0x1, I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_SHIFT)
-#define I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_SHIFT 1
-#define I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_MASK I40E_MASK(0x1, I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_SHIFT)
-#define I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_SHIFT 2
-#define I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_MASK I40E_MASK(0x1, I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_SHIFT)
-#define I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_SHIFT 3
-#define I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_MASK I40E_MASK(0x1, I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_SHIFT)
-#define I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_SHIFT 4
-#define I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_MASK I40E_MASK(0x1, I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_SHIFT)
-#define I40E_GLPE_VFUDAUCFBQPN(_i) (0x0000C100 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPE_VFUDAUCFBQPN_MAX_INDEX 31
-#define I40E_GLPE_VFUDAUCFBQPN_QPN_SHIFT 0
-#define I40E_GLPE_VFUDAUCFBQPN_QPN_MASK I40E_MASK(0x3FFFF, I40E_GLPE_VFUDAUCFBQPN_QPN_SHIFT)
-#define I40E_GLPE_VFUDAUCFBQPN_VALID_SHIFT 31
-#define I40E_GLPE_VFUDAUCFBQPN_VALID_MASK I40E_MASK(0x1, I40E_GLPE_VFUDAUCFBQPN_VALID_SHIFT)
-#define I40E_PFPE_AEQALLOC 0x00131180 /* Reset: PFR */
-#define I40E_PFPE_AEQALLOC_AECOUNT_SHIFT 0
-#define I40E_PFPE_AEQALLOC_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPE_AEQALLOC_AECOUNT_SHIFT)
-#define I40E_PFPE_CCQPHIGH 0x00008200 /* Reset: PFR */
-#define I40E_PFPE_CCQPHIGH_PECCQPHIGH_SHIFT 0
-#define I40E_PFPE_CCQPHIGH_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPE_CCQPHIGH_PECCQPHIGH_SHIFT)
-#define I40E_PFPE_CCQPLOW 0x00008180 /* Reset: PFR */
-#define I40E_PFPE_CCQPLOW_PECCQPLOW_SHIFT 0
-#define I40E_PFPE_CCQPLOW_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPE_CCQPLOW_PECCQPLOW_SHIFT)
-#define I40E_PFPE_CCQPSTATUS 0x00008100 /* Reset: PFR */
-#define I40E_PFPE_CCQPSTATUS_CCQP_DONE_SHIFT 0
-#define I40E_PFPE_CCQPSTATUS_CCQP_DONE_MASK I40E_MASK(0x1, I40E_PFPE_CCQPSTATUS_CCQP_DONE_SHIFT)
-#define I40E_PFPE_CCQPSTATUS_HMC_PROFILE_SHIFT 4
-#define I40E_PFPE_CCQPSTATUS_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_PFPE_CCQPSTATUS_HMC_PROFILE_SHIFT)
-#define I40E_PFPE_CCQPSTATUS_RDMA_EN_VFS_SHIFT 16
-#define I40E_PFPE_CCQPSTATUS_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_PFPE_CCQPSTATUS_RDMA_EN_VFS_SHIFT)
-#define I40E_PFPE_CCQPSTATUS_CCQP_ERR_SHIFT 31
-#define I40E_PFPE_CCQPSTATUS_CCQP_ERR_MASK I40E_MASK(0x1, I40E_PFPE_CCQPSTATUS_CCQP_ERR_SHIFT)
-#define I40E_PFPE_CQACK 0x00131100 /* Reset: PFR */
-#define I40E_PFPE_CQACK_PECQID_SHIFT 0
-#define I40E_PFPE_CQACK_PECQID_MASK I40E_MASK(0x1FFFF, I40E_PFPE_CQACK_PECQID_SHIFT)
-#define I40E_PFPE_CQARM 0x00131080 /* Reset: PFR */
-#define I40E_PFPE_CQARM_PECQID_SHIFT 0
-#define I40E_PFPE_CQARM_PECQID_MASK I40E_MASK(0x1FFFF, I40E_PFPE_CQARM_PECQID_SHIFT)
-#define I40E_PFPE_CQPDB 0x00008000 /* Reset: PFR */
-#define I40E_PFPE_CQPDB_WQHEAD_SHIFT 0
-#define I40E_PFPE_CQPDB_WQHEAD_MASK I40E_MASK(0x7FF, I40E_PFPE_CQPDB_WQHEAD_SHIFT)
-#define I40E_PFPE_CQPERRCODES 0x00008880 /* Reset: PFR */
-#define I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT 0
-#define I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT)
-#define I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT 16
-#define I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT)
-#define I40E_PFPE_CQPTAIL 0x00008080 /* Reset: PFR */
-#define I40E_PFPE_CQPTAIL_WQTAIL_SHIFT 0
-#define I40E_PFPE_CQPTAIL_WQTAIL_MASK I40E_MASK(0x7FF, I40E_PFPE_CQPTAIL_WQTAIL_SHIFT)
-#define I40E_PFPE_CQPTAIL_CQP_OP_ERR_SHIFT 31
-#define I40E_PFPE_CQPTAIL_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_PFPE_CQPTAIL_CQP_OP_ERR_SHIFT)
-#define I40E_PFPE_FLMQ1ALLOCERR 0x00008980 /* Reset: PFR */
-#define I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_SHIFT 0
-#define I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_MASK I40E_MASK(0xFFFF, I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_SHIFT)
-#define I40E_PFPE_FLMXMITALLOCERR 0x00008900 /* Reset: PFR */
-#define I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_SHIFT 0
-#define I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_MASK I40E_MASK(0xFFFF, I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_SHIFT)
-#define I40E_PFPE_IPCONFIG0 0x00008280 /* Reset: PFR */
-#define I40E_PFPE_IPCONFIG0_PEIPID_SHIFT 0
-#define I40E_PFPE_IPCONFIG0_PEIPID_MASK I40E_MASK(0xFFFF, I40E_PFPE_IPCONFIG0_PEIPID_SHIFT)
-#define I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT 16
-#define I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT)
-#define I40E_PFPE_MRTEIDXMASK 0x00008600 /* Reset: PFR */
-#define I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT 0
-#define I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT)
-#define I40E_PFPE_RCVUNEXPECTEDERROR 0x00008680 /* Reset: PFR */
-#define I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT 0
-#define I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT)
-#define I40E_PFPE_TCPNOWTIMER 0x00008580 /* Reset: PFR */
-#define I40E_PFPE_TCPNOWTIMER_TCP_NOW_SHIFT 0
-#define I40E_PFPE_TCPNOWTIMER_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_PFPE_TCPNOWTIMER_TCP_NOW_SHIFT)
-#define I40E_PFPE_UDACTRL 0x00008700 /* Reset: PFR */
-#define I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_SHIFT 0
-#define I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_MASK I40E_MASK(0x1, I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_SHIFT)
-#define I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_SHIFT 1
-#define I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_MASK I40E_MASK(0x1, I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_SHIFT)
-#define I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_SHIFT 2
-#define I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_MASK I40E_MASK(0x1, I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_SHIFT)
-#define I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_SHIFT 3
-#define I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_MASK I40E_MASK(0x1, I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_SHIFT)
-#define I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_SHIFT 4
-#define I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_MASK I40E_MASK(0x1, I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_SHIFT)
-#define I40E_PFPE_UDAUCFBQPN 0x00008780 /* Reset: PFR */
-#define I40E_PFPE_UDAUCFBQPN_QPN_SHIFT 0
-#define I40E_PFPE_UDAUCFBQPN_QPN_MASK I40E_MASK(0x3FFFF, I40E_PFPE_UDAUCFBQPN_QPN_SHIFT)
-#define I40E_PFPE_UDAUCFBQPN_VALID_SHIFT 31
-#define I40E_PFPE_UDAUCFBQPN_VALID_MASK I40E_MASK(0x1, I40E_PFPE_UDAUCFBQPN_VALID_SHIFT)
-#define I40E_PFPE_WQEALLOC 0x00138C00 /* Reset: PFR */
-#define I40E_PFPE_WQEALLOC_PEQPID_SHIFT 0
-#define I40E_PFPE_WQEALLOC_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_PFPE_WQEALLOC_PEQPID_SHIFT)
-#define I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT 20
-#define I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT)
-#define I40E_PRTDCB_RLPMC 0x0001F140 /* Reset: PE_CORER */
-#define I40E_PRTDCB_RLPMC_TC2PFC_SHIFT 0
-#define I40E_PRTDCB_RLPMC_TC2PFC_MASK I40E_MASK(0xFF, I40E_PRTDCB_RLPMC_TC2PFC_SHIFT)
-#define I40E_PRTDCB_TCMSTC_RLPM(_i) (0x0001F040 + ((_i) * 32)) /* _i=0...7 */ /* Reset: PE_CORER */
-#define I40E_PRTDCB_TCMSTC_RLPM_MAX_INDEX 7
-#define I40E_PRTDCB_TCMSTC_RLPM_MSTC_SHIFT 0
-#define I40E_PRTDCB_TCMSTC_RLPM_MSTC_MASK I40E_MASK(0xFFFFF, I40E_PRTDCB_TCMSTC_RLPM_MSTC_SHIFT)
-#define I40E_PRTDCB_TCPMC_RLPM 0x0001F1A0 /* Reset: PE_CORER */
-#define I40E_PRTDCB_TCPMC_RLPM_CPM_SHIFT 0
-#define I40E_PRTDCB_TCPMC_RLPM_CPM_MASK I40E_MASK(0x1FFF, I40E_PRTDCB_TCPMC_RLPM_CPM_SHIFT)
-#define I40E_PRTDCB_TCPMC_RLPM_LLTC_SHIFT 13
-#define I40E_PRTDCB_TCPMC_RLPM_LLTC_MASK I40E_MASK(0xFF, I40E_PRTDCB_TCPMC_RLPM_LLTC_SHIFT)
-#define I40E_PRTDCB_TCPMC_RLPM_TCPM_MODE_SHIFT 30
-#define I40E_PRTDCB_TCPMC_RLPM_TCPM_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_TCPMC_RLPM_TCPM_MODE_SHIFT)
-#define I40E_PRTE_RUPM_TCCNTR03 0x0000DAE0 /* Reset: PE_CORER */
-#define I40E_PRTE_RUPM_TCCNTR03_TC0COUNT_SHIFT 0
-#define I40E_PRTE_RUPM_TCCNTR03_TC0COUNT_MASK I40E_MASK(0xFF, I40E_PRTE_RUPM_TCCNTR03_TC0COUNT_SHIFT)
-#define I40E_PRTE_RUPM_TCCNTR03_TC1COUNT_SHIFT 8
-#define I40E_PRTE_RUPM_TCCNTR03_TC1COUNT_MASK I40E_MASK(0xFF, I40E_PRTE_RUPM_TCCNTR03_TC1COUNT_SHIFT)
-#define I40E_PRTE_RUPM_TCCNTR03_TC2COUNT_SHIFT 16
-#define I40E_PRTE_RUPM_TCCNTR03_TC2COUNT_MASK I40E_MASK(0xFF, I40E_PRTE_RUPM_TCCNTR03_TC2COUNT_SHIFT)
-#define I40E_PRTE_RUPM_TCCNTR03_TC3COUNT_SHIFT 24
-#define I40E_PRTE_RUPM_TCCNTR03_TC3COUNT_MASK I40E_MASK(0xFF, I40E_PRTE_RUPM_TCCNTR03_TC3COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_CNTR 0x0000DB20 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_CNTR_COUNT_SHIFT 0
-#define I40E_PRTPE_RUPM_CNTR_COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_CNTR_COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_CTL 0x0000DA40 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_CTL_LLTC_SHIFT 13
-#define I40E_PRTPE_RUPM_CTL_LLTC_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_CTL_LLTC_SHIFT)
-#define I40E_PRTPE_RUPM_CTL_RUPM_MODE_SHIFT 30
-#define I40E_PRTPE_RUPM_CTL_RUPM_MODE_MASK I40E_MASK(0x1, I40E_PRTPE_RUPM_CTL_RUPM_MODE_SHIFT)
-#define I40E_PRTPE_RUPM_PFCCTL 0x0000DA60 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_PFCCTL_TC2PFC_SHIFT 0
-#define I40E_PRTPE_RUPM_PFCCTL_TC2PFC_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PFCCTL_TC2PFC_SHIFT)
-#define I40E_PRTPE_RUPM_PFCPC 0x0000DA80 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_PFCPC_PORTOFFTH_SHIFT 0
-#define I40E_PRTPE_RUPM_PFCPC_PORTOFFTH_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PFCPC_PORTOFFTH_SHIFT)
-#define I40E_PRTPE_RUPM_PFCTCC 0x0000DAA0 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_PFCTCC_TCOFFTH_SHIFT 0
-#define I40E_PRTPE_RUPM_PFCTCC_TCOFFTH_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PFCTCC_TCOFFTH_SHIFT)
-#define I40E_PRTPE_RUPM_PFCTCC_LL_PRI_TH_SHIFT 16
-#define I40E_PRTPE_RUPM_PFCTCC_LL_PRI_TH_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PFCTCC_LL_PRI_TH_SHIFT)
-#define I40E_PRTPE_RUPM_PFCTCC_LL_PRI_EN_SHIFT 31
-#define I40E_PRTPE_RUPM_PFCTCC_LL_PRI_EN_MASK I40E_MASK(0x1, I40E_PRTPE_RUPM_PFCTCC_LL_PRI_EN_SHIFT)
-#define I40E_PRTPE_RUPM_PTCTCCNTR47 0x0000DB60 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC4COUNT_SHIFT 0
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC4COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTCTCCNTR47_TC4COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC5COUNT_SHIFT 8
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC5COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTCTCCNTR47_TC5COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC6COUNT_SHIFT 16
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC6COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTCTCCNTR47_TC6COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC7COUNT_SHIFT 24
-#define I40E_PRTPE_RUPM_PTCTCCNTR47_TC7COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTCTCCNTR47_TC7COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTXTCCNTR03 0x0000DB40 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC0COUNT_SHIFT 0
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC0COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTXTCCNTR03_TC0COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC1COUNT_SHIFT 8
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC1COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTXTCCNTR03_TC1COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC2COUNT_SHIFT 16
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC2COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTXTCCNTR03_TC2COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC3COUNT_SHIFT 24
-#define I40E_PRTPE_RUPM_PTXTCCNTR03_TC3COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_PTXTCCNTR03_TC3COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_TCCNTR47 0x0000DB00 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_TCCNTR47_TC4COUNT_SHIFT 0
-#define I40E_PRTPE_RUPM_TCCNTR47_TC4COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_TCCNTR47_TC4COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_TCCNTR47_TC5COUNT_SHIFT 8
-#define I40E_PRTPE_RUPM_TCCNTR47_TC5COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_TCCNTR47_TC5COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_TCCNTR47_TC6COUNT_SHIFT 16
-#define I40E_PRTPE_RUPM_TCCNTR47_TC6COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_TCCNTR47_TC6COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_TCCNTR47_TC7COUNT_SHIFT 24
-#define I40E_PRTPE_RUPM_TCCNTR47_TC7COUNT_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_TCCNTR47_TC7COUNT_SHIFT)
-#define I40E_PRTPE_RUPM_THRES 0x0000DA20 /* Reset: PE_CORER */
-#define I40E_PRTPE_RUPM_THRES_MINSPADSPERTC_SHIFT 0
-#define I40E_PRTPE_RUPM_THRES_MINSPADSPERTC_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_THRES_MINSPADSPERTC_SHIFT)
-#define I40E_PRTPE_RUPM_THRES_MAXSPADS_SHIFT 8
-#define I40E_PRTPE_RUPM_THRES_MAXSPADS_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_THRES_MAXSPADS_SHIFT)
-#define I40E_PRTPE_RUPM_THRES_MAXSPADSPERTC_SHIFT 16
-#define I40E_PRTPE_RUPM_THRES_MAXSPADSPERTC_MASK I40E_MASK(0xFF, I40E_PRTPE_RUPM_THRES_MAXSPADSPERTC_SHIFT)
-#define I40E_VFPE_AEQALLOC(_VF) (0x00130C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_AEQALLOC_MAX_INDEX 127
-#define I40E_VFPE_AEQALLOC_AECOUNT_SHIFT 0
-#define I40E_VFPE_AEQALLOC_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_AEQALLOC_AECOUNT_SHIFT)
-#define I40E_VFPE_CCQPHIGH(_VF) (0x00001000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CCQPHIGH_MAX_INDEX 127
-#define I40E_VFPE_CCQPHIGH_PECCQPHIGH_SHIFT 0
-#define I40E_VFPE_CCQPHIGH_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPHIGH_PECCQPHIGH_SHIFT)
-#define I40E_VFPE_CCQPLOW(_VF) (0x00000C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CCQPLOW_MAX_INDEX 127
-#define I40E_VFPE_CCQPLOW_PECCQPLOW_SHIFT 0
-#define I40E_VFPE_CCQPLOW_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPLOW_PECCQPLOW_SHIFT)
-#define I40E_VFPE_CCQPSTATUS(_VF) (0x00000800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CCQPSTATUS_MAX_INDEX 127
-#define I40E_VFPE_CCQPSTATUS_CCQP_DONE_SHIFT 0
-#define I40E_VFPE_CCQPSTATUS_CCQP_DONE_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS_CCQP_DONE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS_HMC_PROFILE_SHIFT 4
-#define I40E_VFPE_CCQPSTATUS_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_VFPE_CCQPSTATUS_HMC_PROFILE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS_RDMA_EN_VFS_SHIFT 16
-#define I40E_VFPE_CCQPSTATUS_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_VFPE_CCQPSTATUS_RDMA_EN_VFS_SHIFT)
-#define I40E_VFPE_CCQPSTATUS_CCQP_ERR_SHIFT 31
-#define I40E_VFPE_CCQPSTATUS_CCQP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS_CCQP_ERR_SHIFT)
-#define I40E_VFPE_CQACK(_VF) (0x00130800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CQACK_MAX_INDEX 127
-#define I40E_VFPE_CQACK_PECQID_SHIFT 0
-#define I40E_VFPE_CQACK_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQACK_PECQID_SHIFT)
-#define I40E_VFPE_CQARM(_VF) (0x00130400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CQARM_MAX_INDEX 127
-#define I40E_VFPE_CQARM_PECQID_SHIFT 0
-#define I40E_VFPE_CQARM_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQARM_PECQID_SHIFT)
-#define I40E_VFPE_CQPDB(_VF) (0x00000000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CQPDB_MAX_INDEX 127
-#define I40E_VFPE_CQPDB_WQHEAD_SHIFT 0
-#define I40E_VFPE_CQPDB_WQHEAD_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPDB_WQHEAD_SHIFT)
-#define I40E_VFPE_CQPERRCODES(_VF) (0x00001800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CQPERRCODES_MAX_INDEX 127
-#define I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT 0
-#define I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT)
-#define I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT 16
-#define I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT)
-#define I40E_VFPE_CQPTAIL(_VF) (0x00000400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_CQPTAIL_MAX_INDEX 127
-#define I40E_VFPE_CQPTAIL_WQTAIL_SHIFT 0
-#define I40E_VFPE_CQPTAIL_WQTAIL_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPTAIL_WQTAIL_SHIFT)
-#define I40E_VFPE_CQPTAIL_CQP_OP_ERR_SHIFT 31
-#define I40E_VFPE_CQPTAIL_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CQPTAIL_CQP_OP_ERR_SHIFT)
-#define I40E_VFPE_IPCONFIG0(_VF) (0x00001400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_IPCONFIG0_MAX_INDEX 127
-#define I40E_VFPE_IPCONFIG0_PEIPID_SHIFT 0
-#define I40E_VFPE_IPCONFIG0_PEIPID_MASK I40E_MASK(0xFFFF, I40E_VFPE_IPCONFIG0_PEIPID_SHIFT)
-#define I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT 16
-#define I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT)
-#define I40E_VFPE_MRTEIDXMASK(_VF) (0x00003000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_MRTEIDXMASK_MAX_INDEX 127
-#define I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT 0
-#define I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT)
-#define I40E_VFPE_RCVUNEXPECTEDERROR(_VF) (0x00003400 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_RCVUNEXPECTEDERROR_MAX_INDEX 127
-#define I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT 0
-#define I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT)
-#define I40E_VFPE_TCPNOWTIMER(_VF) (0x00002C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_TCPNOWTIMER_MAX_INDEX 127
-#define I40E_VFPE_TCPNOWTIMER_TCP_NOW_SHIFT 0
-#define I40E_VFPE_TCPNOWTIMER_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_TCPNOWTIMER_TCP_NOW_SHIFT)
-#define I40E_VFPE_WQEALLOC(_VF) (0x00138000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: VFR */
-#define I40E_VFPE_WQEALLOC_MAX_INDEX 127
-#define I40E_VFPE_WQEALLOC_PEQPID_SHIFT 0
-#define I40E_VFPE_WQEALLOC_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_VFPE_WQEALLOC_PEQPID_SHIFT)
-#define I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT 20
-#define I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT)
-#define I40E_GLPES_PFIP4RXDISCARD(_i) (0x00010600 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXDISCARD_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_SHIFT 0
-#define I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_SHIFT)
-#define I40E_GLPES_PFIP4RXFRAGSHI(_i) (0x00010804 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXFRAGSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT 0
-#define I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT)
-#define I40E_GLPES_PFIP4RXFRAGSLO(_i) (0x00010800 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXFRAGSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT 0
-#define I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT)
-#define I40E_GLPES_PFIP4RXMCOCTSHI(_i) (0x00010A04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXMCOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP4RXMCOCTSLO(_i) (0x00010A00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXMCOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP4RXMCPKTSHI(_i) (0x00010C04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXMCPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP4RXMCPKTSLO(_i) (0x00010C00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXMCPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP4RXOCTSHI(_i) (0x00010204 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP4RXOCTSLO(_i) (0x00010200 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP4RXPKTSHI(_i) (0x00010404 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP4RXPKTSLO(_i) (0x00010400 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP4RXTRUNC(_i) (0x00010700 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4RXTRUNC_MAX_INDEX 15
-#define I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_SHIFT 0
-#define I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_SHIFT)
-#define I40E_GLPES_PFIP4TXFRAGSHI(_i) (0x00011E04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXFRAGSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT 0
-#define I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT)
-#define I40E_GLPES_PFIP4TXFRAGSLO(_i) (0x00011E00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXFRAGSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT 0
-#define I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT)
-#define I40E_GLPES_PFIP4TXMCOCTSHI(_i) (0x00012004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXMCOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP4TXMCOCTSLO(_i) (0x00012000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXMCOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP4TXMCPKTSHI(_i) (0x00012204 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXMCPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP4TXMCPKTSLO(_i) (0x00012200 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXMCPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP4TXNOROUTE(_i) (0x00012E00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXNOROUTE_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT 0
-#define I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT)
-#define I40E_GLPES_PFIP4TXOCTSHI(_i) (0x00011A04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP4TXOCTSLO(_i) (0x00011A00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP4TXPKTSHI(_i) (0x00011C04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP4TXPKTSLO(_i) (0x00011C00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP4TXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXDISCARD(_i) (0x00011200 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXDISCARD_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_SHIFT 0
-#define I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_SHIFT)
-#define I40E_GLPES_PFIP6RXFRAGSHI(_i) (0x00011404 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXFRAGSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT 0
-#define I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT)
-#define I40E_GLPES_PFIP6RXFRAGSLO(_i) (0x00011400 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXFRAGSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT 0
-#define I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXMCOCTSHI(_i) (0x00011604 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXMCOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP6RXMCOCTSLO(_i) (0x00011600 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXMCOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXMCPKTSHI(_i) (0x00011804 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXMCPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP6RXMCPKTSLO(_i) (0x00011800 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXMCPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXOCTSHI(_i) (0x00010E04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP6RXOCTSLO(_i) (0x00010E00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXPKTSHI(_i) (0x00011004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP6RXPKTSLO(_i) (0x00011000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP6RXTRUNC(_i) (0x00011300 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6RXTRUNC_MAX_INDEX 15
-#define I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_SHIFT 0
-#define I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_SHIFT)
-#define I40E_GLPES_PFIP6TXFRAGSHI(_i) (0x00012804 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXFRAGSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT 0
-#define I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT)
-#define I40E_GLPES_PFIP6TXFRAGSLO(_i) (0x00012800 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXFRAGSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT 0
-#define I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT)
-#define I40E_GLPES_PFIP6TXMCOCTSHI(_i) (0x00012A04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXMCOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP6TXMCOCTSLO(_i) (0x00012A00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXMCOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP6TXMCPKTSHI(_i) (0x00012C04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXMCPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP6TXMCPKTSLO(_i) (0x00012C00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXMCPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT)
-#define I40E_GLPES_PFIP6TXNOROUTE(_i) (0x00012F00 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXNOROUTE_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT 0
-#define I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT)
-#define I40E_GLPES_PFIP6TXOCTSHI(_i) (0x00012404 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXOCTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT)
-#define I40E_GLPES_PFIP6TXOCTSLO(_i) (0x00012400 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXOCTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT)
-#define I40E_GLPES_PFIP6TXPKTSHI(_i) (0x00012604 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT)
-#define I40E_GLPES_PFIP6TXPKTSLO(_i) (0x00012600 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFIP6TXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT)
-#define I40E_GLPES_PFRDMARXRDSHI(_i) (0x00013E04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXRDSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_SHIFT 0
-#define I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_SHIFT)
-#define I40E_GLPES_PFRDMARXRDSLO(_i) (0x00013E00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXRDSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_SHIFT 0
-#define I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_SHIFT)
-#define I40E_GLPES_PFRDMARXSNDSHI(_i) (0x00014004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXSNDSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT 0
-#define I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT)
-#define I40E_GLPES_PFRDMARXSNDSLO(_i) (0x00014000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXSNDSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT 0
-#define I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT)
-#define I40E_GLPES_PFRDMARXWRSHI(_i) (0x00013C04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXWRSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_SHIFT 0
-#define I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_SHIFT)
-#define I40E_GLPES_PFRDMARXWRSLO(_i) (0x00013C00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMARXWRSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_SHIFT 0
-#define I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_SHIFT)
-#define I40E_GLPES_PFRDMATXRDSHI(_i) (0x00014404 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXRDSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_SHIFT 0
-#define I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_SHIFT)
-#define I40E_GLPES_PFRDMATXRDSLO(_i) (0x00014400 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXRDSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_SHIFT 0
-#define I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_SHIFT)
-#define I40E_GLPES_PFRDMATXSNDSHI(_i) (0x00014604 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXSNDSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT 0
-#define I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT)
-#define I40E_GLPES_PFRDMATXSNDSLO(_i) (0x00014600 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXSNDSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT 0
-#define I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT)
-#define I40E_GLPES_PFRDMATXWRSHI(_i) (0x00014204 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXWRSHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_SHIFT 0
-#define I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_SHIFT)
-#define I40E_GLPES_PFRDMATXWRSLO(_i) (0x00014200 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMATXWRSLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_SHIFT 0
-#define I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_SHIFT)
-#define I40E_GLPES_PFRDMAVBNDHI(_i) (0x00014804 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMAVBNDHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_SHIFT 0
-#define I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_SHIFT)
-#define I40E_GLPES_PFRDMAVBNDLO(_i) (0x00014800 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMAVBNDLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_SHIFT 0
-#define I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_SHIFT)
-#define I40E_GLPES_PFRDMAVINVHI(_i) (0x00014A04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMAVINVHI_MAX_INDEX 15
-#define I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_SHIFT 0
-#define I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_SHIFT)
-#define I40E_GLPES_PFRDMAVINVLO(_i) (0x00014A00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRDMAVINVLO_MAX_INDEX 15
-#define I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_SHIFT 0
-#define I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_SHIFT)
-#define I40E_GLPES_PFRXVLANERR(_i) (0x00010000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFRXVLANERR_MAX_INDEX 15
-#define I40E_GLPES_PFRXVLANERR_RXVLANERR_SHIFT 0
-#define I40E_GLPES_PFRXVLANERR_RXVLANERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_PFRXVLANERR_RXVLANERR_SHIFT)
-#define I40E_GLPES_PFTCPRTXSEG(_i) (0x00013600 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPRTXSEG_MAX_INDEX 15
-#define I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_SHIFT 0
-#define I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_SHIFT)
-#define I40E_GLPES_PFTCPRXOPTERR(_i) (0x00013200 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPRXOPTERR_MAX_INDEX 15
-#define I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_SHIFT 0
-#define I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_SHIFT)
-#define I40E_GLPES_PFTCPRXPROTOERR(_i) (0x00013300 + ((_i) * 4)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPRXPROTOERR_MAX_INDEX 15
-#define I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT 0
-#define I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT)
-#define I40E_GLPES_PFTCPRXSEGSHI(_i) (0x00013004 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPRXSEGSHI_MAX_INDEX 15
-#define I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT 0
-#define I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT)
-#define I40E_GLPES_PFTCPRXSEGSLO(_i) (0x00013000 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPRXSEGSLO_MAX_INDEX 15
-#define I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT 0
-#define I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT)
-#define I40E_GLPES_PFTCPTXSEGHI(_i) (0x00013404 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPTXSEGHI_MAX_INDEX 15
-#define I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_SHIFT 0
-#define I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_SHIFT)
-#define I40E_GLPES_PFTCPTXSEGLO(_i) (0x00013400 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFTCPTXSEGLO_MAX_INDEX 15
-#define I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_SHIFT 0
-#define I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_SHIFT)
-#define I40E_GLPES_PFUDPRXPKTSHI(_i) (0x00013804 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFUDPRXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT)
-#define I40E_GLPES_PFUDPRXPKTSLO(_i) (0x00013800 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFUDPRXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT)
-#define I40E_GLPES_PFUDPTXPKTSHI(_i) (0x00013A04 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFUDPTXPKTSHI_MAX_INDEX 15
-#define I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT 0
-#define I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT)
-#define I40E_GLPES_PFUDPTXPKTSLO(_i) (0x00013A00 + ((_i) * 8)) /* _i=0...15 */ /* Reset: PE_CORER */
-#define I40E_GLPES_PFUDPTXPKTSLO_MAX_INDEX 15
-#define I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT 0
-#define I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT)
-#define I40E_GLPES_RDMARXMULTFPDUSHI 0x0001E014 /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_SHIFT 0
-#define I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_SHIFT)
-#define I40E_GLPES_RDMARXMULTFPDUSLO 0x0001E010 /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_SHIFT 0
-#define I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_SHIFT)
-#define I40E_GLPES_RDMARXOOODDPHI 0x0001E01C /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_SHIFT 0
-#define I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_SHIFT)
-#define I40E_GLPES_RDMARXOOODDPLO 0x0001E018 /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_SHIFT 0
-#define I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_SHIFT)
-#define I40E_GLPES_RDMARXOOONOMARK 0x0001E004 /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_SHIFT 0
-#define I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_SHIFT)
-#define I40E_GLPES_RDMARXUNALIGN 0x0001E000 /* Reset: PE_CORER */
-#define I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_SHIFT 0
-#define I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_SHIFT)
-#define I40E_GLPES_TCPRXFOURHOLEHI 0x0001E044 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_SHIFT 0
-#define I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_SHIFT)
-#define I40E_GLPES_TCPRXFOURHOLELO 0x0001E040 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_SHIFT 0
-#define I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_SHIFT)
-#define I40E_GLPES_TCPRXONEHOLEHI 0x0001E02C /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_SHIFT 0
-#define I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_SHIFT)
-#define I40E_GLPES_TCPRXONEHOLELO 0x0001E028 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_SHIFT 0
-#define I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_SHIFT)
-#define I40E_GLPES_TCPRXPUREACKHI 0x0001E024 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_SHIFT 0
-#define I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_SHIFT)
-#define I40E_GLPES_TCPRXPUREACKSLO 0x0001E020 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_SHIFT 0
-#define I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_SHIFT)
-#define I40E_GLPES_TCPRXTHREEHOLEHI 0x0001E03C /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_SHIFT 0
-#define I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_SHIFT)
-#define I40E_GLPES_TCPRXTHREEHOLELO 0x0001E038 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_SHIFT 0
-#define I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_SHIFT)
-#define I40E_GLPES_TCPRXTWOHOLEHI 0x0001E034 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_SHIFT 0
-#define I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_SHIFT)
-#define I40E_GLPES_TCPRXTWOHOLELO 0x0001E030 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_SHIFT 0
-#define I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_SHIFT)
-#define I40E_GLPES_TCPTXRETRANSFASTHI 0x0001E04C /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_SHIFT 0
-#define I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_SHIFT)
-#define I40E_GLPES_TCPTXRETRANSFASTLO 0x0001E048 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_SHIFT 0
-#define I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_SHIFT)
-#define I40E_GLPES_TCPTXTOUTSFASTHI 0x0001E054 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_SHIFT 0
-#define I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_SHIFT)
-#define I40E_GLPES_TCPTXTOUTSFASTLO 0x0001E050 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_SHIFT 0
-#define I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_SHIFT)
-#define I40E_GLPES_TCPTXTOUTSHI 0x0001E05C /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_SHIFT 0
-#define I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_SHIFT)
-#define I40E_GLPES_TCPTXTOUTSLO 0x0001E058 /* Reset: PE_CORER */
-#define I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_SHIFT 0
-#define I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXDISCARD(_i) (0x00018600 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXDISCARD_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_SHIFT 0
-#define I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_SHIFT)
-#define I40E_GLPES_VFIP4RXFRAGSHI(_i) (0x00018804 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXFRAGSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT 0
-#define I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT)
-#define I40E_GLPES_VFIP4RXFRAGSLO(_i) (0x00018800 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXFRAGSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT 0
-#define I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXMCOCTSHI(_i) (0x00018A04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXMCOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP4RXMCOCTSLO(_i) (0x00018A00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXMCOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXMCPKTSHI(_i) (0x00018C04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXMCPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP4RXMCPKTSLO(_i) (0x00018C00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXMCPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXOCTSHI(_i) (0x00018204 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP4RXOCTSLO(_i) (0x00018200 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXPKTSHI(_i) (0x00018404 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP4RXPKTSLO(_i) (0x00018400 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP4RXTRUNC(_i) (0x00018700 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4RXTRUNC_MAX_INDEX 31
-#define I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_SHIFT 0
-#define I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_SHIFT)
-#define I40E_GLPES_VFIP4TXFRAGSHI(_i) (0x00019E04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXFRAGSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT 0
-#define I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT)
-#define I40E_GLPES_VFIP4TXFRAGSLO(_i) (0x00019E00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXFRAGSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT 0
-#define I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT)
-#define I40E_GLPES_VFIP4TXMCOCTSHI(_i) (0x0001A004 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXMCOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP4TXMCOCTSLO(_i) (0x0001A000 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXMCOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP4TXMCPKTSHI(_i) (0x0001A204 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXMCPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP4TXMCPKTSLO(_i) (0x0001A200 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXMCPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP4TXNOROUTE(_i) (0x0001AE00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXNOROUTE_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT 0
-#define I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT)
-#define I40E_GLPES_VFIP4TXOCTSHI(_i) (0x00019A04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP4TXOCTSLO(_i) (0x00019A00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP4TXPKTSHI(_i) (0x00019C04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP4TXPKTSLO(_i) (0x00019C00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP4TXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXDISCARD(_i) (0x00019200 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXDISCARD_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_SHIFT 0
-#define I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_SHIFT)
-#define I40E_GLPES_VFIP6RXFRAGSHI(_i) (0x00019404 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXFRAGSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT 0
-#define I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT)
-#define I40E_GLPES_VFIP6RXFRAGSLO(_i) (0x00019400 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXFRAGSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT 0
-#define I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXMCOCTSHI(_i) (0x00019604 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXMCOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP6RXMCOCTSLO(_i) (0x00019600 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXMCOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXMCPKTSHI(_i) (0x00019804 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXMCPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP6RXMCPKTSLO(_i) (0x00019800 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXMCPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXOCTSHI(_i) (0x00018E04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP6RXOCTSLO(_i) (0x00018E00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXPKTSHI(_i) (0x00019004 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP6RXPKTSLO(_i) (0x00019000 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP6RXTRUNC(_i) (0x00019300 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6RXTRUNC_MAX_INDEX 31
-#define I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_SHIFT 0
-#define I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_SHIFT)
-#define I40E_GLPES_VFIP6TXFRAGSHI(_i) (0x0001A804 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXFRAGSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT 0
-#define I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT)
-#define I40E_GLPES_VFIP6TXFRAGSLO(_i) (0x0001A800 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXFRAGSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT 0
-#define I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT)
-#define I40E_GLPES_VFIP6TXMCOCTSHI(_i) (0x0001AA04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXMCOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP6TXMCOCTSLO(_i) (0x0001AA00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXMCOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP6TXMCPKTSHI(_i) (0x0001AC04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXMCPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP6TXMCPKTSLO(_i) (0x0001AC00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXMCPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT)
-#define I40E_GLPES_VFIP6TXNOROUTE(_i) (0x0001AF00 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXNOROUTE_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT 0
-#define I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT)
-#define I40E_GLPES_VFIP6TXOCTSHI(_i) (0x0001A404 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXOCTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT)
-#define I40E_GLPES_VFIP6TXOCTSLO(_i) (0x0001A400 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXOCTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT)
-#define I40E_GLPES_VFIP6TXPKTSHI(_i) (0x0001A604 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT)
-#define I40E_GLPES_VFIP6TXPKTSLO(_i) (0x0001A600 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFIP6TXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT)
-#define I40E_GLPES_VFRDMARXRDSHI(_i) (0x0001BE04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXRDSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_SHIFT 0
-#define I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_SHIFT)
-#define I40E_GLPES_VFRDMARXRDSLO(_i) (0x0001BE00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXRDSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_SHIFT 0
-#define I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_SHIFT)
-#define I40E_GLPES_VFRDMARXSNDSHI(_i) (0x0001C004 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXSNDSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT 0
-#define I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT)
-#define I40E_GLPES_VFRDMARXSNDSLO(_i) (0x0001C000 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXSNDSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT 0
-#define I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT)
-#define I40E_GLPES_VFRDMARXWRSHI(_i) (0x0001BC04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXWRSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_SHIFT 0
-#define I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_SHIFT)
-#define I40E_GLPES_VFRDMARXWRSLO(_i) (0x0001BC00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMARXWRSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_SHIFT 0
-#define I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_SHIFT)
-#define I40E_GLPES_VFRDMATXRDSHI(_i) (0x0001C404 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXRDSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_SHIFT 0
-#define I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_SHIFT)
-#define I40E_GLPES_VFRDMATXRDSLO(_i) (0x0001C400 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXRDSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_SHIFT 0
-#define I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_SHIFT)
-#define I40E_GLPES_VFRDMATXSNDSHI(_i) (0x0001C604 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXSNDSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT 0
-#define I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT)
-#define I40E_GLPES_VFRDMATXSNDSLO(_i) (0x0001C600 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXSNDSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT 0
-#define I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT)
-#define I40E_GLPES_VFRDMATXWRSHI(_i) (0x0001C204 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXWRSHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_SHIFT 0
-#define I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_SHIFT)
-#define I40E_GLPES_VFRDMATXWRSLO(_i) (0x0001C200 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMATXWRSLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_SHIFT 0
-#define I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_SHIFT)
-#define I40E_GLPES_VFRDMAVBNDHI(_i) (0x0001C804 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMAVBNDHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_SHIFT 0
-#define I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_SHIFT)
-#define I40E_GLPES_VFRDMAVBNDLO(_i) (0x0001C800 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMAVBNDLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_SHIFT 0
-#define I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_SHIFT)
-#define I40E_GLPES_VFRDMAVINVHI(_i) (0x0001CA04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMAVINVHI_MAX_INDEX 31
-#define I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_SHIFT 0
-#define I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_SHIFT)
-#define I40E_GLPES_VFRDMAVINVLO(_i) (0x0001CA00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRDMAVINVLO_MAX_INDEX 31
-#define I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_SHIFT 0
-#define I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_SHIFT)
-#define I40E_GLPES_VFRXVLANERR(_i) (0x00018000 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFRXVLANERR_MAX_INDEX 31
-#define I40E_GLPES_VFRXVLANERR_RXVLANERR_SHIFT 0
-#define I40E_GLPES_VFRXVLANERR_RXVLANERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_VFRXVLANERR_RXVLANERR_SHIFT)
-#define I40E_GLPES_VFTCPRTXSEG(_i) (0x0001B600 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPRTXSEG_MAX_INDEX 31
-#define I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_SHIFT 0
-#define I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_SHIFT)
-#define I40E_GLPES_VFTCPRXOPTERR(_i) (0x0001B200 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPRXOPTERR_MAX_INDEX 31
-#define I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_SHIFT 0
-#define I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_SHIFT)
-#define I40E_GLPES_VFTCPRXPROTOERR(_i) (0x0001B300 + ((_i) * 4)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPRXPROTOERR_MAX_INDEX 31
-#define I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT 0
-#define I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_MASK I40E_MASK(0xFFFFFF, I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT)
-#define I40E_GLPES_VFTCPRXSEGSHI(_i) (0x0001B004 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPRXSEGSHI_MAX_INDEX 31
-#define I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT 0
-#define I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT)
-#define I40E_GLPES_VFTCPRXSEGSLO(_i) (0x0001B000 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPRXSEGSLO_MAX_INDEX 31
-#define I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT 0
-#define I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT)
-#define I40E_GLPES_VFTCPTXSEGHI(_i) (0x0001B404 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPTXSEGHI_MAX_INDEX 31
-#define I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_SHIFT 0
-#define I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_SHIFT)
-#define I40E_GLPES_VFTCPTXSEGLO(_i) (0x0001B400 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFTCPTXSEGLO_MAX_INDEX 31
-#define I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_SHIFT 0
-#define I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_SHIFT)
-#define I40E_GLPES_VFUDPRXPKTSHI(_i) (0x0001B804 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFUDPRXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT)
-#define I40E_GLPES_VFUDPRXPKTSLO(_i) (0x0001B800 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFUDPRXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT)
-#define I40E_GLPES_VFUDPTXPKTSHI(_i) (0x0001BA04 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFUDPTXPKTSHI_MAX_INDEX 31
-#define I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT 0
-#define I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_MASK I40E_MASK(0xFFFF, I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT)
-#define I40E_GLPES_VFUDPTXPKTSLO(_i) (0x0001BA00 + ((_i) * 8)) /* _i=0...31 */ /* Reset: PE_CORER */
-#define I40E_GLPES_VFUDPTXPKTSLO_MAX_INDEX 31
-#define I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT 0
-#define I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_MASK I40E_MASK(0xFFFFFFFF, I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT)
-#define I40E_GLGEN_PME_TO 0x000B81BC /* Reset: POR */
-#define I40E_GLGEN_PME_TO_PME_TO_FOR_PE_SHIFT 0
-#define I40E_GLGEN_PME_TO_PME_TO_FOR_PE_MASK I40E_MASK(0x1, I40E_GLGEN_PME_TO_PME_TO_FOR_PE_SHIFT)
-#define I40E_GLQF_APBVT(_i) (0x00260000 + ((_i) * 4)) /* _i=0...2047 */ /* Reset: CORER */
-#define I40E_GLQF_APBVT_MAX_INDEX 2047
-#define I40E_GLQF_APBVT_APBVT_SHIFT 0
-#define I40E_GLQF_APBVT_APBVT_MASK I40E_MASK(0xFFFFFFFF, I40E_GLQF_APBVT_APBVT_SHIFT)
-#define I40E_GLQF_FD_PCTYPES(_i) (0x00268000 + ((_i) * 4)) /* _i=0...63 */ /* Reset: POR */
-#define I40E_GLQF_FD_PCTYPES_MAX_INDEX 63
-#define I40E_GLQF_FD_PCTYPES_FD_PCTYPE_SHIFT 0
-#define I40E_GLQF_FD_PCTYPES_FD_PCTYPE_MASK I40E_MASK(0x3F, I40E_GLQF_FD_PCTYPES_FD_PCTYPE_SHIFT)
-#define I40E_GLQF_FD_MSK(_i, _j) (0x00267200 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_FD_MSK_MAX_INDEX 1
-#define I40E_GLQF_FD_MSK_MASK_SHIFT 0
-#define I40E_GLQF_FD_MSK_MASK_MASK I40E_MASK(0xFFFF, I40E_GLQF_FD_MSK_MASK_SHIFT)
-#define I40E_GLQF_FD_MSK_OFFSET_SHIFT 16
-#define I40E_GLQF_FD_MSK_OFFSET_MASK I40E_MASK(0x3F, I40E_GLQF_FD_MSK_OFFSET_SHIFT)
 #define I40E_GLQF_HASH_INSET(_i, _j) (0x00267600 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_HASH_INSET_MAX_INDEX 1
-#define I40E_GLQF_HASH_INSET_INSET_SHIFT 0
-#define I40E_GLQF_HASH_INSET_INSET_MASK I40E_MASK(0xFFFFFFFF, I40E_GLQF_HASH_INSET_INSET_SHIFT)
-#define I40E_GLQF_HASH_MSK(_i, _j) (0x00267A00 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_HASH_MSK_MAX_INDEX 1
-#define I40E_GLQF_HASH_MSK_MASK_SHIFT 0
-#define I40E_GLQF_HASH_MSK_MASK_MASK I40E_MASK(0xFFFF, I40E_GLQF_HASH_MSK_MASK_SHIFT)
-#define I40E_GLQF_HASH_MSK_OFFSET_SHIFT 16
-#define I40E_GLQF_HASH_MSK_OFFSET_MASK I40E_MASK(0x3F, I40E_GLQF_HASH_MSK_OFFSET_SHIFT)
 #define I40E_GLQF_ORT(_i) (0x00268900 + ((_i) * 4)) /* _i=0...63 */ /* Reset: CORER */
-#define I40E_GLQF_ORT_MAX_INDEX 63
 #define I40E_GLQF_ORT_PIT_INDX_SHIFT 0
 #define I40E_GLQF_ORT_PIT_INDX_MASK I40E_MASK(0x1F, I40E_GLQF_ORT_PIT_INDX_SHIFT)
 #define I40E_GLQF_ORT_FIELD_CNT_SHIFT 5
 #define I40E_GLQF_ORT_FIELD_CNT_MASK I40E_MASK(0x3, I40E_GLQF_ORT_FIELD_CNT_SHIFT)
 #define I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT 7
 #define I40E_GLQF_ORT_FLX_PAYLOAD_MASK I40E_MASK(0x1, I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT)
-#define I40E_GLQF_PIT(_i) (0x00268C80 + ((_i) * 4)) /* _i=0...23 */ /* Reset: CORER */
-#define I40E_GLQF_PIT_MAX_INDEX 23
-#define I40E_GLQF_PIT_SOURCE_OFF_SHIFT 0
-#define I40E_GLQF_PIT_SOURCE_OFF_MASK I40E_MASK(0x1F, I40E_GLQF_PIT_SOURCE_OFF_SHIFT)
-#define I40E_GLQF_PIT_FSIZE_SHIFT 5
-#define I40E_GLQF_PIT_FSIZE_MASK I40E_MASK(0x1F, I40E_GLQF_PIT_FSIZE_SHIFT)
-#define I40E_GLQF_PIT_DEST_OFF_SHIFT 10
-#define I40E_GLQF_PIT_DEST_OFF_MASK I40E_MASK(0x3F, I40E_GLQF_PIT_DEST_OFF_SHIFT)
 #define I40E_GLQF_FDEVICTENA(_i) (0x00270384 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
-#define I40E_GLQF_FDEVICTENA_MAX_INDEX 1
-#define I40E_GLQF_FDEVICTENA_GLQF_FDEVICTENA_SHIFT 0
-#define I40E_GLQF_FDEVICTENA_GLQF_FDEVICTENA_MASK I40E_MASK(0xFFFFFFFF, I40E_GLQF_FDEVICTENA_GLQF_FDEVICTENA_SHIFT)
-#define I40E_GLQF_FDEVICTFLAG 0x00270280 /* Reset: CORER */
-#define I40E_GLQF_FDEVICTFLAG_TX_FLAGS_SHIFT 0
-#define I40E_GLQF_FDEVICTFLAG_TX_FLAGS_MASK I40E_MASK(0xFF, I40E_GLQF_FDEVICTFLAG_TX_FLAGS_SHIFT)
-#define I40E_GLQF_FDEVICTFLAG_RX_FLAGS_SHIFT 8
-#define I40E_GLQF_FDEVICTFLAG_RX_FLAGS_MASK I40E_MASK(0xFF, I40E_GLQF_FDEVICTFLAG_RX_FLAGS_SHIFT)
-#define I40E_PFQF_CTL_2 0x00270300 /* Reset: CORER */
-#define I40E_PFQF_CTL_2_PEHSIZE_SHIFT 0
-#define I40E_PFQF_CTL_2_PEHSIZE_MASK I40E_MASK(0x1F, I40E_PFQF_CTL_2_PEHSIZE_SHIFT)
-#define I40E_PFQF_CTL_2_PEDSIZE_SHIFT 5
-#define I40E_PFQF_CTL_2_PEDSIZE_MASK I40E_MASK(0x1F, I40E_PFQF_CTL_2_PEDSIZE_SHIFT)
 /* Redefined for X722 family */
-#define I40E_X722_PFQF_HLUT(_i) (0x00240000 + ((_i) * 128)) /* _i=0...127 */ /* Reset: CORER */
-#define I40E_X722_PFQF_HLUT_MAX_INDEX 127
-#define I40E_X722_PFQF_HLUT_LUT0_SHIFT 0
-#define I40E_X722_PFQF_HLUT_LUT0_MASK I40E_MASK(0x7F, I40E_X722_PFQF_HLUT_LUT0_SHIFT)
-#define I40E_X722_PFQF_HLUT_LUT1_SHIFT 8
-#define I40E_X722_PFQF_HLUT_LUT1_MASK I40E_MASK(0x7F, I40E_X722_PFQF_HLUT_LUT1_SHIFT)
-#define I40E_X722_PFQF_HLUT_LUT2_SHIFT 16
-#define I40E_X722_PFQF_HLUT_LUT2_MASK I40E_MASK(0x7F, I40E_X722_PFQF_HLUT_LUT2_SHIFT)
-#define I40E_X722_PFQF_HLUT_LUT3_SHIFT 24
-#define I40E_X722_PFQF_HLUT_LUT3_MASK I40E_MASK(0x7F, I40E_X722_PFQF_HLUT_LUT3_SHIFT)
-#define I40E_PFQF_HREGION(_i) (0x00245400 + ((_i) * 128)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_PFQF_HREGION_MAX_INDEX 7
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_0_SHIFT)
-#define I40E_PFQF_HREGION_REGION_0_SHIFT 1
-#define I40E_PFQF_HREGION_REGION_0_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_0_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_1_SHIFT)
-#define I40E_PFQF_HREGION_REGION_1_SHIFT 5
-#define I40E_PFQF_HREGION_REGION_1_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_1_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_2_SHIFT)
-#define I40E_PFQF_HREGION_REGION_2_SHIFT 9
-#define I40E_PFQF_HREGION_REGION_2_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_2_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_3_SHIFT)
-#define I40E_PFQF_HREGION_REGION_3_SHIFT 13
-#define I40E_PFQF_HREGION_REGION_3_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_3_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_4_SHIFT)
-#define I40E_PFQF_HREGION_REGION_4_SHIFT 17
-#define I40E_PFQF_HREGION_REGION_4_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_4_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_5_SHIFT)
-#define I40E_PFQF_HREGION_REGION_5_SHIFT 21
-#define I40E_PFQF_HREGION_REGION_5_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_5_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_6_SHIFT)
-#define I40E_PFQF_HREGION_REGION_6_SHIFT 25
-#define I40E_PFQF_HREGION_REGION_6_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_6_SHIFT)
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28
-#define I40E_PFQF_HREGION_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_PFQF_HREGION_OVERRIDE_ENA_7_SHIFT)
-#define I40E_PFQF_HREGION_REGION_7_SHIFT 29
-#define I40E_PFQF_HREGION_REGION_7_MASK I40E_MASK(0x7, I40E_PFQF_HREGION_REGION_7_SHIFT)
-#define I40E_VSIQF_CTL_RSS_LUT_TYPE_SHIFT 8
-#define I40E_VSIQF_CTL_RSS_LUT_TYPE_MASK I40E_MASK(0x1, I40E_VSIQF_CTL_RSS_LUT_TYPE_SHIFT)
-#define I40E_VSIQF_HKEY(_i, _VSI) (0x002A0000 + ((_i) * 2048 + (_VSI) * 4)) /* _i=0...12, _VSI=0...383 */ /* Reset: CORER */
-#define I40E_VSIQF_HKEY_MAX_INDEX 12
-#define I40E_VSIQF_HKEY_KEY_0_SHIFT 0
-#define I40E_VSIQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_VSIQF_HKEY_KEY_0_SHIFT)
-#define I40E_VSIQF_HKEY_KEY_1_SHIFT 8
-#define I40E_VSIQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_VSIQF_HKEY_KEY_1_SHIFT)
-#define I40E_VSIQF_HKEY_KEY_2_SHIFT 16
-#define I40E_VSIQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_VSIQF_HKEY_KEY_2_SHIFT)
-#define I40E_VSIQF_HKEY_KEY_3_SHIFT 24
-#define I40E_VSIQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_VSIQF_HKEY_KEY_3_SHIFT)
-#define I40E_VSIQF_HLUT(_i, _VSI) (0x00220000 + ((_i) * 2048 + (_VSI) * 4)) /* _i=0...15, _VSI=0...383 */ /* Reset: CORER */
-#define I40E_VSIQF_HLUT_MAX_INDEX 15
-#define I40E_VSIQF_HLUT_LUT0_SHIFT 0
-#define I40E_VSIQF_HLUT_LUT0_MASK I40E_MASK(0xF, I40E_VSIQF_HLUT_LUT0_SHIFT)
-#define I40E_VSIQF_HLUT_LUT1_SHIFT 8
-#define I40E_VSIQF_HLUT_LUT1_MASK I40E_MASK(0xF, I40E_VSIQF_HLUT_LUT1_SHIFT)
-#define I40E_VSIQF_HLUT_LUT2_SHIFT 16
-#define I40E_VSIQF_HLUT_LUT2_MASK I40E_MASK(0xF, I40E_VSIQF_HLUT_LUT2_SHIFT)
-#define I40E_VSIQF_HLUT_LUT3_SHIFT 24
-#define I40E_VSIQF_HLUT_LUT3_MASK I40E_MASK(0xF, I40E_VSIQF_HLUT_LUT3_SHIFT)
 #define I40E_GLGEN_STAT_CLEAR 0x00390004 /* Reset: CORER */
-#define I40E_GLGEN_STAT_CLEAR_GLGEN_STAT_CLEAR_SHIFT 0
-#define I40E_GLGEN_STAT_CLEAR_GLGEN_STAT_CLEAR_MASK I40E_MASK(0x1, I40E_GLGEN_STAT_CLEAR_GLGEN_STAT_CLEAR_SHIFT)
-#define I40E_GLGEN_STAT_HALT 0x00390000 /* Reset: CORER */
-#define I40E_GLGEN_STAT_HALT_HALT_CELLS_SHIFT 0
-#define I40E_GLGEN_STAT_HALT_HALT_CELLS_MASK I40E_MASK(0x3FFFFFFF, I40E_GLGEN_STAT_HALT_HALT_CELLS_SHIFT)
-#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT)
-#define I40E_VFPE_AEQALLOC1 0x0000A400 /* Reset: VFR */
-#define I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT 0
-#define I40E_VFPE_AEQALLOC1_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT)
-#define I40E_VFPE_CCQPHIGH1 0x00009800 /* Reset: VFR */
-#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT 0
-#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT)
-#define I40E_VFPE_CCQPLOW1 0x0000AC00 /* Reset: VFR */
-#define I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT 0
-#define I40E_VFPE_CCQPLOW1_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1 0x0000B800 /* Reset: VFR */
-#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT 0
-#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT 4
-#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT 16
-#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT 31
-#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT)
-#define I40E_VFPE_CQACK1 0x0000B000 /* Reset: VFR */
-#define I40E_VFPE_CQACK1_PECQID_SHIFT 0
-#define I40E_VFPE_CQACK1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQACK1_PECQID_SHIFT)
-#define I40E_VFPE_CQARM1 0x0000B400 /* Reset: VFR */
-#define I40E_VFPE_CQARM1_PECQID_SHIFT 0
-#define I40E_VFPE_CQARM1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQARM1_PECQID_SHIFT)
-#define I40E_VFPE_CQPDB1 0x0000BC00 /* Reset: VFR */
-#define I40E_VFPE_CQPDB1_WQHEAD_SHIFT 0
-#define I40E_VFPE_CQPDB1_WQHEAD_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPDB1_WQHEAD_SHIFT)
-#define I40E_VFPE_CQPERRCODES1 0x00009C00 /* Reset: VFR */
-#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT 0
-#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT)
-#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT 16
-#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT)
-#define I40E_VFPE_CQPTAIL1 0x0000A000 /* Reset: VFR */
-#define I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT 0
-#define I40E_VFPE_CQPTAIL1_WQTAIL_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT)
-#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT 31
-#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT)
-#define I40E_VFPE_IPCONFIG01 0x00008C00 /* Reset: VFR */
-#define I40E_VFPE_IPCONFIG01_PEIPID_SHIFT 0
-#define I40E_VFPE_IPCONFIG01_PEIPID_MASK I40E_MASK(0xFFFF, I40E_VFPE_IPCONFIG01_PEIPID_SHIFT)
-#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT 16
-#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT)
-#define I40E_VFPE_MRTEIDXMASK1 0x00009000 /* Reset: VFR */
-#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT 0
-#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT)
-#define I40E_VFPE_RCVUNEXPECTEDERROR1 0x00009400 /* Reset: VFR */
-#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT 0
-#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT)
-#define I40E_VFPE_TCPNOWTIMER1 0x0000A800 /* Reset: VFR */
-#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT 0
-#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT)
-#define I40E_VFPE_WQEALLOC1 0x0000C000 /* Reset: VFR */
-#define I40E_VFPE_WQEALLOC1_PEQPID_SHIFT 0
-#define I40E_VFPE_WQEALLOC1_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_VFPE_WQEALLOC1_PEQPID_SHIFT)
-#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT 20
-#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT)
 #endif /* _I40E_REGISTER_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 5c255977fd58..8d3c9d37e42e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -18,10 +18,7 @@
 #define I40E_ITR_DYNAMIC	0x8000	/* use top bit as a flag */
 #define I40E_ITR_MASK		0x1FFE	/* mask for ITR register value */
 #define I40E_MIN_ITR		     2	/* reg uses 2 usec resolution */
-#define I40E_ITR_100K		    10	/* all values below must be even */
-#define I40E_ITR_50K		    20
 #define I40E_ITR_20K		    50
-#define I40E_ITR_18K		    60
 #define I40E_ITR_8K		   122
 #define I40E_MAX_ITR		  8160	/* maximum value as per datasheet */
 #define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC)
@@ -52,9 +49,6 @@ static inline u16 i40e_intrl_usec_to_reg(int intrl)
 	else
 		return 0;
 }
-#define I40E_INTRL_8K              125     /* 8000 ints/sec */
-#define I40E_INTRL_62K             16      /* 62500 ints/sec */
-#define I40E_INTRL_83K             12      /* 83333 ints/sec */
 
 #define I40E_QUEUE_END_OF_LIST 0x7FF
 
@@ -73,7 +67,6 @@ enum i40e_dyn_idx_t {
 /* these are indexes into ITRN registers */
 #define I40E_RX_ITR    I40E_IDX_ITR0
 #define I40E_TX_ITR    I40E_IDX_ITR1
-#define I40E_PE_ITR    I40E_IDX_ITR2
 
 /* Supported RSS offloads */
 #define I40E_DEFAULT_RSS_HENA ( \
@@ -193,13 +186,6 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define I40E_RX_BUFFER_WRITE	32	/* Must be power of 2 */
-#define I40E_RX_INCREMENT(r, i) \
-	do {					\
-		(i)++;				\
-		if ((i) == (r)->count)		\
-			i = 0;			\
-		r->next_to_clean = i;		\
-	} while (0)
 
 #define I40E_RX_NEXT_DESC(r, i, n)		\
 	do {					\
@@ -209,11 +195,6 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 		(n) = I40E_RX_DESC((r), (i));	\
 	} while (0)
 
-#define I40E_RX_NEXT_DESC_PREFETCH(r, i, n)		\
-	do {						\
-		I40E_RX_NEXT_DESC((r), (i), (n));	\
-		prefetch((n));				\
-	} while (0)
 
 #define I40E_MAX_BUFFER_TXD	8
 #define I40E_MIN_TX_LEN		17
@@ -262,15 +243,12 @@ static inline unsigned int i40e_txd_use_count(unsigned int size)
 
 /* Tx Descriptors needed, worst case */
 #define DESC_NEEDED (MAX_SKB_FRAGS + 6)
-#define I40E_MIN_DESC_PENDING	4
 
 #define I40E_TX_FLAGS_HW_VLAN		BIT(1)
 #define I40E_TX_FLAGS_SW_VLAN		BIT(2)
 #define I40E_TX_FLAGS_TSO		BIT(3)
 #define I40E_TX_FLAGS_IPV4		BIT(4)
 #define I40E_TX_FLAGS_IPV6		BIT(5)
-#define I40E_TX_FLAGS_FCCRC		BIT(6)
-#define I40E_TX_FLAGS_FSO		BIT(7)
 #define I40E_TX_FLAGS_TSYN		BIT(8)
 #define I40E_TX_FLAGS_FD_SB		BIT(9)
 #define I40E_TX_FLAGS_UDP_TUNNEL	BIT(10)
@@ -332,9 +310,7 @@ enum i40e_ring_state_t {
 /* some useful defines for virtchannel interface, which
  * is the only remaining user of header split
  */
-#define I40E_RX_DTYPE_NO_SPLIT      0
 #define I40E_RX_DTYPE_HEADER_SPLIT  1
-#define I40E_RX_DTYPE_SPLIT_ALWAYS  2
 #define I40E_RX_SPLIT_L2      0x1
 #define I40E_RX_SPLIT_IP      0x2
 #define I40E_RX_SPLIT_TCP_UDP 0x4
@@ -444,7 +420,6 @@ static inline void set_ring_xdp(struct i40e_ring *ring)
 #define I40E_ITR_ADAPTIVE_MAX_USECS	0x007e
 #define I40E_ITR_ADAPTIVE_LATENCY	0x8000
 #define I40E_ITR_ADAPTIVE_BULK		0x0000
-#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY))
 
 struct i40e_ring_container {
 	struct i40e_ring *ring;		/* pointer to linked list of ring(s) */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 63e098f7cb63..52410d609ba1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -84,8 +84,6 @@ enum i40e_debug_mask {
 						  I40E_GLGEN_MSCA_OPCODE_SHIFT)
 #define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK	I40E_MASK(1, \
 						  I40E_GLGEN_MSCA_OPCODE_SHIFT)
-#define I40E_MDIO_CLAUSE45_OPCODE_READ_INC_ADDR_MASK	I40E_MASK(2, \
-						I40E_GLGEN_MSCA_OPCODE_SHIFT)
 #define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK	I40E_MASK(3, \
 						I40E_GLGEN_MSCA_OPCODE_SHIFT)
 
@@ -178,21 +176,9 @@ struct i40e_link_status {
 	u8 module_type[3];
 	/* 1st byte: module identifier */
 #define I40E_MODULE_TYPE_SFP		0x03
-#define I40E_MODULE_TYPE_QSFP		0x0D
-	/* 2nd byte: ethernet compliance codes for 10/40G */
-#define I40E_MODULE_TYPE_40G_ACTIVE	0x01
-#define I40E_MODULE_TYPE_40G_LR4	0x02
-#define I40E_MODULE_TYPE_40G_SR4	0x04
-#define I40E_MODULE_TYPE_40G_CR4	0x08
-#define I40E_MODULE_TYPE_10G_BASE_SR	0x10
-#define I40E_MODULE_TYPE_10G_BASE_LR	0x20
-#define I40E_MODULE_TYPE_10G_BASE_LRM	0x40
-#define I40E_MODULE_TYPE_10G_BASE_ER	0x80
 	/* 3rd byte: ethernet compliance codes for 1G */
 #define I40E_MODULE_TYPE_1000BASE_SX	0x01
 #define I40E_MODULE_TYPE_1000BASE_LX	0x02
-#define I40E_MODULE_TYPE_1000BASE_CX	0x04
-#define I40E_MODULE_TYPE_1000BASE_T	0x08
 };
 
 struct i40e_phy_info {
@@ -262,9 +248,6 @@ struct i40e_phy_info {
 /* Capabilities of a PF or a VF or the whole device */
 struct i40e_hw_capabilities {
 	u32  switch_mode;
-#define I40E_NVM_IMAGE_TYPE_EVB		0x0
-#define I40E_NVM_IMAGE_TYPE_CLOUD	0x2
-#define I40E_NVM_IMAGE_TYPE_UDP_CLOUD	0x3
 
 	/* Cloud filter modes:
 	 * Mode1: Filter on L4 port only
@@ -273,14 +256,10 @@ struct i40e_hw_capabilities {
 	 */
 #define I40E_CLOUD_FILTER_MODE1	0x6
 #define I40E_CLOUD_FILTER_MODE2	0x7
-#define I40E_CLOUD_FILTER_MODE3	0x8
 #define I40E_SWITCH_MODE_MASK	0xF
 
 	u32  management_mode;
 	u32  mng_protocols_over_mctp;
-#define I40E_MNG_PROTOCOL_PLDM		0x2
-#define I40E_MNG_PROTOCOL_OEM_COMMANDS	0x4
-#define I40E_MNG_PROTOCOL_NCSI		0x8
 	u32  npar_enable;
 	u32  os2bmc;
 	u32  valid_functions;
@@ -294,13 +273,8 @@ struct i40e_hw_capabilities {
 	bool flex10_enable;
 	bool flex10_capable;
 	u32  flex10_mode;
-#define I40E_FLEX10_MODE_UNKNOWN	0x0
-#define I40E_FLEX10_MODE_DCC		0x1
-#define I40E_FLEX10_MODE_DCI		0x2
 
 	u32 flex10_status;
-#define I40E_FLEX10_STATUS_DCC_ERROR	0x1
-#define I40E_FLEX10_STATUS_VC_MODE	0x2
 
 	bool sec_rev_disabled;
 	bool update_disabled;
@@ -421,11 +395,8 @@ enum i40e_nvmupd_state {
 #define I40E_NVM_AQE				0xe
 #define I40E_NVM_EXEC				0xf
 
-#define I40E_NVM_ADAPT_SHIFT	16
-#define I40E_NVM_ADAPT_MASK	(0xffff << I40E_NVM_ADAPT_SHIFT)
 
 #define I40E_NVMUPD_MAX_DATA	4096
-#define I40E_NVMUPD_IFACE_TIMEOUT 2 /* seconds */
 
 struct i40e_nvm_access {
 	u32 command;
@@ -438,7 +409,6 @@ struct i40e_nvm_access {
 /* (Q)SFP module access definitions */
 #define I40E_I2C_EEPROM_DEV_ADDR	0xA0
 #define I40E_I2C_EEPROM_DEV_ADDR2	0xA2
-#define I40E_MODULE_TYPE_ADDR		0x00
 #define I40E_MODULE_REVISION_ADDR	0x01
 #define I40E_MODULE_SFF_8472_COMP	0x5E
 #define I40E_MODULE_SFF_8472_SWAP	0x5C
@@ -547,7 +517,6 @@ struct i40e_dcbx_config {
 #define I40E_DCBX_MODE_CEE	0x1
 #define I40E_DCBX_MODE_IEEE	0x2
 	u8  app_mode;
-#define I40E_DCBX_APPS_NON_WILLING	0x1
 	u32 numapps;
 	u32 tlv_status; /* CEE mode TLV status */
 	struct i40e_dcb_ets_config etscfg;
@@ -895,9 +864,6 @@ enum i40e_rx_ptype_payload_layer {
 #define I40E_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
 					 I40E_RXD_QW1_LENGTH_PBUF_SHIFT)
 
-#define I40E_RXD_QW1_LENGTH_HBUF_SHIFT	52
-#define I40E_RXD_QW1_LENGTH_HBUF_MASK	(0x7FFULL << \
-					 I40E_RXD_QW1_LENGTH_HBUF_SHIFT)
 
 #define I40E_RXD_QW1_LENGTH_SPH_SHIFT	63
 #define I40E_RXD_QW1_LENGTH_SPH_MASK	BIT_ULL(I40E_RXD_QW1_LENGTH_SPH_SHIFT)
@@ -926,7 +892,6 @@ enum i40e_rx_desc_pe_status_bits {
 	I40E_RX_DESC_PE_STATUS_IPOPT_SHIFT	= 29
 };
 
-#define I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT		38
 #define I40E_RX_PROG_STATUS_DESC_LENGTH			0x2000000
 
 #define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT	2
@@ -963,8 +928,6 @@ struct i40e_tx_desc {
 	__le64 cmd_type_offset_bsz;
 };
 
-#define I40E_TXD_QW1_DTYPE_SHIFT	0
-#define I40E_TXD_QW1_DTYPE_MASK		(0xFUL << I40E_TXD_QW1_DTYPE_SHIFT)
 
 enum i40e_tx_desc_dtype_value {
 	I40E_TX_DESC_DTYPE_DATA		= 0x0,
@@ -980,7 +943,6 @@ enum i40e_tx_desc_dtype_value {
 };
 
 #define I40E_TXD_QW1_CMD_SHIFT	4
-#define I40E_TXD_QW1_CMD_MASK	(0x3FFUL << I40E_TXD_QW1_CMD_SHIFT)
 
 enum i40e_tx_desc_cmd_bits {
 	I40E_TX_DESC_CMD_EOP			= 0x0001,
@@ -1004,8 +966,6 @@ enum i40e_tx_desc_cmd_bits {
 };
 
 #define I40E_TXD_QW1_OFFSET_SHIFT	16
-#define I40E_TXD_QW1_OFFSET_MASK	(0x3FFFFULL << \
-					 I40E_TXD_QW1_OFFSET_SHIFT)
 
 enum i40e_tx_desc_length_fields {
 	/* Note: These are predefined bit offsets */
@@ -1015,11 +975,8 @@ enum i40e_tx_desc_length_fields {
 };
 
 #define I40E_TXD_QW1_TX_BUF_SZ_SHIFT	34
-#define I40E_TXD_QW1_TX_BUF_SZ_MASK	(0x3FFFULL << \
-					 I40E_TXD_QW1_TX_BUF_SZ_SHIFT)
 
 #define I40E_TXD_QW1_L2TAG1_SHIFT	48
-#define I40E_TXD_QW1_L2TAG1_MASK	(0xFFFFULL << I40E_TXD_QW1_L2TAG1_SHIFT)
 
 /* Context descriptors */
 struct i40e_tx_context_desc {
@@ -1029,11 +986,8 @@ struct i40e_tx_context_desc {
 	__le64 type_cmd_tso_mss;
 };
 
-#define I40E_TXD_CTX_QW1_DTYPE_SHIFT	0
-#define I40E_TXD_CTX_QW1_DTYPE_MASK	(0xFUL << I40E_TXD_CTX_QW1_DTYPE_SHIFT)
 
 #define I40E_TXD_CTX_QW1_CMD_SHIFT	4
-#define I40E_TXD_CTX_QW1_CMD_MASK	(0xFFFFUL << I40E_TXD_CTX_QW1_CMD_SHIFT)
 
 enum i40e_tx_ctx_desc_cmd_bits {
 	I40E_TX_CTX_DESC_TSO		= 0x01,
@@ -1048,19 +1002,10 @@ enum i40e_tx_ctx_desc_cmd_bits {
 };
 
 #define I40E_TXD_CTX_QW1_TSO_LEN_SHIFT	30
-#define I40E_TXD_CTX_QW1_TSO_LEN_MASK	(0x3FFFFULL << \
-					 I40E_TXD_CTX_QW1_TSO_LEN_SHIFT)
 
 #define I40E_TXD_CTX_QW1_MSS_SHIFT	50
-#define I40E_TXD_CTX_QW1_MSS_MASK	(0x3FFFULL << \
-					 I40E_TXD_CTX_QW1_MSS_SHIFT)
 
-#define I40E_TXD_CTX_QW1_VSI_SHIFT	50
-#define I40E_TXD_CTX_QW1_VSI_MASK	(0x1FFULL << I40E_TXD_CTX_QW1_VSI_SHIFT)
 
-#define I40E_TXD_CTX_QW0_EXT_IP_SHIFT	0
-#define I40E_TXD_CTX_QW0_EXT_IP_MASK	(0x3ULL << \
-					 I40E_TXD_CTX_QW0_EXT_IP_SHIFT)
 
 enum i40e_tx_ctx_desc_eipt_offload {
 	I40E_TX_CTX_EXT_IP_NONE		= 0x0,
@@ -1070,28 +1015,16 @@ enum i40e_tx_ctx_desc_eipt_offload {
 };
 
 #define I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT	2
-#define I40E_TXD_CTX_QW0_EXT_IPLEN_MASK	(0x3FULL << \
-					 I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT)
 
 #define I40E_TXD_CTX_QW0_NATT_SHIFT	9
-#define I40E_TXD_CTX_QW0_NATT_MASK	(0x3ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
 
 #define I40E_TXD_CTX_UDP_TUNNELING	BIT_ULL(I40E_TXD_CTX_QW0_NATT_SHIFT)
 #define I40E_TXD_CTX_GRE_TUNNELING	(0x2ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
 
-#define I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT	11
-#define I40E_TXD_CTX_QW0_EIP_NOINC_MASK \
-				       BIT_ULL(I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT)
 
-#define I40E_TXD_CTX_EIP_NOINC_IPID_CONST	I40E_TXD_CTX_QW0_EIP_NOINC_MASK
 
 #define I40E_TXD_CTX_QW0_NATLEN_SHIFT	12
-#define I40E_TXD_CTX_QW0_NATLEN_MASK	(0X7FULL << \
-					 I40E_TXD_CTX_QW0_NATLEN_SHIFT)
 
-#define I40E_TXD_CTX_QW0_DECTTL_SHIFT	19
-#define I40E_TXD_CTX_QW0_DECTTL_MASK	(0xFULL << \
-					 I40E_TXD_CTX_QW0_DECTTL_SHIFT)
 
 #define I40E_TXD_CTX_QW0_L4T_CS_SHIFT	23
 #define I40E_TXD_CTX_QW0_L4T_CS_MASK	BIT_ULL(I40E_TXD_CTX_QW0_L4T_CS_SHIFT)
@@ -1161,11 +1094,8 @@ enum i40e_filter_program_desc_fd_status {
 					 I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
 
 #define I40E_TXD_FLTR_QW1_CMD_SHIFT	4
-#define I40E_TXD_FLTR_QW1_CMD_MASK	(0xFFFFULL << \
-					 I40E_TXD_FLTR_QW1_CMD_SHIFT)
 
 #define I40E_TXD_FLTR_QW1_PCMD_SHIFT	(0x0ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
-#define I40E_TXD_FLTR_QW1_PCMD_MASK	(0x7ULL << I40E_TXD_FLTR_QW1_PCMD_SHIFT)
 
 enum i40e_filter_program_desc_pcmd {
 	I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE	= 0x1,
@@ -1316,7 +1246,6 @@ struct i40e_hw_port_stats {
 #define I40E_NVM_OEM_VER_OFF			0x83
 #define I40E_SR_NVM_DEV_STARTER_VERSION		0x18
 #define I40E_SR_NVM_WAKE_ON_LAN			0x19
-#define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR	0x27
 #define I40E_SR_NVM_EETRACK_LO			0x2D
 #define I40E_SR_NVM_EETRACK_HI			0x2E
 #define I40E_SR_VPD_PTR				0x2F
@@ -1329,7 +1258,6 @@ struct i40e_hw_port_stats {
 #define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE	1024
 #define I40E_SR_CONTROL_WORD_1_SHIFT		0x06
 #define I40E_SR_CONTROL_WORD_1_MASK	(0x03 << I40E_SR_CONTROL_WORD_1_SHIFT)
-#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID	BIT(5)
 #define I40E_SR_NVM_MAP_STRUCTURE_TYPE		BIT(12)
 #define I40E_PTR_TYPE				BIT(15)
 #define I40E_SR_OCP_CFG_WORD0			0x2B
@@ -1463,14 +1391,11 @@ struct i40e_lldp_variables {
 /* Offsets into Alternate Ram */
 #define I40E_ALT_STRUCT_FIRST_PF_OFFSET		0   /* in dwords */
 #define I40E_ALT_STRUCT_DWORDS_PER_PF		64   /* in dwords */
-#define I40E_ALT_STRUCT_OUTER_VLAN_TAG_OFFSET	0xD  /* in dwords */
-#define I40E_ALT_STRUCT_USER_PRIORITY_OFFSET	0xC  /* in dwords */
 #define I40E_ALT_STRUCT_MIN_BW_OFFSET		0xE  /* in dwords */
 #define I40E_ALT_STRUCT_MAX_BW_OFFSET		0xF  /* in dwords */
 
 /* Alternate Ram Bandwidth Masks */
 #define I40E_ALT_BW_VALUE_MASK		0xFF
-#define I40E_ALT_BW_RELATIVE_MASK	0x40000000
 #define I40E_ALT_BW_VALID_MASK		0x80000000
 
 /* RSS Hash Table Size */
@@ -1529,9 +1454,7 @@ struct i40e_package_header {
 /* Generic segment header */
 struct i40e_generic_seg_header {
 #define SEGMENT_TYPE_METADATA	0x00000001
-#define SEGMENT_TYPE_NOTES	0x00000002
 #define SEGMENT_TYPE_I40E	0x00000011
-#define SEGMENT_TYPE_X722	0x00000012
 	u32 type;
 	struct i40e_ddp_version version;
 	u32 size;
@@ -1541,7 +1464,6 @@ struct i40e_generic_seg_header {
 struct i40e_metadata_segment {
 	struct i40e_generic_seg_header header;
 	struct i40e_ddp_version version;
-#define I40E_DDP_TRACKID_RDONLY		0
 #define I40E_DDP_TRACKID_INVALID	0xFFFFFFFF
 	u32 track_id;
 	char name[I40E_DDP_NAME_SIZE];
@@ -1575,10 +1497,6 @@ struct i40e_profile_section_header {
 #define SECTION_TYPE_AQ		0x00000801
 #define SECTION_TYPE_RB_AQ	0x00001801
 #define SECTION_TYPE_NOTE	0x80000000
-#define SECTION_TYPE_NAME	0x80000001
-#define SECTION_TYPE_PROTO	0x80000002
-#define SECTION_TYPE_PCTYPE	0x80000003
-#define SECTION_TYPE_PTYPE	0x80000004
 		u32 type;
 		u32 offset;
 		u32 size;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 631248c0981a..5491215d81de 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -10,7 +10,6 @@
 
 #define I40E_VIRTCHNL_SUPPORTED_QTYPES 2
 
-#define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED	3
 #define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED	10
 
 #define I40E_VLAN_PRIORITY_SHIFT	13
diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
index 72994baf4941..f41387a8969f 100644
--- a/include/linux/net/intel/i40e_client.h
+++ b/include/linux/net/intel/i40e_client.h
@@ -37,11 +37,6 @@ enum i40e_client_instance_state {
 struct i40e_ops;
 struct i40e_client;
 
-/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
- * In order for us to keep the interface simple, SW will define a
- * unique type value for AEQ.
- */
-#define I40E_QUEUE_TYPE_PE_AEQ  0x80
 #define I40E_QUEUE_INVALID_IDX	0xFFFF
 
 struct i40e_qv_info {
@@ -56,7 +51,6 @@ struct i40e_qvlist_info {
 	struct i40e_qv_info qv_info[1];
 };
 
-#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
 
 /* set of LAN parameters useful for clients managed by LAN */
 
@@ -87,7 +81,6 @@ struct i40e_info {
 	u8 __iomem *hw_addr;
 	u8 fid;	/* function id, PF id or VF id */
 #define I40E_CLIENT_FTYPE_PF 0
-#define I40E_CLIENT_FTYPE_VF 1
 	u8 ftype; /* function type, PF or VF */
 	void *pf;
 
@@ -184,8 +177,6 @@ struct i40e_client {
 	unsigned long state;		/* client state */
 	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
 	u32 flags;
-#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
-#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
 	u8 type;
 #define I40E_CLIENT_IWARP 0
 	const struct i40e_client_ops *ops; /* client ops provided by the client */
-- 
cgit v1.2.3


From 33d226f504ed72cba3a2b42bbe2a993b3d6d9548 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 02:25:06 +0200
Subject: mtd: nand: Move nand_device forward declaration to the top

This structure might be used earlier in this file, let's move the
forward declaration at the top.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529002517.3546-10-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 0c7483843a32..a1f38c778d0e 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -12,6 +12,8 @@
 
 #include <linux/mtd/mtd.h>
 
+struct nand_device;
+
 /**
  * struct nand_memory_organization - Memory organization structure
  * @bits_per_cell: number of bits per NAND cell
@@ -133,8 +135,6 @@ struct nand_bbt {
 	unsigned long *cache;
 };
 
-struct nand_device;
-
 /**
  * struct nand_ops - NAND operations
  * @erase: erase a specific block. No need to check if the block is bad before
-- 
cgit v1.2.3


From 85f54c5588885cc3b5be4a07498dd0755de9f5cf Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 02:25:10 +0200
Subject: mtd: nand: Rename a core structure

Prepare the migration to a generic ECC engine by renaming the
nand_ecc_req structure into nand_ecc_props. This structure will be the
base of a wider 'nand_ecc' structure.

In nand_device, these properties are still named "eccreq" even if
"eccprops" might be more descriptive. This is just a transition step,
this field is being replaced very soon by a much wider structure. The
impact of renaming this field would be huge compared to its interest.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529002517.3546-14-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h    | 8 ++++----
 include/linux/mtd/spinand.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index a1f38c778d0e..af99041ceaa9 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -116,11 +116,11 @@ struct nand_page_io_req {
 };
 
 /**
- * struct nand_ecc_req - NAND ECC requirements
+ * struct nand_ecc_props - NAND ECC properties
  * @strength: ECC strength
- * @step_size: ECC step/block size
+ * @step_size: Number of bytes per step
  */
-struct nand_ecc_req {
+struct nand_ecc_props {
 	unsigned int strength;
 	unsigned int step_size;
 };
@@ -179,7 +179,7 @@ struct nand_ops {
 struct nand_device {
 	struct mtd_info mtd;
 	struct nand_memory_organization memorg;
-	struct nand_ecc_req eccreq;
+	struct nand_ecc_props eccreq;
 	struct nand_row_converter rowconv;
 	struct nand_bbt bbt;
 	const struct nand_ops *ops;
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 1077c45721ff..7b78c4ba9b3e 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -309,7 +309,7 @@ struct spinand_info {
 	struct spinand_devid devid;
 	u32 flags;
 	struct nand_memory_organization memorg;
-	struct nand_ecc_req eccreq;
+	struct nand_ecc_props eccreq;
 	struct spinand_ecc_info eccinfo;
 	struct {
 		const struct spinand_op_variants *read_cache;
-- 
cgit v1.2.3


From c4cabc08d09e4b107b685e08bdec8a38a91089d8 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:12:55 +0200
Subject: mtd: rawnand: Use unsigned types for nand_chip unsigned values

page_shift, phys_erase_shift, bbt_erase_shift, chip_shift, pagemask,
subpagesize and badblockbits are all positive values, so declare
them as unsigned.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-2-miquel.raynal@bootlin.com
---
 include/linux/mtd/rawnand.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 65b1c1c18b41..830f2d08937f 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1110,11 +1110,11 @@ struct nand_chip {
 	unsigned int options;
 	unsigned int bbt_options;
 
-	int page_shift;
-	int phys_erase_shift;
-	int bbt_erase_shift;
-	int chip_shift;
-	int pagemask;
+	unsigned int page_shift;
+	unsigned int phys_erase_shift;
+	unsigned int bbt_erase_shift;
+	unsigned int chip_shift;
+	unsigned int pagemask;
 	u8 *data_buf;
 
 	struct {
@@ -1122,10 +1122,10 @@ struct nand_chip {
 		int page;
 	} pagecache;
 
-	int subpagesize;
+	unsigned int subpagesize;
 	int onfi_timing_mode_default;
 	unsigned int badblockpos;
-	int badblockbits;
+	unsigned int badblockbits;
 
 	struct nand_id id;
 	struct nand_parameters parameters;
-- 
cgit v1.2.3


From d1f3837a507d73746f9e2118fad20ee5e57e86cc Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:12:56 +0200
Subject: mtd: rawnand: Only use u8 instead of uint8_t in nand_chip structure

Mechanical change to avoid using old types.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-3-miquel.raynal@bootlin.com
---
 include/linux/mtd/rawnand.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 830f2d08937f..cea137778224 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1141,13 +1141,13 @@ struct nand_chip {
 	int (*suspend)(struct nand_chip *chip);
 	void (*resume)(struct nand_chip *chip);
 
-	uint8_t *oob_poi;
+	u8 *oob_poi;
 	struct nand_controller *controller;
 
 	struct nand_ecc_ctrl ecc;
 	unsigned long buf_align;
 
-	uint8_t *bbt;
+	u8 *bbt;
 	struct nand_bbt_descr *bbt_td;
 	struct nand_bbt_descr *bbt_md;
 
-- 
cgit v1.2.3


From 8e8b2706e15d16443b1ea61a6f994c08ec5b9486 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:12:57 +0200
Subject: mtd: rawnand: Create a nand_chip operations structure

And move nand_chip hooks there.

While moving entries from one structure to the other, adapt the
documentation style.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-4-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c     | 20 ++++++++++----------
 drivers/mtd/nand/raw/nand_hynix.c    |  2 +-
 drivers/mtd/nand/raw/nand_macronix.c | 10 +++++-----
 drivers/mtd/nand/raw/nand_micron.c   |  2 +-
 include/linux/mtd/rawnand.h          | 32 ++++++++++++++++++--------------
 5 files changed, 35 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 45124dbb1835..d9cb71e7c0ed 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -3215,10 +3215,10 @@ static int nand_setup_read_retry(struct nand_chip *chip, int retry_mode)
 	if (retry_mode >= chip->read_retries)
 		return -EINVAL;
 
-	if (!chip->setup_read_retry)
+	if (!chip->ops.setup_read_retry)
 		return -EOPNOTSUPP;
 
-	return chip->setup_read_retry(chip, retry_mode);
+	return chip->ops.setup_read_retry(chip, retry_mode);
 }
 
 static void nand_wait_readrdy(struct nand_chip *chip)
@@ -4462,8 +4462,8 @@ static int nand_suspend(struct mtd_info *mtd)
 	int ret = 0;
 
 	mutex_lock(&chip->lock);
-	if (chip->suspend)
-		ret = chip->suspend(chip);
+	if (chip->ops.suspend)
+		ret = chip->ops.suspend(chip);
 	if (!ret)
 		chip->suspended = 1;
 	mutex_unlock(&chip->lock);
@@ -4481,8 +4481,8 @@ static void nand_resume(struct mtd_info *mtd)
 
 	mutex_lock(&chip->lock);
 	if (chip->suspended) {
-		if (chip->resume)
-			chip->resume(chip);
+		if (chip->ops.resume)
+			chip->ops.resume(chip);
 		chip->suspended = 0;
 	} else {
 		pr_err("%s called for a chip which is not in suspended state\n",
@@ -4511,10 +4511,10 @@ static int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if (!chip->lock_area)
+	if (!chip->ops.lock_area)
 		return -ENOTSUPP;
 
-	return chip->lock_area(chip, ofs, len);
+	return chip->ops.lock_area(chip, ofs, len);
 }
 
 /**
@@ -4527,10 +4527,10 @@ static int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if (!chip->unlock_area)
+	if (!chip->ops.unlock_area)
 		return -ENOTSUPP;
 
-	return chip->unlock_area(chip, ofs, len);
+	return chip->ops.unlock_area(chip, ofs, len);
 }
 
 /* Set default functions */
diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index 7caedaa5b9e5..7d1be53f27f3 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -337,7 +337,7 @@ static int hynix_mlc_1xnm_rr_init(struct nand_chip *chip,
 	rr->nregs = nregs;
 	rr->regs = hynix_1xnm_mlc_read_retry_regs;
 	hynix->read_retry = rr;
-	chip->setup_read_retry = hynix_nand_setup_read_retry;
+	chip->ops.setup_read_retry = hynix_nand_setup_read_retry;
 	chip->read_retries = nmodes;
 
 out:
diff --git a/drivers/mtd/nand/raw/nand_macronix.c b/drivers/mtd/nand/raw/nand_macronix.c
index 09c254c97b5c..1472f925f386 100644
--- a/drivers/mtd/nand/raw/nand_macronix.c
+++ b/drivers/mtd/nand/raw/nand_macronix.c
@@ -130,7 +130,7 @@ static void macronix_nand_onfi_init(struct nand_chip *chip)
 		return;
 
 	chip->read_retries = MACRONIX_NUM_READ_RETRY_MODES;
-	chip->setup_read_retry = macronix_nand_setup_read_retry;
+	chip->ops.setup_read_retry = macronix_nand_setup_read_retry;
 
 	if (p->supports_set_get_features) {
 		bitmap_set(p->set_feature_list,
@@ -242,8 +242,8 @@ static void macronix_nand_block_protection_support(struct nand_chip *chip)
 	bitmap_set(chip->parameters.set_feature_list,
 		   ONFI_FEATURE_ADDR_MXIC_PROTECTION, 1);
 
-	chip->lock_area = mxic_nand_lock;
-	chip->unlock_area = mxic_nand_unlock;
+	chip->ops.lock_area = mxic_nand_lock;
+	chip->ops.unlock_area = mxic_nand_unlock;
 }
 
 static int nand_power_down_op(struct nand_chip *chip)
@@ -312,8 +312,8 @@ static void macronix_nand_deep_power_down_support(struct nand_chip *chip)
 	if (i < 0)
 		return;
 
-	chip->suspend = mxic_nand_suspend;
-	chip->resume = mxic_nand_resume;
+	chip->ops.suspend = mxic_nand_suspend;
+	chip->ops.resume = mxic_nand_resume;
 }
 
 static int macronix_nand_init(struct nand_chip *chip)
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 3589b4fce0d4..4385092a9325 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -84,7 +84,7 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 		struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor;
 
 		chip->read_retries = micron->read_retry_options;
-		chip->setup_read_retry = micron_nand_setup_read_retry;
+		chip->ops.setup_read_retry = micron_nand_setup_read_retry;
 	}
 
 	if (p->supports_set_get_features) {
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index cea137778224..7f9be95ca8dc 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1027,16 +1027,31 @@ struct nand_legacy {
 	struct nand_controller dummy_controller;
 };
 
+/**
+ * struct nand_chip_ops - NAND chip operations
+ * @suspend: Suspend operation
+ * @resume: Resume operation
+ * @lock_area: Lock operation
+ * @unlock_area: Unlock operation
+ * @setup_read_retry: Set the read-retry mode (mostly needed for MLC NANDs)
+ */
+struct nand_chip_ops {
+	int (*suspend)(struct nand_chip *chip);
+	void (*resume)(struct nand_chip *chip);
+	int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
+	int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
+	int (*setup_read_retry)(struct nand_chip *chip, int retry_mode);
+};
+
 /**
  * struct nand_chip - NAND Private Flash Chip Data
  * @base:		Inherit from the generic NAND device
+ * @ops:		NAND chip operations
  * @legacy:		All legacy fields/hooks. If you develop a new driver,
  *			don't even try to use any of these fields/hooks, and if
  *			you're modifying an existing driver that is using those
  *			fields/hooks, you should consider reworking the driver
  *			avoid using them.
- * @setup_read_retry:	[FLASHSPECIFIC] flash (vendor) specific function for
- *			setting the read-retry mode. Mostly needed for MLC NAND.
  * @ecc:		[BOARDSPECIFIC] ECC control structure
  * @buf_align:		minimum buffer alignment required by a platform
  * @oob_poi:		"poison value buffer," used for laying out OOB data
@@ -1081,8 +1096,6 @@ struct nand_legacy {
  * @lock:		lock protecting the suspended field. Also used to
  *			serialize accesses to the NAND device.
  * @suspended:		set to 1 when the device is suspended, 0 when it's not.
- * @suspend:		[REPLACEABLE] specific NAND device suspend operation
- * @resume:		[REPLACEABLE] specific NAND device resume operation
  * @bbt:		[INTERN] bad block table pointer
  * @bbt_td:		[REPLACEABLE] bad block table descriptor for flash
  *			lookup.
@@ -1096,17 +1109,13 @@ struct nand_legacy {
  * @manufacturer:	[INTERN] Contains manufacturer information
  * @manufacturer.desc:	[INTERN] Contains manufacturer's description
  * @manufacturer.priv:	[INTERN] Contains manufacturer private information
- * @lock_area:		[REPLACEABLE] specific NAND chip lock operation
- * @unlock_area:	[REPLACEABLE] specific NAND chip unlock operation
  */
 
 struct nand_chip {
 	struct nand_device base;
-
+	struct nand_chip_ops ops;
 	struct nand_legacy legacy;
 
-	int (*setup_read_retry)(struct nand_chip *chip, int retry_mode);
-
 	unsigned int options;
 	unsigned int bbt_options;
 
@@ -1138,8 +1147,6 @@ struct nand_chip {
 
 	struct mutex lock;
 	unsigned int suspended : 1;
-	int (*suspend)(struct nand_chip *chip);
-	void (*resume)(struct nand_chip *chip);
 
 	u8 *oob_poi;
 	struct nand_controller *controller;
@@ -1159,9 +1166,6 @@ struct nand_chip {
 		const struct nand_manufacturer *desc;
 		void *priv;
 	} manufacturer;
-
-	int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
-	int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
 };
 
 extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
-- 
cgit v1.2.3


From 271de009b7c0c1c15f63491a352ab08835462977 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:12:58 +0200
Subject: mtd: rawnand: Rename the manufacturer structure

It is currently called nand_manufacturer but could actually be called
nand_manufacturer_desc, like its instances, so that the former name is
left unused for now.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-5-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/internals.h |  6 +++---
 drivers/mtd/nand/raw/nand_base.c | 14 +++++++-------
 drivers/mtd/nand/raw/nand_ids.c  | 16 ++++++++--------
 include/linux/mtd/rawnand.h      |  2 +-
 4 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h
index 03866b0aadea..a518acfd9b3f 100644
--- a/drivers/mtd/nand/raw/internals.h
+++ b/drivers/mtd/nand/raw/internals.h
@@ -53,12 +53,12 @@ struct nand_manufacturer_ops {
 };
 
 /**
- * struct nand_manufacturer - NAND Flash Manufacturer structure
+ * struct nand_manufacturer_desc - NAND Flash Manufacturer descriptor
  * @name: Manufacturer name
  * @id: manufacturer ID code of device.
  * @ops: manufacturer operations
  */
-struct nand_manufacturer {
+struct nand_manufacturer_desc {
 	int id;
 	char *name;
 	const struct nand_manufacturer_ops *ops;
@@ -79,7 +79,7 @@ extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops;
 extern const struct mtd_pairing_scheme dist3_pairing_scheme;
 
 /* Core functions */
-const struct nand_manufacturer *nand_get_manufacturer(u8 id);
+const struct nand_manufacturer_desc *nand_get_manufacturer_desc(u8 id);
 int nand_bbm_get_next_page(struct nand_chip *chip, int page);
 int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs);
 int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr,
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index d9cb71e7c0ed..534ee75d0f2b 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4810,9 +4810,9 @@ static void nand_manufacturer_cleanup(struct nand_chip *chip)
 }
 
 static const char *
-nand_manufacturer_name(const struct nand_manufacturer *manufacturer)
+nand_manufacturer_name(const struct nand_manufacturer_desc *manufacturer_desc)
 {
-	return manufacturer ? manufacturer->name : "Unknown";
+	return manufacturer_desc ? manufacturer_desc->name : "Unknown";
 }
 
 /*
@@ -4820,7 +4820,7 @@ nand_manufacturer_name(const struct nand_manufacturer *manufacturer)
  */
 static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 {
-	const struct nand_manufacturer *manufacturer;
+	const struct nand_manufacturer_desc *manufacturer_desc;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_memory_organization *memorg;
 	int busw, ret;
@@ -4877,8 +4877,8 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 	chip->id.len = nand_id_len(id_data, ARRAY_SIZE(chip->id.data));
 
 	/* Try to identify manufacturer */
-	manufacturer = nand_get_manufacturer(maf_id);
-	chip->manufacturer.desc = manufacturer;
+	manufacturer_desc = nand_get_manufacturer_desc(maf_id);
+	chip->manufacturer.desc = manufacturer_desc;
 
 	if (!type)
 		type = nand_flash_ids;
@@ -4957,7 +4957,7 @@ ident_done:
 		 */
 		pr_info("device found, Manufacturer ID: 0x%02x, Chip ID: 0x%02x\n",
 			maf_id, dev_id);
-		pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+		pr_info("%s %s\n", nand_manufacturer_name(manufacturer_desc),
 			mtd->name);
 		pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
 			(chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
@@ -4992,7 +4992,7 @@ ident_done:
 
 	pr_info("device found, Manufacturer ID: 0x%02x, Chip ID: 0x%02x\n",
 		maf_id, dev_id);
-	pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+	pr_info("%s %s\n", nand_manufacturer_name(manufacturer_desc),
 		chip->parameters.model);
 	pr_info("%d MiB, %s, erase size: %d KiB, page size: %d, OOB size: %d\n",
 		(int)(targetsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
diff --git a/drivers/mtd/nand/raw/nand_ids.c b/drivers/mtd/nand/raw/nand_ids.c
index ba27902fc54b..e0dbc2e316c7 100644
--- a/drivers/mtd/nand/raw/nand_ids.c
+++ b/drivers/mtd/nand/raw/nand_ids.c
@@ -166,7 +166,7 @@ struct nand_flash_dev nand_flash_ids[] = {
 };
 
 /* Manufacturer IDs */
-static const struct nand_manufacturer nand_manufacturers[] = {
+static const struct nand_manufacturer_desc nand_manufacturer_descs[] = {
 	{NAND_MFR_AMD, "AMD/Spansion", &amd_nand_manuf_ops},
 	{NAND_MFR_ATO, "ATO"},
 	{NAND_MFR_EON, "Eon"},
@@ -186,20 +186,20 @@ static const struct nand_manufacturer nand_manufacturers[] = {
 };
 
 /**
- * nand_get_manufacturer - Get manufacturer information from the manufacturer
- *			   ID
+ * nand_get_manufacturer_desc - Get manufacturer information from the
+ *                              manufacturer ID
  * @id: manufacturer ID
  *
- * Returns a pointer a nand_manufacturer object if the manufacturer is defined
+ * Returns a nand_manufacturer_desc object if the manufacturer is defined
  * in the NAND manufacturers database, NULL otherwise.
  */
-const struct nand_manufacturer *nand_get_manufacturer(u8 id)
+const struct nand_manufacturer_desc *nand_get_manufacturer_desc(u8 id)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(nand_manufacturers); i++)
-		if (nand_manufacturers[i].id == id)
-			return &nand_manufacturers[i];
+	for (i = 0; i < ARRAY_SIZE(nand_manufacturer_descs); i++)
+		if (nand_manufacturer_descs[i].id == id)
+			return &nand_manufacturer_descs[i];
 
 	return NULL;
 }
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 7f9be95ca8dc..860d3c1020ef 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1163,7 +1163,7 @@ struct nand_chip {
 	void *priv;
 
 	struct {
-		const struct nand_manufacturer *desc;
+		const struct nand_manufacturer_desc *desc;
 		void *priv;
 	} manufacturer;
 };
-- 
cgit v1.2.3


From 36017af430e6b2fad0b2ee5476103706160f1379 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:12:59 +0200
Subject: mtd: rawnand: Declare the nand_manufacturer structure out of
 nand_chip

Now that struct nand_manufacturer type is free, use it to store the
nand_manufacturer_desc and the manufacturer's private data.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-6-miquel.raynal@bootlin.com
---
 include/linux/mtd/rawnand.h | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 860d3c1020ef..a3dfa36a9fd5 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1043,10 +1043,21 @@ struct nand_chip_ops {
 	int (*setup_read_retry)(struct nand_chip *chip, int retry_mode);
 };
 
+/**
+ * struct nand_manufacturer - NAND manufacturer structure
+ * @desc: The manufacturer description
+ * @priv: Private information for the manufacturer driver
+ */
+struct nand_manufacturer {
+	const struct nand_manufacturer_desc *desc;
+	void *priv;
+};
+
 /**
  * struct nand_chip - NAND Private Flash Chip Data
  * @base:		Inherit from the generic NAND device
  * @ops:		NAND chip operations
+ * @manufacturer:	Manufacturer information
  * @legacy:		All legacy fields/hooks. If you develop a new driver,
  *			don't even try to use any of these fields/hooks, and if
  *			you're modifying an existing driver that is using those
@@ -1106,13 +1117,11 @@ struct nand_chip_ops {
  *			structure which is shared among multiple independent
  *			devices.
  * @priv:		[OPTIONAL] pointer to private chip data
- * @manufacturer:	[INTERN] Contains manufacturer information
- * @manufacturer.desc:	[INTERN] Contains manufacturer's description
- * @manufacturer.priv:	[INTERN] Contains manufacturer private information
  */
 
 struct nand_chip {
 	struct nand_device base;
+	struct nand_manufacturer manufacturer;
 	struct nand_chip_ops ops;
 	struct nand_legacy legacy;
 
@@ -1161,11 +1170,6 @@ struct nand_chip {
 	struct nand_bbt_descr *badblock_pattern;
 
 	void *priv;
-
-	struct {
-		const struct nand_manufacturer_desc *desc;
-		void *priv;
-	} manufacturer;
 };
 
 extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
-- 
cgit v1.2.3


From a63674c7cfe62221e05ba73107d9e15d73ff8bbd Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:00 +0200
Subject: mtd: rawnand: Reorganize the nand_chip structure

Reorder fields in this structure and pack entries by theme:
* The main descriptive structures
* The data interface details
* Bad block information
* The device layout
* Extra buffers matching the device layout
* Internal values
* External objects like the ECC controller, the ECC engine and a
  private data pointer.

While at it, adapt the documentation style.

I changed on purpose the description of @oob_poi which was weird.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-7-miquel.raynal@bootlin.com
---
 include/linux/mtd/rawnand.h | 166 ++++++++++++++++++++------------------------
 1 file changed, 76 insertions(+), 90 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index a3dfa36a9fd5..544ec8736793 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1055,120 +1055,106 @@ struct nand_manufacturer {
 
 /**
  * struct nand_chip - NAND Private Flash Chip Data
- * @base:		Inherit from the generic NAND device
- * @ops:		NAND chip operations
- * @manufacturer:	Manufacturer information
- * @legacy:		All legacy fields/hooks. If you develop a new driver,
- *			don't even try to use any of these fields/hooks, and if
- *			you're modifying an existing driver that is using those
- *			fields/hooks, you should consider reworking the driver
- *			avoid using them.
- * @ecc:		[BOARDSPECIFIC] ECC control structure
- * @buf_align:		minimum buffer alignment required by a platform
- * @oob_poi:		"poison value buffer," used for laying out OOB data
- *			before writing
- * @page_shift:		[INTERN] number of address bits in a page (column
- *			address bits).
- * @phys_erase_shift:	[INTERN] number of address bits in a physical eraseblock
- * @bbt_erase_shift:	[INTERN] number of address bits in a bbt entry
- * @chip_shift:		[INTERN] number of address bits in one chip
- * @options:		[BOARDSPECIFIC] various chip options. They can partly
- *			be set to inform nand_scan about special functionality.
- *			See the defines for further explanation.
- * @bbt_options:	[INTERN] bad block specific options. All options used
- *			here must come from bbm.h. By default, these options
- *			will be copied to the appropriate nand_bbt_descr's.
- * @badblockpos:	[INTERN] position of the bad block marker in the oob
- *			area.
- * @badblockbits:	[INTERN] minimum number of set bits in a good block's
- *			bad block marker position; i.e., BBM == 11110111b is
- *			not bad when badblockbits == 7
- * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is
- *			      set to the actually used ONFI mode if the chip is
- *			      ONFI compliant or deduced from the datasheet if
- *			      the NAND chip is not ONFI compliant.
- * @pagemask:		[INTERN] page number mask = number of (pages / chip) - 1
- * @data_buf:		[INTERN] buffer for data, size is (page size + oobsize).
- * @pagecache:		Structure containing page cache related fields
- * @pagecache.bitflips:	Number of bitflips of the cached page
- * @pagecache.page:	Page number currently in the cache. -1 means no page is
- *			currently cached
- * @subpagesize:	[INTERN] holds the subpagesize
- * @id:			[INTERN] holds NAND ID
- * @parameters:		[INTERN] holds generic parameters under an easily
- *			readable form.
- * @data_interface:	[INTERN] NAND interface timing information
- * @cur_cs:		currently selected target. -1 means no target selected,
- *			otherwise we should always have cur_cs >= 0 &&
- *			cur_cs < nanddev_ntargets(). NAND Controller drivers
- *			should not modify this value, but they're allowed to
- *			read it.
- * @read_retries:	[INTERN] the number of read retry modes supported
- * @lock:		lock protecting the suspended field. Also used to
- *			serialize accesses to the NAND device.
- * @suspended:		set to 1 when the device is suspended, 0 when it's not.
- * @bbt:		[INTERN] bad block table pointer
- * @bbt_td:		[REPLACEABLE] bad block table descriptor for flash
- *			lookup.
- * @bbt_md:		[REPLACEABLE] bad block table mirror descriptor
- * @badblock_pattern:	[REPLACEABLE] bad block scan pattern used for initial
- *			bad block scan.
- * @controller:		[REPLACEABLE] a pointer to a hardware controller
- *			structure which is shared among multiple independent
- *			devices.
- * @priv:		[OPTIONAL] pointer to private chip data
+ * @base: Inherit from the generic NAND device
+ * @id: Holds NAND ID
+ * @parameters: Holds generic parameters under an easily readable form
+ * @manufacturer: Manufacturer information
+ * @ops: NAND chip operations
+ * @legacy: All legacy fields/hooks. If you develop a new driver, don't even try
+ *          to use any of these fields/hooks, and if you're modifying an
+ *          existing driver that is using those fields/hooks, you should
+ *          consider reworking the driver and avoid using them.
+ * @options: Various chip options. They can partly be set to inform nand_scan
+ *           about special functionality. See the defines for further
+ *           explanation.
+ * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the
+ *			      actually used ONFI mode if the chip is ONFI
+ *			      compliant or deduced from the datasheet otherwise
+ * @data_interface: NAND interface timing information
+ * @bbt_erase_shift: Number of address bits in a bbt entry
+ * @bbt_options: Bad block table specific options. All options used here must
+ *               come from bbm.h. By default, these options will be copied to
+ *               the appropriate nand_bbt_descr's.
+ * @badblockpos: Bad block marker position in the oob area
+ * @badblockbits: Minimum number of set bits in a good block's bad block marker
+ *                position; i.e., BBM = 11110111b is good when badblockbits = 7
+ * @bbt_td: Bad block table descriptor for flash lookup
+ * @bbt_md: Bad block table mirror descriptor
+ * @badblock_pattern: Bad block scan pattern used for initial bad block scan
+ * @bbt: Bad block table pointer
+ * @page_shift: Number of address bits in a page (column address bits)
+ * @phys_erase_shift: Number of address bits in a physical eraseblock
+ * @chip_shift: Number of address bits in one chip
+ * @pagemask: Page number mask = number of (pages / chip) - 1
+ * @subpagesize: Holds the subpagesize
+ * @data_buf: Buffer for data, size is (page size + oobsize)
+ * @oob_poi: pointer on the OOB area covered by data_buf
+ * @pagecache: Structure containing page cache related fields
+ * @pagecache.bitflips: Number of bitflips of the cached page
+ * @pagecache.page: Page number currently in the cache. -1 means no page is
+ *                  currently cached
+ * @buf_align: Minimum buffer alignment required by a platform
+ * @lock: Lock protecting the suspended field. Also used to serialize accesses
+ *        to the NAND device
+ * @suspended: Set to 1 when the device is suspended, 0 when it's not
+ * @cur_cs: Currently selected target. -1 means no target selected, otherwise we
+ *          should always have cur_cs >= 0 && cur_cs < nanddev_ntargets().
+ *          NAND Controller drivers should not modify this value, but they're
+ *          allowed to read it.
+ * @read_retries: The number of read retry modes supported
+ * @controller: The hardware controller	structure which is shared among multiple
+ *              independent devices
+ * @ecc: The ECC controller structure
+ * @priv: Chip private data
  */
-
 struct nand_chip {
 	struct nand_device base;
+	struct nand_id id;
+	struct nand_parameters parameters;
 	struct nand_manufacturer manufacturer;
 	struct nand_chip_ops ops;
 	struct nand_legacy legacy;
-
 	unsigned int options;
+
+	/* Data interface */
+	int onfi_timing_mode_default;
+	struct nand_data_interface data_interface;
+
+	/* Bad block information */
+	unsigned int bbt_erase_shift;
 	unsigned int bbt_options;
+	unsigned int badblockpos;
+	unsigned int badblockbits;
+	struct nand_bbt_descr *bbt_td;
+	struct nand_bbt_descr *bbt_md;
+	struct nand_bbt_descr *badblock_pattern;
+	u8 *bbt;
 
+	/* Device internal layout */
 	unsigned int page_shift;
 	unsigned int phys_erase_shift;
-	unsigned int bbt_erase_shift;
 	unsigned int chip_shift;
 	unsigned int pagemask;
-	u8 *data_buf;
+	unsigned int subpagesize;
 
+	/* Buffers */
+	u8 *data_buf;
+	u8 *oob_poi;
 	struct {
 		unsigned int bitflips;
 		int page;
 	} pagecache;
+	unsigned long buf_align;
 
-	unsigned int subpagesize;
-	int onfi_timing_mode_default;
-	unsigned int badblockpos;
-	unsigned int badblockbits;
-
-	struct nand_id id;
-	struct nand_parameters parameters;
-
-	struct nand_data_interface data_interface;
-
-	int cur_cs;
-
-	int read_retries;
-
+	/* Internals */
 	struct mutex lock;
 	unsigned int suspended : 1;
+	int cur_cs;
+	int read_retries;
 
-	u8 *oob_poi;
+	/* Externals */
 	struct nand_controller *controller;
-
 	struct nand_ecc_ctrl ecc;
-	unsigned long buf_align;
-
-	u8 *bbt;
-	struct nand_bbt_descr *bbt_td;
-	struct nand_bbt_descr *bbt_md;
-
-	struct nand_bbt_descr *badblock_pattern;
-
 	void *priv;
 };
 
-- 
cgit v1.2.3


From e0160cd41fb81fde9ee4612a7ea2dfd631de2638 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:12 +0200
Subject: mtd: rawnand: Hide the chip->data_interface indirection

As a preparation for allocating the data interface structure
dynamically (and rename it), let's avoid accessing
chip->data_interface directly.

Instead, we introduce a helper, nand_get_interface_config(), and use
it to retrieve the current data interface configuration out of a
nand_chip object.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-19-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/marvell_nand.c    |  9 ++++++---
 drivers/mtd/nand/raw/meson_nand.c      |  8 ++++----
 drivers/mtd/nand/raw/nand_base.c       | 34 +++++++++++++++++-----------------
 drivers/mtd/nand/raw/nand_legacy.c     |  5 ++++-
 drivers/mtd/nand/raw/nand_toshiba.c    |  2 +-
 drivers/mtd/nand/raw/stm32_fmc2_nand.c |  2 +-
 drivers/mtd/nand/raw/tango_nand.c      |  2 +-
 include/linux/mtd/rawnand.h            | 11 +++++++++++
 8 files changed, 45 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 260a0430313e..df859889e4eb 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -1096,6 +1096,8 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip,
 						const u8 *oob_buf, bool raw,
 						int page)
 {
+	const struct nand_sdr_timings *sdr =
+		nand_get_sdr_timings(nand_get_interface_config(chip));
 	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout;
@@ -1141,7 +1143,7 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip,
 		return ret;
 
 	ret = marvell_nfc_wait_op(chip,
-				  PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
+				  PSEC_TO_MSEC(sdr->tPROG_max));
 	return ret;
 }
 
@@ -1562,6 +1564,8 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct nand_chip *chip,
 					     const u8 *buf,
 					     int oob_required, int page)
 {
+	const struct nand_sdr_timings *sdr =
+		nand_get_sdr_timings(nand_get_interface_config(chip));
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout;
 	const u8 *data = buf;
@@ -1598,8 +1602,7 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct nand_chip *chip,
 		marvell_nfc_wait_ndrun(chip);
 	}
 
-	ret = marvell_nfc_wait_op(chip,
-				  PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
+	ret = marvell_nfc_wait_op(chip, PSEC_TO_MSEC(sdr->tPROG_max));
 
 	marvell_nfc_disable_hw_ecc(chip);
 
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 3f376471f3f7..580b7be0719f 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -573,10 +573,10 @@ static int meson_nfc_write_buf(struct nand_chip *nand, u8 *buf, int len)
 static int meson_nfc_rw_cmd_prepare_and_execute(struct nand_chip *nand,
 						int page, bool in)
 {
+	const struct nand_sdr_timings *sdr =
+		nand_get_sdr_timings(nand_get_interface_config(nand));
 	struct mtd_info *mtd = nand_to_mtd(nand);
 	struct meson_nfc *nfc = nand_get_controller_data(nand);
-	const struct nand_sdr_timings *sdr =
-		nand_get_sdr_timings(&nand->data_interface);
 	u32 *addrs = nfc->cmdfifo.rw.addrs;
 	u32 cs = nfc->param.chip_select;
 	u32 cmd0, cmd_num, row_start;
@@ -626,9 +626,9 @@ static int meson_nfc_rw_cmd_prepare_and_execute(struct nand_chip *nand,
 static int meson_nfc_write_page_sub(struct nand_chip *nand,
 				    int page, int raw)
 {
-	struct mtd_info *mtd = nand_to_mtd(nand);
 	const struct nand_sdr_timings *sdr =
-		nand_get_sdr_timings(&nand->data_interface);
+		nand_get_sdr_timings(nand_get_interface_config(nand));
+	struct mtd_info *mtd = nand_to_mtd(nand);
 	struct meson_nfc_nand_chip *meson_chip = to_meson_nand(nand);
 	struct meson_nfc *nfc = nand_get_controller_data(nand);
 	int data_len, info_len;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index b4de85794e07..7d393e1d0252 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -773,7 +773,7 @@ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
 		return -ENOTSUPP;
 
 	/* Wait tWB before polling the STATUS reg. */
-	timings = nand_get_sdr_timings(&chip->data_interface);
+	timings = nand_get_sdr_timings(nand_get_interface_config(chip));
 	ndelay(PSEC_TO_NSEC(timings->tWB_max));
 
 	ret = nand_status_op(chip, NULL);
@@ -1119,9 +1119,9 @@ static int nand_sp_exec_read_page_op(struct nand_chip *chip, unsigned int page,
 				     unsigned int offset_in_page, void *buf,
 				     unsigned int len)
 {
-	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_sdr_timings *sdr =
-		nand_get_sdr_timings(&chip->data_interface);
+		nand_get_sdr_timings(nand_get_interface_config(chip));
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	u8 addrs[4];
 	struct nand_op_instr instrs[] = {
 		NAND_OP_CMD(NAND_CMD_READ0, 0),
@@ -1163,7 +1163,7 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page,
 				     unsigned int len)
 {
 	const struct nand_sdr_timings *sdr =
-		nand_get_sdr_timings(&chip->data_interface);
+		nand_get_sdr_timings(nand_get_interface_config(chip));
 	u8 addrs[5];
 	struct nand_op_instr instrs[] = {
 		NAND_OP_CMD(NAND_CMD_READ0, 0),
@@ -1260,7 +1260,7 @@ int nand_read_param_page_op(struct nand_chip *chip, u8 page, void *buf,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_PARAM, 0),
 			NAND_OP_ADDR(1, &page, PSEC_TO_NSEC(sdr->tWB_max)),
@@ -1315,7 +1315,7 @@ int nand_change_read_column_op(struct nand_chip *chip,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		u8 addrs[2] = {};
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_RNDOUT, 0),
@@ -1389,9 +1389,9 @@ static int nand_exec_prog_page_op(struct nand_chip *chip, unsigned int page,
 				  unsigned int offset_in_page, const void *buf,
 				  unsigned int len, bool prog)
 {
-	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_sdr_timings *sdr =
-		nand_get_sdr_timings(&chip->data_interface);
+		nand_get_sdr_timings(nand_get_interface_config(chip));
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	u8 addrs[5] = {};
 	struct nand_op_instr instrs[] = {
 		/*
@@ -1514,7 +1514,7 @@ int nand_prog_page_end_op(struct nand_chip *chip)
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_PAGEPROG,
 				    PSEC_TO_NSEC(sdr->tWB_max)),
@@ -1621,7 +1621,7 @@ int nand_change_write_column_op(struct nand_chip *chip,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		u8 addrs[2];
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_RNDIN, 0),
@@ -1676,7 +1676,7 @@ int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_READID, 0),
 			NAND_OP_ADDR(1, &addr, PSEC_TO_NSEC(sdr->tADL_min)),
@@ -1715,7 +1715,7 @@ int nand_status_op(struct nand_chip *chip, u8 *status)
 {
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_STATUS,
 				    PSEC_TO_NSEC(sdr->tADL_min)),
@@ -1784,7 +1784,7 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock)
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		u8 addrs[3] = {	page, page >> 8, page >> 16 };
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_ERASE1, 0),
@@ -1843,7 +1843,7 @@ static int nand_set_features_op(struct nand_chip *chip, u8 feature,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_SET_FEATURES, 0),
 			NAND_OP_ADDR(1, &feature, PSEC_TO_NSEC(sdr->tADL_min)),
@@ -1890,7 +1890,7 @@ static int nand_get_features_op(struct nand_chip *chip, u8 feature,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_GET_FEATURES, 0),
 			NAND_OP_ADDR(1, &feature, PSEC_TO_NSEC(sdr->tWB_max)),
@@ -1947,7 +1947,7 @@ int nand_reset_op(struct nand_chip *chip)
 {
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(NAND_CMD_RESET, PSEC_TO_NSEC(sdr->tWB_max)),
 			NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tRST_max), 0),
@@ -3226,7 +3226,7 @@ static void nand_wait_readrdy(struct nand_chip *chip)
 	if (!(chip->options & NAND_NEED_READRDY))
 		return;
 
-	sdr = nand_get_sdr_timings(&chip->data_interface);
+	sdr = nand_get_sdr_timings(nand_get_interface_config(chip));
 	WARN_ON(nand_wait_rdy_op(chip, PSEC_TO_MSEC(sdr->tR_max), 0));
 }
 
diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c
index 848403dcae03..fe769762e1d8 100644
--- a/drivers/mtd/nand/raw/nand_legacy.c
+++ b/drivers/mtd/nand/raw/nand_legacy.c
@@ -354,6 +354,9 @@ static void nand_command(struct nand_chip *chip, unsigned int command,
 
 static void nand_ccs_delay(struct nand_chip *chip)
 {
+	const struct nand_sdr_timings *sdr =
+		nand_get_sdr_timings(nand_get_interface_config(chip));
+
 	/*
 	 * The controller already takes care of waiting for tCCS when the RNDIN
 	 * or RNDOUT command is sent, return directly.
@@ -366,7 +369,7 @@ static void nand_ccs_delay(struct nand_chip *chip)
 	 * (which should be safe for all NANDs).
 	 */
 	if (nand_controller_can_setup_data_iface(chip))
-		ndelay(chip->data_interface.timings.sdr.tCCS_min / 1000);
+		ndelay(sdr->tCCS_min / 1000);
 	else
 		ndelay(500);
 }
diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c
index ae069905d7e4..333037bdca41 100644
--- a/drivers/mtd/nand/raw/nand_toshiba.c
+++ b/drivers/mtd/nand/raw/nand_toshiba.c
@@ -33,7 +33,7 @@ static int toshiba_nand_benand_read_eccstatus_op(struct nand_chip *chip,
 
 	if (nand_has_exec_op(chip)) {
 		const struct nand_sdr_timings *sdr =
-			nand_get_sdr_timings(&chip->data_interface);
+			nand_get_sdr_timings(nand_get_interface_config(chip));
 		struct nand_op_instr instrs[] = {
 			NAND_OP_CMD(TOSHIBA_NAND_CMD_ECC_STATUS_READ,
 				    PSEC_TO_NSEC(sdr->tADL_min)),
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 65c9d17b25a3..7320c0fc19ec 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1308,7 +1308,7 @@ static int stm32_fmc2_nfc_waitrdy(struct nand_chip *chip,
 		dev_warn(nfc->dev, "Waitrdy timeout\n");
 
 	/* Wait tWB before R/B# signal is low */
-	timings = nand_get_sdr_timings(&chip->data_interface);
+	timings = nand_get_sdr_timings(nand_get_interface_config(chip));
 	ndelay(PSEC_TO_NSEC(timings->tWB_max));
 
 	/* R/B# signal is low, clear high level flag */
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index b3a0d08f1733..648dc7e77f6a 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -336,7 +336,7 @@ static int tango_write_page(struct nand_chip *chip, const u8 *buf,
 	if (err)
 		return err;
 
-	timings = nand_get_sdr_timings(&chip->data_interface);
+	timings = nand_get_sdr_timings(nand_get_interface_config(chip));
 	err = tango_waitrdy(chip, PSEC_TO_MSEC(timings->tR_max));
 	if (err)
 		return err;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 544ec8736793..0852df941130 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1203,6 +1203,17 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip)
 	return mtd_get_of_node(nand_to_mtd(chip));
 }
 
+/**
+ * nand_get_interface_config - Retrieve the current interface configuration
+ *                             of a NAND chip
+ * @chip: The NAND chip
+ */
+static inline const struct nand_data_interface *
+nand_get_interface_config(struct nand_chip *chip)
+{
+	return &chip->data_interface;
+}
+
 /*
  * A helper for defining older NAND chips where the second ID byte fully
  * defined the chip, including the geometry (chip size, eraseblock size, page
-- 
cgit v1.2.3


From 4c46667b3d67253604ee42840917844548c86657 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:13 +0200
Subject: mtd: rawnand: s/data_interface/interface_config/

The name/suffix data_interface is a bit misleading in that the field
or functions actually represent a configuration that can be applied by
the controller/chip. Let's rename all fields/functions/hooks that are
worth renaming.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/ams-delta.c               |  6 +--
 drivers/mtd/nand/raw/arasan-nand-controller.c  |  6 +--
 drivers/mtd/nand/raw/atmel/nand-controller.c   | 34 ++++++-------
 drivers/mtd/nand/raw/cadence-nand-controller.c |  6 +--
 drivers/mtd/nand/raw/denali.c                  |  8 +--
 drivers/mtd/nand/raw/fsmc_nand.c               |  6 +--
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c     |  6 +--
 drivers/mtd/nand/raw/internals.h               | 12 ++---
 drivers/mtd/nand/raw/marvell_nand.c            |  9 ++--
 drivers/mtd/nand/raw/meson_nand.c              |  6 +--
 drivers/mtd/nand/raw/mtk_nand.c                |  6 +--
 drivers/mtd/nand/raw/mxc_nand.c                | 20 ++++----
 drivers/mtd/nand/raw/mxic_nand.c               |  6 +--
 drivers/mtd/nand/raw/nand_base.c               | 69 +++++++++++++-------------
 drivers/mtd/nand/raw/nand_legacy.c             |  2 +-
 drivers/mtd/nand/raw/nand_timings.c            | 17 ++++---
 drivers/mtd/nand/raw/s3c2410.c                 |  6 +--
 drivers/mtd/nand/raw/stm32_fmc2_nand.c         |  4 +-
 drivers/mtd/nand/raw/sunxi_nand.c              |  6 +--
 drivers/mtd/nand/raw/tango_nand.c              |  4 +-
 drivers/mtd/nand/raw/tegra_nand.c              |  6 +--
 include/linux/mtd/rawnand.h                    | 33 ++++++------
 22 files changed, 139 insertions(+), 139 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c
index 3711e7a0436c..fdba155416d2 100644
--- a/drivers/mtd/nand/raw/ams-delta.c
+++ b/drivers/mtd/nand/raw/ams-delta.c
@@ -191,8 +191,8 @@ static int gpio_nand_exec_op(struct nand_chip *this,
 	return ret;
 }
 
-static int gpio_nand_setup_data_interface(struct nand_chip *this, int csline,
-					  const struct nand_data_interface *cf)
+static int gpio_nand_setup_interface(struct nand_chip *this, int csline,
+				     const struct nand_interface_config *cf)
 {
 	struct gpio_nand *priv = nand_get_controller_data(this);
 	const struct nand_sdr_timings *sdr = nand_get_sdr_timings(cf);
@@ -217,7 +217,7 @@ static int gpio_nand_setup_data_interface(struct nand_chip *this, int csline,
 
 static const struct nand_controller_ops gpio_nand_ops = {
 	.exec_op = gpio_nand_exec_op,
-	.setup_data_interface = gpio_nand_setup_data_interface,
+	.setup_interface = gpio_nand_setup_interface,
 };
 
 /*
diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index 7141dcccba3c..12c643e97c85 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -854,8 +854,8 @@ static int anfc_exec_op(struct nand_chip *chip,
 	return nand_op_parser_exec_op(chip, &anfc_op_parser, op, check_only);
 }
 
-static int anfc_setup_data_interface(struct nand_chip *chip, int target,
-				     const struct nand_data_interface *conf)
+static int anfc_setup_interface(struct nand_chip *chip, int target,
+				const struct nand_interface_config *conf)
 {
 	struct anand *anand = to_anand(chip);
 	struct arasan_nfc *nfc = to_anfc(chip->controller);
@@ -1083,7 +1083,7 @@ static void anfc_detach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops anfc_ops = {
 	.exec_op = anfc_exec_op,
-	.setup_data_interface = anfc_setup_data_interface,
+	.setup_interface = anfc_setup_interface,
 	.attach_chip = anfc_attach_chip,
 	.detach_chip = anfc_detach_chip,
 };
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 46a3724a788e..c9818f548d07 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -200,8 +200,8 @@ struct atmel_nand_controller_ops {
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
 	int (*ecc_init)(struct nand_chip *chip);
-	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
-				    const struct nand_data_interface *conf);
+	int (*setup_interface)(struct atmel_nand *nand, int csline,
+			       const struct nand_interface_config *conf);
 };
 
 struct atmel_nand_controller_caps {
@@ -1168,7 +1168,7 @@ static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 }
 
 static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand,
-					const struct nand_data_interface *conf,
+					const struct nand_interface_config *conf,
 					struct atmel_smc_cs_conf *smcconf)
 {
 	u32 ncycles, totalcycles, timeps, mckperiodps;
@@ -1397,9 +1397,9 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand,
 	return 0;
 }
 
-static int atmel_smc_nand_setup_data_interface(struct atmel_nand *nand,
+static int atmel_smc_nand_setup_interface(struct atmel_nand *nand,
 					int csline,
-					const struct nand_data_interface *conf)
+					const struct nand_interface_config *conf)
 {
 	struct atmel_nand_controller *nc;
 	struct atmel_smc_cs_conf smcconf;
@@ -1422,9 +1422,9 @@ static int atmel_smc_nand_setup_data_interface(struct atmel_nand *nand,
 	return 0;
 }
 
-static int atmel_hsmc_nand_setup_data_interface(struct atmel_nand *nand,
+static int atmel_hsmc_nand_setup_interface(struct atmel_nand *nand,
 					int csline,
-					const struct nand_data_interface *conf)
+					const struct nand_interface_config *conf)
 {
 	struct atmel_hsmc_nand_controller *nc;
 	struct atmel_smc_cs_conf smcconf;
@@ -1452,8 +1452,8 @@ static int atmel_hsmc_nand_setup_data_interface(struct atmel_nand *nand,
 	return 0;
 }
 
-static int atmel_nand_setup_data_interface(struct nand_chip *chip, int csline,
-					const struct nand_data_interface *conf)
+static int atmel_nand_setup_interface(struct nand_chip *chip, int csline,
+				      const struct nand_interface_config *conf)
 {
 	struct atmel_nand *nand = to_atmel_nand(chip);
 	struct atmel_nand_controller *nc;
@@ -1464,7 +1464,7 @@ static int atmel_nand_setup_data_interface(struct nand_chip *chip, int csline,
 	    (csline < 0 && csline != NAND_DATA_IFACE_CHECK_ONLY))
 		return -EINVAL;
 
-	return nc->caps->ops->setup_data_interface(nand, csline, conf);
+	return nc->caps->ops->setup_interface(nand, csline, conf);
 }
 
 static void atmel_nand_init(struct atmel_nand_controller *nc,
@@ -1483,7 +1483,7 @@ static void atmel_nand_init(struct atmel_nand_controller *nc,
 	chip->legacy.write_buf = atmel_nand_write_buf;
 	chip->legacy.select_chip = atmel_nand_select_chip;
 
-	if (!nc->mck || !nc->caps->ops->setup_data_interface)
+	if (!nc->mck || !nc->caps->ops->setup_interface)
 		chip->options |= NAND_KEEP_TIMINGS;
 
 	/* Some NANDs require a longer delay than the default one (20us). */
@@ -1956,7 +1956,7 @@ static int atmel_nand_attach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops atmel_nand_controller_ops = {
 	.attach_chip = atmel_nand_attach_chip,
-	.setup_data_interface = atmel_nand_setup_data_interface,
+	.setup_interface = atmel_nand_setup_interface,
 };
 
 static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
@@ -2318,7 +2318,7 @@ static const struct atmel_nand_controller_ops atmel_hsmc_nc_ops = {
 	.remove = atmel_hsmc_nand_controller_remove,
 	.ecc_init = atmel_hsmc_nand_ecc_init,
 	.nand_init = atmel_hsmc_nand_init,
-	.setup_data_interface = atmel_hsmc_nand_setup_data_interface,
+	.setup_interface = atmel_hsmc_nand_setup_interface,
 };
 
 static const struct atmel_nand_controller_caps atmel_sama5_nc_caps = {
@@ -2375,10 +2375,10 @@ atmel_smc_nand_controller_remove(struct atmel_nand_controller *nc)
 
 /*
  * The SMC reg layout of at91rm9200 is completely different which prevents us
- * from re-using atmel_smc_nand_setup_data_interface() for the
- * ->setup_data_interface() hook.
+ * from re-using atmel_smc_nand_setup_interface() for the
+ * ->setup_interface() hook.
  * At this point, there's no support for the at91rm9200 SMC IP, so we leave
- * ->setup_data_interface() unassigned.
+ * ->setup_interface() unassigned.
  */
 static const struct atmel_nand_controller_ops at91rm9200_nc_ops = {
 	.probe = atmel_smc_nand_controller_probe,
@@ -2399,7 +2399,7 @@ static const struct atmel_nand_controller_ops atmel_smc_nc_ops = {
 	.remove = atmel_smc_nand_controller_remove,
 	.ecc_init = atmel_nand_ecc_init,
 	.nand_init = atmel_smc_nand_init,
-	.setup_data_interface = atmel_smc_nand_setup_data_interface,
+	.setup_interface = atmel_smc_nand_setup_interface,
 };
 
 static const struct atmel_nand_controller_caps atmel_sam9260_nc_caps = {
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index c405722adfe1..574cbd3446e5 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2303,8 +2303,8 @@ static inline u32 calc_tdvw(u32 trp_cnt, u32 clk_period, u32 trhoh_min,
 }
 
 static int
-cadence_nand_setup_data_interface(struct nand_chip *chip, int chipnr,
-				  const struct nand_data_interface *conf)
+cadence_nand_setup_interface(struct nand_chip *chip, int chipnr,
+			     const struct nand_interface_config *conf)
 {
 	const struct nand_sdr_timings *sdr;
 	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
@@ -2690,7 +2690,7 @@ static int cadence_nand_attach_chip(struct nand_chip *chip)
 static const struct nand_controller_ops cadence_nand_controller_ops = {
 	.attach_chip = cadence_nand_attach_chip,
 	.exec_op = cadence_nand_exec_op,
-	.setup_data_interface = cadence_nand_setup_data_interface,
+	.setup_interface = cadence_nand_setup_interface,
 };
 
 static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl,
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 4e6e1578aa2d..9d99dade95ce 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -761,8 +761,8 @@ static int denali_write_page(struct nand_chip *chip, const u8 *buf,
 	return denali_page_xfer(chip, (void *)buf, mtd->writesize, page, true);
 }
 
-static int denali_setup_data_interface(struct nand_chip *chip, int chipnr,
-				       const struct nand_data_interface *conf)
+static int denali_setup_interface(struct nand_chip *chip, int chipnr,
+				  const struct nand_interface_config *conf)
 {
 	static const unsigned int data_setup_on_host = 10000;
 	struct denali_controller *denali = to_denali_controller(chip);
@@ -1173,7 +1173,7 @@ static int denali_exec_op(struct nand_chip *chip,
 static const struct nand_controller_ops denali_controller_ops = {
 	.attach_chip = denali_attach_chip,
 	.exec_op = denali_exec_op,
-	.setup_data_interface = denali_setup_data_interface,
+	.setup_interface = denali_setup_interface,
 };
 
 int denali_chip_init(struct denali_controller *denali,
@@ -1230,7 +1230,7 @@ int denali_chip_init(struct denali_controller *denali,
 		chip->buf_align = 16;
 	}
 
-	/* clk rate info is needed for setup_data_interface */
+	/* clk rate info is needed for setup_interface */
 	if (!denali->clk_rate || !denali->clk_x_rate)
 		chip->options |= NAND_KEEP_TIMINGS;
 
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 3909752b14c5..92ddc41d0ff0 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -327,8 +327,8 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host,
 	return 0;
 }
 
-static int fsmc_setup_data_interface(struct nand_chip *nand, int csline,
-				     const struct nand_data_interface *conf)
+static int fsmc_setup_interface(struct nand_chip *nand, int csline,
+				const struct nand_interface_config *conf)
 {
 	struct fsmc_nand_data *host = nand_to_fsmc(nand);
 	struct fsmc_nand_timings tims;
@@ -951,7 +951,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 static const struct nand_controller_ops fsmc_nand_controller_ops = {
 	.attach_chip = fsmc_nand_attach_chip,
 	.exec_op = fsmc_exec_op,
-	.setup_data_interface = fsmc_setup_data_interface,
+	.setup_interface = fsmc_setup_interface,
 };
 
 /**
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 061a8ddda275..5d4aee46cc55 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -736,8 +736,8 @@ static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
 	udelay(dll_wait_time_us);
 }
 
-static int gpmi_setup_data_interface(struct nand_chip *chip, int chipnr,
-				     const struct nand_data_interface *conf)
+static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
+				const struct nand_interface_config *conf)
 {
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	const struct nand_sdr_timings *sdr;
@@ -2400,7 +2400,7 @@ unmap:
 
 static const struct nand_controller_ops gpmi_nand_controller_ops = {
 	.attach_chip = gpmi_nand_attach_chip,
-	.setup_data_interface = gpmi_setup_data_interface,
+	.setup_interface = gpmi_setup_interface,
 	.exec_op = gpmi_nfc_exec_op,
 };
 
diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h
index f851ed210d70..114c63a6a349 100644
--- a/drivers/mtd/nand/raw/internals.h
+++ b/drivers/mtd/nand/raw/internals.h
@@ -84,10 +84,10 @@ int nand_bbm_get_next_page(struct nand_chip *chip, int page);
 int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs);
 int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr,
 		    int allowbbt);
-int onfi_fill_data_interface(struct nand_chip *chip,
-			     struct nand_data_interface *iface,
-			     enum nand_data_interface_type type,
-			     unsigned int timing_mode);
+int onfi_fill_interface_config(struct nand_chip *chip,
+			       struct nand_interface_config *iface,
+			       enum nand_interface_type type,
+			       unsigned int timing_mode);
 unsigned int
 onfi_find_closest_sdr_mode(const struct nand_sdr_timings *spec_timings);
 int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param);
@@ -133,10 +133,10 @@ static inline int nand_exec_op(struct nand_chip *chip,
 	return chip->controller->ops->exec_op(chip, op, false);
 }
 
-static inline bool nand_controller_can_setup_data_iface(struct nand_chip *chip)
+static inline bool nand_controller_can_setup_interface(struct nand_chip *chip)
 {
 	if (!chip->controller || !chip->controller->ops ||
-	    !chip->controller->ops->setup_data_interface)
+	    !chip->controller->ops->setup_interface)
 		return false;
 
 	if (chip->options & NAND_KEEP_TIMINGS)
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index df859889e4eb..8482d3bd8b1f 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2308,9 +2308,8 @@ static struct nand_bbt_descr bbt_mirror_descr = {
 	.pattern = bbt_mirror_pattern
 };
 
-static int marvell_nfc_setup_data_interface(struct nand_chip *chip, int chipnr,
-					    const struct nand_data_interface
-					    *conf)
+static int marvell_nfc_setup_interface(struct nand_chip *chip, int chipnr,
+				       const struct nand_interface_config *conf)
 {
 	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
@@ -2511,7 +2510,7 @@ static int marvell_nand_attach_chip(struct nand_chip *chip)
 static const struct nand_controller_ops marvell_nand_controller_ops = {
 	.attach_chip = marvell_nand_attach_chip,
 	.exec_op = marvell_nfc_exec_op,
-	.setup_data_interface = marvell_nfc_setup_data_interface,
+	.setup_interface = marvell_nfc_setup_interface,
 };
 
 static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
@@ -2647,7 +2646,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 
 	/*
 	 * Save a reference value for timing registers before
-	 * ->setup_data_interface() is called.
+	 * ->setup_interface() is called.
 	 */
 	marvell_nand->ndtr0 = readl_relaxed(nfc->regs + NDTR0);
 	marvell_nand->ndtr1 = readl_relaxed(nfc->regs + NDTR1);
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 580b7be0719f..0e5829a2b54f 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1097,8 +1097,8 @@ static int meson_chip_buffer_init(struct nand_chip *nand)
 }
 
 static
-int meson_nfc_setup_data_interface(struct nand_chip *nand, int csline,
-				   const struct nand_data_interface *conf)
+int meson_nfc_setup_interface(struct nand_chip *nand, int csline,
+			      const struct nand_interface_config *conf)
 {
 	struct meson_nfc_nand_chip *meson_chip = to_meson_nand(nand);
 	const struct nand_sdr_timings *timings;
@@ -1222,7 +1222,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand)
 static const struct nand_controller_ops meson_nand_controller_ops = {
 	.attach_chip = meson_nand_attach_chip,
 	.detach_chip = meson_nand_detach_chip,
-	.setup_data_interface = meson_nfc_setup_data_interface,
+	.setup_interface = meson_nfc_setup_interface,
 	.exec_op = meson_nfc_exec_op,
 };
 
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index ca8457626d53..ad1b55dab211 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -531,8 +531,8 @@ static int mtk_nfc_exec_op(struct nand_chip *chip,
 	return ret;
 }
 
-static int mtk_nfc_setup_data_interface(struct nand_chip *chip, int csline,
-					const struct nand_data_interface *conf)
+static int mtk_nfc_setup_interface(struct nand_chip *chip, int csline,
+				   const struct nand_interface_config *conf)
 {
 	struct mtk_nfc *nfc = nand_get_controller_data(chip);
 	const struct nand_sdr_timings *timings;
@@ -1357,7 +1357,7 @@ static int mtk_nfc_attach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops mtk_nfc_controller_ops = {
 	.attach_chip = mtk_nfc_attach_chip,
-	.setup_data_interface = mtk_nfc_setup_data_interface,
+	.setup_interface = mtk_nfc_setup_interface,
 	.exec_op = mtk_nfc_exec_op,
 };
 
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 09dacb83cb5a..07c41e8bae2d 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -137,8 +137,8 @@ struct mxc_nand_devtype_data {
 	u32 (*get_ecc_status)(struct mxc_nand_host *);
 	const struct mtd_ooblayout_ops *ooblayout;
 	void (*select_chip)(struct nand_chip *chip, int cs);
-	int (*setup_data_interface)(struct nand_chip *chip, int csline,
-				    const struct nand_data_interface *conf);
+	int (*setup_interface)(struct nand_chip *chip, int csline,
+			       const struct nand_interface_config *conf);
 	void (*enable_hwecc)(struct nand_chip *chip, bool enable);
 
 	/*
@@ -1139,8 +1139,8 @@ static void preset_v1(struct mtd_info *mtd)
 	writew(0x4, NFC_V1_V2_WRPROT);
 }
 
-static int mxc_nand_v2_setup_data_interface(struct nand_chip *chip, int csline,
-					const struct nand_data_interface *conf)
+static int mxc_nand_v2_setup_interface(struct nand_chip *chip, int csline,
+				       const struct nand_interface_config *conf)
 {
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	int tRC_min_ns, tRC_ps, ret;
@@ -1521,7 +1521,7 @@ static const struct mxc_nand_devtype_data imx25_nand_devtype_data = {
 	.get_ecc_status = get_ecc_status_v2,
 	.ooblayout = &mxc_v2_ooblayout_ops,
 	.select_chip = mxc_nand_select_chip_v2,
-	.setup_data_interface = mxc_nand_v2_setup_data_interface,
+	.setup_interface = mxc_nand_v2_setup_interface,
 	.enable_hwecc = mxc_nand_enable_hwecc_v1_v2,
 	.irqpending_quirk = 0,
 	.needs_ip = 0,
@@ -1738,17 +1738,17 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 	return 0;
 }
 
-static int mxcnd_setup_data_interface(struct nand_chip *chip, int chipnr,
-				      const struct nand_data_interface *conf)
+static int mxcnd_setup_interface(struct nand_chip *chip, int chipnr,
+				 const struct nand_interface_config *conf)
 {
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 
-	return host->devtype_data->setup_data_interface(chip, chipnr, conf);
+	return host->devtype_data->setup_interface(chip, chipnr, conf);
 }
 
 static const struct nand_controller_ops mxcnd_controller_ops = {
 	.attach_chip = mxcnd_attach_chip,
-	.setup_data_interface = mxcnd_setup_data_interface,
+	.setup_interface = mxcnd_setup_interface,
 };
 
 static int mxcnd_probe(struct platform_device *pdev)
@@ -1809,7 +1809,7 @@ static int mxcnd_probe(struct platform_device *pdev)
 	if (err < 0)
 		return err;
 
-	if (!host->devtype_data->setup_data_interface)
+	if (!host->devtype_data->setup_interface)
 		this->options |= NAND_KEEP_TIMINGS;
 
 	if (host->devtype_data->needs_ip) {
diff --git a/drivers/mtd/nand/raw/mxic_nand.c b/drivers/mtd/nand/raw/mxic_nand.c
index 57f36721f4c6..d66b5b0971fa 100644
--- a/drivers/mtd/nand/raw/mxic_nand.c
+++ b/drivers/mtd/nand/raw/mxic_nand.c
@@ -451,8 +451,8 @@ static int mxic_nfc_exec_op(struct nand_chip *chip,
 	return ret;
 }
 
-static int mxic_nfc_setup_data_interface(struct nand_chip *chip, int chipnr,
-					 const struct nand_data_interface *conf)
+static int mxic_nfc_setup_interface(struct nand_chip *chip, int chipnr,
+				    const struct nand_interface_config *conf)
 {
 	struct mxic_nand_ctlr *nfc = nand_get_controller_data(chip);
 	const struct nand_sdr_timings *sdr;
@@ -480,7 +480,7 @@ static int mxic_nfc_setup_data_interface(struct nand_chip *chip, int chipnr,
 
 static const struct nand_controller_ops mxic_nand_controller_ops = {
 	.exec_op = mxic_nfc_exec_op,
-	.setup_data_interface = mxic_nfc_setup_data_interface,
+	.setup_interface = mxic_nfc_setup_interface,
 };
 
 static int mxic_nfc_probe(struct platform_device *pdev)
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 7d393e1d0252..4fa18fb68d62 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -898,7 +898,7 @@ static bool nand_supports_set_features(struct nand_chip *chip, int addr)
 }
 
 /**
- * nand_reset_data_interface - Reset data interface and timings
+ * nand_reset_interface - Reset data interface and timings
  * @chip: The NAND chip
  * @chipnr: Internal die id
  *
@@ -906,11 +906,12 @@ static bool nand_supports_set_features(struct nand_chip *chip, int addr)
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
+static int nand_reset_interface(struct nand_chip *chip, int chipnr)
 {
+	const struct nand_controller_ops *ops = chip->controller->ops;
 	int ret;
 
-	if (!nand_controller_can_setup_data_iface(chip))
+	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
 	/*
@@ -927,9 +928,9 @@ static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
 	 * timings to timing mode 0.
 	 */
 
-	onfi_fill_data_interface(chip, &chip->data_interface, NAND_SDR_IFACE, 0);
-	ret = chip->controller->ops->setup_data_interface(chip, chipnr,
-							&chip->data_interface);
+	onfi_fill_interface_config(chip, &chip->interface_config,
+				   NAND_SDR_IFACE, 0);
+	ret = ops->setup_interface(chip, chipnr, &chip->interface_config);
 	if (ret)
 		pr_err("Failed to configure data interface to SDR timing mode 0\n");
 
@@ -937,7 +938,7 @@ static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
 }
 
 /**
- * nand_setup_data_interface - Setup the best data interface and timings
+ * nand_setup_interface - Setup the best data interface and timings
  * @chip: The NAND chip
  * @chipnr: Internal die id
  *
@@ -946,13 +947,13 @@ static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_setup_data_interface(struct nand_chip *chip, int chipnr)
+static int nand_setup_interface(struct nand_chip *chip, int chipnr)
 {
-	u8 mode = chip->data_interface.timings.mode;
+	u8 mode = chip->interface_config.timings.mode;
 	u8 tmode_param[ONFI_SUBFEATURE_PARAM_LEN] = { mode, };
 	int ret;
 
-	if (!nand_controller_can_setup_data_iface(chip))
+	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
 	/* Change the mode on the chip side (if supported by the NAND chip) */
@@ -966,8 +967,8 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr)
 	}
 
 	/* Change the mode on the controller side */
-	ret = chip->controller->ops->setup_data_interface(chip, chipnr,
-							&chip->data_interface);
+	ret = chip->controller->ops->setup_interface(chip, chipnr,
+						     &chip->interface_config);
 	if (ret)
 		return ret;
 
@@ -996,7 +997,7 @@ err_reset_chip:
 	 * Fallback to mode 0 if the chip explicitly did not ack the chosen
 	 * timing mode.
 	 */
-	nand_reset_data_interface(chip, chipnr);
+	nand_reset_interface(chip, chipnr);
 	nand_select_target(chip, chipnr);
 	nand_reset_op(chip);
 	nand_deselect_target(chip);
@@ -1005,7 +1006,7 @@ err_reset_chip:
 }
 
 /**
- * nand_choose_data_interface - find the best data interface and timings
+ * nand_choose_interface_config - find the best data interface and timings
  * @chip: The NAND chip
  *
  * Find the best data interface and NAND timings supported by the chip
@@ -1013,16 +1014,16 @@ err_reset_chip:
  * First tries to retrieve supported timing modes from ONFI information,
  * and if the NAND chip does not support ONFI, relies on the
  * ->onfi_timing_mode_default specified in the nand_ids table. After this
- * function nand_chip->data_interface is initialized with the best timing mode
+ * function nand_chip->interface_ is initialized with the best timing mode
  * available.
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_choose_data_interface(struct nand_chip *chip)
+static int nand_choose_interface_config(struct nand_chip *chip)
 {
 	int modes, mode, ret;
 
-	if (!nand_controller_can_setup_data_iface(chip))
+	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
 	/*
@@ -1040,8 +1041,8 @@ static int nand_choose_data_interface(struct nand_chip *chip)
 	}
 
 	for (mode = fls(modes) - 1; mode >= 0; mode--) {
-		ret = onfi_fill_data_interface(chip, &chip->data_interface,
-					       NAND_SDR_IFACE, mode);
+		ret = onfi_fill_interface_config(chip, &chip->interface_config,
+						 NAND_SDR_IFACE, mode);
 		if (ret)
 			continue;
 
@@ -1049,9 +1050,9 @@ static int nand_choose_data_interface(struct nand_chip *chip)
 		 * Pass NAND_DATA_IFACE_CHECK_ONLY to only check if the
 		 * controller supports the requested timings.
 		 */
-		ret = chip->controller->ops->setup_data_interface(chip,
+		ret = chip->controller->ops->setup_interface(chip,
 						 NAND_DATA_IFACE_CHECK_ONLY,
-						 &chip->data_interface);
+						 &chip->interface_config);
 		if (!ret) {
 			chip->onfi_timing_mode_default = mode;
 			break;
@@ -2477,17 +2478,17 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_len);
  * @chipnr: Internal die id
  *
  * Save the timings data structure, then apply SDR timings mode 0 (see
- * nand_reset_data_interface for details), do the reset operation, and
- * apply back the previous timings.
+ * nand_reset_interface for details), do the reset operation, and apply
+ * back the previous timings.
  *
  * Returns 0 on success, a negative error code otherwise.
  */
 int nand_reset(struct nand_chip *chip, int chipnr)
 {
-	struct nand_data_interface saved_data_intf = chip->data_interface;
+	struct nand_interface_config saved_intf_config = chip->interface_config;
 	int ret;
 
-	ret = nand_reset_data_interface(chip, chipnr);
+	ret = nand_reset_interface(chip, chipnr);
 	if (ret)
 		return ret;
 
@@ -2503,18 +2504,18 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 		return ret;
 
 	/*
-	 * A nand_reset_data_interface() put both the NAND chip and the NAND
+	 * A nand_reset_interface() put both the NAND chip and the NAND
 	 * controller in timings mode 0. If the default mode for this chip is
 	 * also 0, no need to proceed to the change again. Plus, at probe time,
-	 * nand_setup_data_interface() uses ->set/get_features() which would
+	 * nand_setup_interface() uses ->set/get_features() which would
 	 * fail anyway as the parameter page is not available yet.
 	 */
-	if (!memcmp(&chip->data_interface, &saved_data_intf,
-		    sizeof(saved_data_intf)))
+	if (!memcmp(&chip->interface_config, &saved_intf_config,
+		    sizeof(saved_intf_config)))
 		return 0;
 
-	chip->data_interface = saved_data_intf;
-	ret = nand_setup_data_interface(chip, chipnr);
+	chip->interface_config = saved_intf_config;
+	ret = nand_setup_interface(chip, chipnr);
 	if (ret)
 		return ret;
 
@@ -5183,7 +5184,7 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips,
 	mutex_init(&chip->lock);
 
 	/* Enforce the right timings for reset/detection */
-	onfi_fill_data_interface(chip, &chip->data_interface, NAND_SDR_IFACE, 0);
+	onfi_fill_interface_config(chip, &chip->interface_config, NAND_SDR_IFACE, 0);
 
 	ret = nand_dt_init(chip);
 	if (ret)
@@ -5971,13 +5972,13 @@ static int nand_scan_tail(struct nand_chip *chip)
 		mtd->bitflip_threshold = DIV_ROUND_UP(mtd->ecc_strength * 3, 4);
 
 	/* Find the fastest data interface for this chip */
-	ret = nand_choose_data_interface(chip);
+	ret = nand_choose_interface_config(chip);
 	if (ret)
 		goto err_nanddev_cleanup;
 
 	/* Enter fastest possible mode on all dies. */
 	for (i = 0; i < nanddev_ntargets(&chip->base); i++) {
-		ret = nand_setup_data_interface(chip, i);
+		ret = nand_setup_interface(chip, i);
 		if (ret)
 			goto err_nanddev_cleanup;
 	}
diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c
index fe769762e1d8..2bcc03714432 100644
--- a/drivers/mtd/nand/raw/nand_legacy.c
+++ b/drivers/mtd/nand/raw/nand_legacy.c
@@ -368,7 +368,7 @@ static void nand_ccs_delay(struct nand_chip *chip)
 	 * Wait tCCS_min if it is correctly defined, otherwise wait 500ns
 	 * (which should be safe for all NANDs).
 	 */
-	if (nand_controller_can_setup_data_iface(chip))
+	if (nand_controller_can_setup_interface(chip))
 		ndelay(sdr->tCCS_min / 1000);
 	else
 		ndelay(500);
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index efff3583c549..bf05b4bceaa0 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -19,7 +19,7 @@
  *
  * These four values are tweaked to be more accurate in the case of ONFI chips.
  */
-static const struct nand_data_interface onfi_sdr_timings[] = {
+static const struct nand_interface_config onfi_sdr_timings[] = {
 	/* Mode 0 */
 	{
 		.type = NAND_SDR_IFACE,
@@ -340,16 +340,17 @@ onfi_find_closest_sdr_mode(const struct nand_sdr_timings *spec_timings)
 }
 
 /**
- * onfi_fill_data_interface - Initialize a data interface from a given ONFI mode
+ * onfi_fill_interface_config - Initialize an interface config from a given
+ *                              ONFI mode
  * @chip: The NAND chip
- * @iface: The data interface to fill
- * @type: The data interface type
+ * @iface: The interface configuration to fill
+ * @type: The interface type
  * @timing_mode: The ONFI timing mode
  */
-int onfi_fill_data_interface(struct nand_chip *chip,
-			     struct nand_data_interface *iface,
-			     enum nand_data_interface_type type,
-			     unsigned int timing_mode)
+int onfi_fill_interface_config(struct nand_chip *chip,
+			       struct nand_interface_config *iface,
+			       enum nand_interface_type type,
+			       unsigned int timing_mode)
 {
 	struct onfi_params *onfi = chip->parameters.onfi;
 
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index f86dff311464..f121a3ae294c 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -808,8 +808,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 	return -ENODEV;
 }
 
-static int s3c2410_nand_setup_data_interface(struct nand_chip *chip, int csline,
-					const struct nand_data_interface *conf)
+static int s3c2410_nand_setup_interface(struct nand_chip *chip, int csline,
+					const struct nand_interface_config *conf)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
@@ -999,7 +999,7 @@ static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops s3c24xx_nand_controller_ops = {
 	.attach_chip = s3c2410_nand_attach_chip,
-	.setup_data_interface = s3c2410_nand_setup_data_interface,
+	.setup_interface = s3c2410_nand_setup_interface,
 };
 
 static const struct of_device_id s3c24xx_nand_dt_ids[] = {
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 7320c0fc19ec..a4140af43ed4 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1546,7 +1546,7 @@ static void stm32_fmc2_nfc_calc_timings(struct nand_chip *chip,
 }
 
 static int stm32_fmc2_nfc_setup_interface(struct nand_chip *chip, int chipnr,
-					  const struct nand_data_interface *conf)
+					  const struct nand_interface_config *conf)
 {
 	const struct nand_sdr_timings *sdrt;
 
@@ -1764,7 +1764,7 @@ static int stm32_fmc2_nfc_attach_chip(struct nand_chip *chip)
 static const struct nand_controller_ops stm32_fmc2_nfc_controller_ops = {
 	.attach_chip = stm32_fmc2_nfc_attach_chip,
 	.exec_op = stm32_fmc2_nfc_exec_op,
-	.setup_data_interface = stm32_fmc2_nfc_setup_interface,
+	.setup_interface = stm32_fmc2_nfc_setup_interface,
 };
 
 static int stm32_fmc2_nfc_parse_child(struct stm32_fmc2_nfc *nfc,
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index ffbc1651fadc..9c50c2b965e1 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1376,8 +1376,8 @@ static int _sunxi_nand_lookup_timing(const s32 *lut, int lut_size, u32 duration,
 #define sunxi_nand_lookup_timing(l, p, c) \
 			_sunxi_nand_lookup_timing(l, ARRAY_SIZE(l), p, c)
 
-static int sunxi_nfc_setup_data_interface(struct nand_chip *nand, int csline,
-					const struct nand_data_interface *conf)
+static int sunxi_nfc_setup_interface(struct nand_chip *nand, int csline,
+				     const struct nand_interface_config *conf)
 {
 	struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
 	struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
@@ -1920,7 +1920,7 @@ static int sunxi_nfc_exec_op(struct nand_chip *nand,
 
 static const struct nand_controller_ops sunxi_nand_controller_ops = {
 	.attach_chip = sunxi_nand_attach_chip,
-	.setup_data_interface = sunxi_nfc_setup_data_interface,
+	.setup_interface = sunxi_nfc_setup_interface,
 	.exec_op = sunxi_nfc_exec_op,
 };
 
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index 648dc7e77f6a..bdb965ae7a4a 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -515,7 +515,7 @@ static u32 to_ticks(int kHz, int ps)
 }
 
 static int tango_set_timings(struct nand_chip *chip, int csline,
-			     const struct nand_data_interface *conf)
+			     const struct nand_interface_config *conf)
 {
 	const struct nand_sdr_timings *sdr = nand_get_sdr_timings(conf);
 	struct tango_nfc *nfc = to_tango_nfc(chip->controller);
@@ -565,7 +565,7 @@ static int tango_attach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops tango_controller_ops = {
 	.attach_chip = tango_attach_chip,
-	.setup_data_interface = tango_set_timings,
+	.setup_interface = tango_set_timings,
 	.exec_op = tango_exec_op,
 };
 
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index f9d046b2cd3b..6b6212ffa01c 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -813,8 +813,8 @@ static void tegra_nand_setup_timing(struct tegra_nand_controller *ctrl,
 	writel_relaxed(reg, ctrl->regs + TIMING_2);
 }
 
-static int tegra_nand_setup_data_interface(struct nand_chip *chip, int csline,
-					const struct nand_data_interface *conf)
+static int tegra_nand_setup_interface(struct nand_chip *chip, int csline,
+				      const struct nand_interface_config *conf)
 {
 	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
 	const struct nand_sdr_timings *timings;
@@ -1053,7 +1053,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 static const struct nand_controller_ops tegra_nand_controller_ops = {
 	.attach_chip = &tegra_nand_attach_chip,
 	.exec_op = tegra_nand_exec_op,
-	.setup_data_interface = tegra_nand_setup_data_interface,
+	.setup_interface = tegra_nand_setup_interface,
 };
 
 static int tegra_nand_chips_init(struct device *dev,
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 0852df941130..2ca56eef0f07 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -492,22 +492,22 @@ struct nand_sdr_timings {
 };
 
 /**
- * enum nand_data_interface_type - NAND interface timing type
+ * enum nand_interface_type - NAND interface type
  * @NAND_SDR_IFACE:	Single Data Rate interface
  */
-enum nand_data_interface_type {
+enum nand_interface_type {
 	NAND_SDR_IFACE,
 };
 
 /**
- * struct nand_data_interface - NAND interface timing
+ * struct nand_interface_config - NAND interface timing
  * @type:	 type of the timing
  * @timings:	 The timing information
  * @timings.mode: Timing mode as defined in the specification
  * @timings.sdr: Use it when @type is %NAND_SDR_IFACE.
  */
-struct nand_data_interface {
-	enum nand_data_interface_type type;
+struct nand_interface_config {
+	enum nand_interface_type type;
 	struct nand_timings {
 		unsigned int mode;
 		union {
@@ -521,7 +521,7 @@ struct nand_data_interface {
  * @conf:	The data interface
  */
 static inline const struct nand_sdr_timings *
-nand_get_sdr_timings(const struct nand_data_interface *conf)
+nand_get_sdr_timings(const struct nand_interface_config *conf)
 {
 	if (conf->type != NAND_SDR_IFACE)
 		return ERR_PTR(-EINVAL);
@@ -944,11 +944,10 @@ static inline void nand_op_trace(const char *prefix,
  *		 This method replaces chip->legacy.cmdfunc(),
  *		 chip->legacy.{read,write}_{buf,byte,word}(),
  *		 chip->legacy.dev_ready() and chip->legacy.waifunc().
- * @setup_data_interface: setup the data interface and timing. If
- *			  chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this
- *			  means the configuration should not be applied but
- *			  only checked.
- *			  This hook is optional.
+ * @setup_interface: setup the data interface and timing. If chipnr is set to
+ *		     %NAND_DATA_IFACE_CHECK_ONLY this means the configuration
+ *		     should not be applied but only checked.
+ *		     This hook is optional.
  */
 struct nand_controller_ops {
 	int (*attach_chip)(struct nand_chip *chip);
@@ -956,8 +955,8 @@ struct nand_controller_ops {
 	int (*exec_op)(struct nand_chip *chip,
 		       const struct nand_operation *op,
 		       bool check_only);
-	int (*setup_data_interface)(struct nand_chip *chip, int chipnr,
-				    const struct nand_data_interface *conf);
+	int (*setup_interface)(struct nand_chip *chip, int chipnr,
+			       const struct nand_interface_config *conf);
 };
 
 /**
@@ -1070,7 +1069,7 @@ struct nand_manufacturer {
  * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the
  *			      actually used ONFI mode if the chip is ONFI
  *			      compliant or deduced from the datasheet otherwise
- * @data_interface: NAND interface timing information
+ * @interface_config: NAND interface timing information
  * @bbt_erase_shift: Number of address bits in a bbt entry
  * @bbt_options: Bad block table specific options. All options used here must
  *               come from bbm.h. By default, these options will be copied to
@@ -1118,7 +1117,7 @@ struct nand_chip {
 
 	/* Data interface */
 	int onfi_timing_mode_default;
-	struct nand_data_interface data_interface;
+	struct nand_interface_config interface_config;
 
 	/* Bad block information */
 	unsigned int bbt_erase_shift;
@@ -1208,10 +1207,10 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip)
  *                             of a NAND chip
  * @chip: The NAND chip
  */
-static inline const struct nand_data_interface *
+static inline const struct nand_interface_config *
 nand_get_interface_config(struct nand_chip *chip)
 {
-	return &chip->data_interface;
+	return &chip->interface_config;
 }
 
 /*
-- 
cgit v1.2.3


From 26d014f0400e5ff54cc80c8329e3adbd74db1e04 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:16 +0200
Subject: mtd: rawnand: Add the ->choose_interface_config() hook

This hook can be overloaded by NAND manufacturer drivers to propose
alternative timings when not following the main standards. In this
case, the manufacturer drivers is responsible for choosing the best
interface configuration that fits both the controller and chip
capabilities.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-23-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c | 17 +++++++++++------
 include/linux/mtd/rawnand.h      |  3 +++
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 742d099df5c6..2f4eba1a1082 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -1066,18 +1066,23 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
  * @chip: The NAND chip
  *
  * Find the best data interface and NAND timings supported by the chip
- * and the driver.
- * First tries to retrieve supported timing modes from ONFI information,
- * and if the NAND chip does not support ONFI, relies on the
- * ->onfi_timing_mode_default specified in the nand_ids table. After this
- * function nand_chip->interface_ is initialized with the best timing mode
- * available.
+ * and the driver. Eventually let the NAND manufacturer driver propose his own
+ * set of timings.
+ *
+ * After this function nand_chip->interface_config is initialized with the best
+ * timing mode available.
+ *
+ * Returns 0 for success or negative error code otherwise.
  */
 static int nand_choose_interface_config(struct nand_chip *chip)
 {
 	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
+	if (chip->ops.choose_interface_config)
+		return chip->ops.choose_interface_config(chip,
+							 &chip->interface_config);
+
 	return nand_choose_best_sdr_timings(chip, &chip->interface_config,
 					    NULL);
 }
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 2ca56eef0f07..316a02189da1 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1033,6 +1033,7 @@ struct nand_legacy {
  * @lock_area: Lock operation
  * @unlock_area: Unlock operation
  * @setup_read_retry: Set the read-retry mode (mostly needed for MLC NANDs)
+ * @choose_interface_config: Choose the best interface configuration
  */
 struct nand_chip_ops {
 	int (*suspend)(struct nand_chip *chip);
@@ -1040,6 +1041,8 @@ struct nand_chip_ops {
 	int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
 	int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len);
 	int (*setup_read_retry)(struct nand_chip *chip, int retry_mode);
+	int (*choose_interface_config)(struct nand_chip *chip,
+				       struct nand_interface_config *iface);
 };
 
 /**
-- 
cgit v1.2.3


From a69ad11168dca68b3f0adc6882422f4a2e2cb050 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:21 +0200
Subject: mtd: rawnand: Get rid of the default ONFI timing mode

The ->choose_interface() hook is here for manufacturer drivers to
provide a better timing interface than the default one, this field is
not needed anymore.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-28-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c | 19 ++++---------------
 include/linux/mtd/rawnand.h      |  9 ---------
 2 files changed, 4 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 2f4eba1a1082..753328f106c1 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -1012,10 +1012,8 @@ err_reset_chip:
  * @iface: the interface configuration (can eventually be updated)
  * @spec_timings: specific timings, when not fitting the ONFI specification
  *
- * If specific timings are provided, use them. Otherwise, try to retrieve
- * supported timing modes from ONFI information. Finally, if the NAND chip does
- * not follow the ONFI specification, rely on the ->default_timing_mode
- * specified in the nand_ids table.
+ * If specific timings are provided, use them. Otherwise, retrieve supported
+ * timing modes from ONFI information.
  */
 int nand_choose_best_sdr_timings(struct nand_chip *chip,
 				 struct nand_interface_config *iface,
@@ -1038,15 +1036,8 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
 
 		/* Fallback to slower modes */
 		best_mode = iface->timings.mode;
-	} else {
-		if (chip->parameters.onfi) {
-			unsigned int onfi_modes;
-
-			onfi_modes = chip->parameters.onfi->async_timing_mode;
-			best_mode = fls(onfi_modes) - 1;
-		} else {
-			best_mode = chip->onfi_timing_mode_default;
-		}
+	} else if (chip->parameters.onfi) {
+		best_mode = fls(chip->parameters.onfi->async_timing_mode) - 1;
 	}
 
 	for (mode = best_mode; mode >= 0; mode--) {
@@ -4767,8 +4758,6 @@ static bool find_full_id_nand(struct nand_chip *chip,
 		chip->options |= type->options;
 		chip->base.eccreq.strength = NAND_ECC_STRENGTH(type);
 		chip->base.eccreq.step_size = NAND_ECC_STEP(type);
-		chip->onfi_timing_mode_default =
-					type->onfi_timing_mode_default;
 
 		chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
 		if (!chip->parameters.model)
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 316a02189da1..a2427c67d38b 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1069,9 +1069,6 @@ struct nand_manufacturer {
  * @options: Various chip options. They can partly be set to inform nand_scan
  *           about special functionality. See the defines for further
  *           explanation.
- * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the
- *			      actually used ONFI mode if the chip is ONFI
- *			      compliant or deduced from the datasheet otherwise
  * @interface_config: NAND interface timing information
  * @bbt_erase_shift: Number of address bits in a bbt entry
  * @bbt_options: Bad block table specific options. All options used here must
@@ -1119,7 +1116,6 @@ struct nand_chip {
 	unsigned int options;
 
 	/* Data interface */
-	int onfi_timing_mode_default;
 	struct nand_interface_config interface_config;
 
 	/* Bad block information */
@@ -1268,10 +1264,6 @@ nand_get_interface_config(struct nand_chip *chip)
  *               @ecc_step_ds in nand_chip{}, also from the datasheet.
  *               For example, the "4bit ECC for each 512Byte" can be set with
  *               NAND_ECC_INFO(4, 512).
- * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND
- *			      reset. Should be deduced from timings described
- *			      in the datasheet.
- *
  */
 struct nand_flash_dev {
 	char *name;
@@ -1292,7 +1284,6 @@ struct nand_flash_dev {
 		uint16_t strength_ds;
 		uint16_t step_ds;
 	} ecc;
-	int onfi_timing_mode_default;
 };
 
 int nand_create_bbt(struct nand_chip *chip);
-- 
cgit v1.2.3


From 35b6bcc970f759d4a86d6221d09ca28ea20467c8 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 29 May 2020 13:13:22 +0200
Subject: mtd: rawnand: Allocate the interface configurations dynamically

Instead of manipulating the statically allocated structure and copy
timings around, allocate one at identification time and save it in the
nand_chip structure once it has been initialized.

All NAND chips using the same interface configuration during reset and
startup, we define a helper to retrieve a single reset interface
configuration object, shared across all NAND chips.

We use a second pointer to always have a reference on the currently
applied interface configuration, which may either point to the "best
interface configuration" or to the "default reset interface
configuration".

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-29-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/internals.h    |  1 +
 drivers/mtd/nand/raw/nand_base.c    | 84 +++++++++++++++++++++++--------------
 drivers/mtd/nand/raw/nand_timings.c |  6 +++
 include/linux/mtd/rawnand.h         | 11 +++--
 4 files changed, 67 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h
index 5ebfbb89e572..012876e14317 100644
--- a/drivers/mtd/nand/raw/internals.h
+++ b/drivers/mtd/nand/raw/internals.h
@@ -93,6 +93,7 @@ onfi_find_closest_sdr_mode(const struct nand_sdr_timings *spec_timings);
 int nand_choose_best_sdr_timings(struct nand_chip *chip,
 				 struct nand_interface_config *iface,
 				 struct nand_sdr_timings *spec_timings);
+const struct nand_interface_config *nand_get_reset_interface_config(void);
 int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param);
 int nand_set_features(struct nand_chip *chip, int addr, u8 *subfeature_param);
 int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf,
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 753328f106c1..0c768cb88f96 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -928,9 +928,9 @@ static int nand_reset_interface(struct nand_chip *chip, int chipnr)
 	 * timings to timing mode 0.
 	 */
 
-	onfi_fill_interface_config(chip, &chip->interface_config,
-				   NAND_SDR_IFACE, 0);
-	ret = ops->setup_interface(chip, chipnr, &chip->interface_config);
+	chip->current_interface_config = nand_get_reset_interface_config();
+	ret = ops->setup_interface(chip, chipnr,
+				   chip->current_interface_config);
 	if (ret)
 		pr_err("Failed to configure data interface to SDR timing mode 0\n");
 
@@ -949,13 +949,25 @@ static int nand_reset_interface(struct nand_chip *chip, int chipnr)
  */
 static int nand_setup_interface(struct nand_chip *chip, int chipnr)
 {
-	u8 mode = chip->interface_config.timings.mode;
-	u8 tmode_param[ONFI_SUBFEATURE_PARAM_LEN] = { mode, };
+	const struct nand_controller_ops *ops = chip->controller->ops;
+	u8 tmode_param[ONFI_SUBFEATURE_PARAM_LEN] = { };
 	int ret;
 
 	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
+	/*
+	 * A nand_reset_interface() put both the NAND chip and the NAND
+	 * controller in timings mode 0. If the default mode for this chip is
+	 * also 0, no need to proceed to the change again. Plus, at probe time,
+	 * nand_setup_interface() uses ->set/get_features() which would
+	 * fail anyway as the parameter page is not available yet.
+	 */
+	if (!chip->best_interface_config)
+		return 0;
+
+	tmode_param[0] = chip->best_interface_config->timings.mode;
+
 	/* Change the mode on the chip side (if supported by the NAND chip) */
 	if (nand_supports_set_features(chip, ONFI_FEATURE_ADDR_TIMING_MODE)) {
 		nand_select_target(chip, chipnr);
@@ -967,14 +979,13 @@ static int nand_setup_interface(struct nand_chip *chip, int chipnr)
 	}
 
 	/* Change the mode on the controller side */
-	ret = chip->controller->ops->setup_interface(chip, chipnr,
-						     &chip->interface_config);
+	ret = ops->setup_interface(chip, chipnr, chip->best_interface_config);
 	if (ret)
 		return ret;
 
 	/* Check the mode has been accepted by the chip, if supported */
 	if (!nand_supports_get_features(chip, ONFI_FEATURE_ADDR_TIMING_MODE))
-		return 0;
+		goto update_interface_config;
 
 	memset(tmode_param, 0, ONFI_SUBFEATURE_PARAM_LEN);
 	nand_select_target(chip, chipnr);
@@ -984,12 +995,15 @@ static int nand_setup_interface(struct nand_chip *chip, int chipnr)
 	if (ret)
 		goto err_reset_chip;
 
-	if (tmode_param[0] != mode) {
+	if (tmode_param[0] != chip->best_interface_config->timings.mode) {
 		pr_warn("timing mode %d not acknowledged by the NAND chip\n",
-			mode);
+			chip->best_interface_config->timings.mode);
 		goto err_reset_chip;
 	}
 
+update_interface_config:
+	chip->current_interface_config = chip->best_interface_config;
+
 	return 0;
 
 err_reset_chip:
@@ -1031,8 +1045,10 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
 		/* Verify the controller supports the requested interface */
 		ret = ops->setup_interface(chip, NAND_DATA_IFACE_CHECK_ONLY,
 					   iface);
-		if (!ret)
+		if (!ret) {
+			chip->best_interface_config = iface;
 			return ret;
+		}
 
 		/* Fallback to slower modes */
 		best_mode = iface->timings.mode;
@@ -1046,9 +1062,11 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
 		ret = ops->setup_interface(chip, NAND_DATA_IFACE_CHECK_ONLY,
 					   iface);
 		if (!ret)
-			return 0;
+			break;
 	}
 
+	chip->best_interface_config = iface;
+
 	return 0;
 }
 
@@ -1067,15 +1085,25 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
  */
 static int nand_choose_interface_config(struct nand_chip *chip)
 {
+	struct nand_interface_config *iface;
+	int ret;
+
 	if (!nand_controller_can_setup_interface(chip))
 		return 0;
 
+	iface = kzalloc(sizeof(*iface), GFP_KERNEL);
+	if (!iface)
+		return -ENOMEM;
+
 	if (chip->ops.choose_interface_config)
-		return chip->ops.choose_interface_config(chip,
-							 &chip->interface_config);
+		ret = chip->ops.choose_interface_config(chip, iface);
+	else
+		ret = nand_choose_best_sdr_timings(chip, iface, NULL);
 
-	return nand_choose_best_sdr_timings(chip, &chip->interface_config,
-					    NULL);
+	if (ret)
+		kfree(iface);
+
+	return ret;
 }
 
 /**
@@ -2501,7 +2529,6 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_len);
  */
 int nand_reset(struct nand_chip *chip, int chipnr)
 {
-	struct nand_interface_config saved_intf_config = chip->interface_config;
 	int ret;
 
 	ret = nand_reset_interface(chip, chipnr);
@@ -2519,18 +2546,6 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 	if (ret)
 		return ret;
 
-	/*
-	 * A nand_reset_interface() put both the NAND chip and the NAND
-	 * controller in timings mode 0. If the default mode for this chip is
-	 * also 0, no need to proceed to the change again. Plus, at probe time,
-	 * nand_setup_interface() uses ->set/get_features() which would
-	 * fail anyway as the parameter page is not available yet.
-	 */
-	if (!memcmp(&chip->interface_config, &saved_intf_config,
-		    sizeof(saved_intf_config)))
-		return 0;
-
-	chip->interface_config = saved_intf_config;
 	ret = nand_setup_interface(chip, chipnr);
 	if (ret)
 		return ret;
@@ -5198,7 +5213,7 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips,
 	mutex_init(&chip->lock);
 
 	/* Enforce the right timings for reset/detection */
-	onfi_fill_interface_config(chip, &chip->interface_config, NAND_SDR_IFACE, 0);
+	chip->current_interface_config = nand_get_reset_interface_config();
 
 	ret = nand_dt_init(chip);
 	if (ret)
@@ -5994,7 +6009,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 	for (i = 0; i < nanddev_ntargets(&chip->base); i++) {
 		ret = nand_setup_interface(chip, i);
 		if (ret)
-			goto err_nanddev_cleanup;
+			goto err_free_interface_config;
 	}
 
 	/* Check, if we should skip the bad block table scan */
@@ -6004,10 +6019,12 @@ static int nand_scan_tail(struct nand_chip *chip)
 	/* Build bad block table */
 	ret = nand_create_bbt(chip);
 	if (ret)
-		goto err_nanddev_cleanup;
+		goto err_free_interface_config;
 
 	return 0;
 
+err_free_interface_config:
+	kfree(chip->best_interface_config);
 
 err_nanddev_cleanup:
 	nanddev_cleanup(&chip->base);
@@ -6101,6 +6118,9 @@ void nand_cleanup(struct nand_chip *chip)
 			& NAND_BBT_DYNAMICSTRUCT)
 		kfree(chip->badblock_pattern);
 
+	/* Free the data interface */
+	kfree(chip->best_interface_config);
+
 	/* Free manufacturer priv data. */
 	nand_manufacturer_cleanup(chip);
 
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 1e22006c79ba..94d832646487 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -292,6 +292,12 @@ static const struct nand_interface_config onfi_sdr_timings[] = {
 	},
 };
 
+/* All NAND chips share the same reset data interface: SDR mode 0 */
+const struct nand_interface_config *nand_get_reset_interface_config(void)
+{
+	return &onfi_sdr_timings[0];
+}
+
 /**
  * onfi_find_closest_sdr_mode - Derive the closest ONFI SDR timing mode given a
  *                              set of timings
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index a2427c67d38b..a725b620aca2 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1069,7 +1069,11 @@ struct nand_manufacturer {
  * @options: Various chip options. They can partly be set to inform nand_scan
  *           about special functionality. See the defines for further
  *           explanation.
- * @interface_config: NAND interface timing information
+ * @current_interface_config: The currently used NAND interface configuration
+ * @best_interface_config: The best NAND interface configuration which fits both
+ *                         the NAND chip and NAND controller constraints. If
+ *                         unset, the default reset interface configuration must
+ *                         be used.
  * @bbt_erase_shift: Number of address bits in a bbt entry
  * @bbt_options: Bad block table specific options. All options used here must
  *               come from bbm.h. By default, these options will be copied to
@@ -1116,7 +1120,8 @@ struct nand_chip {
 	unsigned int options;
 
 	/* Data interface */
-	struct nand_interface_config interface_config;
+	const struct nand_interface_config *current_interface_config;
+	struct nand_interface_config *best_interface_config;
 
 	/* Bad block information */
 	unsigned int bbt_erase_shift;
@@ -1209,7 +1214,7 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip)
 static inline const struct nand_interface_config *
 nand_get_interface_config(struct nand_chip *chip)
 {
-	return &chip->interface_config;
+	return chip->current_interface_config;
 }
 
 /*
-- 
cgit v1.2.3


From 31d8fcac00fcf4007f3921edc69ab4dcb3abcd4d Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 25 Jun 2020 20:30:31 -0700
Subject: mm: workingset: age nonresident information alongside anonymous pages

Patch series "fix for "mm: balance LRU lists based on relative
thrashing" patchset"

This patchset fixes some problems of the patchset, "mm: balance LRU
lists based on relative thrashing", which is now merged on the mainline.

Patch "mm: workingset: let cache workingset challenge anon fix" is the
result of discussion with Johannes.  See following link.

  http://lkml.kernel.org/r/20200520232525.798933-6-hannes@cmpxchg.org

And, the other two are minor things which are found when I try to rebase
my patchset.

This patch (of 3):

After ("mm: workingset: let cache workingset challenge anon fix"), we
compare refault distances to active_file + anon.  But age of the
non-resident information is only driven by the file LRU.  As a result,
we may overestimate the recency of any incoming refaults and activate
them too eagerly, causing unnecessary LRU churn in certain situations.

Make anon aging drive nonresident age as well to address that.

Link: http://lkml.kernel.org/r/1592288204-27734-1-git-send-email-iamjoonsoo.kim@lge.com
Link: http://lkml.kernel.org/r/1592288204-27734-2-git-send-email-iamjoonsoo.kim@lge.com
Fixes: 34e58cac6d8f2a ("mm: workingset: let cache workingset challenge anon")
Reported-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |  4 ++--
 include/linux/swap.h   |  1 +
 mm/vmscan.c            |  3 +++
 mm/workingset.c        | 46 +++++++++++++++++++++++++++-------------------
 4 files changed, 33 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c4c37fd12104..f6f884970511 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -257,8 +257,8 @@ struct lruvec {
 	 */
 	unsigned long			anon_cost;
 	unsigned long			file_cost;
-	/* Evictions & activations on the inactive file list */
-	atomic_long_t			inactive_age;
+	/* Non-resident age, driven by LRU movement */
+	atomic_long_t			nonresident_age;
 	/* Refaults at the time of last reclaim cycle */
 	unsigned long			refaults;
 	/* Various lruvec state flags (enum lruvec_flags) */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4c5974bb9ba9..5b3216ba39a9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -313,6 +313,7 @@ struct vma_swap_readahead {
 };
 
 /* linux/mm/workingset.c */
+void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
 void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg);
 void workingset_refault(struct page *page, void *shadow);
 void workingset_activation(struct page *page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b6d84326bdf2..749d239c62b2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -904,6 +904,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		__delete_from_swap_cache(page, swap);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
+		workingset_eviction(page, target_memcg);
 	} else {
 		void (*freepage)(struct page *);
 		void *shadow = NULL;
@@ -1884,6 +1885,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 				list_add(&page->lru, &pages_to_free);
 		} else {
 			nr_moved += nr_pages;
+			if (PageActive(page))
+				workingset_age_nonresident(lruvec, nr_pages);
 		}
 	}
 
diff --git a/mm/workingset.c b/mm/workingset.c
index d481ea452eeb..50b7937bab32 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -156,8 +156,8 @@
  *
  *		Implementation
  *
- * For each node's file LRU lists, a counter for inactive evictions
- * and activations is maintained (node->inactive_age).
+ * For each node's LRU lists, a counter for inactive evictions and
+ * activations is maintained (node->nonresident_age).
  *
  * On eviction, a snapshot of this counter (along with some bits to
  * identify the node) is stored in the now empty page cache
@@ -213,7 +213,17 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 	*workingsetp = workingset;
 }
 
-static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat)
+/**
+ * workingset_age_nonresident - age non-resident entries as LRU ages
+ * @memcg: the lruvec that was aged
+ * @nr_pages: the number of pages to count
+ *
+ * As in-memory pages are aged, non-resident pages need to be aged as
+ * well, in order for the refault distances later on to be comparable
+ * to the in-memory dimensions. This function allows reclaim and LRU
+ * operations to drive the non-resident aging along in parallel.
+ */
+void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
 {
 	/*
 	 * Reclaiming a cgroup means reclaiming all its children in a
@@ -227,11 +237,8 @@ static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat)
 	 * the root cgroup's, age as well.
 	 */
 	do {
-		struct lruvec *lruvec;
-
-		lruvec = mem_cgroup_lruvec(memcg, pgdat);
-		atomic_long_inc(&lruvec->inactive_age);
-	} while (memcg && (memcg = parent_mem_cgroup(memcg)));
+		atomic_long_add(nr_pages, &lruvec->nonresident_age);
+	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
 /**
@@ -254,12 +261,11 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	advance_inactive_age(page_memcg(page), pgdat);
-
 	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 	/* XXX: target_memcg can be NULL, go through lruvec */
 	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
-	eviction = atomic_long_read(&lruvec->inactive_age);
+	eviction = atomic_long_read(&lruvec->nonresident_age);
 	return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
 }
 
@@ -309,20 +315,20 @@ void workingset_refault(struct page *page, void *shadow)
 	if (!mem_cgroup_disabled() && !eviction_memcg)
 		goto out;
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
-	refault = atomic_long_read(&eviction_lruvec->inactive_age);
+	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
 
 	/*
 	 * Calculate the refault distance
 	 *
 	 * The unsigned subtraction here gives an accurate distance
-	 * across inactive_age overflows in most cases. There is a
+	 * across nonresident_age overflows in most cases. There is a
 	 * special case: usually, shadow entries have a short lifetime
 	 * and are either refaulted or reclaimed along with the inode
 	 * before they get too old.  But it is not impossible for the
-	 * inactive_age to lap a shadow entry in the field, which can
-	 * then result in a false small refault distance, leading to a
-	 * false activation should this old entry actually refault
-	 * again.  However, earlier kernels used to deactivate
+	 * nonresident_age to lap a shadow entry in the field, which
+	 * can then result in a false small refault distance, leading
+	 * to a false activation should this old entry actually
+	 * refault again.  However, earlier kernels used to deactivate
 	 * unconditionally with *every* reclaim invocation for the
 	 * longest time, so the occasional inappropriate activation
 	 * leading to pressure on the active list is not a problem.
@@ -359,7 +365,7 @@ void workingset_refault(struct page *page, void *shadow)
 		goto out;
 
 	SetPageActive(page);
-	advance_inactive_age(memcg, pgdat);
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
 
 	/* Page was active prior to eviction */
@@ -382,6 +388,7 @@ out:
 void workingset_activation(struct page *page)
 {
 	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	/*
@@ -394,7 +401,8 @@ void workingset_activation(struct page *page)
 	memcg = page_memcg_rcu(page);
 	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
-	advance_inactive_age(memcg, page_pgdat(page));
+	lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 out:
 	rcu_read_unlock();
 }
-- 
cgit v1.2.3


From 7a0e27b2a0ce2735e27e21ebc8b777550fe0ed81 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 25 Jun 2020 20:30:47 -0700
Subject: mm: remove vmalloc_exec

Merge vmalloc_exec into its only caller.  Note that for !CONFIG_MMU
__vmalloc_node_range maps to __vmalloc, which directly clears the
__GFP_HIGHMEM added by the vmalloc_exec stub anyway.

Link: http://lkml.kernel.org/r/20200618064307.32739-4-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  1 -
 kernel/module.c         |  4 +++-
 mm/nommu.c              | 17 -----------------
 mm/vmalloc.c            | 20 --------------------
 4 files changed, 3 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 48bb681e6c2a..0221f852a7e1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size);
 extern void *vmalloc_user(unsigned long size);
 extern void *vmalloc_node(unsigned long size, int node);
 extern void *vzalloc_node(unsigned long size, int node);
-extern void *vmalloc_exec(unsigned long size);
 extern void *vmalloc_32(unsigned long size);
 extern void *vmalloc_32_user(unsigned long size);
 extern void *__vmalloc(unsigned long size, gfp_t gfp_mask);
diff --git a/kernel/module.c b/kernel/module.c
index e8a198588f26..0c6573b98c36 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2783,7 +2783,9 @@ static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug)
 
 void * __weak module_alloc(unsigned long size)
 {
-	return vmalloc_exec(size);
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __func__);
 }
 
 bool __weak module_init_section(const char *name)
diff --git a/mm/nommu.c b/mm/nommu.c
index cdcad5d61dd1..f32a69095d50 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -290,23 +290,6 @@ void *vzalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vzalloc_node);
 
-/**
- *	vmalloc_exec  -  allocate virtually contiguous, executable memory
- *	@size:		allocation size
- *
- *	Kernel-internal function to allocate enough pages to cover @size
- *	the page level allocator and map them into contiguous and
- *	executable kernel virtual space.
- *
- *	For tight control over page level allocator and protection flags
- *	use __vmalloc() instead.
- */
-
-void *vmalloc_exec(unsigned long size)
-{
-	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM);
-}
-
 /**
  * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
  *	@size:		allocation size
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 957a0be77270..5a2b55c8dd9a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2695,26 +2695,6 @@ void *vzalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vzalloc_node);
 
-/**
- * vmalloc_exec - allocate virtually contiguous, executable memory
- * @size:	  allocation size
- *
- * Kernel-internal function to allocate enough pages to cover @size
- * the page level allocator and map them into contiguous and
- * executable kernel virtual space.
- *
- * For tight control over page level allocator and protection flags
- * use __vmalloc() instead.
- *
- * Return: pointer to the allocated memory or %NULL on error
- */
-void *vmalloc_exec(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
-			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
-			NUMA_NO_NODE, __builtin_return_address(0));
-}
-
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
 #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
 #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
-- 
cgit v1.2.3


From 5946d1f5b309381805bad3ddc3054c04f4ae9c24 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Thu, 4 Jun 2020 15:31:19 +0530
Subject: kdb: Switch to use safer dbg_io_ops over console APIs

In kgdb context, calling console handlers aren't safe due to locks used
in those handlers which could in turn lead to a deadlock. Although, using
oops_in_progress increases the chance to bypass locks in most console
handlers but it might not be sufficient enough in case a console uses
more locks (VT/TTY is good example).

Currently when a driver provides both polling I/O and a console then kdb
will output using the console. We can increase robustness by using the
currently active polling I/O driver (which should be lockless) instead
of the corresponding console. For several common cases (e.g. an
embedded system with a single serial port that is used both for console
output and debugger I/O) this will result in no console handler being
used.

In order to achieve this we need to reverse the order of preference to
use dbg_io_ops (uses polling I/O mode) over console APIs. So we just
store "struct console" that represents debugger I/O in dbg_io_ops and
while emitting kdb messages, skip console that matches dbg_io_ops
console in order to avoid duplicate messages. After this change,
"is_console" param becomes redundant and hence removed.

Suggested-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Link: https://lore.kernel.org/r/1591264879-25920-5-git-send-email-sumit.garg@linaro.org
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
---
 drivers/tty/serial/kgdb_nmi.c |  2 +-
 drivers/tty/serial/kgdboc.c   | 32 ++++++++++++++++----------------
 drivers/usb/early/ehci-dbgp.c |  3 ++-
 include/linux/kgdb.h          |  5 ++---
 kernel/debug/kdb/kdb_io.c     |  4 +++-
 5 files changed, 24 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c
index 5022447afa23..6004c0c1d173 100644
--- a/drivers/tty/serial/kgdb_nmi.c
+++ b/drivers/tty/serial/kgdb_nmi.c
@@ -50,7 +50,7 @@ static int kgdb_nmi_console_setup(struct console *co, char *options)
 	 * I/O utilities that messages sent to the console will automatically
 	 * be displayed on the dbg_io.
 	 */
-	dbg_io_ops->is_console = true;
+	dbg_io_ops->cons = co;
 
 	return 0;
 }
diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c
index 41396982e9e0..84ffede27f23 100644
--- a/drivers/tty/serial/kgdboc.c
+++ b/drivers/tty/serial/kgdboc.c
@@ -45,7 +45,6 @@ static struct platform_device *kgdboc_pdev;
 
 #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE)
 static struct kgdb_io		kgdboc_earlycon_io_ops;
-static struct console		*earlycon;
 static int                      (*earlycon_orig_exit)(struct console *con);
 #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */
 
@@ -145,7 +144,7 @@ static void kgdboc_unregister_kbd(void)
 #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE)
 static void cleanup_earlycon(void)
 {
-	if (earlycon)
+	if (kgdboc_earlycon_io_ops.cons)
 		kgdb_unregister_io_module(&kgdboc_earlycon_io_ops);
 }
 #else /* !IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */
@@ -178,7 +177,7 @@ static int configure_kgdboc(void)
 		goto noconfig;
 	}
 
-	kgdboc_io_ops.is_console = 0;
+	kgdboc_io_ops.cons = NULL;
 	kgdb_tty_driver = NULL;
 
 	kgdboc_use_kms = 0;
@@ -198,7 +197,7 @@ static int configure_kgdboc(void)
 		int idx;
 		if (cons->device && cons->device(cons, &idx) == p &&
 		    idx == tty_line) {
-			kgdboc_io_ops.is_console = 1;
+			kgdboc_io_ops.cons = cons;
 			break;
 		}
 	}
@@ -433,7 +432,8 @@ static int kgdboc_earlycon_get_char(void)
 {
 	char c;
 
-	if (!earlycon->read(earlycon, &c, 1))
+	if (!kgdboc_earlycon_io_ops.cons->read(kgdboc_earlycon_io_ops.cons,
+					       &c, 1))
 		return NO_POLL_CHAR;
 
 	return c;
@@ -441,7 +441,8 @@ static int kgdboc_earlycon_get_char(void)
 
 static void kgdboc_earlycon_put_char(u8 chr)
 {
-	earlycon->write(earlycon, &chr, 1);
+	kgdboc_earlycon_io_ops.cons->write(kgdboc_earlycon_io_ops.cons, &chr,
+					   1);
 }
 
 static void kgdboc_earlycon_pre_exp_handler(void)
@@ -461,7 +462,7 @@ static void kgdboc_earlycon_pre_exp_handler(void)
 	 * boot if we detect this case.
 	 */
 	for_each_console(con)
-		if (con == earlycon)
+		if (con == kgdboc_earlycon_io_ops.cons)
 			return;
 
 	already_warned = true;
@@ -484,25 +485,25 @@ static int kgdboc_earlycon_deferred_exit(struct console *con)
 
 static void kgdboc_earlycon_deinit(void)
 {
-	if (!earlycon)
+	if (!kgdboc_earlycon_io_ops.cons)
 		return;
 
-	if (earlycon->exit == kgdboc_earlycon_deferred_exit)
+	if (kgdboc_earlycon_io_ops.cons->exit == kgdboc_earlycon_deferred_exit)
 		/*
 		 * kgdboc_earlycon is exiting but original boot console exit
 		 * was never called (AKA kgdboc_earlycon_deferred_exit()
 		 * didn't ever run).  Undo our trap.
 		 */
-		earlycon->exit = earlycon_orig_exit;
-	else if (earlycon->exit)
+		kgdboc_earlycon_io_ops.cons->exit = earlycon_orig_exit;
+	else if (kgdboc_earlycon_io_ops.cons->exit)
 		/*
 		 * We skipped calling the exit() routine so we could try to
 		 * keep using the boot console even after it went away.  We're
 		 * finally done so call the function now.
 		 */
-		earlycon->exit(earlycon);
+		kgdboc_earlycon_io_ops.cons->exit(kgdboc_earlycon_io_ops.cons);
 
-	earlycon = NULL;
+	kgdboc_earlycon_io_ops.cons = NULL;
 }
 
 static struct kgdb_io kgdboc_earlycon_io_ops = {
@@ -511,7 +512,6 @@ static struct kgdb_io kgdboc_earlycon_io_ops = {
 	.write_char		= kgdboc_earlycon_put_char,
 	.pre_exception		= kgdboc_earlycon_pre_exp_handler,
 	.deinit			= kgdboc_earlycon_deinit,
-	.is_console		= true,
 };
 
 #define MAX_CONSOLE_NAME_LEN (sizeof((struct console *) 0)->name)
@@ -557,10 +557,10 @@ static int __init kgdboc_earlycon_init(char *opt)
 		goto unlock;
 	}
 
-	earlycon = con;
+	kgdboc_earlycon_io_ops.cons = con;
 	pr_info("Going to register kgdb with earlycon '%s'\n", con->name);
 	if (kgdb_register_io_module(&kgdboc_earlycon_io_ops) != 0) {
-		earlycon = NULL;
+		kgdboc_earlycon_io_ops.cons = NULL;
 		pr_info("Failed to register kgdb with earlycon\n");
 	} else {
 		/* Trap exit so we can keep earlycon longer if needed. */
diff --git a/drivers/usb/early/ehci-dbgp.c b/drivers/usb/early/ehci-dbgp.c
index ea0d531c63e2..775cf70cfb3e 100644
--- a/drivers/usb/early/ehci-dbgp.c
+++ b/drivers/usb/early/ehci-dbgp.c
@@ -1058,7 +1058,8 @@ static int __init kgdbdbgp_parse_config(char *str)
 		kgdbdbgp_wait_time = simple_strtoul(ptr, &ptr, 10);
 	}
 	kgdb_register_io_module(&kgdbdbgp_io_ops);
-	kgdbdbgp_io_ops.is_console = early_dbgp_console.index != -1;
+	if (early_dbgp_console.index != -1)
+		kgdbdbgp_io_ops.cons = &early_dbgp_console;
 
 	return 0;
 }
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index c62d76478adc..529116b0cabe 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -276,8 +276,7 @@ struct kgdb_arch {
  * the I/O driver.
  * @post_exception: Pointer to a function that will do any cleanup work
  * for the I/O driver.
- * @is_console: 1 if the end device is a console 0 if the I/O device is
- * not a console
+ * @cons: valid if the I/O device is a console; else NULL.
  */
 struct kgdb_io {
 	const char		*name;
@@ -288,7 +287,7 @@ struct kgdb_io {
 	void			(*deinit) (void);
 	void			(*pre_exception) (void);
 	void			(*post_exception) (void);
-	int			is_console;
+	struct console		*cons;
 };
 
 extern const struct kgdb_arch		arch_kgdb_ops;
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 0e4f2eda96d8..683a799618ad 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -549,7 +549,7 @@ static void kdb_msg_write(const char *msg, int msg_len)
 	if (msg_len == 0)
 		return;
 
-	if (dbg_io_ops && !dbg_io_ops->is_console) {
+	if (dbg_io_ops) {
 		const char *cp = msg;
 		int len = msg_len;
 
@@ -562,6 +562,8 @@ static void kdb_msg_write(const char *msg, int msg_len)
 	for_each_console(c) {
 		if (!(c->flags & CON_ENABLED))
 			continue;
+		if (c == dbg_io_ops->cons)
+			continue;
 		/*
 		 * Set oops_in_progress to encourage the console drivers to
 		 * disregard their internal spin locks: in the current calling
-- 
cgit v1.2.3


From 5c45a918263e4da142b9cf40a1dfcb4134d454a2 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 23 Jun 2020 09:08:59 +0200
Subject: net: netdevice.h: add a description for napi_defer_hard_irqs

Changeset 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")
added a new element at struct net_device.

Add a description for it, based on what's described at the changeset
which added such feature.

Fixes: 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/807a3840e7bc1562adefadb0535c9f47e6ab52e0.1592895969.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/netdevice.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6fc613ed8eae..f3ca52958a17 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1742,6 +1742,8 @@ enum netdev_priv_flags {
  *	@real_num_rx_queues: 	Number of RX queues currently active in device
  *	@xdp_prog:		XDP sockets filter program pointer
  *	@gro_flush_timeout:	timeout for GRO layer in NAPI
+ *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
+ *				allow to avoid NIC hard IRQ, on busy queues.
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
-- 
cgit v1.2.3


From 5d682f5ec9d1c49e7fe2945e586aa264692859f0 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 23 Jun 2020 09:09:01 +0200
Subject: net: pylink.h: add kernel-doc descriptions for new fields at
 phylink_config

Some fields were moved from struct phylink into phylink_config.
Update the kernel-doc markups for the config struct accordingly

Fixes: 5c05c1dbb177 ("net: phylink, dsa: eliminate phylink_fixed_state_cb()")
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/34970f447ff86415a6cef10a785fbef81c2819a7.1592895969.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/phylink.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index cc5b452a184e..02ff1419d4be 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -62,6 +62,10 @@ enum phylink_op_type {
  * @dev: a pointer to a struct device associated with the MAC
  * @type: operation type of PHYLINK instance
  * @pcs_poll: MAC PCS cannot provide link change interrupt
+ * @poll_fixed_state: if true, starts link_poll,
+ *		      if MAC link is at %MLO_AN_FIXED mode.
+ * @get_fixed_state: callback to execute to determine the fixed link state,
+ *		     if MAC link is at %MLO_AN_FIXED mode.
  */
 struct phylink_config {
 	struct device *dev;
-- 
cgit v1.2.3


From 21b9cb34385d93d661a9134adf19eae2bd734218 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 23 Jun 2020 09:09:03 +0200
Subject: fs: fs.h: fix a kernel-doc parameter description

Changeset 3b0311e7ca71 ("vfs: track per-sb writeback errors and report them to syncfs")
added a variant of filemap_sample_wb_err(), but it forgot to
rename the arguments at the kernel-doc markup. Fix it.

Fix those warnings:
	./include/linux/fs.h:2845: warning: Function parameter or member 'file' not described in 'file_sample_sb_err'
	./include/linux/fs.h:2845: warning: Excess function parameter 'mapping' description in 'file_sample_sb_err'

Fixes: 3b0311e7ca71 ("vfs: track per-sb writeback errors and report them to syncfs")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/7b33bbceb29ac80874622a2bc84127bb10103245.1592895969.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6c4ab4dc1cd7..7e17ecc461d5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2829,7 +2829,7 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
 
 /**
  * file_sample_sb_err - sample the current errseq_t to test for later errors
- * @mapping: mapping to be sampled
+ * @file: file pointer to be sampled
  *
  * Grab the most current superblock-level errseq_t value for the given
  * struct file.
-- 
cgit v1.2.3


From 15d737f8a14e73fcf25f6f797630279a203ce99c Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 23 Jun 2020 09:09:04 +0200
Subject: kcsan: fix a kernel-doc warning

One of the kernel-doc markups there have two "note" sections:

	./include/linux/kcsan-checks.h:346: warning: duplicate section name 'Note'

While this is not the case here, duplicated sections can cause
build issues on Sphinx. So, let's change the notes section
to use, instead, a list for those 2 notes at the same function.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20f7995fab2ba85ce723203e9a7c822a55cca2af.1592895969.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/kcsan-checks.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h
index 7b0b9c44f5f3..c5f6c1dcf7e3 100644
--- a/include/linux/kcsan-checks.h
+++ b/include/linux/kcsan-checks.h
@@ -337,11 +337,13 @@ static inline void __kcsan_disable_current(void) { }
  *		release_for_reuse(obj);
  *	}
  *
- * Note: ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough
- * checking if a clear scope where no concurrent accesses are expected exists.
+ * Note:
  *
- * Note: For cases where the object is freed, `KASAN <kasan.html>`_ is a better
- * fit to detect use-after-free bugs.
+ * 1. ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough
+ *    checking if a clear scope where no concurrent accesses are expected exists.
+ *
+ * 2. For cases where the object is freed, `KASAN <kasan.html>`_ is a better
+ *    fit to detect use-after-free bugs.
  *
  * @var: variable to assert on
  */
-- 
cgit v1.2.3


From 985098a05eee6bf5caca7e997e02a5b15242cfa0 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 23 Jun 2020 09:09:10 +0200
Subject: docs: fix references for DMA*.txt files

As we moved those files to core-api, fix references to point
to their newer locations.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/37b2fd159fbc7655dbf33b3eb1215396a25f6344.1592895969.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/PCI/pci.rst                            |  6 +++---
 Documentation/block/biodoc.rst                       |  2 +-
 Documentation/bus-virt-phys-mapping.txt              |  2 +-
 Documentation/core-api/dma-api.rst                   |  6 +++---
 Documentation/core-api/dma-isa-lpc.rst               |  2 +-
 Documentation/driver-api/usb/dma.rst                 |  6 +++---
 Documentation/translations/ko_KR/memory-barriers.txt |  6 +++---
 arch/ia64/hp/common/sba_iommu.c                      | 12 ++++++------
 arch/parisc/kernel/pci-dma.c                         |  2 +-
 arch/x86/include/asm/dma-mapping.h                   |  4 ++--
 arch/x86/kernel/amd_gart_64.c                        |  2 +-
 drivers/parisc/sba_iommu.c                           | 14 +++++++-------
 include/linux/dma-mapping.h                          |  2 +-
 include/media/videobuf-dma-sg.h                      |  2 +-
 kernel/dma/debug.c                                   |  2 +-
 15 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/PCI/pci.rst b/Documentation/PCI/pci.rst
index 8c016d8c9862..d10d3fe604c5 100644
--- a/Documentation/PCI/pci.rst
+++ b/Documentation/PCI/pci.rst
@@ -265,7 +265,7 @@ Set the DMA mask size
 ---------------------
 .. note::
    If anything below doesn't make sense, please refer to
-   Documentation/DMA-API.txt. This section is just a reminder that
+   :doc:`/core-api/dma-api`. This section is just a reminder that
    drivers need to indicate DMA capabilities of the device and is not
    an authoritative source for DMA interfaces.
 
@@ -291,7 +291,7 @@ Many 64-bit "PCI" devices (before PCI-X) and some PCI-X devices are
 Setup shared control data
 -------------------------
 Once the DMA masks are set, the driver can allocate "consistent" (a.k.a. shared)
-memory.  See Documentation/DMA-API.txt for a full description of
+memory.  See :doc:`/core-api/dma-api` for a full description of
 the DMA APIs. This section is just a reminder that it needs to be done
 before enabling DMA on the device.
 
@@ -421,7 +421,7 @@ owners if there is one.
 
 Then clean up "consistent" buffers which contain the control data.
 
-See Documentation/DMA-API.txt for details on unmapping interfaces.
+See :doc:`/core-api/dma-api` for details on unmapping interfaces.
 
 
 Unregister from other subsystems
diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst
index b964796ec9c7..ba7f45d0271c 100644
--- a/Documentation/block/biodoc.rst
+++ b/Documentation/block/biodoc.rst
@@ -196,7 +196,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/DMA-API-HOWTO.txt for a discussion
+Note: Please refer to :doc:`/core-api/dma-api-howto` for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/bus-virt-phys-mapping.txt b/Documentation/bus-virt-phys-mapping.txt
index 4bb07c2f3e7d..c7bc99cd2e21 100644
--- a/Documentation/bus-virt-phys-mapping.txt
+++ b/Documentation/bus-virt-phys-mapping.txt
@@ -8,7 +8,7 @@ How to access I/O mapped memory from within device drivers
 
 	The virt_to_bus() and bus_to_virt() functions have been
 	superseded by the functionality provided by the PCI DMA interface
-	(see Documentation/DMA-API-HOWTO.txt).  They continue
+	(see :doc:`/core-api/dma-api-howto`).  They continue
 	to be documented below for historical purposes, but new code
 	must not use them. --davidm 00/12/12
 
diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 2d8d2fed7317..63b4a2f20867 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -5,7 +5,7 @@ Dynamic DMA mapping using the generic device
 :Author: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 
 This document describes the DMA API.  For a more gentle introduction
-of the API (and actual examples), see Documentation/DMA-API-HOWTO.txt.
+of the API (and actual examples), see :doc:`/core-api/dma-api-howto`.
 
 This API is split into two pieces.  Part I describes the basic API.
 Part II describes extensions for supporting non-consistent memory
@@ -471,7 +471,7 @@ without the _attrs suffixes, except that they pass an optional
 dma_attrs.
 
 The interpretation of DMA attributes is architecture-specific, and
-each attribute should be documented in Documentation/DMA-attributes.txt.
+each attribute should be documented in :doc:`/core-api/dma-attributes`.
 
 If dma_attrs are 0, the semantics of each of these functions
 is identical to those of the corresponding function
@@ -484,7 +484,7 @@ for DMA::
 
 	#include <linux/dma-mapping.h>
 	/* DMA_ATTR_FOO should be defined in linux/dma-mapping.h and
-	* documented in Documentation/DMA-attributes.txt */
+	* documented in Documentation/core-api/dma-attributes.rst */
 	...
 
 		unsigned long attr;
diff --git a/Documentation/core-api/dma-isa-lpc.rst b/Documentation/core-api/dma-isa-lpc.rst
index b1ec7b16c21f..e59a3d35a93d 100644
--- a/Documentation/core-api/dma-isa-lpc.rst
+++ b/Documentation/core-api/dma-isa-lpc.rst
@@ -17,7 +17,7 @@ To do ISA style DMA you need to include two headers::
 	#include <asm/dma.h>
 
 The first is the generic DMA API used to convert virtual addresses to
-bus addresses (see Documentation/DMA-API.txt for details).
+bus addresses (see :doc:`/core-api/dma-api` for details).
 
 The second contains the routines specific to ISA DMA transfers. Since
 this is not present on all platforms make sure you construct your
diff --git a/Documentation/driver-api/usb/dma.rst b/Documentation/driver-api/usb/dma.rst
index 59d5aee89e37..2b3dbd3265b4 100644
--- a/Documentation/driver-api/usb/dma.rst
+++ b/Documentation/driver-api/usb/dma.rst
@@ -10,7 +10,7 @@ API overview
 
 The big picture is that USB drivers can continue to ignore most DMA issues,
 though they still must provide DMA-ready buffers (see
-``Documentation/DMA-API-HOWTO.txt``).  That's how they've worked through
+:doc:`/core-api/dma-api-howto`).  That's how they've worked through
 the 2.4 (and earlier) kernels, or they can now be DMA-aware.
 
 DMA-aware usb drivers:
@@ -60,7 +60,7 @@ and effects like cache-trashing can impose subtle penalties.
   force a consistent memory access ordering by using memory barriers.  It's
   not using a streaming DMA mapping, so it's good for small transfers on
   systems where the I/O would otherwise thrash an IOMMU mapping.  (See
-  ``Documentation/DMA-API-HOWTO.txt`` for definitions of "coherent" and
+  :doc:`/core-api/dma-api-howto` for definitions of "coherent" and
   "streaming" DMA mappings.)
 
   Asking for 1/Nth of a page (as well as asking for N pages) is reasonably
@@ -91,7 +91,7 @@ Working with existing buffers
 Existing buffers aren't usable for DMA without first being mapped into the
 DMA address space of the device.  However, most buffers passed to your
 driver can safely be used with such DMA mapping.  (See the first section
-of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
+of :doc:`/core-api/dma-api-howto`, titled "What memory is DMA-able?")
 
 - When you're using scatterlists, you can map everything at once.  On some
   systems, this kicks in an IOMMU and turns the scatterlists into single
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 34d041d68f78..604cee350e53 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -570,8 +570,8 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE 
 	[*] 버스 마스터링 DMA 와 일관성에 대해서는 다음을 참고하시기 바랍니다:
 
 	    Documentation/driver-api/pci/pci.rst
-	    Documentation/DMA-API-HOWTO.txt
-	    Documentation/DMA-API.txt
+	    Documentation/core-api/dma-api-howto.rst
+	    Documentation/core-api/dma-api.rst
 
 
 데이터 의존성 배리어 (역사적)
@@ -1907,7 +1907,7 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효
 
      writel_relaxed() 와 같은 완화된 I/O 접근자들에 대한 자세한 내용을 위해서는
      "커널 I/O 배리어의 효과" 섹션을, consistent memory 에 대한 자세한 내용을
-     위해선 Documentation/DMA-API.txt 문서를 참고하세요.
+     위해선 Documentation/core-api/dma-api.rst 문서를 참고하세요.
 
 
 =========================
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index a806227c1fad..656a4888c300 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -907,7 +907,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
  * @dir: dma direction
  * @attrs: optional dma attributes
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static dma_addr_t sba_map_page(struct device *dev, struct page *page,
 			       unsigned long poff, size_t size,
@@ -1028,7 +1028,7 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size)
  * @dir:  R/W or both.
  * @attrs: optional dma attributes
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
 			   enum dma_data_direction dir, unsigned long attrs)
@@ -1105,7 +1105,7 @@ static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
  * @size:  number of bytes mapped in driver buffer.
  * @dma_handle:  IOVA of new buffer.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void *
 sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
@@ -1162,7 +1162,7 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
  * @vaddr:  virtual address IOVA of "consistent" buffer.
  * @dma_handler:  IO virtual address of "consistent" buffer.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void sba_free_coherent(struct device *dev, size_t size, void *vaddr,
 			      dma_addr_t dma_handle, unsigned long attrs)
@@ -1425,7 +1425,7 @@ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
  * @dir:  R/W or both.
  * @attrs: optional dma attributes
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
 			    int nents, enum dma_data_direction dir,
@@ -1524,7 +1524,7 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
  * @dir:  R/W or both.
  * @attrs: optional dma attributes
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
 			       int nents, enum dma_data_direction dir,
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 70cd24bdcfec..4f1596bb1936 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -3,7 +3,7 @@
 ** PARISC 1.1 Dynamic DMA mapping support.
 ** This implementation is for PA-RISC platforms that do not support
 ** I/O TLBs (aka DMA address translation hardware).
-** See Documentation/DMA-API-HOWTO.txt for interface definitions.
+** See Documentation/core-api/dma-api-howto.rst for interface definitions.
 **
 **      (c) Copyright 1999,2000 Hewlett-Packard Company
 **      (c) Copyright 2000 Grant Grundler
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 6b15a24930e0..fed67eafcacc 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -3,8 +3,8 @@
 #define _ASM_X86_DMA_MAPPING_H
 
 /*
- * IOMMU interface. See Documentation/DMA-API-HOWTO.txt and
- * Documentation/DMA-API.txt for documentation.
+ * IOMMU interface. See Documentation/core-api/dma-api-howto.rst and
+ * Documentation/core-api/dma-api.rst for documentation.
  */
 
 #include <linux/scatterlist.h>
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 17cb5b933dcf..e89031e9c847 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -6,7 +6,7 @@
  * This allows to use PCI devices that only support 32bit addresses on systems
  * with more than 4GB.
  *
- * See Documentation/DMA-API-HOWTO.txt for the interface specification.
+ * See Documentation/core-api/dma-api-howto.rst for the interface specification.
  *
  * Copyright 2002 Andi Kleen, SuSE Labs.
  */
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 7e112829d250..5368452eb5a6 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -666,7 +666,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
  * @dev: instance of PCI owned by the driver that's asking
  * @mask:  number of address bits this PCI device can handle
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static int sba_dma_supported( struct device *dev, u64 mask)
 {
@@ -698,7 +698,7 @@ static int sba_dma_supported( struct device *dev, u64 mask)
  * @size:  number of bytes to map in driver buffer.
  * @direction:  R/W or both.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static dma_addr_t
 sba_map_single(struct device *dev, void *addr, size_t size,
@@ -788,7 +788,7 @@ sba_map_page(struct device *dev, struct page *page, unsigned long offset,
  * @size:  number of bytes mapped in driver buffer.
  * @direction:  R/W or both.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void
 sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
@@ -867,7 +867,7 @@ sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
  * @size:  number of bytes mapped in driver buffer.
  * @dma_handle:  IOVA of new buffer.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void *sba_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
@@ -898,7 +898,7 @@ static void *sba_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle
  * @vaddr:  virtual address IOVA of "consistent" buffer.
  * @dma_handler:  IO virtual address of "consistent" buffer.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void
 sba_free(struct device *hwdev, size_t size, void *vaddr,
@@ -933,7 +933,7 @@ int dump_run_sg = 0;
  * @nents:  number of entries in list
  * @direction:  R/W or both.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static int
 sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
@@ -1017,7 +1017,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
  * @nents:  number of entries in list
  * @direction:  R/W or both.
  *
- * See Documentation/DMA-API-HOWTO.txt
+ * See Documentation/core-api/dma-api-howto.rst
  */
 static void 
 sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 78f677cf45ab..ef2b153ddbd9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -14,7 +14,7 @@
 
 /**
  * List of possible attributes associated with a DMA mapping. The semantics
- * of each attribute should be defined in Documentation/DMA-attributes.txt.
+ * of each attribute should be defined in Documentation/core-api/dma-attributes.rst.
  */
 
 /*
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index b89d5e31f172..34450f7ad510 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -31,7 +31,7 @@
  *	does memory allocation too using vmalloc_32().
  *
  * videobuf_dma_*()
- *	see Documentation/DMA-API-HOWTO.txt, these functions to
+ *	see Documentation/core-api/dma-api-howto.rst, these functions to
  *	basically the same.  The map function does also build a
  *	scatterlist for the buffer (and unmap frees it ...)
  *
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 36c962a86bf2..f97f088ace7e 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -1071,7 +1071,7 @@ static void check_unmap(struct dma_debug_entry *ref)
 	/*
 	 * Drivers should use dma_mapping_error() to check the returned
 	 * addresses of dma_map_single() and dma_map_page().
-	 * If not, print this warning message. See Documentation/DMA-API.txt.
+	 * If not, print this warning message. See Documentation/core-api/dma-api.rst.
 	 */
 	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
 		err_printk(ref->dev, entry,
-- 
cgit v1.2.3


From 333740981f94fa80326cc8e5d2da105f17bc1dd5 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 26 Jun 2020 17:53:23 +0200
Subject: net: mdio: add a forward declaration for reset_control to mdio.h

This header refers to struct reset_control but doesn't include any reset
header. The structure definition is probably somehow indirectly pulled in
since no warnings are reported but for the sake of correctness add the
forward declaration for struct reset_control.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mdio.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 36d2e0673d03..898cbf00332a 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -18,6 +18,7 @@
 
 struct gpio_desc;
 struct mii_bus;
+struct reset_control;
 
 /* Multiple levels of nesting are possible. However typically this is
  * limited to nested DSA like layer, a MUX layer, and the normal
-- 
cgit v1.2.3


From adf4f9d49c74a812757c5c67879ece0e54b75417 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sun, 7 Jun 2020 23:51:23 +0200
Subject: irqchip/vic: Drop cascaded intialization call

We got rid of the last user of the cascaded intialization
from board files so drop this API.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200607215124.48638-1-linus.walleij@linaro.org
---
 drivers/irqchip/irq-vic.c       | 21 ---------------------
 include/linux/irqchip/arm-vic.h |  2 --
 2 files changed, 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 3c87d925f74c..927ff2c1bf67 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -481,27 +481,6 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 	__vic_init(base, 0, irq_start, vic_sources, resume_sources, NULL);
 }
 
-/**
- * vic_init_cascaded() - initialise a cascaded vectored interrupt controller
- * @base: iomem base address
- * @parent_irq: the parent IRQ we're cascaded off
- * @vic_sources: bitmask of interrupt sources to allow
- * @resume_sources: bitmask of interrupt sources to allow for resume
- *
- * This returns the base for the new interrupts or negative on error.
- */
-int __init vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
-			      u32 vic_sources, u32 resume_sources)
-{
-	struct vic_device *v;
-
-	v = &vic_devices[vic_id];
-	__vic_init(base, parent_irq, 0, vic_sources, resume_sources, NULL);
-	/* Return out acquired base */
-	return v->irq;
-}
-EXPORT_SYMBOL_GPL(vic_init_cascaded);
-
 #ifdef CONFIG_OF
 static int __init vic_of_init(struct device_node *node,
 			      struct device_node *parent)
diff --git a/include/linux/irqchip/arm-vic.h b/include/linux/irqchip/arm-vic.h
index a158b97242c7..2a4b6a5d8522 100644
--- a/include/linux/irqchip/arm-vic.h
+++ b/include/linux/irqchip/arm-vic.h
@@ -19,7 +19,5 @@ struct pt_regs;
 void __vic_init(void __iomem *base, int parent_irq, int irq_start,
 		u32 vic_sources, u32 resume_sources, struct device_node *node);
 void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources);
-int vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
-		      u32 vic_sources, u32 resume_sources);
 
 #endif
-- 
cgit v1.2.3


From b0b92ab6a86e59779c2b17c5f611b04120fdfbb6 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sun, 7 Jun 2020 23:51:24 +0200
Subject: irqchip/vic: Cut down the external API

There are registers and functions in the header file
that are only used inside the driver. Move these into
the driver.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200607215124.48638-2-linus.walleij@linaro.org
---
 drivers/irqchip/irq-vic.c       | 5 ++++-
 include/linux/irqchip/arm-vic.h | 9 ---------
 2 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 927ff2c1bf67..bc235db8a4c5 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -27,7 +27,10 @@
 
 #define VIC_IRQ_STATUS			0x00
 #define VIC_FIQ_STATUS			0x04
+#define VIC_RAW_STATUS			0x08
 #define VIC_INT_SELECT			0x0c	/* 1 = FIQ, 0 = IRQ */
+#define VIC_INT_ENABLE			0x10	/* 1 = enable, 0 = disable */
+#define VIC_INT_ENABLE_CLEAR		0x14
 #define VIC_INT_SOFT			0x18
 #define VIC_INT_SOFT_CLEAR		0x1c
 #define VIC_PROTECT			0x20
@@ -428,7 +431,7 @@ static void __init vic_init_st(void __iomem *base, unsigned int irq_start,
 	vic_register(base, 0, irq_start, vic_sources, 0, node);
 }
 
-void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
+static void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
 			      u32 vic_sources, u32 resume_sources,
 			      struct device_node *node)
 {
diff --git a/include/linux/irqchip/arm-vic.h b/include/linux/irqchip/arm-vic.h
index 2a4b6a5d8522..f2b11d1df23d 100644
--- a/include/linux/irqchip/arm-vic.h
+++ b/include/linux/irqchip/arm-vic.h
@@ -9,15 +9,6 @@
 
 #include <linux/types.h>
 
-#define VIC_RAW_STATUS			0x08
-#define VIC_INT_ENABLE			0x10	/* 1 = enable, 0 = disable */
-#define VIC_INT_ENABLE_CLEAR		0x14
-
-struct device_node;
-struct pt_regs;
-
-void __vic_init(void __iomem *base, int parent_irq, int irq_start,
-		u32 vic_sources, u32 resume_sources, struct device_node *node);
 void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources);
 
 #endif
-- 
cgit v1.2.3


From 89778093d38d547cd80f6097659d1cf1c2dd4d9d Mon Sep 17 00:00:00 2001
From: Oscar Carter <oscar.carter@gmx.com>
Date: Sat, 30 May 2020 16:34:28 +0200
Subject: drivers/acpi: Add new macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY

In an effort to enable -Wcast-function-type in the top-level Makefile to
support Control Flow Integrity builds, there are the need to remove all
the function callback casts.

To do this, create a new macro called ACPI_DECLARE_SUBTABLE_PROBE_ENTRY
to initialize the acpi_probe_entry struct using the probe_subtbl field
instead of the probe_table field. This is a previous work to be able to
modify the IRQCHIP_ACPI_DECLARE macro to use this new defined macro.

Even though these two commented fields are part of a union, this is
necessary to avoid function cast mismatches. That is, due to the
IRQCHIP_ACPI_DECLARE invocations use as last parameter a function with
the protoype "int (*func)(struct acpi_subtable_header *, const unsigned
long)" it's necessary that this macro initialize the probe_subtbl field
of the acpi_probe_entry struct and not the probe_table field.

Co-developed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200530143430.5203-2-oscar.carter@gmx.com
---
 include/linux/acpi.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d661cd0ee64d..cf74e044a570 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1154,6 +1154,17 @@ struct acpi_probe_entry {
 			.driver_data = data, 				\
 		   }
 
+#define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id,	\
+					  subtable, valid, data, fn)	\
+	static const struct acpi_probe_entry __acpi_probe_##name	\
+		__used __section(__##table##_acpi_probe_table) = {	\
+			.id = table_id,					\
+			.type = subtable,				\
+			.subtable_valid = valid,			\
+			.probe_subtbl = fn,				\
+			.driver_data = data,				\
+		}
+
 #define ACPI_PROBE_TABLE(name)		__##name##_acpi_probe_table
 #define ACPI_PROBE_TABLE_END(name)	__##name##_acpi_probe_table_end
 
-- 
cgit v1.2.3


From aba3c7ed3fcf74524b7072615028827d5e5750d7 Mon Sep 17 00:00:00 2001
From: Oscar Carter <oscar.carter@gmx.com>
Date: Sat, 30 May 2020 16:34:29 +0200
Subject: drivers/irqchip: Use new macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY

In an effort to enable -Wcast-function-type in the top-level Makefile to
support Control Flow Integrity builds, there are the need to remove all
the function callback casts.

To do this, modify the IRQCHIP_ACPI_DECLARE macro to use the new defined
macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY instead of the macro
ACPI_DECLARE_PROBE_ENTRY. This is necessary to be able to initialize the
the acpi_probe_entry struct using the probe_subtbl field instead of the
probe_table field and avoid function cast mismatches.

Also, modify the prototype of the functions used by the invocation of the
IRQCHIP_ACPI_DECLARE macro to match all the parameters.

Co-developed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200530143430.5203-3-oscar.carter@gmx.com
---
 drivers/irqchip/irq-gic-v3.c | 2 +-
 drivers/irqchip/irq-gic.c    | 2 +-
 include/linux/irqchip.h      | 5 +++--
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index cc46bc2d634b..324f280ff606 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -2116,7 +2116,7 @@ static void __init gic_acpi_setup_kvm_info(void)
 }
 
 static int __init
-gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end)
+gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_generic_distributor *dist;
 	struct fwnode_handle *domain_handle;
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 00de05abd3c3..71bd64884ae5 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1592,7 +1592,7 @@ static void __init gic_acpi_setup_kvm_info(void)
 	gic_set_kvm_info(&gic_v2_kvm_info);
 }
 
-static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
+static int __init gic_v2_acpi_init(union acpi_subtable_headers *header,
 				   const unsigned long end)
 {
 	struct acpi_madt_generic_distributor *dist;
diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index 950e4b2458f0..447f22880a69 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -39,8 +39,9 @@
  * @fn: initialization function
  */
 #define IRQCHIP_ACPI_DECLARE(name, subtable, validate, data, fn)	\
-	ACPI_DECLARE_PROBE_ENTRY(irqchip, name, ACPI_SIG_MADT, 		\
-				 subtable, validate, data, fn)
+	ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(irqchip, name,		\
+					  ACPI_SIG_MADT, subtable,	\
+					  validate, data, fn)
 
 #ifdef CONFIG_IRQCHIP
 void irqchip_init(void);
-- 
cgit v1.2.3


From 8ebf642f3d809b59f57d0d408189a2218294e269 Mon Sep 17 00:00:00 2001
From: Oscar Carter <oscar.carter@gmx.com>
Date: Sat, 30 May 2020 16:34:30 +0200
Subject: drivers/acpi: Remove function cast

Remove the function cast in the ACPI_DECLARE_PROBE_ENTRY macro to ensure
that the functions passed as a last parameter to this macro have the
right prototype.

This is an effort to enable -Wcast-function-type in the top-level Makefile
to support Control Flow Integrity builds.

Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200530143430.5203-4-oscar.carter@gmx.com
---
 include/linux/acpi.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index cf74e044a570..1cda2d32e4c4 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1143,16 +1143,16 @@ struct acpi_probe_entry {
 	kernel_ulong_t driver_data;
 };
 
-#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn)	\
+#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable,	\
+				 valid, data, fn)			\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
-		__used __section(__##table##_acpi_probe_table)		\
-		 = {							\
+		__used __section(__##table##_acpi_probe_table) = {	\
 			.id = table_id,					\
 			.type = subtable,				\
 			.subtable_valid = valid,			\
-			.probe_table = (acpi_tbl_table_handler)fn,	\
-			.driver_data = data, 				\
-		   }
+			.probe_table = fn,				\
+			.driver_data = data,				\
+		}
 
 #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id,	\
 					  subtable, valid, data, fn)	\
-- 
cgit v1.2.3


From 167cbce27444be3203081b97ea65178c4088b062 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 10 Jun 2020 17:51:21 +0200
Subject: serial: core: drop unnecessary gpio include

Drop the recently added gpio include from the serial-core header in
favour of a forward declaration and instead include the gpio header only
where needed.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20200610155121.14014-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 1 +
 drivers/tty/serial/serial_core.c    | 1 +
 include/linux/serial_core.h         | 2 +-
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 1632f7d25acc..d64ca77d9cfa 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -16,6 +16,7 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/console.h>
+#include <linux/gpio/consumer.h>
 #include <linux/sysrq.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 57840cf90388..5750f3628357 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -14,6 +14,7 @@
 #include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/console.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 9fd550e7946a..653c653ad0c2 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -10,7 +10,6 @@
 #include <linux/bitops.h>
 #include <linux/compiler.h>
 #include <linux/console.h>
-#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/circ_buf.h>
 #include <linux/spinlock.h>
@@ -30,6 +29,7 @@
 struct uart_port;
 struct serial_struct;
 struct device;
+struct gpio_desc;
 
 /*
  * This structure describes all the operations that can be done on the
-- 
cgit v1.2.3


From 10652a9e9fe3fbcaca090f99cd3060ac3fee2913 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 10 Jun 2020 17:22:30 +0200
Subject: Revert "serial: core: Refactor uart_unlock_and_check_sysrq()"

This reverts commit da9a5aa3402db0ff3b57216d8dbf2478e1046cae.

In order to ease backporting a fix for a sysrq regression, revert this
rewrite which was since added on top.

The other sysrq helpers now bail out early when sysrq is not enabled;
it's better to keep that pattern here as well.

Note that the __releases() attribute won't be needed after the follow-on
fix either.

Fixes: da9a5aa3402d ("serial: core: Refactor uart_unlock_and_check_sysrq()")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200610152232.16925-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 23 +++++++++++++----------
 include/linux/serial_core.h      |  3 ++-
 2 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 13fb92ae3710..fcdb6bfbe2cf 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -3239,19 +3239,22 @@ int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch)
 }
 EXPORT_SYMBOL_GPL(uart_prepare_sysrq_char);
 
-void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long flags)
-__releases(&port->lock)
+void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags)
 {
-	if (port->has_sysrq) {
-		int sysrq_ch = port->sysrq_ch;
+	int sysrq_ch;
 
-		port->sysrq_ch = 0;
-		spin_unlock_irqrestore(&port->lock, flags);
-		if (sysrq_ch)
-			handle_sysrq(sysrq_ch);
-	} else {
-		spin_unlock_irqrestore(&port->lock, flags);
+	if (!port->has_sysrq) {
+		spin_unlock_irqrestore(&port->lock, irqflags);
+		return;
 	}
+
+	sysrq_ch = port->sysrq_ch;
+	port->sysrq_ch = 0;
+
+	spin_unlock_irqrestore(&port->lock, irqflags);
+
+	if (sysrq_ch)
+		handle_sysrq(sysrq_ch);
 }
 EXPORT_SYMBOL_GPL(uart_unlock_and_check_sysrq);
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 9fd550e7946a..ef4921ddbe97 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -464,7 +464,8 @@ extern void uart_insert_char(struct uart_port *port, unsigned int status,
 
 extern int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch);
 extern int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch);
-extern void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long flags);
+extern void uart_unlock_and_check_sysrq(struct uart_port *port,
+					unsigned long irqflags);
 extern int uart_handle_break(struct uart_port *port);
 
 /*
-- 
cgit v1.2.3


From 08d5470308ac3598e7709d08b8979ce6e9de8da2 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 10 Jun 2020 17:22:31 +0200
Subject: serial: core: fix sysrq overhead regression

Commit 8e20fc391711 ("serial_core: Move sysrq functions from header
file") converted the inline sysrq helpers to exported functions which
are now called for every received character, interrupt and break signal
also on systems without CONFIG_MAGIC_SYSRQ_SERIAL instead of being
optimised away by the compiler.

Inlining these helpers again also avoids the function call overhead when
CONFIG_MAGIC_SYSRQ_SERIAL is enabled (e.g. when the port is not used as
a console).

Fixes: 8e20fc391711 ("serial_core: Move sysrq functions from header file")
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Cc: stable <stable@vger.kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://lore.kernel.org/r/20200610152232.16925-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c |  99 +------------------------------------
 include/linux/serial_core.h      | 103 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 100 insertions(+), 102 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index fcdb6bfbe2cf..abb102e71b14 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -41,8 +41,6 @@ static struct lock_class_key port_lock_key;
 
 #define HIGH_BITS_OFFSET	((sizeof(long)-sizeof(int))*8)
 
-#define SYSRQ_TIMEOUT	(HZ * 5)
-
 static void uart_change_speed(struct tty_struct *tty, struct uart_state *state,
 					struct ktermios *old_termios);
 static void uart_wait_until_sent(struct tty_struct *tty, int timeout);
@@ -3163,7 +3161,7 @@ static DECLARE_WORK(sysrq_enable_work, uart_sysrq_on);
  *	Returns false if @ch is out of enabling sequence and should be
  *	handled some other way, true if @ch was consumed.
  */
-static bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch)
+bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch)
 {
 	int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq);
 
@@ -3186,102 +3184,9 @@ static bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch)
 	port->sysrq = 0;
 	return true;
 }
-#else
-static inline bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch)
-{
-	return false;
-}
+EXPORT_SYMBOL_GPL(uart_try_toggle_sysrq);
 #endif
 
-int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch)
-{
-	if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL))
-		return 0;
-
-	if (!port->has_sysrq || !port->sysrq)
-		return 0;
-
-	if (ch && time_before(jiffies, port->sysrq)) {
-		if (sysrq_mask()) {
-			handle_sysrq(ch);
-			port->sysrq = 0;
-			return 1;
-		}
-		if (uart_try_toggle_sysrq(port, ch))
-			return 1;
-	}
-	port->sysrq = 0;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(uart_handle_sysrq_char);
-
-int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch)
-{
-	if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL))
-		return 0;
-
-	if (!port->has_sysrq || !port->sysrq)
-		return 0;
-
-	if (ch && time_before(jiffies, port->sysrq)) {
-		if (sysrq_mask()) {
-			port->sysrq_ch = ch;
-			port->sysrq = 0;
-			return 1;
-		}
-		if (uart_try_toggle_sysrq(port, ch))
-			return 1;
-	}
-	port->sysrq = 0;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(uart_prepare_sysrq_char);
-
-void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags)
-{
-	int sysrq_ch;
-
-	if (!port->has_sysrq) {
-		spin_unlock_irqrestore(&port->lock, irqflags);
-		return;
-	}
-
-	sysrq_ch = port->sysrq_ch;
-	port->sysrq_ch = 0;
-
-	spin_unlock_irqrestore(&port->lock, irqflags);
-
-	if (sysrq_ch)
-		handle_sysrq(sysrq_ch);
-}
-EXPORT_SYMBOL_GPL(uart_unlock_and_check_sysrq);
-
-/*
- * We do the SysRQ and SAK checking like this...
- */
-int uart_handle_break(struct uart_port *port)
-{
-	struct uart_state *state = port->state;
-
-	if (port->handle_break)
-		port->handle_break(port);
-
-	if (port->has_sysrq && uart_console(port)) {
-		if (!port->sysrq) {
-			port->sysrq = jiffies + SYSRQ_TIMEOUT;
-			return 1;
-		}
-		port->sysrq = 0;
-	}
-
-	if (port->flags & UPF_SAK)
-		do_SAK(state->port.tty);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(uart_handle_break);
-
 EXPORT_SYMBOL(uart_write_wakeup);
 EXPORT_SYMBOL(uart_register_driver);
 EXPORT_SYMBOL(uart_unregister_driver);
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index ef4921ddbe97..03fa7b967103 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -462,11 +462,104 @@ extern void uart_handle_cts_change(struct uart_port *uport,
 extern void uart_insert_char(struct uart_port *port, unsigned int status,
 		 unsigned int overrun, unsigned int ch, unsigned int flag);
 
-extern int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch);
-extern int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch);
-extern void uart_unlock_and_check_sysrq(struct uart_port *port,
-					unsigned long irqflags);
-extern int uart_handle_break(struct uart_port *port);
+#ifdef CONFIG_MAGIC_SYSRQ_SERIAL
+#define SYSRQ_TIMEOUT	(HZ * 5)
+
+bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch);
+
+static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch)
+{
+	if (!port->has_sysrq || !port->sysrq)
+		return 0;
+
+	if (ch && time_before(jiffies, port->sysrq)) {
+		if (sysrq_mask()) {
+			handle_sysrq(ch);
+			port->sysrq = 0;
+			return 1;
+		}
+		if (uart_try_toggle_sysrq(port, ch))
+			return 1;
+	}
+	port->sysrq = 0;
+
+	return 0;
+}
+
+static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch)
+{
+	if (!port->has_sysrq || !port->sysrq)
+		return 0;
+
+	if (ch && time_before(jiffies, port->sysrq)) {
+		if (sysrq_mask()) {
+			port->sysrq_ch = ch;
+			port->sysrq = 0;
+			return 1;
+		}
+		if (uart_try_toggle_sysrq(port, ch))
+			return 1;
+	}
+	port->sysrq = 0;
+
+	return 0;
+}
+
+static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags)
+{
+	int sysrq_ch;
+
+	if (!port->has_sysrq) {
+		spin_unlock_irqrestore(&port->lock, irqflags);
+		return;
+	}
+
+	sysrq_ch = port->sysrq_ch;
+	port->sysrq_ch = 0;
+
+	spin_unlock_irqrestore(&port->lock, irqflags);
+
+	if (sysrq_ch)
+		handle_sysrq(sysrq_ch);
+}
+#else	/* CONFIG_MAGIC_SYSRQ_SERIAL */
+static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch)
+{
+	return 0;
+}
+static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch)
+{
+	return 0;
+}
+static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags)
+{
+	spin_unlock_irqrestore(&port->lock, irqflags);
+}
+#endif	/* CONFIG_MAGIC_SYSRQ_SERIAL */
+
+/*
+ * We do the SysRQ and SAK checking like this...
+ */
+static inline int uart_handle_break(struct uart_port *port)
+{
+	struct uart_state *state = port->state;
+
+	if (port->handle_break)
+		port->handle_break(port);
+
+#ifdef CONFIG_MAGIC_SYSRQ_SERIAL
+	if (port->has_sysrq && uart_console(port)) {
+		if (!port->sysrq) {
+			port->sysrq = jiffies + SYSRQ_TIMEOUT;
+			return 1;
+		}
+		port->sysrq = 0;
+	}
+#endif
+	if (port->flags & UPF_SAK)
+		do_SAK(state->port.tty);
+	return 0;
+}
 
 /*
  *	UART_ENABLE_MS - determine if port should enable modem status irqs
-- 
cgit v1.2.3


From 225385657b7d81a99e17e04cd01f9ed5bb3109a8 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 10 Jun 2020 17:22:32 +0200
Subject: serial: core: drop redundant sysrq checks

The sysrq timestamp will never be set unless port->has_sysrq is set (see
uart_handle_break()) so drop the redundant checks that were added by
commit 1997e9dfdc84 ("serial_core: Un-ifdef sysrq SUPPORT_SYSRQ").

Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://lore.kernel.org/r/20200610152232.16925-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 03fa7b967103..791f4844efeb 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -469,7 +469,7 @@ bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch);
 
 static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch)
 {
-	if (!port->has_sysrq || !port->sysrq)
+	if (!port->sysrq)
 		return 0;
 
 	if (ch && time_before(jiffies, port->sysrq)) {
@@ -488,7 +488,7 @@ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch
 
 static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch)
 {
-	if (!port->has_sysrq || !port->sysrq)
+	if (!port->sysrq)
 		return 0;
 
 	if (ch && time_before(jiffies, port->sysrq)) {
-- 
cgit v1.2.3


From 9205d7b1c1cffa827c23bdbf35e04c7cbe1e1f10 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 25 Jun 2020 22:59:41 -0700
Subject: net/mlx5: Avoid RDMA file inclusion in core driver

mlx5 cq.h does not depend on RDMA verbs.
Remove RDMA verbs file inclusion.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/cq.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index b5a9399e07ee..7bfb67363434 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -33,7 +33,6 @@
 #ifndef MLX5_CORE_CQ_H
 #define MLX5_CORE_CQ_H
 
-#include <rdma/ib_verbs.h>
 #include <linux/mlx5/driver.h>
 #include <linux/refcount.h>
 
-- 
cgit v1.2.3


From 2d1b69ed65ee033aa541518cc9f6a815296ac493 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 25 Jun 2020 22:59:43 -0700
Subject: net/mlx5: kTLS, Improve TLS params layout structures

Add explicit WQE segment structures for the TLS static and progress
params.
According to the HW spec, TISN is not part of the progress params context,
take it out of it.
Rename the control segment tisn field as it could hold either a TIS or
a TIR number.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h          |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 14 +++++++++-----
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c    |  2 +-
 include/linux/mlx5/device.h                                |  9 +++++++++
 include/linux/mlx5/mlx5_ifc.h                              |  5 +----
 include/linux/mlx5/qp.h                                    |  2 +-
 7 files changed, 23 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index bfd3e1161bc6..31cac239563d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -182,7 +182,7 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 
 static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
 {
-	return cseg && !!cseg->tisn;
+	return cseg && !!cseg->tis_tir_num;
 }
 
 static inline u8
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index c6180892cfcb..806ed185dd4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -19,7 +19,7 @@
 
 #define MLX5E_KTLS_PROGRESS_WQE_SZ \
 	(offsetof(struct mlx5e_tx_wqe, tls_progress_params_ctx) + \
-	 MLX5_ST_SZ_BYTES(tls_progress_params))
+	 sizeof(struct mlx5_wqe_tls_progress_params_seg))
 #define MLX5E_KTLS_PROGRESS_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 3cd78d9503c1..ad7300f19815 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -64,7 +64,7 @@ build_static_params(struct mlx5e_umr_wqe *wqe, u16 pc, u32 sqn,
 	cseg->qpn_ds           = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
 					     STATIC_PARAMS_DS_CNT);
 	cseg->fm_ce_se         = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
-	cseg->tisn             = cpu_to_be32(priv_tx->tisn << 8);
+	cseg->tis_tir_num      = cpu_to_be32(priv_tx->tisn << 8);
 
 	ucseg->flags = MLX5_UMR_INLINE;
 	ucseg->bsf_octowords = cpu_to_be16(MLX5_ST_SZ_BYTES(tls_static_params) / 16);
@@ -75,10 +75,14 @@ build_static_params(struct mlx5e_umr_wqe *wqe, u16 pc, u32 sqn,
 static void
 fill_progress_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
 {
-	MLX5_SET(tls_progress_params, ctx, tisn, priv_tx->tisn);
-	MLX5_SET(tls_progress_params, ctx, record_tracker_state,
+	struct mlx5_wqe_tls_progress_params_seg *params;
+
+	params = ctx;
+
+	params->tis_tir_num = cpu_to_be32(priv_tx->tisn);
+	MLX5_SET(tls_progress_params, params->ctx, record_tracker_state,
 		 MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_START);
-	MLX5_SET(tls_progress_params, ctx, auth_state,
+	MLX5_SET(tls_progress_params, params->ctx, auth_state,
 		 MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD);
 }
 
@@ -284,7 +288,7 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8)  | MLX5_OPCODE_DUMP);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-	cseg->tisn             = cpu_to_be32(tisn << 8);
+	cseg->tis_tir_num      = cpu_to_be32(tisn << 8);
 	cseg->fm_ce_se         = first ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
 
 	fsz = skb_frag_size(frag);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 05454a843b28..72d26fbc8d5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -305,7 +305,7 @@ err_out:
 void mlx5e_tls_handle_tx_wqe(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
 			     struct mlx5e_accel_tx_tls_state *state)
 {
-	cseg->tisn = cpu_to_be32(state->tls_tisn << 8);
+	cseg->tis_tir_num = cpu_to_be32(state->tls_tisn << 8);
 }
 
 static int tls_update_resync_sn(struct net_device *netdev,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 1bc27aca648b..57db125e5802 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -458,6 +458,15 @@ enum {
 	MLX5_OPC_MOD_TLS_TIR_PROGRESS_PARAMS = 0x2,
 };
 
+struct mlx5_wqe_tls_static_params_seg {
+	u8     ctx[MLX5_ST_SZ_BYTES(tls_static_params)];
+};
+
+struct mlx5_wqe_tls_progress_params_seg {
+	__be32 tis_tir_num;
+	u8     ctx[MLX5_ST_SZ_BYTES(tls_progress_params)];
+};
+
 enum {
 	MLX5_SET_PORT_RESET_QKEY	= 0,
 	MLX5_SET_PORT_GUID0		= 16,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 116bd9bb347f..a227518c70cf 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10638,16 +10638,13 @@ struct mlx5_ifc_tls_static_params_bits {
 };
 
 struct mlx5_ifc_tls_progress_params_bits {
-	u8         reserved_at_0[0x8];
-	u8         tisn[0x18];
-
 	u8         next_record_tcp_sn[0x20];
 
 	u8         hw_resync_tcp_sn[0x20];
 
 	u8         record_tracker_state[0x2];
 	u8         auth_state[0x2];
-	u8         reserved_at_64[0x4];
+	u8         reserved_at_44[0x4];
 	u8         hw_offset_record_number[0x18];
 };
 
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index b8992b861ae6..36492a1342cf 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -209,7 +209,7 @@ struct mlx5_wqe_ctrl_seg {
 		__be32		general_id;
 		__be32		imm;
 		__be32		umr_mkey;
-		__be32		tisn;
+		__be32		tis_tir_num;
 	};
 };
 
-- 
cgit v1.2.3


From 4f311afc2035f7b33d97e69ffaa2e6cd67fca16d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 10 Jun 2020 12:14:09 +0200
Subject: sched/core: Fix CONFIG_GCC_PLUGIN_RANDSTRUCT build fail

As a temporary build fix, the proper cleanup needs more work.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Reported-by: Eric Biggers <ebiggers@kernel.org>
Suggested-by: Eric Biggers <ebiggers@kernel.org>
Suggested-by: Kees Cook <keescook@chromium.org>
Fixes: a148866489fb ("sched: Replace rq::wake_list")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b62e6aaf28f0..224b5de568e7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -654,8 +654,10 @@ struct task_struct {
 	unsigned int			ptrace;
 
 #ifdef CONFIG_SMP
-	struct llist_node		wake_entry;
-	unsigned int			wake_entry_type;
+	struct {
+		struct llist_node		wake_entry;
+		unsigned int			wake_entry_type;
+	};
 	int				on_cpu;
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* Current CPU: */
-- 
cgit v1.2.3


From 8c4890d1c3358fb8023d46e1e554c41d54f02878 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 22 Jun 2020 12:01:25 +0200
Subject: smp, irq_work: Continue smp_call_function*() and irq_work*()
 integration

Instead of relying on BUG_ON() to ensure the various data structures
line up, use a bunch of horrible unions to make it all automatic.

Much of the union magic is to ensure irq_work and smp_call_function do
not (yet) see the members of their respective data structures change
name.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20200622100825.844455025@infradead.org
---
 include/linux/irq_work.h  | 26 ++++++-------------
 include/linux/sched.h     |  5 +---
 include/linux/smp.h       | 23 ++++++-----------
 include/linux/smp_types.h | 66 +++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/core.c       |  6 ++---
 kernel/smp.c              | 18 -------------
 6 files changed, 86 insertions(+), 58 deletions(-)
 create mode 100644 include/linux/smp_types.h

(limited to 'include/linux')

diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 2735da5f839e..30823780c192 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_IRQ_WORK_H
 #define _LINUX_IRQ_WORK_H
 
-#include <linux/llist.h>
+#include <linux/smp_types.h>
 
 /*
  * An entry can be in one of four states:
@@ -13,24 +13,14 @@
  * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
  */
 
-/* flags share CSD_FLAG_ space */
-
-#define IRQ_WORK_PENDING	BIT(0)
-#define IRQ_WORK_BUSY		BIT(1)
-
-/* Doesn't want IPI, wait for tick: */
-#define IRQ_WORK_LAZY		BIT(2)
-/* Run hard IRQ context, even on RT */
-#define IRQ_WORK_HARD_IRQ	BIT(3)
-
-#define IRQ_WORK_CLAIMED	(IRQ_WORK_PENDING | IRQ_WORK_BUSY)
-
-/*
- * structure shares layout with single_call_data_t.
- */
 struct irq_work {
-	struct llist_node llnode;
-	atomic_t flags;
+	union {
+		struct __call_single_node node;
+		struct {
+			struct llist_node llnode;
+			atomic_t flags;
+		};
+	};
 	void (*func)(struct irq_work *);
 };
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 224b5de568e7..692e327d7455 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -654,11 +654,8 @@ struct task_struct {
 	unsigned int			ptrace;
 
 #ifdef CONFIG_SMP
-	struct {
-		struct llist_node		wake_entry;
-		unsigned int			wake_entry_type;
-	};
 	int				on_cpu;
+	struct __call_single_node	wake_entry;
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* Current CPU: */
 	unsigned int			cpu;
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 7ee202ad21a6..80d557ef8a11 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -12,29 +12,22 @@
 #include <linux/list.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
-#include <linux/llist.h>
+#include <linux/smp_types.h>
 
 typedef void (*smp_call_func_t)(void *info);
 typedef bool (*smp_cond_func_t)(int cpu, void *info);
 
-enum {
-	CSD_FLAG_LOCK		= 0x01,
-
-	/* IRQ_WORK_flags */
-
-	CSD_TYPE_ASYNC		= 0x00,
-	CSD_TYPE_SYNC		= 0x10,
-	CSD_TYPE_IRQ_WORK	= 0x20,
-	CSD_TYPE_TTWU		= 0x30,
-	CSD_FLAG_TYPE_MASK	= 0xF0,
-};
-
 /*
  * structure shares (partial) layout with struct irq_work
  */
 struct __call_single_data {
-	struct llist_node llist;
-	unsigned int flags;
+	union {
+		struct __call_single_node node;
+		struct {
+			struct llist_node llist;
+			unsigned int flags;
+		};
+	};
 	smp_call_func_t func;
 	void *info;
 };
diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h
new file mode 100644
index 000000000000..364b3ae3e41d
--- /dev/null
+++ b/include/linux/smp_types.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SMP_TYPES_H
+#define __LINUX_SMP_TYPES_H
+
+#include <linux/llist.h>
+
+enum {
+	CSD_FLAG_LOCK		= 0x01,
+
+	IRQ_WORK_PENDING	= 0x01,
+	IRQ_WORK_BUSY		= 0x02,
+	IRQ_WORK_LAZY		= 0x04, /* No IPI, wait for tick */
+	IRQ_WORK_HARD_IRQ	= 0x08, /* IRQ context on PREEMPT_RT */
+
+	IRQ_WORK_CLAIMED	= (IRQ_WORK_PENDING | IRQ_WORK_BUSY),
+
+	CSD_TYPE_ASYNC		= 0x00,
+	CSD_TYPE_SYNC		= 0x10,
+	CSD_TYPE_IRQ_WORK	= 0x20,
+	CSD_TYPE_TTWU		= 0x30,
+
+	CSD_FLAG_TYPE_MASK	= 0xF0,
+};
+
+/*
+ * struct __call_single_node is the primary type on
+ * smp.c:call_single_queue.
+ *
+ * flush_smp_call_function_queue() only reads the type from
+ * __call_single_node::u_flags as a regular load, the above
+ * (anonymous) enum defines all the bits of this word.
+ *
+ * Other bits are not modified until the type is known.
+ *
+ * CSD_TYPE_SYNC/ASYNC:
+ *	struct {
+ *		struct llist_node node;
+ *		unsigned int flags;
+ *		smp_call_func_t func;
+ *		void *info;
+ *	};
+ *
+ * CSD_TYPE_IRQ_WORK:
+ *	struct {
+ *		struct llist_node node;
+ *		atomic_t flags;
+ *		void (*func)(struct irq_work *);
+ *	};
+ *
+ * CSD_TYPE_TTWU:
+ *	struct {
+ *		struct llist_node node;
+ *		unsigned int flags;
+ *	};
+ *
+ */
+
+struct __call_single_node {
+	struct llist_node	llist;
+	union {
+		unsigned int	u_flags;
+		atomic_t	a_flags;
+	};
+};
+
+#endif /* __LINUX_SMP_TYPES_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f778067de277..ca5db40392d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2293,7 +2293,7 @@ void sched_ttwu_pending(void *arg)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry) {
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
 		if (WARN_ON_ONCE(p->on_cpu))
 			smp_cond_load_acquire(&p->on_cpu, !VAL);
 
@@ -2329,7 +2329,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	__smp_call_single_queue(cpu, &p->wake_entry);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2786,7 +2786,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
-	p->wake_entry_type = CSD_TYPE_TTWU;
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 #endif
 }
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 472c2b274c65..aa17eedff5be 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -669,24 +669,6 @@ void __init smp_init(void)
 {
 	int num_nodes, num_cpus;
 
-	/*
-	 * Ensure struct irq_work layout matches so that
-	 * flush_smp_call_function_queue() can do horrible things.
-	 */
-	BUILD_BUG_ON(offsetof(struct irq_work, llnode) !=
-		     offsetof(struct __call_single_data, llist));
-	BUILD_BUG_ON(offsetof(struct irq_work, func) !=
-		     offsetof(struct __call_single_data, func));
-	BUILD_BUG_ON(offsetof(struct irq_work, flags) !=
-		     offsetof(struct __call_single_data, flags));
-
-	/*
-	 * Assert the CSD_TYPE_TTWU layout is similar enough
-	 * for task_struct to be on the @call_single_queue.
-	 */
-	BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) !=
-		     offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist));
-
 	idle_threads_init();
 	cpuhp_threads_init();
 
-- 
cgit v1.2.3


From bfe373f608cf81b7626dfeb904001b0e867c5110 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Tue, 28 Apr 2020 09:54:56 +0800
Subject: blk-mq-debugfs: update blk_queue_flag_name[] accordingly for new
 flags

Else there may be magic numbers in /sys/kernel/debug/block/*/state.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 3 +++
 include/linux/blkdev.h | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 15df3a36e9fa..e0b2bc131bf5 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -125,6 +125,9 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
 	QUEUE_FLAG_NAME(QUIESCED),
+	QUEUE_FLAG_NAME(PCI_P2PDMA),
+	QUEUE_FLAG_NAME(ZONE_RESETALL),
+	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8fd900998b4e..57241417ff2f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -590,6 +590,7 @@ struct request_queue {
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
 
+/* Keep blk_queue_flag_name[] in sync with the definitions below */
 #define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
 #define QUEUE_FLAG_DYING	1	/* queue being torn down */
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
-- 
cgit v1.2.3


From db9819c76c1fd48c30699381c94bba5c95dd467e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:47 +0200
Subject: block: remove bio_disassociate_blkg

bio_disassociate_blkg has two callers, of which one immediately assigns
a new value to >bi_blkg.  Just open code the function in the two callers.

Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         | 27 ++++++++-------------------
 include/linux/bio.h |  2 --
 2 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index fb5533416fa6..8aef4460b32e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -234,8 +234,12 @@ fallback:
 
 void bio_uninit(struct bio *bio)
 {
-	bio_disassociate_blkg(bio);
-
+#ifdef CONFIG_BLK_CGROUP
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
+#endif
 	if (bio_integrity(bio))
 		bio_integrity_free(bio);
 
@@ -1625,21 +1629,6 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
-/**
- * bio_disassociate_blkg - puts back the blkg reference if associated
- * @bio: target bio
- *
- * Helper to disassociate the blkg from @bio if a blkg is associated.
- */
-void bio_disassociate_blkg(struct bio *bio)
-{
-	if (bio->bi_blkg) {
-		blkg_put(bio->bi_blkg);
-		bio->bi_blkg = NULL;
-	}
-}
-EXPORT_SYMBOL_GPL(bio_disassociate_blkg);
-
 /**
  * __bio_associate_blkg - associate a bio with the a blkg
  * @bio: target bio
@@ -1656,8 +1645,8 @@ EXPORT_SYMBOL_GPL(bio_disassociate_blkg);
  */
 static void __bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
 {
-	bio_disassociate_blkg(bio);
-
+	if (bio->bi_blkg)
+		blkg_put(bio->bi_blkg);
 	bio->bi_blkg = blkg_tryget_closest(blkg);
 }
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 0282f8aa8593..4cd229e175c0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -497,13 +497,11 @@ static inline void bio_associate_blkg_from_page(struct bio *bio,
 #endif
 
 #ifdef CONFIG_BLK_CGROUP
-void bio_disassociate_blkg(struct bio *bio);
 void bio_associate_blkg(struct bio *bio);
 void bio_associate_blkg_from_css(struct bio *bio,
 				 struct cgroup_subsys_state *css);
 void bio_clone_blkg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
-static inline void bio_disassociate_blkg(struct bio *bio) { }
 static inline void bio_associate_blkg(struct bio *bio) { }
 static inline void bio_associate_blkg_from_css(struct bio *bio,
 					       struct cgroup_subsys_state *css)
-- 
cgit v1.2.3


From a18b9b1590ca64f877588700de32c9ad236f405c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:50 +0200
Subject: block: move bio_associate_blkg_from_page to mm/page_io.c

bio_associate_blkg_from_page is a special purpose helper for swap bios
that doesn't need access to bio internals.  Move it to the swap code
instead of having it in bio.c.

Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         | 26 --------------------------
 include/linux/bio.h |  7 -------
 mm/page_io.c        | 17 +++++++++++++++++
 3 files changed, 17 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index bc8de2432e36..901d22715dd4 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1659,32 +1659,6 @@ void bio_associate_blkg_from_css(struct bio *bio,
 }
 EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
 
-#ifdef CONFIG_MEMCG
-/**
- * bio_associate_blkg_from_page - associate a bio with the page's blkg
- * @bio: target bio
- * @page: the page to lookup the blkcg from
- *
- * Associate @bio with the blkg from @page's owning memcg and the respective
- * request_queue.  If cgroup_e_css returns %NULL, fall back to the queue's
- * root_blkg.
- */
-void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
-{
-	struct cgroup_subsys_state *css;
-
-	if (!page->mem_cgroup)
-		return;
-
-	rcu_read_lock();
-
-	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
-	bio_associate_blkg_from_css(bio, css);
-
-	rcu_read_unlock();
-}
-#endif /* CONFIG_MEMCG */
-
 /**
  * bio_associate_blkg - associate a bio with a blkg
  * @bio: target bio
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 4cd229e175c0..c6d765382926 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -489,13 +489,6 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
-#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-void bio_associate_blkg_from_page(struct bio *bio, struct page *page);
-#else
-static inline void bio_associate_blkg_from_page(struct bio *bio,
-						struct page *page) { }
-#endif
-
 #ifdef CONFIG_BLK_CGROUP
 void bio_associate_blkg(struct bio *bio);
 void bio_associate_blkg_from_css(struct bio *bio,
diff --git a/mm/page_io.c b/mm/page_io.c
index e8726f3e3820..ccda76790088 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -277,6 +277,23 @@ static inline void count_swpout_vm_event(struct page *page)
 	count_vm_events(PSWPOUT, hpage_nr_pages(page));
 }
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *css;
+
+	if (!page->mem_cgroup)
+		return;
+
+	rcu_read_lock();
+	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+	bio_associate_blkg_from_css(bio, css);
+	rcu_read_unlock();
+}
+#else
+#define bio_associate_blkg_from_page(bio, page)		do { } while (0)
+#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
+
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		bio_end_io_t end_write_func)
 {
-- 
cgit v1.2.3


From 28fc591ff9d64cbc2b780be95ee3fde8f6ade7fd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:51 +0200
Subject: block: move the bio cgroup associatation helpers to blk-cgroup.c

Keep the cgroup code together.

Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                |  75 ---------------------------------
 block/blk-cgroup.c         | 103 ++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/blk-cgroup.h |  30 -------------
 3 files changed, 101 insertions(+), 107 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index 901d22715dd4..fc1299f9d86a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1627,81 +1627,6 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
 }
 EXPORT_SYMBOL(bioset_init_from_src);
 
-#ifdef CONFIG_BLK_CGROUP
-/**
- * bio_associate_blkg_from_css - associate a bio with a specified css
- * @bio: target bio
- * @css: target css
- *
- * Associate @bio with the blkg found by combining the css's blkg and the
- * request_queue of the @bio.  An association failure is handled by walking up
- * the blkg tree.  Therefore, the blkg associated can be anything between @blkg
- * and q->root_blkg.  This situation only happens when a cgroup is dying and
- * then the remaining bios will spill to the closest alive blkg.
- *
- * A reference will be taken on the blkg and will be released when @bio is
- * freed.
- */
-void bio_associate_blkg_from_css(struct bio *bio,
-				 struct cgroup_subsys_state *css)
-{
-	struct request_queue *q = bio->bi_disk->queue;
-	struct blkcg_gq *blkg = q->root_blkg;
-
-	if (bio->bi_blkg)
-		blkg_put(bio->bi_blkg);
-
-	rcu_read_lock();
-	if (css && css->parent)
-		blkg = blkg_lookup_create(css_to_blkcg(css), q);
-	bio->bi_blkg = blkg_tryget_closest(blkg);
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
-
-/**
- * bio_associate_blkg - associate a bio with a blkg
- * @bio: target bio
- *
- * Associate @bio with the blkg found from the bio's css and request_queue.
- * If one is not found, bio_lookup_blkg() creates the blkg.  If a blkg is
- * already associated, the css is reused and association redone as the
- * request_queue may have changed.
- */
-void bio_associate_blkg(struct bio *bio)
-{
-	struct cgroup_subsys_state *css;
-
-	rcu_read_lock();
-
-	if (bio->bi_blkg)
-		css = &bio_blkcg(bio)->css;
-	else
-		css = blkcg_css();
-
-	bio_associate_blkg_from_css(bio, css);
-
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(bio_associate_blkg);
-
-/**
- * bio_clone_blkg_association - clone blkg association from src to dst bio
- * @dst: destination bio
- * @src: source bio
- */
-void bio_clone_blkg_association(struct bio *dst, struct bio *src)
-{
-	if (src->bi_blkg) {
-		if (dst->bi_blkg)
-			blkg_put(dst->bi_blkg);
-		blkg_get(src->bi_blkg);
-		dst->bi_blkg = src->bi_blkg;
-	}
-}
-EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
-#endif /* CONFIG_BLK_CGROUP */
-
 static void __init biovec_init_slabs(void)
 {
 	int i;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 0ecc897b225c..bb0607bfd771 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -328,7 +328,7 @@ err_free_blkg:
  * Returns the blkg or the closest blkg if blkg_create() fails as it walks
  * down from root.
  */
-struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
+static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
 				      struct request_queue *q)
 {
 	struct blkcg_gq *blkg;
@@ -377,7 +377,7 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
  * This looks up or creates the blkg representing the unique pair
  * of the blkcg and the request_queue.
  */
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
+static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 				    struct request_queue *q)
 {
 	struct blkcg_gq *blkg = blkg_lookup(blkcg, q);
@@ -1727,6 +1727,105 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
 	atomic64_add(delta, &blkg->delay_nsec);
 }
 
+/**
+ * blkg_tryget_closest - try and get a blkg ref on the closet blkg
+ * @blkg: blkg to get
+ *
+ * This needs to be called rcu protected.  As the failure mode here is to walk
+ * up the blkg tree, this ensure that the blkg->parent pointers are always
+ * valid.  This returns the blkg that it ended up taking a reference on or %NULL
+ * if no reference was taken.
+ */
+static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg)
+{
+	struct blkcg_gq *ret_blkg = NULL;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	while (blkg) {
+		if (blkg_tryget(blkg)) {
+			ret_blkg = blkg;
+			break;
+		}
+		blkg = blkg->parent;
+	}
+
+	return ret_blkg;
+}
+
+/**
+ * bio_associate_blkg_from_css - associate a bio with a specified css
+ * @bio: target bio
+ * @css: target css
+ *
+ * Associate @bio with the blkg found by combining the css's blkg and the
+ * request_queue of the @bio.  An association failure is handled by walking up
+ * the blkg tree.  Therefore, the blkg associated can be anything between @blkg
+ * and q->root_blkg.  This situation only happens when a cgroup is dying and
+ * then the remaining bios will spill to the closest alive blkg.
+ *
+ * A reference will be taken on the blkg and will be released when @bio is
+ * freed.
+ */
+void bio_associate_blkg_from_css(struct bio *bio,
+				 struct cgroup_subsys_state *css)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	struct blkcg_gq *blkg = q->root_blkg;
+
+	if (bio->bi_blkg)
+		blkg_put(bio->bi_blkg);
+
+	rcu_read_lock();
+	if (css && css->parent)
+		blkg = blkg_lookup_create(css_to_blkcg(css), q);
+	bio->bi_blkg = blkg_tryget_closest(blkg);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
+
+/**
+ * bio_associate_blkg - associate a bio with a blkg
+ * @bio: target bio
+ *
+ * Associate @bio with the blkg found from the bio's css and request_queue.
+ * If one is not found, bio_lookup_blkg() creates the blkg.  If a blkg is
+ * already associated, the css is reused and association redone as the
+ * request_queue may have changed.
+ */
+void bio_associate_blkg(struct bio *bio)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	if (bio->bi_blkg)
+		css = &bio_blkcg(bio)->css;
+	else
+		css = blkcg_css();
+
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(bio_associate_blkg);
+
+/**
+ * bio_clone_blkg_association - clone blkg association from src to dst bio
+ * @dst: destination bio
+ * @src: source bio
+ */
+void bio_clone_blkg_association(struct bio *dst, struct bio *src)
+{
+	if (src->bi_blkg) {
+		if (dst->bi_blkg)
+			blkg_put(dst->bi_blkg);
+		blkg_get(src->bi_blkg);
+		dst->bi_blkg = src->bi_blkg;
+	}
+}
+EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
+
 static int __init blkcg_init(void)
 {
 	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index a57ebe2f00ab..60df97202314 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -183,10 +183,6 @@ extern bool blkcg_debug_stats;
 
 struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
 				      struct request_queue *q, bool update_hint);
-struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
-				      struct request_queue *q);
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
-				    struct request_queue *q);
 int blkcg_init_queue(struct request_queue *q);
 void blkcg_exit_queue(struct request_queue *q);
 
@@ -480,32 +476,6 @@ static inline bool blkg_tryget(struct blkcg_gq *blkg)
 	return blkg && percpu_ref_tryget(&blkg->refcnt);
 }
 
-/**
- * blkg_tryget_closest - try and get a blkg ref on the closet blkg
- * @blkg: blkg to get
- *
- * This needs to be called rcu protected.  As the failure mode here is to walk
- * up the blkg tree, this ensure that the blkg->parent pointers are always
- * valid.  This returns the blkg that it ended up taking a reference on or %NULL
- * if no reference was taken.
- */
-static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg)
-{
-	struct blkcg_gq *ret_blkg = NULL;
-
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	while (blkg) {
-		if (blkg_tryget(blkg)) {
-			ret_blkg = blkg;
-			break;
-		}
-		blkg = blkg->parent;
-	}
-
-	return ret_blkg;
-}
-
 /**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
-- 
cgit v1.2.3


From 81630e27fff3dc1ccbf64ecb48a70170d7071545 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:55 +0200
Subject: blk-cgroup: remove the !bio->bi_blkg check in blkcg_bio_issue_check

This is purely a sanity check for grave programming errors.  Remove it
to simplify further work in this area.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-cgroup.h | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 60df97202314..8e86b598316c 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -543,24 +543,11 @@ static inline void blkcg_bio_issue_init(struct bio *bio)
 static inline bool blkcg_bio_issue_check(struct request_queue *q,
 					 struct bio *bio)
 {
-	struct blkcg_gq *blkg;
+	struct blkcg_gq *blkg = bio->bi_blkg;
 	bool throtl = false;
 
 	rcu_read_lock();
-
-	if (!bio->bi_blkg) {
-		char b[BDEVNAME_SIZE];
-
-		WARN_ONCE(1,
-			  "no blkg associated for bio on block-device: %s\n",
-			  bio_devname(bio, b));
-		bio_associate_blkg(bio);
-	}
-
-	blkg = bio->bi_blkg;
-
 	throtl = blk_throtl_bio(q, blkg, bio);
-
 	if (!throtl) {
 		struct blkg_iostat_set *bis;
 		int rwd, cpu;
-- 
cgit v1.2.3


From 93b8063804b62b55248e16499d853e1b20eff905 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:57 +0200
Subject: blk-cgroup: move rcu locking from blkcg_bio_issue_check to
 blk_throtl_bio

The only thing in blkcg_bio_issue_check that needs to be under
rcu_read_lock is blk_throtl_bio, so move the locking there.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c       | 3 ++-
 include/linux/blk-cgroup.h | 2 --
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 209fdd8939fb..ac0083450500 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2168,7 +2168,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	bool throttled = false;
 	struct throtl_data *td = tg->td;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	rcu_read_lock();
 
 	/* see throtl_charge_bio() */
 	if (bio_flagged(bio, BIO_THROTTLED))
@@ -2273,6 +2273,7 @@ out:
 	if (throttled || !td->track_bio_latency)
 		bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;
 #endif
+	rcu_read_unlock();
 	return throttled;
 }
 
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 8e86b598316c..8ab043c911f2 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -546,7 +546,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	struct blkcg_gq *blkg = bio->bi_blkg;
 	bool throtl = false;
 
-	rcu_read_lock();
 	throtl = blk_throtl_bio(q, blkg, bio);
 	if (!throtl) {
 		struct blkg_iostat_set *bis;
@@ -582,7 +581,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	blkcg_bio_issue_init(bio);
 
-	rcu_read_unlock();
 	return !throtl;
 }
 
-- 
cgit v1.2.3


From db18a53e5ba840993a3fc908dec648402ed740bd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 27 Jun 2020 09:31:58 +0200
Subject: blk-cgroup: remove blkcg_bio_issue_check

blkcg_bio_issue_check is a giant inline function that does three entirely
different things.  Factor out the blk-cgroup related bio initalization
into a new helper, and the open code the sequence in the only caller,
relying on the fact that all the actual functionality is stubbed out for
non-cgroup builds.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         | 34 ++++++++++++++++++++++++++++
 block/blk-core.c           |  7 +++++-
 block/blk-throttle.c       |  5 +++--
 block/blk.h                |  2 ++
 include/linux/blk-cgroup.h | 56 ++--------------------------------------------
 5 files changed, 47 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d21ec2acd716..1ce94afc03bc 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1813,6 +1813,40 @@ void bio_clone_blkg_association(struct bio *dst, struct bio *src)
 }
 EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
 
+static int blk_cgroup_io_type(struct bio *bio)
+{
+	if (op_is_discard(bio->bi_opf))
+		return BLKG_IOSTAT_DISCARD;
+	if (op_is_write(bio->bi_opf))
+		return BLKG_IOSTAT_WRITE;
+	return BLKG_IOSTAT_READ;
+}
+
+void blk_cgroup_bio_start(struct bio *bio)
+{
+	int rwd = blk_cgroup_io_type(bio), cpu;
+	struct blkg_iostat_set *bis;
+
+	cpu = get_cpu();
+	bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu);
+	u64_stats_update_begin(&bis->sync);
+
+	/*
+	 * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split
+	 * bio and we would have already accounted for the size of the bio.
+	 */
+	if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
+		bio_set_flag(bio, BIO_CGROUP_ACCT);
+			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
+	}
+	bis->cur.ios[rwd]++;
+
+	u64_stats_update_end(&bis->sync);
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys))
+		cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu);
+	put_cpu();
+}
+
 static int __init blkcg_init(void)
 {
 	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
diff --git a/block/blk-core.c b/block/blk-core.c
index a9769c1a2875..76cfd5709f66 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1073,8 +1073,13 @@ generic_make_request_checks(struct bio *bio)
 	if (unlikely(!current->io_context))
 		create_task_io_context(current, GFP_ATOMIC, q->node);
 
-	if (!blkcg_bio_issue_check(q, bio))
+	if (blk_throtl_bio(bio)) {
+		blkcg_bio_issue_init(bio);
 		return false;
+	}
+
+	blk_cgroup_bio_start(bio);
+	blkcg_bio_issue_init(bio);
 
 	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
 		trace_block_bio_queue(q, bio);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index ac0083450500..9d00f62c05ec 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2158,9 +2158,10 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 }
 #endif
 
-bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
-		    struct bio *bio)
+bool blk_throtl_bio(struct bio *bio)
 {
+	struct request_queue *q = bio->bi_disk->queue;
+	struct blkcg_gq *blkg = bio->bi_blkg;
 	struct throtl_qnode *qn = NULL;
 	struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg);
 	struct throtl_service_queue *sq;
diff --git a/block/blk.h b/block/blk.h
index 3a120a070dac..41a50880c94e 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -288,10 +288,12 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
 extern int blk_throtl_init(struct request_queue *q);
 extern void blk_throtl_exit(struct request_queue *q);
 extern void blk_throtl_register_queue(struct request_queue *q);
+bool blk_throtl_bio(struct bio *bio);
 #else /* CONFIG_BLK_DEV_THROTTLING */
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline void blk_throtl_exit(struct request_queue *q) { }
 static inline void blk_throtl_register_queue(struct request_queue *q) { }
+static inline bool blk_throtl_bio(struct bio *bio) { return false; }
 #endif /* CONFIG_BLK_DEV_THROTTLING */
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 8ab043c911f2..431b2d18bf40 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -517,14 +517,6 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
-#ifdef CONFIG_BLK_DEV_THROTTLING
-extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
-			   struct bio *bio);
-#else
-static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
-				  struct bio *bio) { return false; }
-#endif
-
 bool __blkcg_punt_bio_submit(struct bio *bio);
 
 static inline bool blkcg_punt_bio_submit(struct bio *bio)
@@ -540,50 +532,6 @@ static inline void blkcg_bio_issue_init(struct bio *bio)
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 }
 
-static inline bool blkcg_bio_issue_check(struct request_queue *q,
-					 struct bio *bio)
-{
-	struct blkcg_gq *blkg = bio->bi_blkg;
-	bool throtl = false;
-
-	throtl = blk_throtl_bio(q, blkg, bio);
-	if (!throtl) {
-		struct blkg_iostat_set *bis;
-		int rwd, cpu;
-
-		if (op_is_discard(bio->bi_opf))
-			rwd = BLKG_IOSTAT_DISCARD;
-		else if (op_is_write(bio->bi_opf))
-			rwd = BLKG_IOSTAT_WRITE;
-		else
-			rwd = BLKG_IOSTAT_READ;
-
-		cpu = get_cpu();
-		bis = per_cpu_ptr(blkg->iostat_cpu, cpu);
-		u64_stats_update_begin(&bis->sync);
-
-		/*
-		 * If the bio is flagged with BIO_CGROUP_ACCT it means this is a
-		 * split bio and we would have already accounted for the size of
-		 * the bio.
-		 */
-		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
-			bio_set_flag(bio, BIO_CGROUP_ACCT);
-			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
-		}
-		bis->cur.ios[rwd]++;
-
-		u64_stats_update_end(&bis->sync);
-		if (cgroup_subsys_on_dfl(io_cgrp_subsys))
-			cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu);
-		put_cpu();
-	}
-
-	blkcg_bio_issue_init(bio);
-
-	return !throtl;
-}
-
 static inline void blkcg_use_delay(struct blkcg_gq *blkg)
 {
 	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
@@ -657,6 +605,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
 		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
 }
 
+void blk_cgroup_bio_start(struct bio *bio);
 void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
 void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
@@ -710,8 +659,7 @@ static inline void blkg_put(struct blkcg_gq *blkg) { }
 
 static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; }
 static inline void blkcg_bio_issue_init(struct bio *bio) { }
-static inline bool blkcg_bio_issue_check(struct request_queue *q,
-					 struct bio *bio) { return true; }
+static inline void blk_cgroup_bio_start(struct bio *bio) { }
 
 #define blk_queue_for_each_rl(rl, q)	\
 	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
-- 
cgit v1.2.3


From 42fdc5e49c2be97db112d410d07044e0e2c7d5bb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 29 Jun 2020 17:08:34 +0200
Subject: blk-mq: remove the BLK_MQ_REQ_INTERNAL flag

Just check for a non-NULL elevator directly to make the code more clear.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c     |  4 ++--
 block/blk-mq.c         | 10 +++-------
 block/blk-mq.h         |  2 +-
 include/linux/blk-mq.h |  2 --
 4 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index ae722f8b13fb..281367b04527 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -90,9 +90,9 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
 			    struct sbitmap_queue *bt)
 {
-	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
-	    !hctx_may_queue(data->hctx, bt))
+	if (!data->q->elevator && !hctx_may_queue(data->hctx, bt))
 		return BLK_MQ_NO_TAG;
+
 	if (data->shallow_depth)
 		return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
 	else
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d07e55455726..72d3034fe39d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -279,7 +279,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	struct request *rq = tags->static_rqs[tag];
 	req_flags_t rq_flags = 0;
 
-	if (data->flags & BLK_MQ_REQ_INTERNAL) {
+	if (data->q->elevator) {
 		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
 	} else {
@@ -364,8 +364,6 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (e) {
-		data->flags |= BLK_MQ_REQ_INTERNAL;
-
 		/*
 		 * Flush requests are special and go directly to the
 		 * dispatch list. Don't include reserved tags in the
@@ -380,7 +378,7 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 retry:
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!(data->flags & BLK_MQ_REQ_INTERNAL))
+	if (!e)
 		blk_mq_tag_busy(data->hctx);
 
 	/*
@@ -476,9 +474,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	if (q->elevator)
-		data.flags |= BLK_MQ_REQ_INTERNAL;
-	else
+	if (!q->elevator)
 		blk_mq_tag_busy(data.hctx);
 
 	ret = -EWOULDBLOCK;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index b3ce0f3a2ad2..c6330335767c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -159,7 +159,7 @@ struct blk_mq_alloc_data {
 
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
-	if (data->flags & BLK_MQ_REQ_INTERNAL)
+	if (data->q->elevator)
 		return data->hctx->sched_tags;
 
 	return data->hctx->tags;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1641ec6cd7e5..8986e88a986b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -447,8 +447,6 @@ enum {
 	BLK_MQ_REQ_NOWAIT	= (__force blk_mq_req_flags_t)(1 << 0),
 	/* allocate from reserved pool */
 	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
-	/* allocate internal/sched tag */
-	BLK_MQ_REQ_INTERNAL	= (__force blk_mq_req_flags_t)(1 << 2),
 	/* set RQF_PREEMPT */
 	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
 };
-- 
cgit v1.2.3


From cbba1d719534b77b857267890b0f54f0f0a90de4 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Mon, 29 Jun 2020 14:29:17 +0200
Subject: thermal: Add current mode to thermal zone device

Prepare for changing the place where the mode is stored: now it is in
drivers, which might or might not implement get_mode()/set_mode() methods.
A lot of cleanup can be done thanks to storing it in struct tzd. The
get_mode() methods will become redundant.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200629122925.21729-4-andrzej.p@collabora.com
---
 include/linux/thermal.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 216185bb3014..5f91d7f04512 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -128,6 +128,7 @@ struct thermal_cooling_device {
  * @trip_temp_attrs:	attributes for trip points for sysfs: trip temperature
  * @trip_type_attrs:	attributes for trip points for sysfs: trip type
  * @trip_hyst_attrs:	attributes for trip points for sysfs: trip hysteresis
+ * @mode:		current mode of this thermal zone
  * @devdata:	private pointer for device private data
  * @trips:	number of trip points the thermal zone supports
  * @trips_disabled;	bitmap for disabled trips
@@ -170,6 +171,7 @@ struct thermal_zone_device {
 	struct thermal_attr *trip_temp_attrs;
 	struct thermal_attr *trip_type_attrs;
 	struct thermal_attr *trip_hyst_attrs;
+	enum thermal_device_mode mode;
 	void *devdata;
 	int trips;
 	unsigned long trips_disabled;	/* bitmap for disabled trips */
-- 
cgit v1.2.3


From 1ee14820fd8ee79c4fc191155f48c985f28040e2 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Mon, 29 Jun 2020 14:29:19 +0200
Subject: thermal: remove get_mode() operation of drivers

get_mode() is now redundant, as the state is stored in struct
thermal_zone_device.

Consequently the "mode" attribute in sysfs can always be visible, because
it is always possible to get the mode from struct tzd.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
[for acerhdf]
Acked-by: Peter Kaestle <peter@piie.net>
Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200629122925.21729-6-andrzej.p@collabora.com
---
 drivers/acpi/thermal.c                             |  9 -------
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 19 --------------
 drivers/platform/x86/acerhdf.c                     | 12 ---------
 drivers/thermal/da9062-thermal.c                   |  8 ------
 drivers/thermal/imx_thermal.c                      |  9 -------
 .../intel/int340x_thermal/int3400_thermal.c        |  9 -------
 drivers/thermal/intel/intel_quark_dts_thermal.c    |  8 ------
 drivers/thermal/thermal_core.c                     |  7 +----
 drivers/thermal/thermal_of.c                       |  9 -------
 drivers/thermal/thermal_sysfs.c                    | 30 ++--------------------
 include/linux/thermal.h                            |  2 --
 11 files changed, 3 insertions(+), 119 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 4ba273f49d87..592be97c4456 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -525,14 +525,6 @@ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
 	return 0;
 }
 
-static int thermal_get_mode(struct thermal_zone_device *thermal,
-				enum thermal_device_mode *mode)
-{
-	*mode = thermal->mode;
-
-	return 0;
-}
-
 static int thermal_set_mode(struct thermal_zone_device *thermal,
 				enum thermal_device_mode mode)
 {
@@ -847,7 +839,6 @@ static struct thermal_zone_device_ops acpi_thermal_zone_ops = {
 	.bind = acpi_thermal_bind_cooling_device,
 	.unbind	= acpi_thermal_unbind_cooling_device,
 	.get_temp = thermal_get_temp,
-	.get_mode = thermal_get_mode,
 	.set_mode = thermal_set_mode,
 	.get_trip_type = thermal_get_trip_type,
 	.get_trip_temp = thermal_get_trip_temp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 51667ed99c21..ad61b2db30b8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -275,14 +275,6 @@ static int mlxsw_thermal_unbind(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static int mlxsw_thermal_get_mode(struct thermal_zone_device *tzdev,
-				  enum thermal_device_mode *mode)
-{
-	*mode = tzdev->mode;
-
-	return 0;
-}
-
 static int mlxsw_thermal_set_mode(struct thermal_zone_device *tzdev,
 				  enum thermal_device_mode mode)
 {
@@ -402,7 +394,6 @@ static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
 static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.bind = mlxsw_thermal_bind,
 	.unbind = mlxsw_thermal_unbind,
-	.get_mode = mlxsw_thermal_get_mode,
 	.set_mode = mlxsw_thermal_set_mode,
 	.get_temp = mlxsw_thermal_get_temp,
 	.get_trip_type	= mlxsw_thermal_get_trip_type,
@@ -461,14 +452,6 @@ static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev,
 	return err;
 }
 
-static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev,
-					 enum thermal_device_mode *mode)
-{
-	*mode = tzdev->mode;
-
-	return 0;
-}
-
 static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev,
 					 enum thermal_device_mode mode)
 {
@@ -606,7 +589,6 @@ static int mlxsw_thermal_module_trend_get(struct thermal_zone_device *tzdev,
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
-	.get_mode	= mlxsw_thermal_module_mode_get,
 	.set_mode	= mlxsw_thermal_module_mode_set,
 	.get_temp	= mlxsw_thermal_module_temp_get,
 	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
@@ -645,7 +627,6 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
-	.get_mode	= mlxsw_thermal_module_mode_get,
 	.set_mode	= mlxsw_thermal_module_mode_set,
 	.get_temp	= mlxsw_thermal_gearbox_temp_get,
 	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 6f21015e5fd9..58c4e1caaa09 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -413,17 +413,6 @@ static inline void acerhdf_enable_kernelmode(void)
 	pr_notice("kernel mode fan control ON\n");
 }
 
-static int acerhdf_get_mode(struct thermal_zone_device *thermal,
-			    enum thermal_device_mode *mode)
-{
-	if (verbose)
-		pr_notice("kernel mode fan control %d\n", kernelmode);
-
-	*mode = thermal->mode;
-
-	return 0;
-}
-
 /*
  * set operation mode;
  * enabled: the thermal layer of the kernel takes care about
@@ -490,7 +479,6 @@ static struct thermal_zone_device_ops acerhdf_dev_ops = {
 	.bind = acerhdf_bind,
 	.unbind = acerhdf_unbind,
 	.get_temp = acerhdf_get_ec_temp,
-	.get_mode = acerhdf_get_mode,
 	.set_mode = acerhdf_set_mode,
 	.get_trip_type = acerhdf_get_trip_type,
 	.get_trip_hyst = acerhdf_get_trip_hyst,
diff --git a/drivers/thermal/da9062-thermal.c b/drivers/thermal/da9062-thermal.c
index a14c7981c7c7..a7ac8afb063e 100644
--- a/drivers/thermal/da9062-thermal.c
+++ b/drivers/thermal/da9062-thermal.c
@@ -120,13 +120,6 @@ static irqreturn_t da9062_thermal_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int da9062_thermal_get_mode(struct thermal_zone_device *z,
-				   enum thermal_device_mode *mode)
-{
-	*mode = z->mode;
-	return 0;
-}
-
 static int da9062_thermal_get_trip_type(struct thermal_zone_device *z,
 					int trip,
 					enum thermal_trip_type *type)
@@ -179,7 +172,6 @@ static int da9062_thermal_get_temp(struct thermal_zone_device *z,
 
 static struct thermal_zone_device_ops da9062_thermal_ops = {
 	.get_temp	= da9062_thermal_get_temp,
-	.get_mode	= da9062_thermal_get_mode,
 	.get_trip_type	= da9062_thermal_get_trip_type,
 	.get_trip_temp	= da9062_thermal_get_trip_temp,
 };
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 9a1114d721b6..2c7ee5da608a 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -330,14 +330,6 @@ static int imx_get_temp(struct thermal_zone_device *tz, int *temp)
 	return 0;
 }
 
-static int imx_get_mode(struct thermal_zone_device *tz,
-			enum thermal_device_mode *mode)
-{
-	*mode = tz->mode;
-
-	return 0;
-}
-
 static int imx_set_mode(struct thermal_zone_device *tz,
 			enum thermal_device_mode mode)
 {
@@ -464,7 +456,6 @@ static struct thermal_zone_device_ops imx_tz_ops = {
 	.bind = imx_bind,
 	.unbind = imx_unbind,
 	.get_temp = imx_get_temp,
-	.get_mode = imx_get_mode,
 	.set_mode = imx_set_mode,
 	.get_trip_type = imx_get_trip_type,
 	.get_trip_temp = imx_get_trip_temp,
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index f65b2fc09198..9a622aaf29dd 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -377,14 +377,6 @@ static int int3400_thermal_get_temp(struct thermal_zone_device *thermal,
 	return 0;
 }
 
-static int int3400_thermal_get_mode(struct thermal_zone_device *thermal,
-				enum thermal_device_mode *mode)
-{
-	*mode = thermal->mode;
-
-	return 0;
-}
-
 static int int3400_thermal_set_mode(struct thermal_zone_device *thermal,
 				enum thermal_device_mode mode)
 {
@@ -412,7 +404,6 @@ static int int3400_thermal_set_mode(struct thermal_zone_device *thermal,
 
 static struct thermal_zone_device_ops int3400_thermal_ops = {
 	.get_temp = int3400_thermal_get_temp,
-	.get_mode = int3400_thermal_get_mode,
 	.set_mode = int3400_thermal_set_mode,
 };
 
diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c
index d77cb3df5ade..c4879b4bfbf1 100644
--- a/drivers/thermal/intel/intel_quark_dts_thermal.c
+++ b/drivers/thermal/intel/intel_quark_dts_thermal.c
@@ -308,13 +308,6 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	return 0;
 }
 
-static int sys_get_mode(struct thermal_zone_device *tzd,
-				enum thermal_device_mode *mode)
-{
-	*mode = tzd->mode;
-	return 0;
-}
-
 static int sys_set_mode(struct thermal_zone_device *tzd,
 				enum thermal_device_mode mode)
 {
@@ -336,7 +329,6 @@ static struct thermal_zone_device_ops tzone_ops = {
 	.get_trip_type = sys_get_trip_type,
 	.set_trip_temp = sys_set_trip_temp,
 	.get_crit_temp = sys_get_crit_temp,
-	.get_mode = sys_get_mode,
 	.set_mode = sys_set_mode,
 };
 
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index b71196eaf90e..14d3b1b94c4f 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1456,7 +1456,6 @@ static int thermal_pm_notify(struct notifier_block *nb,
 			     unsigned long mode, void *_unused)
 {
 	struct thermal_zone_device *tz;
-	enum thermal_device_mode tz_mode;
 
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
@@ -1469,11 +1468,7 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_POST_SUSPEND:
 		atomic_set(&in_suspend, 0);
 		list_for_each_entry(tz, &thermal_tz_list, node) {
-			tz_mode = THERMAL_DEVICE_ENABLED;
-			if (tz->ops->get_mode)
-				tz->ops->get_mode(tz, &tz_mode);
-
-			if (tz_mode == THERMAL_DEVICE_DISABLED)
+			if (tz->mode == THERMAL_DEVICE_DISABLED)
 				continue;
 
 			thermal_zone_device_init(tz);
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index c495b1e48ef2..ba65d48a48cb 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -267,14 +267,6 @@ static int of_thermal_unbind(struct thermal_zone_device *thermal,
 	return 0;
 }
 
-static int of_thermal_get_mode(struct thermal_zone_device *tz,
-			       enum thermal_device_mode *mode)
-{
-	*mode = tz->mode;
-
-	return 0;
-}
-
 static int of_thermal_set_mode(struct thermal_zone_device *tz,
 			       enum thermal_device_mode mode)
 {
@@ -389,7 +381,6 @@ static int of_thermal_get_crit_temp(struct thermal_zone_device *tz,
 }
 
 static struct thermal_zone_device_ops of_thermal_ops = {
-	.get_mode = of_thermal_get_mode,
 	.set_mode = of_thermal_set_mode,
 
 	.get_trip_type = of_thermal_get_trip_type,
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index aa99edb4dff7..096370977068 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -49,18 +49,9 @@ static ssize_t
 mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	enum thermal_device_mode mode;
-	int result;
-
-	if (!tz->ops->get_mode)
-		return -EPERM;
 
-	result = tz->ops->get_mode(tz, &mode);
-	if (result)
-		return result;
-
-	return sprintf(buf, "%s\n", mode == THERMAL_DEVICE_ENABLED ? "enabled"
-		       : "disabled");
+	return sprintf(buf, "%s\n", tz->mode == THERMAL_DEVICE_ENABLED ?
+		       "enabled" : "disabled");
 }
 
 static ssize_t
@@ -428,30 +419,13 @@ static struct attribute_group thermal_zone_attribute_group = {
 	.attrs = thermal_zone_dev_attrs,
 };
 
-/* We expose mode only if .get_mode is present */
 static struct attribute *thermal_zone_mode_attrs[] = {
 	&dev_attr_mode.attr,
 	NULL,
 };
 
-static umode_t thermal_zone_mode_is_visible(struct kobject *kobj,
-					    struct attribute *attr,
-					    int attrno)
-{
-	struct device *dev = container_of(kobj, struct device, kobj);
-	struct thermal_zone_device *tz;
-
-	tz = container_of(dev, struct thermal_zone_device, device);
-
-	if (tz->ops->get_mode)
-		return attr->mode;
-
-	return 0;
-}
-
 static struct attribute_group thermal_zone_mode_attribute_group = {
 	.attrs = thermal_zone_mode_attrs,
-	.is_visible = thermal_zone_mode_is_visible,
 };
 
 /* We expose passive only if passive trips are present */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 5f91d7f04512..a808f6fa2777 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -76,8 +76,6 @@ struct thermal_zone_device_ops {
 		       struct thermal_cooling_device *);
 	int (*get_temp) (struct thermal_zone_device *, int *);
 	int (*set_trips) (struct thermal_zone_device *, int, int);
-	int (*get_mode) (struct thermal_zone_device *,
-			 enum thermal_device_mode *);
 	int (*set_mode) (struct thermal_zone_device *,
 		enum thermal_device_mode);
 	int (*get_trip_type) (struct thermal_zone_device *, int,
-- 
cgit v1.2.3


From ac5d9ecc74d8beee8c87f1441e4adaf4e9fe90c5 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Mon, 29 Jun 2020 14:29:20 +0200
Subject: thermal: Add mode helpers

Prepare for making the drivers not access tzd's private members.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
[staticize thermal_zone_device_set_mode()]
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200629122925.21729-7-andrzej.p@collabora.com
---
 drivers/thermal/thermal_core.c | 53 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/thermal.h        | 13 +++++++++++
 2 files changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 14d3b1b94c4f..f02c57c986f0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -459,6 +459,59 @@ static void thermal_zone_device_reset(struct thermal_zone_device *tz)
 	thermal_zone_device_init(tz);
 }
 
+static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+					enum thermal_device_mode mode)
+{
+	int ret = 0;
+
+	mutex_lock(&tz->lock);
+
+	/* do nothing if mode isn't changing */
+	if (mode == tz->mode) {
+		mutex_unlock(&tz->lock);
+
+		return ret;
+	}
+
+	if (tz->ops->set_mode)
+		ret = tz->ops->set_mode(tz, mode);
+
+	if (!ret)
+		tz->mode = mode;
+
+	mutex_unlock(&tz->lock);
+
+	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+
+	return ret;
+}
+
+int thermal_zone_device_enable(struct thermal_zone_device *tz)
+{
+	return thermal_zone_device_set_mode(tz, THERMAL_DEVICE_ENABLED);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_device_enable);
+
+int thermal_zone_device_disable(struct thermal_zone_device *tz)
+{
+	return thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_device_disable);
+
+int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
+{
+	enum thermal_device_mode mode;
+
+	mutex_lock(&tz->lock);
+
+	mode = tz->mode;
+
+	mutex_unlock(&tz->lock);
+
+	return mode == THERMAL_DEVICE_ENABLED;
+}
+EXPORT_SYMBOL_GPL(thermal_zone_device_is_enabled);
+
 void thermal_zone_device_update(struct thermal_zone_device *tz,
 				enum thermal_notify_event event)
 {
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a808f6fa2777..df013c39ba9b 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -416,6 +416,9 @@ int thermal_zone_get_offset(struct thermal_zone_device *tz);
 
 void thermal_cdev_update(struct thermal_cooling_device *);
 void thermal_notify_framework(struct thermal_zone_device *, int);
+int thermal_zone_device_enable(struct thermal_zone_device *tz);
+int thermal_zone_device_disable(struct thermal_zone_device *tz);
+int thermal_zone_device_is_enabled(struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
@@ -463,6 +466,16 @@ static inline void thermal_cdev_update(struct thermal_cooling_device *cdev)
 static inline void thermal_notify_framework(struct thermal_zone_device *tz,
 	int trip)
 { }
+
+static inline int thermal_zone_device_enable(struct thermal_zone_device *tz)
+{ return -ENODEV; }
+
+static inline int thermal_zone_device_disable(struct thermal_zone_device *tz)
+{ return -ENODEV; }
+
+static inline int
+thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
+{ return -ENODEV; }
 #endif /* CONFIG_THERMAL */
 
 #endif /* __THERMAL_H__ */
-- 
cgit v1.2.3


From f5e50bf4d3ef0aba4d5414c9ed51fa4a02e2ed12 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Mon, 29 Jun 2020 14:29:25 +0200
Subject: thermal: Rename set_mode() to change_mode()

set_mode() is only called when tzd's mode is about to change. Actual
setting is performed in thermal_core, in thermal_zone_device_set_mode().
The meaning of set_mode() callback is actually to notify the driver about
the mode being changed and giving the driver a chance to oppose such
change.

To better reflect the purpose of the method rename it to change_mode()

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
[for acerhdf]
Acked-by: Peter Kaestle <peter@piie.net>
Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200629122925.21729-12-andrzej.p@collabora.com
---
 drivers/platform/x86/acerhdf.c                          | 6 +++---
 drivers/thermal/imx_thermal.c                           | 8 ++++----
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 6 +++---
 drivers/thermal/intel/intel_quark_dts_thermal.c         | 6 +++---
 drivers/thermal/thermal_core.c                          | 4 ++--
 include/linux/thermal.h                                 | 2 +-
 6 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 76323855c80c..f816a8a13039 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -413,8 +413,8 @@ static inline void acerhdf_enable_kernelmode(void)
  *          the temperature and the fan.
  * disabled: the BIOS takes control of the fan.
  */
-static int acerhdf_set_mode(struct thermal_zone_device *thermal,
-			    enum thermal_device_mode mode)
+static int acerhdf_change_mode(struct thermal_zone_device *thermal,
+			       enum thermal_device_mode mode)
 {
 	if (mode == THERMAL_DEVICE_DISABLED && kernelmode)
 		acerhdf_revert_to_bios_mode();
@@ -473,7 +473,7 @@ static struct thermal_zone_device_ops acerhdf_dev_ops = {
 	.bind = acerhdf_bind,
 	.unbind = acerhdf_unbind,
 	.get_temp = acerhdf_get_ec_temp,
-	.set_mode = acerhdf_set_mode,
+	.change_mode = acerhdf_change_mode,
 	.get_trip_type = acerhdf_get_trip_type,
 	.get_trip_hyst = acerhdf_get_trip_hyst,
 	.get_trip_temp = acerhdf_get_trip_temp,
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index a02398118d88..9700ae39feb7 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -330,8 +330,8 @@ static int imx_get_temp(struct thermal_zone_device *tz, int *temp)
 	return 0;
 }
 
-static int imx_set_mode(struct thermal_zone_device *tz,
-			enum thermal_device_mode mode)
+static int imx_change_mode(struct thermal_zone_device *tz,
+			   enum thermal_device_mode mode)
 {
 	struct imx_thermal_data *data = tz->devdata;
 	struct regmap *map = data->tempmon;
@@ -447,7 +447,7 @@ static struct thermal_zone_device_ops imx_tz_ops = {
 	.bind = imx_bind,
 	.unbind = imx_unbind,
 	.get_temp = imx_get_temp,
-	.set_mode = imx_set_mode,
+	.change_mode = imx_change_mode,
 	.get_trip_type = imx_get_trip_type,
 	.get_trip_temp = imx_get_trip_temp,
 	.get_crit_temp = imx_get_crit_temp,
@@ -860,7 +860,7 @@ static int __maybe_unused imx_thermal_suspend(struct device *dev)
 	 * Need to disable thermal sensor, otherwise, when thermal core
 	 * try to get temperature before thermal sensor resume, a wrong
 	 * temperature will be read as the thermal sensor is powered
-	 * down. This is done in set_mode() operation called from
+	 * down. This is done in change_mode() operation called from
 	 * thermal_zone_device_disable()
 	 */
 	ret = thermal_zone_device_disable(data->tz);
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index ce49d3b100d5..d3732f624913 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -377,8 +377,8 @@ static int int3400_thermal_get_temp(struct thermal_zone_device *thermal,
 	return 0;
 }
 
-static int int3400_thermal_set_mode(struct thermal_zone_device *thermal,
-				enum thermal_device_mode mode)
+static int int3400_thermal_change_mode(struct thermal_zone_device *thermal,
+				       enum thermal_device_mode mode)
 {
 	struct int3400_thermal_priv *priv = thermal->devdata;
 	int result = 0;
@@ -399,7 +399,7 @@ static int int3400_thermal_set_mode(struct thermal_zone_device *thermal,
 
 static struct thermal_zone_device_ops int3400_thermal_ops = {
 	.get_temp = int3400_thermal_get_temp,
-	.set_mode = int3400_thermal_set_mode,
+	.change_mode = int3400_thermal_change_mode,
 };
 
 static struct thermal_zone_params int3400_thermal_params = {
diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c
index e29c3e330b17..3eafc6b0e6c3 100644
--- a/drivers/thermal/intel/intel_quark_dts_thermal.c
+++ b/drivers/thermal/intel/intel_quark_dts_thermal.c
@@ -298,8 +298,8 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	return 0;
 }
 
-static int sys_set_mode(struct thermal_zone_device *tzd,
-				enum thermal_device_mode mode)
+static int sys_change_mode(struct thermal_zone_device *tzd,
+			   enum thermal_device_mode mode)
 {
 	int ret;
 
@@ -319,7 +319,7 @@ static struct thermal_zone_device_ops tzone_ops = {
 	.get_trip_type = sys_get_trip_type,
 	.set_trip_temp = sys_set_trip_temp,
 	.get_crit_temp = sys_get_crit_temp,
-	.set_mode = sys_set_mode,
+	.change_mode = sys_change_mode,
 };
 
 static void free_soc_dts(struct soc_sensor_entry *aux_entry)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index e613f5c07bad..a61e91513584 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -482,8 +482,8 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 		return ret;
 	}
 
-	if (tz->ops->set_mode)
-		ret = tz->ops->set_mode(tz, mode);
+	if (tz->ops->change_mode)
+		ret = tz->ops->change_mode(tz, mode);
 
 	if (!ret)
 		tz->mode = mode;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index df013c39ba9b..b9efaa780d88 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -76,7 +76,7 @@ struct thermal_zone_device_ops {
 		       struct thermal_cooling_device *);
 	int (*get_temp) (struct thermal_zone_device *, int *);
 	int (*set_trips) (struct thermal_zone_device *, int, int);
-	int (*set_mode) (struct thermal_zone_device *,
+	int (*change_mode) (struct thermal_zone_device *,
 		enum thermal_device_mode);
 	int (*get_trip_type) (struct thermal_zone_device *, int,
 		enum thermal_trip_type *);
-- 
cgit v1.2.3


From 2cdb54c93a7e5beb6f3f8b63575d9fb664dfc603 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 21 Apr 2020 19:04:05 +0200
Subject: docs: RCU: Convert rculist_nulls.txt to ReST

- Add a SPDX header;
- Adjust document title;
- Some whitespace fixes and new line breaks;
- Mark literal blocks as such;
- Add it to RCU/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/RCU/index.rst         |   1 +
 Documentation/RCU/rculist_nulls.rst | 194 ++++++++++++++++++++++++++++++++++++
 Documentation/RCU/rculist_nulls.txt | 172 --------------------------------
 include/linux/rculist_nulls.h       |   2 +-
 net/core/sock.c                     |   4 +-
 5 files changed, 198 insertions(+), 175 deletions(-)
 create mode 100644 Documentation/RCU/rculist_nulls.rst
 delete mode 100644 Documentation/RCU/rculist_nulls.txt

(limited to 'include/linux')

diff --git a/Documentation/RCU/index.rst b/Documentation/RCU/index.rst
index fa7a2a8949b7..577a47e27f5d 100644
--- a/Documentation/RCU/index.rst
+++ b/Documentation/RCU/index.rst
@@ -17,6 +17,7 @@ RCU concepts
    rcu_dereference
    whatisRCU
    rcu
+   rculist_nulls
    listRCU
    NMI-RCU
    UP
diff --git a/Documentation/RCU/rculist_nulls.rst b/Documentation/RCU/rculist_nulls.rst
new file mode 100644
index 000000000000..d40374221d69
--- /dev/null
+++ b/Documentation/RCU/rculist_nulls.rst
@@ -0,0 +1,194 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================================
+Using RCU hlist_nulls to protect list and objects
+=================================================
+
+This section describes how to use hlist_nulls to
+protect read-mostly linked lists and
+objects using SLAB_TYPESAFE_BY_RCU allocations.
+
+Please read the basics in Documentation/RCU/listRCU.rst
+
+Using special makers (called 'nulls') is a convenient way
+to solve following problem :
+
+A typical RCU linked list managing objects which are
+allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can
+use following algos :
+
+1) Lookup algo
+--------------
+
+::
+
+  rcu_read_lock()
+  begin:
+  obj = lockless_lookup(key);
+  if (obj) {
+    if (!try_get_ref(obj)) // might fail for free objects
+      goto begin;
+    /*
+    * Because a writer could delete object, and a writer could
+    * reuse these object before the RCU grace period, we
+    * must check key after getting the reference on object
+    */
+    if (obj->key != key) { // not the object we expected
+      put_ref(obj);
+      goto begin;
+    }
+  }
+  rcu_read_unlock();
+
+Beware that lockless_lookup(key) cannot use traditional hlist_for_each_entry_rcu()
+but a version with an additional memory barrier (smp_rmb())
+
+::
+
+  lockless_lookup(key)
+  {
+    struct hlist_node *node, *next;
+    for (pos = rcu_dereference((head)->first);
+        pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) &&
+        ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });
+        pos = rcu_dereference(next))
+      if (obj->key == key)
+        return obj;
+    return NULL;
+  }
+
+And note the traditional hlist_for_each_entry_rcu() misses this smp_rmb()::
+
+  struct hlist_node *node;
+  for (pos = rcu_dereference((head)->first);
+        pos && ({ prefetch(pos->next); 1; }) &&
+        ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });
+        pos = rcu_dereference(pos->next))
+   if (obj->key == key)
+     return obj;
+  return NULL;
+
+Quoting Corey Minyard::
+
+  "If the object is moved from one list to another list in-between the
+  time the hash is calculated and the next field is accessed, and the
+  object has moved to the end of a new list, the traversal will not
+  complete properly on the list it should have, since the object will
+  be on the end of the new list and there's not a way to tell it's on a
+  new list and restart the list traversal. I think that this can be
+  solved by pre-fetching the "next" field (with proper barriers) before
+  checking the key."
+
+2) Insert algo
+--------------
+
+We need to make sure a reader cannot read the new 'obj->obj_next' value
+and previous value of 'obj->key'. Or else, an item could be deleted
+from a chain, and inserted into another chain. If new chain was empty
+before the move, 'next' pointer is NULL, and lockless reader can
+not detect it missed following items in original chain.
+
+::
+
+  /*
+  * Please note that new inserts are done at the head of list,
+  * not in the middle or end.
+  */
+  obj = kmem_cache_alloc(...);
+  lock_chain(); // typically a spin_lock()
+  obj->key = key;
+  /*
+  * we need to make sure obj->key is updated before obj->next
+  * or obj->refcnt
+  */
+  smp_wmb();
+  atomic_set(&obj->refcnt, 1);
+  hlist_add_head_rcu(&obj->obj_node, list);
+  unlock_chain(); // typically a spin_unlock()
+
+
+3) Remove algo
+--------------
+Nothing special here, we can use a standard RCU hlist deletion.
+But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused
+very very fast (before the end of RCU grace period)
+
+::
+
+  if (put_last_reference_on(obj) {
+    lock_chain(); // typically a spin_lock()
+    hlist_del_init_rcu(&obj->obj_node);
+    unlock_chain(); // typically a spin_unlock()
+    kmem_cache_free(cachep, obj);
+  }
+
+
+
+--------------------------------------------------------------------------
+
+With hlist_nulls we can avoid extra smp_rmb() in lockless_lookup()
+and extra smp_wmb() in insert function.
+
+For example, if we choose to store the slot number as the 'nulls'
+end-of-list marker for each slot of the hash table, we can detect
+a race (some writer did a delete and/or a move of an object
+to another chain) checking the final 'nulls' value if
+the lookup met the end of chain. If final 'nulls' value
+is not the slot number, then we must restart the lookup at
+the beginning. If the object was moved to the same chain,
+then the reader doesn't care : It might eventually
+scan the list again without harm.
+
+
+1) lookup algo
+--------------
+
+::
+
+  head = &table[slot];
+  rcu_read_lock();
+  begin:
+  hlist_nulls_for_each_entry_rcu(obj, node, head, member) {
+    if (obj->key == key) {
+      if (!try_get_ref(obj)) // might fail for free objects
+        goto begin;
+      if (obj->key != key) { // not the object we expected
+        put_ref(obj);
+        goto begin;
+      }
+    goto out;
+  }
+  /*
+  * if the nulls value we got at the end of this lookup is
+  * not the expected one, we must restart lookup.
+  * We probably met an item that was moved to another chain.
+  */
+  if (get_nulls_value(node) != slot)
+  goto begin;
+  obj = NULL;
+
+  out:
+  rcu_read_unlock();
+
+2) Insert function
+------------------
+
+::
+
+  /*
+  * Please note that new inserts are done at the head of list,
+  * not in the middle or end.
+  */
+  obj = kmem_cache_alloc(cachep);
+  lock_chain(); // typically a spin_lock()
+  obj->key = key;
+  /*
+  * changes to obj->key must be visible before refcnt one
+  */
+  smp_wmb();
+  atomic_set(&obj->refcnt, 1);
+  /*
+  * insert obj in RCU way (readers might be traversing chain)
+  */
+  hlist_nulls_add_head_rcu(&obj->obj_node, list);
+  unlock_chain(); // typically a spin_unlock()
diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt
deleted file mode 100644
index 23f115dc87cf..000000000000
--- a/Documentation/RCU/rculist_nulls.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-Using hlist_nulls to protect read-mostly linked lists and
-objects using SLAB_TYPESAFE_BY_RCU allocations.
-
-Please read the basics in Documentation/RCU/listRCU.rst
-
-Using special makers (called 'nulls') is a convenient way
-to solve following problem :
-
-A typical RCU linked list managing objects which are
-allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can
-use following algos :
-
-1) Lookup algo
---------------
-rcu_read_lock()
-begin:
-obj = lockless_lookup(key);
-if (obj) {
-  if (!try_get_ref(obj)) // might fail for free objects
-    goto begin;
-  /*
-   * Because a writer could delete object, and a writer could
-   * reuse these object before the RCU grace period, we
-   * must check key after getting the reference on object
-   */
-  if (obj->key != key) { // not the object we expected
-     put_ref(obj);
-     goto begin;
-   }
-}
-rcu_read_unlock();
-
-Beware that lockless_lookup(key) cannot use traditional hlist_for_each_entry_rcu()
-but a version with an additional memory barrier (smp_rmb())
-
-lockless_lookup(key)
-{
-   struct hlist_node *node, *next;
-   for (pos = rcu_dereference((head)->first);
-          pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) &&
-          ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });
-          pos = rcu_dereference(next))
-      if (obj->key == key)
-         return obj;
-   return NULL;
-
-And note the traditional hlist_for_each_entry_rcu() misses this smp_rmb() :
-
-   struct hlist_node *node;
-   for (pos = rcu_dereference((head)->first);
-		pos && ({ prefetch(pos->next); 1; }) &&
-		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });
-		pos = rcu_dereference(pos->next))
-      if (obj->key == key)
-         return obj;
-   return NULL;
-}
-
-Quoting Corey Minyard :
-
-"If the object is moved from one list to another list in-between the
- time the hash is calculated and the next field is accessed, and the
- object has moved to the end of a new list, the traversal will not
- complete properly on the list it should have, since the object will
- be on the end of the new list and there's not a way to tell it's on a
- new list and restart the list traversal.  I think that this can be
- solved by pre-fetching the "next" field (with proper barriers) before
- checking the key."
-
-2) Insert algo :
-----------------
-
-We need to make sure a reader cannot read the new 'obj->obj_next' value
-and previous value of 'obj->key'. Or else, an item could be deleted
-from a chain, and inserted into another chain. If new chain was empty
-before the move, 'next' pointer is NULL, and lockless reader can
-not detect it missed following items in original chain.
-
-/*
- * Please note that new inserts are done at the head of list,
- * not in the middle or end.
- */
-obj = kmem_cache_alloc(...);
-lock_chain(); // typically a spin_lock()
-obj->key = key;
-/*
- * we need to make sure obj->key is updated before obj->next
- * or obj->refcnt
- */
-smp_wmb();
-atomic_set(&obj->refcnt, 1);
-hlist_add_head_rcu(&obj->obj_node, list);
-unlock_chain(); // typically a spin_unlock()
-
-
-3) Remove algo
---------------
-Nothing special here, we can use a standard RCU hlist deletion.
-But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused
-very very fast (before the end of RCU grace period)
-
-if (put_last_reference_on(obj) {
-   lock_chain(); // typically a spin_lock()
-   hlist_del_init_rcu(&obj->obj_node);
-   unlock_chain(); // typically a spin_unlock()
-   kmem_cache_free(cachep, obj);
-}
-
-
-
---------------------------------------------------------------------------
-With hlist_nulls we can avoid extra smp_rmb() in lockless_lookup()
-and extra smp_wmb() in insert function.
-
-For example, if we choose to store the slot number as the 'nulls'
-end-of-list marker for each slot of the hash table, we can detect
-a race (some writer did a delete and/or a move of an object
-to another chain) checking the final 'nulls' value if
-the lookup met the end of chain. If final 'nulls' value
-is not the slot number, then we must restart the lookup at
-the beginning. If the object was moved to the same chain,
-then the reader doesn't care : It might eventually
-scan the list again without harm.
-
-
-1) lookup algo
-
- head = &table[slot];
- rcu_read_lock();
-begin:
- hlist_nulls_for_each_entry_rcu(obj, node, head, member) {
-   if (obj->key == key) {
-      if (!try_get_ref(obj)) // might fail for free objects
-         goto begin;
-      if (obj->key != key) { // not the object we expected
-         put_ref(obj);
-         goto begin;
-      }
-  goto out;
- }
-/*
- * if the nulls value we got at the end of this lookup is
- * not the expected one, we must restart lookup.
- * We probably met an item that was moved to another chain.
- */
- if (get_nulls_value(node) != slot)
-   goto begin;
- obj = NULL;
-
-out:
- rcu_read_unlock();
-
-2) Insert function :
---------------------
-
-/*
- * Please note that new inserts are done at the head of list,
- * not in the middle or end.
- */
-obj = kmem_cache_alloc(cachep);
-lock_chain(); // typically a spin_lock()
-obj->key = key;
-/*
- * changes to obj->key must be visible before refcnt one
- */
-smp_wmb();
-atomic_set(&obj->refcnt, 1);
-/*
- * insert obj in RCU way (readers might be traversing chain)
- */
-hlist_nulls_add_head_rcu(&obj->obj_node, list);
-unlock_chain(); // typically a spin_unlock()
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 9670b54b484a..ff3e94779e73 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -162,7 +162,7 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
  * The barrier() is needed to make sure compiler doesn't cache first element [1],
  * as this loop can be restarted [2]
  * [1] Documentation/core-api/atomic_ops.rst around line 114
- * [2] Documentation/RCU/rculist_nulls.txt around line 146
+ * [2] Documentation/RCU/rculist_nulls.rst around line 146
  */
 #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member)			\
 	for (({barrier();}),							\
diff --git a/net/core/sock.c b/net/core/sock.c
index d832c650287c..6921a85a1177 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1973,7 +1973,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
-		 * (Documentation/RCU/rculist_nulls.txt for details)
+		 * (Documentation/RCU/rculist_nulls.rst for details)
 		 */
 		smp_wmb();
 		refcount_set(&newsk->sk_refcnt, 2);
@@ -3035,7 +3035,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk_rx_queue_clear(sk);
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
-	 * (Documentation/RCU/rculist_nulls.txt for details)
+	 * (Documentation/RCU/rculist_nulls.rst for details)
 	 */
 	smp_wmb();
 	refcount_set(&sk->sk_refcnt, 1);
-- 
cgit v1.2.3


From 24692fa22c30cb8fcfcabdc07a3c82964475b639 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 15 Jun 2020 08:46:49 +0200
Subject: rcu: Fix some kernel-doc warnings

The current code provokes some kernel-doc warnings:

	./kernel/rcu/tree.c:2915: warning: Function parameter or member 'count' not described in 'kfree_rcu_cpu'
	./include/linux/rculist.h:517: warning: bad line:                           [@right ][node2 ... ]
	./include/linux/rculist.h:2: WARNING: Unexpected indentation.

This commit therefore moves the comment for "count" to the kernel-doc
markup and adds a missing "*" on one kernel-doc continuation line.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rculist.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index df587d181844..7eed65b5f713 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -512,7 +512,7 @@ static inline void hlist_replace_rcu(struct hlist_node *old,
  * @right: The hlist head on the right
  *
  * The lists start out as [@left  ][node1 ... ] and
-                          [@right ][node2 ... ]
+ *                        [@right ][node2 ... ]
  * The lists end up as    [@left  ][node2 ... ]
  *                        [@right ][node1 ... ]
  */
-- 
cgit v1.2.3


From c408b215f58f7156bb6bafb64c0263ee907033df Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 25 May 2020 23:47:55 +0200
Subject: rcu: Rename *_kfree_callback/*_kfree_rcu_offset/kfree_call_*

The following changes are introduced:

1. Rename rcu_invoke_kfree_callback() to rcu_invoke_kvfree_callback(),
as well as the associated trace events, so the rcu_kfree_callback(),
becomes rcu_kvfree_callback(). The reason is to be aligned with kvfree()
notation.

2. Rename __is_kfree_rcu_offset to __is_kvfree_rcu_offset. All RCU
paths use kvfree() now instead of kfree(), thus rename it.

3. Rename kfree_call_rcu() to the kvfree_call_rcu(). The reason is,
it is capable of freeing vmalloc() memory now. Do the same with
__kfree_rcu() macro, it becomes __kvfree_rcu(), the goal is the
same.

Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h   | 14 +++++++-------
 include/linux/rcutiny.h    |  2 +-
 include/linux/rcutree.h    |  2 +-
 include/trace/events/rcu.h |  8 ++++----
 kernel/rcu/tiny.c          |  4 ++--
 kernel/rcu/tree.c          | 16 ++++++++--------
 6 files changed, 23 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 659cbfa7581a..b344fc800a9b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -828,17 +828,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
- * structure can be handled by kfree_rcu()?
+ * structure can be handled by kvfree_rcu()?
  */
-#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
+#define __is_kvfree_rcu_offset(offset) ((offset) < 4096)
 
 /*
  * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
  */
-#define __kfree_rcu(head, offset) \
+#define __kvfree_rcu(head, offset) \
 	do { \
-		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
-		kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \
+		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \
+		kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \
 	} while (0)
 
 /**
@@ -857,7 +857,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * Because the functions are not allowed in the low-order 4096 bytes of
  * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
  * If the offset is larger than 4095 bytes, a compile-time error will
- * be generated in __kfree_rcu().  If this error is triggered, you can
+ * be generated in __kvfree_rcu(). If this error is triggered, you can
  * either fall back to use of call_rcu() or rearrange the structure to
  * position the rcu_head structure into the first 4096 bytes.
  *
@@ -872,7 +872,7 @@ do {									\
 	typeof (ptr) ___p = (ptr);					\
 									\
 	if (___p)							\
-		__kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
+		__kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
 } while (0)
 
 /*
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 8512caeb7682..fb2eb39c484f 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -34,7 +34,7 @@ static inline void synchronize_rcu_expedited(void)
 	synchronize_rcu();
 }
 
-static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	call_rcu(head, func);
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d5cc9d675987..d2f4064ebd1d 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -33,7 +33,7 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 void synchronize_rcu_expedited(void);
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
 
 void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index f9a7811148e2..0ee93d0b1daa 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -506,13 +506,13 @@ TRACE_EVENT_RCU(rcu_callback,
 
 /*
  * Tracepoint for the registration of a single RCU callback of the special
- * kfree() form.  The first argument is the RCU type, the second argument
+ * kvfree() form.  The first argument is the RCU type, the second argument
  * is a pointer to the RCU callback, the third argument is the offset
  * of the callback within the enclosing RCU-protected data structure,
  * the fourth argument is the number of lazy callbacks queued, and the
  * fifth argument is the total number of callbacks queued.
  */
-TRACE_EVENT_RCU(rcu_kfree_callback,
+TRACE_EVENT_RCU(rcu_kvfree_callback,
 
 	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset,
 		 long qlen),
@@ -596,12 +596,12 @@ TRACE_EVENT_RCU(rcu_invoke_callback,
 
 /*
  * Tracepoint for the invocation of a single RCU callback of the special
- * kfree() form.  The first argument is the RCU flavor, the second
+ * kvfree() form.  The first argument is the RCU flavor, the second
  * argument is a pointer to the RCU callback, and the third argument
  * is the offset of the callback within the enclosing RCU-protected
  * data structure.
  */
-TRACE_EVENT_RCU(rcu_invoke_kfree_callback,
+TRACE_EVENT_RCU(rcu_invoke_kvfree_callback,
 
 	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset),
 
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 4b99f7b88bee..aa897c3f2e92 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -85,8 +85,8 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
 	unsigned long offset = (unsigned long)head->func;
 
 	rcu_lock_acquire(&rcu_callback_map);
-	if (__is_kfree_rcu_offset(offset)) {
-		trace_rcu_invoke_kfree_callback("", head, offset);
+	if (__is_kvfree_rcu_offset(offset)) {
+		trace_rcu_invoke_kvfree_callback("", head, offset);
 		kvfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
 		return true;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 67c4b984c499..f22c47e72287 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2905,8 +2905,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return; // Enqueued onto ->nocb_bypass, so just leave.
 	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
-	if (__is_kfree_rcu_offset((unsigned long)func))
-		trace_rcu_kfree_callback(rcu_state.name, head,
+	if (__is_kvfree_rcu_offset((unsigned long)func))
+		trace_rcu_kvfree_callback(rcu_state.name, head,
 					 (unsigned long)func,
 					 rcu_segcblist_n_cbs(&rdp->cblist));
 	else
@@ -3146,7 +3146,7 @@ static void kfree_rcu_work(struct work_struct *work)
 					bkvhead[i]->records);
 			} else { // vmalloc() / vfree().
 				for (j = 0; j < bkvhead[i]->nr_records; j++) {
-					trace_rcu_invoke_kfree_callback(
+					trace_rcu_invoke_kvfree_callback(
 						rcu_state.name,
 						bkvhead[i]->records[j], 0);
 
@@ -3179,9 +3179,9 @@ static void kfree_rcu_work(struct work_struct *work)
 		next = head->next;
 		debug_rcu_head_unqueue((struct rcu_head *)ptr);
 		rcu_lock_acquire(&rcu_callback_map);
-		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
+		trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
 
-		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset)))
+		if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
 			kvfree(ptr);
 
 		rcu_lock_release(&rcu_callback_map);
@@ -3344,12 +3344,12 @@ kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
  * one, that is used only when the main path can not be maintained temporary,
  * due to memory pressure.
  *
- * Each kfree_call_rcu() request is added to a batch. The batch will be drained
+ * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
  * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
  * be free'd in workqueue context. This allows us to: batch requests together to
  * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
  */
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
@@ -3388,7 +3388,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
 }
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
 
 static unsigned long
 kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
-- 
cgit v1.2.3


From ce4dce123fdcb5f209752d13f9f06926be65fc78 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 25 May 2020 23:47:57 +0200
Subject: rcu: Introduce 2 arg kvfree_rcu() interface

kvmalloc() can allocate two types of objects: SLAB backed
and vmalloc backed. How it behaves depends on requested
object's size and memory pressure.

Add a kvfree_rcu() interface that can free memory allocated
via kvmalloc(). It is a simple alias to kfree_rcu() which
can now handle either type of object.

<snip>
    struct test_kvfree_rcu {
        struct rcu_head rcu;
        unsigned char array[100];
    };

    struct test_kvfree_rcu *p;

    p = kvmalloc(10 * PAGE_SIZE);
    if (p)
        kvfree_rcu(p, rcu);
<snip>

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index b344fc800a9b..51b26ab02878 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -875,6 +875,15 @@ do {									\
 		__kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
 } while (0)
 
+/**
+ * kvfree_rcu() - kvfree an object after a grace period.
+ * @ptr:	pointer to kvfree
+ * @rhf:	the name of the struct rcu_head within the type of @ptr.
+ *
+ * Same as kfree_rcu(), just simple alias.
+ */
+#define kvfree_rcu(ptr, rhf) kfree_rcu(ptr, rhf)
+
 /*
  * Place this after a lock-acquisition primitive to guarantee that
  * an UNLOCK+LOCK pair acts as a full barrier.  This guarantee applies
-- 
cgit v1.2.3


From 3042f83f19bec2e0cd356f72b39e4d816e8cd5ff Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 25 May 2020 23:47:58 +0200
Subject: rcu: Support reclaim for head-less object

Update the kvfree_call_rcu() function with head-less support.
This allows RCU to reclaim objects without an embedded rcu_head.

tree-RCU:
We introduce two chains of arrays to store SLAB-backed and vmalloc
pointers, each.  Storage in either of these arrays does not require
embedding an rcu_head within the object.

Maintaining the arrays may become impossible due to high memory
pressure. For such cases there is an emergency path. Objects with
rcu_head inside are just queued on a backup rcu_head list. Later on
that list is drained. As for the head-less variant, as the current
context can sleep, the following emergency measures are applied:
   a) Synchronously wait until a grace period has elapsed.
   b) Call kvfree().

tiny-RCU:
For double argument calls, there are no new changes in behavior. For
single argument call, kvfree() is directly inlined on the current
stack after a synchronize_rcu() call. Note that for tiny-RCU, any
call to synchronize_rcu() is actually a quiescent state, therefore
it does nothing.

Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcutiny.h | 18 +++++++++++++++++-
 kernel/rcu/tree.c       | 45 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index fb2eb39c484f..5cc9637cac16 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -34,9 +34,25 @@ static inline void synchronize_rcu_expedited(void)
 	synchronize_rcu();
 }
 
+/*
+ * Add one more declaration of kvfree() here. It is
+ * not so straight forward to just include <linux/mm.h>
+ * where it is defined due to getting many compile
+ * errors caused by that include.
+ */
+extern void kvfree(const void *addr);
+
 static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	call_rcu(head, func);
+	if (head) {
+		call_rcu(head, func);
+		return;
+	}
+
+	// kvfree_rcu(one_arg) call.
+	might_sleep();
+	synchronize_rcu();
+	kvfree((void *) func);
 }
 
 void rcu_qs(void);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f22c47e72287..01f29e4500ba 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3314,6 +3314,13 @@ kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 			if (IS_ENABLED(CONFIG_PREEMPT_RT))
 				return false;
 
+			/*
+			 * NOTE: For one argument of kvfree_rcu() we can
+			 * drop the lock and get the page in sleepable
+			 * context. That would allow to maintain an array
+			 * for the CONFIG_PREEMPT_RT as well if no cached
+			 * pages are available.
+			 */
 			bnode = (struct kvfree_rcu_bulk_data *)
 				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		}
@@ -3353,16 +3360,33 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
+	bool success;
 	void *ptr;
 
+	if (head) {
+		ptr = (void *) head - (unsigned long) func;
+	} else {
+		/*
+		 * Please note there is a limitation for the head-less
+		 * variant, that is why there is a clear rule for such
+		 * objects: it can be used from might_sleep() context
+		 * only. For other places please embed an rcu_head to
+		 * your data.
+		 */
+		might_sleep();
+		ptr = (unsigned long *) func;
+	}
+
 	krcp = krc_this_cpu_lock(&flags);
-	ptr = (void *)head - (unsigned long)func;
 
 	// Queue the object but don't yet schedule the batch.
 	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);
+
+		// Mark as success and leave.
+		success = true;
 		goto unlock_return;
 	}
 
@@ -3370,10 +3394,16 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	 * Under high memory pressure GFP_NOWAIT can fail,
 	 * in that case the emergency path is maintained.
 	 */
-	if (unlikely(!kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr))) {
+	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	if (!success) {
+		if (head == NULL)
+			// Inline if kvfree_rcu(one_arg) call.
+			goto unlock_return;
+
 		head->func = func;
 		head->next = krcp->head;
 		krcp->head = head;
+		success = true;
 	}
 
 	WRITE_ONCE(krcp->count, krcp->count + 1);
@@ -3387,6 +3417,17 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
+
+	/*
+	 * Inline kvfree() after synchronize_rcu(). We can do
+	 * it from might_sleep() context only, so the current
+	 * CPU can pass the QS state.
+	 */
+	if (!success) {
+		debug_rcu_head_unqueue((struct rcu_head *) ptr);
+		synchronize_rcu();
+		kvfree(ptr);
+	}
 }
 EXPORT_SYMBOL_GPL(kvfree_call_rcu);
 
-- 
cgit v1.2.3


From 1835f475e3518ade61e25a57572c78b953778656 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 25 May 2020 23:47:59 +0200
Subject: rcu: Introduce single argument kvfree_rcu() interface

Make kvfree_rcu() capable of freeing objects that will not
embed an rcu_head within it. This saves storage overhead in
such objects. Reclaiming headless objects this way requires
only a single argument (pointer to the object).

After this patch, there are two ways to use kvfree_rcu():

a) kvfree_rcu(ptr, rhf);
    struct X {
        struct rcu_head rhf;
        unsigned char data[100];
    };

    void *ptr = kvmalloc(sizeof(struct X), GFP_KERNEL);
    if (ptr)
        kvfree_rcu(ptr, rhf);

b) kvfree_rcu(ptr);
    void *ptr = kvmalloc(some_bytes, GFP_KERNEL);
    if (ptr)
        kvfree_rcu(ptr);

Note that the headless usage (example b) can only be used in a code
that can sleep. This is enforced by the CONFIG_DEBUG_ATOMIC_SLEEP
option.

Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 38 ++++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 51b26ab02878..d15d46db61f7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -877,12 +877,42 @@ do {									\
 
 /**
  * kvfree_rcu() - kvfree an object after a grace period.
- * @ptr:	pointer to kvfree
- * @rhf:	the name of the struct rcu_head within the type of @ptr.
  *
- * Same as kfree_rcu(), just simple alias.
+ * This macro consists of one or two arguments and it is
+ * based on whether an object is head-less or not. If it
+ * has a head then a semantic stays the same as it used
+ * to be before:
+ *
+ *     kvfree_rcu(ptr, rhf);
+ *
+ * where @ptr is a pointer to kvfree(), @rhf is the name
+ * of the rcu_head structure within the type of @ptr.
+ *
+ * When it comes to head-less variant, only one argument
+ * is passed and that is just a pointer which has to be
+ * freed after a grace period. Therefore the semantic is
+ *
+ *     kvfree_rcu(ptr);
+ *
+ * where @ptr is a pointer to kvfree().
+ *
+ * Please note, head-less way of freeing is permitted to
+ * use from a context that has to follow might_sleep()
+ * annotation. Otherwise, please switch and embed the
+ * rcu_head structure within the type of @ptr.
  */
-#define kvfree_rcu(ptr, rhf) kfree_rcu(ptr, rhf)
+#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__,		\
+	kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__)
+
+#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME
+#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf)
+#define kvfree_rcu_arg_1(ptr)					\
+do {								\
+	typeof(ptr) ___p = (ptr);				\
+								\
+	if (___p)						\
+		kvfree_call_rcu(NULL, (rcu_callback_t) (___p));	\
+} while (0)
 
 /*
  * Place this after a lock-acquisition primitive to guarantee that
-- 
cgit v1.2.3


From c7dcf8106f7570b133b05ff68fd4100064965d9d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 12 Jun 2020 13:11:29 -0700
Subject: rcu-tasks: Fix synchronize_rcu_tasks_trace() header comment

The synchronize_rcu_tasks_trace() header comment incorrectly claims that
any number of things delimit RCU Tasks Trace read-side critical sections,
when in fact only rcu_read_lock_trace() and rcu_read_unlock_trace() do so.
This commit therefore fixes this comment, and, while in the area, fixes
a typo in the rcu_read_lock_trace() header comment.

Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate_trace.h | 4 ++--
 kernel/rcu/tasks.h             | 9 ++++-----
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 4c25a41f8b27..d9015aac78c6 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -36,8 +36,8 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting);
 /**
  * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
  *
- * When synchronize_rcu_trace() is invoked by one task, then that task
- * is guaranteed to block until all other tasks exit their read-side
+ * When synchronize_rcu_tasks_trace() is invoked by one task, then that
+ * task is guaranteed to block until all other tasks exit their read-side
  * critical sections.  Similarly, if call_rcu_trace() is invoked on one
  * task while other tasks are within RCU read-side critical sections,
  * invocation of the corresponding RCU callback is deferred until after
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index ce23f6cc5043..a77298c1d126 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1118,11 +1118,10 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
  * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
  *
  * Control will return to the caller some time after a trace rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed.  These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
- * anyway) cond_resched().
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-tasks read-side critical sections have elapsed.  These read-side
+ * critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
  *
  * This is a very specialized primitive, intended only for a few uses in
  * tracing and other situations requiring manipulation of function preambles
-- 
cgit v1.2.3


From 4a5f133c15b77c4018e8d7996541868ac94afb4f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 24 Apr 2020 11:21:40 -0700
Subject: rcutorture: Add races with task-exit processing

Several variants of Linux-kernel RCU interact with task-exit processing,
including preemptible RCU, Tasks RCU, and Tasks Trace RCU.  This commit
therefore adds testing of this interaction to rcutorture by adding
rcutorture.read_exit_burst and rcutorture.read_exit_delay kernel-boot
parameters.  These kernel parameters control the frequency and spacing
of special read-then-exit kthreads that are spawned.

[ paulmck: Apply feedback from Dan Carpenter's static checker. ]
[ paulmck: Reduce latency to avoid false-positive shutdown hangs. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  14 +++
 include/linux/torture.h                         |   5 ++
 kernel/rcu/rcutorture.c                         | 112 +++++++++++++++++++++++-
 3 files changed, 128 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb95fad81c79..a0dcc925c8a2 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4258,6 +4258,20 @@
 			Set time (jiffies) between CPU-hotplug operations,
 			or zero to disable CPU-hotplug testing.
 
+	rcutorture.read_exit= [KNL]
+			Set the number of read-then-exit kthreads used
+			to test the interaction of RCU updaters and
+			task-exit processing.
+
+	rcutorture.read_exit_burst= [KNL]
+			The number of times in a given read-then-exit
+			episode that a set of read-then-exit kthreads
+			is spawned.
+
+	rcutorture.read_exit_delay= [KNL]
+			The delay, in seconds, between successive
+			read-then-exit testing episodes.
+
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
 			allows some CPUs to go into dyntick-idle mode
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 629b66e6c161..7f65bd1dd307 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -55,6 +55,11 @@ struct torture_random_state {
 #define DEFINE_TORTURE_RANDOM_PERCPU(name) \
 	DEFINE_PER_CPU(struct torture_random_state, name)
 unsigned long torture_random(struct torture_random_state *trsp);
+static inline void torture_random_init(struct torture_random_state *trsp)
+{
+	trsp->trs_state = 0;
+	trsp->trs_count = 0;
+}
 
 /* Task shuffler, which causes CPUs to occasionally go idle. */
 void torture_shuffle_task_register(struct task_struct *tp);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index efb792e13fca..2621a339c8a4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -109,6 +109,10 @@ torture_param(int, object_debug, 0,
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
 	     "Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(int, read_exit_delay, 13,
+	      "Delay between read-then-exit episodes (s)");
+torture_param(int, read_exit_burst, 16,
+	      "# of read-then-exit bursts per episode, zero to disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -146,6 +150,7 @@ static struct task_struct *stall_task;
 static struct task_struct *fwd_prog_task;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
+static struct task_struct *read_exit_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -177,6 +182,7 @@ static long n_rcu_torture_boosts;
 static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
 static long n_barrier_successes; /* did rcu_barrier test succeed? */
+static unsigned long n_read_exits;
 static struct list_head rcu_torture_removed;
 static unsigned long shutdown_jiffies;
 
@@ -1539,10 +1545,11 @@ rcu_torture_stats_print(void)
 		n_rcu_torture_boosts,
 		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
-	pr_cont("barrier: %ld/%ld:%ld\n",
+	pr_cont("barrier: %ld/%ld:%ld ",
 		data_race(n_barrier_successes),
 		data_race(n_barrier_attempts),
 		data_race(n_rcu_torture_barrier_error));
+	pr_cont("read-exits: %ld\n", data_race(n_read_exits));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -1634,7 +1641,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
 		 "stall_cpu_block=%d "
 		 "n_barrier_cbs=%d "
-		 "onoff_interval=%d onoff_holdoff=%d\n",
+		 "onoff_interval=%d onoff_holdoff=%d "
+		 "read_exit_delay=%d read_exit_burst=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
@@ -1643,7 +1651,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
 		 stall_cpu_block,
 		 n_barrier_cbs,
-		 onoff_interval, onoff_holdoff);
+		 onoff_interval, onoff_holdoff,
+		 read_exit_delay, read_exit_burst);
 }
 
 static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -2338,6 +2347,99 @@ static bool rcu_torture_can_boost(void)
 	return true;
 }
 
+static bool read_exit_child_stop;
+static bool read_exit_child_stopped;
+static wait_queue_head_t read_exit_wq;
+
+// Child kthread which just does an rcutorture reader and exits.
+static int rcu_torture_read_exit_child(void *trsp_in)
+{
+	struct torture_random_state *trsp = trsp_in;
+
+	set_user_nice(current, MAX_NICE);
+	// Minimize time between reading and exiting.
+	while (!kthread_should_stop())
+		schedule_timeout_uninterruptible(1);
+	(void)rcu_torture_one_read(trsp);
+	return 0;
+}
+
+// Parent kthread which creates and destroys read-exit child kthreads.
+static int rcu_torture_read_exit(void *unused)
+{
+	int count = 0;
+	bool errexit = false;
+	int i;
+	struct task_struct *tsp;
+	DEFINE_TORTURE_RANDOM(trs);
+
+	// Allocate and initialize.
+	set_user_nice(current, MAX_NICE);
+	VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test");
+
+	// Each pass through this loop does one read-exit episode.
+	do {
+		if (++count > read_exit_burst) {
+			VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
+			rcu_barrier(); // Wait for task_struct free, avoid OOM.
+			for (i = 0; i < read_exit_delay; i++) {
+				schedule_timeout_uninterruptible(HZ);
+				if (READ_ONCE(read_exit_child_stop))
+					break;
+			}
+			if (!READ_ONCE(read_exit_child_stop))
+				VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
+			count = 0;
+		}
+		if (READ_ONCE(read_exit_child_stop))
+			break;
+		// Spawn child.
+		tsp = kthread_run(rcu_torture_read_exit_child,
+				     &trs, "%s",
+				     "rcu_torture_read_exit_child");
+		if (IS_ERR(tsp)) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			errexit = true;
+			tsp = NULL;
+			break;
+		}
+		cond_resched();
+		kthread_stop(tsp);
+		n_read_exits ++;
+		stutter_wait("rcu_torture_read_exit");
+	} while (!errexit && !READ_ONCE(read_exit_child_stop));
+
+	// Clean up and exit.
+	smp_store_release(&read_exit_child_stopped, true); // After reaping.
+	smp_mb(); // Store before wakeup.
+	wake_up(&read_exit_wq);
+	while (!torture_must_stop())
+		schedule_timeout_uninterruptible(1);
+	torture_kthread_stopping("rcu_torture_read_exit");
+	return 0;
+}
+
+static int rcu_torture_read_exit_init(void)
+{
+	if (read_exit_burst <= 0)
+		return -EINVAL;
+	init_waitqueue_head(&read_exit_wq);
+	read_exit_child_stop = false;
+	read_exit_child_stopped = false;
+	return torture_create_kthread(rcu_torture_read_exit, NULL,
+				      read_exit_task);
+}
+
+static void rcu_torture_read_exit_cleanup(void)
+{
+	if (!read_exit_task)
+		return;
+	WRITE_ONCE(read_exit_child_stop, true);
+	smp_mb(); // Above write before wait.
+	wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped));
+	torture_stop_kthread(rcutorture_read_exit, read_exit_task);
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -2359,6 +2461,7 @@ rcu_torture_cleanup(void)
 	}
 
 	show_rcu_gp_kthreads();
+	rcu_torture_read_exit_cleanup();
 	rcu_torture_barrier_cleanup();
 	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
 	torture_stop_kthread(rcu_torture_stall, stall_task);
@@ -2680,6 +2783,9 @@ rcu_torture_init(void)
 	if (firsterr)
 		goto unwind;
 	firsterr = rcu_torture_barrier_init();
+	if (firsterr)
+		goto unwind;
+	firsterr = rcu_torture_read_exit_init();
 	if (firsterr)
 		goto unwind;
 	if (object_debug)
-- 
cgit v1.2.3


From c93773c1a3fedf6c3f6fa12833e2b74a9897c3e3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 12 Feb 2020 13:29:15 -0800
Subject: rculist: Add ASSERT_EXCLUSIVE_ACCESS() to __list_splice_init_rcu()

After the sync() in __list_splice_init_rcu(), there should be no
readers traversing the old list.  This commit therefore enlists the
help of KCSAN to verify this condition via a pair of calls to
ASSERT_EXCLUSIVE_ACCESS().

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Marco Elver <elver@google.com>
---
 include/linux/rculist.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index df587d181844..2ebd112f86f7 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -248,6 +248,8 @@ static inline void __list_splice_init_rcu(struct list_head *list,
 	 */
 
 	sync();
+	ASSERT_EXCLUSIVE_ACCESS(*first);
+	ASSERT_EXCLUSIVE_ACCESS(*last);
 
 	/*
 	 * Readers are finished with the source list, so perform splice.
-- 
cgit v1.2.3


From 0fb8125635e8eb5483fb095f98dcf0651206a7b8 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 9 Jun 2020 22:04:44 +0200
Subject: video: fbdev: amba-clcd: Retire elder CLCD driver

All the functionality in this driver has been reimplemented
in the new DRM driver in drivers/gpu/drm/pl111/* and all
the boards using it have been migrated to use the DRM driver
with all configuration coming from the device tree.

I started the work to migrate the CLCD driver to DRM in
april 2017 and it took a little more than 3 years to do this
properly without leaving any platforms behind.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Russell King <linux@armlinux.org.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200609200446.153209-2-linus.walleij@linaro.org
---
 MAINTAINERS                     |   5 -
 drivers/video/fbdev/Kconfig     |  20 -
 drivers/video/fbdev/Makefile    |   1 -
 drivers/video/fbdev/amba-clcd.c | 986 ----------------------------------------
 include/linux/amba/clcd.h       | 290 ------------
 5 files changed, 1302 deletions(-)
 delete mode 100644 drivers/video/fbdev/amba-clcd.c
 delete mode 100644 include/linux/amba/clcd.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index dad5a62d21a7..40474982a21d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1448,11 +1448,6 @@ S:	Odd Fixes
 F:	drivers/amba/
 F:	include/linux/amba/bus.h
 
-ARM PRIMECELL CLCD PL110 DRIVER
-M:	Russell King <linux@armlinux.org.uk>
-S:	Odd Fixes
-F:	drivers/video/fbdev/amba-clcd.*
-
 ARM PRIMECELL KMI PL050 DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Odd Fixes
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index 0f559aeaf469..b33bb6318c2b 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -272,26 +272,6 @@ config FB_PM2_FIFO_DISCONNECT
 	help
 	  Support the Permedia2 FIFO disconnect feature.
 
-config FB_ARMCLCD
-	tristate "ARM PrimeCell PL110 support"
-	depends on ARM || ARM64 || COMPILE_TEST
-	depends on FB && ARM_AMBA && HAS_IOMEM
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
-	select FB_MODE_HELPERS if OF
-	select VIDEOMODE_HELPERS if OF
-	select BACKLIGHT_CLASS_DEVICE if OF
-	help
-	  This framebuffer device driver is for the ARM PrimeCell PL110
-	  Colour LCD controller.  ARM PrimeCells provide the building
-	  blocks for System on a Chip devices.
-
-	  If you want to compile this as a module (=code which can be
-	  inserted into and removed from the running kernel), say M
-	  here and read <file:Documentation/kbuild/modules.rst>.  The module
-	  will be called amba-clcd.
-
 config FB_ACORN
 	bool "Acorn VIDC support"
 	depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index aa6352798cf4..76a43ec8f24c 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -75,7 +75,6 @@ obj-$(CONFIG_FB_HIT)              += hitfb.o
 obj-$(CONFIG_FB_ATMEL)		  += atmel_lcdfb.o
 obj-$(CONFIG_FB_PVR2)             += pvr2fb.o
 obj-$(CONFIG_FB_VOODOO1)          += sstfb.o
-obj-$(CONFIG_FB_ARMCLCD)	  += amba-clcd.o
 obj-$(CONFIG_FB_GOLDFISH)         += goldfishfb.o
 obj-$(CONFIG_FB_68328)            += 68328fb.o
 obj-$(CONFIG_FB_GBE)              += gbefb.o
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
deleted file mode 100644
index b7682de412d8..000000000000
--- a/drivers/video/fbdev/amba-clcd.c
+++ /dev/null
@@ -1,986 +0,0 @@
-/*
- *  linux/drivers/video/amba-clcd.c
- *
- * Copyright (C) 2001 ARM Limited, by David A Rusling
- * Updated to 2.5, Deep Blue Solutions Ltd.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- *
- *  ARM PrimeCell PL110 Color LCD Controller
- */
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-#include <linux/backlight.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/ioport.h>
-#include <linux/list.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_graph.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <video/display_timing.h>
-#include <video/of_display_timing.h>
-#include <video/videomode.h>
-
-#define to_clcd(info)	container_of(info, struct clcd_fb, fb)
-
-/* This is limited to 16 characters when displayed by X startup */
-static const char *clcd_name = "CLCD FB";
-
-/*
- * Unfortunately, the enable/disable functions may be called either from
- * process or IRQ context, and we _need_ to delay.  This is _not_ good.
- */
-static inline void clcdfb_sleep(unsigned int ms)
-{
-	if (in_atomic()) {
-		mdelay(ms);
-	} else {
-		msleep(ms);
-	}
-}
-
-static inline void clcdfb_set_start(struct clcd_fb *fb)
-{
-	unsigned long ustart = fb->fb.fix.smem_start;
-	unsigned long lstart;
-
-	ustart += fb->fb.var.yoffset * fb->fb.fix.line_length;
-	lstart = ustart + fb->fb.var.yres * fb->fb.fix.line_length / 2;
-
-	writel(ustart, fb->regs + CLCD_UBAS);
-	writel(lstart, fb->regs + CLCD_LBAS);
-}
-
-static void clcdfb_disable(struct clcd_fb *fb)
-{
-	u32 val;
-
-	if (fb->board->disable)
-		fb->board->disable(fb);
-
-	if (fb->panel->backlight) {
-		fb->panel->backlight->props.power = FB_BLANK_POWERDOWN;
-		backlight_update_status(fb->panel->backlight);
-	}
-
-	val = readl(fb->regs + fb->off_cntl);
-	if (val & CNTL_LCDPWR) {
-		val &= ~CNTL_LCDPWR;
-		writel(val, fb->regs + fb->off_cntl);
-
-		clcdfb_sleep(20);
-	}
-	if (val & CNTL_LCDEN) {
-		val &= ~CNTL_LCDEN;
-		writel(val, fb->regs + fb->off_cntl);
-	}
-
-	/*
-	 * Disable CLCD clock source.
-	 */
-	if (fb->clk_enabled) {
-		fb->clk_enabled = false;
-		clk_disable(fb->clk);
-	}
-}
-
-static void clcdfb_enable(struct clcd_fb *fb, u32 cntl)
-{
-	/*
-	 * Enable the CLCD clock source.
-	 */
-	if (!fb->clk_enabled) {
-		fb->clk_enabled = true;
-		clk_enable(fb->clk);
-	}
-
-	/*
-	 * Bring up by first enabling..
-	 */
-	cntl |= CNTL_LCDEN;
-	writel(cntl, fb->regs + fb->off_cntl);
-
-	clcdfb_sleep(20);
-
-	/*
-	 * and now apply power.
-	 */
-	cntl |= CNTL_LCDPWR;
-	writel(cntl, fb->regs + fb->off_cntl);
-
-	/*
-	 * Turn on backlight
-	 */
-	if (fb->panel->backlight) {
-		fb->panel->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(fb->panel->backlight);
-	}
-
-	/*
-	 * finally, enable the interface.
-	 */
-	if (fb->board->enable)
-		fb->board->enable(fb);
-}
-
-static int
-clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
-	u32 caps;
-	int ret = 0;
-
-	if (fb->panel->caps && fb->board->caps)
-		caps = fb->panel->caps & fb->board->caps;
-	else {
-		/* Old way of specifying what can be used */
-		caps = fb->panel->cntl & CNTL_BGR ?
-			CLCD_CAP_BGR : CLCD_CAP_RGB;
-		/* But mask out 444 modes as they weren't supported */
-		caps &= ~CLCD_CAP_444;
-	}
-
-	/* Only TFT panels can do RGB888/BGR888 */
-	if (!(fb->panel->cntl & CNTL_LCDTFT))
-		caps &= ~CLCD_CAP_888;
-
-	memset(&var->transp, 0, sizeof(var->transp));
-
-	var->red.msb_right = 0;
-	var->green.msb_right = 0;
-	var->blue.msb_right = 0;
-
-	switch (var->bits_per_pixel) {
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		/* If we can't do 5551, reject */
-		caps &= CLCD_CAP_5551;
-		if (!caps) {
-			ret = -EINVAL;
-			break;
-		}
-
-		var->red.length		= var->bits_per_pixel;
-		var->red.offset		= 0;
-		var->green.length	= var->bits_per_pixel;
-		var->green.offset	= 0;
-		var->blue.length	= var->bits_per_pixel;
-		var->blue.offset	= 0;
-		break;
-
-	case 16:
-		/* If we can't do 444, 5551 or 565, reject */
-		if (!(caps & (CLCD_CAP_444 | CLCD_CAP_5551 | CLCD_CAP_565))) {
-			ret = -EINVAL;
-			break;
-		}
-
-		/*
-		 * Green length can be 4, 5 or 6 depending whether
-		 * we're operating in 444, 5551 or 565 mode.
-		 */
-		if (var->green.length == 4 && caps & CLCD_CAP_444)
-			caps &= CLCD_CAP_444;
-		if (var->green.length == 5 && caps & CLCD_CAP_5551)
-			caps &= CLCD_CAP_5551;
-		else if (var->green.length == 6 && caps & CLCD_CAP_565)
-			caps &= CLCD_CAP_565;
-		else {
-			/*
-			 * PL110 officially only supports RGB555,
-			 * but may be wired up to allow RGB565.
-			 */
-			if (caps & CLCD_CAP_565) {
-				var->green.length = 6;
-				caps &= CLCD_CAP_565;
-			} else if (caps & CLCD_CAP_5551) {
-				var->green.length = 5;
-				caps &= CLCD_CAP_5551;
-			} else {
-				var->green.length = 4;
-				caps &= CLCD_CAP_444;
-			}
-		}
-
-		if (var->green.length >= 5) {
-			var->red.length = 5;
-			var->blue.length = 5;
-		} else {
-			var->red.length = 4;
-			var->blue.length = 4;
-		}
-		break;
-	case 32:
-		/* If we can't do 888, reject */
-		caps &= CLCD_CAP_888;
-		if (!caps) {
-			ret = -EINVAL;
-			break;
-		}
-
-		var->red.length = 8;
-		var->green.length = 8;
-		var->blue.length = 8;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	/*
-	 * >= 16bpp displays have separate colour component bitfields
-	 * encoded in the pixel data.  Calculate their position from
-	 * the bitfield length defined above.
-	 */
-	if (ret == 0 && var->bits_per_pixel >= 16) {
-		bool bgr, rgb;
-
-		bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0;
-		rgb = caps & CLCD_CAP_RGB && var->red.offset == 0;
-
-		if (!bgr && !rgb)
-			/*
-			 * The requested format was not possible, try just
-			 * our capabilities.  One of BGR or RGB must be
-			 * supported.
-			 */
-			bgr = caps & CLCD_CAP_BGR;
-
-		if (bgr) {
-			var->blue.offset = 0;
-			var->green.offset = var->blue.offset + var->blue.length;
-			var->red.offset = var->green.offset + var->green.length;
-		} else {
-			var->red.offset = 0;
-			var->green.offset = var->red.offset + var->red.length;
-			var->blue.offset = var->green.offset + var->green.length;
-		}
-	}
-
-	return ret;
-}
-
-static int clcdfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	int ret = -EINVAL;
-
-	if (fb->board->check)
-		ret = fb->board->check(fb, var);
-
-	if (ret == 0 &&
-	    var->xres_virtual * var->bits_per_pixel / 8 *
-	    var->yres_virtual > fb->fb.fix.smem_len)
-		ret = -EINVAL;
-
-	if (ret == 0)
-		ret = clcdfb_set_bitfields(fb, var);
-
-	return ret;
-}
-
-static int clcdfb_set_par(struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	struct clcd_regs regs;
-
-	fb->fb.fix.line_length = fb->fb.var.xres_virtual *
-				 fb->fb.var.bits_per_pixel / 8;
-
-	if (fb->fb.var.bits_per_pixel <= 8)
-		fb->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
-	else
-		fb->fb.fix.visual = FB_VISUAL_TRUECOLOR;
-
-	fb->board->decode(fb, &regs);
-
-	clcdfb_disable(fb);
-
-	writel(regs.tim0, fb->regs + CLCD_TIM0);
-	writel(regs.tim1, fb->regs + CLCD_TIM1);
-	writel(regs.tim2, fb->regs + CLCD_TIM2);
-	writel(regs.tim3, fb->regs + CLCD_TIM3);
-
-	clcdfb_set_start(fb);
-
-	clk_set_rate(fb->clk, (1000000000 / regs.pixclock) * 1000);
-
-	fb->clcd_cntl = regs.cntl;
-
-	clcdfb_enable(fb, regs.cntl);
-
-#ifdef DEBUG
-	printk(KERN_INFO
-	       "CLCD: Registers set to\n"
-	       "  %08x %08x %08x %08x\n"
-	       "  %08x %08x %08x %08x\n",
-		readl(fb->regs + CLCD_TIM0), readl(fb->regs + CLCD_TIM1),
-		readl(fb->regs + CLCD_TIM2), readl(fb->regs + CLCD_TIM3),
-		readl(fb->regs + CLCD_UBAS), readl(fb->regs + CLCD_LBAS),
-		readl(fb->regs + fb->off_ienb), readl(fb->regs + fb->off_cntl));
-#endif
-
-	return 0;
-}
-
-static inline u32 convert_bitfield(int val, struct fb_bitfield *bf)
-{
-	unsigned int mask = (1 << bf->length) - 1;
-
-	return (val >> (16 - bf->length) & mask) << bf->offset;
-}
-
-/*
- *  Set a single color register. The values supplied have a 16 bit
- *  magnitude.  Return != 0 for invalid regno.
- */
-static int
-clcdfb_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
-		 unsigned int blue, unsigned int transp, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-
-	if (regno < 16)
-		fb->cmap[regno] = convert_bitfield(transp, &fb->fb.var.transp) |
-				  convert_bitfield(blue, &fb->fb.var.blue) |
-				  convert_bitfield(green, &fb->fb.var.green) |
-				  convert_bitfield(red, &fb->fb.var.red);
-
-	if (fb->fb.fix.visual == FB_VISUAL_PSEUDOCOLOR && regno < 256) {
-		int hw_reg = CLCD_PALETTE + ((regno * 2) & ~3);
-		u32 val, mask, newval;
-
-		newval  = (red >> 11)  & 0x001f;
-		newval |= (green >> 6) & 0x03e0;
-		newval |= (blue >> 1)  & 0x7c00;
-
-		/*
-		 * 3.2.11: if we're configured for big endian
-		 * byte order, the palette entries are swapped.
-		 */
-		if (fb->clcd_cntl & CNTL_BEBO)
-			regno ^= 1;
-
-		if (regno & 1) {
-			newval <<= 16;
-			mask = 0x0000ffff;
-		} else {
-			mask = 0xffff0000;
-		}
-
-		val = readl(fb->regs + hw_reg) & mask;
-		writel(val | newval, fb->regs + hw_reg);
-	}
-
-	return regno > 255;
-}
-
-/*
- *  Blank the screen if blank_mode != 0, else unblank. If blank == NULL
- *  then the caller blanks by setting the CLUT (Color Look Up Table) to all
- *  black. Return 0 if blanking succeeded, != 0 if un-/blanking failed due
- *  to e.g. a video mode which doesn't support it. Implements VESA suspend
- *  and powerdown modes on hardware that supports disabling hsync/vsync:
- *    blank_mode == 2: suspend vsync
- *    blank_mode == 3: suspend hsync
- *    blank_mode == 4: powerdown
- */
-static int clcdfb_blank(int blank_mode, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-
-	if (blank_mode != 0) {
-		clcdfb_disable(fb);
-	} else {
-		clcdfb_enable(fb, fb->clcd_cntl);
-	}
-	return 0;
-}
-
-static int clcdfb_mmap(struct fb_info *info,
-		       struct vm_area_struct *vma)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	unsigned long len, off = vma->vm_pgoff << PAGE_SHIFT;
-	int ret = -EINVAL;
-
-	len = info->fix.smem_len;
-
-	if (off <= len && vma->vm_end - vma->vm_start <= len - off &&
-	    fb->board->mmap)
-		ret = fb->board->mmap(fb, vma);
-
-	return ret;
-}
-
-static const struct fb_ops clcdfb_ops = {
-	.owner		= THIS_MODULE,
-	.fb_check_var	= clcdfb_check_var,
-	.fb_set_par	= clcdfb_set_par,
-	.fb_setcolreg	= clcdfb_setcolreg,
-	.fb_blank	= clcdfb_blank,
-	.fb_fillrect	= cfb_fillrect,
-	.fb_copyarea	= cfb_copyarea,
-	.fb_imageblit	= cfb_imageblit,
-	.fb_mmap	= clcdfb_mmap,
-};
-
-static int clcdfb_register(struct clcd_fb *fb)
-{
-	int ret;
-
-	/*
-	 * ARM PL111 always has IENB at 0x1c; it's only PL110
-	 * which is reversed on some platforms.
-	 */
-	if (amba_manf(fb->dev) == 0x41 && amba_part(fb->dev) == 0x111) {
-		fb->off_ienb = CLCD_PL111_IENB;
-		fb->off_cntl = CLCD_PL111_CNTL;
-	} else {
-		fb->off_ienb = CLCD_PL110_IENB;
-		fb->off_cntl = CLCD_PL110_CNTL;
-	}
-
-	fb->clk = clk_get(&fb->dev->dev, NULL);
-	if (IS_ERR(fb->clk)) {
-		ret = PTR_ERR(fb->clk);
-		goto out;
-	}
-
-	ret = clk_prepare(fb->clk);
-	if (ret)
-		goto free_clk;
-
-	fb->fb.device		= &fb->dev->dev;
-
-	fb->fb.fix.mmio_start	= fb->dev->res.start;
-	fb->fb.fix.mmio_len	= resource_size(&fb->dev->res);
-
-	fb->regs = ioremap(fb->fb.fix.mmio_start, fb->fb.fix.mmio_len);
-	if (!fb->regs) {
-		printk(KERN_ERR "CLCD: unable to remap registers\n");
-		ret = -ENOMEM;
-		goto clk_unprep;
-	}
-
-	fb->fb.fbops		= &clcdfb_ops;
-	fb->fb.flags		= FBINFO_FLAG_DEFAULT;
-	fb->fb.pseudo_palette	= fb->cmap;
-
-	strncpy(fb->fb.fix.id, clcd_name, sizeof(fb->fb.fix.id));
-	fb->fb.fix.type		= FB_TYPE_PACKED_PIXELS;
-	fb->fb.fix.type_aux	= 0;
-	fb->fb.fix.xpanstep	= 0;
-	fb->fb.fix.ypanstep	= 0;
-	fb->fb.fix.ywrapstep	= 0;
-	fb->fb.fix.accel	= FB_ACCEL_NONE;
-
-	fb->fb.var.xres		= fb->panel->mode.xres;
-	fb->fb.var.yres		= fb->panel->mode.yres;
-	fb->fb.var.xres_virtual	= fb->panel->mode.xres;
-	fb->fb.var.yres_virtual	= fb->panel->mode.yres;
-	fb->fb.var.bits_per_pixel = fb->panel->bpp;
-	fb->fb.var.grayscale	= fb->panel->grayscale;
-	fb->fb.var.pixclock	= fb->panel->mode.pixclock;
-	fb->fb.var.left_margin	= fb->panel->mode.left_margin;
-	fb->fb.var.right_margin	= fb->panel->mode.right_margin;
-	fb->fb.var.upper_margin	= fb->panel->mode.upper_margin;
-	fb->fb.var.lower_margin	= fb->panel->mode.lower_margin;
-	fb->fb.var.hsync_len	= fb->panel->mode.hsync_len;
-	fb->fb.var.vsync_len	= fb->panel->mode.vsync_len;
-	fb->fb.var.sync		= fb->panel->mode.sync;
-	fb->fb.var.vmode	= fb->panel->mode.vmode;
-	fb->fb.var.activate	= FB_ACTIVATE_NOW;
-	fb->fb.var.nonstd	= 0;
-	fb->fb.var.height	= fb->panel->height;
-	fb->fb.var.width	= fb->panel->width;
-	fb->fb.var.accel_flags	= 0;
-
-	fb->fb.monspecs.hfmin	= 0;
-	fb->fb.monspecs.hfmax   = 100000;
-	fb->fb.monspecs.vfmin	= 0;
-	fb->fb.monspecs.vfmax	= 400;
-	fb->fb.monspecs.dclkmin = 1000000;
-	fb->fb.monspecs.dclkmax	= 100000000;
-
-	/*
-	 * Make sure that the bitfields are set appropriately.
-	 */
-	clcdfb_set_bitfields(fb, &fb->fb.var);
-
-	/*
-	 * Allocate colourmap.
-	 */
-	ret = fb_alloc_cmap(&fb->fb.cmap, 256, 0);
-	if (ret)
-		goto unmap;
-
-	/*
-	 * Ensure interrupts are disabled.
-	 */
-	writel(0, fb->regs + fb->off_ienb);
-
-	fb_set_var(&fb->fb, &fb->fb.var);
-
-	dev_info(&fb->dev->dev, "%s hardware, %s display\n",
-	         fb->board->name, fb->panel->mode.name);
-
-	ret = register_framebuffer(&fb->fb);
-	if (ret == 0)
-		goto out;
-
-	printk(KERN_ERR "CLCD: cannot register framebuffer (%d)\n", ret);
-
-	fb_dealloc_cmap(&fb->fb.cmap);
- unmap:
-	iounmap(fb->regs);
- clk_unprep:
-	clk_unprepare(fb->clk);
- free_clk:
-	clk_put(fb->clk);
- out:
-	return ret;
-}
-
-#ifdef CONFIG_OF
-static int clcdfb_of_get_dpi_panel_mode(struct device_node *node,
-		struct clcd_panel *clcd_panel)
-{
-	int err;
-	struct display_timing timing;
-	struct videomode video;
-
-	err = of_get_display_timing(node, "panel-timing", &timing);
-	if (err) {
-		pr_err("%pOF: problems parsing panel-timing (%d)\n", node, err);
-		return err;
-	}
-
-	videomode_from_timing(&timing, &video);
-
-	err = fb_videomode_from_videomode(&video, &clcd_panel->mode);
-	if (err)
-		return err;
-
-	/* Set up some inversion flags */
-	if (timing.flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
-		clcd_panel->tim2 |= TIM2_IPC;
-	else if (!(timing.flags & DISPLAY_FLAGS_PIXDATA_POSEDGE))
-		/*
-		 * To preserve backwards compatibility, the IPC (inverted
-		 * pixel clock) flag needs to be set on any display that
-		 * doesn't explicitly specify that the pixel clock is
-		 * active on the negative or positive edge.
-		 */
-		clcd_panel->tim2 |= TIM2_IPC;
-
-	if (timing.flags & DISPLAY_FLAGS_HSYNC_LOW)
-		clcd_panel->tim2 |= TIM2_IHS;
-
-	if (timing.flags & DISPLAY_FLAGS_VSYNC_LOW)
-		clcd_panel->tim2 |= TIM2_IVS;
-
-	if (timing.flags & DISPLAY_FLAGS_DE_LOW)
-		clcd_panel->tim2 |= TIM2_IOE;
-
-	return 0;
-}
-
-static int clcdfb_snprintf_mode(char *buf, int size, struct fb_videomode *mode)
-{
-	return snprintf(buf, size, "%ux%u@%u", mode->xres, mode->yres,
-			mode->refresh);
-}
-
-static int clcdfb_of_get_backlight(struct device *dev,
-				   struct clcd_panel *clcd_panel)
-{
-	struct backlight_device *backlight;
-
-	/* Look up the optional backlight device */
-	backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(backlight))
-		return PTR_ERR(backlight);
-
-	clcd_panel->backlight = backlight;
-	return 0;
-}
-
-static int clcdfb_of_get_mode(struct device *dev, struct device_node *panel,
-			      struct clcd_panel *clcd_panel)
-{
-	int err;
-	struct fb_videomode *mode;
-	char *name;
-	int len;
-
-	/* Only directly connected DPI panels supported for now */
-	if (of_device_is_compatible(panel, "panel-dpi"))
-		err = clcdfb_of_get_dpi_panel_mode(panel, clcd_panel);
-	else
-		err = -ENOENT;
-	if (err)
-		return err;
-	mode = &clcd_panel->mode;
-
-	len = clcdfb_snprintf_mode(NULL, 0, mode);
-	name = devm_kzalloc(dev, len + 1, GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	clcdfb_snprintf_mode(name, len + 1, mode);
-	mode->name = name;
-
-	return 0;
-}
-
-static int clcdfb_of_init_tft_panel(struct clcd_fb *fb, u32 r0, u32 g0, u32 b0)
-{
-	static struct {
-		unsigned int part;
-		u32 r0, g0, b0;
-		u32 caps;
-	} panels[] = {
-		{ 0x110, 1,  7, 13, CLCD_CAP_5551 },
-		{ 0x110, 0,  8, 16, CLCD_CAP_888 },
-		{ 0x110, 16, 8, 0,  CLCD_CAP_888 },
-		{ 0x111, 4, 14, 20, CLCD_CAP_444 },
-		{ 0x111, 3, 11, 19, CLCD_CAP_444 | CLCD_CAP_5551 },
-		{ 0x111, 3, 10, 19, CLCD_CAP_444 | CLCD_CAP_5551 |
-				    CLCD_CAP_565 },
-		{ 0x111, 0,  8, 16, CLCD_CAP_444 | CLCD_CAP_5551 |
-				    CLCD_CAP_565 | CLCD_CAP_888 },
-	};
-	int i;
-
-	/* Bypass pixel clock divider */
-	fb->panel->tim2 |= TIM2_BCD;
-
-	/* TFT display, vert. comp. interrupt at the start of the back porch */
-	fb->panel->cntl |= CNTL_LCDTFT | CNTL_LCDVCOMP(1);
-
-	fb->panel->caps = 0;
-
-	/* Match the setup with known variants */
-	for (i = 0; i < ARRAY_SIZE(panels) && !fb->panel->caps; i++) {
-		if (amba_part(fb->dev) != panels[i].part)
-			continue;
-		if (g0 != panels[i].g0)
-			continue;
-		if (r0 == panels[i].r0 && b0 == panels[i].b0)
-			fb->panel->caps = panels[i].caps;
-	}
-
-	/*
-	 * If we actually physically connected the R lines to B and
-	 * vice versa
-	 */
-	if (r0 != 0 && b0 == 0)
-		fb->panel->bgr_connection = true;
-
-	return fb->panel->caps ? 0 : -EINVAL;
-}
-
-static int clcdfb_of_init_display(struct clcd_fb *fb)
-{
-	struct device_node *endpoint, *panel;
-	int err;
-	unsigned int bpp;
-	u32 max_bandwidth;
-	u32 tft_r0b0g0[3];
-
-	fb->panel = devm_kzalloc(&fb->dev->dev, sizeof(*fb->panel), GFP_KERNEL);
-	if (!fb->panel)
-		return -ENOMEM;
-
-	/*
-	 * Fetch the panel endpoint.
-	 */
-	endpoint = of_graph_get_next_endpoint(fb->dev->dev.of_node, NULL);
-	if (!endpoint)
-		return -ENODEV;
-
-	panel = of_graph_get_remote_port_parent(endpoint);
-	if (!panel)
-		return -ENODEV;
-
-	err = clcdfb_of_get_backlight(&fb->dev->dev, fb->panel);
-	if (err)
-		return err;
-
-	err = clcdfb_of_get_mode(&fb->dev->dev, panel, fb->panel);
-	if (err)
-		return err;
-
-	err = of_property_read_u32(fb->dev->dev.of_node, "max-memory-bandwidth",
-			&max_bandwidth);
-	if (!err) {
-		/*
-		 * max_bandwidth is in bytes per second and pixclock in
-		 * pico-seconds, so the maximum allowed bits per pixel is
-		 *   8 * max_bandwidth / (PICOS2KHZ(pixclock) * 1000)
-		 * Rearrange this calculation to avoid overflow and then ensure
-		 * result is a valid format.
-		 */
-		bpp = max_bandwidth / (1000 / 8)
-			/ PICOS2KHZ(fb->panel->mode.pixclock);
-		bpp = rounddown_pow_of_two(bpp);
-		if (bpp > 32)
-			bpp = 32;
-	} else
-		bpp = 32;
-	fb->panel->bpp = bpp;
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	fb->panel->cntl |= CNTL_BEBO;
-#endif
-	fb->panel->width = -1;
-	fb->panel->height = -1;
-
-	if (of_property_read_u32_array(endpoint,
-			"arm,pl11x,tft-r0g0b0-pads",
-			tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0)
-		return -ENOENT;
-
-	return clcdfb_of_init_tft_panel(fb, tft_r0b0g0[0],
-					tft_r0b0g0[1],  tft_r0b0g0[2]);
-}
-
-static int clcdfb_of_vram_setup(struct clcd_fb *fb)
-{
-	int err;
-	struct device_node *memory;
-	u64 size;
-
-	err = clcdfb_of_init_display(fb);
-	if (err)
-		return err;
-
-	memory = of_parse_phandle(fb->dev->dev.of_node, "memory-region", 0);
-	if (!memory)
-		return -ENODEV;
-
-	fb->fb.screen_base = of_iomap(memory, 0);
-	if (!fb->fb.screen_base)
-		return -ENOMEM;
-
-	fb->fb.fix.smem_start = of_translate_address(memory,
-			of_get_address(memory, 0, &size, NULL));
-	fb->fb.fix.smem_len = size;
-
-	return 0;
-}
-
-static int clcdfb_of_vram_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
-{
-	unsigned long off, user_size, kernel_size;
-
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-	kernel_size = fb->fb.fix.smem_len;
-
-	if (off >= kernel_size || user_size > (kernel_size - off))
-		return -ENXIO;
-
-	return remap_pfn_range(vma, vma->vm_start,
-			__phys_to_pfn(fb->fb.fix.smem_start) + vma->vm_pgoff,
-			user_size,
-			pgprot_writecombine(vma->vm_page_prot));
-}
-
-static void clcdfb_of_vram_remove(struct clcd_fb *fb)
-{
-	iounmap(fb->fb.screen_base);
-}
-
-static int clcdfb_of_dma_setup(struct clcd_fb *fb)
-{
-	unsigned long framesize;
-	dma_addr_t dma;
-	int err;
-
-	err = clcdfb_of_init_display(fb);
-	if (err)
-		return err;
-
-	framesize = PAGE_ALIGN(fb->panel->mode.xres * fb->panel->mode.yres *
-			fb->panel->bpp / 8);
-	fb->fb.screen_base = dma_alloc_coherent(&fb->dev->dev, framesize,
-			&dma, GFP_KERNEL);
-	if (!fb->fb.screen_base)
-		return -ENOMEM;
-
-	fb->fb.fix.smem_start = dma;
-	fb->fb.fix.smem_len = framesize;
-
-	return 0;
-}
-
-static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
-{
-	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
-			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
-}
-
-static void clcdfb_of_dma_remove(struct clcd_fb *fb)
-{
-	dma_free_coherent(&fb->dev->dev, fb->fb.fix.smem_len,
-			fb->fb.screen_base, fb->fb.fix.smem_start);
-}
-
-static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev)
-{
-	struct clcd_board *board = devm_kzalloc(&dev->dev, sizeof(*board),
-			GFP_KERNEL);
-	struct device_node *node = dev->dev.of_node;
-
-	if (!board)
-		return NULL;
-
-	board->name = of_node_full_name(node);
-	board->caps = CLCD_CAP_ALL;
-	board->check = clcdfb_check;
-	board->decode = clcdfb_decode;
-	if (of_find_property(node, "memory-region", NULL)) {
-		board->setup = clcdfb_of_vram_setup;
-		board->mmap = clcdfb_of_vram_mmap;
-		board->remove = clcdfb_of_vram_remove;
-	} else {
-		board->setup = clcdfb_of_dma_setup;
-		board->mmap = clcdfb_of_dma_mmap;
-		board->remove = clcdfb_of_dma_remove;
-	}
-
-	return board;
-}
-#else
-static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev)
-{
-	return NULL;
-}
-#endif
-
-static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct clcd_board *board = dev_get_platdata(&dev->dev);
-	struct clcd_fb *fb;
-	int ret;
-
-	if (!board)
-		board = clcdfb_of_get_board(dev);
-
-	if (!board)
-		return -EINVAL;
-
-	ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
-	if (ret)
-		goto out;
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret) {
-		printk(KERN_ERR "CLCD: unable to reserve regs region\n");
-		goto out;
-	}
-
-	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
-	if (!fb) {
-		ret = -ENOMEM;
-		goto free_region;
-	}
-
-	fb->dev = dev;
-	fb->board = board;
-
-	dev_info(&fb->dev->dev, "PL%03x designer %02x rev%u at 0x%08llx\n",
-		amba_part(dev), amba_manf(dev), amba_rev(dev),
-		(unsigned long long)dev->res.start);
-
-	ret = fb->board->setup(fb);
-	if (ret)
-		goto free_fb;
-
-	ret = clcdfb_register(fb);
-	if (ret == 0) {
-		amba_set_drvdata(dev, fb);
-		goto out;
-	}
-
-	fb->board->remove(fb);
- free_fb:
-	kfree(fb);
- free_region:
-	amba_release_regions(dev);
- out:
-	return ret;
-}
-
-static int clcdfb_remove(struct amba_device *dev)
-{
-	struct clcd_fb *fb = amba_get_drvdata(dev);
-
-	clcdfb_disable(fb);
-	unregister_framebuffer(&fb->fb);
-	if (fb->fb.cmap.len)
-		fb_dealloc_cmap(&fb->fb.cmap);
-	iounmap(fb->regs);
-	clk_unprepare(fb->clk);
-	clk_put(fb->clk);
-
-	fb->board->remove(fb);
-
-	kfree(fb);
-
-	amba_release_regions(dev);
-
-	return 0;
-}
-
-static const struct amba_id clcdfb_id_table[] = {
-	{
-		.id	= 0x00041110,
-		.mask	= 0x000ffffe,
-	},
-	{ 0, 0 },
-};
-
-MODULE_DEVICE_TABLE(amba, clcdfb_id_table);
-
-static struct amba_driver clcd_driver = {
-	.drv 		= {
-		.name	= "clcd-pl11x",
-	},
-	.probe		= clcdfb_probe,
-	.remove		= clcdfb_remove,
-	.id_table	= clcdfb_id_table,
-};
-
-static int __init amba_clcdfb_init(void)
-{
-	if (fb_get_options("ambafb", NULL))
-		return -ENODEV;
-
-	return amba_driver_register(&clcd_driver);
-}
-
-module_init(amba_clcdfb_init);
-
-static void __exit amba_clcdfb_exit(void)
-{
-	amba_driver_unregister(&clcd_driver);
-}
-
-module_exit(amba_clcdfb_exit);
-
-MODULE_DESCRIPTION("ARM PrimeCell PL110 CLCD core driver");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h
deleted file mode 100644
index b6e0cbeaf533..000000000000
--- a/include/linux/amba/clcd.h
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel.
- *
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-#include <linux/fb.h>
-#include <linux/amba/clcd-regs.h>
-
-enum {
-	/* individual formats */
-	CLCD_CAP_RGB444		= (1 << 0),
-	CLCD_CAP_RGB5551	= (1 << 1),
-	CLCD_CAP_RGB565		= (1 << 2),
-	CLCD_CAP_RGB888		= (1 << 3),
-	CLCD_CAP_BGR444		= (1 << 4),
-	CLCD_CAP_BGR5551	= (1 << 5),
-	CLCD_CAP_BGR565		= (1 << 6),
-	CLCD_CAP_BGR888		= (1 << 7),
-
-	/* connection layouts */
-	CLCD_CAP_444		= CLCD_CAP_RGB444 | CLCD_CAP_BGR444,
-	CLCD_CAP_5551		= CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551,
-	CLCD_CAP_565		= CLCD_CAP_RGB565 | CLCD_CAP_BGR565,
-	CLCD_CAP_888		= CLCD_CAP_RGB888 | CLCD_CAP_BGR888,
-
-	/* red/blue ordering */
-	CLCD_CAP_RGB		= CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 |
-				  CLCD_CAP_RGB565 | CLCD_CAP_RGB888,
-	CLCD_CAP_BGR		= CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 |
-				  CLCD_CAP_BGR565 | CLCD_CAP_BGR888,
-
-	CLCD_CAP_ALL		= CLCD_CAP_BGR | CLCD_CAP_RGB,
-};
-
-struct backlight_device;
-
-struct clcd_panel {
-	struct fb_videomode	mode;
-	signed short		width;	/* width in mm */
-	signed short		height;	/* height in mm */
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	u32			caps;
-	unsigned int		bpp:8,
-				fixedtimings:1,
-				grayscale:1;
-	unsigned int		connector;
-	struct backlight_device	*backlight;
-	/*
-	 * If the B/R lines are switched between the CLCD
-	 * and the panel we need to know this and not try to
-	 * compensate with the BGR bit in the control register.
-	 */
-	bool			bgr_connection;
-};
-
-struct clcd_regs {
-	u32			tim0;
-	u32			tim1;
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	unsigned long		pixclock;
-};
-
-struct clcd_fb;
-
-/*
- * the board-type specific routines
- */
-struct clcd_board {
-	const char *name;
-
-	/*
-	 * Optional.  Hardware capability flags.
-	 */
-	u32	caps;
-
-	/*
-	 * Optional.  Check whether the var structure is acceptable
-	 * for this display.
-	 */
-	int	(*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var);
-
-	/*
-	 * Compulsory.  Decode fb->fb.var into regs->*.  In the case of
-	 * fixed timing, set regs->* to the register values required.
-	 */
-	void	(*decode)(struct clcd_fb *fb, struct clcd_regs *regs);
-
-	/*
-	 * Optional.  Disable any extra display hardware.
-	 */
-	void	(*disable)(struct clcd_fb *);
-
-	/*
-	 * Optional.  Enable any extra display hardware.
-	 */
-	void	(*enable)(struct clcd_fb *);
-
-	/*
-	 * Setup platform specific parts of CLCD driver
-	 */
-	int	(*setup)(struct clcd_fb *);
-
-	/*
-	 * mmap the framebuffer memory
-	 */
-	int	(*mmap)(struct clcd_fb *, struct vm_area_struct *);
-
-	/*
-	 * Remove platform specific parts of CLCD driver
-	 */
-	void	(*remove)(struct clcd_fb *);
-};
-
-struct amba_device;
-struct clk;
-
-/* this data structure describes each frame buffer device we find */
-struct clcd_fb {
-	struct fb_info		fb;
-	struct amba_device	*dev;
-	struct clk		*clk;
-	struct clcd_panel	*panel;
-	struct clcd_board	*board;
-	void			*board_data;
-	void __iomem		*regs;
-	u16			off_ienb;
-	u16			off_cntl;
-	u32			clcd_cntl;
-	u32			cmap[16];
-	bool			clk_enabled;
-};
-
-static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
-{
-	struct fb_var_screeninfo *var = &fb->fb.var;
-	u32 val, cpl;
-
-	/*
-	 * Program the CLCD controller registers and start the CLCD
-	 */
-	val = ((var->xres / 16) - 1) << 2;
-	val |= (var->hsync_len - 1) << 8;
-	val |= (var->right_margin - 1) << 16;
-	val |= (var->left_margin - 1) << 24;
-	regs->tim0 = val;
-
-	val = var->yres;
-	if (fb->panel->cntl & CNTL_LCDDUAL)
-		val /= 2;
-	val -= 1;
-	val |= (var->vsync_len - 1) << 10;
-	val |= var->lower_margin << 16;
-	val |= var->upper_margin << 24;
-	regs->tim1 = val;
-
-	val = fb->panel->tim2;
-	val |= var->sync & FB_SYNC_HOR_HIGH_ACT  ? 0 : TIM2_IHS;
-	val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS;
-
-	cpl = var->xres_virtual;
-	if (fb->panel->cntl & CNTL_LCDTFT)	  /* TFT */
-		/* / 1 */;
-	else if (!var->grayscale)		  /* STN color */
-		cpl = cpl * 8 / 3;
-	else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */
-		cpl /= 8;
-	else					  /* STN monochrome, 4bit */
-		cpl /= 4;
-
-	regs->tim2 = val | ((cpl - 1) << 16);
-
-	regs->tim3 = fb->panel->tim3;
-
-	val = fb->panel->cntl;
-	if (var->grayscale)
-		val |= CNTL_LCDBW;
-
-	if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) {
-		/*
-		 * if board and panel supply capabilities, we can support
-		 * changing BGR/RGB depending on supplied parameters. Here
-		 * we switch to what the framebuffer is providing if need
-		 * be, so if the framebuffer is BGR but the display connection
-		 * is RGB (first case) we switch it around. Vice versa mutatis
-		 * mutandis if the framebuffer is RGB but the display connection
-		 * is BGR, we flip it around.
-		 */
-		if (var->red.offset == 0)
-			val &= ~CNTL_BGR;
-		else
-			val |= CNTL_BGR;
-		if (fb->panel->bgr_connection)
-			val ^= CNTL_BGR;
-	}
-
-	switch (var->bits_per_pixel) {
-	case 1:
-		val |= CNTL_LCDBPP1;
-		break;
-	case 2:
-		val |= CNTL_LCDBPP2;
-		break;
-	case 4:
-		val |= CNTL_LCDBPP4;
-		break;
-	case 8:
-		val |= CNTL_LCDBPP8;
-		break;
-	case 16:
-		/*
-		 * PL110 cannot choose between 5551 and 565 modes in its
-		 * control register.  It is possible to use 565 with
-		 * custom external wiring.
-		 */
-		if (amba_part(fb->dev) == 0x110 ||
-		    var->green.length == 5)
-			val |= CNTL_LCDBPP16;
-		else if (var->green.length == 6)
-			val |= CNTL_LCDBPP16_565;
-		else
-			val |= CNTL_LCDBPP16_444;
-		break;
-	case 32:
-		val |= CNTL_LCDBPP24;
-		break;
-	}
-
-	regs->cntl = val;
-	regs->pixclock = var->pixclock;
-}
-
-static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
-	var->xres_virtual = var->xres = (var->xres + 15) & ~15;
-	var->yres_virtual = var->yres = (var->yres + 1) & ~1;
-
-#define CHECK(e,l,h) (var->e < l || var->e > h)
-	if (CHECK(right_margin, (5+1), 256) ||	/* back porch */
-	    CHECK(left_margin, (5+1), 256) ||	/* front porch */
-	    CHECK(hsync_len, (5+1), 256) ||
-	    var->xres > 4096 ||
-	    var->lower_margin > 255 ||		/* back porch */
-	    var->upper_margin > 255 ||		/* front porch */
-	    var->vsync_len > 32 ||
-	    var->yres > 1024)
-		return -EINVAL;
-#undef CHECK
-
-	/* single panel mode: PCD = max(PCD, 1) */
-	/* dual panel mode: PCD = max(PCD, 5) */
-
-	/*
-	 * You can't change the grayscale setting, and
-	 * we can only do non-interlaced video.
-	 */
-	if (var->grayscale != fb->fb.var.grayscale ||
-	    (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED)
-		return -EINVAL;
-
-#define CHECK(e) (var->e != fb->fb.var.e)
-	if (fb->panel->fixedtimings &&
-	    (CHECK(xres)		||
-	     CHECK(yres)		||
-	     CHECK(bits_per_pixel)	||
-	     CHECK(pixclock)		||
-	     CHECK(left_margin)		||
-	     CHECK(right_margin)	||
-	     CHECK(upper_margin)	||
-	     CHECK(lower_margin)	||
-	     CHECK(hsync_len)		||
-	     CHECK(vsync_len)		||
-	     CHECK(sync)))
-		return -EINVAL;
-#undef CHECK
-
-	var->nonstd = 0;
-	var->accel_flags = 0;
-
-	return 0;
-}
-- 
cgit v1.2.3


From 7e4e589db76a3cf4c1f534eb5a09cc6422766b93 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 9 Jun 2020 22:04:45 +0200
Subject: drm: pl111: Absorb the external register header

The PL111 DRM driver is now the sole user of the external
CLCD registers header file, so let's absorb that into the
pl111_drm.h file and save the external include.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Russell King <linux@armlinux.org.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200609200446.153209-3-linus.walleij@linaro.org
---
 drivers/gpu/drm/pl111/pl111_debugfs.c   |  1 -
 drivers/gpu/drm/pl111/pl111_display.c   |  1 -
 drivers/gpu/drm/pl111/pl111_drm.h       | 73 +++++++++++++++++++++++++++
 drivers/gpu/drm/pl111/pl111_drv.c       |  1 -
 drivers/gpu/drm/pl111/pl111_versatile.c |  1 -
 include/linux/amba/clcd-regs.h          | 87 ---------------------------------
 6 files changed, 73 insertions(+), 91 deletions(-)
 delete mode 100644 include/linux/amba/clcd-regs.h

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/pl111/pl111_debugfs.c b/drivers/gpu/drm/pl111/pl111_debugfs.c
index 26ca8cdf3e60..317f68abf18b 100644
--- a/drivers/gpu/drm/pl111/pl111_debugfs.c
+++ b/drivers/gpu/drm/pl111/pl111_debugfs.c
@@ -3,7 +3,6 @@
  *  Copyright © 2017 Broadcom
  */
 
-#include <linux/amba/clcd-regs.h>
 #include <linux/seq_file.h>
 
 #include <drm/drm_debugfs.h>
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 703ddc803c55..b3e8697cafcf 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -9,7 +9,6 @@
  * Copyright (C) 2011 Texas Instruments
  */
 
-#include <linux/amba/clcd-regs.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/version.h>
diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h
index ba399bcb792f..2a46b5bd8576 100644
--- a/drivers/gpu/drm/pl111/pl111_drm.h
+++ b/drivers/gpu/drm/pl111/pl111_drm.h
@@ -23,6 +23,79 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_simple_kms_helper.h>
 
+/*
+ * CLCD Controller Internal Register addresses
+ */
+#define CLCD_TIM0		0x00000000
+#define CLCD_TIM1		0x00000004
+#define CLCD_TIM2		0x00000008
+#define CLCD_TIM3		0x0000000c
+#define CLCD_UBAS		0x00000010
+#define CLCD_LBAS		0x00000014
+
+#define CLCD_PL110_IENB		0x00000018
+#define CLCD_PL110_CNTL		0x0000001c
+#define CLCD_PL110_STAT		0x00000020
+#define CLCD_PL110_INTR		0x00000024
+#define CLCD_PL110_UCUR		0x00000028
+#define CLCD_PL110_LCUR		0x0000002C
+
+#define CLCD_PL111_CNTL		0x00000018
+#define CLCD_PL111_IENB		0x0000001c
+#define CLCD_PL111_RIS		0x00000020
+#define CLCD_PL111_MIS		0x00000024
+#define CLCD_PL111_ICR		0x00000028
+#define CLCD_PL111_UCUR		0x0000002c
+#define CLCD_PL111_LCUR		0x00000030
+
+#define CLCD_PALL		0x00000200
+#define CLCD_PALETTE		0x00000200
+
+#define TIM2_PCD_LO_MASK	GENMASK(4, 0)
+#define TIM2_PCD_LO_BITS	5
+#define TIM2_CLKSEL		(1 << 5)
+#define TIM2_ACB_MASK		GENMASK(10, 6)
+#define TIM2_IVS		(1 << 11)
+#define TIM2_IHS		(1 << 12)
+#define TIM2_IPC		(1 << 13)
+#define TIM2_IOE		(1 << 14)
+#define TIM2_BCD		(1 << 26)
+#define TIM2_PCD_HI_MASK	GENMASK(31, 27)
+#define TIM2_PCD_HI_BITS	5
+#define TIM2_PCD_HI_SHIFT	27
+
+#define CNTL_LCDEN		(1 << 0)
+#define CNTL_LCDBPP1		(0 << 1)
+#define CNTL_LCDBPP2		(1 << 1)
+#define CNTL_LCDBPP4		(2 << 1)
+#define CNTL_LCDBPP8		(3 << 1)
+#define CNTL_LCDBPP16		(4 << 1)
+#define CNTL_LCDBPP16_565	(6 << 1)
+#define CNTL_LCDBPP16_444	(7 << 1)
+#define CNTL_LCDBPP24		(5 << 1)
+#define CNTL_LCDBW		(1 << 4)
+#define CNTL_LCDTFT		(1 << 5)
+#define CNTL_LCDMONO8		(1 << 6)
+#define CNTL_LCDDUAL		(1 << 7)
+#define CNTL_BGR		(1 << 8)
+#define CNTL_BEBO		(1 << 9)
+#define CNTL_BEPO		(1 << 10)
+#define CNTL_LCDPWR		(1 << 11)
+#define CNTL_LCDVCOMP(x)	((x) << 12)
+#define CNTL_LDMAFIFOTIME	(1 << 15)
+#define CNTL_WATERMARK		(1 << 16)
+
+/* ST Microelectronics variant bits */
+#define CNTL_ST_1XBPP_444	0x0
+#define CNTL_ST_1XBPP_5551	(1 << 17)
+#define CNTL_ST_1XBPP_565	(1 << 18)
+#define CNTL_ST_CDWID_12	0x0
+#define CNTL_ST_CDWID_16	(1 << 19)
+#define CNTL_ST_CDWID_18	(1 << 20)
+#define CNTL_ST_CDWID_24	((1 << 19) | (1 << 20))
+#define CNTL_ST_CEAEN		(1 << 21)
+#define CNTL_ST_LCDBPP24_PACKED	(6 << 1)
+
 #define CLCD_IRQ_NEXTBASE_UPDATE BIT(2)
 
 struct drm_minor;
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index da0c39dae874..96e58fda75d8 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -47,7 +47,6 @@
  */
 
 #include <linux/amba/bus.h>
-#include <linux/amba/clcd-regs.h>
 #include <linux/dma-buf.h>
 #include <linux/module.h>
 #include <linux/of.h>
diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c
index 1127082e9a60..bdd883f4f0da 100644
--- a/drivers/gpu/drm/pl111/pl111_versatile.c
+++ b/drivers/gpu/drm/pl111/pl111_versatile.c
@@ -9,7 +9,6 @@
  * Major contributions and discoveries by Russell King.
  */
 
-#include <linux/amba/clcd-regs.h>
 #include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/mfd/syscon.h>
diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h
deleted file mode 100644
index 421b0fa90d6a..000000000000
--- a/include/linux/amba/clcd-regs.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#ifndef AMBA_CLCD_REGS_H
-#define AMBA_CLCD_REGS_H
-
-/*
- * CLCD Controller Internal Register addresses
- */
-#define CLCD_TIM0		0x00000000
-#define CLCD_TIM1 		0x00000004
-#define CLCD_TIM2 		0x00000008
-#define CLCD_TIM3 		0x0000000c
-#define CLCD_UBAS 		0x00000010
-#define CLCD_LBAS 		0x00000014
-
-#define CLCD_PL110_IENB		0x00000018
-#define CLCD_PL110_CNTL		0x0000001c
-#define CLCD_PL110_STAT		0x00000020
-#define CLCD_PL110_INTR 	0x00000024
-#define CLCD_PL110_UCUR		0x00000028
-#define CLCD_PL110_LCUR		0x0000002C
-
-#define CLCD_PL111_CNTL		0x00000018
-#define CLCD_PL111_IENB		0x0000001c
-#define CLCD_PL111_RIS		0x00000020
-#define CLCD_PL111_MIS		0x00000024
-#define CLCD_PL111_ICR		0x00000028
-#define CLCD_PL111_UCUR		0x0000002c
-#define CLCD_PL111_LCUR		0x00000030
-
-#define CLCD_PALL 		0x00000200
-#define CLCD_PALETTE		0x00000200
-
-#define TIM2_PCD_LO_MASK	GENMASK(4, 0)
-#define TIM2_PCD_LO_BITS	5
-#define TIM2_CLKSEL		(1 << 5)
-#define TIM2_ACB_MASK		GENMASK(10, 6)
-#define TIM2_IVS		(1 << 11)
-#define TIM2_IHS		(1 << 12)
-#define TIM2_IPC		(1 << 13)
-#define TIM2_IOE		(1 << 14)
-#define TIM2_BCD		(1 << 26)
-#define TIM2_PCD_HI_MASK	GENMASK(31, 27)
-#define TIM2_PCD_HI_BITS	5
-#define TIM2_PCD_HI_SHIFT	27
-
-#define CNTL_LCDEN		(1 << 0)
-#define CNTL_LCDBPP1		(0 << 1)
-#define CNTL_LCDBPP2		(1 << 1)
-#define CNTL_LCDBPP4		(2 << 1)
-#define CNTL_LCDBPP8		(3 << 1)
-#define CNTL_LCDBPP16		(4 << 1)
-#define CNTL_LCDBPP16_565	(6 << 1)
-#define CNTL_LCDBPP16_444	(7 << 1)
-#define CNTL_LCDBPP24		(5 << 1)
-#define CNTL_LCDBW		(1 << 4)
-#define CNTL_LCDTFT		(1 << 5)
-#define CNTL_LCDMONO8		(1 << 6)
-#define CNTL_LCDDUAL		(1 << 7)
-#define CNTL_BGR		(1 << 8)
-#define CNTL_BEBO		(1 << 9)
-#define CNTL_BEPO		(1 << 10)
-#define CNTL_LCDPWR		(1 << 11)
-#define CNTL_LCDVCOMP(x)	((x) << 12)
-#define CNTL_LDMAFIFOTIME	(1 << 15)
-#define CNTL_WATERMARK		(1 << 16)
-
-/* ST Microelectronics variant bits */
-#define CNTL_ST_1XBPP_444	0x0
-#define CNTL_ST_1XBPP_5551	(1 << 17)
-#define CNTL_ST_1XBPP_565	(1 << 18)
-#define CNTL_ST_CDWID_12	0x0
-#define CNTL_ST_CDWID_16	(1 << 19)
-#define CNTL_ST_CDWID_18	(1 << 20)
-#define CNTL_ST_CDWID_24	((1 << 19)|(1 << 20))
-#define CNTL_ST_CEAEN		(1 << 21)
-#define CNTL_ST_LCDBPP24_PACKED	(6 << 1)
-
-#endif /* AMBA_CLCD_REGS_H */
-- 
cgit v1.2.3


From 142240398e50e5fe3171bcf2459856603be13a39 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Sat, 27 Jun 2020 23:24:19 -0400
Subject: audit: add gfp parameter to audit_log_nfcfg

Fixed an inconsistent use of GFP flags in nft_obj_notify() that used
GFP_KERNEL when a GFP flag was passed in to that function.  Given this
allocated memory was then used in audit_log_nfcfg() it led to an audit
of all other GFP allocations in net/netfilter/nf_tables_api.c and a
modification of audit_log_nfcfg() to accept a GFP parameter.

Reported-by: Dan Carptenter <dan.carpenter@oracle.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h           |  8 ++++----
 kernel/auditsc.c                |  4 ++--
 net/bridge/netfilter/ebtables.c |  6 +++---
 net/netfilter/nf_tables_api.c   | 33 +++++++++++++++++++++------------
 net/netfilter/x_tables.c        |  5 +++--
 5 files changed, 33 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 604ede630580..d93739f7a35a 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -404,7 +404,7 @@ extern void __audit_fanotify(unsigned int response);
 extern void __audit_tk_injoffset(struct timespec64 offset);
 extern void __audit_ntp_log(const struct audit_ntp_data *ad);
 extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries,
-			      enum audit_nfcfgop op);
+			      enum audit_nfcfgop op, gfp_t gfp);
 
 static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 {
@@ -542,10 +542,10 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad)
 
 static inline void audit_log_nfcfg(const char *name, u8 af,
 				   unsigned int nentries,
-				   enum audit_nfcfgop op)
+				   enum audit_nfcfgop op, gfp_t gfp)
 {
 	if (audit_enabled)
-		__audit_log_nfcfg(name, af, nentries, op);
+		__audit_log_nfcfg(name, af, nentries, op, gfp);
 }
 
 extern int audit_n_rules;
@@ -683,7 +683,7 @@ static inline void audit_ptrace(struct task_struct *t)
 
 static inline void audit_log_nfcfg(const char *name, u8 af,
 				   unsigned int nentries,
-				   enum audit_nfcfgop op)
+				   enum audit_nfcfgop op, gfp_t gfp)
 { }
 
 #define audit_n_rules 0
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3a9100e95fda..eae1a599ffe3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2572,12 +2572,12 @@ void __audit_ntp_log(const struct audit_ntp_data *ad)
 }
 
 void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries,
-		       enum audit_nfcfgop op)
+		       enum audit_nfcfgop op, gfp_t gfp)
 {
 	struct audit_buffer *ab;
 	char comm[sizeof(current->comm)];
 
-	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_NETFILTER_CFG);
+	ab = audit_log_start(audit_context(), gfp, AUDIT_NETFILTER_CFG);
 	if (!ab)
 		return;
 	audit_log_format(ab, "table=%s family=%u entries=%u op=%s",
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index c83ffe912163..b13b49b9f75c 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1047,7 +1047,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 	vfree(counterstmp);
 
 	audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries,
-			AUDIT_XT_OP_REPLACE);
+			AUDIT_XT_OP_REPLACE, GFP_KERNEL);
 	return ret;
 
 free_unlock:
@@ -1123,7 +1123,7 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
 	list_del(&table->list);
 	mutex_unlock(&ebt_mutex);
 	audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries,
-			AUDIT_XT_OP_UNREGISTER);
+			AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
 	EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size,
 			  ebt_cleanup_entry, net, NULL);
 	if (table->private->nentries)
@@ -1218,7 +1218,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	}
 
 	audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries,
-			AUDIT_XT_OP_REGISTER);
+			AUDIT_XT_OP_REGISTER, GFP_KERNEL);
 	return ret;
 free_unlock:
 	mutex_unlock(&ebt_mutex);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 164700273947..f7ff91479647 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -702,7 +702,8 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 			ctx->table->use,
 			event == NFT_MSG_NEWTABLE ?
 				AUDIT_NFT_OP_TABLE_REGISTER :
-				AUDIT_NFT_OP_TABLE_UNREGISTER);
+				AUDIT_NFT_OP_TABLE_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (!ctx->report &&
@@ -1448,7 +1449,8 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 			ctx->chain->use,
 			event == NFT_MSG_NEWCHAIN ?
 				AUDIT_NFT_OP_CHAIN_REGISTER :
-				AUDIT_NFT_OP_CHAIN_UNREGISTER);
+				AUDIT_NFT_OP_CHAIN_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (!ctx->report &&
@@ -2724,7 +2726,8 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
 			rule->handle,
 			event == NFT_MSG_NEWRULE ?
 				AUDIT_NFT_OP_RULE_REGISTER :
-				AUDIT_NFT_OP_RULE_UNREGISTER);
+				AUDIT_NFT_OP_RULE_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (!ctx->report &&
@@ -3737,7 +3740,8 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx,
 			set->field_count,
 			event == NFT_MSG_NEWSET ?
 				AUDIT_NFT_OP_SET_REGISTER :
-				AUDIT_NFT_OP_SET_UNREGISTER);
+				AUDIT_NFT_OP_SET_UNREGISTER,
+			gfp_flags);
 	kfree(buf);
 
 	if (!ctx->report &&
@@ -4864,7 +4868,8 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
 			set->handle,
 			event == NFT_MSG_NEWSETELEM ?
 				AUDIT_NFT_OP_SETELEM_REGISTER :
-				AUDIT_NFT_OP_SETELEM_UNREGISTER);
+				AUDIT_NFT_OP_SETELEM_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
@@ -5956,7 +5961,8 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 				audit_log_nfcfg(buf,
 						family,
 						obj->handle,
-						AUDIT_NFT_OP_OBJ_RESET);
+						AUDIT_NFT_OP_OBJ_RESET,
+						GFP_KERNEL);
 				kfree(buf);
 			}
 
@@ -6071,13 +6077,14 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 		reset = true;
 
 	if (reset) {
-		char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+		char *buf = kasprintf(GFP_ATOMIC, "%s:%llu;?:0",
 				      table->name, table->handle);
 
 		audit_log_nfcfg(buf,
 				family,
 				obj->handle,
-				AUDIT_NFT_OP_OBJ_RESET);
+				AUDIT_NFT_OP_OBJ_RESET,
+				GFP_KERNEL);
 		kfree(buf);
 	}
 
@@ -6156,7 +6163,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 {
 	struct sk_buff *skb;
 	int err;
-	char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+	char *buf = kasprintf(gfp, "%s:%llu;?:0",
 			      table->name, table->handle);
 
 	audit_log_nfcfg(buf,
@@ -6164,7 +6171,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 			obj->handle,
 			event == NFT_MSG_NEWOBJ ?
 				AUDIT_NFT_OP_OBJ_REGISTER :
-				AUDIT_NFT_OP_OBJ_UNREGISTER);
+				AUDIT_NFT_OP_OBJ_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (!report &&
@@ -6954,7 +6962,8 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 			flowtable->hooknum,
 			event == NFT_MSG_NEWFLOWTABLE ?
 				AUDIT_NFT_OP_FLOWTABLE_REGISTER :
-				AUDIT_NFT_OP_FLOWTABLE_UNREGISTER);
+				AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+			GFP_KERNEL);
 	kfree(buf);
 
 	if (ctx->report &&
@@ -7078,7 +7087,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
 	int err;
 
 	audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
-			AUDIT_NFT_OP_GEN_REGISTER);
+			AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
 
 	if (nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 99a468be4a59..9ad8f3ff66f5 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1410,7 +1410,8 @@ xt_replace_table(struct xt_table *table,
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
-					   AUDIT_XT_OP_REPLACE);
+					   AUDIT_XT_OP_REPLACE,
+			GFP_KERNEL);
 	return private;
 }
 EXPORT_SYMBOL_GPL(xt_replace_table);
@@ -1473,7 +1474,7 @@ void *xt_unregister_table(struct xt_table *table)
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,
-			AUDIT_XT_OP_UNREGISTER);
+			AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
 	kfree(table);
 
 	return private;
-- 
cgit v1.2.3


From ecc31c60240b9808a274befc5db6b8a249a6ade1 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Mon, 29 Jun 2020 23:46:16 +0300
Subject: ethtool: Add link extended state

Currently, drivers can only tell whether the link is up/down using
LINKSTATE_GET, but no additional information is given.

Add attributes to LINKSTATE_GET command in order to allow drivers
to expose the user more information in addition to link state to ease
the debug process, for example, reason for link down state.

Extended state consists of two attributes - link_ext_state and
link_ext_substate. The idea is to avoid 'vendor specific' states in order
to prevent drivers to use specific link_ext_state that can be in the future
common link_ext_state.

The substates allows drivers to add more information to the common
link_ext_state. For example, vendor can expose 'Autoneg' as link_ext_state
and add 'No partner detected during force mode' as link_ext_substate.

If a driver cannot pinpoint the extended state with the substate
accuracy, it is free to expose only the extended state and omit the
substate attribute.

Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h              | 23 ++++++++++++
 include/uapi/linux/ethtool.h         | 70 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/ethtool_netlink.h |  2 ++
 net/ethtool/linkstate.c              | 52 ++++++++++++++++++++++++---
 4 files changed, 143 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a23b26eab479..48ad3b6a0150 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -86,6 +86,22 @@ struct net_device;
 u32 ethtool_op_get_link(struct net_device *dev);
 int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti);
 
+
+/**
+ * struct ethtool_link_ext_state_info - link extended state and substate.
+ */
+struct ethtool_link_ext_state_info {
+	enum ethtool_link_ext_state link_ext_state;
+	union {
+		enum ethtool_link_ext_substate_autoneg autoneg;
+		enum ethtool_link_ext_substate_link_training link_training;
+		enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch;
+		enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity;
+		enum ethtool_link_ext_substate_cable_issue cable_issue;
+		u8 __link_ext_substate;
+	};
+};
+
 /**
  * ethtool_rxfh_indir_default - get default value for RX flow hash indirection
  * @index: Index in RX flow hash indirection table
@@ -245,6 +261,11 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
  * @get_link: Report whether physical link is up.  Will only be called if
  *	the netdev is up.  Should usually be set to ethtool_op_get_link(),
  *	which uses netif_carrier_ok().
+ * @get_link_ext_state: Report link extended state. Should set link_ext_state and
+ *	link_ext_substate (link_ext_substate of 0 means link_ext_substate is unknown,
+ *	do not attach ext_substate attribute to netlink message). If link_ext_state
+ *	and link_ext_substate are unknown, return -ENODATA. If not implemented,
+ *	link_ext_state and link_ext_substate will not be sent to userspace.
  * @get_eeprom: Read data from the device EEPROM.
  *	Should fill in the magic field.  Don't need to check len for zero
  *	or wraparound.  Fill in the data argument with the eeprom values
@@ -384,6 +405,8 @@ struct ethtool_ops {
 	void	(*set_msglevel)(struct net_device *, u32);
 	int	(*nway_reset)(struct net_device *);
 	u32	(*get_link)(struct net_device *);
+	int	(*get_link_ext_state)(struct net_device *,
+				      struct ethtool_link_ext_state_info *);
 	int	(*get_eeprom_len)(struct net_device *);
 	int	(*get_eeprom)(struct net_device *,
 			      struct ethtool_eeprom *, u8 *);
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f4662b3a9e1e..d1413538ef30 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -579,6 +579,76 @@ struct ethtool_pauseparam {
 	__u32	tx_pause;
 };
 
+/**
+ * enum ethtool_link_ext_state - link extended state
+ */
+enum ethtool_link_ext_state {
+	ETHTOOL_LINK_EXT_STATE_AUTONEG,
+	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
+	ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
+	ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
+	ETHTOOL_LINK_EXT_STATE_NO_CABLE,
+	ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE,
+	ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE,
+	ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE,
+	ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED,
+	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
+};
+
+/**
+ * enum ethtool_link_ext_substate_autoneg - more information in addition to
+ * ETHTOOL_LINK_EXT_STATE_AUTONEG.
+ */
+enum ethtool_link_ext_substate_autoneg {
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NEXT_PAGE_EXCHANGE_FAILED,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED_FORCE_MODE,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_FEC_MISMATCH_DURING_OVERRIDE,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
+};
+
+/**
+ * enum ethtool_link_ext_substate_link_training - more information in addition to
+ * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+ */
+enum ethtool_link_ext_substate_link_training {
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
+};
+
+/**
+ * enum ethtool_link_ext_substate_logical_mismatch - more information in addition
+ * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+ */
+enum ethtool_link_ext_substate_link_logical_mismatch {
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_AM_LOCK,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_GET_ALIGN_STATUS,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
+};
+
+/**
+ * enum ethtool_link_ext_substate_bad_signal_integrity - more information in
+ * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+ */
+enum ethtool_link_ext_substate_bad_signal_integrity {
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
+};
+
+/**
+ * enum ethtool_link_ext_substate_cable_issue - more information in
+ * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE.
+ */
+enum ethtool_link_ext_substate_cable_issue {
+	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
+};
+
 #define ETH_GSTRING_LEN		32
 
 /**
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 4dda5e4244a7..c12ce4df4b6b 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -236,6 +236,8 @@ enum {
 	ETHTOOL_A_LINKSTATE_LINK,		/* u8 */
 	ETHTOOL_A_LINKSTATE_SQI,		/* u32 */
 	ETHTOOL_A_LINKSTATE_SQI_MAX,		/* u32 */
+	ETHTOOL_A_LINKSTATE_EXT_STATE,		/* u8 */
+	ETHTOOL_A_LINKSTATE_EXT_SUBSTATE,	/* u8 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_LINKSTATE_CNT,
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index afe5ac8a0f00..4834091ec24c 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -9,10 +9,12 @@ struct linkstate_req_info {
 };
 
 struct linkstate_reply_data {
-	struct ethnl_reply_data		base;
-	int				link;
-	int				sqi;
-	int				sqi_max;
+	struct ethnl_reply_data			base;
+	int					link;
+	int					sqi;
+	int					sqi_max;
+	bool					link_ext_state_provided;
+	struct ethtool_link_ext_state_info	ethtool_link_ext_state_info;
 };
 
 #define LINKSTATE_REPDATA(__reply_base) \
@@ -25,6 +27,8 @@ linkstate_get_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = {
 	[ETHTOOL_A_LINKSTATE_LINK]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_LINKSTATE_SQI]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_LINKSTATE_SQI_MAX]		= { .type = NLA_REJECT },
+	[ETHTOOL_A_LINKSTATE_EXT_STATE]		= { .type = NLA_REJECT },
+	[ETHTOOL_A_LINKSTATE_EXT_SUBSTATE]	= { .type = NLA_REJECT },
 };
 
 static int linkstate_get_sqi(struct net_device *dev)
@@ -61,6 +65,23 @@ static int linkstate_get_sqi_max(struct net_device *dev)
 	mutex_unlock(&phydev->lock);
 
 	return ret;
+};
+
+static int linkstate_get_link_ext_state(struct net_device *dev,
+					struct linkstate_reply_data *data)
+{
+	int err;
+
+	if (!dev->ethtool_ops->get_link_ext_state)
+		return -EOPNOTSUPP;
+
+	err = dev->ethtool_ops->get_link_ext_state(dev, &data->ethtool_link_ext_state_info);
+	if (err)
+		return err;
+
+	data->link_ext_state_provided = true;
+
+	return 0;
 }
 
 static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
@@ -86,6 +107,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 		goto out;
 	data->sqi_max = ret;
 
+	if (dev->flags & IFF_UP) {
+		ret = linkstate_get_link_ext_state(dev, data);
+		if (ret < 0 && ret != -EOPNOTSUPP && ret != -ENODATA)
+			goto out;
+	}
+
 	ret = 0;
 out:
 	ethnl_ops_complete(dev);
@@ -107,6 +134,12 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base,
 	if (data->sqi_max != -EOPNOTSUPP)
 		len += nla_total_size(sizeof(u32));
 
+	if (data->link_ext_state_provided)
+		len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */
+
+	if (data->ethtool_link_ext_state_info.__link_ext_substate)
+		len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */
+
 	return len;
 }
 
@@ -128,6 +161,17 @@ static int linkstate_fill_reply(struct sk_buff *skb,
 	    nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max))
 		return -EMSGSIZE;
 
+	if (data->link_ext_state_provided) {
+		if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE,
+			       data->ethtool_link_ext_state_info.link_ext_state))
+			return -EMSGSIZE;
+
+		if (data->ethtool_link_ext_state_info.__link_ext_substate &&
+		    nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_SUBSTATE,
+			       data->ethtool_link_ext_state_info.__link_ext_substate))
+			return -EMSGSIZE;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From ca37faf3d7005b5588f045edfac1d82799c408a7 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 30 Jun 2020 10:17:56 +0200
Subject: iommu: Move sg_table wrapper out of CONFIG_IOMMU_SUPPORT

Move the recently added sg_table wrapper out of CONFIG_IOMMU_SUPPORT to
let the client code copile also when IOMMU support is disabled.

Fixes: 48530d9fab0d ("iommu: add generic helper for mapping sgtable objects")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20200630081756.18526-1-m.szyprowski@samsung.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 5f0b7859d2eb..5657d4fef9f2 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -457,22 +457,6 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
-/**
- * iommu_map_sgtable - Map the given buffer to the IOMMU domain
- * @domain:	The IOMMU domain to perform the mapping
- * @iova:	The start address to map the buffer
- * @sgt:	The sg_table object describing the buffer
- * @prot:	IOMMU protection bits
- *
- * Creates a mapping at @iova for the buffer described by a scatterlist
- * stored in the given sg_table object in the provided IOMMU domain.
- */
-static inline size_t iommu_map_sgtable(struct iommu_domain *domain,
-			unsigned long iova, struct sg_table *sgt, int prot)
-{
-	return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot);
-}
-
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern void generic_iommu_put_resv_regions(struct device *dev,
@@ -1079,6 +1063,22 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 }
 #endif /* CONFIG_IOMMU_API */
 
+/**
+ * iommu_map_sgtable - Map the given buffer to the IOMMU domain
+ * @domain:	The IOMMU domain to perform the mapping
+ * @iova:	The start address to map the buffer
+ * @sgt:	The sg_table object describing the buffer
+ * @prot:	IOMMU protection bits
+ *
+ * Creates a mapping at @iova for the buffer described by a scatterlist
+ * stored in the given sg_table object in the provided IOMMU domain.
+ */
+static inline size_t iommu_map_sgtable(struct iommu_domain *domain,
+			unsigned long iova, struct sg_table *sgt, int prot)
+{
+	return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot);
+}
+
 #ifdef CONFIG_IOMMU_DEBUGFS
 extern	struct dentry *iommu_debugfs_dir;
 void iommu_debugfs_setup(void);
-- 
cgit v1.2.3


From 1909872ff20fc378ec6a44ea1a2b2966d834e504 Mon Sep 17 00:00:00 2001
From: Nicola Mazzucato <nicola.mazzucato@arm.com>
Date: Wed, 17 Jun 2020 10:43:31 +0100
Subject: firmware: arm_scmi: Add fast_switch_possible() interface

Add a new fast_switch_possible interface to the existing perf_ops to
export the information of whether or not fast_switch is possible for a
given device.

This can be used by the cpufreq driver and framework to choose proper
mechanism for frequency change.

Link: https://lore.kernel.org/r/20200617094332.8391-1-nicola.mazzucato@arm.com
Suggested-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Nicola Mazzucato <nicola.mazzucato@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/perf.c | 12 ++++++++++++
 include/linux/scmi_protocol.h    |  2 ++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index eadc171e254b..7b8d7cebdac9 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -697,6 +697,17 @@ static int scmi_dvfs_est_power_get(const struct scmi_handle *handle, u32 domain,
 	return ret;
 }
 
+static bool scmi_fast_switch_possible(const struct scmi_handle *handle,
+				      struct device *dev)
+{
+	struct perf_dom_info *dom;
+	struct scmi_perf_info *pi = handle->perf_priv;
+
+	dom = pi->dom_info + scmi_dev_domain_id(dev);
+
+	return dom->fc_info && dom->fc_info->level_set_addr;
+}
+
 static struct scmi_perf_ops perf_ops = {
 	.limits_set = scmi_perf_limits_set,
 	.limits_get = scmi_perf_limits_get,
@@ -708,6 +719,7 @@ static struct scmi_perf_ops perf_ops = {
 	.freq_set = scmi_dvfs_freq_set,
 	.freq_get = scmi_dvfs_freq_get,
 	.est_power_get = scmi_dvfs_est_power_get,
+	.fast_switch_possible = scmi_fast_switch_possible,
 };
 
 static int scmi_perf_protocol_init(struct scmi_handle *handle)
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index ce2f5c28b2df..73911d156a39 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -118,6 +118,8 @@ struct scmi_perf_ops {
 			unsigned long *rate, bool poll);
 	int (*est_power_get)(const struct scmi_handle *handle, u32 domain,
 			     unsigned long *rate, unsigned long *power);
+	bool (*fast_switch_possible)(const struct scmi_handle *handle,
+				     struct device *dev);
 };
 
 /**
-- 
cgit v1.2.3


From 7999096fa9cfd0253497c8d2ed9a5a1537521d25 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 12 Jun 2020 16:57:37 +1000
Subject: iov_iter: Move unnecessary inclusion of crypto/hash.h

The header file linux/uio.h includes crypto/hash.h which pulls in
most of the Crypto API.  Since linux/uio.h is used throughout the
kernel this means that every tiny bit of change to the Crypto API
causes the entire kernel to get rebuilt.

This patch fixes this by moving it into lib/iov_iter.c instead
where it is actually used.

This patch also fixes the ifdef to use CRYPTO_HASH instead of just
CRYPTO which does not guarantee the existence of ahash.

Unfortunately a number of drivers were relying on linux/uio.h to
provide access to linux/slab.h.  This patch adds inclusions of
linux/slab.h as detected by build failures.

Also skbuff.h was relying on this to provide a declaration for
ahash_request.  This patch adds a forward declaration instead.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/lib/test_unwind.c                    | 1 +
 drivers/dma/sf-pdma/sf-pdma.c                  | 1 +
 drivers/dma/st_fdma.c                          | 1 +
 drivers/dma/uniphier-xdmac.c                   | 1 +
 drivers/misc/uacce/uacce.c                     | 1 +
 drivers/mtd/mtdpstore.c                        | 1 +
 drivers/mtd/nand/raw/cadence-nand-controller.c | 1 +
 drivers/remoteproc/qcom_q6v5_mss.c             | 1 +
 drivers/soc/qcom/pdr_interface.c               | 1 +
 fs/btrfs/inode.c                               | 1 +
 include/linux/skbuff.h                         | 1 +
 include/linux/socket.h                         | 1 +
 include/linux/uio.h                            | 1 -
 lib/iov_iter.c                                 | 3 ++-
 14 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c
index 32b7a30b2485..eb382ceaa116 100644
--- a/arch/s390/lib/test_unwind.c
+++ b/arch/s390/lib/test_unwind.c
@@ -9,6 +9,7 @@
 #include <linux/kallsyms.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/kprobes.h>
 #include <linux/wait.h>
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 5c118c7e02bd..6e530dca6d9e 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -20,6 +20,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
+#include <linux/slab.h>
 
 #include "sf-pdma.h"
 
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index 67087dbe2f9f..962b6e05287b 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/remoteproc.h>
+#include <linux/slab.h>
 
 #include "st_fdma.h"
 
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 7b2f8a8c2d31..16b19654873d 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include "dmaengine.h"
 #include "virt-dma.h"
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index 107028e77ca3..e45bfd409cc5 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -4,6 +4,7 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/uacce.h>
 
 static struct class *uacce_class;
diff --git a/drivers/mtd/mtdpstore.c b/drivers/mtd/mtdpstore.c
index a4fe6060b960..a3ae8778f6a9 100644
--- a/drivers/mtd/mtdpstore.c
+++ b/drivers/mtd/mtdpstore.c
@@ -7,6 +7,7 @@
 #include <linux/pstore_blk.h>
 #include <linux/mtd/mtd.h>
 #include <linux/bitops.h>
+#include <linux/slab.h>
 
 static struct mtdpstore_context {
 	int index;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index c405722adfe1..c4f273e2fe78 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -17,6 +17,7 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/of_device.h>
 #include <linux/iopoll.h>
+#include <linux/slab.h>
 
 /*
  * HPNFC can work in 3 modes:
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index feb70283b6a2..903b2bb97e12 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -26,6 +26,7 @@
 #include <linux/reset.h>
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/iopoll.h>
+#include <linux/slab.h>
 
 #include "remoteproc_internal.h"
 #include "qcom_common.h"
diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c
index bdcf16f88a97..a90d707da689 100644
--- a/drivers/soc/qcom/pdr_interface.c
+++ b/drivers/soc/qcom/pdr_interface.c
@@ -5,6 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/workqueue.h>
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d04c82c88418..d901d53e4f03 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
+#include <crypto/hash.h>
 #include <linux/kernel.h>
 #include <linux/bio.h>
 #include <linux/buffer_head.h>
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0c0377fc00c2..1530e81a6cce 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -238,6 +238,7 @@
 			 SKB_DATA_ALIGN(sizeof(struct sk_buff)) +	\
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
+struct ahash_request;
 struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 04d2bc97f497..e9cb30d8cbfb 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>		/* __user			*/
 #include <uapi/linux/socket.h>
 
+struct file;
 struct pid;
 struct cred;
 struct socket;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 9576fd8158d7..3835a8a8e9ea 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -7,7 +7,6 @@
 
 #include <linux/kernel.h>
 #include <linux/thread_info.h>
-#include <crypto/hash.h>
 #include <uapi/linux/uio.h>
 
 struct page;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index bf538c2bec77..5e40786c8f12 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <crypto/hash.h>
 #include <linux/export.h>
 #include <linux/bvec.h>
 #include <linux/uio.h>
@@ -1567,7 +1568,7 @@ EXPORT_SYMBOL(csum_and_copy_to_iter);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {
-#ifdef CONFIG_CRYPTO
+#ifdef CONFIG_CRYPTO_HASH
 	struct ahash_request *hash = hashp;
 	struct scatterlist sg;
 	size_t copied;
-- 
cgit v1.2.3


From 3aa91625007807bfca4155df1867a5c924a08662 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 29 Jun 2020 15:03:56 +0200
Subject: dma-mapping: Add a new dma_need_sync API

Add a new API to check if calls to dma_sync_single_for_{device,cpu} are
required for a given DMA streaming mapping.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200629130359.2690853-2-hch@lst.de
---
 Documentation/core-api/dma-api.rst |  8 ++++++++
 include/linux/dma-direct.h         |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 kernel/dma/direct.c                |  6 ++++++
 kernel/dma/mapping.c               | 10 ++++++++++
 5 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 2d8d2fed7317..f41620439ef3 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -204,6 +204,14 @@ Returns the maximum size of a mapping for the device. The size parameter
 of the mapping functions like dma_map_single(), dma_map_page() and
 others should not be larger than the returned value.
 
+::
+
+	bool
+	dma_need_sync(struct device *dev, dma_addr_t dma_addr);
+
+Returns %true if dma_sync_single_for_{device,cpu} calls are required to
+transfer memory ownership.  Returns %false if those calls can be skipped.
+
 ::
 
 	unsigned long
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 136f984df0d9..8b006730687b 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -87,4 +87,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 78f677cf45ab..a33ed3954ed4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 #else /* CONFIG_HAS_DMA */
 static inline dma_addr_t dma_map_page_attrs(struct device *dev,
@@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return false;
+}
 static inline unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	return 0;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 0a4881e59aa7..ecb922a0bfa0 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -530,3 +530,9 @@ size_t dma_direct_max_mapping_size(struct device *dev)
 		return swiotlb_max_mapping_size(dev);
 	return SIZE_MAX;
 }
+
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dev_is_dma_coherent(dev) ||
+		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 98e3d873792e..a8c18c9a796f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_is_direct(ops))
+		return dma_direct_need_sync(dev, dma_addr);
+	return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+
 unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
cgit v1.2.3


From 65c763694398a2de63803b264dcf906b47f9d4c1 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 30 Jun 2020 18:24:56 +0800
Subject: blk-mq: pass request queue into get/put budget callback

blk-mq budget is abstract from scsi's device queue depth, and it is
always per-request-queue instead of hctx.

It can be quite absurd to get a budget from one hctx, then dequeue a
request from scheduler queue, and this request may not belong to this
hctx, at least for bfq and deadline.

So fix the mess and always pass request queue to get/put budget
callback.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Baolin Wang <baolin.wang7@gmail.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Baolin Wang <baolin.wang7@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c    |  8 ++++----
 block/blk-mq.c          |  8 ++++----
 block/blk-mq.h          | 12 ++++--------
 drivers/scsi/scsi_lib.c |  8 +++-----
 include/linux/blk-mq.h  |  4 ++--
 5 files changed, 17 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index fdcc2c1dd178..a31e281e9d31 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -108,12 +108,12 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 			break;
 		}
 
-		if (!blk_mq_get_dispatch_budget(hctx))
+		if (!blk_mq_get_dispatch_budget(q))
 			break;
 
 		rq = e->type->ops.dispatch_request(hctx);
 		if (!rq) {
-			blk_mq_put_dispatch_budget(hctx);
+			blk_mq_put_dispatch_budget(q);
 			/*
 			 * We're releasing without dispatching. Holding the
 			 * budget could have blocked any "hctx"s with the
@@ -173,12 +173,12 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 		if (!sbitmap_any_bit_set(&hctx->ctx_map))
 			break;
 
-		if (!blk_mq_get_dispatch_budget(hctx))
+		if (!blk_mq_get_dispatch_budget(q))
 			break;
 
 		rq = blk_mq_dequeue_from_ctx(hctx, ctx);
 		if (!rq) {
-			blk_mq_put_dispatch_budget(hctx);
+			blk_mq_put_dispatch_budget(q);
 			/*
 			 * We're releasing without dispatching. Holding the
 			 * budget could have blocked any "hctx"s with the
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 72d3034fe39d..8cdc868f4249 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1284,7 +1284,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		rq = list_first_entry(list, struct request, queuelist);
 
 		hctx = rq->mq_hctx;
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
+		if (!got_budget && !blk_mq_get_dispatch_budget(q)) {
 			blk_mq_put_driver_tag(rq);
 			no_budget_avail = true;
 			break;
@@ -1299,7 +1299,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * we'll re-run it below.
 			 */
 			if (!blk_mq_mark_tag_wait(hctx, rq)) {
-				blk_mq_put_dispatch_budget(hctx);
+				blk_mq_put_dispatch_budget(q);
 				/*
 				 * For non-shared tags, the RESTART check
 				 * will suffice.
@@ -1947,11 +1947,11 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (q->elevator && !bypass_insert)
 		goto insert;
 
-	if (!blk_mq_get_dispatch_budget(hctx))
+	if (!blk_mq_get_dispatch_budget(q))
 		goto insert;
 
 	if (!blk_mq_get_driver_tag(rq)) {
-		blk_mq_put_dispatch_budget(hctx);
+		blk_mq_put_dispatch_budget(q);
 		goto insert;
 	}
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c6330335767c..e4af193d39ac 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -179,20 +179,16 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
 void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 			 unsigned int inflight[2]);
 
-static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
+static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
 {
-	struct request_queue *q = hctx->queue;
-
 	if (q->mq_ops->put_budget)
-		q->mq_ops->put_budget(hctx);
+		q->mq_ops->put_budget(q);
 }
 
-static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
+static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
 {
-	struct request_queue *q = hctx->queue;
-
 	if (q->mq_ops->get_budget)
-		return q->mq_ops->get_budget(hctx);
+		return q->mq_ops->get_budget(q);
 	return true;
 }
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 6ca91d09eca1..534b85e87c80 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1597,17 +1597,15 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
-static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)
+static void scsi_mq_put_budget(struct request_queue *q)
 {
-	struct request_queue *q = hctx->queue;
 	struct scsi_device *sdev = q->queuedata;
 
 	atomic_dec(&sdev->device_busy);
 }
 
-static bool scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx)
+static bool scsi_mq_get_budget(struct request_queue *q)
 {
-	struct request_queue *q = hctx->queue;
 	struct scsi_device *sdev = q->queuedata;
 
 	return scsi_dev_queue_ready(q, sdev);
@@ -1674,7 +1672,7 @@ out_dec_target_busy:
 	if (scsi_target(sdev)->can_queue > 0)
 		atomic_dec(&scsi_target(sdev)->target_busy);
 out_put_budget:
-	scsi_mq_put_budget(hctx);
+	scsi_mq_put_budget(q);
 	switch (ret) {
 	case BLK_STS_OK:
 		break;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8986e88a986b..faa340b70123 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -270,8 +270,8 @@ struct blk_mq_queue_data {
 typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *,
 		const struct blk_mq_queue_data *);
 typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *);
-typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *);
-typedef void (put_budget_fn)(struct blk_mq_hw_ctx *);
+typedef bool (get_budget_fn)(struct request_queue *);
+typedef void (put_budget_fn)(struct request_queue *);
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
-- 
cgit v1.2.3


From e3f88cdb8fdd5876ef3a0373e35ba7f2598fcf17 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 9 Jun 2020 04:54:33 +0800
Subject: soundwire: add definitions for 1.2 spec

Add definitions for register offsets and bit fields from the MIPI
SoundWire 1.2 specification (available to MIPI members at
https://members.mipi.org/wg/All-Members/document/download/78371)

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200608205436.2402-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw_registers.h | 107 +++++++++++++++++++++++++++++++-
 1 file changed, 106 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index a686f7988156..12f9ffc3eb3b 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -12,7 +12,7 @@
 #define SDW_REG_SHIFT(n)			(ffs(n) - 1)
 
 /*
- * SDW registers as defined by MIPI 1.1 Spec
+ * SDW registers as defined by MIPI 1.2 Spec
  */
 #define SDW_REGADDR				GENMASK(14, 0)
 #define SDW_SCP_ADDRPAGE2_MASK			GENMASK(22, 15)
@@ -43,6 +43,8 @@
 #define SDW_DP0_INT_TEST_FAIL			BIT(0)
 #define SDW_DP0_INT_PORT_READY			BIT(1)
 #define SDW_DP0_INT_BRA_FAILURE			BIT(2)
+#define SDW_DP0_SDCA_CASCADE			BIT(3)
+/* BIT(4) not allocated in SoundWire specification 1.2 */
 #define SDW_DP0_INT_IMPDEF1			BIT(5)
 #define SDW_DP0_INT_IMPDEF2			BIT(6)
 #define SDW_DP0_INT_IMPDEF3			BIT(7)
@@ -106,6 +108,10 @@
 #define SDW_SCP_ADDRPAGE2			0x49
 #define SDW_SCP_KEEPEREN			0x4A
 #define SDW_SCP_BANKDELAY			0x4B
+#define SDW_SCP_COMMIT				0x4C
+#define SDW_SCP_BUS_CLOCK_BASE			0x4D
+#define SDW_SCP_BASE_CLOCK_FREQ			GENMASK(2, 0)
+/* 0x4E is not allocated in SoundWire specification 1.2 */
 #define SDW_SCP_TESTMODE			0x4F
 #define SDW_SCP_DEVID_0				0x50
 #define SDW_SCP_DEVID_1				0x51
@@ -114,12 +120,111 @@
 #define SDW_SCP_DEVID_4				0x54
 #define SDW_SCP_DEVID_5				0x55
 
+/* Both INT and STATUS register are same */
+#define SDW_SCP_SDCA_INT1			0x58
+#define SDW_SCP_SDCA_INT_SDCA_0			BIT(0)
+#define SDW_SCP_SDCA_INT_SDCA_1			BIT(1)
+#define SDW_SCP_SDCA_INT_SDCA_2			BIT(2)
+#define SDW_SCP_SDCA_INT_SDCA_3			BIT(3)
+#define SDW_SCP_SDCA_INT_SDCA_4			BIT(4)
+#define SDW_SCP_SDCA_INT_SDCA_5			BIT(5)
+#define SDW_SCP_SDCA_INT_SDCA_6			BIT(6)
+#define SDW_SCP_SDCA_INT_SDCA_7			BIT(7)
+
+#define SDW_SCP_SDCA_INT2			0x59
+#define SDW_SCP_SDCA_INT_SDCA_8			BIT(0)
+#define SDW_SCP_SDCA_INT_SDCA_9			BIT(1)
+#define SDW_SCP_SDCA_INT_SDCA_10		BIT(2)
+#define SDW_SCP_SDCA_INT_SDCA_11		BIT(3)
+#define SDW_SCP_SDCA_INT_SDCA_12		BIT(4)
+#define SDW_SCP_SDCA_INT_SDCA_13		BIT(5)
+#define SDW_SCP_SDCA_INT_SDCA_14		BIT(6)
+#define SDW_SCP_SDCA_INT_SDCA_15		BIT(7)
+
+#define SDW_SCP_SDCA_INT3			0x5A
+#define SDW_SCP_SDCA_INT_SDCA_16		BIT(0)
+#define SDW_SCP_SDCA_INT_SDCA_17		BIT(1)
+#define SDW_SCP_SDCA_INT_SDCA_18		BIT(2)
+#define SDW_SCP_SDCA_INT_SDCA_19		BIT(3)
+#define SDW_SCP_SDCA_INT_SDCA_20		BIT(4)
+#define SDW_SCP_SDCA_INT_SDCA_21		BIT(5)
+#define SDW_SCP_SDCA_INT_SDCA_22		BIT(6)
+#define SDW_SCP_SDCA_INT_SDCA_23		BIT(7)
+
+#define SDW_SCP_SDCA_INT4			0x5B
+#define SDW_SCP_SDCA_INT_SDCA_24		BIT(0)
+#define SDW_SCP_SDCA_INT_SDCA_25		BIT(1)
+#define SDW_SCP_SDCA_INT_SDCA_26		BIT(2)
+#define SDW_SCP_SDCA_INT_SDCA_27		BIT(3)
+#define SDW_SCP_SDCA_INT_SDCA_28		BIT(4)
+#define SDW_SCP_SDCA_INT_SDCA_29		BIT(5)
+#define SDW_SCP_SDCA_INT_SDCA_30		BIT(6)
+/* BIT(7) not allocated in SoundWire 1.2 specification */
+
+#define SDW_SCP_SDCA_INTMASK1			0x5C
+#define SDW_SCP_SDCA_INTMASK_SDCA_0		BIT(0)
+#define SDW_SCP_SDCA_INTMASK_SDCA_1		BIT(1)
+#define SDW_SCP_SDCA_INTMASK_SDCA_2		BIT(2)
+#define SDW_SCP_SDCA_INTMASK_SDCA_3		BIT(3)
+#define SDW_SCP_SDCA_INTMASK_SDCA_4		BIT(4)
+#define SDW_SCP_SDCA_INTMASK_SDCA_5		BIT(5)
+#define SDW_SCP_SDCA_INTMASK_SDCA_6		BIT(6)
+#define SDW_SCP_SDCA_INTMASK_SDCA_7		BIT(7)
+
+#define SDW_SCP_SDCA_INTMASK2			0x5D
+#define SDW_SCP_SDCA_INTMASK_SDCA_8		BIT(0)
+#define SDW_SCP_SDCA_INTMASK_SDCA_9		BIT(1)
+#define SDW_SCP_SDCA_INTMASK_SDCA_10		BIT(2)
+#define SDW_SCP_SDCA_INTMASK_SDCA_11		BIT(3)
+#define SDW_SCP_SDCA_INTMASK_SDCA_12		BIT(4)
+#define SDW_SCP_SDCA_INTMASK_SDCA_13		BIT(5)
+#define SDW_SCP_SDCA_INTMASK_SDCA_14		BIT(6)
+#define SDW_SCP_SDCA_INTMASK_SDCA_15		BIT(7)
+
+#define SDW_SCP_SDCA_INTMASK3			0x5E
+#define SDW_SCP_SDCA_INTMASK_SDCA_16		BIT(0)
+#define SDW_SCP_SDCA_INTMASK_SDCA_17		BIT(1)
+#define SDW_SCP_SDCA_INTMASK_SDCA_18		BIT(2)
+#define SDW_SCP_SDCA_INTMASK_SDCA_19		BIT(3)
+#define SDW_SCP_SDCA_INTMASK_SDCA_20		BIT(4)
+#define SDW_SCP_SDCA_INTMASK_SDCA_21		BIT(5)
+#define SDW_SCP_SDCA_INTMASK_SDCA_22		BIT(6)
+#define SDW_SCP_SDCA_INTMASK_SDCA_23		BIT(7)
+
+#define SDW_SCP_SDCA_INTMASK4			0x5F
+#define SDW_SCP_SDCA_INTMASK_SDCA_24		BIT(0)
+#define SDW_SCP_SDCA_INTMASK_SDCA_25		BIT(1)
+#define SDW_SCP_SDCA_INTMASK_SDCA_26		BIT(2)
+#define SDW_SCP_SDCA_INTMASK_SDCA_27		BIT(3)
+#define SDW_SCP_SDCA_INTMASK_SDCA_28		BIT(4)
+#define SDW_SCP_SDCA_INTMASK_SDCA_29		BIT(5)
+#define SDW_SCP_SDCA_INTMASK_SDCA_30		BIT(6)
+/* BIT(7) not allocated in SoundWire 1.2 specification */
+
 /* Banked Registers */
 #define SDW_SCP_FRAMECTRL_B0			0x60
 #define SDW_SCP_FRAMECTRL_B1			(0x60 + SDW_BANK1_OFFSET)
 #define SDW_SCP_NEXTFRAME_B0			0x61
 #define SDW_SCP_NEXTFRAME_B1			(0x61 + SDW_BANK1_OFFSET)
 
+#define SDW_SCP_BUSCLOCK_SCALE_B0		0x62
+#define SDW_SCP_BUSCLOCK_SCALE_B1		(0x62 + SDW_BANK1_OFFSET)
+#define SDW_SCP_CLOCK_SCALE			GENMASK(3, 0)
+
+/* PHY registers - CTRL and STAT are the same address */
+#define SDW_SCP_PHY_OUT_CTRL_0			0x80
+#define SDW_SCP_PHY_OUT_CTRL_1			0x81
+#define SDW_SCP_PHY_OUT_CTRL_2			0x82
+#define SDW_SCP_PHY_OUT_CTRL_3			0x83
+#define SDW_SCP_PHY_OUT_CTRL_4			0x84
+#define SDW_SCP_PHY_OUT_CTRL_5			0x85
+#define SDW_SCP_PHY_OUT_CTRL_6			0x86
+#define SDW_SCP_PHY_OUT_CTRL_7			0x87
+
+#define SDW_SCP_CAP_LOAD_CTRL			GENMASK(2, 0)
+#define SDW_SCP_DRIVE_STRENGTH_CTRL		GENMASK(5, 3)
+#define SDW_SCP_SLEW_TIME_CTRL			GENMASK(7, 6)
+
 /* Both INT and STATUS register is same */
 #define SDW_DPN_INT(n)				(0x0 + SDW_DPN_SIZE * (n))
 #define SDW_DPN_INTMASK(n)			(0x1 + SDW_DPN_SIZE * (n))
-- 
cgit v1.2.3


From b5924268d6700821fbd8afe815073b05cebaa308 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 9 Jun 2020 04:54:35 +0800
Subject: soundwire: extend SDW_SLAVE_ENTRY

The SoundWire 1.2 specification adds new capabilities that were not
present in previous version, such as the class ID.

To enable support for class drivers, and well as drivers that address
a specific version, all fields of the sdw_device_id structure need to
be exposed. For SoundWire 1.0 and 1.1 devices, a wildcard is used so
class and version information are ignored.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200608205436.2402-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus_type.c      | 13 +++++++++----
 include/linux/mod_devicetable.h   |  2 ++
 include/linux/soundwire/sdw.h     | 11 +++++++----
 scripts/mod/devicetable-offsets.c |  2 ++
 scripts/mod/file2alias.c          |  6 +++++-
 5 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index c8d948c09d9d..6fba55898cf0 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -24,7 +24,11 @@ sdw_get_device_id(struct sdw_slave *slave, struct sdw_driver *drv)
 
 	for (id = drv->id_table; id && id->mfg_id; id++)
 		if (slave->id.mfg_id == id->mfg_id &&
-		    slave->id.part_id == id->part_id)
+		    slave->id.part_id == id->part_id  &&
+		    (!id->sdw_version ||
+		     slave->id.sdw_version == id->sdw_version) &&
+		    (!id->class_id ||
+		     slave->id.class_id == id->class_id))
 			return id;
 
 	return NULL;
@@ -47,10 +51,11 @@ static int sdw_bus_match(struct device *dev, struct device_driver *ddrv)
 
 int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size)
 {
-	/* modalias is sdw:m<mfg_id>p<part_id> */
+	/* modalias is sdw:m<mfg_id>p<part_id>v<version>c<class_id> */
 
-	return snprintf(buf, size, "sdw:m%04Xp%04X\n",
-			slave->id.mfg_id, slave->id.part_id);
+	return snprintf(buf, size, "sdw:m%04Xp%04Xv%02Xc%02X\n",
+			slave->id.mfg_id, slave->id.part_id,
+			slave->id.sdw_version, slave->id.class_id);
 }
 
 int sdw_slave_uevent(struct device *dev, struct kobj_uevent_env *env)
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 8d764aab29de..f8585e3a2c43 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -251,6 +251,8 @@ struct hda_device_id {
 struct sdw_device_id {
 	__u16 mfg_id;
 	__u16 part_id;
+	__u8  sdw_version;
+	__u8  class_id;
 	kernel_ulong_t driver_data;
 };
 
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 9c27a32df9bb..64c9314cb903 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -426,8 +426,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave);
  * struct sdw_slave_id - Slave ID
  * @mfg_id: MIPI Manufacturer ID
  * @part_id: Device Part ID
- * @class_id: MIPI Class ID, unused now.
- * Currently a placeholder in MIPI SoundWire Spec
+ * @class_id: MIPI Class ID (defined starting with SoundWire 1.2 spec)
  * @unique_id: Device unique ID
  * @sdw_version: SDW version implemented
  *
@@ -659,10 +658,14 @@ struct sdw_driver {
 	struct device_driver driver;
 };
 
-#define SDW_SLAVE_ENTRY(_mfg_id, _part_id, _drv_data) \
-	{ .mfg_id = (_mfg_id), .part_id = (_part_id), \
+#define SDW_SLAVE_ENTRY_EXT(_mfg_id, _part_id, _version, _c_id, _drv_data) \
+	{ .mfg_id = (_mfg_id), .part_id = (_part_id),		\
+	  .sdw_version = (_version), .class_id = (_c_id),	\
 	  .driver_data = (unsigned long)(_drv_data) }
 
+#define SDW_SLAVE_ENTRY(_mfg_id, _part_id, _drv_data)	\
+	SDW_SLAVE_ENTRY_EXT((_mfg_id), (_part_id), 0, 0, (_drv_data))
+
 int sdw_handle_slave_status(struct sdw_bus *bus,
 			enum sdw_slave_status status[]);
 
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index 010be8ba2116..27007c18e754 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -216,6 +216,8 @@ int main(void)
 	DEVID(sdw_device_id);
 	DEVID_FIELD(sdw_device_id, mfg_id);
 	DEVID_FIELD(sdw_device_id, part_id);
+	DEVID_FIELD(sdw_device_id, sdw_version);
+	DEVID_FIELD(sdw_device_id, class_id);
 
 	DEVID(fsl_mc_device_id);
 	DEVID_FIELD(fsl_mc_device_id, vendor);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 9599e2a3f1e6..2417dd1dee33 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1258,15 +1258,19 @@ static int do_hda_entry(const char *filename, void *symval, char *alias)
 	return 1;
 }
 
-/* Looks like: sdw:mNpN */
+/* Looks like: sdw:mNpNvNcN */
 static int do_sdw_entry(const char *filename, void *symval, char *alias)
 {
 	DEF_FIELD(symval, sdw_device_id, mfg_id);
 	DEF_FIELD(symval, sdw_device_id, part_id);
+	DEF_FIELD(symval, sdw_device_id, sdw_version);
+	DEF_FIELD(symval, sdw_device_id, class_id);
 
 	strcpy(alias, "sdw:");
 	ADD(alias, "m", mfg_id != 0, mfg_id);
 	ADD(alias, "p", part_id != 0, part_id);
+	ADD(alias, "v", sdw_version != 0, sdw_version);
+	ADD(alias, "c", class_id != 0, class_id);
 
 	add_wildcard(alias);
 	return 1;
-- 
cgit v1.2.3


From 29d158f906907ce8e52ea75ec87b4e35461f2018 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 9 Jun 2020 04:54:36 +0800
Subject: soundwire: bus: initialize bus clock base and scale registers

The SoundWire 1.2 specification adds new registers to allow for
seamless clock changes while audio transfers are on-going. Program
them following the specification.

Note that dynamic clock changes are not supported for now, this only
adds the register initialization.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200608205436.2402-5-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c                 | 107 ++++++++++++++++++++++++++++++++
 include/linux/soundwire/sdw_registers.h |  10 +++
 2 files changed, 117 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index fcfba1c38267..e6e0fb9a81b4 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1070,12 +1070,119 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave,
 	return ret;
 }
 
+static int sdw_slave_set_frequency(struct sdw_slave *slave)
+{
+	u32 mclk_freq = slave->bus->prop.mclk_freq;
+	u32 curr_freq = slave->bus->params.curr_dr_freq >> 1;
+	unsigned int scale;
+	u8 scale_index;
+	u8 base;
+	int ret;
+
+	/*
+	 * frequency base and scale registers are required for SDCA
+	 * devices. They may also be used for 1.2+/non-SDCA devices,
+	 * but we will need a DisCo property to cover this case
+	 */
+	if (!slave->id.class_id)
+		return 0;
+
+	if (!mclk_freq) {
+		dev_err(&slave->dev,
+			"no bus MCLK, cannot set SDW_SCP_BUS_CLOCK_BASE\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * map base frequency using Table 89 of SoundWire 1.2 spec.
+	 * The order of the tests just follows the specification, this
+	 * is not a selection between possible values or a search for
+	 * the best value but just a mapping.  Only one case per platform
+	 * is relevant.
+	 * Some BIOS have inconsistent values for mclk_freq but a
+	 * correct root so we force the mclk_freq to avoid variations.
+	 */
+	if (!(19200000 % mclk_freq)) {
+		mclk_freq = 19200000;
+		base = SDW_SCP_BASE_CLOCK_19200000_HZ;
+	} else if (!(24000000 % mclk_freq)) {
+		mclk_freq = 24000000;
+		base = SDW_SCP_BASE_CLOCK_24000000_HZ;
+	} else if (!(24576000 % mclk_freq)) {
+		mclk_freq = 24576000;
+		base = SDW_SCP_BASE_CLOCK_24576000_HZ;
+	} else if (!(22579200 % mclk_freq)) {
+		mclk_freq = 22579200;
+		base = SDW_SCP_BASE_CLOCK_22579200_HZ;
+	} else if (!(32000000 % mclk_freq)) {
+		mclk_freq = 32000000;
+		base = SDW_SCP_BASE_CLOCK_32000000_HZ;
+	} else {
+		dev_err(&slave->dev,
+			"Unsupported clock base, mclk %d\n",
+			mclk_freq);
+		return -EINVAL;
+	}
+
+	if (mclk_freq % curr_freq) {
+		dev_err(&slave->dev,
+			"mclk %d is not multiple of bus curr_freq %d\n",
+			mclk_freq, curr_freq);
+		return -EINVAL;
+	}
+
+	scale = mclk_freq / curr_freq;
+
+	/*
+	 * map scale to Table 90 of SoundWire 1.2 spec - and check
+	 * that the scale is a power of two and maximum 64
+	 */
+	scale_index = ilog2(scale);
+
+	if (BIT(scale_index) != scale || scale_index > 6) {
+		dev_err(&slave->dev,
+			"No match found for scale %d, bus mclk %d curr_freq %d\n",
+			scale, mclk_freq, curr_freq);
+		return -EINVAL;
+	}
+	scale_index++;
+
+	ret = sdw_write(slave, SDW_SCP_BUS_CLOCK_BASE, base);
+	if (ret < 0) {
+		dev_err(&slave->dev,
+			"SDW_SCP_BUS_CLOCK_BASE write failed:%d\n", ret);
+		return ret;
+	}
+
+	/* initialize scale for both banks */
+	ret = sdw_write(slave, SDW_SCP_BUSCLOCK_SCALE_B0, scale_index);
+	if (ret < 0) {
+		dev_err(&slave->dev,
+			"SDW_SCP_BUSCLOCK_SCALE_B0 write failed:%d\n", ret);
+		return ret;
+	}
+	ret = sdw_write(slave, SDW_SCP_BUSCLOCK_SCALE_B1, scale_index);
+	if (ret < 0)
+		dev_err(&slave->dev,
+			"SDW_SCP_BUSCLOCK_SCALE_B1 write failed:%d\n", ret);
+
+	dev_dbg(&slave->dev,
+		"Configured bus base %d, scale %d, mclk %d, curr_freq %d\n",
+		base, scale_index, mclk_freq, curr_freq);
+
+	return ret;
+}
+
 static int sdw_initialize_slave(struct sdw_slave *slave)
 {
 	struct sdw_slave_prop *prop = &slave->prop;
 	int ret;
 	u8 val;
 
+	ret = sdw_slave_set_frequency(slave);
+	if (ret < 0)
+		return ret;
+
 	/*
 	 * Set bus clash, parity and SCP implementation
 	 * defined interrupt mask
diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index 12f9ffc3eb3b..5d3c271af7d1 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -109,8 +109,18 @@
 #define SDW_SCP_KEEPEREN			0x4A
 #define SDW_SCP_BANKDELAY			0x4B
 #define SDW_SCP_COMMIT				0x4C
+
 #define SDW_SCP_BUS_CLOCK_BASE			0x4D
 #define SDW_SCP_BASE_CLOCK_FREQ			GENMASK(2, 0)
+#define SDW_SCP_BASE_CLOCK_UNKNOWN		0x0
+#define SDW_SCP_BASE_CLOCK_19200000_HZ		0x1
+#define SDW_SCP_BASE_CLOCK_24000000_HZ		0x2
+#define SDW_SCP_BASE_CLOCK_24576000_HZ		0x3
+#define SDW_SCP_BASE_CLOCK_22579200_HZ		0x4
+#define SDW_SCP_BASE_CLOCK_32000000_HZ		0x5
+#define SDW_SCP_BASE_CLOCK_RESERVED		0x6
+#define SDW_SCP_BASE_CLOCK_IMP_DEF		0x7
+
 /* 0x4E is not allocated in SoundWire specification 1.2 */
 #define SDW_SCP_TESTMODE			0x4F
 #define SDW_SCP_DEVID_0				0x50
-- 
cgit v1.2.3


From 4ac2add65974e4efafb8d4ccd8fc5660417ea312 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 29 Jun 2020 10:56:26 +0100
Subject: bpf: flow_dissector: Check value of unused flags to BPF_PROG_DETACH

Using BPF_PROG_DETACH on a flow dissector program supports neither
attach_flags nor attach_bpf_fd. Yet no value is enforced for them.

Enforce that attach_flags are zero, and require the current program
to be passed via attach_bpf_fd. This allows us to remove the check
for CAP_SYS_ADMIN, since userspace can now no longer remove
arbitrary flow dissector programs.

Fixes: b27f7bb590ba ("flow_dissector: Move out netns_bpf prog callbacks")
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200629095630.7933-3-lmb@cloudflare.com
---
 include/linux/bpf-netns.h  |  5 +++--
 kernel/bpf/net_namespace.c | 19 +++++++++++++++----
 kernel/bpf/syscall.c       |  4 +---
 3 files changed, 19 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 4052d649f36d..47d5b0c708c9 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
 			 union bpf_attr __user *uattr);
 int netns_bpf_prog_attach(const union bpf_attr *attr,
 			  struct bpf_prog *prog);
-int netns_bpf_prog_detach(const union bpf_attr *attr);
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int netns_bpf_link_create(const union bpf_attr *attr,
 			  struct bpf_prog *prog);
 #else
@@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr,
 	return -EOPNOTSUPP;
 }
 
-static inline int netns_bpf_prog_detach(const union bpf_attr *attr)
+static inline int netns_bpf_prog_detach(const union bpf_attr *attr,
+					enum bpf_prog_type ptype)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 03045f45afec..3dbc29b6f51d 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -269,7 +269,8 @@ out_unlock:
 
 /* Must be called with netns_bpf_mutex held. */
 static int __netns_bpf_prog_detach(struct net *net,
-				   enum netns_bpf_attach_type type)
+				   enum netns_bpf_attach_type type,
+				   struct bpf_prog *old)
 {
 	struct bpf_prog *attached;
 
@@ -278,7 +279,7 @@ static int __netns_bpf_prog_detach(struct net *net,
 		return -EINVAL;
 
 	attached = net->bpf.progs[type];
-	if (!attached)
+	if (!attached || attached != old)
 		return -ENOENT;
 	netns_bpf_run_array_detach(net, type);
 	net->bpf.progs[type] = NULL;
@@ -286,19 +287,29 @@ static int __netns_bpf_prog_detach(struct net *net,
 	return 0;
 }
 
-int netns_bpf_prog_detach(const union bpf_attr *attr)
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 {
 	enum netns_bpf_attach_type type;
+	struct bpf_prog *prog;
 	int ret;
 
+	if (attr->target_fd)
+		return -EINVAL;
+
 	type = to_netns_bpf_attach_type(attr->attach_type);
 	if (type < 0)
 		return -EINVAL;
 
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
 	mutex_lock(&netns_bpf_mutex);
-	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type);
+	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog);
 	mutex_unlock(&netns_bpf_mutex);
 
+	bpf_prog_put(prog);
+
 	return ret;
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7d946435587d..28c6ef759037 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2897,9 +2897,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		return netns_bpf_prog_detach(attr);
+		return netns_bpf_prog_detach(attr, ptype);
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
-- 
cgit v1.2.3


From bb0de3131f4c60a9bf976681e0fe4d1e55c7a821 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 29 Jun 2020 10:56:28 +0100
Subject: bpf: sockmap: Require attach_bpf_fd when detaching a program

The sockmap code currently ignores the value of attach_bpf_fd when
detaching a program. This is contrary to the usual behaviour of
checking that attach_bpf_fd represents the currently attached
program.

Ensure that attach_bpf_fd is indeed the currently attached
program. It turns out that all sockmap selftests already do this,
which indicates that this is unlikely to cause breakage.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200629095630.7933-5-lmb@cloudflare.com
---
 include/linux/bpf.h   | 13 +++++++++++--
 include/linux/skmsg.h | 13 +++++++++++++
 kernel/bpf/syscall.c  |  2 +-
 net/core/sock_map.c   | 50 +++++++++++++++++++++++++++++++++++++++++++++-----
 4 files changed, 70 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07052d44bca1..9750a1902ee5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
-int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
+int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+			 struct bpf_prog *old, u32 which);
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 void sock_map_unhash(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int sock_map_prog_update(struct bpf_map *map,
-				       struct bpf_prog *prog, u32 which)
+				       struct bpf_prog *prog,
+				       struct bpf_prog *old, u32 which)
 {
 	return -EOPNOTSUPP;
 }
@@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_prog_detach(const union bpf_attr *attr,
+				       enum bpf_prog_type ptype)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_STREAM_PARSER */
 
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 08674cd14d5a..1e9ed840b9fc 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog,
 		bpf_prog_put(prog);
 }
 
+static inline int psock_replace_prog(struct bpf_prog **pprog,
+				     struct bpf_prog *prog,
+				     struct bpf_prog *old)
+{
+	if (cmpxchg(pprog, old, prog) != old)
+		return -ENOENT;
+
+	if (old)
+		bpf_prog_put(old);
+
+	return 0;
+}
+
 static inline void psock_progs_drop(struct sk_psock_progs *progs)
 {
 	psock_set_prog(&progs->msg_parser, NULL);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 28c6ef759037..a74fce8ce043 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2893,7 +2893,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (ptype) {
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_SK_SKB:
-		return sock_map_get_from_fd(attr, NULL);
+		return sock_map_prog_detach(attr, ptype);
 	case BPF_PROG_TYPE_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 58016a5c63ff..0971f17e8e54 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -77,7 +77,42 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	ret = sock_map_prog_update(map, prog, attr->attach_type);
+	ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+	fdput(f);
+	return ret;
+}
+
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	u32 ufd = attr->target_fd;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct fd f;
+	int ret;
+
+	if (attr->attach_flags || attr->replace_bpf_fd)
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	prog = bpf_prog_get(attr->attach_bpf_fd);
+	if (IS_ERR(prog)) {
+		ret = PTR_ERR(prog);
+		goto put_map;
+	}
+
+	if (prog->type != ptype) {
+		ret = -EINVAL;
+		goto put_prog;
+	}
+
+	ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+put_prog:
+	bpf_prog_put(prog);
+put_map:
 	fdput(f);
 	return ret;
 }
@@ -1206,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
 }
 
 int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-			 u32 which)
+			 struct bpf_prog *old, u32 which)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
+	struct bpf_prog **pprog;
 
 	if (!progs)
 		return -EOPNOTSUPP;
 
 	switch (which) {
 	case BPF_SK_MSG_VERDICT:
-		psock_set_prog(&progs->msg_parser, prog);
+		pprog = &progs->msg_parser;
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
-		psock_set_prog(&progs->skb_parser, prog);
+		pprog = &progs->skb_parser;
 		break;
 	case BPF_SK_SKB_STREAM_VERDICT:
-		psock_set_prog(&progs->skb_verdict, prog);
+		pprog = &progs->skb_verdict;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	if (old)
+		return psock_replace_prog(pprog, prog, old);
+
+	psock_set_prog(pprog, prog);
 	return 0;
 }
 
-- 
cgit v1.2.3


From e91b48162332480f5840902268108bb7fb7a44c7 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 30 Jun 2020 17:32:54 +0200
Subject: task_work: teach task_work_add() to do signal_wake_up()

So that the target task will exit the wait_event_interruptible-like
loop and call task_work_run() asap.

The patch turns "bool notify" into 0,TWA_RESUME,TWA_SIGNAL enum, the
new TWA_SIGNAL flag implies signal_wake_up().  However, it needs to
avoid the race with recalc_sigpending(), so the patch also adds the
new JOBCTL_TASK_WORK bit included in JOBCTL_PENDING_MASK.

TODO: once this patch is merged we need to change all current users
of task_work_add(notify = true) to use TWA_RESUME.

Cc: stable@vger.kernel.org # v5.7
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched/jobctl.h |  4 +++-
 include/linux/task_work.h    |  5 ++++-
 kernel/signal.c              | 10 +++++++---
 kernel/task_work.c           | 16 ++++++++++++++--
 4 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..d2b4204ba4d3 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,7 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,9 +29,10 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index bd9a6a91c097..0fb93aafa478 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -13,7 +13,10 @@ init_task_work(struct callback_head *twork, task_work_func_t func)
 	twork->func = func;
 }
 
-int task_work_add(struct task_struct *task, struct callback_head *twork, bool);
+#define TWA_RESUME	1
+#define TWA_SIGNAL	2
+int task_work_add(struct task_struct *task, struct callback_head *twork, int);
+
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 5ca48cc5da76..ee22ec78fd6d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2529,9 +2529,6 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
-	if (unlikely(current->task_works))
-		task_work_run();
-
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2544,6 +2541,13 @@ bool get_signal(struct ksignal *ksig)
 
 relock:
 	spin_lock_irq(&sighand->siglock);
+	current->jobctl &= ~JOBCTL_TASK_WORK;
+	if (unlikely(current->task_works)) {
+		spin_unlock_irq(&sighand->siglock);
+		task_work_run();
+		goto relock;
+	}
+
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
 	 * we should notify the parent, prepare_signal(SIGCONT) encodes
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 825f28259a19..5c0848ca1287 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -25,9 +25,10 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * 0 if succeeds or -ESRCH.
  */
 int
-task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 {
 	struct callback_head *head;
+	unsigned long flags;
 
 	do {
 		head = READ_ONCE(task->task_works);
@@ -36,8 +37,19 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 		work->next = head;
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
-	if (notify)
+	switch (notify) {
+	case TWA_RESUME:
 		set_notify_resume(task);
+		break;
+	case TWA_SIGNAL:
+		if (lock_task_sighand(task, &flags)) {
+			task->jobctl |= JOBCTL_TASK_WORK;
+			signal_wake_up(task, 0);
+			unlock_task_sighand(task, &flags);
+		}
+		break;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From c463bb2a8f8d7d97aa414bf7714fc77e9d3b10df Mon Sep 17 00:00:00 2001
From: Merlijn Wajer <merlijn@wizzup.org>
Date: Tue, 30 Jun 2020 11:47:04 -0700
Subject: Input: add `SW_MACHINE_COVER`

This event code represents the state of a removable cover of a device.
Value 0 means that the cover is open or removed, value 1 means that the
cover is closed.

Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Merlijn Wajer <merlijn@wizzup.org>
Link: https://lore.kernel.org/r/20200612125402.18393-2-merlijn@wizzup.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/mod_devicetable.h        | 2 +-
 include/uapi/linux/input-event-codes.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index e3596db077dc..04a19e30b168 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -318,7 +318,7 @@ struct pcmcia_device_id {
 #define INPUT_DEVICE_ID_LED_MAX		0x0f
 #define INPUT_DEVICE_ID_SND_MAX		0x07
 #define INPUT_DEVICE_ID_FF_MAX		0x7f
-#define INPUT_DEVICE_ID_SW_MAX		0x0f
+#define INPUT_DEVICE_ID_SW_MAX		0x10
 #define INPUT_DEVICE_ID_PROP_MAX	0x1f
 
 #define INPUT_DEVICE_ID_MATCH_BUS	1
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index b6a835d37826..0c2e27d28e0a 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -888,7 +888,8 @@
 #define SW_LINEIN_INSERT	0x0d  /* set = inserted */
 #define SW_MUTE_DEVICE		0x0e  /* set = device disabled */
 #define SW_PEN_INSERTED		0x0f  /* set = pen inserted */
-#define SW_MAX			0x0f
+#define SW_MACHINE_COVER	0x10  /* set = cover closed */
+#define SW_MAX			0x10
 #define SW_CNT			(SW_MAX+1)
 
 /*
-- 
cgit v1.2.3


From b23d7a5f4a07af02343cdd28fe1f7488bac3afda Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Thu, 25 Jun 2020 15:34:03 +1000
Subject: ring-buffer: speed up buffer resets by avoiding synchronize_rcu for
 each CPU

On a 144 thread system, `perf ftrace` takes about 20 seconds to start
up, due to calling synchronize_rcu() for each CPU.

  cat /proc/108560/stack
    0xc0003e7eb336f470
    __switch_to+0x2e0/0x480
    __wait_rcu_gp+0x20c/0x220
    synchronize_rcu+0x9c/0xc0
    ring_buffer_reset_cpu+0x88/0x2e0
    tracing_reset_online_cpus+0x84/0xe0
    tracing_open+0x1d4/0x1f0

On a system with 10x more threads, it starts to become an annoyance.

Batch these up so we disable all the per-cpu buffers first, then
synchronize_rcu() once, then reset each of the buffers. This brings
the time down to about 0.5s.

Link: https://lkml.kernel.org/r/20200625053403.2386972-1-npiggin@gmail.com

Tested-by: Anton Blanchard <anton@ozlabs.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 85 +++++++++++++++++++++++++++++++++++++--------
 kernel/trace/trace.c        |  4 +--
 3 files changed, 73 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index c76b2f3b3ac4..136ea0997e6d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -143,6 +143,7 @@ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
+void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
 void ring_buffer_reset(struct trace_buffer *buffer);
 
 #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 802bb38d9c81..ed1941304f69 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -270,6 +270,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define for_each_buffer_cpu(buffer, cpu)		\
 	for_each_cpu(cpu, buffer->cpumask)
 
+#define for_each_online_buffer_cpu(buffer, cpu)		\
+	for_each_cpu_and(cpu, buffer->cpumask, cpu_online_mask)
+
 #define TS_SHIFT	27
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
@@ -4790,6 +4793,26 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_head_page_activate(cpu_buffer);
 }
 
+/* Must have disabled the cpu buffer then done a synchronize_rcu */
+static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+		goto out;
+
+	arch_spin_lock(&cpu_buffer->lock);
+
+	rb_reset_cpu(cpu_buffer);
+
+	arch_spin_unlock(&cpu_buffer->lock);
+
+ out:
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
 /**
  * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
  * @buffer: The ring buffer to reset a per cpu buffer of
@@ -4798,7 +4821,6 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
-	unsigned long flags;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
@@ -4809,24 +4831,42 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 	/* Make sure all commits have finished */
 	synchronize_rcu();
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	reset_disabled_cpu_buffer(cpu_buffer);
 
-	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
-		goto out;
+	atomic_dec(&cpu_buffer->record_disabled);
+	atomic_dec(&cpu_buffer->resize_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
-	arch_spin_lock(&cpu_buffer->lock);
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
 
-	rb_reset_cpu(cpu_buffer);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
 
-	arch_spin_unlock(&cpu_buffer->lock);
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
 
- out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	/* Make sure all commits have finished */
+	synchronize_rcu();
 
-	atomic_dec(&cpu_buffer->record_disabled);
-	atomic_dec(&cpu_buffer->resize_disabled);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
-EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
  * ring_buffer_reset - reset a ring buffer
@@ -4834,10 +4874,27 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
  */
 void ring_buffer_reset(struct trace_buffer *buffer)
 {
+	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu;
 
-	for_each_buffer_cpu(buffer, cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 64c5b8146cca..4aab712f9567 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2003,7 +2003,6 @@ static void tracing_reset_cpu(struct array_buffer *buf, int cpu)
 void tracing_reset_online_cpus(struct array_buffer *buf)
 {
 	struct trace_buffer *buffer = buf->buffer;
-	int cpu;
 
 	if (!buffer)
 		return;
@@ -2015,8 +2014,7 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 
 	buf->time_start = buffer_ftrace_now(buf, buf->cpu);
 
-	for_each_online_cpu(cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	ring_buffer_reset_online_cpus(buffer);
 
 	ring_buffer_record_enable(buffer);
 }
-- 
cgit v1.2.3


From 5396956cc7c6874180c9bfc1ceceb02b739a6a87 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 22 Jun 2020 19:12:48 +0300
Subject: PCI: Make pcie_find_root_port() work for Root Ports

Commit 6ae72bfa656e ("PCI: Unify pcie_find_root_port() and
pci_find_pcie_root_port()") broke acpi_pci_bridge_d3() because calling
pcie_find_root_port() on a Root Port returned NULL when it should return
the Root Port, which in turn broke power management of PCIe hierarchies.

Rework pcie_find_root_port() so it returns its argument when it is already
a Root Port.

[bhelgaas: test device only once, test for PCIe]
Fixes: 6ae72bfa656e ("PCI: Unify pcie_find_root_port() and pci_find_pcie_root_port()")
Link: https://lore.kernel.org/r/20200622161248.51099-1-mika.westerberg@linux.intel.com
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index c79d83304e52..34c1c4f45288 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2169,12 +2169,11 @@ static inline int pci_pcie_type(const struct pci_dev *dev)
  */
 static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
 {
-	struct pci_dev *bridge = pci_upstream_bridge(dev);
-
-	while (bridge) {
-		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
-			return bridge;
-		bridge = pci_upstream_bridge(bridge);
+	while (dev) {
+		if (pci_is_pcie(dev) &&
+		    pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			return dev;
+		dev = pci_upstream_bridge(dev);
 	}
 
 	return NULL;
-- 
cgit v1.2.3


From ab81e23cf77905896a5e51422eb58e8763507b85 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 29 Jun 2020 14:05:07 +0300
Subject: net: qed: correct existing SPDX tags

QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Correct already existing but wrong SPDX tags to match the actual
license.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/Makefile       | 3 ++-
 drivers/net/ethernet/qlogic/qed/qed_debug.c    | 2 +-
 drivers/net/ethernet/qlogic/qed/qed_debug.h    | 2 +-
 drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c  | 3 ++-
 drivers/net/ethernet/qlogic/qed/qed_selftest.h | 3 ++-
 include/linux/qed/fcoe_common.h                | 2 +-
 include/linux/qed/qed_fcoe_if.h                | 3 ++-
 7 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index a0acb94d65f0..cee566faba2f 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -1,4 +1,5 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+
 obj-$(CONFIG_QED) := qed.o
 
 qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 81e8fbe4a05b..8b14e6852daf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
  */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.h b/drivers/net/ethernet/qlogic/qed/qed_debug.h
index edf99d296bd1..685696878ec2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
  */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index 6c16158d8090..56b7567d7a60 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -1,4 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <linux/bug.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.h b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
index ad00d082fec8..d8121fd39bc1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
@@ -1,4 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+
 #ifndef _QED_SELFTEST_API_H
 #define _QED_SELFTEST_API_H
 #include <linux/types.h>
diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h
index 98cfc195abe2..a669d7d84284 100644
--- a/include/linux/qed/fcoe_common.h
+++ b/include/linux/qed/fcoe_common.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
  */
diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h
index 46082480a2c3..65d0317ef67e 100644
--- a/include/linux/qed/qed_fcoe_if.h
+++ b/include/linux/qed/qed_fcoe_if.h
@@ -1,4 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+
 #ifndef _QED_FCOE_IF_H
 #define _QED_FCOE_IF_H
 #include <linux/types.h>
-- 
cgit v1.2.3


From 1f4d4ed6acc5b74974fa038e5e9d2e19f3b532f3 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 29 Jun 2020 14:05:08 +0300
Subject: net: qed: convert to SPDX License Identifiers

QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Remove all the boilerplates in the existing code and replace it with the
correct SPDX tag.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h              | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_cxt.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_cxt.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c         | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_dcbx.h         | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_dev.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_dev_api.h      | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_fcoe.c         | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_fcoe.h         | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_hsi.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_hw.c           | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_hw.h           | 29 +--------------------
 .../net/ethernet/qlogic/qed/qed_init_fw_funcs.c    | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_init_ops.c     | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_init_ops.h     | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_int.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_int.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_iscsi.c        | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_iscsi.h        | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c        | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_iwarp.h        | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_l2.c           | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_l2.h           | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_ll2.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_ll2.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_main.c         | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_mcp.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_mcp.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_ooo.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_ooo.h          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_ptp.c          | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_rdma.c         | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_rdma.h         | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_reg_addr.h     | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_roce.c         | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_roce.h         | 30 ++--------------------
 drivers/net/ethernet/qlogic/qed/qed_selftest.c     | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_sp.h           | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_sp_commands.c  | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_spq.c          | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_sriov.c        | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_sriov.h        | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_vf.c           | 29 +--------------------
 drivers/net/ethernet/qlogic/qed/qed_vf.h           | 29 +--------------------
 include/linux/qed/common_hsi.h                     | 29 +--------------------
 include/linux/qed/eth_common.h                     | 29 +--------------------
 include/linux/qed/iscsi_common.h                   | 29 +--------------------
 include/linux/qed/iwarp_common.h                   | 29 +--------------------
 include/linux/qed/qed_chain.h                      | 29 +--------------------
 include/linux/qed/qed_eth_if.h                     | 29 +--------------------
 include/linux/qed/qed_if.h                         | 29 +--------------------
 include/linux/qed/qed_iov_if.h                     | 29 +--------------------
 include/linux/qed/qed_iscsi_if.h                   | 29 +--------------------
 include/linux/qed/qed_ll2_if.h                     | 29 +--------------------
 include/linux/qed/qed_rdma_if.h                    | 30 ++--------------------
 include/linux/qed/qede_rdma.h                      | 30 ++--------------------
 include/linux/qed/rdma_common.h                    | 29 +--------------------
 include/linux/qed/roce_common.h                    | 29 +--------------------
 include/linux/qed/storage_common.h                 | 29 +--------------------
 include/linux/qed/tcp_common.h                     | 29 +--------------------
 60 files changed, 70 insertions(+), 1680 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index a49743d56b9c..52130dcbfe4c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 08ba9d54ab63..3985dd746ca2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index ce08ae8d8498..05b28919653a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_CXT_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 5c6a276f69ac..a72523298307 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 01f253ea4b22..537d60de4e2b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_DCBX_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 3aa51374e727..fa7c10e8aa7a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index eb4808b3bf67..1f2122c699cc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_DEV_API_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index 4c7fa391fd33..91d6cdf4abe8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
index 027a76ac839a..bf324736c7cb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_FCOE_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index f00460d00cab..ebbca7d999a4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_HSI_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 5fa251489536..bdbb8fa8d399 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index f5b109b04b66..68f44b747565 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_HW_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 2f1049b0b93a..72ff2e5c5f24 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 5a6e4ac4fef4..74c425640d67 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
index e9e8ade50ed3..cf33c41e0952 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_INIT_OPS_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index b7b974f0ef21..be336d47c934 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index e09db3386367..6fca82f6c7fa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_INT_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 7245a615517a..164b4d953b67 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
index 225c75b02a06..8b6518a31b7e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_ISCSI_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 5409a2da6106..7fac39744275 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1,34 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index c1b2057d23b8..83ca05cd74d7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef _QED_IWARP_H
 #define _QED_IWARP_H
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 29810a1aa210..750098e60c64 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index 7127d5aaac42..dce39f5a87ca 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef _QED_L2_H
 #define _QED_L2_H
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 4afd8572ada6..47da6d4e226c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 288642d526b7..c0d13bd6c3a6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_LL2_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 11367a248d55..d00335cc145b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/stddef.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 9624616806e7..c17b140aa7ae 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 5750b4c5ef63..351a13215ddd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_MCP_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index ffac4ac87394..d01f91f7f661 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index 49c4e75b15b1..2731c392a3f4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_OOO_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index 3e613058e225..f10ddf9d1704 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -1,34 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #include <linux/types.h>
 #include "qed.h"
 #include "qed_dev_api.h"
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 19c0c8864da1..9a3541f159dc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1,34 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index 1e69d5bb0a70..a20397a395cf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef _QED_RDMA_H
 #define _QED_RDMA_H
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index 3dcb6ff58e73..bdfd90748042 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef REG_ADDR_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 7271dd7166e5..1e03d66e33d1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -1,34 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index f801f39fde61..9178904bf0e9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef _QED_ROCE_H
 #define _QED_ROCE_H
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.c b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
index cf1d4476f9d8..d24ee1ea8d3c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2016  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/crc32.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index b7b4fbbbccfe..4f646e101074 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_SP_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 900bc603e30a..23d630b37199 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 790c28d696a0..18c59981cab7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 20679fd4204b..6d3c6d4f6308 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index 368e88565783..43dfaf410332 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_SRIOV_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index adc2c8f3d48e..c800f8812492 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/crc32.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 033409db86ae..60d2bb64e65f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_VF_H
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 2c4737e6694a..294d01eae5cb 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2016  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _COMMON_HSI_H
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index 95f5fd615852..a9566ef3c2ce 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __ETH_COMMON__
diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h
index 2f0a771a9176..7ca89fb9247f 100644
--- a/include/linux/qed/iscsi_common.h
+++ b/include/linux/qed/iscsi_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __ISCSI_COMMON__
diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h
index c6cfd39cd910..23583e644257 100644
--- a/include/linux/qed/iwarp_common.h
+++ b/include/linux/qed/iwarp_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __IWARP_COMMON__
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 6d15040c642c..e6e25197f7cb 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_CHAIN_H
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index a1310482c4ed..7803dedbcb52 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_ETH_IF_H
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 8cb76405cbce..4a36608ff3a8 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_IF_H
diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h
index ac2e6a3199a3..c2ca8196def9 100644
--- a/include/linux/qed/qed_iov_if.h
+++ b/include/linux/qed/qed_iov_if.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_IOV_IF_H
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index d0df1bec5357..89912c6c440c 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_ISCSI_IF_H
diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index 1313c34d9a68..79cac277e38b 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef _QED_LL2_IF_H
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 2d3ddd2b85e0..041a5b005a82 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef _QED_RDMA_IF_H
 #define _QED_RDMA_IF_H
 #include <linux/types.h>
diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h
index 5a00c7a473bf..20ed7f2c55bb 100644
--- a/include/linux/qed/qede_rdma.h
+++ b/include/linux/qed/qede_rdma.h
@@ -1,34 +1,8 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qedr NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
+
 #ifndef QEDE_ROCE_H
 #define QEDE_ROCE_H
 
diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h
index 480a57eb36cc..3e3f01136c06 100644
--- a/include/linux/qed/rdma_common.h
+++ b/include/linux/qed/rdma_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __RDMA_COMMON__
diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h
index 473fba76aa77..89065f023813 100644
--- a/include/linux/qed/roce_common.h
+++ b/include/linux/qed/roce_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __ROCE_COMMON__
diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h
index 9a973ffbbff5..34f069c79067 100644
--- a/include/linux/qed/storage_common.h
+++ b/include/linux/qed/storage_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __STORAGE_COMMON__
diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h
index 4a4845193539..925e7cb7a582 100644
--- a/include/linux/qed/tcp_common.h
+++ b/include/linux/qed/tcp_common.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef __TCP_COMMON__
-- 
cgit v1.2.3


From 663eacd899ac131dcfc2279184c1ce3c4fd2815f Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 29 Jun 2020 14:05:09 +0300
Subject: net: qed: update copyright years

Set the actual copyright holder and years in all qed source files.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/Makefile            | 1 +
 drivers/net/ethernet/qlogic/qed/qed.h               | 1 +
 drivers/net/ethernet/qlogic/qed/qed_cxt.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_cxt.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_dcbx.h          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_debug.c         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_debug.h         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_dev.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_dev_api.h       | 1 +
 drivers/net/ethernet/qlogic/qed/qed_fcoe.c          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_fcoe.h          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_hsi.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_hw.c            | 1 +
 drivers/net/ethernet/qlogic/qed/qed_hw.h            | 1 +
 drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 1 +
 drivers/net/ethernet/qlogic/qed/qed_init_ops.c      | 1 +
 drivers/net/ethernet/qlogic/qed/qed_init_ops.h      | 1 +
 drivers/net/ethernet/qlogic/qed/qed_int.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_int.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_iscsi.c         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_iscsi.h         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_iwarp.h         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_l2.c            | 1 +
 drivers/net/ethernet/qlogic/qed/qed_l2.h            | 1 +
 drivers/net/ethernet/qlogic/qed/qed_ll2.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_ll2.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_main.c          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_mcp.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_mcp.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c       | 1 +
 drivers/net/ethernet/qlogic/qed/qed_ooo.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_ooo.h           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_ptp.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_rdma.c          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_rdma.h          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_reg_addr.h      | 1 +
 drivers/net/ethernet/qlogic/qed/qed_roce.c          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_roce.h          | 1 +
 drivers/net/ethernet/qlogic/qed/qed_selftest.c      | 1 +
 drivers/net/ethernet/qlogic/qed/qed_selftest.h      | 1 +
 drivers/net/ethernet/qlogic/qed/qed_sp.h            | 1 +
 drivers/net/ethernet/qlogic/qed/qed_sp_commands.c   | 1 +
 drivers/net/ethernet/qlogic/qed/qed_spq.c           | 1 +
 drivers/net/ethernet/qlogic/qed/qed_sriov.c         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_sriov.h         | 1 +
 drivers/net/ethernet/qlogic/qed/qed_vf.c            | 1 +
 include/linux/qed/common_hsi.h                      | 1 +
 include/linux/qed/eth_common.h                      | 1 +
 include/linux/qed/fcoe_common.h                     | 1 +
 include/linux/qed/iscsi_common.h                    | 1 +
 include/linux/qed/iwarp_common.h                    | 1 +
 include/linux/qed/qed_chain.h                       | 1 +
 include/linux/qed/qed_eth_if.h                      | 1 +
 include/linux/qed/qed_fcoe_if.h                     | 1 +
 include/linux/qed/qed_if.h                          | 1 +
 include/linux/qed/qed_iov_if.h                      | 1 +
 include/linux/qed/qed_iscsi_if.h                    | 1 +
 include/linux/qed/qed_ll2_if.h                      | 1 +
 include/linux/qed/qed_rdma_if.h                     | 1 +
 include/linux/qed/qede_rdma.h                       | 1 +
 include/linux/qed/rdma_common.h                     | 1 +
 include/linux/qed/roce_common.h                     | 1 +
 include/linux/qed/storage_common.h                  | 1 +
 include/linux/qed/tcp_common.h                      | 1 +
 66 files changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index cee566faba2f..4176bbf2a22b 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+# Copyright (c) 2019-2020 Marvell International Ltd.
 
 obj-$(CONFIG_QED) := qed.o
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 52130dcbfe4c..68fe745c9b99 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 3985dd746ca2..e72d25854d79 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 05b28919653a..8b64495f8745 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_CXT_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index a72523298307..9f16a3a66007 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 537d60de4e2b..ba5f3927034c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_DCBX_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 8b14e6852daf..45cbe1c87106 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.h b/drivers/net/ethernet/qlogic/qed/qed_debug.h
index 685696878ec2..e71af82d3200 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_DEBUGFS_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index fa7c10e8aa7a..74142896b707 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index 1f2122c699cc..395d4932c262 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_DEV_API_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index 91d6cdf4abe8..a10e57bba6b9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
index bf324736c7cb..13c5ccfe06e7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_FCOE_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index ebbca7d999a4..d7e70625bdc4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_HSI_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index bdbb8fa8d399..e8c777f30207 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index 68f44b747565..6a61b88b544d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_HW_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 72ff2e5c5f24..1eb48ea80484 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 74c425640d67..736702fb81b5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
index cf33c41e0952..a573c8921982 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_INIT_OPS_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index be336d47c934..297983d66e2f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 6fca82f6c7fa..aea04b121586 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_INT_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 164b4d953b67..f9d9e21cb66b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
index 8b6518a31b7e..d6af7ea19bbb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_ISCSI_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 7fac39744275..b7a0a717ee6d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/if_ether.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index 83ca05cd74d7..c3872cd9457f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_IWARP_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 750098e60c64..03dc804c92a9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index dce39f5a87ca..8eceeebb1a7b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_L2_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 47da6d4e226c..cce6fd27c042 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index c0d13bd6c3a6..8356c7d4a193 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_LL2_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index d00335cc145b..0cd6b8bf023a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/stddef.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index c17b140aa7ae..25433d162a54 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 351a13215ddd..d77b4c262cff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_MCP_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index 56b7567d7a60..1dd01e0373ab 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/* Copyright (c) 2019-2020 Marvell International Ltd. */
 
 #include <linux/types.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index d01f91f7f661..88353aa404dc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index 2731c392a3f4..3a7e1b59d6fc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_OOO_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index f10ddf9d1704..3bd2f8c961c9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 9a3541f159dc..59d916693654 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index a20397a395cf..fba43adbb68e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_RDMA_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index bdfd90748042..9db22be42476 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef REG_ADDR_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 1e03d66e33d1..d5db07db65b1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 9178904bf0e9..3a4a2d72a826 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_ROCE_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.c b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
index d24ee1ea8d3c..6e70781ab87c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2016  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/crc32.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.h b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
index d8121fd39bc1..e27dd9a4547e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright (c) 2019-2020 Marvell International Ltd. */
 
 #ifndef _QED_SELFTEST_API_H
 #define _QED_SELFTEST_API_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 4f646e101074..35539e951bee 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_SP_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 23d630b37199..745d76d13732 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 18c59981cab7..ee89a8f4f585 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 6d3c6d4f6308..fcf4d82da161 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index 43dfaf410332..552892c45670 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_SRIOV_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index c800f8812492..72a38d53d33f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #include <linux/crc32.h>
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 294d01eae5cb..977807e1be53 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2016  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _COMMON_HSI_H
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index a9566ef3c2ce..cd1207ad4ada 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __ETH_COMMON__
diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h
index a669d7d84284..68eda1c21cde 100644
--- a/include/linux/qed/fcoe_common.h
+++ b/include/linux/qed/fcoe_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __FCOE_COMMON__
diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h
index 7ca89fb9247f..157019f716f1 100644
--- a/include/linux/qed/iscsi_common.h
+++ b/include/linux/qed/iscsi_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __ISCSI_COMMON__
diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h
index 23583e644257..14f9e4c0ddd9 100644
--- a/include/linux/qed/iwarp_common.h
+++ b/include/linux/qed/iwarp_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __IWARP_COMMON__
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index e6e25197f7cb..92cdc79e5019 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_CHAIN_H
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 7803dedbcb52..812a4d751163 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_ETH_IF_H
diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h
index 65d0317ef67e..16752eca5cbd 100644
--- a/include/linux/qed/qed_fcoe_if.h
+++ b/include/linux/qed/qed_fcoe_if.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright (c) 2019-2020 Marvell International Ltd. */
 
 #ifndef _QED_FCOE_IF_H
 #define _QED_FCOE_IF_H
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 4a36608ff3a8..5ca081cd2ed9 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_IF_H
diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h
index c2ca8196def9..8e31a28e51b9 100644
--- a/include/linux/qed/qed_iov_if.h
+++ b/include/linux/qed/qed_iov_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_IOV_IF_H
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index 89912c6c440c..04180d9af560 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_ISCSI_IF_H
diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index 79cac277e38b..2f64ed79cee9 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_LL2_IF_H
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 041a5b005a82..f464d85e88a4 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef _QED_RDMA_IF_H
diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h
index 20ed7f2c55bb..072da2f6da37 100644
--- a/include/linux/qed/qede_rdma.h
+++ b/include/linux/qed/qede_rdma.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qedr NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef QEDE_ROCE_H
diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h
index 3e3f01136c06..bab078b25834 100644
--- a/include/linux/qed/rdma_common.h
+++ b/include/linux/qed/rdma_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __RDMA_COMMON__
diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h
index 89065f023813..ccddd7a96b67 100644
--- a/include/linux/qed/roce_common.h
+++ b/include/linux/qed/roce_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __ROCE_COMMON__
diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h
index 34f069c79067..91896e8793bf 100644
--- a/include/linux/qed/storage_common.h
+++ b/include/linux/qed/storage_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __STORAGE_COMMON__
diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h
index 925e7cb7a582..2b2c87d10e0a 100644
--- a/include/linux/qed/tcp_common.h
+++ b/include/linux/qed/tcp_common.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015-2017  QLogic Corporation
+ * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
 #ifndef __TCP_COMMON__
-- 
cgit v1.2.3


From 8b11c20a658de159fcf18ebce4f2acfdf747ff25 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 29 Jun 2020 14:03:41 +0200
Subject: phy: un-inline devm_mdiobus_register()

Functions should only be static inline if they're very short. This
devres helper is already over 10 lines and it will grow soon as we'll
be improving upon its approach. Pull it into mdio_devres.c.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Makefile      |  2 +-
 drivers/net/phy/mdio_devres.c | 18 ++++++++++++++++++
 include/linux/phy.h           | 15 ++-------------
 3 files changed, 21 insertions(+), 14 deletions(-)
 create mode 100644 drivers/net/phy/mdio_devres.c

(limited to 'include/linux')

diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index dc9e53b511d6..896afdcac437 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -3,7 +3,7 @@
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
 				   linkmode.o
-mdio-bus-y			+= mdio_bus.o mdio_device.o
+mdio-bus-y			+= mdio_bus.o mdio_device.o mdio_devres.o
 
 ifdef CONFIG_MDIO_DEVICE
 obj-y				+= mdio-boardinfo.o
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
new file mode 100644
index 000000000000..f0b4b6cfe5e3
--- /dev/null
+++ b/drivers/net/phy/mdio_devres.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/phy.h>
+
+int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner)
+{
+	int ret;
+
+	if (!bus->is_managed)
+		return -EPERM;
+
+	ret = __mdiobus_register(bus, owner);
+	if (!ret)
+		bus->is_managed_registered = 1;
+
+	return ret;
+}
+EXPORT_SYMBOL(__devm_mdiobus_register);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ecc7640705b9..7c75e1c90141 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -322,20 +322,9 @@ static inline struct mii_bus *mdiobus_alloc(void)
 }
 
 int __mdiobus_register(struct mii_bus *bus, struct module *owner);
+int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner);
 #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE)
-static inline int devm_mdiobus_register(struct mii_bus *bus)
-{
-	int ret;
-
-	if (!bus->is_managed)
-		return -EPERM;
-
-	ret = mdiobus_register(bus);
-	if (!ret)
-		bus->is_managed_registered = 1;
-
-	return ret;
-}
+#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE)
 
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
-- 
cgit v1.2.3


From ac3a68d56651c3dad2c12c7afce065fe15267f44 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 29 Jun 2020 14:03:43 +0200
Subject: net: phy: don't abuse devres in devm_mdiobus_register()

We currently have two managed helpers for mdiobus - devm_mdiobus_alloc()
and devm_mdiobus_register(). The idea behind devres is that the release
callback releases whatever resource the devm function allocates. In the
mdiobus case however there's no devres associated with the device by
devm_mdiobus_register(). Instead the release callback for
devm_mdiobus_alloc(): _devm_mdiobus_free() unregisters the device if
it is marked as managed.

This all seems wrong. The managed structure shouldn't need to know or
care about whether it's managed or not - and this is the case now for
struct mii_bus. The devres wrapper should be opaque to the managed
resource.

This changeset makes devm_mdiobus_alloc() and devm_mdiobus_register()
conform to common devres standards: devm_mdiobus_alloc() allocates a
devres structure and registers a callback that will call mdiobus_free().
__devm_mdiobus_register() allocated another devres and registers a
callback that will unregister the bus.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/driver-api/driver-model/devres.rst |  1 -
 drivers/net/ethernet/realtek/r8169_main.c        |  2 +-
 drivers/net/phy/mdio_bus.c                       | 73 ---------------------
 drivers/net/phy/mdio_devres.c                    | 83 ++++++++++++++++++++++--
 include/linux/phy.h                              | 10 ++-
 5 files changed, 82 insertions(+), 87 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 5463fc8a60c1..e0333d66a7f4 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -342,7 +342,6 @@ LED
 MDIO
   devm_mdiobus_alloc()
   devm_mdiobus_alloc_size()
-  devm_mdiobus_free()
   devm_mdiobus_register()
 
 MEM
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 07a33af1f64e..745e1739e9c8 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5012,7 +5012,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
 
-	ret = devm_mdiobus_register(new_bus);
+	ret = devm_mdiobus_register(&pdev->dev, new_bus);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 134f82d72da8..46b33701ad4b 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -165,79 +165,6 @@ struct mii_bus *mdiobus_alloc_size(size_t size)
 }
 EXPORT_SYMBOL(mdiobus_alloc_size);
 
-static void _devm_mdiobus_free(struct device *dev, void *res)
-{
-	struct mii_bus *bus = *(struct mii_bus **)res;
-
-	if (bus->is_managed_registered && bus->state == MDIOBUS_REGISTERED)
-		mdiobus_unregister(bus);
-
-	mdiobus_free(bus);
-}
-
-static int devm_mdiobus_match(struct device *dev, void *res, void *data)
-{
-	struct mii_bus **r = res;
-
-	if (WARN_ON(!r || !*r))
-		return 0;
-
-	return *r == data;
-}
-
-/**
- * devm_mdiobus_alloc_size - Resource-managed mdiobus_alloc_size()
- * @dev:		Device to allocate mii_bus for
- * @sizeof_priv:	Space to allocate for private structure.
- *
- * Managed mdiobus_alloc_size. mii_bus allocated with this function is
- * automatically freed on driver detach.
- *
- * If an mii_bus allocated with this function needs to be freed separately,
- * devm_mdiobus_free() must be used.
- *
- * RETURNS:
- * Pointer to allocated mii_bus on success, NULL on failure.
- */
-struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv)
-{
-	struct mii_bus **ptr, *bus;
-
-	ptr = devres_alloc(_devm_mdiobus_free, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
-		return NULL;
-
-	/* use raw alloc_dr for kmalloc caller tracing */
-	bus = mdiobus_alloc_size(sizeof_priv);
-	if (bus) {
-		*ptr = bus;
-		devres_add(dev, ptr);
-		bus->is_managed = 1;
-	} else {
-		devres_free(ptr);
-	}
-
-	return bus;
-}
-EXPORT_SYMBOL_GPL(devm_mdiobus_alloc_size);
-
-/**
- * devm_mdiobus_free - Resource-managed mdiobus_free()
- * @dev:		Device this mii_bus belongs to
- * @bus:		the mii_bus associated with the device
- *
- * Free mii_bus allocated with devm_mdiobus_alloc_size().
- */
-void devm_mdiobus_free(struct device *dev, struct mii_bus *bus)
-{
-	int rc;
-
-	rc = devres_release(dev, _devm_mdiobus_free,
-			    devm_mdiobus_match, bus);
-	WARN_ON(rc);
-}
-EXPORT_SYMBOL_GPL(devm_mdiobus_free);
-
 /**
  * mdiobus_release - mii_bus device release callback
  * @d: the target struct device that contains the mii_bus
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
index 3ee887733d4a..0b9bd9a61378 100644
--- a/drivers/net/phy/mdio_devres.c
+++ b/drivers/net/phy/mdio_devres.c
@@ -1,25 +1,96 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/device.h>
 #include <linux/phy.h>
+#include <linux/stddef.h>
+
+struct mdiobus_devres {
+	struct mii_bus *mii;
+};
+
+static void devm_mdiobus_free(struct device *dev, void *this)
+{
+	struct mdiobus_devres *dr = this;
+
+	mdiobus_free(dr->mii);
+}
+
+/**
+ * devm_mdiobus_alloc_size - Resource-managed mdiobus_alloc_size()
+ * @dev:		Device to allocate mii_bus for
+ * @sizeof_priv:	Space to allocate for private structure
+ *
+ * Managed mdiobus_alloc_size. mii_bus allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated mii_bus on success, NULL on out-of-memory error.
+ */
+struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv)
+{
+	struct mdiobus_devres *dr;
+
+	dr = devres_alloc(devm_mdiobus_free, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return NULL;
+
+	dr->mii = mdiobus_alloc_size(sizeof_priv);
+	if (!dr->mii) {
+		devres_free(dr);
+		return NULL;
+	}
+
+	devres_add(dev, dr);
+	return dr->mii;
+}
+EXPORT_SYMBOL(devm_mdiobus_alloc_size);
+
+static void devm_mdiobus_unregister(struct device *dev, void *this)
+{
+	struct mdiobus_devres *dr = this;
+
+	mdiobus_unregister(dr->mii);
+}
+
+static int mdiobus_devres_match(struct device *dev,
+				void *this, void *match_data)
+{
+	struct mdiobus_devres *res = this;
+	struct mii_bus *mii = match_data;
+
+	return mii == res->mii;
+}
 
 /**
  * __devm_mdiobus_register - Resource-managed variant of mdiobus_register()
+ * @dev:	Device to register mii_bus for
  * @bus:	MII bus structure to register
  * @owner:	Owning module
  *
  * Returns 0 on success, negative error number on failure.
  */
-int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner)
+int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus,
+			    struct module *owner)
 {
+	struct mdiobus_devres *dr;
 	int ret;
 
-	if (!bus->is_managed)
-		return -EPERM;
+	if (WARN_ON(!devres_find(dev, devm_mdiobus_free,
+				 mdiobus_devres_match, bus)))
+		return -EINVAL;
+
+	dr = devres_alloc(devm_mdiobus_unregister, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
 
 	ret = __mdiobus_register(bus, owner);
-	if (!ret)
-		bus->is_managed_registered = 1;
+	if (ret) {
+		devres_free(dr);
+		return ret;
+	}
 
-	return ret;
+	dr->mii = bus;
+	devres_add(dev, dr);
+	return 0;
 }
 EXPORT_SYMBOL(__devm_mdiobus_register);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7c75e1c90141..101a48fa6750 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -261,9 +261,6 @@ struct mii_bus {
 	int (*reset)(struct mii_bus *bus);
 	struct mdio_bus_stats stats[PHY_MAX_ADDR];
 
-	unsigned int is_managed:1;	/* is device-managed */
-	unsigned int is_managed_registered:1;
-
 	/*
 	 * A lock to ensure that only one thing can read/write
 	 * the MDIO bus at a time
@@ -322,9 +319,11 @@ static inline struct mii_bus *mdiobus_alloc(void)
 }
 
 int __mdiobus_register(struct mii_bus *bus, struct module *owner);
-int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner);
+int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus,
+			    struct module *owner);
 #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE)
-#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE)
+#define devm_mdiobus_register(dev, bus) \
+		__devm_mdiobus_register(dev, bus, THIS_MODULE)
 
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
@@ -335,7 +334,6 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev)
 }
 
 struct mii_bus *mdio_find_bus(const char *mdio_name);
-void devm_mdiobus_free(struct device *dev, struct mii_bus *bus);
 struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 
 #define PHY_INTERRUPT_DISABLED	false
-- 
cgit v1.2.3


From a0bd96f5aed2108505386733abe76f37362c2f50 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 29 Jun 2020 14:03:44 +0200
Subject: of: mdio: remove the 'extern' keyword from function declarations

The 'extern' keyword in headers doesn't have any benefit. Remove them
all from the of_mdio.h header.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/of_mdio.h | 37 ++++++++++++++++++-------------------
 1 file changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 0f61a4ac6bcf..ba8e157f24ad 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -12,27 +12,26 @@
 #include <linux/of.h>
 
 #if IS_ENABLED(CONFIG_OF_MDIO)
-extern bool of_mdiobus_child_is_phy(struct device_node *child);
-extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
-extern struct phy_device *of_phy_find_device(struct device_node *phy_np);
-extern struct phy_device *of_phy_connect(struct net_device *dev,
-					 struct device_node *phy_np,
-					 void (*hndlr)(struct net_device *),
-					 u32 flags, phy_interface_t iface);
-extern struct phy_device *
+bool of_mdiobus_child_is_phy(struct device_node *child);
+int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
+struct phy_device *of_phy_find_device(struct device_node *phy_np);
+struct phy_device *
+of_phy_connect(struct net_device *dev, struct device_node *phy_np,
+	       void (*hndlr)(struct net_device *), u32 flags,
+	       phy_interface_t iface);
+struct phy_device *
 of_phy_get_and_connect(struct net_device *dev, struct device_node *np,
 		       void (*hndlr)(struct net_device *));
-struct phy_device *of_phy_attach(struct net_device *dev,
-				 struct device_node *phy_np, u32 flags,
-				 phy_interface_t iface);
-
-extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
-extern int of_phy_register_fixed_link(struct device_node *np);
-extern void of_phy_deregister_fixed_link(struct device_node *np);
-extern bool of_phy_is_fixed_link(struct device_node *np);
-extern int of_mdiobus_phy_device_register(struct mii_bus *mdio,
-				     struct phy_device *phy,
-				     struct device_node *child, u32 addr);
+struct phy_device *
+of_phy_attach(struct net_device *dev, struct device_node *phy_np,
+	      u32 flags, phy_interface_t iface);
+
+struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
+int of_phy_register_fixed_link(struct device_node *np);
+void of_phy_deregister_fixed_link(struct device_node *np);
+bool of_phy_is_fixed_link(struct device_node *np);
+int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy,
+				   struct device_node *child, u32 addr);
 
 static inline int of_mdio_parse_addr(struct device *dev,
 				     const struct device_node *np)
-- 
cgit v1.2.3


From 14eeb6e086d6b9004c600e5f0f62bacb458ecfba Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 29 Jun 2020 14:03:45 +0200
Subject: of: mdio: provide devm_of_mdiobus_register()

Implement a managed variant of of_mdiobus_register(). We need to make
mdio_devres into its own module because otherwise we'd hit circular
sumbol dependencies between phylib and of_mdio.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/driver-api/driver-model/devres.rst |  1 +
 drivers/net/phy/Makefile                         |  4 ++-
 drivers/net/phy/mdio_devres.c                    | 37 ++++++++++++++++++++++++
 include/linux/of_mdio.h                          |  3 ++
 4 files changed, 44 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index e0333d66a7f4..eaaaafc21134 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -343,6 +343,7 @@ MDIO
   devm_mdiobus_alloc()
   devm_mdiobus_alloc_size()
   devm_mdiobus_register()
+  devm_of_mdiobus_register()
 
 MEM
   devm_free_pages()
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 896afdcac437..c9a9adf194d5 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -3,7 +3,8 @@
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
 				   linkmode.o
-mdio-bus-y			+= mdio_bus.o mdio_device.o mdio_devres.o
+mdio-bus-y			+= mdio_bus.o mdio_device.o
+mdio-devres-y			+= mdio_devres.o
 
 ifdef CONFIG_MDIO_DEVICE
 obj-y				+= mdio-boardinfo.o
@@ -17,6 +18,7 @@ libphy-y			+= $(mdio-bus-y)
 else
 obj-$(CONFIG_MDIO_DEVICE)	+= mdio-bus.o
 endif
+obj-$(CONFIG_MDIO_DEVICE)	+= mdio-devres.o
 libphy-$(CONFIG_SWPHY)		+= swphy.o
 libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
 
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
index 0b9bd9a61378..b560e99695df 100644
--- a/drivers/net/phy/mdio_devres.c
+++ b/drivers/net/phy/mdio_devres.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <linux/device.h>
+#include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/stddef.h>
 
@@ -94,3 +95,39 @@ int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus,
 	return 0;
 }
 EXPORT_SYMBOL(__devm_mdiobus_register);
+
+#if IS_ENABLED(CONFIG_OF_MDIO)
+/**
+ * devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register()
+ * @dev:	Device to register mii_bus for
+ * @mdio:	MII bus structure to register
+ * @np:		Device node to parse
+ */
+int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
+			     struct device_node *np)
+{
+	struct mdiobus_devres *dr;
+	int ret;
+
+	if (WARN_ON(!devres_find(dev, devm_mdiobus_free,
+				 mdiobus_devres_match, mdio)))
+		return -EINVAL;
+
+	dr = devres_alloc(devm_mdiobus_unregister, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	ret = of_mdiobus_register(mdio, np);
+	if (ret) {
+		devres_free(dr);
+		return ret;
+	}
+
+	dr->mii = mdio;
+	devres_add(dev, dr);
+	return 0;
+}
+EXPORT_SYMBOL(devm_of_mdiobus_register);
+#endif /* CONFIG_OF_MDIO */
+
+MODULE_LICENSE("GPL");
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index ba8e157f24ad..1efb88d9f892 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -8,12 +8,15 @@
 #ifndef __LINUX_OF_MDIO_H
 #define __LINUX_OF_MDIO_H
 
+#include <linux/device.h>
 #include <linux/phy.h>
 #include <linux/of.h>
 
 #if IS_ENABLED(CONFIG_OF_MDIO)
 bool of_mdiobus_child_is_phy(struct device_node *child);
 int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
+int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
+			     struct device_node *np);
 struct phy_device *of_phy_find_device(struct device_node *phy_np);
 struct phy_device *
 of_phy_connect(struct net_device *dev, struct device_node *phy_np,
-- 
cgit v1.2.3


From 4ec0a44ba8d797876ff416fc0317a0169483d240 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 1 Jul 2020 10:42:31 +0300
Subject: of_graph: add of_graph_is_present()

In some cases it's very useful to silently check whether port node exists
at all in a device-tree before proceeding with parsing the graph. The DRM
bridges code is one example of such case where absence of a graph in a
device-tree is a legit condition.

This patch adds of_graph_is_present() which returns true if given
device-tree node contains OF graph port.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200701074232.13632-2-digetx@gmail.com
---
 drivers/of/property.c    | 23 +++++++++++++++++++++++
 include/linux/of_graph.h |  6 ++++++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/property.c b/drivers/of/property.c
index 1f2086f4e7ce..d3f9fb98e882 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -29,6 +29,29 @@
 
 #include "of_private.h"
 
+/**
+ * of_graph_is_present() - check graph's presence
+ * @node: pointer to device_node containing graph port
+ *
+ * Return: True if @node has a port or ports (with a port) sub-node,
+ * false otherwise.
+ */
+bool of_graph_is_present(const struct device_node *node)
+{
+	struct device_node *ports, *port;
+
+	ports = of_get_child_by_name(node, "ports");
+	if (ports)
+		node = ports;
+
+	port = of_get_child_by_name(node, "port");
+	of_node_put(ports);
+	of_node_put(port);
+
+	return !!port;
+}
+EXPORT_SYMBOL(of_graph_is_present);
+
 /**
  * of_property_count_elems_of_size - Count the number of elements in a property
  *
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
index 01038a6aade0..4d7756087b6b 100644
--- a/include/linux/of_graph.h
+++ b/include/linux/of_graph.h
@@ -38,6 +38,7 @@ struct of_endpoint {
 	     child = of_graph_get_next_endpoint(parent, child))
 
 #ifdef CONFIG_OF
+bool of_graph_is_present(const struct device_node *node);
 int of_graph_parse_endpoint(const struct device_node *node,
 				struct of_endpoint *endpoint);
 int of_graph_get_endpoint_count(const struct device_node *np);
@@ -56,6 +57,11 @@ struct device_node *of_graph_get_remote_node(const struct device_node *node,
 					     u32 port, u32 endpoint);
 #else
 
+static inline bool of_graph_is_present(const struct device_node *node)
+{
+	return false;
+}
+
 static inline int of_graph_parse_endpoint(const struct device_node *node,
 					struct of_endpoint *endpoint)
 {
-- 
cgit v1.2.3


From e1915eec54a6b4902664eaf6fb7a20de5624c4dd Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 26 Jun 2020 22:37:41 +0200
Subject: backlight: sky81452: Convert to GPIO descriptors

The SKY81452 backlight driver just obtains a GPIO (named "gpios"
in the device tree) drives it high and leaves it high until the
driver is removed.

Switch to use GPIO descriptors for this, simple and
straight-forward.

Cc: Gyungoh Yoo <jack.yoo@skyworksinc.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/video/backlight/sky81452-backlight.c     | 18 ++++--------------
 include/linux/platform_data/sky81452-backlight.h |  6 ++++--
 2 files changed, 8 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c
index 2355f00f5773..81d2c8f3ca50 100644
--- a/drivers/video/backlight/sky81452-backlight.c
+++ b/drivers/video/backlight/sky81452-backlight.c
@@ -8,12 +8,11 @@
 
 #include <linux/backlight.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/platform_data/sky81452-backlight.h>
@@ -182,7 +181,7 @@ static struct sky81452_bl_platform_data *sky81452_bl_parse_dt(
 	pdata->ignore_pwm = of_property_read_bool(np, "skyworks,ignore-pwm");
 	pdata->dpwm_mode = of_property_read_bool(np, "skyworks,dpwm-mode");
 	pdata->phase_shift = of_property_read_bool(np, "skyworks,phase-shift");
-	pdata->gpio_enable = of_get_gpio(np, 0);
+	pdata->gpiod_enable = devm_gpiod_get_optional(dev, NULL, GPIOD_OUT_HIGH);
 
 	ret = of_property_count_u32_elems(np, "led-sources");
 	if (ret < 0) {
@@ -264,15 +263,6 @@ static int sky81452_bl_probe(struct platform_device *pdev)
 			return PTR_ERR(pdata);
 	}
 
-	if (gpio_is_valid(pdata->gpio_enable)) {
-		ret = devm_gpio_request_one(dev, pdata->gpio_enable,
-					GPIOF_OUT_INIT_HIGH, "sky81452-en");
-		if (ret < 0) {
-			dev_err(dev, "failed to request GPIO. err=%d\n", ret);
-			return ret;
-		}
-	}
-
 	ret = sky81452_bl_init_device(regmap, pdata);
 	if (ret < 0) {
 		dev_err(dev, "failed to initialize. err=%d\n", ret);
@@ -312,8 +302,8 @@ static int sky81452_bl_remove(struct platform_device *pdev)
 	bd->props.brightness = 0;
 	backlight_update_status(bd);
 
-	if (gpio_is_valid(pdata->gpio_enable))
-		gpio_set_value_cansleep(pdata->gpio_enable, 0);
+	if (pdata->gpiod_enable)
+		gpiod_set_value_cansleep(pdata->gpiod_enable, 0);
 
 	return 0;
 }
diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h
index 02653d92d84f..d6f46670d923 100644
--- a/include/linux/platform_data/sky81452-backlight.h
+++ b/include/linux/platform_data/sky81452-backlight.h
@@ -9,11 +9,13 @@
 #ifndef _SKY81452_BACKLIGHT_H
 #define _SKY81452_BACKLIGHT_H
 
+#include <linux/gpio/consumer.h>
+
 /**
  * struct sky81452_platform_data
  * @name:	backlight driver name.
 		If it is not defined, default name is lcd-backlight.
- * @gpio_enable:GPIO number which control EN pin
+ * @gpios_enable:GPIO descriptor which control EN pin
  * @enable:	Enable mask for current sink channel 1, 2, 3, 4, 5 and 6.
  * @ignore_pwm:	true if DPWMI should be ignored.
  * @dpwm_mode:	true is DPWM dimming mode, otherwise Analog dimming mode.
@@ -23,7 +25,7 @@
  */
 struct sky81452_bl_platform_data {
 	const char *name;
-	int gpio_enable;
+	struct gpio_desc *gpiod_enable;
 	unsigned int enable;
 	bool ignore_pwm;
 	bool dpwm_mode;
-- 
cgit v1.2.3


From 08bf73a6f056d84fd52a58c5d165523dd84be535 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 26 Jun 2020 22:37:42 +0200
Subject: backlight: sky81452: Privatize platform data

The only way the platform data for the SKY81452 ever gets populated
is through the device tree.

The MFD device is bothered with this for no reason at all. Just
allocate the platform data in the driver and be happy.

Cc: Gyungoh Yoo <jack.yoo@skyworksinc.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sky81452.c                           |  2 --
 drivers/video/backlight/sky81452-backlight.c     | 34 +++++++++++++++++-----
 include/linux/mfd/sky81452.h                     |  2 --
 include/linux/platform_data/sky81452-backlight.h | 37 ------------------------
 4 files changed, 27 insertions(+), 48 deletions(-)
 delete mode 100644 include/linux/platform_data/sky81452-backlight.h

(limited to 'include/linux')

diff --git a/drivers/mfd/sky81452.c b/drivers/mfd/sky81452.c
index 76eedfae8553..3ad35bf0c015 100644
--- a/drivers/mfd/sky81452.c
+++ b/drivers/mfd/sky81452.c
@@ -47,8 +47,6 @@ static int sky81452_probe(struct i2c_client *client,
 	memset(cells, 0, sizeof(cells));
 	cells[0].name = "sky81452-backlight";
 	cells[0].of_compatible = "skyworks,sky81452-backlight";
-	cells[0].platform_data = pdata->bl_pdata;
-	cells[0].pdata_size = sizeof(*pdata->bl_pdata);
 	cells[1].name = "sky81452-regulator";
 	cells[1].platform_data = pdata->regulator_init_data;
 	cells[1].pdata_size = sizeof(*pdata->regulator_init_data);
diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c
index 81d2c8f3ca50..83ccb3d940fa 100644
--- a/drivers/video/backlight/sky81452-backlight.c
+++ b/drivers/video/backlight/sky81452-backlight.c
@@ -15,7 +15,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/platform_data/sky81452-backlight.h>
 #include <linux/slab.h>
 
 /* registers */
@@ -41,6 +40,29 @@
 #define SKY81452_DEFAULT_NAME "lcd-backlight"
 #define SKY81452_MAX_BRIGHTNESS	(SKY81452_CS + 1)
 
+/**
+ * struct sky81452_platform_data
+ * @name:	backlight driver name.
+		If it is not defined, default name is lcd-backlight.
+ * @gpios_enable:GPIO descriptor which control EN pin
+ * @enable:	Enable mask for current sink channel 1, 2, 3, 4, 5 and 6.
+ * @ignore_pwm:	true if DPWMI should be ignored.
+ * @dpwm_mode:	true is DPWM dimming mode, otherwise Analog dimming mode.
+ * @phase_shift:true is phase shift mode.
+ * @short_detecion_threshold:	It should be one of 4, 5, 6 and 7V.
+ * @boost_current_limit:	It should be one of 2300, 2750mA.
+ */
+struct sky81452_bl_platform_data {
+	const char *name;
+	struct gpio_desc *gpiod_enable;
+	unsigned int enable;
+	bool ignore_pwm;
+	bool dpwm_mode;
+	bool phase_shift;
+	unsigned int short_detection_threshold;
+	unsigned int boost_current_limit;
+};
+
 #define CTZ(b) __builtin_ctz(b)
 
 static int sky81452_bl_update_status(struct backlight_device *bd)
@@ -251,17 +273,15 @@ static int sky81452_bl_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct regmap *regmap = dev_get_drvdata(dev->parent);
-	struct sky81452_bl_platform_data *pdata = dev_get_platdata(dev);
+	struct sky81452_bl_platform_data *pdata;
 	struct backlight_device *bd;
 	struct backlight_properties props;
 	const char *name;
 	int ret;
 
-	if (!pdata) {
-		pdata = sky81452_bl_parse_dt(dev);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-	}
+	pdata = sky81452_bl_parse_dt(dev);
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
 
 	ret = sky81452_bl_init_device(regmap, pdata);
 	if (ret < 0) {
diff --git a/include/linux/mfd/sky81452.h b/include/linux/mfd/sky81452.h
index d469aa481243..b08570ff34df 100644
--- a/include/linux/mfd/sky81452.h
+++ b/include/linux/mfd/sky81452.h
@@ -9,11 +9,9 @@
 #ifndef _SKY81452_H
 #define _SKY81452_H
 
-#include <linux/platform_data/sky81452-backlight.h>
 #include <linux/regulator/machine.h>
 
 struct sky81452_platform_data {
-	struct sky81452_bl_platform_data *bl_pdata;
 	struct regulator_init_data *regulator_init_data;
 };
 
diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h
deleted file mode 100644
index d6f46670d923..000000000000
--- a/include/linux/platform_data/sky81452-backlight.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * sky81452.h	SKY81452 backlight driver
- *
- * Copyright 2014 Skyworks Solutions Inc.
- * Author : Gyungoh Yoo <jack.yoo@skyworksinc.com>
- */
-
-#ifndef _SKY81452_BACKLIGHT_H
-#define _SKY81452_BACKLIGHT_H
-
-#include <linux/gpio/consumer.h>
-
-/**
- * struct sky81452_platform_data
- * @name:	backlight driver name.
-		If it is not defined, default name is lcd-backlight.
- * @gpios_enable:GPIO descriptor which control EN pin
- * @enable:	Enable mask for current sink channel 1, 2, 3, 4, 5 and 6.
- * @ignore_pwm:	true if DPWMI should be ignored.
- * @dpwm_mode:	true is DPWM dimming mode, otherwise Analog dimming mode.
- * @phase_shift:true is phase shift mode.
- * @short_detecion_threshold:	It should be one of 4, 5, 6 and 7V.
- * @boost_current_limit:	It should be one of 2300, 2750mA.
- */
-struct sky81452_bl_platform_data {
-	const char *name;
-	struct gpio_desc *gpiod_enable;
-	unsigned int enable;
-	bool ignore_pwm;
-	bool dpwm_mode;
-	bool phase_shift;
-	unsigned int short_detection_threshold;
-	unsigned int boost_current_limit;
-};
-
-#endif
-- 
cgit v1.2.3


From 43ff98695cc01779407d489fd546359c188222b4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 28 Jun 2020 19:54:45 -0700
Subject: usb: fix kernel-doc warnings and formatting in <linux/usb.h>

Fix kernel-doc warnings in <linux/usb.h>:

../include/linux/usb.h:713: warning: Function parameter or member 'use_generic_driver' not described in 'usb_device'
../include/linux/usb.h:1253: warning: Function parameter or member 'match' not described in 'usb_device_driver'
../include/linux/usb.h:1253: warning: Function parameter or member 'id_table' not described in 'usb_device_driver'

Also drop an extra blank line and fix indentation.

Fixes: 77419aa403ca ("USB: Fallback to generic driver when specific driver fails")
Fixes: 88b7381a939d ("USB: Select better matching USB drivers when available")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Bastien Nocera <hadess@hadess.net>
Link: https://lore.kernel.org/r/7014bab2-268c-69f6-7ef5-57fbd45c8b08@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 9f3c721c70dc..c86e4ec4d00f 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -620,9 +620,9 @@ struct usb3_lpm_parameters {
  *	Management to be disabled for this usb_device.  This count should only
  *	be manipulated by those functions, with the bandwidth_mutex is held.
  * @hub_delay: cached value consisting of:
- *		parent->hub_delay + wHubDelay + tTPTransmissionDelay (40ns)
- *
+ *	parent->hub_delay + wHubDelay + tTPTransmissionDelay (40ns)
  *	Will be used as wValue for SetIsochDelay requests.
+ * @use_generic_driver: ask driver core to reprobe using the generic driver.
  *
  * Notes:
  * Usbcore drivers should not set usbdev->state directly.  Instead use
@@ -1215,6 +1215,7 @@ struct usb_driver {
  * struct usb_device_driver - identifies USB device driver to usbcore
  * @name: The driver name should be unique among USB drivers,
  *	and should normally be the same as the module name.
+ * @match: If set, used for better device/driver matching.
  * @probe: Called to see if the driver is willing to manage a particular
  *	device.  If it is, probe returns zero and uses dev_set_drvdata()
  *	to associate driver-specific data with the device.  If unwilling
@@ -1227,13 +1228,16 @@ struct usb_driver {
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
  * @drvwrap: Driver-model core structure wrapper.
+ * @id_table: used with @match() to select better matching driver at
+ * 	probe() time.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
  *	for devices bound to this driver.
  * @generic_subclass: if set to 1, the generic USB driver's probe, disconnect,
  *	resume and suspend functions will be called in addition to the driver's
  *	own, so this part of the setup does not need to be replicated.
  *
- * USB drivers must provide all the fields listed above except drvwrap.
+ * USB drivers must provide all the fields listed above except drvwrap,
+ * match, and id_table.
  */
 struct usb_device_driver {
 	const char *name;
-- 
cgit v1.2.3


From f470a6554854123f763f6273e8266bd6ee89a97a Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 1 Jul 2020 14:56:15 +0300
Subject: usb: typec: Combine the definitions for Accessory and USB modes

There is no need to describe them sparately.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200701115618.22482-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/typec_altmode.h | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h
index d834e236c6df..a4b65eaa0f62 100644
--- a/include/linux/usb/typec_altmode.h
+++ b/include/linux/usb/typec_altmode.h
@@ -95,13 +95,7 @@ enum {
  *
  * Port drivers can use TYPEC_MODE_AUDIO and TYPEC_MODE_DEBUG as the mode
  * value for typec_set_mode() when accessory modes are supported.
- */
-enum {
-	TYPEC_MODE_AUDIO = TYPEC_STATE_MODAL,	/* Audio Accessory */
-	TYPEC_MODE_DEBUG,			/* Debug Accessory */
-};
-
-/*
+ *
  * USB4 also requires that the pins on the connector are repurposed, just like
  * Alternate Modes. USB4 mode is however not entered with the Enter Mode Command
  * like the Alternate Modes are, but instead with a special Enter_USB Message.
@@ -112,9 +106,11 @@ enum {
  * state values, just like the Accessory Modes.
  */
 enum {
-	TYPEC_MODE_USB2 = TYPEC_MODE_DEBUG,	/* USB 2.0 mode */
+	TYPEC_MODE_USB2 = TYPEC_STATE_MODAL,	/* USB 2.0 mode */
 	TYPEC_MODE_USB3,			/* USB 3.2 mode */
-	TYPEC_MODE_USB4				/* USB4 mode */
+	TYPEC_MODE_USB4,			/* USB4 mode */
+	TYPEC_MODE_AUDIO,			/* Audio Accessory */
+	TYPEC_MODE_DEBUG,			/* Debug Accessory */
 };
 
 #define TYPEC_MODAL_STATE(_state_)	((_state_) + TYPEC_STATE_MODAL)
-- 
cgit v1.2.3


From ad8db94d6813dc659bd4de0531a8a1150559eafb Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 1 Jul 2020 14:56:16 +0300
Subject: usb: typec: Add data structure for Enter_USB message

This data structure can be delivered to the mux drivers when
Enter_USB Message is used exactly the same way as the
Alternate Mode specific data structures are delivered to the
mux drivers when Enter Mode Messages are used.

The Enter_USB data structure shall have all details related
to the Enter_USB Message, most importantly the Enter_USB
Date Object that was used.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200701115618.22482-3-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/typec.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index 5daa1c49761c..9cb1bec94b71 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -72,6 +72,20 @@ enum typec_orientation {
 	TYPEC_ORIENTATION_REVERSE,
 };
 
+/*
+ * struct enter_usb_data - Enter_USB Message details
+ * @eudo: Enter_USB Data Object
+ * @active_link_training: Active Cable Plug Link Training
+ *
+ * @active_link_training is a flag that should be set with uni-directional SBRX
+ * communication, and left 0 with passive cables and with bi-directional SBRX
+ * communication.
+ */
+struct enter_usb_data {
+	u32			eudo;
+	unsigned char		active_link_training:1;
+};
+
 /*
  * struct usb_pd_identity - USB Power Delivery identity data
  * @id_header: ID Header VDO
-- 
cgit v1.2.3


From f695ca3886ce72b027af7aa6040cd420cae2088c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 10:59:39 +0200
Subject: block: remove the request_queue argument from blk_queue_split

The queue can be trivially derived from the bio, so pass one less
argument.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c             | 21 ++++++++++-----------
 block/blk-mq.c                |  2 +-
 block/blk.h                   |  3 +--
 drivers/block/drbd/drbd_req.c |  2 +-
 drivers/block/pktcdvd.c       |  2 +-
 drivers/block/ps3vram.c       |  2 +-
 drivers/block/rsxx/dev.c      |  2 +-
 drivers/block/umem.c          |  2 +-
 drivers/lightnvm/pblk-init.c  |  4 ++--
 drivers/md/dm.c               |  2 +-
 drivers/md/md.c               |  2 +-
 drivers/nvme/host/multipath.c |  9 ++++-----
 drivers/s390/block/dcssblk.c  |  2 +-
 drivers/s390/block/xpram.c    |  2 +-
 include/linux/blkdev.h        |  2 +-
 15 files changed, 28 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 9c9fb21584b6..20fa22906041 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -283,20 +283,20 @@ split:
 
 /**
  * __blk_queue_split - split a bio and submit the second half
- * @q:       [in] request queue pointer
  * @bio:     [in, out] bio to be split
  * @nr_segs: [out] number of segments in the first bio
  *
  * Split a bio into two bios, chain the two bios, submit the second half and
  * store a pointer to the first half in *@bio. If the second bio is still too
  * big it will be split by a recursive call to this function. Since this
- * function may allocate a new bio from @q->bio_split, it is the responsibility
- * of the caller to ensure that @q is only released after processing of the
+ * function may allocate a new bio from @bio->bi_disk->queue->bio_split, it is
+ * the responsibility of the caller to ensure that
+ * @bio->bi_disk->queue->bio_split is only released after processing of the
  * split bio has finished.
  */
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
-		unsigned int *nr_segs)
+void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
 {
+	struct request_queue *q = (*bio)->bi_disk->queue;
 	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
@@ -345,20 +345,19 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 
 /**
  * blk_queue_split - split a bio and submit the second half
- * @q:   [in] request queue pointer
  * @bio: [in, out] bio to be split
  *
  * Split a bio into two bios, chains the two bios, submit the second half and
  * store a pointer to the first half in *@bio. Since this function may allocate
- * a new bio from @q->bio_split, it is the responsibility of the caller to
- * ensure that @q is only released after processing of the split bio has
- * finished.
+ * a new bio from @bio->bi_disk->queue->bio_split, it is the responsibility of
+ * the caller to ensure that @bio->bi_disk->queue->bio_split is only released
+ * after processing of the split bio has finished.
  */
-void blk_queue_split(struct request_queue *q, struct bio **bio)
+void blk_queue_split(struct bio **bio)
 {
 	unsigned int nr_segs;
 
-	__blk_queue_split(q, bio, &nr_segs);
+	__blk_queue_split(bio, &nr_segs);
 }
 EXPORT_SYMBOL(blk_queue_split);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 65e0846fd065..dbadb7defd61 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2166,7 +2166,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	blk_status_t ret;
 
 	blk_queue_bounce(q, &bio);
-	__blk_queue_split(q, &bio, &nr_segs);
+	__blk_queue_split(&bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
 		goto queue_exit;
diff --git a/block/blk.h b/block/blk.h
index 0184a31fe4df..0114fd92c8a0 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -220,8 +220,7 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
 
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
-		unsigned int *nr_segs);
+void __blk_queue_split(struct bio **bio, unsigned int *nr_segs);
 int ll_back_merge_fn(struct request *req, struct bio *bio,
 		unsigned int nr_segs);
 int ll_front_merge_fn(struct request *req,  struct bio *bio,
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3f09b2ab9778..936868047422 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1598,7 +1598,7 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
 	struct drbd_device *device = bio->bi_disk->private_data;
 	unsigned long start_jif;
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	start_jif = jiffies;
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 27a33adc41e4..29b0c62dc86c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2434,7 +2434,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 	char b[BDEVNAME_SIZE];
 	struct bio *split;
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	pd = q->queuedata;
 	if (!pd) {
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 5a1d1d137c72..76cc584aa763 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -593,7 +593,7 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
 
 	dev_dbg(&dev->core, "%s\n", __func__);
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	spin_lock_irq(&priv->lock);
 	busy = !bio_list_empty(&priv->list);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 6a4d8d26e32c..1d52bc73dd0f 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -123,7 +123,7 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
 	struct rsxx_bio_meta *bio_meta;
 	blk_status_t st = BLK_STS_IOERR;
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	might_sleep();
 
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 5498f1cf36b3..3b89c07f9e9d 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -527,7 +527,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
 		 (unsigned long long)bio->bi_iter.bi_sector,
 		 bio->bi_iter.bi_size);
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 6e677ff62cc9..7a4a1b7a941d 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -63,7 +63,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
 	 * constraint. Writes can be of arbitrary size.
 	 */
 	if (bio_data_dir(bio) == READ) {
-		blk_queue_split(q, &bio);
+		blk_queue_split(&bio);
 		pblk_submit_read(pblk, bio);
 	} else {
 		/* Prevent deadlock in the case of a modest LUN configuration
@@ -71,7 +71,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
 		 * leaves at least 256KB available for user I/O.
 		 */
 		if (pblk_get_secs(bio) > pblk_rl_max_io(&pblk->rl))
-			blk_queue_split(q, &bio);
+			blk_queue_split(&bio);
 
 		pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c8d91f271c27..5aa7a604f4cb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1776,7 +1776,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
 	 */
 	if (current->bio_list) {
 		if (is_abnormal_io(bio))
-			blk_queue_split(md->queue, &bio);
+			blk_queue_split(&bio);
 		else
 			dm_queue_split(md, ti, &bio);
 	}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f567f536b529..ff20868e5e1b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -475,7 +475,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	if (mddev == NULL || mddev->pers == NULL) {
 		bio_io_error(bio);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index da78e499947a..5a5205ea570a 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -301,12 +301,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	int srcu_idx;
 
 	/*
-	 * The namespace might be going away and the bio might
-	 * be moved to a different queue via blk_steal_bios(),
-	 * so we need to use the bio_split pool from the original
-	 * queue to allocate the bvecs from.
+	 * The namespace might be going away and the bio might be moved to a
+	 * different queue via blk_steal_bios(), so we need to use the bio_split
+	 * pool from the original queue to allocate the bvecs from.
 	 */
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 384edffe5cb4..dfe21eb72760 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -878,7 +878,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 	unsigned long source_addr;
 	unsigned long bytes_done;
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	bytes_done = 0;
 	dev_info = bio->bi_disk->private_data;
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 45a04daec89e..5456f0ad5a40 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -191,7 +191,7 @@ static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio)
 	unsigned long page_addr;
 	unsigned long bytes;
 
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	if ((bio->bi_iter.bi_sector & 7) != 0 ||
 	    (bio->bi_iter.bi_size & 4095) != 0)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 15497782c176..d002defc1789 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -871,7 +871,7 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
-extern void blk_queue_split(struct request_queue *, struct bio **);
+extern void blk_queue_split(struct bio **);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
 			      unsigned int, void __user *);
-- 
cgit v1.2.3


From c62b37d96b6eb3ec5ae4cbe00db107bf15aebc93 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 10:59:43 +0200
Subject: block: move ->make_request_fn to struct block_device_operations

The make_request_fn is a little weird in that it sits directly in
struct request_queue instead of an operation vector.  Replace it with
a block_device_operations method called submit_bio (which describes much
better what it does).  Also remove the request_queue argument to it, as
the queue can be derived pretty trivially from the bio.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/biodoc.rst                  |  2 +-
 Documentation/block/writeback_cache_control.rst |  2 +-
 arch/m68k/emu/nfblock.c                         |  5 ++-
 arch/xtensa/platforms/iss/simdisk.c             |  5 ++-
 block/blk-cgroup.c                              |  2 +-
 block/blk-core.c                                | 53 +++++++++----------------
 block/blk-mq.c                                  | 10 ++---
 block/blk.h                                     |  2 -
 drivers/block/brd.c                             |  5 ++-
 drivers/block/drbd/drbd_int.h                   |  2 +-
 drivers/block/drbd/drbd_main.c                  |  9 +++--
 drivers/block/drbd/drbd_req.c                   |  2 +-
 drivers/block/null_blk_main.c                   | 17 ++++++--
 drivers/block/pktcdvd.c                         | 11 ++---
 drivers/block/ps3vram.c                         | 15 ++++---
 drivers/block/rsxx/dev.c                        |  7 +++-
 drivers/block/umem.c                            |  5 ++-
 drivers/block/zram/zram_drv.c                   | 11 ++---
 drivers/lightnvm/core.c                         |  8 +---
 drivers/lightnvm/pblk-init.c                    | 12 ++++--
 drivers/md/bcache/request.c                     |  4 +-
 drivers/md/bcache/request.h                     |  4 +-
 drivers/md/bcache/super.c                       | 23 +++++++----
 drivers/md/dm.c                                 | 23 ++++++-----
 drivers/md/md.c                                 |  5 ++-
 drivers/nvdimm/blk.c                            |  5 ++-
 drivers/nvdimm/btt.c                            |  5 ++-
 drivers/nvdimm/pmem.c                           |  5 ++-
 drivers/nvme/host/core.c                        |  1 +
 drivers/nvme/host/multipath.c                   |  5 +--
 drivers/nvme/host/nvme.h                        |  1 +
 drivers/s390/block/dcssblk.c                    |  9 ++---
 drivers/s390/block/xpram.c                      |  6 +--
 include/linux/blk-mq.h                          |  2 +-
 include/linux/blkdev.h                          |  7 +---
 include/linux/lightnvm.h                        |  3 +-
 36 files changed, 153 insertions(+), 140 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst
index b964796ec9c7..267384159bf7 100644
--- a/Documentation/block/biodoc.rst
+++ b/Documentation/block/biodoc.rst
@@ -1036,7 +1036,7 @@ Now the generic block layer performs partition-remapping early and thus
 provides drivers with a sector number relative to whole device, rather than
 having to take partition number into account in order to arrive at the true
 sector number. The routine blk_partition_remap() is invoked by
-generic_make_request even before invoking the queue specific make_request_fn,
+generic_make_request even before invoking the queue specific ->submit_bio,
 so the i/o scheduler also gets to operate on whole disk sector numbers. This
 should typically not require changes to block drivers, it just never gets
 to invoke its own partition sector offset calculations since all bios
diff --git a/Documentation/block/writeback_cache_control.rst b/Documentation/block/writeback_cache_control.rst
index 2c752c57c14c..b208488d0aae 100644
--- a/Documentation/block/writeback_cache_control.rst
+++ b/Documentation/block/writeback_cache_control.rst
@@ -47,7 +47,7 @@ the Forced Unit Access is implemented.  The REQ_PREFLUSH and REQ_FUA flags
 may both be set on a single bio.
 
 
-Implementation details for make_request_fn based block drivers
+Implementation details for bio based block drivers
 --------------------------------------------------------------
 
 These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 87e8b1700acd..92d26c812441 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -59,7 +59,7 @@ struct nfhd_device {
 	struct gendisk *disk;
 };
 
-static blk_qc_t nfhd_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t nfhd_submit_bio(struct bio *bio)
 {
 	struct nfhd_device *dev = bio->bi_disk->private_data;
 	struct bio_vec bvec;
@@ -93,6 +93,7 @@ static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 static const struct block_device_operations nfhd_ops = {
 	.owner	= THIS_MODULE,
+	.submit_bio = nfhd_submit_bio,
 	.getgeo	= nfhd_getgeo,
 };
 
@@ -118,7 +119,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE);
+	dev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (dev->queue == NULL)
 		goto free_dev;
 
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 31b5020077a0..5107140dbb7e 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -101,7 +101,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	spin_unlock(&dev->lock);
 }
 
-static blk_qc_t simdisk_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t simdisk_submit_bio(struct bio *bio)
 {
 	struct simdisk *dev = bio->bi_disk->private_data;
 	struct bio_vec bvec;
@@ -144,6 +144,7 @@ static void simdisk_release(struct gendisk *disk, fmode_t mode)
 
 static const struct block_device_operations simdisk_ops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= simdisk_submit_bio,
 	.open		= simdisk_open,
 	.release	= simdisk_release,
 };
@@ -267,7 +268,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE);
+	dev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (dev->queue == NULL) {
 		pr_err("blk_alloc_queue failed\n");
 		goto out_alloc_queue;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 748c4b2a9273..594f1d0b0e5a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1012,7 +1012,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
  * blkcg_init_queue - initialize blkcg part of request queue
  * @q: request_queue to initialize
  *
- * Called from __blk_alloc_queue(). Responsible for initializing blkcg
+ * Called from blk_alloc_queue(). Responsible for initializing blkcg
  * part of new request_queue @q.
  *
  * RETURNS:
diff --git a/block/blk-core.c b/block/blk-core.c
index 28f60985dc75..cb07a726dd71 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -283,7 +283,7 @@ EXPORT_SYMBOL(blk_dump_rq_flags);
  *     A block device may call blk_sync_queue to ensure that any
  *     such activity is cancelled, thus allowing it to release resources
  *     that the callbacks might use. The caller must already have made sure
- *     that its ->make_request_fn will not re-add plugging prior to calling
+ *     that its ->submit_bio will not re-add plugging prior to calling
  *     this function.
  *
  *     This function does not cancel any asynchronous activity arising
@@ -510,7 +510,7 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *__blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(int node_id)
 {
 	struct request_queue *q;
 	int ret;
@@ -575,6 +575,7 @@ struct request_queue *__blk_alloc_queue(int node_id)
 
 	blk_queue_dma_alignment(q, 511);
 	blk_set_default_limits(&q->limits);
+	q->nr_requests = BLKDEV_MAX_RQ;
 
 	return q;
 
@@ -592,21 +593,6 @@ fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
 	return NULL;
 }
-
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id)
-{
-	struct request_queue *q;
-
-	if (WARN_ON_ONCE(!make_request))
-		return NULL;
-
-	q = __blk_alloc_queue(node_id);
-	if (!q)
-		return NULL;
-	q->make_request_fn = make_request;
-	q->nr_requests = BLKDEV_MAX_RQ;
-	return q;
-}
 EXPORT_SYMBOL(blk_alloc_queue);
 
 /**
@@ -1088,15 +1074,15 @@ end_io:
 
 static blk_qc_t do_make_request(struct bio *bio)
 {
-	struct request_queue *q = bio->bi_disk->queue;
+	struct gendisk *disk = bio->bi_disk;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (blk_crypto_bio_prep(&bio)) {
-		if (!q->make_request_fn)
-			return blk_mq_make_request(q, bio);
-		ret = q->make_request_fn(q, bio);
+		if (!disk->fops->submit_bio)
+			return blk_mq_submit_bio(bio);
+		ret = disk->fops->submit_bio(bio);
 	}
-	blk_queue_exit(q);
+	blk_queue_exit(disk->queue);
 	return ret;
 }
 
@@ -1113,10 +1099,9 @@ blk_qc_t generic_make_request(struct bio *bio)
 {
 	/*
 	 * bio_list_on_stack[0] contains bios submitted by the current
-	 * make_request_fn.
-	 * bio_list_on_stack[1] contains bios that were submitted before
-	 * the current make_request_fn, but that haven't been processed
-	 * yet.
+	 * ->submit_bio.
+	 * bio_list_on_stack[1] contains bios that were submitted before the
+	 * current ->submit_bio_bio, but that haven't been processed yet.
 	 */
 	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
@@ -1125,10 +1110,10 @@ blk_qc_t generic_make_request(struct bio *bio)
 		goto out;
 
 	/*
-	 * We only want one ->make_request_fn to be active at a time, else
+	 * We only want one ->submit_bio to be active at a time, else
 	 * stack usage with stacked devices could be a problem.  So use
 	 * current->bio_list to keep a list of requests submited by a
-	 * make_request_fn function.  current->bio_list is also used as a
+	 * ->submit_bio method.  current->bio_list is also used as a
 	 * flag to say if generic_make_request is currently active in this
 	 * task or not.  If it is NULL, then no make_request is active.  If
 	 * it is non-NULL, then a make_request is active, and new requests
@@ -1146,12 +1131,12 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * We pretend that we have just taken it off a longer list, so
 	 * we assign bio_list to a pointer to the bio_list_on_stack,
 	 * thus initialising the bio_list of new bios to be
-	 * added.  ->make_request() may indeed add some more bios
+	 * added.  ->submit_bio() may indeed add some more bios
 	 * through a recursive call to generic_make_request.  If it
 	 * did, we find a non-NULL value in bio_list and re-enter the loop
 	 * from the top.  In this case we really did just take the bio
 	 * of the top of the list (no pretending) and so remove it from
-	 * bio_list, and call into ->make_request() again.
+	 * bio_list, and call into ->submit_bio() again.
 	 */
 	BUG_ON(bio->bi_next);
 	bio_list_init(&bio_list_on_stack[0]);
@@ -1201,9 +1186,9 @@ EXPORT_SYMBOL(generic_make_request);
  */
 blk_qc_t direct_make_request(struct bio *bio)
 {
-	struct request_queue *q = bio->bi_disk->queue;
+	struct gendisk *disk = bio->bi_disk;
 
-	if (WARN_ON_ONCE(q->make_request_fn)) {
+	if (WARN_ON_ONCE(!disk->queue->mq_ops)) {
 		bio_io_error(bio);
 		return BLK_QC_T_NONE;
 	}
@@ -1212,10 +1197,10 @@ blk_qc_t direct_make_request(struct bio *bio)
 	if (unlikely(bio_queue_enter(bio)))
 		return BLK_QC_T_NONE;
 	if (!blk_crypto_bio_prep(&bio)) {
-		blk_queue_exit(q);
+		blk_queue_exit(disk->queue);
 		return BLK_QC_T_NONE;
 	}
-	return blk_mq_make_request(q, bio);
+	return blk_mq_submit_bio(bio);
 }
 EXPORT_SYMBOL_GPL(direct_make_request);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index dbadb7defd61..948987e9b6ab 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2136,8 +2136,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 }
 
 /**
- * blk_mq_make_request - Create and send a request to block device.
- * @q: Request queue pointer.
+ * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
  *
  * Builds up a request structure from @q and @bio and send to the device. The
@@ -2151,8 +2150,9 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  *
  * Returns: Request queue cookie.
  */
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t blk_mq_submit_bio(struct bio *bio)
 {
+	struct request_queue *q = bio->bi_disk->queue;
 	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_mq_alloc_data data = {
@@ -2277,7 +2277,7 @@ queue_exit:
 	blk_queue_exit(q);
 	return BLK_QC_T_NONE;
 }
-EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
+EXPORT_SYMBOL_GPL(blk_mq_submit_bio); /* only for request based dm */
 
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx)
@@ -3017,7 +3017,7 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 {
 	struct request_queue *uninit_q, *q;
 
-	uninit_q = __blk_alloc_queue(set->numa_node);
+	uninit_q = blk_alloc_queue(set->numa_node);
 	if (!uninit_q)
 		return ERR_PTR(-ENOMEM);
 	uninit_q->queuedata = queuedata;
diff --git a/block/blk.h b/block/blk.h
index 0114fd92c8a0..9dcf51c94096 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -419,8 +419,6 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 #endif
 }
 
-struct request_queue *__blk_alloc_queue(int node_id);
-
 int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2fb25c348d53..2723a70eb855 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -282,7 +282,7 @@ out:
 	return err;
 }
 
-static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t brd_submit_bio(struct bio *bio)
 {
 	struct brd_device *brd = bio->bi_disk->private_data;
 	struct bio_vec bvec;
@@ -330,6 +330,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
+	.submit_bio =		brd_submit_bio,
 	.rw_page =		brd_rw_page,
 };
 
@@ -381,7 +382,7 @@ static struct brd_device *brd_alloc(int i)
 	spin_lock_init(&brd->brd_lock);
 	INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
 
-	brd->brd_queue = blk_alloc_queue(brd_make_request, NUMA_NO_NODE);
+	brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!brd->brd_queue)
 		goto out_free_dev;
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 33d0831c99b6..0327408da79c 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1451,7 +1451,7 @@ extern void conn_free_crypto(struct drbd_connection *connection);
 /* drbd_req */
 extern void do_submit(struct work_struct *ws);
 extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long);
-extern blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio);
+extern blk_qc_t drbd_submit_bio(struct bio *bio);
 extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
 extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 26f4e0aa7393..2b05de0896e2 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -132,9 +132,10 @@ wait_queue_head_t drbd_pp_wait;
 DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5);
 
 static const struct block_device_operations drbd_ops = {
-	.owner =   THIS_MODULE,
-	.open =    drbd_open,
-	.release = drbd_release,
+	.owner		= THIS_MODULE,
+	.submit_bio	= drbd_submit_bio,
+	.open		= drbd_open,
+	.release	= drbd_release,
 };
 
 struct bio *bio_alloc_drbd(gfp_t gfp_mask)
@@ -2801,7 +2802,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	drbd_init_set_defaults(device);
 
-	q = blk_alloc_queue(drbd_make_request, NUMA_NO_NODE);
+	q = blk_alloc_queue(NUMA_NO_NODE);
 	if (!q)
 		goto out_no_q;
 	device->rq_queue = q;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 936868047422..c7e14c9a6e5f 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1593,7 +1593,7 @@ void do_submit(struct work_struct *ws)
 	}
 }
 
-blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t drbd_submit_bio(struct bio *bio)
 {
 	struct drbd_device *device = bio->bi_disk->private_data;
 	unsigned long start_jif;
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 93ce0a00b2ae..907c6858aec0 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -1388,7 +1388,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
 	return &nullb->queues[index];
 }
 
-static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
+static blk_qc_t null_submit_bio(struct bio *bio)
 {
 	sector_t sector = bio->bi_iter.bi_sector;
 	sector_t nr_sectors = bio_sectors(bio);
@@ -1575,7 +1575,13 @@ static void null_config_discard(struct nullb *nullb)
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
 }
 
-static const struct block_device_operations null_ops = {
+static const struct block_device_operations null_bio_ops = {
+	.owner		= THIS_MODULE,
+	.submit_bio	= null_submit_bio,
+	.report_zones	= null_report_zones,
+};
+
+static const struct block_device_operations null_rq_ops = {
 	.owner		= THIS_MODULE,
 	.report_zones	= null_report_zones,
 };
@@ -1647,7 +1653,10 @@ static int null_gendisk_register(struct nullb *nullb)
 	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
-	disk->fops		= &null_ops;
+	if (queue_is_mq(nullb->q))
+		disk->fops		= &null_rq_ops;
+	else
+		disk->fops		= &null_bio_ops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
@@ -1792,7 +1801,7 @@ static int null_add_dev(struct nullb_device *dev)
 			goto out_cleanup_tags;
 		}
 	} else if (dev->queue_mode == NULL_Q_BIO) {
-		nullb->q = blk_alloc_queue(null_queue_bio, dev->home_node);
+		nullb->q = blk_alloc_queue(dev->home_node);
 		if (!nullb->q) {
 			rv = -ENOMEM;
 			goto out_cleanup_queues;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 29b0c62dc86c..5588bd4cd267 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -36,7 +36,7 @@
  * block device, assembling the pieces to full packets and queuing them to the
  * packet I/O scheduler.
  *
- * At the top layer there is a custom make_request_fn function that forwards
+ * At the top layer there is a custom ->submit_bio function that forwards
  * read requests directly to the iosched queue and puts write requests in the
  * unaligned write queue. A kernel thread performs the necessary read
  * gathering to convert the unaligned writes to aligned writes and then feeds
@@ -2428,7 +2428,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 	}
 }
 
-static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pkt_submit_bio(struct bio *bio)
 {
 	struct pktcdvd_device *pd;
 	char b[BDEVNAME_SIZE];
@@ -2436,7 +2436,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(&bio);
 
-	pd = q->queuedata;
+	pd = bio->bi_disk->queue->queuedata;
 	if (!pd) {
 		pr_err("%s incorrect request queue\n", bio_devname(bio, b));
 		goto end_io;
@@ -2480,7 +2480,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 			split = bio;
 		}
 
-		pkt_make_request_write(q, split);
+		pkt_make_request_write(bio->bi_disk->queue, split);
 	} while (split != bio);
 
 	return BLK_QC_T_NONE;
@@ -2685,6 +2685,7 @@ static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
 
 static const struct block_device_operations pktcdvd_ops = {
 	.owner =		THIS_MODULE,
+	.submit_bio =		pkt_submit_bio,
 	.open =			pkt_open,
 	.release =		pkt_close,
 	.ioctl =		pkt_ioctl,
@@ -2749,7 +2750,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	disk->flags = GENHD_FL_REMOVABLE;
 	strcpy(disk->disk_name, pd->name);
 	disk->private_data = pd;
-	disk->queue = blk_alloc_queue(pkt_make_request, NUMA_NO_NODE);
+	disk->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!disk->queue)
 		goto out_mem2;
 
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 76cc584aa763..1088798c8dd0 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -90,12 +90,6 @@ struct ps3vram_priv {
 
 static int ps3vram_major;
 
-
-static const struct block_device_operations ps3vram_fops = {
-	.owner		= THIS_MODULE,
-};
-
-
 #define DMA_NOTIFIER_HANDLE_BASE 0x66604200 /* first DMA notifier handle */
 #define DMA_NOTIFIER_OFFSET_BASE 0x1000     /* first DMA notifier offset */
 #define DMA_NOTIFIER_SIZE        0x40
@@ -585,7 +579,7 @@ out:
 	return next;
 }
 
-static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t ps3vram_submit_bio(struct bio *bio)
 {
 	struct ps3_system_bus_device *dev = bio->bi_disk->private_data;
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -610,6 +604,11 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
+static const struct block_device_operations ps3vram_fops = {
+	.owner		= THIS_MODULE,
+	.submit_bio	= ps3vram_submit_bio,
+};
+
 static int ps3vram_probe(struct ps3_system_bus_device *dev)
 {
 	struct ps3vram_priv *priv;
@@ -737,7 +736,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 
 	ps3vram_proc_init(dev);
 
-	queue = blk_alloc_queue(ps3vram_make_request, NUMA_NO_NODE);
+	queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!queue) {
 		dev_err(&dev->core, "blk_alloc_queue failed\n");
 		error = -ENOMEM;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 1d52bc73dd0f..edacefff6e35 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -50,6 +50,8 @@ struct rsxx_bio_meta {
 
 static struct kmem_cache *bio_meta_pool;
 
+static blk_qc_t rsxx_submit_bio(struct bio *bio);
+
 /*----------------- Block Device Operations -----------------*/
 static int rsxx_blkdev_ioctl(struct block_device *bdev,
 				 fmode_t mode,
@@ -92,6 +94,7 @@ static int rsxx_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 static const struct block_device_operations rsxx_fops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= rsxx_submit_bio,
 	.getgeo		= rsxx_getgeo,
 	.ioctl		= rsxx_blkdev_ioctl,
 };
@@ -117,7 +120,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
 	}
 }
 
-static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t rsxx_submit_bio(struct bio *bio)
 {
 	struct rsxx_cardinfo *card = bio->bi_disk->private_data;
 	struct rsxx_bio_meta *bio_meta;
@@ -233,7 +236,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 		return -ENOMEM;
 	}
 
-	card->queue = blk_alloc_queue(rsxx_make_request, NUMA_NO_NODE);
+	card->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!card->queue) {
 		dev_err(CARD_TO_DEV(card), "Failed queue alloc\n");
 		unregister_blkdev(card->major, DRIVER_NAME);
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 3b89c07f9e9d..2b95d7b33b91 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -519,7 +519,7 @@ static int mm_check_plugged(struct cardinfo *card)
 	return !!blk_check_plugged(mm_unplug, card, sizeof(struct blk_plug_cb));
 }
 
-static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t mm_submit_bio(struct bio *bio)
 {
 	struct cardinfo *card = bio->bi_disk->private_data;
 
@@ -779,6 +779,7 @@ static int mm_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 static const struct block_device_operations mm_fops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= mm_submit_bio,
 	.getgeo		= mm_getgeo,
 	.revalidate_disk = mm_revalidate,
 };
@@ -886,7 +887,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	card->biotail = &card->bio;
 	spin_lock_init(&card->lock);
 
-	card->queue = blk_alloc_queue(mm_make_request, NUMA_NO_NODE);
+	card->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!card->queue)
 		goto failed_alloc;
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 0564e3f38408..f9a57f147ee1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -793,9 +793,9 @@ static void zram_sync_read(struct work_struct *work)
 }
 
 /*
- * Block layer want one ->make_request_fn to be active at a time
- * so if we use chained IO with parent IO in same context,
- * it's a deadlock. To avoid, it, it uses worker thread context.
+ * Block layer want one ->submit_bio to be active at a time, so if we use
+ * chained IO with parent IO in same context, it's a deadlock. To avoid that,
+ * use a worker thread context.
  */
 static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 				unsigned long entry, struct bio *bio)
@@ -1584,7 +1584,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 /*
  * Handler function for all zram I/O requests.
  */
-static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t zram_submit_bio(struct bio *bio)
 {
 	struct zram *zram = bio->bi_disk->private_data;
 
@@ -1813,6 +1813,7 @@ static int zram_open(struct block_device *bdev, fmode_t mode)
 
 static const struct block_device_operations zram_devops = {
 	.open = zram_open,
+	.submit_bio = zram_submit_bio,
 	.swap_slot_free_notify = zram_slot_free_notify,
 	.rw_page = zram_rw_page,
 	.owner = THIS_MODULE
@@ -1891,7 +1892,7 @@ static int zram_add(void)
 #ifdef CONFIG_ZRAM_WRITEBACK
 	spin_lock_init(&zram->wb_limit_lock);
 #endif
-	queue = blk_alloc_queue(zram_make_request, NUMA_NO_NODE);
+	queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!queue) {
 		pr_err("Error allocating disk queue for device %d\n",
 			device_id);
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index db38a68abb6c..fe78bf0fdce5 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -236,10 +236,6 @@ err_dev:
 	return tgt_dev;
 }
 
-static const struct block_device_operations nvm_fops = {
-	.owner		= THIS_MODULE,
-};
-
 static struct nvm_tgt_type *__nvm_find_target_type(const char *name)
 {
 	struct nvm_tgt_type *tt;
@@ -380,7 +376,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 		goto err_dev;
 	}
 
-	tqueue = blk_alloc_queue(tt->make_rq, dev->q->node);
+	tqueue = blk_alloc_queue(dev->q->node);
 	if (!tqueue) {
 		ret = -ENOMEM;
 		goto err_disk;
@@ -390,7 +386,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 	tdisk->flags = GENHD_FL_EXT_DEVT;
 	tdisk->major = 0;
 	tdisk->first_minor = 0;
-	tdisk->fops = &nvm_fops;
+	tdisk->fops = tt->bops;
 	tdisk->queue = tqueue;
 
 	targetdata = tt->init(tgt_dev, tdisk, create->flags);
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 7a4a1b7a941d..b6246f73895c 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -47,9 +47,9 @@ static struct pblk_global_caches pblk_caches = {
 
 struct bio_set pblk_bio_set;
 
-static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
+static blk_qc_t pblk_submit_bio(struct bio *bio)
 {
-	struct pblk *pblk = q->queuedata;
+	struct pblk *pblk = bio->bi_disk->queue->queuedata;
 
 	if (bio_op(bio) == REQ_OP_DISCARD) {
 		pblk_discard(pblk, bio);
@@ -79,6 +79,12 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
+static const struct block_device_operations pblk_bops = {
+	.owner		= THIS_MODULE,
+	.submit_bio	= pblk_submit_bio,
+};
+
+
 static size_t pblk_trans_map_size(struct pblk *pblk)
 {
 	int entry_size = 8;
@@ -1280,7 +1286,7 @@ static struct nvm_tgt_type tt_pblk = {
 	.name		= "pblk",
 	.version	= {1, 0, 0},
 
-	.make_rq	= pblk_make_rq,
+	.bops		= &pblk_bops,
 	.capacity	= pblk_capacity,
 
 	.init		= pblk_init,
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 7acf024e99f3..fc5702b10074 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1158,7 +1158,7 @@ static void quit_max_writeback_rate(struct cache_set *c,
 
 /* Cached devices - read & write stuff */
 
-blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t cached_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct bcache_device *d = bio->bi_disk->private_data;
@@ -1291,7 +1291,7 @@ static void flash_dev_nodata(struct closure *cl)
 	continue_at(cl, search_free, NULL);
 }
 
-blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t flash_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct closure *cl;
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index bb005c93dd72..82b38366a95d 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c);
 void bch_data_insert(struct closure *cl);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
-blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t cached_dev_submit_bio(struct bio *bio);
 
 void bch_flash_dev_request_init(struct bcache_device *d);
-blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t flash_dev_submit_bio(struct bio *bio);
 
 extern struct kmem_cache *bch_search_cache;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 21aa168113d3..de13f6e91696 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -680,7 +680,16 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
 	return d->ioctl(d, mode, cmd, arg);
 }
 
-static const struct block_device_operations bcache_ops = {
+static const struct block_device_operations bcache_cached_ops = {
+	.submit_bio	= cached_dev_submit_bio,
+	.open		= open_dev,
+	.release	= release_dev,
+	.ioctl		= ioctl_dev,
+	.owner		= THIS_MODULE,
+};
+
+static const struct block_device_operations bcache_flash_ops = {
+	.submit_bio	= flash_dev_submit_bio,
 	.open		= open_dev,
 	.release	= release_dev,
 	.ioctl		= ioctl_dev,
@@ -820,8 +829,8 @@ static void bcache_device_free(struct bcache_device *d)
 }
 
 static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
-			      sector_t sectors, make_request_fn make_request_fn,
-			      struct block_device *cached_bdev)
+		sector_t sectors, struct block_device *cached_bdev,
+		const struct block_device_operations *ops)
 {
 	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
@@ -868,10 +877,10 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	d->disk->major		= bcache_major;
 	d->disk->first_minor	= idx_to_first_minor(idx);
-	d->disk->fops		= &bcache_ops;
+	d->disk->fops		= ops;
 	d->disk->private_data	= d;
 
-	q = blk_alloc_queue(make_request_fn, NUMA_NO_NODE);
+	q = blk_alloc_queue(NUMA_NO_NODE);
 	if (!q)
 		return -ENOMEM;
 
@@ -1355,7 +1364,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 
 	ret = bcache_device_init(&dc->disk, block_size,
 			 dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
-			 cached_dev_make_request, dc->bdev);
+			 dc->bdev, &bcache_cached_ops);
 	if (ret)
 		return ret;
 
@@ -1468,7 +1477,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
 	if (bcache_device_init(d, block_bytes(c), u->sectors,
-			flash_dev_make_request, NULL))
+			NULL, &bcache_flash_ops))
 		goto err;
 
 	bcache_device_attach(d, c, u - c->uuids);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5aa7a604f4cb..5acfaba3700d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1770,7 +1770,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
 	}
 
 	/*
-	 * If in ->make_request_fn we need to use blk_queue_split(), otherwise
+	 * If in ->queue_bio we need to use blk_queue_split(), otherwise
 	 * queue_limits for abnormal requests (e.g. discard, writesame, etc)
 	 * won't be imposed.
 	 */
@@ -1787,7 +1787,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
 		return __split_and_process_bio(md, map, bio);
 }
 
-static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t dm_submit_bio(struct bio *bio)
 {
 	struct mapped_device *md = bio->bi_disk->private_data;
 	blk_qc_t ret = BLK_QC_T_NONE;
@@ -1798,12 +1798,12 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
 		/*
 		 * We are called with a live reference on q_usage_counter, but
 		 * that one will be released as soon as we return.  Grab an
-		 * extra one as blk_mq_make_request expects to be able to
-		 * consume a reference (which lives until the request is freed
-		 * in case a request is allocated).
+		 * extra one as blk_mq_submit_bio expects to be able to consume
+		 * a reference (which lives until the request is freed in case a
+		 * request is allocated).
 		 */
-		percpu_ref_get(&q->q_usage_counter);
-		return blk_mq_make_request(q, bio);
+		percpu_ref_get(&bio->bi_disk->queue->q_usage_counter);
+		return blk_mq_submit_bio(bio);
 	}
 
 	map = dm_get_live_table(md, &srcu_idx);
@@ -1988,11 +1988,11 @@ static struct mapped_device *alloc_dev(int minor)
 	spin_lock_init(&md->uevent_lock);
 
 	/*
-	 * default to bio-based required ->make_request_fn until DM
-	 * table is loaded and md->type established. If request-based
-	 * table is loaded: blk-mq will override accordingly.
+	 * default to bio-based until DM table is loaded and md->type
+	 * established. If request-based table is loaded: blk-mq will
+	 * override accordingly.
 	 */
-	md->queue = blk_alloc_queue(dm_make_request, numa_node_id);
+	md->queue = blk_alloc_queue(numa_node_id);
 	if (!md->queue)
 		goto bad;
 
@@ -3232,6 +3232,7 @@ static const struct pr_ops dm_pr_ops = {
 };
 
 static const struct block_device_operations dm_blk_dops = {
+	.submit_bio = dm_submit_bio,
 	.open = dm_blk_open,
 	.release = dm_blk_close,
 	.ioctl = dm_blk_ioctl,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ff20868e5e1b..7b7cb49be351 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -463,7 +463,7 @@ check_suspended:
 }
 EXPORT_SYMBOL(md_handle_request);
 
-static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
 	const int sgrp = op_stat_group(bio_op(bio));
@@ -5641,7 +5641,7 @@ static int md_alloc(dev_t dev, char *name)
 		mddev->hold_active = UNTIL_STOP;
 
 	error = -ENOMEM;
-	mddev->queue = blk_alloc_queue(md_make_request, NUMA_NO_NODE);
+	mddev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!mddev->queue)
 		goto abort;
 
@@ -7823,6 +7823,7 @@ static int md_revalidate(struct gendisk *disk)
 static const struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
+	.submit_bio	= md_submit_bio,
 	.open		= md_open,
 	.release	= md_release,
 	.ioctl		= md_ioctl,
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 39030a324d7f..1f718381a045 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
 	return err;
 }
 
-static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t nd_blk_submit_bio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct nd_namespace_blk *nsblk = bio->bi_disk->private_data;
@@ -225,6 +225,7 @@ static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
 
 static const struct block_device_operations nd_blk_fops = {
 	.owner = THIS_MODULE,
+	.submit_bio =  nd_blk_submit_bio,
 	.revalidate_disk = nvdimm_revalidate_disk,
 };
 
@@ -250,7 +251,7 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk)
 	internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk));
 	available_disk_size = internal_nlba * nsblk_sector_size(nsblk);
 
-	q = blk_alloc_queue(nd_blk_make_request, NUMA_NO_NODE);
+	q = blk_alloc_queue(NUMA_NO_NODE);
 	if (!q)
 		return -ENOMEM;
 	if (devm_add_action_or_reset(dev, nd_blk_release_queue, q))
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 48e9d169b6f9..412d21d8f643 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1439,7 +1439,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 	return ret;
 }
 
-static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t btt_submit_bio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct btt *btt = bio->bi_disk->private_data;
@@ -1512,6 +1512,7 @@ static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo)
 
 static const struct block_device_operations btt_fops = {
 	.owner =		THIS_MODULE,
+	.submit_bio =		btt_submit_bio,
 	.rw_page =		btt_rw_page,
 	.getgeo =		btt_getgeo,
 	.revalidate_disk =	nvdimm_revalidate_disk,
@@ -1523,7 +1524,7 @@ static int btt_blk_init(struct btt *btt)
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
 	/* create a new disk and request queue for btt */
-	btt->btt_queue = blk_alloc_queue(btt_make_request, NUMA_NO_NODE);
+	btt->btt_queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!btt->btt_queue)
 		return -ENOMEM;
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d25e66fd942d..94790e6e0e4c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -189,7 +189,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
 	return rc;
 }
 
-static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pmem_submit_bio(struct bio *bio)
 {
 	int ret = 0;
 	blk_status_t rc = 0;
@@ -281,6 +281,7 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 
 static const struct block_device_operations pmem_fops = {
 	.owner =		THIS_MODULE,
+	.submit_bio =		pmem_submit_bio,
 	.rw_page =		pmem_rw_page,
 	.revalidate_disk =	nvdimm_revalidate_disk,
 };
@@ -423,7 +424,7 @@ static int pmem_attach_disk(struct device *dev,
 		return -EBUSY;
 	}
 
-	q = blk_alloc_queue(pmem_make_request, dev_to_node(dev));
+	q = blk_alloc_queue(dev_to_node(dev));
 	if (!q)
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 6810c8812aed..5192a024dc1b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2178,6 +2178,7 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
 
 const struct block_device_operations nvme_ns_head_ops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= nvme_ns_head_submit_bio,
 	.open		= nvme_ns_head_open,
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ioctl,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5a5205ea570a..89afcf943bf8 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -291,8 +291,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	return false;
 }
 
-static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
-		struct bio *bio)
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 {
 	struct nvme_ns_head *head = bio->bi_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
@@ -374,7 +373,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
 		return 0;
 
-	q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node);
+	q = blk_alloc_queue(ctrl->numa_node);
 	if (!q)
 		goto out;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 61780c38f51f..9f2b0e0b4558 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -586,6 +586,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio);
 
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index dfe21eb72760..35666c3537de 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -31,8 +31,7 @@
 
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
-static blk_qc_t dcssblk_make_request(struct request_queue *q,
-						struct bio *bio);
+static blk_qc_t dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
 
@@ -41,6 +40,7 @@ static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 static int dcssblk_major;
 static const struct block_device_operations dcssblk_devops = {
 	.owner   	= THIS_MODULE,
+	.submit_bio	= dcssblk_submit_bio,
 	.open    	= dcssblk_open,
 	.release 	= dcssblk_release,
 };
@@ -651,8 +651,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	}
 	dev_info->gd->major = dcssblk_major;
 	dev_info->gd->fops = &dcssblk_devops;
-	dev_info->dcssblk_queue =
-		blk_alloc_queue(dcssblk_make_request, NUMA_NO_NODE);
+	dev_info->dcssblk_queue = blk_alloc_queue(NUMA_NO_NODE);
 	dev_info->gd->queue = dev_info->dcssblk_queue;
 	dev_info->gd->private_data = dev_info;
 	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
@@ -868,7 +867,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode)
 }
 
 static blk_qc_t
-dcssblk_make_request(struct request_queue *q, struct bio *bio)
+dcssblk_submit_bio(struct bio *bio)
 {
 	struct dcssblk_dev_info *dev_info;
 	struct bio_vec bvec;
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 5456f0ad5a40..c2536f7767b3 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -182,7 +182,7 @@ static unsigned long xpram_highest_page_index(void)
 /*
  * Block device make request function.
  */
-static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t xpram_submit_bio(struct bio *bio)
 {
 	xpram_device_t *xdev = bio->bi_disk->private_data;
 	struct bio_vec bvec;
@@ -250,6 +250,7 @@ static int xpram_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 static const struct block_device_operations xpram_devops =
 {
 	.owner	= THIS_MODULE,
+	.submit_bio = xpram_submit_bio,
 	.getgeo	= xpram_getgeo,
 };
 
@@ -343,8 +344,7 @@ static int __init xpram_setup_blkdev(void)
 		xpram_disks[i] = alloc_disk(1);
 		if (!xpram_disks[i])
 			goto out;
-		xpram_queues[i] = blk_alloc_queue(xpram_make_request,
-				NUMA_NO_NODE);
+		xpram_queues[i] = blk_alloc_queue(NUMA_NO_NODE);
 		if (!xpram_queues[i]) {
 			put_disk(xpram_disks[i]);
 			goto out;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index faa340b70123..23230c1d031e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -596,6 +596,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t blk_mq_submit_bio(struct bio *bio);
 
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d002defc1789..083ffc5bc51b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -286,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
 
 struct blk_queue_ctx;
 
-typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
-
 struct bio_vec;
 
 enum blk_eh_timer_return {
@@ -398,8 +396,6 @@ struct request_queue {
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
-	make_request_fn		*make_request_fn;
-
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
@@ -1162,7 +1158,7 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 extern void blk_dump_rq_flags(struct request *, char *);
 
 bool __must_check blk_get_queue(struct request_queue *);
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
+struct request_queue *blk_alloc_queue(int node_id);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
@@ -1778,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { }
 
 
 struct block_device_operations {
+	blk_qc_t (*submit_bio) (struct bio *bio);
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
 	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index ee8ec2e68055..1db223710b28 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev,
 	return last;
 }
 
-typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
 typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
 				int flags);
@@ -650,7 +649,7 @@ struct nvm_tgt_type {
 	int flags;
 
 	/* target entry points */
-	nvm_tgt_make_rq_fn *make_rq;
+	const struct block_device_operations *bops;
 	nvm_tgt_capacity_fn *capacity;
 
 	/* module-specific init/teardown */
-- 
cgit v1.2.3


From ed00aabd5eb9fb44d6aff1173234a2e911b9fead Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 10:59:44 +0200
Subject: block: rename generic_make_request to submit_bio_noacct

generic_make_request has always been very confusingly misnamed, so rename
it to submit_bio_noacct to make it clear that it is submit_bio minus
accounting and a few checks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/biodoc.rst                    |  2 +-
 Documentation/fault-injection/fault-injection.rst |  2 +-
 Documentation/trace/ftrace.rst                    |  4 +--
 block/bio.c                                       | 14 +++++-----
 block/blk-core.c                                  | 32 +++++++++++------------
 block/blk-crypto-fallback.c                       |  2 +-
 block/blk-crypto.c                                |  2 +-
 block/blk-merge.c                                 |  2 +-
 block/blk-throttle.c                              |  4 +--
 block/bounce.c                                    |  2 +-
 drivers/block/drbd/drbd_int.h                     |  6 ++---
 drivers/block/drbd/drbd_main.c                    |  2 +-
 drivers/block/drbd/drbd_receiver.c                |  2 +-
 drivers/block/drbd/drbd_req.c                     |  2 +-
 drivers/block/drbd/drbd_worker.c                  |  2 +-
 drivers/block/pktcdvd.c                           |  2 +-
 drivers/lightnvm/pblk-read.c                      |  2 +-
 drivers/md/bcache/bcache.h                        |  2 +-
 drivers/md/bcache/btree.c                         |  2 +-
 drivers/md/bcache/request.c                       |  7 +++--
 drivers/md/dm-cache-target.c                      |  6 ++---
 drivers/md/dm-clone-target.c                      | 10 +++----
 drivers/md/dm-crypt.c                             |  6 ++---
 drivers/md/dm-delay.c                             |  2 +-
 drivers/md/dm-era-target.c                        |  2 +-
 drivers/md/dm-integrity.c                         |  4 +--
 drivers/md/dm-mpath.c                             |  2 +-
 drivers/md/dm-raid1.c                             |  2 +-
 drivers/md/dm-snap-persistent.c                   |  2 +-
 drivers/md/dm-snap.c                              |  6 ++---
 drivers/md/dm-thin.c                              |  4 +--
 drivers/md/dm-verity-target.c                     |  2 +-
 drivers/md/dm-writecache.c                        |  2 +-
 drivers/md/dm-zoned-target.c                      |  2 +-
 drivers/md/dm.c                                   | 10 +++----
 drivers/md/md-faulty.c                            |  4 +--
 drivers/md/md-linear.c                            |  4 +--
 drivers/md/md-multipath.c                         |  4 +--
 drivers/md/raid0.c                                |  8 +++---
 drivers/md/raid1.c                                | 14 +++++-----
 drivers/md/raid10.c                               | 28 ++++++++++----------
 drivers/md/raid5.c                                | 10 +++----
 drivers/nvme/host/multipath.c                     |  2 +-
 include/linux/blkdev.h                            |  2 +-
 44 files changed, 115 insertions(+), 118 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst
index 267384159bf7..afda5e30a82e 100644
--- a/Documentation/block/biodoc.rst
+++ b/Documentation/block/biodoc.rst
@@ -1036,7 +1036,7 @@ Now the generic block layer performs partition-remapping early and thus
 provides drivers with a sector number relative to whole device, rather than
 having to take partition number into account in order to arrive at the true
 sector number. The routine blk_partition_remap() is invoked by
-generic_make_request even before invoking the queue specific ->submit_bio,
+submit_bio_noacct even before invoking the queue specific ->submit_bio,
 so the i/o scheduler also gets to operate on whole disk sector numbers. This
 should typically not require changes to block drivers, it just never gets
 to invoke its own partition sector offset calculations since all bios
diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst
index f51bb21d20e4..f850ad018b70 100644
--- a/Documentation/fault-injection/fault-injection.rst
+++ b/Documentation/fault-injection/fault-injection.rst
@@ -24,7 +24,7 @@ Available fault injection capabilities
 
   injects disk IO errors on devices permitted by setting
   /sys/block/<device>/make-it-fail or
-  /sys/block/<device>/<partition>/make-it-fail. (generic_make_request())
+  /sys/block/<device>/<partition>/make-it-fail. (submit_bio_noacct())
 
 - fail_mmc_request
 
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 430a16283103..80ba765a8237 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -1453,7 +1453,7 @@ function-trace, we get a much larger output::
    => __blk_run_queue_uncond
    => __blk_run_queue
    => blk_queue_bio
-   => generic_make_request
+   => submit_bio_noacct
    => submit_bio
    => submit_bh
    => __ext3_get_inode_loc
@@ -1738,7 +1738,7 @@ tracers.
    => __blk_run_queue_uncond
    => __blk_run_queue
    => blk_queue_bio
-   => generic_make_request
+   => submit_bio_noacct
    => submit_bio
    => submit_bh
    => ext3_bread
diff --git a/block/bio.c b/block/bio.c
index fc1299f9d86a..ef91782fd668 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -358,7 +358,7 @@ static void bio_alloc_rescue(struct work_struct *work)
 		if (!bio)
 			break;
 
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 }
 
@@ -416,19 +416,19 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *   submit the previously allocated bio for IO before attempting to allocate
  *   a new one. Failure to do so can cause deadlocks under memory pressure.
  *
- *   Note that when running under generic_make_request() (i.e. any block
+ *   Note that when running under submit_bio_noacct() (i.e. any block
  *   driver), bios are not submitted until after you return - see the code in
- *   generic_make_request() that converts recursion into iteration, to prevent
+ *   submit_bio_noacct() that converts recursion into iteration, to prevent
  *   stack overflows.
  *
  *   This would normally mean allocating multiple bios under
- *   generic_make_request() would be susceptible to deadlocks, but we have
+ *   submit_bio_noacct() would be susceptible to deadlocks, but we have
  *   deadlock avoidance code that resubmits any blocked bios from a rescuer
  *   thread.
  *
  *   However, we do not guarantee forward progress for allocations from other
  *   mempools. Doing multiple allocations from the same mempool under
- *   generic_make_request() should be avoided - instead, use bio_set's front_pad
+ *   submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
  *   for per bio allocations.
  *
  *   RETURNS:
@@ -457,14 +457,14 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 				 nr_iovecs > 0))
 			return NULL;
 		/*
-		 * generic_make_request() converts recursion to iteration; this
+		 * submit_bio_noacct() converts recursion to iteration; this
 		 * means if we're running beneath it, any bios we allocate and
 		 * submit will not be submitted (and thus freed) until after we
 		 * return.
 		 *
 		 * This exposes us to a potential deadlock if we allocate
 		 * multiple bios from the same bio_set() while running
-		 * underneath generic_make_request(). If we were to allocate
+		 * underneath submit_bio_noacct(). If we were to allocate
 		 * multiple bios (say a stacking block driver that was splitting
 		 * bios), we would deadlock if we exhausted the mempool's
 		 * reserve.
diff --git a/block/blk-core.c b/block/blk-core.c
index cb07a726dd71..ff9a88d2d244 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -956,8 +956,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 	return BLK_STS_OK;
 }
 
-static noinline_for_stack bool
-generic_make_request_checks(struct bio *bio)
+static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_disk->queue;
 	blk_status_t status = BLK_STS_IOERR;
@@ -985,9 +984,8 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	/*
-	 * Filter flush bio's early so that make_request based
-	 * drivers without flush support don't have to worry
-	 * about them.
+	 * Filter flush bio's early so that bio based drivers without flush
+	 * support don't have to worry about them.
 	 */
 	if (op_is_flush(bio->bi_opf) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
@@ -1072,7 +1070,7 @@ end_io:
 	return false;
 }
 
-static blk_qc_t do_make_request(struct bio *bio)
+static blk_qc_t __submit_bio(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_disk;
 	blk_qc_t ret = BLK_QC_T_NONE;
@@ -1087,7 +1085,7 @@ static blk_qc_t do_make_request(struct bio *bio)
 }
 
 /**
- * generic_make_request - re-submit a bio to the block device layer for I/O
+ * submit_bio_noacct - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
  *
  * This is a version of submit_bio() that shall only be used for I/O that is
@@ -1095,7 +1093,7 @@ static blk_qc_t do_make_request(struct bio *bio)
  * systems and other upper level users of the block layer should use
  * submit_bio() instead.
  */
-blk_qc_t generic_make_request(struct bio *bio)
+blk_qc_t submit_bio_noacct(struct bio *bio)
 {
 	/*
 	 * bio_list_on_stack[0] contains bios submitted by the current
@@ -1106,7 +1104,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
-	if (!generic_make_request_checks(bio))
+	if (!submit_bio_checks(bio))
 		goto out;
 
 	/*
@@ -1114,7 +1112,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * stack usage with stacked devices could be a problem.  So use
 	 * current->bio_list to keep a list of requests submited by a
 	 * ->submit_bio method.  current->bio_list is also used as a
-	 * flag to say if generic_make_request is currently active in this
+	 * flag to say if submit_bio_noacct is currently active in this
 	 * task or not.  If it is NULL, then no make_request is active.  If
 	 * it is non-NULL, then a make_request is active, and new requests
 	 * should be added at the tail
@@ -1132,7 +1130,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * we assign bio_list to a pointer to the bio_list_on_stack,
 	 * thus initialising the bio_list of new bios to be
 	 * added.  ->submit_bio() may indeed add some more bios
-	 * through a recursive call to generic_make_request.  If it
+	 * through a recursive call to submit_bio_noacct.  If it
 	 * did, we find a non-NULL value in bio_list and re-enter the loop
 	 * from the top.  In this case we really did just take the bio
 	 * of the top of the list (no pretending) and so remove it from
@@ -1150,7 +1148,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 			/* Create a fresh bio_list for all subordinate requests */
 			bio_list_on_stack[1] = bio_list_on_stack[0];
 			bio_list_init(&bio_list_on_stack[0]);
-			ret = do_make_request(bio);
+			ret = __submit_bio(bio);
 
 			/* sort new bios into those for a lower level
 			 * and those for the same level
@@ -1174,13 +1172,13 @@ blk_qc_t generic_make_request(struct bio *bio)
 out:
 	return ret;
 }
-EXPORT_SYMBOL(generic_make_request);
+EXPORT_SYMBOL(submit_bio_noacct);
 
 /**
  * direct_make_request - hand a buffer directly to its device driver for I/O
  * @bio:  The bio describing the location in memory and on the device.
  *
- * This function behaves like generic_make_request(), but does not protect
+ * This function behaves like submit_bio_noacct(), but does not protect
  * against recursion.  Must only be used if the called driver is known
  * to be blk-mq based.
  */
@@ -1192,7 +1190,7 @@ blk_qc_t direct_make_request(struct bio *bio)
 		bio_io_error(bio);
 		return BLK_QC_T_NONE;
 	}
-	if (!generic_make_request_checks(bio))
+	if (!submit_bio_checks(bio))
 		return BLK_QC_T_NONE;
 	if (unlikely(bio_queue_enter(bio)))
 		return BLK_QC_T_NONE;
@@ -1263,13 +1261,13 @@ blk_qc_t submit_bio(struct bio *bio)
 		blk_qc_t ret;
 
 		psi_memstall_enter(&pflags);
-		ret = generic_make_request(bio);
+		ret = submit_bio_noacct(bio);
 		psi_memstall_leave(&pflags);
 
 		return ret;
 	}
 
-	return generic_make_request(bio);
+	return submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio);
 
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index 6e49688a2d80..c162b754efbd 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -228,7 +228,7 @@ static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
 			return false;
 		}
 		bio_chain(split_bio, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		*bio_ptr = split_bio;
 	}
 
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 6533c9b36ab8..2d5e60023b08 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -239,7 +239,7 @@ void __blk_crypto_free_request(struct request *rq)
  * kernel crypto API. When the crypto API fallback is used for encryption,
  * blk-crypto may choose to split the bio into 2 - the first one that will
  * continue to be processed and the second one that will be resubmitted via
- * generic_make_request. A bounce bio will be allocated to encrypt the contents
+ * submit_bio_noacct. A bounce bio will be allocated to encrypt the contents
  * of the aforementioned "first one", and *bio_ptr will be updated to this
  * bounce bio.
  *
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 20fa22906041..5196dc145270 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -338,7 +338,7 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
 
 		bio_chain(split, *bio);
 		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
-		generic_make_request(*bio);
+		submit_bio_noacct(*bio);
 		*bio = split;
 	}
 }
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index ad37043297ed..fee3325edf27 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1339,8 +1339,8 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work)
 
 	if (!bio_list_empty(&bio_list_on_stack)) {
 		blk_start_plug(&plug);
-		while((bio = bio_list_pop(&bio_list_on_stack)))
-			generic_make_request(bio);
+		while ((bio = bio_list_pop(&bio_list_on_stack)))
+			submit_bio_noacct(bio);
 		blk_finish_plug(&plug);
 	}
 }
diff --git a/block/bounce.c b/block/bounce.c
index c3aaed070124..431be88a0240 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -309,7 +309,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	if (!passthrough && sectors < bio_sectors(*bio_orig)) {
 		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
 		bio_chain(bio, *bio_orig);
-		generic_make_request(*bio_orig);
+		submit_bio_noacct(*bio_orig);
 		*bio_orig = bio;
 	}
 	bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL :
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 0327408da79c..fe6cb99eb917 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1576,12 +1576,12 @@ void drbd_set_my_capacity(struct drbd_device *device, sector_t size);
 /*
  * used to submit our private bio
  */
-static inline void drbd_generic_make_request(struct drbd_device *device,
+static inline void drbd_submit_bio_noacct(struct drbd_device *device,
 					     int fault_type, struct bio *bio)
 {
 	__release(local);
 	if (!bio->bi_disk) {
-		drbd_err(device, "drbd_generic_make_request: bio->bi_disk == NULL\n");
+		drbd_err(device, "drbd_submit_bio_noacct: bio->bi_disk == NULL\n");
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
 		return;
@@ -1590,7 +1590,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
 	if (drbd_insert_fault(device, fault_type))
 		bio_io_error(bio);
 	else
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 }
 
 void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backing_dev *bdev,
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 2b05de0896e2..7c34cc0ad8cc 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2325,7 +2325,7 @@ static void do_retry(struct work_struct *ws)
 		 * workqueues instead.
 		 */
 
-		/* We are not just doing generic_make_request(),
+		/* We are not just doing submit_bio_noacct(),
 		 * as we want to keep the start_time information. */
 		inc_ap_bio(device);
 		__drbd_make_request(device, bio, start_jif);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 3a3f2b6a821f..c74f561b4eab 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1723,7 +1723,7 @@ next_bio:
 		bios = bios->bi_next;
 		bio->bi_next = NULL;
 
-		drbd_generic_make_request(device, fault_type, bio);
+		drbd_submit_bio_noacct(device, fault_type, bio);
 	} while (bios);
 	return 0;
 
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c7e14c9a6e5f..674be09b2da9 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1164,7 +1164,7 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 		else if (bio_op(bio) == REQ_OP_DISCARD)
 			drbd_process_discard_or_zeroes_req(req, EE_TRIM);
 		else
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		put_ldev(device);
 	} else
 		bio_io_error(bio);
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 2b89c9f2ca70..7c903de5c4e1 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1525,7 +1525,7 @@ int w_restart_disk_io(struct drbd_work *w, int cancel)
 
 	drbd_req_make_private_bio(req, req->master_bio);
 	bio_set_dev(req->private_bio, device->ldev->backing_bdev);
-	generic_make_request(req->private_bio);
+	submit_bio_noacct(req->private_bio);
 
 	return 0;
 }
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 5588bd4cd267..4becc1efe775 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -913,7 +913,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
 		}
 
 		atomic_inc(&pd->cdrw.pending_bios);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 }
 
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 140927ebf41e..c28537a489bc 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -320,7 +320,7 @@ split_retry:
 		split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL,
 					&pblk_bio_set);
 		bio_chain(split_bio, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 
 		/* New bio contains first N sectors of the previous one, so
 		 * we can continue to use existing rqd, but we need to shrink
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 221e0191b687..3c708e8b5e2d 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -929,7 +929,7 @@ static inline void closure_bio_submit(struct cache_set *c,
 		bio_endio(bio);
 		return;
 	}
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 }
 
 /*
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 6548a601edf0..d5c51e332046 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -959,7 +959,7 @@ err:
  * bch_btree_node_get - find a btree node in the cache and lock it, reading it
  * in from disk if necessary.
  *
- * If IO is necessary and running under generic_make_request, returns -EAGAIN.
+ * If IO is necessary and running under submit_bio_noacct, returns -EAGAIN.
  *
  * The btree node will have either a read or a write lock held, depending on
  * level and op->lock.
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index fc5702b10074..dd012ebface0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
 		bio->bi_end_io(bio);
 	else
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 }
 
 static void quit_max_writeback_rate(struct cache_set *c,
@@ -1197,7 +1197,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
 		if (!bio->bi_iter.bi_size) {
 			/*
 			 * can't call bch_journal_meta from under
-			 * generic_make_request
+			 * submit_bio_noacct
 			 */
 			continue_at_nobarrier(&s->cl,
 					      cached_dev_nodata,
@@ -1311,8 +1311,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 
 	if (!bio->bi_iter.bi_size) {
 		/*
-		 * can't call bch_journal_meta from under
-		 * generic_make_request
+		 * can't call bch_journal_meta from under submit_bio_noacct
 		 */
 		continue_at_nobarrier(&s->cl,
 				      flash_dev_nodata,
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index d3bb355819a4..9eccced92896 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -886,7 +886,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio)
 static void accounted_request(struct cache *cache, struct bio *bio)
 {
 	accounted_begin(cache, bio);
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 }
 
 static void issue_op(struct bio *bio, void *context)
@@ -1792,7 +1792,7 @@ static bool process_bio(struct cache *cache, struct bio *bio)
 	bool commit_needed;
 
 	if (map_bio(cache, bio, get_bio_block(cache, bio), &commit_needed) == DM_MAPIO_REMAPPED)
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 
 	return commit_needed;
 }
@@ -1858,7 +1858,7 @@ static bool process_discard_bio(struct cache *cache, struct bio *bio)
 
 	if (cache->features.discard_passdown) {
 		remap_to_origin(cache, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	} else
 		bio_endio(bio);
 
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 5ce96ddf1ce1..59ed8a67c2e3 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -330,7 +330,7 @@ static void submit_bios(struct bio_list *bios)
 	blk_start_plug(&plug);
 
 	while ((bio = bio_list_pop(bios)))
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 
 	blk_finish_plug(&plug);
 }
@@ -346,7 +346,7 @@ static void submit_bios(struct bio_list *bios)
 static void issue_bio(struct clone *clone, struct bio *bio)
 {
 	if (!bio_triggers_commit(clone, bio)) {
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		return;
 	}
 
@@ -473,7 +473,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ
 		bio_region_range(clone, bio, &rs, &nr_regions);
 		trim_bio(bio, region_to_sector(clone, rs),
 			 nr_regions << clone->region_shift);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	} else
 		bio_endio(bio);
 }
@@ -865,7 +865,7 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio
 	bio->bi_private = hd;
 
 	atomic_inc(&hd->clone->hydrations_in_flight);
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 }
 
 /*
@@ -1281,7 +1281,7 @@ static void process_deferred_flush_bios(struct clone *clone)
 			 */
 			bio_endio(bio);
 		} else {
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		}
 	}
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 000ddfab5ba0..ad324abb8c49 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1789,7 +1789,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 		return 1;
 	}
 
-	generic_make_request(clone);
+	submit_bio_noacct(clone);
 	return 0;
 }
 
@@ -1815,7 +1815,7 @@ static void kcryptd_io_write(struct dm_crypt_io *io)
 {
 	struct bio *clone = io->ctx.bio_out;
 
-	generic_make_request(clone);
+	submit_bio_noacct(clone);
 }
 
 #define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node)
@@ -1893,7 +1893,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) {
-		generic_make_request(clone);
+		submit_bio_noacct(clone);
 		return;
 	}
 
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index f496213f8b67..2628a832787b 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -72,7 +72,7 @@ static void flush_bios(struct bio *bio)
 	while (bio) {
 		n = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = n;
 	}
 }
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index bdb84b8e7162..566ddbdb16a4 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1265,7 +1265,7 @@ static void process_deferred_bios(struct era *era)
 			bio_io_error(bio);
 	else
 		while ((bio = bio_list_pop(&marked_bios)))
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 }
 
 static void process_rpc_calls(struct era *era)
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 81dc5ff08909..ae866e469e1b 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2115,12 +2115,12 @@ offload_to_thread:
 		dio->in_flight = (atomic_t)ATOMIC_INIT(1);
 		dio->completion = NULL;
 
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 
 		return;
 	}
 
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 
 	if (need_sync_io) {
 		wait_for_completion_io(&read_comp);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 78cff42d987e..73bb23de6336 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -677,7 +677,7 @@ static void process_queued_bios(struct work_struct *work)
 			bio_endio(bio);
 			break;
 		case DM_MAPIO_REMAPPED:
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 			break;
 		case DM_MAPIO_SUBMITTED:
 			break;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 2f655d9f4200..fa09bc4e4c54 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -779,7 +779,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 			wakeup_mirrord(ms);
 		} else {
 			map_bio(get_default_mirror(ms), bio);
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		}
 	}
 }
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 963d3774c93e..2d1d4a4c399c 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -252,7 +252,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op,
 
 	/*
 	 * Issue the synchronous I/O from a different thread
-	 * to avoid generic_make_request recursion.
+	 * to avoid submit_bio_noacct recursion.
 	 */
 	INIT_WORK_ONSTACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 6b11a266299f..4668b2cd98f4 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1568,7 +1568,7 @@ static void flush_bios(struct bio *bio)
 	while (bio) {
 		n = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = n;
 	}
 }
@@ -1588,7 +1588,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio)
 		bio->bi_next = NULL;
 		r = do_origin(s->origin, bio, false);
 		if (r == DM_MAPIO_REMAPPED)
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		bio = n;
 	}
 }
@@ -1829,7 +1829,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
 	bio->bi_end_io = full_bio_end_io;
 	bio->bi_private = callback_data;
 
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 }
 
 static struct dm_snap_pending_exception *
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fa8d5464c1fb..fe2de2888709 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -758,7 +758,7 @@ static void issue(struct thin_c *tc, struct bio *bio)
 	struct pool *pool = tc->pool;
 
 	if (!bio_triggers_commit(tc, bio)) {
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		return;
 	}
 
@@ -2394,7 +2394,7 @@ static void process_deferred_bios(struct pool *pool)
 		if (bio->bi_opf & REQ_PREFLUSH)
 			bio_endio(bio);
 		else
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 	}
 }
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index eec9f252e935..75fa4d9b7617 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -681,7 +681,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 
 	verity_submit_prefetch(v, io);
 
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 
 	return DM_MAPIO_SUBMITTED;
 }
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 74f3c506f084..62421554b838 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1238,7 +1238,7 @@ static int writecache_flush_thread(void *data)
 					   bio_end_sector(bio));
 			wc_unlock(wc);
 			bio_set_dev(bio, wc->dev->bdev);
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		} else {
 			writecache_flush(wc);
 			wc_unlock(wc);
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index a907a9446c0b..05a3cfefe937 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -140,7 +140,7 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
 	bio_advance(bio, clone->bi_iter.bi_size);
 
 	refcount_inc(&bioctx->ref);
-	generic_make_request(clone);
+	submit_bio_noacct(clone);
 
 	if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
 		zone->wp_block += nr_blocks;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5acfaba3700d..b32b539dbace 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1305,7 +1305,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		if (md->type == DM_TYPE_NVME_BIO_BASED)
 			ret = direct_make_request(clone);
 		else
-			ret = generic_make_request(clone);
+			ret = submit_bio_noacct(clone);
 		break;
 	case DM_MAPIO_KILL:
 		free_tio(tio);
@@ -1652,7 +1652,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 			error = __split_and_process_non_flush(&ci);
 			if (current->bio_list && ci.sector_count && !error) {
 				/*
-				 * Remainder must be passed to generic_make_request()
+				 * Remainder must be passed to submit_bio_noacct()
 				 * so that it gets handled *after* bios already submitted
 				 * have been completely processed.
 				 * We take a clone of the original to store in
@@ -1677,7 +1677,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 
 				bio_chain(b, bio);
 				trace_block_split(md->queue, b, bio->bi_iter.bi_sector);
-				ret = generic_make_request(bio);
+				ret = submit_bio_noacct(bio);
 				break;
 			}
 		}
@@ -1745,7 +1745,7 @@ static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struc
 
 		bio_chain(split, *bio);
 		trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector);
-		generic_make_request(*bio);
+		submit_bio_noacct(*bio);
 		*bio = split;
 	}
 }
@@ -2500,7 +2500,7 @@ static void dm_wq_work(struct work_struct *work)
 			break;
 
 		if (dm_request_based(md))
-			(void) generic_make_request(c);
+			(void) submit_bio_noacct(c);
 		else
 			(void) dm_process_bio(md, map, c);
 	}
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
index 50ad4ba86f0e..fda4cb3f936f 100644
--- a/drivers/md/md-faulty.c
+++ b/drivers/md/md-faulty.c
@@ -169,7 +169,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == WRITE) {
 		/* write request */
 		if (atomic_read(&conf->counters[WriteAll])) {
-			/* special case - don't decrement, don't generic_make_request,
+			/* special case - don't decrement, don't submit_bio_noacct,
 			 * just fail immediately
 			 */
 			bio_io_error(bio);
@@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
 	} else
 		bio_set_dev(bio, conf->rdev->bdev);
 
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 	return true;
 }
 
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 26c75c0199fa..8efada3ee16f 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -267,7 +267,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		struct bio *split = bio_split(bio, end_sector - bio_sector,
 					      GFP_NOIO, &mddev->bio_set);
 		bio_chain(split, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = split;
 	}
 
@@ -286,7 +286,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 					      bio_sector);
 		mddev_check_writesame(mddev, bio);
 		mddev_check_write_zeroes(mddev, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 	return true;
 
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 152f9e65a226..277fdfd9ee54 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -131,7 +131,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	mp_bh->bio.bi_private = mp_bh;
 	mddev_check_writesame(mddev, &mp_bh->bio);
 	mddev_check_write_zeroes(mddev, &mp_bh->bio);
-	generic_make_request(&mp_bh->bio);
+	submit_bio_noacct(&mp_bh->bio);
 	return true;
 }
 
@@ -348,7 +348,7 @@ static void multipathd(struct md_thread *thread)
 			bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
 			bio->bi_end_io = multipath_end_request;
 			bio->bi_private = mp_bh;
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		}
 	}
 	spin_unlock_irqrestore(&conf->device_lock, flags);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 322386ff5d22..e9e91c8d8afc 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -495,7 +495,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
 			&mddev->bio_set);
 		bio_chain(split, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = split;
 		end = zone->zone_end;
 	} else
@@ -559,7 +559,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
 				discard_bio, disk_devt(mddev->gendisk),
 				bio->bi_iter.bi_sector);
-		generic_make_request(discard_bio);
+		submit_bio_noacct(discard_bio);
 	}
 	bio_endio(bio);
 }
@@ -600,7 +600,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		struct bio *split = bio_split(bio, sectors, GFP_NOIO,
 					      &mddev->bio_set);
 		bio_chain(split, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = split;
 	}
 
@@ -633,7 +633,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 				disk_devt(mddev->gendisk), bio_sector);
 	mddev_check_writesame(mddev, bio);
 	mddev_check_write_zeroes(mddev, bio);
-	generic_make_request(bio);
+	submit_bio_noacct(bio);
 	return true;
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index dcd27f3da84e..2aa2649cca66 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -834,7 +834,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 			/* Just ignore it */
 			bio_endio(bio);
 		else
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		bio = next;
 		cond_resched();
 	}
@@ -1312,7 +1312,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
 		bio_chain(split, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = split;
 		r1_bio->master_bio = bio;
 		r1_bio->sectors = max_sectors;
@@ -1338,7 +1338,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	        trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
 				disk_devt(mddev->gendisk), r1_bio->sector);
 
-	generic_make_request(read_bio);
+	submit_bio_noacct(read_bio);
 }
 
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
@@ -1483,7 +1483,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		struct bio *split = bio_split(bio, max_sectors,
 					      GFP_NOIO, &conf->bio_split);
 		bio_chain(split, bio);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		bio = split;
 		r1_bio->master_bio = bio;
 		r1_bio->sectors = max_sectors;
@@ -2240,7 +2240,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 		atomic_inc(&r1_bio->remaining);
 		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
 
-		generic_make_request(wbio);
+		submit_bio_noacct(wbio);
 	}
 
 	put_sync_write_buf(r1_bio, 1);
@@ -2926,7 +2926,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 				md_sync_acct_bio(bio, nr_sectors);
 				if (read_targets == 1)
 					bio->bi_opf &= ~MD_FAILFAST;
-				generic_make_request(bio);
+				submit_bio_noacct(bio);
 			}
 		}
 	} else {
@@ -2935,7 +2935,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		md_sync_acct_bio(bio, nr_sectors);
 		if (read_targets == 1)
 			bio->bi_opf &= ~MD_FAILFAST;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 	return nr_sectors;
 }
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ec136e44aef7..e45fd56cf584 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -917,7 +917,7 @@ static void flush_pending_writes(struct r10conf *conf)
 				/* Just ignore it */
 				bio_endio(bio);
 			else
-				generic_make_request(bio);
+				submit_bio_noacct(bio);
 			bio = next;
 		}
 		blk_finish_plug(&plug);
@@ -1102,7 +1102,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 			/* Just ignore it */
 			bio_endio(bio);
 		else
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		bio = next;
 	}
 	kfree(plug);
@@ -1194,7 +1194,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 					      gfp, &conf->bio_split);
 		bio_chain(split, bio);
 		allow_barrier(conf);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		wait_barrier(conf);
 		bio = split;
 		r10_bio->master_bio = bio;
@@ -1221,7 +1221,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	        trace_block_bio_remap(read_bio->bi_disk->queue,
 	                              read_bio, disk_devt(mddev->gendisk),
 	                              r10_bio->sector);
-	generic_make_request(read_bio);
+	submit_bio_noacct(read_bio);
 	return;
 }
 
@@ -1479,7 +1479,7 @@ retry_write:
 					      GFP_NOIO, &conf->bio_split);
 		bio_chain(split, bio);
 		allow_barrier(conf);
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 		wait_barrier(conf);
 		bio = split;
 		r10_bio->master_bio = bio;
@@ -2099,7 +2099,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			tbio->bi_opf |= MD_FAILFAST;
 		tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
 		bio_set_dev(tbio, conf->mirrors[d].rdev->bdev);
-		generic_make_request(tbio);
+		submit_bio_noacct(tbio);
 	}
 
 	/* Now write out to any replacement devices
@@ -2118,7 +2118,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
 			     bio_sectors(tbio));
-		generic_make_request(tbio);
+		submit_bio_noacct(tbio);
 	}
 
 done:
@@ -2241,7 +2241,7 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	wbio = r10_bio->devs[1].bio;
 	wbio2 = r10_bio->devs[1].repl_bio;
 	/* Need to test wbio2->bi_end_io before we call
-	 * generic_make_request as if the former is NULL,
+	 * submit_bio_noacct as if the former is NULL,
 	 * the latter is free to free wbio2.
 	 */
 	if (wbio2 && !wbio2->bi_end_io)
@@ -2249,13 +2249,13 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
-		generic_make_request(wbio);
+		submit_bio_noacct(wbio);
 	}
 	if (wbio2) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
 			     bio_sectors(wbio2));
-		generic_make_request(wbio2);
+		submit_bio_noacct(wbio2);
 	}
 }
 
@@ -2889,7 +2889,7 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf)
  * a number of r10_bio structures, one for each out-of-sync device.
  * As we setup these structures, we collect all bio's together into a list
  * which we then process collectively to add pages, and then process again
- * to pass to generic_make_request.
+ * to pass to submit_bio_noacct.
  *
  * The r10_bio structures are linked using a borrowed master_bio pointer.
  * This link is counted in ->remaining.  When the r10_bio that points to NULL
@@ -3496,7 +3496,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct_bio(bio, nr_sectors);
 			bio->bi_status = 0;
-			generic_make_request(bio);
+			submit_bio_noacct(bio);
 		}
 	}
 
@@ -4654,7 +4654,7 @@ read_more:
 	md_sync_acct_bio(read_bio, r10_bio->sectors);
 	atomic_inc(&r10_bio->remaining);
 	read_bio->bi_next = NULL;
-	generic_make_request(read_bio);
+	submit_bio_noacct(read_bio);
 	sectors_done += nr_sectors;
 	if (sector_nr <= last)
 		goto read_more;
@@ -4717,7 +4717,7 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		md_sync_acct_bio(b, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
-		generic_make_request(b);
+		submit_bio_noacct(b);
 	}
 	end_reshape_request(r10_bio);
 }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ab8067f9ce8c..8dea4398b191 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -873,7 +873,7 @@ static void dispatch_bio_list(struct bio_list *tmp)
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(tmp)))
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 }
 
 static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b)
@@ -1151,7 +1151,7 @@ again:
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
-				generic_make_request(bi);
+				submit_bio_noacct(bi);
 		}
 		if (rrdev) {
 			if (s->syncing || s->expanding || s->expanded
@@ -1201,7 +1201,7 @@ again:
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
-				generic_make_request(rbi);
+				submit_bio_noacct(rbi);
 		}
 		if (!rdev && !rrdev) {
 			if (op_is_write(op))
@@ -5289,7 +5289,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 			trace_block_bio_remap(align_bi->bi_disk->queue,
 					      align_bi, disk_devt(mddev->gendisk),
 					      raid_bio->bi_iter.bi_sector);
-		generic_make_request(align_bi);
+		submit_bio_noacct(align_bi);
 		return 1;
 	} else {
 		rcu_read_unlock();
@@ -5309,7 +5309,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 		struct r5conf *conf = mddev->private;
 		split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split);
 		bio_chain(split, raid_bio);
-		generic_make_request(raid_bio);
+		submit_bio_noacct(raid_bio);
 		raid_bio = split;
 	}
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 89afcf943bf8..f07fa47c251d 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -351,7 +351,7 @@ static void nvme_requeue_work(struct work_struct *work)
 		 * path.
 		 */
 		bio->bi_disk = head->disk;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 083ffc5bc51b..b73cfa6a5141 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -852,7 +852,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
-extern blk_qc_t generic_make_request(struct bio *bio);
+blk_qc_t submit_bio_noacct(struct bio *bio);
 extern blk_qc_t direct_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
-- 
cgit v1.2.3


From 5a6c35f9af416114588298aa7a90b15bbed15a41 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 10:59:47 +0200
Subject: block: remove direct_make_request

Now that submit_bio_noacct has a decent blk-mq fast path there is no
more need for this bypass.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c              | 28 ----------------------------
 drivers/md/dm.c               |  5 +----
 drivers/nvme/host/multipath.c |  2 +-
 include/linux/blkdev.h        |  1 -
 4 files changed, 2 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 2ff166f0d24e..bf882b8d8445 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1211,34 +1211,6 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
-/**
- * direct_make_request - hand a buffer directly to its device driver for I/O
- * @bio:  The bio describing the location in memory and on the device.
- *
- * This function behaves like submit_bio_noacct(), but does not protect
- * against recursion.  Must only be used if the called driver is known
- * to be blk-mq based.
- */
-blk_qc_t direct_make_request(struct bio *bio)
-{
-	struct gendisk *disk = bio->bi_disk;
-
-	if (WARN_ON_ONCE(!disk->queue->mq_ops)) {
-		bio_io_error(bio);
-		return BLK_QC_T_NONE;
-	}
-	if (!submit_bio_checks(bio))
-		return BLK_QC_T_NONE;
-	if (unlikely(bio_queue_enter(bio)))
-		return BLK_QC_T_NONE;
-	if (!blk_crypto_bio_prep(&bio)) {
-		blk_queue_exit(disk->queue);
-		return BLK_QC_T_NONE;
-	}
-	return blk_mq_submit_bio(bio);
-}
-EXPORT_SYMBOL_GPL(direct_make_request);
-
 /**
  * submit_bio - submit a bio to the block device layer for I/O
  * @bio: The &struct bio which describes the I/O
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b32b539dbace..2cb33896198c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1302,10 +1302,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		/* the bio has been remapped so dispatch it */
 		trace_block_bio_remap(clone->bi_disk->queue, clone,
 				      bio_dev(io->orig_bio), sector);
-		if (md->type == DM_TYPE_NVME_BIO_BASED)
-			ret = direct_make_request(clone);
-		else
-			ret = submit_bio_noacct(clone);
+		ret = submit_bio_noacct(clone);
 		break;
 	case DM_MAPIO_KILL:
 		free_tio(tio);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f07fa47c251d..a986ac52c4cc 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -314,7 +314,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 		trace_block_bio_remap(bio->bi_disk->queue, bio,
 				      disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
-		ret = direct_make_request(bio);
+		ret = submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
 		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b73cfa6a5141..1cc913ffdbe2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -853,7 +853,6 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 blk_qc_t submit_bio_noacct(struct bio *bio);
-extern blk_qc_t direct_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
-- 
cgit v1.2.3


From 6b7b181b67aa8177e57732723106a0411570a86d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Jun 2020 10:01:55 +0200
Subject: block: remove the bd_block_size field from struct block_device

We can trivially calculate the block size from the inodes i_blkbits
variable.  Use that instead of keeping two redundant copies of the
information in slightly different formats.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c            | 9 ++-------
 include/linux/blk_types.h | 1 -
 include/linux/blkdev.h    | 2 +-
 3 files changed, 3 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8b7a9c76d33e..06d31e459048 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -105,10 +105,7 @@ EXPORT_SYMBOL(invalidate_bdev);
 
 static void set_init_blocksize(struct block_device *bdev)
 {
-	unsigned bsize = bdev_logical_block_size(bdev);
-
-	bdev->bd_block_size = bsize;
-	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
 }
 
 int set_blocksize(struct block_device *bdev, int size)
@@ -122,9 +119,8 @@ int set_blocksize(struct block_device *bdev, int size)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
-	if (bdev->bd_block_size != size) {
+	if (bdev->bd_inode->i_blkbits != blksize_bits(size)) {
 		sync_blockdev(bdev);
-		bdev->bd_block_size = size;
 		bdev->bd_inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
 	}
@@ -889,7 +885,6 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index a602132cbe32..b01cd19bbe8a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -33,7 +33,6 @@ struct block_device {
 	struct list_head	bd_holder_disks;
 #endif
 	struct block_device *	bd_contains;
-	unsigned		bd_block_size;
 	u8			bd_partno;
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1cc913ffdbe2..408eb66a82fd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1543,7 +1543,7 @@ static inline unsigned int blksize_bits(unsigned int size)
 
 static inline unsigned int block_size(struct block_device *bdev)
 {
-	return bdev->bd_block_size;
+	return 1 << bdev->bd_inode->i_blkbits;
 }
 
 int kblockd_schedule_work(struct work_struct *work);
-- 
cgit v1.2.3


From e556f6ba10f0f3c3484a1597382ceaec1e7bc700 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Jun 2020 10:01:56 +0200
Subject: block: remove the bd_queue field from struct block_device

Just use bd_disk->queue instead.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/dax/super.c        |  2 +-
 drivers/md/md.c            |  2 +-
 drivers/nvme/target/core.c |  2 +-
 fs/block_dev.c             | 11 ++++-------
 fs/direct-io.c             |  4 ++--
 fs/xfs/xfs_pwork.c         |  2 +-
 include/linux/blk_types.h  |  1 -
 mm/swapfile.c              |  2 +-
 8 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 8e32345be0f7..f50828526331 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -59,7 +59,7 @@ EXPORT_SYMBOL(bdev_dax_pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 {
-	if (!blk_queue_dax(bdev->bd_queue))
+	if (!blk_queue_dax(bdev->bd_disk->queue))
 		return NULL;
 	return dax_get_by_host(bdev->bd_disk->disk_name);
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7b7cb49be351..8bb69c61afe0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -199,7 +199,7 @@ static int rdevs_init_serial(struct mddev *mddev)
 static int rdev_need_serial(struct md_rdev *rdev)
 {
 	return (rdev && rdev->mddev->bitmap_info.max_write_behind > 0 &&
-		rdev->bdev->bd_queue->nr_hw_queues != 1 &&
+		rdev->bdev->bd_disk->queue->nr_hw_queues != 1 &&
 		test_bit(WriteMostly, &rdev->flags));
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6e2f623e472e..6816507fba58 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -467,7 +467,7 @@ static int nvmet_p2pmem_ns_enable(struct nvmet_ns *ns)
 		return -EINVAL;
 	}
 
-	if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) {
+	if (!blk_queue_pci_p2pdma(ns->bdev->bd_disk->queue)) {
 		pr_err("peer-to-peer DMA is not supported by the driver of %s\n",
 		       ns->device_path);
 		return -EINVAL;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 06d31e459048..68cb08bc1b7a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -693,12 +693,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return result;
 
-	result = blk_queue_enter(bdev->bd_queue, 0);
+	result = blk_queue_enter(bdev->bd_disk->queue, 0);
 	if (result)
 		return result;
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
 			      REQ_OP_READ);
-	blk_queue_exit(bdev->bd_queue);
+	blk_queue_exit(bdev->bd_disk->queue);
 	return result;
 }
 
@@ -729,7 +729,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
-	result = blk_queue_enter(bdev->bd_queue, 0);
+	result = blk_queue_enter(bdev->bd_disk->queue, 0);
 	if (result)
 		return result;
 
@@ -742,7 +742,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		clean_page_buffers(page);
 		unlock_page(page);
 	}
-	blk_queue_exit(bdev->bd_queue);
+	blk_queue_exit(bdev->bd_disk->queue);
 	return result;
 }
 
@@ -1568,7 +1568,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	if (!bdev->bd_openers) {
 		first_open = true;
 		bdev->bd_disk = disk;
-		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		bdev->bd_partno = partno;
 
@@ -1589,7 +1588,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					disk_put_part(bdev->bd_part);
 					bdev->bd_part = NULL;
 					bdev->bd_disk = NULL;
-					bdev->bd_queue = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
 					put_disk_and_module(disk);
@@ -1666,7 +1664,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
-	bdev->bd_queue = NULL;
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 6d5370eac2a8..183299892465 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1387,8 +1387,8 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 * Attempt to prefetch the pieces we likely need later.
 	 */
 	prefetch(&bdev->bd_disk->part_tbl);
-	prefetch(bdev->bd_queue);
-	prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
+	prefetch(bdev->bd_disk->queue);
+	prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES);
 
 	return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block,
 				     end_io, submit_io, flags);
diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c
index 4bcc3e61056c..b03333f1c84a 100644
--- a/fs/xfs/xfs_pwork.c
+++ b/fs/xfs/xfs_pwork.c
@@ -132,5 +132,5 @@ xfs_pwork_guess_datadev_parallelism(
 	 * For now we'll go with the most conservative setting possible,
 	 * which is two threads for an SSD and 1 thread everywhere else.
 	 */
-	return blk_queue_nonrot(btp->bt_bdev->bd_queue) ? 2 : 1;
+	return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1;
 }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b01cd19bbe8a..667cd365fd04 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -39,7 +39,6 @@ struct block_device {
 	unsigned		bd_part_count;
 	int			bd_invalidated;
 	struct gendisk *	bd_disk;
-	struct request_queue *  bd_queue;
 	struct backing_dev_info *bd_bdi;
 	struct list_head	bd_list;
 	/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 987276c557d1..6c26916e95fd 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2929,7 +2929,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		 * write only restriction.  Hence zoned block devices are not
 		 * suitable for swapping.  Disallow them here.
 		 */
-		if (blk_queue_is_zoned(p->bdev->bd_queue))
+		if (blk_queue_is_zoned(p->bdev->bd_disk->queue))
 			return -EINVAL;
 		p->flags |= SWP_BLKDEV;
 	} else if (S_ISREG(inode->i_mode)) {
-- 
cgit v1.2.3


From 47b5e00322a3033851ab304f3c3873aebdfb4979 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Jun 2020 10:01:57 +0200
Subject: block: remove the unused bd_private field from struct block_device

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 667cd365fd04..b5f7105806e4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -41,13 +41,6 @@ struct block_device {
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
 	struct list_head	bd_list;
-	/*
-	 * Private data.  You must have bd_claim'ed the block_device
-	 * to use this.  NOTE:  bd_claim allows an owner to claim
-	 * the same device multiple times, the owner must take special
-	 * care to not mess up bd_private for that case.
-	 */
-	unsigned long		bd_private;
 
 	/* The counter of freeze processes */
 	int			bd_fsfreeze_count;
-- 
cgit v1.2.3


From 1008fe6dc36dd87dfd02d4307f49162f0b4f1665 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Jun 2020 10:01:58 +0200
Subject: block: remove the all_bdevs list

Instead just iterate over the inodes for the block device superblock.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c            | 22 +++++++---------------
 include/linux/blk_types.h |  1 -
 2 files changed, 7 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 68cb08bc1b7a..2d2fcb50e78e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -773,7 +773,6 @@ static void init_once(void *foo)
 
 	memset(bdev, 0, sizeof(*bdev));
 	mutex_init(&bdev->bd_mutex);
-	INIT_LIST_HEAD(&bdev->bd_list);
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
@@ -789,9 +788,6 @@ static void bdev_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
 	clear_inode(inode);
-	spin_lock(&bdev_lock);
-	list_del_init(&bdev->bd_list);
-	spin_unlock(&bdev_lock);
 	/* Detach inode from wb early as bdi_put() may free bdi->wb */
 	inode_detach_wb(inode);
 	if (bdev->bd_bdi != &noop_backing_dev_info) {
@@ -866,8 +862,6 @@ static int bdev_set(struct inode *inode, void *data)
 	return 0;
 }
 
-static LIST_HEAD(all_bdevs);
-
 struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
@@ -892,9 +886,6 @@ struct block_device *bdget(dev_t dev)
 		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		spin_lock(&bdev_lock);
-		list_add(&bdev->bd_list, &all_bdevs);
-		spin_unlock(&bdev_lock);
 		unlock_new_inode(inode);
 	}
 	return bdev;
@@ -915,13 +906,14 @@ EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
-	struct block_device *bdev;
+	struct inode *inode;
 	long ret = 0;
-	spin_lock(&bdev_lock);
-	list_for_each_entry(bdev, &all_bdevs, bd_list) {
-		ret += bdev->bd_inode->i_mapping->nrpages;
-	}
-	spin_unlock(&bdev_lock);
+
+	spin_lock(&blockdev_superblock->s_inode_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list)
+		ret += inode->i_mapping->nrpages;
+	spin_unlock(&blockdev_superblock->s_inode_list_lock);
+
 	return ret;
 }
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b5f7105806e4..07facaf62b72 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -40,7 +40,6 @@ struct block_device {
 	int			bd_invalidated;
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
-	struct list_head	bd_list;
 
 	/* The counter of freeze processes */
 	int			bd_fsfreeze_count;
-- 
cgit v1.2.3


From d141b8bc5773cbbaf5b8530f08f94fc10fff9e8c Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 29 Jun 2020 23:28:43 -0700
Subject: perf: Expose get/put_callchain_entry()

Sanitize and expose get/put_callchain_entry(). This would be used by bpf
stack map.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630062846.664389-2-songliubraving@fb.com
---
 include/linux/perf_event.h |  2 ++
 kernel/events/callchain.c  | 13 ++++++-------
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b4bb32082342..00ab5efa3833 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1244,6 +1244,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
+extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
+extern void put_callchain_entry(int rctx);
 
 extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 334d48b16c36..c6ce894e4ce9 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -149,7 +149,7 @@ void put_callchain_buffers(void)
 	}
 }
 
-static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+struct perf_callchain_entry *get_callchain_entry(int *rctx)
 {
 	int cpu;
 	struct callchain_cpus_entries *entries;
@@ -159,8 +159,10 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 		return NULL;
 
 	entries = rcu_dereference(callchain_cpus_entries);
-	if (!entries)
+	if (!entries) {
+		put_recursion_context(this_cpu_ptr(callchain_recursion), *rctx);
 		return NULL;
+	}
 
 	cpu = smp_processor_id();
 
@@ -168,7 +170,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 		(*rctx * perf_callchain_entry__sizeof()));
 }
 
-static void
+void
 put_callchain_entry(int rctx)
 {
 	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
@@ -183,11 +185,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 	int rctx;
 
 	entry = get_callchain_entry(&rctx);
-	if (rctx == -1)
-		return NULL;
-
 	if (!entry)
-		goto exit_put;
+		return NULL;
 
 	ctx.entry     = entry;
 	ctx.max_stack = max_stack;
-- 
cgit v1.2.3


From fa28dcb82a38f8e3993b0fae9106b1a80b59e4f0 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 29 Jun 2020 23:28:44 -0700
Subject: bpf: Introduce helper bpf_get_task_stack()

Introduce helper bpf_get_task_stack(), which dumps stack trace of given
task. This is different to bpf_get_stack(), which gets stack track of
current task. One potential use case of bpf_get_task_stack() is to call
it from bpf_iter__task and dump all /proc/<pid>/stack to a seq_file.

bpf_get_task_stack() uses stack_trace_save_tsk() instead of
get_perf_callchain() for kernel stack. The benefit of this choice is that
stack_trace_save_tsk() doesn't require changes in arch/. The downside of
using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the
stack trace to unsigned long array. For 32-bit systems, we need to
translate it to u64 array.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 37 +++++++++++++++++++-
 kernel/bpf/stackmap.c          | 77 +++++++++++++++++++++++++++++++++++++++---
 kernel/bpf/verifier.c          |  4 ++-
 kernel/trace/bpf_trace.c       |  2 ++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h | 37 +++++++++++++++++++-
 7 files changed, 153 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3d2ade703a35..0cd7f6884c5c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1627,6 +1627,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
+extern const struct bpf_func_proto bpf_get_task_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0cb8ec948816..da9bf35a26f8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
+ *	Description
+ *		Return a user or a kernel stack in bpf program provided buffer.
+ *		To achieve this, the helper needs *task*, which is a valid
+ *		pointer to struct task_struct. To store the stacktrace, the
+ *		bpf program provides *buf* with	a nonnegative *size*.
+ *
+ *		The last argument, *flags*, holds the number of stack frames to
+ *		skip (from 0 to 255), masked with
+ *		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ *		the following flags:
+ *
+ *		**BPF_F_USER_STACK**
+ *			Collect a user space stack instead of a kernel stack.
+ *		**BPF_F_USER_BUILD_ID**
+ *			Collect buildid+offset instead of ips for user stack,
+ *			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ *		**bpf_get_task_stack**\ () can collect up to
+ *		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ *		to sufficient large buffer size. Note that
+ *		this limit can be controlled with the **sysctl** program, and
+ *		that it should be manually increased in order to profile long
+ *		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ *		::
+ *
+ *			# sysctl kernel.perf_event_max_stack=<new value>
+ *	Return
+ *		A non-negative value equal to or less than *size* on success,
+ *		or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 071f98d0f7c6..5ad72ab2276b 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -348,6 +348,40 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 }
 
+static struct perf_callchain_entry *
+get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
+{
+	struct perf_callchain_entry *entry;
+	int rctx;
+
+	entry = get_callchain_entry(&rctx);
+
+	if (!entry)
+		return NULL;
+
+	entry->nr = init_nr +
+		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
+				     sysctl_perf_event_max_stack - init_nr, 0);
+
+	/* stack_trace_save_tsk() works on unsigned long array, while
+	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is
+	 * necessary to fix this mismatch.
+	 */
+	if (__BITS_PER_LONG != 64) {
+		unsigned long *from = (unsigned long *) entry->ip;
+		u64 *to = entry->ip;
+		int i;
+
+		/* copy data from the end to avoid using extra buffer */
+		for (i = entry->nr - 1; i >= (int)init_nr; i--)
+			to[i] = (u64)(from[i]);
+	}
+
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags)
 {
@@ -448,8 +482,8 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
-	   u64, flags)
+static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -471,13 +505,22 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	if (unlikely(size % elem_size))
 		goto clear;
 
+	/* cannot get valid user stack for task without user_mode regs */
+	if (task && user && !user_mode(regs))
+		goto err_fault;
+
 	num_elem = size / elem_size;
 	if (sysctl_perf_event_max_stack < num_elem)
 		init_nr = 0;
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
+
+	if (kernel && task)
+		trace = get_callchain_entry_for_task(task, init_nr);
+	else
+		trace = get_perf_callchain(regs, init_nr, kernel, user,
+					   sysctl_perf_event_max_stack,
+					   false, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
@@ -505,6 +548,12 @@ clear:
 	return err;
 }
 
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, buf, size, flags);
+}
+
 const struct bpf_func_proto bpf_get_stack_proto = {
 	.func		= bpf_get_stack,
 	.gpl_only	= true,
@@ -515,6 +564,26 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	struct pt_regs *regs = task_pt_regs(task);
+
+	return __bpf_get_stack(regs, task, buf, size, flags);
+}
+
+static int bpf_get_task_stack_btf_ids[5];
+const struct bpf_func_proto bpf_get_task_stack_proto = {
+	.func		= bpf_get_task_stack,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_get_task_stack_btf_ids,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7de98906ddf4..b608185e1ffd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4864,7 +4864,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (err)
 		return err;
 
-	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+	if ((func_id == BPF_FUNC_get_stack ||
+	     func_id == BPF_FUNC_get_task_stack) &&
+	    !env->prog->has_callchain_buf) {
 		const char *err_str;
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5d59dda5f661..977ba3b6f6c6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1137,6 +1137,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ringbuf_query_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
+	case BPF_FUNC_get_task_stack:
+		return &bpf_get_task_stack_proto;
 	default:
 		return NULL;
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6bab40ff442e..6843376733df 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -426,6 +426,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -468,6 +469,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0cb8ec948816..da9bf35a26f8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
+ *	Description
+ *		Return a user or a kernel stack in bpf program provided buffer.
+ *		To achieve this, the helper needs *task*, which is a valid
+ *		pointer to struct task_struct. To store the stacktrace, the
+ *		bpf program provides *buf* with	a nonnegative *size*.
+ *
+ *		The last argument, *flags*, holds the number of stack frames to
+ *		skip (from 0 to 255), masked with
+ *		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ *		the following flags:
+ *
+ *		**BPF_F_USER_STACK**
+ *			Collect a user space stack instead of a kernel stack.
+ *		**BPF_F_USER_BUILD_ID**
+ *			Collect buildid+offset instead of ips for user stack,
+ *			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ *		**bpf_get_task_stack**\ () can collect up to
+ *		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ *		to sufficient large buffer size. Note that
+ *		this limit can be controlled with the **sysctl** program, and
+ *		that it should be manually increased in order to profile long
+ *		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ *		::
+ *
+ *			# sysctl kernel.perf_event_max_stack=<new value>
+ *	Return
+ *		A non-negative value equal to or less than *size* on success,
+ *		or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 1fc2dd1864c2b18860fb619caeee758504c3aac8 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:40 +0100
Subject: firmware: arm_scmi: Add notification protocol-registration

Add the core SCMI notifications protocol-registration support: allow
protocols to register their own set of supported events, during their
initialization phase. Notification core can track multiple platform
instances by their handles.

Link: https://lore.kernel.org/r/20200701155348.52864-2-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/Makefile |   2 +-
 drivers/firmware/arm_scmi/common.h |   4 +
 drivers/firmware/arm_scmi/notify.c | 440 +++++++++++++++++++++++++++++++++++++
 drivers/firmware/arm_scmi/notify.h |  56 +++++
 include/linux/scmi_protocol.h      |   3 +
 5 files changed, 504 insertions(+), 1 deletion(-)
 create mode 100644 drivers/firmware/arm_scmi/notify.c
 create mode 100644 drivers/firmware/arm_scmi/notify.h

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index 70c5a8c986a5..6f9cbc4aef22 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y	= scmi-bus.o scmi-driver.o scmi-protocols.o scmi-transport.o
 scmi-bus-y = bus.o
-scmi-driver-y = driver.o
+scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index 31fe5a22a011..c113e578cc6c 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -6,6 +6,8 @@
  *
  * Copyright (C) 2018 ARM Ltd.
  */
+#ifndef _SCMI_COMMON_H
+#define _SCMI_COMMON_H
 
 #include <linux/bitfield.h>
 #include <linux/completion.h>
@@ -235,3 +237,5 @@ void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem,
 void shmem_clear_channel(struct scmi_shared_mem __iomem *shmem);
 bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem,
 		     struct scmi_xfer *xfer);
+
+#endif /* _SCMI_COMMON_H */
diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
new file mode 100644
index 000000000000..0505433043d8
--- /dev/null
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -0,0 +1,440 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Management Interface (SCMI) Notification support
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+/**
+ * DOC: Theory of operation
+ *
+ * SCMI Protocol specification allows the platform to signal events to
+ * interested agents via notification messages: this is an implementation
+ * of the dispatch and delivery of such notifications to the interested users
+ * inside the Linux kernel.
+ *
+ * An SCMI Notification core instance is initialized for each active platform
+ * instance identified by the means of the usual &struct scmi_handle.
+ *
+ * Each SCMI Protocol implementation, during its initialization, registers with
+ * this core its set of supported events using scmi_register_protocol_events():
+ * all the needed descriptors are stored in the &struct registered_protocols and
+ * &struct registered_events arrays.
+ */
+
+#define dev_fmt(fmt) "SCMI Notifications - " fmt
+
+#include <linux/bitfield.h>
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/kfifo.h>
+#include <linux/mutex.h>
+#include <linux/refcount.h>
+#include <linux/scmi_protocol.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "notify.h"
+
+#define SCMI_MAX_PROTO		256
+
+#define PROTO_ID_MASK		GENMASK(31, 24)
+#define EVT_ID_MASK		GENMASK(23, 16)
+#define SRC_ID_MASK		GENMASK(15, 0)
+
+/*
+ * Builds an unsigned 32bit key from the given input tuple to be used
+ * as a key in hashtables.
+ */
+#define MAKE_HASH_KEY(p, e, s)			\
+	(FIELD_PREP(PROTO_ID_MASK, (p)) |	\
+	   FIELD_PREP(EVT_ID_MASK, (e)) |	\
+	   FIELD_PREP(SRC_ID_MASK, (s)))
+
+#define MAKE_ALL_SRCS_KEY(p, e)		MAKE_HASH_KEY((p), (e), SRC_ID_MASK)
+
+struct scmi_registered_events_desc;
+
+/**
+ * struct scmi_notify_instance  - Represents an instance of the notification
+ * core
+ * @gid: GroupID used for devres
+ * @handle: A reference to the platform instance
+ * @registered_protocols: A statically allocated array containing pointers to
+ *			  all the registered protocol-level specific information
+ *			  related to events' handling
+ *
+ * Each platform instance, represented by a handle, has its own instance of
+ * the notification subsystem represented by this structure.
+ */
+struct scmi_notify_instance {
+	void			*gid;
+	struct scmi_handle	*handle;
+	struct scmi_registered_events_desc	**registered_protocols;
+};
+
+/**
+ * struct events_queue  - Describes a queue and its associated worker
+ * @sz: Size in bytes of the related kfifo
+ * @kfifo: A dedicated Kernel kfifo descriptor
+ *
+ * Each protocol has its own dedicated events_queue descriptor.
+ */
+struct events_queue {
+	size_t		sz;
+	struct kfifo	kfifo;
+};
+
+/**
+ * struct scmi_event_header  - A utility header
+ * @timestamp: The timestamp, in nanoseconds (boottime), which was associated
+ *	       to this event as soon as it entered the SCMI RX ISR
+ * @evt_id: Event ID (corresponds to the Event MsgID for this Protocol)
+ * @payld_sz: Effective size of the embedded message payload which follows
+ * @payld: A reference to the embedded event payload
+ *
+ * This header is prepended to each received event message payload before
+ * queueing it on the related &struct events_queue.
+ */
+struct scmi_event_header {
+	u64	timestamp;
+	u8	evt_id;
+	size_t	payld_sz;
+	u8	payld[];
+} __packed;
+
+struct scmi_registered_event;
+
+/**
+ * struct scmi_registered_events_desc  - Protocol Specific information
+ * @id: Protocol ID
+ * @ops: Protocol specific and event-related operations
+ * @equeue: The embedded per-protocol events_queue
+ * @ni: A reference to the initialized instance descriptor
+ * @eh: A reference to pre-allocated buffer to be used as a scratch area by the
+ *	deferred worker when fetching data from the kfifo
+ * @eh_sz: Size of the pre-allocated buffer @eh
+ * @in_flight: A reference to an in flight &struct scmi_registered_event
+ * @num_events: Number of events in @registered_events
+ * @registered_events: A dynamically allocated array holding all the registered
+ *		       events' descriptors, whose fixed-size is determined at
+ *		       compile time.
+ *
+ * All protocols that register at least one event have their protocol-specific
+ * information stored here, together with the embedded allocated events_queue.
+ * These descriptors are stored in the @registered_protocols array at protocol
+ * registration time.
+ *
+ * Once these descriptors are successfully registered, they are NEVER again
+ * removed or modified since protocols do not unregister ever, so that, once
+ * we safely grab a NON-NULL reference from the array we can keep it and use it.
+ */
+struct scmi_registered_events_desc {
+	u8				id;
+	const struct scmi_event_ops	*ops;
+	struct events_queue		equeue;
+	struct scmi_notify_instance	*ni;
+	struct scmi_event_header	*eh;
+	size_t				eh_sz;
+	void				*in_flight;
+	int				num_events;
+	struct scmi_registered_event	**registered_events;
+};
+
+/**
+ * struct scmi_registered_event  - Event Specific Information
+ * @proto: A reference to the associated protocol descriptor
+ * @evt: A reference to the associated event descriptor (as provided at
+ *       registration time)
+ * @report: A pre-allocated buffer used by the deferred worker to fill a
+ *	    customized event report
+ * @num_sources: The number of possible sources for this event as stated at
+ *		 events' registration time
+ * @sources: A reference to a dynamically allocated array used to refcount the
+ *	     events' enable requests for all the existing sources
+ * @sources_mtx: A mutex to serialize the access to @sources
+ *
+ * All registered events are represented by one of these structures that are
+ * stored in the @registered_events array at protocol registration time.
+ *
+ * Once these descriptors are successfully registered, they are NEVER again
+ * removed or modified since protocols do not unregister ever, so that once we
+ * safely grab a NON-NULL reference from the table we can keep it and use it.
+ */
+struct scmi_registered_event {
+	struct scmi_registered_events_desc *proto;
+	const struct scmi_event	*evt;
+	void		*report;
+	u32		num_sources;
+	refcount_t	*sources;
+	/* locking to serialize the access to sources */
+	struct mutex	sources_mtx;
+};
+
+/**
+ * scmi_kfifo_free()  - Devres action helper to free the kfifo
+ * @kfifo: The kfifo to free
+ */
+static void scmi_kfifo_free(void *kfifo)
+{
+	kfifo_free((struct kfifo *)kfifo);
+}
+
+/**
+ * scmi_initialize_events_queue()  - Allocate/Initialize a kfifo buffer
+ * @ni: A reference to the notification instance to use
+ * @equeue: The events_queue to initialize
+ * @sz: Size of the kfifo buffer to allocate
+ *
+ * Allocate a buffer for the kfifo and initialize it.
+ *
+ * Return: 0 on Success
+ */
+static int scmi_initialize_events_queue(struct scmi_notify_instance *ni,
+					struct events_queue *equeue, size_t sz)
+{
+	if (kfifo_alloc(&equeue->kfifo, sz, GFP_KERNEL))
+		return -ENOMEM;
+	/* Size could have been roundup to power-of-two */
+	equeue->sz = kfifo_size(&equeue->kfifo);
+
+	return devm_add_action_or_reset(ni->handle->dev, scmi_kfifo_free,
+					&equeue->kfifo);
+}
+
+/**
+ * scmi_allocate_registered_events_desc()  - Allocate a registered events'
+ * descriptor
+ * @ni: A reference to the &struct scmi_notify_instance notification instance
+ *	to use
+ * @proto_id: Protocol ID
+ * @queue_sz: Size of the associated queue to allocate
+ * @eh_sz: Size of the event header scratch area to pre-allocate
+ * @num_events: Number of events to support (size of @registered_events)
+ * @ops: Pointer to a struct holding references to protocol specific helpers
+ *	 needed during events handling
+ *
+ * It is supposed to be called only once for each protocol at protocol
+ * initialization time, so it warns if the requested protocol is found already
+ * registered.
+ *
+ * Return: The allocated and registered descriptor on Success
+ */
+static struct scmi_registered_events_desc *
+scmi_allocate_registered_events_desc(struct scmi_notify_instance *ni,
+				     u8 proto_id, size_t queue_sz, size_t eh_sz,
+				     int num_events,
+				     const struct scmi_event_ops *ops)
+{
+	int ret;
+	struct scmi_registered_events_desc *pd;
+
+	/* Ensure protocols are up to date */
+	smp_rmb();
+	if (WARN_ON(ni->registered_protocols[proto_id]))
+		return ERR_PTR(-EINVAL);
+
+	pd = devm_kzalloc(ni->handle->dev, sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+	pd->id = proto_id;
+	pd->ops = ops;
+	pd->ni = ni;
+
+	ret = scmi_initialize_events_queue(ni, &pd->equeue, queue_sz);
+	if (ret)
+		return ERR_PTR(ret);
+
+	pd->eh = devm_kzalloc(ni->handle->dev, eh_sz, GFP_KERNEL);
+	if (!pd->eh)
+		return ERR_PTR(-ENOMEM);
+	pd->eh_sz = eh_sz;
+
+	pd->registered_events = devm_kcalloc(ni->handle->dev, num_events,
+					     sizeof(char *), GFP_KERNEL);
+	if (!pd->registered_events)
+		return ERR_PTR(-ENOMEM);
+	pd->num_events = num_events;
+
+	return pd;
+}
+
+/**
+ * scmi_register_protocol_events()  - Register Protocol Events with the core
+ * @handle: The handle identifying the platform instance against which the
+ *	    the protocol's events are registered
+ * @proto_id: Protocol ID
+ * @queue_sz: Size in bytes of the associated queue to be allocated
+ * @ops: Protocol specific event-related operations
+ * @evt: Event descriptor array
+ * @num_events: Number of events in @evt array
+ * @num_sources: Number of possible sources for this protocol on this
+ *		 platform.
+ *
+ * Used by SCMI Protocols initialization code to register with the notification
+ * core the list of supported events and their descriptors: takes care to
+ * pre-allocate and store all needed descriptors, scratch buffers and event
+ * queues.
+ *
+ * Return: 0 on Success
+ */
+int scmi_register_protocol_events(const struct scmi_handle *handle,
+				  u8 proto_id, size_t queue_sz,
+				  const struct scmi_event_ops *ops,
+				  const struct scmi_event *evt, int num_events,
+				  int num_sources)
+{
+	int i;
+	size_t payld_sz = 0;
+	struct scmi_registered_events_desc *pd;
+	struct scmi_notify_instance *ni;
+
+	if (!ops || !evt)
+		return -EINVAL;
+
+	/* Ensure notify_priv is updated */
+	smp_rmb();
+	if (!handle->notify_priv)
+		return -ENOMEM;
+	ni = handle->notify_priv;
+
+	/* Attach to the notification main devres group */
+	if (!devres_open_group(ni->handle->dev, ni->gid, GFP_KERNEL))
+		return -ENOMEM;
+
+	for (i = 0; i < num_events; i++)
+		payld_sz = max_t(size_t, payld_sz, evt[i].max_payld_sz);
+	payld_sz += sizeof(struct scmi_event_header);
+
+	pd = scmi_allocate_registered_events_desc(ni, proto_id, queue_sz,
+						  payld_sz, num_events, ops);
+	if (IS_ERR(pd))
+		goto err;
+
+	for (i = 0; i < num_events; i++, evt++) {
+		struct scmi_registered_event *r_evt;
+
+		r_evt = devm_kzalloc(ni->handle->dev, sizeof(*r_evt),
+				     GFP_KERNEL);
+		if (!r_evt)
+			goto err;
+		r_evt->proto = pd;
+		r_evt->evt = evt;
+
+		r_evt->sources = devm_kcalloc(ni->handle->dev, num_sources,
+					      sizeof(refcount_t), GFP_KERNEL);
+		if (!r_evt->sources)
+			goto err;
+		r_evt->num_sources = num_sources;
+		mutex_init(&r_evt->sources_mtx);
+
+		r_evt->report = devm_kzalloc(ni->handle->dev,
+					     evt->max_report_sz, GFP_KERNEL);
+		if (!r_evt->report)
+			goto err;
+
+		pd->registered_events[i] = r_evt;
+		/* Ensure events are updated */
+		smp_wmb();
+		dev_dbg(handle->dev, "registered event - %lX\n",
+			MAKE_ALL_SRCS_KEY(r_evt->proto->id, r_evt->evt->id));
+	}
+
+	/* Register protocol and events...it will never be removed */
+	ni->registered_protocols[proto_id] = pd;
+	/* Ensure protocols are updated */
+	smp_wmb();
+
+	devres_close_group(ni->handle->dev, ni->gid);
+
+	return 0;
+
+err:
+	dev_warn(handle->dev, "Proto:%X - Registration Failed !\n", proto_id);
+	/* A failing protocol registration does not trigger full failure */
+	devres_close_group(ni->handle->dev, ni->gid);
+
+	return -ENOMEM;
+}
+
+/**
+ * scmi_notification_init()  - Initializes Notification Core Support
+ * @handle: The handle identifying the platform instance to initialize
+ *
+ * This function lays out all the basic resources needed by the notification
+ * core instance identified by the provided handle: once done, all of the
+ * SCMI Protocols can register their events with the core during their own
+ * initializations.
+ *
+ * Note that failing to initialize the core notifications support does not
+ * cause the whole SCMI Protocols stack to fail its initialization.
+ *
+ * SCMI Notification Initialization happens in 2 steps:
+ * * initialization: basic common allocations (this function)
+ * * registration: protocols asynchronously come into life and registers their
+ *		   own supported list of events with the core; this causes
+ *		   further per-protocol allocations
+ *
+ * Any user's callback registration attempt, referring a still not registered
+ * event, will be registered as pending and finalized later (if possible)
+ * by scmi_protocols_late_init() work.
+ * This allows for lazy initialization of SCMI Protocols due to late (or
+ * missing) SCMI drivers' modules loading.
+ *
+ * Return: 0 on Success
+ */
+int scmi_notification_init(struct scmi_handle *handle)
+{
+	void *gid;
+	struct scmi_notify_instance *ni;
+
+	gid = devres_open_group(handle->dev, NULL, GFP_KERNEL);
+	if (!gid)
+		return -ENOMEM;
+
+	ni = devm_kzalloc(handle->dev, sizeof(*ni), GFP_KERNEL);
+	if (!ni)
+		goto err;
+
+	ni->gid = gid;
+	ni->handle = handle;
+
+	ni->registered_protocols = devm_kcalloc(handle->dev, SCMI_MAX_PROTO,
+						sizeof(char *), GFP_KERNEL);
+	if (!ni->registered_protocols)
+		goto err;
+
+	handle->notify_priv = ni;
+	/* Ensure handle is up to date */
+	smp_wmb();
+
+	dev_info(handle->dev, "Core Enabled.\n");
+
+	devres_close_group(handle->dev, ni->gid);
+
+	return 0;
+
+err:
+	dev_warn(handle->dev, "Initialization Failed.\n");
+	devres_release_group(handle->dev, NULL);
+	return -ENOMEM;
+}
+
+/**
+ * scmi_notification_exit()  - Shutdown and clean Notification core
+ * @handle: The handle identifying the platform instance to shutdown
+ */
+void scmi_notification_exit(struct scmi_handle *handle)
+{
+	struct scmi_notify_instance *ni;
+
+	/* Ensure notify_priv is updated */
+	smp_rmb();
+	if (!handle->notify_priv)
+		return;
+	ni = handle->notify_priv;
+
+	devres_release_group(ni->handle->dev, ni->gid);
+}
diff --git a/drivers/firmware/arm_scmi/notify.h b/drivers/firmware/arm_scmi/notify.h
new file mode 100644
index 000000000000..48702e42995f
--- /dev/null
+++ b/drivers/firmware/arm_scmi/notify.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * System Control and Management Interface (SCMI) Message Protocol
+ * notification header file containing some definitions, structures
+ * and function prototypes related to SCMI Notification handling.
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef _SCMI_NOTIFY_H
+#define _SCMI_NOTIFY_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+#define SCMI_PROTO_QUEUE_SZ	4096
+
+/**
+ * struct scmi_event  - Describes an event to be supported
+ * @id: Event ID
+ * @max_payld_sz: Max possible size for the payload of a notification message
+ * @max_report_sz: Max possible size for the report of a notification message
+ *
+ * Each SCMI protocol, during its initialization phase, can describe the events
+ * it wishes to support in a few struct scmi_event and pass them to the core
+ * using scmi_register_protocol_events().
+ */
+struct scmi_event {
+	u8	id;
+	size_t	max_payld_sz;
+	size_t	max_report_sz;
+};
+
+/**
+ * struct scmi_event_ops  - Protocol helpers called by the notification core.
+ * @set_notify_enabled: Enable/disable the required evt_id/src_id notifications
+ *			using the proper custom protocol commands.
+ *			Return 0 on Success
+ *
+ * Context: Helpers described in &struct scmi_event_ops are called only in
+ *	    process context.
+ */
+struct scmi_event_ops {
+	int (*set_notify_enabled)(const struct scmi_handle *handle,
+				  u8 evt_id, u32 src_id, bool enabled);
+};
+
+int scmi_notification_init(struct scmi_handle *handle);
+void scmi_notification_exit(struct scmi_handle *handle);
+
+int scmi_register_protocol_events(const struct scmi_handle *handle,
+				  u8 proto_id, size_t queue_sz,
+				  const struct scmi_event_ops *ops,
+				  const struct scmi_event *evt, int num_events,
+				  int num_sources);
+
+#endif /* _SCMI_NOTIFY_H */
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 73911d156a39..9a34b02a9cce 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -233,6 +233,8 @@ struct scmi_reset_ops {
  *	protocol(for internal use only)
  * @reset_priv: pointer to private data structure specific to reset
  *	protocol(for internal use only)
+ * @notify_priv: pointer to private data structure specific to notifications
+ *	(for internal use only)
  */
 struct scmi_handle {
 	struct device *dev;
@@ -248,6 +250,7 @@ struct scmi_handle {
 	void *power_priv;
 	void *sensor_priv;
 	void *reset_priv;
+	void *notify_priv;
 };
 
 enum scmi_std_protocol {
-- 
cgit v1.2.3


From e7c215f358a350c4bc326b9cea86763f480a97f9 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:41 +0100
Subject: firmware: arm_scmi: Add notification callbacks-registration

Add the core SCMI notifications callbacks-registration support: allow
users to register their own callbacks against the desired events.

Whenever a registration request is issued against a still non existent
event, mark such request as pending for later processing, in order to
account for possible late initializations of SCMI Protocols associated
to loadable drivers.

Link: https://lore.kernel.org/r/20200701155348.52864-3-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/notify.c | 726 +++++++++++++++++++++++++++++++++++++
 include/linux/scmi_protocol.h      |  46 +++
 2 files changed, 772 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
index 0505433043d8..79615eef0148 100644
--- a/drivers/firmware/arm_scmi/notify.c
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -19,18 +19,50 @@
  * this core its set of supported events using scmi_register_protocol_events():
  * all the needed descriptors are stored in the &struct registered_protocols and
  * &struct registered_events arrays.
+ *
+ * Kernel users interested in some specific event can register their callbacks
+ * providing the usual notifier_block descriptor, since this core implements
+ * events' delivery using the standard Kernel notification chains machinery.
+ *
+ * Given the number of possible events defined by SCMI and the extensibility
+ * of the SCMI Protocol itself, the underlying notification chains are created
+ * and destroyed dynamically on demand depending on the number of users
+ * effectively registered for an event, so that no support structures or chains
+ * are allocated until at least one user has registered a notifier_block for
+ * such event. Similarly, events' generation itself is enabled at the platform
+ * level only after at least one user has registered, and it is shutdown after
+ * the last user for that event has gone.
+ *
+ * All users provided callbacks and allocated notification-chains are stored in
+ * the @registered_events_handlers hashtable. Callbacks' registration requests
+ * for still to be registered events are instead kept in the dedicated common
+ * hashtable @pending_events_handlers.
+ *
+ * An event is identified univocally by the tuple (proto_id, evt_id, src_id)
+ * and is served by its own dedicated notification chain; information contained
+ * in such tuples is used, in a few different ways, to generate the needed
+ * hash-keys.
+ *
+ * Here proto_id and evt_id are simply the protocol_id and message_id numbers
+ * as described in the SCMI Protocol specification, while src_id represents an
+ * optional, protocol dependent, source identifier (like domain_id, perf_id
+ * or sensor_id and so forth).
  */
 
 #define dev_fmt(fmt) "SCMI Notifications - " fmt
+#define pr_fmt(fmt) "SCMI Notifications - " fmt
 
 #include <linux/bitfield.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/device.h>
 #include <linux/err.h>
+#include <linux/hashtable.h>
 #include <linux/kernel.h>
 #include <linux/kfifo.h>
+#include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/notifier.h>
 #include <linux/refcount.h>
 #include <linux/scmi_protocol.h>
 #include <linux/slab.h>
@@ -55,6 +87,86 @@
 
 #define MAKE_ALL_SRCS_KEY(p, e)		MAKE_HASH_KEY((p), (e), SRC_ID_MASK)
 
+/*
+ * Assumes that the stored obj includes its own hash-key in a field named 'key':
+ * with this simplification this macro can be equally used for all the objects'
+ * types hashed by this implementation.
+ *
+ * @__ht: The hashtable name
+ * @__obj: A pointer to the object type to be retrieved from the hashtable;
+ *	   it will be used as a cursor while scanning the hastable and it will
+ *	   be possibly left as NULL when @__k is not found
+ * @__k: The key to search for
+ */
+#define KEY_FIND(__ht, __obj, __k)				\
+({								\
+	typeof(__k) k_ = __k;					\
+	typeof(__obj) obj_;					\
+								\
+	hash_for_each_possible((__ht), obj_, hash, k_)		\
+		if (obj_->key == k_)				\
+			break;					\
+	__obj = obj_;						\
+})
+
+#define KEY_XTRACT_PROTO_ID(key)	FIELD_GET(PROTO_ID_MASK, (key))
+#define KEY_XTRACT_EVT_ID(key)		FIELD_GET(EVT_ID_MASK, (key))
+#define KEY_XTRACT_SRC_ID(key)		FIELD_GET(SRC_ID_MASK, (key))
+
+/*
+ * A set of macros used to access safely @registered_protocols and
+ * @registered_events arrays; these are fixed in size and each entry is possibly
+ * populated at protocols' registration time and then only read but NEVER
+ * modified or removed.
+ */
+#define SCMI_GET_PROTO(__ni, __pid)					\
+({									\
+	typeof(__ni) ni_ = __ni;					\
+	struct scmi_registered_events_desc *__pd = NULL;		\
+									\
+	if (ni_)							\
+		__pd = READ_ONCE(ni_->registered_protocols[(__pid)]);	\
+	__pd;								\
+})
+
+#define SCMI_GET_REVT_FROM_PD(__pd, __eid)				\
+({									\
+	typeof(__pd) pd_ = __pd;					\
+	typeof(__eid) eid_ = __eid;					\
+	struct scmi_registered_event *__revt = NULL;			\
+									\
+	if (pd_ && eid_ < pd_->num_events)				\
+		__revt = READ_ONCE(pd_->registered_events[eid_]);	\
+	__revt;								\
+})
+
+#define SCMI_GET_REVT(__ni, __pid, __eid)				\
+({									\
+	struct scmi_registered_event *__revt;				\
+	struct scmi_registered_events_desc *__pd;			\
+									\
+	__pd = SCMI_GET_PROTO((__ni), (__pid));				\
+	__revt = SCMI_GET_REVT_FROM_PD(__pd, (__eid));			\
+	__revt;								\
+})
+
+/* A couple of utility macros to limit cruft when calling protocols' helpers */
+#define REVT_NOTIFY_SET_STATUS(revt, eid, sid, state)		\
+({								\
+	typeof(revt) r = revt;					\
+	r->proto->ops->set_notify_enabled(r->proto->ni->handle,	\
+					(eid), (sid), (state));	\
+})
+
+#define REVT_NOTIFY_ENABLE(revt, eid, sid)			\
+	REVT_NOTIFY_SET_STATUS((revt), (eid), (sid), true)
+
+#define REVT_NOTIFY_DISABLE(revt, eid, sid)			\
+	REVT_NOTIFY_SET_STATUS((revt), (eid), (sid), false)
+
+#define SCMI_PENDING_HASH_SZ		4
+#define SCMI_REGISTERED_HASH_SZ		6
+
 struct scmi_registered_events_desc;
 
 /**
@@ -62,9 +174,13 @@ struct scmi_registered_events_desc;
  * core
  * @gid: GroupID used for devres
  * @handle: A reference to the platform instance
+ * @init_work: A work item to perform final initializations of pending handlers
+ * @pending_mtx: A mutex to protect @pending_events_handlers
  * @registered_protocols: A statically allocated array containing pointers to
  *			  all the registered protocol-level specific information
  *			  related to events' handling
+ * @pending_events_handlers: An hashtable containing all pending events'
+ *			     handlers descriptors
  *
  * Each platform instance, represented by a handle, has its own instance of
  * the notification subsystem represented by this structure.
@@ -72,7 +188,11 @@ struct scmi_registered_events_desc;
 struct scmi_notify_instance {
 	void			*gid;
 	struct scmi_handle	*handle;
+	struct work_struct	init_work;
+	/* lock to protect pending_events_handlers */
+	struct mutex		pending_mtx;
 	struct scmi_registered_events_desc	**registered_protocols;
+	DECLARE_HASHTABLE(pending_events_handlers, SCMI_PENDING_HASH_SZ);
 };
 
 /**
@@ -121,6 +241,9 @@ struct scmi_registered_event;
  * @registered_events: A dynamically allocated array holding all the registered
  *		       events' descriptors, whose fixed-size is determined at
  *		       compile time.
+ * @registered_mtx: A mutex to protect @registered_events_handlers
+ * @registered_events_handlers: An hashtable containing all events' handlers
+ *				descriptors registered for this protocol
  *
  * All protocols that register at least one event have their protocol-specific
  * information stored here, together with the embedded allocated events_queue.
@@ -141,6 +264,9 @@ struct scmi_registered_events_desc {
 	void				*in_flight;
 	int				num_events;
 	struct scmi_registered_event	**registered_events;
+	/* mutex to protect registered_events_handlers */
+	struct mutex			registered_mtx;
+	DECLARE_HASHTABLE(registered_events_handlers, SCMI_REGISTERED_HASH_SZ);
 };
 
 /**
@@ -173,6 +299,38 @@ struct scmi_registered_event {
 	struct mutex	sources_mtx;
 };
 
+/**
+ * struct scmi_event_handler  - Event handler information
+ * @key: The used hashkey
+ * @users: A reference count for number of active users for this handler
+ * @r_evt: A reference to the associated registered event; when this is NULL
+ *	   this handler is pending, which means that identifies a set of
+ *	   callbacks intended to be attached to an event which is still not
+ *	   known nor registered by any protocol at that point in time
+ * @chain: The notification chain dedicated to this specific event tuple
+ * @hash: The hlist_node used for collision handling
+ * @enabled: A boolean which records if event's generation has been already
+ *	     enabled for this handler as a whole
+ *
+ * This structure collects all the information needed to process a received
+ * event identified by the tuple (proto_id, evt_id, src_id).
+ * These descriptors are stored in a per-protocol @registered_events_handlers
+ * table using as a key a value derived from that tuple.
+ */
+struct scmi_event_handler {
+	u32				key;
+	refcount_t			users;
+	struct scmi_registered_event	*r_evt;
+	struct blocking_notifier_head	chain;
+	struct hlist_node		hash;
+	bool				enabled;
+};
+
+#define IS_HNDL_PENDING(hndl)	(!(hndl)->r_evt)
+
+static void scmi_put_handler_unlocked(struct scmi_notify_instance *ni,
+				      struct scmi_event_handler *hndl);
+
 /**
  * scmi_kfifo_free()  - Devres action helper to free the kfifo
  * @kfifo: The kfifo to free
@@ -258,6 +416,10 @@ scmi_allocate_registered_events_desc(struct scmi_notify_instance *ni,
 		return ERR_PTR(-ENOMEM);
 	pd->num_events = num_events;
 
+	/* Initialize per protocol handlers table */
+	mutex_init(&pd->registered_mtx);
+	hash_init(pd->registered_events_handlers);
+
 	return pd;
 }
 
@@ -349,6 +511,12 @@ int scmi_register_protocol_events(const struct scmi_handle *handle,
 
 	devres_close_group(ni->handle->dev, ni->gid);
 
+	/*
+	 * Finalize any pending events' handler which could have been waiting
+	 * for this protocol's events registration.
+	 */
+	schedule_work(&ni->init_work);
+
 	return 0;
 
 err:
@@ -359,6 +527,558 @@ err:
 	return -ENOMEM;
 }
 
+/**
+ * scmi_allocate_event_handler()  - Allocate Event handler
+ * @ni: A reference to the notification instance to use
+ * @evt_key: 32bit key uniquely bind to the event identified by the tuple
+ *	     (proto_id, evt_id, src_id)
+ *
+ * Allocate an event handler and related notification chain associated with
+ * the provided event handler key.
+ * Note that, at this point, a related registered_event is still to be
+ * associated to this handler descriptor (hndl->r_evt == NULL), so the handler
+ * is initialized as pending.
+ *
+ * Context: Assumes to be called with @pending_mtx already acquired.
+ * Return: the freshly allocated structure on Success
+ */
+static struct scmi_event_handler *
+scmi_allocate_event_handler(struct scmi_notify_instance *ni, u32 evt_key)
+{
+	struct scmi_event_handler *hndl;
+
+	hndl = kzalloc(sizeof(*hndl), GFP_KERNEL);
+	if (!hndl)
+		return NULL;
+	hndl->key = evt_key;
+	BLOCKING_INIT_NOTIFIER_HEAD(&hndl->chain);
+	refcount_set(&hndl->users, 1);
+	/* New handlers are created pending */
+	hash_add(ni->pending_events_handlers, &hndl->hash, hndl->key);
+
+	return hndl;
+}
+
+/**
+ * scmi_free_event_handler()  - Free the provided Event handler
+ * @hndl: The event handler structure to free
+ *
+ * Context: Assumes to be called with proper locking acquired depending
+ *	    on the situation.
+ */
+static void scmi_free_event_handler(struct scmi_event_handler *hndl)
+{
+	hash_del(&hndl->hash);
+	kfree(hndl);
+}
+
+/**
+ * scmi_bind_event_handler()  - Helper to attempt binding an handler to an event
+ * @ni: A reference to the notification instance to use
+ * @hndl: The event handler to bind
+ *
+ * If an associated registered event is found, move the handler from the pending
+ * into the registered table.
+ *
+ * Context: Assumes to be called with @pending_mtx already acquired.
+ *
+ * Return: 0 on Success
+ */
+static inline int scmi_bind_event_handler(struct scmi_notify_instance *ni,
+					  struct scmi_event_handler *hndl)
+{
+	struct scmi_registered_event *r_evt;
+
+	r_evt = SCMI_GET_REVT(ni, KEY_XTRACT_PROTO_ID(hndl->key),
+			      KEY_XTRACT_EVT_ID(hndl->key));
+	if (!r_evt)
+		return -EINVAL;
+
+	/* Remove from pending and insert into registered */
+	hash_del(&hndl->hash);
+	hndl->r_evt = r_evt;
+	mutex_lock(&r_evt->proto->registered_mtx);
+	hash_add(r_evt->proto->registered_events_handlers,
+		 &hndl->hash, hndl->key);
+	mutex_unlock(&r_evt->proto->registered_mtx);
+
+	return 0;
+}
+
+/**
+ * scmi_valid_pending_handler()  - Helper to check pending status of handlers
+ * @ni: A reference to the notification instance to use
+ * @hndl: The event handler to check
+ *
+ * An handler is considered pending when its r_evt == NULL, because the related
+ * event was still unknown at handler's registration time; anyway, since all
+ * protocols register their supported events once for all at protocols'
+ * initialization time, a pending handler cannot be considered valid anymore if
+ * the underlying event (which it is waiting for), belongs to an already
+ * initialized and registered protocol.
+ *
+ * Return: 0 on Success
+ */
+static inline int scmi_valid_pending_handler(struct scmi_notify_instance *ni,
+					     struct scmi_event_handler *hndl)
+{
+	struct scmi_registered_events_desc *pd;
+
+	if (!IS_HNDL_PENDING(hndl))
+		return -EINVAL;
+
+	pd = SCMI_GET_PROTO(ni, KEY_XTRACT_PROTO_ID(hndl->key));
+	if (pd)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * scmi_register_event_handler()  - Register whenever possible an Event handler
+ * @ni: A reference to the notification instance to use
+ * @hndl: The event handler to register
+ *
+ * At first try to bind an event handler to its associated event, then check if
+ * it was at least a valid pending handler: if it was not bound nor valid return
+ * false.
+ *
+ * Valid pending incomplete bindings will be periodically retried by a dedicated
+ * worker which is kicked each time a new protocol completes its own
+ * registration phase.
+ *
+ * Context: Assumes to be called with @pending_mtx acquired.
+ *
+ * Return: 0 on Success
+ */
+static int scmi_register_event_handler(struct scmi_notify_instance *ni,
+				       struct scmi_event_handler *hndl)
+{
+	int ret;
+
+	ret = scmi_bind_event_handler(ni, hndl);
+	if (!ret) {
+		dev_dbg(ni->handle->dev, "registered NEW handler - key:%X\n",
+			hndl->key);
+	} else {
+		ret = scmi_valid_pending_handler(ni, hndl);
+		if (!ret)
+			dev_dbg(ni->handle->dev,
+				"registered PENDING handler - key:%X\n",
+				hndl->key);
+	}
+
+	return ret;
+}
+
+/**
+ * __scmi_event_handler_get_ops()  - Utility to get or create an event handler
+ * @ni: A reference to the notification instance to use
+ * @evt_key: The event key to use
+ * @create: A boolean flag to specify if a handler must be created when
+ *	    not already existent
+ *
+ * Search for the desired handler matching the key in both the per-protocol
+ * registered table and the common pending table:
+ * * if found adjust users refcount
+ * * if not found and @create is true, create and register the new handler:
+ *   handler could end up being registered as pending if no matching event
+ *   could be found.
+ *
+ * An handler is guaranteed to reside in one and only one of the tables at
+ * any one time; to ensure this the whole search and create is performed
+ * holding the @pending_mtx lock, with @registered_mtx additionally acquired
+ * if needed.
+ *
+ * Note that when a nested acquisition of these mutexes is needed the locking
+ * order is always (same as in @init_work):
+ * 1. pending_mtx
+ * 2. registered_mtx
+ *
+ * Events generation is NOT enabled right after creation within this routine
+ * since at creation time we usually want to have all setup and ready before
+ * events really start flowing.
+ *
+ * Return: A properly refcounted handler on Success, NULL on Failure
+ */
+static inline struct scmi_event_handler *
+__scmi_event_handler_get_ops(struct scmi_notify_instance *ni,
+			     u32 evt_key, bool create)
+{
+	struct scmi_registered_event *r_evt;
+	struct scmi_event_handler *hndl = NULL;
+
+	r_evt = SCMI_GET_REVT(ni, KEY_XTRACT_PROTO_ID(evt_key),
+			      KEY_XTRACT_EVT_ID(evt_key));
+
+	mutex_lock(&ni->pending_mtx);
+	/* Search registered events at first ... if possible at all */
+	if (r_evt) {
+		mutex_lock(&r_evt->proto->registered_mtx);
+		hndl = KEY_FIND(r_evt->proto->registered_events_handlers,
+				hndl, evt_key);
+		if (hndl)
+			refcount_inc(&hndl->users);
+		mutex_unlock(&r_evt->proto->registered_mtx);
+	}
+
+	/* ...then amongst pending. */
+	if (!hndl) {
+		hndl = KEY_FIND(ni->pending_events_handlers, hndl, evt_key);
+		if (hndl)
+			refcount_inc(&hndl->users);
+	}
+
+	/* Create if still not found and required */
+	if (!hndl && create) {
+		hndl = scmi_allocate_event_handler(ni, evt_key);
+		if (hndl && scmi_register_event_handler(ni, hndl)) {
+			dev_dbg(ni->handle->dev,
+				"purging UNKNOWN handler - key:%X\n",
+				hndl->key);
+			/* this hndl can be only a pending one */
+			scmi_put_handler_unlocked(ni, hndl);
+			hndl = NULL;
+		}
+	}
+	mutex_unlock(&ni->pending_mtx);
+
+	return hndl;
+}
+
+static struct scmi_event_handler *
+scmi_get_handler(struct scmi_notify_instance *ni, u32 evt_key)
+{
+	return __scmi_event_handler_get_ops(ni, evt_key, false);
+}
+
+static struct scmi_event_handler *
+scmi_get_or_create_handler(struct scmi_notify_instance *ni, u32 evt_key)
+{
+	return __scmi_event_handler_get_ops(ni, evt_key, true);
+}
+
+/**
+ * __scmi_enable_evt()  - Enable/disable events generation
+ * @r_evt: The registered event to act upon
+ * @src_id: The src_id to act upon
+ * @enable: The action to perform: true->Enable, false->Disable
+ *
+ * Takes care of proper refcounting while performing enable/disable: handles
+ * the special case of ALL sources requests by itself.
+ * Returns successfully if at least one of the required src_id has been
+ * successfully enabled/disabled.
+ *
+ * Return: 0 on Success
+ */
+static inline int __scmi_enable_evt(struct scmi_registered_event *r_evt,
+				    u32 src_id, bool enable)
+{
+	int retvals = 0;
+	u32 num_sources;
+	refcount_t *sid;
+
+	if (src_id == SRC_ID_MASK) {
+		src_id = 0;
+		num_sources = r_evt->num_sources;
+	} else if (src_id < r_evt->num_sources) {
+		num_sources = 1;
+	} else {
+		return -EINVAL;
+	}
+
+	mutex_lock(&r_evt->sources_mtx);
+	if (enable) {
+		for (; num_sources; src_id++, num_sources--) {
+			int ret = 0;
+
+			sid = &r_evt->sources[src_id];
+			if (refcount_read(sid) == 0) {
+				ret = REVT_NOTIFY_ENABLE(r_evt, r_evt->evt->id,
+							 src_id);
+				if (!ret)
+					refcount_set(sid, 1);
+			} else {
+				refcount_inc(sid);
+			}
+			retvals += !ret;
+		}
+	} else {
+		for (; num_sources; src_id++, num_sources--) {
+			sid = &r_evt->sources[src_id];
+			if (refcount_dec_and_test(sid))
+				REVT_NOTIFY_DISABLE(r_evt,
+						    r_evt->evt->id, src_id);
+		}
+		retvals = 1;
+	}
+	mutex_unlock(&r_evt->sources_mtx);
+
+	return retvals ? 0 : -EINVAL;
+}
+
+static int scmi_enable_events(struct scmi_event_handler *hndl)
+{
+	int ret = 0;
+
+	if (!hndl->enabled) {
+		ret = __scmi_enable_evt(hndl->r_evt,
+					KEY_XTRACT_SRC_ID(hndl->key), true);
+		if (!ret)
+			hndl->enabled = true;
+	}
+
+	return ret;
+}
+
+static int scmi_disable_events(struct scmi_event_handler *hndl)
+{
+	int ret = 0;
+
+	if (hndl->enabled) {
+		ret = __scmi_enable_evt(hndl->r_evt,
+					KEY_XTRACT_SRC_ID(hndl->key), false);
+		if (!ret)
+			hndl->enabled = false;
+	}
+
+	return ret;
+}
+
+/**
+ * scmi_put_handler_unlocked()  - Put an event handler
+ * @ni: A reference to the notification instance to use
+ * @hndl: The event handler to act upon
+ *
+ * After having got exclusive access to the registered handlers hashtable,
+ * update the refcount and if @hndl is no more in use by anyone:
+ * * ask for events' generation disabling
+ * * unregister and free the handler itself
+ *
+ * Context: Assumes all the proper locking has been managed by the caller.
+ */
+static void scmi_put_handler_unlocked(struct scmi_notify_instance *ni,
+				      struct scmi_event_handler *hndl)
+{
+	if (refcount_dec_and_test(&hndl->users)) {
+		if (!IS_HNDL_PENDING(hndl))
+			scmi_disable_events(hndl);
+		scmi_free_event_handler(hndl);
+	}
+}
+
+static void scmi_put_handler(struct scmi_notify_instance *ni,
+			     struct scmi_event_handler *hndl)
+{
+	struct scmi_registered_event *r_evt = hndl->r_evt;
+
+	mutex_lock(&ni->pending_mtx);
+	if (r_evt)
+		mutex_lock(&r_evt->proto->registered_mtx);
+
+	scmi_put_handler_unlocked(ni, hndl);
+
+	if (r_evt)
+		mutex_unlock(&r_evt->proto->registered_mtx);
+	mutex_unlock(&ni->pending_mtx);
+}
+
+/**
+ * scmi_event_handler_enable_events()  - Enable events associated to an handler
+ * @hndl: The Event handler to act upon
+ *
+ * Return: 0 on Success
+ */
+static int scmi_event_handler_enable_events(struct scmi_event_handler *hndl)
+{
+	if (scmi_enable_events(hndl)) {
+		pr_err("Failed to ENABLE events for key:%X !\n", hndl->key);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * scmi_register_notifier()  - Register a notifier_block for an event
+ * @handle: The handle identifying the platform instance against which the
+ *	    callback is registered
+ * @proto_id: Protocol ID
+ * @evt_id: Event ID
+ * @src_id: Source ID, when NULL register for events coming form ALL possible
+ *	    sources
+ * @nb: A standard notifier block to register for the specified event
+ *
+ * Generic helper to register a notifier_block against a protocol event.
+ *
+ * A notifier_block @nb will be registered for each distinct event identified
+ * by the tuple (proto_id, evt_id, src_id) on a dedicated notification chain
+ * so that:
+ *
+ *	(proto_X, evt_Y, src_Z) --> chain_X_Y_Z
+ *
+ * @src_id meaning is protocol specific and identifies the origin of the event
+ * (like domain_id, sensor_id and so forth).
+ *
+ * @src_id can be NULL to signify that the caller is interested in receiving
+ * notifications from ALL the available sources for that protocol OR simply that
+ * the protocol does not support distinct sources.
+ *
+ * As soon as one user for the specified tuple appears, an handler is created,
+ * and that specific event's generation is enabled at the platform level, unless
+ * an associated registered event is found missing, meaning that the needed
+ * protocol is still to be initialized and the handler has just been registered
+ * as still pending.
+ *
+ * Return: 0 on Success
+ */
+static int scmi_register_notifier(const struct scmi_handle *handle,
+				  u8 proto_id, u8 evt_id, u32 *src_id,
+				  struct notifier_block *nb)
+{
+	int ret = 0;
+	u32 evt_key;
+	struct scmi_event_handler *hndl;
+	struct scmi_notify_instance *ni;
+
+	/* Ensure notify_priv is updated */
+	smp_rmb();
+	if (!handle->notify_priv)
+		return -ENODEV;
+	ni = handle->notify_priv;
+
+	evt_key = MAKE_HASH_KEY(proto_id, evt_id,
+				src_id ? *src_id : SRC_ID_MASK);
+	hndl = scmi_get_or_create_handler(ni, evt_key);
+	if (!hndl)
+		return -EINVAL;
+
+	blocking_notifier_chain_register(&hndl->chain, nb);
+
+	/* Enable events for not pending handlers */
+	if (!IS_HNDL_PENDING(hndl)) {
+		ret = scmi_event_handler_enable_events(hndl);
+		if (ret)
+			scmi_put_handler(ni, hndl);
+	}
+
+	return ret;
+}
+
+/**
+ * scmi_unregister_notifier()  - Unregister a notifier_block for an event
+ * @handle: The handle identifying the platform instance against which the
+ *	    callback is unregistered
+ * @proto_id: Protocol ID
+ * @evt_id: Event ID
+ * @src_id: Source ID
+ * @nb: The notifier_block to unregister
+ *
+ * Takes care to unregister the provided @nb from the notification chain
+ * associated to the specified event and, if there are no more users for the
+ * event handler, frees also the associated event handler structures.
+ * (this could possibly cause disabling of event's generation at platform level)
+ *
+ * Return: 0 on Success
+ */
+static int scmi_unregister_notifier(const struct scmi_handle *handle,
+				    u8 proto_id, u8 evt_id, u32 *src_id,
+				    struct notifier_block *nb)
+{
+	u32 evt_key;
+	struct scmi_event_handler *hndl;
+	struct scmi_notify_instance *ni;
+
+	/* Ensure notify_priv is updated */
+	smp_rmb();
+	if (!handle->notify_priv)
+		return -ENODEV;
+	ni = handle->notify_priv;
+
+	evt_key = MAKE_HASH_KEY(proto_id, evt_id,
+				src_id ? *src_id : SRC_ID_MASK);
+	hndl = scmi_get_handler(ni, evt_key);
+	if (!hndl)
+		return -EINVAL;
+
+	/*
+	 * Note that this chain unregistration call is safe on its own
+	 * being internally protected by an rwsem.
+	 */
+	blocking_notifier_chain_unregister(&hndl->chain, nb);
+	scmi_put_handler(ni, hndl);
+
+	/*
+	 * This balances the initial get issued in @scmi_register_notifier.
+	 * If this notifier_block happened to be the last known user callback
+	 * for this event, the handler is here freed and the event's generation
+	 * stopped.
+	 *
+	 * Note that, an ongoing concurrent lookup on the delivery workqueue
+	 * path could still hold the refcount to 1 even after this routine
+	 * completes: in such a case it will be the final put on the delivery
+	 * path which will finally free this unused handler.
+	 */
+	scmi_put_handler(ni, hndl);
+
+	return 0;
+}
+
+/**
+ * scmi_protocols_late_init()  - Worker for late initialization
+ * @work: The work item to use associated to the proper SCMI instance
+ *
+ * This kicks in whenever a new protocol has completed its own registration via
+ * scmi_register_protocol_events(): it is in charge of scanning the table of
+ * pending handlers (registered by users while the related protocol was still
+ * not initialized) and finalizing their initialization whenever possible;
+ * invalid pending handlers are purged at this point in time.
+ */
+static void scmi_protocols_late_init(struct work_struct *work)
+{
+	int bkt;
+	struct scmi_event_handler *hndl;
+	struct scmi_notify_instance *ni;
+	struct hlist_node *tmp;
+
+	ni = container_of(work, struct scmi_notify_instance, init_work);
+
+	/* Ensure protocols and events are up to date */
+	smp_rmb();
+
+	mutex_lock(&ni->pending_mtx);
+	hash_for_each_safe(ni->pending_events_handlers, bkt, tmp, hndl, hash) {
+		int ret;
+
+		ret = scmi_bind_event_handler(ni, hndl);
+		if (!ret) {
+			dev_dbg(ni->handle->dev,
+				"finalized PENDING handler - key:%X\n",
+				hndl->key);
+			ret = scmi_event_handler_enable_events(hndl);
+		} else {
+			ret = scmi_valid_pending_handler(ni, hndl);
+		}
+		if (ret) {
+			dev_dbg(ni->handle->dev,
+				"purging PENDING handler - key:%X\n",
+				hndl->key);
+			/* this hndl can be only a pending one */
+			scmi_put_handler_unlocked(ni, hndl);
+		}
+	}
+	mutex_unlock(&ni->pending_mtx);
+}
+
+/*
+ * notify_ops are attached to the handle so that can be accessed
+ * directly from an scmi_driver to register its own notifiers.
+ */
+static struct scmi_notify_ops notify_ops = {
+	.register_event_notifier = scmi_register_notifier,
+	.unregister_event_notifier = scmi_unregister_notifier,
+};
+
 /**
  * scmi_notification_init()  - Initializes Notification Core Support
  * @handle: The handle identifying the platform instance to initialize
@@ -406,6 +1126,12 @@ int scmi_notification_init(struct scmi_handle *handle)
 	if (!ni->registered_protocols)
 		goto err;
 
+	mutex_init(&ni->pending_mtx);
+	hash_init(ni->pending_events_handlers);
+
+	INIT_WORK(&ni->init_work, scmi_protocols_late_init);
+
+	handle->notify_ops = &notify_ops;
 	handle->notify_priv = ni;
 	/* Ensure handle is up to date */
 	smp_wmb();
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 9a34b02a9cce..26957d6872a5 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -9,6 +9,7 @@
 #define _LINUX_SCMI_PROTOCOL_H
 
 #include <linux/device.h>
+#include <linux/notifier.h>
 #include <linux/types.h>
 
 #define SCMI_MAX_STR_SIZE	16
@@ -213,6 +214,49 @@ struct scmi_reset_ops {
 	int (*deassert)(const struct scmi_handle *handle, u32 domain);
 };
 
+/**
+ * struct scmi_notify_ops  - represents notifications' operations provided by
+ * SCMI core
+ * @register_event_notifier: Register a notifier_block for the requested event
+ * @unregister_event_notifier: Unregister a notifier_block for the requested
+ *			       event
+ *
+ * A user can register/unregister its own notifier_block against the wanted
+ * platform instance regarding the desired event identified by the
+ * tuple: (proto_id, evt_id, src_id) using the provided register/unregister
+ * interface where:
+ *
+ * @handle: The handle identifying the platform instance to use
+ * @proto_id: The protocol ID as in SCMI Specification
+ * @evt_id: The message ID of the desired event as in SCMI Specification
+ * @src_id: A pointer to the desired source ID if different sources are
+ *	    possible for the protocol (like domain_id, sensor_id...etc)
+ *
+ * @src_id can be provided as NULL if it simply does NOT make sense for
+ * the protocol at hand, OR if the user is explicitly interested in
+ * receiving notifications from ANY existent source associated to the
+ * specified proto_id / evt_id.
+ *
+ * Received notifications are finally delivered to the registered users,
+ * invoking the callback provided with the notifier_block *nb as follows:
+ *
+ *	int user_cb(nb, evt_id, report)
+ *
+ * with:
+ *
+ * @nb: The notifier block provided by the user
+ * @evt_id: The message ID of the delivered event
+ * @report: A custom struct describing the specific event delivered
+ */
+struct scmi_notify_ops {
+	int (*register_event_notifier)(const struct scmi_handle *handle,
+				       u8 proto_id, u8 evt_id, u32 *src_id,
+				       struct notifier_block *nb);
+	int (*unregister_event_notifier)(const struct scmi_handle *handle,
+					 u8 proto_id, u8 evt_id, u32 *src_id,
+					 struct notifier_block *nb);
+};
+
 /**
  * struct scmi_handle - Handle returned to ARM SCMI clients for usage.
  *
@@ -223,6 +267,7 @@ struct scmi_reset_ops {
  * @clk_ops: pointer to set of clock protocol operations
  * @sensor_ops: pointer to set of sensor protocol operations
  * @reset_ops: pointer to set of reset protocol operations
+ * @notify_ops: pointer to set of notifications related operations
  * @perf_priv: pointer to private data structure specific to performance
  *	protocol(for internal use only)
  * @clk_priv: pointer to private data structure specific to clock
@@ -244,6 +289,7 @@ struct scmi_handle {
 	struct scmi_power_ops *power_ops;
 	struct scmi_sensor_ops *sensor_ops;
 	struct scmi_reset_ops *reset_ops;
+	struct scmi_notify_ops *notify_ops;
 	/* for protocol internal use */
 	void *perf_priv;
 	void *clk_priv;
-- 
cgit v1.2.3


From e27077bc04d5a2e09a0860ca086e1d55adf6a16d Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:44 +0100
Subject: firmware: arm_scmi: Add power notifications support

Make SCMI power protocol register with the notification core.

Link: https://lore.kernel.org/r/20200701155348.52864-6-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/power.c | 92 ++++++++++++++++++++++++++++++++++++---
 include/linux/scmi_protocol.h     | 12 +++++
 2 files changed, 98 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index cf7f0312381b..4f6757980739 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -5,19 +5,18 @@
  * Copyright (C) 2018 ARM Ltd.
  */
 
+#define pr_fmt(fmt) "SCMI Notifications POWER - " fmt
+
+#include <linux/scmi_protocol.h>
+
 #include "common.h"
+#include "notify.h"
 
 enum scmi_power_protocol_cmd {
 	POWER_DOMAIN_ATTRIBUTES = 0x3,
 	POWER_STATE_SET = 0x4,
 	POWER_STATE_GET = 0x5,
 	POWER_STATE_NOTIFY = 0x6,
-	POWER_STATE_CHANGE_REQUESTED_NOTIFY = 0x7,
-};
-
-enum scmi_power_protocol_notify {
-	POWER_STATE_CHANGED = 0x0,
-	POWER_STATE_CHANGE_REQUESTED = 0x1,
 };
 
 struct scmi_msg_resp_power_attributes {
@@ -48,6 +47,12 @@ struct scmi_power_state_notify {
 	__le32 notify_enable;
 };
 
+struct scmi_power_state_notify_payld {
+	__le32 agent_id;
+	__le32 domain_id;
+	__le32 power_state;
+};
+
 struct power_dom_info {
 	bool state_set_sync;
 	bool state_set_async;
@@ -186,6 +191,75 @@ static struct scmi_power_ops power_ops = {
 	.state_get = scmi_power_state_get,
 };
 
+static int scmi_power_request_notify(const struct scmi_handle *handle,
+				     u32 domain, bool enable)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_power_state_notify *notify;
+
+	ret = scmi_xfer_get_init(handle, POWER_STATE_NOTIFY,
+				 SCMI_PROTOCOL_POWER, sizeof(*notify), 0, &t);
+	if (ret)
+		return ret;
+
+	notify = t->tx.buf;
+	notify->domain = cpu_to_le32(domain);
+	notify->notify_enable = enable ? cpu_to_le32(BIT(0)) : 0;
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_power_set_notify_enabled(const struct scmi_handle *handle,
+					 u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_power_request_notify(handle, src_id, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLE - evt[%X] dom[%d] - ret:%d\n",
+			 evt_id, src_id, ret);
+
+	return ret;
+}
+
+static void *scmi_power_fill_custom_report(const struct scmi_handle *handle,
+					   u8 evt_id, u64 timestamp,
+					   const void *payld, size_t payld_sz,
+					   void *report, u32 *src_id)
+{
+	const struct scmi_power_state_notify_payld *p = payld;
+	struct scmi_power_state_changed_report *r = report;
+
+	if (evt_id != SCMI_EVENT_POWER_STATE_CHANGED || sizeof(*p) != payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->domain_id = le32_to_cpu(p->domain_id);
+	r->power_state = le32_to_cpu(p->power_state);
+	*src_id = r->domain_id;
+
+	return r;
+}
+
+static const struct scmi_event power_events[] = {
+	{
+		.id = SCMI_EVENT_POWER_STATE_CHANGED,
+		.max_payld_sz = sizeof(struct scmi_power_state_notify_payld),
+		.max_report_sz =
+			sizeof(struct scmi_power_state_changed_report),
+	},
+};
+
+static const struct scmi_event_ops power_event_ops = {
+	.set_notify_enabled = scmi_power_set_notify_enabled,
+	.fill_custom_report = scmi_power_fill_custom_report,
+};
+
 static int scmi_power_protocol_init(struct scmi_handle *handle)
 {
 	int domain;
@@ -214,6 +288,12 @@ static int scmi_power_protocol_init(struct scmi_handle *handle)
 		scmi_power_domain_attributes_get(handle, domain, dom);
 	}
 
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_POWER, SCMI_PROTO_QUEUE_SZ,
+				      &power_event_ops, power_events,
+				      ARRAY_SIZE(power_events),
+				      pinfo->num_domains);
+
 	pinfo->version = version;
 	handle->power_ops = &power_ops;
 	handle->power_priv = pinfo;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 26957d6872a5..81dc3b132fda 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -375,4 +375,16 @@ typedef int (*scmi_prot_init_fn_t)(struct scmi_handle *);
 int scmi_protocol_register(int protocol_id, scmi_prot_init_fn_t fn);
 void scmi_protocol_unregister(int protocol_id);
 
+/* SCMI Notification API - Custom Event Reports */
+enum scmi_notification_events {
+	SCMI_EVENT_POWER_STATE_CHANGED = 0x0,
+};
+
+struct scmi_power_state_changed_report {
+	u64 timestamp;
+	u32 agent_id;
+	u32 domain_id;
+	u32 power_state;
+};
+
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From fb5086dc4746184a9325fc25411226a750fb252c Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:45 +0100
Subject: firmware: arm_scmi: Add perf notifications support

Make SCMI perf protocol register with the notification core.

Link: https://lore.kernel.org/r/20200701155348.52864-7-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/perf.c | 139 +++++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h    |  17 +++++
 2 files changed, 151 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 7b8d7cebdac9..8bcad96e06ca 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -5,15 +5,19 @@
  * Copyright (C) 2018 ARM Ltd.
  */
 
+#define pr_fmt(fmt) "SCMI Notifications PERF - " fmt
+
 #include <linux/bits.h>
 #include <linux/of.h>
 #include <linux/io.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
+#include <linux/scmi_protocol.h>
 #include <linux/sort.h>
 
 #include "common.h"
+#include "notify.h"
 
 enum scmi_performance_protocol_cmd {
 	PERF_DOMAIN_ATTRIBUTES = 0x3,
@@ -27,11 +31,6 @@ enum scmi_performance_protocol_cmd {
 	PERF_DESCRIBE_FASTCHANNEL = 0xb,
 };
 
-enum scmi_performance_protocol_notify {
-	PERFORMANCE_LIMITS_CHANGED = 0x0,
-	PERFORMANCE_LEVEL_CHANGED = 0x1,
-};
-
 struct scmi_opp {
 	u32 perf;
 	u32 power;
@@ -86,6 +85,19 @@ struct scmi_perf_notify_level_or_limits {
 	__le32 notify_enable;
 };
 
+struct scmi_perf_limits_notify_payld {
+	__le32 agent_id;
+	__le32 domain_id;
+	__le32 range_max;
+	__le32 range_min;
+};
+
+struct scmi_perf_level_notify_payld {
+	__le32 agent_id;
+	__le32 domain_id;
+	__le32 performance_level;
+};
+
 struct scmi_msg_resp_perf_describe_levels {
 	__le16 num_returned;
 	__le16 num_remaining;
@@ -158,6 +170,11 @@ struct scmi_perf_info {
 	struct perf_dom_info *dom_info;
 };
 
+static enum scmi_performance_protocol_cmd evt_2_cmd[] = {
+	PERF_NOTIFY_LIMITS,
+	PERF_NOTIFY_LEVEL,
+};
+
 static int scmi_perf_attributes_get(const struct scmi_handle *handle,
 				    struct scmi_perf_info *pi)
 {
@@ -488,6 +505,29 @@ static int scmi_perf_level_get(const struct scmi_handle *handle, u32 domain,
 	return scmi_perf_mb_level_get(handle, domain, level, poll);
 }
 
+static int scmi_perf_level_limits_notify(const struct scmi_handle *handle,
+					 u32 domain, int message_id,
+					 bool enable)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_perf_notify_level_or_limits *notify;
+
+	ret = scmi_xfer_get_init(handle, message_id, SCMI_PROTOCOL_PERF,
+				 sizeof(*notify), 0, &t);
+	if (ret)
+		return ret;
+
+	notify = t->tx.buf;
+	notify->domain = cpu_to_le32(domain);
+	notify->notify_enable = enable ? cpu_to_le32(BIT(0)) : 0;
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
 static bool scmi_perf_fc_size_is_valid(u32 msg, u32 size)
 {
 	if ((msg == PERF_LEVEL_GET || msg == PERF_LEVEL_SET) && size == 4)
@@ -722,6 +762,89 @@ static struct scmi_perf_ops perf_ops = {
 	.fast_switch_possible = scmi_fast_switch_possible,
 };
 
+static int scmi_perf_set_notify_enabled(const struct scmi_handle *handle,
+					u8 evt_id, u32 src_id, bool enable)
+{
+	int ret, cmd_id;
+
+	if (evt_id >= ARRAY_SIZE(evt_2_cmd))
+		return -EINVAL;
+
+	cmd_id = evt_2_cmd[evt_id];
+	ret = scmi_perf_level_limits_notify(handle, src_id, cmd_id, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n",
+			 evt_id, src_id, ret);
+
+	return ret;
+}
+
+static void *scmi_perf_fill_custom_report(const struct scmi_handle *handle,
+					  u8 evt_id, u64 timestamp,
+					  const void *payld, size_t payld_sz,
+					  void *report, u32 *src_id)
+{
+	void *rep = NULL;
+
+	switch (evt_id) {
+	case SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED:
+	{
+		const struct scmi_perf_limits_notify_payld *p = payld;
+		struct scmi_perf_limits_report *r = report;
+
+		if (sizeof(*p) != payld_sz)
+			break;
+
+		r->timestamp = timestamp;
+		r->agent_id = le32_to_cpu(p->agent_id);
+		r->domain_id = le32_to_cpu(p->domain_id);
+		r->range_max = le32_to_cpu(p->range_max);
+		r->range_min = le32_to_cpu(p->range_min);
+		*src_id = r->domain_id;
+		rep = r;
+		break;
+	}
+	case SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED:
+	{
+		const struct scmi_perf_level_notify_payld *p = payld;
+		struct scmi_perf_level_report *r = report;
+
+		if (sizeof(*p) != payld_sz)
+			break;
+
+		r->timestamp = timestamp;
+		r->agent_id = le32_to_cpu(p->agent_id);
+		r->domain_id = le32_to_cpu(p->domain_id);
+		r->performance_level = le32_to_cpu(p->performance_level);
+		*src_id = r->domain_id;
+		rep = r;
+		break;
+	}
+	default:
+		break;
+	}
+
+	return rep;
+}
+
+static const struct scmi_event perf_events[] = {
+	{
+		.id = SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED,
+		.max_payld_sz = sizeof(struct scmi_perf_limits_notify_payld),
+		.max_report_sz = sizeof(struct scmi_perf_limits_report),
+	},
+	{
+		.id = SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED,
+		.max_payld_sz = sizeof(struct scmi_perf_level_notify_payld),
+		.max_report_sz = sizeof(struct scmi_perf_level_report),
+	},
+};
+
+static const struct scmi_event_ops perf_event_ops = {
+	.set_notify_enabled = scmi_perf_set_notify_enabled,
+	.fill_custom_report = scmi_perf_fill_custom_report,
+};
+
 static int scmi_perf_protocol_init(struct scmi_handle *handle)
 {
 	int domain;
@@ -754,6 +877,12 @@ static int scmi_perf_protocol_init(struct scmi_handle *handle)
 			scmi_perf_domain_init_fc(handle, domain, &dom->fc_info);
 	}
 
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_PERF, SCMI_PROTO_QUEUE_SZ,
+				      &perf_event_ops, perf_events,
+				      ARRAY_SIZE(perf_events),
+				      pinfo->num_domains);
+
 	pinfo->version = version;
 	handle->perf_ops = &perf_ops;
 	handle->perf_priv = pinfo;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 81dc3b132fda..65ad83ddde70 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -378,6 +378,8 @@ void scmi_protocol_unregister(int protocol_id);
 /* SCMI Notification API - Custom Event Reports */
 enum scmi_notification_events {
 	SCMI_EVENT_POWER_STATE_CHANGED = 0x0,
+	SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0,
+	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
 };
 
 struct scmi_power_state_changed_report {
@@ -387,4 +389,19 @@ struct scmi_power_state_changed_report {
 	u32 power_state;
 };
 
+struct scmi_perf_limits_report {
+	u64 timestamp;
+	u32 agent_id;
+	u32 domain_id;
+	u32 range_max;
+	u32 range_min;
+};
+
+struct scmi_perf_level_report {
+	u64 timestamp;
+	u32 agent_id;
+	u32 domain_id;
+	u32 performance_level;
+};
+
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From 128e3e9311a95bab6b267b7a93eb9ebe2347dbda Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:46 +0100
Subject: firmware: arm_scmi: Add sensor notifications support

Make SCMI sensor protocol register with the notification core.

Link: https://lore.kernel.org/r/20200701155348.52864-8-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/sensors.c | 69 ++++++++++++++++++++++++++++++++++---
 include/linux/scmi_protocol.h       | 13 ++++---
 2 files changed, 72 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index db1b1ab303da..2120ac4787c9 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -5,7 +5,12 @@
  * Copyright (C) 2018 ARM Ltd.
  */
 
+#define pr_fmt(fmt) "SCMI Notifications SENSOR - " fmt
+
+#include <linux/scmi_protocol.h>
+
 #include "common.h"
+#include "notify.h"
 
 enum scmi_sensor_protocol_cmd {
 	SENSOR_DESCRIPTION_GET = 0x3,
@@ -14,10 +19,6 @@ enum scmi_sensor_protocol_cmd {
 	SENSOR_READING_GET = 0x6,
 };
 
-enum scmi_sensor_protocol_notify {
-	SENSOR_TRIP_POINT_EVENT = 0x0,
-};
-
 struct scmi_msg_resp_sensor_attributes {
 	__le16 num_sensors;
 	u8 max_requests;
@@ -71,6 +72,12 @@ struct scmi_msg_sensor_reading_get {
 #define SENSOR_READ_ASYNC	BIT(0)
 };
 
+struct scmi_sensor_trip_notify_payld {
+	__le32 agent_id;
+	__le32 sensor_id;
+	__le32 trip_point_desc;
+};
+
 struct sensors_info {
 	u32 version;
 	int num_sensors;
@@ -271,11 +278,57 @@ static int scmi_sensor_count_get(const struct scmi_handle *handle)
 static struct scmi_sensor_ops sensor_ops = {
 	.count_get = scmi_sensor_count_get,
 	.info_get = scmi_sensor_info_get,
-	.trip_point_notify = scmi_sensor_trip_point_notify,
 	.trip_point_config = scmi_sensor_trip_point_config,
 	.reading_get = scmi_sensor_reading_get,
 };
 
+static int scmi_sensor_set_notify_enabled(const struct scmi_handle *handle,
+					  u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_sensor_trip_point_notify(handle, src_id, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n",
+			 evt_id, src_id, ret);
+
+	return ret;
+}
+
+static void *scmi_sensor_fill_custom_report(const struct scmi_handle *handle,
+					    u8 evt_id, u64 timestamp,
+					    const void *payld, size_t payld_sz,
+					    void *report, u32 *src_id)
+{
+	const struct scmi_sensor_trip_notify_payld *p = payld;
+	struct scmi_sensor_trip_point_report *r = report;
+
+	if (evt_id != SCMI_EVENT_SENSOR_TRIP_POINT_EVENT ||
+	    sizeof(*p) != payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->sensor_id = le32_to_cpu(p->sensor_id);
+	r->trip_point_desc = le32_to_cpu(p->trip_point_desc);
+	*src_id = r->sensor_id;
+
+	return r;
+}
+
+static const struct scmi_event sensor_events[] = {
+	{
+		.id = SCMI_EVENT_SENSOR_TRIP_POINT_EVENT,
+		.max_payld_sz = sizeof(struct scmi_sensor_trip_notify_payld),
+		.max_report_sz = sizeof(struct scmi_sensor_trip_point_report),
+	},
+};
+
+static const struct scmi_event_ops sensor_event_ops = {
+	.set_notify_enabled = scmi_sensor_set_notify_enabled,
+	.fill_custom_report = scmi_sensor_fill_custom_report,
+};
+
 static int scmi_sensors_protocol_init(struct scmi_handle *handle)
 {
 	u32 version;
@@ -299,6 +352,12 @@ static int scmi_sensors_protocol_init(struct scmi_handle *handle)
 
 	scmi_sensor_description_get(handle, sinfo);
 
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_SENSOR, SCMI_PROTO_QUEUE_SZ,
+				      &sensor_event_ops, sensor_events,
+				      ARRAY_SIZE(sensor_events),
+				      sinfo->num_sensors);
+
 	sinfo->version = version;
 	handle->sensor_ops = &sensor_ops;
 	handle->sensor_priv = sinfo;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 65ad83ddde70..d0ea4a5037e7 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -176,18 +176,13 @@ enum scmi_sensor_class {
  *
  * @count_get: get the count of sensors provided by SCMI
  * @info_get: get the information of the specified sensor
- * @trip_point_notify: control notifications on cross-over events for
- *	the trip-points
  * @trip_point_config: selects and configures a trip-point of interest
  * @reading_get: gets the current value of the sensor
  */
 struct scmi_sensor_ops {
 	int (*count_get)(const struct scmi_handle *handle);
-
 	const struct scmi_sensor_info *(*info_get)
 		(const struct scmi_handle *handle, u32 sensor_id);
-	int (*trip_point_notify)(const struct scmi_handle *handle,
-				 u32 sensor_id, bool enable);
 	int (*trip_point_config)(const struct scmi_handle *handle,
 				 u32 sensor_id, u8 trip_id, u64 trip_value);
 	int (*reading_get)(const struct scmi_handle *handle, u32 sensor_id,
@@ -380,6 +375,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_POWER_STATE_CHANGED = 0x0,
 	SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0,
 	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
+	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
 };
 
 struct scmi_power_state_changed_report {
@@ -404,4 +400,11 @@ struct scmi_perf_level_report {
 	u32 performance_level;
 };
 
+struct scmi_sensor_trip_point_report {
+	u64 timestamp;
+	u32 agent_id;
+	u32 sensor_id;
+	u32 trip_point_desc;
+};
+
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From 469ca1822d64e4a786935576edb696c52119aa11 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:47 +0100
Subject: firmware: arm_scmi: Add reset notifications support

Make SCMI reset protocol register with the notification core.

Link: https://lore.kernel.org/r/20200701155348.52864-9-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/reset.c | 96 +++++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h     |  8 ++++
 2 files changed, 100 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index de73054554f3..fb7cb517900b 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -5,7 +5,12 @@
  * Copyright (C) 2019 ARM Ltd.
  */
 
+#define pr_fmt(fmt) "SCMI Notifications RESET - " fmt
+
+#include <linux/scmi_protocol.h>
+
 #include "common.h"
+#include "notify.h"
 
 enum scmi_reset_protocol_cmd {
 	RESET_DOMAIN_ATTRIBUTES = 0x3,
@@ -13,10 +18,6 @@ enum scmi_reset_protocol_cmd {
 	RESET_NOTIFY = 0x5,
 };
 
-enum scmi_reset_protocol_notify {
-	RESET_ISSUED = 0x0,
-};
-
 #define NUM_RESET_DOMAIN_MASK	0xffff
 #define RESET_NOTIFY_ENABLE	BIT(0)
 
@@ -40,6 +41,18 @@ struct scmi_msg_reset_domain_reset {
 #define ARCH_COLD_RESET		(ARCH_RESET_TYPE | COLD_RESET_STATE)
 };
 
+struct scmi_msg_reset_notify {
+	__le32 id;
+	__le32 event_control;
+#define RESET_TP_NOTIFY_ALL	BIT(0)
+};
+
+struct scmi_reset_issued_notify_payld {
+	__le32 agent_id;
+	__le32 domain_id;
+	__le32 reset_state;
+};
+
 struct reset_dom_info {
 	bool async_reset;
 	bool reset_notify;
@@ -190,6 +203,75 @@ static struct scmi_reset_ops reset_ops = {
 	.deassert = scmi_reset_domain_deassert,
 };
 
+static int scmi_reset_notify(const struct scmi_handle *handle, u32 domain_id,
+			     bool enable)
+{
+	int ret;
+	u32 evt_cntl = enable ? RESET_TP_NOTIFY_ALL : 0;
+	struct scmi_xfer *t;
+	struct scmi_msg_reset_notify *cfg;
+
+	ret = scmi_xfer_get_init(handle, RESET_NOTIFY,
+				 SCMI_PROTOCOL_RESET, sizeof(*cfg), 0, &t);
+	if (ret)
+		return ret;
+
+	cfg = t->tx.buf;
+	cfg->id = cpu_to_le32(domain_id);
+	cfg->event_control = cpu_to_le32(evt_cntl);
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_reset_set_notify_enabled(const struct scmi_handle *handle,
+					 u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_reset_notify(handle, src_id, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n",
+			 evt_id, src_id, ret);
+
+	return ret;
+}
+
+static void *scmi_reset_fill_custom_report(const struct scmi_handle *handle,
+					   u8 evt_id, u64 timestamp,
+					   const void *payld, size_t payld_sz,
+					   void *report, u32 *src_id)
+{
+	const struct scmi_reset_issued_notify_payld *p = payld;
+	struct scmi_reset_issued_report *r = report;
+
+	if (evt_id != SCMI_EVENT_RESET_ISSUED || sizeof(*p) != payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->domain_id = le32_to_cpu(p->domain_id);
+	r->reset_state = le32_to_cpu(p->reset_state);
+	*src_id = r->domain_id;
+
+	return r;
+}
+
+static const struct scmi_event reset_events[] = {
+	{
+		.id = SCMI_EVENT_RESET_ISSUED,
+		.max_payld_sz = sizeof(struct scmi_reset_issued_notify_payld),
+		.max_report_sz = sizeof(struct scmi_reset_issued_report),
+	},
+};
+
+static const struct scmi_event_ops reset_event_ops = {
+	.set_notify_enabled = scmi_reset_set_notify_enabled,
+	.fill_custom_report = scmi_reset_fill_custom_report,
+};
+
 static int scmi_reset_protocol_init(struct scmi_handle *handle)
 {
 	int domain;
@@ -218,6 +300,12 @@ static int scmi_reset_protocol_init(struct scmi_handle *handle)
 		scmi_reset_domain_attributes_get(handle, domain, dom);
 	}
 
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_RESET, SCMI_PROTO_QUEUE_SZ,
+				      &reset_event_ops, reset_events,
+				      ARRAY_SIZE(reset_events),
+				      pinfo->num_domains);
+
 	pinfo->version = version;
 	handle->reset_ops = &reset_ops;
 	handle->reset_priv = pinfo;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index d0ea4a5037e7..d04d66be596d 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -376,6 +376,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0,
 	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
+	SCMI_EVENT_RESET_ISSUED = 0x0,
 };
 
 struct scmi_power_state_changed_report {
@@ -407,4 +408,11 @@ struct scmi_sensor_trip_point_report {
 	u32 trip_point_desc;
 };
 
+struct scmi_reset_issued_report {
+	u64 timestamp;
+	u32 agent_id;
+	u32 domain_id;
+	u32 reset_state;
+};
+
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From 585dfab3fb80e67b3a54790b3d5ef2991feb3950 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 1 Jul 2020 16:53:48 +0100
Subject: firmware: arm_scmi: Add base notifications support

Make SCMI base protocol register with the notification core.

Link: https://lore.kernel.org/r/20200701155348.52864-10-cristian.marussi@arm.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/base.c | 108 +++++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h    |   9 ++++
 2 files changed, 113 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c
index ce7d9203e41b..54f378e946f1 100644
--- a/drivers/firmware/arm_scmi/base.c
+++ b/drivers/firmware/arm_scmi/base.c
@@ -5,7 +5,15 @@
  * Copyright (C) 2018 ARM Ltd.
  */
 
+#define pr_fmt(fmt) "SCMI Notifications BASE - " fmt
+
+#include <linux/scmi_protocol.h>
+
 #include "common.h"
+#include "notify.h"
+
+#define SCMI_BASE_NUM_SOURCES		1
+#define SCMI_BASE_MAX_CMD_ERR_COUNT	1024
 
 enum scmi_base_protocol_cmd {
 	BASE_DISCOVER_VENDOR = 0x3,
@@ -19,16 +27,25 @@ enum scmi_base_protocol_cmd {
 	BASE_RESET_AGENT_CONFIGURATION = 0xb,
 };
 
-enum scmi_base_protocol_notify {
-	BASE_ERROR_EVENT = 0x0,
-};
-
 struct scmi_msg_resp_base_attributes {
 	u8 num_protocols;
 	u8 num_agents;
 	__le16 reserved;
 };
 
+struct scmi_msg_base_error_notify {
+	__le32 event_control;
+#define BASE_TP_NOTIFY_ALL	BIT(0)
+};
+
+struct scmi_base_error_notify_payld {
+	__le32 agent_id;
+	__le32 error_status;
+#define IS_FATAL_ERROR(x)	((x) & BIT(31))
+#define ERROR_CMD_COUNT(x)	FIELD_GET(GENMASK(9, 0), (x))
+	__le64 msg_reports[SCMI_BASE_MAX_CMD_ERR_COUNT];
+};
+
 /**
  * scmi_base_attributes_get() - gets the implementation details
  *	that are associated with the base protocol.
@@ -222,6 +239,83 @@ static int scmi_base_discover_agent_get(const struct scmi_handle *handle,
 	return ret;
 }
 
+static int scmi_base_error_notify(const struct scmi_handle *handle, bool enable)
+{
+	int ret;
+	u32 evt_cntl = enable ? BASE_TP_NOTIFY_ALL : 0;
+	struct scmi_xfer *t;
+	struct scmi_msg_base_error_notify *cfg;
+
+	ret = scmi_xfer_get_init(handle, BASE_NOTIFY_ERRORS,
+				 SCMI_PROTOCOL_BASE, sizeof(*cfg), 0, &t);
+	if (ret)
+		return ret;
+
+	cfg = t->tx.buf;
+	cfg->event_control = cpu_to_le32(evt_cntl);
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_base_set_notify_enabled(const struct scmi_handle *handle,
+					u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_base_error_notify(handle, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLED - evt[%X] ret:%d\n", evt_id, ret);
+
+	return ret;
+}
+
+static void *scmi_base_fill_custom_report(const struct scmi_handle *handle,
+					  u8 evt_id, u64 timestamp,
+					  const void *payld, size_t payld_sz,
+					  void *report, u32 *src_id)
+{
+	int i;
+	const struct scmi_base_error_notify_payld *p = payld;
+	struct scmi_base_error_report *r = report;
+
+	/*
+	 * BaseError notification payload is variable in size but
+	 * up to a maximum length determined by the struct ponted by p.
+	 * Instead payld_sz is the effective length of this notification
+	 * payload so cannot be greater of the maximum allowed size as
+	 * pointed by p.
+	 */
+	if (evt_id != SCMI_EVENT_BASE_ERROR_EVENT || sizeof(*p) < payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->fatal = IS_FATAL_ERROR(le32_to_cpu(p->error_status));
+	r->cmd_count = ERROR_CMD_COUNT(le32_to_cpu(p->error_status));
+	for (i = 0; i < r->cmd_count; i++)
+		r->reports[i] = le64_to_cpu(p->msg_reports[i]);
+	*src_id = 0;
+
+	return r;
+}
+
+static const struct scmi_event base_events[] = {
+	{
+		.id = SCMI_EVENT_BASE_ERROR_EVENT,
+		.max_payld_sz = sizeof(struct scmi_base_error_notify_payld),
+		.max_report_sz = sizeof(struct scmi_base_error_report) +
+				  SCMI_BASE_MAX_CMD_ERR_COUNT * sizeof(u64),
+	},
+};
+
+static const struct scmi_event_ops base_event_ops = {
+	.set_notify_enabled = scmi_base_set_notify_enabled,
+	.fill_custom_report = scmi_base_fill_custom_report,
+};
+
 int scmi_base_protocol_init(struct scmi_handle *h)
 {
 	int id, ret;
@@ -256,6 +350,12 @@ int scmi_base_protocol_init(struct scmi_handle *h)
 	dev_dbg(dev, "Found %d protocol(s) %d agent(s)\n", rev->num_protocols,
 		rev->num_agents);
 
+	scmi_register_protocol_events(handle, SCMI_PROTOCOL_BASE,
+				      (4 * SCMI_PROTO_QUEUE_SZ),
+				      &base_event_ops, base_events,
+				      ARRAY_SIZE(base_events),
+				      SCMI_BASE_NUM_SOURCES);
+
 	for (id = 0; id < rev->num_agents; id++) {
 		scmi_base_discover_agent_get(handle, id, name);
 		dev_dbg(dev, "Agent %d: %s\n", id, name);
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index d04d66be596d..46d98be92466 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -377,6 +377,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
 	SCMI_EVENT_RESET_ISSUED = 0x0,
+	SCMI_EVENT_BASE_ERROR_EVENT = 0x0,
 };
 
 struct scmi_power_state_changed_report {
@@ -415,4 +416,12 @@ struct scmi_reset_issued_report {
 	u32 reset_state;
 };
 
+struct scmi_base_error_report {
+	u64 timestamp;
+	u32 agent_id;
+	bool fatal;
+	u16 cmd_count;
+	u64 reports[0];
+};
+
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From 3022c6a1b4b76c40aab9dcdf5142c501f3d3ae8c Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 25 Jun 2020 16:51:03 -0700
Subject: driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW}

A common pattern for using plain DEVICE_ATTR() instead of
DEVICE_ATTR_RO() and DEVICE_ATTR_RW() is for attributes that want to
limit read to only root.  I.e. many users of DEVICE_ATTR() are
specifying 0400 or 0600 for permissions.

Given the expectation that CAP_SYS_ADMIN is needed to access these
sensitive attributes and an explicit helper with the _ADMIN_ identifier
for DEVICE_ATTR_ADMIN_{RO,RW}.

Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/159312906372.1850128.11611897078988158727.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 4 ++++
 include/linux/sysfs.h  | 7 +++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..d7c2570368fa 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -128,8 +128,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
 		__ATTR_PREALLOC(_name, _mode, _show, _store)
 #define DEVICE_ATTR_RW(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
+#define DEVICE_ATTR_ADMIN_RW(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600)
 #define DEVICE_ATTR_RO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
+#define DEVICE_ATTR_ADMIN_RO(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400)
 #define DEVICE_ATTR_WO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
 #define DEVICE_ULONG_ATTR(_name, _mode, _var) \
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 86067dbe7745..34e84122f635 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -123,6 +123,13 @@ struct attribute_group {
 	.show	= _name##_show,						\
 }
 
+#define __ATTR_RW_MODE(_name, _mode) {					\
+	.attr	= { .name = __stringify(_name),				\
+		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
+	.show	= _name##_show,						\
+	.store	= _name##_store,					\
+}
+
 #define __ATTR_WO(_name) {						\
 	.attr	= { .name = __stringify(_name), .mode = 0200 },		\
 	.store	= _name##_store,					\
-- 
cgit v1.2.3


From 9fc54012d7aec4b23f2042dc37b26738f3e68942 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 30 Jun 2020 18:17:07 -0400
Subject: audit: remove unused !CONFIG_AUDITSYSCALL __audit_inode* stubs

Added 14 years ago in commit 73241ccca0f7 ("[PATCH] Collect more inode
information during syscall processing.") but never used however
needlessly churned no less than 10 times since.  Remove the unused
__audit_inode* stubs in the !CONFIG_AUDITSYSCALL case.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index d93739f7a35a..b5478c64bc69 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -579,14 +579,6 @@ static inline struct filename *audit_reusename(const __user char *name)
 }
 static inline void audit_getname(struct filename *name)
 { }
-static inline void __audit_inode(struct filename *name,
-					const struct dentry *dentry,
-					unsigned int flags)
-{ }
-static inline void __audit_inode_child(struct inode *parent,
-					const struct dentry *dentry,
-					const unsigned char type)
-{ }
 static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int aflags)
-- 
cgit v1.2.3


From d40f0b6f2e21f2400ae8b1b120d11877d9ffd8ec Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 29 Jun 2020 16:41:06 -0700
Subject: spi: Avoid setting the chip select if we don't need to

On some SPI controllers (like spi-geni-qcom) setting the chip select
is a heavy operation.  For instance on spi-geni-qcom, with the current
code, is was measured as taking upwards of 20 us.  Even on SPI
controllers that aren't as heavy, setting the chip select is at least
something like a MMIO operation over some peripheral bus which isn't
as fast as a RAM access.

While it would be good to find ways to mitigate problems like this in
the drivers for those SPI controllers, it can also be noted that the
SPI framework could also help out.  Specifically, in some situations,
we can see the SPI framework calling the driver's set_cs() with the
same parameter several times in a row.  This is specifically observed
when looking at the way the Chrome OS EC SPI driver (cros_ec_spi)
works but other drivers likely trip it to some extent.

Let's solve this by caching the chip select state in the core and only
calling into the controller if there was a change.  We check not only
the "enable" state but also the chip select mode (active high or
active low) since controllers may care about both the mode and the
enable flag in their callback.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20200629164103.1.Ied8e8ad8bbb2df7f947e3bc5ea1c315e041785a2@changeid
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 11 +++++++++++
 include/linux/spi/spi.h |  4 ++++
 2 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 6fa56590bba2..d4ba723a30da 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -778,6 +778,17 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 {
 	bool enable1 = enable;
 
+	/*
+	 * Avoid calling into the driver (or doing delays) if the chip select
+	 * isn't actually changing from the last time this was called.
+	 */
+	if ((spi->controller->last_cs_enable == enable) &&
+	    (spi->controller->last_cs_mode_high == (spi->mode & SPI_CS_HIGH)))
+		return;
+
+	spi->controller->last_cs_enable = enable;
+	spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH;
+
 	if (!spi->controller->set_cs_timing) {
 		if (enable1)
 			spi_delay_exec(&spi->controller->cs_setup, NULL);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index b4917df79637..0e67a9a3a1d3 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -368,6 +368,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
  * @cur_msg_mapped: message has been mapped for DMA
+ * @last_cs_enable: was enable true on the last call to set_cs.
+ * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs.
  * @xfer_completion: used by core transfer_one_message()
  * @busy: message pump is busy
  * @running: message pump is running
@@ -604,6 +606,8 @@ struct spi_controller {
 	bool				auto_runtime_pm;
 	bool                            cur_msg_prepared;
 	bool				cur_msg_mapped;
+	bool				last_cs_enable;
+	bool				last_cs_mode_high;
 	bool                            fallback;
 	struct completion               xfer_completion;
 	size_t				max_dma_len;
-- 
cgit v1.2.3


From 10dd8573b09e84b81539d939d55ebdb6a36c5f3a Mon Sep 17 00:00:00 2001
From: Quentin Perret <qperret@google.com>
Date: Mon, 29 Jun 2020 13:54:59 +0530
Subject: cpufreq: Register governors at core_initcall

Currently, most CPUFreq governors are registered at the core_initcall
time when the given governor is the default one, and the module_init
time otherwise.

In preparation for letting users specify the default governor on the
kernel command line, change all of them to be registered at the
core_initcall unconditionally, as it is already the case for the
schedutil and performance governors. This will allow us to assume
that builtin governors have been registered before the built-in
CPUFreq drivers probe.

And since all governors have similar init/exit patterns now, introduce
two new macros, cpufreq_governor_{init,exit}(), to factorize the code.

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/powerpc/platforms/cell/cpufreq_spudemand.c | 26 ++-----------------------
 drivers/cpufreq/cpufreq_conservative.c          | 22 +++++----------------
 drivers/cpufreq/cpufreq_ondemand.c              | 24 ++++++-----------------
 drivers/cpufreq/cpufreq_performance.c           | 14 ++-----------
 drivers/cpufreq/cpufreq_powersave.c             | 18 +++--------------
 drivers/cpufreq/cpufreq_userspace.c             | 18 +++--------------
 include/linux/cpufreq.h                         | 14 +++++++++++++
 kernel/sched/cpufreq_schedutil.c                |  6 +-----
 8 files changed, 36 insertions(+), 106 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 55b31eadb3c8..ca7849e113d7 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -126,30 +126,8 @@ static struct cpufreq_governor spu_governor = {
 	.stop = spu_gov_stop,
 	.owner = THIS_MODULE,
 };
-
-/*
- * module init and destoy
- */
-
-static int __init spu_gov_init(void)
-{
-	int ret;
-
-	ret = cpufreq_register_governor(&spu_governor);
-	if (ret)
-		printk(KERN_ERR "registration of governor failed\n");
-	return ret;
-}
-
-static void __exit spu_gov_exit(void)
-{
-	cpufreq_unregister_governor(&spu_governor);
-}
-
-
-module_init(spu_gov_init);
-module_exit(spu_gov_exit);
+cpufreq_governor_init(spu_governor);
+cpufreq_governor_exit(spu_governor);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 737ff3b9c2c0..aa39ff31ec9f 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -322,17 +322,7 @@ static struct dbs_governor cs_governor = {
 	.start = cs_start,
 };
 
-#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_governor.gov)
-
-static int __init cpufreq_gov_dbs_init(void)
-{
-	return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE);
-}
-
-static void __exit cpufreq_gov_dbs_exit(void)
-{
-	cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE);
-}
+#define CPU_FREQ_GOV_CONSERVATIVE	(cs_governor.gov)
 
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
 MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
@@ -343,11 +333,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return CPU_FREQ_GOV_CONSERVATIVE;
+	return &CPU_FREQ_GOV_CONSERVATIVE;
 }
-
-core_initcall(cpufreq_gov_dbs_init);
-#else
-module_init(cpufreq_gov_dbs_init);
 #endif
-module_exit(cpufreq_gov_dbs_exit);
+
+cpufreq_governor_init(CPU_FREQ_GOV_CONSERVATIVE);
+cpufreq_governor_exit(CPU_FREQ_GOV_CONSERVATIVE);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 82a4d37ddecb..ac361a8b1d3b 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -408,7 +408,7 @@ static struct dbs_governor od_dbs_gov = {
 	.start = od_start,
 };
 
-#define CPU_FREQ_GOV_ONDEMAND	(&od_dbs_gov.gov)
+#define CPU_FREQ_GOV_ONDEMAND	(od_dbs_gov.gov)
 
 static void od_set_powersave_bias(unsigned int powersave_bias)
 {
@@ -429,7 +429,7 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 			continue;
 
 		policy = cpufreq_cpu_get_raw(cpu);
-		if (!policy || policy->governor != CPU_FREQ_GOV_ONDEMAND)
+		if (!policy || policy->governor != &CPU_FREQ_GOV_ONDEMAND)
 			continue;
 
 		policy_dbs = policy->governor_data;
@@ -461,16 +461,6 @@ void od_unregister_powersave_bias_handler(void)
 }
 EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
 
-static int __init cpufreq_gov_dbs_init(void)
-{
-	return cpufreq_register_governor(CPU_FREQ_GOV_ONDEMAND);
-}
-
-static void __exit cpufreq_gov_dbs_exit(void)
-{
-	cpufreq_unregister_governor(CPU_FREQ_GOV_ONDEMAND);
-}
-
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
 MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
@@ -480,11 +470,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return CPU_FREQ_GOV_ONDEMAND;
+	return &CPU_FREQ_GOV_ONDEMAND;
 }
-
-core_initcall(cpufreq_gov_dbs_init);
-#else
-module_init(cpufreq_gov_dbs_init);
 #endif
-module_exit(cpufreq_gov_dbs_exit);
+
+cpufreq_governor_init(CPU_FREQ_GOV_ONDEMAND);
+cpufreq_governor_exit(CPU_FREQ_GOV_ONDEMAND);
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index def9afe0f5b8..71c1d9aba772 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -23,16 +23,6 @@ static struct cpufreq_governor cpufreq_gov_performance = {
 	.limits		= cpufreq_gov_performance_limits,
 };
 
-static int __init cpufreq_gov_performance_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_performance);
-}
-
-static void __exit cpufreq_gov_performance_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_performance);
-}
-
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
@@ -50,5 +40,5 @@ MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
 MODULE_LICENSE("GPL");
 
-core_initcall(cpufreq_gov_performance_init);
-module_exit(cpufreq_gov_performance_exit);
+cpufreq_governor_init(cpufreq_gov_performance);
+cpufreq_governor_exit(cpufreq_gov_performance);
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 1ae66019eb83..7749522355b5 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -23,16 +23,6 @@ static struct cpufreq_governor cpufreq_gov_powersave = {
 	.owner		= THIS_MODULE,
 };
 
-static int __init cpufreq_gov_powersave_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_powersave);
-}
-
-static void __exit cpufreq_gov_powersave_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_powersave);
-}
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
 MODULE_LICENSE("GPL");
@@ -42,9 +32,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &cpufreq_gov_powersave;
 }
-
-core_initcall(cpufreq_gov_powersave_init);
-#else
-module_init(cpufreq_gov_powersave_init);
 #endif
-module_exit(cpufreq_gov_powersave_exit);
+
+cpufreq_governor_init(cpufreq_gov_powersave);
+cpufreq_governor_exit(cpufreq_gov_powersave);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index b43e7cd502c5..50a4d7846580 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -126,16 +126,6 @@ static struct cpufreq_governor cpufreq_gov_userspace = {
 	.owner		= THIS_MODULE,
 };
 
-static int __init cpufreq_gov_userspace_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_userspace);
-}
-
-static void __exit cpufreq_gov_userspace_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_userspace);
-}
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>, "
 		"Russell King <rmk@arm.linux.org.uk>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'");
@@ -146,9 +136,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &cpufreq_gov_userspace;
 }
-
-core_initcall(cpufreq_gov_userspace_init);
-#else
-module_init(cpufreq_gov_userspace_init);
 #endif
-module_exit(cpufreq_gov_userspace_exit);
+
+cpufreq_governor_init(cpufreq_gov_userspace);
+cpufreq_governor_exit(cpufreq_gov_userspace);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 3494f6763597..e62b022cb07e 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -577,6 +577,20 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy);
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
+#define cpufreq_governor_init(__governor)			\
+static int __init __governor##_init(void)			\
+{								\
+	return cpufreq_register_governor(&__governor);	\
+}								\
+core_initcall(__governor##_init)
+
+#define cpufreq_governor_exit(__governor)			\
+static void __exit __governor##_exit(void)			\
+{								\
+	return cpufreq_unregister_governor(&__governor);	\
+}								\
+module_exit(__governor##_exit)
+
 struct cpufreq_governor *cpufreq_default_governor(void);
 struct cpufreq_governor *cpufreq_fallback_governor(void);
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7fbaee24c824..402a09af9f43 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -909,11 +909,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
-static int __init sugov_register(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-core_initcall(sugov_register);
+cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;
-- 
cgit v1.2.3


From 67dd0772396905a108c37202d4a5949ab69131a0 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 29 Jun 2020 08:50:05 +0200
Subject: device: remove 'extern' attribute from function prototypes in
 device.h

Functions are declared 'extern' implicitly by the compiler. There's no
reason to prepend every prototype with it. Remove the 'extern' keyword
from all function declarations in linux/device.h.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Link: https://lore.kernel.org/r/20200629065008.27620-4-brgl@bgdev.pl
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 223 ++++++++++++++++++++++++-------------------------
 1 file changed, 107 insertions(+), 116 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index d7c2570368fa..9a62f7f43d55 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -149,68 +149,66 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
 	struct device_attribute dev_attr_##_name =		\
 		__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
 
-extern int device_create_file(struct device *device,
-			      const struct device_attribute *entry);
-extern void device_remove_file(struct device *dev,
-			       const struct device_attribute *attr);
-extern bool device_remove_file_self(struct device *dev,
-				    const struct device_attribute *attr);
-extern int __must_check device_create_bin_file(struct device *dev,
+int device_create_file(struct device *device,
+		       const struct device_attribute *entry);
+void device_remove_file(struct device *dev,
+			const struct device_attribute *attr);
+bool device_remove_file_self(struct device *dev,
+			     const struct device_attribute *attr);
+int __must_check device_create_bin_file(struct device *dev,
 					const struct bin_attribute *attr);
-extern void device_remove_bin_file(struct device *dev,
-				   const struct bin_attribute *attr);
+void device_remove_bin_file(struct device *dev,
+			    const struct bin_attribute *attr);
 
 /* device resource management */
 typedef void (*dr_release_t)(struct device *dev, void *res);
 typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data);
 
 #ifdef CONFIG_DEBUG_DEVRES
-extern void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp,
-				 int nid, const char *name) __malloc;
+void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp,
+			  int nid, const char *name) __malloc;
 #define devres_alloc(release, size, gfp) \
 	__devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release)
 #define devres_alloc_node(release, size, gfp, nid) \
 	__devres_alloc_node(release, size, gfp, nid, #release)
 #else
-extern void *devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp,
-			       int nid) __malloc;
+void *devres_alloc_node(dr_release_t release, size_t size,
+			gfp_t gfp, int nid) __malloc;
 static inline void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp)
 {
 	return devres_alloc_node(release, size, gfp, NUMA_NO_NODE);
 }
 #endif
 
-extern void devres_for_each_res(struct device *dev, dr_release_t release,
-				dr_match_t match, void *match_data,
-				void (*fn)(struct device *, void *, void *),
-				void *data);
-extern void devres_free(void *res);
-extern void devres_add(struct device *dev, void *res);
-extern void *devres_find(struct device *dev, dr_release_t release,
-			 dr_match_t match, void *match_data);
-extern void *devres_get(struct device *dev, void *new_res,
-			dr_match_t match, void *match_data);
-extern void *devres_remove(struct device *dev, dr_release_t release,
-			   dr_match_t match, void *match_data);
-extern int devres_destroy(struct device *dev, dr_release_t release,
-			  dr_match_t match, void *match_data);
-extern int devres_release(struct device *dev, dr_release_t release,
-			  dr_match_t match, void *match_data);
+void devres_for_each_res(struct device *dev, dr_release_t release,
+			 dr_match_t match, void *match_data,
+			 void (*fn)(struct device *, void *, void *),
+			 void *data);
+void devres_free(void *res);
+void devres_add(struct device *dev, void *res);
+void *devres_find(struct device *dev, dr_release_t release,
+		  dr_match_t match, void *match_data);
+void *devres_get(struct device *dev, void *new_res,
+		 dr_match_t match, void *match_data);
+void *devres_remove(struct device *dev, dr_release_t release,
+		    dr_match_t match, void *match_data);
+int devres_destroy(struct device *dev, dr_release_t release,
+		   dr_match_t match, void *match_data);
+int devres_release(struct device *dev, dr_release_t release,
+		   dr_match_t match, void *match_data);
 
 /* devres group */
-extern void * __must_check devres_open_group(struct device *dev, void *id,
-					     gfp_t gfp);
-extern void devres_close_group(struct device *dev, void *id);
-extern void devres_remove_group(struct device *dev, void *id);
-extern int devres_release_group(struct device *dev, void *id);
+void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp);
+void devres_close_group(struct device *dev, void *id);
+void devres_remove_group(struct device *dev, void *id);
+int devres_release_group(struct device *dev, void *id);
 
 /* managed devm_k.alloc/kfree for device drivers */
-extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc;
-extern __printf(3, 0)
-char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt,
-		      va_list ap) __malloc;
-extern __printf(3, 4)
-char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc;
+void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc;
+__printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp,
+				     const char *fmt, va_list ap) __malloc;
+__printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp,
+				    const char *fmt, ...) __malloc;
 static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
 {
 	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
@@ -230,16 +228,14 @@ static inline void *devm_kcalloc(struct device *dev,
 {
 	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
 }
-extern void devm_kfree(struct device *dev, const void *p);
-extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc;
-extern const char *devm_kstrdup_const(struct device *dev,
-				      const char *s, gfp_t gfp);
-extern void *devm_kmemdup(struct device *dev, const void *src, size_t len,
-			  gfp_t gfp);
+void devm_kfree(struct device *dev, const void *p);
+char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc;
+const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp);
+void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp);
 
-extern unsigned long devm_get_free_pages(struct device *dev,
-					 gfp_t gfp_mask, unsigned int order);
-extern void devm_free_pages(struct device *dev, unsigned long addr);
+unsigned long devm_get_free_pages(struct device *dev,
+				  gfp_t gfp_mask, unsigned int order);
+void devm_free_pages(struct device *dev, unsigned long addr);
 
 void __iomem *devm_ioremap_resource(struct device *dev,
 				    const struct resource *res);
@@ -655,8 +651,7 @@ static inline const char *dev_name(const struct device *dev)
 	return kobject_name(&dev->kobj);
 }
 
-extern __printf(2, 3)
-int dev_set_name(struct device *dev, const char *name, ...);
+__printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...);
 
 #ifdef CONFIG_NUMA
 static inline int dev_to_node(struct device *dev)
@@ -813,39 +808,38 @@ static inline bool dev_has_sync_state(struct device *dev)
 /*
  * High level routines for use by the bus drivers
  */
-extern int __must_check device_register(struct device *dev);
-extern void device_unregister(struct device *dev);
-extern void device_initialize(struct device *dev);
-extern int __must_check device_add(struct device *dev);
-extern void device_del(struct device *dev);
-extern int device_for_each_child(struct device *dev, void *data,
-		     int (*fn)(struct device *dev, void *data));
-extern int device_for_each_child_reverse(struct device *dev, void *data,
-		     int (*fn)(struct device *dev, void *data));
-extern struct device *device_find_child(struct device *dev, void *data,
-				int (*match)(struct device *dev, void *data));
-extern struct device *device_find_child_by_name(struct device *parent,
-						const char *name);
-extern int device_rename(struct device *dev, const char *new_name);
-extern int device_move(struct device *dev, struct device *new_parent,
-		       enum dpm_order dpm_order);
-extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
-extern const char *device_get_devnode(struct device *dev,
-				      umode_t *mode, kuid_t *uid, kgid_t *gid,
-				      const char **tmp);
+int __must_check device_register(struct device *dev);
+void device_unregister(struct device *dev);
+void device_initialize(struct device *dev);
+int __must_check device_add(struct device *dev);
+void device_del(struct device *dev);
+int device_for_each_child(struct device *dev, void *data,
+			  int (*fn)(struct device *dev, void *data));
+int device_for_each_child_reverse(struct device *dev, void *data,
+				  int (*fn)(struct device *dev, void *data));
+struct device *device_find_child(struct device *dev, void *data,
+				 int (*match)(struct device *dev, void *data));
+struct device *device_find_child_by_name(struct device *parent,
+					 const char *name);
+int device_rename(struct device *dev, const char *new_name);
+int device_move(struct device *dev, struct device *new_parent,
+		enum dpm_order dpm_order);
+int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
+const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid,
+			       kgid_t *gid, const char **tmp);
 
 static inline bool device_supports_offline(struct device *dev)
 {
 	return dev->bus && dev->bus->offline && dev->bus->online;
 }
 
-extern void lock_device_hotplug(void);
-extern void unlock_device_hotplug(void);
-extern int lock_device_hotplug_sysfs(void);
-extern int device_offline(struct device *dev);
-extern int device_online(struct device *dev);
-extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
-extern void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
+void lock_device_hotplug(void);
+void unlock_device_hotplug(void);
+int lock_device_hotplug_sysfs(void);
+int device_offline(struct device *dev);
+int device_online(struct device *dev);
+void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
+void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
 void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
 
 static inline int dev_num_vf(struct device *dev)
@@ -858,14 +852,13 @@ static inline int dev_num_vf(struct device *dev)
 /*
  * Root device objects for grouping under /sys/devices
  */
-extern struct device *__root_device_register(const char *name,
-					     struct module *owner);
+struct device *__root_device_register(const char *name, struct module *owner);
 
 /* This is a macro to avoid include problems with THIS_MODULE */
 #define root_device_register(name) \
 	__root_device_register(name, THIS_MODULE)
 
-extern void root_device_unregister(struct device *root);
+void root_device_unregister(struct device *root);
 
 static inline void *dev_get_platdata(const struct device *dev)
 {
@@ -876,33 +869,31 @@ static inline void *dev_get_platdata(const struct device *dev)
  * Manual binding of a device to driver. See drivers/base/bus.c
  * for information on use.
  */
-extern int __must_check device_bind_driver(struct device *dev);
-extern void device_release_driver(struct device *dev);
-extern int  __must_check device_attach(struct device *dev);
-extern int __must_check driver_attach(struct device_driver *drv);
-extern void device_initial_probe(struct device *dev);
-extern int __must_check device_reprobe(struct device *dev);
+int __must_check device_bind_driver(struct device *dev);
+void device_release_driver(struct device *dev);
+int  __must_check device_attach(struct device *dev);
+int __must_check driver_attach(struct device_driver *drv);
+void device_initial_probe(struct device *dev);
+int __must_check device_reprobe(struct device *dev);
 
-extern bool device_is_bound(struct device *dev);
+bool device_is_bound(struct device *dev);
 
 /*
  * Easy functions for dynamically creating devices on the fly
  */
-extern __printf(5, 6)
-struct device *device_create(struct class *cls, struct device *parent,
-			     dev_t devt, void *drvdata,
-			     const char *fmt, ...);
-extern __printf(6, 7)
-struct device *device_create_with_groups(struct class *cls,
-			     struct device *parent, dev_t devt, void *drvdata,
-			     const struct attribute_group **groups,
-			     const char *fmt, ...);
-extern void device_destroy(struct class *cls, dev_t devt);
-
-extern int __must_check device_add_groups(struct device *dev,
-					const struct attribute_group **groups);
-extern void device_remove_groups(struct device *dev,
-				 const struct attribute_group **groups);
+__printf(5, 6) struct device *
+device_create(struct class *cls, struct device *parent, dev_t devt,
+	      void *drvdata, const char *fmt, ...);
+__printf(6, 7) struct device *
+device_create_with_groups(struct class *cls, struct device *parent, dev_t devt,
+			  void *drvdata, const struct attribute_group **groups,
+			  const char *fmt, ...);
+void device_destroy(struct class *cls, dev_t devt);
+
+int __must_check device_add_groups(struct device *dev,
+				   const struct attribute_group **groups);
+void device_remove_groups(struct device *dev,
+			  const struct attribute_group **groups);
 
 static inline int __must_check device_add_group(struct device *dev,
 					const struct attribute_group *grp)
@@ -920,14 +911,14 @@ static inline void device_remove_group(struct device *dev,
 	return device_remove_groups(dev, groups);
 }
 
-extern int __must_check devm_device_add_groups(struct device *dev,
+int __must_check devm_device_add_groups(struct device *dev,
 					const struct attribute_group **groups);
-extern void devm_device_remove_groups(struct device *dev,
-				      const struct attribute_group **groups);
-extern int __must_check devm_device_add_group(struct device *dev,
-					const struct attribute_group *grp);
-extern void devm_device_remove_group(struct device *dev,
-				     const struct attribute_group *grp);
+void devm_device_remove_groups(struct device *dev,
+			       const struct attribute_group **groups);
+int __must_check devm_device_add_group(struct device *dev,
+				       const struct attribute_group *grp);
+void devm_device_remove_group(struct device *dev,
+			      const struct attribute_group *grp);
 
 /*
  * Platform "fixup" functions - allow the platform to have their say
@@ -944,21 +935,21 @@ extern int (*platform_notify_remove)(struct device *dev);
  * get_device - atomically increment the reference count for the device.
  *
  */
-extern struct device *get_device(struct device *dev);
-extern void put_device(struct device *dev);
-extern bool kill_device(struct device *dev);
+struct device *get_device(struct device *dev);
+void put_device(struct device *dev);
+bool kill_device(struct device *dev);
 
 #ifdef CONFIG_DEVTMPFS
-extern int devtmpfs_mount(void);
+int devtmpfs_mount(void);
 #else
 static inline int devtmpfs_mount(void) { return 0; }
 #endif
 
 /* drivers/base/power/shutdown.c */
-extern void device_shutdown(void);
+void device_shutdown(void);
 
 /* debugging and troubleshooting/diagnostic helpers. */
-extern const char *dev_driver_string(const struct device *dev);
+const char *dev_driver_string(const struct device *dev);
 
 /* Device links interface. */
 struct device_link *device_link_add(struct device *consumer,
-- 
cgit v1.2.3


From 36847f9e3e56c192ef95e7669df38189443530a0 Mon Sep 17 00:00:00 2001
From: Richard Gong <richard.gong@intel.com>
Date: Mon, 15 Jun 2020 09:29:05 -0500
Subject: firmware: stratix10-svc: correct reconfig flag and timeout values

Correct the incorrect flag value for COMMAND_RECONFIG_FLAG_PARTIAL and
increase FPGA reconfig timeout values so that Intel service layer and
FPGA manager drivers can work with all versions of firmware.

Signed-off-by: Richard Gong <richard.gong@intel.com>
Link: https://lore.kernel.org/r/1592231348-31334-2-git-send-email-richard.gong@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/firmware/intel/stratix10-svc-client.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index 64213c3e82f5..040bc3f3bedd 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -54,18 +54,17 @@
  * Flag bit for COMMAND_RECONFIG
  *
  * COMMAND_RECONFIG_FLAG_PARTIAL:
- * Set to FPGA configuration type (full or partial), the default
- * is full reconfig.
+ * Set to FPGA configuration type (full or partial).
  */
-#define COMMAND_RECONFIG_FLAG_PARTIAL	0
+#define COMMAND_RECONFIG_FLAG_PARTIAL	1
 
 /**
  * Timeout settings for service clients:
  * timeout value used in Stratix10 FPGA manager driver.
  * timeout value used in RSU driver
  */
-#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         100
-#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          240
+#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         300
+#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          720
 #define SVC_RSU_REQUEST_TIMEOUT_MS              300
 
 struct stratix10_svc_chan;
-- 
cgit v1.2.3


From bf0e5bf68a207b14727caf13da576339590a9504 Mon Sep 17 00:00:00 2001
From: Richard Gong <richard.gong@intel.com>
Date: Mon, 15 Jun 2020 09:29:06 -0500
Subject: firmware: stratix10-svc: extend svc to support new RSU features

Extend Intel Stratix10 service layer driver to support new RSU DCMF
versions and max retry parameter.

DCMF = Decision Configuration Management Firmware. The max retry parameter
is the maximum times the images is allowed to reload itself before giving
up and starting RSU failover flow.

Signed-off-by: Richard Gong <richard.gong@intel.com>
Link: https://lore.kernel.org/r/1592231348-31334-3-git-send-email-richard.gong@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/stratix10-svc.c                   | 17 +++++++++
 include/linux/firmware/intel/stratix10-smc.h       | 43 ++++++++++++++++++++++
 .../linux/firmware/intel/stratix10-svc-client.h    |  8 ++++
 3 files changed, 68 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index e0db8dbfc9d1..3aa489dba30a 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -305,9 +305,15 @@ static void svc_thread_recv_status_ok(struct stratix10_svc_data *p_data,
 		cb_data->status = BIT(SVC_STATUS_COMPLETED);
 		break;
 	case COMMAND_RSU_RETRY:
+	case COMMAND_RSU_MAX_RETRY:
 		cb_data->status = BIT(SVC_STATUS_OK);
 		cb_data->kaddr1 = &res.a1;
 		break;
+	case COMMAND_RSU_DCMF_VERSION:
+		cb_data->status = BIT(SVC_STATUS_OK);
+		cb_data->kaddr1 = &res.a1;
+		cb_data->kaddr2 = &res.a2;
+		break;
 	default:
 		pr_warn("it shouldn't happen\n");
 		break;
@@ -406,6 +412,16 @@ static int svc_normal_to_secure_thread(void *data)
 			a1 = 0;
 			a2 = 0;
 			break;
+		case COMMAND_RSU_MAX_RETRY:
+			a0 = INTEL_SIP_SMC_RSU_MAX_RETRY;
+			a1 = 0;
+			a2 = 0;
+			break;
+		case COMMAND_RSU_DCMF_VERSION:
+			a0 = INTEL_SIP_SMC_RSU_DCMF_VERSION;
+			a1 = 0;
+			a2 = 0;
+			break;
 		default:
 			pr_warn("it shouldn't happen\n");
 			break;
@@ -474,6 +490,7 @@ static int svc_normal_to_secure_thread(void *data)
 			 * doesn't support RSU notify or retry
 			 */
 			if ((pdata->command == COMMAND_RSU_RETRY) ||
+			    (pdata->command == COMMAND_RSU_MAX_RETRY) ||
 				(pdata->command == COMMAND_RSU_NOTIFY)) {
 				cbdata->status =
 					BIT(SVC_STATUS_NO_SUPPORT);
diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h
index 682dbf694007..c3e5ab014caf 100644
--- a/include/linux/firmware/intel/stratix10-smc.h
+++ b/include/linux/firmware/intel/stratix10-smc.h
@@ -361,3 +361,46 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
 #define INTEL_SIP_SMC_FUNCID_RSU_RETRY_COUNTER 15
 #define INTEL_SIP_SMC_RSU_RETRY_COUNTER \
 	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_RETRY_COUNTER)
+
+/**
+ * Request INTEL_SIP_SMC_RSU_DCMF_VERSION
+ *
+ * Sync call used by service driver at EL1 to query DCMF (Decision
+ * Configuration Management Firmware) version from FW
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_RSU_DCMF_VERSION
+ * a1-7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ * a1 dcmf1 | dcmf0
+ * a2 dcmf3 | dcmf2
+ *
+ * Or
+ *
+ * a0 INTEL_SIP_SMC_RSU_ERROR
+ */
+#define INTEL_SIP_SMC_FUNCID_RSU_DCMF_VERSION 16
+#define INTEL_SIP_SMC_RSU_DCMF_VERSION \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_DCMF_VERSION)
+
+/**
+ * Request INTEL_SIP_SMC_RSU_MAX_RETRY
+ *
+ * Sync call used by service driver at EL1 to query max retry value from FW
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_RSU_MAX_RETRY
+ * a1-7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ * a1 max retry value
+ *
+ * Or
+ * a0 INTEL_SIP_SMC_RSU_ERROR
+ */
+#define INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY 18
+#define INTEL_SIP_SMC_RSU_MAX_RETRY \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY)
diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index 040bc3f3bedd..a93d85932eb9 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -98,6 +98,12 @@ struct stratix10_svc_chan;
  *
  * @COMMAND_RSU_RETRY: query firmware for the current image's retry counter,
  * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
+ *
+ * @COMMAND_RSU_MAX_RETRY: query firmware for the max retry value,
+ * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
+ *
+ * @COMMAND_RSU_DCMF_VERSION: query firmware for the DCMF version, return status
+ * is SVC_STATUS_OK or SVC_STATUS_ERROR
  */
 enum stratix10_svc_command_code {
 	COMMAND_NOOP = 0,
@@ -109,6 +115,8 @@ enum stratix10_svc_command_code {
 	COMMAND_RSU_UPDATE,
 	COMMAND_RSU_NOTIFY,
 	COMMAND_RSU_RETRY,
+	COMMAND_RSU_MAX_RETRY,
+	COMMAND_RSU_DCMF_VERSION,
 };
 
 /**
-- 
cgit v1.2.3


From c8d141ce1b85d29aba008c8caa1faf174e564843 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 1 Jul 2020 19:15:55 +0200
Subject: USB: Fix up terminology in include files

USB is a HOST/DEVICE protocol, as per the specification and all
documentation.  Fix up terms that are not applicable to make things
match up with the terms used through the rest of the USB stack.

Acked-by: Felipe Balbi <balbi@kernel.org>
Link: https://lore.kernel.org/r/20200701171555.3198836-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h        | 2 +-
 include/linux/usb/ch9.h    | 8 ++++----
 include/linux/usb/gadget.h | 7 ++++---
 3 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index c86e4ec4d00f..c28fc391444a 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -422,7 +422,7 @@ struct usb_devmap {
  * Allocated per bus (tree of devices) we have:
  */
 struct usb_bus {
-	struct device *controller;	/* host/master side hardware */
+	struct device *controller;	/* host side hardware */
 	struct device *sysdev;		/* as seen from firmware or bus */
 	int busnum;			/* Bus number (in order of reg) */
 	const char *bus_name;		/* stable id (PCI slot_name etc) */
diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h
index 58b83066bea4..604c6c514a50 100644
--- a/include/linux/usb/ch9.h
+++ b/include/linux/usb/ch9.h
@@ -6,13 +6,13 @@
  * Wireless USB 1.0 (spread around).  Linux has several APIs in C that
  * need these:
  *
- * - the master/host side Linux-USB kernel driver API;
+ * - the host side Linux-USB kernel driver API;
  * - the "usbfs" user space API; and
- * - the Linux "gadget" slave/device/peripheral side driver API.
+ * - the Linux "gadget" device/peripheral side driver API.
  *
  * USB 2.0 adds an additional "On The Go" (OTG) mode, which lets systems
- * act either as a USB master/host or as a USB slave/device.  That means
- * the master and slave side APIs benefit from working well together.
+ * act either as a USB host or as a USB device.  That means the host and
+ * device side APIs benefit from working well together.
  *
  * There's also "Wireless USB", using low power short range radios for
  * peripheral interconnection but otherwise building on the USB framework.
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 6a178177e4c9..298b334e2951 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -4,7 +4,8 @@
  *
  * We call the USB code inside a Linux-based peripheral device a "gadget"
  * driver, except for the hardware-specific bus glue.  One USB host can
- * master many USB gadgets, but the gadgets are only slaved to one host.
+ * talk to many USB gadgets, but the gadgets are only able to communicate
+ * to one host.
  *
  *
  * (C) Copyright 2002-2004 by David Brownell
@@ -328,7 +329,7 @@ struct usb_gadget_ops {
 };
 
 /**
- * struct usb_gadget - represents a usb slave device
+ * struct usb_gadget - represents a usb device
  * @work: (internal use) Workqueue to be used for sysfs_notify()
  * @udc: struct usb_udc pointer for this gadget
  * @ops: Function pointers used to access hardware-specific operations.
@@ -602,7 +603,7 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget)
 /*-------------------------------------------------------------------------*/
 
 /**
- * struct usb_gadget_driver - driver for usb 'slave' devices
+ * struct usb_gadget_driver - driver for usb gadget devices
  * @function: String describing the gadget's function
  * @max_speed: Highest speed the driver handles.
  * @setup: Invoked for ep0 control requests that aren't handled by
-- 
cgit v1.2.3


From 4dca650991e4175b8d5bae7ff6f1637a0c42be4a Mon Sep 17 00:00:00 2001
From: Michael Guralnik <michaelgur@mellanox.com>
Date: Wed, 20 May 2020 13:59:06 +0300
Subject: net/mlx5: Enable QP number request when creating IPoIB underlay QP

If in the process of creating the underlay QP for an IPoIB interface
the user has set the address and specifically the 1st-3rd bytes
representing the QP number, use the requested QP number when creating
the underlay QP.

For a user to be able to request a QP number on QP creation, the MKEY_BY_NAME
NVCONFIG should be set. As mkey_by_name and qp_by_name are coupled in FW.
This requires driver to query the mkey_by_name max cap during initialization
and set the current cap if it was enabled in FW.

Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 7 +++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c        | 3 +++
 include/linux/mlx5/mlx5_ifc.h                         | 9 +++++++--
 3 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 690b822c6152..d1266d8fed97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -226,13 +226,20 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv)
 
 int mlx5i_create_underlay_qp(struct mlx5e_priv *priv)
 {
+	unsigned char *dev_addr = priv->netdev->dev_addr;
 	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {};
 	struct mlx5i_priv *ipriv = priv->ppriv;
 	void *addr_path;
+	int qpn = 0;
 	int ret = 0;
 	void *qpc;
 
+	if (MLX5_CAP_GEN(priv->mdev, mkey_by_name)) {
+		qpn = (dev_addr[1] << 16) + (dev_addr[2] << 8) + dev_addr[3];
+		MLX5_SET(create_qp_in, in, input_qpn, qpn);
+	}
+
 	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
 	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD);
 	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 8b658908f044..623785fe74b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -557,6 +557,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN_MAX(dev, release_all_pages))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, release_all_pages, 1);
 
+	if (MLX5_CAP_GEN_MAX(dev, mkey_by_name))
+		MLX5_SET(cmd_hca_cap, set_hca_cap, mkey_by_name, 1);
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a227518c70cf..3786888cb1ba 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1392,7 +1392,10 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         bf[0x1];
 	u8         driver_version[0x1];
 	u8         pad_tx_eth_packet[0x1];
-	u8         reserved_at_263[0x8];
+	u8         reserved_at_263[0x3];
+	u8         mkey_by_name[0x1];
+	u8         reserved_at_267[0x4];
+
 	u8         log_bf_reg_size[0x5];
 
 	u8         reserved_at_270[0x8];
@@ -7712,8 +7715,10 @@ struct mlx5_ifc_create_qp_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x8];
+	u8         input_qpn[0x18];
 
+	u8         reserved_at_60[0x20];
 	u8         opt_param_mask[0x20];
 
 	u8         ece[0x20];
-- 
cgit v1.2.3


From d7bf2ebebc2bd61ab95e2a8e33541ef282f303d4 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 3 Jul 2020 22:26:43 +0200
Subject: sched: consistently handle layer3 header accesses in the presence of
 VLANs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.

However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).

To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.

To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.

v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
  bpf_skb_ecn_set_ce()

v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
  calling the helper twice

Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h  | 28 ++++++++++++++++++++++++++++
 include/net/inet_ecn.h   | 25 +++++++++++++++++--------
 include/net/pkt_sched.h  | 11 -----------
 net/core/filter.c        | 10 +++++++---
 net/sched/act_connmark.c |  9 ++++++---
 net/sched/act_csum.c     |  2 +-
 net/sched/act_ct.c       |  9 ++++-----
 net/sched/act_ctinfo.c   |  9 ++++++---
 net/sched/act_mpls.c     |  2 +-
 net/sched/act_skbedit.c  |  2 +-
 net/sched/cls_api.c      |  2 +-
 net/sched/cls_flow.c     |  8 ++++----
 net/sched/cls_flower.c   |  2 +-
 net/sched/em_ipset.c     |  2 +-
 net/sched/em_ipt.c       |  2 +-
 net/sched/em_meta.c      |  2 +-
 net/sched/sch_cake.c     |  4 ++--
 net/sched/sch_dsmark.c   |  6 +++---
 net/sched/sch_teql.c     |  2 +-
 19 files changed, 86 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b05e855f1ddd..427a5b8597c2 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -308,6 +308,34 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
+	__be16 proto = skb->protocol;
+
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
+
+	while (eth_type_vlan(proto)) {
+		struct vlan_hdr vhdr, *vh;
+
+		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
+		if (!vh)
+			break;
+
+		proto = vh->h_vlan_encapsulated_proto;
+		offset += sizeof(vhdr);
+	}
+
+	return proto;
+}
+
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 0f0d1efe06dd..e1eaf1780288 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -4,6 +4,7 @@
 
 #include <linux/ip.h>
 #include <linux/skbuff.h>
+#include <linux/if_vlan.h>
 
 #include <net/inet_sock.h>
 #include <net/dsfield.h>
@@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 
 static inline int INET_ECN_set_ce(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 
 static inline int INET_ECN_set_ect1(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, oiph->tos, inner);
 }
@@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9092e697059e..ac8c890a2657 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -136,17 +136,6 @@ static inline void qdisc_run(struct Qdisc *q)
 	}
 }
 
-static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
-{
-	/* We need to take extra care in case the skb came via
-	 * vlan accelerated path. In that case, use skb->vlan_proto
-	 * as the original vlan header was already stripped.
-	 */
-	if (skb_vlan_tag_present(skb))
-		return skb->vlan_proto;
-	return skb->protocol;
-}
-
 /* Calculate maximal size of packet seen by hard_start_xmit
    routine of this device.
  */
diff --git a/net/core/filter.c b/net/core/filter.c
index 73395384afe2..82e1b5b06167 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5853,12 +5853,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 {
 	unsigned int iphdr_len;
 
-	if (skb->protocol == cpu_to_be16(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case cpu_to_be16(ETH_P_IP):
 		iphdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+		break;
+	case cpu_to_be16(ETH_P_IPV6):
 		iphdr_len = sizeof(struct ipv6hdr);
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	if (skb_headlen(skb) < iphdr_len)
 		return 0;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 43a243081e7d..f901421b0634 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		if (skb->len < sizeof(struct iphdr))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		if (skb->len < sizeof(struct ipv6hdr))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index cb8608f0a77a..c60674cf25c4 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
 		goto drop;
 
 	update_flags = params->update_flags;
-	protocol = tc_skb_protocol(skb);
+	protocol = skb_protocol(skb, false);
 again:
 	switch (protocol) {
 	case cpu_to_be16(ETH_P_IP):
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index e9f3576cbf71..86ed02487467 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -624,7 +624,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
 {
 	u8 family = NFPROTO_UNSPEC;
 
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		family = NFPROTO_IPV4;
 		break;
@@ -748,6 +748,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			  const struct nf_nat_range2 *range,
 			  enum nf_nat_manip_type maniptype)
 {
+	__be16 proto = skb_protocol(skb, true);
 	int hooknum, err = NF_ACCEPT;
 
 	/* See HOOK2MANIP(). */
@@ -759,14 +760,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	switch (ctinfo) {
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
-		if (skb->protocol == htons(ETH_P_IP) &&
+		if (proto == htons(ETH_P_IP) &&
 		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   hooknum))
 				err = NF_DROP;
 			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) &&
-			   skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
 			__be16 frag_off;
 			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 			int hdrlen = ipv6_skip_exthdr(skb,
@@ -1550,4 +1550,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
 MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
 MODULE_DESCRIPTION("Connection tracking action");
 MODULE_LICENSE("GPL v2");
-
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 19649623493b..b5042f3ea079 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
 	action = READ_ONCE(ca->tcf_action);
 
 	wlen = skb_network_offset(skb);
-	if (tc_skb_protocol(skb) == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		wlen += sizeof(struct iphdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		wlen += sizeof(struct ipv6hdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index be3f215cd027..8118e2640979 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
-		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
+		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true)));
 		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b125b2be4467..b2b3faa57294 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen))
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index faa78b7dd962..e62beec0d844 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1538,7 +1538,7 @@ static inline int __tcf_classify(struct sk_buff *skb,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
-		__be16 protocol = tc_skb_protocol(skb);
+		__be16 protocol = skb_protocol(skb, false);
 		int err;
 
 		if (tp->protocol != protocol &&
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 80ae7b9fa90a..ab53a93b2f2b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 	if (dst)
 		return ntohl(dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb,
@@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb,
 	if (flow->ports.ports)
 		return ntohs(flow->ports.dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 static u32 flow_get_nfct_src(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -164,7 +164,7 @@ fallback:
 static u32 flow_get_nfct_dst(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index b2da37286082..e30bd969fc48 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -313,7 +313,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		/* skb_flow_dissect() does not set n_proto in case an unknown
 		 * protocol, so do it rather here.
 		 */
-		skb_key.basic.n_proto = skb->protocol;
+		skb_key.basic.n_proto = skb_protocol(skb, false);
 		skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
 				    fl_ct_info_to_flower_map,
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index df00566d327d..c95cf86fb431 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	};
 	int ret, network_offset;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		state.pf = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c
index 18755d29fd15..3650117da47f 100644
--- a/net/sched/em_ipt.c
+++ b/net/sched/em_ipt.c
@@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em,
 	struct nf_hook_state state;
 	int ret;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
 			return 0;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index d99966a55c84..46254968d390 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -195,7 +195,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = tc_skb_protocol(skb);
+	dst->value = skb_protocol(skb, false);
 }
 
 META_COLLECTOR(int_pkttype)
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index ca813697728e..ebaeec1e5c82 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -592,7 +592,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys,
 	bool rev = !skb->_nfct, upd = false;
 	__be32 ip;
 
-	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+	if (skb_protocol(skb, true) != htons(ETH_P_IP))
 		return false;
 
 	if (!nf_ct_get_tuple_skb(&tuple, skb))
@@ -1557,7 +1557,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 	u16 *buf, buf_;
 	u8 dscp;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
 		if (unlikely(!buf))
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 05605b30bef3..2b88710994d7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (p->set_tc_index) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen) ||
@@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
 				    p->mv[index].value);
@@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mv[index].mask != 0xff || p->mv[index].value)
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(tc_skb_protocol(skb)));
+				__func__, ntohs(skb_protocol(skb, true)));
 		break;
 	}
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 689ef6f3ded8..2f1f0a378408 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+		err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)),
 				      haddr, NULL, skb->len);
 
 		if (err < 0)
-- 
cgit v1.2.3


From 8fa88a88d573093868565a1afba43b5ae5b3a316 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Fri, 3 Jul 2020 16:56:45 +0100
Subject: genirq: Remove preflow handler support

That was put in place for sparc64, and blackfin also used it for some time;
sparc64 no longer uses those, and blackfin is dead.

As there are no more users, remove preflow handlers.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200703155645.29703-3-valentin.schneider@arm.com
---
 include/linux/irqdesc.h    | 15 ---------------
 include/linux/irqhandler.h |  1 -
 kernel/irq/Kconfig         |  4 ----
 kernel/irq/chip.c          | 13 -------------
 4 files changed, 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 8f2820c5e69e..5745491303e0 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -22,7 +22,6 @@ struct pt_regs;
  * @irq_common_data:	per irq and chip data passed down to chip functions
  * @kstat_irqs:		irq stats per cpu
  * @handle_irq:		highlevel irq-events handler
- * @preflow_handler:	handler called before the flow handler (currently used by sparc)
  * @action:		the irq action chain
  * @status_use_accessors: status information
  * @core_internal_state__do_not_mess_with_it: core internal status information
@@ -58,9 +57,6 @@ struct irq_desc {
 	struct irq_data		irq_data;
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
-#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
-	irq_preflow_handler_t	preflow_handler;
-#endif
 	struct irqaction	*action;	/* IRQ action list */
 	unsigned int		status_use_accessors;
 	unsigned int		core_internal_state__do_not_mess_with_it;
@@ -268,15 +264,4 @@ irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
 	}
 }
 
-#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
-static inline void
-__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	desc->preflow_handler = handler;
-}
-#endif
-
 #endif
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
index 1e6f4e7123d6..c30f454a9518 100644
--- a/include/linux/irqhandler.h
+++ b/include/linux/irqhandler.h
@@ -10,6 +10,5 @@
 struct irq_desc;
 struct irq_data;
 typedef	void (*irq_flow_handler_t)(struct irq_desc *desc);
-typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
 
 #endif
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 20512252ecc9..10a5aff4eecc 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -51,10 +51,6 @@ config GENERIC_IRQ_INJECTION
 config HARDIRQS_SW_RESEND
        bool
 
-# Preflow handler support for fasteoi (sparc64)
-config IRQ_PREFLOW_FASTEOI
-       bool
-
 # Edge style eoi based handler (cell)
 config IRQ_EDGE_EOI_HANDLER
        bool
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 41e7e37a0928..75bbaa8b38f1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -656,16 +656,6 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
-#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
-static inline void preflow_handler(struct irq_desc *desc)
-{
-	if (desc->preflow_handler)
-		desc->preflow_handler(&desc->irq_data);
-}
-#else
-static inline void preflow_handler(struct irq_desc *desc) { }
-#endif
-
 static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip)
 {
 	if (!(desc->istate & IRQS_ONESHOT)) {
@@ -721,7 +711,6 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
@@ -1231,7 +1220,6 @@ void handle_fasteoi_ack_irq(struct irq_desc *desc)
 	/* Start handling the irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
@@ -1281,7 +1269,6 @@ void handle_fasteoi_mask_irq(struct irq_desc *desc)
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
-- 
cgit v1.2.3


From ce548396a4334a4c6e9faada8db89dacf35822b2 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Fri, 26 Jun 2020 13:53:18 +0200
Subject: media: mach-omap1: board-ams-delta.c: remove soc_camera dependencies

The soc_camera driver is about to be removed, so drop camera
support from this board. Note that the soc_camera driver itself has
long since been deprecated and can't be compiled anymore (it depends
on BROKEN), so camera support on this board has been broken for a long
time (at least since 4.6 when the omap1_camera.c was removed from soc_camera).

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Cc: Tony Lindgren <tony@atomide.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 arch/arm/mach-omap1/board-ams-delta.c            | 32 ------------------
 arch/arm/mach-omap1/camera.h                     | 14 --------
 arch/arm/mach-omap1/devices.c                    | 43 ------------------------
 include/linux/platform_data/media/omap1_camera.h | 32 ------------------
 4 files changed, 121 deletions(-)
 delete mode 100644 arch/arm/mach-omap1/camera.h
 delete mode 100644 include/linux/platform_data/media/omap1_camera.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 8d32894ecd2e..2ee527c00284 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -29,8 +29,6 @@
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
 
-#include <media/soc_camera.h>
-
 #include <asm/serial.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -40,7 +38,6 @@
 #include <mach/mux.h>
 
 #include <mach/hardware.h>
-#include "camera.h"
 #include <mach/usb.h>
 
 #include "ams-delta-fiq.h"
@@ -459,12 +456,6 @@ static struct gpiod_lookup_table leds_gpio_table = {
 	},
 };
 
-static struct i2c_board_info ams_delta_camera_board_info[] = {
-	{
-		I2C_BOARD_INFO("ov6650", 0x60),
-	},
-};
-
 #ifdef CONFIG_LEDS_TRIGGERS
 DEFINE_LED_TRIGGER(ams_delta_camera_led_trigger);
 
@@ -483,27 +474,6 @@ static int ams_delta_camera_power(struct device *dev, int power)
 #define ams_delta_camera_power	NULL
 #endif
 
-static struct soc_camera_link ams_delta_iclink = {
-	.bus_id         = 0,	/* OMAP1 SoC camera bus */
-	.i2c_adapter_id = 1,
-	.board_info     = &ams_delta_camera_board_info[0],
-	.module_name    = "ov6650",
-	.power		= ams_delta_camera_power,
-};
-
-static struct platform_device ams_delta_camera_device = {
-	.name   = "soc-camera-pdrv",
-	.id     = 0,
-	.dev    = {
-		.platform_data = &ams_delta_iclink,
-	},
-};
-
-static struct omap1_cam_platform_data ams_delta_camera_platform_data = {
-	.camexclk_khz	= 12000,	/* default 12MHz clock, no extra DPLL */
-	.lclk_khz_max	= 1334,		/* results in 5fps CIF, 10fps QCIF */
-};
-
 static struct platform_device ams_delta_audio_device = {
 	.name   = "ams-delta-audio",
 	.id     = -1,
@@ -598,7 +568,6 @@ static struct platform_device *ams_delta_devices[] __initdata = {
 	&latch1_gpio_device,
 	&latch2_gpio_device,
 	&ams_delta_kp_device,
-	&ams_delta_camera_device,
 	&ams_delta_audio_device,
 	&ams_delta_serio_device,
 	&ams_delta_nand_device,
@@ -750,7 +719,6 @@ static void __init ams_delta_init(void)
 	omap_register_i2c_bus(1, 100, NULL, 0);
 
 	omap1_usb_init(&ams_delta_usb_config);
-	omap1_set_camera_info(&ams_delta_camera_platform_data);
 #ifdef CONFIG_LEDS_TRIGGERS
 	led_trigger_register_simple("ams_delta_camera",
 			&ams_delta_camera_led_trigger);
diff --git a/arch/arm/mach-omap1/camera.h b/arch/arm/mach-omap1/camera.h
deleted file mode 100644
index 8018f410d024..000000000000
--- a/arch/arm/mach-omap1/camera.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_ARCH_CAMERA_H_
-#define __ASM_ARCH_CAMERA_H_
-
-#include <linux/platform_data/media/omap1_camera.h>
-
-void omap1_camera_init(void *);
-
-static inline void omap1_set_camera_info(struct omap1_cam_platform_data *info)
-{
-	omap1_camera_init(info);
-}
-
-#endif /* __ASM_ARCH_CAMERA_H_ */
diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index 3c4900ac72fc..eb0f09edb3d1 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -21,7 +21,6 @@
 #include <mach/mux.h>
 
 #include <mach/omap7xx.h>
-#include "camera.h"
 #include <mach/hardware.h>
 
 #include "common.h"
@@ -258,48 +257,6 @@ static inline void omap_init_spi100k(void)
 }
 #endif
 
-
-#define OMAP1_CAMERA_BASE	0xfffb6800
-#define OMAP1_CAMERA_IOSIZE	0x1c
-
-static struct resource omap1_camera_resources[] = {
-	[0] = {
-		.start	= OMAP1_CAMERA_BASE,
-		.end	= OMAP1_CAMERA_BASE + OMAP1_CAMERA_IOSIZE - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= INT_CAMERA,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static u64 omap1_camera_dma_mask = DMA_BIT_MASK(32);
-
-static struct platform_device omap1_camera_device = {
-	.name		= "omap1-camera",
-	.id		= 0, /* This is used to put cameras on this interface */
-	.dev		= {
-		.dma_mask		= &omap1_camera_dma_mask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-	},
-	.num_resources	= ARRAY_SIZE(omap1_camera_resources),
-	.resource	= omap1_camera_resources,
-};
-
-void __init omap1_camera_init(void *info)
-{
-	struct platform_device *dev = &omap1_camera_device;
-	int ret;
-
-	dev->dev.platform_data = info;
-
-	ret = platform_device_register(dev);
-	if (ret)
-		dev_err(&dev->dev, "unable to register device: %d\n", ret);
-}
-
-
 /*-------------------------------------------------------------------------*/
 
 static inline void omap_init_sti(void) {}
diff --git a/include/linux/platform_data/media/omap1_camera.h b/include/linux/platform_data/media/omap1_camera.h
deleted file mode 100644
index 386439db68de..000000000000
--- a/include/linux/platform_data/media/omap1_camera.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Header for V4L2 SoC Camera driver for OMAP1 Camera Interface
- *
- * Copyright (C) 2010, Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>
- */
-
-#ifndef __MEDIA_OMAP1_CAMERA_H_
-#define __MEDIA_OMAP1_CAMERA_H_
-
-#include <linux/bitops.h>
-
-#define OMAP1_CAMERA_IOSIZE		0x1c
-
-enum omap1_cam_vb_mode {
-	OMAP1_CAM_DMA_CONTIG = 0,
-	OMAP1_CAM_DMA_SG,
-};
-
-#define OMAP1_CAMERA_MIN_BUF_COUNT(x)	((x) == OMAP1_CAM_DMA_CONTIG ? 3 : 2)
-
-struct omap1_cam_platform_data {
-	unsigned long	camexclk_khz;
-	unsigned long	lclk_khz_max;
-	unsigned long	flags;
-};
-
-#define OMAP1_CAMERA_LCLK_RISING	BIT(0)
-#define OMAP1_CAMERA_RST_LOW		BIT(1)
-#define OMAP1_CAMERA_RST_HIGH		BIT(2)
-
-#endif /* __MEDIA_OMAP1_CAMERA_H_ */
-- 
cgit v1.2.3


From 5fec25f2cb959cb5f189d7f6127bee3efc782530 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 24 Jun 2020 16:34:57 -0500
Subject: umh: Capture the pid in umh_pipe_setup

The pid in struct subprocess_info is only used by umh_clean_and_save_pid to
write the pid into umh_info.

Instead always capture the pid on struct umh_info in umh_pipe_setup, removing
code that is specific to user mode drivers from the common user path of
user mode helpers.

v1: https://lkml.kernel.org/r/87h7uygf9i.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/875zb97iix.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-1-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/umh.h | 1 -
 kernel/umh.c        | 5 ++---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/umh.h b/include/linux/umh.h
index 0c08de356d0d..aae16a0ebd0f 100644
--- a/include/linux/umh.h
+++ b/include/linux/umh.h
@@ -25,7 +25,6 @@ struct subprocess_info {
 	struct file *file;
 	int wait;
 	int retval;
-	pid_t pid;
 	int (*init)(struct subprocess_info *info, struct cred *new);
 	void (*cleanup)(struct subprocess_info *info);
 	void *data;
diff --git a/kernel/umh.c b/kernel/umh.c
index 79f139a7ca03..c2a582b3a2bf 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -102,7 +102,6 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
-	sub_info->pid = task_pid_nr(current);
 	if (sub_info->file) {
 		retval = do_execve_file(sub_info->file,
 					sub_info->argv, sub_info->envp);
@@ -468,6 +467,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 
 	umh_info->pipe_to_umh = to_umh[1];
 	umh_info->pipe_from_umh = from_umh[0];
+	umh_info->pid = task_pid_nr(current);
 	return 0;
 }
 
@@ -476,13 +476,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 	struct umh_info *umh_info = info->data;
 
 	/* cleanup if umh_pipe_setup() was successful but exec failed */
-	if (info->pid && info->retval) {
+	if (info->retval) {
 		fput(umh_info->pipe_to_umh);
 		fput(umh_info->pipe_from_umh);
 	}
 
 	argv_free(info->argv);
-	umh_info->pid = info->pid;
 }
 
 /**
-- 
cgit v1.2.3


From 21d598280675c463ea1b264fab06e9614aacd1e1 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 24 Jun 2020 17:01:18 -0500
Subject: umh: Remove call_usermodehelper_setup_file.

The only caller of call_usermodehelper_setup_file is fork_usermode_blob.
In fork_usermode_blob replace call_usermodehelper_setup_file with
call_usermodehelper_setup and delete fork_usermodehelper_setup_file.

For this to work the argv_free is moved from umh_clean_and_save_pid
to fork_usermode_blob.

v1: https://lkml.kernel.org/r/87zh8qf0mp.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87o8p163u1.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-4-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/umh.h |  3 ---
 kernel/umh.c        | 42 +++++++++++-------------------------------
 2 files changed, 11 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/umh.h b/include/linux/umh.h
index aae16a0ebd0f..de08af00c68a 100644
--- a/include/linux/umh.h
+++ b/include/linux/umh.h
@@ -39,9 +39,6 @@ call_usermodehelper_setup(const char *path, char **argv, char **envp,
 			  int (*init)(struct subprocess_info *info, struct cred *new),
 			  void (*cleanup)(struct subprocess_info *), void *data);
 
-struct subprocess_info *call_usermodehelper_setup_file(struct file *file,
-			  int (*init)(struct subprocess_info *info, struct cred *new),
-			  void (*cleanup)(struct subprocess_info *), void *data);
 struct umh_info {
 	const char *cmdline;
 	struct file *pipe_to_umh;
diff --git a/kernel/umh.c b/kernel/umh.c
index 26c3d493f168..b8fa9b99b366 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -402,33 +402,6 @@ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv,
 }
 EXPORT_SYMBOL(call_usermodehelper_setup);
 
-struct subprocess_info *call_usermodehelper_setup_file(struct file *file,
-		int (*init)(struct subprocess_info *info, struct cred *new),
-		void (*cleanup)(struct subprocess_info *info), void *data)
-{
-	struct subprocess_info *sub_info;
-	struct umh_info *info = data;
-	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
-
-	sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL);
-	if (!sub_info)
-		return NULL;
-
-	sub_info->argv = argv_split(GFP_KERNEL, cmdline, NULL);
-	if (!sub_info->argv) {
-		kfree(sub_info);
-		return NULL;
-	}
-
-	INIT_WORK(&sub_info->work, call_usermodehelper_exec_work);
-	sub_info->path = "none";
-	sub_info->file = file;
-	sub_info->init = init;
-	sub_info->cleanup = cleanup;
-	sub_info->data = data;
-	return sub_info;
-}
-
 static int umd_setup(struct subprocess_info *info, struct cred *new)
 {
 	struct umh_info *umh_info = info->data;
@@ -479,8 +452,6 @@ static void umd_cleanup(struct subprocess_info *info)
 		fput(umh_info->pipe_to_umh);
 		fput(umh_info->pipe_from_umh);
 	}
-
-	argv_free(info->argv);
 }
 
 /**
@@ -501,7 +472,9 @@ static void umd_cleanup(struct subprocess_info *info)
  */
 int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
 {
+	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
 	struct subprocess_info *sub_info;
+	char **argv = NULL;
 	struct file *file;
 	ssize_t written;
 	loff_t pos = 0;
@@ -520,11 +493,16 @@ int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
 	}
 
 	err = -ENOMEM;
-	sub_info = call_usermodehelper_setup_file(file, umd_setup, umd_cleanup,
-						  info);
+	argv = argv_split(GFP_KERNEL, cmdline, NULL);
+	if (!argv)
+		goto out;
+
+	sub_info = call_usermodehelper_setup("none", argv, NULL, GFP_KERNEL,
+					     umd_setup, umd_cleanup, info);
 	if (!sub_info)
 		goto out;
 
+	sub_info->file = file;
 	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
 	if (!err) {
 		mutex_lock(&umh_list_lock);
@@ -532,6 +510,8 @@ int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
 		mutex_unlock(&umh_list_lock);
 	}
 out:
+	if (argv)
+		argv_free(argv);
 	fput(file);
 	return err;
 }
-- 
cgit v1.2.3


From 884c5e683b67dbc52892e24c29eed864f330ec08 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 26 Jun 2020 12:23:00 -0500
Subject: umh: Separate the user mode driver and the user mode helper support

This makes it clear which code is part of the core user mode
helper support and which code is needed to implement user mode
drivers.

This makes the kernel smaller for everyone who does not use a usermode
driver.

v1: https://lkml.kernel.org/r/87tuyyf0ln.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87imf963s6.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-5-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/bpfilter.h        |   2 +-
 include/linux/sched.h           |   8 ---
 include/linux/umh.h             |  10 ---
 include/linux/usermode_driver.h |  30 +++++++++
 kernel/Makefile                 |   1 +
 kernel/exit.c                   |   1 +
 kernel/umh.c                    | 139 --------------------------------------
 kernel/usermode_driver.c        | 146 ++++++++++++++++++++++++++++++++++++++++
 8 files changed, 179 insertions(+), 158 deletions(-)
 create mode 100644 include/linux/usermode_driver.h
 create mode 100644 kernel/usermode_driver.c

(limited to 'include/linux')

diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index d815622cd31e..d6d6206052a6 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -3,7 +3,7 @@
 #define _LINUX_BPFILTER_H
 
 #include <uapi/linux/bpfilter.h>
-#include <linux/umh.h>
+#include <linux/usermode_driver.h>
 
 struct sock;
 int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b62e6aaf28f0..59d1e92bb88e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2020,14 +2020,6 @@ static inline void rseq_execve(struct task_struct *t)
 
 #endif
 
-void __exit_umh(struct task_struct *tsk);
-
-static inline void exit_umh(struct task_struct *tsk)
-{
-	if (unlikely(tsk->flags & PF_UMH))
-		__exit_umh(tsk);
-}
-
 #ifdef CONFIG_DEBUG_RSEQ
 
 void rseq_syscall(struct pt_regs *regs);
diff --git a/include/linux/umh.h b/include/linux/umh.h
index de08af00c68a..73173c4a07e5 100644
--- a/include/linux/umh.h
+++ b/include/linux/umh.h
@@ -39,16 +39,6 @@ call_usermodehelper_setup(const char *path, char **argv, char **envp,
 			  int (*init)(struct subprocess_info *info, struct cred *new),
 			  void (*cleanup)(struct subprocess_info *), void *data);
 
-struct umh_info {
-	const char *cmdline;
-	struct file *pipe_to_umh;
-	struct file *pipe_from_umh;
-	struct list_head list;
-	void (*cleanup)(struct umh_info *info);
-	pid_t pid;
-};
-int fork_usermode_blob(void *data, size_t len, struct umh_info *info);
-
 extern int
 call_usermodehelper_exec(struct subprocess_info *info, int wait);
 
diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
new file mode 100644
index 000000000000..c5f6dc950227
--- /dev/null
+++ b/include/linux/usermode_driver.h
@@ -0,0 +1,30 @@
+#ifndef __LINUX_USERMODE_DRIVER_H__
+#define __LINUX_USERMODE_DRIVER_H__
+
+#include <linux/umh.h>
+
+#ifdef CONFIG_BPFILTER
+void __exit_umh(struct task_struct *tsk);
+
+static inline void exit_umh(struct task_struct *tsk)
+{
+	if (unlikely(tsk->flags & PF_UMH))
+		__exit_umh(tsk);
+}
+#else
+static inline void exit_umh(struct task_struct *tsk)
+{
+}
+#endif
+
+struct umh_info {
+	const char *cmdline;
+	struct file *pipe_to_umh;
+	struct file *pipe_from_umh;
+	struct list_head list;
+	void (*cleanup)(struct umh_info *info);
+	pid_t pid;
+};
+int fork_usermode_blob(void *data, size_t len, struct umh_info *info);
+
+#endif /* __LINUX_USERMODE_DRIVER_H__ */
diff --git a/kernel/Makefile b/kernel/Makefile
index f3218bc5ec69..43928759893a 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -12,6 +12,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o smpboot.o ucount.o
 
+obj-$(CONFIG_BPFILTER) += usermode_driver.o
 obj-$(CONFIG_MODULES) += kmod.o
 obj-$(CONFIG_MULTIUSER) += groups.o
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 727150f28103..a081deea52ca 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -63,6 +63,7 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
+#include <linux/usermode_driver.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
diff --git a/kernel/umh.c b/kernel/umh.c
index b8fa9b99b366..3e4e453d45c8 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -26,8 +26,6 @@
 #include <linux/ptrace.h>
 #include <linux/async.h>
 #include <linux/uaccess.h>
-#include <linux/shmem_fs.h>
-#include <linux/pipe_fs_i.h>
 
 #include <trace/events/module.h>
 
@@ -38,8 +36,6 @@ static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
 static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
 static DEFINE_SPINLOCK(umh_sysctl_lock);
 static DECLARE_RWSEM(umhelper_sem);
-static LIST_HEAD(umh_list);
-static DEFINE_MUTEX(umh_list_lock);
 
 static void call_usermodehelper_freeinfo(struct subprocess_info *info)
 {
@@ -402,121 +398,6 @@ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv,
 }
 EXPORT_SYMBOL(call_usermodehelper_setup);
 
-static int umd_setup(struct subprocess_info *info, struct cred *new)
-{
-	struct umh_info *umh_info = info->data;
-	struct file *from_umh[2];
-	struct file *to_umh[2];
-	int err;
-
-	/* create pipe to send data to umh */
-	err = create_pipe_files(to_umh, 0);
-	if (err)
-		return err;
-	err = replace_fd(0, to_umh[0], 0);
-	fput(to_umh[0]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		return err;
-	}
-
-	/* create pipe to receive data from umh */
-	err = create_pipe_files(from_umh, 0);
-	if (err) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		return err;
-	}
-	err = replace_fd(1, from_umh[1], 0);
-	fput(from_umh[1]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		fput(from_umh[0]);
-		return err;
-	}
-
-	umh_info->pipe_to_umh = to_umh[1];
-	umh_info->pipe_from_umh = from_umh[0];
-	umh_info->pid = task_pid_nr(current);
-	current->flags |= PF_UMH;
-	return 0;
-}
-
-static void umd_cleanup(struct subprocess_info *info)
-{
-	struct umh_info *umh_info = info->data;
-
-	/* cleanup if umh_setup() was successful but exec failed */
-	if (info->retval) {
-		fput(umh_info->pipe_to_umh);
-		fput(umh_info->pipe_from_umh);
-	}
-}
-
-/**
- * fork_usermode_blob - fork a blob of bytes as a usermode process
- * @data: a blob of bytes that can be do_execv-ed as a file
- * @len: length of the blob
- * @info: information about usermode process (shouldn't be NULL)
- *
- * If info->cmdline is set it will be used as command line for the
- * user process, else "usermodehelper" is used.
- *
- * Returns either negative error or zero which indicates success
- * in executing a blob of bytes as a usermode process. In such
- * case 'struct umh_info *info' is populated with two pipes
- * and a pid of the process. The caller is responsible for health
- * check of the user process, killing it via pid, and closing the
- * pipes when user process is no longer needed.
- */
-int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
-{
-	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
-	struct subprocess_info *sub_info;
-	char **argv = NULL;
-	struct file *file;
-	ssize_t written;
-	loff_t pos = 0;
-	int err;
-
-	file = shmem_kernel_file_setup("", len, 0);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	written = kernel_write(file, data, len, &pos);
-	if (written != len) {
-		err = written;
-		if (err >= 0)
-			err = -ENOMEM;
-		goto out;
-	}
-
-	err = -ENOMEM;
-	argv = argv_split(GFP_KERNEL, cmdline, NULL);
-	if (!argv)
-		goto out;
-
-	sub_info = call_usermodehelper_setup("none", argv, NULL, GFP_KERNEL,
-					     umd_setup, umd_cleanup, info);
-	if (!sub_info)
-		goto out;
-
-	sub_info->file = file;
-	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
-	if (!err) {
-		mutex_lock(&umh_list_lock);
-		list_add(&info->list, &umh_list);
-		mutex_unlock(&umh_list_lock);
-	}
-out:
-	if (argv)
-		argv_free(argv);
-	fput(file);
-	return err;
-}
-EXPORT_SYMBOL_GPL(fork_usermode_blob);
-
 /**
  * call_usermodehelper_exec - start a usermode application
  * @sub_info: information about the subprocessa
@@ -678,26 +559,6 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
-void __exit_umh(struct task_struct *tsk)
-{
-	struct umh_info *info;
-	pid_t pid = tsk->pid;
-
-	mutex_lock(&umh_list_lock);
-	list_for_each_entry(info, &umh_list, list) {
-		if (info->pid == pid) {
-			list_del(&info->list);
-			mutex_unlock(&umh_list_lock);
-			goto out;
-		}
-	}
-	mutex_unlock(&umh_list_lock);
-	return;
-out:
-	if (info->cleanup)
-		info->cleanup(info);
-}
-
 struct ctl_table usermodehelper_table[] = {
 	{
 		.procname	= "bset",
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
new file mode 100644
index 000000000000..5b05863af855
--- /dev/null
+++ b/kernel/usermode_driver.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * umd - User mode driver support
+ */
+#include <linux/shmem_fs.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/usermode_driver.h>
+
+static LIST_HEAD(umh_list);
+static DEFINE_MUTEX(umh_list_lock);
+
+static int umd_setup(struct subprocess_info *info, struct cred *new)
+{
+	struct umh_info *umh_info = info->data;
+	struct file *from_umh[2];
+	struct file *to_umh[2];
+	int err;
+
+	/* create pipe to send data to umh */
+	err = create_pipe_files(to_umh, 0);
+	if (err)
+		return err;
+	err = replace_fd(0, to_umh[0], 0);
+	fput(to_umh[0]);
+	if (err < 0) {
+		fput(to_umh[1]);
+		return err;
+	}
+
+	/* create pipe to receive data from umh */
+	err = create_pipe_files(from_umh, 0);
+	if (err) {
+		fput(to_umh[1]);
+		replace_fd(0, NULL, 0);
+		return err;
+	}
+	err = replace_fd(1, from_umh[1], 0);
+	fput(from_umh[1]);
+	if (err < 0) {
+		fput(to_umh[1]);
+		replace_fd(0, NULL, 0);
+		fput(from_umh[0]);
+		return err;
+	}
+
+	umh_info->pipe_to_umh = to_umh[1];
+	umh_info->pipe_from_umh = from_umh[0];
+	umh_info->pid = task_pid_nr(current);
+	current->flags |= PF_UMH;
+	return 0;
+}
+
+static void umd_cleanup(struct subprocess_info *info)
+{
+	struct umh_info *umh_info = info->data;
+
+	/* cleanup if umh_setup() was successful but exec failed */
+	if (info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+}
+
+/**
+ * fork_usermode_blob - fork a blob of bytes as a usermode process
+ * @data: a blob of bytes that can be do_execv-ed as a file
+ * @len: length of the blob
+ * @info: information about usermode process (shouldn't be NULL)
+ *
+ * If info->cmdline is set it will be used as command line for the
+ * user process, else "usermodehelper" is used.
+ *
+ * Returns either negative error or zero which indicates success
+ * in executing a blob of bytes as a usermode process. In such
+ * case 'struct umh_info *info' is populated with two pipes
+ * and a pid of the process. The caller is responsible for health
+ * check of the user process, killing it via pid, and closing the
+ * pipes when user process is no longer needed.
+ */
+int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
+{
+	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
+	struct subprocess_info *sub_info;
+	char **argv = NULL;
+	struct file *file;
+	ssize_t written;
+	loff_t pos = 0;
+	int err;
+
+	file = shmem_kernel_file_setup("", len, 0);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	written = kernel_write(file, data, len, &pos);
+	if (written != len) {
+		err = written;
+		if (err >= 0)
+			err = -ENOMEM;
+		goto out;
+	}
+
+	err = -ENOMEM;
+	argv = argv_split(GFP_KERNEL, cmdline, NULL);
+	if (!argv)
+		goto out;
+
+	sub_info = call_usermodehelper_setup("none", argv, NULL, GFP_KERNEL,
+					     umd_setup, umd_cleanup, info);
+	if (!sub_info)
+		goto out;
+
+	sub_info->file = file;
+	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
+	if (!err) {
+		mutex_lock(&umh_list_lock);
+		list_add(&info->list, &umh_list);
+		mutex_unlock(&umh_list_lock);
+	}
+out:
+	if (argv)
+		argv_free(argv);
+	fput(file);
+	return err;
+}
+EXPORT_SYMBOL_GPL(fork_usermode_blob);
+
+void __exit_umh(struct task_struct *tsk)
+{
+	struct umh_info *info;
+	pid_t pid = tsk->pid;
+
+	mutex_lock(&umh_list_lock);
+	list_for_each_entry(info, &umh_list, list) {
+		if (info->pid == pid) {
+			list_del(&info->list);
+			mutex_unlock(&umh_list_lock);
+			goto out;
+		}
+	}
+	mutex_unlock(&umh_list_lock);
+	return;
+out:
+	if (info->cleanup)
+		info->cleanup(info);
+}
+
-- 
cgit v1.2.3


From 74be2d3b80af1bb264c3b9905b52c15efc03c0fe Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 26 Jun 2020 11:16:06 -0500
Subject: umd: For clarity rename umh_info umd_info

This structure is only used for user mode drivers so change
the prefix from umh to umd to make that clear.

v1: https://lkml.kernel.org/r/87o8p6f0kw.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/878sg563po.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-6-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/bpfilter.h        |  2 +-
 include/linux/usermode_driver.h |  6 +++---
 kernel/usermode_driver.c        | 20 ++++++++++----------
 net/ipv4/bpfilter/sockopt.c     |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index d6d6206052a6..ec9972d822e0 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -11,7 +11,7 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
 int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
 			    int __user *optlen);
 struct bpfilter_umh_ops {
-	struct umh_info info;
+	struct umd_info info;
 	/* since ip_getsockopt() can run in parallel, serialize access to umh */
 	struct mutex lock;
 	int (*sockopt)(struct sock *sk, int optname,
diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index c5f6dc950227..7131ea611bab 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -17,14 +17,14 @@ static inline void exit_umh(struct task_struct *tsk)
 }
 #endif
 
-struct umh_info {
+struct umd_info {
 	const char *cmdline;
 	struct file *pipe_to_umh;
 	struct file *pipe_from_umh;
 	struct list_head list;
-	void (*cleanup)(struct umh_info *info);
+	void (*cleanup)(struct umd_info *info);
 	pid_t pid;
 };
-int fork_usermode_blob(void *data, size_t len, struct umh_info *info);
+int fork_usermode_blob(void *data, size_t len, struct umd_info *info);
 
 #endif /* __LINUX_USERMODE_DRIVER_H__ */
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index 5b05863af855..e73550e946d6 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -11,7 +11,7 @@ static DEFINE_MUTEX(umh_list_lock);
 
 static int umd_setup(struct subprocess_info *info, struct cred *new)
 {
-	struct umh_info *umh_info = info->data;
+	struct umd_info *umd_info = info->data;
 	struct file *from_umh[2];
 	struct file *to_umh[2];
 	int err;
@@ -43,21 +43,21 @@ static int umd_setup(struct subprocess_info *info, struct cred *new)
 		return err;
 	}
 
-	umh_info->pipe_to_umh = to_umh[1];
-	umh_info->pipe_from_umh = from_umh[0];
-	umh_info->pid = task_pid_nr(current);
+	umd_info->pipe_to_umh = to_umh[1];
+	umd_info->pipe_from_umh = from_umh[0];
+	umd_info->pid = task_pid_nr(current);
 	current->flags |= PF_UMH;
 	return 0;
 }
 
 static void umd_cleanup(struct subprocess_info *info)
 {
-	struct umh_info *umh_info = info->data;
+	struct umd_info *umd_info = info->data;
 
 	/* cleanup if umh_setup() was successful but exec failed */
 	if (info->retval) {
-		fput(umh_info->pipe_to_umh);
-		fput(umh_info->pipe_from_umh);
+		fput(umd_info->pipe_to_umh);
+		fput(umd_info->pipe_from_umh);
 	}
 }
 
@@ -72,12 +72,12 @@ static void umd_cleanup(struct subprocess_info *info)
  *
  * Returns either negative error or zero which indicates success
  * in executing a blob of bytes as a usermode process. In such
- * case 'struct umh_info *info' is populated with two pipes
+ * case 'struct umd_info *info' is populated with two pipes
  * and a pid of the process. The caller is responsible for health
  * check of the user process, killing it via pid, and closing the
  * pipes when user process is no longer needed.
  */
-int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
+int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 {
 	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
 	struct subprocess_info *sub_info;
@@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
 
 void __exit_umh(struct task_struct *tsk)
 {
-	struct umh_info *info;
+	struct umd_info *info;
 	pid_t pid = tsk->pid;
 
 	mutex_lock(&umh_list_lock);
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 0480918bfc7c..c0dbcc86fcdb 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -12,7 +12,7 @@
 struct bpfilter_umh_ops bpfilter_ops;
 EXPORT_SYMBOL_GPL(bpfilter_ops);
 
-static void bpfilter_umh_cleanup(struct umh_info *info)
+static void bpfilter_umh_cleanup(struct umd_info *info)
 {
 	mutex_lock(&bpfilter_ops.lock);
 	bpfilter_ops.stop = true;
-- 
cgit v1.2.3


From 1199c6c3da5197e9924a906b9de71b8d0ac62a01 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 11:38:08 -0500
Subject: umd: Rename umd_info.cmdline umd_info.driver_name

The only thing supplied in the cmdline today is the driver name so
rename the field to clarify the code.

As this value is always supplied stop trying to handle the case of
a NULL cmdline.

Additionally since we now have a name we can count on use the
driver_name any place where the code is looking for a name
of the binary.

v1: https://lkml.kernel.org/r/87imfef0k3.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87366d63os.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-7-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/usermode_driver.h |  2 +-
 kernel/usermode_driver.c        | 11 ++++-------
 net/ipv4/bpfilter/sockopt.c     |  2 +-
 3 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 7131ea611bab..48cf25e3145d 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -18,7 +18,7 @@ static inline void exit_umh(struct task_struct *tsk)
 #endif
 
 struct umd_info {
-	const char *cmdline;
+	const char *driver_name;
 	struct file *pipe_to_umh;
 	struct file *pipe_from_umh;
 	struct list_head list;
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index e73550e946d6..46d60d855e93 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -67,9 +67,6 @@ static void umd_cleanup(struct subprocess_info *info)
  * @len: length of the blob
  * @info: information about usermode process (shouldn't be NULL)
  *
- * If info->cmdline is set it will be used as command line for the
- * user process, else "usermodehelper" is used.
- *
  * Returns either negative error or zero which indicates success
  * in executing a blob of bytes as a usermode process. In such
  * case 'struct umd_info *info' is populated with two pipes
@@ -79,7 +76,6 @@ static void umd_cleanup(struct subprocess_info *info)
  */
 int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 {
-	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
 	struct subprocess_info *sub_info;
 	char **argv = NULL;
 	struct file *file;
@@ -87,7 +83,7 @@ int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 	loff_t pos = 0;
 	int err;
 
-	file = shmem_kernel_file_setup("", len, 0);
+	file = shmem_kernel_file_setup(info->driver_name, len, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
@@ -100,11 +96,12 @@ int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 	}
 
 	err = -ENOMEM;
-	argv = argv_split(GFP_KERNEL, cmdline, NULL);
+	argv = argv_split(GFP_KERNEL, info->driver_name, NULL);
 	if (!argv)
 		goto out;
 
-	sub_info = call_usermodehelper_setup("none", argv, NULL, GFP_KERNEL,
+	sub_info = call_usermodehelper_setup(info->driver_name, argv, NULL,
+					     GFP_KERNEL,
 					     umd_setup, umd_cleanup, info);
 	if (!sub_info)
 		goto out;
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index c0dbcc86fcdb..5050de28333d 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -70,7 +70,7 @@ static int __init bpfilter_sockopt_init(void)
 {
 	mutex_init(&bpfilter_ops.lock);
 	bpfilter_ops.stop = true;
-	bpfilter_ops.info.cmdline = "bpfilter_umh";
+	bpfilter_ops.info.driver_name = "bpfilter_umh";
 	bpfilter_ops.info.cleanup = &bpfilter_umh_cleanup;
 
 	return 0;
-- 
cgit v1.2.3


From e2dc9bf3f5275ca372001541e5f26af572976e65 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 13:12:59 -0500
Subject: umd: Transform fork_usermode_blob into fork_usermode_driver

Instead of loading a binary blob into a temporary file with
shmem_kernel_file_setup load a binary blob into a temporary tmpfs
filesystem.  This means that the blob can be stored in an init section
and discared, and it means the binary blob will have a filename so can
be executed normally.

The only tricky thing about this code is that in the helper function
blob_to_mnt __fput_sync is used.  That is because a file can not be
executed if it is still open for write, and the ordinary delayed close
for kernel threads does not happen soon enough, which causes the
following exec to fail.  The function umd_load_blob is not called with
any locks so this should be safe.

Executing the blob normally winds up correcting several problems with
the user mode driver code discovered by Tetsuo Handa[1].  By passing
an ordinary filename into the exec, it is no longer necessary to
figure out how to turn a O_RDWR file descriptor into a properly
referende counted O_EXEC file descriptor that forbids all writes.  For
path based LSMs there are no new special cases.

[1] https://lore.kernel.org/linux-fsdevel/2a8775b4-1dd5-9d5c-aa42-9872445e0942@i-love.sakura.ne.jp/
v1: https://lkml.kernel.org/r/87d05mf0j9.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87wo3p4p35.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-8-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/usermode_driver.h |   6 +-
 kernel/usermode_driver.c        | 126 +++++++++++++++++++++++++++++++---------
 net/bpfilter/bpfilter_kern.c    |  14 ++++-
 3 files changed, 113 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 48cf25e3145d..97c919b7147c 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -2,6 +2,7 @@
 #define __LINUX_USERMODE_DRIVER_H__
 
 #include <linux/umh.h>
+#include <linux/path.h>
 
 #ifdef CONFIG_BPFILTER
 void __exit_umh(struct task_struct *tsk);
@@ -23,8 +24,11 @@ struct umd_info {
 	struct file *pipe_from_umh;
 	struct list_head list;
 	void (*cleanup)(struct umd_info *info);
+	struct path wd;
 	pid_t pid;
 };
-int fork_usermode_blob(void *data, size_t len, struct umd_info *info);
+int umd_load_blob(struct umd_info *info, const void *data, size_t len);
+int umd_unload_blob(struct umd_info *info);
+int fork_usermode_driver(struct umd_info *info);
 
 #endif /* __LINUX_USERMODE_DRIVER_H__ */
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index 46d60d855e93..a86798759f83 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -4,11 +4,98 @@
  */
 #include <linux/shmem_fs.h>
 #include <linux/pipe_fs_i.h>
+#include <linux/mount.h>
+#include <linux/fs_struct.h>
+#include <linux/task_work.h>
 #include <linux/usermode_driver.h>
 
 static LIST_HEAD(umh_list);
 static DEFINE_MUTEX(umh_list_lock);
 
+static struct vfsmount *blob_to_mnt(const void *data, size_t len, const char *name)
+{
+	struct file_system_type *type;
+	struct vfsmount *mnt;
+	struct file *file;
+	ssize_t written;
+	loff_t pos = 0;
+
+	type = get_fs_type("tmpfs");
+	if (!type)
+		return ERR_PTR(-ENODEV);
+
+	mnt = kern_mount(type);
+	put_filesystem(type);
+	if (IS_ERR(mnt))
+		return mnt;
+
+	file = file_open_root(mnt->mnt_root, mnt, name, O_CREAT | O_WRONLY, 0700);
+	if (IS_ERR(file)) {
+		mntput(mnt);
+		return ERR_CAST(file);
+	}
+
+	written = kernel_write(file, data, len, &pos);
+	if (written != len) {
+		int err = written;
+		if (err >= 0)
+			err = -ENOMEM;
+		filp_close(file, NULL);
+		mntput(mnt);
+		return ERR_PTR(err);
+	}
+
+	fput(file);
+
+	/* Flush delayed fput so exec can open the file read-only */
+	flush_delayed_fput();
+	task_work_run();
+	return mnt;
+}
+
+/**
+ * umd_load_blob - Remember a blob of bytes for fork_usermode_driver
+ * @info: information about usermode driver
+ * @data: a blob of bytes that can be executed as a file
+ * @len:  The lentgh of the blob
+ *
+ */
+int umd_load_blob(struct umd_info *info, const void *data, size_t len)
+{
+	struct vfsmount *mnt;
+
+	if (WARN_ON_ONCE(info->wd.dentry || info->wd.mnt))
+		return -EBUSY;
+
+	mnt = blob_to_mnt(data, len, info->driver_name);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	info->wd.mnt = mnt;
+	info->wd.dentry = mnt->mnt_root;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(umd_load_blob);
+
+/**
+ * umd_unload_blob - Disassociate @info from a previously loaded blob
+ * @info: information about usermode driver
+ *
+ */
+int umd_unload_blob(struct umd_info *info)
+{
+	if (WARN_ON_ONCE(!info->wd.mnt ||
+			 !info->wd.dentry ||
+			 info->wd.mnt->mnt_root != info->wd.dentry))
+		return -EINVAL;
+
+	kern_unmount(info->wd.mnt);
+	info->wd.mnt = NULL;
+	info->wd.dentry = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(umd_unload_blob);
+
 static int umd_setup(struct subprocess_info *info, struct cred *new)
 {
 	struct umd_info *umd_info = info->data;
@@ -43,6 +130,7 @@ static int umd_setup(struct subprocess_info *info, struct cred *new)
 		return err;
 	}
 
+	set_fs_pwd(current->fs, &umd_info->wd);
 	umd_info->pipe_to_umh = to_umh[1];
 	umd_info->pipe_from_umh = from_umh[0];
 	umd_info->pid = task_pid_nr(current);
@@ -62,39 +150,21 @@ static void umd_cleanup(struct subprocess_info *info)
 }
 
 /**
- * fork_usermode_blob - fork a blob of bytes as a usermode process
- * @data: a blob of bytes that can be do_execv-ed as a file
- * @len: length of the blob
- * @info: information about usermode process (shouldn't be NULL)
+ * fork_usermode_driver - fork a usermode driver
+ * @info: information about usermode driver (shouldn't be NULL)
  *
- * Returns either negative error or zero which indicates success
- * in executing a blob of bytes as a usermode process. In such
- * case 'struct umd_info *info' is populated with two pipes
- * and a pid of the process. The caller is responsible for health
- * check of the user process, killing it via pid, and closing the
- * pipes when user process is no longer needed.
+ * Returns either negative error or zero which indicates success in
+ * executing a usermode driver. In such case 'struct umd_info *info'
+ * is populated with two pipes and a pid of the process. The caller is
+ * responsible for health check of the user process, killing it via
+ * pid, and closing the pipes when user process is no longer needed.
  */
-int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
+int fork_usermode_driver(struct umd_info *info)
 {
 	struct subprocess_info *sub_info;
 	char **argv = NULL;
-	struct file *file;
-	ssize_t written;
-	loff_t pos = 0;
 	int err;
 
-	file = shmem_kernel_file_setup(info->driver_name, len, 0);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	written = kernel_write(file, data, len, &pos);
-	if (written != len) {
-		err = written;
-		if (err >= 0)
-			err = -ENOMEM;
-		goto out;
-	}
-
 	err = -ENOMEM;
 	argv = argv_split(GFP_KERNEL, info->driver_name, NULL);
 	if (!argv)
@@ -106,7 +176,6 @@ int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 	if (!sub_info)
 		goto out;
 
-	sub_info->file = file;
 	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
 	if (!err) {
 		mutex_lock(&umh_list_lock);
@@ -116,10 +185,9 @@ int fork_usermode_blob(void *data, size_t len, struct umd_info *info)
 out:
 	if (argv)
 		argv_free(argv);
-	fput(file);
 	return err;
 }
-EXPORT_SYMBOL_GPL(fork_usermode_blob);
+EXPORT_SYMBOL_GPL(fork_usermode_driver);
 
 void __exit_umh(struct task_struct *tsk)
 {
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index c0f0990f30b6..28883b00609d 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -77,9 +77,7 @@ static int start_umh(void)
 	int err;
 
 	/* fork usermode process */
-	err = fork_usermode_blob(&bpfilter_umh_start,
-				 &bpfilter_umh_end - &bpfilter_umh_start,
-				 &bpfilter_ops.info);
+	err = fork_usermode_driver(&bpfilter_ops.info);
 	if (err)
 		return err;
 	bpfilter_ops.stop = false;
@@ -98,6 +96,12 @@ static int __init load_umh(void)
 {
 	int err;
 
+	err = umd_load_blob(&bpfilter_ops.info,
+			    &bpfilter_umh_start,
+			    &bpfilter_umh_end - &bpfilter_umh_start);
+	if (err)
+		return err;
+
 	mutex_lock(&bpfilter_ops.lock);
 	if (!bpfilter_ops.stop) {
 		err = -EFAULT;
@@ -110,6 +114,8 @@ static int __init load_umh(void)
 	}
 out:
 	mutex_unlock(&bpfilter_ops.lock);
+	if (err)
+		umd_unload_blob(&bpfilter_ops.info);
 	return err;
 }
 
@@ -122,6 +128,8 @@ static void __exit fini_umh(void)
 		bpfilter_ops.sockopt = NULL;
 	}
 	mutex_unlock(&bpfilter_ops.lock);
+
+	umd_unload_blob(&bpfilter_ops.info);
 }
 module_init(load_umh);
 module_exit(fini_umh);
-- 
cgit v1.2.3


From 55e6074e3fa67e1fb9ec140904db7e6cae6eda4b Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 13:52:50 -0500
Subject: umh: Stop calling do_execve_file

With the user mode driver code changed to not set subprocess_info.file
there are no more users of subproces_info.file.  Remove this field
from struct subprocess_info and remove the only user in
call_usermodehelper_exec_async that would call do_execve_file instead
of do_execve if file was set.

v1: https://lkml.kernel.org/r/877dvuf0i7.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87r1tx4p2a.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-9-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/umh.h |  1 -
 kernel/umh.c        | 10 +++-------
 2 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/umh.h b/include/linux/umh.h
index 73173c4a07e5..244aff638220 100644
--- a/include/linux/umh.h
+++ b/include/linux/umh.h
@@ -22,7 +22,6 @@ struct subprocess_info {
 	const char *path;
 	char **argv;
 	char **envp;
-	struct file *file;
 	int wait;
 	int retval;
 	int (*init)(struct subprocess_info *info, struct cred *new);
diff --git a/kernel/umh.c b/kernel/umh.c
index 3e4e453d45c8..6ca2096298b9 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -98,13 +98,9 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
-	if (sub_info->file)
-		retval = do_execve_file(sub_info->file,
-					sub_info->argv, sub_info->envp);
-	else
-		retval = do_execve(getname_kernel(sub_info->path),
-				   (const char __user *const __user *)sub_info->argv,
-				   (const char __user *const __user *)sub_info->envp);
+	retval = do_execve(getname_kernel(sub_info->path),
+			   (const char __user *const __user *)sub_info->argv,
+			   (const char __user *const __user *)sub_info->envp);
 out:
 	sub_info->retval = retval;
 	/*
-- 
cgit v1.2.3


From 25cf336de51b51a3e440e1893751f9532095eff0 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 13:56:40 -0500
Subject: exec: Remove do_execve_file

Now that the last callser has been removed remove this code from exec.

For anyone thinking of resurrecing do_execve_file please note that
the code was buggy in several fundamental ways.

- It did not ensure the file it was passed was read-only and that
  deny_write_access had been called on it.  Which subtlely breaks
  invaniants in exec.

- The caller of do_execve_file was expected to hold and put a
  reference to the file, but an extra reference for use by exec was
  not taken so that when exec put it's reference to the file an
  underflow occured on the file reference count.

- The point of the interface was so that a pathname did not need to
  exist.  Which breaks pathname based LSMs.

Tetsuo Handa originally reported these issues[1].  While it was clear
that deny_write_access was missing the fundamental incompatibility
with the passed in O_RDWR filehandle was not immediately recognized.

All of these issues were fixed by modifying the usermode driver code
to have a path, so it did not need this hack.

Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
[1] https://lore.kernel.org/linux-fsdevel/2a8775b4-1dd5-9d5c-aa42-9872445e0942@i-love.sakura.ne.jp/
v1: https://lkml.kernel.org/r/871rm2f0hi.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87lfk54p0m.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-10-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/exec.c               | 38 +++++++++-----------------------------
 include/linux/binfmts.h |  1 -
 2 files changed, 9 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index e6e8a9a70327..23dfbb820626 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1818,13 +1818,14 @@ static int exec_binprm(struct linux_binprm *bprm)
 /*
  * sys_execve() executes a new program.
  */
-static int __do_execve_file(int fd, struct filename *filename,
-			    struct user_arg_ptr argv,
-			    struct user_arg_ptr envp,
-			    int flags, struct file *file)
+static int do_execveat_common(int fd, struct filename *filename,
+			      struct user_arg_ptr argv,
+			      struct user_arg_ptr envp,
+			      int flags)
 {
 	char *pathbuf = NULL;
 	struct linux_binprm *bprm;
+	struct file *file;
 	struct files_struct *displaced;
 	int retval;
 
@@ -1863,8 +1864,7 @@ static int __do_execve_file(int fd, struct filename *filename,
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	if (!file)
-		file = do_open_execat(fd, filename, flags);
+	file = do_open_execat(fd, filename, flags);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1872,9 +1872,7 @@ static int __do_execve_file(int fd, struct filename *filename,
 	sched_exec();
 
 	bprm->file = file;
-	if (!filename) {
-		bprm->filename = "none";
-	} else if (fd == AT_FDCWD || filename->name[0] == '/') {
+	if (fd == AT_FDCWD || filename->name[0] == '/') {
 		bprm->filename = filename->name;
 	} else {
 		if (filename->name[0] == '\0')
@@ -1935,8 +1933,7 @@ static int __do_execve_file(int fd, struct filename *filename,
 	task_numa_free(current, false);
 	free_bprm(bprm);
 	kfree(pathbuf);
-	if (filename)
-		putname(filename);
+	putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
 	return retval;
@@ -1967,27 +1964,10 @@ out_files:
 	if (displaced)
 		reset_files_struct(displaced);
 out_ret:
-	if (filename)
-		putname(filename);
+	putname(filename);
 	return retval;
 }
 
-static int do_execveat_common(int fd, struct filename *filename,
-			      struct user_arg_ptr argv,
-			      struct user_arg_ptr envp,
-			      int flags)
-{
-	return __do_execve_file(fd, filename, argv, envp, flags, NULL);
-}
-
-int do_execve_file(struct file *file, void *__argv, void *__envp)
-{
-	struct user_arg_ptr argv = { .ptr.native = __argv };
-	struct user_arg_ptr envp = { .ptr.native = __envp };
-
-	return __do_execve_file(AT_FDCWD, NULL, argv, envp, 0, file);
-}
-
 int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
 	const char __user *const __user *__envp)
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 4a20b7517dd0..7c27d7b57871 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -141,6 +141,5 @@ extern int do_execveat(int, struct filename *,
 		       const char __user * const __user *,
 		       const char __user * const __user *,
 		       int);
-int do_execve_file(struct file *file, void *__argv, void *__envp);
 
 #endif /* _LINUX_BINFMTS_H */
-- 
cgit v1.2.3


From 1c340ead18ee4b4a84357abdef6d4f39ee08328b Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 16:48:26 -0500
Subject: umd: Track user space drivers with struct pid

Use struct pid instead of user space pid values that are prone to wrap
araound.

In addition track the entire thread group instead of just the first
thread that is started by exec.  There are no multi-threaded user mode
drivers today but there is nothing preclucing user drivers from being
multi-threaded, so it is just a good idea to track the entire process.

Take a reference count on the tgid's in question to make it possible
to remove exit_umh in a future change.

As a struct pid is available directly use kill_pid_info.

The prior process signalling code was iffy in using a userspace pid
known to be in the initial pid namespace and then looking up it's task
in whatever the current pid namespace is.  It worked only because
kernel threads always run in the initial pid namespace.

As the tgid is now refcounted verify the tgid is NULL at the start of
fork_usermode_driver to avoid the possibility of silent pid leaks.

v1: https://lkml.kernel.org/r/87mu4qdlv2.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/a70l4oy8.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-12-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/usermode_driver.h |  2 +-
 kernel/exit.c                   |  3 ++-
 kernel/usermode_driver.c        | 15 ++++++++++-----
 net/bpfilter/bpfilter_kern.c    | 13 +++++--------
 net/ipv4/bpfilter/sockopt.c     |  3 ++-
 5 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 97c919b7147c..45adbffb31d9 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -25,7 +25,7 @@ struct umd_info {
 	struct list_head list;
 	void (*cleanup)(struct umd_info *info);
 	struct path wd;
-	pid_t pid;
+	struct pid *tgid;
 };
 int umd_load_blob(struct umd_info *info, const void *data, size_t len);
 int umd_unload_blob(struct umd_info *info);
diff --git a/kernel/exit.c b/kernel/exit.c
index a081deea52ca..d3294b611df1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -805,7 +805,8 @@ void __noreturn do_exit(long code)
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
-	exit_umh(tsk);
+	if (group_dead)
+		exit_umh(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index a86798759f83..f77f8d7ce9e3 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -133,7 +133,7 @@ static int umd_setup(struct subprocess_info *info, struct cred *new)
 	set_fs_pwd(current->fs, &umd_info->wd);
 	umd_info->pipe_to_umh = to_umh[1];
 	umd_info->pipe_from_umh = from_umh[0];
-	umd_info->pid = task_pid_nr(current);
+	umd_info->tgid = get_pid(task_tgid(current));
 	current->flags |= PF_UMH;
 	return 0;
 }
@@ -146,6 +146,8 @@ static void umd_cleanup(struct subprocess_info *info)
 	if (info->retval) {
 		fput(umd_info->pipe_to_umh);
 		fput(umd_info->pipe_from_umh);
+		put_pid(umd_info->tgid);
+		umd_info->tgid = NULL;
 	}
 }
 
@@ -155,9 +157,9 @@ static void umd_cleanup(struct subprocess_info *info)
  *
  * Returns either negative error or zero which indicates success in
  * executing a usermode driver. In such case 'struct umd_info *info'
- * is populated with two pipes and a pid of the process. The caller is
+ * is populated with two pipes and a tgid of the process. The caller is
  * responsible for health check of the user process, killing it via
- * pid, and closing the pipes when user process is no longer needed.
+ * tgid, and closing the pipes when user process is no longer needed.
  */
 int fork_usermode_driver(struct umd_info *info)
 {
@@ -165,6 +167,9 @@ int fork_usermode_driver(struct umd_info *info)
 	char **argv = NULL;
 	int err;
 
+	if (WARN_ON_ONCE(info->tgid))
+		return -EBUSY;
+
 	err = -ENOMEM;
 	argv = argv_split(GFP_KERNEL, info->driver_name, NULL);
 	if (!argv)
@@ -192,11 +197,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_driver);
 void __exit_umh(struct task_struct *tsk)
 {
 	struct umd_info *info;
-	pid_t pid = tsk->pid;
+	struct pid *tgid = task_tgid(tsk);
 
 	mutex_lock(&umh_list_lock);
 	list_for_each_entry(info, &umh_list, list) {
-		if (info->pid == pid) {
+		if (info->tgid == tgid) {
 			list_del(&info->list);
 			mutex_unlock(&umh_list_lock);
 			goto out;
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 28883b00609d..08ea77c2b137 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -15,16 +15,13 @@ extern char bpfilter_umh_end;
 
 static void shutdown_umh(void)
 {
-	struct task_struct *tsk;
+	struct umd_info *info = &bpfilter_ops.info;
+	struct pid *tgid = info->tgid;
 
 	if (bpfilter_ops.stop)
 		return;
 
-	tsk = get_pid_task(find_vpid(bpfilter_ops.info.pid), PIDTYPE_PID);
-	if (tsk) {
-		send_sig(SIGKILL, tsk, 1);
-		put_task_struct(tsk);
-	}
+	kill_pid(tgid, SIGKILL, 1);
 }
 
 static void __stop_umh(void)
@@ -48,7 +45,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname,
 	req.cmd = optname;
 	req.addr = (long __force __user)optval;
 	req.len = optlen;
-	if (!bpfilter_ops.info.pid)
+	if (!bpfilter_ops.info.tgid)
 		goto out;
 	n = __kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req),
 			   &pos);
@@ -81,7 +78,7 @@ static int start_umh(void)
 	if (err)
 		return err;
 	bpfilter_ops.stop = false;
-	pr_info("Loaded bpfilter_umh pid %d\n", bpfilter_ops.info.pid);
+	pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
 
 	/* health check that usermode process started correctly */
 	if (__bpfilter_process_sockopt(NULL, 0, NULL, 0, 0) != 0) {
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 5050de28333d..56cbc43145f6 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -18,7 +18,8 @@ static void bpfilter_umh_cleanup(struct umd_info *info)
 	bpfilter_ops.stop = true;
 	fput(info->pipe_to_umh);
 	fput(info->pipe_from_umh);
-	info->pid = 0;
+	put_pid(info->tgid);
+	info->tgid = NULL;
 	mutex_unlock(&bpfilter_ops.lock);
 }
 
-- 
cgit v1.2.3


From ff2a91127b374c75ae024b31d22f23ad49d16eb4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Sun, 24 May 2020 20:57:00 +0200
Subject: fork: remove do_fork()

Now that all architectures have been switched to use _do_fork() and the new
struct kernel_clone_args calling convention we can remove the legacy
do_fork() helper completely. The calling convention used to be brittle and
do_fork() didn't buy us anything. The only calling convention accepted
should be based on struct kernel_clone_args going forward. It's cleaner and
uniform.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/sched/task.h |  1 -
 kernel/fork.c              | 25 +------------------------
 2 files changed, 1 insertion(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ddce0ea515d1..9f03c44941fb 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -96,7 +96,6 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern long _do_fork(struct kernel_clone_args *kargs);
-extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/kernel/fork.c b/kernel/fork.c
index 9875aeb2ba41..0fd7eb1b38f9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2493,29 +2493,6 @@ long _do_fork(struct kernel_clone_args *args)
 	return nr;
 }
 
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-/* For compatibility with architectures that call do_fork directly rather than
- * using the syscall entry points below. */
-long do_fork(unsigned long clone_flags,
-	      unsigned long stack_start,
-	      unsigned long stack_size,
-	      int __user *parent_tidptr,
-	      int __user *child_tidptr)
-{
-	struct kernel_clone_args args = {
-		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
-		.pidfd		= parent_tidptr,
-		.child_tid	= child_tidptr,
-		.parent_tid	= parent_tidptr,
-		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
-		.stack		= stack_start,
-		.stack_size	= stack_size,
-	};
-
-	return _do_fork(&args);
-}
-#endif
-
 /*
  * Create a kernel thread.
  */
@@ -2923,7 +2900,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by do_fork() cannot be used here directly
+ * functions used by _do_fork() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.
-- 
cgit v1.2.3


From 140c8180eb7c7cbda399f64474788b86db72db32 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Sun, 24 May 2020 23:34:20 +0200
Subject: arch: remove HAVE_COPY_THREAD_TLS

All architectures support copy_thread_tls() now, so remove the legacy
copy_thread() function and the HAVE_COPY_THREAD_TLS config option. Everyone
uses the same process creation calling convention based on
copy_thread_tls() and struct kernel_clone_args. This will make it easier to
maintain the core process creation code under kernel/, simplifies the
callpaths and makes the identical for all architectures.

Cc: linux-arch@vger.kernel.org
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 arch/Kconfig               |  7 -------
 arch/alpha/Kconfig         |  1 -
 arch/arc/Kconfig           |  1 -
 arch/arm/Kconfig           |  1 -
 arch/arm64/Kconfig         |  1 -
 arch/c6x/Kconfig           |  1 -
 arch/csky/Kconfig          |  1 -
 arch/h8300/Kconfig         |  1 -
 arch/hexagon/Kconfig       |  1 -
 arch/ia64/Kconfig          |  1 -
 arch/m68k/Kconfig          |  1 -
 arch/microblaze/Kconfig    |  1 -
 arch/mips/Kconfig          |  1 -
 arch/nds32/Kconfig         |  1 -
 arch/nios2/Kconfig         |  1 -
 arch/openrisc/Kconfig      |  1 -
 arch/parisc/Kconfig        |  1 -
 arch/powerpc/Kconfig       |  1 -
 arch/riscv/Kconfig         |  1 -
 arch/s390/Kconfig          |  1 -
 arch/sh/Kconfig            |  1 -
 arch/sparc/Kconfig         |  1 -
 arch/um/Kconfig            |  1 -
 arch/unicore32/Kconfig     |  1 -
 arch/x86/Kconfig           |  1 -
 arch/xtensa/Kconfig        |  1 -
 include/linux/sched/task.h | 15 +--------------
 kernel/fork.c              |  9 ---------
 28 files changed, 1 insertion(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 8cc35dc556c7..943aac2f3ebe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -754,13 +754,6 @@ config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	depends on MMU
 	select ARCH_HAS_ELF_RANDOMIZE
 
-config HAVE_COPY_THREAD_TLS
-	bool
-	help
-	  Architecture provides copy_thread_tls to accept tls argument via
-	  normal C parameter passing, rather than extracting the syscall
-	  argument from pt_regs.
-
 config HAVE_STACK_VALIDATION
 	bool
 	help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index b01515c6b2ed..10862c5a8c76 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -38,7 +38,6 @@ config ALPHA
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
 	select MMU_GATHER_NO_RANGE
-	select HAVE_COPY_THREAD_TLS
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index fddc70029727..1fa0b98ed9ce 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -29,7 +29,6 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_FUTEX_CMPXCHG if FUTEX
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2ac74904a3ce..445b5ed693f0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -72,7 +72,6 @@ config ARM
 	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
 	select HAVE_CONTEXT_TRACKING
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL
 	select HAVE_DMA_CONTIGUOUS if MMU
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4a094bedcb2..de93e965727d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -148,7 +148,6 @@ config ARM64
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CONTEXT_TRACKING
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 9cde76a5928e..6444ebfd06a6 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -22,7 +22,6 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select MMU_GATHER_NO_RANGE if MMU
-	select HAVE_COPY_THREAD_TLS
 
 config MMU
 	def_bool n
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index bd31ab12f77d..902f1142d550 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -38,7 +38,6 @@ config CSKY
 	select GX6605S_TIMER if CPU_CK610
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index de0eb417a0b9..d11666d538fe 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -26,7 +26,6 @@ config H8300
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
 	select UACCESS_MEMCPY
-	select HAVE_COPY_THREAD_TLS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 19bc2f2ee331..667cfc511cf9 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -31,7 +31,6 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
-	select HAVE_COPY_THREAD_TLS
 	help
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1b6034b89a04..1fa2fe2ef053 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -55,7 +55,6 @@ config IA64
 	select HAVE_ARCH_AUDITSYSCALL
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
-	select HAVE_COPY_THREAD_TLS
 	select NUMA if !FLATMEM
 	default y
 	help
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 6ad6cdac74b3..6663f1741798 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -14,7 +14,6 @@ config M68K
 	select HAVE_AOUT if MMU
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_DEBUG_BUGVERBOSE
-	select HAVE_COPY_THREAD_TLS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_ATOMIC64
 	select HAVE_UID16
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index e3a211a41880..d262ac0c8714 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -46,7 +46,6 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
-	select HAVE_COPY_THREAD_TLS
 
 # Endianness selection
 choice
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 6fee1a133e9d..ca92c3ed2dc5 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -51,7 +51,6 @@ config MIPS
 	select HAVE_CBPF_JIT if !64BIT && !CPU_MICROMIPS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_TIF_NOHZ
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 7b6eaca81cce..e30298e99e1b 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -48,7 +48,6 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_COPY_THREAD_TLS
 	help
 	  Andes(nds32) Linux support.
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index f9a05957a883..c6645141bb2a 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -27,7 +27,6 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
-	select HAVE_COPY_THREAD_TLS
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 8588996165ae..7e94fe37cb2f 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -16,7 +16,6 @@ config OPENRISC
 	select HANDLE_DOMAIN_IRQ
 	select GPIOLIB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_COPY_THREAD_TLS
 	select SPARSE_IRQ
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_PROBE
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 8e4c3708773d..2667eeb6c6f1 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -62,7 +62,6 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_COPY_THREAD_TLS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9fa23eb320ff..3b262d87e9c4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -186,7 +186,6 @@ config PPC
 	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
 	select HAVE_CONTEXT_TRACKING		if PPC64
 	select HAVE_TIF_NOHZ			if PPC64
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 128192e14ff2..f6a3a2bea3d8 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -52,7 +52,6 @@ config RISCV
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ASM_MODVERSIONS
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_EBPF_JIT if MMU
 	select HAVE_FUTEX_CMPXCHG if FUTEX
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c7d7ede6300c..959969759453 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -136,7 +136,6 @@ config S390
 	select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index e10118d61ce7..9fc2b010e938 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -70,7 +70,6 @@ config SUPERH
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 	select SPARSE_IRQ
 	select HAVE_STACKPROTECTOR
-	select HAVE_COPY_THREAD_TLS
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 66213c0cb557..5bf2dc163540 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -48,7 +48,6 @@ config SPARC
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
-	select HAVE_COPY_THREAD_TLS
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 9318dc6d1a0c..ef69be17ff70 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -14,7 +14,6 @@ config UML
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_BUGVERBOSE
-	select HAVE_COPY_THREAD_TLS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 01451cf500d2..11ba1839d198 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -22,7 +22,6 @@ config UNICORE32
 	select MODULES_USE_ELF_REL
 	select NEED_DMA_MAP_STATE
 	select MMU_GATHER_NO_RANGE if MMU
-	select HAVE_COPY_THREAD_TLS
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a0cc524882d..214b8bf39bbe 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -161,7 +161,6 @@ config X86
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CONTEXT_TRACKING		if X86_64
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 3a9f1e80394a..b71ba910d92f 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -24,7 +24,6 @@ config XTENSA
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EXIT_THREAD
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 9f03c44941fb..77cbe14c3034 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -65,22 +65,9 @@ extern void fork_init(void);
 
 extern void release_task(struct task_struct * p);
 
-#ifdef CONFIG_HAVE_COPY_THREAD_TLS
 extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
 			struct task_struct *, unsigned long);
-#else
-extern int copy_thread(unsigned long, unsigned long, unsigned long,
-			struct task_struct *);
-
-/* Architectures that haven't opted into copy_thread_tls get the tls argument
- * via pt_regs, so ignore the tls argument passed via C. */
-static inline int copy_thread_tls(
-		unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
-{
-	return copy_thread(clone_flags, sp, arg, p);
-}
-#endif
+
 extern void flush_thread(void);
 
 #ifdef CONFIG_HAVE_EXIT_THREAD
diff --git a/kernel/fork.c b/kernel/fork.c
index 0fd7eb1b38f9..8e52e16a1b5e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2577,15 +2577,6 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 
 #ifdef __ARCH_WANT_SYS_CLONE3
 
-/*
- * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
- * the registers containing the syscall arguments for clone. This doesn't work
- * with clone3 since the TLS value is passed in clone_args instead.
- */
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-#error clone3 requires copy_thread_tls support in arch
-#endif
-
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)
-- 
cgit v1.2.3


From 714acdbd1c94e7e3ab90f6b6938f1ccb27b662f0 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Thu, 11 Jun 2020 11:04:15 +0200
Subject: arch: rename copy_thread_tls() back to copy_thread()

Now that HAVE_COPY_THREAD_TLS has been removed, rename copy_thread_tls()
back simply copy_thread(). It's a simpler name, and doesn't imply that only
tls is copied here. This finishes an outstanding chunk of internal process
creation work since we've added clone3().

Cc: linux-arch@vger.kernel.org
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>A
Acked-by: Stafford Horne <shorne@gmail.com>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>A
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 arch/alpha/kernel/process.c      | 6 +++---
 arch/arc/kernel/process.c        | 5 +++--
 arch/arm/kernel/process.c        | 5 ++---
 arch/arm64/kernel/process.c      | 2 +-
 arch/c6x/kernel/process.c        | 6 +++---
 arch/csky/kernel/process.c       | 2 +-
 arch/h8300/kernel/process.c      | 5 ++---
 arch/hexagon/kernel/process.c    | 4 ++--
 arch/ia64/kernel/process.c       | 7 +++----
 arch/m68k/kernel/process.c       | 5 ++---
 arch/microblaze/kernel/process.c | 4 ++--
 arch/mips/kernel/process.c       | 5 +++--
 arch/nds32/kernel/process.c      | 5 ++---
 arch/nios2/kernel/process.c      | 4 ++--
 arch/openrisc/kernel/process.c   | 6 +++---
 arch/parisc/kernel/process.c     | 2 +-
 arch/powerpc/kernel/process.c    | 2 +-
 arch/riscv/kernel/process.c      | 4 ++--
 arch/s390/kernel/process.c       | 4 ++--
 arch/sh/kernel/process_32.c      | 4 ++--
 arch/sparc/kernel/process.c      | 6 +++---
 arch/sparc/kernel/process_32.c   | 5 ++---
 arch/sparc/kernel/process_64.c   | 5 ++---
 arch/um/kernel/process.c         | 2 +-
 arch/unicore32/kernel/process.c  | 5 ++---
 arch/x86/kernel/process.c        | 4 ++--
 arch/x86/kernel/unwind_frame.c   | 2 +-
 arch/xtensa/kernel/process.c     | 2 +-
 include/linux/sched/task.h       | 4 ++--
 kernel/fork.c                    | 3 +--
 30 files changed, 59 insertions(+), 66 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index dfdb6b6ba61c..7462a7911002 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -233,9 +233,9 @@ release_thread(struct task_struct *dead_task)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long kthread_arg, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 8c8e5172fecd..105420c23c8b 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -173,8 +173,9 @@ asmlinkage void ret_from_fork(void);
  * |    user_r25    |
  * ------------------  <===== END of PAGE
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 58eaa1f60e16..3395be186c7d 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -225,9 +225,8 @@ void release_thread(struct task_struct *dead_task)
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-int
-copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6089638c7d43..84ec630b8ab5 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -375,7 +375,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index afa3ea9a93aa..9f4fd6a40a10 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -104,9 +104,9 @@ void start_thread(struct pt_regs *regs, unsigned int pc, unsigned long usp)
 /*
  * Copy a new thread context in its stack.
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long ustk_size, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long ustk_size, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *childregs;
 
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index 8b3fad062ab2..28cfeaaf902a 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -40,7 +40,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return sw->r15;
 }
 
-int copy_thread_tls(unsigned long clone_flags,
+int copy_thread(unsigned long clone_flags,
 		unsigned long usp,
 		unsigned long kthread_arg,
 		struct task_struct *p,
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index ae23de4dcf42..83ce3caf7313 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -105,9 +105,8 @@ void flush_thread(void)
 {
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long topstk, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long topstk, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs;
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index d756f9556dd7..d294e71d11d8 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -50,8 +50,8 @@ void arch_cpu_idle(void)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct hexagon_switch_stack *ss;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 416dca619da5..9cedb56c3fda 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -311,7 +311,7 @@ ia64_load_extra (struct task_struct *task)
  *	<clone syscall>	        <some kernel call frames>
  *	sys_clone		   :
  *	_do_fork		_do_fork
- *	copy_thread_tls		copy_thread_tls
+ *	copy_thread		copy_thread
  *
  * This means that the stack layout is as follows:
  *
@@ -333,9 +333,8 @@ ia64_load_extra (struct task_struct *task)
  * so there is nothing to worry about.
  */
 int
-copy_thread_tls(unsigned long clone_flags, unsigned long user_stack_base,
-		    unsigned long user_stack_size, struct task_struct *p,
-		    unsigned long tls)
+copy_thread(unsigned long clone_flags, unsigned long user_stack_base,
+	    unsigned long user_stack_size, struct task_struct *p, unsigned long tls)
 {
 	extern char ia64_ret_from_clone;
 	struct switch_stack *child_stack, *stack;
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 0608439ba452..6492a2c54dbc 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -138,9 +138,8 @@ asmlinkage int m68k_clone3(struct pt_regs *regs)
 	return sys_clone3((struct clone_args __user *)regs->d1, regs->d2);
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long arg, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct fork_frame {
 		struct switch_stack sw;
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index c2ca9c326510..6cabeab9e2ba 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -54,8 +54,8 @@ void flush_thread(void)
 {
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct thread_info *ti = task_thread_info(p);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index ff5320b79100..f5dc316a826a 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -119,8 +119,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index 7dbb1bf64165..e85bbbadc0e7 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -149,9 +149,8 @@ void flush_thread(void)
 DEFINE_PER_CPU(struct task_struct *, __entry_task);
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
-		    unsigned long stk_sz, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 3dde4d6d8fbe..0a42ab8e4c32 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -100,8 +100,8 @@ void flush_thread(void)
 {
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct pt_regs *regs;
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index d7010e72450c..848f74c2c47a 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -116,7 +116,7 @@ void release_thread(struct task_struct *dead_task)
 extern asmlinkage void ret_from_fork(void);
 
 /*
- * copy_thread_tls
+ * copy_thread
  * @clone_flags: flags
  * @usp: user stack pointer or fn for kernel thread
  * @arg: arg to fn for kernel thread; always NULL for userspace thread
@@ -147,8 +147,8 @@ extern asmlinkage void ret_from_fork(void);
  */
 
 int
-copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg, struct task_struct *p, unsigned long tls)
+copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+	    struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *userregs;
 	struct pt_regs *kregs;
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index b7abb12edd3a..de6299ff1530 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -208,7 +208,7 @@ arch_initcall(parisc_idle_init);
  * Copy architecture-specific thread state
  */
 int
-copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+copy_thread(unsigned long clone_flags, unsigned long usp,
 	    unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *cregs = &(p->thread.regs);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4650b9bb217f..794b754deec2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1593,7 +1593,7 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long kthread_arg, struct task_struct *p,
 		unsigned long tls)
 {
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 824d117cf202..31f39442df72 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -101,8 +101,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index eb6e23ad15a2..b06dec1267d0 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -80,8 +80,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
+		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct fake_frame
 	{
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 537a82d80616..b0fefd8f53a6 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -115,8 +115,8 @@ EXPORT_SYMBOL(dump_fpu);
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs;
diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process.c
index 8bbe62d77b77..5234b5ccc0b9 100644
--- a/arch/sparc/kernel/process.c
+++ b/arch/sparc/kernel/process.c
@@ -28,7 +28,7 @@ asmlinkage long sparc_fork(struct pt_regs *regs)
 	ret = _do_fork(&args);
 
 	/* If we get an error and potentially restart the system
-	 * call, we're screwed because copy_thread_tls() clobbered
+	 * call, we're screwed because copy_thread() clobbered
 	 * the parent's %o1.  So detect that case and restore it
 	 * here.
 	 */
@@ -53,7 +53,7 @@ asmlinkage long sparc_vfork(struct pt_regs *regs)
 	ret = _do_fork(&args);
 
 	/* If we get an error and potentially restart the system
-	 * call, we're screwed because copy_thread_tls() clobbered
+	 * call, we're screwed because copy_thread() clobbered
 	 * the parent's %o1.  So detect that case and restore it
 	 * here.
 	 */
@@ -99,7 +99,7 @@ asmlinkage long sparc_clone(struct pt_regs *regs)
 	ret = _do_fork(&args);
 
 	/* If we get an error and potentially restart the system
-	 * call, we're screwed because copy_thread_tls() clobbered
+	 * call, we're screwed because copy_thread() clobbered
 	 * the parent's %o1.  So detect that case and restore it
 	 * here.
 	 */
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 3e1f7b639e9a..bd123f1de2e7 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -273,9 +273,8 @@ clone_stackframe(struct sparc_stackf __user *dst,
 extern void ret_from_fork(void);
 extern void ret_from_kernel_thread(void);
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
-		    unsigned long arg, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 278bf287c4be..04ef19b88632 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -577,9 +577,8 @@ barf:
  * Parent -->  %o0 == childs  pid, %o1 == 0
  * Child  -->  %o0 == parents pid, %o1 == 1
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
-		    unsigned long arg, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *t = task_thread_info(p);
 	struct pt_regs *regs = current_pt_regs();
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index e3a2cf92a373..26b5e243d3fc 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -152,7 +152,7 @@ void fork_handler(void)
 	userspace(&current->thread.regs.regs, current_thread_info()->aux_fp_regs);
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct * p, unsigned long tls)
 {
 	void (*handler)(void);
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 49a305565a53..d5ae5a971c19 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -219,9 +219,8 @@ void release_thread(struct task_struct *dead_task)
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
-		    unsigned long stk_sz, struct task_struct *p,
-		    unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f362ce0d5ac0..b35cd50ed0dc 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -121,8 +121,8 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
-		    unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
 {
 	struct inactive_task_frame *frame;
 	struct fork_frame *fork_frame;
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 722a85f3b2dd..3070fd6561be 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -269,7 +269,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		/*
 		 * kthreads (other than the boot CPU's idle thread) have some
 		 * partial regs at the end of their stack which were placed
-		 * there by copy_thread_tls().  But the regs don't have any
+		 * there by copy_thread().  But the regs don't have any
 		 * useful information, so we can skip them.
 		 *
 		 * This user_mode() check is slightly broader than a PF_KTHREAD
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index b7fe6f443b42..397a7de56377 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -201,7 +201,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  * involved.  Much simpler to just not copy those live frames across.
  */
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp_thread_fn,
+int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
 		unsigned long thread_fn_arg, struct task_struct *p,
 		unsigned long tls)
 {
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 77cbe14c3034..b6253f2ea96a 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -65,8 +65,8 @@ extern void fork_init(void);
 
 extern void release_task(struct task_struct * p);
 
-extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
-			struct task_struct *, unsigned long);
+extern int copy_thread(unsigned long, unsigned long, unsigned long,
+		       struct task_struct *, unsigned long);
 
 extern void flush_thread(void);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 8e52e16a1b5e..790841eb0a21 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2104,8 +2104,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread_tls(clone_flags, args->stack, args->stack_size, p,
-				 args->tls);
+	retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
-- 
cgit v1.2.3


From b1c7b87443c2c12c4fe095114736b8ad6f963f67 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 5 Jul 2020 19:16:22 +0300
Subject: net: dsa: felix: support half-duplex link modes

Ping tested:

  [   11.808455] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Full - flow control rx/tx
  [   11.816497] IPv6: ADDRCONF(NETDEV_CHANGE): swp0: link becomes ready

  [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x4
  [   18.844591] mscc_felix 0000:00:00.5 swp0: Link is Down
  [   22.048337] mscc_felix 0000:00:00.5 swp0: Link is Up - 100Mbps/Half - flow control off

  [root@LS1028ARDB ~] # ip addr add 192.168.1.1/24 dev swp0

  [root@LS1028ARDB ~] # ping 192.168.1.2
  PING 192.168.1.2 (192.168.1.2): 56 data bytes
  (...)
  ^C--- 192.168.1.2 ping statistics ---
  3 packets transmitted, 3 packets received, 0% packet loss
  round-trip min/avg/max = 0.383/0.611/1.051 ms

  [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x10
  [  355.637747] mscc_felix 0000:00:00.5 swp0: Link is Down
  [  358.788034] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Half - flow control off

  [root@LS1028ARDB ~] # ping 192.168.1.2
  PING 192.168.1.2 (192.168.1.2): 56 data bytes
  (...)
  ^C
  --- 192.168.1.2 ping statistics ---
  16 packets transmitted, 16 packets received, 0% packet loss
  round-trip min/avg/max = 0.301/0.384/1.138 ms

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c         |  4 +++-
 drivers/net/dsa/ocelot/felix_vsc9959.c | 23 +++++++++++++----------
 include/linux/fsl/enetc_mdio.h         |  1 +
 3 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 75020af7f7a4..f54648dff0ec 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -194,13 +194,15 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port,
 		return;
 	}
 
-	/* No half-duplex. */
 	phylink_set_port_modes(mask);
 	phylink_set(mask, Autoneg);
 	phylink_set(mask, Pause);
 	phylink_set(mask, Asym_Pause);
+	phylink_set(mask, 10baseT_Half);
 	phylink_set(mask, 10baseT_Full);
+	phylink_set(mask, 100baseT_Half);
 	phylink_set(mask, 100baseT_Full);
+	phylink_set(mask, 1000baseT_Half);
 	phylink_set(mask, 1000baseT_Full);
 
 	if (state->interface == PHY_INTERFACE_MODE_INTERNAL ||
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 9f4c8343652f..94e946b26f90 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -817,12 +817,9 @@ static void vsc9959_pcs_init_sgmii(struct phy_device *pcs,
 
 		phy_set_bits(pcs, MII_BMCR, BMCR_ANENABLE);
 	} else {
+		u16 if_mode = ENETC_PCS_IF_MODE_SGMII_EN;
 		int speed;
 
-		if (state->duplex == DUPLEX_HALF) {
-			phydev_err(pcs, "Half duplex not supported\n");
-			return;
-		}
 		switch (state->speed) {
 		case SPEED_1000:
 			speed = ENETC_PCS_SPEED_1000;
@@ -841,9 +838,9 @@ static void vsc9959_pcs_init_sgmii(struct phy_device *pcs,
 			return;
 		}
 
-		phy_write(pcs, ENETC_PCS_IF_MODE,
-			  ENETC_PCS_IF_MODE_SGMII_EN |
-			  ENETC_PCS_IF_MODE_SGMII_SPEED(speed));
+		if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(speed);
+		if (state->duplex == DUPLEX_HALF)
+			if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF;
 
 		phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE);
 	}
@@ -870,15 +867,18 @@ static void vsc9959_pcs_init_2500basex(struct phy_device *pcs,
 				       unsigned int link_an_mode,
 				       const struct phylink_link_state *state)
 {
+	u16 if_mode = ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_2500) |
+		      ENETC_PCS_IF_MODE_SGMII_EN;
+
 	if (link_an_mode == MLO_AN_INBAND) {
 		phydev_err(pcs, "AN not supported on 3.125GHz SerDes lane\n");
 		return;
 	}
 
-	phy_write(pcs, ENETC_PCS_IF_MODE,
-		  ENETC_PCS_IF_MODE_SGMII_EN |
-		  ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_2500));
+	if (state->duplex == DUPLEX_HALF)
+		if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF;
 
+	phy_write(pcs, ENETC_PCS_IF_MODE, if_mode);
 	phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE);
 }
 
@@ -919,8 +919,11 @@ static void vsc9959_pcs_init(struct ocelot *ocelot, int port,
 	linkmode_set_bit_array(phy_basic_ports_array,
 			       ARRAY_SIZE(phy_basic_ports_array),
 			       pcs->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, pcs->supported);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, pcs->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, pcs->supported);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, pcs->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, pcs->supported);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, pcs->supported);
 	if (pcs->interface == PHY_INTERFACE_MODE_2500BASEX ||
 	    pcs->interface == PHY_INTERFACE_MODE_USXGMII)
diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h
index 4875dd38af7e..2d9203314865 100644
--- a/include/linux/fsl/enetc_mdio.h
+++ b/include/linux/fsl/enetc_mdio.h
@@ -15,6 +15,7 @@
 #define ENETC_PCS_IF_MODE_SGMII_EN		BIT(0)
 #define ENETC_PCS_IF_MODE_USE_SGMII_AN		BIT(1)
 #define ENETC_PCS_IF_MODE_SGMII_SPEED(x)	(((x) << 2) & GENMASK(3, 2))
+#define ENETC_PCS_IF_MODE_DUPLEX_HALF		BIT(3)
 
 /* Not a mistake, the SerDes PLL needs to be set at 3.125 GHz by Reset
  * Configuration Word (RCW, outside Linux control) for 2.5G SGMII mode. The PCS
-- 
cgit v1.2.3


From 821b67fa46390baea0ac5139a60eaa48805261b2 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Thu, 25 Jun 2020 10:59:39 +0100
Subject: firmware: smccc: Add ARCH_SOC_ID support

SMCCC v1.2 adds a new optional function SMCCC_ARCH_SOC_ID to obtain a
SiP defined SoC identification value. Add support for the same.

Also using the SoC bus infrastructure, let us expose the platform
specific SoC atrributes under sysfs.

There are various ways in which it can be represented in shortened form
for efficiency and ease of parsing for userspace. The chosen form is
described in the ABI document.

Link: https://lore.kernel.org/r/20200625095939.50861-1-sudeep.holla@arm.com
Cc: Etienne Carriere <etienne.carriere@st.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 Documentation/ABI/testing/sysfs-devices-soc |  30 ++++++++
 drivers/firmware/smccc/Kconfig              |   9 +++
 drivers/firmware/smccc/Makefile             |   1 +
 drivers/firmware/smccc/soc_id.c             | 114 ++++++++++++++++++++++++++++
 include/linux/arm-smccc.h                   |   5 ++
 5 files changed, 159 insertions(+)
 create mode 100644 drivers/firmware/smccc/soc_id.c

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-devices-soc b/Documentation/ABI/testing/sysfs-devices-soc
index ba3a3fac0ee1..ea999e292f11 100644
--- a/Documentation/ABI/testing/sysfs-devices-soc
+++ b/Documentation/ABI/testing/sysfs-devices-soc
@@ -26,6 +26,30 @@ Description:
 		Read-only attribute common to all SoCs. Contains SoC family name
 		(e.g. DB8500).
 
+		On many of ARM based silicon with SMCCC v1.2+ compliant firmware
+		this will contain the JEDEC JEP106 manufacturer’s identification
+		code. The format is "jep106:XXYY" where XX is identity code and
+		YY is continuation code.
+
+		This manufacturer’s identification code is defined by one
+		or more eight (8) bit fields, each consisting of seven (7)
+		data bits plus one (1) odd parity bit. It is a single field,
+		limiting the possible number of vendors to 126. To expand
+		the maximum number of identification codes, a continuation
+		scheme has been defined.
+
+		The specified mechanism is that an identity code of 0x7F
+		represents the "continuation code" and implies the presence
+		of an additional identity code field, and this mechanism
+		may be extended to multiple continuation codes followed
+		by the manufacturer's identity code.
+
+		For example, ARM has identity code 0x7F 0x7F 0x7F 0x7F 0x3B,
+		which is code 0x3B on the fifth 'page'. This is shortened
+		as JEP106 identity code of 0x3B and a continuation code of
+		0x4 to represent the four continuation codes preceding the
+		identity code.
+
 What:		/sys/devices/socX/serial_number
 Date:		January 2019
 contact:	Bjorn Andersson <bjorn.andersson@linaro.org>
@@ -40,6 +64,12 @@ Description:
 		Read-only attribute supported by most SoCs. In the case of
 		ST-Ericsson's chips this contains the SoC serial number.
 
+		On many of ARM based silicon with SMCCC v1.2+ compliant firmware
+		this will contain the SOC ID appended to the family attribute
+		to ensure there is no conflict in this namespace across various
+		vendors. The format is "jep106:XXYY:ZZZZ" where XX is identity
+		code, YY is continuation code and ZZZZ is the SOC ID.
+
 What:		/sys/devices/socX/revision
 Date:		January 2012
 contact:	Lee Jones <lee.jones@linaro.org>
diff --git a/drivers/firmware/smccc/Kconfig b/drivers/firmware/smccc/Kconfig
index 27b675d76235..15e7466179a6 100644
--- a/drivers/firmware/smccc/Kconfig
+++ b/drivers/firmware/smccc/Kconfig
@@ -14,3 +14,12 @@ config HAVE_ARM_SMCCC_DISCOVERY
 	 to add SMCCC discovery mechanism though the PSCI firmware
 	 implementation of PSCI_FEATURES(SMCCC_VERSION) which returns
 	 success on firmware compliant to SMCCC v1.1 and above.
+
+config ARM_SMCCC_SOC_ID
+	bool "SoC bus device for the ARM SMCCC SOC_ID"
+	depends on HAVE_ARM_SMCCC_DISCOVERY
+	default y
+	select SOC_BUS
+	help
+	  Include support for the SoC bus on the ARM SMCCC firmware based
+	  platforms providing some sysfs information about the SoC variant.
diff --git a/drivers/firmware/smccc/Makefile b/drivers/firmware/smccc/Makefile
index 6f369fe3f0b9..72ab84042832 100644
--- a/drivers/firmware/smccc/Makefile
+++ b/drivers/firmware/smccc/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 obj-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY)	+= smccc.o
+obj-$(CONFIG_ARM_SMCCC_SOC_ID)	+= soc_id.o
diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c
new file mode 100644
index 000000000000..581aa5e9b077
--- /dev/null
+++ b/drivers/firmware/smccc/soc_id.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020 Arm Limited
+ */
+
+#define pr_fmt(fmt) "SMCCC: SOC_ID: " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sys_soc.h>
+
+#define SMCCC_SOC_ID_JEP106_BANK_IDX_MASK	GENMASK(30, 24)
+/*
+ * As per the SMC Calling Convention specification v1.2 (ARM DEN 0028C)
+ * Section 7.4 SMCCC_ARCH_SOC_ID bits[23:16] are JEP-106 identification
+ * code with parity bit for the SiP. We can drop the parity bit.
+ */
+#define SMCCC_SOC_ID_JEP106_ID_CODE_MASK	GENMASK(22, 16)
+#define SMCCC_SOC_ID_IMP_DEF_SOC_ID_MASK	GENMASK(15, 0)
+
+#define JEP106_BANK_CONT_CODE(x)	\
+	(u8)(FIELD_GET(SMCCC_SOC_ID_JEP106_BANK_IDX_MASK, (x)))
+#define JEP106_ID_CODE(x)	\
+	(u8)(FIELD_GET(SMCCC_SOC_ID_JEP106_ID_CODE_MASK, (x)))
+#define IMP_DEF_SOC_ID(x)	\
+	(u16)(FIELD_GET(SMCCC_SOC_ID_IMP_DEF_SOC_ID_MASK, (x)))
+
+static struct soc_device *soc_dev;
+static struct soc_device_attribute *soc_dev_attr;
+
+static int __init smccc_soc_init(void)
+{
+	struct arm_smccc_res res;
+	int soc_id_rev, soc_id_version;
+	static char soc_id_str[20], soc_id_rev_str[12];
+	static char soc_id_jep106_id_str[12];
+
+	if (arm_smccc_get_version() < ARM_SMCCC_VERSION_1_2)
+		return 0;
+
+	if (arm_smccc_1_1_get_conduit() == SMCCC_CONDUIT_NONE) {
+		pr_err("%s: invalid SMCCC conduit\n", __func__);
+		return -EOPNOTSUPP;
+	}
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_SOC_ID, &res);
+
+	if (res.a0 == SMCCC_RET_NOT_SUPPORTED) {
+		pr_info("ARCH_SOC_ID not implemented, skipping ....\n");
+		return 0;
+	}
+
+	if ((int)res.a0 < 0) {
+		pr_info("ARCH_FEATURES(ARCH_SOC_ID) returned error: %lx\n",
+			res.a0);
+		return -EINVAL;
+	}
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_SOC_ID, 0, &res);
+	if ((int)res.a0 < 0) {
+		pr_err("ARCH_SOC_ID(0) returned error: %lx\n", res.a0);
+		return -EINVAL;
+	}
+
+	soc_id_version = res.a0;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_SOC_ID, 1, &res);
+	if ((int)res.a0 < 0) {
+		pr_err("ARCH_SOC_ID(1) returned error: %lx\n", res.a0);
+		return -EINVAL;
+	}
+
+	soc_id_rev = res.a0;
+
+	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
+	if (!soc_dev_attr)
+		return -ENOMEM;
+
+	sprintf(soc_id_rev_str, "0x%08x", soc_id_rev);
+	sprintf(soc_id_jep106_id_str, "jep106:%02x%02x",
+		JEP106_BANK_CONT_CODE(soc_id_version),
+		JEP106_ID_CODE(soc_id_version));
+	sprintf(soc_id_str, "%s:%04x", soc_id_jep106_id_str,
+		IMP_DEF_SOC_ID(soc_id_version));
+
+	soc_dev_attr->soc_id = soc_id_str;
+	soc_dev_attr->revision = soc_id_rev_str;
+	soc_dev_attr->family = soc_id_jep106_id_str;
+
+	soc_dev = soc_device_register(soc_dev_attr);
+	if (IS_ERR(soc_dev)) {
+		kfree(soc_dev_attr);
+		return PTR_ERR(soc_dev);
+	}
+
+	pr_info("ID = %s Revision = %s\n", soc_dev_attr->soc_id,
+		soc_dev_attr->revision);
+
+	return 0;
+}
+module_init(smccc_soc_init);
+
+static void __exit smccc_soc_exit(void)
+{
+	if (soc_dev)
+		soc_device_unregister(soc_dev);
+	kfree(soc_dev_attr);
+}
+module_exit(smccc_soc_exit);
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 56d6a5c6e353..8254e11ea857 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -71,6 +71,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 1)
 
+#define ARM_SMCCC_ARCH_SOC_ID						\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 2)
+
 #define ARM_SMCCC_ARCH_WORKAROUND_1					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
 			   ARM_SMCCC_SMC_32,				\
-- 
cgit v1.2.3


From 68d237056e007c88031d80900cdba0945121a287 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 30 Jun 2020 10:16:02 +0200
Subject: scatterlist: protect parameters of the sg_table related macros

Add brackets to protect parameters of the recently added sg_table related
macros from side-effects.

Fixes: 709d6d73c756 ("scatterlist: add generic wrappers for iterating over sgtable objects")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/scatterlist.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 4f922afb607a..45cf7b69d852 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -155,7 +155,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
  * Loop over each sg element in the given sg_table object.
  */
 #define for_each_sgtable_sg(sgt, sg, i)		\
-	for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
+	for_each_sg((sgt)->sgl, sg, (sgt)->orig_nents, i)
 
 /*
  * Loop over each sg element in the given *DMA mapped* sg_table object.
@@ -163,7 +163,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
  * of the each element.
  */
 #define for_each_sgtable_dma_sg(sgt, sg, i)	\
-	for_each_sg(sgt->sgl, sg, sgt->nents, i)
+	for_each_sg((sgt)->sgl, sg, (sgt)->nents, i)
 
 /**
  * sg_chain - Chain two sglists together
@@ -451,7 +451,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter)
  * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit.
  */
 #define for_each_sgtable_page(sgt, piter, pgoffset)	\
-	for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset)
+	for_each_sg_page((sgt)->sgl, piter, (sgt)->orig_nents, pgoffset)
 
 /**
  * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object
@@ -465,7 +465,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter)
  * unit.
  */
 #define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset)	\
-	for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset)
+	for_each_sg_dma_page((sgt)->sgl, dma_iter, (sgt)->nents, pgoffset)
 
 
 /*
-- 
cgit v1.2.3


From 5ab903418ad14732131df0af0d63f19b73e377ae Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 6 Jul 2020 18:38:19 +0300
Subject: net: qed: sanitize BE/LE data processing

Current code assumes that both host and device operates in Little Endian
in lots of places. While this is true for x86 platform, this doesn't mean
we should not care about this.

This commit addresses all parts of the code that were pointed out by sparse
checker. All operations with restricted (__be*/__le*) types are now
protected with explicit from/to CPU conversions, even if they're noops on
common setups.

I'm sure there are more such places, but this implies a deeper code
investigation, and is a subject for future works.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_cxt.c          |  11 +-
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c         |  27 ++--
 drivers/net/ethernet/qlogic/qed/qed_debug.c        |  49 +++---
 drivers/net/ethernet/qlogic/qed/qed_fcoe.c         |  54 ++++---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h          |  48 +++---
 .../net/ethernet/qlogic/qed/qed_init_fw_funcs.c    |  93 ++++++-----
 drivers/net/ethernet/qlogic/qed/qed_int.c          |  74 +++++----
 drivers/net/ethernet/qlogic/qed/qed_iscsi.c        |  43 +++--
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c        | 132 ++++++++++------
 drivers/net/ethernet/qlogic/qed/qed_l2.c           |  22 +--
 drivers/net/ethernet/qlogic/qed/qed_ll2.c          |   9 +-
 drivers/net/ethernet/qlogic/qed/qed_main.c         |  12 +-
 drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c      |   4 +-
 drivers/net/ethernet/qlogic/qed/qed_rdma.c         |  52 +++---
 drivers/net/ethernet/qlogic/qed/qed_rdma.h         |   2 +-
 drivers/net/ethernet/qlogic/qed/qed_roce.c         | 176 +++++++++------------
 drivers/net/ethernet/qlogic/qed/qed_sp.h           |   2 +-
 drivers/net/ethernet/qlogic/qed/qed_sp_commands.c  |   4 +-
 drivers/net/ethernet/qlogic/qed/qed_sriov.c        |   4 +-
 include/linux/qed/qed_if.h                         |  15 +-
 20 files changed, 434 insertions(+), 399 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 3a62358b9749..5362dc18b6c2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -73,8 +73,8 @@ union type1_task_context {
 };
 
 struct src_ent {
-	u8				opaque[56];
-	u64				next;
+	__u8				opaque[56];
+	__be64				next;
 };
 
 #define CDUT_SEG_ALIGNMET		3 /* in 4k chunks */
@@ -2177,6 +2177,7 @@ qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
 	dma_addr_t p_phys;
 	u64 ilt_hw_entry;
 	void *p_virt;
+	u32 flags1;
 	int rc = 0;
 
 	switch (elem_type) {
@@ -2255,8 +2256,10 @@ qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
 			elem = (union type1_task_context *)elem_start;
 			tdif_context = &elem->roce_ctx.tdif_context;
 
-			SET_FIELD(tdif_context->flags1,
-				  TDIF_TASK_CONTEXT_REF_TAG_MASK, 0xf);
+			flags1 = le32_to_cpu(tdif_context->flags1);
+			SET_FIELD(flags1, TDIF_TASK_CONTEXT_REF_TAG_MASK, 0xf);
+			tdif_context->flags1 = cpu_to_le32(flags1);
+
 			elem_start += TYPE1_TASK_CXT_SIZE(p_hwfn);
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 9f16a3a66007..17d5b649eb36 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -547,7 +547,8 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn,
 		      struct dcbx_ets_feature *p_ets,
 		      struct qed_dcbx_params *p_params)
 {
-	u32 bw_map[2], tsa_map[2], pri_map;
+	__be32 bw_map[2], tsa_map[2];
+	u32 pri_map;
 	int i;
 
 	p_params->ets_willing = QED_MFW_GET_FIELD(p_ets->flags,
@@ -573,11 +574,10 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn,
 	/* 8 bit tsa and bw data corresponding to each of the 8 TC's are
 	 * encoded in a type u32 array of size 2.
 	 */
-	bw_map[0] = be32_to_cpu(p_ets->tc_bw_tbl[0]);
-	bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]);
-	tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]);
-	tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]);
+	cpu_to_be32_array(bw_map, p_ets->tc_bw_tbl, 2);
+	cpu_to_be32_array(tsa_map, p_ets->tc_tsa_tbl, 2);
 	pri_map = p_ets->pri_tc_tbl[0];
+
 	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
 		p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i];
 		p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i];
@@ -1054,7 +1054,7 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn,
 		      struct dcbx_ets_feature *p_ets,
 		      struct qed_dcbx_params *p_params)
 {
-	u8 *bw_map, *tsa_map;
+	__be32 bw_map[2], tsa_map[2];
 	u32 val;
 	int i;
 
@@ -1076,22 +1076,21 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn,
 	p_ets->flags &= ~DCBX_ETS_MAX_TCS_MASK;
 	p_ets->flags |= (u32)p_params->max_ets_tc << DCBX_ETS_MAX_TCS_SHIFT;
 
-	bw_map = (u8 *)&p_ets->tc_bw_tbl[0];
-	tsa_map = (u8 *)&p_ets->tc_tsa_tbl[0];
 	p_ets->pri_tc_tbl[0] = 0;
+
 	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
-		bw_map[i] = p_params->ets_tc_bw_tbl[i];
-		tsa_map[i] = p_params->ets_tc_tsa_tbl[i];
+		((u8 *)bw_map)[i] = p_params->ets_tc_bw_tbl[i];
+		((u8 *)tsa_map)[i] = p_params->ets_tc_tsa_tbl[i];
+
 		/* Copy the priority value to the corresponding 4 bits in the
 		 * traffic class table.
 		 */
 		val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4));
 		p_ets->pri_tc_tbl[0] |= val;
 	}
-	for (i = 0; i < 2; i++) {
-		p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]);
-		p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]);
-	}
+
+	be32_to_cpu_array(p_ets->tc_bw_tbl, bw_map, 2);
+	be32_to_cpu_array(p_ets->tc_tsa_tbl, tsa_map, 2);
 }
 
 static void
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index f856bb9a3897..41ab23712bbd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -972,7 +972,7 @@ static void qed_read_storm_fw_info(struct qed_hwfn *p_hwfn,
 {
 	struct storm_defs *storm = &s_storm_defs[storm_id];
 	struct fw_info_location fw_info_location;
-	u32 addr, i, *dest;
+	u32 addr, i, size, *dest;
 
 	memset(&fw_info_location, 0, sizeof(fw_info_location));
 	memset(fw_info, 0, sizeof(*fw_info));
@@ -985,20 +985,29 @@ static void qed_read_storm_fw_info(struct qed_hwfn *p_hwfn,
 	    sizeof(fw_info_location);
 
 	dest = (u32 *)&fw_info_location;
+	size = BYTES_TO_DWORDS(sizeof(fw_info_location));
 
-	for (i = 0; i < BYTES_TO_DWORDS(sizeof(fw_info_location));
-	     i++, addr += BYTES_IN_DWORD)
+	for (i = 0; i < size; i++, addr += BYTES_IN_DWORD)
 		dest[i] = qed_rd(p_hwfn, p_ptt, addr);
 
+	/* qed_rq() fetches data in CPU byteorder. Swap it back to
+	 * the device's to get right structure layout.
+	 */
+	cpu_to_le32_array(dest, size);
+
 	/* Read FW version info from Storm RAM */
-	if (fw_info_location.size > 0 && fw_info_location.size <=
-	    sizeof(*fw_info)) {
-		addr = fw_info_location.grc_addr;
-		dest = (u32 *)fw_info;
-		for (i = 0; i < BYTES_TO_DWORDS(fw_info_location.size);
-		     i++, addr += BYTES_IN_DWORD)
-			dest[i] = qed_rd(p_hwfn, p_ptt, addr);
-	}
+	size = le32_to_cpu(fw_info_location.size);
+	if (!size || size > sizeof(*fw_info))
+		return;
+
+	addr = le32_to_cpu(fw_info_location.grc_addr);
+	dest = (u32 *)fw_info;
+	size = BYTES_TO_DWORDS(size);
+
+	for (i = 0; i < size; i++, addr += BYTES_IN_DWORD)
+		dest[i] = qed_rd(p_hwfn, p_ptt, addr);
+
+	cpu_to_le32_array(dest, size);
 }
 
 /* Dumps the specified string to the specified buffer.
@@ -1123,7 +1132,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn,
 	offset += qed_dump_str_param(dump_buf + offset,
 				     dump, "fw-image", fw_img_str);
 	offset += qed_dump_num_param(dump_buf + offset, dump, "fw-timestamp",
-				     fw_info.ver.timestamp);
+				     le32_to_cpu(fw_info.ver.timestamp));
 
 	return offset;
 }
@@ -4440,9 +4449,11 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 			continue;
 		}
 
+		addr = le16_to_cpu(asserts->section_ram_line_offset);
 		fw_asserts_section_addr = storm->sem_fast_mem_addr +
-			SEM_FAST_REG_INT_RAM +
-			RAM_LINES_TO_BYTES(asserts->section_ram_line_offset);
+					  SEM_FAST_REG_INT_RAM +
+					  RAM_LINES_TO_BYTES(addr);
+
 		next_list_idx_addr = fw_asserts_section_addr +
 			DWORDS_TO_BYTES(asserts->list_next_index_dword_offset);
 		next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr);
@@ -7650,8 +7661,7 @@ static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
 {
 	struct qed_hwfn *p_hwfn =
 		&cdev->hwfns[cdev->engine_for_debug];
-	u32 len_rounded, i;
-	__be32 val;
+	u32 len_rounded;
 	int rc;
 
 	*num_dumped_bytes = 0;
@@ -7670,10 +7680,9 @@ static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
 
 	/* QED_NVM_IMAGE_NVM_META image is not swapped like other images */
 	if (image_id != QED_NVM_IMAGE_NVM_META)
-		for (i = 0; i < len_rounded; i += 4) {
-			val = cpu_to_be32(*(u32 *)(buffer + i));
-			*(u32 *)(buffer + i) = val;
-		}
+		cpu_to_be32_array((__force __be32 *)buffer,
+				  (const u32 *)buffer,
+				  len_rounded / sizeof(u32));
 
 	*num_dumped_bytes = len_rounded;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index a10e57bba6b9..b768f0698170 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -95,7 +95,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
 	struct qed_cxt_info cxt_info;
 	u32 dummy_cid;
 	int rc = 0;
-	u16 tmp;
+	__le16 tmp;
 	u8 i;
 
 	/* Get SPQ entry */
@@ -162,17 +162,13 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
 	tmp = cpu_to_le16(fcoe_pf_params->cmdq_num_entries);
 	p_data->q_params.cmdq_num_entries = tmp;
 
-	tmp = fcoe_pf_params->num_cqs;
-	p_data->q_params.num_queues = (u8)tmp;
+	p_data->q_params.num_queues = fcoe_pf_params->num_cqs;
 
-	tmp = (u16)p_hwfn->hw_info.resc_start[QED_CMDQS_CQS];
-	p_data->q_params.queue_relative_offset = (u8)tmp;
+	tmp = (__force __le16)p_hwfn->hw_info.resc_start[QED_CMDQS_CQS];
+	p_data->q_params.queue_relative_offset = (__force u8)tmp;
 
 	for (i = 0; i < fcoe_pf_params->num_cqs; i++) {
-		u16 igu_sb_id;
-
-		igu_sb_id = qed_get_igu_sb_id(p_hwfn, i);
-		tmp = cpu_to_le16(igu_sb_id);
+		tmp = cpu_to_le16(qed_get_igu_sb_id(p_hwfn, i));
 		p_data->q_params.cq_cmdq_sb_num_arr[i] = tmp;
 	}
 
@@ -185,21 +181,21 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
 		       fcoe_pf_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
 	p_data->q_params.bdq_pbl_num_entries[BDQ_ID_RQ] =
 	    fcoe_pf_params->bdq_pbl_num_entries[BDQ_ID_RQ];
-	tmp = fcoe_pf_params->bdq_xoff_threshold[BDQ_ID_RQ];
-	p_data->q_params.bdq_xoff_threshold[BDQ_ID_RQ] = cpu_to_le16(tmp);
-	tmp = fcoe_pf_params->bdq_xon_threshold[BDQ_ID_RQ];
-	p_data->q_params.bdq_xon_threshold[BDQ_ID_RQ] = cpu_to_le16(tmp);
+	tmp = cpu_to_le16(fcoe_pf_params->bdq_xoff_threshold[BDQ_ID_RQ]);
+	p_data->q_params.bdq_xoff_threshold[BDQ_ID_RQ] = tmp;
+	tmp = cpu_to_le16(fcoe_pf_params->bdq_xon_threshold[BDQ_ID_RQ]);
+	p_data->q_params.bdq_xon_threshold[BDQ_ID_RQ] = tmp;
 
 	DMA_REGPAIR_LE(p_data->q_params.bdq_pbl_base_address[BDQ_ID_IMM_DATA],
 		       fcoe_pf_params->bdq_pbl_base_addr[BDQ_ID_IMM_DATA]);
 	p_data->q_params.bdq_pbl_num_entries[BDQ_ID_IMM_DATA] =
 	    fcoe_pf_params->bdq_pbl_num_entries[BDQ_ID_IMM_DATA];
-	tmp = fcoe_pf_params->bdq_xoff_threshold[BDQ_ID_IMM_DATA];
-	p_data->q_params.bdq_xoff_threshold[BDQ_ID_IMM_DATA] = cpu_to_le16(tmp);
-	tmp = fcoe_pf_params->bdq_xon_threshold[BDQ_ID_IMM_DATA];
-	p_data->q_params.bdq_xon_threshold[BDQ_ID_IMM_DATA] = cpu_to_le16(tmp);
-	tmp = fcoe_pf_params->rq_buffer_size;
-	p_data->q_params.rq_buffer_size = cpu_to_le16(tmp);
+	tmp = cpu_to_le16(fcoe_pf_params->bdq_xoff_threshold[BDQ_ID_IMM_DATA]);
+	p_data->q_params.bdq_xoff_threshold[BDQ_ID_IMM_DATA] = tmp;
+	tmp = cpu_to_le16(fcoe_pf_params->bdq_xon_threshold[BDQ_ID_IMM_DATA]);
+	p_data->q_params.bdq_xon_threshold[BDQ_ID_IMM_DATA] = tmp;
+	tmp = cpu_to_le16(fcoe_pf_params->rq_buffer_size);
+	p_data->q_params.rq_buffer_size = tmp;
 
 	if (fcoe_pf_params->is_target) {
 		SET_FIELD(p_data->q_params.q_validity,
@@ -233,7 +229,8 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 	struct fcoe_conn_offload_ramrod_data *p_data;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	u16 physical_q0, tmp;
+	u16 physical_q0;
+	__le16 tmp;
 	int rc;
 
 	/* Get SPQ entry */
@@ -254,7 +251,7 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 
 	/* Transmission PQ is the first of the PF */
 	physical_q0 = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-	p_conn->physical_q0 = cpu_to_le16(physical_q0);
+	p_conn->physical_q0 = physical_q0;
 	p_data->physical_q0 = cpu_to_le16(physical_q0);
 
 	p_data->conn_id = cpu_to_le16(p_conn->conn_id);
@@ -553,8 +550,8 @@ int qed_fcoe_alloc(struct qed_hwfn *p_hwfn)
 void qed_fcoe_setup(struct qed_hwfn *p_hwfn)
 {
 	struct e4_fcoe_task_context *p_task_ctx = NULL;
+	u32 i, lc;
 	int rc;
-	u32 i;
 
 	spin_lock_init(&p_hwfn->p_fcoe_info->lock);
 	for (i = 0; i < p_hwfn->pf_params.fcoe_pf_params.num_tasks; i++) {
@@ -565,10 +562,15 @@ void qed_fcoe_setup(struct qed_hwfn *p_hwfn)
 			continue;
 
 		memset(p_task_ctx, 0, sizeof(struct e4_fcoe_task_context));
-		SET_FIELD(p_task_ctx->timer_context.logical_client_0,
-			  TIMERS_CONTEXT_VALIDLC0, 1);
-		SET_FIELD(p_task_ctx->timer_context.logical_client_1,
-			  TIMERS_CONTEXT_VALIDLC1, 1);
+
+		lc = 0;
+		SET_FIELD(lc, TIMERS_CONTEXT_VALIDLC0, 1);
+		p_task_ctx->timer_context.logical_client_0 = cpu_to_le32(lc);
+
+		lc = 0;
+		SET_FIELD(lc, TIMERS_CONTEXT_VALIDLC1, 1);
+		p_task_ctx->timer_context.logical_client_1 = cpu_to_le32(lc);
+
 		SET_FIELD(p_task_ctx->tstorm_ag_context.flags0,
 			  E4_TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, 1);
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 71809ff97a03..6bb0bbc0013b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -2793,7 +2793,7 @@ struct fw_overlay_buf_hdr {
 
 /* init array header: raw */
 struct init_array_raw_hdr {
-	u32						data;
+	__le32						data;
 #define INIT_ARRAY_RAW_HDR_TYPE_MASK			0xF
 #define INIT_ARRAY_RAW_HDR_TYPE_SHIFT			0
 #define INIT_ARRAY_RAW_HDR_PARAMS_MASK			0xFFFFFFF
@@ -2802,7 +2802,7 @@ struct init_array_raw_hdr {
 
 /* init array header: standard */
 struct init_array_standard_hdr {
-	u32						data;
+	__le32						data;
 #define INIT_ARRAY_STANDARD_HDR_TYPE_MASK		0xF
 #define INIT_ARRAY_STANDARD_HDR_TYPE_SHIFT		0
 #define INIT_ARRAY_STANDARD_HDR_SIZE_MASK		0xFFFFFFF
@@ -2811,7 +2811,7 @@ struct init_array_standard_hdr {
 
 /* init array header: zipped */
 struct init_array_zipped_hdr {
-	u32						data;
+	__le32						data;
 #define INIT_ARRAY_ZIPPED_HDR_TYPE_MASK			0xF
 #define INIT_ARRAY_ZIPPED_HDR_TYPE_SHIFT		0
 #define INIT_ARRAY_ZIPPED_HDR_ZIPPED_SIZE_MASK		0xFFFFFFF
@@ -2820,7 +2820,7 @@ struct init_array_zipped_hdr {
 
 /* init array header: pattern */
 struct init_array_pattern_hdr {
-	u32						data;
+	__le32						data;
 #define INIT_ARRAY_PATTERN_HDR_TYPE_MASK		0xF
 #define INIT_ARRAY_PATTERN_HDR_TYPE_SHIFT		0
 #define INIT_ARRAY_PATTERN_HDR_PATTERN_SIZE_MASK	0xF
@@ -2847,48 +2847,48 @@ enum init_array_types {
 
 /* init operation: callback */
 struct init_callback_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_CALLBACK_OP_OP_MASK			0xF
 #define INIT_CALLBACK_OP_OP_SHIFT			0
 #define INIT_CALLBACK_OP_RESERVED_MASK			0xFFFFFFF
 #define INIT_CALLBACK_OP_RESERVED_SHIFT			4
-	u16						callback_id;
-	u16						block_id;
+	__le16						callback_id;
+	__le16						block_id;
 };
 
 /* init operation: delay */
 struct init_delay_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_DELAY_OP_OP_MASK				0xF
 #define INIT_DELAY_OP_OP_SHIFT				0
 #define INIT_DELAY_OP_RESERVED_MASK			0xFFFFFFF
 #define INIT_DELAY_OP_RESERVED_SHIFT			4
-	u32						delay;
+	__le32						delay;
 };
 
 /* init operation: if_mode */
 struct init_if_mode_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_IF_MODE_OP_OP_MASK				0xF
 #define INIT_IF_MODE_OP_OP_SHIFT			0
 #define INIT_IF_MODE_OP_RESERVED1_MASK			0xFFF
 #define INIT_IF_MODE_OP_RESERVED1_SHIFT			4
 #define INIT_IF_MODE_OP_CMD_OFFSET_MASK			0xFFFF
 #define INIT_IF_MODE_OP_CMD_OFFSET_SHIFT		16
-	u16						reserved2;
-	u16						modes_buf_offset;
+	__le16						reserved2;
+	__le16						modes_buf_offset;
 };
 
 /* init operation: if_phase */
 struct init_if_phase_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_IF_PHASE_OP_OP_MASK			0xF
 #define INIT_IF_PHASE_OP_OP_SHIFT			0
 #define INIT_IF_PHASE_OP_RESERVED1_MASK			0xFFF
 #define INIT_IF_PHASE_OP_RESERVED1_SHIFT		4
 #define INIT_IF_PHASE_OP_CMD_OFFSET_MASK		0xFFFF
 #define INIT_IF_PHASE_OP_CMD_OFFSET_SHIFT		16
-	u32						phase_data;
+	__le32						phase_data;
 #define INIT_IF_PHASE_OP_PHASE_MASK			0xFF
 #define INIT_IF_PHASE_OP_PHASE_SHIFT			0
 #define INIT_IF_PHASE_OP_RESERVED2_MASK			0xFF
@@ -2907,31 +2907,31 @@ enum init_mode_ops {
 
 /* init operation: raw */
 struct init_raw_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_RAW_OP_OP_MASK				0xF
 #define INIT_RAW_OP_OP_SHIFT				0
 #define INIT_RAW_OP_PARAM1_MASK				0xFFFFFFF
 #define INIT_RAW_OP_PARAM1_SHIFT			4
-	u32						param2;
+	__le32						param2;
 };
 
 /* init array params */
 struct init_op_array_params {
-	u16						size;
-	u16						offset;
+	__le16						size;
+	__le16						offset;
 };
 
 /* Write init operation arguments */
 union init_write_args {
-	u32						inline_val;
-	u32						zeros_count;
-	u32						array_offset;
+	__le32						inline_val;
+	__le32						zeros_count;
+	__le32						array_offset;
 	struct init_op_array_params			runtime;
 };
 
 /* init operation: write */
 struct init_write_op {
-	u32						data;
+	__le32						data;
 #define INIT_WRITE_OP_OP_MASK				0xF
 #define INIT_WRITE_OP_OP_SHIFT				0
 #define INIT_WRITE_OP_SOURCE_MASK			0x7
@@ -2947,7 +2947,7 @@ struct init_write_op {
 
 /* init operation: read */
 struct init_read_op {
-	u32						op_data;
+	__le32						op_data;
 #define INIT_READ_OP_OP_MASK				0xF
 #define INIT_READ_OP_OP_SHIFT				0
 #define INIT_READ_OP_POLL_TYPE_MASK			0xF
@@ -2956,7 +2956,7 @@ struct init_read_op {
 #define INIT_READ_OP_RESERVED_SHIFT			8
 #define INIT_READ_OP_ADDRESS_MASK			0x7FFFFF
 #define INIT_READ_OP_ADDRESS_SHIFT			9
-	u32						expected_val;
+	__le32						expected_val;
 };
 
 /* Init operations union */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 775ef5eaefd4..ea888a2c6ddb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -159,23 +159,22 @@ static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES_E4] = {
 #define QM_INIT_TX_PQ_MAP(p_hwfn, map, chip, pq_id, vp_pq_id, rl_valid,	      \
 			  rl_id, ext_voq, wrr)				      \
 	do {								      \
-		typeof(map) __map;					      \
+		u32 __reg = 0;						      \
 									      \
-		memset(&__map, 0, sizeof(__map));			      \
+		BUILD_BUG_ON(sizeof((map).reg) != sizeof(__reg));	      \
 									      \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_PQ_VALID, 1);      \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_RL_VALID,	      \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_PQ_VALID, 1);	      \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_RL_VALID,	      \
 			  !!(rl_valid));				      \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_VP_PQ_ID,	      \
-			  (vp_pq_id));					      \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_RL_ID, (rl_id));   \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_VOQ, (ext_voq));   \
-		SET_FIELD(__map.reg, QM_RF_PQ_MAP_##chip##_WRR_WEIGHT_GROUP,  \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_VP_PQ_ID, (vp_pq_id)); \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_RL_ID, (rl_id));	      \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_VOQ, (ext_voq));	      \
+		SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_WRR_WEIGHT_GROUP,      \
 			  (wrr));					      \
 									      \
 		STORE_RT_REG((p_hwfn), QM_REG_TXPQMAP_RT_OFFSET + (pq_id),    \
-			     *((u32 *)&__map));				      \
-		(map) = __map;						      \
+			     __reg);					      \
+		(map).reg = cpu_to_le32(__reg);				      \
 	} while (0)
 
 #define WRITE_PQ_INFO_TO_RAM	1
@@ -1012,9 +1011,10 @@ bool qed_send_qm_stop_cmd(struct qed_hwfn *p_hwfn,
  *         input.
  */
 static int qed_dmae_to_grc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
-			   u32 *p_data, u32 addr, u32 len_in_dwords)
+			   __le32 *p_data, u32 addr, u32 len_in_dwords)
 {
 	struct qed_dmae_params params = {};
+	u32 *data_cpu;
 	int rc;
 
 	if (!p_data)
@@ -1033,8 +1033,13 @@ static int qed_dmae_to_grc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_DEBUG,
 			   "Failed writing to chip using DMAE, using GRC instead\n");
-		/* write to registers using GRC */
-		ARR_REG_WR(p_hwfn, p_ptt, addr, p_data, len_in_dwords);
+
+		/* Swap to CPU byteorder and write to registers using GRC */
+		data_cpu = (__force u32 *)p_data;
+		le32_to_cpu_array(data_cpu, len_in_dwords);
+
+		ARR_REG_WR(p_hwfn, p_ptt, addr, data_cpu, len_in_dwords);
+		cpu_to_le32_array(data_cpu, len_in_dwords);
 	}
 
 	return len_in_dwords;
@@ -1235,7 +1240,7 @@ void qed_gft_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id)
 	qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id, 0);
 
 	/* Zero ramline */
-	qed_dmae_to_grc(p_hwfn, p_ptt, (u32 *)&ram_line,
+	qed_dmae_to_grc(p_hwfn, p_ptt, &ram_line.lo,
 			PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * pf_id,
 			sizeof(ram_line) / REG_SIZE);
 }
@@ -1247,8 +1252,10 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 		    bool udp,
 		    bool ipv4, bool ipv6, enum gft_profile_type profile_type)
 {
-	u32 reg_val, cam_line, search_non_ip_as_gft;
-	struct regpair ram_line = { };
+	struct regpair ram_line;
+	u32 search_non_ip_as_gft;
+	u32 reg_val, cam_line;
+	u32 lo = 0, hi = 0;
 
 	if (!ipv6 && !ipv4)
 		DP_NOTICE(p_hwfn,
@@ -1319,43 +1326,46 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 	search_non_ip_as_gft = 0;
 
 	/* Tunnel type */
-	SET_FIELD(ram_line.lo, GFT_RAM_LINE_TUNNEL_DST_PORT, 1);
-	SET_FIELD(ram_line.lo, GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL, 1);
+	SET_FIELD(lo, GFT_RAM_LINE_TUNNEL_DST_PORT, 1);
+	SET_FIELD(lo, GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL, 1);
 
 	if (profile_type == GFT_PROFILE_TYPE_4_TUPLE) {
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_DST_IP, 1);
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_SRC_IP, 1);
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_OVER_IP_PROTOCOL, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_ETHERTYPE, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_SRC_PORT, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_DST_PORT, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_DST_IP, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_SRC_IP, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_OVER_IP_PROTOCOL, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_ETHERTYPE, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_SRC_PORT, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_DST_PORT, 1);
 	} else if (profile_type == GFT_PROFILE_TYPE_L4_DST_PORT) {
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_OVER_IP_PROTOCOL, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_ETHERTYPE, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_DST_PORT, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_OVER_IP_PROTOCOL, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_ETHERTYPE, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_DST_PORT, 1);
 	} else if (profile_type == GFT_PROFILE_TYPE_IP_DST_ADDR) {
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_DST_IP, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_ETHERTYPE, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_DST_IP, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_ETHERTYPE, 1);
 	} else if (profile_type == GFT_PROFILE_TYPE_IP_SRC_ADDR) {
-		SET_FIELD(ram_line.hi, GFT_RAM_LINE_SRC_IP, 1);
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_ETHERTYPE, 1);
+		SET_FIELD(hi, GFT_RAM_LINE_SRC_IP, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_ETHERTYPE, 1);
 	} else if (profile_type == GFT_PROFILE_TYPE_TUNNEL_TYPE) {
-		SET_FIELD(ram_line.lo, GFT_RAM_LINE_TUNNEL_ETHERTYPE, 1);
+		SET_FIELD(lo, GFT_RAM_LINE_TUNNEL_ETHERTYPE, 1);
 
 		/* Allow tunneled traffic without inner IP */
 		search_non_ip_as_gft = 1;
 	}
 
+	ram_line.lo = cpu_to_le32(lo);
+	ram_line.hi = cpu_to_le32(hi);
+
 	qed_wr(p_hwfn,
 	       p_ptt, PRS_REG_SEARCH_NON_IP_AS_GFT, search_non_ip_as_gft);
-	qed_dmae_to_grc(p_hwfn, p_ptt, (u32 *)&ram_line,
+	qed_dmae_to_grc(p_hwfn, p_ptt, &ram_line.lo,
 			PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * pf_id,
 			sizeof(ram_line) / REG_SIZE);
 
 	/* Set default profile so that no filter match will happen */
-	ram_line.lo = 0xffffffff;
-	ram_line.hi = 0x3ff;
-	qed_dmae_to_grc(p_hwfn, p_ptt, (u32 *)&ram_line,
+	ram_line.lo = cpu_to_le32(0xffffffff);
+	ram_line.hi = cpu_to_le32(0x3ff);
+	qed_dmae_to_grc(p_hwfn, p_ptt, &ram_line.lo,
 			PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE *
 			PRS_GFT_CAM_LINES_NO_MATCH,
 			sizeof(ram_line) / REG_SIZE);
@@ -1373,7 +1383,7 @@ static u8 qed_calc_cdu_validation_byte(u8 conn_type, u8 region, u32 cid)
 	u8 crc, validation_byte = 0;
 	static u8 crc8_table_valid; /* automatically initialized to 0 */
 	u32 validation_string = 0;
-	u32 data_to_crc;
+	__be32 data_to_crc;
 
 	if (!crc8_table_valid) {
 		crc8_populate_msb(cdu_crc8_table, 0x07);
@@ -1395,10 +1405,9 @@ static u8 qed_calc_cdu_validation_byte(u8 conn_type, u8 region, u32 cid)
 		validation_string |= (conn_type & 0xF);
 
 	/* Convert to big-endian and calculate CRC8 */
-	data_to_crc = be32_to_cpu(validation_string);
-
-	crc = crc8(cdu_crc8_table,
-		   (u8 *)&data_to_crc, sizeof(data_to_crc), CRC8_INIT_VALUE);
+	data_to_crc = cpu_to_be32(validation_string);
+	crc = crc8(cdu_crc8_table, (u8 *)&data_to_crc, sizeof(data_to_crc),
+		   CRC8_INIT_VALUE);
 
 	/* The validation byte [7:0] is composed:
 	 * for type A validation
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 0da38c47a8cf..9be40280eaaa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -1191,16 +1191,15 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn)
 static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn,
 			    void __iomem *igu_addr, u32 ack_cons)
 {
-	struct igu_prod_cons_update igu_ack = { 0 };
+	u32 igu_ack;
 
-	igu_ack.sb_id_and_flags =
-		((ack_cons << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) |
-		 (1 << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) |
-		 (IGU_INT_NOP << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) |
-		 (IGU_SEG_ACCESS_ATTN <<
-		  IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT));
+	igu_ack = ((ack_cons << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) |
+		   (1 << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) |
+		   (IGU_INT_NOP << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) |
+		   (IGU_SEG_ACCESS_ATTN <<
+		    IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT));
 
-	DIRECT_REG_WR(igu_addr, igu_ack.sb_id_and_flags);
+	DIRECT_REG_WR(igu_addr, igu_ack);
 
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
@@ -1414,16 +1413,16 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 			   u8 pf_id, u16 vf_number, u8 vf_valid)
 {
 	struct qed_dev *cdev = p_hwfn->cdev;
-	u32 cau_state;
+	u32 cau_state, params = 0, data = 0;
 	u8 timer_res;
 
 	memset(p_sb_entry, 0, sizeof(*p_sb_entry));
 
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_PF_NUMBER, pf_id);
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_VF_NUMBER, vf_number);
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_VF_VALID, vf_valid);
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_SB_TIMESET0, 0x7F);
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_SB_TIMESET1, 0x7F);
+	SET_FIELD(params, CAU_SB_ENTRY_PF_NUMBER, pf_id);
+	SET_FIELD(params, CAU_SB_ENTRY_VF_NUMBER, vf_number);
+	SET_FIELD(params, CAU_SB_ENTRY_VF_VALID, vf_valid);
+	SET_FIELD(params, CAU_SB_ENTRY_SB_TIMESET0, 0x7F);
+	SET_FIELD(params, CAU_SB_ENTRY_SB_TIMESET1, 0x7F);
 
 	cau_state = CAU_HC_DISABLE_STATE;
 
@@ -1442,7 +1441,8 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 		timer_res = 1;
 	else
 		timer_res = 2;
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
+
+	SET_FIELD(params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
 
 	if (cdev->tx_coalesce_usecs <= 0x7F)
 		timer_res = 0;
@@ -1450,10 +1450,13 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 		timer_res = 1;
 	else
 		timer_res = 2;
-	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
 
-	SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE0, cau_state);
-	SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE1, cau_state);
+	SET_FIELD(params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
+	p_sb_entry->params = cpu_to_le32(params);
+
+	SET_FIELD(data, CAU_SB_ENTRY_STATE0, cau_state);
+	SET_FIELD(data, CAU_SB_ENTRY_STATE1, cau_state);
+	p_sb_entry->data = cpu_to_le32(data);
 }
 
 static void qed_int_cau_conf_pi(struct qed_hwfn *p_hwfn,
@@ -1463,31 +1466,27 @@ static void qed_int_cau_conf_pi(struct qed_hwfn *p_hwfn,
 				enum qed_coalescing_fsm coalescing_fsm,
 				u8 timeset)
 {
-	struct cau_pi_entry pi_entry;
 	u32 sb_offset, pi_offset;
+	u32 prod = 0;
 
 	if (IS_VF(p_hwfn->cdev))
 		return;
 
-	sb_offset = igu_sb_id * PIS_PER_SB_E4;
-	memset(&pi_entry, 0, sizeof(struct cau_pi_entry));
-
-	SET_FIELD(pi_entry.prod, CAU_PI_ENTRY_PI_TIMESET, timeset);
+	SET_FIELD(prod, CAU_PI_ENTRY_PI_TIMESET, timeset);
 	if (coalescing_fsm == QED_COAL_RX_STATE_MACHINE)
-		SET_FIELD(pi_entry.prod, CAU_PI_ENTRY_FSM_SEL, 0);
+		SET_FIELD(prod, CAU_PI_ENTRY_FSM_SEL, 0);
 	else
-		SET_FIELD(pi_entry.prod, CAU_PI_ENTRY_FSM_SEL, 1);
+		SET_FIELD(prod, CAU_PI_ENTRY_FSM_SEL, 1);
 
+	sb_offset = igu_sb_id * PIS_PER_SB_E4;
 	pi_offset = sb_offset + pi_index;
-	if (p_hwfn->hw_init_done) {
+
+	if (p_hwfn->hw_init_done)
 		qed_wr(p_hwfn, p_ptt,
-		       CAU_REG_PI_MEMORY + pi_offset * sizeof(u32),
-		       *((u32 *)&(pi_entry)));
-	} else {
-		STORE_RT_REG(p_hwfn,
-			     CAU_REG_PI_MEMORY_RT_OFFSET + pi_offset,
-			     *((u32 *)&(pi_entry)));
-	}
+		       CAU_REG_PI_MEMORY + pi_offset * sizeof(u32), prod);
+	else
+		STORE_RT_REG(p_hwfn, CAU_REG_PI_MEMORY_RT_OFFSET + pi_offset,
+			     prod);
 }
 
 void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
@@ -2356,6 +2355,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			  u8 timer_res, u16 sb_id, bool tx)
 {
 	struct cau_sb_entry sb_entry;
+	u32 params;
 	int rc;
 
 	if (!p_hwfn->hw_init_done) {
@@ -2371,10 +2371,14 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		return rc;
 	}
 
+	params = le32_to_cpu(sb_entry.params);
+
 	if (tx)
-		SET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
+		SET_FIELD(params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
 	else
-		SET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
+		SET_FIELD(params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
+
+	sb_entry.params = cpu_to_le32(params);
 
 	rc = qed_dmae_host2grc(p_hwfn, p_ptt,
 			       (u64)(uintptr_t)&sb_entry,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 8abb31b63e4e..25d2c882d7ac 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -118,7 +118,7 @@ struct qed_iscsi_conn {
 };
 
 static int qed_iscsi_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
-				 u16 echo, union event_ring_data *data,
+				 __le16 echo, union event_ring_data *data,
 				 u8 fw_return_code)
 {
 	if (p_hwfn->p_iscsi_info->event_cb) {
@@ -270,6 +270,7 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 	dma_addr_t xhq_pbl_addr;
 	dma_addr_t uhq_pbl_addr;
 	u16 physical_q;
+	__le16 tmp;
 	int rc = 0;
 	u32 dval;
 	u16 wval;
@@ -293,12 +294,12 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 
 	/* Transmission PQ is the first of the PF */
 	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-	p_conn->physical_q0 = cpu_to_le16(physical_q);
+	p_conn->physical_q0 = physical_q;
 	p_ramrod->iscsi.physical_q0 = cpu_to_le16(physical_q);
 
 	/* iSCSI Pure-ACK PQ */
 	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK);
-	p_conn->physical_q1 = cpu_to_le16(physical_q);
+	p_conn->physical_q1 = physical_q;
 	p_ramrod->iscsi.physical_q1 = cpu_to_le16(physical_q);
 
 	p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id);
@@ -324,14 +325,20 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 		p_tcp = &p_ramrod->tcp;
 
 		p = (u16 *)p_conn->local_mac;
-		p_tcp->local_mac_addr_hi = swab16(get_unaligned(p));
-		p_tcp->local_mac_addr_mid = swab16(get_unaligned(p + 1));
-		p_tcp->local_mac_addr_lo = swab16(get_unaligned(p + 2));
+		tmp = cpu_to_le16(get_unaligned_be16(p));
+		p_tcp->local_mac_addr_hi = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 1));
+		p_tcp->local_mac_addr_mid = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 2));
+		p_tcp->local_mac_addr_lo = tmp;
 
 		p = (u16 *)p_conn->remote_mac;
-		p_tcp->remote_mac_addr_hi = swab16(get_unaligned(p));
-		p_tcp->remote_mac_addr_mid = swab16(get_unaligned(p + 1));
-		p_tcp->remote_mac_addr_lo = swab16(get_unaligned(p + 2));
+		tmp = cpu_to_le16(get_unaligned_be16(p));
+		p_tcp->remote_mac_addr_hi = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 1));
+		p_tcp->remote_mac_addr_mid = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 2));
+		p_tcp->remote_mac_addr_lo = tmp;
 
 		p_tcp->vlan_id = cpu_to_le16(p_conn->vlan_id);
 
@@ -390,14 +397,20 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 		    &((struct iscsi_spe_conn_offload_option2 *)p_ramrod)->tcp;
 
 		p = (u16 *)p_conn->local_mac;
-		p_tcp2->local_mac_addr_hi = swab16(get_unaligned(p));
-		p_tcp2->local_mac_addr_mid = swab16(get_unaligned(p + 1));
-		p_tcp2->local_mac_addr_lo = swab16(get_unaligned(p + 2));
+		tmp = cpu_to_le16(get_unaligned_be16(p));
+		p_tcp2->local_mac_addr_hi = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 1));
+		p_tcp2->local_mac_addr_mid = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 2));
+		p_tcp2->local_mac_addr_lo = tmp;
 
 		p = (u16 *)p_conn->remote_mac;
-		p_tcp2->remote_mac_addr_hi = swab16(get_unaligned(p));
-		p_tcp2->remote_mac_addr_mid = swab16(get_unaligned(p + 1));
-		p_tcp2->remote_mac_addr_lo = swab16(get_unaligned(p + 2));
+		tmp = cpu_to_le16(get_unaligned_be16(p));
+		p_tcp2->remote_mac_addr_hi = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 1));
+		p_tcp2->remote_mac_addr_mid = tmp;
+		tmp = cpu_to_le16(get_unaligned_be16(p + 2));
+		p_tcp2->remote_mac_addr_lo = tmp;
 
 		p_tcp2->vlan_id = cpu_to_le16(p_conn->vlan_id);
 		p_tcp2->flags = cpu_to_le16(p_conn->tcp_flags);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 55e73a842507..512cbef24097 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -60,7 +60,7 @@ struct mpa_v2_hdr {
 #define QED_IWARP_DEF_KA_INTERVAL	(1000)		/* 1 sec */
 
 static int qed_iwarp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
-				 u16 echo, union event_ring_data *data,
+				 __le16 echo, union event_ring_data *data,
 				 u8 fw_return_code);
 
 /* Override devinfo with iWARP specific values */
@@ -246,14 +246,14 @@ int qed_iwarp_create_qp(struct qed_hwfn *p_hwfn,
 	SET_FIELD(p_ramrod->flags,
 		  IWARP_CREATE_QP_RAMROD_DATA_SRQ_FLG, qp->use_srq);
 
-	p_ramrod->pd = qp->pd;
-	p_ramrod->sq_num_pages = qp->sq_num_pages;
-	p_ramrod->rq_num_pages = qp->rq_num_pages;
+	p_ramrod->pd = cpu_to_le16(qp->pd);
+	p_ramrod->sq_num_pages = cpu_to_le16(qp->sq_num_pages);
+	p_ramrod->rq_num_pages = cpu_to_le16(qp->rq_num_pages);
 
 	p_ramrod->srq_id.srq_idx = cpu_to_le16(qp->srq_id);
 	p_ramrod->srq_id.opaque_fid = cpu_to_le16(p_hwfn->hw_info.opaque_fid);
-	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
-	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
+	p_ramrod->qp_handle_for_cqe.hi = qp->qp_handle.hi;
+	p_ramrod->qp_handle_for_cqe.lo = qp->qp_handle.lo;
 
 	p_ramrod->cq_cid_for_sq =
 	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
@@ -288,6 +288,7 @@ static int qed_iwarp_modify_fw(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 	struct iwarp_modify_qp_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
 	struct qed_spq_entry *p_ent;
+	u16 flags, trans_to_state;
 	int rc;
 
 	/* Get SPQ entry */
@@ -303,12 +304,17 @@ static int qed_iwarp_modify_fw(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 		return rc;
 
 	p_ramrod = &p_ent->ramrod.iwarp_modify_qp;
-	SET_FIELD(p_ramrod->flags, IWARP_MODIFY_QP_RAMROD_DATA_STATE_TRANS_EN,
-		  0x1);
+
+	flags = le16_to_cpu(p_ramrod->flags);
+	SET_FIELD(flags, IWARP_MODIFY_QP_RAMROD_DATA_STATE_TRANS_EN, 0x1);
+	p_ramrod->flags = cpu_to_le16(flags);
+
 	if (qp->iwarp_state == QED_IWARP_QP_STATE_CLOSING)
-		p_ramrod->transition_to_state = IWARP_MODIFY_QP_STATE_CLOSING;
+		trans_to_state = IWARP_MODIFY_QP_STATE_CLOSING;
 	else
-		p_ramrod->transition_to_state = IWARP_MODIFY_QP_STATE_ERROR;
+		trans_to_state = IWARP_MODIFY_QP_STATE_ERROR;
+
+	p_ramrod->transition_to_state = cpu_to_le16(trans_to_state);
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 
@@ -621,6 +627,7 @@ qed_iwarp_tcp_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	dma_addr_t async_output_phys;
 	dma_addr_t in_pdata_phys;
 	u16 physical_q;
+	u16 flags = 0;
 	u8 tcp_flags;
 	int rc;
 	int i;
@@ -673,13 +680,14 @@ qed_iwarp_tcp_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	tcp->vlan_id = cpu_to_le16(ep->cm_info.vlan);
 
 	tcp_flags = p_hwfn->p_rdma_info->iwarp.tcp_flags;
-	tcp->flags = 0;
-	SET_FIELD(tcp->flags, TCP_OFFLOAD_PARAMS_OPT2_TS_EN,
+
+	SET_FIELD(flags, TCP_OFFLOAD_PARAMS_OPT2_TS_EN,
 		  !!(tcp_flags & QED_IWARP_TS_EN));
 
-	SET_FIELD(tcp->flags, TCP_OFFLOAD_PARAMS_OPT2_DA_EN,
+	SET_FIELD(flags, TCP_OFFLOAD_PARAMS_OPT2_DA_EN,
 		  !!(tcp_flags & QED_IWARP_DA_EN));
 
+	tcp->flags = cpu_to_le16(flags);
 	tcp->ip_version = ep->cm_info.ip_version;
 
 	for (i = 0; i < 4; i++) {
@@ -695,10 +703,10 @@ qed_iwarp_tcp_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	tcp->tos_or_tc = 0;
 
 	tcp->max_rt_time = QED_IWARP_DEF_MAX_RT_TIME;
-	tcp->cwnd = QED_IWARP_DEF_CWND_FACTOR *  tcp->mss;
+	tcp->cwnd = cpu_to_le32(QED_IWARP_DEF_CWND_FACTOR * ep->mss);
 	tcp->ka_max_probe_cnt = QED_IWARP_DEF_KA_MAX_PROBE_CNT;
-	tcp->ka_timeout = QED_IWARP_DEF_KA_TIMEOUT;
-	tcp->ka_interval = QED_IWARP_DEF_KA_INTERVAL;
+	tcp->ka_timeout = cpu_to_le32(QED_IWARP_DEF_KA_TIMEOUT);
+	tcp->ka_interval = cpu_to_le32(QED_IWARP_DEF_KA_INTERVAL);
 
 	tcp->rcv_wnd_scale = (u8)p_hwfn->p_rdma_info->iwarp.rcv_wnd_scale;
 	tcp->connect_mode = ep->connect_mode;
@@ -729,6 +737,7 @@ qed_iwarp_mpa_received(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	union async_output *async_data;
 	u16 mpa_ord, mpa_ird;
 	u8 mpa_hdr_size = 0;
+	u16 ulp_data_len;
 	u8 mpa_rev;
 
 	async_data = &ep->ep_buffer_virt->async_output;
@@ -792,8 +801,8 @@ qed_iwarp_mpa_received(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	/* Strip mpa v2 hdr from private data before sending to upper layer */
 	ep->cm_info.private_data = ep->ep_buffer_virt->in_pdata + mpa_hdr_size;
 
-	ep->cm_info.private_data_len = async_data->mpa_request.ulp_data_len -
-				       mpa_hdr_size;
+	ulp_data_len = le16_to_cpu(async_data->mpa_request.ulp_data_len);
+	ep->cm_info.private_data_len = ulp_data_len - mpa_hdr_size;
 
 	params.event = QED_IWARP_EVENT_MPA_REQUEST;
 	params.cm_info = &ep->cm_info;
@@ -817,6 +826,7 @@ qed_iwarp_mpa_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	dma_addr_t in_pdata_phys;
 	struct qed_rdma_qp *qp;
 	bool reject;
+	u32 val;
 	int rc;
 
 	if (!ep)
@@ -847,13 +857,15 @@ qed_iwarp_mpa_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 			 offsetof(struct qed_iwarp_ep_memory, out_pdata);
 	DMA_REGPAIR_LE(common->outgoing_ulp_buffer.addr, out_pdata_phys);
 
-	common->outgoing_ulp_buffer.len = ep->cm_info.private_data_len;
+	val = ep->cm_info.private_data_len;
+	common->outgoing_ulp_buffer.len = cpu_to_le16(val);
 	common->crc_needed = p_hwfn->p_rdma_info->iwarp.crc_needed;
 
-	common->out_rq.ord = ep->cm_info.ord;
-	common->out_rq.ird = ep->cm_info.ird;
+	common->out_rq.ord = cpu_to_le32(ep->cm_info.ord);
+	common->out_rq.ird = cpu_to_le32(ep->cm_info.ird);
 
-	p_mpa_ramrod->tcp_cid = p_hwfn->hw_info.opaque_fid << 16 | ep->tcp_cid;
+	val = p_hwfn->hw_info.opaque_fid << 16 | ep->tcp_cid;
+	p_mpa_ramrod->tcp_cid = cpu_to_le32(val);
 
 	in_pdata_phys = ep->ep_buffer_phys +
 			offsetof(struct qed_iwarp_ep_memory, in_pdata);
@@ -879,7 +891,7 @@ qed_iwarp_mpa_offload(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	}
 
 	iwarp_info = &p_hwfn->p_rdma_info->iwarp;
-	p_mpa_ramrod->rcv_wnd = iwarp_info->rcv_wnd_size;
+	p_mpa_ramrod->rcv_wnd = cpu_to_le16(iwarp_info->rcv_wnd_size);
 	p_mpa_ramrod->mode = ep->mpa_rev;
 	SET_FIELD(p_mpa_ramrod->rtr_pref,
 		  IWARP_MPA_OFFLOAD_RAMROD_DATA_RTR_SUPPORTED, ep->rtr_type);
@@ -930,6 +942,7 @@ qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	union async_output *async_data;
 	u16 mpa_ird, mpa_ord;
 	u8 mpa_data_size = 0;
+	u16 ulp_data_len;
 
 	if (MPA_REV2(p_hwfn->p_rdma_info->iwarp.mpa_rev)) {
 		mpa_v2_params =
@@ -941,11 +954,12 @@ qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 		ep->cm_info.ird = (u8)(mpa_ord & MPA_V2_IRD_ORD_MASK);
 		ep->cm_info.ord = (u8)(mpa_ird & MPA_V2_IRD_ORD_MASK);
 	}
-	async_data = &ep->ep_buffer_virt->async_output;
 
+	async_data = &ep->ep_buffer_virt->async_output;
 	ep->cm_info.private_data = ep->ep_buffer_virt->in_pdata + mpa_data_size;
-	ep->cm_info.private_data_len = async_data->mpa_response.ulp_data_len -
-				       mpa_data_size;
+
+	ulp_data_len = le16_to_cpu(async_data->mpa_response.ulp_data_len);
+	ep->cm_info.private_data_len = ulp_data_len - mpa_data_size;
 }
 
 static void
@@ -1822,7 +1836,7 @@ qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn,
 		goto out;
 	}
 
-	mpa_len = ntohs(*((u16 *)(mpa_data)));
+	mpa_len = ntohs(*(__force __be16 *)mpa_data);
 	fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len);
 
 	if (fpdu->fpdu_length <= tcp_payload_len)
@@ -1844,11 +1858,13 @@ qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf,
 		    struct unaligned_opaque_data *pkt_data,
 		    u16 tcp_payload_size, u8 placement_offset)
 {
+	u16 first_mpa_offset = le16_to_cpu(pkt_data->first_mpa_offset);
+
 	fpdu->mpa_buf = buf;
 	fpdu->pkt_hdr = buf->data_phys_addr + placement_offset;
 	fpdu->pkt_hdr_size = pkt_data->tcp_payload_offset;
-	fpdu->mpa_frag = buf->data_phys_addr + pkt_data->first_mpa_offset;
-	fpdu->mpa_frag_virt = (u8 *)(buf->data) + pkt_data->first_mpa_offset;
+	fpdu->mpa_frag = buf->data_phys_addr + first_mpa_offset;
+	fpdu->mpa_frag_virt = (u8 *)(buf->data) + first_mpa_offset;
 
 	if (tcp_payload_size == 1)
 		fpdu->incomplete_bytes = QED_IWARP_INVALID_FPDU_LENGTH;
@@ -1866,6 +1882,7 @@ qed_iwarp_cp_pkt(struct qed_hwfn *p_hwfn,
 		 struct unaligned_opaque_data *pkt_data,
 		 struct qed_iwarp_ll2_buff *buf, u16 tcp_payload_size)
 {
+	u16 first_mpa_offset = le16_to_cpu(pkt_data->first_mpa_offset);
 	u8 *tmp_buf = p_hwfn->p_rdma_info->iwarp.mpa_intermediate_buf;
 	int rc;
 
@@ -1886,13 +1903,11 @@ qed_iwarp_cp_pkt(struct qed_hwfn *p_hwfn,
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 		   "MPA ALIGN Copying fpdu: [%p, %d] [%p, %d]\n",
 		   fpdu->mpa_frag_virt, fpdu->mpa_frag_len,
-		   (u8 *)(buf->data) + pkt_data->first_mpa_offset,
-		   tcp_payload_size);
+		   (u8 *)(buf->data) + first_mpa_offset, tcp_payload_size);
 
 	memcpy(tmp_buf, fpdu->mpa_frag_virt, fpdu->mpa_frag_len);
 	memcpy(tmp_buf + fpdu->mpa_frag_len,
-	       (u8 *)(buf->data) + pkt_data->first_mpa_offset,
-	       tcp_payload_size);
+	       (u8 *)(buf->data) + first_mpa_offset, tcp_payload_size);
 
 	rc = qed_iwarp_recycle_pkt(p_hwfn, fpdu, fpdu->mpa_buf);
 	if (rc)
@@ -2035,6 +2050,7 @@ qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn,
 		    u16 tcp_payload_size, enum qed_iwarp_mpa_pkt_type pkt_type)
 {
 	struct qed_ll2_tx_pkt_info tx_pkt;
+	u16 first_mpa_offset;
 	u8 ll2_handle;
 	int rc;
 
@@ -2086,11 +2102,13 @@ qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn,
 	if (!fpdu->incomplete_bytes)
 		goto out;
 
+	first_mpa_offset = le16_to_cpu(curr_pkt->first_mpa_offset);
+
 	/* Set third fragment to second part of the packet */
 	rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn,
 					       ll2_handle,
 					       buf->data_phys_addr +
-					       curr_pkt->first_mpa_offset,
+					       first_mpa_offset,
 					       fpdu->incomplete_bytes);
 out:
 	DP_VERBOSE(p_hwfn,
@@ -2111,12 +2129,12 @@ qed_iwarp_mpa_get_data(struct qed_hwfn *p_hwfn,
 {
 	u64 opaque_data;
 
-	opaque_data = HILO_64(opaque_data1, opaque_data0);
+	opaque_data = HILO_64(cpu_to_le32(opaque_data1),
+			      cpu_to_le32(opaque_data0));
 	*curr_pkt = *((struct unaligned_opaque_data *)&opaque_data);
 
-	curr_pkt->first_mpa_offset = curr_pkt->tcp_payload_offset +
-				     le16_to_cpu(curr_pkt->first_mpa_offset);
-	curr_pkt->cid = le32_to_cpu(curr_pkt->cid);
+	le16_add_cpu(&curr_pkt->first_mpa_offset,
+		     curr_pkt->tcp_payload_offset);
 }
 
 /* This function is called when an unaligned or incomplete MPA packet arrives
@@ -2131,18 +2149,22 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn,
 	struct qed_iwarp_ll2_buff *buf = mpa_buf->ll2_buf;
 	enum qed_iwarp_mpa_pkt_type pkt_type;
 	struct qed_iwarp_fpdu *fpdu;
+	u16 cid, first_mpa_offset;
 	int rc = -EINVAL;
 	u8 *mpa_data;
 
-	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, curr_pkt->cid & 0xffff);
+	cid = le32_to_cpu(curr_pkt->cid);
+
+	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)cid);
 	if (!fpdu) { /* something corrupt with cid, post rx back */
 		DP_ERR(p_hwfn, "Invalid cid, drop and post back to rx cid=%x\n",
-		       curr_pkt->cid);
+		       cid);
 		goto err;
 	}
 
 	do {
-		mpa_data = ((u8 *)(buf->data) + curr_pkt->first_mpa_offset);
+		first_mpa_offset = le16_to_cpu(curr_pkt->first_mpa_offset);
+		mpa_data = ((u8 *)(buf->data) + first_mpa_offset);
 
 		pkt_type = qed_iwarp_mpa_classify(p_hwfn, fpdu,
 						  mpa_buf->tcp_payload_len,
@@ -2188,7 +2210,8 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn,
 			}
 
 			mpa_buf->tcp_payload_len -= fpdu->fpdu_length;
-			curr_pkt->first_mpa_offset += fpdu->fpdu_length;
+			le16_add_cpu(&curr_pkt->first_mpa_offset,
+				     fpdu->fpdu_length);
 			break;
 		case QED_IWARP_MPA_PKT_UNALIGNED:
 			qed_iwarp_update_fpdu_length(p_hwfn, fpdu, mpa_data);
@@ -2227,7 +2250,9 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn,
 			}
 
 			mpa_buf->tcp_payload_len -= fpdu->incomplete_bytes;
-			curr_pkt->first_mpa_offset += fpdu->incomplete_bytes;
+			le16_add_cpu(&curr_pkt->first_mpa_offset,
+				     fpdu->incomplete_bytes);
+
 			/* The framed PDU was sent - no more incomplete bytes */
 			fpdu->incomplete_bytes = 0;
 			break;
@@ -2278,6 +2303,7 @@ qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
 	struct qed_iwarp_ll2_mpa_buf *mpa_buf;
 	struct qed_iwarp_info *iwarp_info;
 	struct qed_hwfn *p_hwfn = cxt;
+	u16 first_mpa_offset;
 
 	iwarp_info = &p_hwfn->p_rdma_info->iwarp;
 	mpa_buf = list_first_entry(&iwarp_info->mpa_buf_list,
@@ -2291,17 +2317,21 @@ qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
 	qed_iwarp_mpa_get_data(p_hwfn, &mpa_buf->data,
 			       data->opaque_data_0, data->opaque_data_1);
 
+	first_mpa_offset = le16_to_cpu(mpa_buf->data.first_mpa_offset);
+
 	DP_VERBOSE(p_hwfn,
 		   QED_MSG_RDMA,
 		   "LL2 MPA CompRx payload_len:0x%x\tfirst_mpa_offset:0x%x\ttcp_payload_offset:0x%x\tflags:0x%x\tcid:0x%x\n",
-		   data->length.packet_length, mpa_buf->data.first_mpa_offset,
+		   data->length.packet_length, first_mpa_offset,
 		   mpa_buf->data.tcp_payload_offset, mpa_buf->data.flags,
 		   mpa_buf->data.cid);
 
 	mpa_buf->ll2_buf = data->cookie;
 	mpa_buf->tcp_payload_len = data->length.packet_length -
-				   mpa_buf->data.first_mpa_offset;
-	mpa_buf->data.first_mpa_offset += data->u.placement_offset;
+				   first_mpa_offset;
+
+	first_mpa_offset += data->u.placement_offset;
+	mpa_buf->data.first_mpa_offset = cpu_to_le16(first_mpa_offset);
 	mpa_buf->placement_offset = data->u.placement_offset;
 
 	list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_pending_list);
@@ -2500,14 +2530,16 @@ qed_iwarp_ll2_slowpath(void *cxt,
 	struct unaligned_opaque_data unalign_data;
 	struct qed_hwfn *p_hwfn = cxt;
 	struct qed_iwarp_fpdu *fpdu;
+	u32 cid;
 
 	qed_iwarp_mpa_get_data(p_hwfn, &unalign_data,
 			       opaque_data_0, opaque_data_1);
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "(0x%x) Flush fpdu\n",
-		   unalign_data.cid);
+	cid = le32_to_cpu(unalign_data.cid);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "(0x%x) Flush fpdu\n", cid);
 
-	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)unalign_data.cid);
+	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)cid);
 	if (fpdu)
 		memset(fpdu, 0, sizeof(*fpdu));
 }
@@ -3010,7 +3042,7 @@ qed_iwarp_check_ep_ok(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 }
 
 static int qed_iwarp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
-				 u16 echo, union event_ring_data *data,
+				 __le16 echo, union event_ring_data *data,
 				 u8 fw_return_code)
 {
 	struct qed_rdma_events events = p_hwfn->p_rdma_info->events;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 41afd15f4991..4c6ac8862744 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -345,8 +345,8 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn,
 	struct eth_vport_tpa_param *tpa_param;
 	struct qed_spq_entry *p_ent =  NULL;
 	struct qed_sp_init_data init_data;
+	u16 min_size, rx_mode = 0;
 	u8 abs_vport_id = 0;
-	u16 rx_mode = 0;
 	int rc;
 
 	rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id);
@@ -386,10 +386,12 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn,
 
 	switch (p_params->tpa_mode) {
 	case QED_TPA_MODE_GRO:
+		min_size = p_params->mtu / 2;
+
 		tpa_param->tpa_max_aggs_num = ETH_TPA_MAX_AGGS_NUM;
-		tpa_param->tpa_max_size = (u16)-1;
-		tpa_param->tpa_min_size_to_cont = p_params->mtu / 2;
-		tpa_param->tpa_min_size_to_start = p_params->mtu / 2;
+		tpa_param->tpa_max_size = cpu_to_le16(U16_MAX);
+		tpa_param->tpa_min_size_to_cont = cpu_to_le16(min_size);
+		tpa_param->tpa_min_size_to_start = cpu_to_le16(min_size);
 		tpa_param->tpa_ipv4_en_flg = 1;
 		tpa_param->tpa_ipv6_en_flg = 1;
 		tpa_param->tpa_pkt_split_flg = 1;
@@ -626,9 +628,9 @@ qed_sp_vport_update_sge_tpa(struct qed_hwfn *p_hwfn,
 	tpa->tpa_hdr_data_split_flg = param->tpa_hdr_data_split_flg;
 	tpa->tpa_gro_consistent_flg = param->tpa_gro_consistent_flg;
 	tpa->tpa_max_aggs_num = param->tpa_max_aggs_num;
-	tpa->tpa_max_size = param->tpa_max_size;
-	tpa->tpa_min_size_to_start = param->tpa_min_size_to_start;
-	tpa->tpa_min_size_to_cont = param->tpa_min_size_to_cont;
+	tpa->tpa_max_size = cpu_to_le16(param->tpa_max_size);
+	tpa->tpa_min_size_to_start = cpu_to_le16(param->tpa_min_size_to_start);
+	tpa->tpa_min_size_to_cont = cpu_to_le16(param->tpa_min_size_to_cont);
 }
 
 static void
@@ -2090,7 +2092,8 @@ int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn,
 		return rc;
 	}
 
-	timer_res = GET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES0);
+	timer_res = GET_FIELD(le32_to_cpu(sb_entry.params),
+			      CAU_SB_ENTRY_TIMER_RES0);
 
 	address = BAR0_MAP_REG_USDM_RAM +
 		  USTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id);
@@ -2123,7 +2126,8 @@ int qed_get_txq_coalesce(struct qed_hwfn *p_hwfn,
 		return rc;
 	}
 
-	timer_res = GET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES1);
+	timer_res = GET_FIELD(le32_to_cpu(sb_entry.params),
+			      CAU_SB_ENTRY_TIMER_RES1);
 
 	address = BAR0_MAP_REG_XSDM_RAM +
 		  XSTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index cce6fd27c042..6f4aec339cd4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1798,6 +1798,7 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 	enum core_roce_flavor_type roce_flavor;
 	enum core_tx_dest tx_dest;
 	u16 bd_data = 0, frag_idx;
+	u16 bitfield1;
 
 	roce_flavor = (pkt->qed_roce_flavor == QED_LL2_ROCE) ? CORE_ROCE
 							     : CORE_RROCE;
@@ -1829,9 +1830,11 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 			pkt->remove_stag = true;
 	}
 
-	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
-		  cpu_to_le16(pkt->l4_hdr_offset_w));
-	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
+	bitfield1 = le16_to_cpu(start_bd->bitfield1);
+	SET_FIELD(bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, pkt->l4_hdr_offset_w);
+	SET_FIELD(bitfield1, CORE_TX_BD_TX_DST, tx_dest);
+	start_bd->bitfield1 = cpu_to_le16(bitfield1);
+
 	bd_data |= pkt->bd_flags;
 	SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1);
 	SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, pkt->num_of_bds);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 236013da9453..4c5f5bd91359 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1962,8 +1962,7 @@ static u32 qed_nvm_flash_image_access_crc(struct qed_dev *cdev,
 					  u32 *crc)
 {
 	u8 *buf = NULL;
-	int rc, j;
-	u32 val;
+	int rc;
 
 	/* Allocate a buffer for holding the nvram image */
 	buf = kzalloc(nvm_image->length, GFP_KERNEL);
@@ -1981,15 +1980,14 @@ static u32 qed_nvm_flash_image_access_crc(struct qed_dev *cdev,
 	/* Convert the buffer into big-endian format (excluding the
 	 * closing 4 bytes of CRC).
 	 */
-	for (j = 0; j < nvm_image->length - 4; j += 4) {
-		val = cpu_to_be32(*(u32 *)&buf[j]);
-		*(u32 *)&buf[j] = val;
-	}
+	cpu_to_be32_array((__force __be32 *)buf, (const u32 *)buf,
+			  DIV_ROUND_UP(nvm_image->length - 4, 4));
 
 	/* Calc CRC for the "actual" image buffer, i.e. not including
 	 * the last 4 CRC bytes.
 	 */
-	*crc = (~cpu_to_be32(crc32(0xffffffff, buf, nvm_image->length - 4)));
+	*crc = ~crc32(~0U, buf, nvm_image->length - 4);
+	*crc = (__force u32)cpu_to_be32p(crc);
 
 out:
 	kfree(buf);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index 1dd01e0373ab..3e3192a3ad9b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -1276,7 +1276,7 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	 */
 	for (offset = 0; offset < size; offset += sizeof(u32)) {
 		val = qed_rd(p_hwfn, p_ptt, addr + offset);
-		val = be32_to_cpu(val);
+		val = be32_to_cpu((__force __be32)val);
 		memcpy(&p_mfw_buf[offset], &val, sizeof(u32));
 	}
 
@@ -1325,7 +1325,7 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	 */
 	for (offset = 0; offset < size; offset += sizeof(u32)) {
 		memcpy(&val, &p_mfw_buf[offset], sizeof(u32));
-		val = cpu_to_be32(val);
+		val = (__force u32)cpu_to_be32(val);
 		qed_wr(p_hwfn, p_ptt, addr + offset, val);
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 59d916693654..e5648ca2838b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1106,7 +1106,7 @@ static int qed_rdma_create_cq(void *rdma_cxt,
 	p_ramrod->pbl_num_pages = cpu_to_le16(params->pbl_num_pages);
 	p_ramrod->cnq_id = (u8)RESC_START(p_hwfn, QED_RDMA_CNQ_RAM) +
 			   params->cnq_id;
-	p_ramrod->int_timeout = params->int_timeout;
+	p_ramrod->int_timeout = cpu_to_le16(params->int_timeout);
 
 	/* toggle the bit for every resize or create cq for a given icid */
 	toggle_bit = qed_rdma_toggle_bit_create_resize_cq(p_hwfn, *icid);
@@ -1206,7 +1206,7 @@ err:	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
 	return rc;
 }
 
-void qed_rdma_set_fw_mac(u16 *p_fw_mac, u8 *p_qed_mac)
+void qed_rdma_set_fw_mac(__le16 *p_fw_mac, const u8 *p_qed_mac)
 {
 	p_fw_mac[0] = cpu_to_le16((p_qed_mac[0] << 8) + p_qed_mac[1]);
 	p_fw_mac[1] = cpu_to_le16((p_qed_mac[2] << 8) + p_qed_mac[3]);
@@ -1495,6 +1495,7 @@ qed_rdma_register_tid(void *rdma_cxt,
 	struct qed_spq_entry *p_ent;
 	enum rdma_tid_type tid_type;
 	u8 fw_return_code;
+	u16 flags = 0;
 	int rc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", params->itid);
@@ -1514,54 +1515,46 @@ qed_rdma_register_tid(void *rdma_cxt,
 	if (p_hwfn->p_rdma_info->last_tid < params->itid)
 		p_hwfn->p_rdma_info->last_tid = params->itid;
 
-	p_ramrod = &p_ent->ramrod.rdma_register_tid;
-
-	p_ramrod->flags = 0;
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_TWO_LEVEL_PBL,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_TWO_LEVEL_PBL,
 		  params->pbl_two_level);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_ZERO_BASED, params->zbva);
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_ZERO_BASED,
+		  params->zbva);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_PHY_MR, params->phy_mr);
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_PHY_MR, params->phy_mr);
 
 	/* Don't initialize D/C field, as it may override other bits. */
 	if (!(params->tid_type == QED_RDMA_TID_FMR) && !(params->dma_mr))
-		SET_FIELD(p_ramrod->flags,
-			  RDMA_REGISTER_TID_RAMROD_DATA_PAGE_SIZE_LOG,
+		SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_PAGE_SIZE_LOG,
 			  params->page_size_log - 12);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_READ,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_READ,
 		  params->remote_read);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_WRITE,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_WRITE,
 		  params->remote_write);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_ATOMIC,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_REMOTE_ATOMIC,
 		  params->remote_atomic);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_LOCAL_WRITE,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_LOCAL_WRITE,
 		  params->local_write);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_LOCAL_READ, params->local_read);
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_LOCAL_READ,
+		  params->local_read);
 
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_REGISTER_TID_RAMROD_DATA_ENABLE_MW_BIND,
+	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_ENABLE_MW_BIND,
 		  params->mw_bind);
 
+	p_ramrod = &p_ent->ramrod.rdma_register_tid;
+	p_ramrod->flags = cpu_to_le16(flags);
+
 	SET_FIELD(p_ramrod->flags1,
 		  RDMA_REGISTER_TID_RAMROD_DATA_PBL_PAGE_SIZE_LOG,
 		  params->pbl_page_size_log - 12);
 
-	SET_FIELD(p_ramrod->flags2,
-		  RDMA_REGISTER_TID_RAMROD_DATA_DMA_MR, params->dma_mr);
+	SET_FIELD(p_ramrod->flags2, RDMA_REGISTER_TID_RAMROD_DATA_DMA_MR,
+		  params->dma_mr);
 
 	switch (params->tid_type) {
 	case QED_RDMA_TID_REGISTERED_MR:
@@ -1579,8 +1572,9 @@ qed_rdma_register_tid(void *rdma_cxt,
 		qed_sp_destroy_request(p_hwfn, p_ent);
 		return rc;
 	}
-	SET_FIELD(p_ramrod->flags1,
-		  RDMA_REGISTER_TID_RAMROD_DATA_TID_TYPE, tid_type);
+
+	SET_FIELD(p_ramrod->flags1, RDMA_REGISTER_TID_RAMROD_DATA_TID_TYPE,
+		  tid_type);
 
 	p_ramrod->itid = cpu_to_le32(params->itid);
 	p_ramrod->key = params->key;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index fba43adbb68e..6a1de3a25257 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -201,7 +201,7 @@ qed_bmap_release_id(struct qed_hwfn *p_hwfn, struct qed_bmap *bmap, u32 id_num);
 int
 qed_bmap_test_id(struct qed_hwfn *p_hwfn, struct qed_bmap *bmap, u32 id_num);
 
-void qed_rdma_set_fw_mac(u16 *p_fw_mac, u8 *p_qed_mac);
+void qed_rdma_set_fw_mac(__le16 *p_fw_mac, const u8 *p_qed_mac);
 
 bool qed_rdma_allocated_qps(struct qed_hwfn *p_hwfn);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 5433e43a1930..a1423ec0edf7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -38,7 +38,7 @@
 static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid);
 
 static int qed_roce_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
-				u16 echo, union event_ring_data *data,
+				__le16 echo, union event_ring_data *data,
 				u8 fw_return_code)
 {
 	struct qed_rdma_events events = p_hwfn->p_rdma_info->events;
@@ -54,7 +54,7 @@ static int qed_roce_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
 		qed_roce_free_real_icid(p_hwfn, icid);
 	} else if (fw_event_code == ROCE_ASYNC_EVENT_SRQ_EMPTY ||
 		   fw_event_code == ROCE_ASYNC_EVENT_SRQ_LIMIT) {
-		u16 srq_id = (u16)rdata->async_handle.lo;
+		u16 srq_id = (u16)le32_to_cpu(rdata->async_handle.lo);
 
 		events.affiliated_event(events.context, fw_event_code,
 					&srq_id);
@@ -217,9 +217,9 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
 	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
-	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
 	enum protocol_type proto;
+	u32 flags = 0;
 	int rc;
 	u8 tc;
 
@@ -252,45 +252,34 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto err;
 
-	p_ramrod = &p_ent->ramrod.roce_create_qp_resp;
-
-	p_ramrod->flags = 0;
-
-	roce_flavor = qed_roce_mode_to_flavor(qp->roce_mode);
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_ROCE_FLAVOR, roce_flavor);
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_ROCE_FLAVOR,
+		  qed_roce_mode_to_flavor(qp->roce_mode));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_RDMA_RD_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_RDMA_RD_EN,
 		  qp->incoming_rdma_read_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_RDMA_WR_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_RDMA_WR_EN,
 		  qp->incoming_rdma_write_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_ATOMIC_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_ATOMIC_EN,
 		  qp->incoming_atomic_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_E2E_FLOW_CONTROL_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_E2E_FLOW_CONTROL_EN,
 		  qp->e2e_flow_control_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_SRQ_FLG, qp->use_srq);
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_SRQ_FLG, qp->use_srq);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_KEY_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_KEY_EN,
 		  qp->fmr_and_reserved_lkey);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER,
 		  qp->min_rnr_nak_timer);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_XRC_FLAG,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_XRC_FLAG,
 		  qed_rdma_is_xrc_qp(qp));
 
+	p_ramrod = &p_ent->ramrod.roce_create_qp_resp;
+	p_ramrod->flags = cpu_to_le32(flags);
 	p_ramrod->max_ird = qp->max_rd_atomic_resp;
 	p_ramrod->traffic_class = qp->traffic_class_tos;
 	p_ramrod->hop_limit = qp->hop_limit_ttl;
@@ -305,10 +294,10 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	DMA_REGPAIR_LE(p_ramrod->rq_pbl_addr, qp->rq_pbl_ptr);
 	DMA_REGPAIR_LE(p_ramrod->irq_pbl_addr, qp->irq_phys_addr);
 	qed_rdma_copy_gids(qp, p_ramrod->src_gid, p_ramrod->dst_gid);
-	p_ramrod->qp_handle_for_async.hi = cpu_to_le32(qp->qp_handle_async.hi);
-	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
-	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
-	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
+	p_ramrod->qp_handle_for_async.hi = qp->qp_handle_async.hi;
+	p_ramrod->qp_handle_for_async.lo = qp->qp_handle_async.lo;
+	p_ramrod->qp_handle_for_cqe.hi = qp->qp_handle.hi;
+	p_ramrod->qp_handle_for_cqe.lo = qp->qp_handle.lo;
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 	p_ramrod->xrc_domain = cpu_to_le16(qp->xrcd_id);
@@ -330,7 +319,7 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
 	qed_rdma_set_fw_mac(p_ramrod->local_mac_addr, qp->local_mac_addr);
 
-	p_ramrod->udp_src_port = qp->udp_src_port;
+	p_ramrod->udp_src_port = cpu_to_le16(qp->udp_src_port);
 	p_ramrod->vlan_id = cpu_to_le16(qp->vlan_id);
 	p_ramrod->srq_id.srq_idx = cpu_to_le16(qp->srq_id);
 	p_ramrod->srq_id.opaque_fid = cpu_to_le16(p_hwfn->hw_info.opaque_fid);
@@ -366,9 +355,9 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
 	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
-	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
 	enum protocol_type proto;
+	u16 flags = 0;
 	int rc;
 	u8 tc;
 
@@ -402,34 +391,29 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto err;
 
-	p_ramrod = &p_ent->ramrod.roce_create_qp_req;
-
-	p_ramrod->flags = 0;
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_ROCE_FLAVOR,
+		  qed_roce_mode_to_flavor(qp->roce_mode));
 
-	roce_flavor = qed_roce_mode_to_flavor(qp->roce_mode);
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_ROCE_FLAVOR, roce_flavor);
-
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_FMR_AND_RESERVED_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_FMR_AND_RESERVED_EN,
 		  qp->fmr_and_reserved_lkey);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_SIGNALED_COMP, qp->signal_all);
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_SIGNALED_COMP,
+		  qp->signal_all);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT, qp->retry_cnt);
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT,
+		  qp->retry_cnt);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_RNR_NAK_CNT,
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_RNR_NAK_CNT,
 		  qp->rnr_retry_cnt);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_XRC_FLAG,
+	SET_FIELD(flags, ROCE_CREATE_QP_REQ_RAMROD_DATA_XRC_FLAG,
 		  qed_rdma_is_xrc_qp(qp));
 
-	SET_FIELD(p_ramrod->flags2,
-		  ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE, qp->edpm_mode);
+	p_ramrod = &p_ent->ramrod.roce_create_qp_req;
+	p_ramrod->flags = cpu_to_le16(flags);
+
+	SET_FIELD(p_ramrod->flags2, ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE,
+		  qp->edpm_mode);
 
 	p_ramrod->max_ord = qp->max_rd_atomic_req;
 	p_ramrod->traffic_class = qp->traffic_class_tos;
@@ -446,10 +430,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	DMA_REGPAIR_LE(p_ramrod->sq_pbl_addr, qp->sq_pbl_ptr);
 	DMA_REGPAIR_LE(p_ramrod->orq_pbl_addr, qp->orq_phys_addr);
 	qed_rdma_copy_gids(qp, p_ramrod->src_gid, p_ramrod->dst_gid);
-	p_ramrod->qp_handle_for_async.hi = cpu_to_le32(qp->qp_handle_async.hi);
-	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
-	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
-	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
+	p_ramrod->qp_handle_for_async.hi = qp->qp_handle_async.hi;
+	p_ramrod->qp_handle_for_async.lo = qp->qp_handle_async.lo;
+	p_ramrod->qp_handle_for_cqe.hi = qp->qp_handle.hi;
+	p_ramrod->qp_handle_for_cqe.lo = qp->qp_handle.lo;
 	p_ramrod->cq_cid =
 	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
 
@@ -470,7 +454,7 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
 	qed_rdma_set_fw_mac(p_ramrod->local_mac_addr, qp->local_mac_addr);
 
-	p_ramrod->udp_src_port = qp->udp_src_port;
+	p_ramrod->udp_src_port = cpu_to_le16(qp->udp_src_port);
 	p_ramrod->vlan_id = cpu_to_le16(qp->vlan_id);
 	p_ramrod->stats_counter_id = RESC_START(p_hwfn, QED_RDMA_STATS_QUEUE) +
 				     qp->stats_queue;
@@ -502,6 +486,7 @@ static int qed_roce_sp_modify_responder(struct qed_hwfn *p_hwfn,
 	struct roce_modify_qp_resp_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
 	struct qed_spq_entry *p_ent;
+	u16 flags = 0;
 	int rc;
 
 	if (!qp->has_resp)
@@ -526,53 +511,43 @@ static int qed_roce_sp_modify_responder(struct qed_hwfn *p_hwfn,
 		return rc;
 	}
 
-	p_ramrod = &p_ent->ramrod.roce_modify_qp_resp;
-
-	p_ramrod->flags = 0;
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_MOVE_TO_ERR_FLG,
+		  !!move_to_err);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_MOVE_TO_ERR_FLG, move_to_err);
-
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_RD_EN,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_RD_EN,
 		  qp->incoming_rdma_read_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_WR_EN,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_WR_EN,
 		  qp->incoming_rdma_write_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_ATOMIC_EN,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_ATOMIC_EN,
 		  qp->incoming_atomic_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_CREATE_QP_RESP_RAMROD_DATA_E2E_FLOW_CONTROL_EN,
+	SET_FIELD(flags, ROCE_CREATE_QP_RESP_RAMROD_DATA_E2E_FLOW_CONTROL_EN,
 		  qp->e2e_flow_control_en);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_OPS_EN_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_OPS_EN_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_RDMA_MODIFY_QP_VALID_RDMA_OPS_EN));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_P_KEY_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_P_KEY_FLG,
 		  GET_FIELD(modify_flags, QED_ROCE_MODIFY_QP_VALID_PKEY));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_ADDRESS_VECTOR_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_ADDRESS_VECTOR_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_ROCE_MODIFY_QP_VALID_ADDRESS_VECTOR));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_MAX_IRD_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_MAX_IRD_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_RESP));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_ROCE_MODIFY_QP_VALID_MIN_RNR_NAK_TIMER));
 
+	p_ramrod = &p_ent->ramrod.roce_modify_qp_resp;
+	p_ramrod->flags = cpu_to_le16(flags);
+
 	p_ramrod->fields = 0;
 	SET_FIELD(p_ramrod->fields,
 		  ROCE_MODIFY_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER,
@@ -599,6 +574,7 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
 	struct roce_modify_qp_req_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
 	struct qed_spq_entry *p_ent;
+	u16 flags = 0;
 	int rc;
 
 	if (!qp->has_req)
@@ -623,54 +599,44 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
 		return rc;
 	}
 
-	p_ramrod = &p_ent->ramrod.roce_modify_qp_req;
-
-	p_ramrod->flags = 0;
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_MOVE_TO_ERR_FLG,
+		  !!move_to_err);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_MOVE_TO_ERR_FLG, move_to_err);
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_MOVE_TO_SQD_FLG,
+		  !!move_to_sqd);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_MOVE_TO_SQD_FLG, move_to_sqd);
-
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_EN_SQD_ASYNC_NOTIFY,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_EN_SQD_ASYNC_NOTIFY,
 		  qp->sqd_async);
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_P_KEY_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_P_KEY_FLG,
 		  GET_FIELD(modify_flags, QED_ROCE_MODIFY_QP_VALID_PKEY));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_ADDRESS_VECTOR_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_ADDRESS_VECTOR_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_ROCE_MODIFY_QP_VALID_ADDRESS_VECTOR));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_MAX_ORD_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_MAX_ORD_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_REQ));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_RNR_NAK_CNT_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_RNR_NAK_CNT_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_ROCE_MODIFY_QP_VALID_RNR_RETRY_CNT));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT_FLG,
 		  GET_FIELD(modify_flags, QED_ROCE_MODIFY_QP_VALID_RETRY_CNT));
 
-	SET_FIELD(p_ramrod->flags,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_ACK_TIMEOUT_FLG,
+	SET_FIELD(flags, ROCE_MODIFY_QP_REQ_RAMROD_DATA_ACK_TIMEOUT_FLG,
 		  GET_FIELD(modify_flags,
 			    QED_ROCE_MODIFY_QP_VALID_ACK_TIMEOUT));
 
+	p_ramrod = &p_ent->ramrod.roce_modify_qp_req;
+	p_ramrod->flags = cpu_to_le16(flags);
+
 	p_ramrod->fields = 0;
 	SET_FIELD(p_ramrod->fields,
 		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT, qp->retry_cnt);
-
-	SET_FIELD(p_ramrod->fields,
-		  ROCE_MODIFY_QP_REQ_RAMROD_DATA_RNR_NAK_CNT,
+	SET_FIELD(p_ramrod->fields, ROCE_MODIFY_QP_REQ_RAMROD_DATA_RNR_NAK_CNT,
 		  qp->rnr_retry_cnt);
 
 	p_ramrod->max_ord = qp->max_rd_atomic_req;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index f7f983a8bf44..993f1357b6fc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -155,7 +155,7 @@ struct qed_consq {
 };
 
 typedef int (*qed_spq_async_comp_cb)(struct qed_hwfn *p_hwfn, u8 opcode,
-				     u16 echo, union event_ring_data *data,
+				     __le16 echo, union event_ring_data *data,
 				     u8 fw_return_code);
 
 int
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 71ab57bca7c9..8142f5669b26 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -341,9 +341,9 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
 	outer_tag_config->outer_tag.tci = cpu_to_le16(p_hwfn->hw_info.ovlan);
 
 	if (test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits)) {
-		outer_tag_config->outer_tag.tpid = ETH_P_8021Q;
+		outer_tag_config->outer_tag.tpid = cpu_to_le16(ETH_P_8021Q);
 	} else if (test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits)) {
-		outer_tag_config->outer_tag.tpid = ETH_P_8021AD;
+		outer_tag_config->outer_tag.tpid = cpu_to_le16(ETH_P_8021AD);
 		outer_tag_config->enable_stag_pri_change = 1;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index b4e21e4792b7..aa215eeeb4df 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -4005,7 +4005,7 @@ static int qed_sriov_vfpf_msg(struct qed_hwfn *p_hwfn,
 	/* List the physical address of the request so that handler
 	 * could later on copy the message from it.
 	 */
-	p_vf->vf_mbx.pending_req = (((u64)vf_msg->hi) << 32) | vf_msg->lo;
+	p_vf->vf_mbx.pending_req = HILO_64(vf_msg->hi, vf_msg->lo);
 
 	/* Mark the event and schedule the workqueue */
 	p_vf->vf_mbx.b_pending_msg = true;
@@ -4037,7 +4037,7 @@ static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn,
 	}
 }
 
-static int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, u16 echo,
+static int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, __le16 echo,
 			       union event_ring_data *data, u8 fw_return_code)
 {
 	switch (opcode) {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 5ca081cd2ed9..90e1060da02b 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1403,16 +1403,15 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info,
 			      enum igu_int_cmd int_cmd,
 			      u8 upd_flg)
 {
-	struct igu_prod_cons_update igu_ack = { 0 };
+	u32 igu_ack;
 
-	igu_ack.sb_id_and_flags =
-		((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) |
-		 (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) |
-		 (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) |
-		 (IGU_SEG_ACCESS_REG <<
-		  IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT));
+	igu_ack = ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) |
+		   (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) |
+		   (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) |
+		   (IGU_SEG_ACCESS_REG <<
+		    IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT));
 
-	DIRECT_REG_WR(sb_info->igu_addr, igu_ack.sb_id_and_flags);
+	DIRECT_REG_WR(sb_info->igu_addr, igu_ack);
 
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
-- 
cgit v1.2.3


From 514acd00f957afa9b2a1fd521b2f180a950ee5e3 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Fri, 3 Jul 2020 12:43:54 +0200
Subject: thermal: Make thermal_zone_device_is_enabled() available to core only

This function is not needed by drivers.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200703104354.19657-4-andrzej.p@collabora.com
---
 drivers/thermal/thermal_core.c | 1 -
 drivers/thermal/thermal_core.h | 2 ++
 include/linux/thermal.h        | 5 -----
 3 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index a61e91513584..052343c59b0a 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -519,7 +519,6 @@ int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
 
 	return mode == THERMAL_DEVICE_ENABLED;
 }
-EXPORT_SYMBOL_GPL(thermal_zone_device_is_enabled);
 
 void thermal_zone_device_update(struct thermal_zone_device *tz,
 				enum thermal_notify_event event)
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index c95689586e19..b1464b3a21e2 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -166,4 +166,6 @@ of_thermal_get_trip_points(struct thermal_zone_device *tz)
 }
 #endif
 
+int thermal_zone_device_is_enabled(struct thermal_zone_device *tz);
+
 #endif /* __THERMAL_CORE_H__ */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index b9efaa780d88..108251f23e5c 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -418,7 +418,6 @@ void thermal_cdev_update(struct thermal_cooling_device *);
 void thermal_notify_framework(struct thermal_zone_device *, int);
 int thermal_zone_device_enable(struct thermal_zone_device *tz);
 int thermal_zone_device_disable(struct thermal_zone_device *tz);
-int thermal_zone_device_is_enabled(struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
@@ -472,10 +471,6 @@ static inline int thermal_zone_device_enable(struct thermal_zone_device *tz)
 
 static inline int thermal_zone_device_disable(struct thermal_zone_device *tz)
 { return -ENODEV; }
-
-static inline int
-thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
-{ return -ENODEV; }
 #endif /* CONFIG_THERMAL */
 
 #endif /* __THERMAL_H__ */
-- 
cgit v1.2.3


From 7af928851508fb25207806f57e287272dd498981 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 18 Jun 2020 15:55:11 +0100
Subject: smccc: Make constants available to assembly

Move constants out of the C-only section of the header next to the other
constants that are available to assembly.

Signed-off-by: Andrew Scull <ascull@google.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20200618145511.69203-1-ascull@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 include/linux/arm-smccc.h | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 56d6a5c6e353..efcbde731f03 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -81,6 +81,28 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x7fff)
 
+/* Paravirtualised time calls (defined by ARM DEN0057A) */
+#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x20)
+
+#define ARM_SMCCC_HV_PV_TIME_ST					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x21)
+
+/*
+ * Return codes defined in ARM DEN 0070A
+ * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
+ */
+#define SMCCC_RET_SUCCESS			0
+#define SMCCC_RET_NOT_SUPPORTED			-1
+#define SMCCC_RET_NOT_REQUIRED			-2
+#define SMCCC_RET_INVALID_PARAMETER		-3
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
@@ -331,15 +353,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
 
-/*
- * Return codes defined in ARM DEN 0070A
- * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
- */
-#define SMCCC_RET_SUCCESS			0
-#define SMCCC_RET_NOT_SUPPORTED			-1
-#define SMCCC_RET_NOT_REQUIRED			-2
-#define SMCCC_RET_INVALID_PARAMETER		-3
-
 /*
  * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED.
  * Used when the SMCCC conduit is not defined. The empty asm statement
@@ -385,18 +398,5 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		method;							\
 	})
 
-/* Paravirtualised time calls (defined by ARM DEN0057A) */
-#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
-			   ARM_SMCCC_SMC_64,			\
-			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
-			   0x20)
-
-#define ARM_SMCCC_HV_PV_TIME_ST					\
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
-			   ARM_SMCCC_SMC_64,			\
-			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
-			   0x21)
-
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
-- 
cgit v1.2.3


From 1ce50e7d408ef2bdc8ca021363fd46d1b8bfad00 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jul 2020 12:55:37 +0200
Subject: thermal: core: genetlink support for events/cmd/sampling

Initially the thermal framework had a very simple notification
mechanism to send generic netlink messages to the userspace.

The notification function was never called from anywhere and the
corresponding dead code was removed. It was probably a first attempt
to introduce the netlink notification.

At LPC2018, the presentation "Linux thermal: User kernel interface",
proposed to create the notifications to the userspace via a kfifo.

The advantage of the kfifo is the performance. It is usually used from
a 1:1 communication channel where a driver captures data and sends it
as fast as possible to a userspace process.

The drawback is that only one process uses the notification channel
exclusively, thus no other process is allowed to use the channel to
get temperature or notifications.

This patch defines a generic netlink API to discover the current
thermal setup and adds event notifications as well as temperature
sampling. As any genetlink protocol, it can evolve and the versioning
allows to keep the backward compatibility.

In order to prevent the user from getting flooded with data on a
single channel, there are two multicast channels, one for the
temperature sampling when the thermal zone is updated and another one
for the events, so the user can get the events only without the
thermal zone temperature sampling.

Also, a list of commands to discover the thermal setup is added and
can be extended when needed.

Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20200706105538.2159-3-daniel.lezcano@linaro.org
---
 drivers/thermal/Makefile          |   2 +-
 drivers/thermal/thermal_core.h    |  18 ++
 drivers/thermal/thermal_netlink.c | 648 ++++++++++++++++++++++++++++++++++++++
 include/linux/thermal.h           |  17 -
 include/uapi/linux/thermal.h      |  89 +++++-
 5 files changed, 739 insertions(+), 35 deletions(-)
 create mode 100644 drivers/thermal/thermal_netlink.c

(limited to 'include/linux')

diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 0c8b84a09b9a..1bbf0805fb04 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -5,7 +5,7 @@
 
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
 thermal_sys-y			+= thermal_core.o thermal_sysfs.o \
-					thermal_helpers.o
+					thermal_helpers.o thermal_netlink.o
 
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 967b0ba6593e..4d9455ef0c32 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -52,6 +52,24 @@ int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *),
 
 struct thermal_zone_device *thermal_zone_get_by_id(int id);
 
+/* Netlink notification function */
+int thermal_notify_tz_create(int tz_id, const char *name);
+int thermal_notify_tz_delete(int tz_id);
+int thermal_notify_tz_enable(int tz_id);
+int thermal_notify_tz_disable(int tz_id);
+int thermal_notify_tz_trip_down(int tz_id, int id);
+int thermal_notify_tz_trip_up(int tz_id, int id);
+int thermal_notify_tz_trip_delete(int tz_id, int id);
+int thermal_notify_tz_trip_add(int tz_id, int id, int type,
+			       int temp, int hyst);
+int thermal_notify_tz_trip_change(int tz_id, int id, int type,
+				  int temp, int hyst);
+int thermal_notify_cdev_state_update(int cdev_id, int state);
+int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
+int thermal_notify_cdev_delete(int cdev_id);
+int thermal_notify_tz_gov_change(int tz_id, const char *name);
+int thermal_genl_sampling_temp(int id, int temp);
+
 struct thermal_attr {
 	struct device_attribute attr;
 	char name[THERMAL_NAME_LENGTH];
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
new file mode 100644
index 000000000000..dd0a3b889674
--- /dev/null
+++ b/drivers/thermal/thermal_netlink.c
@@ -0,0 +1,648 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Generic netlink for thermal management framework
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <net/genetlink.h>
+#include <uapi/linux/thermal.h>
+
+#include "thermal_core.h"
+
+static const struct genl_multicast_group thermal_genl_mcgrps[] = {
+	{ .name = THERMAL_GENL_SAMPLING_GROUP_NAME, },
+	{ .name = THERMAL_GENL_EVENT_GROUP_NAME,  },
+};
+
+static const struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = {
+	/* Thermal zone */
+	[THERMAL_GENL_ATTR_TZ]			= { .type = NLA_NESTED },
+	[THERMAL_GENL_ATTR_TZ_ID]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_TEMP]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_TRIP]		= { .type = NLA_NESTED },
+	[THERMAL_GENL_ATTR_TZ_TRIP_ID]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_TRIP_HYST]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_MODE]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_TZ_NAME]		= { .type = NLA_STRING,
+						    .len = THERMAL_NAME_LENGTH },
+	/* Governor(s) */
+	[THERMAL_GENL_ATTR_TZ_GOV]		= { .type = NLA_NESTED },
+	[THERMAL_GENL_ATTR_TZ_GOV_NAME]		= { .type = NLA_STRING,
+						    .len = THERMAL_NAME_LENGTH },
+	/* Cooling devices */
+	[THERMAL_GENL_ATTR_CDEV]		= { .type = NLA_NESTED },
+	[THERMAL_GENL_ATTR_CDEV_ID]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_CDEV_CUR_STATE]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_CDEV_MAX_STATE]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_CDEV_NAME]		= { .type = NLA_STRING,
+						    .len = THERMAL_NAME_LENGTH },
+};
+
+struct param {
+	struct nlattr **attrs;
+	struct sk_buff *msg;
+	const char *name;
+	int tz_id;
+	int cdev_id;
+	int trip_id;
+	int trip_temp;
+	int trip_type;
+	int trip_hyst;
+	int temp;
+	int cdev_state;
+	int cdev_max_state;
+};
+
+typedef int (*cb_t)(struct param *);
+
+static struct genl_family thermal_gnl_family;
+
+/************************** Sampling encoding *******************************/
+
+int thermal_genl_sampling_temp(int id, int temp)
+{
+	struct sk_buff *skb;
+	void *hdr;
+
+	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(skb, 0, 0, &thermal_gnl_family, 0,
+			  THERMAL_GENL_SAMPLING_TEMP);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, THERMAL_GENL_ATTR_TZ_ID, id))
+		goto out_cancel;
+
+	if (nla_put_u32(skb, THERMAL_GENL_ATTR_TZ_TEMP, temp))
+		goto out_cancel;
+
+	genlmsg_end(skb, hdr);
+
+	genlmsg_multicast(&thermal_gnl_family, skb, 0, 0, GFP_KERNEL);
+
+	return 0;
+out_cancel:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+
+	return -EMSGSIZE;
+}
+
+/**************************** Event encoding *********************************/
+
+static int thermal_genl_event_tz_create(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
+	    nla_put_string(p->msg, THERMAL_GENL_ATTR_TZ_NAME, p->name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_tz(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_tz_trip_up(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_tz_trip_add(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, p->trip_type) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, p->trip_temp) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, p->trip_hyst))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_tz_trip_delete(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_cdev_add(struct param *p)
+{
+	if (nla_put_string(p->msg, THERMAL_GENL_ATTR_CDEV_NAME,
+			   p->name) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID,
+			p->cdev_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_MAX_STATE,
+			p->cdev_max_state))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_cdev_delete(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID, p->cdev_id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_cdev_state_update(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID,
+			p->cdev_id) ||
+	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_CUR_STATE,
+			p->cdev_state))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_event_gov_change(struct param *p)
+{
+	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
+	    nla_put_string(p->msg, THERMAL_GENL_ATTR_GOV_NAME, p->name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+int thermal_genl_event_tz_delete(struct param *p)
+	__attribute__((alias("thermal_genl_event_tz")));
+
+int thermal_genl_event_tz_enable(struct param *p)
+	__attribute__((alias("thermal_genl_event_tz")));
+
+int thermal_genl_event_tz_disable(struct param *p)
+	__attribute__((alias("thermal_genl_event_tz")));
+
+int thermal_genl_event_tz_trip_down(struct param *p)
+	__attribute__((alias("thermal_genl_event_tz_trip_up")));
+
+int thermal_genl_event_tz_trip_change(struct param *p)
+	__attribute__((alias("thermal_genl_event_tz_trip_add")));
+
+static cb_t event_cb[] = {
+	[THERMAL_GENL_EVENT_TZ_CREATE]		= thermal_genl_event_tz_create,
+	[THERMAL_GENL_EVENT_TZ_DELETE]		= thermal_genl_event_tz_delete,
+	[THERMAL_GENL_EVENT_TZ_ENABLE]		= thermal_genl_event_tz_enable,
+	[THERMAL_GENL_EVENT_TZ_DISABLE]		= thermal_genl_event_tz_disable,
+	[THERMAL_GENL_EVENT_TZ_TRIP_UP]		= thermal_genl_event_tz_trip_up,
+	[THERMAL_GENL_EVENT_TZ_TRIP_DOWN]	= thermal_genl_event_tz_trip_down,
+	[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE]	= thermal_genl_event_tz_trip_change,
+	[THERMAL_GENL_EVENT_TZ_TRIP_ADD]	= thermal_genl_event_tz_trip_add,
+	[THERMAL_GENL_EVENT_TZ_TRIP_DELETE]	= thermal_genl_event_tz_trip_delete,
+	[THERMAL_GENL_EVENT_CDEV_ADD]		= thermal_genl_event_cdev_add,
+	[THERMAL_GENL_EVENT_CDEV_DELETE]	= thermal_genl_event_cdev_delete,
+	[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE]	= thermal_genl_event_cdev_state_update,
+	[THERMAL_GENL_EVENT_TZ_GOV_CHANGE]	= thermal_genl_event_gov_change,
+};
+
+/*
+ * Generic netlink event encoding
+ */
+static int thermal_genl_send_event(enum thermal_genl_event event,
+				   struct param *p)
+{
+	struct sk_buff *msg;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+	p->msg = msg;
+
+	hdr = genlmsg_put(msg, 0, 0, &thermal_gnl_family, 0, event);
+	if (!hdr)
+		goto out_free_msg;
+
+	ret = event_cb[event](p);
+	if (ret)
+		goto out_cancel_msg;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast(&thermal_gnl_family, msg, 0, 1, GFP_KERNEL);
+
+	return 0;
+
+out_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+out_free_msg:
+	nlmsg_free(msg);
+
+	return ret;
+}
+
+int thermal_notify_tz_create(int tz_id, const char *name)
+{
+	struct param p = { .tz_id = tz_id, .name = name };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_CREATE, &p);
+}
+
+int thermal_notify_tz_delete(int tz_id)
+{
+	struct param p = { .tz_id = tz_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DELETE, &p);
+}
+
+int thermal_notify_tz_enable(int tz_id)
+{
+	struct param p = { .tz_id = tz_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_ENABLE, &p);
+}
+
+int thermal_notify_tz_disable(int tz_id)
+{
+	struct param p = { .tz_id = tz_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p);
+}
+
+int thermal_notify_tz_trip_down(int tz_id, int trip_id)
+{
+	struct param p = { .tz_id = tz_id, .trip_id = trip_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DOWN, &p);
+}
+
+int thermal_notify_tz_trip_up(int tz_id, int trip_id)
+{
+	struct param p = { .tz_id = tz_id, .trip_id = trip_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_UP, &p);
+}
+
+int thermal_notify_tz_trip_add(int tz_id, int trip_id, int trip_type,
+			       int trip_temp, int trip_hyst)
+{
+	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
+			   .trip_type = trip_type, .trip_temp = trip_temp,
+			   .trip_hyst = trip_hyst };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_ADD, &p);
+}
+
+int thermal_notify_tz_trip_delete(int tz_id, int trip_id)
+{
+	struct param p = { .tz_id = tz_id, .trip_id = trip_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DELETE, &p);
+}
+
+int thermal_notify_tz_trip_change(int tz_id, int trip_id, int trip_type,
+				  int trip_temp, int trip_hyst)
+{
+	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
+			   .trip_type = trip_type, .trip_temp = trip_temp,
+			   .trip_hyst = trip_hyst };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, &p);
+}
+
+int thermal_notify_cdev_state_update(int cdev_id, int cdev_state)
+{
+	struct param p = { .cdev_id = cdev_id, .cdev_state = cdev_state };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, &p);
+}
+
+int thermal_notify_cdev_add(int cdev_id, const char *name, int cdev_max_state)
+{
+	struct param p = { .cdev_id = cdev_id, .name = name,
+			   .cdev_max_state = cdev_max_state };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_ADD, &p);
+}
+
+int thermal_notify_cdev_delete(int cdev_id)
+{
+	struct param p = { .cdev_id = cdev_id };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_DELETE, &p);
+}
+
+int thermal_notify_tz_gov_change(int tz_id, const char *name)
+{
+	struct param p = { .tz_id = tz_id, .name = name };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_GOV_CHANGE, &p);
+}
+
+/*************************** Command encoding ********************************/
+
+static int __thermal_genl_cmd_tz_get_id(struct thermal_zone_device *tz,
+					void *data)
+{
+	struct sk_buff *msg = data;
+
+	if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, tz->id) ||
+	    nla_put_string(msg, THERMAL_GENL_ATTR_TZ_NAME, tz->type))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_cmd_tz_get_id(struct param *p)
+{
+	struct sk_buff *msg = p->msg;
+	struct nlattr *start_tz;
+	int ret;
+
+	start_tz = nla_nest_start(msg, THERMAL_GENL_ATTR_TZ);
+	if (!start_tz)
+		return -EMSGSIZE;
+
+	ret = for_each_thermal_zone(__thermal_genl_cmd_tz_get_id, msg);
+	if (ret)
+		goto out_cancel_nest;
+
+	nla_nest_end(msg, start_tz);
+
+	return 0;
+
+out_cancel_nest:
+	nla_nest_cancel(msg, start_tz);
+
+	return ret;
+}
+
+static int thermal_genl_cmd_tz_get_trip(struct param *p)
+{
+	struct sk_buff *msg = p->msg;
+	struct thermal_zone_device *tz;
+	struct nlattr *start_trip;
+	int i, id;
+
+	if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID])
+		return -EINVAL;
+
+	id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]);
+
+	tz = thermal_zone_get_by_id(id);
+	if (!tz)
+		return -EINVAL;
+
+	start_trip = nla_nest_start(msg, THERMAL_GENL_ATTR_TZ_TRIP);
+	if (!start_trip)
+		return -EMSGSIZE;
+
+	mutex_lock(&tz->lock);
+
+	for (i = 0; i < tz->trips; i++) {
+
+		enum thermal_trip_type type;
+		int temp, hyst;
+
+		tz->ops->get_trip_type(tz, i, &type);
+		tz->ops->get_trip_temp(tz, i, &temp);
+		tz->ops->get_trip_hyst(tz, i, &hyst);
+
+		if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, i) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, type) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, temp) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, hyst))
+			goto out_cancel_nest;
+	}
+
+	mutex_unlock(&tz->lock);
+
+	nla_nest_end(msg, start_trip);
+
+	return 0;
+
+out_cancel_nest:
+	mutex_unlock(&tz->lock);
+
+	return -EMSGSIZE;
+}
+
+static int thermal_genl_cmd_tz_get_temp(struct param *p)
+{
+	struct sk_buff *msg = p->msg;
+	struct thermal_zone_device *tz;
+	int temp, ret, id;
+
+	if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID])
+		return -EINVAL;
+
+	id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]);
+
+	tz = thermal_zone_get_by_id(id);
+	if (!tz)
+		return -EINVAL;
+
+	ret = thermal_zone_get_temp(tz, &temp);
+	if (ret)
+		return ret;
+
+	if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id) ||
+	    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TEMP, temp))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_cmd_tz_get_gov(struct param *p)
+{
+	struct sk_buff *msg = p->msg;
+	struct thermal_zone_device *tz;
+	int id, ret = 0;
+
+	if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID])
+		return -EINVAL;
+
+	id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]);
+
+	tz = thermal_zone_get_by_id(id);
+	if (!tz)
+		return -EINVAL;
+
+	mutex_lock(&tz->lock);
+
+	if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id) ||
+	    nla_put_string(msg, THERMAL_GENL_ATTR_TZ_GOV_NAME,
+			   tz->governor->name))
+		ret = -EMSGSIZE;
+
+	mutex_unlock(&tz->lock);
+
+	return ret;
+}
+
+static int __thermal_genl_cmd_cdev_get(struct thermal_cooling_device *cdev,
+				       void *data)
+{
+	struct sk_buff *msg = data;
+
+	if (nla_put_u32(msg, THERMAL_GENL_ATTR_CDEV_ID, cdev->id))
+		return -EMSGSIZE;
+
+	if (nla_put_string(msg, THERMAL_GENL_ATTR_CDEV_NAME, cdev->type))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int thermal_genl_cmd_cdev_get(struct param *p)
+{
+	struct sk_buff *msg = p->msg;
+	struct nlattr *start_cdev;
+	int ret;
+
+	start_cdev = nla_nest_start(msg, THERMAL_GENL_ATTR_CDEV);
+	if (!start_cdev)
+		return -EMSGSIZE;
+
+	ret = for_each_thermal_cooling_device(__thermal_genl_cmd_cdev_get, msg);
+	if (ret)
+		goto out_cancel_nest;
+
+	nla_nest_end(msg, start_cdev);
+
+	return 0;
+out_cancel_nest:
+	nla_nest_cancel(msg, start_cdev);
+
+	return ret;
+}
+
+static cb_t cmd_cb[] = {
+	[THERMAL_GENL_CMD_TZ_GET_ID]	= thermal_genl_cmd_tz_get_id,
+	[THERMAL_GENL_CMD_TZ_GET_TRIP]	= thermal_genl_cmd_tz_get_trip,
+	[THERMAL_GENL_CMD_TZ_GET_TEMP]	= thermal_genl_cmd_tz_get_temp,
+	[THERMAL_GENL_CMD_TZ_GET_GOV]	= thermal_genl_cmd_tz_get_gov,
+	[THERMAL_GENL_CMD_CDEV_GET]	= thermal_genl_cmd_cdev_get,
+};
+
+static int thermal_genl_cmd_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	struct param p = { .msg = skb };
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	int cmd = info->ops->cmd;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, 0, 0, &thermal_gnl_family, 0, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	ret = cmd_cb[cmd](&p);
+	if (ret)
+		goto out_cancel_msg;
+
+	genlmsg_end(skb, hdr);
+
+	return 0;
+
+out_cancel_msg:
+	genlmsg_cancel(skb, hdr);
+
+	return ret;
+}
+
+static int thermal_genl_cmd_doit(struct sk_buff *skb,
+				 struct genl_info *info)
+{
+	struct param p = { .attrs = info->attrs };
+	struct sk_buff *msg;
+	void *hdr;
+	int cmd = info->genlhdr->cmd;
+	int ret = -EMSGSIZE;
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+	p.msg = msg;
+
+	hdr = genlmsg_put_reply(msg, info, &thermal_gnl_family, 0, cmd);
+	if (!hdr)
+		goto out_free_msg;
+
+	ret = cmd_cb[cmd](&p);
+	if (ret)
+		goto out_cancel_msg;
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+out_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+out_free_msg:
+	nlmsg_free(msg);
+
+	return ret;
+}
+
+static const struct genl_ops thermal_genl_ops[] = {
+	{
+		.cmd = THERMAL_GENL_CMD_TZ_GET_ID,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.dumpit = thermal_genl_cmd_dumpit,
+	},
+	{
+		.cmd = THERMAL_GENL_CMD_TZ_GET_TRIP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = thermal_genl_cmd_doit,
+	},
+	{
+		.cmd = THERMAL_GENL_CMD_TZ_GET_TEMP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = thermal_genl_cmd_doit,
+	},
+	{
+		.cmd = THERMAL_GENL_CMD_TZ_GET_GOV,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = thermal_genl_cmd_doit,
+	},
+	{
+		.cmd = THERMAL_GENL_CMD_CDEV_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.dumpit = thermal_genl_cmd_dumpit,
+	},
+};
+
+static struct genl_family thermal_gnl_family __ro_after_init = {
+	.hdrsize	= 0,
+	.name		= THERMAL_GENL_FAMILY_NAME,
+	.version	= THERMAL_GENL_VERSION,
+	.maxattr	= THERMAL_GENL_ATTR_MAX,
+	.policy		= thermal_genl_policy,
+	.ops		= thermal_genl_ops,
+	.n_ops		= ARRAY_SIZE(thermal_genl_ops),
+	.mcgrps		= thermal_genl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(thermal_genl_mcgrps),
+};
+
+static int __init thermal_netlink_init(void)
+{
+	return genl_register_family(&thermal_gnl_family);
+}
+core_initcall(thermal_netlink_init);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 108251f23e5c..42ef807e5d84 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -37,18 +37,6 @@ struct thermal_cooling_device;
 struct thermal_instance;
 struct thermal_attr;
 
-enum thermal_device_mode {
-	THERMAL_DEVICE_DISABLED = 0,
-	THERMAL_DEVICE_ENABLED,
-};
-
-enum thermal_trip_type {
-	THERMAL_TRIP_ACTIVE = 0,
-	THERMAL_TRIP_PASSIVE,
-	THERMAL_TRIP_HOT,
-	THERMAL_TRIP_CRITICAL,
-};
-
 enum thermal_trend {
 	THERMAL_TREND_STABLE, /* temperature is stable */
 	THERMAL_TREND_RAISING, /* temperature is raising */
@@ -303,11 +291,6 @@ struct thermal_zone_params {
 	int offset;
 };
 
-struct thermal_genl_event {
-	u32 orig;
-	enum events event;
-};
-
 /**
  * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones
  *
diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h
index 96218378dda8..c105054cbb57 100644
--- a/include/uapi/linux/thermal.h
+++ b/include/uapi/linux/thermal.h
@@ -4,31 +4,86 @@
 
 #define THERMAL_NAME_LENGTH	20
 
-/* Adding event notification support elements */
-#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
-#define THERMAL_GENL_VERSION                    0x01
-#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
-
-/* Events supported by Thermal Netlink */
-enum events {
-	THERMAL_AUX0,
-	THERMAL_AUX1,
-	THERMAL_CRITICAL,
-	THERMAL_DEV_FAULT,
+enum thermal_device_mode {
+	THERMAL_DEVICE_DISABLED = 0,
+	THERMAL_DEVICE_ENABLED,
+};
+
+enum thermal_trip_type {
+	THERMAL_TRIP_ACTIVE = 0,
+	THERMAL_TRIP_PASSIVE,
+	THERMAL_TRIP_HOT,
+	THERMAL_TRIP_CRITICAL,
 };
 
-/* attributes of thermal_genl_family */
-enum {
+/* Adding event notification support elements */
+#define THERMAL_GENL_FAMILY_NAME		"thermal"
+#define THERMAL_GENL_VERSION			0x01
+#define THERMAL_GENL_SAMPLING_GROUP_NAME	"sampling"
+#define THERMAL_GENL_EVENT_GROUP_NAME		"event"
+
+/* Attributes of thermal_genl_family */
+enum thermal_genl_attr {
 	THERMAL_GENL_ATTR_UNSPEC,
-	THERMAL_GENL_ATTR_EVENT,
+	THERMAL_GENL_ATTR_TZ,
+	THERMAL_GENL_ATTR_TZ_ID,
+	THERMAL_GENL_ATTR_TZ_TEMP,
+	THERMAL_GENL_ATTR_TZ_TRIP,
+	THERMAL_GENL_ATTR_TZ_TRIP_ID,
+	THERMAL_GENL_ATTR_TZ_TRIP_TYPE,
+	THERMAL_GENL_ATTR_TZ_TRIP_TEMP,
+	THERMAL_GENL_ATTR_TZ_TRIP_HYST,
+	THERMAL_GENL_ATTR_TZ_MODE,
+	THERMAL_GENL_ATTR_TZ_NAME,
+	THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT,
+	THERMAL_GENL_ATTR_TZ_GOV,
+	THERMAL_GENL_ATTR_TZ_GOV_NAME,
+	THERMAL_GENL_ATTR_CDEV,
+	THERMAL_GENL_ATTR_CDEV_ID,
+	THERMAL_GENL_ATTR_CDEV_CUR_STATE,
+	THERMAL_GENL_ATTR_CDEV_MAX_STATE,
+	THERMAL_GENL_ATTR_CDEV_NAME,
+	THERMAL_GENL_ATTR_GOV_NAME,
+
 	__THERMAL_GENL_ATTR_MAX,
 };
 #define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
 
-/* commands supported by the thermal_genl_family */
-enum {
+enum thermal_genl_sampling {
+	THERMAL_GENL_SAMPLING_TEMP,
+	__THERMAL_GENL_SAMPLING_MAX,
+};
+#define THERMAL_GENL_SAMPLING_MAX (__THERMAL_GENL_SAMPLING_MAX - 1)
+
+/* Events of thermal_genl_family */
+enum thermal_genl_event {
+	THERMAL_GENL_EVENT_UNSPEC,
+	THERMAL_GENL_EVENT_TZ_CREATE,		/* Thermal zone creation */
+	THERMAL_GENL_EVENT_TZ_DELETE,		/* Thermal zone deletion */
+	THERMAL_GENL_EVENT_TZ_DISABLE,		/* Thermal zone disabed */
+	THERMAL_GENL_EVENT_TZ_ENABLE,		/* Thermal zone enabled */
+	THERMAL_GENL_EVENT_TZ_TRIP_UP,		/* Trip point crossed the way up */
+	THERMAL_GENL_EVENT_TZ_TRIP_DOWN,	/* Trip point crossed the way down */
+	THERMAL_GENL_EVENT_TZ_TRIP_CHANGE,	/* Trip point changed */
+	THERMAL_GENL_EVENT_TZ_TRIP_ADD,		/* Trip point added */
+	THERMAL_GENL_EVENT_TZ_TRIP_DELETE,	/* Trip point deleted */
+	THERMAL_GENL_EVENT_CDEV_ADD,		/* Cdev bound to the thermal zone */
+	THERMAL_GENL_EVENT_CDEV_DELETE,		/* Cdev unbound */
+	THERMAL_GENL_EVENT_CDEV_STATE_UPDATE,	/* Cdev state updated */
+	THERMAL_GENL_EVENT_TZ_GOV_CHANGE,	/* Governor policy changed  */
+	__THERMAL_GENL_EVENT_MAX,
+};
+#define THERMAL_GENL_EVENT_MAX (__THERMAL_GENL_EVENT_MAX - 1)
+
+/* Commands supported by the thermal_genl_family */
+enum thermal_genl_cmd {
 	THERMAL_GENL_CMD_UNSPEC,
-	THERMAL_GENL_CMD_EVENT,
+	THERMAL_GENL_CMD_TZ_GET_ID,	/* List of thermal zones id */
+	THERMAL_GENL_CMD_TZ_GET_TRIP,	/* List of thermal trips */
+	THERMAL_GENL_CMD_TZ_GET_TEMP,	/* Get the thermal zone temperature */
+	THERMAL_GENL_CMD_TZ_GET_GOV,	/* Get the thermal zone governor */
+	THERMAL_GENL_CMD_TZ_GET_MODE,	/* Get the thermal zone mode */
+	THERMAL_GENL_CMD_CDEV_GET,	/* List of cdev id */
 	__THERMAL_GENL_CMD_MAX,
 };
 #define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
-- 
cgit v1.2.3


From 38fd525a4c61e7ecdc9ad4dcbf7b767d0a007962 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 1 Jul 2020 07:30:06 -0500
Subject: exit: Factor thread_group_exited out of pidfd_poll

Create an independent helper thread_group_exited which returns true
when all threads have passed exit_notify in do_exit.  AKA all of the
threads are at least zombies and might be dead or completely gone.

Create this helper by taking the logic out of pidfd_poll where it is
already tested, and adding a READ_ONCE on the read of
task->exit_state.

I will be changing the user mode driver code to use this same logic
to know when a user mode driver needs to be restarted.

Place the new helper thread_group_exited in kernel/exit.c and
EXPORT it so it can be used by modules.

Link: https://lkml.kernel.org/r/20200702164140.4468-13-ebiederm@xmission.com
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/sched/signal.h |  2 ++
 kernel/exit.c                | 24 ++++++++++++++++++++++++
 kernel/fork.c                |  6 +-----
 3 files changed, 27 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 0ee5e696c5d8..1bad18a1d8ba 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -674,6 +674,8 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
+extern bool thread_group_exited(struct pid *pid);
+
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
 							unsigned long *flags);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index d3294b611df1..dee246c0866f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1713,6 +1713,30 @@ Efault:
 }
 #endif
 
+/**
+ * thread_group_exited - check that a thread group has exited
+ * @pid: tgid of thread group to be checked.
+ *
+ * Test if the thread group represented by tgid has exited (all
+ * threads are zombies, dead or completely gone).
+ *
+ * Return: true if the thread group has exited. false otherwise.
+ */
+bool thread_group_exited(struct pid *pid)
+{
+	struct task_struct *task;
+	bool exited;
+
+	rcu_read_lock();
+	task = pid_task(pid, PIDTYPE_PID);
+	exited = !task ||
+		(READ_ONCE(task->exit_state) && thread_group_empty(task));
+	rcu_read_unlock();
+
+	return exited;
+}
+EXPORT_SYMBOL(thread_group_exited);
+
 __weak void abort(void)
 {
 	BUG();
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..bf215af7a904 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1787,22 +1787,18 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
  */
 static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 {
-	struct task_struct *task;
 	struct pid *pid = file->private_data;
 	__poll_t poll_flags = 0;
 
 	poll_wait(file, &pid->wait_pidfd, pts);
 
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
 	/*
 	 * Inform pollers only when the whole thread group exits.
 	 * If the thread group leader exits before all other threads in the
 	 * group, then poll(2) should block, similar to the wait(2) family.
 	 */
-	if (!task || (task->exit_state && thread_group_empty(task)))
+	if (thread_group_exited(pid))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
-	rcu_read_unlock();
 
 	return poll_flags;
 }
-- 
cgit v1.2.3


From e80eb1dc868bc1ed93602389d54b27f170ca770c Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 17:23:22 -0500
Subject: bpfilter: Take advantage of the facilities of struct pid

Instead of relying on the exit_umh cleanup callback use the fact a
struct pid can be tested to see if a process still exists, and that
struct pid has a wait queue that notifies when the process dies.

v1: https://lkml.kernel.org/r/87h7uydlu9.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/874kqt4owu.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-14-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/bpfilter.h     |  3 ++-
 net/bpfilter/bpfilter_kern.c | 15 +++++----------
 net/ipv4/bpfilter/sockopt.c  | 15 ++++++++-------
 3 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index ec9972d822e0..9b114c718a76 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -10,6 +10,8 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
 			    unsigned int optlen);
 int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
 			    int __user *optlen);
+void bpfilter_umh_cleanup(struct umd_info *info);
+
 struct bpfilter_umh_ops {
 	struct umd_info info;
 	/* since ip_getsockopt() can run in parallel, serialize access to umh */
@@ -18,7 +20,6 @@ struct bpfilter_umh_ops {
 		       char __user *optval,
 		       unsigned int optlen, bool is_set);
 	int (*start)(void);
-	bool stop;
 };
 extern struct bpfilter_umh_ops bpfilter_ops;
 #endif
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 08ea77c2b137..9616fb7defeb 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -18,10 +18,11 @@ static void shutdown_umh(void)
 	struct umd_info *info = &bpfilter_ops.info;
 	struct pid *tgid = info->tgid;
 
-	if (bpfilter_ops.stop)
-		return;
-
-	kill_pid(tgid, SIGKILL, 1);
+	if (tgid) {
+		kill_pid(tgid, SIGKILL, 1);
+		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+		bpfilter_umh_cleanup(info);
+	}
 }
 
 static void __stop_umh(void)
@@ -77,7 +78,6 @@ static int start_umh(void)
 	err = fork_usermode_driver(&bpfilter_ops.info);
 	if (err)
 		return err;
-	bpfilter_ops.stop = false;
 	pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
 
 	/* health check that usermode process started correctly */
@@ -100,16 +100,11 @@ static int __init load_umh(void)
 		return err;
 
 	mutex_lock(&bpfilter_ops.lock);
-	if (!bpfilter_ops.stop) {
-		err = -EFAULT;
-		goto out;
-	}
 	err = start_umh();
 	if (!err && IS_ENABLED(CONFIG_INET)) {
 		bpfilter_ops.sockopt = &__bpfilter_process_sockopt;
 		bpfilter_ops.start = &start_umh;
 	}
-out:
 	mutex_unlock(&bpfilter_ops.lock);
 	if (err)
 		umd_unload_blob(&bpfilter_ops.info);
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 56cbc43145f6..9063c6767d34 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -12,16 +12,14 @@
 struct bpfilter_umh_ops bpfilter_ops;
 EXPORT_SYMBOL_GPL(bpfilter_ops);
 
-static void bpfilter_umh_cleanup(struct umd_info *info)
+void bpfilter_umh_cleanup(struct umd_info *info)
 {
-	mutex_lock(&bpfilter_ops.lock);
-	bpfilter_ops.stop = true;
 	fput(info->pipe_to_umh);
 	fput(info->pipe_from_umh);
 	put_pid(info->tgid);
 	info->tgid = NULL;
-	mutex_unlock(&bpfilter_ops.lock);
 }
+EXPORT_SYMBOL_GPL(bpfilter_umh_cleanup);
 
 static int bpfilter_mbox_request(struct sock *sk, int optname,
 				 char __user *optval,
@@ -39,7 +37,11 @@ static int bpfilter_mbox_request(struct sock *sk, int optname,
 			goto out;
 		}
 	}
-	if (bpfilter_ops.stop) {
+	if (bpfilter_ops.info.tgid &&
+	    thread_group_exited(bpfilter_ops.info.tgid))
+		bpfilter_umh_cleanup(&bpfilter_ops.info);
+
+	if (!bpfilter_ops.info.tgid) {
 		err = bpfilter_ops.start();
 		if (err)
 			goto out;
@@ -70,9 +72,8 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
 static int __init bpfilter_sockopt_init(void)
 {
 	mutex_init(&bpfilter_ops.lock);
-	bpfilter_ops.stop = true;
+	bpfilter_ops.info.tgid = NULL;
 	bpfilter_ops.info.driver_name = "bpfilter_umh";
-	bpfilter_ops.info.cleanup = &bpfilter_umh_cleanup;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 8c2f52663973e643c617663d826e2b0daa008b38 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 25 Jun 2020 17:40:40 -0500
Subject: umd: Remove exit_umh

The bpfilter code no longer uses the umd_info.cleanup callback.  This
callback is what exit_umh exists to call.  So remove exit_umh and all
of it's associated booking.

v1: https://lkml.kernel.org/r/87bll6dlte.fsf_-_@x220.int.ebiederm.org
v2: https://lkml.kernel.org/r/87y2o53abg.fsf_-_@x220.int.ebiederm.org
Link: https://lkml.kernel.org/r/20200702164140.4468-15-ebiederm@xmission.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/sched.h           |  1 -
 include/linux/usermode_driver.h | 16 ----------------
 kernel/exit.c                   |  3 ---
 kernel/usermode_driver.c        | 28 ----------------------------
 4 files changed, 48 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 59d1e92bb88e..edb2020875ad 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1511,7 +1511,6 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
-#define PF_UMH			0x02000000	/* I'm an Usermodehelper process */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 45adbffb31d9..073a9e0ec07d 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -4,26 +4,10 @@
 #include <linux/umh.h>
 #include <linux/path.h>
 
-#ifdef CONFIG_BPFILTER
-void __exit_umh(struct task_struct *tsk);
-
-static inline void exit_umh(struct task_struct *tsk)
-{
-	if (unlikely(tsk->flags & PF_UMH))
-		__exit_umh(tsk);
-}
-#else
-static inline void exit_umh(struct task_struct *tsk)
-{
-}
-#endif
-
 struct umd_info {
 	const char *driver_name;
 	struct file *pipe_to_umh;
 	struct file *pipe_from_umh;
-	struct list_head list;
-	void (*cleanup)(struct umd_info *info);
 	struct path wd;
 	struct pid *tgid;
 };
diff --git a/kernel/exit.c b/kernel/exit.c
index dee246c0866f..39226a018ed7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -63,7 +63,6 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
-#include <linux/usermode_driver.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -805,8 +804,6 @@ void __noreturn do_exit(long code)
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
-	if (group_dead)
-		exit_umh(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index f77f8d7ce9e3..cd136f86f799 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -9,9 +9,6 @@
 #include <linux/task_work.h>
 #include <linux/usermode_driver.h>
 
-static LIST_HEAD(umh_list);
-static DEFINE_MUTEX(umh_list_lock);
-
 static struct vfsmount *blob_to_mnt(const void *data, size_t len, const char *name)
 {
 	struct file_system_type *type;
@@ -134,7 +131,6 @@ static int umd_setup(struct subprocess_info *info, struct cred *new)
 	umd_info->pipe_to_umh = to_umh[1];
 	umd_info->pipe_from_umh = from_umh[0];
 	umd_info->tgid = get_pid(task_tgid(current));
-	current->flags |= PF_UMH;
 	return 0;
 }
 
@@ -182,11 +178,6 @@ int fork_usermode_driver(struct umd_info *info)
 		goto out;
 
 	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
-	if (!err) {
-		mutex_lock(&umh_list_lock);
-		list_add(&info->list, &umh_list);
-		mutex_unlock(&umh_list_lock);
-	}
 out:
 	if (argv)
 		argv_free(argv);
@@ -194,23 +185,4 @@ out:
 }
 EXPORT_SYMBOL_GPL(fork_usermode_driver);
 
-void __exit_umh(struct task_struct *tsk)
-{
-	struct umd_info *info;
-	struct pid *tgid = task_tgid(tsk);
-
-	mutex_lock(&umh_list_lock);
-	list_for_each_entry(info, &umh_list, list) {
-		if (info->tgid == tgid) {
-			list_del(&info->list);
-			mutex_unlock(&umh_list_lock);
-			goto out;
-		}
-	}
-	mutex_unlock(&umh_list_lock);
-	return;
-out:
-	if (info->cleanup)
-		info->cleanup(info);
-}
 
-- 
cgit v1.2.3


From 6d4ebd565d15f374aab3d0f16f156bafec3c61b3 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 30 Jun 2020 07:57:03 +0300
Subject: iio: core: wrap IIO device into an iio_dev_opaque object

There are plenty of bad designs we want to discourage or not have to review
manually usually about accessing private (marked as [INTERN]) fields of
'struct iio_dev'.

Sometimes users copy drivers that are not always the best examples.

A better idea is to hide those fields into the framework.
For 'struct iio_dev' this is a 'struct iio_dev_opaque' which wraps a public
'struct iio_dev' object.

In the next series, some fields will be moved to this new struct, each with
it's own rework.

This rework will not be complete-able for a while, as many fields need some
drivers to be reworked in order to finalize them (e.g. 'indio_dev->mlock').

But some fields can already be moved, and in time, all of them may get
there (in the 'struct iio_dev_opaque' object).

Since a lot of drivers also call 'iio_priv()', in order to preserve
fast-paths (where this matters), the public iio_dev object will have a
'priv' field that will have the pointer to the private information already
computed. The reference returned by this field should be guaranteed to be
cacheline aligned.

The opaque parts will be moved into the 'include/linux/iio/iio-opaque.h'
header. Should the hidden information be required for some debugging or
some special needs, it can be made available via this header.
Otherwise, only the IIO core files should include this file.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 19 +++++++++++++------
 include/linux/iio/iio-opaque.h  | 17 +++++++++++++++++
 include/linux/iio/iio.h         |  6 +++++-
 3 files changed, 35 insertions(+), 7 deletions(-)
 create mode 100644 include/linux/iio/iio-opaque.h

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 75661661aaba..33e2953cf021 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -25,6 +25,7 @@
 #include <linux/debugfs.h>
 #include <linux/mutex.h>
 #include <linux/iio/iio.h>
+#include <linux/iio/iio-opaque.h>
 #include "iio_core.h"
 #include "iio_core_trigger.h"
 #include <linux/iio/sysfs.h>
@@ -1473,6 +1474,8 @@ static void iio_device_unregister_sysfs(struct iio_dev *indio_dev)
 static void iio_dev_release(struct device *device)
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(device);
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
 	if (indio_dev->modes & INDIO_ALL_TRIGGERED_MODES)
 		iio_device_unregister_trigger_consumer(indio_dev);
 	iio_device_unregister_eventset(indio_dev);
@@ -1481,7 +1484,7 @@ static void iio_dev_release(struct device *device)
 	iio_buffer_put(indio_dev->buffer);
 
 	ida_simple_remove(&iio_ida, indio_dev->id);
-	kfree(indio_dev);
+	kfree(iio_dev_opaque);
 }
 
 struct device_type iio_device_type = {
@@ -1495,10 +1498,11 @@ struct device_type iio_device_type = {
  **/
 struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 {
+	struct iio_dev_opaque *iio_dev_opaque;
 	struct iio_dev *dev;
 	size_t alloc_size;
 
-	alloc_size = sizeof(struct iio_dev);
+	alloc_size = sizeof(struct iio_dev_opaque);
 	if (sizeof_priv) {
 		alloc_size = ALIGN(alloc_size, IIO_ALIGN);
 		alloc_size += sizeof_priv;
@@ -1506,11 +1510,14 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 	/* ensure 32-byte alignment of whole construct ? */
 	alloc_size += IIO_ALIGN - 1;
 
-	dev = kzalloc(alloc_size, GFP_KERNEL);
-	if (!dev)
+	iio_dev_opaque = kzalloc(alloc_size, GFP_KERNEL);
+	if (!iio_dev_opaque)
 		return NULL;
 
-	dev->dev.parent = parent;
+	dev = &iio_dev_opaque->indio_dev;
+	dev->priv = (char *)iio_dev_opaque +
+		ALIGN(sizeof(struct iio_dev_opaque), IIO_ALIGN);
+
 	dev->dev.groups = dev->groups;
 	dev->dev.type = &iio_device_type;
 	dev->dev.bus = &iio_bus_type;
@@ -1524,7 +1531,7 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 	if (dev->id < 0) {
 		/* cannot use a dev_err as the name isn't available */
 		pr_err("failed to get device id\n");
-		kfree(dev);
+		kfree(iio_dev_opaque);
 		return NULL;
 	}
 	dev_set_name(&dev->dev, "iio:device%d", dev->id);
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
new file mode 100644
index 000000000000..1375674f14cd
--- /dev/null
+++ b/include/linux/iio/iio-opaque.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _INDUSTRIAL_IO_OPAQUE_H_
+#define _INDUSTRIAL_IO_OPAQUE_H_
+
+/**
+ * struct iio_dev_opaque - industrial I/O device opaque information
+ * @indio_dev:			public industrial I/O device information
+ */
+struct iio_dev_opaque {
+	struct iio_dev			indio_dev;
+};
+
+#define to_iio_dev_opaque(indio_dev)		\
+	container_of(indio_dev, struct iio_dev_opaque, indio_dev)
+
+#endif
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 1c1d02107722..c2f6d9ef213a 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -522,6 +522,8 @@ struct iio_buffer_setup_ops {
  * @flags:		[INTERN] file ops related flags including busy flag.
  * @debugfs_dentry:	[INTERN] device specific debugfs dentry.
  * @cached_reg_addr:	[INTERN] cached register address for debugfs reads.
+ * @priv:		[DRIVER] reference to driver's private information
+ *			**MUST** be accessed **ONLY** via iio_priv() helper
  */
 struct iio_dev {
 	int				id;
@@ -571,6 +573,7 @@ struct iio_dev {
 	char				read_buf[20];
 	unsigned int			read_buf_len;
 #endif
+	void				*priv;
 };
 
 const struct iio_chan_spec
@@ -698,9 +701,10 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
 #define IIO_ALIGN L1_CACHE_BYTES
 struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv);
 
+/* The information at the returned address is guaranteed to be cacheline aligned */
 static inline void *iio_priv(const struct iio_dev *indio_dev)
 {
-	return (char *)indio_dev + ALIGN(sizeof(struct iio_dev), IIO_ALIGN);
+	return indio_dev->priv;
 }
 
 static inline struct iio_dev *iio_priv_to_dev(void *priv)
-- 
cgit v1.2.3


From 96fb1b67422ed652e3217a140cf9be505041db07 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 30 Jun 2020 07:57:05 +0300
Subject: iio: core: move debugfs data on the private iio dev info

This change moves all iio_dev debugfs fields to the iio_dev_priv object.
It's not the biggest advantage yet (to the whole thing of abstractization)
but it's a start.

The iio_get_debugfs_dentry() function (which is moved in
industrialio-core.c) needs to also be guarded against the CONFIG_DEBUG_FS
symbol, when it isn't defined. We do want to keep the inline definition in
the iio.h header, so that the compiler can better infer when to compile out
debugfs code that is related to the IIO debugfs directory.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 46 +++++++++++++++++++++++++++++------------
 include/linux/iio/iio-opaque.h  | 10 +++++++++
 include/linux/iio/iio.h         | 13 +-----------
 3 files changed, 44 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 27005ba4d09c..bb2771974404 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -165,6 +165,19 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
 };
 
+#if defined(CONFIG_DEBUG_FS)
+/**
+ * There's also a CONFIG_DEBUG_FS guard in include/linux/iio/iio.h for
+ * iio_get_debugfs_dentry() to make it inline if CONFIG_DEBUG_FS is undefined
+ */
+struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
+{
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	return iio_dev_opaque->debugfs_dentry;
+}
+EXPORT_SYMBOL_GPL(iio_get_debugfs_dentry);
+#endif
+
 /**
  * iio_find_channel_from_si() - get channel from its scan index
  * @indio_dev:		device
@@ -308,35 +321,37 @@ static ssize_t iio_debugfs_read_reg(struct file *file, char __user *userbuf,
 			      size_t count, loff_t *ppos)
 {
 	struct iio_dev *indio_dev = file->private_data;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	unsigned val = 0;
 	int ret;
 
 	if (*ppos > 0)
 		return simple_read_from_buffer(userbuf, count, ppos,
-					       indio_dev->read_buf,
-					       indio_dev->read_buf_len);
+					       iio_dev_opaque->read_buf,
+					       iio_dev_opaque->read_buf_len);
 
 	ret = indio_dev->info->debugfs_reg_access(indio_dev,
-						  indio_dev->cached_reg_addr,
+						  iio_dev_opaque->cached_reg_addr,
 						  0, &val);
 	if (ret) {
 		dev_err(indio_dev->dev.parent, "%s: read failed\n", __func__);
 		return ret;
 	}
 
-	indio_dev->read_buf_len = snprintf(indio_dev->read_buf,
-					   sizeof(indio_dev->read_buf),
-					   "0x%X\n", val);
+	iio_dev_opaque->read_buf_len = snprintf(iio_dev_opaque->read_buf,
+					      sizeof(iio_dev_opaque->read_buf),
+					      "0x%X\n", val);
 
 	return simple_read_from_buffer(userbuf, count, ppos,
-				       indio_dev->read_buf,
-				       indio_dev->read_buf_len);
+				       iio_dev_opaque->read_buf,
+				       iio_dev_opaque->read_buf_len);
 }
 
 static ssize_t iio_debugfs_write_reg(struct file *file,
 		     const char __user *userbuf, size_t count, loff_t *ppos)
 {
 	struct iio_dev *indio_dev = file->private_data;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	unsigned reg, val;
 	char buf[80];
 	int ret;
@@ -351,10 +366,10 @@ static ssize_t iio_debugfs_write_reg(struct file *file,
 
 	switch (ret) {
 	case 1:
-		indio_dev->cached_reg_addr = reg;
+		iio_dev_opaque->cached_reg_addr = reg;
 		break;
 	case 2:
-		indio_dev->cached_reg_addr = reg;
+		iio_dev_opaque->cached_reg_addr = reg;
 		ret = indio_dev->info->debugfs_reg_access(indio_dev, reg,
 							  val, NULL);
 		if (ret) {
@@ -378,23 +393,28 @@ static const struct file_operations iio_debugfs_reg_fops = {
 
 static void iio_device_unregister_debugfs(struct iio_dev *indio_dev)
 {
-	debugfs_remove_recursive(indio_dev->debugfs_dentry);
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	debugfs_remove_recursive(iio_dev_opaque->debugfs_dentry);
 }
 
 static void iio_device_register_debugfs(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque;
+
 	if (indio_dev->info->debugfs_reg_access == NULL)
 		return;
 
 	if (!iio_debugfs_dentry)
 		return;
 
-	indio_dev->debugfs_dentry =
+	iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	iio_dev_opaque->debugfs_dentry =
 		debugfs_create_dir(dev_name(&indio_dev->dev),
 				   iio_debugfs_dentry);
 
 	debugfs_create_file("direct_reg_access", 0644,
-			    indio_dev->debugfs_dentry, indio_dev,
+			    iio_dev_opaque->debugfs_dentry, indio_dev,
 			    &iio_debugfs_reg_fops);
 }
 #else
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index 1375674f14cd..b3f234b4c1e9 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -6,9 +6,19 @@
 /**
  * struct iio_dev_opaque - industrial I/O device opaque information
  * @indio_dev:			public industrial I/O device information
+ * @debugfs_dentry:		device specific debugfs dentry
+ * @cached_reg_addr:		cached register address for debugfs reads
+ * @read_buf:			read buffer to be used for the initial reg read
+ * @read_buf_len:		data length in @read_buf
  */
 struct iio_dev_opaque {
 	struct iio_dev			indio_dev;
+#if defined(CONFIG_DEBUG_FS)
+	struct dentry			*debugfs_dentry;
+	unsigned			cached_reg_addr;
+	char				read_buf[20];
+	unsigned int			read_buf_len;
+#endif
 };
 
 #define to_iio_dev_opaque(indio_dev)		\
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index c2f6d9ef213a..36915282269b 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -520,8 +520,6 @@ struct iio_buffer_setup_ops {
  * @groups:		[INTERN] attribute groups
  * @groupcounter:	[INTERN] index of next attribute group
  * @flags:		[INTERN] file ops related flags including busy flag.
- * @debugfs_dentry:	[INTERN] device specific debugfs dentry.
- * @cached_reg_addr:	[INTERN] cached register address for debugfs reads.
  * @priv:		[DRIVER] reference to driver's private information
  *			**MUST** be accessed **ONLY** via iio_priv() helper
  */
@@ -567,12 +565,6 @@ struct iio_dev {
 	int				groupcounter;
 
 	unsigned long			flags;
-#if defined(CONFIG_DEBUG_FS)
-	struct dentry			*debugfs_dentry;
-	unsigned			cached_reg_addr;
-	char				read_buf[20];
-	unsigned int			read_buf_len;
-#endif
 	void				*priv;
 };
 
@@ -733,10 +725,7 @@ static inline bool iio_buffer_enabled(struct iio_dev *indio_dev)
  * @indio_dev:		IIO device structure for device
  **/
 #if defined(CONFIG_DEBUG_FS)
-static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
-{
-	return indio_dev->debugfs_dentry;
-}
+struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev);
 #else
 static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
 {
-- 
cgit v1.2.3


From 207c2d27a010c0154691833960756b60816fe59d Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 30 Jun 2020 07:57:06 +0300
Subject: iio: core: move channel list & group to private iio device object

This change bit straightforward and simple, since the
'channel_attr_list' & 'chan_attr_group' fields are only used in
'industrialio-core.c'.

This change moves to the private IIO device object

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 46 +++++++++++++++++++++++------------------
 include/linux/iio/iio-opaque.h  |  5 +++++
 include/linux/iio/iio.h         |  5 -----
 3 files changed, 31 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index bb2771974404..1629559e680e 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1137,6 +1137,7 @@ static int iio_device_add_info_mask_type(struct iio_dev *indio_dev,
 					 enum iio_shared_by shared_by,
 					 const long *infomask)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	int i, ret, attrcount = 0;
 
 	for_each_set_bit(i, infomask, sizeof(*infomask)*8) {
@@ -1149,7 +1150,7 @@ static int iio_device_add_info_mask_type(struct iio_dev *indio_dev,
 					     i,
 					     shared_by,
 					     &indio_dev->dev,
-					     &indio_dev->channel_attr_list);
+					     &iio_dev_opaque->channel_attr_list);
 		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
 			continue;
 		else if (ret < 0)
@@ -1165,6 +1166,7 @@ static int iio_device_add_info_mask_type_avail(struct iio_dev *indio_dev,
 					       enum iio_shared_by shared_by,
 					       const long *infomask)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	int i, ret, attrcount = 0;
 	char *avail_postfix;
 
@@ -1184,7 +1186,7 @@ static int iio_device_add_info_mask_type_avail(struct iio_dev *indio_dev,
 					     i,
 					     shared_by,
 					     &indio_dev->dev,
-					     &indio_dev->channel_attr_list);
+					     &iio_dev_opaque->channel_attr_list);
 		kfree(avail_postfix);
 		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
 			continue;
@@ -1199,6 +1201,7 @@ static int iio_device_add_info_mask_type_avail(struct iio_dev *indio_dev,
 static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
 					struct iio_chan_spec const *chan)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	int ret, attrcount = 0;
 	const struct iio_chan_spec_ext_info *ext_info;
 
@@ -1274,7 +1277,7 @@ static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
 					i,
 					ext_info->shared,
 					&indio_dev->dev,
-					&indio_dev->channel_attr_list);
+					&iio_dev_opaque->channel_attr_list);
 			i++;
 			if (ret == -EBUSY && ext_info->shared)
 				continue;
@@ -1409,6 +1412,7 @@ static DEVICE_ATTR(current_timestamp_clock, S_IRUGO | S_IWUSR,
 
 static int iio_device_register_sysfs(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	int i, ret = 0, attrcount, attrn, attrcount_orig = 0;
 	struct iio_dev_attr *p;
 	struct attribute **attr, *clk = NULL;
@@ -1448,47 +1452,49 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev)
 	if (clk)
 		attrcount++;
 
-	indio_dev->chan_attr_group.attrs = kcalloc(attrcount + 1,
-						   sizeof(indio_dev->chan_attr_group.attrs[0]),
-						   GFP_KERNEL);
-	if (indio_dev->chan_attr_group.attrs == NULL) {
+	iio_dev_opaque->chan_attr_group.attrs =
+		kcalloc(attrcount + 1,
+			sizeof(iio_dev_opaque->chan_attr_group.attrs[0]),
+			GFP_KERNEL);
+	if (iio_dev_opaque->chan_attr_group.attrs == NULL) {
 		ret = -ENOMEM;
 		goto error_clear_attrs;
 	}
 	/* Copy across original attributes */
 	if (indio_dev->info->attrs)
-		memcpy(indio_dev->chan_attr_group.attrs,
+		memcpy(iio_dev_opaque->chan_attr_group.attrs,
 		       indio_dev->info->attrs->attrs,
-		       sizeof(indio_dev->chan_attr_group.attrs[0])
+		       sizeof(iio_dev_opaque->chan_attr_group.attrs[0])
 		       *attrcount_orig);
 	attrn = attrcount_orig;
 	/* Add all elements from the list. */
-	list_for_each_entry(p, &indio_dev->channel_attr_list, l)
-		indio_dev->chan_attr_group.attrs[attrn++] = &p->dev_attr.attr;
+	list_for_each_entry(p, &iio_dev_opaque->channel_attr_list, l)
+		iio_dev_opaque->chan_attr_group.attrs[attrn++] = &p->dev_attr.attr;
 	if (indio_dev->name)
-		indio_dev->chan_attr_group.attrs[attrn++] = &dev_attr_name.attr;
+		iio_dev_opaque->chan_attr_group.attrs[attrn++] = &dev_attr_name.attr;
 	if (indio_dev->label)
-		indio_dev->chan_attr_group.attrs[attrn++] = &dev_attr_label.attr;
+		iio_dev_opaque->chan_attr_group.attrs[attrn++] = &dev_attr_label.attr;
 	if (clk)
-		indio_dev->chan_attr_group.attrs[attrn++] = clk;
+		iio_dev_opaque->chan_attr_group.attrs[attrn++] = clk;
 
 	indio_dev->groups[indio_dev->groupcounter++] =
-		&indio_dev->chan_attr_group;
+		&iio_dev_opaque->chan_attr_group;
 
 	return 0;
 
 error_clear_attrs:
-	iio_free_chan_devattr_list(&indio_dev->channel_attr_list);
+	iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list);
 
 	return ret;
 }
 
 static void iio_device_unregister_sysfs(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 
-	iio_free_chan_devattr_list(&indio_dev->channel_attr_list);
-	kfree(indio_dev->chan_attr_group.attrs);
-	indio_dev->chan_attr_group.attrs = NULL;
+	iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list);
+	kfree(iio_dev_opaque->chan_attr_group.attrs);
+	iio_dev_opaque->chan_attr_group.attrs = NULL;
 }
 
 static void iio_dev_release(struct device *device)
@@ -1543,7 +1549,7 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 	dev_set_drvdata(&dev->dev, (void *)dev);
 	mutex_init(&dev->mlock);
 	mutex_init(&dev->info_exist_lock);
-	INIT_LIST_HEAD(&dev->channel_attr_list);
+	INIT_LIST_HEAD(&iio_dev_opaque->channel_attr_list);
 
 	dev->id = ida_simple_get(&iio_ida, 0, 0, GFP_KERNEL);
 	if (dev->id < 0) {
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index b3f234b4c1e9..9419a05c698d 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -6,6 +6,9 @@
 /**
  * struct iio_dev_opaque - industrial I/O device opaque information
  * @indio_dev:			public industrial I/O device information
+ * @channel_attr_list:		keep track of automatically created channel
+ *				attributes
+ * @chan_attr_group:		group for all attrs in base directory
  * @debugfs_dentry:		device specific debugfs dentry
  * @cached_reg_addr:		cached register address for debugfs reads
  * @read_buf:			read buffer to be used for the initial reg read
@@ -13,6 +16,8 @@
  */
 struct iio_dev_opaque {
 	struct iio_dev			indio_dev;
+	struct list_head		channel_attr_list;
+	struct attribute_group		chan_attr_group;
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_dentry;
 	unsigned			cached_reg_addr;
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 36915282269b..61c4bf9c03ec 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -506,9 +506,6 @@ struct iio_buffer_setup_ops {
  * @pollfunc_event:	[DRIVER] function run on events trigger being received
  * @channels:		[DRIVER] channel specification structure table
  * @num_channels:	[DRIVER] number of channels specified in @channels.
- * @channel_attr_list:	[INTERN] keep track of automatically created channel
- *			attributes
- * @chan_attr_group:	[INTERN] group for all attrs in base directory
  * @name:		[DRIVER] name of the device.
  * @label:              [DRIVER] unique name to identify which device this is
  * @info:		[DRIVER] callbacks and constant info from driver
@@ -551,8 +548,6 @@ struct iio_dev {
 	struct iio_chan_spec const	*channels;
 	int				num_channels;
 
-	struct list_head		channel_attr_list;
-	struct attribute_group		chan_attr_group;
 	const char			*name;
 	const char			*label;
 	const struct iio_info		*info;
-- 
cgit v1.2.3


From 6a8c6b26f7531a85803380911c7c4a05a639afbe Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 30 Jun 2020 07:57:07 +0300
Subject: iio: core: move iio_dev's buffer_list to the private iio device
 object

This change moves the 'buffer_list' away from the public IIO device object
into the private part.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 38 ++++++++++++++++++++++++--------------
 drivers/iio/industrialio-core.c   |  2 +-
 include/linux/iio/iio-opaque.h    |  2 ++
 include/linux/iio/iio.h           |  2 --
 4 files changed, 27 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 329dd4d6757a..2aec8b85f40d 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -19,6 +19,7 @@
 #include <linux/sched/signal.h>
 
 #include <linux/iio/iio.h>
+#include <linux/iio/iio-opaque.h>
 #include "iio_core.h"
 #include "iio_core_trigger.h"
 #include <linux/iio/sysfs.h>
@@ -599,8 +600,10 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
 static void iio_buffer_activate(struct iio_dev *indio_dev,
 	struct iio_buffer *buffer)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
 	iio_buffer_get(buffer);
-	list_add(&buffer->buffer_list, &indio_dev->buffer_list);
+	list_add(&buffer->buffer_list, &iio_dev_opaque->buffer_list);
 }
 
 static void iio_buffer_deactivate(struct iio_buffer *buffer)
@@ -612,10 +615,11 @@ static void iio_buffer_deactivate(struct iio_buffer *buffer)
 
 static void iio_buffer_deactivate_all(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_buffer *buffer, *_buffer;
 
 	list_for_each_entry_safe(buffer, _buffer,
-			&indio_dev->buffer_list, buffer_list)
+			&iio_dev_opaque->buffer_list, buffer_list)
 		iio_buffer_deactivate(buffer);
 }
 
@@ -688,6 +692,7 @@ static int iio_verify_update(struct iio_dev *indio_dev,
 	struct iio_buffer *insert_buffer, struct iio_buffer *remove_buffer,
 	struct iio_device_config *config)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	unsigned long *compound_mask;
 	const unsigned long *scan_mask;
 	bool strict_scanmask = false;
@@ -710,12 +715,12 @@ static int iio_verify_update(struct iio_dev *indio_dev,
 	 * to verify.
 	 */
 	if (remove_buffer && !insert_buffer &&
-		list_is_singular(&indio_dev->buffer_list))
+		list_is_singular(&iio_dev_opaque->buffer_list))
 			return 0;
 
 	modes = indio_dev->modes;
 
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list) {
 		if (buffer == remove_buffer)
 			continue;
 		modes &= buffer->access->modes;
@@ -736,7 +741,7 @@ static int iio_verify_update(struct iio_dev *indio_dev,
 		 * Keep things simple for now and only allow a single buffer to
 		 * be connected in hardware mode.
 		 */
-		if (insert_buffer && !list_empty(&indio_dev->buffer_list))
+		if (insert_buffer && !list_empty(&iio_dev_opaque->buffer_list))
 			return -EINVAL;
 		config->mode = INDIO_BUFFER_HARDWARE;
 		strict_scanmask = true;
@@ -756,7 +761,7 @@ static int iio_verify_update(struct iio_dev *indio_dev,
 
 	scan_timestamp = false;
 
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list) {
 		if (buffer == remove_buffer)
 			continue;
 		bitmap_or(compound_mask, compound_mask, buffer->scan_mask,
@@ -902,10 +907,11 @@ error_clear_mux_table:
 
 static int iio_update_demux(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_buffer *buffer;
 	int ret;
 
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list) {
 		ret = iio_buffer_update_demux(indio_dev, buffer);
 		if (ret < 0)
 			goto error_clear_mux_table;
@@ -913,7 +919,7 @@ static int iio_update_demux(struct iio_dev *indio_dev)
 	return 0;
 
 error_clear_mux_table:
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list)
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list)
 		iio_buffer_demux_free(buffer);
 
 	return ret;
@@ -922,6 +928,7 @@ error_clear_mux_table:
 static int iio_enable_buffers(struct iio_dev *indio_dev,
 	struct iio_device_config *config)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_buffer *buffer;
 	int ret;
 
@@ -958,7 +965,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 		indio_dev->info->hwfifo_set_watermark(indio_dev,
 			config->watermark);
 
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list) {
 		ret = iio_buffer_enable(buffer, indio_dev);
 		if (ret)
 			goto err_disable_buffers;
@@ -983,7 +990,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 	return 0;
 
 err_disable_buffers:
-	list_for_each_entry_continue_reverse(buffer, &indio_dev->buffer_list,
+	list_for_each_entry_continue_reverse(buffer, &iio_dev_opaque->buffer_list,
 					     buffer_list)
 		iio_buffer_disable(buffer, indio_dev);
 err_run_postdisable:
@@ -998,12 +1005,13 @@ err_undo_config:
 
 static int iio_disable_buffers(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_buffer *buffer;
 	int ret = 0;
 	int ret2;
 
 	/* Wind down existing buffers - iff there are any */
-	if (list_empty(&indio_dev->buffer_list))
+	if (list_empty(&iio_dev_opaque->buffer_list))
 		return 0;
 
 	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
@@ -1024,7 +1032,7 @@ static int iio_disable_buffers(struct iio_dev *indio_dev)
 			ret = ret2;
 	}
 
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buffer, &iio_dev_opaque->buffer_list, buffer_list) {
 		ret2 = iio_buffer_disable(buffer, indio_dev);
 		if (ret2 && !ret)
 			ret = ret2;
@@ -1047,6 +1055,7 @@ static int __iio_update_buffers(struct iio_dev *indio_dev,
 		       struct iio_buffer *insert_buffer,
 		       struct iio_buffer *remove_buffer)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_device_config new_config;
 	int ret;
 
@@ -1071,7 +1080,7 @@ static int __iio_update_buffers(struct iio_dev *indio_dev,
 		iio_buffer_activate(indio_dev, insert_buffer);
 
 	/* If no buffers in list, we are done */
-	if (list_empty(&indio_dev->buffer_list))
+	if (list_empty(&iio_dev_opaque->buffer_list))
 		return 0;
 
 	ret = iio_enable_buffers(indio_dev, &new_config);
@@ -1420,10 +1429,11 @@ static int iio_push_to_buffer(struct iio_buffer *buffer, const void *data)
  */
 int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	int ret;
 	struct iio_buffer *buf;
 
-	list_for_each_entry(buf, &indio_dev->buffer_list, buffer_list) {
+	list_for_each_entry(buf, &iio_dev_opaque->buffer_list, buffer_list) {
 		ret = iio_push_to_buffer(buf, data);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 1629559e680e..fab5720a7901 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1559,7 +1559,7 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 		return NULL;
 	}
 	dev_set_name(&dev->dev, "iio:device%d", dev->id);
-	INIT_LIST_HEAD(&dev->buffer_list);
+	INIT_LIST_HEAD(&iio_dev_opaque->buffer_list);
 
 	return dev;
 }
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index 9419a05c698d..af6c69a40169 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -6,6 +6,7 @@
 /**
  * struct iio_dev_opaque - industrial I/O device opaque information
  * @indio_dev:			public industrial I/O device information
+ * @buffer_list:		list of all buffers currently attached
  * @channel_attr_list:		keep track of automatically created channel
  *				attributes
  * @chan_attr_group:		group for all attrs in base directory
@@ -16,6 +17,7 @@
  */
 struct iio_dev_opaque {
 	struct iio_dev			indio_dev;
+	struct list_head		buffer_list;
 	struct list_head		channel_attr_list;
 	struct attribute_group		chan_attr_group;
 #if defined(CONFIG_DEBUG_FS)
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 61c4bf9c03ec..a0110b1e29fe 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -490,7 +490,6 @@ struct iio_buffer_setup_ops {
  *			and owner
  * @event_interface:	[INTERN] event chrdevs associated with interrupt lines
  * @buffer:		[DRIVER] any buffer present
- * @buffer_list:	[INTERN] list of all buffers currently attached
  * @scan_bytes:		[INTERN] num bytes captured to be fed to buffer demux
  * @mlock:		[INTERN] lock used to prevent simultaneous device state
  *			changes
@@ -531,7 +530,6 @@ struct iio_dev {
 	struct iio_event_interface	*event_interface;
 
 	struct iio_buffer		*buffer;
-	struct list_head		buffer_list;
 	int				scan_bytes;
 	struct mutex			mlock;
 
-- 
cgit v1.2.3


From fa83c3baa539a7ec734c7ee65fad499122f427d7 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 30 Jun 2020 07:57:08 +0300
Subject: iio: core: move event interface on the opaque struct

Same as with other private fields, this moves the event interface reference
to the opaque IIO device object, to be invisible to drivers.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c  |  5 +--
 drivers/iio/industrialio-event.c | 68 +++++++++++++++++++++++-----------------
 include/linux/iio/iio-opaque.h   |  2 ++
 include/linux/iio/iio.h          |  3 --
 4 files changed, 45 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index fab5720a7901..ef5e23c33c9d 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -211,7 +211,8 @@ EXPORT_SYMBOL(iio_read_const_attr);
 int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id)
 {
 	int ret;
-	const struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	const struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 
 	ret = mutex_lock_interruptible(&indio_dev->mlock);
 	if (ret)
@@ -1442,7 +1443,7 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev)
 			attrcount += ret;
 		}
 
-	if (indio_dev->event_interface)
+	if (iio_dev_opaque->event_interface)
 		clk = &dev_attr_current_timestamp_clock.attr;
 
 	if (indio_dev->name)
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 5b17c92d3b50..2ab4d4c44427 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>
 #include <linux/wait.h>
 #include <linux/iio/iio.h>
+#include <linux/iio/iio-opaque.h>
 #include "iio_core.h"
 #include <linux/iio/sysfs.h>
 #include <linux/iio/events.h>
@@ -62,7 +63,8 @@ bool iio_event_enabled(const struct iio_event_interface *ev_int)
  **/
 int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp)
 {
-	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 	struct iio_event_data ev;
 	int copied;
 
@@ -96,7 +98,8 @@ static __poll_t iio_event_poll(struct file *filep,
 			     struct poll_table_struct *wait)
 {
 	struct iio_dev *indio_dev = filep->private_data;
-	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 	__poll_t events = 0;
 
 	if (!indio_dev->info)
@@ -116,7 +119,8 @@ static ssize_t iio_event_chrdev_read(struct file *filep,
 				     loff_t *f_ps)
 {
 	struct iio_dev *indio_dev = filep->private_data;
-	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 	unsigned int copied;
 	int ret;
 
@@ -165,7 +169,8 @@ static ssize_t iio_event_chrdev_read(struct file *filep,
 static int iio_event_chrdev_release(struct inode *inode, struct file *filep)
 {
 	struct iio_dev *indio_dev = filep->private_data;
-	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 
 	clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags);
 
@@ -184,7 +189,8 @@ static const struct file_operations iio_event_chrdev_fileops = {
 
 int iio_event_getfd(struct iio_dev *indio_dev)
 {
-	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
 	int fd;
 
 	if (ev_int == NULL)
@@ -343,6 +349,7 @@ static int iio_device_add_event(struct iio_dev *indio_dev,
 	enum iio_event_type type, enum iio_event_direction dir,
 	enum iio_shared_by shared_by, const unsigned long *mask)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	ssize_t (*show)(struct device *, struct device_attribute *, char *);
 	ssize_t (*store)(struct device *, struct device_attribute *,
 		const char *, size_t);
@@ -376,7 +383,7 @@ static int iio_device_add_event(struct iio_dev *indio_dev,
 
 		ret = __iio_add_chan_devattr(postfix, chan, show, store,
 			 (i << 16) | spec_index, shared_by, &indio_dev->dev,
-			&indio_dev->event_interface->dev_attr_list);
+			&iio_dev_opaque->event_interface->dev_attr_list);
 		kfree(postfix);
 
 		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
@@ -469,6 +476,7 @@ static void iio_setup_ev_int(struct iio_event_interface *ev_int)
 static const char *iio_event_group_name = "events";
 int iio_device_register_eventset(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_dev_attr *p;
 	int ret = 0, attrcount_orig = 0, attrcount, attrn;
 	struct attribute **attr;
@@ -477,14 +485,14 @@ int iio_device_register_eventset(struct iio_dev *indio_dev)
 	      iio_check_for_dynamic_events(indio_dev)))
 		return 0;
 
-	indio_dev->event_interface =
+	iio_dev_opaque->event_interface =
 		kzalloc(sizeof(struct iio_event_interface), GFP_KERNEL);
-	if (indio_dev->event_interface == NULL)
+	if (iio_dev_opaque->event_interface == NULL)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&indio_dev->event_interface->dev_attr_list);
+	INIT_LIST_HEAD(&iio_dev_opaque->event_interface->dev_attr_list);
 
-	iio_setup_ev_int(indio_dev->event_interface);
+	iio_setup_ev_int(iio_dev_opaque->event_interface);
 	if (indio_dev->info->event_attrs != NULL) {
 		attr = indio_dev->info->event_attrs->attrs;
 		while (*attr++ != NULL)
@@ -498,35 +506,35 @@ int iio_device_register_eventset(struct iio_dev *indio_dev)
 		attrcount += ret;
 	}
 
-	indio_dev->event_interface->group.name = iio_event_group_name;
-	indio_dev->event_interface->group.attrs = kcalloc(attrcount + 1,
-							  sizeof(indio_dev->event_interface->group.attrs[0]),
+	iio_dev_opaque->event_interface->group.name = iio_event_group_name;
+	iio_dev_opaque->event_interface->group.attrs = kcalloc(attrcount + 1,
+							  sizeof(iio_dev_opaque->event_interface->group.attrs[0]),
 							  GFP_KERNEL);
-	if (indio_dev->event_interface->group.attrs == NULL) {
+	if (iio_dev_opaque->event_interface->group.attrs == NULL) {
 		ret = -ENOMEM;
 		goto error_free_setup_event_lines;
 	}
 	if (indio_dev->info->event_attrs)
-		memcpy(indio_dev->event_interface->group.attrs,
+		memcpy(iio_dev_opaque->event_interface->group.attrs,
 		       indio_dev->info->event_attrs->attrs,
-		       sizeof(indio_dev->event_interface->group.attrs[0])
+		       sizeof(iio_dev_opaque->event_interface->group.attrs[0])
 		       *attrcount_orig);
 	attrn = attrcount_orig;
 	/* Add all elements from the list. */
 	list_for_each_entry(p,
-			    &indio_dev->event_interface->dev_attr_list,
+			    &iio_dev_opaque->event_interface->dev_attr_list,
 			    l)
-		indio_dev->event_interface->group.attrs[attrn++] =
+		iio_dev_opaque->event_interface->group.attrs[attrn++] =
 			&p->dev_attr.attr;
 	indio_dev->groups[indio_dev->groupcounter++] =
-		&indio_dev->event_interface->group;
+		&iio_dev_opaque->event_interface->group;
 
 	return 0;
 
 error_free_setup_event_lines:
-	iio_free_chan_devattr_list(&indio_dev->event_interface->dev_attr_list);
-	kfree(indio_dev->event_interface);
-	indio_dev->event_interface = NULL;
+	iio_free_chan_devattr_list(&iio_dev_opaque->event_interface->dev_attr_list);
+	kfree(iio_dev_opaque->event_interface);
+	iio_dev_opaque->event_interface = NULL;
 	return ret;
 }
 
@@ -539,16 +547,20 @@ error_free_setup_event_lines:
  */
 void iio_device_wakeup_eventset(struct iio_dev *indio_dev)
 {
-	if (indio_dev->event_interface == NULL)
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	if (iio_dev_opaque->event_interface == NULL)
 		return;
-	wake_up(&indio_dev->event_interface->wait);
+	wake_up(&iio_dev_opaque->event_interface->wait);
 }
 
 void iio_device_unregister_eventset(struct iio_dev *indio_dev)
 {
-	if (indio_dev->event_interface == NULL)
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	if (iio_dev_opaque->event_interface == NULL)
 		return;
-	iio_free_chan_devattr_list(&indio_dev->event_interface->dev_attr_list);
-	kfree(indio_dev->event_interface->group.attrs);
-	kfree(indio_dev->event_interface);
+	iio_free_chan_devattr_list(&iio_dev_opaque->event_interface->dev_attr_list);
+	kfree(iio_dev_opaque->event_interface->group.attrs);
+	kfree(iio_dev_opaque->event_interface);
 }
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index af6c69a40169..f2e94196d31f 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -6,6 +6,7 @@
 /**
  * struct iio_dev_opaque - industrial I/O device opaque information
  * @indio_dev:			public industrial I/O device information
+ * @event_interface:		event chrdevs associated with interrupt lines
  * @buffer_list:		list of all buffers currently attached
  * @channel_attr_list:		keep track of automatically created channel
  *				attributes
@@ -17,6 +18,7 @@
  */
 struct iio_dev_opaque {
 	struct iio_dev			indio_dev;
+	struct iio_event_interface	*event_interface;
 	struct list_head		buffer_list;
 	struct list_head		channel_attr_list;
 	struct attribute_group		chan_attr_group;
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index a0110b1e29fe..30c9c9502478 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -488,7 +488,6 @@ struct iio_buffer_setup_ops {
  * @currentmode:	[DRIVER] current operating mode
  * @dev:		[DRIVER] device structure, should be assigned a parent
  *			and owner
- * @event_interface:	[INTERN] event chrdevs associated with interrupt lines
  * @buffer:		[DRIVER] any buffer present
  * @scan_bytes:		[INTERN] num bytes captured to be fed to buffer demux
  * @mlock:		[INTERN] lock used to prevent simultaneous device state
@@ -527,8 +526,6 @@ struct iio_dev {
 	int				currentmode;
 	struct device			dev;
 
-	struct iio_event_interface	*event_interface;
-
 	struct iio_buffer		*buffer;
 	int				scan_bytes;
 	struct mutex			mlock;
-- 
cgit v1.2.3


From 3970ed49a46bd0b062870edcc0894b2bd820371d Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 7 Jul 2020 03:49:35 +0200
Subject: net: phy: Properly define genphy_c45_driver

Avoid the W=1 warning that symbol 'genphy_c45_driver' was not
declared. Should it be static?

Declare it on the phy header file.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 1 -
 include/linux/phy.h          | 3 +++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index eb1068a77ce1..98be28567c65 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -227,7 +227,6 @@ static void phy_mdio_device_remove(struct mdio_device *mdiodev)
 }
 
 static struct phy_driver genphy_driver;
-extern struct phy_driver genphy_c45_driver;
 
 static LIST_HEAD(phy_fixup_list);
 static DEFINE_MUTEX(phy_fixup_lock);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 101a48fa6750..1592c3d0e12f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1385,6 +1385,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
 int genphy_c45_config_aneg(struct phy_device *phydev);
 
+/* Generic C45 PHY driver */
+extern struct phy_driver genphy_c45_driver;
+
 /* The gen10g_* functions are the old Clause 45 stub */
 int gen10g_config_aneg(struct phy_device *phydev);
 
-- 
cgit v1.2.3


From ad0f75e5f57ccbceec13274e1e242f2b5a6397ed Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Jul 2020 11:52:56 -0700
Subject: cgroup: fix cgroup_sk_alloc() for sk_clone_lock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When we clone a socket in sk_clone_lock(), its sk_cgrp_data is
copied, so the cgroup refcnt must be taken too. And, unlike the
sk_alloc() path, sock_update_netprioidx() is not called here.
Therefore, it is safe and necessary to grab the cgroup refcnt
even when cgroup_sk_alloc is disabled.

sk_clone_lock() is in BH context anyway, the in_interrupt()
would terminate this function if called there. And for sk_alloc()
skcd->val is always zero. So it's safe to factor out the code
to make it more readable.

The global variable 'cgroup_sk_alloc_disabled' is used to determine
whether to take these reference counts. It is impossible to make
the reference counting correct unless we save this bit of information
in skcd->val. So, add a new bit there to record whether the socket
has already taken the reference counts. This obviously relies on
kmalloc() to align cgroup pointers to at least 4 bytes,
ARCH_KMALLOC_MINALIGN is certainly larger than that.

This bug seems to be introduced since the beginning, commit
d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
tried to fix it but not compeletely. It seems not easy to trigger until
the recent commit 090e28b229af
("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Cameron Berkenpas <cam@neo-zeon.de>
Reported-by: Peter Geis <pgwipeout@gmail.com>
Reported-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reported-by: Daniël Sonck <dsonck92@gmail.com>
Reported-by: Zhang Qiang <qiang.zhang@windriver.com>
Tested-by: Cameron Berkenpas <cam@neo-zeon.de>
Tested-by: Peter Geis <pgwipeout@gmail.com>
Tested-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Zefan Li <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h |  6 ++++--
 include/linux/cgroup.h      |  4 +++-
 kernel/cgroup/cgroup.c      | 31 +++++++++++++++++++------------
 net/core/sock.c             |  2 +-
 4 files changed, 27 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 52661155f85f..4f1cd0edc57d 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -790,7 +790,8 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -800,7 +801,8 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4598e4da6b1b..618838c48313 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1ea181a58465..dd247747ec14 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6439,18 +6439,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -6475,10 +6465,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
+	if (skcd->no_refcnt)
+		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index d832c650287c..2e5b7870e5d3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1926,7 +1926,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		/* sk->sk_memcg will be populated at accept() time */
 		newsk->sk_memcg = NULL;
 
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
-- 
cgit v1.2.3


From 41da51bce36f44eefc1e3d0f47d18841cbd065ba Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 21 Nov 2019 23:25:07 +0000
Subject: fs: Add IOCB_NOIO flag for generic_file_read_iter

Add an IOCB_NOIO flag that indicates to generic_file_read_iter that it
shouldn't trigger any filesystem I/O for the actual request or for
readahead.  This allows to do tentative reads out of the page cache as
some filesystems allow, and to take the appropriate locks and retry the
reads only if the requested pages are not cached.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 include/linux/fs.h |  1 +
 mm/filemap.c       | 23 +++++++++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..4b7cb76e5837 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -315,6 +315,7 @@ enum rw_hint {
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
 #define IOCB_NOWAIT		(1 << 7)
+#define IOCB_NOIO		(1 << 9)
 
 struct kiocb {
 	struct file		*ki_filp;
diff --git a/mm/filemap.c b/mm/filemap.c
index f0ae9a6308cb..385759c4ce4b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2028,7 +2028,7 @@ find_page:
 
 		page = find_get_page(mapping, index);
 		if (!page) {
-			if (iocb->ki_flags & IOCB_NOWAIT)
+			if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
 				goto would_block;
 			page_cache_sync_readahead(mapping,
 					ra, filp,
@@ -2038,6 +2038,10 @@ find_page:
 				goto no_cached_page;
 		}
 		if (PageReadahead(page)) {
+			if (iocb->ki_flags & IOCB_NOIO) {
+				put_page(page);
+				goto out;
+			}
 			page_cache_async_readahead(mapping,
 					ra, filp, page,
 					index, last_index - index);
@@ -2160,6 +2164,11 @@ page_not_up_to_date_locked:
 		}
 
 readpage:
+		if (iocb->ki_flags & IOCB_NOIO) {
+			unlock_page(page);
+			put_page(page);
+			goto would_block;
+		}
 		/*
 		 * A previous I/O error may have been due to temporary
 		 * failures, eg. multipath errors.
@@ -2249,9 +2258,19 @@ EXPORT_SYMBOL_GPL(generic_file_buffered_read);
  *
  * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
+ * be returned when no data can be read without waiting for I/O requests
+ * to complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
+ * requests shall be made for the read or for readahead.  When no data
+ * can be read, -EAGAIN shall be returned.  When readahead would be
+ * triggered, a partial, possibly empty read shall be returned.
+ *
  * Return:
  * * number of bytes copied, even for partial reads
- * * negative error code if nothing was read
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
  */
 ssize_t
 generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
-- 
cgit v1.2.3


From 16d79cd4e23b1964d36c041ab027505ceacbbeeb Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Thu, 2 Jul 2020 18:26:49 +0200
Subject: PCI: Use 'pci_channel_state_t' instead of 'enum pci_channel_state'

The method struct pci_error_handlers.error_detected() is defined and
documented as taking an 'enum pci_channel_state' for the second argument,
but most drivers use 'pci_channel_state_t' instead.

This 'pci_channel_state_t' is not a typedef for the enum but a typedef for
a bitwise type in order to have better/stricter typechecking.

Consolidate everything by using 'pci_channel_state_t' in the method's
definition, in the related helpers and in the drivers.

Enforce use of 'pci_channel_state_t' by replacing 'enum pci_channel_state'
with an anonymous 'enum'.

Note: Currently, from a typechecking point of view this patch changes
nothing because only the constants defined by the enum are bitwise, not the
enum itself (sparse doesn't have the notion of 'bitwise enum'). This may
change in some not too far future, hence the patch.

[bhelgaas: squash in
  https://lore.kernel.org/r/20200702162651.49526-3-luc.vanoostenryck@gmail.com
  https://lore.kernel.org/r/20200702162651.49526-4-luc.vanoostenryck@gmail.com]
Link: https://lore.kernel.org/r/20200702162651.49526-2-luc.vanoostenryck@gmail.com
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 Documentation/PCI/pci-error-recovery.rst    | 8 ++++----
 arch/powerpc/kernel/eeh_driver.c            | 2 +-
 drivers/block/rsxx/core.c                   | 2 +-
 drivers/dma/ioat/init.c                     | 2 +-
 drivers/media/pci/ngene/ngene-cards.c       | 2 +-
 drivers/misc/genwqe/card_base.c             | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 drivers/net/ethernet/intel/ice/ice_main.c   | 2 +-
 drivers/net/ethernet/intel/ixgb/ixgb_main.c | 4 ++--
 drivers/net/ethernet/sfc/efx.c              | 2 +-
 drivers/net/ethernet/sfc/falcon/efx.c       | 2 +-
 drivers/pci/pci.h                           | 2 +-
 drivers/pci/pcie/err.c                      | 4 ++--
 drivers/pci/pcie/portdrv_pci.c              | 2 +-
 drivers/scsi/aacraid/linit.c                | 2 +-
 drivers/scsi/sym53c8xx_2/sym_glue.c         | 2 +-
 drivers/staging/qlge/qlge_main.c            | 2 +-
 include/linux/pci.h                         | 4 ++--
 18 files changed, 24 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/PCI/pci-error-recovery.rst b/Documentation/PCI/pci-error-recovery.rst
index 13beee23cb04..ccd713423133 100644
--- a/Documentation/PCI/pci-error-recovery.rst
+++ b/Documentation/PCI/pci-error-recovery.rst
@@ -79,7 +79,7 @@ This structure has the form::
 
 	struct pci_error_handlers
 	{
-		int (*error_detected)(struct pci_dev *dev, enum pci_channel_state);
+		int (*error_detected)(struct pci_dev *dev, pci_channel_state_t);
 		int (*mmio_enabled)(struct pci_dev *dev);
 		int (*slot_reset)(struct pci_dev *dev);
 		void (*resume)(struct pci_dev *dev);
@@ -87,11 +87,11 @@ This structure has the form::
 
 The possible channel states are::
 
-	enum pci_channel_state {
+	typedef enum {
 		pci_channel_io_normal,  /* I/O channel is in normal state */
 		pci_channel_io_frozen,  /* I/O to channel is blocked */
 		pci_channel_io_perm_failure, /* PCI card is dead */
-	};
+	} pci_channel_state_t;
 
 Possible return values are::
 
@@ -348,7 +348,7 @@ STEP 6: Permanent Failure
 -------------------------
 A "permanent failure" has occurred, and the platform cannot recover
 the device.  The platform will call error_detected() with a
-pci_channel_state value of pci_channel_io_perm_failure.
+pci_channel_state_t value of pci_channel_io_perm_failure.
 
 The device driver should, at this point, assume the worst. It should
 cancel all pending I/O, refuse all new I/O, returning -EIO to
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7b048cee767c..ab8806d2e03e 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -214,7 +214,7 @@ static void eeh_dev_save_state(struct eeh_dev *edev, void *userdata)
 	pci_save_state(pdev);
 }
 
-static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s)
+static void eeh_set_channel_state(struct eeh_pe *root, pci_channel_state_t s)
 {
 	struct eeh_pe *pe;
 	struct eeh_dev *edev, *tmp;
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 10f6368117d8..34e937dd6bca 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -625,7 +625,7 @@ static int rsxx_eeh_fifo_flush_poll(struct rsxx_cardinfo *card)
 }
 
 static pci_ers_result_t rsxx_error_detected(struct pci_dev *dev,
-					    enum pci_channel_state error)
+					    pci_channel_state_t error)
 {
 	int st;
 
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 58d13564f88b..089893f2bbb8 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -1267,7 +1267,7 @@ static void ioat_resume(struct ioatdma_device *ioat_dma)
 #define DRV_NAME "ioatdma"
 
 static pci_ers_result_t ioat_pcie_error_detected(struct pci_dev *pdev,
-						 enum pci_channel_state error)
+						 pci_channel_state_t error)
 {
 	dev_dbg(&pdev->dev, "%s: PCIe AER error %d\n", DRV_NAME, error);
 
diff --git a/drivers/media/pci/ngene/ngene-cards.c b/drivers/media/pci/ngene/ngene-cards.c
index 6185806a00e0..8bfb3d8ea610 100644
--- a/drivers/media/pci/ngene/ngene-cards.c
+++ b/drivers/media/pci/ngene/ngene-cards.c
@@ -1186,7 +1186,7 @@ MODULE_DEVICE_TABLE(pci, ngene_id_tbl);
 /****************************************************************************/
 
 static pci_ers_result_t ngene_error_detected(struct pci_dev *dev,
-					     enum pci_channel_state state)
+					     pci_channel_state_t state)
 {
 	dev_err(&dev->dev, "PCI error\n");
 	if (state == pci_channel_io_perm_failure)
diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c
index 1dc6c7c5cbce..97b8ecc42383 100644
--- a/drivers/misc/genwqe/card_base.c
+++ b/drivers/misc/genwqe/card_base.c
@@ -1240,7 +1240,7 @@ static void genwqe_remove(struct pci_dev *pci_dev)
  * error is detected.
  */
 static pci_ers_result_t genwqe_err_error_detected(struct pci_dev *pci_dev,
-						 enum pci_channel_state state)
+						 pci_channel_state_t state)
 {
 	struct genwqe_dev *cd;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5d807c8004f8..f0de2d1842b4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -15465,7 +15465,7 @@ unmap:
  * remediation.
  **/
 static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
-						enum pci_channel_state error)
+						pci_channel_state_t error)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 082825e3cb39..4dd9226a12df 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3586,7 +3586,7 @@ static void ice_remove(struct pci_dev *pdev)
  * is in progress.  Allows the driver to gracefully prepare/handle PCI errors.
  */
 static pci_ers_result_t
-ice_pci_err_detected(struct pci_dev *pdev, enum pci_channel_state err)
+ice_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t err)
 {
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index b64e91ea3465..00db4b5863b1 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -82,7 +82,7 @@ static int ixgb_vlan_rx_kill_vid(struct net_device *netdev,
 static void ixgb_restore_vlan(struct ixgb_adapter *adapter);
 
 static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev,
-                             enum pci_channel_state state);
+                             pci_channel_state_t state);
 static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev);
 static void ixgb_io_resume (struct pci_dev *pdev);
 
@@ -2194,7 +2194,7 @@ ixgb_restore_vlan(struct ixgb_adapter *adapter)
  * a PCI bus error is detected.
  */
 static pci_ers_result_t ixgb_io_error_detected(struct pci_dev *pdev,
-                                               enum pci_channel_state state)
+                                               pci_channel_state_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 256807c28ff7..ed627aff7b36 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1519,7 +1519,7 @@ static const struct dev_pm_ops efx_pm_ops = {
  * Stop the software path and request a slot reset.
  */
 static pci_ers_result_t efx_io_error_detected(struct pci_dev *pdev,
-					      enum pci_channel_state state)
+					      pci_channel_state_t state)
 {
 	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
 	struct efx_nic *efx = pci_get_drvdata(pdev);
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 42bcd34fc508..f8979991970e 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -3118,7 +3118,7 @@ static const struct dev_pm_ops ef4_pm_ops = {
  * Stop the software path and request a slot reset.
  */
 static pci_ers_result_t ef4_io_error_detected(struct pci_dev *pdev,
-					      enum pci_channel_state state)
+					      pci_channel_state_t state)
 {
 	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
 	struct ef4_nic *efx = pci_get_drvdata(pdev);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6d3f75867106..c6c0c455f59f 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -555,7 +555,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
 
 /* PCI error reporting and recovery */
 pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
-			enum pci_channel_state state,
+			pci_channel_state_t state,
 			pci_ers_result_t (*reset_link)(struct pci_dev *pdev));
 
 bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 14bb8f54723e..467686ee2d8b 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -46,7 +46,7 @@ static pci_ers_result_t merge_result(enum pci_ers_result orig,
 }
 
 static int report_error_detected(struct pci_dev *dev,
-				 enum pci_channel_state state,
+				 pci_channel_state_t state,
 				 enum pci_ers_result *result)
 {
 	pci_ers_result_t vote;
@@ -147,7 +147,7 @@ out:
 }
 
 pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
-			enum pci_channel_state state,
+			pci_channel_state_t state,
 			pci_ers_result_t (*reset_link)(struct pci_dev *pdev))
 {
 	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 3acf151ae015..3a3ce40ae1ab 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -146,7 +146,7 @@ static void pcie_portdrv_remove(struct pci_dev *dev)
 }
 
 static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
-					enum pci_channel_state error)
+					pci_channel_state_t error)
 {
 	/* Root Port has no impact. Always recovers. */
 	return PCI_ERS_RESULT_CAN_RECOVER;
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index a308e86a97f1..37f65602b0ec 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -2002,7 +2002,7 @@ static void aac_remove_one(struct pci_dev *pdev)
 }
 
 static pci_ers_result_t aac_pci_error_detected(struct pci_dev *pdev,
-					enum pci_channel_state error)
+					pci_channel_state_t error)
 {
 	struct Scsi_Host *shost = pci_get_drvdata(pdev);
 	struct aac_dev *aac = shost_priv(shost);
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index 2ca018ce796f..f455243bdb9b 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -1743,7 +1743,7 @@ static void sym2_remove(struct pci_dev *pdev)
  * @state: current state of the PCI slot
  */
 static pci_ers_result_t sym2_io_error_detected(struct pci_dev *pdev,
-                                         enum pci_channel_state state)
+                                         pci_channel_state_t state)
 {
 	/* If slot is permanently frozen, turn everything off */
 	if (state == pci_channel_io_perm_failure) {
diff --git a/drivers/staging/qlge/qlge_main.c b/drivers/staging/qlge/qlge_main.c
index 402edaeffe12..ac30aefe49a1 100644
--- a/drivers/staging/qlge/qlge_main.c
+++ b/drivers/staging/qlge/qlge_main.c
@@ -4678,7 +4678,7 @@ static void ql_eeh_close(struct net_device *ndev)
  * a PCI bus error is detected.
  */
 static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev,
-					       enum pci_channel_state state)
+					       pci_channel_state_t state)
 {
 	struct net_device *ndev = pci_get_drvdata(pdev);
 	struct ql_adapter *qdev = netdev_priv(ndev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c79d83304e52..adcee9e30bfa 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -179,7 +179,7 @@ static inline const char *pci_power_name(pci_power_t state)
  */
 typedef unsigned int __bitwise pci_channel_state_t;
 
-enum pci_channel_state {
+enum {
 	/* I/O channel is in normal state */
 	pci_channel_io_normal = (__force pci_channel_state_t) 1,
 
@@ -785,7 +785,7 @@ enum pci_ers_result {
 struct pci_error_handlers {
 	/* PCI bus error detected on this device */
 	pci_ers_result_t (*error_detected)(struct pci_dev *dev,
-					   enum pci_channel_state error);
+					   pci_channel_state_t error);
 
 	/* MMIO has been re-enabled, but not DMA */
 	pci_ers_result_t (*mmio_enabled)(struct pci_dev *dev);
-- 
cgit v1.2.3


From 4895d7808e7030c831f2ef83a3cc6ec0d46c30b1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 5 Jul 2020 21:27:56 -0700
Subject: net: ethtool: Introduce ethtool_phy_ops

In order to decouple ethtool from its PHY library dependency, define an
ethtool_phy_ops singleton which can be overriden by the PHY library when
it loads with an appropriate set of function pointers.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h | 25 +++++++++++++++++++++++++
 net/ethtool/common.c    | 11 +++++++++++
 net/ethtool/common.h    |  2 ++
 3 files changed, 38 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 48ad3b6a0150..0c139a93b67a 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -502,5 +502,30 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
 				       const struct ethtool_link_ksettings *cmd,
 				       u32 *dev_speed, u8 *dev_duplex);
 
+struct netlink_ext_ack;
+struct phy_device;
+struct phy_tdr_config;
+
+/**
+ * struct ethtool_phy_ops - Optional PHY device options
+ * @start_cable_test - Start a cable test
+ * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test
+ *
+ * All operations are optional (i.e. the function pointer may be set to %NULL)
+ * and callers must take this into account. Callers must hold the RTNL lock.
+ */
+struct ethtool_phy_ops {
+	int (*start_cable_test)(struct phy_device *phydev,
+				struct netlink_ext_ack *extack);
+	int (*start_cable_test_tdr)(struct phy_device *phydev,
+				    struct netlink_ext_ack *extack,
+				    const struct phy_tdr_config *config);
+};
+
+/**
+ * ethtool_set_ethtool_phy_ops - Set the ethtool_phy_ops singleton
+ * @ops: Ethtool PHY operations to set
+ */
+void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops);
 
 #endif /* _LINUX_ETHTOOL_H */
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index aaecfc916a4d..ce4dbae5a943 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -2,6 +2,7 @@
 
 #include <linux/net_tstamp.h>
 #include <linux/phy.h>
+#include <linux/rtnetlink.h>
 
 #include "common.h"
 
@@ -373,3 +374,13 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
 
 	return 0;
 }
+
+const struct ethtool_phy_ops *ethtool_phy_ops;
+
+void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
+{
+	rtnl_lock();
+	ethtool_phy_ops = ops;
+	rtnl_unlock();
+}
+EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops);
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index a62f68ccc43a..b83bef38368c 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -37,4 +37,6 @@ bool convert_legacy_settings_to_link_ksettings(
 int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max);
 int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info);
 
+extern const struct ethtool_phy_ops *ethtool_phy_ops;
+
 #endif /* _ETHTOOL_COMMON_H */
-- 
cgit v1.2.3


From 469aceddfa3ed16e17ee30533fae45e90f62efd8 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 7 Jul 2020 13:03:25 +0200
Subject: vlan: consolidate VLAN parsing code and limit max parsing depth
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Toshiaki pointed out that we now have two very similar functions to extract
the L3 protocol number in the presence of VLAN tags. And Daniel pointed out
that the unbounded parsing loop makes it possible for maliciously crafted
packets to loop through potentially hundreds of tags.

Fix both of these issues by consolidating the two parsing functions and
limiting the VLAN tag parsing to a max depth of 8 tags. As part of this,
switch over __vlan_get_protocol() to use skb_header_pointer() instead of
pskb_may_pull(), to avoid the possible side effects of the latter and keep
the skb pointer 'const' through all the parsing functions.

v2:
- Use limit of 8 tags instead of 32 (matching XMIT_RECURSION_LIMIT)

Reported-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Fixes: d7bf2ebebc2b ("sched: consistently handle layer3 header accesses in the presence of VLANs")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 57 +++++++++++++++++++------------------------------
 1 file changed, 22 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 427a5b8597c2..41a518336673 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
 #define VLAN_ETH_DATA_LEN	1500	/* Max. octets in payload	 */
 #define VLAN_ETH_FRAME_LEN	1518	/* Max. octets in frame sans FCS */
 
+#define VLAN_MAX_DEPTH	8		/* Max. number of nested VLAN tags parsed */
+
 /*
  * 	struct vlan_hdr - vlan header
  * 	@h_vlan_TCI: priority and VLAN ID
@@ -308,34 +310,6 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
-/* A getter for the SKB protocol field which will handle VLAN tags consistently
- * whether VLAN acceleration is enabled or not.
- */
-static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
-{
-	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
-	__be16 proto = skb->protocol;
-
-	if (!skip_vlan)
-		/* VLAN acceleration strips the VLAN header from the skb and
-		 * moves it to skb->vlan_proto
-		 */
-		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
-
-	while (eth_type_vlan(proto)) {
-		struct vlan_hdr vhdr, *vh;
-
-		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
-		if (!vh)
-			break;
-
-		proto = vh->h_vlan_encapsulated_proto;
-		offset += sizeof(vhdr);
-	}
-
-	return proto;
-}
-
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
@@ -605,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 					 int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
+	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
 	/* if type is 802.1Q/AD then the header should already be
 	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -623,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
 			vlan_depth = ETH_HLEN;
 		}
 		do {
-			struct vlan_hdr *vh;
+			struct vlan_hdr vhdr, *vh;
 
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
+			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
 			type = vh->h_vlan_encapsulated_proto;
 			vlan_depth += VLAN_HLEN;
 		} while (eth_type_vlan(type));
@@ -648,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+	return vlan_get_protocol(skb);
+}
+
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
 					struct vlan_hdr *vhdr)
 {
-- 
cgit v1.2.3


From f5836749c9c04a10decd2742845ad4870965fdef Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 6 Jul 2020 16:01:25 -0700
Subject: bpf: Add BPF_CGROUP_INET_SOCK_RELEASE hook

Sometimes it's handy to know when the socket gets freed. In
particular, we'd like to try to use a smarter allocation of
ports for bpf_bind and explore the possibility of limiting
the number of SOCK_DGRAM sockets the process can have.

Implement BPF_CGROUP_INET_SOCK_RELEASE hook that triggers on
inet socket release. It triggers only for userspace sockets
(not in-kernel ones) and therefore has the same semantics as
the existing BPF_CGROUP_INET_SOCK_CREATE.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200706230128.4073544-2-sdf@google.com
---
 include/linux/bpf-cgroup.h | 4 ++++
 include/uapi/linux/bpf.h   | 1 +
 kernel/bpf/syscall.c       | 3 +++
 net/core/filter.c          | 1 +
 net/ipv4/af_inet.c         | 3 +++
 5 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index c66c545e161a..2c6f26670acc 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -210,6 +210,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE)
 
+#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk)			       \
+	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE)
+
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND)
 
@@ -401,6 +404,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index da9bf35a26f8..548a749aebb3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -226,6 +226,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
+	BPF_CGROUP_INET_SOCK_RELEASE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8da159936bab..156f51ffada2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1981,6 +1981,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 		switch (expected_attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
+		case BPF_CGROUP_INET_SOCK_RELEASE:
 		case BPF_CGROUP_INET4_POST_BIND:
 		case BPF_CGROUP_INET6_POST_BIND:
 			return 0;
@@ -2779,6 +2780,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_CGROUP_SKB;
 		break;
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_POST_BIND:
 	case BPF_CGROUP_INET6_POST_BIND:
 		return BPF_PROG_TYPE_CGROUP_SOCK;
@@ -2929,6 +2931,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_POST_BIND:
diff --git a/net/core/filter.c b/net/core/filter.c
index c5e696e6c315..ddcc0d6209e1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6890,6 +6890,7 @@ static bool __sock_filter_check_attach_type(int off,
 	case offsetof(struct bpf_sock, priority):
 		switch (attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
+		case BPF_CGROUP_INET_SOCK_RELEASE:
 			goto full_access;
 		default:
 			return false;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ea6ed6d487ed..ff141d630bdf 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -411,6 +411,9 @@ int inet_release(struct socket *sock)
 	if (sk) {
 		long timeout;
 
+		if (!sk->sk_kern_sock)
+			BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk);
+
 		/* Applications forget to leave groups before exiting */
 		ip_mc_drop_socket(sk);
 
-- 
cgit v1.2.3


From 61a707c543e2afe3aa7e88f87267c5dafa4b5afa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 8 May 2020 08:54:16 +0200
Subject: fs: add a __kernel_read helper

This is the counterpart to __kernel_write, and skip the rw_verify_area
call compared to kernel_read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c    | 23 +++++++++++++++++++++++
 include/linux/fs.h |  1 +
 2 files changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index 96e8e354f99b..21c9d90a257e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -430,6 +430,29 @@ ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
 		return -EINVAL;
 }
 
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
+{
+	mm_segment_t old_fs = get_fs();
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	set_fs(KERNEL_DS);
+	ret = __vfs_read(file, (void __user *)buf, count, pos);
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
+	return ret;
+}
+
 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..22cbe7b2e919 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3033,6 +3033,7 @@ extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, lo
 extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
 				    enum kernel_read_file_id);
 extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
 extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
 extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
 extern struct file * open_exec(const char *);
-- 
cgit v1.2.3


From 775802c0571fb438cd4f6548a323f9e4cb89f5aa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 8 May 2020 11:17:46 +0200
Subject: fs: remove __vfs_read

Fold it into the two callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c    | 43 +++++++++++++++++++++----------------------
 include/linux/fs.h |  1 -
 2 files changed, 21 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index 42a027719324..4fb797822567 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,17 +419,6 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
-ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
-		   loff_t *pos)
-{
-	if (file->f_op->read)
-		return file->f_op->read(file, buf, count, pos);
-	else if (file->f_op->read_iter)
-		return new_sync_read(file, buf, count, pos);
-	else
-		return -EINVAL;
-}
-
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs = get_fs();
@@ -443,7 +432,12 @@ ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 	if (count > MAX_RW_COUNT)
 		count =  MAX_RW_COUNT;
 	set_fs(KERNEL_DS);
-	ret = __vfs_read(file, (void __user *)buf, count, pos);
+	if (file->f_op->read)
+		ret = file->f_op->read(file, (void __user *)buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, (void __user *)buf, count, pos);
+	else
+		ret = -EINVAL;
 	set_fs(old_fs);
 	if (ret > 0) {
 		fsnotify_access(file);
@@ -476,17 +470,22 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 		return -EFAULT;
 
 	ret = rw_verify_area(READ, file, pos, count);
-	if (!ret) {
-		if (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		ret = __vfs_read(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_access(file);
-			add_rchar(current, ret);
-		}
-		inc_syscr(current);
-	}
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
 
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
 	return ret;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 22cbe7b2e919..0c0ec76b600b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1917,7 +1917,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      struct iovec *fast_pointer,
 			      struct iovec **ret_pointer);
 
-extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
-- 
cgit v1.2.3


From 76c12881a38aaa83e1eb4ce2fada36c3a732bad4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Mon, 6 Jul 2020 17:49:11 +0200
Subject: nsproxy: support CLONE_NEWTIME with setns()

So far setns() was missing time namespace support. This was partially due
to it simply not being implemented but also because vdso_join_timens()
could still fail which made switching to multiple namespaces atomically
problematic. This is now fixed so support CLONE_NEWTIME with setns()

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Andrei Vagin <avagin@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20200706154912.3248030-4-christian.brauner@ubuntu.com
---
 include/linux/time_namespace.h |  6 ++++++
 kernel/nsproxy.c               | 21 +++++++++++++++++++--
 kernel/time/namespace.c        |  5 +----
 3 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 824d54e057eb..5b6031385db0 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -33,6 +33,7 @@ extern struct time_namespace init_time_ns;
 #ifdef CONFIG_TIME_NS
 extern int vdso_join_timens(struct task_struct *task,
 			    struct time_namespace *ns);
+extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
@@ -96,6 +97,11 @@ static inline int vdso_join_timens(struct task_struct *task,
 	return 0;
 }
 
+static inline void timens_commit(struct task_struct *tsk,
+				 struct time_namespace *ns)
+{
+}
+
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
 	return NULL;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index cd356630a311..12dd41b39a7f 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -262,8 +262,8 @@ void exit_task_namespaces(struct task_struct *p)
 static int check_setns_flags(unsigned long flags)
 {
 	if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-				 CLONE_NEWNET | CLONE_NEWUSER | CLONE_NEWPID |
-				 CLONE_NEWCGROUP)))
+				 CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER |
+				 CLONE_NEWPID | CLONE_NEWCGROUP)))
 		return -EINVAL;
 
 #ifndef CONFIG_USER_NS
@@ -290,6 +290,10 @@ static int check_setns_flags(unsigned long flags)
 	if (flags & CLONE_NEWNET)
 		return -EINVAL;
 #endif
+#ifndef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		return -EINVAL;
+#endif
 
 	return 0;
 }
@@ -464,6 +468,14 @@ static int validate_nsset(struct nsset *nsset, struct pid *pid)
 	}
 #endif
 
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME) {
+		ret = validate_ns(nsset, &nsp->time_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
 out:
 	if (pid_ns)
 		put_pid_ns(pid_ns);
@@ -507,6 +519,11 @@ static void commit_nsset(struct nsset *nsset)
 		exit_sem(me);
 #endif
 
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		timens_commit(me, nsset->nsproxy->time_ns);
+#endif
+
 	/* transfer ownership */
 	switch_task_namespaces(me, nsset->nsproxy);
 	nsset->nsproxy = NULL;
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index aa7b90aac2a7..afc65e6be33e 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -280,7 +280,7 @@ static void timens_put(struct ns_common *ns)
 	put_time_ns(to_time_ns(ns));
 }
 
-static void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
 {
 	timens_set_vvar_page(tsk, ns);
 	vdso_join_timens(tsk, ns);
@@ -298,9 +298,6 @@ static int timens_install(struct nsset *nsset, struct ns_common *new)
 	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-
-	timens_commit(current, ns);
-
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
-- 
cgit v1.2.3


From dbfb089d360b1cc623c51a2c7cf9b99eff78e0e7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 3 Jul 2020 12:40:33 +0200
Subject: sched: Fix loadavg accounting race

The recent commit:

  c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")

moved these lines in ttwu():

	p->sched_contributes_to_load = !!task_contributes_to_load(p);
	p->state = TASK_WAKING;

up before:

	smp_cond_load_acquire(&p->on_cpu, !VAL);

into the 'p->on_rq == 0' block, with the thinking that once we hit
schedule() the current task cannot change it's ->state anymore. And
while this is true, it is both incorrect and flawed.

It is incorrect in that we need at least an ACQUIRE on 'p->on_rq == 0'
to avoid weak hardware from re-ordering things for us. This can fairly
easily be achieved by relying on the control-dependency already in
place.

The second problem, which makes the flaw in the original argument, is
that while schedule() will not change prev->state, it will read it a
number of times (arguably too many times since it's marked volatile).
The previous condition 'p->on_cpu == 0' was sufficient because that
indicates schedule() has completed, and will no longer read
prev->state. So now the trick is to make this same true for the (much)
earlier 'prev->on_rq == 0' case.

Furthermore, in order to make the ordering stick, the 'prev->on_rq = 0'
assignment needs to he a RELEASE, but adding additional ordering to
schedule() is an unwelcome proposition at the best of times, doubly so
for mere accounting.

Luckily we can push the prev->state load up before rq->lock, with the
only caveat that we then have to re-read the state after. However, we
know that if it changed, we no longer have to worry about the blocking
path. This gives us the required ordering, if we block, we did the
prev->state load before an (effective) smp_mb() and the p->on_rq store
needs not change.

With this we end up with the effective ordering:

	LOAD p->state           LOAD-ACQUIRE p->on_rq == 0
	MB
	STORE p->on_rq, 0       STORE p->state, TASK_WAKING

which ensures the TASK_WAKING store happens after the prev->state
load, and all is well again.

Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Dave Jones <davej@codemonkey.org.uk>
Tested-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Link: https://lkml.kernel.org/r/20200707102957.GN117543@hirez.programming.kicks-ass.net
---
 include/linux/sched.h |  4 ---
 kernel/sched/core.c   | 67 +++++++++++++++++++++++++++++++++++++++------------
 2 files changed, 51 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 692e327d7455..683372943093 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -114,10 +114,6 @@ struct task_group;
 
 #define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 
-#define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-					 (task->flags & PF_FROZEN) == 0 && \
-					 (task->state & TASK_NOLOAD) == 0)
-
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ca5db40392d4..950ac45d5480 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1311,9 +1311,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1323,9 +1320,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
 
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -2236,10 +2230,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2583,7 +2577,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -2592,9 +2586,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 
 #ifdef CONFIG_SMP
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
 	 * possible to, falsely, observe p->on_cpu == 0.
@@ -2613,8 +2604,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -4097,6 +4100,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4113,12 +4117,22 @@ static void __sched notrace __schedule(bool preempt)
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
 
+	/* See deactivate_task() below. */
+	prev_state = prev->state;
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
+	 *
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4129,10 +4143,31 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+	/*
+	 * We must re-load prev->state in case ttwu_remote() changed it
+	 * before we acquired rq->lock.
+	 */
+	if (!preempt && prev_state && prev_state == prev->state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;	  if (READ_ONCE(p->on_rq) && ...)
+			 *   LOCK rq->lock		    goto out;
+			 *   smp_mb__after_spinlock();	  smp_acquire__after_ctrl_dep();
+			 *   p->on_rq = 0;		  p->state = TASK_WAKING;
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
-- 
cgit v1.2.3


From 217c2a633ebb36f1cc6d249f4ef2e4a809d46818 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 3 Jul 2020 05:49:22 -0700
Subject: perf/core: Use kmem_cache to allocate the PMU specific data

Currently, the PMU specific data task_ctx_data is allocated by the
function kzalloc() in the perf generic code. When there is no specific
alignment requirement for the task_ctx_data, the method works well for
now. However, there will be a problem once a specific alignment
requirement is introduced in future features, e.g., the Architecture LBR
XSAVE feature requires 64-byte alignment. If the specific alignment
requirement is not fulfilled, the XSAVE family of instructions will fail
to save/restore the xstate to/from the task_ctx_data.

The function kzalloc() itself only guarantees a natural alignment. A
new method to allocate the task_ctx_data has to be introduced, which
has to meet the requirements as below:
- must be a generic method can be used by different architectures,
  because the allocation of the task_ctx_data is implemented in the
  perf generic code;
- must be an alignment-guarantee method (The alignment requirement is
  not changed after the boot);
- must be able to allocate/free a buffer (smaller than a page size)
  dynamically;
- should not cause extra CPU overhead or space overhead.

Several options were considered as below:
- One option is to allocate a larger buffer for task_ctx_data. E.g.,
    ptr = kmalloc(size + alignment, GFP_KERNEL);
    ptr &= ~(alignment - 1);
  This option causes space overhead.
- Another option is to allocate the task_ctx_data in the PMU specific
  code. To do so, several function pointers have to be added. As a
  result, both the generic structure and the PMU specific structure
  will become bigger. Besides, extra function calls are added when
  allocating/freeing the buffer. This option will increase both the
  space overhead and CPU overhead.
- The third option is to use a kmem_cache to allocate a buffer for the
  task_ctx_data. The kmem_cache can be created with a specific alignment
  requirement by the PMU at boot time. A new pointer for kmem_cache has
  to be added in the generic struct pmu, which would be used to
  dynamically allocate a buffer for the task_ctx_data at run time.
  Although the new pointer is added to the struct pmu, the existing
  variable task_ctx_size is not required anymore. The size of the
  generic structure is kept the same.

The third option which meets all the aforementioned requirements is used
to replace kzalloc() for the PMU specific data allocation. A later patch
will remove the kzalloc() method and the related variables.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-17-git-send-email-kan.liang@linux.intel.com
---
 include/linux/perf_event.h | 5 +++++
 kernel/events/core.c       | 8 +++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 46fe5cfb5163..09915ae06d28 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -424,6 +424,11 @@ struct pmu {
 	 */
 	size_t				task_ctx_size;
 
+	/*
+	 * Kmem cache of PMU specific data
+	 */
+	struct kmem_cache		*task_ctx_cache;
+
 	/*
 	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
 	 * can be synchronized using this function. See Intel LBR callstack support
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 75090403f942..30d9b3182369 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1240,12 +1240,18 @@ static void get_ctx(struct perf_event_context *ctx)
 
 static void *alloc_task_ctx_data(struct pmu *pmu)
 {
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
 	return kzalloc(pmu->task_ctx_size, GFP_KERNEL);
 }
 
 static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
 {
-	kfree(task_ctx_data);
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+	else
+		kfree(task_ctx_data);
 }
 
 static void free_ctx(struct rcu_head *head)
-- 
cgit v1.2.3


From 5a09928d339f3cf0973991ddc3a2798825c84c99 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 3 Jul 2020 05:49:24 -0700
Subject: perf/x86: Remove task_ctx_size

A new kmem_cache method has replaced the kzalloc() to allocate the PMU
specific data. The task_ctx_size is not required anymore.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-19-git-send-email-kan.liang@linux.intel.com
---
 arch/x86/events/core.c      | 1 -
 arch/x86/events/intel/lbr.c | 1 -
 include/linux/perf_event.h  | 4 ----
 kernel/events/core.c        | 4 +---
 4 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d740c861724c..6b1228ae007d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2371,7 +2371,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index e784c1d485ca..3ad528996d1c 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1672,7 +1672,6 @@ void __init intel_pmu_arch_lbr_init(void)
 
 	size = sizeof(struct x86_perf_task_context_arch_lbr) +
 	       lbr_nr * sizeof(struct lbr_entry);
-	x86_get_pmu()->task_ctx_size = size;
 	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
 
 	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 09915ae06d28..3b22db08b6fb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -419,10 +419,6 @@ struct pmu {
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,
 					bool sched_in);
-	/*
-	 * PMU specific data size
-	 */
-	size_t				task_ctx_size;
 
 	/*
 	 * Kmem cache of PMU specific data
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 30d9b3182369..7c436d705fbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,15 +1243,13 @@ static void *alloc_task_ctx_data(struct pmu *pmu)
 	if (pmu->task_ctx_cache)
 		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
 
-	return kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+	return NULL;
 }
 
 static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
 {
 	if (pmu->task_ctx_cache && task_ctx_data)
 		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
-	else
-		kfree(task_ctx_data);
 }
 
 static void free_ctx(struct rcu_head *head)
-- 
cgit v1.2.3


From 9d246053a69196c7c27068870e9b4b66ac536f68 Mon Sep 17 00:00:00 2001
From: Phil Auld <pauld@redhat.com>
Date: Mon, 29 Jun 2020 15:23:03 -0400
Subject: sched: Add a tracepoint to track rq->nr_running

Add a bare tracepoint trace_sched_update_nr_running_tp which tracks
->nr_running CPU's rq. This is used to accurately trace this data and
provide a visualization of scheduler imbalances in, for example, the
form of a heat map.  The tracepoint is accessed by loading an external
kernel module. An example module (forked from Qais' module and including
the pelt related tracepoints) can be found at:

  https://github.com/auldp/tracepoints-helpers.git

A script to turn the trace-cmd report output into a heatmap plot can be
found at:

  https://github.com/jirvoz/plot-nr-running

The tracepoints are added to add_nr_running() and sub_nr_running() which
are in kernel/sched/sched.h. In order to avoid CREATE_TRACE_POINTS in
the header a wrapper call is used and the trace/events/sched.h include
is moved before sched.h in kernel/sched/core.

Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200629192303.GC120228@lorien.usersys.redhat.com
---
 include/linux/sched.h        |  1 +
 include/trace/events/sched.h |  4 ++++
 kernel/sched/core.c          | 13 +++++++++----
 kernel/sched/fair.c          |  8 ++++++--
 kernel/sched/pelt.c          |  2 --
 kernel/sched/sched.h         | 10 ++++++++++
 6 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 683372943093..12b10ce51a08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04f9a4c7b0d9..0d5ff0958d48 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -642,6 +642,10 @@ DECLARE_TRACE(sched_util_est_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_update_nr_running_tp,
+	TP_PROTO(struct rq *rq, int change),
+	TP_ARGS(rq, change));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4cf30e4de653..ff0519551188 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,10 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
@@ -23,9 +27,6 @@
 #include "pelt.h"
 #include "smp.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
  * associated with them) to allow external modules to probe them.
@@ -38,6 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -8195,4 +8197,7 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6fab1d17c575..3213cb247aff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
  */
 #include "sched.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Targeted preemption latency for CPU-bound tasks:
  *
@@ -11296,3 +11294,9 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 #endif
 }
 EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+        return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 11bea3b08115..2c613e1cff3a 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
 #include "sched.h"
 #include "pelt.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1432f608061..65b72e0487bf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -76,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -97,6 +99,7 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -1973,6 +1976,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1987,6 +1993,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }
-- 
cgit v1.2.3


From 5cc2013bfeee756a1ee6da9bfbe42e52b4695035 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Mon, 6 Jul 2020 19:53:41 +0200
Subject: regmap-irq: use fwnode instead of device node in add_irq_chip()

Convert the argument to the newer fwnode_handle instead a device tree
node. Fortunately, there are no users for now. So this is an easy
change.

Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20200706175353.16404-2-michael@walle.cc
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-irq.c | 53 ++++++++++++++++++++++------------------
 include/linux/regmap.h           | 21 +++++++++-------
 2 files changed, 41 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 4340e1d268b6..369a57e6f89d 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -541,9 +541,9 @@ static const struct irq_domain_ops regmap_domain_ops = {
 };
 
 /**
- * regmap_add_irq_chip_np() - Use standard regmap IRQ controller handling
+ * regmap_add_irq_chip_fwnode() - Use standard regmap IRQ controller handling
  *
- * @np: The device_node where the IRQ domain should be added to.
+ * @fwnode: The firmware node where the IRQ domain should be added to.
  * @map: The regmap for the device.
  * @irq: The IRQ the device uses to signal interrupts.
  * @irq_flags: The IRQF_ flags to use for the primary interrupt.
@@ -557,10 +557,11 @@ static const struct irq_domain_ops regmap_domain_ops = {
  * register cache.  The chip driver is responsible for restoring the
  * register values used by the IRQ controller over suspend and resume.
  */
-int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq,
-			   int irq_flags, int irq_base,
-			   const struct regmap_irq_chip *chip,
-			   struct regmap_irq_chip_data **data)
+int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode,
+			       struct regmap *map, int irq,
+			       int irq_flags, int irq_base,
+			       const struct regmap_irq_chip *chip,
+			       struct regmap_irq_chip_data **data)
 {
 	struct regmap_irq_chip_data *d;
 	int i;
@@ -771,10 +772,12 @@ int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq,
 	}
 
 	if (irq_base)
-		d->domain = irq_domain_add_legacy(np, chip->num_irqs, irq_base,
+		d->domain = irq_domain_add_legacy(to_of_node(fwnode),
+						  chip->num_irqs, irq_base,
 						  0, &regmap_domain_ops, d);
 	else
-		d->domain = irq_domain_add_linear(np, chip->num_irqs,
+		d->domain = irq_domain_add_linear(to_of_node(fwnode),
+						  chip->num_irqs,
 						  &regmap_domain_ops, d);
 	if (!d->domain) {
 		dev_err(map->dev, "Failed to create IRQ domain\n");
@@ -808,7 +811,7 @@ err_alloc:
 	kfree(d);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(regmap_add_irq_chip_np);
+EXPORT_SYMBOL_GPL(regmap_add_irq_chip_fwnode);
 
 /**
  * regmap_add_irq_chip() - Use standard regmap IRQ controller handling
@@ -822,15 +825,15 @@ EXPORT_SYMBOL_GPL(regmap_add_irq_chip_np);
  *
  * Returns 0 on success or an errno on failure.
  *
- * This is the same as regmap_add_irq_chip_np, except that the device
+ * This is the same as regmap_add_irq_chip_fwnode, except that the firmware
  * node of the regmap is used.
  */
 int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 			int irq_base, const struct regmap_irq_chip *chip,
 			struct regmap_irq_chip_data **data)
 {
-	return regmap_add_irq_chip_np(map->dev->of_node, map, irq, irq_flags,
-				      irq_base, chip, data);
+	return regmap_add_irq_chip_fwnode(dev_fwnode(map->dev), map, irq,
+					  irq_flags, irq_base, chip, data);
 }
 EXPORT_SYMBOL_GPL(regmap_add_irq_chip);
 
@@ -899,10 +902,10 @@ static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
 }
 
 /**
- * devm_regmap_add_irq_chip_np() - Resource manager regmap_add_irq_chip_np()
+ * devm_regmap_add_irq_chip_fwnode() - Resource managed regmap_add_irq_chip_fwnode()
  *
  * @dev: The device pointer on which irq_chip belongs to.
- * @np: The device_node where the IRQ domain should be added to.
+ * @fwnode: The firmware node where the IRQ domain should be added to.
  * @map: The regmap for the device.
  * @irq: The IRQ the device uses to signal interrupts
  * @irq_flags: The IRQF_ flags to use for the primary interrupt.
@@ -915,11 +918,12 @@ static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
  * The &regmap_irq_chip_data will be automatically released when the device is
  * unbound.
  */
-int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
-				struct regmap *map, int irq, int irq_flags,
-				int irq_base,
-				const struct regmap_irq_chip *chip,
-				struct regmap_irq_chip_data **data)
+int devm_regmap_add_irq_chip_fwnode(struct device *dev,
+				    struct fwnode_handle *fwnode,
+				    struct regmap *map, int irq,
+				    int irq_flags, int irq_base,
+				    const struct regmap_irq_chip *chip,
+				    struct regmap_irq_chip_data **data)
 {
 	struct regmap_irq_chip_data **ptr, *d;
 	int ret;
@@ -929,8 +933,8 @@ int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
 	if (!ptr)
 		return -ENOMEM;
 
-	ret = regmap_add_irq_chip_np(np, map, irq, irq_flags, irq_base,
-				     chip, &d);
+	ret = regmap_add_irq_chip_fwnode(fwnode, map, irq, irq_flags, irq_base,
+					 chip, &d);
 	if (ret < 0) {
 		devres_free(ptr);
 		return ret;
@@ -941,7 +945,7 @@ int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
 	*data = d;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip_np);
+EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip_fwnode);
 
 /**
  * devm_regmap_add_irq_chip() - Resource manager regmap_add_irq_chip()
@@ -964,8 +968,9 @@ int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 			     const struct regmap_irq_chip *chip,
 			     struct regmap_irq_chip_data **data)
 {
-	return devm_regmap_add_irq_chip_np(dev, map->dev->of_node, map, irq,
-					   irq_flags, irq_base, chip, data);
+	return devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(map->dev), map,
+					       irq, irq_flags, irq_base, chip,
+					       data);
 }
 EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip);
 
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index cb666b9c6b6a..e2c22c0f3b9a 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -18,6 +18,7 @@
 #include <linux/bug.h>
 #include <linux/lockdep.h>
 #include <linux/iopoll.h>
+#include <linux/fwnode.h>
 
 struct module;
 struct clk;
@@ -1311,21 +1312,23 @@ struct regmap_irq_chip_data;
 int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 			int irq_base, const struct regmap_irq_chip *chip,
 			struct regmap_irq_chip_data **data);
-int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq,
-			   int irq_flags, int irq_base,
-			   const struct regmap_irq_chip *chip,
-			   struct regmap_irq_chip_data **data);
+int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode,
+			       struct regmap *map, int irq,
+			       int irq_flags, int irq_base,
+			       const struct regmap_irq_chip *chip,
+			       struct regmap_irq_chip_data **data);
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data);
 
 int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 			     int irq_flags, int irq_base,
 			     const struct regmap_irq_chip *chip,
 			     struct regmap_irq_chip_data **data);
-int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
-				struct regmap *map, int irq, int irq_flags,
-				int irq_base,
-				const struct regmap_irq_chip *chip,
-				struct regmap_irq_chip_data **data);
+int devm_regmap_add_irq_chip_fwnode(struct device *dev,
+				    struct fwnode_handle *fwnode,
+				    struct regmap *map, int irq,
+				    int irq_flags, int irq_base,
+				    const struct regmap_irq_chip *chip,
+				    struct regmap_irq_chip_data **data);
 void devm_regmap_del_irq_chip(struct device *dev, int irq,
 			      struct regmap_irq_chip_data *data);
 
-- 
cgit v1.2.3


From 71010c30945425203da8d069a10fa45a05a00f96 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Mon, 29 Jun 2020 12:06:39 -0700
Subject: nvme: implement multiple I/O Command Set support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implements support for multiple I/O Command Sets.  NVMe TP 4056
introduces a method to enumerate multiple command sets per namespace. If
the command set is exposed, this method for enumeration will be used
instead of the traditional method that uses the CC.CSS register command
set register for command set identification.

For namespaces where the Command Set Identifier is not supported or
recognized, the specific namespace will not be created.

Reviewed-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Matias Bjørling <matias.bjorling@wdc.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 53 +++++++++++++++++++++++++++++++++++++++---------
 drivers/nvme/host/nvme.h |  1 +
 include/linux/nvme.h     | 19 +++++++++++++++--
 3 files changed, 61 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 96898040a6d5..892291dbee64 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1056,8 +1056,13 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 	return error;
 }
 
+static bool nvme_multi_css(struct nvme_ctrl *ctrl)
+{
+	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
+}
+
 static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
-		struct nvme_ns_id_desc *cur)
+		struct nvme_ns_id_desc *cur, bool *csi_seen)
 {
 	const char *warn_str = "ctrl returned bogus length:";
 	void *data = cur;
@@ -1087,6 +1092,15 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
 		}
 		uuid_copy(&ids->uuid, data + sizeof(*cur));
 		return NVME_NIDT_UUID_LEN;
+	case NVME_NIDT_CSI:
+		if (cur->nidl != NVME_NIDT_CSI_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
+		*csi_seen = true;
+		return NVME_NIDT_CSI_LEN;
 	default:
 		/* Skip unknown types */
 		return cur->nidl;
@@ -1097,10 +1111,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		struct nvme_ns_ids *ids)
 {
 	struct nvme_command c = { };
-	int status;
+	bool csi_seen = false;
+	int status, pos, len;
 	void *data;
-	int pos;
-	int len;
 
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.nsid = cpu_to_le32(nsid);
@@ -1125,7 +1138,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		  * device just because of a temporal retry-able error (such
 		  * as path of transport errors).
 		  */
-		if (status > 0 && (status & NVME_SC_DNR))
+		if (status > 0 && (status & NVME_SC_DNR) && !nvme_multi_css(ctrl))
 			status = 0;
 		goto free_data;
 	}
@@ -1136,12 +1149,19 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		if (cur->nidl == 0)
 			break;
 
-		len = nvme_process_ns_desc(ctrl, ids, cur);
+		len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen);
 		if (len < 0)
-			goto free_data;
+			break;
 
 		len += sizeof(*cur);
 	}
+
+	if (nvme_multi_css(ctrl) && !csi_seen) {
+		dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
+			 nsid);
+		status = -EINVAL;
+	}
+
 free_data:
 	kfree(data);
 	return status;
@@ -1798,7 +1818,7 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
 		memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
 	if (ctrl->vs >= NVME_VS(1, 2, 0))
 		memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
-	if (ctrl->vs >= NVME_VS(1, 3, 0))
+	if (ctrl->vs >= NVME_VS(1, 3, 0) || nvme_multi_css(ctrl))
 		return nvme_identify_ns_descs(ctrl, nsid, ids);
 	return 0;
 }
@@ -1814,7 +1834,8 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
 		memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
-		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
+		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
+		a->csi == b->csi;
 }
 
 static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
@@ -1936,6 +1957,15 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
+	switch (ns->head->ids.csi) {
+	case NVME_CSI_NVM:
+		break;
+	default:
+		dev_warn(ctrl->device, "unknown csi:%d ns:%d\n",
+			ns->head->ids.csi, ns->head->ns_id);
+		return -ENODEV;
+	}
+
 	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
 	    is_power_of_2(ctrl->max_hw_sectors))
 		iob = ctrl->max_hw_sectors;
@@ -2270,7 +2300,10 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 
 	ctrl->page_size = 1 << page_shift;
 
-	ctrl->ctrl_config = NVME_CC_CSS_NVM;
+	if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI)
+		ctrl->ctrl_config = NVME_CC_CSS_CSI;
+	else
+		ctrl->ctrl_config = NVME_CC_CSS_NVM;
 	ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b5a2e8b7e0be..5573159f714d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -339,6 +339,7 @@ struct nvme_ns_ids {
 	u8	eui64[8];
 	u8	nguid[16];
 	uuid_t	uuid;
+	u8	csi;
 };
 
 /*
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 5ce51ab4c50e..81ffe5247505 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -132,6 +132,7 @@ enum {
 #define NVME_CAP_TIMEOUT(cap)	(((cap) >> 24) & 0xff)
 #define NVME_CAP_STRIDE(cap)	(((cap) >> 32) & 0xf)
 #define NVME_CAP_NSSRC(cap)	(((cap) >> 36) & 0x1)
+#define NVME_CAP_CSS(cap)	(((cap) >> 37) & 0xff)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
 #define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
 
@@ -162,7 +163,6 @@ enum {
 
 enum {
 	NVME_CC_ENABLE		= 1 << 0,
-	NVME_CC_CSS_NVM		= 0 << 4,
 	NVME_CC_EN_SHIFT	= 0,
 	NVME_CC_CSS_SHIFT	= 4,
 	NVME_CC_MPS_SHIFT	= 7,
@@ -170,6 +170,9 @@ enum {
 	NVME_CC_SHN_SHIFT	= 14,
 	NVME_CC_IOSQES_SHIFT	= 16,
 	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
+	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
@@ -179,6 +182,8 @@ enum {
 	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+	NVME_CAP_CSS_NVM	= 1 << 0,
+	NVME_CAP_CSS_CSI	= 1 << 6,
 	NVME_CSTS_RDY		= 1 << 0,
 	NVME_CSTS_CFS		= 1 << 1,
 	NVME_CSTS_NSSRO		= 1 << 4,
@@ -374,6 +379,8 @@ enum {
 	NVME_ID_CNS_CTRL		= 0x01,
 	NVME_ID_CNS_NS_ACTIVE_LIST	= 0x02,
 	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
+	NVME_ID_CNS_CS_NS		= 0x05,
+	NVME_ID_CNS_CS_CTRL		= 0x06,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
 	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
@@ -383,6 +390,10 @@ enum {
 	NVME_ID_CNS_UUID_LIST		= 0x17,
 };
 
+enum {
+	NVME_CSI_NVM			= 0,
+};
+
 enum {
 	NVME_DIR_IDENTIFY		= 0x00,
 	NVME_DIR_STREAMS		= 0x01,
@@ -435,11 +446,13 @@ struct nvme_ns_id_desc {
 #define NVME_NIDT_EUI64_LEN	8
 #define NVME_NIDT_NGUID_LEN	16
 #define NVME_NIDT_UUID_LEN	16
+#define NVME_NIDT_CSI_LEN	1
 
 enum {
 	NVME_NIDT_EUI64		= 0x01,
 	NVME_NIDT_NGUID		= 0x02,
 	NVME_NIDT_UUID		= 0x03,
+	NVME_NIDT_CSI		= 0x04,
 };
 
 struct nvme_smart_log {
@@ -972,7 +985,9 @@ struct nvme_identify {
 	__u8			cns;
 	__u8			rsvd3;
 	__le16			ctrlid;
-	__u32			rsvd11[5];
+	__u8			rsvd11[3];
+	__u8			csi;
+	__u32			rsvd12[4];
 };
 
 #define NVME_IDENTIFY_DATA_SIZE 4096
-- 
cgit v1.2.3


From be93e87e780253780df9bb6ecc9bc1199b0d94c3 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@wdc.com>
Date: Mon, 29 Jun 2020 12:06:40 -0700
Subject: nvme: support for multiple Command Sets Supported and Effects log
 pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Commands Supported and Effects log page was extended with a CSI
field that enables the host to query the log page for each command set
supported. Retrieve this log page for each command set that an attached
namespace supports, and save a pointer to that log in the namespace head.

Reviewed-by: Matias Bjørling <matias.bjorling@wdc.com>
Reviewed-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <keith.busch@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c      | 79 ++++++++++++++++++++++++++++++++-----------
 drivers/nvme/host/hwmon.c     |  2 +-
 drivers/nvme/host/lightnvm.c  |  4 +--
 drivers/nvme/host/multipath.c |  2 +-
 drivers/nvme/host/nvme.h      | 10 +++++-
 include/linux/nvme.h          |  4 ++-
 6 files changed, 76 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 892291dbee64..62b2cdc764da 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1370,8 +1370,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	u32 effects = 0;
 
 	if (ns) {
-		if (ctrl->effects)
-			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+		if (ns->head->effects)
+			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn(ctrl->device,
 				 "IO command:%02x has unhandled effects:%08x\n",
@@ -2851,7 +2851,7 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
@@ -2865,27 +2865,55 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
 	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
+	c.get_log_page.csi = csi;
 
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
+static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
+	struct nvme_cel *cel, *ret = NULL;
+
+	spin_lock(&ctrl->lock);
+	list_for_each_entry(cel, &ctrl->cels, entry) {
+		if (cel->csi == csi) {
+			ret = cel;
+			break;
+		}
+	}
+	spin_unlock(&ctrl->lock);
+
+	return ret;
+}
+
+static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
+				struct nvme_effects_log **log)
+{
+	struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
 	int ret;
 
-	if (!ctrl->effects)
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
+	if (cel)
+		goto out;
 
-	if (!ctrl->effects)
-		return 0;
+	cel = kzalloc(sizeof(*cel), GFP_KERNEL);
+	if (!cel)
+		return -ENOMEM;
 
-	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
-			ctrl->effects, sizeof(*ctrl->effects), 0);
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi,
+			&cel->log, sizeof(cel->log), 0);
 	if (ret) {
-		kfree(ctrl->effects);
-		ctrl->effects = NULL;
+		kfree(cel);
+		return ret;
 	}
-	return ret;
+
+	cel->csi = csi;
+
+	spin_lock(&ctrl->lock);
+	list_add_tail(&cel->entry, &ctrl->cels);
+	spin_unlock(&ctrl->lock);
+out:
+	*log = &cel->log;
+	return 0;
 }
 
 /*
@@ -2918,7 +2946,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
-		ret = nvme_get_effects_log(ctrl);
+		ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
 		if (ret < 0)
 			goto out_free;
 	}
@@ -3551,6 +3579,13 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		goto out_cleanup_srcu;
 	}
 
+	if (head->ids.csi) {
+		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
+		if (ret)
+			goto out_cleanup_srcu;
+	} else
+		head->effects = ctrl->effects;
+
 	ret = nvme_mpath_alloc_disk(ctrl, head);
 	if (ret)
 		goto out_cleanup_srcu;
@@ -3891,8 +3926,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
-			log_size, 0);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0,
+			NVME_CSI_NVM, log, log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -4036,8 +4071,8 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
-			sizeof(*log), 0))
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
+			log, sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
@@ -4174,11 +4209,16 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_ctrl *ctrl =
 		container_of(dev, struct nvme_ctrl, ctrl_device);
 	struct nvme_subsystem *subsys = ctrl->subsys;
+	struct nvme_cel *cel, *next;
 
 	if (subsys && ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
-	kfree(ctrl->effects);
+	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
+		list_del(&cel->entry);
+		kfree(cel);
+	}
+
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
 
@@ -4209,6 +4249,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
+	INIT_LIST_HEAD(&ctrl->cels);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index 2e6477ed420f..23ba8bf678ae 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -62,7 +62,7 @@ static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
 	int ret;
 
 	ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
-			   &data->log, sizeof(data->log), 0);
+			   NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
 
 	return ret <= 0 ? ret : -EIO;
 }
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 69608755d415..8e562d0f2c30 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -593,8 +593,8 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 		dev_meta_off = dev_meta;
 
 		ret = nvme_get_log(ctrl, ns->head->ns_id,
-				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
-				offset);
+				NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM,
+				dev_meta, len, offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5a37a595411e..74bad4e3d377 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -527,7 +527,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
 	int error;
 
 	mutex_lock(&ctrl->ana_lock);
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, NVME_CSI_NVM,
 			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
 	if (error) {
 		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 5573159f714d..fe9424c7097f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -191,6 +191,12 @@ struct nvme_fault_inject {
 #endif
 };
 
+struct nvme_cel {
+	struct list_head	entry;
+	struct nvme_effects_log	log;
+	u8			csi;
+};
+
 struct nvme_ctrl {
 	bool comp_seen;
 	enum nvme_ctrl_state state;
@@ -257,6 +263,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
+	struct list_head cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -359,6 +366,7 @@ struct nvme_ns_head {
 	struct kref		ref;
 	bool			shared;
 	int			instance;
+	struct nvme_effects_log *effects;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct gendisk		*disk;
 	struct bio_list		requeue_list;
@@ -561,7 +569,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 81ffe5247505..95cd03e240a1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1101,7 +1101,9 @@ struct nvme_get_log_page_command {
 		};
 		__le64 lpo;
 	};
-	__u32			rsvd14[2];
+	__u8			rsvd14[3];
+	__u8			csi;
+	__u32			rsvd15;
 };
 
 struct nvme_directive_cmd {
-- 
cgit v1.2.3


From 240e6ee272c07a2636dfc7d65f5bbb18377c49e5 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@wdc.com>
Date: Mon, 29 Jun 2020 12:06:41 -0700
Subject: nvme: support for zoned namespaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for NVM Express Zoned Namespaces (ZNS) Command Set defined
in NVM Express TP4053. Zoned namespaces are discovered based on their
Command Set Identifier reported in the namespaces Namespace
Identification Descriptor list. A successfully discovered Zoned
Namespace will be registered with the block layer as a host managed
zoned block device with Zone Append command support. A namespace that
does not support append is not supported by the driver.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Signed-off-by: Ajay Joshi <ajay.joshi@wdc.com>
Signed-off-by: Aravind Ramesh <aravind.ramesh@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Matias Bjørling <matias.bjorling@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Keith Busch <keith.busch@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/Kconfig              |   5 +-
 drivers/nvme/host/Makefile |   1 +
 drivers/nvme/host/core.c   |  97 ++++++++++++++---
 drivers/nvme/host/nvme.h   |  39 +++++++
 drivers/nvme/host/zns.c    | 254 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme.h       | 111 ++++++++++++++++++++
 6 files changed, 492 insertions(+), 15 deletions(-)
 create mode 100644 drivers/nvme/host/zns.c

(limited to 'include/linux')

diff --git a/block/Kconfig b/block/Kconfig
index 9357d7302398..bbad5e8bbffe 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -86,9 +86,10 @@ config BLK_DEV_ZONED
 	select MQ_IOSCHED_DEADLINE
 	help
 	Block layer zoned block device support. This option enables
-	support for ZAC/ZBC host-managed and host-aware zoned block devices.
+	support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
+	devices.
 
-	Say yes here if you have a ZAC or ZBC storage device.
+	Say yes here if you have a ZAC, ZBC, or ZNS storage device.
 
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index fc7b26be692d..d7f6a87687b8 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -13,6 +13,7 @@ nvme-core-y				:= core.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
+nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 62b2cdc764da..a8ee10a0cd32 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,7 +89,7 @@ static dev_t nvme_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
-static int nvme_revalidate_disk(struct gendisk *disk);
+static int _nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
@@ -287,6 +287,10 @@ void nvme_complete_rq(struct request *req)
 			nvme_retry_req(req);
 			return;
 		}
+	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		   req_op(req) == REQ_OP_ZONE_APPEND) {
+		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+			le64_to_cpu(nvme_req(req)->result.u64));
 	}
 
 	nvme_trace_bio_complete(req, status);
@@ -673,7 +677,8 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 }
 
 static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
-		struct request *req, struct nvme_command *cmnd)
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_opcode op)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 control = 0;
@@ -687,7 +692,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.opcode = op;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
@@ -716,6 +721,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
+			if (op == nvme_cmd_zone_append)
+				control |= NVME_RW_APPEND_PIREMAP;
 			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
@@ -756,6 +763,19 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
 		break;
+	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_RESET:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
+		break;
+	case REQ_OP_ZONE_OPEN:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
+		break;
+	case REQ_OP_ZONE_FINISH:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
+		break;
 	case REQ_OP_WRITE_ZEROES:
 		ret = nvme_setup_write_zeroes(ns, req, cmd);
 		break;
@@ -763,8 +783,13 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
 	case REQ_OP_READ:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
+		break;
 	case REQ_OP_WRITE:
-		ret = nvme_setup_rw(ns, req, cmd);
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+		break;
+	case REQ_OP_ZONE_APPEND:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1398,14 +1423,23 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
-static void nvme_update_formats(struct nvme_ctrl *ctrl)
+static void nvme_update_formats(struct nvme_ctrl *ctrl, u32 *effects)
 {
 	struct nvme_ns *ns;
 
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (ns->disk && nvme_revalidate_disk(ns->disk))
+		if (ns->disk && _nvme_revalidate_disk(ns->disk))
 			nvme_set_queue_dying(ns);
+		else if (blk_queue_is_zoned(ns->disk->queue)) {
+			/*
+			 * IO commands are required to fully revalidate a zoned
+			 * device. Force the command effects to trigger rescan
+			 * work so report zones can run in a context with
+			 * unfrozen IO queues.
+			 */
+			*effects |= NVME_CMD_EFFECTS_NCC;
+		}
 	up_read(&ctrl->namespaces_rwsem);
 }
 
@@ -1417,7 +1451,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	 * this command.
 	 */
 	if (effects & NVME_CMD_EFFECTS_LBCC)
-		nvme_update_formats(ctrl);
+		nvme_update_formats(ctrl, &effects);
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
@@ -1532,7 +1566,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
  */
-static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 		struct nvme_ns_head **head, int *srcu_idx)
 {
 #ifdef CONFIG_NVME_MULTIPATH
@@ -1552,7 +1586,7 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 	return disk->private_data;
 }
 
-static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 {
 	if (head)
 		srcu_read_unlock(&head->srcu, idx);
@@ -1945,23 +1979,34 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
+	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
 	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
 	 * block layer can use before failing read/write for 0 capacity.
 	 */
-	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
+	ns->lba_shift = id->lbaf[lbaf].ds;
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
 	switch (ns->head->ids.csi) {
 	case NVME_CSI_NVM:
 		break;
+	case NVME_CSI_ZNS:
+		ret = nvme_update_zone_info(disk, ns, lbaf);
+		if (ret) {
+			dev_warn(ctrl->device,
+				"failed to add zoned namespace:%u ret:%d\n",
+				ns->head->ns_id, ret);
+			return ret;
+		}
+		break;
 	default:
-		dev_warn(ctrl->device, "unknown csi:%d ns:%d\n",
+		dev_warn(ctrl->device, "unknown csi:%u ns:%u\n",
 			ns->head->ids.csi, ns->head->ns_id);
 		return -ENODEV;
 	}
@@ -1973,7 +2018,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
 
 	ns->features = 0;
-	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
 	if (ns->ms == sizeof(struct t10_pi_tuple))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
@@ -2015,7 +2060,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	return 0;
 }
 
-static int nvme_revalidate_disk(struct gendisk *disk)
+static int _nvme_revalidate_disk(struct gendisk *disk)
 {
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
@@ -2063,6 +2108,28 @@ out:
 	return ret;
 }
 
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+	int ret;
+
+	ret = _nvme_revalidate_disk(disk);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (blk_queue_is_zoned(disk->queue)) {
+		struct nvme_ns *ns = disk->private_data;
+		struct nvme_ctrl *ctrl = ns->ctrl;
+
+		ret = blk_revalidate_disk_zones(disk, NULL);
+		if (!ret)
+			blk_queue_max_zone_append_sectors(disk->queue,
+							  ctrl->max_zone_append);
+	}
+#endif
+	return ret;
+}
+
 static char nvme_pr_type(enum pr_type type)
 {
 	switch (type) {
@@ -2193,6 +2260,7 @@ static const struct block_device_operations nvme_fops = {
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
 	.revalidate_disk= nvme_revalidate_disk,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 
@@ -2219,6 +2287,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.ioctl		= nvme_ioctl,
 	.compat_ioctl	= nvme_compat_ioctl,
 	.getgeo		= nvme_getgeo,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 #endif /* CONFIG_NVME_MULTIPATH */
@@ -4446,6 +4515,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index fe9424c7097f..13ca90bcd352 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -238,6 +238,9 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u32 max_zone_append;
+#endif
 	u16 crdt[3];
 	u16 oncs;
 	u16 oacs;
@@ -404,6 +407,9 @@ struct nvme_ns {
 	u16 sgs;
 	u32 sws;
 	u8 pi_type;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64 zsze;
+#endif
 	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
@@ -571,6 +577,9 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
 int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset);
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+		struct nvme_ns_head **head, int *srcu_idx);
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct block_device_operations nvme_ns_head_ops;
@@ -693,6 +702,36 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
+			  unsigned lbaf);
+
+int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data);
+
+blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
+				       struct nvme_command *cmnd,
+				       enum nvme_zone_mgmt_action action);
+#else
+#define nvme_report_zones NULL
+
+static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_zone_mgmt_action action)
+{
+	return BLK_STS_NOTSUPP;
+}
+
+static inline int nvme_update_zone_info(struct gendisk *disk,
+					struct nvme_ns *ns,
+					unsigned lbaf)
+{
+	dev_warn(ns->ctrl->device,
+		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
+	return -EPROTONOSUPPORT;
+}
+#endif
+
 #ifdef CONFIG_NVM
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
new file mode 100644
index 000000000000..04e5b991c00c
--- /dev/null
+++ b/drivers/nvme/host/zns.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include "nvme.h"
+
+static int nvme_set_max_append(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command c = { };
+	struct nvme_id_ctrl_zns *id;
+	int status;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return -ENOMEM;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = NVME_ID_CNS_CS_CTRL;
+	c.identify.csi = NVME_CSI_ZNS;
+
+	status = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
+	if (status) {
+		kfree(id);
+		return status;
+	}
+
+	if (id->zasl)
+		ctrl->max_zone_append = 1 << (id->zasl + 3);
+	else
+		ctrl->max_zone_append = ctrl->max_hw_sectors;
+	kfree(id);
+	return 0;
+}
+
+int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
+			  unsigned lbaf)
+{
+	struct nvme_effects_log *log = ns->head->effects;
+	struct request_queue *q = disk->queue;
+	struct nvme_command c = { };
+	struct nvme_id_ns_zns *id;
+	int status;
+
+	/* Driver requires zone append support */
+	if (!(le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
+			NVME_CMD_EFFECTS_CSUPP)) {
+		dev_warn(ns->ctrl->device,
+			"append not supported for zoned namespace:%d\n",
+			ns->head->ns_id);
+		return -EINVAL;
+	}
+
+	/* Lazily query controller append limit for the first zoned namespace */
+	if (!ns->ctrl->max_zone_append) {
+		status = nvme_set_max_append(ns->ctrl);
+		if (status)
+			return status;
+	}
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return -ENOMEM;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
+	c.identify.cns = NVME_ID_CNS_CS_NS;
+	c.identify.csi = NVME_CSI_ZNS;
+
+	status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, id, sizeof(*id));
+	if (status)
+		goto free_data;
+
+	/*
+	 * We currently do not handle devices requiring any of the zoned
+	 * operation characteristics.
+	 */
+	if (id->zoc) {
+		dev_warn(ns->ctrl->device,
+			"zone operations:%x not supported for namespace:%u\n",
+			le16_to_cpu(id->zoc), ns->head->ns_id);
+		status = -EINVAL;
+		goto free_data;
+	}
+
+	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
+	if (!is_power_of_2(ns->zsze)) {
+		dev_warn(ns->ctrl->device,
+			"invalid zone size:%llu for namespace:%u\n",
+			ns->zsze, ns->head->ns_id);
+		status = -EINVAL;
+		goto free_data;
+	}
+
+	q->limits.zoned = BLK_ZONED_HM;
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+free_data:
+	kfree(id);
+	return status;
+}
+
+static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
+					  unsigned int nr_zones, size_t *buflen)
+{
+	struct request_queue *q = ns->disk->queue;
+	size_t bufsize;
+	void *buf;
+
+	const size_t min_bufsize = sizeof(struct nvme_zone_report) +
+				   sizeof(struct nvme_zone_descriptor);
+
+	nr_zones = min_t(unsigned int, nr_zones,
+			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+
+	bufsize = sizeof(struct nvme_zone_report) +
+		nr_zones * sizeof(struct nvme_zone_descriptor);
+	bufsize = min_t(size_t, bufsize,
+			queue_max_hw_sectors(q) << SECTOR_SHIFT);
+	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+
+	while (bufsize >= min_bufsize) {
+		buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
+		if (buf) {
+			*buflen = bufsize;
+			return buf;
+		}
+		bufsize >>= 1;
+	}
+	return NULL;
+}
+
+static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+				  struct nvme_zone_report *report,
+				  size_t buflen)
+{
+	struct nvme_command c = { };
+	int ret;
+
+	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
+	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
+	c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
+	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
+	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
+	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
+
+	ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
+	if (ret)
+		return ret;
+
+	return le64_to_cpu(report->nr_zones);
+}
+
+static int nvme_zone_parse_entry(struct nvme_ns *ns,
+				 struct nvme_zone_descriptor *entry,
+				 unsigned int idx, report_zones_cb cb,
+				 void *data)
+{
+	struct blk_zone zone = { };
+
+	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
+		dev_err(ns->ctrl->device, "invalid zone type %#x\n",
+				entry->zt);
+		return -EINVAL;
+	}
+
+	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+	zone.cond = entry->zs >> 4;
+	zone.len = ns->zsze;
+	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
+	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
+	zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+
+	return cb(&zone, idx, data);
+}
+
+static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+			unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_zone_report *report;
+	int ret, zone_idx = 0;
+	unsigned int nz, i;
+	size_t buflen;
+
+	report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
+	if (!report)
+		return -ENOMEM;
+
+	sector &= ~(ns->zsze - 1);
+	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
+		memset(report, 0, buflen);
+		ret = __nvme_ns_report_zones(ns, sector, report, buflen);
+		if (ret < 0)
+			goto out_free;
+
+		nz = min_t(unsigned int, ret, nr_zones);
+		if (!nz)
+			break;
+
+		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
+			ret = nvme_zone_parse_entry(ns, &report->entries[i],
+						    zone_idx, cb, data);
+			if (ret)
+				goto out_free;
+			zone_idx++;
+		}
+
+		sector += ns->zsze * nz;
+	}
+
+	if (zone_idx > 0)
+		ret = zone_idx;
+	else
+		ret = -EINVAL;
+out_free:
+	kvfree(report);
+	return ret;
+}
+
+int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_ns_head *head = NULL;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
+
+	ns = nvme_get_ns_from_disk(disk, &head, &srcu_idx);
+	if (unlikely(!ns))
+		return -EWOULDBLOCK;
+
+	if (ns->head->ids.csi == NVME_CSI_ZNS)
+		ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
+	else
+		ret = -EINVAL;
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	return ret;
+}
+
+blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *c, enum nvme_zone_mgmt_action action)
+{
+	c->zms.opcode = nvme_cmd_zone_mgmt_send;
+	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
+	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	c->zms.zsa = action;
+
+	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)
+		c->zms.select_all = 1;
+
+	return BLK_STS_OK;
+}
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 95cd03e240a1..1643005d21e3 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -374,6 +374,30 @@ struct nvme_id_ns {
 	__u8			vs[3712];
 };
 
+struct nvme_zns_lbafe {
+	__le64			zsze;
+	__u8			zdes;
+	__u8			rsvd9[7];
+};
+
+struct nvme_id_ns_zns {
+	__le16			zoc;
+	__le16			ozcs;
+	__le32			mar;
+	__le32			mor;
+	__le32			rrl;
+	__le32			frl;
+	__u8			rsvd20[2796];
+	struct nvme_zns_lbafe	lbafe[16];
+	__u8			rsvd3072[768];
+	__u8			vs[256];
+};
+
+struct nvme_id_ctrl_zns {
+	__u8	zasl;
+	__u8	rsvd1[4095];
+};
+
 enum {
 	NVME_ID_CNS_NS			= 0x00,
 	NVME_ID_CNS_CTRL		= 0x01,
@@ -392,6 +416,7 @@ enum {
 
 enum {
 	NVME_CSI_NVM			= 0,
+	NVME_CSI_ZNS			= 2,
 };
 
 enum {
@@ -532,6 +557,27 @@ struct nvme_ana_rsp_hdr {
 	__le16	rsvd10[3];
 };
 
+struct nvme_zone_descriptor {
+	__u8		zt;
+	__u8		zs;
+	__u8		za;
+	__u8		rsvd3[5];
+	__le64		zcap;
+	__le64		zslba;
+	__le64		wp;
+	__u8		rsvd32[32];
+};
+
+enum {
+	NVME_ZONE_TYPE_SEQWRITE_REQ	= 0x2,
+};
+
+struct nvme_zone_report {
+	__le64		nr_zones;
+	__u8		resv8[56];
+	struct nvme_zone_descriptor entries[];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -626,6 +672,9 @@ enum nvme_opcode {
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
 	nvme_cmd_resv_release	= 0x15,
+	nvme_cmd_zone_mgmt_send	= 0x79,
+	nvme_cmd_zone_mgmt_recv	= 0x7a,
+	nvme_cmd_zone_append	= 0x7d,
 };
 
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
@@ -764,6 +813,7 @@ struct nvme_rw_command {
 enum {
 	NVME_RW_LR			= 1 << 15,
 	NVME_RW_FUA			= 1 << 14,
+	NVME_RW_APPEND_PIREMAP		= 1 << 9,
 	NVME_RW_DSM_FREQ_UNSPEC		= 0,
 	NVME_RW_DSM_FREQ_TYPICAL	= 1,
 	NVME_RW_DSM_FREQ_RARE		= 2,
@@ -829,6 +879,53 @@ struct nvme_write_zeroes_cmd {
 	__le16			appmask;
 };
 
+enum nvme_zone_mgmt_action {
+	NVME_ZONE_CLOSE		= 0x1,
+	NVME_ZONE_FINISH	= 0x2,
+	NVME_ZONE_OPEN		= 0x3,
+	NVME_ZONE_RESET		= 0x4,
+	NVME_ZONE_OFFLINE	= 0x5,
+	NVME_ZONE_SET_DESC_EXT	= 0x10,
+};
+
+struct nvme_zone_mgmt_send_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le32			cdw2[2];
+	__le64			metadata;
+	union nvme_data_ptr	dptr;
+	__le64			slba;
+	__le32			cdw12;
+	__u8			zsa;
+	__u8			select_all;
+	__u8			rsvd13[2];
+	__le32			cdw14[2];
+};
+
+struct nvme_zone_mgmt_recv_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__le64			slba;
+	__le32			numd;
+	__u8			zra;
+	__u8			zrasf;
+	__u8			pr;
+	__u8			rsvd13;
+	__le32			cdw14[2];
+};
+
+enum {
+	NVME_ZRA_ZONE_REPORT		= 0,
+	NVME_ZRASF_ZONE_REPORT_ALL	= 0,
+	NVME_REPORT_ZONE_PARTIAL	= 1,
+};
+
 /* Features */
 
 enum {
@@ -1300,6 +1397,8 @@ struct nvme_command {
 		struct nvme_format_cmd format;
 		struct nvme_dsm_cmd dsm;
 		struct nvme_write_zeroes_cmd write_zeroes;
+		struct nvme_zone_mgmt_send_cmd zms;
+		struct nvme_zone_mgmt_recv_cmd zmr;
 		struct nvme_abort_cmd abort;
 		struct nvme_get_log_page_command get_log_page;
 		struct nvmf_common_command fabrics;
@@ -1433,6 +1532,18 @@ enum {
 	NVME_SC_DISCOVERY_RESTART	= 0x190,
 	NVME_SC_AUTH_REQUIRED		= 0x191,
 
+	/*
+	 * I/O Command Set Specific - Zoned commands:
+	 */
+	NVME_SC_ZONE_BOUNDARY_ERROR	= 0x1b8,
+	NVME_SC_ZONE_FULL		= 0x1b9,
+	NVME_SC_ZONE_READ_ONLY		= 0x1ba,
+	NVME_SC_ZONE_OFFLINE		= 0x1bb,
+	NVME_SC_ZONE_INVALID_WRITE	= 0x1bc,
+	NVME_SC_ZONE_TOO_MANY_ACTIVE	= 0x1bd,
+	NVME_SC_ZONE_TOO_MANY_OPEN	= 0x1be,
+	NVME_SC_ZONE_INVALID_TRANSITION	= 0x1bf,
+
 	/*
 	 * Media and Data Integrity Errors:
 	 */
-- 
cgit v1.2.3


From 457e7a135cbf0a0b5ed2717c192c0c57112c3b32 Mon Sep 17 00:00:00 2001
From: Satya Tangirala <satyat@google.com>
Date: Thu, 2 Jul 2020 01:56:04 +0000
Subject: fs: introduce SB_INLINECRYPT

Introduce SB_INLINECRYPT, which is set by filesystems that wish to use
blk-crypto for file content en/decryption. This flag maps to the
'-o inlinecrypt' mount option which multiple filesystems will implement,
and code in fs/crypto/ needs to be able to check for this mount option
in a filesystem-independent way.

Signed-off-by: Satya Tangirala <satyat@google.com>
Reviewed-by: Jaegeuk Kim <jaegeuk@kernel.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20200702015607.1215430-2-satyat@google.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 include/linux/fs.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..b5e07fcdd11d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1380,6 +1380,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_NODIRATIME	2048	/* Do not update directory access times */
 #define SB_SILENT	32768
 #define SB_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define SB_INLINECRYPT	(1<<17)	/* Use blk-crypto for encrypted files */
 #define SB_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define SB_I_VERSION	(1<<23) /* Update inode I_version field */
 #define SB_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
-- 
cgit v1.2.3


From 5fee36095cda45d34555aed3a2e8973b80cd6bf8 Mon Sep 17 00:00:00 2001
From: Satya Tangirala <satyat@google.com>
Date: Thu, 2 Jul 2020 01:56:05 +0000
Subject: fscrypt: add inline encryption support

Add support for inline encryption to fs/crypto/.  With "inline
encryption", the block layer handles the decryption/encryption as part
of the bio, instead of the filesystem doing the crypto itself via
Linux's crypto API. This model is needed in order to take advantage of
the inline encryption hardware present on most modern mobile SoCs.

To use inline encryption, the filesystem needs to be mounted with
'-o inlinecrypt'. Blk-crypto will then be used instead of the traditional
filesystem-layer crypto whenever possible to encrypt the contents
of any encrypted files in that filesystem. Fscrypt still provides the key
and IV to use, and the actual ciphertext on-disk is still the same;
therefore it's testable using the existing fscrypt ciphertext verification
tests.

Note that since blk-crypto has a fallback to Linux's crypto API, and
also supports all the encryption modes currently supported by fscrypt,
this feature is usable and testable even without actual inline
encryption hardware.

Per-filesystem changes will be needed to set encryption contexts when
submitting bios and to implement the 'inlinecrypt' mount option.  This
patch just adds the common code.

Signed-off-by: Satya Tangirala <satyat@google.com>
Reviewed-by: Jaegeuk Kim <jaegeuk@kernel.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20200702015607.1215430-3-satyat@google.com
Co-developed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 Documentation/filesystems/fscrypt.rst |   3 +
 fs/crypto/Kconfig                     |   6 +
 fs/crypto/Makefile                    |   1 +
 fs/crypto/bio.c                       |  51 +++++
 fs/crypto/crypto.c                    |   2 +-
 fs/crypto/fname.c                     |   4 +-
 fs/crypto/fscrypt_private.h           | 115 ++++++++++-
 fs/crypto/inline_crypt.c              | 364 ++++++++++++++++++++++++++++++++++
 fs/crypto/keyring.c                   |   6 +-
 fs/crypto/keysetup.c                  |  70 +++++--
 fs/crypto/keysetup_v1.c               |  16 +-
 include/linux/fscrypt.h               |  82 ++++++++
 12 files changed, 673 insertions(+), 47 deletions(-)
 create mode 100644 fs/crypto/inline_crypt.c

(limited to 'include/linux')

diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index f517af8ec11c..f5d8b0303ddf 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -1255,6 +1255,7 @@ f2fs encryption using `kvm-xfstests
 <https://github.com/tytso/xfstests-bld/blob/master/Documentation/kvm-quickstart.md>`_::
 
     kvm-xfstests -c ext4,f2fs -g encrypt
+    kvm-xfstests -c ext4,f2fs -g encrypt -m inlinecrypt
 
 UBIFS encryption can also be tested this way, but it should be done in
 a separate command, and it takes some time for kvm-xfstests to set up
@@ -1276,6 +1277,7 @@ This tests the encrypted I/O paths more thoroughly.  To do this with
 kvm-xfstests, use the "encrypt" filesystem configuration::
 
     kvm-xfstests -c ext4/encrypt,f2fs/encrypt -g auto
+    kvm-xfstests -c ext4/encrypt,f2fs/encrypt -g auto -m inlinecrypt
 
 Because this runs many more tests than "-g encrypt" does, it takes
 much longer to run; so also consider using `gce-xfstests
@@ -1283,3 +1285,4 @@ much longer to run; so also consider using `gce-xfstests
 instead of kvm-xfstests::
 
     gce-xfstests -c ext4/encrypt,f2fs/encrypt -g auto
+    gce-xfstests -c ext4/encrypt,f2fs/encrypt -g auto -m inlinecrypt
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index 8046d7c7a3e9..f1f11a6228eb 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -24,3 +24,9 @@ config FS_ENCRYPTION_ALGS
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
 	select CRYPTO_XTS
+
+config FS_ENCRYPTION_INLINE_CRYPT
+	bool "Enable fscrypt to use inline crypto"
+	depends on FS_ENCRYPTION && BLK_INLINE_ENCRYPTION
+	help
+	  Enable fscrypt to use inline encryption hardware if available.
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
index 232e2bb5a337..652c7180ec6d 100644
--- a/fs/crypto/Makefile
+++ b/fs/crypto/Makefile
@@ -11,3 +11,4 @@ fscrypto-y := crypto.o \
 	      policy.o
 
 fscrypto-$(CONFIG_BLOCK) += bio.o
+fscrypto-$(CONFIG_FS_ENCRYPTION_INLINE_CRYPT) += inline_crypt.o
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 4fa18fff9c4e..b048a0e38516 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -41,6 +41,53 @@ void fscrypt_decrypt_bio(struct bio *bio)
 }
 EXPORT_SYMBOL(fscrypt_decrypt_bio);
 
+static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode,
+					      pgoff_t lblk, sector_t pblk,
+					      unsigned int len)
+{
+	const unsigned int blockbits = inode->i_blkbits;
+	const unsigned int blocks_per_page = 1 << (PAGE_SHIFT - blockbits);
+	struct bio *bio;
+	int ret, err = 0;
+	int num_pages = 0;
+
+	/* This always succeeds since __GFP_DIRECT_RECLAIM is set. */
+	bio = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+
+	while (len) {
+		unsigned int blocks_this_page = min(len, blocks_per_page);
+		unsigned int bytes_this_page = blocks_this_page << blockbits;
+
+		if (num_pages == 0) {
+			fscrypt_set_bio_crypt_ctx(bio, inode, lblk, GFP_NOFS);
+			bio_set_dev(bio, inode->i_sb->s_bdev);
+			bio->bi_iter.bi_sector =
+					pblk << (blockbits - SECTOR_SHIFT);
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		}
+		ret = bio_add_page(bio, ZERO_PAGE(0), bytes_this_page, 0);
+		if (WARN_ON(ret != bytes_this_page)) {
+			err = -EIO;
+			goto out;
+		}
+		num_pages++;
+		len -= blocks_this_page;
+		lblk += blocks_this_page;
+		pblk += blocks_this_page;
+		if (num_pages == BIO_MAX_PAGES || !len ||
+		    !fscrypt_mergeable_bio(bio, inode, lblk)) {
+			err = submit_bio_wait(bio);
+			if (err)
+				goto out;
+			bio_reset(bio);
+			num_pages = 0;
+		}
+	}
+out:
+	bio_put(bio);
+	return err;
+}
+
 /**
  * fscrypt_zeroout_range() - zero out a range of blocks in an encrypted file
  * @inode: the file's inode
@@ -75,6 +122,10 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 	if (len == 0)
 		return 0;
 
+	if (fscrypt_inode_uses_inline_crypto(inode))
+		return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk,
+							  len);
+
 	BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_PAGES);
 	nr_pages = min_t(unsigned int, ARRAY_SIZE(pages),
 			 (len + blocks_per_page - 1) >> blocks_per_page_bits);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index ed015cb66c7c..a52cf32733ab 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -100,7 +100,7 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw,
 	DECLARE_CRYPTO_WAIT(wait);
 	struct scatterlist dst, src;
 	struct fscrypt_info *ci = inode->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_enc_key.tfm;
 	int res = 0;
 
 	if (WARN_ON_ONCE(len <= 0))
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 83ca5f1e7934..d828e3df898b 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -115,7 +115,7 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 	struct skcipher_request *req = NULL;
 	DECLARE_CRYPTO_WAIT(wait);
 	const struct fscrypt_info *ci = inode->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_enc_key.tfm;
 	union fscrypt_iv iv;
 	struct scatterlist sg;
 	int res;
@@ -171,7 +171,7 @@ static int fname_decrypt(const struct inode *inode,
 	DECLARE_CRYPTO_WAIT(wait);
 	struct scatterlist src_sg, dst_sg;
 	const struct fscrypt_info *ci = inode->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_enc_key.tfm;
 	union fscrypt_iv iv;
 	int res;
 
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index eb7fcd2b7fb8..5bb40d0109c8 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -14,6 +14,7 @@
 #include <linux/fscrypt.h>
 #include <linux/siphash.h>
 #include <crypto/hash.h>
+#include <linux/blk-crypto.h>
 
 #define CONST_STRLEN(str)	(sizeof(str) - 1)
 
@@ -166,6 +167,20 @@ struct fscrypt_symlink_data {
 	char encrypted_path[1];
 } __packed;
 
+/**
+ * struct fscrypt_prepared_key - a key prepared for actual encryption/decryption
+ * @tfm: crypto API transform object
+ * @blk_key: key for blk-crypto
+ *
+ * Normally only one of the fields will be non-NULL.
+ */
+struct fscrypt_prepared_key {
+	struct crypto_skcipher *tfm;
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+	struct fscrypt_blk_crypto_key *blk_key;
+#endif
+};
+
 /*
  * fscrypt_info - the "encryption key" for an inode
  *
@@ -175,12 +190,20 @@ struct fscrypt_symlink_data {
  */
 struct fscrypt_info {
 
-	/* The actual crypto transform used for encryption and decryption */
-	struct crypto_skcipher *ci_ctfm;
+	/* The key in a form prepared for actual encryption/decryption */
+	struct fscrypt_prepared_key ci_enc_key;
 
-	/* True if the key should be freed when this fscrypt_info is freed */
+	/* True if ci_enc_key should be freed when this fscrypt_info is freed */
 	bool ci_owns_key;
 
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+	/*
+	 * True if this inode will use inline encryption (blk-crypto) instead of
+	 * the traditional filesystem-layer encryption.
+	 */
+	bool ci_inlinecrypt;
+#endif
+
 	/*
 	 * Encryption mode used for this inode.  It corresponds to either the
 	 * contents or filenames encryption mode, depending on the inode type.
@@ -205,7 +228,7 @@ struct fscrypt_info {
 
 	/*
 	 * If non-NULL, then encryption is done using the master key directly
-	 * and ci_ctfm will equal ci_direct_key->dk_ctfm.
+	 * and ci_enc_key will equal ci_direct_key->dk_key.
 	 */
 	struct fscrypt_direct_key *ci_direct_key;
 
@@ -260,6 +283,7 @@ union fscrypt_iv {
 		u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
 	};
 	u8 raw[FSCRYPT_MAX_IV_SIZE];
+	__le64 dun[FSCRYPT_MAX_IV_SIZE / sizeof(__le64)];
 };
 
 void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
@@ -302,6 +326,75 @@ int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context,
 
 void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
 
+/* inline_crypt.c */
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+int fscrypt_select_encryption_impl(struct fscrypt_info *ci);
+
+static inline bool
+fscrypt_using_inline_encryption(const struct fscrypt_info *ci)
+{
+	return ci->ci_inlinecrypt;
+}
+
+int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
+				     const u8 *raw_key,
+				     const struct fscrypt_info *ci);
+
+void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key);
+
+/*
+ * Check whether the crypto transform or blk-crypto key has been allocated in
+ * @prep_key, depending on which encryption implementation the file will use.
+ */
+static inline bool
+fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key,
+			const struct fscrypt_info *ci)
+{
+	/*
+	 * The READ_ONCE() here pairs with the smp_store_release() in
+	 * fscrypt_prepare_key().  (This only matters for the per-mode keys,
+	 * which are shared by multiple inodes.)
+	 */
+	if (fscrypt_using_inline_encryption(ci))
+		return READ_ONCE(prep_key->blk_key) != NULL;
+	return READ_ONCE(prep_key->tfm) != NULL;
+}
+
+#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
+
+static inline int fscrypt_select_encryption_impl(struct fscrypt_info *ci)
+{
+	return 0;
+}
+
+static inline bool
+fscrypt_using_inline_encryption(const struct fscrypt_info *ci)
+{
+	return false;
+}
+
+static inline int
+fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
+				 const u8 *raw_key,
+				 const struct fscrypt_info *ci)
+{
+	WARN_ON(1);
+	return -EOPNOTSUPP;
+}
+
+static inline void
+fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key)
+{
+}
+
+static inline bool
+fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key,
+			const struct fscrypt_info *ci)
+{
+	return READ_ONCE(prep_key->tfm) != NULL;
+}
+#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
+
 /* keyring.c */
 
 /*
@@ -395,9 +488,9 @@ struct fscrypt_master_key {
 	 * Per-mode encryption keys for the various types of encryption policies
 	 * that use them.  Allocated and derived on-demand.
 	 */
-	struct crypto_skcipher *mk_direct_keys[__FSCRYPT_MODE_MAX + 1];
-	struct crypto_skcipher *mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1];
-	struct crypto_skcipher *mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1];
+	struct fscrypt_prepared_key mk_direct_keys[__FSCRYPT_MODE_MAX + 1];
+	struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1];
+	struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1];
 
 	/* Hash key for inode numbers.  Initialized only when needed. */
 	siphash_key_t		mk_ino_hash_key;
@@ -461,13 +554,15 @@ struct fscrypt_mode {
 	int keysize;
 	int ivsize;
 	int logged_impl_name;
+	enum blk_crypto_mode_num blk_crypto_mode;
 };
 
 extern struct fscrypt_mode fscrypt_modes[];
 
-struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode,
-						  const u8 *raw_key,
-						  const struct inode *inode);
+int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
+			const u8 *raw_key, const struct fscrypt_info *ci);
+
+void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key);
 
 int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key);
 
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
new file mode 100644
index 000000000000..d7aecadf33c1
--- /dev/null
+++ b/fs/crypto/inline_crypt.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Inline encryption support for fscrypt
+ *
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * With "inline encryption", the block layer handles the decryption/encryption
+ * as part of the bio, instead of the filesystem doing the crypto itself via
+ * crypto API.  See Documentation/block/inline-encryption.rst.  fscrypt still
+ * provides the key and IV to use.
+ */
+
+#include <linux/blk-crypto.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/sched/mm.h>
+
+#include "fscrypt_private.h"
+
+struct fscrypt_blk_crypto_key {
+	struct blk_crypto_key base;
+	int num_devs;
+	struct request_queue *devs[];
+};
+
+static int fscrypt_get_num_devices(struct super_block *sb)
+{
+	if (sb->s_cop->get_num_devices)
+		return sb->s_cop->get_num_devices(sb);
+	return 1;
+}
+
+static void fscrypt_get_devices(struct super_block *sb, int num_devs,
+				struct request_queue **devs)
+{
+	if (num_devs == 1)
+		devs[0] = bdev_get_queue(sb->s_bdev);
+	else
+		sb->s_cop->get_devices(sb, devs);
+}
+
+static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci)
+{
+	struct super_block *sb = ci->ci_inode->i_sb;
+	unsigned int flags = fscrypt_policy_flags(&ci->ci_policy);
+	int ino_bits = 64, lblk_bits = 64;
+
+	if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY)
+		return offsetofend(union fscrypt_iv, nonce);
+
+	if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64)
+		return sizeof(__le64);
+
+	if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)
+		return sizeof(__le32);
+
+	/* Default case: IVs are just the file logical block number */
+	if (sb->s_cop->get_ino_and_lblk_bits)
+		sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits);
+	return DIV_ROUND_UP(lblk_bits, 8);
+}
+
+/* Enable inline encryption for this file if supported. */
+int fscrypt_select_encryption_impl(struct fscrypt_info *ci)
+{
+	const struct inode *inode = ci->ci_inode;
+	struct super_block *sb = inode->i_sb;
+	struct blk_crypto_config crypto_cfg;
+	int num_devs;
+	struct request_queue **devs;
+	int i;
+
+	/* The file must need contents encryption, not filenames encryption */
+	if (!fscrypt_needs_contents_encryption(inode))
+		return 0;
+
+	/* The crypto mode must have a blk-crypto counterpart */
+	if (ci->ci_mode->blk_crypto_mode == BLK_ENCRYPTION_MODE_INVALID)
+		return 0;
+
+	/* The filesystem must be mounted with -o inlinecrypt */
+	if (!(sb->s_flags & SB_INLINECRYPT))
+		return 0;
+
+	/*
+	 * When a page contains multiple logically contiguous filesystem blocks,
+	 * some filesystem code only calls fscrypt_mergeable_bio() for the first
+	 * block in the page. This is fine for most of fscrypt's IV generation
+	 * strategies, where contiguous blocks imply contiguous IVs. But it
+	 * doesn't work with IV_INO_LBLK_32. For now, simply exclude
+	 * IV_INO_LBLK_32 with blocksize != PAGE_SIZE from inline encryption.
+	 */
+	if ((fscrypt_policy_flags(&ci->ci_policy) &
+	     FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) &&
+	    sb->s_blocksize != PAGE_SIZE)
+		return 0;
+
+	/*
+	 * On all the filesystem's devices, blk-crypto must support the crypto
+	 * configuration that the file would use.
+	 */
+	crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode;
+	crypto_cfg.data_unit_size = sb->s_blocksize;
+	crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci);
+	num_devs = fscrypt_get_num_devices(sb);
+	devs = kmalloc_array(num_devs, sizeof(*devs), GFP_NOFS);
+	if (!devs)
+		return -ENOMEM;
+	fscrypt_get_devices(sb, num_devs, devs);
+
+	for (i = 0; i < num_devs; i++) {
+		if (!blk_crypto_config_supported(devs[i], &crypto_cfg))
+			goto out_free_devs;
+	}
+
+	ci->ci_inlinecrypt = true;
+out_free_devs:
+	kfree(devs);
+
+	return 0;
+}
+
+int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
+				     const u8 *raw_key,
+				     const struct fscrypt_info *ci)
+{
+	const struct inode *inode = ci->ci_inode;
+	struct super_block *sb = inode->i_sb;
+	enum blk_crypto_mode_num crypto_mode = ci->ci_mode->blk_crypto_mode;
+	int num_devs = fscrypt_get_num_devices(sb);
+	int queue_refs = 0;
+	struct fscrypt_blk_crypto_key *blk_key;
+	int err;
+	int i;
+	unsigned int flags;
+
+	blk_key = kzalloc(struct_size(blk_key, devs, num_devs), GFP_NOFS);
+	if (!blk_key)
+		return -ENOMEM;
+
+	blk_key->num_devs = num_devs;
+	fscrypt_get_devices(sb, num_devs, blk_key->devs);
+
+	err = blk_crypto_init_key(&blk_key->base, raw_key, crypto_mode,
+				  fscrypt_get_dun_bytes(ci), sb->s_blocksize);
+	if (err) {
+		fscrypt_err(inode, "error %d initializing blk-crypto key", err);
+		goto fail;
+	}
+
+	/*
+	 * We have to start using blk-crypto on all the filesystem's devices.
+	 * We also have to save all the request_queue's for later so that the
+	 * key can be evicted from them.  This is needed because some keys
+	 * aren't destroyed until after the filesystem was already unmounted
+	 * (namely, the per-mode keys in struct fscrypt_master_key).
+	 */
+	for (i = 0; i < num_devs; i++) {
+		if (!blk_get_queue(blk_key->devs[i])) {
+			fscrypt_err(inode, "couldn't get request_queue");
+			err = -EAGAIN;
+			goto fail;
+		}
+		queue_refs++;
+
+		flags = memalloc_nofs_save();
+		err = blk_crypto_start_using_key(&blk_key->base,
+						 blk_key->devs[i]);
+		memalloc_nofs_restore(flags);
+		if (err) {
+			fscrypt_err(inode,
+				    "error %d starting to use blk-crypto", err);
+			goto fail;
+		}
+	}
+	/*
+	 * Pairs with READ_ONCE() in fscrypt_is_key_prepared().  (Only matters
+	 * for the per-mode keys, which are shared by multiple inodes.)
+	 */
+	smp_store_release(&prep_key->blk_key, blk_key);
+	return 0;
+
+fail:
+	for (i = 0; i < queue_refs; i++)
+		blk_put_queue(blk_key->devs[i]);
+	kzfree(blk_key);
+	return err;
+}
+
+void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key)
+{
+	struct fscrypt_blk_crypto_key *blk_key = prep_key->blk_key;
+	int i;
+
+	if (blk_key) {
+		for (i = 0; i < blk_key->num_devs; i++) {
+			blk_crypto_evict_key(blk_key->devs[i], &blk_key->base);
+			blk_put_queue(blk_key->devs[i]);
+		}
+		kzfree(blk_key);
+	}
+}
+
+bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode)
+{
+	return inode->i_crypt_info->ci_inlinecrypt;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_inode_uses_inline_crypto);
+
+static void fscrypt_generate_dun(const struct fscrypt_info *ci, u64 lblk_num,
+				 u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE])
+{
+	union fscrypt_iv iv;
+	int i;
+
+	fscrypt_generate_iv(&iv, lblk_num, ci);
+
+	BUILD_BUG_ON(FSCRYPT_MAX_IV_SIZE > BLK_CRYPTO_MAX_IV_SIZE);
+	memset(dun, 0, BLK_CRYPTO_MAX_IV_SIZE);
+	for (i = 0; i < ci->ci_mode->ivsize/sizeof(dun[0]); i++)
+		dun[i] = le64_to_cpu(iv.dun[i]);
+}
+
+/**
+ * fscrypt_set_bio_crypt_ctx() - prepare a file contents bio for inline crypto
+ * @bio: a bio which will eventually be submitted to the file
+ * @inode: the file's inode
+ * @first_lblk: the first file logical block number in the I/O
+ * @gfp_mask: memory allocation flags - these must be a waiting mask so that
+ *					bio_crypt_set_ctx can't fail.
+ *
+ * If the contents of the file should be encrypted (or decrypted) with inline
+ * encryption, then assign the appropriate encryption context to the bio.
+ *
+ * Normally the bio should be newly allocated (i.e. no pages added yet), as
+ * otherwise fscrypt_mergeable_bio() won't work as intended.
+ *
+ * The encryption context will be freed automatically when the bio is freed.
+ */
+void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
+			       u64 first_lblk, gfp_t gfp_mask)
+{
+	const struct fscrypt_info *ci = inode->i_crypt_info;
+	u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+
+	if (!fscrypt_inode_uses_inline_crypto(inode))
+		return;
+
+	fscrypt_generate_dun(ci, first_lblk, dun);
+	bio_crypt_set_ctx(bio, &ci->ci_enc_key.blk_key->base, dun, gfp_mask);
+}
+EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx);
+
+/* Extract the inode and logical block number from a buffer_head. */
+static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh,
+				      const struct inode **inode_ret,
+				      u64 *lblk_num_ret)
+{
+	struct page *page = bh->b_page;
+	const struct address_space *mapping;
+	const struct inode *inode;
+
+	/*
+	 * The ext4 journal (jbd2) can submit a buffer_head it directly created
+	 * for a non-pagecache page.  fscrypt doesn't care about these.
+	 */
+	mapping = page_mapping(page);
+	if (!mapping)
+		return false;
+	inode = mapping->host;
+
+	*inode_ret = inode;
+	*lblk_num_ret = ((u64)page->index << (PAGE_SHIFT - inode->i_blkbits)) +
+			(bh_offset(bh) >> inode->i_blkbits);
+	return true;
+}
+
+/**
+ * fscrypt_set_bio_crypt_ctx_bh() - prepare a file contents bio for inline
+ *				    crypto
+ * @bio: a bio which will eventually be submitted to the file
+ * @first_bh: the first buffer_head for which I/O will be submitted
+ * @gfp_mask: memory allocation flags
+ *
+ * Same as fscrypt_set_bio_crypt_ctx(), except this takes a buffer_head instead
+ * of an inode and block number directly.
+ */
+void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio,
+				  const struct buffer_head *first_bh,
+				  gfp_t gfp_mask)
+{
+	const struct inode *inode;
+	u64 first_lblk;
+
+	if (bh_get_inode_and_lblk_num(first_bh, &inode, &first_lblk))
+		fscrypt_set_bio_crypt_ctx(bio, inode, first_lblk, gfp_mask);
+}
+EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx_bh);
+
+/**
+ * fscrypt_mergeable_bio() - test whether data can be added to a bio
+ * @bio: the bio being built up
+ * @inode: the inode for the next part of the I/O
+ * @next_lblk: the next file logical block number in the I/O
+ *
+ * When building a bio which may contain data which should undergo inline
+ * encryption (or decryption) via fscrypt, filesystems should call this function
+ * to ensure that the resulting bio contains only contiguous data unit numbers.
+ * This will return false if the next part of the I/O cannot be merged with the
+ * bio because either the encryption key would be different or the encryption
+ * data unit numbers would be discontiguous.
+ *
+ * fscrypt_set_bio_crypt_ctx() must have already been called on the bio.
+ *
+ * Return: true iff the I/O is mergeable
+ */
+bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
+			   u64 next_lblk)
+{
+	const struct bio_crypt_ctx *bc = bio->bi_crypt_context;
+	u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+
+	if (!!bc != fscrypt_inode_uses_inline_crypto(inode))
+		return false;
+	if (!bc)
+		return true;
+
+	/*
+	 * Comparing the key pointers is good enough, as all I/O for each key
+	 * uses the same pointer.  I.e., there's currently no need to support
+	 * merging requests where the keys are the same but the pointers differ.
+	 */
+	if (bc->bc_key != &inode->i_crypt_info->ci_enc_key.blk_key->base)
+		return false;
+
+	fscrypt_generate_dun(inode->i_crypt_info, next_lblk, next_dun);
+	return bio_crypt_dun_is_contiguous(bc, bio->bi_iter.bi_size, next_dun);
+}
+EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio);
+
+/**
+ * fscrypt_mergeable_bio_bh() - test whether data can be added to a bio
+ * @bio: the bio being built up
+ * @next_bh: the next buffer_head for which I/O will be submitted
+ *
+ * Same as fscrypt_mergeable_bio(), except this takes a buffer_head instead of
+ * an inode and block number directly.
+ *
+ * Return: true iff the I/O is mergeable
+ */
+bool fscrypt_mergeable_bio_bh(struct bio *bio,
+			      const struct buffer_head *next_bh)
+{
+	const struct inode *inode;
+	u64 next_lblk;
+
+	if (!bh_get_inode_and_lblk_num(next_bh, &inode, &next_lblk))
+		return !bio->bi_crypt_context;
+
+	return fscrypt_mergeable_bio(bio, inode, next_lblk);
+}
+EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh);
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index e24eb48bfbe1..7f8ac61a20d6 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -45,9 +45,9 @@ static void free_master_key(struct fscrypt_master_key *mk)
 	wipe_master_key_secret(&mk->mk_secret);
 
 	for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) {
-		crypto_free_skcipher(mk->mk_direct_keys[i]);
-		crypto_free_skcipher(mk->mk_iv_ino_lblk_64_keys[i]);
-		crypto_free_skcipher(mk->mk_iv_ino_lblk_32_keys[i]);
+		fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]);
+		fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]);
+		fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]);
 	}
 
 	key_put(mk->mk_users);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 1129adfa097d..99d3e0d07fc6 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -19,6 +19,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.cipher_str = "xts(aes)",
 		.keysize = 64,
 		.ivsize = 16,
+		.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_256_XTS,
 	},
 	[FSCRYPT_MODE_AES_256_CTS] = {
 		.friendly_name = "AES-256-CTS-CBC",
@@ -31,6 +32,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.cipher_str = "essiv(cbc(aes),sha256)",
 		.keysize = 16,
 		.ivsize = 16,
+		.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV,
 	},
 	[FSCRYPT_MODE_AES_128_CTS] = {
 		.friendly_name = "AES-128-CTS-CBC",
@@ -43,6 +45,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.cipher_str = "adiantum(xchacha12,aes)",
 		.keysize = 32,
 		.ivsize = 32,
+		.blk_crypto_mode = BLK_ENCRYPTION_MODE_ADIANTUM,
 	},
 };
 
@@ -64,9 +67,9 @@ select_encryption_mode(const union fscrypt_policy *policy,
 }
 
 /* Create a symmetric cipher object for the given encryption mode and key */
-struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode,
-						  const u8 *raw_key,
-						  const struct inode *inode)
+static struct crypto_skcipher *
+fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key,
+			  const struct inode *inode)
 {
 	struct crypto_skcipher *tfm;
 	int err;
@@ -109,30 +112,54 @@ err_free_tfm:
 	return ERR_PTR(err);
 }
 
-/* Given a per-file encryption key, set up the file's crypto transform object */
-int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key)
+/*
+ * Prepare the crypto transform object or blk-crypto key in @prep_key, given the
+ * raw key, encryption mode, and flag indicating which encryption implementation
+ * (fs-layer or blk-crypto) will be used.
+ */
+int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
+			const u8 *raw_key, const struct fscrypt_info *ci)
 {
 	struct crypto_skcipher *tfm;
 
+	if (fscrypt_using_inline_encryption(ci))
+		return fscrypt_prepare_inline_crypt_key(prep_key, raw_key, ci);
+
 	tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
+	/*
+	 * Pairs with READ_ONCE() in fscrypt_is_key_prepared().  (Only matters
+	 * for the per-mode keys, which are shared by multiple inodes.)
+	 */
+	smp_store_release(&prep_key->tfm, tfm);
+	return 0;
+}
+
+/* Destroy a crypto transform object and/or blk-crypto key. */
+void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key)
+{
+	crypto_free_skcipher(prep_key->tfm);
+	fscrypt_destroy_inline_crypt_key(prep_key);
+}
 
-	ci->ci_ctfm = tfm;
+/* Given a per-file encryption key, set up the file's crypto transform object */
+int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key)
+{
 	ci->ci_owns_key = true;
-	return 0;
+	return fscrypt_prepare_key(&ci->ci_enc_key, raw_key, ci);
 }
 
 static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 				  struct fscrypt_master_key *mk,
-				  struct crypto_skcipher **tfms,
+				  struct fscrypt_prepared_key *keys,
 				  u8 hkdf_context, bool include_fs_uuid)
 {
 	const struct inode *inode = ci->ci_inode;
 	const struct super_block *sb = inode->i_sb;
 	struct fscrypt_mode *mode = ci->ci_mode;
 	const u8 mode_num = mode - fscrypt_modes;
-	struct crypto_skcipher *tfm;
+	struct fscrypt_prepared_key *prep_key;
 	u8 mode_key[FSCRYPT_MAX_KEY_SIZE];
 	u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)];
 	unsigned int hkdf_infolen = 0;
@@ -141,16 +168,15 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 	if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX))
 		return -EINVAL;
 
-	/* pairs with smp_store_release() below */
-	tfm = READ_ONCE(tfms[mode_num]);
-	if (likely(tfm != NULL)) {
-		ci->ci_ctfm = tfm;
+	prep_key = &keys[mode_num];
+	if (fscrypt_is_key_prepared(prep_key, ci)) {
+		ci->ci_enc_key = *prep_key;
 		return 0;
 	}
 
 	mutex_lock(&fscrypt_mode_key_setup_mutex);
 
-	if (tfms[mode_num])
+	if (fscrypt_is_key_prepared(prep_key, ci))
 		goto done_unlock;
 
 	BUILD_BUG_ON(sizeof(mode_num) != 1);
@@ -167,16 +193,12 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 				  mode_key, mode->keysize);
 	if (err)
 		goto out_unlock;
-	tfm = fscrypt_allocate_skcipher(mode, mode_key, inode);
+	err = fscrypt_prepare_key(prep_key, mode_key, ci);
 	memzero_explicit(mode_key, mode->keysize);
-	if (IS_ERR(tfm)) {
-		err = PTR_ERR(tfm);
+	if (err)
 		goto out_unlock;
-	}
-	/* pairs with READ_ONCE() above */
-	smp_store_release(&tfms[mode_num], tfm);
 done_unlock:
-	ci->ci_ctfm = tfm;
+	ci->ci_enc_key = *prep_key;
 	err = 0;
 out_unlock:
 	mutex_unlock(&fscrypt_mode_key_setup_mutex);
@@ -310,6 +332,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 	struct fscrypt_key_specifier mk_spec;
 	int err;
 
+	err = fscrypt_select_encryption_impl(ci);
+	if (err)
+		return err;
+
 	switch (ci->ci_policy.version) {
 	case FSCRYPT_POLICY_V1:
 		mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
@@ -402,7 +428,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	if (ci->ci_direct_key)
 		fscrypt_put_direct_key(ci->ci_direct_key);
 	else if (ci->ci_owns_key)
-		crypto_free_skcipher(ci->ci_ctfm);
+		fscrypt_destroy_prepared_key(&ci->ci_enc_key);
 
 	key = ci->ci_master_key;
 	if (key) {
diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c
index 801b48c0cd7f..a52686729a67 100644
--- a/fs/crypto/keysetup_v1.c
+++ b/fs/crypto/keysetup_v1.c
@@ -146,7 +146,7 @@ struct fscrypt_direct_key {
 	struct hlist_node		dk_node;
 	refcount_t			dk_refcount;
 	const struct fscrypt_mode	*dk_mode;
-	struct crypto_skcipher		*dk_ctfm;
+	struct fscrypt_prepared_key	dk_key;
 	u8				dk_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
 	u8				dk_raw[FSCRYPT_MAX_KEY_SIZE];
 };
@@ -154,7 +154,7 @@ struct fscrypt_direct_key {
 static void free_direct_key(struct fscrypt_direct_key *dk)
 {
 	if (dk) {
-		crypto_free_skcipher(dk->dk_ctfm);
+		fscrypt_destroy_prepared_key(&dk->dk_key);
 		kzfree(dk);
 	}
 }
@@ -199,6 +199,8 @@ find_or_insert_direct_key(struct fscrypt_direct_key *to_insert,
 			continue;
 		if (ci->ci_mode != dk->dk_mode)
 			continue;
+		if (!fscrypt_is_key_prepared(&dk->dk_key, ci))
+			continue;
 		if (crypto_memneq(raw_key, dk->dk_raw, ci->ci_mode->keysize))
 			continue;
 		/* using existing tfm with same (descriptor, mode, raw_key) */
@@ -231,13 +233,9 @@ fscrypt_get_direct_key(const struct fscrypt_info *ci, const u8 *raw_key)
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&dk->dk_refcount, 1);
 	dk->dk_mode = ci->ci_mode;
-	dk->dk_ctfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key,
-						ci->ci_inode);
-	if (IS_ERR(dk->dk_ctfm)) {
-		err = PTR_ERR(dk->dk_ctfm);
-		dk->dk_ctfm = NULL;
+	err = fscrypt_prepare_key(&dk->dk_key, raw_key, ci);
+	if (err)
 		goto err_free_dk;
-	}
 	memcpy(dk->dk_descriptor, ci->ci_policy.v1.master_key_descriptor,
 	       FSCRYPT_KEY_DESCRIPTOR_SIZE);
 	memcpy(dk->dk_raw, raw_key, ci->ci_mode->keysize);
@@ -259,7 +257,7 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci,
 	if (IS_ERR(dk))
 		return PTR_ERR(dk);
 	ci->ci_direct_key = dk;
-	ci->ci_ctfm = dk->dk_ctfm;
+	ci->ci_enc_key = dk->dk_key;
 	return 0;
 }
 
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 2862ca5fea33..bb257411365f 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -69,6 +69,9 @@ struct fscrypt_operations {
 	bool (*has_stable_inodes)(struct super_block *sb);
 	void (*get_ino_and_lblk_bits)(struct super_block *sb,
 				      int *ino_bits_ret, int *lblk_bits_ret);
+	int (*get_num_devices)(struct super_block *sb);
+	void (*get_devices)(struct super_block *sb,
+			    struct request_queue **devs);
 };
 
 static inline bool fscrypt_has_encryption_key(const struct inode *inode)
@@ -537,6 +540,85 @@ static inline void fscrypt_set_ops(struct super_block *sb,
 
 #endif	/* !CONFIG_FS_ENCRYPTION */
 
+/* inline_crypt.c */
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+
+bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode);
+
+void fscrypt_set_bio_crypt_ctx(struct bio *bio,
+			       const struct inode *inode, u64 first_lblk,
+			       gfp_t gfp_mask);
+
+void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio,
+				  const struct buffer_head *first_bh,
+				  gfp_t gfp_mask);
+
+bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
+			   u64 next_lblk);
+
+bool fscrypt_mergeable_bio_bh(struct bio *bio,
+			      const struct buffer_head *next_bh);
+
+#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
+
+static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode)
+{
+	return false;
+}
+
+static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio,
+					     const struct inode *inode,
+					     u64 first_lblk, gfp_t gfp_mask) { }
+
+static inline void fscrypt_set_bio_crypt_ctx_bh(
+					 struct bio *bio,
+					 const struct buffer_head *first_bh,
+					 gfp_t gfp_mask) { }
+
+static inline bool fscrypt_mergeable_bio(struct bio *bio,
+					 const struct inode *inode,
+					 u64 next_lblk)
+{
+	return true;
+}
+
+static inline bool fscrypt_mergeable_bio_bh(struct bio *bio,
+					    const struct buffer_head *next_bh)
+{
+	return true;
+}
+#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
+
+/**
+ * fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline
+ *					encryption
+ * @inode: an inode. If encrypted, its key must be set up.
+ *
+ * Return: true if the inode requires file contents encryption and if the
+ *	   encryption should be done in the block layer via blk-crypto rather
+ *	   than in the filesystem layer.
+ */
+static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode)
+{
+	return fscrypt_needs_contents_encryption(inode) &&
+	       __fscrypt_inode_uses_inline_crypto(inode);
+}
+
+/**
+ * fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer
+ *					  encryption
+ * @inode: an inode. If encrypted, its key must be set up.
+ *
+ * Return: true if the inode requires file contents encryption and if the
+ *	   encryption should be done in the filesystem layer rather than in the
+ *	   block layer via blk-crypto.
+ */
+static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode)
+{
+	return fscrypt_needs_contents_encryption(inode) &&
+	       !__fscrypt_inode_uses_inline_crypto(inode);
+}
+
 /**
  * fscrypt_require_key() - require an inode's encryption key
  * @inode: the inode we need the key for
-- 
cgit v1.2.3


From 6ec4476ac82512f09c94aff5972654b70f3772b2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 8 Jul 2020 10:48:35 -0700
Subject: Raise gcc version requirement to 4.9

I realize that we fairly recently raised it to 4.8, but the fact is, 4.9
is a much better minimum version to target.

We have a number of workarounds for actual bugs in pre-4.9 gcc versions
(including things like internal compiler errors on ARM), but we also
have some syntactic workarounds for lacking features.

In particular, raising the minimum to 4.9 means that we can now just
assume _Generic() exists, which is likely the much better replacement
for a lot of very convoluted built-time magic with conditionals on
sizeof and/or __builtin_choose_expr() with same_type() etc.

Using _Generic also means that you will need to have a very recent
version of 'sparse', but thats easy to build yourself, and much less of
a hassle than some old gcc version can be.

The latest (in a long string) of reasons for minimum compiler version
upgrades was commit 5435f73d5c4a ("efi/x86: Fix build with gcc 4").

Ard points out that RHEL 7 uses gcc-4.8, but the people who stay back on
old RHEL versions persumably also don't build their own kernels anyway.
And maybe they should cross-built or just have a little side affair with
a newer compiler?

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/asm-offsets.c  |  9 ---------
 arch/mips/include/asm/unroll.h |  7 +++----
 include/linux/bits.h           |  3 +--
 include/linux/compiler-gcc.h   |  2 +-
 include/linux/compiler_types.h | 27 +--------------------------
 mm/migrate.c                   | 13 +------------
 tools/include/linux/bits.h     |  3 +--
 7 files changed, 8 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c036a4a2f8e2..a1570c8bab25 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -31,15 +31,6 @@
 #if defined(__APCS_26__)
 #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32
 #endif
-/*
- * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854
- *	      miscompiles find_get_entry(), and can result in EXT3 and EXT4
- *	      filesystem corruption (possibly other FS too).
- */
-#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803
-#error Your compiler is too buggy; it is known to miscompile kernels
-#error and result in filesystem corruption and oopses.
-#endif
 
 int main(void)
 {
diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h
index c628747d4ecd..8ed660adc84f 100644
--- a/arch/mips/include/asm/unroll.h
+++ b/arch/mips/include/asm/unroll.h
@@ -19,14 +19,13 @@
 								\
 	/*							\
 	 * We can't unroll if the number of iterations isn't	\
-	 * compile-time constant. Unfortunately GCC versions	\
-	 * up until 4.6 tend to miss obvious constants & cause	\
+	 * compile-time constant. Unfortunately clang versions	\
+	 * up until 8.0 tend to miss obvious constants & cause	\
 	 * this check to fail, even though they go on to	\
 	 * generate reasonable code for the switch statement,	\
 	 * so we skip the sanity check for those compilers.	\
 	 */							\
-	BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 ||		\
-		      CONFIG_CLANG_VERSION >= 80000) &&		\
+	BUILD_BUG_ON((CONFIG_CLANG_VERSION >= 80000) &&		\
 		     !__builtin_constant_p(times));		\
 								\
 	switch (times) {					\
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 4671fbf28842..7f475d59a097 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -18,8 +18,7 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#if !defined(__ASSEMBLY__) && \
-	(!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000)
+#if !defined(__ASSEMBLY__)
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 1c74464c80c6..0b1dc61f3955 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -11,7 +11,7 @@
 		     + __GNUC_PATCHLEVEL__)
 
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
-#if GCC_VERSION < 40800
+#if GCC_VERSION < 40900
 # error Sorry, your compiler is too old - please upgrade it.
 #endif
 
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index c3bf7710f69a..01dd58c74d80 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -252,32 +252,8 @@ struct ftrace_likely_data {
  * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving
  *			       non-scalar types unchanged.
  */
-#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__)
 /*
- * We build this out of a couple of helper macros in a vain attempt to
- * help you keep your lunch down while reading it.
- */
-#define __pick_scalar_type(x, type, otherwise)					\
-	__builtin_choose_expr(__same_type(x, type), (type)0, otherwise)
-
-/*
- * 'char' is not type-compatible with either 'signed char' or 'unsigned char',
- * so we include the naked type here as well as the signed/unsigned variants.
- */
-#define __pick_integer_type(x, type, otherwise)					\
-	__pick_scalar_type(x, type,						\
-		__pick_scalar_type(x, unsigned type,				\
-			__pick_scalar_type(x, signed type, otherwise)))
-
-#define __unqual_scalar_typeof(x) typeof(					\
-	__pick_integer_type(x, char,						\
-		__pick_integer_type(x, short,					\
-			__pick_integer_type(x, int,				\
-				__pick_integer_type(x, long,			\
-					__pick_integer_type(x, long long, x))))))
-#else
-/*
- * If supported, prefer C11 _Generic for better compile-times. As above, 'char'
+ * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char'
  * is not type-compatible with 'signed char', and we define a separate case.
  */
 #define __scalar_type_to_expr_cases(type)				\
@@ -293,7 +269,6 @@ struct ftrace_likely_data {
 			 __scalar_type_to_expr_cases(long),		\
 			 __scalar_type_to_expr_cases(long long),	\
 			 default: (x)))
-#endif
 
 /* Is this type a native word size -- useful for atomic operations */
 #define __native_word(t) \
diff --git a/mm/migrate.c b/mm/migrate.c
index f37729673558..40cd7016ae6f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1160,22 +1160,11 @@ out:
 	return rc;
 }
 
-/*
- * gcc 4.7 and 4.8 on arm get an ICEs when inlining unmap_and_move().  Work
- * around it.
- */
-#if defined(CONFIG_ARM) && \
-	defined(GCC_VERSION) && GCC_VERSION < 40900 && GCC_VERSION >= 40700
-#define ICE_noinline noinline
-#else
-#define ICE_noinline
-#endif
-
 /*
  * Obtain the lock on page, remove all ptes and migrate the page
  * to the newly allocated page in newpage.
  */
-static ICE_noinline int unmap_and_move(new_page_t get_new_page,
+static int unmap_and_move(new_page_t get_new_page,
 				   free_page_t put_new_page,
 				   unsigned long private, struct page *page,
 				   int force, enum migrate_mode mode,
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 4671fbf28842..7f475d59a097 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -18,8 +18,7 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#if !defined(__ASSEMBLY__) && \
-	(!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000)
+#if !defined(__ASSEMBLY__)
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-- 
cgit v1.2.3


From bd36ed1c935144a0e3b788bba659258f666e7b5b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 8 Jul 2020 09:46:24 -0700
Subject: net: phy: Define PHY statistics ethtool_phy_ops

Extend ethtool_phy_ops to include the 3 function pointers necessary for
implementing PHY statistics. In a subsequent change we will uninline
those functions.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 3 +++
 include/linux/ethtool.h      | 7 +++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 233334406f0f..7cda95330aea 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3028,6 +3028,9 @@ static struct phy_driver genphy_driver = {
 };
 
 static const struct ethtool_phy_ops phy_ethtool_phy_ops = {
+	.get_sset_count		= phy_ethtool_get_sset_count,
+	.get_strings		= phy_ethtool_get_strings,
+	.get_stats		= phy_ethtool_get_stats,
 	.start_cable_test	= phy_start_cable_test,
 	.start_cable_test_tdr	= phy_start_cable_test_tdr,
 };
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 0c139a93b67a..969a80211df6 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -508,6 +508,9 @@ struct phy_tdr_config;
 
 /**
  * struct ethtool_phy_ops - Optional PHY device options
+ * @get_sset_count: Get number of strings that @get_strings will write.
+ * @get_strings: Return a set of strings that describe the requested objects
+ * @get_stats: Return extended statistics about the PHY device.
  * @start_cable_test - Start a cable test
  * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test
  *
@@ -515,6 +518,10 @@ struct phy_tdr_config;
  * and callers must take this into account. Callers must hold the RTNL lock.
  */
 struct ethtool_phy_ops {
+	int (*get_sset_count)(struct phy_device *dev);
+	int (*get_strings)(struct phy_device *dev, u8 *data);
+	int (*get_stats)(struct phy_device *dev,
+			 struct ethtool_stats *stats, u64 *data);
 	int (*start_cable_test)(struct phy_device *phydev,
 				struct netlink_ext_ack *extack);
 	int (*start_cable_test_tdr)(struct phy_device *phydev,
-- 
cgit v1.2.3


From 17809516a03a045565ad6a80e6241754615871ac Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 8 Jul 2020 09:46:25 -0700
Subject: net: phy: Uninline PHY ethtool statistics operations

Now that we have moved the PHY ethtool statistics to be dynamically
registered, we no longer need to inline those for ethtool. This used to
be done to avoid cross symbol referencing and allow ethtool to be
decoupled from PHYLIB entirely.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h   | 49 ++++---------------------------------------------
 net/ethtool/ioctl.c   | 23 +++++++++++++++--------
 net/ethtool/strset.c  | 11 +++++++----
 4 files changed, 74 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 56cfae950472..79b4f35d151e 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -489,6 +489,54 @@ static void phy_abort_cable_test(struct phy_device *phydev)
 		phydev_err(phydev, "Error while aborting cable test");
 }
 
+int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
+{
+	if (!phydev->drv)
+		return -EIO;
+
+	mutex_lock(&phydev->lock);
+	phydev->drv->get_strings(phydev, data);
+	mutex_unlock(&phydev->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_get_strings);
+
+int phy_ethtool_get_sset_count(struct phy_device *phydev)
+{
+	int ret;
+
+	if (!phydev->drv)
+		return -EIO;
+
+	if (phydev->drv->get_sset_count &&
+	    phydev->drv->get_strings &&
+	    phydev->drv->get_stats) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->get_sset_count(phydev);
+		mutex_unlock(&phydev->lock);
+
+		return ret;
+	}
+
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(phy_ethtool_get_sset_count);
+
+int phy_ethtool_get_stats(struct phy_device *phydev,
+			  struct ethtool_stats *stats, u64 *data)
+{
+	if (!phydev->drv)
+		return -EIO;
+
+	mutex_lock(&phydev->lock);
+	phydev->drv->get_stats(phydev, stats, data);
+	mutex_unlock(&phydev->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_get_stats);
+
 int phy_start_cable_test(struct phy_device *phydev,
 			 struct netlink_ext_ack *extack)
 {
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 1592c3d0e12f..0403eb799913 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1474,51 +1474,10 @@ int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
 #endif
 
-/* Inline function for use within net/core/ethtool.c (built-in) */
-static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
-{
-	if (!phydev->drv)
-		return -EIO;
-
-	mutex_lock(&phydev->lock);
-	phydev->drv->get_strings(phydev, data);
-	mutex_unlock(&phydev->lock);
-
-	return 0;
-}
-
-static inline int phy_ethtool_get_sset_count(struct phy_device *phydev)
-{
-	int ret;
-
-	if (!phydev->drv)
-		return -EIO;
-
-	if (phydev->drv->get_sset_count &&
-	    phydev->drv->get_strings &&
-	    phydev->drv->get_stats) {
-		mutex_lock(&phydev->lock);
-		ret = phydev->drv->get_sset_count(phydev);
-		mutex_unlock(&phydev->lock);
-
-		return ret;
-	}
-
-	return -EOPNOTSUPP;
-}
-
-static inline int phy_ethtool_get_stats(struct phy_device *phydev,
-					struct ethtool_stats *stats, u64 *data)
-{
-	if (!phydev->drv)
-		return -EIO;
-
-	mutex_lock(&phydev->lock);
-	phydev->drv->get_stats(phydev, stats, data);
-	mutex_unlock(&phydev->lock);
-
-	return 0;
-}
+int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data);
+int phy_ethtool_get_sset_count(struct phy_device *phydev);
+int phy_ethtool_get_stats(struct phy_device *phydev,
+			  struct ethtool_stats *stats, u64 *data);
 
 static inline int phy_package_read(struct phy_device *phydev, u32 regnum)
 {
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 83f22196d64c..441794e0034f 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -135,6 +135,7 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
 
 static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 {
+	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 
 	if (sset == ETH_SS_FEATURES)
@@ -150,8 +151,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 		return ARRAY_SIZE(phy_tunable_strings);
 
 	if (sset == ETH_SS_PHY_STATS && dev->phydev &&
-	    !ops->get_ethtool_phy_stats)
-		return phy_ethtool_get_sset_count(dev->phydev);
+	    !ops->get_ethtool_phy_stats &&
+	    phy_ops && phy_ops->get_sset_count)
+		return phy_ops->get_sset_count(dev->phydev);
 
 	if (sset == ETH_SS_LINK_MODES)
 		return __ETHTOOL_LINK_MODE_MASK_NBITS;
@@ -165,6 +167,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 static void __ethtool_get_strings(struct net_device *dev,
 	u32 stringset, u8 *data)
 {
+	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 
 	if (stringset == ETH_SS_FEATURES)
@@ -178,8 +181,9 @@ static void __ethtool_get_strings(struct net_device *dev,
 	else if (stringset == ETH_SS_PHY_TUNABLES)
 		memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings));
 	else if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
-		 !ops->get_ethtool_phy_stats)
-		phy_ethtool_get_strings(dev->phydev, data);
+		 !ops->get_ethtool_phy_stats && phy_ops &&
+		 phy_ops->get_strings)
+		phy_ops->get_strings(dev->phydev, data);
 	else if (stringset == ETH_SS_LINK_MODES)
 		memcpy(data, link_mode_names,
 		       __ETHTOOL_LINK_MODE_MASK_NBITS * ETH_GSTRING_LEN);
@@ -1929,6 +1933,7 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 
 static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 {
+	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
 	struct ethtool_stats stats;
@@ -1938,8 +1943,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 	if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
 		return -EOPNOTSUPP;
 
-	if (dev->phydev && !ops->get_ethtool_phy_stats)
-		n_stats = phy_ethtool_get_sset_count(dev->phydev);
+	if (dev->phydev && !ops->get_ethtool_phy_stats &&
+	    phy_ops && phy_ops->get_sset_count)
+		n_stats = phy_ops->get_sset_count(dev->phydev);
 	else
 		n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
 	if (n_stats < 0)
@@ -1958,8 +1964,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		if (!data)
 			return -ENOMEM;
 
-		if (dev->phydev && !ops->get_ethtool_phy_stats) {
-			ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+		if (dev->phydev && !ops->get_ethtool_phy_stats &&
+		    phy_ops && phy_ops->get_stats) {
+			ret = phy_ops->get_stats(dev->phydev, &stats, data);
 			if (ret < 0)
 				goto out;
 		} else {
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 0eed4e4909ab..773634b6b048 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -209,13 +209,15 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base)
 static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
 			      unsigned int id, bool counts_only)
 {
+	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	void *strings;
 	int count, ret;
 
 	if (id == ETH_SS_PHY_STATS && dev->phydev &&
-	    !ops->get_ethtool_phy_stats)
-		ret = phy_ethtool_get_sset_count(dev->phydev);
+	    !ops->get_ethtool_phy_stats && phy_ops &&
+	    phy_ops->get_sset_count)
+		ret = phy_ops->get_sset_count(dev->phydev);
 	else if (ops->get_sset_count && ops->get_strings)
 		ret = ops->get_sset_count(dev, id);
 	else
@@ -231,8 +233,9 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
 		if (!strings)
 			return -ENOMEM;
 		if (id == ETH_SS_PHY_STATS && dev->phydev &&
-		    !ops->get_ethtool_phy_stats)
-			phy_ethtool_get_strings(dev->phydev, strings);
+		    !ops->get_ethtool_phy_stats && phy_ops &&
+		    phy_ops->get_strings)
+			phy_ops->get_strings(dev->phydev, strings);
 		else
 			ops->get_strings(dev, id, strings);
 		info->strings = strings;
-- 
cgit v1.2.3


From e8c22266e68f0db2a7e11b0a9f29fd88ec0cfd4a Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 15 Jun 2020 14:13:34 +0200
Subject: KVM: async_pf: change kvm_setup_async_pf()/kvm_arch_setup_async_pf()
 return type to bool

Unlike normal 'int' functions returning '0' on success, kvm_setup_async_pf()/
kvm_arch_setup_async_pf() return '1' when a job to handle page fault
asynchronously was scheduled and '0' otherwise. To avoid the confusion
change return type to 'bool'.

No functional change intended.

Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200615121334.91300-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 20 +++++++++-----------
 arch/x86/kvm/mmu/mmu.c   |  4 ++--
 include/linux/kvm_host.h |  4 ++--
 virt/kvm/async_pf.c      | 16 ++++++++++------
 4 files changed, 23 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d47c19718615..7fd4fdb165fc 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3954,33 +3954,31 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
 {
 	hva_t hva;
 	struct kvm_arch_async_pf arch;
-	int rc;
 
 	if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
-		return 0;
+		return false;
 	if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
 	    vcpu->arch.pfault_compare)
-		return 0;
+		return false;
 	if (psw_extint_disabled(vcpu))
-		return 0;
+		return false;
 	if (kvm_s390_vcpu_has_irq(vcpu, 0))
-		return 0;
+		return false;
 	if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK))
-		return 0;
+		return false;
 	if (!vcpu->arch.gmap->pfault_enabled)
-		return 0;
+		return false;
 
 	hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr));
 	hva += current->thread.gmap_addr & ~PAGE_MASK;
 	if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8))
-		return 0;
+		return false;
 
-	rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
-	return rc;
+	return kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
 }
 
 static int vcpu_pre_run(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3ca70554d5f1..a1850120ede0 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4045,8 +4045,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-				   gfn_t gfn)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				    gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 62ec926c78a0..9edc6fc71a89 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -211,8 +211,8 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-		       unsigned long hva, struct kvm_arch_async_pf *arch);
+bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			unsigned long hva, struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 45799606bb3e..390f758d5a27 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -156,17 +156,21 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-		       unsigned long hva, struct kvm_arch_async_pf *arch)
+/*
+ * Try to schedule a job to handle page fault asynchronously. Returns 'true' on
+ * success, 'false' on failure (page fault has to be handled synchronously).
+ */
+bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			unsigned long hva, struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
 
 	if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
-		return 0;
+		return false;
 
 	/* Arch specific code should not do async PF in this case */
 	if (unlikely(kvm_is_error_hva(hva)))
-		return 0;
+		return false;
 
 	/*
 	 * do alloc nowait since if we are going to sleep anyway we
@@ -174,7 +178,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	 */
 	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
 	if (!work)
-		return 0;
+		return false;
 
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
@@ -193,7 +197,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 
 	schedule_work(&work->work);
 
-	return 1;
+	return true;
 }
 
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
-- 
cgit v1.2.3


From ecd7274fb4cd2d6c035a52d59ca3d6ec936a07be Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 4 Jun 2020 18:11:15 +0100
Subject: iommu: Remove unused IOMMU_SYS_CACHE_ONLY flag

The IOMMU_SYS_CACHE_ONLY flag was never exposed via the DMA API and
has no in-tree users. Remove it.

Cc: Robin Murphy <robin.murphy@arm.com>
Cc: "Isaac J. Manjarres" <isaacm@codeaurora.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm.c | 3 ---
 include/linux/iommu.h          | 6 ------
 2 files changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 04fbd4bf0ff9..8f175c02f8e3 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -438,9 +438,6 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		else if (prot & IOMMU_CACHE)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
-		else if (prot & IOMMU_SYS_CACHE_ONLY)
-			pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE
-				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
 	if (prot & IOMMU_CACHE)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 5f0b7859d2eb..bee1a8fa1fb1 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -31,12 +31,6 @@
  * if the IOMMU page table format is equivalent.
  */
 #define IOMMU_PRIV	(1 << 5)
-/*
- * Non-coherent masters can use this page protection flag to set cacheable
- * memory attributes for only a transparent outer level of cache, also known as
- * the last-level or system cache.
- */
-#define IOMMU_SYS_CACHE_ONLY	(1 << 6)
 
 struct iommu_ops;
 struct iommu_group;
-- 
cgit v1.2.3


From a564e23f0f99759f453dbefcb9160dec6d99df96 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jul 2020 14:25:41 +0200
Subject: md: switch to ->check_events for media change notifications

md is the last driver using the legacy media_changed method.  Switch
it over to (not so) new ->clear_events approach, which also removes the
need for the ->revalidate_disk method.

Signed-off-by: Christoph Hellwig <hch@lst.de>
[axboe: remove unused 'bdops' variable in disk_clear_events()]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/filesystems/locking.rst |  4 +---
 block/genhd.c                         |  8 +-------
 drivers/md/md.c                       | 19 ++++++++-----------
 include/linux/blkdev.h                |  2 --
 4 files changed, 10 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 318605de83f3..17bea12538c3 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -467,7 +467,6 @@ prototypes::
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t, void **,
 				unsigned long *);
-	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
@@ -483,14 +482,13 @@ release:		yes
 ioctl:			no
 compat_ioctl:		no
 direct_access:		no
-media_changed:		no
 unlock_native_capacity:	no
 revalidate_disk:	no
 getgeo:			no
 swap_slot_free_notify:	no	(see below)
 ======================= ===================
 
-media_changed, unlock_native_capacity and revalidate_disk are called only from
+unlock_native_capacity and revalidate_disk are called only from
 check_disk_change().
 
 swap_slot_free_notify is called with swap_lock and sometimes the page lock
diff --git a/block/genhd.c b/block/genhd.c
index 60ae4e1b4d38..c42a49f2f537 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -2056,18 +2056,12 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
  */
 unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 {
-	const struct block_device_operations *bdops = disk->fops;
 	struct disk_events *ev = disk->ev;
 	unsigned int pending;
 	unsigned int clearing = mask;
 
-	if (!ev) {
-		/* for drivers still using the old ->media_changed method */
-		if ((mask & DISK_EVENT_MEDIA_CHANGE) &&
-		    bdops->media_changed && bdops->media_changed(disk))
-			return DISK_EVENT_MEDIA_CHANGE;
+	if (!ev)
 		return 0;
-	}
 
 	disk_block_events(disk);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8bb69c61afe0..77dfe4765c31 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5670,6 +5670,7 @@ static int md_alloc(dev_t dev, char *name)
 	 * remove it now.
 	 */
 	disk->flags |= GENHD_FL_EXT_DEVT;
+	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	/* As soon as we call add_disk(), another thread could get
 	 * through to md_open, so make sure it doesn't get too far
@@ -7806,20 +7807,17 @@ static void md_release(struct gendisk *disk, fmode_t mode)
 	mddev_put(mddev);
 }
 
-static int md_media_changed(struct gendisk *disk)
-{
-	struct mddev *mddev = disk->private_data;
-
-	return mddev->changed;
-}
-
-static int md_revalidate(struct gendisk *disk)
+static unsigned int md_check_events(struct gendisk *disk, unsigned int clearing)
 {
 	struct mddev *mddev = disk->private_data;
+	unsigned int ret = 0;
 
+	if (mddev->changed)
+		ret = DISK_EVENT_MEDIA_CHANGE;
 	mddev->changed = 0;
-	return 0;
+	return ret;
 }
+
 static const struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
@@ -7831,8 +7829,7 @@ static const struct block_device_operations md_fops =
 	.compat_ioctl	= md_compat_ioctl,
 #endif
 	.getgeo		= md_getgeo,
-	.media_changed  = md_media_changed,
-	.revalidate_disk= md_revalidate,
+	.check_events	= md_check_events,
 };
 
 static int md_thread(void *arg)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 408eb66a82fd..71173a1ffa8b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1781,8 +1781,6 @@ struct block_device_operations {
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
-	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
-	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
-- 
cgit v1.2.3


From 8c22eb3a77373c616f141b56f44ef225ee15c96b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jul 2020 14:25:42 +0200
Subject: cdrom: remove the unused cdrom_media_changed function

As well as the ->media_changed method.  All these are left over from
before the drivers were switched over to the check_events scheme.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/cdrom/cdrom-standard.rst | 18 +-----------------
 drivers/cdrom/cdrom.c                  | 28 +++++-----------------------
 include/linux/cdrom.h                  |  2 --
 3 files changed, 6 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst
index dde4f7f7fdbf..2de905810590 100644
--- a/Documentation/cdrom/cdrom-standard.rst
+++ b/Documentation/cdrom/cdrom-standard.rst
@@ -157,7 +157,6 @@ with the kernel as a block device by registering the following general
 		cdrom_release,		/∗ release ∗/
 		NULL,			/∗ fsync ∗/
 		NULL,			/∗ fasync ∗/
-		cdrom_media_changed,	/∗ media change ∗/
 		NULL			/∗ revalidate ∗/
 	};
 
@@ -366,19 +365,6 @@ which may or may not be in the drive). If the drive is not a changer,
 	CDS_DRIVE_NOT_READY	/* something is wrong, tray is moving? */
 	CDS_DISC_OK		/* a disc is loaded and everything is fine */
 
-::
-
-	int media_changed(struct cdrom_device_info *cdi, int disc_nr)
-
-This function is very similar to the original function in $struct
-file_operations*. It returns 1 if the medium of the device *cdi->dev*
-has changed since the last call, and 0 otherwise. The parameter
-*disc_nr* identifies a specific slot in a juke-box, it should be
-ignored for single-disc drives. Note that by `re-routing` this
-function through *cdrom_media_changed()*, we can implement separate
-queues for the VFS and a new *ioctl()* function that can report device
-changes to software (e. g., an auto-mounting daemon).
-
 ::
 
 	int tray_move(struct cdrom_device_info *cdi, int position)
@@ -917,9 +903,7 @@ commands can be identified by the underscores in their names.
 	maximum number of discs in the juke-box found in the *cdrom_dops*.
 `CDROM_MEDIA_CHANGED`
 	Returns 1 if a disc has been changed since the last call.
-	Note that calls to *cdrom_media_changed* by the VFS are treated
-	by an independent queue, so both mechanisms will detect a
-	media change once. For juke-boxes, an extra argument *arg*
+	For juke-boxes, an extra argument *arg*
 	specifies the slot for which the information is given. The special
 	value *CDSL_CURRENT* requests that information about the currently
 	selected slot be returned.
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index d82b3b7658bd..0c271b9e3c5b 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -605,7 +605,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi)
 	disk->cdi = cdi;
 
 	ENSURE(cdo, drive_status, CDC_DRIVE_STATUS);
-	if (cdo->check_events == NULL && cdo->media_changed == NULL)
+	if (cdo->check_events == NULL)
 		WARN_ON_ONCE(cdo->capability & (CDC_MEDIA_CHANGED | CDC_SELECT_DISC));
 	ENSURE(cdo, tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY);
 	ENSURE(cdo, lock_door, CDC_LOCK);
@@ -1419,8 +1419,6 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot)
 
 	if (cdi->ops->check_events)
 		cdi->ops->check_events(cdi, 0, slot);
-	else
-		cdi->ops->media_changed(cdi, slot);
 
 	if (slot == CDSL_NONE) {
 		/* set media changed bits, on both queues */
@@ -1517,13 +1515,10 @@ int media_changed(struct cdrom_device_info *cdi, int queue)
 		return ret;
 
 	/* changed since last call? */
-	if (cdi->ops->check_events) {
-		BUG_ON(!queue);	/* shouldn't be called from VFS path */
-		cdrom_update_events(cdi, DISK_EVENT_MEDIA_CHANGE);
-		changed = cdi->ioctl_events & DISK_EVENT_MEDIA_CHANGE;
-		cdi->ioctl_events = 0;
-	} else
-		changed = cdi->ops->media_changed(cdi, CDSL_CURRENT);
+	BUG_ON(!queue);	/* shouldn't be called from VFS path */
+	cdrom_update_events(cdi, DISK_EVENT_MEDIA_CHANGE);
+	changed = cdi->ioctl_events & DISK_EVENT_MEDIA_CHANGE;
+	cdi->ioctl_events = 0;
 
 	if (changed) {
 		cdi->mc_flags = 0x3;    /* set bit on both queues */
@@ -1535,18 +1530,6 @@ int media_changed(struct cdrom_device_info *cdi, int queue)
 	return ret;
 }
 
-int cdrom_media_changed(struct cdrom_device_info *cdi)
-{
-	/* This talks to the VFS, which doesn't like errors - just 1 or 0.  
-	 * Returning "0" is always safe (media hasn't been changed). Do that 
-	 * if the low-level cdrom driver dosn't support media changed. */ 
-	if (cdi == NULL || cdi->ops->media_changed == NULL)
-		return 0;
-	if (!CDROM_CAN(CDC_MEDIA_CHANGED))
-		return 0;
-	return media_changed(cdi, 0);
-}
-
 /* Requests to the low-level drivers will /always/ be done in the
    following format convention:
 
@@ -3464,7 +3447,6 @@ EXPORT_SYMBOL(unregister_cdrom);
 EXPORT_SYMBOL(cdrom_open);
 EXPORT_SYMBOL(cdrom_release);
 EXPORT_SYMBOL(cdrom_ioctl);
-EXPORT_SYMBOL(cdrom_media_changed);
 EXPORT_SYMBOL(cdrom_number_of_slots);
 EXPORT_SYMBOL(cdrom_mode_select);
 EXPORT_SYMBOL(cdrom_mode_sense);
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 8543fa59da72..f48d0a31deae 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -73,7 +73,6 @@ struct cdrom_device_ops {
 	int (*drive_status) (struct cdrom_device_info *, int);
 	unsigned int (*check_events) (struct cdrom_device_info *cdi,
 				      unsigned int clearing, int slot);
-	int (*media_changed) (struct cdrom_device_info *, int);
 	int (*tray_move) (struct cdrom_device_info *, int);
 	int (*lock_door) (struct cdrom_device_info *, int);
 	int (*select_speed) (struct cdrom_device_info *, int);
@@ -107,7 +106,6 @@ extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
 		       fmode_t mode, unsigned int cmd, unsigned long arg);
 extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
 				       unsigned int clearing);
-extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi);
 extern void unregister_cdrom(struct cdrom_device_info *cdi);
-- 
cgit v1.2.3


From 12fdafb817c6cde87a4fa0e674e66b0226a0889d Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Mon, 6 Jul 2020 20:42:33 -0700
Subject: net/mlx5: Added support for 100Gbps per lane link modes

This patch exposes new link modes using 100Gbps per lane, including 100G,
200G and 400G modes.

Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c   |  3 +++
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c    | 21 ++++++++++++++++++++-
 include/linux/mlx5/port.h                           |  3 +++
 3 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 2a8950b3056f..be83db63aca0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -76,6 +76,9 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= 100000,
 	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= 200000,
 	[MLX5E_400GAUI_8]			= 400000,
+	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= 100000,
+	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= 200000,
+	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= 400000,
 };
 
 static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ec5658bbe3c5..6183bee7d21b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -194,6 +194,24 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_1_100GBASE_CR_KR, ext,
+				       ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseDR_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseCR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_2_200GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_4_400GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT);
 }
 
 static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
@@ -1012,7 +1030,8 @@ static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes)
 	unsigned long modes[2];
 
 	for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) {
-		if (*ptys2ext_ethtool_table[i].advertised == 0)
+		if (ptys2ext_ethtool_table[i].advertised[0] == 0 &&
+		    ptys2ext_ethtool_table[i].advertised[1] == 0)
 			continue;
 		memset(modes, 0, sizeof(modes));
 		bitmap_and(modes, ptys2ext_ethtool_table[i].advertised,
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index de9a272c9f3d..2d45a6af52a4 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -104,8 +104,11 @@ enum mlx5e_ext_link_mode {
 	MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR	= 8,
 	MLX5E_CAUI_4_100GBASE_CR4_KR4		= 9,
 	MLX5E_100GAUI_2_100GBASE_CR2_KR2	= 10,
+	MLX5E_100GAUI_1_100GBASE_CR_KR		= 11,
 	MLX5E_200GAUI_4_200GBASE_CR4_KR4	= 12,
+	MLX5E_200GAUI_2_200GBASE_CR2_KR2	= 13,
 	MLX5E_400GAUI_8				= 15,
+	MLX5E_400GAUI_4_400GBASE_CR4_KR4	= 16,
 	MLX5E_EXT_LINK_MODES_NUMBER,
 };
 
-- 
cgit v1.2.3


From 160251842cd35a75edfb0a1d76afa3eb674ff40a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 2 Jul 2020 11:49:23 -0700
Subject: kallsyms: Refactor kallsyms_show_value() to take cred

In order to perform future tests against the cred saved during open(),
switch kallsyms_show_value() to operate on a cred, and have all current
callers pass current_cred(). This makes it very obvious where callers
are checking the wrong credential in their "read" contexts. These will
be fixed in the coming patches.

Additionally switch return value to bool, since it is always used as a
direct permission check, not a 0-on-success, negative-on-error style
function return.

Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/filter.h   |  2 +-
 include/linux/kallsyms.h |  5 +++--
 kernel/kallsyms.c        | 17 +++++++++++------
 kernel/kprobes.c         |  4 ++--
 kernel/module.c          |  2 +-
 5 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 259377723603..55104f6c78e8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -889,7 +889,7 @@ static inline bool bpf_dump_raw_ok(void)
 	/* Reconstruction of call-sites is dependent on kallsyms,
 	 * thus make dump the same restriction.
 	 */
-	return kallsyms_show_value() == 1;
+	return kallsyms_show_value(current_cred());
 }
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index 98338dc6b5d2..481273f0c72d 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -18,6 +18,7 @@
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
 			 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
 
+struct cred;
 struct module;
 
 static inline int is_kernel_inittext(unsigned long addr)
@@ -98,7 +99,7 @@ int lookup_symbol_name(unsigned long addr, char *symname);
 int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
 
 /* How and when do we show kallsyms values? */
-extern int kallsyms_show_value(void);
+extern bool kallsyms_show_value(const struct cred *cred);
 
 #else /* !CONFIG_KALLSYMS */
 
@@ -158,7 +159,7 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u
 	return -ERANGE;
 }
 
-static inline int kallsyms_show_value(void)
+static inline bool kallsyms_show_value(const struct cred *cred)
 {
 	return false;
 }
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 16c8c605f4b0..bb14e64f62a4 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -644,19 +644,20 @@ static inline int kallsyms_for_perf(void)
  * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
  * block even that).
  */
-int kallsyms_show_value(void)
+bool kallsyms_show_value(const struct cred *cred)
 {
 	switch (kptr_restrict) {
 	case 0:
 		if (kallsyms_for_perf())
-			return 1;
+			return true;
 	/* fallthrough */
 	case 1:
-		if (has_capability_noaudit(current, CAP_SYSLOG))
-			return 1;
+		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
+				     CAP_OPT_NOAUDIT) == 0)
+			return true;
 	/* fallthrough */
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -673,7 +674,11 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	reset_iter(iter, 0);
 
-	iter->show_value = kallsyms_show_value();
+	/*
+	 * Instead of checking this on every s_show() call, cache
+	 * the result here at open time.
+	 */
+	iter->show_value = kallsyms_show_value(file->f_cred);
 	return 0;
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 4a904cc56d68..d4de217e4a91 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2448,7 +2448,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 	else
 		kprobe_type = "k";
 
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(current_cred()))
 		addr = NULL;
 
 	if (sym)
@@ -2540,7 +2540,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	 * If /proc/kallsyms is not showing kernel address, we won't
 	 * show them here either.
 	 */
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(current_cred()))
 		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
 			   (void *)ent->start_addr);
 	else
diff --git a/kernel/module.c b/kernel/module.c
index e8a198588f26..a5022ae84e50 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4377,7 +4377,7 @@ static int modules_open(struct inode *inode, struct file *file)
 
 	if (!err) {
 		struct seq_file *m = file->private_data;
-		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
+		m->private = kallsyms_show_value(current_cred()) ? NULL : (void *)8ul;
 	}
 
 	return err;
-- 
cgit v1.2.3


From 63960260457a02af2a6cb35d75e6bdb17299c882 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 2 Jul 2020 15:45:23 -0700
Subject: bpf: Check correct cred for CAP_SYSLOG in bpf_dump_raw_ok()

When evaluating access control over kallsyms visibility, credentials at
open() time need to be used, not the "current" creds (though in BPF's
case, this has likely always been the same). Plumb access to associated
file->f_cred down through bpf_dump_raw_ok() and its callers now that
kallsysm_show_value() has been refactored to take struct cred.

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: bpf@vger.kernel.org
Cc: stable@vger.kernel.org
Fixes: 7105e828c087 ("bpf: allow for correlation of maps and helpers in dump")
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/filter.h     |  4 ++--
 kernel/bpf/syscall.c       | 37 +++++++++++++++++++++----------------
 net/core/sysctl_net_core.c |  2 +-
 3 files changed, 24 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 55104f6c78e8..0b0144752d78 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -884,12 +884,12 @@ void bpf_jit_compile(struct bpf_prog *prog);
 bool bpf_jit_needs_zext(void);
 bool bpf_helper_changes_pkt_data(void *func);
 
-static inline bool bpf_dump_raw_ok(void)
+static inline bool bpf_dump_raw_ok(const struct cred *cred)
 {
 	/* Reconstruction of call-sites is dependent on kallsyms,
 	 * thus make dump the same restriction.
 	 */
-	return kallsyms_show_value(current_cred());
+	return kallsyms_show_value(cred);
 }
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8da159936bab..859053ddf05b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3139,7 +3139,8 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	return NULL;
 }
 
-static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
+					      const struct cred *f_cred)
 {
 	const struct bpf_map *map;
 	struct bpf_insn *insns;
@@ -3165,7 +3166,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 		    code == (BPF_JMP | BPF_CALL_ARGS)) {
 			if (code == (BPF_JMP | BPF_CALL_ARGS))
 				insns[i].code = BPF_JMP | BPF_CALL;
-			if (!bpf_dump_raw_ok())
+			if (!bpf_dump_raw_ok(f_cred))
 				insns[i].imm = 0;
 			continue;
 		}
@@ -3221,7 +3222,8 @@ static int set_info_rec_size(struct bpf_prog_info *info)
 	return 0;
 }
 
-static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+static int bpf_prog_get_info_by_fd(struct file *file,
+				   struct bpf_prog *prog,
 				   const union bpf_attr *attr,
 				   union bpf_attr __user *uattr)
 {
@@ -3290,11 +3292,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		struct bpf_insn *insns_sanitized;
 		bool fault;
 
-		if (prog->blinded && !bpf_dump_raw_ok()) {
+		if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
 			info.xlated_prog_insns = 0;
 			goto done;
 		}
-		insns_sanitized = bpf_insn_prepare_dump(prog);
+		insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
 		if (!insns_sanitized)
 			return -ENOMEM;
 		uinsns = u64_to_user_ptr(info.xlated_prog_insns);
@@ -3328,7 +3330,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	if (info.jited_prog_len && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			uinsns = u64_to_user_ptr(info.jited_prog_insns);
 			ulen = min_t(u32, info.jited_prog_len, ulen);
 
@@ -3363,7 +3365,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_ksyms;
 	info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			unsigned long ksym_addr;
 			u64 __user *user_ksyms;
 			u32 i;
@@ -3394,7 +3396,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_func_lens;
 	info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			u32 __user *user_lens;
 			u32 func_len, i;
 
@@ -3451,7 +3453,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	else
 		info.nr_jited_line_info = 0;
 	if (info.nr_jited_line_info && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			__u64 __user *user_linfo;
 			u32 i;
 
@@ -3497,7 +3499,8 @@ done:
 	return 0;
 }
 
-static int bpf_map_get_info_by_fd(struct bpf_map *map,
+static int bpf_map_get_info_by_fd(struct file *file,
+				  struct bpf_map *map,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3540,7 +3543,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	return 0;
 }
 
-static int bpf_btf_get_info_by_fd(struct btf *btf,
+static int bpf_btf_get_info_by_fd(struct file *file,
+				  struct btf *btf,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3555,7 +3559,8 @@ static int bpf_btf_get_info_by_fd(struct btf *btf,
 	return btf_get_info_by_fd(btf, attr, uattr);
 }
 
-static int bpf_link_get_info_by_fd(struct bpf_link *link,
+static int bpf_link_get_info_by_fd(struct file *file,
+				  struct bpf_link *link,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3608,15 +3613,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 		return -EBADFD;
 
 	if (f.file->f_op == &bpf_prog_fops)
-		err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
 					      uattr);
 	else if (f.file->f_op == &bpf_map_fops)
-		err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
-		err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
+		err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
 	else if (f.file->f_op == &bpf_link_fops)
-		err = bpf_link_get_info_by_fd(f.file->private_data,
+		err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
 					      attr, uattr);
 	else
 		err = -EINVAL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f93f8ace6c56..6ada114bbcca 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -274,7 +274,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 	if (write && !ret) {
 		if (jit_enable < 2 ||
-		    (jit_enable == 2 && bpf_dump_raw_ok())) {
+		    (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
 			*(int *)table->data = jit_enable;
 			if (jit_enable == 2)
 				pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
-- 
cgit v1.2.3


From d7481b24b816b8c3955a9eaf01b97e2bd7f61a37 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Fri, 3 Jul 2020 12:56:19 -0400
Subject: audit: issue CWD record to accompany LSM_AUDIT_DATA_* records

The LSM_AUDIT_DATA_* records for PATH, FILE, IOCTL_OP, DENTRY and INODE
are incomplete without the task context of the AUDIT Current Working
Directory record.  Add it.

This record addition can't use audit_dummy_context to determine whether
or not to store the record information since the LSM_AUDIT_DATA_*
records are initiated by various LSMs independent of any audit rules.
context->in_syscall is used to determine if it was called in user
context like audit_getname.

Please see the upstream issue
https://github.com/linux-audit/audit-kernel/issues/96

Adapted from Vladis Dronov's v2 patch.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h |  9 ++++++++-
 kernel/auditsc.c      | 17 +++++++++++++++--
 security/lsm_audit.c  |  5 +++++
 3 files changed, 28 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index b5478c64bc69..523f77494847 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -292,7 +292,7 @@ extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1,
 extern void __audit_syscall_exit(int ret_success, long ret_value);
 extern struct filename *__audit_reusename(const __user char *uptr);
 extern void __audit_getname(struct filename *name);
-
+extern void __audit_getcwd(void);
 extern void __audit_inode(struct filename *name, const struct dentry *dentry,
 				unsigned int flags);
 extern void __audit_file(const struct file *);
@@ -351,6 +351,11 @@ static inline void audit_getname(struct filename *name)
 	if (unlikely(!audit_dummy_context()))
 		__audit_getname(name);
 }
+static inline void audit_getcwd(void)
+{
+	if (unlikely(audit_context()))
+		__audit_getcwd();
+}
 static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int aflags) {
@@ -579,6 +584,8 @@ static inline struct filename *audit_reusename(const __user char *name)
 }
 static inline void audit_getname(struct filename *name)
 { }
+static inline void audit_getcwd(void)
+{ }
 static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int aflags)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index eae1a599ffe3..6884b50069d1 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1891,6 +1891,20 @@ __audit_reusename(const __user char *uptr)
 	return NULL;
 }
 
+inline void _audit_getcwd(struct audit_context *context)
+{
+	if (!context->pwd.dentry)
+		get_fs_pwd(current->fs, &context->pwd);
+}
+
+void __audit_getcwd(void)
+{
+	struct audit_context *context = audit_context();
+
+	if (context->in_syscall)
+		_audit_getcwd(context);
+}
+
 /**
  * __audit_getname - add a name to the list
  * @name: name to add
@@ -1915,8 +1929,7 @@ void __audit_getname(struct filename *name)
 	name->aname = n;
 	name->refcnt++;
 
-	if (!context->pwd.dentry)
-		get_fs_pwd(current->fs, &context->pwd);
+	_audit_getcwd(context);
 }
 
 static inline int audit_copy_fcaps(struct audit_names *name,
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 2d2bf49016f4..7c555621c2bd 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -241,6 +241,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
+		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_FILE: {
@@ -254,6 +255,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
+		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_IOCTL_OP: {
@@ -269,6 +271,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		}
 
 		audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd);
+		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_DENTRY: {
@@ -283,6 +286,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
+		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_INODE: {
@@ -300,6 +304,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		audit_log_format(ab, " dev=");
 		audit_log_untrustedstring(ab, inode->i_sb->s_id);
 		audit_log_format(ab, " ino=%lu", inode->i_ino);
+		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_TASK: {
-- 
cgit v1.2.3


From 492d76b215660be833f12c3fa7cf2faf39434841 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 11:06:20 +0200
Subject: writeback: remove {set,clear}_wb_congested

Just merge them into their only callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/backing-dev-defs.h | 14 ++------------
 mm/backing-dev.c                 | 12 ++++++------
 2 files changed, 8 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 90a7e844a098..cc5aa1f32b91 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -232,18 +232,8 @@ enum {
 	BLK_RW_SYNC	= 1,
 };
 
-void clear_wb_congested(struct bdi_writeback_congested *congested, int sync);
-void set_wb_congested(struct bdi_writeback_congested *congested, int sync);
-
-static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	clear_wb_congested(bdi->wb.congested, sync);
-}
-
-static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	set_wb_congested(bdi->wb.congested, sync);
-}
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
+void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 
 struct wb_lock_cookie {
 	bool locked;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d382272bcc31..3ebe5144a102 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1047,29 +1047,29 @@ static wait_queue_head_t congestion_wqh[2] = {
 	};
 static atomic_t nr_wb_congested[2];
 
-void clear_wb_congested(struct bdi_writeback_congested *congested, int sync)
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (test_and_clear_bit(bit, &congested->state))
+	if (test_and_clear_bit(bit, &bdi->wb.congested->state))
 		atomic_dec(&nr_wb_congested[sync]);
 	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))
 		wake_up(wqh);
 }
-EXPORT_SYMBOL(clear_wb_congested);
+EXPORT_SYMBOL(clear_bdi_congested);
 
-void set_wb_congested(struct bdi_writeback_congested *congested, int sync)
+void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (!test_and_set_bit(bit, &congested->state))
+	if (!test_and_set_bit(bit, &bdi->wb.congested->state))
 		atomic_inc(&nr_wb_congested[sync]);
 }
-EXPORT_SYMBOL(set_wb_congested);
+EXPORT_SYMBOL(set_bdi_congested);
 
 /**
  * congestion_wait - wait for a backing_dev to become uncongested
-- 
cgit v1.2.3


From 8c911f3d4c074a17955a1757c9d1d5a9a5209ca5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 11:06:21 +0200
Subject: writeback: remove struct bdi_writeback_congested

We never set any congested bits in the group writeback instances of it.
And for the simpler bdi-wide case a simple scalar field is all that
that is needed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c               |  19 +----
 drivers/md/dm.c                  |   2 +-
 include/linux/backing-dev-defs.h |  25 +------
 include/linux/backing-dev.h      |  18 +----
 include/linux/blk-cgroup.h       |   6 --
 mm/backing-dev.c                 | 149 +++------------------------------------
 6 files changed, 14 insertions(+), 205 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 594f1d0b0e5a..e00d0458a9d6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -95,9 +95,6 @@ static void __blkg_release(struct rcu_head *rcu)
 	css_put(&blkg->blkcg->css);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
-
-	wb_congested_put(blkg->wb_congested);
-
 	blkg_free(blkg);
 }
 
@@ -227,7 +224,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 				    struct blkcg_gq *new_blkg)
 {
 	struct blkcg_gq *blkg;
-	struct bdi_writeback_congested *wb_congested;
 	int i, ret;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
@@ -245,31 +241,22 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 		goto err_free_blkg;
 	}
 
-	wb_congested = wb_congested_get_create(q->backing_dev_info,
-					       blkcg->css.id,
-					       GFP_NOWAIT | __GFP_NOWARN);
-	if (!wb_congested) {
-		ret = -ENOMEM;
-		goto err_put_css;
-	}
-
 	/* allocate */
 	if (!new_blkg) {
 		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
-			goto err_put_congested;
+			goto err_put_css;
 		}
 	}
 	blkg = new_blkg;
-	blkg->wb_congested = wb_congested;
 
 	/* link parent */
 	if (blkcg_parent(blkcg)) {
 		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
 		if (WARN_ON_ONCE(!blkg->parent)) {
 			ret = -ENODEV;
-			goto err_put_congested;
+			goto err_put_css;
 		}
 		blkg_get(blkg->parent);
 	}
@@ -306,8 +293,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	blkg_put(blkg);
 	return ERR_PTR(ret);
 
-err_put_congested:
-	wb_congested_put(wb_congested);
 err_put_css:
 	css_put(&blkcg->css);
 err_free_blkg:
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2d368cafb23e..48bfd41658aa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1834,7 +1834,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * top-level queue for congestion.
 			 */
 			struct backing_dev_info *bdi = md->queue->backing_dev_info;
-			r = bdi->wb.congested->state & bdi_bits;
+			r = bdi->wb.congested & bdi_bits;
 		} else {
 			map = dm_get_live_table_fast(md);
 			if (map)
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index cc5aa1f32b91..1cec4521e1fb 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -87,26 +87,6 @@ struct wb_completion {
 #define DEFINE_WB_COMPLETION(cmpl, bdi)	\
 	struct wb_completion cmpl = WB_COMPLETION_INIT(bdi)
 
-/*
- * For cgroup writeback, multiple wb's may map to the same blkcg.  Those
- * wb's can operate mostly independently but should share the congested
- * state.  To facilitate such sharing, the congested state is tracked using
- * the following struct which is created on demand, indexed by blkcg ID on
- * its bdi, and refcounted.
- */
-struct bdi_writeback_congested {
-	unsigned long state;		/* WB_[a]sync_congested flags */
-	refcount_t refcnt;		/* nr of attached wb's and blkg */
-
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct backing_dev_info *__bdi;	/* the associated bdi, set to NULL
-					 * on bdi unregistration. For memcg-wb
-					 * internal use only! */
-	int blkcg_id;			/* ID of the associated blkcg */
-	struct rb_node rb_node;		/* on bdi->cgwb_congestion_tree */
-#endif
-};
-
 /*
  * Each wb (bdi_writeback) can perform writeback operations, is measured
  * and throttled, independently.  Without cgroup writeback, each bdi
@@ -140,7 +120,7 @@ struct bdi_writeback {
 
 	struct percpu_counter stat[NR_WB_STAT_ITEMS];
 
-	struct bdi_writeback_congested *congested;
+	unsigned long congested;	/* WB_[a]sync_congested flags */
 
 	unsigned long bw_time_stamp;	/* last time write bw is updated */
 	unsigned long dirtied_stamp;
@@ -208,11 +188,8 @@ struct backing_dev_info {
 	struct list_head wb_list; /* list of all wbs */
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
-	struct rb_root cgwb_congested_tree; /* their congested states */
 	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 	struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
-#else
-	struct bdi_writeback_congested *wb_congested;
 #endif
 	wait_queue_head_t wb_waitq;
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 6b3504bf7a42..9173d2c22b4a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -173,7 +173,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 
 	if (bdi->congested_fn)
 		return bdi->congested_fn(bdi->congested_data, cong_bits);
-	return wb->congested->state & cong_bits;
+	return wb->congested & cong_bits;
 }
 
 long congestion_wait(int sync, long timeout);
@@ -224,9 +224,6 @@ static inline int bdi_sched_wait(void *word)
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
-void wb_congested_put(struct bdi_writeback_congested *congested);
 struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi,
 				    struct cgroup_subsys_state *memcg_css);
 struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
@@ -404,19 +401,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 	return false;
 }
 
-static inline struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
-{
-	refcount_inc(&bdi->wb_congested->refcnt);
-	return bdi->wb_congested;
-}
-
-static inline void wb_congested_put(struct bdi_writeback_congested *congested)
-{
-	if (refcount_dec_and_test(&congested->refcnt))
-		kfree(congested);
-}
-
 static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
 {
 	return &bdi->wb;
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 431b2d18bf40..c8fc9792ac77 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -109,12 +109,6 @@ struct blkcg_gq {
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
 
-	/*
-	 * Each blkg gets congested separately and the congestion state is
-	 * propagated to the matching bdi_writeback_congested.
-	 */
-	struct bdi_writeback_congested	*wb_congested;
-
 	/* all non-root blkcg_gq's are guaranteed to have access to parent */
 	struct blkcg_gq			*parent;
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3ebe5144a102..8e8b00627bb2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -281,7 +281,7 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 #define INIT_BW		(100 << (20 - PAGE_SHIFT))
 
 static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
-		   int blkcg_id, gfp_t gfp)
+		   gfp_t gfp)
 {
 	int i, err;
 
@@ -308,15 +308,9 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	wb->dirty_sleep = jiffies;
 
-	wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);
-	if (!wb->congested) {
-		err = -ENOMEM;
-		goto out_put_bdi;
-	}
-
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
-		goto out_put_cong;
+		goto out_put_bdi;
 
 	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&wb->stat[i], 0, gfp);
@@ -330,8 +324,6 @@ out_destroy_stat:
 	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
-out_put_cong:
-	wb_congested_put(wb->congested);
 out_put_bdi:
 	if (wb != &bdi->wb)
 		bdi_put(bdi);
@@ -374,7 +366,6 @@ static void wb_exit(struct bdi_writeback *wb)
 		percpu_counter_destroy(&wb->stat[i]);
 
 	fprop_local_destroy_percpu(&wb->completions);
-	wb_congested_put(wb->congested);
 	if (wb != &wb->bdi->wb)
 		bdi_put(wb->bdi);
 }
@@ -384,99 +375,12 @@ static void wb_exit(struct bdi_writeback *wb)
 #include <linux/memcontrol.h>
 
 /*
- * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree,
- * blkcg->cgwb_list, and memcg->cgwb_list.  bdi->cgwb_tree is also RCU
- * protected.
+ * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list.
+ * bdi->cgwb_tree is also RCU protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
 static struct workqueue_struct *cgwb_release_wq;
 
-/**
- * wb_congested_get_create - get or create a wb_congested
- * @bdi: associated bdi
- * @blkcg_id: ID of the associated blkcg
- * @gfp: allocation mask
- *
- * Look up the wb_congested for @blkcg_id on @bdi.  If missing, create one.
- * The returned wb_congested has its reference count incremented.  Returns
- * NULL on failure.
- */
-struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
-{
-	struct bdi_writeback_congested *new_congested = NULL, *congested;
-	struct rb_node **node, *parent;
-	unsigned long flags;
-retry:
-	spin_lock_irqsave(&cgwb_lock, flags);
-
-	node = &bdi->cgwb_congested_tree.rb_node;
-	parent = NULL;
-
-	while (*node != NULL) {
-		parent = *node;
-		congested = rb_entry(parent, struct bdi_writeback_congested,
-				     rb_node);
-		if (congested->blkcg_id < blkcg_id)
-			node = &parent->rb_left;
-		else if (congested->blkcg_id > blkcg_id)
-			node = &parent->rb_right;
-		else
-			goto found;
-	}
-
-	if (new_congested) {
-		/* !found and storage for new one already allocated, insert */
-		congested = new_congested;
-		rb_link_node(&congested->rb_node, parent, node);
-		rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree);
-		spin_unlock_irqrestore(&cgwb_lock, flags);
-		return congested;
-	}
-
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-
-	/* allocate storage for new one and retry */
-	new_congested = kzalloc(sizeof(*new_congested), gfp);
-	if (!new_congested)
-		return NULL;
-
-	refcount_set(&new_congested->refcnt, 1);
-	new_congested->__bdi = bdi;
-	new_congested->blkcg_id = blkcg_id;
-	goto retry;
-
-found:
-	refcount_inc(&congested->refcnt);
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-	kfree(new_congested);
-	return congested;
-}
-
-/**
- * wb_congested_put - put a wb_congested
- * @congested: wb_congested to put
- *
- * Put @congested and destroy it if the refcnt reaches zero.
- */
-void wb_congested_put(struct bdi_writeback_congested *congested)
-{
-	unsigned long flags;
-
-	if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags))
-		return;
-
-	/* bdi might already have been destroyed leaving @congested unlinked */
-	if (congested->__bdi) {
-		rb_erase(&congested->rb_node,
-			 &congested->__bdi->cgwb_congested_tree);
-		congested->__bdi = NULL;
-	}
-
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-	kfree(congested);
-}
-
 static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -558,7 +462,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 		goto out_put;
 	}
 
-	ret = wb_init(wb, bdi, blkcg_css->id, gfp);
+	ret = wb_init(wb, bdi, gfp);
 	if (ret)
 		goto err_free;
 
@@ -696,11 +600,10 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	int ret;
 
 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
-	bdi->cgwb_congested_tree = RB_ROOT;
 	mutex_init(&bdi->cgwb_release_mutex);
 	init_rwsem(&bdi->wb_switch_rwsem);
 
-	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
+	ret = wb_init(&bdi->wb, bdi, GFP_KERNEL);
 	if (!ret) {
 		bdi->wb.memcg_css = &root_mem_cgroup->css;
 		bdi->wb.blkcg_css = blkcg_root_css;
@@ -769,21 +672,6 @@ void wb_blkcg_offline(struct blkcg *blkcg)
 	spin_unlock_irq(&cgwb_lock);
 }
 
-static void cgwb_bdi_exit(struct backing_dev_info *bdi)
-{
-	struct rb_node *rbn;
-
-	spin_lock_irq(&cgwb_lock);
-	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
-		struct bdi_writeback_congested *congested =
-			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
-		rb_erase(rbn, &bdi->cgwb_congested_tree);
-		congested->__bdi = NULL;	/* mark @congested unlinked */
-	}
-	spin_unlock_irq(&cgwb_lock);
-}
-
 static void cgwb_bdi_register(struct backing_dev_info *bdi)
 {
 	spin_lock_irq(&cgwb_lock);
@@ -810,29 +698,11 @@ subsys_initcall(cgwb_init);
 
 static int cgwb_bdi_init(struct backing_dev_info *bdi)
 {
-	int err;
-
-	bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL);
-	if (!bdi->wb_congested)
-		return -ENOMEM;
-
-	refcount_set(&bdi->wb_congested->refcnt, 1);
-
-	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
-	if (err) {
-		wb_congested_put(bdi->wb_congested);
-		return err;
-	}
-	return 0;
+	return wb_init(&bdi->wb, bdi, GFP_KERNEL);
 }
 
 static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { }
 
-static void cgwb_bdi_exit(struct backing_dev_info *bdi)
-{
-	wb_congested_put(bdi->wb_congested);
-}
-
 static void cgwb_bdi_register(struct backing_dev_info *bdi)
 {
 	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
@@ -1023,7 +893,6 @@ static void release_bdi(struct kref *ref)
 		bdi_unregister(bdi);
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
-	cgwb_bdi_exit(bdi);
 	kfree(bdi);
 }
 
@@ -1053,7 +922,7 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (test_and_clear_bit(bit, &bdi->wb.congested->state))
+	if (test_and_clear_bit(bit, &bdi->wb.congested))
 		atomic_dec(&nr_wb_congested[sync]);
 	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))
@@ -1066,7 +935,7 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (!test_and_set_bit(bit, &bdi->wb.congested->state))
+	if (!test_and_set_bit(bit, &bdi->wb.congested))
 		atomic_inc(&nr_wb_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);
-- 
cgit v1.2.3


From 21cf866145047f8bfecb38ec8d2fed64464c074f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 1 Jul 2020 11:06:22 +0200
Subject: writeback: remove bdi->congested_fn

Except for pktdvd, the only places setting congested bits are file
systems that allocate their own backing_dev_info structures.  And
pktdvd is a deprecated driver that isn't useful in stack setup
either.  So remove the dead congested_fn stacking infrastructure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Song Liu <song@kernel.org>
Acked-by: David Sterba <dsterba@suse.com>
[axboe: fixup unused variables in bcache/request.c]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_main.c   | 59 ----------------------------------------
 drivers/md/bcache/request.c      | 47 --------------------------------
 drivers/md/bcache/super.c        |  1 -
 drivers/md/dm-cache-target.c     | 19 -------------
 drivers/md/dm-clone-target.c     | 15 ----------
 drivers/md/dm-era-target.c       | 15 ----------
 drivers/md/dm-raid.c             | 12 --------
 drivers/md/dm-table.c            | 37 +------------------------
 drivers/md/dm-thin.c             | 16 -----------
 drivers/md/dm.c                  | 33 ----------------------
 drivers/md/dm.h                  |  1 -
 drivers/md/md-linear.c           | 24 ----------------
 drivers/md/md-multipath.c        | 23 ----------------
 drivers/md/md.c                  | 23 ----------------
 drivers/md/md.h                  |  4 ---
 drivers/md/raid0.c               | 16 -----------
 drivers/md/raid1.c               | 31 ---------------------
 drivers/md/raid10.c              | 26 ------------------
 drivers/md/raid5.c               | 25 -----------------
 fs/btrfs/disk-io.c               | 23 ----------------
 include/linux/backing-dev-defs.h |  4 ---
 include/linux/backing-dev.h      |  4 ---
 include/linux/device-mapper.h    | 11 --------
 23 files changed, 1 insertion(+), 468 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 7c34cc0ad8cc..cb687ccdbd96 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2415,62 +2415,6 @@ static void drbd_cleanup(void)
 	pr_info("module cleanup done.\n");
 }
 
-/**
- * drbd_congested() - Callback for the flusher thread
- * @congested_data:	User data
- * @bdi_bits:		Bits the BDI flusher thread is currently interested in
- *
- * Returns 1<<WB_async_congested and/or 1<<WB_sync_congested if we are congested.
- */
-static int drbd_congested(void *congested_data, int bdi_bits)
-{
-	struct drbd_device *device = congested_data;
-	struct request_queue *q;
-	char reason = '-';
-	int r = 0;
-
-	if (!may_inc_ap_bio(device)) {
-		/* DRBD has frozen IO */
-		r = bdi_bits;
-		reason = 'd';
-		goto out;
-	}
-
-	if (test_bit(CALLBACK_PENDING, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << WB_async_congested);
-		/* Without good local data, we would need to read from remote,
-		 * and that would need the worker thread as well, which is
-		 * currently blocked waiting for that usermode helper to
-		 * finish.
-		 */
-		if (!get_ldev_if_state(device, D_UP_TO_DATE))
-			r |= (1 << WB_sync_congested);
-		else
-			put_ldev(device);
-		r &= bdi_bits;
-		reason = 'c';
-		goto out;
-	}
-
-	if (get_ldev(device)) {
-		q = bdev_get_queue(device->ldev->backing_bdev);
-		r = bdi_congested(q->backing_dev_info, bdi_bits);
-		put_ldev(device);
-		if (r)
-			reason = 'b';
-	}
-
-	if (bdi_bits & (1 << WB_async_congested) &&
-	    test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << WB_async_congested);
-		reason = reason == 'b' ? 'a' : 'n';
-	}
-
-out:
-	device->congestion_reason = reason;
-	return r;
-}
-
 static void drbd_init_workqueue(struct drbd_work_queue* wq)
 {
 	spin_lock_init(&wq->q_lock);
@@ -2825,9 +2769,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	/* we have no partitions. we contain only ourselves. */
 	device->this_bdev->bd_contains = device->this_bdev;
 
-	q->backing_dev_info->congested_fn = drbd_congested;
-	q->backing_dev_info->congested_data = device;
-
 	blk_queue_write_cache(q, true, true);
 	/* Setting the max_hw_sectors to an odd value of 8kibyte here
 	   This triggers a max_bio_size message upon first attach or connect */
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index dd012ebface0..a190bf47076d 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1228,36 +1228,8 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
 }
 
-static int cached_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-	struct request_queue *q = bdev_get_queue(dc->bdev);
-	int ret = 0;
-
-	if (bdi_congested(q->backing_dev_info, bits))
-		return 1;
-
-	if (cached_dev_get(dc)) {
-		unsigned int i;
-		struct cache *ca;
-
-		for_each_cache(ca, d->c, i) {
-			q = bdev_get_queue(ca->bdev);
-			ret |= bdi_congested(q->backing_dev_info, bits);
-		}
-
-		cached_dev_put(dc);
-	}
-
-	return ret;
-}
-
 void bch_cached_dev_request_init(struct cached_dev *dc)
 {
-	struct gendisk *g = dc->disk.disk;
-
-	g->queue->backing_dev_info->congested_fn = cached_dev_congested;
 	dc->disk.cache_miss			= cached_dev_cache_miss;
 	dc->disk.ioctl				= cached_dev_ioctl;
 }
@@ -1341,27 +1313,8 @@ static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
 	return -ENOTTY;
 }
 
-static int flash_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct request_queue *q;
-	struct cache *ca;
-	unsigned int i;
-	int ret = 0;
-
-	for_each_cache(ca, d->c, i) {
-		q = bdev_get_queue(ca->bdev);
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-
-	return ret;
-}
-
 void bch_flash_dev_request_init(struct bcache_device *d)
 {
-	struct gendisk *g = d->disk;
-
-	g->queue->backing_dev_info->congested_fn = flash_dev_congested;
 	d->cache_miss				= flash_dev_cache_miss;
 	d->ioctl				= flash_dev_ioctl;
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index de13f6e91696..9e45faa054b6 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -885,7 +885,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 		return -ENOMEM;
 
 	d->disk->queue			= q;
-	q->backing_dev_info->congested_data = d;
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9eccced92896..96c93802ee4d 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -421,8 +421,6 @@ struct cache {
 
 	struct rw_semaphore quiesce_lock;
 
-	struct dm_target_callbacks callbacks;
-
 	/*
 	 * origin_blocks entries, discarded if set.
 	 */
@@ -2423,20 +2421,6 @@ static void set_cache_size(struct cache *cache, dm_cblock_t size)
 	cache->cache_size = size;
 }
 
-static int is_congested(struct dm_dev *dev, int bdi_bits)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
-static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct cache *cache = container_of(cb, struct cache, callbacks);
-
-	return is_congested(cache->origin_dev, bdi_bits) ||
-		is_congested(cache->cache_dev, bdi_bits);
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2471,9 +2455,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 			goto bad;
 	}
 
-	cache->callbacks.congested_fn = cache_is_congested;
-	dm_table_add_target_callbacks(ti->table, &cache->callbacks);
-
 	cache->metadata_dev = ca->metadata_dev;
 	cache->origin_dev = ca->origin_dev;
 	cache->cache_dev = ca->cache_dev;
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 59ed8a67c2e3..bdb255edc200 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -68,7 +68,6 @@ struct hash_table_bucket;
 
 struct clone {
 	struct dm_target *ti;
-	struct dm_target_callbacks callbacks;
 
 	struct dm_dev *metadata_dev;
 	struct dm_dev *dest_dev;
@@ -1518,18 +1517,6 @@ error:
 	DMEMIT("Error");
 }
 
-static int clone_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct request_queue *dest_q, *source_q;
-	struct clone *clone = container_of(cb, struct clone, callbacks);
-
-	source_q = bdev_get_queue(clone->source_dev->bdev);
-	dest_q = bdev_get_queue(clone->dest_dev->bdev);
-
-	return (bdi_congested(dest_q->backing_dev_info, bdi_bits) |
-		bdi_congested(source_q->backing_dev_info, bdi_bits));
-}
-
 static sector_t get_dev_size(struct dm_dev *dev)
 {
 	return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
@@ -1930,8 +1917,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto out_with_mempool;
 
 	mutex_init(&clone->commit_lock);
-	clone->callbacks.congested_fn = clone_is_congested;
-	dm_table_add_target_callbacks(ti->table, &clone->callbacks);
 
 	/* Enable flushes */
 	ti->num_flush_bios = 1;
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 566ddbdb16a4..b24e3839bb3a 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1137,7 +1137,6 @@ static int metadata_get_stats(struct era_metadata *md, void *ptr)
 
 struct era {
 	struct dm_target *ti;
-	struct dm_target_callbacks callbacks;
 
 	struct dm_dev *metadata_dev;
 	struct dm_dev *origin_dev;
@@ -1375,18 +1374,6 @@ static void stop_worker(struct era *era)
 /*----------------------------------------------------------------
  * Target methods
  *--------------------------------------------------------------*/
-static int dev_is_congested(struct dm_dev *dev, int bdi_bits)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
-static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct era *era = container_of(cb, struct era, callbacks);
-	return dev_is_congested(era->origin_dev, bdi_bits);
-}
-
 static void era_destroy(struct era *era)
 {
 	if (era->md)
@@ -1514,8 +1501,6 @@ static int era_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->flush_supported = true;
 
 	ti->num_discard_bios = 1;
-	era->callbacks.congested_fn = era_is_congested;
-	dm_table_add_target_callbacks(ti->table, &era->callbacks);
 
 	return 0;
 }
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 10e8b2fe787b..d9e270957e18 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -242,7 +242,6 @@ struct raid_set {
 
 	struct mddev md;
 	struct raid_type *raid_type;
-	struct dm_target_callbacks callbacks;
 
 	sector_t array_sectors;
 	sector_t dev_sectors;
@@ -1705,13 +1704,6 @@ static void do_table_event(struct work_struct *ws)
 	dm_table_event(rs->ti->table);
 }
 
-static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
-{
-	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
-
-	return mddev_congested(&rs->md, bits);
-}
-
 /*
  * Make sure a valid takover (level switch) is being requested on @rs
  *
@@ -3248,9 +3240,6 @@ size_check:
 		goto bad_md_start;
 	}
 
-	rs->callbacks.congested_fn = raid_is_congested;
-	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
-
 	/* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */
 	if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) {
 		r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode);
@@ -3310,7 +3299,6 @@ static void raid_dtr(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
-	list_del_init(&rs->callbacks.list);
 	md_stop(&rs->md);
 	raid_set_free(rs);
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 8277b959e00b..0ea5b7367179 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -64,8 +64,6 @@ struct dm_table {
 	void *event_context;
 
 	struct dm_md_mempools *mempools;
-
-	struct list_head target_callbacks;
 };
 
 /*
@@ -190,7 +188,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
-	INIT_LIST_HEAD(&t->target_callbacks);
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -361,7 +358,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
  * This upgrades the mode on an already open dm_dev, being
  * careful to leave things as they were if we fail to reopen the
  * device and not to touch the existing bdev field in case
- * it is accessed concurrently inside dm_table_any_congested().
+ * it is accessed concurrently.
  */
 static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
@@ -2052,38 +2049,6 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
-void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb)
-{
-	list_add(&cb->list, &t->target_callbacks);
-}
-EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks);
-
-int dm_table_any_congested(struct dm_table *t, int bdi_bits)
-{
-	struct dm_dev_internal *dd;
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_target_callbacks *cb;
-	int r = 0;
-
-	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
-		char b[BDEVNAME_SIZE];
-
-		if (likely(q))
-			r |= bdi_congested(q->backing_dev_info, bdi_bits);
-		else
-			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
-				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev->bdev, b));
-	}
-
-	list_for_each_entry(cb, &t->target_callbacks, list)
-		if (cb->congested_fn)
-			r |= cb->congested_fn(cb, bdi_bits);
-
-	return r;
-}
-
 struct mapped_device *dm_table_get_md(struct dm_table *t)
 {
 	return t->md;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fe2de2888709..fff4c50df74d 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -326,7 +326,6 @@ struct pool_c {
 	struct pool *pool;
 	struct dm_dev *data_dev;
 	struct dm_dev *metadata_dev;
-	struct dm_target_callbacks callbacks;
 
 	dm_block_t low_water_blocks;
 	struct pool_features requested_pf; /* Features requested during table load */
@@ -2796,18 +2795,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 	}
 }
 
-static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct pool_c *pt = container_of(cb, struct pool_c, callbacks);
-	struct request_queue *q;
-
-	if (get_pool_mode(pt->pool) == PM_OUT_OF_DATA_SPACE)
-		return 1;
-
-	q = bdev_get_queue(pt->data_dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
 static void requeue_bios(struct pool *pool)
 {
 	struct thin_c *tc;
@@ -3420,9 +3407,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	dm_pool_register_pre_commit_callback(pool->pmd,
 					     metadata_pre_commit_callback, pool);
 
-	pt->callbacks.congested_fn = pool_is_congested;
-	dm_table_add_target_callbacks(ti->table, &pt->callbacks);
-
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
 	return 0;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 48bfd41658aa..e2148fcb88bb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1821,31 +1821,6 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	return ret;
 }
 
-static int dm_any_congested(void *congested_data, int bdi_bits)
-{
-	int r = bdi_bits;
-	struct mapped_device *md = congested_data;
-	struct dm_table *map;
-
-	if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
-		if (dm_request_based(md)) {
-			/*
-			 * With request-based DM we only need to check the
-			 * top-level queue for congestion.
-			 */
-			struct backing_dev_info *bdi = md->queue->backing_dev_info;
-			r = bdi->wb.congested & bdi_bits;
-		} else {
-			map = dm_get_live_table_fast(md);
-			if (map)
-				r = dm_table_any_congested(map, bdi_bits);
-			dm_put_live_table_fast(md);
-		}
-	}
-
-	return r;
-}
-
 /*-----------------------------------------------------------------
  * An IDR is used to keep track of allocated minor numbers.
  *---------------------------------------------------------------*/
@@ -2284,12 +2259,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
-static void dm_init_congested_fn(struct mapped_device *md)
-{
-	md->queue->backing_dev_info->congested_data = md;
-	md->queue->backing_dev_info->congested_fn = dm_any_congested;
-}
-
 /*
  * Setup the DM device's queue based on md's type
  */
@@ -2306,12 +2275,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
 			return r;
 		}
-		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
 	case DM_TYPE_NVME_BIO_BASED:
-		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index d7c4f6606b5f..4f5fe664d05a 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -63,7 +63,6 @@ void dm_table_presuspend_targets(struct dm_table *t);
 void dm_table_presuspend_undo_targets(struct dm_table *t);
 void dm_table_postsuspend_targets(struct dm_table *t);
 int dm_table_resume_targets(struct dm_table *t);
-int dm_table_any_congested(struct dm_table *t, int bdi_bits);
 enum dm_queue_mode dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 8efada3ee16f..c2ae9125c4c3 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -46,29 +46,6 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
-/*
- * In linear_congested() conf->raid_disks is used as a copy of
- * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
- * and conf->disks[] are created in linear_conf(), they are always
- * consitent with each other, but mddev->raid_disks does not.
- */
-static int linear_congested(struct mddev *mddev, int bits)
-{
-	struct linear_conf *conf;
-	int i, ret = 0;
-
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
-
-	for (i = 0; i < conf->raid_disks && !ret ; i++) {
-		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-
-	rcu_read_unlock();
-	return ret;
-}
-
 static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
 	struct linear_conf *conf;
@@ -322,7 +299,6 @@ static struct md_personality linear_personality =
 	.hot_add_disk	= linear_add,
 	.size		= linear_size,
 	.quiesce	= linear_quiesce,
-	.congested	= linear_congested,
 };
 
 static int __init linear_init (void)
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 277fdfd9ee54..776bbe542db5 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -151,28 +151,6 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev)
 	seq_putc(seq, ']');
 }
 
-static int multipath_congested(struct mddev *mddev, int bits)
-{
-	struct mpconf *conf = mddev->private;
-	int i, ret = 0;
-
-	rcu_read_lock();
-	for (i = 0; i < mddev->raid_disks ; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			ret |= bdi_congested(q->backing_dev_info, bits);
-			/* Just like multipath_map, we just check the
-			 * first available device
-			 */
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 /*
  * Careful, this can execute in IRQ contexts as well!
  */
@@ -478,7 +456,6 @@ static struct md_personality multipath_personality =
 	.hot_add_disk	= multipath_add_disk,
 	.hot_remove_disk= multipath_remove_disk,
 	.size		= multipath_size,
-	.congested	= multipath_congested,
 };
 
 static int __init multipath_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 77dfe4765c31..96b28f6d025c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -549,26 +549,6 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
-int mddev_congested(struct mddev *mddev, int bits)
-{
-	struct md_personality *pers = mddev->pers;
-	int ret = 0;
-
-	rcu_read_lock();
-	if (mddev->suspended)
-		ret = 1;
-	else if (pers && pers->congested)
-		ret = pers->congested(mddev, bits);
-	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mddev_congested);
-static int md_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-	return mddev_congested(mddev, bits);
-}
-
 /*
  * Generic flush handling for md
  */
@@ -5965,8 +5945,6 @@ int md_run(struct mddev *mddev)
 			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		mddev->queue->backing_dev_info->congested_data = mddev;
-		mddev->queue->backing_dev_info->congested_fn = md_congested;
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6351,7 +6329,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->backing_dev_info->congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 612814d07d35..e2f1ad9afc48 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -597,9 +597,6 @@ struct md_personality
 	 * array.
 	 */
 	void *(*takeover) (struct mddev *mddev);
-	/* congested implements bdi.congested_fn().
-	 * Will not be called while array is 'suspended' */
-	int (*congested)(struct mddev *mddev, int bits);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
 };
@@ -710,7 +707,6 @@ extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
-extern int mddev_congested(struct mddev *mddev, int bits);
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e9e91c8d8afc..f54a449f97aa 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -29,21 +29,6 @@ module_param(default_layout, int, 0644);
 	 (1L << MD_HAS_PPL) |		\
 	 (1L << MD_HAS_MULTIPLE_PPLS))
 
-static int raid0_congested(struct mddev *mddev, int bits)
-{
-	struct r0conf *conf = mddev->private;
-	struct md_rdev **devlist = conf->devlist;
-	int raid_disks = conf->strip_zone[0].nb_dev;
-	int i, ret = 0;
-
-	for (i = 0; i < raid_disks && !ret ; i++) {
-		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
-
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-	return ret;
-}
-
 /*
  * inform the user of the raid configuration
 */
@@ -818,7 +803,6 @@ static struct md_personality raid0_personality=
 	.size		= raid0_size,
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
-	.congested	= raid0_congested,
 };
 
 static int __init raid0_init (void)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2aa2649cca66..960d854c07f8 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -786,36 +786,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
-static int raid1_congested(struct mddev *mddev, int bits)
-{
-	struct r1conf *conf = mddev->private;
-	int i, ret = 0;
-
-	if ((bits & (1 << WB_async_congested)) &&
-	    conf->pending_count >= max_queued_requests)
-		return 1;
-
-	rcu_read_lock();
-	for (i = 0; i < conf->raid_disks * 2; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			BUG_ON(!q);
-
-			/* Note the '|| 1' - when read_balance prefers
-			 * non-congested targets, it can be removed
-			 */
-			if ((bits & (1 << WB_async_congested)) || 1)
-				ret |= bdi_congested(q->backing_dev_info, bits);
-			else
-				ret &= bdi_congested(q->backing_dev_info, bits);
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 {
 	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
@@ -3396,7 +3366,6 @@ static struct md_personality raid1_personality =
 	.check_reshape	= raid1_reshape,
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
-	.congested	= raid1_congested,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e45fd56cf584..353288bc4cb7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -848,31 +848,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	return rdev;
 }
 
-static int raid10_congested(struct mddev *mddev, int bits)
-{
-	struct r10conf *conf = mddev->private;
-	int i, ret = 0;
-
-	if ((bits & (1 << WB_async_congested)) &&
-	    conf->pending_count >= max_queued_requests)
-		return 1;
-
-	rcu_read_lock();
-	for (i = 0;
-	     (i < conf->geo.raid_disks || i < conf->prev.raid_disks)
-		     && ret == 0;
-	     i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			ret |= bdi_congested(q->backing_dev_info, bits);
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static void flush_pending_writes(struct r10conf *conf)
 {
 	/* Any writes that have been queued but are awaiting
@@ -4929,7 +4904,6 @@ static struct md_personality raid10_personality =
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
 	.update_reshape_pos = raid10_update_reshape_pos,
-	.congested	= raid10_congested,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8dea4398b191..774ea893d47e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5099,28 +5099,6 @@ static void activate_bit_delay(struct r5conf *conf,
 	}
 }
 
-static int raid5_congested(struct mddev *mddev, int bits)
-{
-	struct r5conf *conf = mddev->private;
-
-	/* No difference between reads and writes.  Just check
-	 * how busy the stripe_cache is
-	 */
-
-	if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state))
-		return 1;
-
-	/* Also checks whether there is pressure on r5cache log space */
-	if (test_bit(R5C_LOG_TIGHT, &conf->cache_state))
-		return 1;
-	if (conf->quiesce)
-		return 1;
-	if (atomic_read(&conf->empty_inactive_list_nr))
-		return 1;
-
-	return 0;
-}
-
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
 	struct r5conf *conf = mddev->private;
@@ -8427,7 +8405,6 @@ static struct md_personality raid6_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };
 static struct md_personality raid5_personality =
@@ -8452,7 +8429,6 @@ static struct md_personality raid5_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
@@ -8478,7 +8454,6 @@ static struct md_personality raid4_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7c6f0bbb54a5..eb5f2506cede 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1616,27 +1616,6 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static int btrfs_congested_fn(void *congested_data, int bdi_bits)
-{
-	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
-	int ret = 0;
-	struct btrfs_device *device;
-	struct backing_dev_info *bdi;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
-		if (!device->bdev)
-			continue;
-		bdi = device->bdev->bd_bdi;
-		if (bdi_congested(bdi, bdi_bits)) {
-			ret = 1;
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 /*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
@@ -3051,8 +3030,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->congested_fn = btrfs_congested_fn;
-	sb->s_bdi->congested_data = fs_info;
 	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
 	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 1cec4521e1fb..fff9367a6348 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -33,8 +33,6 @@ enum wb_congested_state {
 	WB_sync_congested,	/* The sync queue is getting full */
 };
 
-typedef int (congested_fn)(void *, int);
-
 enum wb_stat_item {
 	WB_RECLAIMABLE,
 	WB_WRITEBACK,
@@ -170,8 +168,6 @@ struct backing_dev_info {
 	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_SIZE units */
 	unsigned long io_pages;	/* max allowed IO size */
-	congested_fn *congested_fn; /* Function pointer if device is md/dm */
-	void *congested_data;	/* Pointer to aux data for congested func */
 
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 9173d2c22b4a..0b06b2d26c9a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -169,10 +169,6 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 
 static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 {
-	struct backing_dev_info *bdi = wb->bdi;
-
-	if (bdi->congested_fn)
-		return bdi->congested_fn(bdi->congested_data, cong_bits);
 	return wb->congested & cong_bits;
 }
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8750f2dc5613..d5306d9c29c4 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -322,12 +322,6 @@ struct dm_target {
 	bool discards_supported:1;
 };
 
-/* Each target can link one of these into the table */
-struct dm_target_callbacks {
-	struct list_head list;
-	int (*congested_fn) (struct dm_target_callbacks *, int);
-};
-
 void *dm_per_bio_data(struct bio *bio, size_t data_size);
 struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size);
 unsigned dm_bio_get_target_bio_nr(const struct bio *bio);
@@ -477,11 +471,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
-/*
- * Target_ctr should call this if it needs to add any callbacks.
- */
-void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
-
 /*
  * Target can use this to set the table's type.
  * Can only ever be called from a target's ctr.
-- 
cgit v1.2.3


From 5abfe5cf0b8358b8ad0da99e4188c2519839d67c Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Tue, 23 Jun 2020 19:23:27 -0700
Subject: remoteproc: qcom: Add per subsystem SSR notification

Currently there is a single notification chain which is called whenever any
remoteproc shuts down. This leads to all the listeners being notified, and
is not an optimal design as kernel drivers might only be interested in
listening to notifications from a particular remoteproc. Create a global
list of remoteproc notification info data structures. This will hold the
name and notifier_list information for a particular remoteproc. The API
to register for notifications will use name argument to retrieve the
notification info data structure and the notifier block will be added to
that data structure's notification chain. Also move from blocking notifier
to srcu notifer based implementation to support dynamic notifier head
creation.

Reviewed-by: Alex Elder <elder@linaro.org>
Co-developed-by: Siddharth Gupta <sidgup@codeaurora.org>
Signed-off-by: Siddharth Gupta <sidgup@codeaurora.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Link: https://lore.kernel.org/r/1592965408-16908-2-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/qcom_common.c      | 90 ++++++++++++++++++++++++++++++-----
 drivers/remoteproc/qcom_common.h      |  5 +-
 include/linux/remoteproc/qcom_rproc.h | 20 ++++++--
 3 files changed, 95 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/qcom_common.c b/drivers/remoteproc/qcom_common.c
index 9028cea2d81e..48b399af9c83 100644
--- a/drivers/remoteproc/qcom_common.c
+++ b/drivers/remoteproc/qcom_common.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/notifier.h>
 #include <linux/remoteproc.h>
+#include <linux/remoteproc/qcom_rproc.h>
 #include <linux/rpmsg/qcom_glink.h>
 #include <linux/rpmsg/qcom_smd.h>
 #include <linux/soc/qcom/mdt_loader.h>
@@ -23,7 +24,14 @@
 #define to_smd_subdev(d) container_of(d, struct qcom_rproc_subdev, subdev)
 #define to_ssr_subdev(d) container_of(d, struct qcom_rproc_ssr, subdev)
 
-static BLOCKING_NOTIFIER_HEAD(ssr_notifiers);
+struct qcom_ssr_subsystem {
+	const char *name;
+	struct srcu_notifier_head notifier_list;
+	struct list_head list;
+};
+
+static LIST_HEAD(qcom_ssr_subsystem_list);
+static DEFINE_MUTEX(qcom_ssr_subsys_lock);
 
 static int glink_subdev_start(struct rproc_subdev *subdev)
 {
@@ -189,37 +197,83 @@ void qcom_remove_smd_subdev(struct rproc *rproc, struct qcom_rproc_subdev *smd)
 }
 EXPORT_SYMBOL_GPL(qcom_remove_smd_subdev);
 
+static struct qcom_ssr_subsystem *qcom_ssr_get_subsys(const char *name)
+{
+	struct qcom_ssr_subsystem *info;
+
+	mutex_lock(&qcom_ssr_subsys_lock);
+	/* Match in the global qcom_ssr_subsystem_list with name */
+	list_for_each_entry(info, &qcom_ssr_subsystem_list, list)
+		if (!strcmp(info->name, name))
+			goto out;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		info = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+	info->name = kstrdup_const(name, GFP_KERNEL);
+	srcu_init_notifier_head(&info->notifier_list);
+
+	/* Add to global notification list */
+	list_add_tail(&info->list, &qcom_ssr_subsystem_list);
+
+out:
+	mutex_unlock(&qcom_ssr_subsys_lock);
+	return info;
+}
+
 /**
  * qcom_register_ssr_notifier() - register SSR notification handler
- * @nb:		notifier_block to notify for restart notifications
+ * @name:	Subsystem's SSR name
+ * @nb:		notifier_block to be invoked upon subsystem's state change
  *
- * Returns 0 on success, negative errno on failure.
+ * This registers the @nb notifier block as part the notifier chain for a
+ * remoteproc associated with @name. The notifier block's callback
+ * will be invoked when the remote processor's SSR events occur
+ * (pre/post startup and pre/post shutdown).
  *
- * This register the @notify function as handler for restart notifications. As
- * remote processors are stopped this function will be called, with the SSR
- * name passed as a parameter.
+ * Return: a subsystem cookie on success, ERR_PTR on failure.
  */
-int qcom_register_ssr_notifier(struct notifier_block *nb)
+void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb)
 {
-	return blocking_notifier_chain_register(&ssr_notifiers, nb);
+	struct qcom_ssr_subsystem *info;
+
+	info = qcom_ssr_get_subsys(name);
+	if (IS_ERR(info))
+		return info;
+
+	srcu_notifier_chain_register(&info->notifier_list, nb);
+
+	return &info->notifier_list;
 }
 EXPORT_SYMBOL_GPL(qcom_register_ssr_notifier);
 
 /**
  * qcom_unregister_ssr_notifier() - unregister SSR notification handler
+ * @notify:	subsystem cookie returned from qcom_register_ssr_notifier
  * @nb:		notifier_block to unregister
+ *
+ * This function will unregister the notifier from the particular notifier
+ * chain.
+ *
+ * Return: 0 on success, %ENOENT otherwise.
  */
-void qcom_unregister_ssr_notifier(struct notifier_block *nb)
+int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&ssr_notifiers, nb);
+	return srcu_notifier_chain_unregister(notify, nb);
 }
 EXPORT_SYMBOL_GPL(qcom_unregister_ssr_notifier);
 
 static void ssr_notify_unprepare(struct rproc_subdev *subdev)
 {
 	struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev);
+	struct qcom_ssr_notify_data data = {
+		.name = ssr->info->name,
+		.crashed = false,
+	};
 
-	blocking_notifier_call_chain(&ssr_notifiers, 0, (void *)ssr->name);
+	srcu_notifier_call_chain(&ssr->info->notifier_list, 0, &data);
 }
 
 /**
@@ -229,12 +283,21 @@ static void ssr_notify_unprepare(struct rproc_subdev *subdev)
  * @ssr_name:	identifier to use for notifications originating from @rproc
  *
  * As the @ssr is registered with the @rproc SSR events will be sent to all
- * registered listeners in the system as the remoteproc is shut down.
+ * registered listeners for the remoteproc when it's SSR events occur
+ * (pre/post startup and pre/post shutdown).
  */
 void qcom_add_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr,
 			 const char *ssr_name)
 {
-	ssr->name = ssr_name;
+	struct qcom_ssr_subsystem *info;
+
+	info = qcom_ssr_get_subsys(ssr_name);
+	if (IS_ERR(info)) {
+		dev_err(&rproc->dev, "Failed to add ssr subdevice\n");
+		return;
+	}
+
+	ssr->info = info;
 	ssr->subdev.unprepare = ssr_notify_unprepare;
 
 	rproc_add_subdev(rproc, &ssr->subdev);
@@ -249,6 +312,7 @@ EXPORT_SYMBOL_GPL(qcom_add_ssr_subdev);
 void qcom_remove_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr)
 {
 	rproc_remove_subdev(rproc, &ssr->subdev);
+	ssr->info = NULL;
 }
 EXPORT_SYMBOL_GPL(qcom_remove_ssr_subdev);
 
diff --git a/drivers/remoteproc/qcom_common.h b/drivers/remoteproc/qcom_common.h
index 34e5188187dc..dfc641c3a98b 100644
--- a/drivers/remoteproc/qcom_common.h
+++ b/drivers/remoteproc/qcom_common.h
@@ -26,10 +26,11 @@ struct qcom_rproc_subdev {
 	struct qcom_smd_edge *edge;
 };
 
+struct qcom_ssr_subsystem;
+
 struct qcom_rproc_ssr {
 	struct rproc_subdev subdev;
-
-	const char *name;
+	struct qcom_ssr_subsystem *info;
 };
 
 void qcom_add_glink_subdev(struct rproc *rproc, struct qcom_rproc_glink *glink,
diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h
index fa8e38681b4b..2a1d6d0249d9 100644
--- a/include/linux/remoteproc/qcom_rproc.h
+++ b/include/linux/remoteproc/qcom_rproc.h
@@ -5,17 +5,27 @@ struct notifier_block;
 
 #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON)
 
-int qcom_register_ssr_notifier(struct notifier_block *nb);
-void qcom_unregister_ssr_notifier(struct notifier_block *nb);
+struct qcom_ssr_notify_data {
+	const char *name;
+	bool crashed;
+};
+
+void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb);
+int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb);
 
 #else
 
-static inline int qcom_register_ssr_notifier(struct notifier_block *nb)
+static inline void *qcom_register_ssr_notifier(const char *name,
+					       struct notifier_block *nb)
 {
-	return 0;
+	return NULL;
 }
 
-static inline void qcom_unregister_ssr_notifier(struct notifier_block *nb) {}
+static inline int qcom_unregister_ssr_notifier(void *notify,
+					       struct notifier_block *nb)
+{
+	return 0;
+}
 
 #endif
 
-- 
cgit v1.2.3


From 62495d778439a4e47571293511a785cba754874c Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Tue, 23 Jun 2020 19:23:28 -0700
Subject: remoteproc: qcom: Add notification types to SSR

The SSR subdevice only adds callback for the unprepare event. Add callbacks
for prepare, start and prepare events. The client driver for a particular
remoteproc might be interested in knowing the status of the remoteproc
while undergoing SSR, not just when the remoteproc has finished shutting
down.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Siddharth Gupta <sidgup@codeaurora.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Link: https://lore.kernel.org/r/1592965408-16908-3-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/qcom_common.c      | 44 ++++++++++++++++++++++++++++++++++-
 include/linux/remoteproc/qcom_rproc.h | 16 +++++++++++++
 2 files changed, 59 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/qcom_common.c b/drivers/remoteproc/qcom_common.c
index 48b399af9c83..2f45f0c79914 100644
--- a/drivers/remoteproc/qcom_common.c
+++ b/drivers/remoteproc/qcom_common.c
@@ -265,6 +265,44 @@ int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(qcom_unregister_ssr_notifier);
 
+static int ssr_notify_prepare(struct rproc_subdev *subdev)
+{
+	struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev);
+	struct qcom_ssr_notify_data data = {
+		.name = ssr->info->name,
+		.crashed = false,
+	};
+
+	srcu_notifier_call_chain(&ssr->info->notifier_list,
+				 QCOM_SSR_BEFORE_POWERUP, &data);
+	return 0;
+}
+
+static int ssr_notify_start(struct rproc_subdev *subdev)
+{
+	struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev);
+	struct qcom_ssr_notify_data data = {
+		.name = ssr->info->name,
+		.crashed = false,
+	};
+
+	srcu_notifier_call_chain(&ssr->info->notifier_list,
+				 QCOM_SSR_AFTER_POWERUP, &data);
+	return 0;
+}
+
+static void ssr_notify_stop(struct rproc_subdev *subdev, bool crashed)
+{
+	struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev);
+	struct qcom_ssr_notify_data data = {
+		.name = ssr->info->name,
+		.crashed = crashed,
+	};
+
+	srcu_notifier_call_chain(&ssr->info->notifier_list,
+				 QCOM_SSR_BEFORE_SHUTDOWN, &data);
+}
+
 static void ssr_notify_unprepare(struct rproc_subdev *subdev)
 {
 	struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev);
@@ -273,7 +311,8 @@ static void ssr_notify_unprepare(struct rproc_subdev *subdev)
 		.crashed = false,
 	};
 
-	srcu_notifier_call_chain(&ssr->info->notifier_list, 0, &data);
+	srcu_notifier_call_chain(&ssr->info->notifier_list,
+				 QCOM_SSR_AFTER_SHUTDOWN, &data);
 }
 
 /**
@@ -298,6 +337,9 @@ void qcom_add_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr,
 	}
 
 	ssr->info = info;
+	ssr->subdev.prepare = ssr_notify_prepare;
+	ssr->subdev.start = ssr_notify_start;
+	ssr->subdev.stop = ssr_notify_stop;
 	ssr->subdev.unprepare = ssr_notify_unprepare;
 
 	rproc_add_subdev(rproc, &ssr->subdev);
diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h
index 2a1d6d0249d9..647051662174 100644
--- a/include/linux/remoteproc/qcom_rproc.h
+++ b/include/linux/remoteproc/qcom_rproc.h
@@ -5,6 +5,22 @@ struct notifier_block;
 
 #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON)
 
+/**
+ * enum qcom_ssr_notify_type - Startup/Shutdown events related to a remoteproc
+ * processor.
+ *
+ * @QCOM_SSR_BEFORE_POWERUP:	Remoteproc about to start (prepare stage)
+ * @QCOM_SSR_AFTER_POWERUP:	Remoteproc is running (start stage)
+ * @QCOM_SSR_BEFORE_SHUTDOWN:	Remoteproc crashed or shutting down (stop stage)
+ * @QCOM_SSR_AFTER_SHUTDOWN:	Remoteproc is down (unprepare stage)
+ */
+enum qcom_ssr_notify_type {
+	QCOM_SSR_BEFORE_POWERUP,
+	QCOM_SSR_AFTER_POWERUP,
+	QCOM_SSR_BEFORE_SHUTDOWN,
+	QCOM_SSR_AFTER_SHUTDOWN,
+};
+
 struct qcom_ssr_notify_data {
 	const char *name;
 	bool crashed;
-- 
cgit v1.2.3


From a50ca29523b18baea548bdf5df9b4b923c2bb4f6 Mon Sep 17 00:00:00 2001
From: Dave Wang <dave.wang@emc.com.tw>
Date: Wed, 8 Jul 2020 22:25:03 -0700
Subject: Input: elan_i2c - add more hardware ID for Lenovo laptops

This adds more hardware IDs for Elan touchpads found in various Lenovo
laptops.

Signed-off-by: Dave Wang <dave.wang@emc.com.tw>
Link: https://lore.kernel.org/r/000201d5a8bd$9fead3f0$dfc07bd0$@emc.com.tw
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/input/elan-i2c-ids.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/input/elan-i2c-ids.h b/include/linux/input/elan-i2c-ids.h
index 1ecb6b45812c..520858d12680 100644
--- a/include/linux/input/elan-i2c-ids.h
+++ b/include/linux/input/elan-i2c-ids.h
@@ -67,8 +67,15 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN062B", 0 },
 	{ "ELAN062C", 0 },
 	{ "ELAN062D", 0 },
+	{ "ELAN062E", 0 }, /* Lenovo V340 Whiskey Lake U */
+	{ "ELAN062F", 0 }, /* Lenovo V340 Comet Lake U */
 	{ "ELAN0631", 0 },
 	{ "ELAN0632", 0 },
+	{ "ELAN0633", 0 }, /* Lenovo S145 */
+	{ "ELAN0634", 0 }, /* Lenovo V340 Ice lake */
+	{ "ELAN0635", 0 }, /* Lenovo V1415-IIL */
+	{ "ELAN0636", 0 }, /* Lenovo V1415-Dali */
+	{ "ELAN0637", 0 }, /* Lenovo V1415-IGLR */
 	{ "ELAN1000", 0 },
 	{ }
 };
-- 
cgit v1.2.3


From f88814cc2578c121e6edef686365036db72af0ed Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 8 Jul 2020 13:01:57 +0300
Subject: efi/efivars: Expose RT service availability via efivars abstraction

Commit

  bf67fad19e493b ("efi: Use more granular check for availability for variable services")

introduced a check into the efivarfs, efi-pstore and other drivers that
aborts loading of the module if not all three variable runtime services
(GetVariable, SetVariable and GetNextVariable) are supported. However, this
results in efivarfs being unavailable entirely if only SetVariable support
is missing, which is only needed if you want to make any modifications.
Also, efi-pstore and the sysfs EFI variable interface could be backed by
another implementation of the 'efivars' abstraction, in which case it is
completely irrelevant which services are supported by the EFI firmware.

So make the generic 'efivars' abstraction dependent on the availibility of
the GetVariable and GetNextVariable EFI runtime services, and add a helper
'efivar_supports_writes()' to find out whether the currently active efivars
abstraction supports writes (and wire it up to the availability of
SetVariable for the generic one).

Then, use the efivar_supports_writes() helper to decide whether to permit
efivarfs to be mounted read-write, and whether to enable efi-pstore or the
sysfs EFI variable interface altogether.

Fixes: bf67fad19e493b ("efi: Use more granular check for availability for variable services")
Reported-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Tested-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-pstore.c |  5 +----
 drivers/firmware/efi/efi.c        | 12 ++++++++----
 drivers/firmware/efi/efivars.c    |  5 +----
 drivers/firmware/efi/vars.c       |  6 ++++++
 fs/efivarfs/super.c               |  6 +++---
 include/linux/efi.h               |  1 +
 6 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index c2f1d4e6630b..feb7fe6f2da7 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -356,10 +356,7 @@ static struct pstore_info efi_pstore_info = {
 
 static __init int efivars_pstore_init(void)
 {
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return 0;
-
-	if (!efivars_kobject())
+	if (!efivars_kobject() || !efivar_supports_writes())
 		return 0;
 
 	if (efivars_pstore_disable)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5114cae4ec97..fdd1db025dbf 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -176,11 +176,13 @@ static struct efivar_operations generic_ops;
 static int generic_ops_register(void)
 {
 	generic_ops.get_variable = efi.get_variable;
-	generic_ops.set_variable = efi.set_variable;
-	generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
 	generic_ops.get_next_variable = efi.get_next_variable;
 	generic_ops.query_variable_store = efi_query_variable_store;
 
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE)) {
+		generic_ops.set_variable = efi.set_variable;
+		generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
+	}
 	return efivars_register(&generic_efivars, &generic_ops, efi_kobj);
 }
 
@@ -382,7 +384,8 @@ static int __init efisubsys_init(void)
 		return -ENOMEM;
 	}
 
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) {
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
+				      EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) {
 		efivar_ssdt_load();
 		error = generic_ops_register();
 		if (error)
@@ -416,7 +419,8 @@ static int __init efisubsys_init(void)
 err_remove_group:
 	sysfs_remove_group(efi_kobj, &efi_subsys_attr_group);
 err_unregister:
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
+				      EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME))
 		generic_ops_unregister();
 err_put:
 	kobject_put(efi_kobj);
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 26528a46d99e..dcea137142b3 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -680,11 +680,8 @@ int efivars_sysfs_init(void)
 	struct kobject *parent_kobj = efivars_kobject();
 	int error = 0;
 
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return -ENODEV;
-
 	/* No efivars has been registered yet */
-	if (!parent_kobj)
+	if (!parent_kobj || !efivar_supports_writes())
 		return 0;
 
 	printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION,
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 5f2a4d162795..973eef234b36 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -1229,3 +1229,9 @@ out:
 	return rv;
 }
 EXPORT_SYMBOL_GPL(efivars_unregister);
+
+int efivar_supports_writes(void)
+{
+	return __efivars && __efivars->ops->set_variable;
+}
+EXPORT_SYMBOL_GPL(efivar_supports_writes);
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 12c66f5d92dd..28bb5689333a 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -201,6 +201,9 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
+	if (!efivar_supports_writes())
+		sb->s_flags |= SB_RDONLY;
+
 	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
@@ -252,9 +255,6 @@ static struct file_system_type efivarfs_type = {
 
 static __init int efivarfs_init(void)
 {
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return -ENODEV;
-
 	if (!efivars_kobject())
 		return -ENODEV;
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index bb35f3305e55..05c47f857383 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -994,6 +994,7 @@ int efivars_register(struct efivars *efivars,
 int efivars_unregister(struct efivars *efivars);
 struct kobject *efivars_kobject(void);
 
+int efivar_supports_writes(void);
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
 		void *data, bool duplicates, struct list_head *head);
 
-- 
cgit v1.2.3


From 4fbfbdb5726ff15bdce1c371efa1281b28322f64 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 8 Jul 2020 14:49:56 +0200
Subject: USB: serial: inline sysrq dummy function

Inline the dummy sysrq character handling when either console support or
magic-sysrq support isn't enabled to allow the compiler to eliminate
unused code.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/generic.c | 9 ++-------
 include/linux/usb/serial.h   | 9 +++++++++
 2 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index c5b35252c931..a9b6d103aaf6 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -571,7 +571,7 @@ int usb_serial_generic_get_icount(struct tty_struct *tty,
 }
 EXPORT_SYMBOL_GPL(usb_serial_generic_get_icount);
 
-#ifdef CONFIG_MAGIC_SYSRQ
+#if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
 {
 	if (port->sysrq) {
@@ -584,13 +584,8 @@ int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
 	}
 	return 0;
 }
-#else
-int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
-{
-	return 0;
-}
-#endif
 EXPORT_SYMBOL_GPL(usb_serial_handle_sysrq_char);
+#endif
 
 int usb_serial_handle_break(struct usb_serial_port *port)
 {
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 14cac4a1ae8f..be73646706a9 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -365,8 +365,17 @@ extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port,
 extern void usb_serial_generic_process_read_urb(struct urb *urb);
 extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port,
 						void *dest, size_t size);
+
+#if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port,
 					unsigned int ch);
+#else
+static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
+{
+	return 0;
+}
+#endif
+
 extern int usb_serial_handle_break(struct usb_serial_port *port);
 extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port,
 					 struct tty_struct *tty,
-- 
cgit v1.2.3


From 4b5cf2b8f90faf32bbb735b545510edefce094be Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 8 Jul 2020 14:49:57 +0200
Subject: USB: serial: add sysrq break-handler dummy

Add inline sysrq break-handler dummy to allow the compiler to eliminate
further code when either console or sysrq support isn't enabled and to
clearly mark the two sysrq functions as belonging together.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/generic.c | 4 ++--
 include/linux/usb/serial.h   | 6 +++++-
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index a9b6d103aaf6..e60f74f11acc 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -585,11 +585,10 @@ int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_serial_handle_sysrq_char);
-#endif
 
 int usb_serial_handle_break(struct usb_serial_port *port)
 {
-	if (!port->port.console || !IS_ENABLED(CONFIG_MAGIC_SYSRQ))
+	if (!port->port.console)
 		return 0;
 
 	if (!port->sysrq) {
@@ -600,6 +599,7 @@ int usb_serial_handle_break(struct usb_serial_port *port)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_serial_handle_break);
+#endif
 
 /**
  * usb_serial_handle_dcd_change - handle a change of carrier detect state
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index be73646706a9..c4ed4404335e 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -369,14 +369,18 @@ extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port,
 #if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port,
 					unsigned int ch);
+extern int usb_serial_handle_break(struct usb_serial_port *port);
 #else
 static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
 {
 	return 0;
 }
+static inline int usb_serial_handle_break(struct usb_serial_port *port)
+{
+	return 0;
+}
 #endif
 
-extern int usb_serial_handle_break(struct usb_serial_port *port);
 extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port,
 					 struct tty_struct *tty,
 					 unsigned int status);
-- 
cgit v1.2.3


From 1cafb03d5d88631c218a072e4116ac92e9782dd0 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 8 Jul 2020 14:49:58 +0200
Subject: USB: serial: drop unnecessary sysrq include

There's no need to include sysrq.h in the subsystem header.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 include/linux/usb/serial.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index c4ed4404335e..4becca7ae264 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -17,7 +17,6 @@
 #include <linux/kref.h>
 #include <linux/mutex.h>
 #include <linux/serial.h>
-#include <linux/sysrq.h>
 #include <linux/kfifo.h>
 
 /* The maximum number of ports one device can grab at once */
-- 
cgit v1.2.3


From 7aab96d6e3c54128f9e335fa8b11a0bd8815e118 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 8 Jul 2020 14:49:59 +0200
Subject: USB: serial: drop extern keyword from function declarations

Drop the redundant extern keyword from function declarations in the
subsystem header file to improve readability (and make it easier to spot
the global variables).

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 include/linux/usb/serial.h | 81 +++++++++++++++++++++-------------------------
 1 file changed, 36 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 4becca7ae264..6d756d03f46f 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -315,19 +315,19 @@ struct usb_serial_driver {
 #define to_usb_serial_driver(d) \
 	container_of(d, struct usb_serial_driver, driver)
 
-extern int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[],
+int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[],
 		const char *name, const struct usb_device_id *id_table);
-extern void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]);
-extern void usb_serial_port_softint(struct usb_serial_port *port);
+void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]);
+void usb_serial_port_softint(struct usb_serial_port *port);
 
-extern int usb_serial_suspend(struct usb_interface *intf, pm_message_t message);
-extern int usb_serial_resume(struct usb_interface *intf);
+int usb_serial_suspend(struct usb_interface *intf, pm_message_t message);
+int usb_serial_resume(struct usb_interface *intf);
 
 /* USB Serial console functions */
 #ifdef CONFIG_USB_SERIAL_CONSOLE
-extern void usb_serial_console_init(int minor);
-extern void usb_serial_console_exit(void);
-extern void usb_serial_console_disconnect(struct usb_serial *serial);
+void usb_serial_console_init(int minor);
+void usb_serial_console_exit(void);
+void usb_serial_console_disconnect(struct usb_serial *serial);
 #else
 static inline void usb_serial_console_init(int minor) { }
 static inline void usb_serial_console_exit(void) { }
@@ -335,40 +335,32 @@ static inline void usb_serial_console_disconnect(struct usb_serial *serial) {}
 #endif
 
 /* Functions needed by other parts of the usbserial core */
-extern struct usb_serial_port *usb_serial_port_get_by_minor(unsigned int minor);
-extern void usb_serial_put(struct usb_serial *serial);
-extern int usb_serial_generic_open(struct tty_struct *tty,
-	struct usb_serial_port *port);
-extern int usb_serial_generic_write_start(struct usb_serial_port *port,
-							gfp_t mem_flags);
-extern int usb_serial_generic_write(struct tty_struct *tty,
-	struct usb_serial_port *port, const unsigned char *buf, int count);
-extern void usb_serial_generic_close(struct usb_serial_port *port);
-extern int usb_serial_generic_resume(struct usb_serial *serial);
-extern int usb_serial_generic_write_room(struct tty_struct *tty);
-extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty);
-extern void usb_serial_generic_wait_until_sent(struct tty_struct *tty,
-								long timeout);
-extern void usb_serial_generic_read_bulk_callback(struct urb *urb);
-extern void usb_serial_generic_write_bulk_callback(struct urb *urb);
-extern void usb_serial_generic_throttle(struct tty_struct *tty);
-extern void usb_serial_generic_unthrottle(struct tty_struct *tty);
-extern int usb_serial_generic_tiocmiwait(struct tty_struct *tty,
-							unsigned long arg);
-extern int usb_serial_generic_get_icount(struct tty_struct *tty,
-					struct serial_icounter_struct *icount);
-extern int usb_serial_generic_register(void);
-extern void usb_serial_generic_deregister(void);
-extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port,
-						 gfp_t mem_flags);
-extern void usb_serial_generic_process_read_urb(struct urb *urb);
-extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port,
-						void *dest, size_t size);
+struct usb_serial_port *usb_serial_port_get_by_minor(unsigned int minor);
+void usb_serial_put(struct usb_serial *serial);
+int usb_serial_generic_open(struct tty_struct *tty, struct usb_serial_port *port);
+int usb_serial_generic_write_start(struct usb_serial_port *port, gfp_t mem_flags);
+int usb_serial_generic_write(struct tty_struct *tty, struct usb_serial_port *port,
+		const unsigned char *buf, int count);
+void usb_serial_generic_close(struct usb_serial_port *port);
+int usb_serial_generic_resume(struct usb_serial *serial);
+int usb_serial_generic_write_room(struct tty_struct *tty);
+int usb_serial_generic_chars_in_buffer(struct tty_struct *tty);
+void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout);
+void usb_serial_generic_read_bulk_callback(struct urb *urb);
+void usb_serial_generic_write_bulk_callback(struct urb *urb);
+void usb_serial_generic_throttle(struct tty_struct *tty);
+void usb_serial_generic_unthrottle(struct tty_struct *tty);
+int usb_serial_generic_tiocmiwait(struct tty_struct *tty, unsigned long arg);
+int usb_serial_generic_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount);
+int usb_serial_generic_register(void);
+void usb_serial_generic_deregister(void);
+int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, gfp_t mem_flags);
+void usb_serial_generic_process_read_urb(struct urb *urb);
+int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, void *dest, size_t size);
 
 #if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
-extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port,
-					unsigned int ch);
-extern int usb_serial_handle_break(struct usb_serial_port *port);
+int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch);
+int usb_serial_handle_break(struct usb_serial_port *port);
 #else
 static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
 {
@@ -380,13 +372,12 @@ static inline int usb_serial_handle_break(struct usb_serial_port *port)
 }
 #endif
 
-extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port,
-					 struct tty_struct *tty,
-					 unsigned int status);
+void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port,
+		struct tty_struct *tty, unsigned int status);
 
 
-extern int usb_serial_bus_register(struct usb_serial_driver *device);
-extern void usb_serial_bus_deregister(struct usb_serial_driver *device);
+int usb_serial_bus_register(struct usb_serial_driver *device);
+void usb_serial_bus_deregister(struct usb_serial_driver *device);
 
 extern struct bus_type usb_serial_bus_type;
 extern struct tty_driver *usb_serial_tty_driver;
-- 
cgit v1.2.3


From f7f611f2b1dc69547d425de0daeac548add2c761 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 8 Jul 2020 09:11:49 +0200
Subject: ARM: s3c24xx: leds: Convert to use GPIO descriptors

This converts the s3c24xx LED driver to use GPIO descriptors
and also modify all board files to account for these changes
by registering the appropriate GPIO tables for each board.

The driver was using a custom flag to indicate open drain
(tristate) but this can be handled by standard descriptor
machine tables.

The driver was setting non-pull-up for the pin using the custom
S3C24xx GPIO API, but this is a custom pin control system used
by the S3C24xx and no generic GPIO function, so this has simply
been pushed back into the respective board files.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/common-smdk.c        | 67 ++++++++++++++++++++----------
 arch/arm/mach-s3c24xx/mach-mini2440.c      | 63 ++++++++++++++++++++++++----
 arch/arm/mach-s3c24xx/mach-n30.c           | 54 +++++++++++++++++++++---
 arch/arm/mach-s3c24xx/mach-qt2410.c        | 12 +++++-
 arch/arm/mach-s3c24xx/mach-vr1000.c        | 38 +++++++++++++++--
 drivers/leds/leds-s3c24xx.c                | 36 ++++------------
 include/linux/platform_data/leds-s3c24xx.h |  6 ---
 7 files changed, 199 insertions(+), 77 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/common-smdk.c b/arch/arm/mach-s3c24xx/common-smdk.c
index 58e30cad386c..75064dfaceb1 100644
--- a/arch/arm/mach-s3c24xx/common-smdk.c
+++ b/arch/arm/mach-s3c24xx/common-smdk.c
@@ -14,6 +14,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 
@@ -44,29 +45,53 @@
 
 /* LED devices */
 
+static struct gpiod_lookup_table smdk_led4_gpio_table = {
+	.dev_id = "s3c24xx_led.0",
+	.table = {
+		GPIO_LOOKUP("GPF", 4, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table smdk_led5_gpio_table = {
+	.dev_id = "s3c24xx_led.1",
+	.table = {
+		GPIO_LOOKUP("GPF", 5, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table smdk_led6_gpio_table = {
+	.dev_id = "s3c24xx_led.2",
+	.table = {
+		GPIO_LOOKUP("GPF", 6, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table smdk_led7_gpio_table = {
+	.dev_id = "s3c24xx_led.3",
+	.table = {
+		GPIO_LOOKUP("GPF", 7, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata smdk_pdata_led4 = {
-	.gpio		= S3C2410_GPF(4),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.name		= "led4",
 	.def_trigger	= "timer",
 };
 
 static struct s3c24xx_led_platdata smdk_pdata_led5 = {
-	.gpio		= S3C2410_GPF(5),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.name		= "led5",
 	.def_trigger	= "nand-disk",
 };
 
 static struct s3c24xx_led_platdata smdk_pdata_led6 = {
-	.gpio		= S3C2410_GPF(6),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.name		= "led6",
 };
 
 static struct s3c24xx_led_platdata smdk_pdata_led7 = {
-	.gpio		= S3C2410_GPF(7),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.name		= "led7",
 };
 
@@ -179,27 +204,25 @@ static struct platform_device __initdata *smdk_devs[] = {
 	&smdk_led7,
 };
 
-static const struct gpio smdk_led_gpios[] = {
-	{ S3C2410_GPF(4), GPIOF_OUT_INIT_HIGH, NULL },
-	{ S3C2410_GPF(5), GPIOF_OUT_INIT_HIGH, NULL },
-	{ S3C2410_GPF(6), GPIOF_OUT_INIT_HIGH, NULL },
-	{ S3C2410_GPF(7), GPIOF_OUT_INIT_HIGH, NULL },
-};
-
 void __init smdk_machine_init(void)
 {
-	/* Configure the LEDs (even if we have no LED support)*/
-
-	int ret = gpio_request_array(smdk_led_gpios,
-				     ARRAY_SIZE(smdk_led_gpios));
-	if (!WARN_ON(ret < 0))
-		gpio_free_array(smdk_led_gpios, ARRAY_SIZE(smdk_led_gpios));
-
 	if (machine_is_smdk2443())
 		smdk_nand_info.twrph0 = 50;
 
 	s3c_nand_set_platdata(&smdk_nand_info);
 
+	/* Disable pull-up on the LED lines */
+	s3c_gpio_setpull(S3C2410_GPF(4), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPF(5), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPF(6), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPF(7), S3C_GPIO_PULL_NONE);
+
+	/* Add lookups for the lines */
+	gpiod_add_lookup_table(&smdk_led4_gpio_table);
+	gpiod_add_lookup_table(&smdk_led5_gpio_table);
+	gpiod_add_lookup_table(&smdk_led6_gpio_table);
+	gpiod_add_lookup_table(&smdk_led7_gpio_table);
+
 	platform_add_devices(smdk_devs, ARRAY_SIZE(smdk_devs));
 
 	s3c_pm_init();
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index 9035f868fb34..aa0c33109865 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -402,37 +402,68 @@ static struct platform_device mini2440_button_device = {
 
 /* LEDS */
 
+static struct gpiod_lookup_table mini2440_led1_gpio_table = {
+	.dev_id = "s3c24xx_led.1",
+	.table = {
+		GPIO_LOOKUP("GPB", 5, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table mini2440_led2_gpio_table = {
+	.dev_id = "s3c24xx_led.2",
+	.table = {
+		GPIO_LOOKUP("GPB", 6, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table mini2440_led3_gpio_table = {
+	.dev_id = "s3c24xx_led.3",
+	.table = {
+		GPIO_LOOKUP("GPB", 7, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table mini2440_led4_gpio_table = {
+	.dev_id = "s3c24xx_led.4",
+	.table = {
+		GPIO_LOOKUP("GPB", 8, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table mini2440_backlight_gpio_table = {
+	.dev_id = "s3c24xx_led.5",
+	.table = {
+		GPIO_LOOKUP("GPG", 4, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata mini2440_led1_pdata = {
 	.name		= "led1",
-	.gpio		= S3C2410_GPB(5),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.def_trigger	= "heartbeat",
 };
 
 static struct s3c24xx_led_platdata mini2440_led2_pdata = {
 	.name		= "led2",
-	.gpio		= S3C2410_GPB(6),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.def_trigger	= "nand-disk",
 };
 
 static struct s3c24xx_led_platdata mini2440_led3_pdata = {
 	.name		= "led3",
-	.gpio		= S3C2410_GPB(7),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.def_trigger	= "mmc0",
 };
 
 static struct s3c24xx_led_platdata mini2440_led4_pdata = {
 	.name		= "led4",
-	.gpio		= S3C2410_GPB(8),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.def_trigger	= "",
 };
 
 static struct s3c24xx_led_platdata mini2440_led_backlight_pdata = {
 	.name		= "backlight",
-	.gpio		= S3C2410_GPG(4),
 	.def_trigger	= "backlight",
 };
 
@@ -714,6 +745,20 @@ static void __init mini2440_init(void)
 	i2c_register_board_info(0, mini2440_i2c_devs,
 				ARRAY_SIZE(mini2440_i2c_devs));
 
+	/* Disable pull-up on the LED lines */
+	s3c_gpio_setpull(S3C2410_GPB(5), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPB(6), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPB(7), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPB(8), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPG(4), S3C_GPIO_PULL_NONE);
+
+	/* Add lookups for the lines */
+	gpiod_add_lookup_table(&mini2440_led1_gpio_table);
+	gpiod_add_lookup_table(&mini2440_led2_gpio_table);
+	gpiod_add_lookup_table(&mini2440_led3_gpio_table);
+	gpiod_add_lookup_table(&mini2440_led4_gpio_table);
+	gpiod_add_lookup_table(&mini2440_backlight_gpio_table);
+
 	platform_add_devices(mini2440_devices, ARRAY_SIZE(mini2440_devices));
 
 	if (features.count)	/* the optional features */
diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c
index d856f23939af..58a64f6d5fd0 100644
--- a/arch/arm/mach-s3c24xx/mach-n30.c
+++ b/arch/arm/mach-s3c24xx/mach-n30.c
@@ -45,6 +45,7 @@
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
+#include <plat/gpio-cfg.h>
 #include <linux/platform_data/mmc-s3cmci.h>
 #include <linux/platform_data/usb-s3c2410_udc.h>
 #include <plat/samsung-time.h>
@@ -246,17 +247,33 @@ static struct platform_device n35_button_device = {
 };
 
 /* This is the bluetooth LED on the device. */
+
+static struct gpiod_lookup_table n30_blue_led_gpio_table = {
+	.dev_id = "s3c24xx_led.1",
+	.table = {
+		GPIO_LOOKUP("GPG", 6, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata n30_blue_led_pdata = {
 	.name		= "blue_led",
-	.gpio		= S3C2410_GPG(6),
 	.def_trigger	= "",
 };
 
 /* This is the blue LED on the device. Originally used to indicate GPS activity
  * by flashing. */
+
+static struct gpiod_lookup_table n35_blue_led_gpio_table = {
+	.dev_id = "s3c24xx_led.1",
+	.table = {
+		GPIO_LOOKUP("GPD", 8, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata n35_blue_led_pdata = {
 	.name		= "blue_led",
-	.gpio		= S3C2410_GPD(8),
 	.def_trigger	= "",
 };
 
@@ -264,17 +281,30 @@ static struct s3c24xx_led_platdata n35_blue_led_pdata = {
  * red, blinking green or solid green when the battery is low,
  * charging or full respectively.  By driving GPD9 low, it's possible
  * to force the LED to blink red, so call that warning LED.  */
+
+static struct gpiod_lookup_table n30_warning_led_gpio_table = {
+	.dev_id = "s3c24xx_led.2",
+	.table = {
+		GPIO_LOOKUP("GPD", 9, NULL, GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata n30_warning_led_pdata = {
 	.name		= "warning_led",
-	.flags          = S3C24XX_LEDF_ACTLOW,
-	.gpio		= S3C2410_GPD(9),
 	.def_trigger	= "",
 };
 
+static struct gpiod_lookup_table n35_warning_led_gpio_table = {
+	.dev_id = "s3c24xx_led.2",
+	.table = {
+		GPIO_LOOKUP("GPD", 9, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata n35_warning_led_pdata = {
 	.name		= "warning_led",
-	.flags          = S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
-	.gpio		= S3C2410_GPD(9),
 	.def_trigger	= "",
 };
 
@@ -577,6 +607,12 @@ static void __init n30_init(void)
 				      S3C2410_MISCCR_USBSUSPND0 |
 				      S3C2410_MISCCR_USBSUSPND1, 0x0);
 
+		/* Disable pull-up and add GPIO tables */
+		s3c_gpio_setpull(S3C2410_GPG(6), S3C_GPIO_PULL_NONE);
+		s3c_gpio_setpull(S3C2410_GPD(9), S3C_GPIO_PULL_NONE);
+		gpiod_add_lookup_table(&n30_blue_led_gpio_table);
+		gpiod_add_lookup_table(&n30_warning_led_gpio_table);
+
 		platform_add_devices(n30_devices, ARRAY_SIZE(n30_devices));
 	}
 
@@ -594,6 +630,12 @@ static void __init n30_init(void)
 				      S3C2410_MISCCR_USBSUSPND1,
 				      S3C2410_MISCCR_USBSUSPND0);
 
+		/* Disable pull-up and add GPIO tables */
+		s3c_gpio_setpull(S3C2410_GPD(8), S3C_GPIO_PULL_NONE);
+		s3c_gpio_setpull(S3C2410_GPD(9), S3C_GPIO_PULL_NONE);
+		gpiod_add_lookup_table(&n35_blue_led_gpio_table);
+		gpiod_add_lookup_table(&n35_warning_led_gpio_table);
+
 		platform_add_devices(n35_devices, ARRAY_SIZE(n35_devices));
 	}
 }
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index 5d48e5b6e738..ff9e3197309b 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -177,9 +177,15 @@ static struct platform_device qt2410_cs89x0 = {
 
 /* LED */
 
+static struct gpiod_lookup_table qt2410_led_gpio_table = {
+	.dev_id = "s3c24xx_led.0",
+	.table = {
+		GPIO_LOOKUP("GPB", 0, NULL, GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata qt2410_pdata_led = {
-	.gpio		= S3C2410_GPB(0),
-	.flags		= S3C24XX_LEDF_ACTLOW | S3C24XX_LEDF_TRISTATE,
 	.name		= "led",
 	.def_trigger	= "timer",
 };
@@ -338,6 +344,8 @@ static void __init qt2410_machine_init(void)
 	s3c_i2c0_set_platdata(NULL);
 
 	gpiod_add_lookup_table(&qt2410_spi_gpiod_table);
+	s3c_gpio_setpull(S3C2410_GPB(0), S3C_GPIO_PULL_NONE);
+	gpiod_add_lookup_table(&qt2410_led_gpio_table);
 	platform_add_devices(qt2410_devices, ARRAY_SIZE(qt2410_devices));
 	s3c_pm_init();
 }
diff --git a/arch/arm/mach-s3c24xx/mach-vr1000.c b/arch/arm/mach-s3c24xx/mach-vr1000.c
index 853e74f9b8b5..6a3fb2becc7c 100644
--- a/arch/arm/mach-s3c24xx/mach-vr1000.c
+++ b/arch/arm/mach-s3c24xx/mach-vr1000.c
@@ -13,6 +13,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/dm9000.h>
 #include <linux/i2c.h>
 
@@ -40,6 +41,7 @@
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
+#include <plat/gpio-cfg.h>
 #include <plat/samsung-time.h>
 
 #include "bast.h"
@@ -223,21 +225,42 @@ static struct platform_device vr1000_dm9k1 = {
 
 /* LEDS */
 
+static struct gpiod_lookup_table vr1000_led1_gpio_table = {
+	.dev_id = "s3c24xx_led.1",
+	.table = {
+		GPIO_LOOKUP("GPB", 0, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table vr1000_led2_gpio_table = {
+	.dev_id = "s3c24xx_led.2",
+	.table = {
+		GPIO_LOOKUP("GPB", 1, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table vr1000_led3_gpio_table = {
+	.dev_id = "s3c24xx_led.3",
+	.table = {
+		GPIO_LOOKUP("GPB", 2, NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct s3c24xx_led_platdata vr1000_led1_pdata = {
 	.name		= "led1",
-	.gpio		= S3C2410_GPB(0),
 	.def_trigger	= "",
 };
 
 static struct s3c24xx_led_platdata vr1000_led2_pdata = {
 	.name		= "led2",
-	.gpio		= S3C2410_GPB(1),
 	.def_trigger	= "",
 };
 
 static struct s3c24xx_led_platdata vr1000_led3_pdata = {
 	.name		= "led3",
-	.gpio		= S3C2410_GPB(2),
 	.def_trigger	= "",
 };
 
@@ -317,6 +340,15 @@ static void __init vr1000_init_time(void)
 static void __init vr1000_init(void)
 {
 	s3c_i2c0_set_platdata(NULL);
+
+	/* Disable pull-up on LED lines and register GPIO lookups */
+	s3c_gpio_setpull(S3C2410_GPB(0), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPB(1), S3C_GPIO_PULL_NONE);
+	s3c_gpio_setpull(S3C2410_GPB(2), S3C_GPIO_PULL_NONE);
+	gpiod_add_lookup_table(&vr1000_led1_gpio_table);
+	gpiod_add_lookup_table(&vr1000_led2_gpio_table);
+	gpiod_add_lookup_table(&vr1000_led3_gpio_table);
+
 	platform_add_devices(vr1000_devices, ARRAY_SIZE(vr1000_devices));
 
 	i2c_register_board_info(0, vr1000_i2c_devs,
diff --git a/drivers/leds/leds-s3c24xx.c b/drivers/leds/leds-s3c24xx.c
index f8b8d6e313ee..9b5e67664ba3 100644
--- a/drivers/leds/leds-s3c24xx.c
+++ b/drivers/leds/leds-s3c24xx.c
@@ -11,19 +11,19 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_data/leds-s3c24xx.h>
 
 #include <mach/regs-gpio.h>
-#include <plat/gpio-cfg.h>
 
 /* our context */
 
 struct s3c24xx_gpio_led {
 	struct led_classdev		 cdev;
 	struct s3c24xx_led_platdata	*pdata;
+	struct gpio_desc		*gpiod;
 };
 
 static inline struct s3c24xx_gpio_led *to_gpio(struct led_classdev *led_cdev)
@@ -35,20 +35,8 @@ static void s3c24xx_led_set(struct led_classdev *led_cdev,
 			    enum led_brightness value)
 {
 	struct s3c24xx_gpio_led *led = to_gpio(led_cdev);
-	struct s3c24xx_led_platdata *pd = led->pdata;
-	int state = (value ? 1 : 0) ^ (pd->flags & S3C24XX_LEDF_ACTLOW);
 
-	/* there will be a short delay between setting the output and
-	 * going from output to input when using tristate. */
-
-	gpio_set_value(pd->gpio, state);
-
-	if (pd->flags & S3C24XX_LEDF_TRISTATE) {
-		if (value)
-			gpio_direction_output(pd->gpio, state);
-		else
-			gpio_direction_input(pd->gpio);
-	}
+	gpiod_set_value(led->gpiod, !!value);
 }
 
 static int s3c24xx_led_probe(struct platform_device *dev)
@@ -69,22 +57,12 @@ static int s3c24xx_led_probe(struct platform_device *dev)
 
 	led->pdata = pdata;
 
-	ret = devm_gpio_request(&dev->dev, pdata->gpio, "S3C24XX_LED");
-	if (ret < 0)
-		return ret;
-
-	/* no point in having a pull-up if we are always driving */
-
-	s3c_gpio_setpull(pdata->gpio, S3C_GPIO_PULL_NONE);
-
-	if (pdata->flags & S3C24XX_LEDF_TRISTATE)
-		gpio_direction_input(pdata->gpio);
-	else
-		gpio_direction_output(pdata->gpio,
-			pdata->flags & S3C24XX_LEDF_ACTLOW ? 1 : 0);
+	/* Default to off */
+	led->gpiod = devm_gpiod_get(&dev->dev, NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(led->gpiod))
+		return PTR_ERR(led->gpiod);
 
 	/* register our new led device */
-
 	ret = devm_led_classdev_register(&dev->dev, &led->cdev);
 	if (ret < 0)
 		dev_err(&dev->dev, "led_classdev_register failed\n");
diff --git a/include/linux/platform_data/leds-s3c24xx.h b/include/linux/platform_data/leds-s3c24xx.h
index 5bbae85811e2..64f8d14876e0 100644
--- a/include/linux/platform_data/leds-s3c24xx.h
+++ b/include/linux/platform_data/leds-s3c24xx.h
@@ -10,13 +10,7 @@
 #ifndef __LEDS_S3C24XX_H
 #define __LEDS_S3C24XX_H
 
-#define S3C24XX_LEDF_ACTLOW	(1<<0)		/* LED is on when GPIO low */
-#define S3C24XX_LEDF_TRISTATE	(1<<1)		/* tristate to turn off */
-
 struct s3c24xx_led_platdata {
-	unsigned int		 gpio;
-	unsigned int		 flags;
-
 	char			*name;
 	char			*def_trigger;
 };
-- 
cgit v1.2.3


From 7bc13b5b60e9412a7ddef300ce2c661eecd1fd5d Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Sun, 5 Jul 2020 21:18:58 +1200
Subject: crypto: api - permit users to specify numa node of acomp hardware

For a Linux server with NUMA, there are possibly multiple (de)compressors
which are either local or remote to some NUMA node. Some drivers will
automatically use the (de)compressor near the CPU calling acomp_alloc().
However, it is not necessarily correct because users who send acomp_req
could be from different NUMA node with the CPU which allocates acomp.

Just like kernel has kmalloc() and kmalloc_node(), here crypto can have
same support.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/acompress.c         |  8 ++++++++
 crypto/api.c               | 24 +++++++++++++++---------
 crypto/internal.h          | 23 +++++++++++++++++++----
 include/crypto/acompress.h | 18 ++++++++++++++++++
 include/linux/crypto.h     |  2 ++
 5 files changed, 62 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/acompress.c b/crypto/acompress.c
index 84a76723e851..c32c72048a1c 100644
--- a/crypto/acompress.c
+++ b/crypto/acompress.c
@@ -109,6 +109,14 @@ struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type,
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_acomp);
 
+struct crypto_acomp *crypto_alloc_acomp_node(const char *alg_name, u32 type,
+					u32 mask, int node)
+{
+	return crypto_alloc_tfm_node(alg_name, &crypto_acomp_type, type, mask,
+				node);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_acomp_node);
+
 struct acomp_req *acomp_request_alloc(struct crypto_acomp *acomp)
 {
 	struct crypto_tfm *tfm = crypto_acomp_tfm(acomp);
diff --git a/crypto/api.c b/crypto/api.c
index edcf690800d4..5d8fe60b36c1 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -433,8 +433,9 @@ err:
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_base);
 
-void *crypto_create_tfm(struct crypto_alg *alg,
-			const struct crypto_type *frontend)
+void *crypto_create_tfm_node(struct crypto_alg *alg,
+			const struct crypto_type *frontend,
+			int node)
 {
 	char *mem;
 	struct crypto_tfm *tfm = NULL;
@@ -445,12 +446,13 @@ void *crypto_create_tfm(struct crypto_alg *alg,
 	tfmsize = frontend->tfmsize;
 	total = tfmsize + sizeof(*tfm) + frontend->extsize(alg);
 
-	mem = kzalloc(total, GFP_KERNEL);
+	mem = kzalloc_node(total, GFP_KERNEL, node);
 	if (mem == NULL)
 		goto out_err;
 
 	tfm = (struct crypto_tfm *)(mem + tfmsize);
 	tfm->__crt_alg = alg;
+	tfm->node = node;
 
 	err = frontend->init_tfm(tfm);
 	if (err)
@@ -472,7 +474,7 @@ out_err:
 out:
 	return mem;
 }
-EXPORT_SYMBOL_GPL(crypto_create_tfm);
+EXPORT_SYMBOL_GPL(crypto_create_tfm_node);
 
 struct crypto_alg *crypto_find_alg(const char *alg_name,
 				   const struct crypto_type *frontend,
@@ -490,11 +492,13 @@ struct crypto_alg *crypto_find_alg(const char *alg_name,
 EXPORT_SYMBOL_GPL(crypto_find_alg);
 
 /*
- *	crypto_alloc_tfm - Locate algorithm and allocate transform
+ *	crypto_alloc_tfm_node - Locate algorithm and allocate transform
  *	@alg_name: Name of algorithm
  *	@frontend: Frontend algorithm type
  *	@type: Type of algorithm
  *	@mask: Mask for type comparison
+ *	@node: NUMA node in which users desire to put requests, if node is
+ *		NUMA_NO_NODE, it means users have no special requirement.
  *
  *	crypto_alloc_tfm() will first attempt to locate an already loaded
  *	algorithm.  If that fails and the kernel supports dynamically loadable
@@ -509,8 +513,10 @@ EXPORT_SYMBOL_GPL(crypto_find_alg);
  *
  *	In case of error the return value is an error pointer.
  */
-void *crypto_alloc_tfm(const char *alg_name,
-		       const struct crypto_type *frontend, u32 type, u32 mask)
+
+void *crypto_alloc_tfm_node(const char *alg_name,
+		       const struct crypto_type *frontend, u32 type, u32 mask,
+		       int node)
 {
 	void *tfm;
 	int err;
@@ -524,7 +530,7 @@ void *crypto_alloc_tfm(const char *alg_name,
 			goto err;
 		}
 
-		tfm = crypto_create_tfm(alg, frontend);
+		tfm = crypto_create_tfm_node(alg, frontend, node);
 		if (!IS_ERR(tfm))
 			return tfm;
 
@@ -542,7 +548,7 @@ err:
 
 	return ERR_PTR(err);
 }
-EXPORT_SYMBOL_GPL(crypto_alloc_tfm);
+EXPORT_SYMBOL_GPL(crypto_alloc_tfm_node);
 
 /*
  *	crypto_destroy_tfm - Free crypto transform
diff --git a/crypto/internal.h b/crypto/internal.h
index ff06a3bd1ca1..1b92a5a61852 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -68,13 +68,28 @@ void crypto_remove_final(struct list_head *list);
 void crypto_shoot_alg(struct crypto_alg *alg);
 struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask);
-void *crypto_create_tfm(struct crypto_alg *alg,
-			const struct crypto_type *frontend);
+void *crypto_create_tfm_node(struct crypto_alg *alg,
+			const struct crypto_type *frontend, int node);
+
+static inline void *crypto_create_tfm(struct crypto_alg *alg,
+			const struct crypto_type *frontend)
+{
+	return crypto_create_tfm_node(alg, frontend, NUMA_NO_NODE);
+}
+
 struct crypto_alg *crypto_find_alg(const char *alg_name,
 				   const struct crypto_type *frontend,
 				   u32 type, u32 mask);
-void *crypto_alloc_tfm(const char *alg_name,
-		       const struct crypto_type *frontend, u32 type, u32 mask);
+
+void *crypto_alloc_tfm_node(const char *alg_name,
+		       const struct crypto_type *frontend, u32 type, u32 mask,
+		       int node);
+
+static inline void *crypto_alloc_tfm(const char *alg_name,
+		       const struct crypto_type *frontend, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm_node(alg_name, frontend, type, mask, NUMA_NO_NODE);
+}
 
 int crypto_probing_notify(unsigned long val, void *v);
 
diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h
index 2b4d2b06ccbd..fcde59c65a81 100644
--- a/include/crypto/acompress.h
+++ b/include/crypto/acompress.h
@@ -106,6 +106,24 @@ struct acomp_alg {
  */
 struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type,
 					u32 mask);
+/**
+ * crypto_alloc_acomp_node() -- allocate ACOMPRESS tfm handle with desired NUMA node
+ * @alg_name:	is the cra_name / name or cra_driver_name / driver name of the
+ *		compression algorithm e.g. "deflate"
+ * @type:	specifies the type of the algorithm
+ * @mask:	specifies the mask for the algorithm
+ * @node:	specifies the NUMA node the ZIP hardware belongs to
+ *
+ * Allocate a handle for a compression algorithm. Drivers should try to use
+ * (de)compressors on the specified NUMA node.
+ * The returned struct crypto_acomp is the handle that is required for any
+ * subsequent API invocation for the compression operations.
+ *
+ * Return:	allocated handle in case of success; IS_ERR() is true in case
+ *		of an error, PTR_ERR() returns the error code.
+ */
+struct crypto_acomp *crypto_alloc_acomp_node(const char *alg_name, u32 type,
+					u32 mask, int node);
 
 static inline struct crypto_tfm *crypto_acomp_tfm(struct crypto_acomp *tfm)
 {
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index bc5d2d4bfc3d..7cd2d00f0a05 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -594,6 +594,8 @@ int crypto_has_alg(const char *name, u32 type, u32 mask);
 struct crypto_tfm {
 
 	u32 crt_flags;
+
+	int node;
 	
 	void (*exit)(struct crypto_tfm *tfm);
 	
-- 
cgit v1.2.3


From 995decb6c43e1d6e9d6a7d590471f2eea74600f4 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Wed, 8 Jul 2020 16:00:23 +0200
Subject: KVM: x86: take as_id into account when checking PGD

OVMF booted guest running on shadow pages crashes on TRIPLE FAULT after
enabling paging from SMM. The crash is triggered from mmu_check_root() and
is caused by kvm_is_visible_gfn() searching through memslots with as_id = 0
while vCPU may be in a different context (address space).

Introduce kvm_vcpu_is_visible_gfn() and use it from mmu_check_root().

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200708140023.1476020-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 2 +-
 include/linux/kvm_host.h | 1 +
 virt/kvm/kvm_main.c      | 8 ++++++++
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0011b2c97f65..231beb6d9cf7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3693,7 +3693,7 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
 {
 	int ret = 0;
 
-	if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
+	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
 		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		ret = 1;
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9edc6fc71a89..87140e79648b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -774,6 +774,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
+bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0a68c9d3d3ab..b528a59b0a84 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1626,6 +1626,14 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
+bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+
+	return kvm_is_visible_memslot(memslot);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn);
+
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	struct vm_area_struct *vma;
-- 
cgit v1.2.3


From 8d87ae48ced2dffd5e7247d19eb4c88be6f1c6f1 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 8 Jul 2020 16:32:13 -0700
Subject: PM: domains: Fix up terminology with parent/child

The genpd infrastructure uses the terms master/slave, but such uses have
no external exposures (not even in Documentation/driver-api/pm/*) and are
not mandated by nor associated with any external specifications. Change
the language used through-out to parent/child.

There was one possible exception in the debugfs node
"pm_genpd/pm_genpd_summary" but its path has no hits outside of the
kernel itself when performing a code search[1], and it seems even this
single usage has been non-functional since it was introduced due to a
typo in the Python ("apend" instead of correct "append"). Fix the typo
while we're at it.

Link: https://codesearch.debian.net/ # [1]
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Kieran Bingham <kieran.bingham@ideasonboard.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c          | 194 +++++++++++++++++------------------
 drivers/base/power/domain_governor.c |  12 +--
 include/linux/pm_domain.h            |  12 +--
 scripts/gdb/linux/genpd.py           |  12 +--
 4 files changed, 115 insertions(+), 115 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 0a01df608849..2cb5e04cf86c 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -263,18 +263,18 @@ static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd,
 	/*
 	 * Traverse all sub-domains within the domain. This can be
 	 * done without any additional locking as the link->performance_state
-	 * field is protected by the master genpd->lock, which is already taken.
+	 * field is protected by the parent genpd->lock, which is already taken.
 	 *
 	 * Also note that link->performance_state (subdomain's performance state
-	 * requirement to master domain) is different from
-	 * link->slave->performance_state (current performance state requirement
+	 * requirement to parent domain) is different from
+	 * link->child->performance_state (current performance state requirement
 	 * of the devices/sub-domains of the subdomain) and so can have a
 	 * different value.
 	 *
 	 * Note that we also take vote from powered-off sub-domains into account
 	 * as the same is done for devices right now.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
 		if (link->performance_state > state)
 			state = link->performance_state;
 	}
@@ -285,40 +285,40 @@ static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd,
 static int _genpd_set_performance_state(struct generic_pm_domain *genpd,
 					unsigned int state, int depth)
 {
-	struct generic_pm_domain *master;
+	struct generic_pm_domain *parent;
 	struct gpd_link *link;
-	int master_state, ret;
+	int parent_state, ret;
 
 	if (state == genpd->performance_state)
 		return 0;
 
-	/* Propagate to masters of genpd */
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		master = link->master;
+	/* Propagate to parents of genpd */
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		parent = link->parent;
 
-		if (!master->set_performance_state)
+		if (!parent->set_performance_state)
 			continue;
 
-		/* Find master's performance state */
+		/* Find parent's performance state */
 		ret = dev_pm_opp_xlate_performance_state(genpd->opp_table,
-							 master->opp_table,
+							 parent->opp_table,
 							 state);
 		if (unlikely(ret < 0))
 			goto err;
 
-		master_state = ret;
+		parent_state = ret;
 
-		genpd_lock_nested(master, depth + 1);
+		genpd_lock_nested(parent, depth + 1);
 
 		link->prev_performance_state = link->performance_state;
-		link->performance_state = master_state;
-		master_state = _genpd_reeval_performance_state(master,
-						master_state);
-		ret = _genpd_set_performance_state(master, master_state, depth + 1);
+		link->performance_state = parent_state;
+		parent_state = _genpd_reeval_performance_state(parent,
+						parent_state);
+		ret = _genpd_set_performance_state(parent, parent_state, depth + 1);
 		if (ret)
 			link->performance_state = link->prev_performance_state;
 
-		genpd_unlock(master);
+		genpd_unlock(parent);
 
 		if (ret)
 			goto err;
@@ -333,26 +333,26 @@ static int _genpd_set_performance_state(struct generic_pm_domain *genpd,
 
 err:
 	/* Encountered an error, lets rollback */
-	list_for_each_entry_continue_reverse(link, &genpd->slave_links,
-					     slave_node) {
-		master = link->master;
+	list_for_each_entry_continue_reverse(link, &genpd->child_links,
+					     child_node) {
+		parent = link->parent;
 
-		if (!master->set_performance_state)
+		if (!parent->set_performance_state)
 			continue;
 
-		genpd_lock_nested(master, depth + 1);
+		genpd_lock_nested(parent, depth + 1);
 
-		master_state = link->prev_performance_state;
-		link->performance_state = master_state;
+		parent_state = link->prev_performance_state;
+		link->performance_state = parent_state;
 
-		master_state = _genpd_reeval_performance_state(master,
-						master_state);
-		if (_genpd_set_performance_state(master, master_state, depth + 1)) {
+		parent_state = _genpd_reeval_performance_state(parent,
+						parent_state);
+		if (_genpd_set_performance_state(parent, parent_state, depth + 1)) {
 			pr_err("%s: Failed to roll back to %d performance state\n",
-			       master->name, master_state);
+			       parent->name, parent_state);
 		}
 
-		genpd_unlock(master);
+		genpd_unlock(parent);
 	}
 
 	return ret;
@@ -552,7 +552,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call genpd_power_on() for the master yet after
+		 * managed to call genpd_power_on() for the parent yet after
 		 * incrementing it.  In that case genpd_power_on() will wait
 		 * for us to drop the lock, so we can call .power_off() and let
 		 * the genpd_power_on() restore power for us (this shouldn't
@@ -566,22 +566,22 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 	genpd->status = GPD_STATE_POWER_OFF;
 	genpd_update_accounting(genpd);
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_dec(link->master);
-		genpd_lock_nested(link->master, depth + 1);
-		genpd_power_off(link->master, false, depth + 1);
-		genpd_unlock(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_dec(link->parent);
+		genpd_lock_nested(link->parent, depth + 1);
+		genpd_power_off(link->parent, false, depth + 1);
+		genpd_unlock(link->parent);
 	}
 
 	return 0;
 }
 
 /**
- * genpd_power_on - Restore power to a given PM domain and its masters.
+ * genpd_power_on - Restore power to a given PM domain and its parents.
  * @genpd: PM domain to power up.
  * @depth: nesting count for lockdep.
  *
- * Restore power to @genpd and all of its masters so that it is possible to
+ * Restore power to @genpd and all of its parents so that it is possible to
  * resume a device belonging to it.
  */
 static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
@@ -594,20 +594,20 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 
 	/*
 	 * The list is guaranteed not to change while the loop below is being
-	 * executed, unless one of the masters' .power_on() callbacks fiddles
+	 * executed, unless one of the parents' .power_on() callbacks fiddles
 	 * with it.
 	 */
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		struct generic_pm_domain *master = link->master;
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		struct generic_pm_domain *parent = link->parent;
 
-		genpd_sd_counter_inc(master);
+		genpd_sd_counter_inc(parent);
 
-		genpd_lock_nested(master, depth + 1);
-		ret = genpd_power_on(master, depth + 1);
-		genpd_unlock(master);
+		genpd_lock_nested(parent, depth + 1);
+		ret = genpd_power_on(parent, depth + 1);
+		genpd_unlock(parent);
 
 		if (ret) {
-			genpd_sd_counter_dec(master);
+			genpd_sd_counter_dec(parent);
 			goto err;
 		}
 	}
@@ -623,12 +623,12 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 
  err:
 	list_for_each_entry_continue_reverse(link,
-					&genpd->slave_links,
-					slave_node) {
-		genpd_sd_counter_dec(link->master);
-		genpd_lock_nested(link->master, depth + 1);
-		genpd_power_off(link->master, false, depth + 1);
-		genpd_unlock(link->master);
+					&genpd->child_links,
+					child_node) {
+		genpd_sd_counter_dec(link->parent);
+		genpd_lock_nested(link->parent, depth + 1);
+		genpd_power_off(link->parent, false, depth + 1);
+		genpd_unlock(link->parent);
 	}
 
 	return ret;
@@ -932,13 +932,13 @@ late_initcall(genpd_power_off_unused);
 #ifdef CONFIG_PM_SLEEP
 
 /**
- * genpd_sync_power_off - Synchronously power off a PM domain and its masters.
+ * genpd_sync_power_off - Synchronously power off a PM domain and its parents.
  * @genpd: PM domain to power off, if possible.
  * @use_lock: use the lock.
  * @depth: nesting count for lockdep.
  *
  * Check if the given PM domain can be powered off (during system suspend or
- * hibernation) and do that if so.  Also, in that case propagate to its masters.
+ * hibernation) and do that if so.  Also, in that case propagate to its parents.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
  * transitions. The "noirq" callbacks may be executed asynchronously, thus in
@@ -963,21 +963,21 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_dec(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_dec(link->parent);
 
 		if (use_lock)
-			genpd_lock_nested(link->master, depth + 1);
+			genpd_lock_nested(link->parent, depth + 1);
 
-		genpd_sync_power_off(link->master, use_lock, depth + 1);
+		genpd_sync_power_off(link->parent, use_lock, depth + 1);
 
 		if (use_lock)
-			genpd_unlock(link->master);
+			genpd_unlock(link->parent);
 	}
 }
 
 /**
- * genpd_sync_power_on - Synchronously power on a PM domain and its masters.
+ * genpd_sync_power_on - Synchronously power on a PM domain and its parents.
  * @genpd: PM domain to power on.
  * @use_lock: use the lock.
  * @depth: nesting count for lockdep.
@@ -994,16 +994,16 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 	if (genpd_status_on(genpd))
 		return;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_inc(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_inc(link->parent);
 
 		if (use_lock)
-			genpd_lock_nested(link->master, depth + 1);
+			genpd_lock_nested(link->parent, depth + 1);
 
-		genpd_sync_power_on(link->master, use_lock, depth + 1);
+		genpd_sync_power_on(link->parent, use_lock, depth + 1);
 
 		if (use_lock)
-			genpd_unlock(link->master);
+			genpd_unlock(link->parent);
 	}
 
 	_genpd_power_on(genpd, false);
@@ -1443,12 +1443,12 @@ static void genpd_update_cpumask(struct generic_pm_domain *genpd,
 	if (!genpd_is_cpu_domain(genpd))
 		return;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		struct generic_pm_domain *master = link->master;
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		struct generic_pm_domain *parent = link->parent;
 
-		genpd_lock_nested(master, depth + 1);
-		genpd_update_cpumask(master, cpu, set, depth + 1);
-		genpd_unlock(master);
+		genpd_lock_nested(parent, depth + 1);
+		genpd_update_cpumask(parent, cpu, set, depth + 1);
+		genpd_unlock(parent);
 	}
 
 	if (set)
@@ -1636,17 +1636,17 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 		goto out;
 	}
 
-	list_for_each_entry(itr, &genpd->master_links, master_node) {
-		if (itr->slave == subdomain && itr->master == genpd) {
+	list_for_each_entry(itr, &genpd->parent_links, parent_node) {
+		if (itr->child == subdomain && itr->parent == genpd) {
 			ret = -EINVAL;
 			goto out;
 		}
 	}
 
-	link->master = genpd;
-	list_add_tail(&link->master_node, &genpd->master_links);
-	link->slave = subdomain;
-	list_add_tail(&link->slave_node, &subdomain->slave_links);
+	link->parent = genpd;
+	list_add_tail(&link->parent_node, &genpd->parent_links);
+	link->child = subdomain;
+	list_add_tail(&link->child_node, &subdomain->child_links);
 	if (genpd_status_on(subdomain))
 		genpd_sd_counter_inc(genpd);
 
@@ -1660,7 +1660,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 
 /**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
- * @genpd: Master PM domain to add the subdomain to.
+ * @genpd: Leader PM domain to add the subdomain to.
  * @subdomain: Subdomain to be added.
  */
 int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
@@ -1678,7 +1678,7 @@ EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain);
 
 /**
  * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
- * @genpd: Master PM domain to remove the subdomain from.
+ * @genpd: Leader PM domain to remove the subdomain from.
  * @subdomain: Subdomain to be removed.
  */
 int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
@@ -1693,19 +1693,19 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	genpd_lock(subdomain);
 	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
-	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
+	if (!list_empty(&subdomain->parent_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n",
 			genpd->name, subdomain->name);
 		ret = -EBUSY;
 		goto out;
 	}
 
-	list_for_each_entry_safe(link, l, &genpd->master_links, master_node) {
-		if (link->slave != subdomain)
+	list_for_each_entry_safe(link, l, &genpd->parent_links, parent_node) {
+		if (link->child != subdomain)
 			continue;
 
-		list_del(&link->master_node);
-		list_del(&link->slave_node);
+		list_del(&link->parent_node);
+		list_del(&link->child_node);
 		kfree(link);
 		if (genpd_status_on(subdomain))
 			genpd_sd_counter_dec(genpd);
@@ -1770,8 +1770,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	INIT_LIST_HEAD(&genpd->master_links);
-	INIT_LIST_HEAD(&genpd->slave_links);
+	INIT_LIST_HEAD(&genpd->parent_links);
+	INIT_LIST_HEAD(&genpd->child_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
 	genpd_lock_init(genpd);
 	genpd->gov = gov;
@@ -1848,15 +1848,15 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 		return -EBUSY;
 	}
 
-	if (!list_empty(&genpd->master_links) || genpd->device_count) {
+	if (!list_empty(&genpd->parent_links) || genpd->device_count) {
 		genpd_unlock(genpd);
 		pr_err("%s: unable to remove %s\n", __func__, genpd->name);
 		return -EBUSY;
 	}
 
-	list_for_each_entry_safe(link, l, &genpd->slave_links, slave_node) {
-		list_del(&link->master_node);
-		list_del(&link->slave_node);
+	list_for_each_entry_safe(link, l, &genpd->child_links, child_node) {
+		list_del(&link->parent_node);
+		list_del(&link->child_node);
 		kfree(link);
 	}
 
@@ -2827,12 +2827,12 @@ static int genpd_summary_one(struct seq_file *s,
 
 	/*
 	 * Modifications on the list require holding locks on both
-	 * master and slave, so we are safe.
+	 * parent and child, so we are safe.
 	 * Also genpd->name is immutable.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
-		seq_printf(s, "%s", link->slave->name);
-		if (!list_is_last(&link->master_node, &genpd->master_links))
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		seq_printf(s, "%s", link->child->name);
+		if (!list_is_last(&link->parent_node, &genpd->parent_links))
 			seq_puts(s, ", ");
 	}
 
@@ -2860,7 +2860,7 @@ static int summary_show(struct seq_file *s, void *data)
 	struct generic_pm_domain *genpd;
 	int ret = 0;
 
-	seq_puts(s, "domain                          status          slaves\n");
+	seq_puts(s, "domain                          status          children\n");
 	seq_puts(s, "    /device                                             runtime status\n");
 	seq_puts(s, "----------------------------------------------------------------------\n");
 
@@ -2915,8 +2915,8 @@ static int sub_domains_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	list_for_each_entry(link, &genpd->master_links, master_node)
-		seq_printf(s, "%s\n", link->slave->name);
+	list_for_each_entry(link, &genpd->parent_links, parent_node)
+		seq_printf(s, "%s\n", link->child->name);
 
 	genpd_unlock(genpd);
 	return ret;
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index daa8c7689f7e..490ed7deb99a 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -135,8 +135,8 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 	 *
 	 * All subdomains have been powered off already at this point.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
-		struct generic_pm_domain *sd = link->slave;
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		struct generic_pm_domain *sd = link->child;
 		s64 sd_max_off_ns = sd->max_off_time_ns;
 
 		if (sd_max_off_ns < 0)
@@ -217,13 +217,13 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	}
 
 	/*
-	 * We have to invalidate the cached results for the masters, so
+	 * We have to invalidate the cached results for the parents, so
 	 * use the observation that default_power_down_ok() is not
-	 * going to be called for any master until this instance
+	 * going to be called for any parent until this instance
 	 * returns.
 	 */
-	list_for_each_entry(link, &genpd->slave_links, slave_node)
-		link->master->max_off_time_changed = true;
+	list_for_each_entry(link, &genpd->child_links, child_node)
+		link->parent->max_off_time_changed = true;
 
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = false;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9ec78ee53652..574a1fadb1e5 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -95,8 +95,8 @@ struct generic_pm_domain {
 	struct device dev;
 	struct dev_pm_domain domain;	/* PM domain operations */
 	struct list_head gpd_list_node;	/* Node in the global PM domains list */
-	struct list_head master_links;	/* Links with PM domain as a master */
-	struct list_head slave_links;	/* Links with PM domain as a slave */
+	struct list_head parent_links;	/* Links with PM domain as a parent */
+	struct list_head child_links;/* Links with PM domain as a child */
 	struct list_head dev_list;	/* List of devices */
 	struct dev_power_governor *gov;
 	struct work_struct power_off_work;
@@ -151,10 +151,10 @@ static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
 }
 
 struct gpd_link {
-	struct generic_pm_domain *master;
-	struct list_head master_node;
-	struct generic_pm_domain *slave;
-	struct list_head slave_node;
+	struct generic_pm_domain *parent;
+	struct list_head parent_node;
+	struct generic_pm_domain *child;
+	struct list_head child_node;
 
 	/* Sub-domain's per-master domain performance state */
 	unsigned int performance_state;
diff --git a/scripts/gdb/linux/genpd.py b/scripts/gdb/linux/genpd.py
index 6ca93bd2949e..39cd1abd8559 100644
--- a/scripts/gdb/linux/genpd.py
+++ b/scripts/gdb/linux/genpd.py
@@ -49,17 +49,17 @@ Output is similar to /sys/kernel/debug/pm_genpd/pm_genpd_summary'''
         else:
             status_string = 'off-{}'.format(genpd['state_idx'])
 
-        slave_names = []
+        child_names = []
         for link in list_for_each_entry(
-                genpd['master_links'],
+                genpd['parent_links'],
                 device_link_type.get_type().pointer(),
-                'master_node'):
-            slave_names.apend(link['slave']['name'])
+                'parent_node'):
+            child_names.append(link['child']['name'])
 
         gdb.write('%-30s  %-15s %s\n' % (
                 genpd['name'].string(),
                 status_string,
-                ', '.join(slave_names)))
+                ', '.join(child_names)))
 
         # Print devices in domain
         for pm_data in list_for_each_entry(genpd['dev_list'],
@@ -70,7 +70,7 @@ Output is similar to /sys/kernel/debug/pm_genpd/pm_genpd_summary'''
             gdb.write('    %-50s  %s\n' % (kobj_path, rtpm_status_str(dev)))
 
     def invoke(self, arg, from_tty):
-        gdb.write('domain                          status          slaves\n');
+        gdb.write('domain                          status          children\n');
         gdb.write('    /device                                             runtime status\n');
         gdb.write('----------------------------------------------------------------------\n');
         for genpd in list_for_each_entry(
-- 
cgit v1.2.3


From 2aa9c199cf8151c190c7e7ca3ddfcfbb2d85ac36 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Thu, 2 Jul 2020 19:35:38 -0700
Subject: KVM: Move x86's version of struct kvm_mmu_memory_cache to common code

Move x86's 'struct kvm_mmu_memory_cache' to common code in anticipation
of moving the entire x86 implementation code to common KVM and reusing
it for arm64 and MIPS.  Add a new architecture specific asm/kvm_types.h
to control the existence and parameters of the struct.  The new header
is needed to avoid a chicken-and-egg problem with asm/kvm_host.h as all
architectures define instances of the struct in their vCPU structs.

Add an asm-generic version of kvm_types.h to avoid having empty files on
PPC and s390 in the long term, and for arm64 and mips in the short term.

Suggested-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200703023545.8771-15-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/Kbuild    |  1 +
 arch/mips/include/asm/Kbuild     |  1 +
 arch/powerpc/include/asm/Kbuild  |  1 +
 arch/s390/include/asm/Kbuild     |  1 +
 arch/x86/include/asm/kvm_host.h  | 13 -------------
 arch/x86/include/asm/kvm_types.h |  7 +++++++
 include/asm-generic/kvm_types.h  |  5 +++++
 include/linux/kvm_types.h        | 19 +++++++++++++++++++
 8 files changed, 35 insertions(+), 13 deletions(-)
 create mode 100644 arch/x86/include/asm/kvm_types.h
 create mode 100644 include/asm-generic/kvm_types.h

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index ff9cbb631212..35a68155cd0e 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += early_ioremap.h
+generic-y += kvm_types.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 8643d313890e..397e6d24d2ab 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -5,6 +5,7 @@ generated-y += syscall_table_64_n32.h
 generated-y += syscall_table_64_n64.h
 generated-y += syscall_table_64_o32.h
 generic-y += export.h
+generic-y += kvm_types.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index dadbcf3a0b1e..2d444d09b553 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -4,6 +4,7 @@ generated-y += syscall_table_64.h
 generated-y += syscall_table_c32.h
 generated-y += syscall_table_spu.h
 generic-y += export.h
+generic-y += kvm_types.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += vtime.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 83f6e85de7bc..319efa0e6d02 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -6,5 +6,6 @@ generated-y += unistd_nr.h
 
 generic-y += asm-offsets.h
 generic-y += export.h
+generic-y += kvm_types.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9d41eb5a8453..5aaef036627f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -193,8 +193,6 @@ struct x86_exception;
 enum x86_intercept;
 enum x86_intercept_stage;
 
-#define KVM_NR_MEM_OBJS 40
-
 #define KVM_NR_DB_REGS	4
 
 #define DR6_BD		(1 << 13)
@@ -245,17 +243,6 @@ enum x86_intercept_stage;
 
 struct kvm_kernel_irq_routing_entry;
 
-/*
- * We don't want allocation failures within the mmu code, so we preallocate
- * enough memory for a single page fault in a cache.
- */
-struct kvm_mmu_memory_cache {
-	int nobjs;
-	gfp_t gfp_zero;
-	struct kmem_cache *kmem_cache;
-	void *objects[KVM_NR_MEM_OBJS];
-};
-
 /*
  * the pages used as guest page table on soft mmu are tracked by
  * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
diff --git a/arch/x86/include/asm/kvm_types.h b/arch/x86/include/asm/kvm_types.h
new file mode 100644
index 000000000000..08f1b57d3b62
--- /dev/null
+++ b/arch/x86/include/asm/kvm_types.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_KVM_TYPES_H
+#define _ASM_X86_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
+
+#endif /* _ASM_X86_KVM_TYPES_H */
diff --git a/include/asm-generic/kvm_types.h b/include/asm-generic/kvm_types.h
new file mode 100644
index 000000000000..2a82daf110f1
--- /dev/null
+++ b/include/asm-generic/kvm_types.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_KVM_TYPES_H
+#define _ASM_GENERIC_KVM_TYPES_H
+
+#endif
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 68e84cf42a3f..a7580f69dda0 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -20,6 +20,8 @@ enum kvm_mr_change;
 
 #include <linux/types.h>
 
+#include <asm/kvm_types.h>
+
 /*
  * Address types:
  *
@@ -58,4 +60,21 @@ struct gfn_to_pfn_cache {
 	bool dirty;
 };
 
+#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
+/*
+ * Memory caches are used to preallocate memory ahead of various MMU flows,
+ * e.g. page fault handlers.  Gracefully handling allocation failures deep in
+ * MMU flows is problematic, as is triggering reclaim, I/O, etc... while
+ * holding MMU locks.  Note, these caches act more like prefetch buffers than
+ * classical caches, i.e. objects are not returned to the cache on being freed.
+ */
+struct kvm_mmu_memory_cache {
+	int nobjs;
+	gfp_t gfp_zero;
+	struct kmem_cache *kmem_cache;
+	void *objects[KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE];
+};
+#endif
+
+
 #endif /* __KVM_TYPES_H__ */
-- 
cgit v1.2.3


From 6926f95accee3f8ceb5f69dbecd880687028ae70 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Thu, 2 Jul 2020 19:35:39 -0700
Subject: KVM: Move x86's MMU memory cache helpers to common KVM code

Move x86's memory cache helpers to common KVM code so that they can be
reused by arm64 and MIPS in future patches.

Suggested-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200703023545.8771-16-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 53 ----------------------------------------------
 include/linux/kvm_host.h |  7 ++++++
 virt/kvm/kvm_main.c      | 55 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 942b6a90cb17..fa506aaaf019 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1061,47 +1061,6 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 }
 
-static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
-					       gfp_t gfp_flags)
-{
-	gfp_flags |= mc->gfp_zero;
-
-	if (mc->kmem_cache)
-		return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
-	else
-		return (void *)__get_free_page(gfp_flags);
-}
-
-static int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
-{
-	void *obj;
-
-	if (mc->nobjs >= min)
-		return 0;
-	while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
-		obj = mmu_memory_cache_alloc_obj(mc, GFP_KERNEL_ACCOUNT);
-		if (!obj)
-			return mc->nobjs >= min ? 0 : -ENOMEM;
-		mc->objects[mc->nobjs++] = obj;
-	}
-	return 0;
-}
-
-static int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
-{
-	return mc->nobjs;
-}
-
-static void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
-{
-	while (mc->nobjs) {
-		if (mc->kmem_cache)
-			kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]);
-		else
-			free_page((unsigned long)mc->objects[--mc->nobjs]);
-	}
-}
-
 static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
 {
 	int r;
@@ -1133,18 +1092,6 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
 }
 
-static void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
-{
-	void *p;
-
-	if (WARN_ON(!mc->nobjs))
-		p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT);
-	else
-		p = mc->objects[--mc->nobjs];
-	BUG_ON(!p);
-	return p;
-}
-
 static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
 {
 	return kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 87140e79648b..989afcbe642f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -817,6 +817,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 
+#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
+int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc);
+void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
+void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
+#endif
+
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 				 struct kvm_vcpu *except,
 				 unsigned long *vcpu_bitmap, cpumask_var_t tmp);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b528a59b0a84..2c2c0254c2d8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -340,6 +340,61 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
+#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
+static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
+					       gfp_t gfp_flags)
+{
+	gfp_flags |= mc->gfp_zero;
+
+	if (mc->kmem_cache)
+		return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
+	else
+		return (void *)__get_free_page(gfp_flags);
+}
+
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+	void *obj;
+
+	if (mc->nobjs >= min)
+		return 0;
+	while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
+		obj = mmu_memory_cache_alloc_obj(mc, GFP_KERNEL_ACCOUNT);
+		if (!obj)
+			return mc->nobjs >= min ? 0 : -ENOMEM;
+		mc->objects[mc->nobjs++] = obj;
+	}
+	return 0;
+}
+
+int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
+{
+	return mc->nobjs;
+}
+
+void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
+{
+	while (mc->nobjs) {
+		if (mc->kmem_cache)
+			kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]);
+		else
+			free_page((unsigned long)mc->objects[--mc->nobjs]);
+	}
+}
+
+void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
+{
+	void *p;
+
+	if (WARN_ON(!mc->nobjs))
+		p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT);
+	else
+		p = mc->objects[--mc->nobjs];
+	BUG_ON(!p);
+	return p;
+}
+#endif
+
 static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	mutex_init(&vcpu->mutex);
-- 
cgit v1.2.3


From 60a883d119ab9ef63f830c85bbd2f0e2e2314f4f Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Thu, 9 Jul 2020 08:50:07 +0200
Subject: spi: use kthread_create_worker() helper

Use kthread_create_worker() helper to simplify the code. It uses
the kthread worker API the right way. It will eventually allow
to remove the FIXME in kthread_worker_fn() and add more consistency
checks in the future.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20200709065007.26896-1-m.szyprowski@samsung.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 26 ++++++++++++--------------
 include/linux/spi/spi.h |  6 ++----
 2 files changed, 14 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d4ba723a30da..1d7bba434225 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1368,7 +1368,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 
 	/* If another context is idling the device then defer */
 	if (ctlr->idling) {
-		kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+		kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 		spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 		return;
 	}
@@ -1382,7 +1382,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 
 		/* Only do teardown in the thread */
 		if (!in_kthread) {
-			kthread_queue_work(&ctlr->kworker,
+			kthread_queue_work(ctlr->kworker,
 					   &ctlr->pump_messages);
 			spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 			return;
@@ -1618,7 +1618,7 @@ static void spi_set_thread_rt(struct spi_controller *ctlr)
 
 	dev_info(&ctlr->dev,
 		"will run message pump with realtime priority\n");
-	sched_setscheduler(ctlr->kworker_task, SCHED_FIFO, &param);
+	sched_setscheduler(ctlr->kworker->task, SCHED_FIFO, &param);
 }
 
 static int spi_init_queue(struct spi_controller *ctlr)
@@ -1626,13 +1626,12 @@ static int spi_init_queue(struct spi_controller *ctlr)
 	ctlr->running = false;
 	ctlr->busy = false;
 
-	kthread_init_worker(&ctlr->kworker);
-	ctlr->kworker_task = kthread_run(kthread_worker_fn, &ctlr->kworker,
-					 "%s", dev_name(&ctlr->dev));
-	if (IS_ERR(ctlr->kworker_task)) {
-		dev_err(&ctlr->dev, "failed to create message pump task\n");
-		return PTR_ERR(ctlr->kworker_task);
+	ctlr->kworker = kthread_create_worker(0, dev_name(&ctlr->dev));
+	if (IS_ERR(ctlr->kworker)) {
+		dev_err(&ctlr->dev, "failed to create message pump kworker\n");
+		return PTR_ERR(ctlr->kworker);
 	}
+
 	kthread_init_work(&ctlr->pump_messages, spi_pump_messages);
 
 	/*
@@ -1716,7 +1715,7 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 	ctlr->cur_msg = NULL;
 	ctlr->cur_msg_prepared = false;
 	ctlr->fallback = false;
-	kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+	kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
 	trace_spi_message_done(mesg);
@@ -1742,7 +1741,7 @@ static int spi_start_queue(struct spi_controller *ctlr)
 	ctlr->cur_msg = NULL;
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
-	kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+	kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 
 	return 0;
 }
@@ -1798,8 +1797,7 @@ static int spi_destroy_queue(struct spi_controller *ctlr)
 		return ret;
 	}
 
-	kthread_flush_worker(&ctlr->kworker);
-	kthread_stop(ctlr->kworker_task);
+	kthread_destroy_worker(ctlr->kworker);
 
 	return 0;
 }
@@ -1822,7 +1820,7 @@ static int __spi_queued_transfer(struct spi_device *spi,
 
 	list_add_tail(&msg->queue, &ctlr->queue);
 	if (!ctlr->busy && need_pump)
-		kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+		kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 	return 0;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 0e67a9a3a1d3..5fcf5da13fdb 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -358,8 +358,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cleanup: frees controller-specific state
  * @can_dma: determine whether this controller supports DMA
  * @queued: whether this controller is providing an internal message queue
- * @kworker: thread struct for message pump
- * @kworker_task: pointer to task for message pump kworker thread
+ * @kworker: pointer to thread struct for message pump
  * @pump_messages: work struct for scheduling work to the message pump
  * @queue_lock: spinlock to syncronise access to message queue
  * @queue: message queue
@@ -593,8 +592,7 @@ struct spi_controller {
 	 * Over time we expect SPI drivers to be phased over to this API.
 	 */
 	bool				queued;
-	struct kthread_worker		kworker;
-	struct task_struct		*kworker_task;
+	struct kthread_worker		*kworker;
 	struct kthread_work		pump_messages;
 	spinlock_t			queue_lock;
 	struct list_head		queue;
-- 
cgit v1.2.3


From 2575b2f3ee711f4638e772e07a5146afcc704f30 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Wed, 8 Jul 2020 15:59:30 +0800
Subject: PCI: Move PCI_VENDOR_ID_REDHAT definition to pci_ids.h

Instead of duplicating the PCI_VENDOR_ID_REDHAT definition everywhere, move
it to include/linux/pci_ids.h.

[bhelgaas: also update MDPY_PCI_VENDOR_ID]
Link: https://lore.kernel.org/r/1594195170-11119-1-git-send-email-chenhc@lemote.com
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
---
 drivers/gpu/drm/qxl/qxl_dev.h           | 2 --
 drivers/net/ethernet/rocker/rocker_hw.h | 1 -
 include/linux/pci_ids.h                 | 2 ++
 samples/vfio-mdev/mdpy-defs.h           | 2 +-
 4 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/qxl/qxl_dev.h b/drivers/gpu/drm/qxl/qxl_dev.h
index a0ee41632d7e..a7bc31f6d565 100644
--- a/drivers/gpu/drm/qxl/qxl_dev.h
+++ b/drivers/gpu/drm/qxl/qxl_dev.h
@@ -131,8 +131,6 @@ enum SpiceCursorType {
 
 #pragma pack(push, 1)
 
-#define REDHAT_PCI_VENDOR_ID 0x1b36
-
 /* 0x100-0x11f reserved for spice, 0x1ff used for unstable work */
 #define QXL_DEVICE_ID_STABLE 0x0100
 
diff --git a/drivers/net/ethernet/rocker/rocker_hw.h b/drivers/net/ethernet/rocker/rocker_hw.h
index 59f1f8b690d2..62fd84cf3435 100644
--- a/drivers/net/ethernet/rocker/rocker_hw.h
+++ b/drivers/net/ethernet/rocker/rocker_hw.h
@@ -25,7 +25,6 @@ enum {
 
 #define ROCKER_FP_PORTS_MAX 62
 
-#define PCI_VENDOR_ID_REDHAT		0x1b36
 #define PCI_DEVICE_ID_REDHAT_ROCKER	0x0006
 
 #define ROCKER_PCI_BAR0_SIZE		0x2000
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0ad57693f392..5c709a1450b1 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2585,6 +2585,8 @@
 
 #define PCI_VENDOR_ID_ASMEDIA		0x1b21
 
+#define PCI_VENDOR_ID_REDHAT		0x1b36
+
 #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS	0x1c36
 
 #define PCI_VENDOR_ID_CIRCUITCO		0x1cc8
diff --git a/samples/vfio-mdev/mdpy-defs.h b/samples/vfio-mdev/mdpy-defs.h
index eb26421b6429..961c55ec3ffd 100644
--- a/samples/vfio-mdev/mdpy-defs.h
+++ b/samples/vfio-mdev/mdpy-defs.h
@@ -9,7 +9,7 @@
  */
 
 /* pci ids */
-#define MDPY_PCI_VENDOR_ID	0x1b36 /* redhat */
+#define MDPY_PCI_VENDOR_ID	PCI_VENDOR_ID_REDHAT
 #define MDPY_PCI_DEVICE_ID	0x000f
 #define MDPY_PCI_SUBVENDOR_ID	PCI_SUBVENDOR_ID_REDHAT_QUMRANET
 #define MDPY_PCI_SUBDEVICE_ID	PCI_SUBDEVICE_ID_QEMU
-- 
cgit v1.2.3


From 14b032b8f8fce03a546dcf365454bec8c4a58d7d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 9 Jul 2020 16:28:44 -0700
Subject: cgroup: Fix sock_cgroup_data on big-endian.

In order for no_refcnt and is_data to be the lowest order two
bits in the 'val' we have to pad out the bitfield of the u8.

Fixes: ad0f75e5f57c ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4f1cd0edc57d..fee0b5547cd0 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -792,6 +792,7 @@ struct sock_cgroup_data {
 		struct {
 			u8	is_data : 1;
 			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -801,6 +802,7 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
+			u8	unused : 6;
 			u8	no_refcnt : 1;
 			u8	is_data : 1;
 		} __packed;
-- 
cgit v1.2.3


From 88b3d5c90e9685be54dd5bc441970044020eca76 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 22 Jun 2020 09:03:31 +0300
Subject: net/mlx5e: Fix port buffers cell size value

Device unit for port buffers size, xoff_threshold and xon_threshold is
cells. Fix a bug in driver where cell unit size was hard-coded to
128 bytes. This hard-coded value is buggy, as it is wrong for some hardware
versions.

Driver to read cell size from SBCAM register and translate bytes to cell
units accordingly.

In order to fix the bug, this patch exposes SBCAM (Shared buffer
capabilities mask) layout and defines.

If SBCAM.cap_cell_size is valid, use it for all bytes to cells
calculations. If not valid, fallback to 128.

Cell size do not change on the fly per device. Instead of issuing SBCAM
access reg command every time such translation is needed, cache it in
mlx5e_dcbx as part of mlx5e_dcbnl_initialize(). Pass dcbx.port_buff_cell_sz
as a param to every function that needs bytes to cells translation.

While fixing the bug, move MLX5E_BUFFER_CELL_SHIFT macro to
en_dcbnl.c, as it is only used by that file.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h |  1 +
 .../ethernet/mellanox/mlx5/core/en/port_buffer.c   | 53 ++++++++++++----------
 .../ethernet/mellanox/mlx5/core/en/port_buffer.h   |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 19 ++++++++
 include/linux/mlx5/driver.h                        |  1 +
 include/linux/mlx5/mlx5_ifc.h                      | 28 ++++++++++++
 6 files changed, 78 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
index 7be6b2d36b60..9976de8b9047 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
@@ -29,6 +29,7 @@ struct mlx5e_dcbx {
 	bool                       manual_buffer;
 	u32                        cable_len;
 	u32                        xoff;
+	u16                        port_buff_cell_sz;
 };
 
 #define MLX5E_MAX_DSCP (64)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index ae99fac08b53..673f1c82d381 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -34,6 +34,7 @@
 int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			    struct mlx5e_port_buffer *port_buffer)
 {
+	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
 	u32 total_used = 0;
@@ -57,11 +58,11 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 		port_buffer->buffer[i].epsb =
 			MLX5_GET(bufferx_reg, buffer, epsb);
 		port_buffer->buffer[i].size =
-			MLX5_GET(bufferx_reg, buffer, size) << MLX5E_BUFFER_CELL_SHIFT;
+			MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz;
 		port_buffer->buffer[i].xon =
-			MLX5_GET(bufferx_reg, buffer, xon_threshold) << MLX5E_BUFFER_CELL_SHIFT;
+			MLX5_GET(bufferx_reg, buffer, xon_threshold) * port_buff_cell_sz;
 		port_buffer->buffer[i].xoff =
-			MLX5_GET(bufferx_reg, buffer, xoff_threshold) << MLX5E_BUFFER_CELL_SHIFT;
+			MLX5_GET(bufferx_reg, buffer, xoff_threshold) * port_buff_cell_sz;
 		total_used += port_buffer->buffer[i].size;
 
 		mlx5e_dbg(HW, priv, "buffer %d: size=%d, xon=%d, xoff=%d, epsb=%d, lossy=%d\n", i,
@@ -73,7 +74,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 	}
 
 	port_buffer->port_buffer_size =
-		MLX5_GET(pbmc_reg, out, port_buffer_size) << MLX5E_BUFFER_CELL_SHIFT;
+		MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz;
 	port_buffer->spare_buffer_size =
 		port_buffer->port_buffer_size - total_used;
 
@@ -88,9 +89,9 @@ out:
 static int port_set_buffer(struct mlx5e_priv *priv,
 			   struct mlx5e_port_buffer *port_buffer)
 {
+	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	void *buffer;
 	void *in;
 	int err;
 	int i;
@@ -104,16 +105,18 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		goto out;
 
 	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
-		buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
-
-		MLX5_SET(bufferx_reg, buffer, size,
-			 port_buffer->buffer[i].size >> MLX5E_BUFFER_CELL_SHIFT);
-		MLX5_SET(bufferx_reg, buffer, lossy,
-			 port_buffer->buffer[i].lossy);
-		MLX5_SET(bufferx_reg, buffer, xoff_threshold,
-			 port_buffer->buffer[i].xoff >> MLX5E_BUFFER_CELL_SHIFT);
-		MLX5_SET(bufferx_reg, buffer, xon_threshold,
-			 port_buffer->buffer[i].xon >> MLX5E_BUFFER_CELL_SHIFT);
+		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		u64 size = port_buffer->buffer[i].size;
+		u64 xoff = port_buffer->buffer[i].xoff;
+		u64 xon = port_buffer->buffer[i].xon;
+
+		do_div(size, port_buff_cell_sz);
+		do_div(xoff, port_buff_cell_sz);
+		do_div(xon, port_buff_cell_sz);
+		MLX5_SET(bufferx_reg, buffer, size, size);
+		MLX5_SET(bufferx_reg, buffer, lossy, port_buffer->buffer[i].lossy);
+		MLX5_SET(bufferx_reg, buffer, xoff_threshold, xoff);
+		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
 	err = mlx5e_port_set_pbmc(mdev, in);
@@ -143,7 +146,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int max_mtu)
+				 u32 xoff, unsigned int max_mtu, u16 port_buff_cell_sz)
 {
 	int i;
 
@@ -155,7 +158,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) {
+		    (xoff + max_mtu + port_buff_cell_sz)) {
 			pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n",
 			       i, port_buffer->buffer[i].size);
 			return -ENOMEM;
@@ -175,6 +178,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *	@pfc_en: <input> current pfc configuration
  *	@buffer: <input> current prio to buffer mapping
  *	@xoff:   <input> xoff value
+ *	@port_buff_cell_sz: <input> port buffer cell_size
  *	@port_buffer: <output> port receive buffer configuration
  *	@change: <output>
  *
@@ -189,7 +193,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *	sets change to true if buffer configuration was modified.
  */
 static int update_buffer_lossy(unsigned int max_mtu,
-			       u8 pfc_en, u8 *buffer, u32 xoff,
+			       u8 pfc_en, u8 *buffer, u32 xoff, u16 port_buff_cell_sz,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
 {
@@ -225,7 +229,7 @@ static int update_buffer_lossy(unsigned int max_mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 
@@ -262,6 +266,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 *buffer_size,
 				    u8 *prio2buffer)
 {
+	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5e_port_buffer port_buffer;
 	u32 xoff = calculate_xoff(priv, mtu);
 	bool update_prio2buffer = false;
@@ -282,7 +287,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 	}
@@ -292,7 +297,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, port_buff_cell_sz,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -304,7 +309,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, port_buff_cell_sz,
 					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -329,7 +334,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 	}
@@ -337,7 +342,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
index 34f55b81a0de..80af7a5ac604 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
@@ -36,7 +36,6 @@
 #include "port.h"
 
 #define MLX5E_MAX_BUFFER 8
-#define MLX5E_BUFFER_CELL_SHIFT 7
 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */
 
 #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index bc102d094bbd..d20243d6a032 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1217,6 +1217,24 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv)
 	return 0;
 }
 
+#define MLX5E_BUFFER_CELL_SHIFT 7
+
+static u16 mlx5e_query_port_buffers_cell_size(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 out[MLX5_ST_SZ_DW(sbcam_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(sbcam_reg)] = {};
+
+	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
+		return (1 << MLX5E_BUFFER_CELL_SHIFT);
+
+	if (mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
+				 MLX5_REG_SBCAM, 0, 0))
+		return (1 << MLX5E_BUFFER_CELL_SHIFT);
+
+	return MLX5_GET(sbcam_reg, out, cap_cell_size);
+}
+
 void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 {
 	struct mlx5e_dcbx *dcbx = &priv->dcbx;
@@ -1234,6 +1252,7 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 	if (priv->dcbx.mode == MLX5E_DCBX_PARAM_VER_OPER_HOST)
 		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;
 
+	priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv);
 	priv->dcbx.manual_buffer = false;
 	priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 13c0e4556eda..1e6ca716635a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -147,6 +147,7 @@ enum {
 	MLX5_REG_MCDA		 = 0x9063,
 	MLX5_REG_MCAM		 = 0x907f,
 	MLX5_REG_MIRC		 = 0x9162,
+	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ca1887dd0423..073b79eacc99 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9960,6 +9960,34 @@ struct mlx5_ifc_pptb_reg_bits {
 	u8         untagged_buff[0x4];
 };
 
+struct mlx5_ifc_sbcam_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         feature_group[0x8];
+	u8         reserved_at_10[0x8];
+	u8         access_reg_group[0x8];
+
+	u8         reserved_at_20[0x20];
+
+	u8         sb_access_reg_cap_mask[4][0x20];
+
+	u8         reserved_at_c0[0x80];
+
+	u8         sb_feature_cap_mask[4][0x20];
+
+	u8         reserved_at_1c0[0x40];
+
+	u8         cap_total_buffer_size[0x20];
+
+	u8         cap_cell_size[0x10];
+	u8         cap_max_pg_buffers[0x8];
+	u8         cap_num_pool_supported[0x8];
+
+	u8         reserved_at_240[0x8];
+	u8         cap_sbsr_stat_size[0x8];
+	u8         cap_max_tclass_data[0x8];
+	u8         cap_max_cpu_ingress_tclass_sb[0x8];
+};
+
 struct mlx5_ifc_pbmc_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-- 
cgit v1.2.3


From 8c080d3a974ad471d8324825851044284f1886c9 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Tue, 23 Jun 2020 13:36:42 +0800
Subject: kgdb: enable arch to support XML packet.

The XML packet could be supported by required architecture if the
architecture defines CONFIG_HAVE_ARCH_KGDB_QXFER_PKT and implement its own
kgdb_arch_handle_qxfer_pkt(). Except for the kgdb_arch_handle_qxfer_pkt(),
the architecture also needs to record the feature supported by gdb stub
into the kgdb_arch_gdb_stub_feature, and these features will be reported
to host gdb when gdb stub receives the qSupported packet.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/linux/kgdb.h   | 11 +++++++++++
 kernel/debug/gdbstub.c | 13 +++++++++++++
 lib/Kconfig.kgdb       |  5 +++++
 3 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 529116b0cabe..0e4e3a80d58c 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -176,6 +176,17 @@ kgdb_arch_handle_exception(int vector, int signo, int err_code,
 			   char *remcom_out_buffer,
 			   struct pt_regs *regs);
 
+/**
+ *	kgdb_arch_handle_qxfer_pkt - Handle architecture specific GDB XML
+ *				     packets.
+ *	@remcom_in_buffer: The buffer of the packet we have read.
+ *	@remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into.
+ */
+
+extern void
+kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
+			   char *remcom_out_buffer);
+
 /**
  *	kgdb_call_nmi_hook - Call kgdb_nmicallback() on the current CPU
  *	@ignored: This parameter is only here to match the prototype.
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 61774aec46b4..a790026e42d0 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -792,6 +792,19 @@ static void gdb_cmd_query(struct kgdb_state *ks)
 		}
 		break;
 #endif
+#ifdef CONFIG_HAVE_ARCH_KGDB_QXFER_PKT
+	case 'S':
+		if (!strncmp(remcom_in_buffer, "qSupported:", 11))
+			strcpy(remcom_out_buffer, kgdb_arch_gdb_stub_feature);
+		break;
+	case 'X':
+		if (!strncmp(remcom_in_buffer, "qXfer:", 6))
+			kgdb_arch_handle_qxfer_pkt(remcom_in_buffer,
+						   remcom_out_buffer);
+		break;
+#endif
+	default:
+		break;
 	}
 }
 
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index ffa7a76de086..256f2486f9bd 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -3,6 +3,11 @@
 config HAVE_ARCH_KGDB
 	bool
 
+# set if architecture has the its kgdb_arch_handle_qxfer_pkt
+# function to enable gdb stub to address XML packet sent from GDB.
+config HAVE_ARCH_KGDB_QXFER_PKT
+	bool
+
 menuconfig KGDB
 	bool "KGDB: kernel debugger"
 	depends on HAVE_ARCH_KGDB
-- 
cgit v1.2.3


From def0aa218e6d42231540329e6f5741fdec9e7da4 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Tue, 23 Jun 2020 13:37:25 +0800
Subject: kgdb: Move the extern declaration kgdb_has_hit_break() to generic
 kgdb.h

Currently, only riscv kgdb.c uses the kgdb_has_hit_break() to identify
the kgdb breakpoint. It causes other architectures will encounter the "no
previous prototype" warnings if the compile option has W=1. Moving the
declaration of extern kgdb_has_hit_break() from risc-v kgdb.h to generic
kgdb.h to avoid generating these warnings.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/kgdb.h | 1 -
 include/linux/kgdb.h          | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 8177a457caff..f45889bbb965 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,7 +19,6 @@
 
 #ifndef	__ASSEMBLY__
 
-extern int kgdb_has_hit_break(unsigned long addr);
 extern unsigned long kgdb_compiled_break;
 
 static inline void arch_kgdb_breakpoint(void)
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 0e4e3a80d58c..477b8b7c908f 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -325,6 +325,7 @@ extern int kgdb_hex2mem(char *buf, char *mem, int count);
 
 extern int kgdb_isremovedbreak(unsigned long addr);
 extern void kgdb_schedule_breakpoint(void);
+extern int kgdb_has_hit_break(unsigned long addr);
 
 extern int
 kgdb_handle_exception(int ex_vector, int signo, int err_code,
-- 
cgit v1.2.3


From ba1f2b2eaa2a529dba722507c55ff3d761d325dd Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 27 May 2020 15:50:29 +0200
Subject: x86/entry: Fix NMI vs IRQ state tracking

While the nmi_enter() users did
trace_hardirqs_{off_prepare,on_finish}() there was no matching
lockdep_hardirqs_*() calls to complete the picture.

Introduce idtentry_{enter,exit}_nmi() to enable proper IRQ state
tracking across the NMIs.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200623083721.216740948@infradead.org
---
 arch/x86/entry/common.c         | 42 +++++++++++++++++++++++++++++++++++++----
 arch/x86/include/asm/idtentry.h |  3 +++
 arch/x86/kernel/nmi.c           |  9 ++++-----
 arch/x86/kernel/traps.c         | 17 ++++++-----------
 include/linux/hardirq.h         | 28 ++++++++++++++++++---------
 5 files changed, 70 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 0521546022cb..63c607dd6c52 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -592,7 +592,7 @@ SYSCALL_DEFINE0(ni_syscall)
  * The return value must be fed into the state argument of
  * idtentry_exit().
  */
-idtentry_state_t noinstr idtentry_enter(struct pt_regs *regs)
+noinstr idtentry_state_t idtentry_enter(struct pt_regs *regs)
 {
 	idtentry_state_t ret = {
 		.exit_rcu = false,
@@ -687,7 +687,7 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
  * Counterpart to idtentry_enter(). The return value of the entry
  * function must be fed into the @state argument.
  */
-void noinstr idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
+noinstr void idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
 {
 	lockdep_assert_irqs_disabled();
 
@@ -731,7 +731,7 @@ void noinstr idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
  * Invokes enter_from_user_mode() to establish the proper context for
  * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
  */
-void noinstr idtentry_enter_user(struct pt_regs *regs)
+noinstr void idtentry_enter_user(struct pt_regs *regs)
 {
 	check_user_regs(regs);
 	enter_from_user_mode();
@@ -749,13 +749,47 @@ void noinstr idtentry_enter_user(struct pt_regs *regs)
  *
  * Counterpart to idtentry_enter_user().
  */
-void noinstr idtentry_exit_user(struct pt_regs *regs)
+noinstr void idtentry_exit_user(struct pt_regs *regs)
 {
 	lockdep_assert_irqs_disabled();
 
 	prepare_exit_to_usermode(regs);
 }
 
+noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
+{
+	bool irq_state = lockdep_hardirqs_enabled(current);
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	rcu_nmi_enter();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (restore) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	}
+	instrumentation_end();
+
+	rcu_nmi_exit();
+	lockdep_hardirq_exit();
+	if (restore)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
+
 #ifdef CONFIG_XEN_PV
 #ifndef CONFIG_PREEMPTION
 /*
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 7227225cf45d..2b0497486525 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -20,6 +20,9 @@ typedef struct idtentry_state {
 idtentry_state_t idtentry_enter(struct pt_regs *regs);
 void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
 
+bool idtentry_enter_nmi(struct pt_regs *regs);
+void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
+
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
  *		      No error code pushed by hardware
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index d7c5e44b26f7..4fc9954a9560 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -330,7 +330,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 	__this_cpu_write(last_nmi_rip, regs->ip);
 
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
 
 	handled = nmi_handle(NMI_LOCAL, regs);
 	__this_cpu_add(nmi_stats.normal, handled);
@@ -417,8 +416,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 		unknown_nmi_error(reason, regs);
 
 out:
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
 }
 
@@ -478,6 +475,8 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
+	bool irq_state;
+
 	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
@@ -491,14 +490,14 @@ nmi_restart:
 
 	this_cpu_write(nmi_dr7, local_db_save());
 
-	nmi_enter();
+	irq_state = idtentry_enter_nmi(regs);
 
 	inc_irq_stat(__nmi_count);
 
 	if (!ignore_nmis)
 		default_do_nmi(regs);
 
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 
 	local_db_restore(this_cpu_read(nmi_dr7));
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 4627f826fb57..cdd73829e637 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -403,7 +403,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 	}
 #endif
 
-	nmi_enter();
+	idtentry_enter_nmi(regs);
 	instrumentation_begin();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -649,15 +649,12 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 		instrumentation_end();
 		idtentry_exit_user(regs);
 	} else {
-		nmi_enter();
+		bool irq_state = idtentry_enter_nmi(regs);
 		instrumentation_begin();
-		trace_hardirqs_off_finish();
 		if (!do_int3(regs))
 			die("int3", regs, 0);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
 		instrumentation_end();
-		nmi_exit();
+		idtentry_exit_nmi(regs, irq_state);
 	}
 }
 
@@ -865,9 +862,8 @@ out:
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
-	nmi_enter();
+	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
 
 	/*
 	 * If something gets miswired and we end up here for a user mode
@@ -884,10 +880,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 
 	handle_debug(regs, dr6, false);
 
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
@@ -903,6 +897,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	instrumentation_begin();
 
 	handle_debug(regs, dr6, true);
+
 	instrumentation_end();
 	idtentry_exit_user(regs);
 }
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 03c9fece7d43..754f67ac4326 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -111,32 +111,42 @@ extern void rcu_nmi_exit(void);
 /*
  * nmi_enter() can nest up to 15 times; see NMI_BITS.
  */
-#define nmi_enter()						\
+#define __nmi_enter()						\
 	do {							\
+		lockdep_off();					\
 		arch_nmi_enter();				\
 		printk_nmi_enter();				\
-		lockdep_off();					\
 		BUG_ON(in_nmi() == NMI_MASK);			\
 		__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
-		rcu_nmi_enter();				\
+	} while (0)
+
+#define nmi_enter()						\
+	do {							\
+		__nmi_enter();					\
 		lockdep_hardirq_enter();			\
+		rcu_nmi_enter();				\
 		instrumentation_begin();			\
 		ftrace_nmi_enter();				\
 		instrumentation_end();				\
 	} while (0)
 
+#define __nmi_exit()						\
+	do {							\
+		BUG_ON(!in_nmi());				\
+		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		printk_nmi_exit();				\
+		arch_nmi_exit();				\
+		lockdep_on();					\
+	} while (0)
+
 #define nmi_exit()						\
 	do {							\
 		instrumentation_begin();			\
 		ftrace_nmi_exit();				\
 		instrumentation_end();				\
-		lockdep_hardirq_exit();				\
 		rcu_nmi_exit();					\
-		BUG_ON(!in_nmi());				\
-		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
-		lockdep_on();					\
-		printk_nmi_exit();				\
-		arch_nmi_exit();				\
+		lockdep_hardirq_exit();				\
+		__nmi_exit();					\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
-- 
cgit v1.2.3


From a21ee6055c30ce68c4e201c6496f0ed2a1936230 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 25 May 2020 12:22:41 +0200
Subject: lockdep: Change hardirq{s_enabled,_context} to per-cpu variables

Currently all IRQ-tracking state is in task_struct, this means that
task_struct needs to be defined before we use it.

Especially for lockdep_assert_irq*() this can lead to header-hell.

Move the hardirq state into per-cpu variables to avoid the task_struct
dependency.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200623083721.512673481@infradead.org
---
 include/linux/irqflags.h | 19 ++++++++++++-------
 include/linux/lockdep.h  | 34 ++++++++++++++++++----------------
 include/linux/sched.h    |  2 --
 kernel/fork.c            |  4 +---
 kernel/locking/lockdep.c | 30 +++++++++++++++---------------
 kernel/softirq.c         |  6 ++++++
 6 files changed, 52 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 6384d2813ded..255444fe4609 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -14,6 +14,7 @@
 
 #include <linux/typecheck.h>
 #include <asm/irqflags.h>
+#include <asm/percpu.h>
 
 /* Currently lockdep_softirqs_on/off is used only by lockdep */
 #ifdef CONFIG_PROVE_LOCKING
@@ -31,18 +32,22 @@
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
+
+DECLARE_PER_CPU(int, hardirqs_enabled);
+DECLARE_PER_CPU(int, hardirq_context);
+
   extern void trace_hardirqs_on_prepare(void);
   extern void trace_hardirqs_off_finish(void);
   extern void trace_hardirqs_on(void);
   extern void trace_hardirqs_off(void);
-# define lockdep_hardirq_context(p)	((p)->hardirq_context)
+# define lockdep_hardirq_context(p)	(this_cpu_read(hardirq_context))
 # define lockdep_softirq_context(p)	((p)->softirq_context)
-# define lockdep_hardirqs_enabled(p)	((p)->hardirqs_enabled)
+# define lockdep_hardirqs_enabled(p)	(this_cpu_read(hardirqs_enabled))
 # define lockdep_softirqs_enabled(p)	((p)->softirqs_enabled)
-# define lockdep_hardirq_enter()		\
-do {						\
-	if (!current->hardirq_context++)	\
-		current->hardirq_threaded = 0;	\
+# define lockdep_hardirq_enter()			\
+do {							\
+	if (this_cpu_inc_return(hardirq_context) == 1)	\
+		current->hardirq_threaded = 0;		\
 } while (0)
 # define lockdep_hardirq_threaded()		\
 do {						\
@@ -50,7 +55,7 @@ do {						\
 } while (0)
 # define lockdep_hardirq_exit()			\
 do {						\
-	current->hardirq_context--;		\
+	this_cpu_dec(hardirq_context);		\
 } while (0)
 # define lockdep_softirq_enter()		\
 do {						\
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 3b73cf84f77d..be6cb17a8879 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -11,6 +11,7 @@
 #define __LINUX_LOCKDEP_H
 
 #include <linux/lockdep_types.h>
+#include <asm/percpu.h>
 
 struct task_struct;
 
@@ -529,28 +530,29 @@ do {									\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
 
-#define lockdep_assert_irqs_enabled()	do {				\
-		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
-			  !current->hardirqs_enabled,			\
-			  "IRQs not enabled as expected\n");		\
-	} while (0)
+DECLARE_PER_CPU(int, hardirqs_enabled);
+DECLARE_PER_CPU(int, hardirq_context);
 
-#define lockdep_assert_irqs_disabled()	do {				\
-		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
-			  current->hardirqs_enabled,			\
-			  "IRQs not disabled as expected\n");		\
-	} while (0)
+#define lockdep_assert_irqs_enabled()					\
+do {									\
+	WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled));	\
+} while (0)
 
-#define lockdep_assert_in_irq() do {					\
-		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
-			  !current->hardirq_context,			\
-			  "Not in hardirq as expected\n");		\
-	} while (0)
+#define lockdep_assert_irqs_disabled()					\
+do {									\
+	WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled));	\
+} while (0)
+
+#define lockdep_assert_in_irq()						\
+do {									\
+	WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context));	\
+} while (0)
 
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
 # define might_lock_nested(lock, subclass) do { } while (0)
+
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
 # define lockdep_assert_in_irq() do { } while (0)
@@ -560,7 +562,7 @@ do {									\
 
 # define lockdep_assert_RT_in_threaded_ctx() do {			\
 		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
-			  current->hardirq_context &&			\
+			  lockdep_hardirq_context(current) &&		\
 			  !(current->hardirq_threaded || current->irq_config),	\
 			  "Not in threaded context on PREEMPT_RT as expected\n");	\
 } while (0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 692e327d7455..3903a9500926 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -990,8 +990,6 @@ struct task_struct {
 	unsigned long			hardirq_disable_ip;
 	unsigned int			hardirq_enable_event;
 	unsigned int			hardirq_disable_event;
-	int				hardirqs_enabled;
-	int				hardirq_context;
 	u64				hardirq_chain_key;
 	unsigned long			softirq_disable_ip;
 	unsigned long			softirq_enable_ip;
diff --git a/kernel/fork.c b/kernel/fork.c
index efc5493203ae..70d9d0a4de2a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1954,8 +1954,8 @@ static __latent_entropy struct task_struct *copy_process(
 
 	rt_mutex_init_task(p);
 
+	lockdep_assert_irqs_enabled();
 #ifdef CONFIG_PROVE_LOCKING
-	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
 	retval = -EAGAIN;
@@ -2036,7 +2036,6 @@ static __latent_entropy struct task_struct *copy_process(
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
-	p->hardirqs_enabled = 0;
 	p->hardirq_enable_ip = 0;
 	p->hardirq_enable_event = 0;
 	p->hardirq_disable_ip = _THIS_IP_;
@@ -2046,7 +2045,6 @@ static __latent_entropy struct task_struct *copy_process(
 	p->softirq_enable_event = 0;
 	p->softirq_disable_ip = 0;
 	p->softirq_disable_event = 0;
-	p->hardirq_context = 0;
 	p->softirq_context = 0;
 #endif
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index d595623c4b34..ab4ffbe0e9e9 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2062,9 +2062,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	pr_warn("-----------------------------------------------------\n");
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, task_pid_nr(curr),
-		curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT,
 		curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT,
-		curr->hardirqs_enabled,
+		lockdep_hardirqs_enabled(curr),
 		curr->softirqs_enabled);
 	print_lock(next);
 
@@ -3658,7 +3658,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
-	if (unlikely(current->hardirqs_enabled)) {
+	if (unlikely(lockdep_hardirqs_enabled(current))) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3686,7 +3686,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	 * Can't allow enabling interrupts while in an interrupt handler,
 	 * that's general bad form and such. Recursion, limited stack etc..
 	 */
-	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
+	if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context(current)))
 		return;
 
 	current->hardirq_chain_key = current->curr_chain_key;
@@ -3724,7 +3724,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
-	if (curr->hardirqs_enabled) {
+	if (lockdep_hardirqs_enabled(curr)) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3751,7 +3751,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 
 skip_checks:
 	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
+	this_cpu_write(hardirqs_enabled, 1);
 	curr->hardirq_enable_ip = ip;
 	curr->hardirq_enable_event = ++curr->irq_events;
 	debug_atomic_inc(hardirqs_on_events);
@@ -3783,11 +3783,11 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->hardirqs_enabled) {
+	if (lockdep_hardirqs_enabled(curr)) {
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->hardirqs_enabled = 0;
+		this_cpu_write(hardirqs_enabled, 0);
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
@@ -3832,7 +3832,7 @@ void lockdep_softirqs_on(unsigned long ip)
 	 * usage bit for all held locks, if hardirqs are
 	 * enabled too:
 	 */
-	if (curr->hardirqs_enabled)
+	if (lockdep_hardirqs_enabled(curr))
 		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 	lockdep_recursion_finish();
 }
@@ -3881,7 +3881,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 	 */
 	if (!hlock->trylock) {
 		if (hlock->read) {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context(curr))
 				if (!mark_lock(curr, hlock,
 						LOCK_USED_IN_HARDIRQ_READ))
 					return 0;
@@ -3890,7 +3890,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 						LOCK_USED_IN_SOFTIRQ_READ))
 					return 0;
 		} else {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context(curr))
 				if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ))
 					return 0;
 			if (curr->softirq_context)
@@ -3928,7 +3928,7 @@ lock_used:
 
 static inline unsigned int task_irq_context(struct task_struct *task)
 {
-	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context +
+	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context(task) +
 	       LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context;
 }
 
@@ -4021,7 +4021,7 @@ static inline short task_wait_context(struct task_struct *curr)
 	 * Set appropriate wait type for the context; for IRQs we have to take
 	 * into account force_irqthread as that is implied by PREEMPT_RT.
 	 */
-	if (curr->hardirq_context) {
+	if (lockdep_hardirq_context(curr)) {
 		/*
 		 * Check if force_irqthreads will run us threaded.
 		 */
@@ -4864,11 +4864,11 @@ static void check_flags(unsigned long flags)
 		return;
 
 	if (irqs_disabled_flags(flags)) {
-		if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled(current))) {
 			printk("possible reason: unannotated irqs-off.\n");
 		}
 	} else {
-		if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled(current))) {
 			printk("possible reason: unannotated irqs-on.\n");
 		}
 	}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c4201b7f42b1..342c53feaa7a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -107,6 +107,12 @@ static bool ksoftirqd_running(unsigned long pending)
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
+
+DEFINE_PER_CPU(int, hardirqs_enabled);
+DEFINE_PER_CPU(int, hardirq_context);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
+
 void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
-- 
cgit v1.2.3


From f9ad4a5f3f20bee022b1bdde94e5ece6dc0b0edc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 27 May 2020 13:03:26 +0200
Subject: lockdep: Remove lockdep_hardirq{s_enabled,_context}() argument

Now that the macros use per-cpu data, we no longer need the argument.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200623083721.571835311@infradead.org
---
 arch/x86/entry/common.c        |  2 +-
 include/linux/irqflags.h       |  8 ++++----
 include/linux/lockdep.h        |  2 +-
 kernel/locking/lockdep.c       | 30 +++++++++++++++---------------
 kernel/softirq.c               |  2 +-
 tools/include/linux/irqflags.h |  4 ++--
 6 files changed, 24 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 63c607dd6c52..4ea640363f5d 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -758,7 +758,7 @@ noinstr void idtentry_exit_user(struct pt_regs *regs)
 
 noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
 {
-	bool irq_state = lockdep_hardirqs_enabled(current);
+	bool irq_state = lockdep_hardirqs_enabled();
 
 	__nmi_enter();
 	lockdep_hardirqs_off(CALLER_ADDR0);
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 255444fe4609..5811ee8a5cd8 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -40,9 +40,9 @@ DECLARE_PER_CPU(int, hardirq_context);
   extern void trace_hardirqs_off_finish(void);
   extern void trace_hardirqs_on(void);
   extern void trace_hardirqs_off(void);
-# define lockdep_hardirq_context(p)	(this_cpu_read(hardirq_context))
+# define lockdep_hardirq_context()	(this_cpu_read(hardirq_context))
 # define lockdep_softirq_context(p)	((p)->softirq_context)
-# define lockdep_hardirqs_enabled(p)	(this_cpu_read(hardirqs_enabled))
+# define lockdep_hardirqs_enabled()	(this_cpu_read(hardirqs_enabled))
 # define lockdep_softirqs_enabled(p)	((p)->softirqs_enabled)
 # define lockdep_hardirq_enter()			\
 do {							\
@@ -109,9 +109,9 @@ do {						\
 # define trace_hardirqs_off_finish()		do { } while (0)
 # define trace_hardirqs_on()		do { } while (0)
 # define trace_hardirqs_off()		do { } while (0)
-# define lockdep_hardirq_context(p)	0
+# define lockdep_hardirq_context()	0
 # define lockdep_softirq_context(p)	0
-# define lockdep_hardirqs_enabled(p)	0
+# define lockdep_hardirqs_enabled()	0
 # define lockdep_softirqs_enabled(p)	0
 # define lockdep_hardirq_enter()	do { } while (0)
 # define lockdep_hardirq_threaded()	do { } while (0)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index be6cb17a8879..fd04b9e96091 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -562,7 +562,7 @@ do {									\
 
 # define lockdep_assert_RT_in_threaded_ctx() do {			\
 		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
-			  lockdep_hardirq_context(current) &&		\
+			  lockdep_hardirq_context() &&			\
 			  !(current->hardirq_threaded || current->irq_config),	\
 			  "Not in threaded context on PREEMPT_RT as expected\n");	\
 } while (0)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ab4ffbe0e9e9..c9ea05edce25 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2062,9 +2062,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	pr_warn("-----------------------------------------------------\n");
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, task_pid_nr(curr),
-		lockdep_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
 		curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT,
-		lockdep_hardirqs_enabled(curr),
+		lockdep_hardirqs_enabled(),
 		curr->softirqs_enabled);
 	print_lock(next);
 
@@ -3331,9 +3331,9 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n",
 		curr->comm, task_pid_nr(curr),
-		lockdep_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
 		lockdep_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT,
-		lockdep_hardirqs_enabled(curr),
+		lockdep_hardirqs_enabled(),
 		lockdep_softirqs_enabled(curr));
 	print_lock(this);
 
@@ -3658,7 +3658,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
-	if (unlikely(lockdep_hardirqs_enabled(current))) {
+	if (unlikely(lockdep_hardirqs_enabled())) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3686,7 +3686,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	 * Can't allow enabling interrupts while in an interrupt handler,
 	 * that's general bad form and such. Recursion, limited stack etc..
 	 */
-	if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context(current)))
+	if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context()))
 		return;
 
 	current->hardirq_chain_key = current->curr_chain_key;
@@ -3724,7 +3724,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
-	if (lockdep_hardirqs_enabled(curr)) {
+	if (lockdep_hardirqs_enabled()) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3783,7 +3783,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (lockdep_hardirqs_enabled(curr)) {
+	if (lockdep_hardirqs_enabled()) {
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
@@ -3832,7 +3832,7 @@ void lockdep_softirqs_on(unsigned long ip)
 	 * usage bit for all held locks, if hardirqs are
 	 * enabled too:
 	 */
-	if (lockdep_hardirqs_enabled(curr))
+	if (lockdep_hardirqs_enabled())
 		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 	lockdep_recursion_finish();
 }
@@ -3881,7 +3881,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 	 */
 	if (!hlock->trylock) {
 		if (hlock->read) {
-			if (lockdep_hardirq_context(curr))
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock,
 						LOCK_USED_IN_HARDIRQ_READ))
 					return 0;
@@ -3890,7 +3890,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 						LOCK_USED_IN_SOFTIRQ_READ))
 					return 0;
 		} else {
-			if (lockdep_hardirq_context(curr))
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ))
 					return 0;
 			if (curr->softirq_context)
@@ -3928,7 +3928,7 @@ lock_used:
 
 static inline unsigned int task_irq_context(struct task_struct *task)
 {
-	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context(task) +
+	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context() +
 	       LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context;
 }
 
@@ -4021,7 +4021,7 @@ static inline short task_wait_context(struct task_struct *curr)
 	 * Set appropriate wait type for the context; for IRQs we have to take
 	 * into account force_irqthread as that is implied by PREEMPT_RT.
 	 */
-	if (lockdep_hardirq_context(curr)) {
+	if (lockdep_hardirq_context()) {
 		/*
 		 * Check if force_irqthreads will run us threaded.
 		 */
@@ -4864,11 +4864,11 @@ static void check_flags(unsigned long flags)
 		return;
 
 	if (irqs_disabled_flags(flags)) {
-		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled(current))) {
+		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-off.\n");
 		}
 	} else {
-		if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled(current))) {
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-on.\n");
 		}
 	}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 342c53feaa7a..5e9aaa648a74 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -230,7 +230,7 @@ static inline bool lockdep_softirq_start(void)
 {
 	bool in_hardirq = false;
 
-	if (lockdep_hardirq_context(current)) {
+	if (lockdep_hardirq_context()) {
 		in_hardirq = true;
 		lockdep_hardirq_exit();
 	}
diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h
index 67e01bbadbfe..501262aee8ff 100644
--- a/tools/include/linux/irqflags.h
+++ b/tools/include/linux/irqflags.h
@@ -2,9 +2,9 @@
 #ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
 #define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
 
-# define lockdep_hardirq_context(p)	0
+# define lockdep_hardirq_context()	0
 # define lockdep_softirq_context(p)	0
-# define lockdep_hardirqs_enabled(p)	0
+# define lockdep_hardirqs_enabled()	0
 # define lockdep_softirqs_enabled(p)	0
 # define lockdep_hardirq_enter()	do { } while (0)
 # define lockdep_hardirq_exit()		do { } while (0)
-- 
cgit v1.2.3


From 6348dd291e3653534a9e28e6917569bc9967b35b Mon Sep 17 00:00:00 2001
From: Charan Teja Kalla <charante@codeaurora.org>
Date: Fri, 19 Jun 2020 17:27:19 +0530
Subject: dmabuf: use spinlock to access dmabuf->name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There exists a sleep-while-atomic bug while accessing the dmabuf->name
under mutex in the dmabuffs_dname(). This is caused from the SELinux
permissions checks on a process where it tries to validate the inherited
files from fork() by traversing them through iterate_fd() (which
traverse files under spin_lock) and call
match_file(security/selinux/hooks.c) where the permission checks happen.
This audit information is logged using dump_common_audit_data() where it
calls d_path() to get the file path name. If the file check happen on
the dmabuf's fd, then it ends up in ->dmabuffs_dname() and use mutex to
access dmabuf->name. The flow will be like below:
flush_unauthorized_files()
  iterate_fd()
    spin_lock() --> Start of the atomic section.
      match_file()
        file_has_perm()
          avc_has_perm()
            avc_audit()
              slow_avc_audit()
	        common_lsm_audit()
		  dump_common_audit_data()
		    audit_log_d_path()
		      d_path()
                        dmabuffs_dname()
                          mutex_lock()--> Sleep while atomic.

Call trace captured (on 4.19 kernels) is below:
___might_sleep+0x204/0x208
__might_sleep+0x50/0x88
__mutex_lock_common+0x5c/0x1068
__mutex_lock_common+0x5c/0x1068
mutex_lock_nested+0x40/0x50
dmabuffs_dname+0xa0/0x170
d_path+0x84/0x290
audit_log_d_path+0x74/0x130
common_lsm_audit+0x334/0x6e8
slow_avc_audit+0xb8/0xf8
avc_has_perm+0x154/0x218
file_has_perm+0x70/0x180
match_file+0x60/0x78
iterate_fd+0x128/0x168
selinux_bprm_committing_creds+0x178/0x248
security_bprm_committing_creds+0x30/0x48
install_exec_creds+0x1c/0x68
load_elf_binary+0x3a4/0x14e0
search_binary_handler+0xb0/0x1e0

So, use spinlock to access dmabuf->name to avoid sleep-while-atomic.

Cc: <stable@vger.kernel.org> [5.3+]
Signed-off-by: Charan Teja Kalla <charante@codeaurora.org>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
 [sumits: added comment to spinlock_t definition to avoid warning]
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/a83e7f0d-4e54-9848-4b58-e1acdbe06735@codeaurora.org
---
 drivers/dma-buf/dma-buf.c | 11 +++++++----
 include/linux/dma-buf.h   |  1 +
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 412629601ad3..1ca609f66fdf 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -45,10 +45,10 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen)
 	size_t ret = 0;
 
 	dmabuf = dentry->d_fsdata;
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 
 	return dynamic_dname(dentry, buffer, buflen, "/%s:%s",
 			     dentry->d_name.name, ret > 0 ? name : "");
@@ -338,8 +338,10 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf)
 		kfree(name);
 		goto out_unlock;
 	}
+	spin_lock(&dmabuf->name_lock);
 	kfree(dmabuf->name);
 	dmabuf->name = name;
+	spin_unlock(&dmabuf->name_lock);
 
 out_unlock:
 	dma_resv_unlock(dmabuf->resv);
@@ -402,10 +404,10 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file)
 	/* Don't count the temporary reference taken inside procfs seq_show */
 	seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1);
 	seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name);
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		seq_printf(m, "name:\t%s\n", dmabuf->name);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 }
 
 static const struct file_operations dma_buf_fops = {
@@ -542,6 +544,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	dmabuf->size = exp_info->size;
 	dmabuf->exp_name = exp_info->exp_name;
 	dmabuf->owner = exp_info->owner;
+	spin_lock_init(&dmabuf->name_lock);
 	init_waitqueue_head(&dmabuf->poll);
 	dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll;
 	dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0;
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index ab0c156abee6..a2ca294eaebe 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -311,6 +311,7 @@ struct dma_buf {
 	void *vmap_ptr;
 	const char *exp_name;
 	const char *name;
+	spinlock_t name_lock; /* spinlock to protect name access */
 	struct module *owner;
 	struct list_head list_node;
 	void *priv;
-- 
cgit v1.2.3


From 5bc117a27fd044bd5ddeb8ab22c58976bf01b50d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 9 Jul 2020 14:08:57 +0200
Subject: virt: vbox: Log unknown ioctl requests as error

Every now and then upstream adds new ioctls without notifying us,
log unknown ioctl requests as an error to catch these.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200709120858.63928-8-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/vboxguest_core.c  | 2 +-
 drivers/virt/vboxguest/vboxguest_utils.c | 1 +
 include/linux/vbox_utils.h               | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index ffd76b949276..c5dfcd42fd07 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -1739,7 +1739,7 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 		return vbg_ioctl_log(data);
 	}
 
-	vbg_debug("VGDrvCommonIoCtl: Unknown req %#08x\n", req);
+	vbg_err_ratelimited("Userspace made an unknown ioctl req %#08x\n", req);
 	return -ENOTTY;
 }
 
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 7396187ee32a..ea05af41ec69 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -59,6 +59,7 @@ EXPORT_SYMBOL(name)
 VBG_LOG(vbg_info, pr_info);
 VBG_LOG(vbg_warn, pr_warn);
 VBG_LOG(vbg_err, pr_err);
+VBG_LOG(vbg_err_ratelimited, pr_err_ratelimited);
 #if defined(DEBUG) && !defined(CONFIG_DYNAMIC_DEBUG)
 VBG_LOG(vbg_debug, pr_debug);
 #endif
diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h
index ff56c443180c..db8a7d118093 100644
--- a/include/linux/vbox_utils.h
+++ b/include/linux/vbox_utils.h
@@ -16,6 +16,7 @@ struct vbg_dev;
 __printf(1, 2) void vbg_info(const char *fmt, ...);
 __printf(1, 2) void vbg_warn(const char *fmt, ...);
 __printf(1, 2) void vbg_err(const char *fmt, ...);
+__printf(1, 2) void vbg_err_ratelimited(const char *fmt, ...);
 
 /* Only use backdoor logging for non-dynamic debug builds */
 #if defined(DEBUG) && !defined(CONFIG_DYNAMIC_DEBUG)
-- 
cgit v1.2.3


From a9f91cebbeb8ea1355e852cce6d40efbcddbfe2b Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Wed, 8 Jul 2020 13:57:09 +0100
Subject: misc: vmw_vmci_defs: Mark 'struct vmci_handle VMCI_ANON_SRC_HANDLE'
 as __maybe_unused
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vmw_vmci_defs.h is included by multiple source files.  Some of which
do not make use of 'struct vmci_handle VMCI_ANON_SRC_HANDLE' rendering
it unused.  Ensure the compiler knows that this is in fact intentional
by marking it as __maybe_unused.  This fixes the following W=1 warnings:

 In file included from drivers/misc/vmw_vmci/vmci_context.c:8:
 include/linux/vmw_vmci_defs.h:162:33: warning: ‘VMCI_ANON_SRC_HANDLE’ defined but not used [-Wunused-const-variable=]
 162 | static const struct vmci_handle VMCI_ANON_SRC_HANDLE = {
 | ^~~~~~~~~~~~~~~~~~~~
 In file included from drivers/misc/vmw_vmci/vmci_datagram.c:8:
 include/linux/vmw_vmci_defs.h:162:33: warning: ‘VMCI_ANON_SRC_HANDLE’ defined but not used [-Wunused-const-variable=]
 162 | static const struct vmci_handle VMCI_ANON_SRC_HANDLE = {
 | ^~~~~~~~~~~~~~~~~~~~

Cc: George Zhang <georgezhang@vmware.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200708125711.3443569-2-lee.jones@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/vmw_vmci_defs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h
index fefb5292403b..be0afe6f379b 100644
--- a/include/linux/vmw_vmci_defs.h
+++ b/include/linux/vmw_vmci_defs.h
@@ -159,7 +159,7 @@ static inline bool vmci_handle_is_invalid(struct vmci_handle h)
  */
 #define VMCI_ANON_SRC_CONTEXT_ID   VMCI_INVALID_ID
 #define VMCI_ANON_SRC_RESOURCE_ID  VMCI_INVALID_ID
-static const struct vmci_handle VMCI_ANON_SRC_HANDLE = {
+static const struct vmci_handle __maybe_unused VMCI_ANON_SRC_HANDLE = {
 	.context = VMCI_ANON_SRC_CONTEXT_ID,
 	.resource = VMCI_ANON_SRC_RESOURCE_ID
 };
-- 
cgit v1.2.3


From 849a9366cba92cb5dc9dc1161ef49416a290aae9 Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Mon, 6 Jul 2020 15:02:59 +0800
Subject: misc: rtsx: Add support new chip rts5228 mmc: rtsx: Add support
 MMC_CAP2_NO_MMC

In order to support new chip rts5228, the definitions of some internal
registers and workflow have to be modified.
Added rts5228.c rts5228.h for independent functions of the new chip rts5228

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20200706070259.32565-1-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/Makefile   |   2 +-
 drivers/misc/cardreader/rts5228.c  | 740 +++++++++++++++++++++++++++++++++++++
 drivers/misc/cardreader/rts5228.h  | 168 +++++++++
 drivers/misc/cardreader/rtsx_pcr.c |  89 +++--
 drivers/misc/cardreader/rtsx_pcr.h |   5 +
 drivers/mmc/host/rtsx_pci_sdmmc.c  |   2 +
 include/linux/rtsx_pci.h           |  11 +
 7 files changed, 985 insertions(+), 32 deletions(-)
 create mode 100644 drivers/misc/cardreader/rts5228.c
 create mode 100644 drivers/misc/cardreader/rts5228.h

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile
index 1f56267ed2f4..895128475d83 100644
--- a/drivers/misc/cardreader/Makefile
+++ b/drivers/misc/cardreader/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MISC_ALCOR_PCI)	+= alcor_pci.o
 obj-$(CONFIG_MISC_RTSX_PCI)	+= rtsx_pci.o
-rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o
+rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o
 obj-$(CONFIG_MISC_RTSX_USB)	+= rtsx_usb.o
diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
new file mode 100644
index 000000000000..99aff7cd0a93
--- /dev/null
+++ b/drivers/misc/cardreader/rts5228.c
@@ -0,0 +1,740 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky WU <ricky_wu@realtek.com>
+ *   Rui FENG <rui_feng@realsil.com.cn>
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/rtsx_pci.h>
+
+#include "rts5228.h"
+#include "rtsx_pcr.h"
+
+static u8 rts5228_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & IC_VERSION_MASK;
+}
+
+static void rts5228_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 driving_3v3[4][3] = {
+		{0x13, 0x13, 0x13},
+		{0x96, 0x96, 0x96},
+		{0x7F, 0x7F, 0x7F},
+		{0x96, 0x96, 0x96},
+	};
+	u8 driving_1v8[4][3] = {
+		{0x99, 0x99, 0x99},
+		{0xB5, 0xB5, 0xB5},
+		{0xE6, 0x7E, 0xFE},
+		{0x6B, 0x6B, 0x6B},
+	};
+	u8 (*driving)[3], drive_sel;
+
+	if (voltage == OUTPUT_3V3) {
+		driving = driving_3v3;
+		drive_sel = pcr->sd30_drive_sel_3v3;
+	} else {
+		driving = driving_1v8;
+		drive_sel = pcr->sd30_drive_sel_1v8;
+	}
+
+	rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL,
+			 0xFF, driving[drive_sel][0]);
+
+	rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL,
+			 0xFF, driving[drive_sel][1]);
+
+	rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL,
+			 0xFF, driving[drive_sel][2]);
+}
+
+static void rtsx5228_fetch_vendor_settings(struct rtsx_pcr *pcr)
+{
+	u32 reg;
+	/* 0x724~0x727 */
+	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
+
+	if (!rtsx_vendor_setting_valid(reg)) {
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+	pcr->sd30_drive_sel_1v8 = rtsx_reg_to_sd30_drive_sel_1v8(reg);
+	pcr->aspm_en = rtsx_reg_to_aspm(reg);
+
+	/* 0x814~0x817 */
+	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
+
+	pcr->rtd3_en = rtsx_reg_to_rtd3(reg);
+	if (rtsx_check_mmc_support(reg))
+		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
+	pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg);
+	if (rtsx_reg_check_reverse_socket(reg))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+}
+
+static int rts5228_optimize_phy(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_phy_register(pcr, 0x07, 0x8F40);
+}
+
+static void rts5228_force_power_down(struct rtsx_pcr *pcr, u8 pm_state)
+{
+	/* Set relink_time to 0 */
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3,
+				RELINK_TIME_MASK, 0);
+
+	if (pm_state == HOST_ENTER_S3)
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, D3_DELINK_MODE_EN);
+
+	rtsx_pci_write_register(pcr, FPDCTL,
+		SSC_POWER_DOWN, SSC_POWER_DOWN);
+}
+
+static int rts5228_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_EN);
+}
+
+static int rts5228_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_DISABLE);
+}
+
+static int rts5228_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x02);
+}
+
+static int rts5228_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x00);
+}
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5228_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5228_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+static int rts5228_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK
+		| SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF,
+			CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+
+	return 0;
+}
+
+static int rts5228_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en)
+		rtsx_pci_enable_ocp(pcr);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+			CFG_SD_POW_AUTO_PD, CFG_SD_POW_AUTO_PD);
+
+	rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG1,
+			RTS5228_LDO1_TUNE_MASK, RTS5228_LDO1_33);
+
+	rtsx_pci_write_register(pcr, RTS5228_LDO1233318_POW_CTL,
+			RTS5228_LDO1_POWERON_MASK, RTS5228_LDO1_SOFTSTART);
+	mdelay(2);
+	rtsx_pci_write_register(pcr, RTS5228_LDO1233318_POW_CTL,
+			RTS5228_LDO1_POWERON_MASK, RTS5228_LDO1_FULLON);
+
+
+	rtsx_pci_write_register(pcr, RTS5228_LDO1233318_POW_CTL,
+			RTS5228_LDO3318_POWERON, RTS5228_LDO3318_POWERON);
+
+	msleep(20);
+
+	rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN);
+
+	/* Initialize SD_CFG1 register */
+	rtsx_pci_write_register(pcr, SD_CFG1, 0xFF,
+			SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT);
+
+	rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL,
+			0xFF, SD20_RX_POS_EDGE);
+	rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0);
+	rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR,
+			SD_STOP | SD_CLR_ERR);
+
+	/* Reset SD_CFG3 register */
+	rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0);
+	rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG,
+			SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 |
+			SD30_CLK_STOP_CFG0, 0);
+
+	if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 ||
+	    pcr->extra_caps & EXTRA_CAPS_SD_SDR104)
+		rts5228_sd_set_sample_push_timing_sd30(pcr);
+
+	return 0;
+}
+
+static int rts5228_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+	u16 val = 0;
+
+	rtsx_pci_write_register(pcr, RTS5228_CARD_PWR_CTL,
+			RTS5228_PUPDC, RTS5228_PUPDC);
+
+	switch (voltage) {
+	case OUTPUT_3V3:
+		rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val);
+		val |= PHY_TUNE_SDBUS_33;
+		err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val);
+		if (err < 0)
+			return err;
+
+		rtsx_pci_write_register(pcr, RTS5228_DV3318_CFG,
+				RTS5228_DV3318_TUNE_MASK, RTS5228_DV3318_33);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, 0);
+		break;
+	case OUTPUT_1V8:
+		rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val);
+		val &= ~PHY_TUNE_SDBUS_33;
+		err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val);
+		if (err < 0)
+			return err;
+
+		rtsx_pci_write_register(pcr, RTS5228_DV3318_CFG,
+				RTS5228_DV3318_TUNE_MASK, RTS5228_DV3318_18);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, SD_IO_USING_1V8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* set pad drive */
+	rts5228_fill_driving(pcr, voltage);
+
+	return 0;
+}
+
+static void rts5228_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+	rtsx_pci_write_register(pcr, RTS5260_DMA_RST_CTL_0,
+				RTS5260_DMA_RST | RTS5260_ADMA3_RST,
+				RTS5260_DMA_RST | RTS5260_ADMA3_RST);
+	rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH);
+}
+
+static void rts5228_card_before_power_off(struct rtsx_pcr *pcr)
+{
+	rts5228_stop_cmd(pcr);
+	rts5228_switch_output_voltage(pcr, OUTPUT_3V3);
+}
+
+static void rts5228_enable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 val = 0;
+
+	val = SD_OCP_INT_EN | SD_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, 0xFF, val);
+	rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN);
+}
+
+static void rts5228_disable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+	rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN, 0);
+}
+
+static int rts5228_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err = 0;
+
+	rts5228_card_before_power_off(pcr);
+	err = rtsx_pci_write_register(pcr, RTS5228_LDO1233318_POW_CTL,
+				RTS5228_LDO_POWERON_MASK, 0);
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0, CFG_SD_POW_AUTO_PD, 0);
+
+	if (pcr->option.ocp_en)
+		rtsx_pci_disable_ocp(pcr);
+
+	return err;
+}
+
+static void rts5228_init_ocp(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en) {
+		u8 mask, val;
+
+		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN);
+
+		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd);
+
+		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_LMT_THD_MASK,
+			RTS5228_LDO1_LMT_THD_1500);
+
+		rtsx_pci_read_register(pcr, RTS5228_LDO1_CFG0, &val);
+
+		mask = SD_OCP_GLITCH_MASK;
+		val = pcr->hw_param.ocp_glitch;
+		rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val);
+
+		rts5228_enable_ocp(pcr);
+
+	} else {
+		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG0,
+			RTS5228_LDO1_OCP_EN | RTS5228_LDO1_OCP_LMT_EN, 0);
+	}
+}
+
+static void rts5228_clear_ocpstat(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	mask = SD_OCP_INT_CLR | SD_OC_CLR;
+	val = SD_OCP_INT_CLR | SD_OC_CLR;
+
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+
+	udelay(1000);
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+
+}
+
+static void rts5228_process_ocp(struct rtsx_pcr *pcr)
+{
+	if (!pcr->option.ocp_en)
+		return;
+
+	rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat);
+
+	if (pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER)) {
+		rts5228_clear_ocpstat(pcr);
+		rts5228_card_power_off(pcr, RTSX_SD_CARD);
+		rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0);
+		pcr->ocp_stat = 0;
+	}
+
+}
+
+static void rts5228_init_from_cfg(struct rtsx_pcr *pcr)
+{
+	u32 lval;
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_REG1, &lval);
+
+
+	if (0 == (lval & 0x0F))
+		rtsx_pci_enable_oobs_polling(pcr);
+	else
+		rtsx_pci_disable_oobs_polling(pcr);
+
+	if (lval & ASPM_L1_1_EN_MASK)
+		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
+	else
+		rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
+
+	if (lval & ASPM_L1_2_EN_MASK)
+		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
+	else
+		rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (lval & PM_L1_1_EN_MASK)
+		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
+	else
+		rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
+
+	if (lval & PM_L1_2_EN_MASK)
+		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
+	else
+		rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
+
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
+	if (option->ltr_en) {
+		u16 val;
+
+		pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
+		if (val & PCI_EXP_DEVCTL2_LTR_EN) {
+			option->ltr_enabled = true;
+			option->ltr_active = true;
+			rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
+		} else {
+			option->ltr_enabled = false;
+		}
+	}
+
+	if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+				| PM_L1_1_EN | PM_L1_2_EN))
+		option->force_clkreq_0 = false;
+	else
+		option->force_clkreq_0 = true;
+}
+
+static int rts5228_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1,
+			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
+
+	rts5228_init_from_cfg(pcr);
+
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG1,
+			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
+
+	rtsx_pci_write_register(pcr, FUNC_FORCE_CTL,
+			FUNC_FORCE_UPME_XMT_DBG, FUNC_FORCE_UPME_XMT_DBG);
+
+	rtsx_pci_write_register(pcr, PCLK_CTL,
+			PCLK_MODE_SEL, PCLK_MODE_SEL);
+
+	rtsx_pci_write_register(pcr, PM_EVENT_DEBUG, PME_DEBUG_0, PME_DEBUG_0);
+	rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, CLK_PM_EN, CLK_PM_EN);
+
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02);
+
+	/* Configure driving */
+	rts5228_fill_driving(pcr, OUTPUT_3V3);
+
+	if (pcr->flags & PCR_REVERSE_SOCKET)
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+
+	/*
+	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+	 * to drive low, and we forcibly request clock.
+	 */
+	if (option->force_clkreq_0)
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
+	rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB);
+	rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00);
+	rtsx_pci_write_register(pcr, RTS5228_REG_PME_FORCE_CTL,
+			FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+
+	return 0;
+}
+
+static void rts5228_enable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 mask, val;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	val |= (pcr->aspm_en & 0x02);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, pcr->aspm_en);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5228_disable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 mask, val;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, 0);
+	mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0);
+	mdelay(10);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5228_set_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	if (enable)
+		rts5228_enable_aspm(pcr, true);
+	else
+		rts5228_disable_aspm(pcr, false);
+}
+
+static void rts5228_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	int aspm_L1_1, aspm_L1_2;
+	u8 val = 0;
+
+	aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN);
+	aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (active) {
+		/* run, latency: 60us */
+		if (aspm_L1_1)
+			val = option->ltr_l1off_snooze_sspwrgate;
+	} else {
+		/* l1off, latency: 300us */
+		if (aspm_L1_2)
+			val = option->ltr_l1off_sspwrgate;
+	}
+
+	rtsx_set_l1off_sub(pcr, val);
+}
+
+static const struct pcr_ops rts5228_pcr_ops = {
+	.fetch_vendor_settings = rtsx5228_fetch_vendor_settings,
+	.turn_on_led = rts5228_turn_on_led,
+	.turn_off_led = rts5228_turn_off_led,
+	.extra_init_hw = rts5228_extra_init_hw,
+	.enable_auto_blink = rts5228_enable_auto_blink,
+	.disable_auto_blink = rts5228_disable_auto_blink,
+	.card_power_on = rts5228_card_power_on,
+	.card_power_off = rts5228_card_power_off,
+	.switch_output_voltage = rts5228_switch_output_voltage,
+	.force_power_down = rts5228_force_power_down,
+	.stop_cmd = rts5228_stop_cmd,
+	.set_aspm = rts5228_set_aspm,
+	.set_l1off_cfg_sub_d0 = rts5228_set_l1off_cfg_sub_d0,
+	.enable_ocp = rts5228_enable_ocp,
+	.disable_ocp = rts5228_disable_ocp,
+	.init_ocp = rts5228_init_ocp,
+	.process_ocp = rts5228_process_ocp,
+	.clear_ocpstat = rts5228_clear_ocpstat,
+	.optimize_phy = rts5228_optimize_phy,
+};
+
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+int rts5228_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u16 n;
+	u8 clk_divider, mcu_cnt, div;
+	static const u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = RTS5228_SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = RTS5228_SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = RTS5228_SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = RTS5228_SSC_DEPTH_512K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock);
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n",
+		clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	if (pcr->ops->conv_clk_and_div_n)
+		n = pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		n = clk - 4;
+	if ((clk <= 4) || (n > 396))
+		return -EINVAL;
+
+	mcu_cnt = 125/clk + 3;
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	div = CLK_DIV_1;
+	while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) {
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(n,
+					DIV_N_TO_CLK) * 2;
+			n = pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			n = (n + 4) * 2 - 4;
+		}
+		div++;
+	}
+
+	n = (n / 2) - 1;
+	pcr_dbg(pcr, "n = %d, div = %d\n", n, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	if (ssc_depth) {
+		if (div == CLK_DIV_2) {
+			if (ssc_depth > 1)
+				ssc_depth -= 1;
+			else
+				ssc_depth = RTS5228_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_4) {
+			if (ssc_depth > 2)
+				ssc_depth -= 2;
+			else
+				ssc_depth = RTS5228_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_8) {
+			if (ssc_depth > 3)
+				ssc_depth -= 3;
+			else
+				ssc_depth = RTS5228_SSC_DEPTH_8M;
+		}
+	} else {
+		ssc_depth = 0;
+	}
+	pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+				CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(SSC_CLOCK_STABLE_WAIT);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+
+}
+
+void rts5228_init_params(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 1;
+	pcr->ops = &rts5228_pcr_ops;
+
+	pcr->flags = 0;
+	pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT;
+	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
+	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
+	pcr->aspm_en = ASPM_L1_EN;
+	pcr->tx_initial_phase = SET_CLOCK_PHASE(28, 27, 11);
+	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
+
+	pcr->ic_version = rts5228_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5228_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5228_sd_pull_ctl_disable_tbl;
+
+	pcr->reg_pm_ctrl3 = RTS5228_AUTOLOAD_CFG3;
+
+	option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN
+				| LTR_L1SS_PWR_GATE_EN);
+	option->ltr_en = true;
+
+	/* init latency of active, idle, L1OFF to 60us, 300us, 3ms */
+	option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF;
+	option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF;
+	option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF;
+	option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF;
+	option->ltr_l1off_sspwrgate = 0x7F;
+	option->ltr_l1off_snooze_sspwrgate = 0x78;
+
+	option->ocp_en = 1;
+	hw_param->interrupt_en |= SD_OC_INT_EN;
+	hw_param->ocp_glitch =  SD_OCP_GLITCH_800U;
+	option->sd_800mA_ocp_thd =  RTS5228_LDO1_OCP_THD_930;
+}
diff --git a/drivers/misc/cardreader/rts5228.h b/drivers/misc/cardreader/rts5228.h
new file mode 100644
index 000000000000..6a872246aeed
--- /dev/null
+++ b/drivers/misc/cardreader/rts5228.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky WU <ricky_wu@realtek.com>
+ *   Rui FENG <rui_feng@realsil.com.cn>
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ */
+#ifndef RTS5228_H
+#define RTS5228_H
+
+
+#define RTS5228_AUTOLOAD_CFG0			0xFF7B
+#define RTS5228_AUTOLOAD_CFG1			0xFF7C
+#define RTS5228_AUTOLOAD_CFG2			0xFF7D
+#define RTS5228_AUTOLOAD_CFG3			0xFF7E
+#define RTS5228_AUTOLOAD_CFG4			0xFF7F
+
+#define RTS5228_REG_VREF			0xFE97
+#define RTS5228_PWD_SUSPND_EN			(1 << 4)
+
+#define RTS5228_PAD_H3L1			0xFF79
+#define PAD_GPIO_H3L1			(1 << 3)
+
+/* SSC_CTL2 0xFC12 */
+#define RTS5228_SSC_DEPTH_MASK		0x07
+#define RTS5228_SSC_DEPTH_DISALBE	0x00
+#define RTS5228_SSC_DEPTH_8M		0x01
+#define RTS5228_SSC_DEPTH_4M		0x02
+#define RTS5228_SSC_DEPTH_2M		0x03
+#define RTS5228_SSC_DEPTH_1M		0x04
+#define RTS5228_SSC_DEPTH_512K		0x05
+#define RTS5228_SSC_DEPTH_256K		0x06
+#define RTS5228_SSC_DEPTH_128K		0x07
+
+/* DMACTL 0xFE2C */
+#define RTS5228_DMA_PACK_SIZE_MASK		0xF0
+
+#define RTS5228_REG_LDO12_CFG			0xFF6E
+#define RTS5228_LDO12_VO_TUNE_MASK		(0x07<<1)
+#define RTS5228_LDO12_100				(0x00<<1)
+#define RTS5228_LDO12_105				(0x01<<1)
+#define RTS5228_LDO12_110				(0x02<<1)
+#define RTS5228_LDO12_115				(0x03<<1)
+#define RTS5228_LDO12_120				(0x04<<1)
+#define RTS5228_LDO12_125				(0x05<<1)
+#define RTS5228_LDO12_130				(0x06<<1)
+#define RTS5228_LDO12_135				(0x07<<1)
+#define RTS5228_REG_PWD_LDO12			(0x01<<0)
+
+#define RTS5228_REG_LDO12_L12	0xFF6F
+#define RTS5228_LDO12_L12_MASK			(0x07<<4)
+#define RTS5228_LDO12_L12_120			(0x04<<4)
+
+/* LDO control register */
+#define RTS5228_CARD_PWR_CTL			0xFD50
+#define RTS5228_PUPDC					(0x01<<5)
+
+#define RTS5228_LDO1233318_POW_CTL		0xFF70
+#define RTS5228_LDO3318_POWERON			(0x01<<3)
+#define RTS5228_LDO1_POWEROFF			(0x00<<0)
+#define RTS5228_LDO1_SOFTSTART			(0x01<<0)
+#define RTS5228_LDO1_FULLON				(0x03<<0)
+#define RTS5228_LDO1_POWERON_MASK		(0x03<<0)
+#define RTS5228_LDO_POWERON_MASK		(0x0F<<0)
+
+#define RTS5228_DV3318_CFG				0xFF71
+#define RTS5228_DV3318_TUNE_MASK		(0x07<<4)
+#define RTS5228_DV3318_17				(0x00<<4)
+#define RTS5228_DV3318_1V75				(0x01<<4)
+#define RTS5228_DV3318_18				(0x02<<4)
+#define RTS5228_DV3318_1V85				(0x03<<4)
+#define RTS5228_DV3318_19				(0x04<<4)
+#define RTS5228_DV3318_33				(0x07<<4)
+#define RTS5228_DV3318_SR_MASK			(0x03<<2)
+#define RTS5228_DV3318_SR_0				(0x00<<2)
+#define RTS5228_DV3318_SR_250			(0x01<<2)
+#define RTS5228_DV3318_SR_500			(0x02<<2)
+#define RTS5228_DV3318_SR_1000			(0x03<<2)
+
+#define RTS5228_LDO1_CFG0				0xFF72
+#define RTS5228_LDO1_OCP_THD_MASK		(0x07<<5)
+#define RTS5228_LDO1_OCP_EN				(0x01<<4)
+#define RTS5228_LDO1_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5228_LDO1_OCP_LMT_EN			(0x01<<1)
+
+#define RTS5228_LDO1_OCP_THD_730		(0x00<<5)
+#define RTS5228_LDO1_OCP_THD_780		(0x01<<5)
+#define RTS5228_LDO1_OCP_THD_860		(0x02<<5)
+#define RTS5228_LDO1_OCP_THD_930		(0x03<<5)
+#define RTS5228_LDO1_OCP_THD_1000		(0x04<<5)
+#define RTS5228_LDO1_OCP_THD_1070		(0x05<<5)
+#define RTS5228_LDO1_OCP_THD_1140		(0x06<<5)
+#define RTS5228_LDO1_OCP_THD_1220		(0x07<<5)
+
+#define RTS5228_LDO1_LMT_THD_450		(0x00<<2)
+#define RTS5228_LDO1_LMT_THD_1000		(0x01<<2)
+#define RTS5228_LDO1_LMT_THD_1500		(0x02<<2)
+#define RTS5228_LDO1_LMT_THD_2000		(0x03<<2)
+
+#define RTS5228_LDO1_CFG1				0xFF73
+#define RTS5228_LDO1_SR_TIME_MASK		(0x03<<6)
+#define RTS5228_LDO1_SR_0_0				(0x00<<6)
+#define RTS5228_LDO1_SR_0_25			(0x01<<6)
+#define RTS5228_LDO1_SR_0_5				(0x02<<6)
+#define RTS5228_LDO1_SR_1_0				(0x03<<6)
+#define RTS5228_LDO1_TUNE_MASK			(0x07<<1)
+#define RTS5228_LDO1_18					(0x05<<1)
+#define RTS5228_LDO1_33					(0x07<<1)
+#define RTS5228_LDO1_PWD_MASK			(0x01<<0)
+
+#define RTS5228_AUXCLK_GAT_CTL			0xFF74
+
+#define RTS5228_REG_RREF_CTL_0			0xFF75
+#define RTS5228_FORCE_RREF_EXTL			(0x01<<7)
+#define RTS5228_REG_BG33_MASK			(0x07<<0)
+#define RTS5228_RREF_12_1V				(0x04<<0)
+#define RTS5228_RREF_12_3V				(0x05<<0)
+
+#define RTS5228_REG_RREF_CTL_1			0xFF76
+
+#define RTS5228_REG_RREF_CTL_2			0xFF77
+#define RTS5228_TEST_INTL_RREF			(0x01<<7)
+#define RTS5228_DGLCH_TIME_MASK			(0x03<<5)
+#define RTS5228_DGLCH_TIME_50			(0x00<<5)
+#define RTS5228_DGLCH_TIME_75			(0x01<<5)
+#define RTS5228_DGLCH_TIME_100			(0x02<<5)
+#define RTS5228_DGLCH_TIME_125			(0x03<<5)
+#define RTS5228_REG_REXT_TUNE_MASK		(0x1F<<0)
+
+#define RTS5228_REG_PME_FORCE_CTL		0xFF78
+#define FORCE_PM_CONTROL		0x20
+#define FORCE_PM_VALUE			0x10
+
+
+/* Single LUN, support SD */
+#define DEFAULT_SINGLE		0
+#define SD_LUN				1
+
+
+/* For Change_FPGA_SSCClock Function */
+#define MULTIPLY_BY_1    0x00
+#define MULTIPLY_BY_2    0x01
+#define MULTIPLY_BY_3    0x02
+#define MULTIPLY_BY_4    0x03
+#define MULTIPLY_BY_5    0x04
+#define MULTIPLY_BY_6    0x05
+#define MULTIPLY_BY_7    0x06
+#define MULTIPLY_BY_8    0x07
+#define MULTIPLY_BY_9    0x08
+#define MULTIPLY_BY_10   0x09
+
+#define DIVIDE_BY_2      0x01
+#define DIVIDE_BY_3      0x02
+#define DIVIDE_BY_4      0x03
+#define DIVIDE_BY_5      0x04
+#define DIVIDE_BY_6      0x05
+#define DIVIDE_BY_7      0x06
+#define DIVIDE_BY_8      0x07
+#define DIVIDE_BY_9      0x08
+#define DIVIDE_BY_10     0x09
+
+int rts5228_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+
+#endif /* RTS5228_H */
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 0d5928bc1b6d..5ff690d2e9a9 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -23,6 +23,7 @@
 
 #include "rtsx_pcr.h"
 #include "rts5261.h"
+#include "rts5228.h"
 
 static bool msi_en = true;
 module_param(msi_en, bool, S_IRUGO | S_IWUSR);
@@ -50,6 +51,7 @@ static const struct pci_device_id rtsx_pci_ids[] = {
 	{ PCI_DEVICE(0x10EC, 0x525A), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5260), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5261), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5228), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ 0, }
 };
 
@@ -206,16 +208,10 @@ int __rtsx_pci_write_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 val)
 	int err, i, finished = 0;
 	u8 tmp;
 
-	rtsx_pci_init_cmd(pcr);
-
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA0, 0xFF, (u8)val);
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA1, 0xFF, (u8)(val >> 8));
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x81);
-
-	err = rtsx_pci_send_cmd(pcr, 100);
-	if (err < 0)
-		return err;
+	rtsx_pci_write_register(pcr, PHYDATA0, 0xFF, (u8)val);
+	rtsx_pci_write_register(pcr, PHYDATA1, 0xFF, (u8)(val >> 8));
+	rtsx_pci_write_register(pcr, PHYADDR, 0xFF, addr);
+	rtsx_pci_write_register(pcr, PHYRWCTL, 0xFF, 0x81);
 
 	for (i = 0; i < 100000; i++) {
 		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
@@ -247,16 +243,10 @@ int __rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val)
 {
 	int err, i, finished = 0;
 	u16 data;
-	u8 *ptr, tmp;
-
-	rtsx_pci_init_cmd(pcr);
+	u8 tmp, val1, val2;
 
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x80);
-
-	err = rtsx_pci_send_cmd(pcr, 100);
-	if (err < 0)
-		return err;
+	rtsx_pci_write_register(pcr, PHYADDR, 0xFF, addr);
+	rtsx_pci_write_register(pcr, PHYRWCTL, 0xFF, 0x80);
 
 	for (i = 0; i < 100000; i++) {
 		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
@@ -272,17 +262,9 @@ int __rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val)
 	if (!finished)
 		return -ETIMEDOUT;
 
-	rtsx_pci_init_cmd(pcr);
-
-	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA0, 0, 0);
-	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA1, 0, 0);
-
-	err = rtsx_pci_send_cmd(pcr, 100);
-	if (err < 0)
-		return err;
-
-	ptr = rtsx_pci_get_cmd_data(pcr);
-	data = ((u16)ptr[1] << 8) | ptr[0];
+	rtsx_pci_read_register(pcr, PHYDATA0, &val1);
+	rtsx_pci_read_register(pcr, PHYDATA1, &val2);
+	data = val1 | (val2 << 8);
 
 	if (val)
 		*val = data;
@@ -417,7 +399,7 @@ static void rtsx_pci_add_sg_tbl(struct rtsx_pcr *pcr,
 	if (end)
 		option |= RTSX_SG_END;
 
-	if (PCI_PID(pcr) == PID_5261) {
+	if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5228)) {
 		if (len > 0xFFFF)
 			val = ((u64)addr << 32) | (((u64)len & 0xFFFF) << 16)
 				| (((u64)len >> 16) << 6) | option;
@@ -723,6 +705,9 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 	if (PCI_PID(pcr) == PID_5261)
 		return rts5261_pci_switch_clock(pcr, card_clock,
 				ssc_depth, initial_mode, double_clk, vpclk);
+	if (PCI_PID(pcr) == PID_5228)
+		return rts5228_pci_switch_clock(pcr, card_clock,
+				ssc_depth, initial_mode, double_clk, vpclk);
 
 	if (initial_mode) {
 		/* We use 250k(around) here, in initial stage */
@@ -1202,6 +1187,36 @@ void rtsx_pci_clear_ocpstat(struct rtsx_pcr *pcr)
 	}
 }
 
+void rtsx_pci_enable_oobs_polling(struct rtsx_pcr *pcr)
+{
+	u16 val;
+
+	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+		rtsx_pci_read_phy_register(pcr, 0x01, &val);
+		val |= 1<<9;
+		rtsx_pci_write_phy_register(pcr, 0x01, val);
+	}
+	rtsx_pci_write_register(pcr, REG_CFG_OOBS_OFF_TIMER, 0xFF, 0x32);
+	rtsx_pci_write_register(pcr, REG_CFG_OOBS_ON_TIMER, 0xFF, 0x05);
+	rtsx_pci_write_register(pcr, REG_CFG_VCM_ON_TIMER, 0xFF, 0x83);
+	rtsx_pci_write_register(pcr, REG_CFG_OOBS_POLLING, 0xFF, 0xDE);
+
+}
+
+void rtsx_pci_disable_oobs_polling(struct rtsx_pcr *pcr)
+{
+	u16 val;
+
+	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+		rtsx_pci_read_phy_register(pcr, 0x01, &val);
+		val &= ~(1<<9);
+		rtsx_pci_write_phy_register(pcr, 0x01, val);
+	}
+	rtsx_pci_write_register(pcr, REG_CFG_VCM_ON_TIMER, 0xFF, 0x03);
+	rtsx_pci_write_register(pcr, REG_CFG_OOBS_POLLING, 0xFF, 0x00);
+
+}
+
 int rtsx_sd_power_off_card3v3(struct rtsx_pcr *pcr)
 {
 	rtsx_pci_write_register(pcr, CARD_CLK_EN, SD_CLK_EN |
@@ -1233,6 +1248,10 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 {
 	int err;
 
+	if (PCI_PID(pcr) == PID_5228)
+		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG1, RTS5228_LDO1_SR_TIME_MASK,
+				RTS5228_LDO1_SR_0_5);
+
 	pcr->pcie_cap = pci_find_capability(pcr->pci, PCI_CAP_ID_EXP);
 	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
 
@@ -1280,6 +1299,9 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	if (PCI_PID(pcr) == PID_5261)
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
 			RTS5261_SSC_DEPTH_2M);
+	else if (PCI_PID(pcr) == PID_5228)
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
+			RTS5228_SSC_DEPTH_2M);
 	else
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
 
@@ -1314,6 +1336,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	case PID_525A:
 	case PID_5260:
 	case PID_5261:
+	case PID_5228:
 		rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, 1, 1);
 		break;
 	default:
@@ -1401,6 +1424,10 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 	case 0x5261:
 		rts5261_init_params(pcr);
 		break;
+
+	case 0x5228:
+		rts5228_init_params(pcr);
+		break;
 	}
 
 	pcr_dbg(pcr, "PID: 0x%04x, IC version: 0x%02x\n",
diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h
index 024cbd998b2a..6b322db8738e 100644
--- a/drivers/misc/cardreader/rtsx_pcr.h
+++ b/drivers/misc/cardreader/rtsx_pcr.h
@@ -53,6 +53,7 @@ void rts525a_init_params(struct rtsx_pcr *pcr);
 void rtl8411b_init_params(struct rtsx_pcr *pcr);
 void rts5260_init_params(struct rtsx_pcr *pcr);
 void rts5261_init_params(struct rtsx_pcr *pcr);
+void rts5228_init_params(struct rtsx_pcr *pcr);
 
 static inline u8 map_sd_drive(int idx)
 {
@@ -70,6 +71,8 @@ static inline u8 map_sd_drive(int idx)
 #define rts5209_vendor_setting1_valid(reg)	(!((reg) & 0x80))
 #define rts5209_vendor_setting2_valid(reg)	((reg) & 0x80)
 
+#define rtsx_check_mmc_support(reg)		((reg) & 0x10)
+#define rtsx_reg_to_rtd3(reg)				((reg) & 0x02)
 #define rtsx_reg_to_aspm(reg)			(((reg) >> 28) & 0x03)
 #define rtsx_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 26) & 0x03)
 #define rtsx_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 5) & 0x03)
@@ -100,6 +103,8 @@ void rtsx_pci_disable_ocp(struct rtsx_pcr *pcr);
 void rtsx_pci_enable_ocp(struct rtsx_pcr *pcr);
 int rtsx_pci_get_ocpstat(struct rtsx_pcr *pcr, u8 *val);
 void rtsx_pci_clear_ocpstat(struct rtsx_pcr *pcr);
+void rtsx_pci_enable_oobs_polling(struct rtsx_pcr *pcr);
+void rtsx_pci_disable_oobs_polling(struct rtsx_pcr *pcr);
 int rtsx_sd_power_off_card3v3(struct rtsx_pcr *pcr);
 int rtsx_ms_power_off_card3v3(struct rtsx_pcr *pcr);
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 5a71f6678fd3..bce910de8b4d 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -1336,6 +1336,8 @@ static void init_extra_caps(struct realtek_pci_sdmmc *host)
 		mmc->caps |= MMC_CAP_1_8V_DDR;
 	if (pcr->extra_caps & EXTRA_CAPS_MMC_8BIT)
 		mmc->caps |= MMC_CAP_8_BIT_DATA;
+	if (pcr->extra_caps & EXTRA_CAPS_NO_MMC)
+		mmc->caps2 |= MMC_CAP2_NO_MMC;
 }
 
 static void realtek_init_host(struct realtek_pci_sdmmc *host)
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index e8780d4e4636..27a6ea82aeea 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -305,6 +305,8 @@
 #define   SD30_CLK_STOP_CFG0		0x01
 #define REG_PRE_RW_MODE			0xFD70
 #define EN_INFINITE_MODE		0x01
+#define REG_CRC_DUMMY_0		0xFD71
+#define CFG_SD_POW_AUTO_PD		(1<<0)
 
 #define SRCTL				0xFC13
 
@@ -599,6 +601,7 @@
 
 #define ASPM_FORCE_CTL			0xFE57
 #define   FORCE_ASPM_CTL0		0x10
+#define   FORCE_ASPM_CTL1		0x20
 #define   FORCE_ASPM_VAL_MASK		0x03
 #define   FORCE_ASPM_L1_EN		0x02
 #define   FORCE_ASPM_L0_EN		0x01
@@ -667,6 +670,11 @@
 #define   PM_WAKE_EN			0x01
 #define PM_CTRL4			0xFF47
 
+#define REG_CFG_OOBS_OFF_TIMER 0xFEA6
+#define REG_CFG_OOBS_ON_TIMER 0xFEA7
+#define REG_CFG_VCM_ON_TIMER 0xFEA8
+#define REG_CFG_OOBS_POLLING 0xFEA9
+
 /* Memory mapping */
 #define SRAM_BASE			0xE600
 #define RBUF_BASE			0xF400
@@ -1204,6 +1212,7 @@ struct rtsx_pcr {
 #define EXTRA_CAPS_MMC_HSDDR		(1 << 3)
 #define EXTRA_CAPS_MMC_HS200		(1 << 4)
 #define EXTRA_CAPS_MMC_8BIT		(1 << 5)
+#define EXTRA_CAPS_NO_MMC		(1 << 7)
 	u32				extra_caps;
 
 #define IC_VER_A			0
@@ -1242,6 +1251,7 @@ struct rtsx_pcr {
 	u8				dma_error_count;
 	u8			ocp_stat;
 	u8			ocp_stat2;
+	u8			rtd3_en;
 };
 
 #define PID_524A	0x524A
@@ -1250,6 +1260,7 @@ struct rtsx_pcr {
 #define PID_525A	0x525A
 #define PID_5260	0x5260
 #define PID_5261	0x5261
+#define PID_5228	0x5228
 
 #define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
 #define PCI_VID(pcr)			((pcr)->pci->vendor)
-- 
cgit v1.2.3


From 776499058167d9f41c8eb468e21fe2d241c0b8e6 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 1 Jul 2020 16:18:29 +0200
Subject: mm/memblock: expose only miminal interface to add/walk physmem

"physmem" in the memblock allocator is somewhat weird: it's not actually
used for allocation, it's simply information collected during boot, which
describes the unmodified physical memory map at boot time, without any
standby/hotplugged memory. It's only used on s390 and is currently the
only reason s390 keeps using CONFIG_ARCH_KEEP_MEMBLOCK.

Physmem isn't numa aware and current users don't specify any flags. Let's
hide it from the user, exposing only for_each_physmem(), and simplify. The
interface for physmem is now really minimalistic:
- memblock_physmem_add() to add ranges
- for_each_physmem() / __next_physmem_range() to walk physmem ranges

Don't place it into an __init section and don't discard it without
CONFIG_ARCH_KEEP_MEMBLOCK. As we're reusing __next_mem_range(), remove
the __meminit notifier to avoid section mismatch warnings once
CONFIG_ARCH_KEEP_MEMBLOCK is no longer used with
CONFIG_HAVE_MEMBLOCK_PHYS_MAP.

While fixing up the documentation, sneak in some related cleanups. We can
stop setting CONFIG_ARCH_KEEP_MEMBLOCK for s390 next.

Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Message-Id: <20200701141830.18749-2-david@redhat.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/crash_dump.c |  6 ++---
 include/linux/memblock.h      | 28 ++++++++++++++++++---
 mm/memblock.c                 | 57 ++++++++++++++++++++++---------------------
 3 files changed, 55 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index f96a5857bbfd..c42ce348103c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -549,8 +549,7 @@ static int get_mem_chunk_cnt(void)
 	int cnt = 0;
 	u64 idx;
 
-	for_each_mem_range(idx, &memblock.physmem, &oldmem_type, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, NULL, NULL, NULL)
+	for_each_physmem_range(idx, &oldmem_type, NULL, NULL)
 		cnt++;
 	return cnt;
 }
@@ -563,8 +562,7 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
 	phys_addr_t start, end;
 	u64 idx;
 
-	for_each_mem_range(idx, &memblock.physmem, &oldmem_type, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
 		phdr->p_filesz = end - start;
 		phdr->p_type = PT_LOAD;
 		phdr->p_offset = start;
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 017fae833d4a..9d925db0d355 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -77,16 +77,12 @@ struct memblock_type {
  * @current_limit: physical address of the current allocation limit
  * @memory: usable memory regions
  * @reserved: reserved memory regions
- * @physmem: all physical memory
  */
 struct memblock {
 	bool bottom_up;  /* is bottom up direction? */
 	phys_addr_t current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;
-#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-	struct memblock_type physmem;
-#endif
 };
 
 extern struct memblock memblock;
@@ -145,6 +141,30 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
 
 void __memblock_free_late(phys_addr_t base, phys_addr_t size);
 
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
+					phys_addr_t *out_start,
+					phys_addr_t *out_end)
+{
+	extern struct memblock_type physmem;
+
+	__next_mem_range(idx, NUMA_NO_NODE, MEMBLOCK_NONE, &physmem, type,
+			 out_start, out_end, NULL);
+}
+
+/**
+ * for_each_physmem_range - iterate through physmem areas not included in type.
+ * @i: u64 used as loop variable
+ * @type: ptr to memblock_type which excludes from the iteration, can be %NULL
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ */
+#define for_each_physmem_range(i, type, p_start, p_end)			\
+	for (i = 0, __next_physmem_range(&i, type, p_start, p_end);	\
+	     i != (u64)ULLONG_MAX;					\
+	     __next_physmem_range(&i, type, p_start, p_end))
+#endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */
+
 /**
  * for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.
diff --git a/mm/memblock.c b/mm/memblock.c
index 39aceafc57f6..45f198750be9 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -44,19 +44,20 @@
  *   in the system, for instance when the memory is restricted with
  *   ``mem=`` command line parameter
  * * ``reserved`` - describes the regions that were allocated
- * * ``physmap`` - describes the actual physical memory regardless of
- *   the possible restrictions; the ``physmap`` type is only available
- *   on some architectures.
+ * * ``physmem`` - describes the actual physical memory available during
+ *   boot regardless of the possible restrictions and memory hot(un)plug;
+ *   the ``physmem`` type is only available on some architectures.
  *
  * Each region is represented by :c:type:`struct memblock_region` that
  * defines the region extents, its attributes and NUMA node id on NUMA
  * systems. Every memory type is described by the :c:type:`struct
  * memblock_type` which contains an array of memory regions along with
- * the allocator metadata. The memory types are nicely wrapped with
- * :c:type:`struct memblock`. This structure is statically initialzed
- * at build time. The region arrays for the "memory" and "reserved"
- * types are initially sized to %INIT_MEMBLOCK_REGIONS and for the
- * "physmap" type to %INIT_PHYSMEM_REGIONS.
+ * the allocator metadata. The "memory" and "reserved" types are nicely
+ * wrapped with :c:type:`struct memblock`. This structure is statically
+ * initialized at build time. The region arrays are initially sized to
+ * %INIT_MEMBLOCK_REGIONS for "memory" and %INIT_MEMBLOCK_RESERVED_REGIONS
+ * for "reserved". The region array for "physmem" is initially sized to
+ * %INIT_PHYSMEM_REGIONS.
  * The memblock_allow_resize() enables automatic resizing of the region
  * arrays during addition of new regions. This feature should be used
  * with care so that memory allocated for the region array will not
@@ -87,8 +88,8 @@
  * function frees all the memory to the buddy page allocator.
  *
  * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the
- * memblock data structures will be discarded after the system
- * initialization completes.
+ * memblock data structures (except "physmem") will be discarded after the
+ * system initialization completes.
  */
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -104,7 +105,7 @@ unsigned long long max_possible_pfn;
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock;
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
+static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS];
 #endif
 
 struct memblock memblock __initdata_memblock = {
@@ -118,17 +119,19 @@ struct memblock memblock __initdata_memblock = {
 	.reserved.max		= INIT_MEMBLOCK_RESERVED_REGIONS,
 	.reserved.name		= "reserved",
 
-#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-	.physmem.regions	= memblock_physmem_init_regions,
-	.physmem.cnt		= 1,	/* empty dummy entry */
-	.physmem.max		= INIT_PHYSMEM_REGIONS,
-	.physmem.name		= "physmem",
-#endif
-
 	.bottom_up		= false,
 	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
 };
 
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+struct memblock_type physmem = {
+	.regions		= memblock_physmem_init_regions,
+	.cnt			= 1,	/* empty dummy entry */
+	.max			= INIT_PHYSMEM_REGIONS,
+	.name			= "physmem",
+};
+#endif
+
 int memblock_debug __initdata_memblock;
 static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
@@ -838,7 +841,7 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size)
 	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
-	return memblock_add_range(&memblock.physmem, base, size, MAX_NUMNODES, 0);
+	return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0);
 }
 #endif
 
@@ -1019,12 +1022,10 @@ static bool should_skip_region(struct memblock_region *m, int nid, int flags)
  * As both region arrays are sorted, the function advances the two indices
  * in lockstep and returns each intersection.
  */
-void __init_memblock __next_mem_range(u64 *idx, int nid,
-				      enum memblock_flags flags,
-				      struct memblock_type *type_a,
-				      struct memblock_type *type_b,
-				      phys_addr_t *out_start,
-				      phys_addr_t *out_end, int *out_nid)
+void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
+		      struct memblock_type *type_a,
+		      struct memblock_type *type_b, phys_addr_t *out_start,
+		      phys_addr_t *out_end, int *out_nid)
 {
 	int idx_a = *idx & 0xffffffff;
 	int idx_b = *idx >> 32;
@@ -1924,7 +1925,7 @@ void __init_memblock __memblock_dump_all(void)
 	memblock_dump(&memblock.memory);
 	memblock_dump(&memblock.reserved);
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-	memblock_dump(&memblock.physmem);
+	memblock_dump(&physmem);
 #endif
 }
 
@@ -2064,8 +2065,8 @@ static int __init memblock_init_debugfs(void)
 	debugfs_create_file("reserved", 0444, root,
 			    &memblock.reserved, &memblock_debug_fops);
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-	debugfs_create_file("physmem", 0444, root,
-			    &memblock.physmem, &memblock_debug_fops);
+	debugfs_create_file("physmem", 0444, root, &physmem,
+			    &memblock_debug_fops);
 #endif
 
 	return 0;
-- 
cgit v1.2.3


From ec7bd78498f29680f536451fbdf9464e851273ed Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Wed, 1 Jul 2020 12:42:58 -0700
Subject: driver core: Rename dev_links_info.defer_sync to defer_hook

The defer_sync field is used as a hook to add the device to the
deferred_sync list. Rename it so that it's more meaningful for the next
patch that'll also use this field as a hook to a deferred_fw_devlink
list.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Reviewed-by: Rafael J. Wysocki <rafael@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20200701194259.3337652-3-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 22 +++++++++++-----------
 include/linux/device.h |  4 ++--
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 35cc9896eb9e..d1d2cdc3a8d8 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -754,11 +754,11 @@ static void __device_links_queue_sync_state(struct device *dev,
 	 */
 	dev->state_synced = true;
 
-	if (WARN_ON(!list_empty(&dev->links.defer_sync)))
+	if (WARN_ON(!list_empty(&dev->links.defer_hook)))
 		return;
 
 	get_device(dev);
-	list_add_tail(&dev->links.defer_sync, list);
+	list_add_tail(&dev->links.defer_hook, list);
 }
 
 /**
@@ -776,8 +776,8 @@ static void device_links_flush_sync_list(struct list_head *list,
 {
 	struct device *dev, *tmp;
 
-	list_for_each_entry_safe(dev, tmp, list, links.defer_sync) {
-		list_del_init(&dev->links.defer_sync);
+	list_for_each_entry_safe(dev, tmp, list, links.defer_hook) {
+		list_del_init(&dev->links.defer_hook);
 
 		if (dev != dont_lock_dev)
 			device_lock(dev);
@@ -815,12 +815,12 @@ void device_links_supplier_sync_state_resume(void)
 	if (defer_sync_state_count)
 		goto out;
 
-	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) {
+	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_hook) {
 		/*
 		 * Delete from deferred_sync list before queuing it to
-		 * sync_list because defer_sync is used for both lists.
+		 * sync_list because defer_hook is used for both lists.
 		 */
-		list_del_init(&dev->links.defer_sync);
+		list_del_init(&dev->links.defer_hook);
 		__device_links_queue_sync_state(dev, &sync_list);
 	}
 out:
@@ -838,8 +838,8 @@ late_initcall(sync_state_resume_initcall);
 
 static void __device_links_supplier_defer_sync(struct device *sup)
 {
-	if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup))
-		list_add_tail(&sup->links.defer_sync, &deferred_sync);
+	if (list_empty(&sup->links.defer_hook) && dev_has_sync_state(sup))
+		list_add_tail(&sup->links.defer_hook, &deferred_sync);
 }
 
 static void device_link_drop_managed(struct device_link *link)
@@ -1052,7 +1052,7 @@ void device_links_driver_cleanup(struct device *dev)
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
-	list_del_init(&dev->links.defer_sync);
+	list_del_init(&dev->links.defer_hook);
 	__device_links_no_driver(dev);
 
 	device_links_write_unlock();
@@ -2171,7 +2171,7 @@ void device_initialize(struct device *dev)
 	INIT_LIST_HEAD(&dev->links.consumers);
 	INIT_LIST_HEAD(&dev->links.suppliers);
 	INIT_LIST_HEAD(&dev->links.needs_suppliers);
-	INIT_LIST_HEAD(&dev->links.defer_sync);
+	INIT_LIST_HEAD(&dev->links.defer_hook);
 	dev->links.status = DL_DEV_NO_DRIVER;
 }
 EXPORT_SYMBOL_GPL(device_initialize);
diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..9bb2bc7bb8e3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -433,7 +433,7 @@ enum dl_dev_state {
  * @suppliers: List of links to supplier devices.
  * @consumers: List of links to consumer devices.
  * @needs_suppliers: Hook to global list of devices waiting for suppliers.
- * @defer_sync: Hook to global list of devices that have deferred sync_state.
+ * @defer_hook: Hook to global list of devices that have deferred sync_state.
  * @need_for_probe: If needs_suppliers is on a list, this indicates if the
  *		    suppliers are needed for probe or not.
  * @status: Driver status information.
@@ -442,7 +442,7 @@ struct dev_links_info {
 	struct list_head suppliers;
 	struct list_head consumers;
 	struct list_head needs_suppliers;
-	struct list_head defer_sync;
+	struct list_head defer_hook;
 	bool need_for_probe;
 	enum dl_dev_state status;
 };
-- 
cgit v1.2.3


From 2451e746478a6a6e981cfa66b62b791ca93b90c8 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Wed, 1 Jul 2020 12:42:59 -0700
Subject: driver core: Avoid deferred probe due to fw_devlink_pause/resume()

With the earlier patch in this series, all devices that deferred probe
due to fw_devlink_pause() will have their probes delayed till the
deferred probe thread is kicked off during late_initcall. This will also
affect all their consumers.

This delayed probing in unnecessary. So this patch just keeps track of
the devices that had their probe deferred due to fw_devlink_pause() and
attempts to probe them once during fw_devlink_resume().

Fixes: 716a7a259690 ("driver core: fw_devlink: Add support for batching fwnode parsing")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20200701194259.3337652-4-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 21 +++++++++++++++++++++
 include/linux/device.h |  3 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index d1d2cdc3a8d8..05d414e9e8a4 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -50,6 +50,7 @@ static DEFINE_MUTEX(wfs_lock);
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
 static unsigned int defer_fw_devlink_count;
+static LIST_HEAD(deferred_fw_devlink);
 static DEFINE_MUTEX(defer_fw_devlink_lock);
 static bool fw_devlink_is_permissive(void);
 
@@ -1244,6 +1245,12 @@ static void fw_devlink_link_device(struct device *dev)
 			fw_ret = -EAGAIN;
 	} else {
 		fw_ret = -ENODEV;
+		/*
+		 * defer_hook is not used to add device to deferred_sync list
+		 * until device is bound. Since deferred fw devlink also blocks
+		 * probing, same list hook can be used for deferred_fw_devlink.
+		 */
+		list_add_tail(&dev->links.defer_hook, &deferred_fw_devlink);
 	}
 
 	if (fw_ret == -ENODEV)
@@ -1312,6 +1319,9 @@ void fw_devlink_pause(void)
  */
 void fw_devlink_resume(void)
 {
+	struct device *dev, *tmp;
+	LIST_HEAD(probe_list);
+
 	mutex_lock(&defer_fw_devlink_lock);
 	if (!defer_fw_devlink_count) {
 		WARN(true, "Unmatched fw_devlink pause/resume!");
@@ -1323,8 +1333,19 @@ void fw_devlink_resume(void)
 		goto out;
 
 	device_link_add_missing_supplier_links();
+	list_splice_tail_init(&deferred_fw_devlink, &probe_list);
 out:
 	mutex_unlock(&defer_fw_devlink_lock);
+
+	/*
+	 * bus_probe_device() can cause new devices to get added and they'll
+	 * try to grab defer_fw_devlink_lock. So, this needs to be done outside
+	 * the defer_fw_devlink_lock.
+	 */
+	list_for_each_entry_safe(dev, tmp, &probe_list, links.defer_hook) {
+		list_del_init(&dev->links.defer_hook);
+		bus_probe_device(dev);
+	}
 }
 /* Device links support end. */
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 9bb2bc7bb8e3..5efed864b387 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -433,7 +433,8 @@ enum dl_dev_state {
  * @suppliers: List of links to supplier devices.
  * @consumers: List of links to consumer devices.
  * @needs_suppliers: Hook to global list of devices waiting for suppliers.
- * @defer_hook: Hook to global list of devices that have deferred sync_state.
+ * @defer_hook: Hook to global list of devices that have deferred sync_state or
+ *		deferred fw_devlink.
  * @need_for_probe: If needs_suppliers is on a list, this indicates if the
  *		    suppliers are needed for probe or not.
  * @status: Driver status information.
-- 
cgit v1.2.3


From 287905e68dd29873bcb7986a8290cd1e4cfde600 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Thu, 21 May 2020 12:17:58 -0700
Subject: driver core: Expose device link details in sysfs

It's helpful to be able to look at device link details from sysfs. So,
expose it in sysfs.

Say device-A is supplier of device-B. These are the additional files
this patch would create:

/sys/class/devlink/device-A:device-B/
	auto_remove_on
	consumer/ -> .../device-B/
	runtime_pm
	status
	supplier/ -> .../device-A/
	sync_state_only

/sys/devices/.../device-A/
	consumer:device-B/ -> /sys/class/devlink/device-A:device-B/

/sys/devices/.../device-B/
	supplier:device-A/ -> /sys/class/devlink/device-A:device-B/

That way:
To get a list of all the device link in the system:
ls /sys/class/devlink/

To get the consumer names and links of a device:
ls -d /sys/devices/.../device-X/consumer:*

To get the supplier names and links of a device:
ls -d /sys/devices/.../device-X/supplier:*

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20200521191800.136035-2-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-devlink    | 126 ++++++++++++++
 Documentation/ABI/testing/sysfs-devices-consumer |   8 +
 Documentation/ABI/testing/sysfs-devices-supplier |   8 +
 drivers/base/core.c                              | 211 ++++++++++++++++++++++-
 include/linux/device.h                           |  58 ++++---
 5 files changed, 375 insertions(+), 36 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-class-devlink
 create mode 100644 Documentation/ABI/testing/sysfs-devices-consumer
 create mode 100644 Documentation/ABI/testing/sysfs-devices-supplier

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink
new file mode 100644
index 000000000000..3a24973abb83
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-devlink
@@ -0,0 +1,126 @@
+What:		/sys/class/devlink/.../
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		Provide a place in sysfs for the device link objects in the
+		kernel at any given time.  The name of a device link directory,
+		denoted as ... above, is of the form <supplier>:<consumer>
+		where <supplier> is the supplier device name and <consumer> is
+		the consumer device name.
+
+What:		/sys/class/devlink/.../auto_remove_on
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file indicates if the device link will ever be
+		automatically removed by the driver core when the consumer and
+		supplier devices themselves are still present.
+
+		This will be one of the following strings:
+
+		'consumer unbind'
+		'supplier unbind'
+		'never'
+
+		'consumer unbind' means the device link will be removed when
+		the consumer's driver is unbound from the consumer device.
+
+		'supplier unbind' means the device link will be removed when
+		the supplier's driver is unbound from the supplier device.
+
+		'never' means the device link will not be automatically removed
+		when as long as the supplier and consumer devices themselves
+		are still present.
+
+What:		/sys/class/devlink/.../consumer
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file is a symlink to the consumer device's sysfs directory.
+
+What:		/sys/class/devlink/.../runtime_pm
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file indicates if the device link has any impact on the
+		runtime power management behavior of the consumer and supplier
+		devices. For example: Making sure the supplier doesn't enter
+		runtime suspend while the consumer is active.
+
+		This will be one of the following strings:
+
+		'0' - Does not affect runtime power management
+		'1' - Affects runtime power management
+
+What:		/sys/class/devlink/.../status
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file indicates the status of the device link. The status
+		of a device link is affected by whether the supplier and
+		consumer devices have been bound to their corresponding
+		drivers. The status of a device link also affects the binding
+		and unbinding of the supplier and consumer devices with their
+		drivers and also affects whether the software state of the
+		supplier device is synced with the hardware state of the
+		supplier device after boot up.
+		See also: sysfs-devices-state_synced.
+
+		This will be one of the following strings:
+
+		'not tracked'
+		'dormant'
+		'available'
+		'consumer probing'
+		'active'
+		'supplier unbinding'
+		'unknown'
+
+		'not tracked' means this device link does not track the status
+		and has no impact on the binding, unbinding and syncing the
+		hardware and software device state.
+
+		'dormant' means the supplier and the consumer devices have not
+		bound to their driver.
+
+		'available' means the supplier has bound to its driver and is
+		available to supply resources to the consumer device.
+
+		'consumer probing' means the consumer device is currently
+		trying to bind to its driver.
+
+		'active' means the supplier and consumer devices have both
+		bound successfully to their drivers.
+
+		'supplier unbinding' means the supplier devices is currently in
+		the process of unbinding from its driver.
+
+		'unknown' means the state of the device link is not any of the
+		above. If this is ever the value, there's a bug in the kernel.
+
+What:		/sys/class/devlink/.../supplier
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file is a symlink to the supplier device's sysfs directory.
+
+What:		/sys/class/devlink/.../sync_state_only
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		This file indicates if the device link is limited to only
+		affecting the syncing of the hardware and software state of the
+		supplier device.
+
+		This will be one of the following strings:
+
+		'0'
+		'1' - Affects runtime power management
+
+		'0' means the device link can affect other device behaviors
+		like binding/unbinding, suspend/resume, runtime power
+		management, etc.
+
+		'1' means the device link will only affect the syncing of
+		hardware and software state of the supplier device after boot
+		up and doesn't not affect other behaviors of the devices.
diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer
new file mode 100644
index 000000000000..1f06d74d1c3c
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-consumer
@@ -0,0 +1,8 @@
+What:		/sys/devices/.../consumer:<consumer>
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		The /sys/devices/.../consumer:<consumer> are symlinks to device
+		links where this device is the supplier. <consumer> denotes the
+		name of the consumer in that device link. There can be zero or
+		more of these symlinks for a given device.
diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier
new file mode 100644
index 000000000000..a919e0db5e90
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-supplier
@@ -0,0 +1,8 @@
+What:		/sys/devices/.../supplier:<supplier>
+Date:		May 2020
+Contact:	Saravana Kannan <saravanak@google.com>
+Description:
+		The /sys/devices/.../supplier:<supplier> are symlinks to device
+		links where this device is the consumer. <supplier> denotes the
+		name of the supplier in that device link. There can be zero or
+		more of these symlinks for a given device.
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67d39a90b45c..ca6403343515 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -235,6 +235,186 @@ void device_pm_move_to_tail(struct device *dev)
 	device_links_read_unlock(idx);
 }
 
+#define to_devlink(dev)	container_of((dev), struct device_link, link_dev)
+
+static ssize_t status_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	char *status;
+
+	switch (to_devlink(dev)->status) {
+	case DL_STATE_NONE:
+		status = "not tracked"; break;
+	case DL_STATE_DORMANT:
+		status = "dormant"; break;
+	case DL_STATE_AVAILABLE:
+		status = "available"; break;
+	case DL_STATE_CONSUMER_PROBE:
+		status = "consumer probing"; break;
+	case DL_STATE_ACTIVE:
+		status = "active"; break;
+	case DL_STATE_SUPPLIER_UNBIND:
+		status = "supplier unbinding"; break;
+	default:
+		status = "unknown"; break;
+	}
+	return sprintf(buf, "%s\n", status);
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t auto_remove_on_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct device_link *link = to_devlink(dev);
+	char *str;
+
+	if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+		str = "supplier unbind";
+	else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
+		str = "consumer unbind";
+	else
+		str = "never";
+
+	return sprintf(buf, "%s\n", str);
+}
+static DEVICE_ATTR_RO(auto_remove_on);
+
+static ssize_t runtime_pm_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct device_link *link = to_devlink(dev);
+
+	return sprintf(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME));
+}
+static DEVICE_ATTR_RO(runtime_pm);
+
+static ssize_t sync_state_only_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct device_link *link = to_devlink(dev);
+
+	return sprintf(buf, "%d\n", !!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
+}
+static DEVICE_ATTR_RO(sync_state_only);
+
+static struct attribute *devlink_attrs[] = {
+	&dev_attr_status.attr,
+	&dev_attr_auto_remove_on.attr,
+	&dev_attr_runtime_pm.attr,
+	&dev_attr_sync_state_only.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(devlink);
+
+static void devlink_dev_release(struct device *dev)
+{
+	kfree(to_devlink(dev));
+}
+
+static struct class devlink_class = {
+	.name = "devlink",
+	.owner = THIS_MODULE,
+	.dev_groups = devlink_groups,
+	.dev_release = devlink_dev_release,
+};
+
+static int devlink_add_symlinks(struct device *dev,
+				struct class_interface *class_intf)
+{
+	int ret;
+	size_t len;
+	struct device_link *link = to_devlink(dev);
+	struct device *sup = link->supplier;
+	struct device *con = link->consumer;
+	char *buf;
+
+	len = max(strlen(dev_name(sup)), strlen(dev_name(con)));
+	len += strlen("supplier:") + 1;
+	buf = kzalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier");
+	if (ret)
+		goto out;
+
+	ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer");
+	if (ret)
+		goto err_con;
+
+	snprintf(buf, len, "consumer:%s", dev_name(con));
+	ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf);
+	if (ret)
+		goto err_con_dev;
+
+	snprintf(buf, len, "supplier:%s", dev_name(sup));
+	ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf);
+	if (ret)
+		goto err_sup_dev;
+
+	goto out;
+
+err_sup_dev:
+	snprintf(buf, len, "consumer:%s", dev_name(con));
+	sysfs_remove_link(&sup->kobj, buf);
+err_con_dev:
+	sysfs_remove_link(&link->link_dev.kobj, "consumer");
+err_con:
+	sysfs_remove_link(&link->link_dev.kobj, "supplier");
+out:
+	kfree(buf);
+	return ret;
+}
+
+static void devlink_remove_symlinks(struct device *dev,
+				   struct class_interface *class_intf)
+{
+	struct device_link *link = to_devlink(dev);
+	size_t len;
+	struct device *sup = link->supplier;
+	struct device *con = link->consumer;
+	char *buf;
+
+	sysfs_remove_link(&link->link_dev.kobj, "consumer");
+	sysfs_remove_link(&link->link_dev.kobj, "supplier");
+
+	len = max(strlen(dev_name(sup)), strlen(dev_name(con)));
+	len += strlen("supplier:") + 1;
+	buf = kzalloc(len, GFP_KERNEL);
+	if (!buf) {
+		WARN(1, "Unable to properly free device link symlinks!\n");
+		return;
+	}
+
+	snprintf(buf, len, "supplier:%s", dev_name(sup));
+	sysfs_remove_link(&con->kobj, buf);
+	snprintf(buf, len, "consumer:%s", dev_name(con));
+	sysfs_remove_link(&sup->kobj, buf);
+	kfree(buf);
+}
+
+static struct class_interface devlink_class_intf = {
+	.class = &devlink_class,
+	.add_dev = devlink_add_symlinks,
+	.remove_dev = devlink_remove_symlinks,
+};
+
+static int __init devlink_class_init(void)
+{
+	int ret;
+
+	ret = class_register(&devlink_class);
+	if (ret)
+		return ret;
+
+	ret = class_interface_register(&devlink_class_intf);
+	if (ret)
+		class_unregister(&devlink_class);
+
+	return ret;
+}
+postcore_initcall(devlink_class_init);
+
 #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \
 			       DL_FLAG_AUTOREMOVE_SUPPLIER | \
 			       DL_FLAG_AUTOPROBE_CONSUMER  | \
@@ -407,13 +587,6 @@ struct device_link *device_link_add(struct device *consumer,
 
 	refcount_set(&link->rpm_active, 1);
 
-	if (flags & DL_FLAG_PM_RUNTIME) {
-		if (flags & DL_FLAG_RPM_ACTIVE)
-			refcount_inc(&link->rpm_active);
-
-		pm_runtime_new_link(consumer);
-	}
-
 	get_device(supplier);
 	link->supplier = supplier;
 	INIT_LIST_HEAD(&link->s_node);
@@ -423,6 +596,25 @@ struct device_link *device_link_add(struct device *consumer,
 	link->flags = flags;
 	kref_init(&link->kref);
 
+	link->link_dev.class = &devlink_class;
+	device_set_pm_not_required(&link->link_dev);
+	dev_set_name(&link->link_dev, "%s:%s",
+		     dev_name(supplier), dev_name(consumer));
+	if (device_register(&link->link_dev)) {
+		put_device(consumer);
+		put_device(supplier);
+		kfree(link);
+		link = NULL;
+		goto out;
+	}
+
+	if (flags & DL_FLAG_PM_RUNTIME) {
+		if (flags & DL_FLAG_RPM_ACTIVE)
+			refcount_inc(&link->rpm_active);
+
+		pm_runtime_new_link(consumer);
+	}
+
 	/* Determine the initial link state. */
 	if (flags & DL_FLAG_STATELESS)
 		link->status = DL_STATE_NONE;
@@ -545,7 +737,7 @@ static void device_link_free(struct device_link *link)
 
 	put_device(link->consumer);
 	put_device(link->supplier);
-	kfree(link);
+	device_unregister(&link->link_dev);
 }
 
 #ifdef CONFIG_SRCU
@@ -1159,6 +1351,9 @@ static void device_links_purge(struct device *dev)
 {
 	struct device_link *link, *ln;
 
+	if (dev->class == &devlink_class)
+		return;
+
 	mutex_lock(&wfs_lock);
 	list_del(&dev->links.needs_suppliers);
 	mutex_unlock(&wfs_lock);
diff --git a/include/linux/device.h b/include/linux/device.h
index 9a62f7f43d55..efad96ea17a0 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -386,34 +386,6 @@ enum device_link_state {
 #define DL_FLAG_MANAGED			BIT(6)
 #define DL_FLAG_SYNC_STATE_ONLY		BIT(7)
 
-/**
- * struct device_link - Device link representation.
- * @supplier: The device on the supplier end of the link.
- * @s_node: Hook to the supplier device's list of links to consumers.
- * @consumer: The device on the consumer end of the link.
- * @c_node: Hook to the consumer device's list of links to suppliers.
- * @status: The state of the link (with respect to the presence of drivers).
- * @flags: Link flags.
- * @rpm_active: Whether or not the consumer device is runtime-PM-active.
- * @kref: Count repeated addition of the same link.
- * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks.
- * @supplier_preactivated: Supplier has been made active before consumer probe.
- */
-struct device_link {
-	struct device *supplier;
-	struct list_head s_node;
-	struct device *consumer;
-	struct list_head c_node;
-	enum device_link_state status;
-	u32 flags;
-	refcount_t rpm_active;
-	struct kref kref;
-#ifdef CONFIG_SRCU
-	struct rcu_head rcu_head;
-#endif
-	bool supplier_preactivated; /* Owned by consumer probe. */
-};
-
 /**
  * enum dl_dev_state - Device driver presence tracking information.
  * @DL_DEV_NO_DRIVER: There is no driver attached to the device.
@@ -624,6 +596,36 @@ struct device {
 #endif
 };
 
+/**
+ * struct device_link - Device link representation.
+ * @supplier: The device on the supplier end of the link.
+ * @s_node: Hook to the supplier device's list of links to consumers.
+ * @consumer: The device on the consumer end of the link.
+ * @c_node: Hook to the consumer device's list of links to suppliers.
+ * @link_dev: device used to expose link details in sysfs
+ * @status: The state of the link (with respect to the presence of drivers).
+ * @flags: Link flags.
+ * @rpm_active: Whether or not the consumer device is runtime-PM-active.
+ * @kref: Count repeated addition of the same link.
+ * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks.
+ * @supplier_preactivated: Supplier has been made active before consumer probe.
+ */
+struct device_link {
+	struct device *supplier;
+	struct list_head s_node;
+	struct device *consumer;
+	struct list_head c_node;
+	struct device link_dev;
+	enum device_link_state status;
+	u32 flags;
+	refcount_t rpm_active;
+	struct kref kref;
+#ifdef CONFIG_SRCU
+	struct rcu_head rcu_head;
+#endif
+	bool supplier_preactivated; /* Owned by consumer probe. */
+};
+
 static inline struct device *kobj_to_dev(struct kobject *kobj)
 {
 	return container_of(kobj, struct device, kobj);
-- 
cgit v1.2.3


From 17d8dcf5330a97f6e5ae01d336eb1641782043f9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 17 Jun 2020 12:56:47 -0500
Subject: fbdev/fb.h: Use struct_size() helper in kzalloc()

Make use of the struct_size() helper instead of an open-coded version
in order to avoid any potential type mistakes.

This code was detected with the help of Coccinelle and, audited and
fixed manually.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200617175647.GA26370@embeddedor
---
 include/linux/fb.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fb.h b/include/linux/fb.h
index 3b4b2f0c6994..2b530e6d86e4 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -506,8 +506,9 @@ struct fb_info {
 };
 
 static inline struct apertures_struct *alloc_apertures(unsigned int max_num) {
-	struct apertures_struct *a = kzalloc(sizeof(struct apertures_struct)
-			+ max_num * sizeof(struct aperture), GFP_KERNEL);
+	struct apertures_struct *a;
+
+	a = kzalloc(struct_size(a, ranges, max_num), GFP_KERNEL);
 	if (!a)
 		return NULL;
 	a->count = max_num;
-- 
cgit v1.2.3


From 52fbf5bdeeef415b28b8e6cdade1e48927927f60 Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Tue, 7 Jul 2020 15:46:02 -0700
Subject: PCI: Cache ACS capability offset in device

Currently the ACS capability is being looked up at a number of places. Read
and store it once at enumeration so that it can be used by all later.  No
functional change intended.

Link: https://lore.kernel.org/r/20200707224604.3737893-2-rajatja@google.com
Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/p2pdma.c |  2 +-
 drivers/pci/pci.c    | 20 ++++++++++++++++----
 drivers/pci/pci.h    |  2 +-
 drivers/pci/probe.c  |  2 +-
 drivers/pci/quirks.c |  8 ++++----
 include/linux/pci.h  |  1 +
 6 files changed, 24 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index e8e444eeb1cd..f29a48f8fa59 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -253,7 +253,7 @@ static int pci_bridge_has_acs_redir(struct pci_dev *pdev)
 	int pos;
 	u16 ctrl;
 
-	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+	pos = pdev->acs_cap;
 	if (!pos)
 		return 0;
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index eec625f0e594..73a862782214 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -831,7 +831,7 @@ static void pci_disable_acs_redir(struct pci_dev *dev)
 	if (!pci_dev_specific_disable_acs_redir(dev))
 		return;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	pos = dev->acs_cap;
 	if (!pos) {
 		pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
 		return;
@@ -857,7 +857,7 @@ static void pci_std_enable_acs(struct pci_dev *dev)
 	u16 cap;
 	u16 ctrl;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	pos = dev->acs_cap;
 	if (!pos)
 		return;
 
@@ -883,7 +883,7 @@ static void pci_std_enable_acs(struct pci_dev *dev)
  * pci_enable_acs - enable ACS if hardware support it
  * @dev: the PCI device
  */
-void pci_enable_acs(struct pci_dev *dev)
+static void pci_enable_acs(struct pci_dev *dev)
 {
 	if (!pci_acs_enable)
 		goto disable_acs_redir;
@@ -3362,7 +3362,7 @@ static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
 	int pos;
 	u16 cap, ctrl;
 
-	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+	pos = pdev->acs_cap;
 	if (!pos)
 		return false;
 
@@ -3487,6 +3487,18 @@ bool pci_acs_path_enabled(struct pci_dev *start,
 	return true;
 }
 
+/**
+ * pci_acs_init - Initialize ACS if hardware supports it
+ * @dev: the PCI device
+ */
+void pci_acs_init(struct pci_dev *dev)
+{
+	dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+
+	if (dev->acs_cap)
+		pci_enable_acs(dev);
+}
+
 /**
  * pci_rebar_find_pos - find position of resize ctrl reg for BAR
  * @pdev: PCI device
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6d3f75867106..12fb79fbe29d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -532,7 +532,7 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 	return resource_alignment(res);
 }
 
-void pci_enable_acs(struct pci_dev *dev);
+void pci_acs_init(struct pci_dev *dev);
 #ifdef CONFIG_PCI_QUIRKS
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 int pci_dev_specific_enable_acs(struct pci_dev *dev);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 2f66988cea25..6d87066a5ecc 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2390,7 +2390,7 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_ats_init(dev);		/* Address Translation Services */
 	pci_pri_init(dev);		/* Page Request Interface */
 	pci_pasid_init(dev);		/* Process Address Space ID */
-	pci_enable_acs(dev);		/* Enable ACS P2P upstream forwarding */
+	pci_acs_init(dev);		/* Access Control Services */
 	pci_ptm_init(dev);		/* Precision Time Measurement */
 	pci_aer_init(dev);		/* Advanced Error Reporting */
 	pci_dpc_init(dev);		/* Downstream Port Containment */
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 812bfc32ecb8..b341628e4752 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4653,7 +4653,7 @@ static int pci_quirk_intel_spt_pch_acs(struct pci_dev *dev, u16 acs_flags)
 	if (!pci_quirk_intel_spt_pch_acs_match(dev))
 		return -ENOTTY;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	pos = dev->acs_cap;
 	if (!pos)
 		return -ENOTTY;
 
@@ -4961,7 +4961,7 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev)
 	if (!pci_quirk_intel_spt_pch_acs_match(dev))
 		return -ENOTTY;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	pos = dev->acs_cap;
 	if (!pos)
 		return -ENOTTY;
 
@@ -4988,7 +4988,7 @@ static int pci_quirk_disable_intel_spt_pch_acs_redir(struct pci_dev *dev)
 	if (!pci_quirk_intel_spt_pch_acs_match(dev))
 		return -ENOTTY;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	pos = dev->acs_cap;
 	if (!pos)
 		return -ENOTTY;
 
@@ -5355,7 +5355,7 @@ int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout)
 	bool found;
 	struct pci_dev *bridge = bus->self;
 
-	pos = pci_find_ext_capability(bridge, PCI_EXT_CAP_ID_ACS);
+	pos = bridge->acs_cap;
 
 	/* Disable ACS SV before initial config reads */
 	if (pos) {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c79d83304e52..a26be5332bba 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -486,6 +486,7 @@ struct pci_dev {
 #ifdef CONFIG_PCI_P2PDMA
 	struct pci_p2pdma *p2pdma;
 #endif
+	u16		acs_cap;	/* ACS Capability offset */
 	phys_addr_t	rom;		/* Physical address if not from BAR */
 	size_t		romlen;		/* Length if not from BAR */
 	char		*driver_override; /* Driver name to force a match */
-- 
cgit v1.2.3


From 99b50be9d8ec9ef319cc7d5de07f4d405fac7764 Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Tue, 7 Jul 2020 15:46:03 -0700
Subject: PCI: Treat "external-facing" devices themselves as internal

"External-facing" devices are internal devices that expose PCIe hierarchies
such as Thunderbolt outside the platform [1].  Previously these internal
devices were marked as "untrusted" the same as devices downstream from
them.

Use the ACPI or DT information to identify external-facing devices, but
only mark the devices *downstream* from them as "untrusted" [2].  The
external-facing device itself is no longer marked as untrusted.

[1] https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports#identifying-externally-exposed-pcie-root-ports
[2] https://lore.kernel.org/linux-pci/20200610230906.GA1528594@bjorn-Precision-5520/
Link: https://lore.kernel.org/r/20200707224604.3737893-3-rajatja@google.com
Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/iommu/intel/iommu.c | 6 +++---
 drivers/pci/of.c            | 2 +-
 drivers/pci/pci-acpi.c      | 9 ++++-----
 drivers/pci/probe.c         | 2 +-
 include/linux/pci.h         | 6 ++++++
 5 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 9129663a7406..d23ce26b8833 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4730,12 +4730,12 @@ const struct attribute_group *intel_iommu_groups[] = {
 	NULL,
 };
 
-static inline bool has_untrusted_dev(void)
+static inline bool has_external_pci(void)
 {
 	struct pci_dev *pdev = NULL;
 
 	for_each_pci_dev(pdev)
-		if (pdev->untrusted)
+		if (pdev->external_facing)
 			return true;
 
 	return false;
@@ -4743,7 +4743,7 @@ static inline bool has_untrusted_dev(void)
 
 static int __init platform_optin_force_iommu(void)
 {
-	if (!dmar_platform_optin() || no_platform_optin || !has_untrusted_dev())
+	if (!dmar_platform_optin() || no_platform_optin || !has_external_pci())
 		return 0;
 
 	if (no_iommu || dmar_disabled)
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 27839cd2459f..22727fc9558d 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -42,7 +42,7 @@ void pci_set_bus_of_node(struct pci_bus *bus)
 	} else {
 		node = of_node_get(bus->self->dev.of_node);
 		if (node && of_property_read_bool(node, "external-facing"))
-			bus->self->untrusted = true;
+			bus->self->external_facing = true;
 	}
 
 	bus->dev.of_node = node;
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 7224b1e5f2a8..54520d34e27e 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1213,7 +1213,7 @@ static void pci_acpi_optimize_delay(struct pci_dev *pdev,
 	ACPI_FREE(obj);
 }
 
-static void pci_acpi_set_untrusted(struct pci_dev *dev)
+static void pci_acpi_set_external_facing(struct pci_dev *dev)
 {
 	u8 val;
 
@@ -1224,11 +1224,10 @@ static void pci_acpi_set_untrusted(struct pci_dev *dev)
 
 	/*
 	 * These root ports expose PCIe (including DMA) outside of the
-	 * system so make sure we treat them and everything behind as
-	 * untrusted.
+	 * system.  Everything downstream from them is external.
 	 */
 	if (val)
-		dev->untrusted = 1;
+		dev->external_facing = 1;
 }
 
 static void pci_acpi_setup(struct device *dev)
@@ -1240,7 +1239,7 @@ static void pci_acpi_setup(struct device *dev)
 		return;
 
 	pci_acpi_optimize_delay(pci_dev, adev->handle);
-	pci_acpi_set_untrusted(pci_dev);
+	pci_acpi_set_external_facing(pci_dev);
 	pci_acpi_add_edr_notifier(pci_dev);
 
 	pci_acpi_add_pm_notifier(adev, pci_dev);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6d87066a5ecc..8c40c00413e7 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1552,7 +1552,7 @@ static void set_pcie_untrusted(struct pci_dev *dev)
 	 * untrusted as well.
 	 */
 	parent = pci_upstream_bridge(dev);
-	if (parent && parent->untrusted)
+	if (parent && (parent->untrusted || parent->external_facing))
 		dev->untrusted = true;
 }
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index a26be5332bba..7a40cd5caed0 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -432,6 +432,12 @@ struct pci_dev {
 	 * mappings to make sure they cannot access arbitrary memory.
 	 */
 	unsigned int	untrusted:1;
+	/*
+	 * Info from the platform, e.g., ACPI or device tree, may mark a
+	 * device as "external-facing".  An external-facing device is
+	 * itself internal but devices downstream from it are external.
+	 */
+	unsigned int	external_facing:1;
 	unsigned int	broken_intx_masking:1;	/* INTx masking can't be used */
 	unsigned int	io_window_1k:1;		/* Intel bridge 1K I/O windows */
 	unsigned int	irq_managed:1;
-- 
cgit v1.2.3


From 3b50a6e536d2d843857ffe5f923eff7be4222afe Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Wed, 1 Jul 2020 15:53:49 -0700
Subject: mm/hmm: provide the page mapping order in hmm_range_fault()

hmm_range_fault() returns an array of page frame numbers and flags for how
the pages are mapped in the requested process' page tables. The PFN can be
used to get the struct page with hmm_pfn_to_page() and the page size order
can be determined with compound_order(page).

However, if the page is larger than order 0 (PAGE_SIZE), there is no
indication that a compound page is mapped by the CPU using a larger page
size. Without this information, the caller can't safely use a large device
PTE to map the compound page because the CPU might be using smaller PTEs
with different read/write permissions.

Add a new function hmm_pfn_to_map_order() to return the mapping size order
so that callers know the pages are being mapped with consistent
permissions and a large device page table mapping can be used if one is
available.

This will allow devices to optimize mapping the page into HW by avoiding
or batching work for huge pages. For instance the dma_map can be done with
a high order directly.

Link: https://lore.kernel.org/r/20200701225352.9649-3-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/hmm.h | 24 ++++++++++++++++++++++--
 mm/hmm.c            | 16 +++++++++++++---
 2 files changed, 35 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index f4a09ed223ac..866a0fa104c4 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -37,16 +37,17 @@
  *                     will fail. Must be combined with HMM_PFN_REQ_FAULT.
  */
 enum hmm_pfn_flags {
-	/* Output flags */
+	/* Output fields and flags */
 	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
 	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
+	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
 
 	/* Input flags */
 	HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
 	HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
 
-	HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR,
+	HMM_PFN_FLAGS = 0xFFUL << HMM_PFN_ORDER_SHIFT,
 };
 
 /*
@@ -61,6 +62,25 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
 	return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS);
 }
 
+/*
+ * hmm_pfn_to_map_order() - return the CPU mapping size order
+ *
+ * This is optionally useful to optimize processing of the pfn result
+ * array. It indicates that the page starts at the order aligned VA and is
+ * 1<<order bytes long.  Every pfn within an high order page will have the
+ * same pfn flags, both access protections and the map_order.  The caller must
+ * be careful with edge cases as the start and end VA of the given page may
+ * extend past the range used with hmm_range_fault().
+ *
+ * This must be called under the caller 'user_lock' after a successful
+ * mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID
+ * already.
+ */
+static inline unsigned int hmm_pfn_to_map_order(unsigned long hmm_pfn)
+{
+	return (hmm_pfn >> HMM_PFN_ORDER_SHIFT) & 0x1F;
+}
+
 /*
  * struct hmm_range - track invalidation lock on virtual address range
  *
diff --git a/mm/hmm.c b/mm/hmm.c
index e9a545751108..0809baee49d0 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -165,12 +165,19 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
 	return hmm_pfns_fill(addr, end, range, 0);
 }
 
+static inline unsigned long hmm_pfn_flags_order(unsigned long order)
+{
+	return order << HMM_PFN_ORDER_SHIFT;
+}
+
 static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
 						 pmd_t pmd)
 {
 	if (pmd_protnone(pmd))
 		return 0;
-	return pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
+	return (pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
+				 HMM_PFN_VALID) |
+	       hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -389,7 +396,9 @@ static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
 {
 	if (!pud_present(pud))
 		return 0;
-	return pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
+	return (pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
+				 HMM_PFN_VALID) |
+	       hmm_pfn_flags_order(PUD_SHIFT - PAGE_SHIFT);
 }
 
 static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
@@ -474,7 +483,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 
 	i = (start - range->start) >> PAGE_SHIFT;
 	pfn_req_flags = range->hmm_pfns[i];
-	cpu_flags = pte_to_hmm_pfn_flags(range, entry);
+	cpu_flags = pte_to_hmm_pfn_flags(range, entry) |
+		    hmm_pfn_flags_order(huge_page_order(hstate_vma(vma)));
 	required_fault =
 		hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
 	if (required_fault) {
-- 
cgit v1.2.3


From a2b992c828f7651db369ba8f0eb0818d70232636 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 9 Jul 2020 17:42:44 -0700
Subject: debugfs: make sure we can remove u32_array files cleanly

debugfs_create_u32_array() allocates a small structure to wrap
the data and size information about the array. If users ever
try to remove the file this leads to a leak since nothing ever
frees this wrapper.

That said there are no upstream users of debugfs_create_u32_array()
that'd remove a u32 array file (we only have one u32 array user in
CMA), so there is no real bug here.

Make callers pass a wrapper they allocated. This way the lifetime
management of the wrapper is on the caller, and we can avoid the
potential leak in debugfs.

CC: Chucheng Luo <luochucheng@vivo.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/filesystems/debugfs.rst | 12 ++++++++----
 fs/debugfs/file.c                     | 27 +++++++--------------------
 include/linux/debugfs.h               | 12 +++++++++---
 mm/cma.h                              |  3 +++
 mm/cma_debug.c                        |  7 ++++---
 5 files changed, 31 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index 1da7a4b7383d..728ab57a611a 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -185,13 +185,17 @@ byte offsets over a base for the register block.
 
 If you want to dump an u32 array in debugfs, you can create file with::
 
+    struct debugfs_u32_array {
+	u32 *array;
+	u32 n_elements;
+    };
+
     void debugfs_create_u32_array(const char *name, umode_t mode,
 			struct dentry *parent,
-			u32 *array, u32 elements);
+			struct debugfs_u32_array *array);
 
-The "array" argument provides data, and the "elements" argument is
-the number of elements in the array. Note: Once array is created its
-size can not be changed.
+The "array" argument wraps a pointer to the array's data and the number
+of its elements. Note: Once array is created its size can not be changed.
 
 There is a helper function to create device related seq_file::
 
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index ae49a55bda00..d0ed71f37511 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -918,11 +918,6 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_blob);
 
-struct array_data {
-	void *array;
-	u32 elements;
-};
-
 static size_t u32_format_array(char *buf, size_t bufsize,
 			       u32 *array, int array_size)
 {
@@ -943,8 +938,8 @@ static size_t u32_format_array(char *buf, size_t bufsize,
 
 static int u32_array_open(struct inode *inode, struct file *file)
 {
-	struct array_data *data = inode->i_private;
-	int size, elements = data->elements;
+	struct debugfs_u32_array *data = inode->i_private;
+	int size, elements = data->n_elements;
 	char *buf;
 
 	/*
@@ -959,7 +954,7 @@ static int u32_array_open(struct inode *inode, struct file *file)
 	buf[size] = 0;
 
 	file->private_data = buf;
-	u32_format_array(buf, size, data->array, data->elements);
+	u32_format_array(buf, size, data->array, data->n_elements);
 
 	return nonseekable_open(inode, file);
 }
@@ -996,8 +991,7 @@ static const struct file_operations u32_array_fops = {
  * @parent: a pointer to the parent dentry for this file.  This should be a
  *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
- * @array: u32 array that provides data.
- * @elements: total number of elements in the array.
+ * @array: wrapper struct containing data pointer and size of the array.
  *
  * This function creates a file in debugfs with the given name that exports
  * @array as data. If the @mode variable is so set it can be read from.
@@ -1005,17 +999,10 @@ static const struct file_operations u32_array_fops = {
  * Once array is created its size can not be changed.
  */
 void debugfs_create_u32_array(const char *name, umode_t mode,
-			      struct dentry *parent, u32 *array, u32 elements)
+			      struct dentry *parent,
+			      struct debugfs_u32_array *array)
 {
-	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
-
-	if (data == NULL)
-		return;
-
-	data->array = array;
-	data->elements = elements;
-
-	debugfs_create_file_unsafe(name, mode, parent, data, &u32_array_fops);
+	debugfs_create_file_unsafe(name, mode, parent, array, &u32_array_fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
 
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 63cb3606dea7..851dd1f9a8a5 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -38,6 +38,11 @@ struct debugfs_regset32 {
 	struct device *dev;	/* Optional device for Runtime PM */
 };
 
+struct debugfs_u32_array {
+	u32 *array;
+	u32 n_elements;
+};
+
 extern struct dentry *arch_debugfs_dir;
 
 #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt)		\
@@ -136,7 +141,8 @@ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
 			  int nregs, void __iomem *base, char *prefix);
 
 void debugfs_create_u32_array(const char *name, umode_t mode,
-			      struct dentry *parent, u32 *array, u32 elements);
+			      struct dentry *parent,
+			      struct debugfs_u32_array *array);
 
 struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
 					   struct dentry *parent,
@@ -316,8 +322,8 @@ static inline bool debugfs_initialized(void)
 }
 
 static inline void debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent, u32 *array,
-					    u32 elements)
+					    struct dentry *parent,
+					    struct debugfs_u32_array *array)
 {
 }
 
diff --git a/mm/cma.h b/mm/cma.h
index 33c0b517733c..6698fa63279b 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -2,6 +2,8 @@
 #ifndef __MM_CMA_H__
 #define __MM_CMA_H__
 
+#include <linux/debugfs.h>
+
 struct cma {
 	unsigned long   base_pfn;
 	unsigned long   count;
@@ -11,6 +13,7 @@ struct cma {
 #ifdef CONFIG_CMA_DEBUGFS
 	struct hlist_head mem_head;
 	spinlock_t mem_head_lock;
+	struct debugfs_u32_array dfs_bitmap;
 #endif
 	const char *name;
 };
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index 4e6cbe2f586e..d5bf8aa34fdc 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -164,7 +164,6 @@ static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry)
 {
 	struct dentry *tmp;
 	char name[16];
-	int u32s;
 
 	scnprintf(name, sizeof(name), "cma-%s", cma->name);
 
@@ -180,8 +179,10 @@ static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry)
 	debugfs_create_file("used", 0444, tmp, cma, &cma_used_fops);
 	debugfs_create_file("maxchunk", 0444, tmp, cma, &cma_maxchunk_fops);
 
-	u32s = DIV_ROUND_UP(cma_bitmap_maxno(cma), BITS_PER_BYTE * sizeof(u32));
-	debugfs_create_u32_array("bitmap", 0444, tmp, (u32 *)cma->bitmap, u32s);
+	cma->dfs_bitmap.array = (u32 *)cma->bitmap;
+	cma->dfs_bitmap.n_elements = DIV_ROUND_UP(cma_bitmap_maxno(cma),
+						  BITS_PER_BYTE * sizeof(u32));
+	debugfs_create_u32_array("bitmap", 0444, tmp, &cma->dfs_bitmap);
 }
 
 static int __init cma_debugfs_init(void)
-- 
cgit v1.2.3


From cc4e3835eff474aa274d6e1d18f69d9d296d3b76 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 9 Jul 2020 17:42:46 -0700
Subject: udp_tunnel: add central NIC RX port offload infrastructure

Cater to devices which:
 (a) may want to sleep in the callbacks;
 (b) only have IPv4 support;
 (c) need all the programming to happen while the netdev is up.

Drivers attach UDP tunnel offload info struct to their netdevs,
where they declare how many UDP ports of various tunnel types
they support. Core takes care of tracking which ports to offload.

Use a fixed-size array since this matches what almost all drivers
do, and avoids a complexity and uncertainty around memory allocations
in an atomic context.

Make sure that tunnel drivers don't try to replay the ports when
new NIC netdev is registered. Automatic replays would mess up
reference counting, and will be removed completely once all drivers
are converted.

v4:
 - use a #define NULL to avoid build issues with CONFIG_INET=n.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c       |   6 +-
 drivers/net/vxlan.c        |   6 +-
 include/linux/netdevice.h  |   8 +
 include/net/udp_tunnel.h   | 137 ++++++++
 net/ipv4/Makefile          |   3 +-
 net/ipv4/udp_tunnel.c      | 224 -------------
 net/ipv4/udp_tunnel_core.c | 224 +++++++++++++
 net/ipv4/udp_tunnel_nic.c  | 821 +++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_tunnel_stub.c |   7 +
 9 files changed, 1207 insertions(+), 229 deletions(-)
 delete mode 100644 net/ipv4/udp_tunnel.c
 create mode 100644 net/ipv4/udp_tunnel_core.c
 create mode 100644 net/ipv4/udp_tunnel_nic.c
 create mode 100644 net/ipv4/udp_tunnel_stub.c

(limited to 'include/linux')

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index e3d074008da2..49b00def2eef 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1796,9 +1796,11 @@ static int geneve_netdevice_event(struct notifier_block *unused,
 	    event == NETDEV_UDP_TUNNEL_DROP_INFO) {
 		geneve_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO);
 	} else if (event == NETDEV_UNREGISTER) {
-		geneve_offload_rx_ports(dev, false);
+		if (!dev->udp_tunnel_nic_info)
+			geneve_offload_rx_ports(dev, false);
 	} else if (event == NETDEV_REGISTER) {
-		geneve_offload_rx_ports(dev, true);
+		if (!dev->udp_tunnel_nic_info)
+			geneve_offload_rx_ports(dev, true);
 	}
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 89d85dcb200e..a43c97b13924 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -4477,10 +4477,12 @@ static int vxlan_netdevice_event(struct notifier_block *unused,
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 
 	if (event == NETDEV_UNREGISTER) {
-		vxlan_offload_rx_ports(dev, false);
+		if (!dev->udp_tunnel_nic_info)
+			vxlan_offload_rx_ports(dev, false);
 		vxlan_handle_lowerdev_unregister(vn, dev);
 	} else if (event == NETDEV_REGISTER) {
-		vxlan_offload_rx_ports(dev, true);
+		if (!dev->udp_tunnel_nic_info)
+			vxlan_offload_rx_ports(dev, true);
 	} else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO ||
 		   event == NETDEV_UDP_TUNNEL_DROP_INFO) {
 		vxlan_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 39e28e11863c..ac2cd3f49aba 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -65,6 +65,8 @@ struct wpan_dev;
 struct mpls_dev;
 /* UDP Tunnel offloads */
 struct udp_tunnel_info;
+struct udp_tunnel_nic_info;
+struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
 
@@ -1836,6 +1838,10 @@ enum netdev_priv_flags {
  *
  *	@macsec_ops:    MACsec offloading ops
  *
+ *	@udp_tunnel_nic_info:	static structure describing the UDP tunnel
+ *				offload capabilities of the device
+ *	@udp_tunnel_nic:	UDP tunnel offload state
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2134,6 +2140,8 @@ struct net_device {
 	/* MACsec management functions */
 	const struct macsec_ops *macsec_ops;
 #endif
+	const struct udp_tunnel_nic_info	*udp_tunnel_nic_info;
+	struct udp_tunnel_nic	*udp_tunnel_nic;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 0615e25f041c..ee34619e4cfa 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -115,6 +115,7 @@ struct udp_tunnel_info {
 	unsigned short type;
 	sa_family_t sa_family;
 	__be16 port;
+	u8 hw_priv;
 };
 
 /* Notify network devices of offloadable types */
@@ -181,4 +182,140 @@ static inline void udp_tunnel_encap_enable(struct socket *sock)
 		udp_encap_enable();
 }
 
+#define UDP_TUNNEL_NIC_MAX_TABLES	4
+
+enum udp_tunnel_nic_info_flags {
+	/* Device callbacks may sleep */
+	UDP_TUNNEL_NIC_INFO_MAY_SLEEP	= BIT(0),
+	/* Device only supports offloads when it's open, all ports
+	 * will be removed before close and re-added after open.
+	 */
+	UDP_TUNNEL_NIC_INFO_OPEN_ONLY	= BIT(1),
+	/* Device supports only IPv4 tunnels */
+	UDP_TUNNEL_NIC_INFO_IPV4_ONLY	= BIT(2),
+};
+
+/**
+ * struct udp_tunnel_nic_info - driver UDP tunnel offload information
+ * @set_port:	callback for adding a new port
+ * @unset_port:	callback for removing a port
+ * @sync_table:	callback for syncing the entire port table at once
+ * @flags:	device flags from enum udp_tunnel_nic_info_flags
+ * @tables:	UDP port tables this device has
+ * @tables.n_entries:		number of entries in this table
+ * @tables.tunnel_types:	types of tunnels this table accepts
+ *
+ * Drivers are expected to provide either @set_port and @unset_port callbacks
+ * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
+ *
+ * Known limitations:
+ *  - UDP tunnel port notifications are fundamentally best-effort -
+ *    it is likely the driver will both see skbs which use a UDP tunnel port,
+ *    while not being a tunneled skb, and tunnel skbs from other ports -
+ *    drivers should only use these ports for non-critical RX-side offloads,
+ *    e.g. the checksum offload;
+ *  - none of the devices care about the socket family at present, so we don't
+ *    track it. Please extend this code if you care.
+ */
+struct udp_tunnel_nic_info {
+	/* one-by-one */
+	int (*set_port)(struct net_device *dev,
+			unsigned int table, unsigned int entry,
+			struct udp_tunnel_info *ti);
+	int (*unset_port)(struct net_device *dev,
+			  unsigned int table, unsigned int entry,
+			  struct udp_tunnel_info *ti);
+
+	/* all at once */
+	int (*sync_table)(struct net_device *dev, unsigned int table);
+
+	unsigned int flags;
+
+	struct udp_tunnel_nic_table_info {
+		unsigned int n_entries;
+		unsigned int tunnel_types;
+	} tables[UDP_TUNNEL_NIC_MAX_TABLES];
+};
+
+/* UDP tunnel module dependencies
+ *
+ * Tunnel drivers are expected to have a hard dependency on the udp_tunnel
+ * module. NIC drivers are not, they just attach their
+ * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come.
+ * Loading a tunnel driver will cause the udp_tunnel module to be loaded
+ * and only then will all the required state structures be allocated.
+ * Since we want a weak dependency from the drivers and the core to udp_tunnel
+ * we call things through the following stubs.
+ */
+struct udp_tunnel_nic_ops {
+	void (*get_port)(struct net_device *dev, unsigned int table,
+			 unsigned int idx, struct udp_tunnel_info *ti);
+	void (*set_port_priv)(struct net_device *dev, unsigned int table,
+			      unsigned int idx, u8 priv);
+	void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti);
+	void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti);
+	void (*reset_ntf)(struct net_device *dev);
+};
+
+#ifdef CONFIG_INET
+extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
+#else
+#define udp_tunnel_nic_ops	((struct udp_tunnel_nic_ops *)NULL)
+#endif
+
+static inline void
+udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
+			unsigned int idx, struct udp_tunnel_info *ti)
+{
+	/* This helper is used from .sync_table, we indicate empty entries
+	 * by zero'ed @ti. Drivers which need to know the details of a port
+	 * when it gets deleted should use the .set_port / .unset_port
+	 * callbacks.
+	 * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings.
+	 */
+	memset(ti, 0, sizeof(*ti));
+
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->get_port(dev, table, idx, ti);
+}
+
+static inline void
+udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
+			     unsigned int idx, u8 priv)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
+}
+
+static inline void
+udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->add_port(dev, ti);
+}
+
+static inline void
+udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->del_port(dev, ti);
+}
+
+/**
+ * udp_tunnel_nic_reset_ntf() - device-originating reset notification
+ * @dev: network interface device structure
+ *
+ * Called by the driver to inform the core that the entire UDP tunnel port
+ * state has been lost, usually due to device reset. Core will assume device
+ * forgot all the ports and issue .set_port and .sync_table callbacks as
+ * necessary.
+ *
+ * This function must be called with rtnl lock held, and will issue all
+ * the callbacks before returning.
+ */
+static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->reset_ntf(dev);
+}
 #endif
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 9e1a186a3671..5b77a46885b9 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -14,7 +14,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
-	     metrics.o netlink.o nexthop.o
+	     metrics.o netlink.o nexthop.o udp_tunnel_stub.o
 
 obj-$(CONFIG_BPFILTER) += bpfilter/
 
@@ -29,6 +29,7 @@ gre-y := gre_demux.o
 obj-$(CONFIG_NET_FOU) += fou.o
 obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
 obj-$(CONFIG_NET_IPGRE) += ip_gre.o
+udp_tunnel-y := udp_tunnel_core.o udp_tunnel_nic.o
 obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o
 obj-$(CONFIG_NET_IPVTI) += ip_vti.o
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
deleted file mode 100644
index 3eecba0874aa..000000000000
--- a/net/ipv4/udp_tunnel.c
+++ /dev/null
@@ -1,224 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/socket.h>
-#include <linux/udp.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <net/dst_metadata.h>
-#include <net/net_namespace.h>
-#include <net/udp.h>
-#include <net/udp_tunnel.h>
-
-int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
-		     struct socket **sockp)
-{
-	int err;
-	struct socket *sock = NULL;
-	struct sockaddr_in udp_addr;
-
-	err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock);
-	if (err < 0)
-		goto error;
-
-	if (cfg->bind_ifindex) {
-		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true);
-		if (err < 0)
-			goto error;
-	}
-
-	udp_addr.sin_family = AF_INET;
-	udp_addr.sin_addr = cfg->local_ip;
-	udp_addr.sin_port = cfg->local_udp_port;
-	err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
-			  sizeof(udp_addr));
-	if (err < 0)
-		goto error;
-
-	if (cfg->peer_udp_port) {
-		udp_addr.sin_family = AF_INET;
-		udp_addr.sin_addr = cfg->peer_ip;
-		udp_addr.sin_port = cfg->peer_udp_port;
-		err = kernel_connect(sock, (struct sockaddr *)&udp_addr,
-				     sizeof(udp_addr), 0);
-		if (err < 0)
-			goto error;
-	}
-
-	sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
-
-	*sockp = sock;
-	return 0;
-
-error:
-	if (sock) {
-		kernel_sock_shutdown(sock, SHUT_RDWR);
-		sock_release(sock);
-	}
-	*sockp = NULL;
-	return err;
-}
-EXPORT_SYMBOL(udp_sock_create4);
-
-void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
-			   struct udp_tunnel_sock_cfg *cfg)
-{
-	struct sock *sk = sock->sk;
-
-	/* Disable multicast loopback */
-	inet_sk(sk)->mc_loop = 0;
-
-	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
-	inet_inc_convert_csum(sk);
-
-	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
-
-	udp_sk(sk)->encap_type = cfg->encap_type;
-	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
-	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
-	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
-	udp_sk(sk)->gro_receive = cfg->gro_receive;
-	udp_sk(sk)->gro_complete = cfg->gro_complete;
-
-	udp_tunnel_encap_enable(sock);
-}
-EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
-
-void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
-			     unsigned short type)
-{
-	struct sock *sk = sock->sk;
-	struct udp_tunnel_info ti;
-
-	if (!dev->netdev_ops->ndo_udp_tunnel_add ||
-	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-		return;
-
-	ti.type = type;
-	ti.sa_family = sk->sk_family;
-	ti.port = inet_sk(sk)->inet_sport;
-
-	dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
-
-void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
-			     unsigned short type)
-{
-	struct sock *sk = sock->sk;
-	struct udp_tunnel_info ti;
-
-	if (!dev->netdev_ops->ndo_udp_tunnel_del ||
-	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-		return;
-
-	ti.type = type;
-	ti.sa_family = sk->sk_family;
-	ti.port = inet_sk(sk)->inet_sport;
-
-	dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port);
-
-/* Notify netdevs that UDP port started listening */
-void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
-{
-	struct sock *sk = sock->sk;
-	struct net *net = sock_net(sk);
-	struct udp_tunnel_info ti;
-	struct net_device *dev;
-
-	ti.type = type;
-	ti.sa_family = sk->sk_family;
-	ti.port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (!dev->netdev_ops->ndo_udp_tunnel_add)
-			continue;
-		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-			continue;
-		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
-
-/* Notify netdevs that UDP port is no more listening */
-void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
-{
-	struct sock *sk = sock->sk;
-	struct net *net = sock_net(sk);
-	struct udp_tunnel_info ti;
-	struct net_device *dev;
-
-	ti.type = type;
-	ti.sa_family = sk->sk_family;
-	ti.port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (!dev->netdev_ops->ndo_udp_tunnel_del)
-			continue;
-		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-			continue;
-		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
-
-void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
-			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
-			 __be16 df, __be16 src_port, __be16 dst_port,
-			 bool xnet, bool nocheck)
-{
-	struct udphdr *uh;
-
-	__skb_push(skb, sizeof(*uh));
-	skb_reset_transport_header(skb);
-	uh = udp_hdr(skb);
-
-	uh->dest = dst_port;
-	uh->source = src_port;
-	uh->len = htons(skb->len);
-
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-
-	udp_set_csum(nocheck, skb, src, dst, skb->len);
-
-	iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet);
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
-
-void udp_tunnel_sock_release(struct socket *sock)
-{
-	rcu_assign_sk_user_data(sock->sk, NULL);
-	kernel_sock_shutdown(sock, SHUT_RDWR);
-	sock_release(sock);
-}
-EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
-
-struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb,  unsigned short family,
-				    __be16 flags, __be64 tunnel_id, int md_size)
-{
-	struct metadata_dst *tun_dst;
-	struct ip_tunnel_info *info;
-
-	if (family == AF_INET)
-		tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size);
-	else
-		tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size);
-	if (!tun_dst)
-		return NULL;
-
-	info = &tun_dst->u.tun_info;
-	info->key.tp_src = udp_hdr(skb)->source;
-	info->key.tp_dst = udp_hdr(skb)->dest;
-	if (udp_hdr(skb)->check)
-		info->key.tun_flags |= TUNNEL_CSUM;
-	return tun_dst;
-}
-EXPORT_SYMBOL_GPL(udp_tun_rx_dst);
-
-MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
new file mode 100644
index 000000000000..3eecba0874aa
--- /dev/null
+++ b/net/ipv4/udp_tunnel_core.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <net/dst_metadata.h>
+#include <net/net_namespace.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+
+int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp)
+{
+	int err;
+	struct socket *sock = NULL;
+	struct sockaddr_in udp_addr;
+
+	err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock);
+	if (err < 0)
+		goto error;
+
+	if (cfg->bind_ifindex) {
+		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true);
+		if (err < 0)
+			goto error;
+	}
+
+	udp_addr.sin_family = AF_INET;
+	udp_addr.sin_addr = cfg->local_ip;
+	udp_addr.sin_port = cfg->local_udp_port;
+	err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
+			  sizeof(udp_addr));
+	if (err < 0)
+		goto error;
+
+	if (cfg->peer_udp_port) {
+		udp_addr.sin_family = AF_INET;
+		udp_addr.sin_addr = cfg->peer_ip;
+		udp_addr.sin_port = cfg->peer_udp_port;
+		err = kernel_connect(sock, (struct sockaddr *)&udp_addr,
+				     sizeof(udp_addr), 0);
+		if (err < 0)
+			goto error;
+	}
+
+	sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
+
+	*sockp = sock;
+	return 0;
+
+error:
+	if (sock) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		sock_release(sock);
+	}
+	*sockp = NULL;
+	return err;
+}
+EXPORT_SYMBOL(udp_sock_create4);
+
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *cfg)
+{
+	struct sock *sk = sock->sk;
+
+	/* Disable multicast loopback */
+	inet_sk(sk)->mc_loop = 0;
+
+	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+	inet_inc_convert_csum(sk);
+
+	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
+
+	udp_sk(sk)->encap_type = cfg->encap_type;
+	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
+	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
+	udp_sk(sk)->gro_receive = cfg->gro_receive;
+	udp_sk(sk)->gro_complete = cfg->gro_complete;
+
+	udp_tunnel_encap_enable(sock);
+}
+EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
+
+void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_add ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
+
+void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_del ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port);
+
+/* Notify netdevs that UDP port started listening */
+void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_add)
+			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
+
+/* Notify netdevs that UDP port is no more listening */
+void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_del)
+			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
+
+void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
+			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
+			 __be16 df, __be16 src_port, __be16 dst_port,
+			 bool xnet, bool nocheck)
+{
+	struct udphdr *uh;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+	uh->len = htons(skb->len);
+
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
+	udp_set_csum(nocheck, skb, src, dst, skb->len);
+
+	iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
+
+void udp_tunnel_sock_release(struct socket *sock)
+{
+	rcu_assign_sk_user_data(sock->sk, NULL);
+	kernel_sock_shutdown(sock, SHUT_RDWR);
+	sock_release(sock);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
+
+struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb,  unsigned short family,
+				    __be16 flags, __be64 tunnel_id, int md_size)
+{
+	struct metadata_dst *tun_dst;
+	struct ip_tunnel_info *info;
+
+	if (family == AF_INET)
+		tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size);
+	else
+		tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size);
+	if (!tun_dst)
+		return NULL;
+
+	info = &tun_dst->u.tun_info;
+	info->key.tp_src = udp_hdr(skb)->source;
+	info->key.tp_dst = udp_hdr(skb)->dest;
+	if (udp_hdr(skb)->check)
+		info->key.tun_flags |= TUNNEL_CSUM;
+	return tun_dst;
+}
+EXPORT_SYMBOL_GPL(udp_tun_rx_dst);
+
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
new file mode 100644
index 000000000000..056cfe0b770e
--- /dev/null
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2020 Facebook Inc.
+
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <net/udp_tunnel.h>
+
+enum udp_tunnel_nic_table_entry_flags {
+	UDP_TUNNEL_NIC_ENTRY_ADD	= BIT(0),
+	UDP_TUNNEL_NIC_ENTRY_DEL	= BIT(1),
+	UDP_TUNNEL_NIC_ENTRY_OP_FAIL	= BIT(2),
+	UDP_TUNNEL_NIC_ENTRY_FROZEN	= BIT(3),
+};
+
+struct udp_tunnel_nic_table_entry {
+	__be16 port;
+	u8 type;
+	u8 use_cnt;
+	u8 flags;
+	u8 hw_priv;
+};
+
+/**
+ * struct udp_tunnel_nic - UDP tunnel port offload state
+ * @work:	async work for talking to hardware from process context
+ * @dev:	netdev pointer
+ * @need_sync:	at least one port start changed
+ * @need_replay: space was freed, we need a replay of all ports
+ * @work_pending: @work is currently scheduled
+ * @n_tables:	number of tables under @entries
+ * @missed:	bitmap of tables which overflown
+ * @entries:	table of tables of ports currently offloaded
+ */
+struct udp_tunnel_nic {
+	struct work_struct work;
+
+	struct net_device *dev;
+
+	u8 need_sync:1;
+	u8 need_replay:1;
+	u8 work_pending:1;
+
+	unsigned int n_tables;
+	unsigned long missed;
+	struct udp_tunnel_nic_table_entry **entries;
+};
+
+/* We ensure all work structs are done using driver state, but not the code.
+ * We need a workqueue we can flush before module gets removed.
+ */
+static struct workqueue_struct *udp_tunnel_nic_workqueue;
+
+static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type)
+{
+	switch (type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		return "vxlan";
+	case UDP_TUNNEL_TYPE_GENEVE:
+		return "geneve";
+	case UDP_TUNNEL_TYPE_VXLAN_GPE:
+		return "vxlan-gpe";
+	default:
+		return "unknown";
+	}
+}
+
+static bool
+udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry)
+{
+	return entry->use_cnt == 0 && !entry->flags;
+}
+
+static bool
+udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry)
+{
+	return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN;
+}
+
+static void
+udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry)
+{
+	if (!udp_tunnel_nic_entry_is_free(entry))
+		entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN;
+}
+
+static void
+udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry)
+{
+	entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN;
+}
+
+static bool
+udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry)
+{
+	return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD |
+			       UDP_TUNNEL_NIC_ENTRY_DEL);
+}
+
+static void
+udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn,
+			   struct udp_tunnel_nic_table_entry *entry,
+			   unsigned int flag)
+{
+	entry->flags |= flag;
+	utn->need_sync = 1;
+}
+
+static void
+udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry,
+			     struct udp_tunnel_info *ti)
+{
+	memset(ti, 0, sizeof(*ti));
+	ti->port = entry->port;
+	ti->type = entry->type;
+	ti->hw_priv = entry->hw_priv;
+}
+
+static bool
+udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++)
+			if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j]))
+				return false;
+	return true;
+}
+
+static bool
+udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_table_info *table;
+	unsigned int i, j;
+
+	if (!utn->missed)
+		return false;
+
+	for (i = 0; i < utn->n_tables; i++) {
+		table = &dev->udp_tunnel_nic_info->tables[i];
+		if (!test_bit(i, &utn->missed))
+			continue;
+
+		for (j = 0; j < table->n_entries; j++)
+			if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j]))
+				return true;
+	}
+
+	return false;
+}
+
+static void
+__udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
+			  unsigned int idx, struct udp_tunnel_info *ti)
+{
+	struct udp_tunnel_nic_table_entry *entry;
+	struct udp_tunnel_nic *utn;
+
+	utn = dev->udp_tunnel_nic;
+	entry = &utn->entries[table][idx];
+
+	if (entry->use_cnt)
+		udp_tunnel_nic_ti_from_entry(entry, ti);
+}
+
+static void
+__udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
+			       unsigned int idx, u8 priv)
+{
+	dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv;
+}
+
+static void
+udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry,
+				 int err)
+{
+	bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
+
+	WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD &&
+		     entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL);
+
+	if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD &&
+	    (!err || (err == -EEXIST && dodgy)))
+		entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD;
+
+	if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL &&
+	    (!err || (err == -ENOENT && dodgy)))
+		entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL;
+
+	if (!err)
+		entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
+	else
+		entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
+}
+
+static void
+udp_tunnel_nic_device_sync_one(struct net_device *dev,
+			       struct udp_tunnel_nic *utn,
+			       unsigned int table, unsigned int idx)
+{
+	struct udp_tunnel_nic_table_entry *entry;
+	struct udp_tunnel_info ti;
+	int err;
+
+	entry = &utn->entries[table][idx];
+	if (!udp_tunnel_nic_entry_is_queued(entry))
+		return;
+
+	udp_tunnel_nic_ti_from_entry(entry, &ti);
+	if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD)
+		err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti);
+	else
+		err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx,
+							   &ti);
+	udp_tunnel_nic_entry_update_done(entry, err);
+
+	if (err)
+		netdev_warn(dev,
+			    "UDP tunnel port sync failed port %d type %s: %d\n",
+			    be16_to_cpu(entry->port),
+			    udp_tunnel_nic_tunnel_type_name(entry->type),
+			    err);
+}
+
+static void
+udp_tunnel_nic_device_sync_by_port(struct net_device *dev,
+				   struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++)
+			udp_tunnel_nic_device_sync_one(dev, utn, i, j);
+}
+
+static void
+udp_tunnel_nic_device_sync_by_table(struct net_device *dev,
+				    struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < utn->n_tables; i++) {
+		/* Find something that needs sync in this table */
+		for (j = 0; j < info->tables[i].n_entries; j++)
+			if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j]))
+				break;
+		if (j == info->tables[i].n_entries)
+			continue;
+
+		err = info->sync_table(dev, i);
+		if (err)
+			netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n",
+				    i, err);
+
+		for (j = 0; j < info->tables[i].n_entries; j++) {
+			struct udp_tunnel_nic_table_entry *entry;
+
+			entry = &utn->entries[i][j];
+			if (udp_tunnel_nic_entry_is_queued(entry))
+				udp_tunnel_nic_entry_update_done(entry, err);
+		}
+	}
+}
+
+static void
+__udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	if (!utn->need_sync)
+		return;
+
+	if (dev->udp_tunnel_nic_info->sync_table)
+		udp_tunnel_nic_device_sync_by_table(dev, utn);
+	else
+		udp_tunnel_nic_device_sync_by_port(dev, utn);
+
+	utn->need_sync = 0;
+	/* Can't replay directly here, in case we come from the tunnel driver's
+	 * notification - trying to replay may deadlock inside tunnel driver.
+	 */
+	utn->need_replay = udp_tunnel_nic_should_replay(dev, utn);
+}
+
+static void
+udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	bool may_sleep;
+
+	if (!utn->need_sync)
+		return;
+
+	/* Drivers which sleep in the callback need to update from
+	 * the workqueue, if we come from the tunnel driver's notification.
+	 */
+	may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
+	if (!may_sleep)
+		__udp_tunnel_nic_device_sync(dev, utn);
+	if (may_sleep || utn->need_replay) {
+		queue_work(udp_tunnel_nic_workqueue, &utn->work);
+		utn->work_pending = 1;
+	}
+}
+
+static bool
+udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table,
+				struct udp_tunnel_info *ti)
+{
+	return table->tunnel_types & ti->type;
+}
+
+static bool
+udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn,
+			  struct udp_tunnel_info *ti)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i;
+
+	/* Special case IPv4-only NICs */
+	if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY &&
+	    ti->sa_family != AF_INET)
+		return false;
+
+	for (i = 0; i < utn->n_tables; i++)
+		if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti))
+			return true;
+	return false;
+}
+
+static int
+udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn,
+			     struct udp_tunnel_info *ti)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_table_entry *entry;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++) {
+			entry =	&utn->entries[i][j];
+
+			if (!udp_tunnel_nic_entry_is_free(entry) &&
+			    entry->port == ti->port &&
+			    entry->type != ti->type) {
+				__set_bit(i, &utn->missed);
+				return true;
+			}
+		}
+	return false;
+}
+
+static void
+udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn,
+			 unsigned int table, unsigned int idx, int use_cnt_adj)
+{
+	struct udp_tunnel_nic_table_entry *entry =  &utn->entries[table][idx];
+	bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
+	unsigned int from, to;
+
+	/* If not going from used to unused or vice versa - all done.
+	 * For dodgy entries make sure we try to sync again (queue the entry).
+	 */
+	entry->use_cnt += use_cnt_adj;
+	if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj))
+		return;
+
+	/* Cancel the op before it was sent to the device, if possible,
+	 * otherwise we'd need to take special care to issue commands
+	 * in the same order the ports arrived.
+	 */
+	if (use_cnt_adj < 0) {
+		from = UDP_TUNNEL_NIC_ENTRY_ADD;
+		to = UDP_TUNNEL_NIC_ENTRY_DEL;
+	} else {
+		from = UDP_TUNNEL_NIC_ENTRY_DEL;
+		to = UDP_TUNNEL_NIC_ENTRY_ADD;
+	}
+
+	if (entry->flags & from) {
+		entry->flags &= ~from;
+		if (!dodgy)
+			return;
+	}
+
+	udp_tunnel_nic_entry_queue(utn, entry, to);
+}
+
+static bool
+udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn,
+			     unsigned int table, unsigned int idx,
+			     struct udp_tunnel_info *ti, int use_cnt_adj)
+{
+	struct udp_tunnel_nic_table_entry *entry =  &utn->entries[table][idx];
+
+	if (udp_tunnel_nic_entry_is_free(entry) ||
+	    entry->port != ti->port ||
+	    entry->type != ti->type)
+		return false;
+
+	if (udp_tunnel_nic_entry_is_frozen(entry))
+		return true;
+
+	udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj);
+	return true;
+}
+
+/* Try to find existing matching entry and adjust its use count, instead of
+ * adding a new one. Returns true if entry was found. In case of delete the
+ * entry may have gotten removed in the process, in which case it will be
+ * queued for removal.
+ */
+static bool
+udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn,
+			    struct udp_tunnel_info *ti, int use_cnt_adj)
+{
+	const struct udp_tunnel_nic_table_info *table;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++) {
+		table = &dev->udp_tunnel_nic_info->tables[i];
+		if (!udp_tunnel_nic_table_is_capable(table, ti))
+			continue;
+
+		for (j = 0; j < table->n_entries; j++)
+			if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti,
+							 use_cnt_adj))
+				return true;
+	}
+
+	return false;
+}
+
+static bool
+udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn,
+			    struct udp_tunnel_info *ti)
+{
+	return udp_tunnel_nic_try_existing(dev, utn, ti, +1);
+}
+
+static bool
+udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn,
+			    struct udp_tunnel_info *ti)
+{
+	return udp_tunnel_nic_try_existing(dev, utn, ti, -1);
+}
+
+static bool
+udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn,
+		       struct udp_tunnel_info *ti)
+{
+	const struct udp_tunnel_nic_table_info *table;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++) {
+		table = &dev->udp_tunnel_nic_info->tables[i];
+		if (!udp_tunnel_nic_table_is_capable(table, ti))
+			continue;
+
+		for (j = 0; j < table->n_entries; j++) {
+			struct udp_tunnel_nic_table_entry *entry;
+
+			entry = &utn->entries[i][j];
+			if (!udp_tunnel_nic_entry_is_free(entry))
+				continue;
+
+			entry->port = ti->port;
+			entry->type = ti->type;
+			entry->use_cnt = 1;
+			udp_tunnel_nic_entry_queue(utn, entry,
+						   UDP_TUNNEL_NIC_ENTRY_ADD);
+			return true;
+		}
+
+		/* The different table may still fit this port in, but there
+		 * are no devices currently which have multiple tables accepting
+		 * the same tunnel type, and false positives are okay.
+		 */
+		__set_bit(i, &utn->missed);
+	}
+
+	return false;
+}
+
+static void
+__udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic *utn;
+
+	utn = dev->udp_tunnel_nic;
+	if (!utn)
+		return;
+	if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)
+		return;
+
+	if (!udp_tunnel_nic_is_capable(dev, utn, ti))
+		return;
+
+	/* It may happen that a tunnel of one type is removed and different
+	 * tunnel type tries to reuse its port before the device was informed.
+	 * Rely on utn->missed to re-add this port later.
+	 */
+	if (udp_tunnel_nic_has_collision(dev, utn, ti))
+		return;
+
+	if (!udp_tunnel_nic_add_existing(dev, utn, ti))
+		udp_tunnel_nic_add_new(dev, utn, ti);
+
+	udp_tunnel_nic_device_sync(dev, utn);
+}
+
+static void
+__udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	struct udp_tunnel_nic *utn;
+
+	utn = dev->udp_tunnel_nic;
+	if (!utn)
+		return;
+
+	if (!udp_tunnel_nic_is_capable(dev, utn, ti))
+		return;
+
+	udp_tunnel_nic_del_existing(dev, utn, ti);
+
+	udp_tunnel_nic_device_sync(dev, utn);
+}
+
+static void __udp_tunnel_nic_reset_ntf(struct net_device *dev)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic *utn;
+	unsigned int i, j;
+
+	ASSERT_RTNL();
+
+	utn = dev->udp_tunnel_nic;
+	if (!utn)
+		return;
+
+	utn->need_sync = false;
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++) {
+			struct udp_tunnel_nic_table_entry *entry;
+
+			entry = &utn->entries[i][j];
+
+			entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL |
+					  UDP_TUNNEL_NIC_ENTRY_OP_FAIL);
+			/* We don't release rtnl across ops */
+			WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN);
+			if (!entry->use_cnt)
+				continue;
+
+			udp_tunnel_nic_entry_queue(utn, entry,
+						   UDP_TUNNEL_NIC_ENTRY_ADD);
+		}
+
+	__udp_tunnel_nic_device_sync(dev, utn);
+}
+
+static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = {
+	.get_port	= __udp_tunnel_nic_get_port,
+	.set_port_priv	= __udp_tunnel_nic_set_port_priv,
+	.add_port	= __udp_tunnel_nic_add_port,
+	.del_port	= __udp_tunnel_nic_del_port,
+	.reset_ntf	= __udp_tunnel_nic_reset_ntf,
+};
+
+static void
+udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i, j;
+
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++) {
+			int adj_cnt = -utn->entries[i][j].use_cnt;
+
+			if (adj_cnt)
+				udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt);
+		}
+
+	__udp_tunnel_nic_device_sync(dev, utn);
+
+	for (i = 0; i < utn->n_tables; i++)
+		memset(utn->entries[i], 0, array_size(info->tables[i].n_entries,
+						      sizeof(**utn->entries)));
+	WARN_ON(utn->need_sync);
+	utn->need_replay = 0;
+}
+
+static void
+udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	unsigned int i, j;
+
+	/* Freeze all the ports we are already tracking so that the replay
+	 * does not double up the refcount.
+	 */
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++)
+			udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]);
+	utn->missed = 0;
+	utn->need_replay = 0;
+
+	udp_tunnel_get_rx_info(dev);
+
+	for (i = 0; i < utn->n_tables; i++)
+		for (j = 0; j < info->tables[i].n_entries; j++)
+			udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]);
+}
+
+static void udp_tunnel_nic_device_sync_work(struct work_struct *work)
+{
+	struct udp_tunnel_nic *utn =
+		container_of(work, struct udp_tunnel_nic, work);
+
+	rtnl_lock();
+	utn->work_pending = 0;
+	__udp_tunnel_nic_device_sync(utn->dev, utn);
+
+	if (utn->need_replay)
+		udp_tunnel_nic_replay(utn->dev, utn);
+	rtnl_unlock();
+}
+
+static struct udp_tunnel_nic *
+udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info,
+		     unsigned int n_tables)
+{
+	struct udp_tunnel_nic *utn;
+	unsigned int i;
+
+	utn = kzalloc(sizeof(*utn), GFP_KERNEL);
+	if (!utn)
+		return NULL;
+	utn->n_tables = n_tables;
+	INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work);
+
+	utn->entries = kmalloc_array(n_tables, sizeof(void *), GFP_KERNEL);
+	if (!utn->entries)
+		goto err_free_utn;
+
+	for (i = 0; i < n_tables; i++) {
+		utn->entries[i] = kcalloc(info->tables[i].n_entries,
+					  sizeof(*utn->entries[i]), GFP_KERNEL);
+		if (!utn->entries[i])
+			goto err_free_prev_entries;
+	}
+
+	return utn;
+
+err_free_prev_entries:
+	while (i--)
+		kfree(utn->entries[i]);
+	kfree(utn->entries);
+err_free_utn:
+	kfree(utn);
+	return NULL;
+}
+
+static int udp_tunnel_nic_register(struct net_device *dev)
+{
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic *utn;
+	unsigned int n_tables, i;
+
+	BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE <
+		     UDP_TUNNEL_NIC_MAX_TABLES);
+
+	if (WARN_ON(!info->set_port != !info->unset_port) ||
+	    WARN_ON(!info->set_port == !info->sync_table) ||
+	    WARN_ON(!info->tables[0].n_entries))
+		return -EINVAL;
+
+	n_tables = 1;
+	for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
+		if (!info->tables[i].n_entries)
+			continue;
+
+		n_tables++;
+		if (WARN_ON(!info->tables[i - 1].n_entries))
+			return -EINVAL;
+	}
+
+	utn = udp_tunnel_nic_alloc(info, n_tables);
+	if (!utn)
+		return -ENOMEM;
+
+	utn->dev = dev;
+	dev_hold(dev);
+	dev->udp_tunnel_nic = utn;
+
+	if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY))
+		udp_tunnel_get_rx_info(dev);
+
+	return 0;
+}
+
+static void
+udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
+{
+	unsigned int i;
+
+	/* Flush before we check work, so we don't waste time adding entries
+	 * from the work which we will boot immediately.
+	 */
+	udp_tunnel_nic_flush(dev, utn);
+
+	/* Wait for the work to be done using the state, netdev core will
+	 * retry unregister until we give up our reference on this device.
+	 */
+	if (utn->work_pending)
+		return;
+
+	for (i = 0; i < utn->n_tables; i++)
+		kfree(utn->entries[i]);
+	kfree(utn->entries);
+	kfree(utn);
+	dev->udp_tunnel_nic = NULL;
+	dev_put(dev);
+}
+
+static int
+udp_tunnel_nic_netdevice_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	const struct udp_tunnel_nic_info *info;
+	struct udp_tunnel_nic *utn;
+
+	info = dev->udp_tunnel_nic_info;
+	if (!info)
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_REGISTER) {
+		int err;
+
+		err = udp_tunnel_nic_register(dev);
+		if (err)
+			netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err);
+		return notifier_from_errno(err);
+	}
+	/* All other events will need the udp_tunnel_nic state */
+	utn = dev->udp_tunnel_nic;
+	if (!utn)
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_UNREGISTER) {
+		udp_tunnel_nic_unregister(dev, utn);
+		return NOTIFY_OK;
+	}
+
+	/* All other events only matter if NIC has to be programmed open */
+	if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY))
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_UP) {
+		WARN_ON(!udp_tunnel_nic_is_empty(dev, utn));
+		udp_tunnel_get_rx_info(dev);
+		return NOTIFY_OK;
+	}
+	if (event == NETDEV_GOING_DOWN) {
+		udp_tunnel_nic_flush(dev, utn);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = {
+	.notifier_call = udp_tunnel_nic_netdevice_event,
+};
+
+static int __init udp_tunnel_nic_init_module(void)
+{
+	int err;
+
+	udp_tunnel_nic_workqueue = alloc_workqueue("udp_tunnel_nic", 0, 0);
+	if (!udp_tunnel_nic_workqueue)
+		return -ENOMEM;
+
+	rtnl_lock();
+	udp_tunnel_nic_ops = &__udp_tunnel_nic_ops;
+	rtnl_unlock();
+
+	err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block);
+	if (err)
+		goto err_unset_ops;
+
+	return 0;
+
+err_unset_ops:
+	rtnl_lock();
+	udp_tunnel_nic_ops = NULL;
+	rtnl_unlock();
+	destroy_workqueue(udp_tunnel_nic_workqueue);
+	return err;
+}
+late_initcall(udp_tunnel_nic_init_module);
+
+static void __exit udp_tunnel_nic_cleanup_module(void)
+{
+	unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block);
+
+	rtnl_lock();
+	udp_tunnel_nic_ops = NULL;
+	rtnl_unlock();
+
+	destroy_workqueue(udp_tunnel_nic_workqueue);
+}
+module_exit(udp_tunnel_nic_cleanup_module);
+
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp_tunnel_stub.c b/net/ipv4/udp_tunnel_stub.c
new file mode 100644
index 000000000000..c4b2888f5fef
--- /dev/null
+++ b/net/ipv4/udp_tunnel_stub.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2020 Facebook Inc.
+
+#include <net/udp_tunnel.h>
+
+const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
+EXPORT_SYMBOL_GPL(udp_tunnel_nic_ops);
-- 
cgit v1.2.3


From c818c03b661cd769e035e41673d5543ba2ebda64 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 13 May 2020 14:11:26 -0700
Subject: seccomp: Report number of loaded filters in /proc/$pid/status

A common question asked when debugging seccomp filters is "how many
filters are attached to your process?" Provide a way to easily answer
this question through /proc/$pid/status with a "Seccomp_filters" line.

Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/proc/array.c         | 2 ++
 include/linux/seccomp.h | 2 ++
 init/init_task.c        | 3 +++
 kernel/seccomp.c        | 3 +++
 4 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 55ecbeb3a721..65ec2029fa80 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -341,6 +341,8 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 	seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p));
 #ifdef CONFIG_SECCOMP
 	seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
+	seq_put_decimal_ull(m, "\nSeccomp_filters:\t",
+			    atomic_read(&p->seccomp.filter_count));
 #endif
 	seq_puts(m, "\nSpeculation_Store_Bypass:\t");
 	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 4192369b8418..2ec2720f83cc 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -13,6 +13,7 @@
 #ifdef CONFIG_SECCOMP
 
 #include <linux/thread_info.h>
+#include <linux/atomic.h>
 #include <asm/seccomp.h>
 
 struct seccomp_filter;
@@ -29,6 +30,7 @@ struct seccomp_filter;
  */
 struct seccomp {
 	int mode;
+	atomic_t filter_count;
 	struct seccomp_filter *filter;
 };
 
diff --git a/init/init_task.c b/init/init_task.c
index 15089d15010a..a3eb3847e1f4 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -204,6 +204,9 @@ struct task_struct init_task
 #ifdef CONFIG_SECURITY
 	.security	= NULL,
 #endif
+#ifdef CONFIG_SECCOMP
+	.seccomp	= { .filter_count = ATOMIC_INIT(0) },
+#endif
 };
 EXPORT_SYMBOL(init_task);
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d653d8426de9..f387e5004c29 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -398,6 +398,8 @@ static inline void seccomp_sync_threads(unsigned long flags)
 		put_seccomp_filter(thread);
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
+		atomic_set(&thread->seccomp.filter_count,
+			   atomic_read(&thread->seccomp.filter_count));
 
 		/*
 		 * Don't let an unprivileged task work around
@@ -544,6 +546,7 @@ static long seccomp_attach_filter(unsigned int flags,
 	 */
 	filter->prev = current->seccomp.filter;
 	current->seccomp.filter = filter;
+	atomic_inc(&current->seccomp.filter_count);
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
-- 
cgit v1.2.3


From 3a15fb6ed92cb32b0a83f406aa4a96f28c9adbc3 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Sun, 31 May 2020 13:50:29 +0200
Subject: seccomp: release filter after task is fully dead

The seccomp filter used to be released in free_task() which is called
asynchronously via call_rcu() and assorted mechanisms. Since we need
to inform tasks waiting on the seccomp notifier when a filter goes empty
we will notify them as soon as a task has been marked fully dead in
release_task(). To not split seccomp cleanup into two parts, move
filter release out of free_task() and into release_task() after we've
unhashed struct task from struct pid, exited signals, and unlinked it
from the threadgroups' thread list. We'll put the empty filter
notification infrastructure into it in a follow up patch.

This also renames put_seccomp_filter() to seccomp_filter_release() which
is a more descriptive name of what we're doing here especially once
we've added the empty filter notification mechanism in there.

We're also NULL-ing the task's filter tree entrypoint which seems
cleaner than leaving a dangling pointer in there. Note that this shouldn't
need any memory barriers since we're calling this when the task is in
release_task() which means it's EXIT_DEAD. So it can't modify its seccomp
filters anymore. You can also see this from the point where we're calling
seccomp_filter_release(). It's after __exit_signal() and at this point,
tsk->sighand will already have been NULLed which is required for
thread-sync and filter installation alike.

Cc: Tycho Andersen <tycho@tycho.ws>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matt Denton <mpdenton@google.com>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Jann Horn <jannh@google.com>
Cc: Chris Palmer <palmer@google.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Robert Sesek <rsesek@google.com>
Cc: Jeffrey Vander Stoep <jeffv@google.com>
Cc: Linux Containers <containers@lists.linux-foundation.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200531115031.391515-2-christian.brauner@ubuntu.com
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/seccomp.h |  4 ++--
 kernel/exit.c           |  1 +
 kernel/fork.c           |  1 -
 kernel/seccomp.c        | 62 +++++++++++++++++++++++++++++--------------------
 4 files changed, 40 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 2ec2720f83cc..babcd6c02d09 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -84,10 +84,10 @@ static inline int seccomp_mode(struct seccomp *s)
 #endif /* CONFIG_SECCOMP */
 
 #ifdef CONFIG_SECCOMP_FILTER
-extern void put_seccomp_filter(struct task_struct *tsk);
+extern void seccomp_filter_release(struct task_struct *tsk);
 extern void get_seccomp_filter(struct task_struct *tsk);
 #else  /* CONFIG_SECCOMP_FILTER */
-static inline void put_seccomp_filter(struct task_struct *tsk)
+static inline void seccomp_filter_release(struct task_struct *tsk)
 {
 	return;
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 727150f28103..00d77e5ba700 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -217,6 +217,7 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
+	seccomp_filter_release(p);
 	proc_flush_pid(thread_pid);
 	put_pid(thread_pid);
 	release_thread(p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..c51a9cd824c5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -473,7 +473,6 @@ void free_task(struct task_struct *tsk)
 #endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
-	put_seccomp_filter(tsk);
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d4dd3344e312..0ca6d5243427 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -368,6 +368,42 @@ static inline pid_t seccomp_can_sync_threads(void)
 	return 0;
 }
 
+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+	if (filter) {
+		bpf_prog_destroy(filter->prog);
+		kfree(filter);
+	}
+}
+
+static void __put_seccomp_filter(struct seccomp_filter *orig)
+{
+	/* Clean up single-reference branches iteratively. */
+	while (orig && refcount_dec_and_test(&orig->refs)) {
+		struct seccomp_filter *freeme = orig;
+		orig = orig->prev;
+		seccomp_filter_free(freeme);
+	}
+}
+
+/**
+ * seccomp_filter_release - Detach the task from its filter tree
+ *			    and drop its reference count during
+ *			    exit.
+ *
+ * This function should only be called when the task is exiting as
+ * it detaches it from its filter tree. As such, READ_ONCE() and
+ * barriers are not needed here, as would normally be needed.
+ */
+void seccomp_filter_release(struct task_struct *tsk)
+{
+	struct seccomp_filter *orig = tsk->seccomp.filter;
+
+	/* Detach task from its filter tree. */
+	tsk->seccomp.filter = NULL;
+	__put_seccomp_filter(orig);
+}
+
 /**
  * seccomp_sync_threads: sets all threads to use current's filter
  *
@@ -397,7 +433,7 @@ static inline void seccomp_sync_threads(unsigned long flags)
 		 * current's path will hold a reference.  (This also
 		 * allows a put before the assignment.)
 		 */
-		put_seccomp_filter(thread);
+		__put_seccomp_filter(thread->seccomp.filter);
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
 		atomic_set(&thread->seccomp.filter_count,
@@ -571,30 +607,6 @@ void get_seccomp_filter(struct task_struct *tsk)
 	__get_seccomp_filter(orig);
 }
 
-static inline void seccomp_filter_free(struct seccomp_filter *filter)
-{
-	if (filter) {
-		bpf_prog_destroy(filter->prog);
-		kfree(filter);
-	}
-}
-
-static void __put_seccomp_filter(struct seccomp_filter *orig)
-{
-	/* Clean up single-reference branches iteratively. */
-	while (orig && refcount_dec_and_test(&orig->refs)) {
-		struct seccomp_filter *freeme = orig;
-		orig = orig->prev;
-		seccomp_filter_free(freeme);
-	}
-}
-
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
-{
-	__put_seccomp_filter(tsk->seccomp.filter);
-}
-
 static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason)
 {
 	clear_siginfo(info);
-- 
cgit v1.2.3


From 943c8a80830b88b7b203fa3e2d755620d85129d1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 29 Jun 2020 09:43:52 -0700
Subject: <linux/of.h>: add stub for of_get_next_parent() to fix qcom build
 error

Fix a (COMPILE_TEST) build error when CONFIG_OF is not set/enabled
by adding a stub for of_get_next_parent().

../drivers/soc/qcom/qcom-geni-se.c:819:11: error: implicit declaration of function 'of_get_next_parent'; did you mean 'of_get_parent'? [-Werror=implicit-function-declaration]
../drivers/soc/qcom/qcom-geni-se.c:819:9: warning: assignment makes pointer from integer without a cast [-Wint-conversion]

Fixes: 048eb908a1f2 ("soc: qcom-geni-se: Add interconnect support to fix earlycon crash")
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Frank Rowand <frowand.list@gmail.com>
Cc: devicetree@vger.kernel.org
Cc: Andy Gross <agross@kernel.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: linux-arm-msm@vger.kernel.org
Link: https://lore.kernel.org/r/ce0d7561-ff93-d267-b57a-6505014c728c@infradead.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/of.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/of.h b/include/linux/of.h
index c669c0a4732f..c98ed245b815 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -630,6 +630,11 @@ static inline struct device_node *of_get_parent(const struct device_node *node)
 	return NULL;
 }
 
+static inline struct device_node *of_get_next_parent(struct device_node *node)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_get_next_child(
 	const struct device_node *node, struct device_node *prev)
 {
-- 
cgit v1.2.3


From ac219bf3c9bdf9200767e8c98a56ad42c75e5cd5 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 27 Jun 2020 00:40:11 +0200
Subject: leds: lp55xx: Convert to use GPIO descriptors

The LP55xx driver is already using the of_gpio() functions to
pick a global GPIO number for "enable" from the device tree and
request the line. Simplify it by just using a GPIO descriptor.

Make sure to keep the enable GPIO line optional, change the
naming from "lp5523_enable" to "LP55xx enable" to reflect that
this is used on all LP55xx LED drivers.

Cc: Milo Kim <milo.kim@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/leds-lp55xx-common.c         | 27 +++++++++++----------------
 include/linux/platform_data/leds-lp55xx.h |  6 ++++--
 2 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 44ced02b49f9..1354965ac866 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -17,8 +17,7 @@
 #include <linux/module.h>
 #include <linux/platform_data/leds-lp55xx.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include "leds-lp55xx-common.h"
 
@@ -395,18 +394,11 @@ int lp55xx_init_device(struct lp55xx_chip *chip)
 	if (!pdata || !cfg)
 		return -EINVAL;
 
-	if (gpio_is_valid(pdata->enable_gpio)) {
-		ret = devm_gpio_request_one(dev, pdata->enable_gpio,
-					    GPIOF_DIR_OUT, "lp5523_enable");
-		if (ret < 0) {
-			dev_err(dev, "could not acquire enable gpio (err=%d)\n",
-				ret);
-			goto err;
-		}
-
-		gpio_set_value(pdata->enable_gpio, 0);
+	if (pdata->enable_gpiod) {
+		gpiod_set_consumer_name(pdata->enable_gpiod, "LP55xx enable");
+		gpiod_set_value(pdata->enable_gpiod, 0);
 		usleep_range(1000, 2000); /* Keep enable down at least 1ms */
-		gpio_set_value(pdata->enable_gpio, 1);
+		gpiod_set_value(pdata->enable_gpiod, 1);
 		usleep_range(1000, 2000); /* 500us abs min. */
 	}
 
@@ -447,8 +439,8 @@ void lp55xx_deinit_device(struct lp55xx_chip *chip)
 	if (chip->clk)
 		clk_disable_unprepare(chip->clk);
 
-	if (gpio_is_valid(pdata->enable_gpio))
-		gpio_set_value(pdata->enable_gpio, 0);
+	if (pdata->enable_gpiod)
+		gpiod_set_value(pdata->enable_gpiod, 0);
 }
 EXPORT_SYMBOL_GPL(lp55xx_deinit_device);
 
@@ -579,7 +571,10 @@ struct lp55xx_platform_data *lp55xx_of_populate_pdata(struct device *dev,
 	of_property_read_string(np, "label", &pdata->label);
 	of_property_read_u8(np, "clock-mode", &pdata->clock_mode);
 
-	pdata->enable_gpio = of_get_named_gpio(np, "enable-gpio", 0);
+	pdata->enable_gpiod = devm_gpiod_get_optional(dev, "enable",
+						      GPIOD_ASIS);
+	if (IS_ERR(pdata->enable_gpiod))
+		return ERR_CAST(pdata->enable_gpiod);
 
 	/* LP8501 specific */
 	of_property_read_u8(np, "pwr-sel", (u8 *)&pdata->pwr_sel);
diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h
index 96a787100fda..00492d6ff018 100644
--- a/include/linux/platform_data/leds-lp55xx.h
+++ b/include/linux/platform_data/leds-lp55xx.h
@@ -12,6 +12,8 @@
 #ifndef _LEDS_LP55XX_H
 #define _LEDS_LP55XX_H
 
+#include <linux/gpio/consumer.h>
+
 /* Clock configuration */
 #define LP55XX_CLOCK_AUTO	0
 #define LP55XX_CLOCK_INT	1
@@ -49,7 +51,7 @@ enum lp8501_pwr_sel {
  * @clock_mode        : Input clock mode. LP55XX_CLOCK_AUTO or _INT or _EXT
  * @setup_resources   : Platform specific function before enabling the chip
  * @release_resources : Platform specific function after  disabling the chip
- * @enable            : EN pin control by platform side
+ * @enable_gpiod      : enable GPIO descriptor
  * @patterns          : Predefined pattern data for RGB channels
  * @num_patterns      : Number of patterns
  * @update_config     : Value of CONFIG register
@@ -65,7 +67,7 @@ struct lp55xx_platform_data {
 	u8 clock_mode;
 
 	/* optional enable GPIO */
-	int enable_gpio;
+	struct gpio_desc *enable_gpiod;
 
 	/* Predefined pattern data */
 	struct lp55xx_predef_pattern *patterns;
-- 
cgit v1.2.3


From a24015fa8b89e4605a9c6581d56b48d991e2b66b Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Fri, 26 Jun 2020 05:14:07 +0800
Subject: firmware: imx: Move i.MX SCU soc driver into imx firmware folder

The i.MX SCU soc driver depends on SCU firmware driver, so it has to
use platform driver model for proper defer probe operation, since
it has no device binding in DT file, a simple platform device is
created together inside the platform driver. To make it more clean,
we can just move the entire SCU soc driver into imx firmware folder
and initialized by i.MX SCU firmware driver.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/configs/defconfig       |   1 -
 drivers/firmware/imx/Makefile      |   2 +-
 drivers/firmware/imx/imx-scu-soc.c | 138 +++++++++++++++++++++++++++++
 drivers/firmware/imx/imx-scu.c     |   4 +
 drivers/soc/imx/Kconfig            |   9 --
 drivers/soc/imx/Makefile           |   1 -
 drivers/soc/imx/soc-imx-scu.c      | 172 -------------------------------------
 include/linux/firmware/imx/sci.h   |   1 +
 8 files changed, 144 insertions(+), 184 deletions(-)
 create mode 100644 drivers/firmware/imx/imx-scu-soc.c
 delete mode 100644 drivers/soc/imx/soc-imx-scu.c

(limited to 'include/linux')

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 883e8bace3ed..c99237ac10a4 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -850,7 +850,6 @@ CONFIG_OWL_PM_DOMAINS=y
 CONFIG_RASPBERRYPI_POWER=y
 CONFIG_FSL_DPAA=y
 CONFIG_FSL_MC_DPIO=y
-CONFIG_IMX_SCU_SOC=y
 CONFIG_QCOM_AOSS_QMP=y
 CONFIG_QCOM_GENI_SE=y
 CONFIG_QCOM_RMTFS_MEM=m
diff --git a/drivers/firmware/imx/Makefile b/drivers/firmware/imx/Makefile
index 17ea3613e142..b76acbade2a0 100644
--- a/drivers/firmware/imx/Makefile
+++ b/drivers/firmware/imx/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_IMX_DSP)		+= imx-dsp.o
-obj-$(CONFIG_IMX_SCU)		+= imx-scu.o misc.o imx-scu-irq.o rm.o
+obj-$(CONFIG_IMX_SCU)		+= imx-scu.o misc.o imx-scu-irq.o rm.o imx-scu-soc.o
 obj-$(CONFIG_IMX_SCU_PD)	+= scu-pd.o
diff --git a/drivers/firmware/imx/imx-scu-soc.c b/drivers/firmware/imx/imx-scu-soc.c
new file mode 100644
index 000000000000..2f32353de2c9
--- /dev/null
+++ b/drivers/firmware/imx/imx-scu-soc.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP.
+ */
+
+#include <dt-bindings/firmware/imx/rsrc.h>
+#include <linux/firmware/imx/sci.h>
+#include <linux/slab.h>
+#include <linux/sys_soc.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+
+static struct imx_sc_ipc *imx_sc_soc_ipc_handle;
+
+struct imx_sc_msg_misc_get_soc_id {
+	struct imx_sc_rpc_msg hdr;
+	union {
+		struct {
+			u32 control;
+			u16 resource;
+		} __packed req;
+		struct {
+			u32 id;
+		} resp;
+	} data;
+} __packed __aligned(4);
+
+struct imx_sc_msg_misc_get_soc_uid {
+	struct imx_sc_rpc_msg hdr;
+	u32 uid_low;
+	u32 uid_high;
+} __packed;
+
+static int imx_scu_soc_uid(u64 *soc_uid)
+{
+	struct imx_sc_msg_misc_get_soc_uid msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_MISC;
+	hdr->func = IMX_SC_MISC_FUNC_UNIQUE_ID;
+	hdr->size = 1;
+
+	ret = imx_scu_call_rpc(imx_sc_soc_ipc_handle, &msg, true);
+	if (ret) {
+		pr_err("%s: get soc uid failed, ret %d\n", __func__, ret);
+		return ret;
+	}
+
+	*soc_uid = msg.uid_high;
+	*soc_uid <<= 32;
+	*soc_uid |= msg.uid_low;
+
+	return 0;
+}
+
+static int imx_scu_soc_id(void)
+{
+	struct imx_sc_msg_misc_get_soc_id msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_MISC;
+	hdr->func = IMX_SC_MISC_FUNC_GET_CONTROL;
+	hdr->size = 3;
+
+	msg.data.req.control = IMX_SC_C_ID;
+	msg.data.req.resource = IMX_SC_R_SYSTEM;
+
+	ret = imx_scu_call_rpc(imx_sc_soc_ipc_handle, &msg, true);
+	if (ret) {
+		pr_err("%s: get soc info failed, ret %d\n", __func__, ret);
+		return ret;
+	}
+
+	return msg.data.resp.id;
+}
+
+int imx_scu_soc_init(struct device *dev)
+{
+	struct soc_device_attribute *soc_dev_attr;
+	struct soc_device *soc_dev;
+	int id, ret;
+	u64 uid = 0;
+	u32 val;
+
+	ret = imx_scu_get_handle(&imx_sc_soc_ipc_handle);
+	if (ret)
+		return ret;
+
+	soc_dev_attr = devm_kzalloc(dev, sizeof(*soc_dev_attr),
+				    GFP_KERNEL);
+	if (!soc_dev_attr)
+		return -ENOMEM;
+
+	soc_dev_attr->family = "Freescale i.MX";
+
+	ret = of_property_read_string(of_root,
+				      "model",
+				      &soc_dev_attr->machine);
+	if (ret)
+		return ret;
+
+	id = imx_scu_soc_id();
+	if (id < 0)
+		return -EINVAL;
+
+	ret = imx_scu_soc_uid(&uid);
+	if (ret < 0)
+		return -EINVAL;
+
+	/* format soc_id value passed from SCU firmware */
+	val = id & 0x1f;
+	soc_dev_attr->soc_id = devm_kasprintf(dev, GFP_KERNEL, "0x%x", val);
+	if (!soc_dev_attr->soc_id)
+		return -ENOMEM;
+
+	/* format revision value passed from SCU firmware */
+	val = (id >> 5) & 0xf;
+	val = (((val >> 2) + 1) << 4) | (val & 0x3);
+	soc_dev_attr->revision = devm_kasprintf(dev, GFP_KERNEL, "%d.%d",
+						(val >> 4) & 0xf, val & 0xf);
+	if (!soc_dev_attr->revision)
+		return -ENOMEM;
+
+	soc_dev_attr->serial_number = devm_kasprintf(dev, GFP_KERNEL,
+						     "%016llX", uid);
+	if (!soc_dev_attr->serial_number)
+		return -ENOMEM;
+
+	soc_dev = soc_device_register(soc_dev_attr);
+	if (IS_ERR(soc_dev))
+		return PTR_ERR(soc_dev);
+
+	return 0;
+}
diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c
index 2ab048222fe9..dca79caccd01 100644
--- a/drivers/firmware/imx/imx-scu.c
+++ b/drivers/firmware/imx/imx-scu.c
@@ -328,6 +328,10 @@ static int imx_scu_probe(struct platform_device *pdev)
 
 	imx_sc_ipc_handle = sc_ipc;
 
+	ret = imx_scu_soc_init(dev);
+	if (ret)
+		dev_warn(dev, "failed to initialize SoC info: %d\n", ret);
+
 	ret = imx_scu_enable_general_irq_channel(dev);
 	if (ret)
 		dev_warn(dev,
diff --git a/drivers/soc/imx/Kconfig b/drivers/soc/imx/Kconfig
index d515d2cc20ed..d49fa63ed9c9 100644
--- a/drivers/soc/imx/Kconfig
+++ b/drivers/soc/imx/Kconfig
@@ -8,15 +8,6 @@ config IMX_GPCV2_PM_DOMAINS
 	select PM_GENERIC_DOMAINS
 	default y if SOC_IMX7D
 
-config IMX_SCU_SOC
-	bool "i.MX System Controller Unit SoC info support"
-	depends on IMX_SCU
-	select SOC_BUS
-	help
-	  If you say yes here you get support for the NXP i.MX System
-	  Controller Unit SoC info module, it will provide the SoC info
-	  like SoC family, ID and revision etc.
-
 config SOC_IMX8M
 	bool "i.MX8M SoC family support"
 	depends on ARCH_MXC || COMPILE_TEST
diff --git a/drivers/soc/imx/Makefile b/drivers/soc/imx/Makefile
index 446143241fe7..078dc918f4f3 100644
--- a/drivers/soc/imx/Makefile
+++ b/drivers/soc/imx/Makefile
@@ -5,4 +5,3 @@ endif
 obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o
 obj-$(CONFIG_IMX_GPCV2_PM_DOMAINS) += gpcv2.o
 obj-$(CONFIG_SOC_IMX8M) += soc-imx8m.o
-obj-$(CONFIG_IMX_SCU_SOC) += soc-imx-scu.o
diff --git a/drivers/soc/imx/soc-imx-scu.c b/drivers/soc/imx/soc-imx-scu.c
deleted file mode 100644
index 92448ca9a6f8..000000000000
--- a/drivers/soc/imx/soc-imx-scu.c
+++ /dev/null
@@ -1,172 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright 2019 NXP.
- */
-
-#include <dt-bindings/firmware/imx/rsrc.h>
-#include <linux/firmware/imx/sci.h>
-#include <linux/slab.h>
-#include <linux/sys_soc.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
-
-#define IMX_SCU_SOC_DRIVER_NAME		"imx-scu-soc"
-
-static struct imx_sc_ipc *soc_ipc_handle;
-
-struct imx_sc_msg_misc_get_soc_id {
-	struct imx_sc_rpc_msg hdr;
-	union {
-		struct {
-			u32 control;
-			u16 resource;
-		} __packed req;
-		struct {
-			u32 id;
-		} resp;
-	} data;
-} __packed __aligned(4);
-
-struct imx_sc_msg_misc_get_soc_uid {
-	struct imx_sc_rpc_msg hdr;
-	u32 uid_low;
-	u32 uid_high;
-} __packed;
-
-static int imx_scu_soc_uid(u64 *soc_uid)
-{
-	struct imx_sc_msg_misc_get_soc_uid msg;
-	struct imx_sc_rpc_msg *hdr = &msg.hdr;
-	int ret;
-
-	hdr->ver = IMX_SC_RPC_VERSION;
-	hdr->svc = IMX_SC_RPC_SVC_MISC;
-	hdr->func = IMX_SC_MISC_FUNC_UNIQUE_ID;
-	hdr->size = 1;
-
-	ret = imx_scu_call_rpc(soc_ipc_handle, &msg, true);
-	if (ret) {
-		pr_err("%s: get soc uid failed, ret %d\n", __func__, ret);
-		return ret;
-	}
-
-	*soc_uid = msg.uid_high;
-	*soc_uid <<= 32;
-	*soc_uid |= msg.uid_low;
-
-	return 0;
-}
-
-static int imx_scu_soc_id(void)
-{
-	struct imx_sc_msg_misc_get_soc_id msg;
-	struct imx_sc_rpc_msg *hdr = &msg.hdr;
-	int ret;
-
-	hdr->ver = IMX_SC_RPC_VERSION;
-	hdr->svc = IMX_SC_RPC_SVC_MISC;
-	hdr->func = IMX_SC_MISC_FUNC_GET_CONTROL;
-	hdr->size = 3;
-
-	msg.data.req.control = IMX_SC_C_ID;
-	msg.data.req.resource = IMX_SC_R_SYSTEM;
-
-	ret = imx_scu_call_rpc(soc_ipc_handle, &msg, true);
-	if (ret) {
-		pr_err("%s: get soc info failed, ret %d\n", __func__, ret);
-		return ret;
-	}
-
-	return msg.data.resp.id;
-}
-
-static int imx_scu_soc_probe(struct platform_device *pdev)
-{
-	struct soc_device_attribute *soc_dev_attr;
-	struct soc_device *soc_dev;
-	int id, ret;
-	u64 uid = 0;
-	u32 val;
-
-	ret = imx_scu_get_handle(&soc_ipc_handle);
-	if (ret)
-		return ret;
-
-	soc_dev_attr = devm_kzalloc(&pdev->dev, sizeof(*soc_dev_attr),
-				    GFP_KERNEL);
-	if (!soc_dev_attr)
-		return -ENOMEM;
-
-	soc_dev_attr->family = "Freescale i.MX";
-
-	ret = of_property_read_string(of_root,
-				      "model",
-				      &soc_dev_attr->machine);
-	if (ret)
-		return ret;
-
-	id = imx_scu_soc_id();
-	if (id < 0)
-		return -EINVAL;
-
-	ret = imx_scu_soc_uid(&uid);
-	if (ret < 0)
-		return -EINVAL;
-
-	/* format soc_id value passed from SCU firmware */
-	val = id & 0x1f;
-	soc_dev_attr->soc_id = devm_kasprintf(&pdev->dev, GFP_KERNEL, "0x%x", val);
-	if (!soc_dev_attr->soc_id)
-		return -ENOMEM;
-
-	/* format revision value passed from SCU firmware */
-	val = (id >> 5) & 0xf;
-	val = (((val >> 2) + 1) << 4) | (val & 0x3);
-	soc_dev_attr->revision = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%d.%d",
-						(val >> 4) & 0xf, val & 0xf);
-	if (!soc_dev_attr->revision)
-		return -ENOMEM;
-
-	soc_dev_attr->serial_number = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-						     "%016llX", uid);
-	if (!soc_dev_attr->serial_number)
-		return -ENOMEM;
-
-	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR(soc_dev))
-		return PTR_ERR(soc_dev);
-
-	return 0;
-}
-
-static struct platform_driver imx_scu_soc_driver = {
-	.driver = {
-		.name = IMX_SCU_SOC_DRIVER_NAME,
-	},
-	.probe = imx_scu_soc_probe,
-};
-
-static int __init imx_scu_soc_init(void)
-{
-	struct platform_device *pdev;
-	struct device_node *np;
-	int ret;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx-scu");
-	if (!np)
-		return -ENODEV;
-
-	of_node_put(np);
-
-	ret = platform_driver_register(&imx_scu_soc_driver);
-	if (ret)
-		return ret;
-
-	pdev = platform_device_register_simple(IMX_SCU_SOC_DRIVER_NAME,
-					       -1, NULL, 0);
-	if (IS_ERR(pdev))
-		platform_driver_unregister(&imx_scu_soc_driver);
-
-	return PTR_ERR_OR_ZERO(pdev);
-}
-device_initcall(imx_scu_soc_init);
diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h
index 3c459f54a88f..22c76571a294 100644
--- a/include/linux/firmware/imx/sci.h
+++ b/include/linux/firmware/imx/sci.h
@@ -20,4 +20,5 @@ int imx_scu_enable_general_irq_channel(struct device *dev);
 int imx_scu_irq_register_notifier(struct notifier_block *nb);
 int imx_scu_irq_unregister_notifier(struct notifier_block *nb);
 int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable);
+int imx_scu_soc_init(struct device *dev);
 #endif /* _SC_SCI_H */
-- 
cgit v1.2.3


From 02c003cc18dfb6db1001856fccb978a1179fe89a Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Fri, 10 Jul 2020 14:39:17 +0100
Subject: firmware: arm_scmi: Remove zero-length array in SCMI notifications

Substitute zero-length array defined in scmi_base_error_report with
a flexible length array definition.

Link: https://lore.kernel.org/r/20200710133919.39792-1-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/scmi_protocol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 46d98be92466..7d4348fb7330 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -421,7 +421,7 @@ struct scmi_base_error_report {
 	u32 agent_id;
 	bool fatal;
 	u16 cmd_count;
-	u64 reports[0];
+	u64 reports[];
 };
 
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From 72a5eb9d9c319c99c11cfd9cfb486380dd136840 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Fri, 10 Jul 2020 14:39:19 +0100
Subject: firmware: arm_scmi: Remove fixed size fields from
 reports/scmi_event_header

Event reports are used to convey information describing events to the
registered user-callbacks: they are necessarily derived from the underlying
raw SCMI events' messages but they are not meant to expose or directly
mirror any of those messages data layout, which belong to the protocol
layer.

Using fixed size types for report fields, mirroring messages structure,
is at odd with this: get rid of them using more generic, equivalent,
typing.

Substitute scmi_event_header fixed size fields with generic types too and
shuffle around fields definitions to minimize implicit padding while
adapting involved functions.

Link: https://lore.kernel.org/r/20200710133919.39792-3-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/base.c    |  2 +-
 drivers/firmware/arm_scmi/driver.c  |  4 +--
 drivers/firmware/arm_scmi/notify.c  | 15 ++++++-----
 drivers/firmware/arm_scmi/notify.h  |  8 +++---
 drivers/firmware/arm_scmi/perf.c    |  2 +-
 drivers/firmware/arm_scmi/power.c   |  2 +-
 drivers/firmware/arm_scmi/reset.c   |  2 +-
 drivers/firmware/arm_scmi/sensors.c |  2 +-
 include/linux/scmi_protocol.h       | 52 ++++++++++++++++++-------------------
 9 files changed, 46 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c
index 54f378e946f1..9853bd3c4d45 100644
--- a/drivers/firmware/arm_scmi/base.c
+++ b/drivers/firmware/arm_scmi/base.c
@@ -273,7 +273,7 @@ static int scmi_base_set_notify_enabled(const struct scmi_handle *handle,
 }
 
 static void *scmi_base_fill_custom_report(const struct scmi_handle *handle,
-					  u8 evt_id, u64 timestamp,
+					  u8 evt_id, ktime_t timestamp,
 					  const void *payld, size_t payld_sz,
 					  void *report, u32 *src_id)
 {
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 19a4287fc0f7..03ec74242c14 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -205,13 +205,13 @@ __scmi_xfer_put(struct scmi_xfers_info *minfo, struct scmi_xfer *xfer)
 
 static void scmi_handle_notification(struct scmi_chan_info *cinfo, u32 msg_hdr)
 {
-	u64 ts;
 	struct scmi_xfer *xfer;
 	struct device *dev = cinfo->dev;
 	struct scmi_info *info = handle_to_scmi_info(cinfo->handle);
 	struct scmi_xfers_info *minfo = &info->rx_minfo;
+	ktime_t ts;
 
-	ts = ktime_get_boottime_ns();
+	ts = ktime_get_boottime();
 	xfer = scmi_xfer_get(cinfo->handle, minfo);
 	if (IS_ERR(xfer)) {
 		dev_err(dev, "failed to get free message slot (%ld)\n",
diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
index 752415367305..4731daaacd19 100644
--- a/drivers/firmware/arm_scmi/notify.c
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -80,6 +80,7 @@
 #include <linux/err.h>
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
+#include <linux/ktime.h>
 #include <linux/kfifo.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -246,18 +247,18 @@ struct events_queue {
  * struct scmi_event_header  - A utility header
  * @timestamp: The timestamp, in nanoseconds (boottime), which was associated
  *	       to this event as soon as it entered the SCMI RX ISR
- * @evt_id: Event ID (corresponds to the Event MsgID for this Protocol)
  * @payld_sz: Effective size of the embedded message payload which follows
+ * @evt_id: Event ID (corresponds to the Event MsgID for this Protocol)
  * @payld: A reference to the embedded event payload
  *
  * This header is prepended to each received event message payload before
  * queueing it on the related &struct events_queue.
  */
 struct scmi_event_header {
-	u64	timestamp;
-	u8	evt_id;
-	size_t	payld_sz;
-	u8	payld[];
+	ktime_t timestamp;
+	size_t payld_sz;
+	unsigned char evt_id;
+	unsigned char payld[];
 };
 
 struct scmi_registered_event;
@@ -572,7 +573,7 @@ static void scmi_events_dispatcher(struct work_struct *work)
  * Return: 0 on Success
  */
 int scmi_notify(const struct scmi_handle *handle, u8 proto_id, u8 evt_id,
-		const void *buf, size_t len, u64 ts)
+		const void *buf, size_t len, ktime_t ts)
 {
 	struct scmi_registered_event *r_evt;
 	struct scmi_event_header eh;
@@ -595,7 +596,7 @@ int scmi_notify(const struct scmi_handle *handle, u8 proto_id, u8 evt_id,
 	if (kfifo_avail(&r_evt->proto->equeue.kfifo) < sizeof(eh) + len) {
 		dev_warn(handle->dev,
 			 "queue full, dropping proto_id:%d  evt_id:%d  ts:%lld\n",
-			 proto_id, evt_id, ts);
+			 proto_id, evt_id, ktime_to_ns(ts));
 		return -ENOMEM;
 	}
 
diff --git a/drivers/firmware/arm_scmi/notify.h b/drivers/firmware/arm_scmi/notify.h
index 3791bb7aa79b..3485f20fa70e 100644
--- a/drivers/firmware/arm_scmi/notify.h
+++ b/drivers/firmware/arm_scmi/notify.h
@@ -10,6 +10,7 @@
 #define _SCMI_NOTIFY_H
 
 #include <linux/device.h>
+#include <linux/ktime.h>
 #include <linux/types.h>
 
 #define SCMI_PROTO_QUEUE_SZ	4096
@@ -48,8 +49,9 @@ struct scmi_event_ops {
 	int (*set_notify_enabled)(const struct scmi_handle *handle,
 				  u8 evt_id, u32 src_id, bool enabled);
 	void *(*fill_custom_report)(const struct scmi_handle *handle,
-				    u8 evt_id, u64 timestamp, const void *payld,
-				    size_t payld_sz, void *report, u32 *src_id);
+				    u8 evt_id, ktime_t timestamp,
+				    const void *payld, size_t payld_sz,
+				    void *report, u32 *src_id);
 };
 
 int scmi_notification_init(struct scmi_handle *handle);
@@ -61,6 +63,6 @@ int scmi_register_protocol_events(const struct scmi_handle *handle,
 				  const struct scmi_event *evt, int num_events,
 				  int num_sources);
 int scmi_notify(const struct scmi_handle *handle, u8 proto_id, u8 evt_id,
-		const void *buf, size_t len, u64 ts);
+		const void *buf, size_t len, ktime_t ts);
 
 #endif /* _SCMI_NOTIFY_H */
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 8bcad96e06ca..3e1e87012c95 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -780,7 +780,7 @@ static int scmi_perf_set_notify_enabled(const struct scmi_handle *handle,
 }
 
 static void *scmi_perf_fill_custom_report(const struct scmi_handle *handle,
-					  u8 evt_id, u64 timestamp,
+					  u8 evt_id, ktime_t timestamp,
 					  const void *payld, size_t payld_sz,
 					  void *report, u32 *src_id)
 {
diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index 4f6757980739..46f213644c49 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -227,7 +227,7 @@ static int scmi_power_set_notify_enabled(const struct scmi_handle *handle,
 }
 
 static void *scmi_power_fill_custom_report(const struct scmi_handle *handle,
-					   u8 evt_id, u64 timestamp,
+					   u8 evt_id, ktime_t timestamp,
 					   const void *payld, size_t payld_sz,
 					   void *report, u32 *src_id)
 {
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index fb7cb517900b..3691bafca057 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -240,7 +240,7 @@ static int scmi_reset_set_notify_enabled(const struct scmi_handle *handle,
 }
 
 static void *scmi_reset_fill_custom_report(const struct scmi_handle *handle,
-					   u8 evt_id, u64 timestamp,
+					   u8 evt_id, ktime_t timestamp,
 					   const void *payld, size_t payld_sz,
 					   void *report, u32 *src_id)
 {
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 2120ac4787c9..1af0ad362e82 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -296,7 +296,7 @@ static int scmi_sensor_set_notify_enabled(const struct scmi_handle *handle,
 }
 
 static void *scmi_sensor_fill_custom_report(const struct scmi_handle *handle,
-					    u8 evt_id, u64 timestamp,
+					    u8 evt_id, ktime_t timestamp,
 					    const void *payld, size_t payld_sz,
 					    void *report, u32 *src_id)
 {
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 7d4348fb7330..7e5dd7d1e221 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -381,47 +381,47 @@ enum scmi_notification_events {
 };
 
 struct scmi_power_state_changed_report {
-	u64 timestamp;
-	u32 agent_id;
-	u32 domain_id;
-	u32 power_state;
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	domain_id;
+	unsigned int	power_state;
 };
 
 struct scmi_perf_limits_report {
-	u64 timestamp;
-	u32 agent_id;
-	u32 domain_id;
-	u32 range_max;
-	u32 range_min;
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	domain_id;
+	unsigned int	range_max;
+	unsigned int	range_min;
 };
 
 struct scmi_perf_level_report {
-	u64 timestamp;
-	u32 agent_id;
-	u32 domain_id;
-	u32 performance_level;
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	domain_id;
+	unsigned int	performance_level;
 };
 
 struct scmi_sensor_trip_point_report {
-	u64 timestamp;
-	u32 agent_id;
-	u32 sensor_id;
-	u32 trip_point_desc;
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	sensor_id;
+	unsigned int	trip_point_desc;
 };
 
 struct scmi_reset_issued_report {
-	u64 timestamp;
-	u32 agent_id;
-	u32 domain_id;
-	u32 reset_state;
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	domain_id;
+	unsigned int	reset_state;
 };
 
 struct scmi_base_error_report {
-	u64 timestamp;
-	u32 agent_id;
-	bool fatal;
-	u16 cmd_count;
-	u64 reports[];
+	ktime_t			timestamp;
+	unsigned int		agent_id;
+	bool			fatal;
+	unsigned int		cmd_count;
+	unsigned long long	reports[];
 };
 
 #endif /* _LINUX_SCMI_PROTOCOL_H */
-- 
cgit v1.2.3


From b52fb259dff8d0da76d38005464edf4201b01d76 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 29 May 2020 12:23:41 +0200
Subject: mmc: core: Always allow the card detect uevent to be consumed

The approach to allow userspace ~5s to consume the uevent, which is
triggered when a new card is inserted/initialized, currently requires the
mmc host to support system wakeup.

This is unnecessary limiting, especially for an mmc host that relies on a
GPIO IRQ for card detect. More precisely, the mmc host may not support
system wakeup for its corresponding struct device, while the GPIO IRQ still
could be configured as a wakeup IRQ via enable_irq_wake().

To support all various cases, let's simply drop the need for the wakeup
support. Instead let's always register a wakeup source and activate it for
all card detect IRQs by calling __pm_wakeup_event().

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20200529102341.12529-1-ulf.hansson@linaro.org
---
 drivers/mmc/core/core.c  | 10 +++++-----
 drivers/mmc/core/host.c  |  3 +++
 include/linux/mmc/host.h |  1 +
 3 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 8d2b808e9b58..aff3fa937674 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1455,12 +1455,12 @@ void mmc_detach_bus(struct mmc_host *host)
 void _mmc_detect_change(struct mmc_host *host, unsigned long delay, bool cd_irq)
 {
 	/*
-	 * If the device is configured as wakeup, we prevent a new sleep for
-	 * 5 s to give provision for user space to consume the event.
+	 * Prevent system sleep for 5s to allow user space to consume the
+	 * corresponding uevent. This is especially useful, when CD irq is used
+	 * as a system wakeup, but doesn't hurt in other cases.
 	 */
-	if (cd_irq && !(host->caps & MMC_CAP_NEEDS_POLL) &&
-		device_can_wakeup(mmc_dev(host)))
-		pm_wakeup_event(mmc_dev(host), 5000);
+	if (cd_irq && !(host->caps & MMC_CAP_NEEDS_POLL))
+		__pm_wakeup_event(host->ws, 5000);
 
 	host->detect_change = 1;
 	mmc_schedule_delayed_work(&host->detect, delay);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index c8768726d925..6141a85749ca 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/pagemap.h>
+#include <linux/pm_wakeup.h>
 #include <linux/export.h>
 #include <linux/leds.h>
 #include <linux/slab.h>
@@ -36,6 +37,7 @@ static DEFINE_IDA(mmc_host_ida);
 static void mmc_host_classdev_release(struct device *dev)
 {
 	struct mmc_host *host = cls_dev_to_mmc_host(dev);
+	wakeup_source_unregister(host->ws);
 	ida_simple_remove(&mmc_host_ida, host->index);
 	kfree(host);
 }
@@ -400,6 +402,7 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	host->index = err;
 
 	dev_set_name(&host->class_dev, "mmc%d", host->index);
+	host->ws = wakeup_source_register(NULL, dev_name(&host->class_dev));
 
 	host->parent = dev;
 	host->class_dev.parent = dev;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 7149bab555d7..1fa4fa1caef5 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -287,6 +287,7 @@ struct mmc_host {
 #ifdef CONFIG_PM_SLEEP
 	struct notifier_block	pm_notify;
 #endif
+	struct wakeup_source	*ws;		/* Enable consume of uevents */
 	u32			max_current_330;
 	u32			max_current_300;
 	u32			max_current_180;
-- 
cgit v1.2.3


From 4f7872ae920fccf6a07ca64cc40792bd6be0d0d5 Mon Sep 17 00:00:00 2001
From: Pali Rohár <pali@kernel.org>
Date: Mon, 29 Jun 2020 09:21:44 +0200
Subject: mmc: sdio: Move SDIO IDs from rsi_sdio driver to common include file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Define appropriate macro names for consistency with other macros.

Signed-off-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20200629072144.24351-1-pali@kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/net/wireless/rsi/rsi_91x_sdio.c | 8 ++++----
 drivers/net/wireless/rsi/rsi_sdio.h     | 4 ----
 include/linux/mmc/sdio_ids.h            | 4 ++++
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 5d6143a55187..a04ff75c409f 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -1038,10 +1038,10 @@ static int rsi_probe(struct sdio_func *pfunction,
 		goto fail_free_adapter;
 	}
 
-	if (pfunction->device == RSI_SDIO_PID_9113) {
+	if (pfunction->device == SDIO_DEVICE_ID_RSI_9113) {
 		rsi_dbg(ERR_ZONE, "%s: 9113 module detected\n", __func__);
 		adapter->device_model = RSI_DEV_9113;
-	} else  if (pfunction->device == RSI_SDIO_PID_9116) {
+	} else  if (pfunction->device == SDIO_DEVICE_ID_RSI_9116) {
 		rsi_dbg(ERR_ZONE, "%s: 9116 module detected\n", __func__);
 		adapter->device_model = RSI_DEV_9116;
 	} else {
@@ -1526,8 +1526,8 @@ static const struct dev_pm_ops rsi_pm_ops = {
 #endif
 
 static const struct sdio_device_id rsi_dev_table[] =  {
-	{ SDIO_DEVICE(RSI_SDIO_VENDOR_ID, RSI_SDIO_PID_9113) },
-	{ SDIO_DEVICE(RSI_SDIO_VENDOR_ID, RSI_SDIO_PID_9116) },
+	{ SDIO_DEVICE(SDIO_VENDOR_ID_RSI, SDIO_DEVICE_ID_RSI_9113) },
+	{ SDIO_DEVICE(SDIO_VENDOR_ID_RSI, SDIO_DEVICE_ID_RSI_9116) },
 	{ /* Blank */},
 };
 
diff --git a/drivers/net/wireless/rsi/rsi_sdio.h b/drivers/net/wireless/rsi/rsi_sdio.h
index c5cfb6238f73..9afc1d0d2684 100644
--- a/drivers/net/wireless/rsi/rsi_sdio.h
+++ b/drivers/net/wireless/rsi/rsi_sdio.h
@@ -28,10 +28,6 @@
 #include <linux/mmc/sdio_ids.h>
 #include "rsi_main.h"
 
-#define RSI_SDIO_VENDOR_ID   0x041B
-#define RSI_SDIO_PID_9113    0x9330
-#define RSI_SDIO_PID_9116    0x9116
-
 enum sdio_interrupt_type {
 	BUFFER_FULL         = 0x0,
 	BUFFER_AVAILABLE    = 0x2,
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 15ed8ce9d394..ab41801c5f51 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -118,6 +118,10 @@
 #define SDIO_DEVICE_ID_SIANO_NOVA_A0		0x1100
 #define SDIO_DEVICE_ID_SIANO_STELLAR 		0x5347
 
+#define SDIO_VENDOR_ID_RSI			0x041b
+#define SDIO_DEVICE_ID_RSI_9113			0x9330
+#define SDIO_DEVICE_ID_RSI_9116			0x9116
+
 #define SDIO_VENDOR_ID_TI_WL1251		0x104c
 #define SDIO_DEVICE_ID_TI_WL1251		0x9066
 
-- 
cgit v1.2.3


From 2f96126500991f356b9eacdc6611bec78e6253ed Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Wed, 1 Jul 2020 11:23:17 +0100
Subject: arch: arm: mach-omap2: mmc: Move omap_mmc_notify_cover_event()
 prototype
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building the kernel with W=1 the build system complains of:

 drivers/mmc/host/omap.c:854:6: warning: no previous prototype for ‘omap_mmc_notify_cover_event’ [-Wmissing-prototypes]
 854 | void omap_mmc_notify_cover_event(struct device *dev, int num, int is_closed)
 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~

If we move the prototype into a shared headerfile the build system
will be satisfied.  Rather than create a whole new headerfile just
for this purpose, it makes sense to use the already existing
mmc-omap.h.

Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: linux-mmc@vger.kernel.org
Cc: Tony Lindgren <tony@atomide.com>
Cc: linux-omap@vger.kernel.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20200701102317.235032-1-lee.jones@linaro.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/mmc.h              | 4 ----
 include/linux/platform_data/mmc-omap.h | 3 +++
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap2/mmc.h b/arch/arm/mach-omap2/mmc.h
index 7f4e053c3434..b5533e93cb63 100644
--- a/arch/arm/mach-omap2/mmc.h
+++ b/arch/arm/mach-omap2/mmc.h
@@ -16,7 +16,3 @@ static inline int omap_msdi_reset(struct omap_hwmod *oh)
 	return 0;
 }
 #endif
-
-/* called from board-specific card detection service routine */
-extern void omap_mmc_notify_cover_event(struct device *dev, int slot,
-					int is_closed);
diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h
index 9acf0e87aa9b..f0b8947e6b07 100644
--- a/include/linux/platform_data/mmc-omap.h
+++ b/include/linux/platform_data/mmc-omap.h
@@ -116,3 +116,6 @@ struct omap_mmc_platform_data {
 
 	} slots[OMAP_MMC_MAX_SLOTS];
 };
+
+extern void omap_mmc_notify_cover_event(struct device *dev, int slot,
+					int is_closed);
-- 
cgit v1.2.3


From ec02760b63c21c439d44956e9c66d0af24011f03 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Tue, 7 Jul 2020 20:58:42 +0900
Subject: mmc: core: Add MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND

The commit 5a36d6bcdf23 ("mmc: core: Add DT-bindings for
MMC_CAP2_FULL_PWR_CYCLE") added the "full-pwr-cycle" property which
is possible to perform a full power cycle of the card at any time.

However, some environment (like r8a77951-salvator-xs) is possible
to perform a full power cycle of the card in suspend via firmware
(PSCI on arm-trusted-firmware). So, in worst case, since we are
not doing a graceful shutdown of the eMMC device (just cut VCCQ
while the eMMC is "sleeping") in suspend, it could lead to internal
data corruptions. So, add MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND
to do a graceful shutdown which issues Power Off notification
before entering system suspend.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1594123122-13156-3-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/host.c  | 2 ++
 drivers/mmc/core/mmc.c   | 3 ++-
 include/linux/mmc/host.h | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 793597556cd7..ce43f7573d80 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -277,6 +277,8 @@ int mmc_of_parse(struct mmc_host *host)
 		host->caps |= MMC_CAP_SDIO_IRQ;
 	if (device_property_read_bool(dev, "full-pwr-cycle"))
 		host->caps2 |= MMC_CAP2_FULL_PWR_CYCLE;
+	if (device_property_read_bool(dev, "full-pwr-cycle-in-suspend"))
+		host->caps2 |= MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND;
 	if (device_property_read_bool(dev, "keep-power-in-suspend"))
 		host->pm_caps |= MMC_PM_KEEP_POWER;
 	if (device_property_read_bool(dev, "wakeup-source") ||
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 4203303f946a..b3fa193de846 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -2038,7 +2038,8 @@ static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
 		goto out;
 
 	if (mmc_can_poweroff_notify(host->card) &&
-		((host->caps2 & MMC_CAP2_FULL_PWR_CYCLE) || !is_suspend))
+	    ((host->caps2 & MMC_CAP2_FULL_PWR_CYCLE) || !is_suspend ||
+	     (host->caps2 & MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND)))
 		err = mmc_poweroff_notify(host->card, notify_type);
 	else if (mmc_can_sleep(host->card))
 		err = mmc_sleep(host);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 1fa4fa1caef5..c5b6e97cb21a 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -352,6 +352,7 @@ struct mmc_host {
 
 #define MMC_CAP2_BOOTPART_NOACC	(1 << 0)	/* Boot partition no access */
 #define MMC_CAP2_FULL_PWR_CYCLE	(1 << 2)	/* Can do full power cycle */
+#define MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND (1 << 3) /* Can do full power cycle in suspend */
 #define MMC_CAP2_HS200_1_8V_SDR	(1 << 5)        /* can support */
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
-- 
cgit v1.2.3


From f4bf09d5303ab3896604c58363fc705ba649ccb8 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Sun, 21 Jun 2020 15:33:39 +0300
Subject: iio: core: remove iio_priv_to_dev() helper

All users of this helper have been updated to not use it.
Remove it now, so that we don't need to move it when creating the
iio_dev_opaque structure.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 30c9c9502478..e2df67a3b9ab 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -689,12 +689,6 @@ static inline void *iio_priv(const struct iio_dev *indio_dev)
 	return indio_dev->priv;
 }
 
-static inline struct iio_dev *iio_priv_to_dev(void *priv)
-{
-	return (struct iio_dev *)((char *)priv -
-				  ALIGN(sizeof(struct iio_dev), IIO_ALIGN));
-}
-
 void iio_device_free(struct iio_dev *indio_dev);
 struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv);
 struct iio_trigger *devm_iio_trigger_alloc(struct device *dev,
-- 
cgit v1.2.3


From 8cdcd8aeee2819199ec7f68114b77b04c10611d3 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 25 Jun 2020 22:02:52 +0200
Subject: spi: imx/fsl-lpspi: Convert to GPIO descriptors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This converts the two Freescale i.MX SPI drivers
Freescale i.MX (CONFIG_SPI_IMX) and Freescale i.MX LPSPI
(CONFIG_SPI_FSL_LPSPI) to use GPIO descriptors handled in
the SPI core for GPIO chip selects whether defined in
the device tree or a board file.

The reason why both are converted at the same time is
that they were both using the same platform data and
platform device population helpers when using
board files intertwining the code so this gives a cleaner
cut.

The platform device creation was passing a platform data
container from each boardfile down to the driver using
struct spi_imx_master from <linux/platform_data/spi-imx.h>,
but this was only conveying the number of chipselects and
an int * array of the chipselect GPIO numbers.

The imx27 and imx31 platforms had code passing the
now-unused platform data when creating the platform devices,
this has been repurposed to pass around GPIO descriptor
tables. The platform data struct that was just passing an
array of integers and number of chip selects for the GPIO
lines has been removed.

The number of chipselects used to be passed from the board
file, because this number also limits the number of native
chipselects that the platform can use. To deal with this we
just augment the i.MX (CONFIG_SPI_IMX) driver to support 3
chipselects if the platform does not define "num-cs" as a
device property (such as from the device tree). This covers
all the legacy boards as these use <= 3 native chip selects
(or GPIO lines, and in that case the number of chip selects
is determined by the core from the number of available
GPIO lines). Any new boards should use device tree, so
this is a reasonable simplification to cover all old
boards.

The LPSPI driver never assigned the number of chipselects
and thus always fall back to the core default of 1 chip
select if no GPIOs are defined in the device tree.

The Freescale i.MX driver was already partly utilizing
the SPI core to obtain the GPIO numbers from the device tree,
so this completes the transtion to let the core handle all
of it.

All board files and the core i.MX boardfile registration
code is augmented to account for these changes.

This has been compile-tested with the imx_v4_v5_defconfig
and the imx_v6_v7_defconfig.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Shawn Guo <shawnguo@kernel.org>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Robin Gong <yibin.gong@nxp.com>
Cc: Trent Piepho <tpiepho@impinj.com>
Cc: Clark Wang <xiaoning.wang@nxp.com>
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Pengutronix Kernel Team <kernel@pengutronix.de>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: NXP Linux Team <linux-imx@nxp.com>
Link: https://lore.kernel.org/r/20200625200252.207614-1-linus.walleij@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-imx/devices-imx27.h            | 10 +--
 arch/arm/mach-imx/devices-imx31.h            | 10 +--
 arch/arm/mach-imx/devices/devices-common.h   |  5 +-
 arch/arm/mach-imx/devices/platform-spi_imx.c |  9 +--
 arch/arm/mach-imx/mach-mx27_3ds.c            | 40 ++++++++----
 arch/arm/mach-imx/mach-mx31_3ds.c            | 13 +---
 arch/arm/mach-imx/mach-mx31lilly.c           | 14 +----
 arch/arm/mach-imx/mach-mx31lite.c            | 19 +-----
 arch/arm/mach-imx/mach-mx31moboard.c         | 12 +---
 arch/arm/mach-imx/mach-pca100.c              | 21 +++++--
 arch/arm/mach-imx/mach-pcm037_eet.c          |  7 +--
 drivers/spi/spi-fsl-lpspi.c                  | 47 +-------------
 drivers/spi/spi-imx.c                        | 92 +++++-----------------------
 include/linux/platform_data/spi-imx.h        | 33 ----------
 14 files changed, 88 insertions(+), 244 deletions(-)
 delete mode 100644 include/linux/platform_data/spi-imx.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-imx/devices-imx27.h b/arch/arm/mach-imx/devices-imx27.h
index f89f4ae0e1ca..583a1d773d68 100644
--- a/arch/arm/mach-imx/devices-imx27.h
+++ b/arch/arm/mach-imx/devices-imx27.h
@@ -75,11 +75,11 @@ extern const struct imx_mxc_w1_data imx27_mxc_w1_data;
 	imx_add_mxc_w1(&imx27_mxc_w1_data)
 
 extern const struct imx_spi_imx_data imx27_cspi_data[];
-#define imx27_add_cspi(id, pdata)	\
-	imx_add_spi_imx(&imx27_cspi_data[id], pdata)
-#define imx27_add_spi_imx0(pdata)	imx27_add_cspi(0, pdata)
-#define imx27_add_spi_imx1(pdata)	imx27_add_cspi(1, pdata)
-#define imx27_add_spi_imx2(pdata)	imx27_add_cspi(2, pdata)
+#define imx27_add_cspi(id, gtable) \
+	imx_add_spi_imx(&imx27_cspi_data[id], gtable)
+#define imx27_add_spi_imx0(gtable)	imx27_add_cspi(0, gtable)
+#define imx27_add_spi_imx1(gtable)	imx27_add_cspi(1, gtable)
+#define imx27_add_spi_imx2(gtable)	imx27_add_cspi(2, gtable)
 
 extern const struct imx_pata_imx_data imx27_pata_imx_data;
 #define imx27_add_pata_imx() \
diff --git a/arch/arm/mach-imx/devices-imx31.h b/arch/arm/mach-imx/devices-imx31.h
index 5a4ba35a47ed..f7cc62372532 100644
--- a/arch/arm/mach-imx/devices-imx31.h
+++ b/arch/arm/mach-imx/devices-imx31.h
@@ -69,11 +69,11 @@ extern const struct imx_mxc_w1_data imx31_mxc_w1_data;
 	imx_add_mxc_w1(&imx31_mxc_w1_data)
 
 extern const struct imx_spi_imx_data imx31_cspi_data[];
-#define imx31_add_cspi(id, pdata)	\
-	imx_add_spi_imx(&imx31_cspi_data[id], pdata)
-#define imx31_add_spi_imx0(pdata)	imx31_add_cspi(0, pdata)
-#define imx31_add_spi_imx1(pdata)	imx31_add_cspi(1, pdata)
-#define imx31_add_spi_imx2(pdata)	imx31_add_cspi(2, pdata)
+#define imx31_add_cspi(id, gtable) \
+	imx_add_spi_imx(&imx31_cspi_data[id], gtable)
+#define imx31_add_spi_imx0(gtable)	imx31_add_cspi(0, gtable)
+#define imx31_add_spi_imx1(gtable)	imx31_add_cspi(1, gtable)
+#define imx31_add_spi_imx2(gtable)	imx31_add_cspi(2, gtable)
 
 extern const struct imx_pata_imx_data imx31_pata_imx_data;
 #define imx31_add_pata_imx() \
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index 2a685adec1df..f8f3e4967c31 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/init.h>
+#include <linux/gpio/machine.h>
 #include <linux/platform_data/dma-imx-sdma.h>
 
 extern struct device mxc_aips_bus;
@@ -276,7 +277,6 @@ struct platform_device *__init imx_add_sdhci_esdhc_imx(
 		const struct imx_sdhci_esdhc_imx_data *data,
 		const struct esdhc_platform_data *pdata);
 
-#include <linux/platform_data/spi-imx.h>
 struct imx_spi_imx_data {
 	const char *devid;
 	int id;
@@ -285,8 +285,7 @@ struct imx_spi_imx_data {
 	int irq;
 };
 struct platform_device *__init imx_add_spi_imx(
-		const struct imx_spi_imx_data *data,
-		const struct spi_imx_master *pdata);
+	const struct imx_spi_imx_data *data, struct gpiod_lookup_table *gtable);
 
 struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase,
 					int irq, int irq_err);
diff --git a/arch/arm/mach-imx/devices/platform-spi_imx.c b/arch/arm/mach-imx/devices/platform-spi_imx.c
index f2cafa52c187..27747bf628a3 100644
--- a/arch/arm/mach-imx/devices/platform-spi_imx.c
+++ b/arch/arm/mach-imx/devices/platform-spi_imx.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2009-2010 Pengutronix
  * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
  */
+#include <linux/gpio/machine.h>
 #include "../hardware.h"
 #include "devices-common.h"
 
@@ -57,8 +58,7 @@ const struct imx_spi_imx_data imx35_cspi_data[] __initconst = {
 #endif /* ifdef CONFIG_SOC_IMX35 */
 
 struct platform_device *__init imx_add_spi_imx(
-		const struct imx_spi_imx_data *data,
-		const struct spi_imx_master *pdata)
+	const struct imx_spi_imx_data *data, struct gpiod_lookup_table *gtable)
 {
 	struct resource res[] = {
 		{
@@ -71,7 +71,8 @@ struct platform_device *__init imx_add_spi_imx(
 			.flags = IORESOURCE_IRQ,
 		},
 	};
-
+	if (gtable)
+		gpiod_add_lookup_table(gtable);
 	return imx_add_platform_device(data->devid, data->id,
-			res, ARRAY_SIZE(res), pdata, sizeof(*pdata));
+			res, ARRAY_SIZE(res), NULL, 0);
 }
diff --git a/arch/arm/mach-imx/mach-mx27_3ds.c b/arch/arm/mach-imx/mach-mx27_3ds.c
index 1da5f07952ac..2db4475b7f85 100644
--- a/arch/arm/mach-imx/mach-mx27_3ds.c
+++ b/arch/arm/mach-imx/mach-mx27_3ds.c
@@ -303,18 +303,34 @@ static struct imx_ssi_platform_data mx27_3ds_ssi_pdata = {
 };
 
 /* SPI */
-static int spi1_chipselect[] = {SPI1_SS0};
-
-static const struct spi_imx_master spi1_pdata __initconst = {
-	.chipselect	= spi1_chipselect,
-	.num_chipselect	= ARRAY_SIZE(spi1_chipselect),
+static struct gpiod_lookup_table mx27_spi1_gpiod_table = {
+	.dev_id = "imx27-cspi.0", /* Actual device name for spi1 */
+	.table = {
+		/*
+		 * The i.MX27 has the i.MX21 GPIO controller, the SPI1 CS GPIO
+		 * SPI1_SS0 is numbered IMX_GPIO_NR(4, 28).
+		 *
+		 * This is in "bank 4" which is subtracted by one in the macro
+		 * so this is actually bank 3 on "imx21-gpio.3".
+		 */
+		GPIO_LOOKUP_IDX("imx21-gpio.3", 28, "cs", 0, GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
-static int spi2_chipselect[] = {SPI2_SS0};
-
-static const struct spi_imx_master spi2_pdata __initconst = {
-	.chipselect	= spi2_chipselect,
-	.num_chipselect	= ARRAY_SIZE(spi2_chipselect),
+static struct gpiod_lookup_table mx27_spi2_gpiod_table = {
+	.dev_id = "imx27-cspi.1", /* Actual device name for spi2 */
+	.table = {
+		/*
+		 * The i.MX27 has the i.MX21 GPIO controller, the SPI2 CS GPIO
+		 * SPI2_SS0 is numbered IMX_GPIO_NR(4, 21).
+		 *
+		 * This is in "bank 4" which is subtracted by one in the macro
+		 * so this is actually bank 3 on "imx21-gpio.3".
+		 */
+		GPIO_LOOKUP_IDX("imx21-gpio.3", 21, "cs", 0, GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct imx_fb_videomode mx27_3ds_modes[] = {
@@ -397,8 +413,8 @@ static void __init mx27pdk_init(void)
 	imx27_add_imx_keypad(&mx27_3ds_keymap_data);
 	imx27_add_imx2_wdt();
 
-	imx27_add_spi_imx1(&spi2_pdata);
-	imx27_add_spi_imx0(&spi1_pdata);
+	imx27_add_spi_imx1(&mx27_spi2_gpiod_table);
+	imx27_add_spi_imx0(&mx27_spi1_gpiod_table);
 
 	imx27_add_imx_i2c(0, &mx27_3ds_i2c0_data);
 	imx27_add_imx_fb(&mx27_3ds_fb_data);
diff --git a/arch/arm/mach-imx/mach-mx31_3ds.c b/arch/arm/mach-imx/mach-mx31_3ds.c
index e81386190479..23e63d3b4c6a 100644
--- a/arch/arm/mach-imx/mach-mx31_3ds.c
+++ b/arch/arm/mach-imx/mach-mx31_3ds.c
@@ -378,15 +378,6 @@ static struct imx_ssi_platform_data mx31_3ds_ssi_pdata = {
 	.flags = IMX_SSI_DMA | IMX_SSI_NET,
 };
 
-/* SPI */
-static const struct spi_imx_master spi0_pdata __initconst = {
-	.num_chipselect	= 3,
-};
-
-static const struct spi_imx_master spi1_pdata __initconst = {
-	.num_chipselect	= 3,
-};
-
 static struct spi_board_info mx31_3ds_spi_devs[] __initdata = {
 	{
 		.modalias	= "mc13783",
@@ -561,14 +552,14 @@ static void __init mx31_3ds_init(void)
 	imx31_add_imx_uart0(&uart_pdata);
 	imx31_add_mxc_nand(&mx31_3ds_nand_board_info);
 
-	imx31_add_spi_imx1(&spi1_pdata);
+	imx31_add_spi_imx1(NULL);
 
 	imx31_add_imx_keypad(&mx31_3ds_keymap_data);
 
 	imx31_add_imx2_wdt();
 	imx31_add_imx_i2c0(&mx31_3ds_i2c0_data);
 
-	imx31_add_spi_imx0(&spi0_pdata);
+	imx31_add_spi_imx0(NULL);
 	imx31_add_ipu_core();
 	imx31_add_mx3_sdc_fb(&mx3fb_pdata);
 
diff --git a/arch/arm/mach-imx/mach-mx31lilly.c b/arch/arm/mach-imx/mach-mx31lilly.c
index 8f725248299e..4b955ccc92cd 100644
--- a/arch/arm/mach-imx/mach-mx31lilly.c
+++ b/arch/arm/mach-imx/mach-mx31lilly.c
@@ -215,16 +215,6 @@ static void __init lilly1131_usb_init(void)
 		imx31_add_mxc_ehci_hs(2, &usbh2_pdata);
 }
 
-/* SPI */
-
-static const struct spi_imx_master spi0_pdata __initconst = {
-	.num_chipselect = 3,
-};
-
-static const struct spi_imx_master spi1_pdata __initconst = {
-	.num_chipselect = 3,
-};
-
 static struct mc13xxx_platform_data mc13783_pdata __initdata = {
 	.flags = MC13XXX_USE_RTC | MC13XXX_USE_TOUCHSCREEN,
 };
@@ -281,8 +271,8 @@ static void __init mx31lilly_board_init(void)
 	mxc_iomux_alloc_pin(MX31_PIN_CSPI2_SS1__SS1, "SPI2_SS1");
 	mxc_iomux_alloc_pin(MX31_PIN_CSPI2_SS2__SS2, "SPI2_SS2");
 
-	imx31_add_spi_imx0(&spi0_pdata);
-	imx31_add_spi_imx1(&spi1_pdata);
+	imx31_add_spi_imx0(NULL);
+	imx31_add_spi_imx1(NULL);
 
 	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 }
diff --git a/arch/arm/mach-imx/mach-mx31lite.c b/arch/arm/mach-imx/mach-mx31lite.c
index c0055f57c02d..aaccf52f7ac1 100644
--- a/arch/arm/mach-imx/mach-mx31lite.c
+++ b/arch/arm/mach-imx/mach-mx31lite.c
@@ -73,11 +73,6 @@ static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
-/* SPI */
-static const struct spi_imx_master spi0_pdata __initconst = {
-	.num_chipselect	= 3,
-};
-
 static const struct mxc_nand_platform_data
 mx31lite_nand_board_info __initconst  = {
 	.width = 1,
@@ -111,16 +106,6 @@ static struct platform_device smsc911x_device = {
 	},
 };
 
-/*
- * SPI
- *
- * The MC13783 is the only hard-wired SPI device on the module.
- */
-
-static const struct spi_imx_master spi1_pdata __initconst = {
-	.num_chipselect	= 1,
-};
-
 static struct mc13xxx_platform_data mc13783_pdata __initdata = {
 	.flags = MC13XXX_USE_RTC,
 };
@@ -246,13 +231,13 @@ static void __init mx31lite_init(void)
 				      "mx31lite");
 
 	imx31_add_imx_uart0(&uart_pdata);
-	imx31_add_spi_imx0(&spi0_pdata);
+	imx31_add_spi_imx0(NULL);
 
 	/* NOR and NAND flash */
 	platform_device_register(&physmap_flash_device);
 	imx31_add_mxc_nand(&mx31lite_nand_board_info);
 
-	imx31_add_spi_imx1(&spi1_pdata);
+	imx31_add_spi_imx1(NULL);
 
 	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 }
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index 36f08f45b0ca..96845a4eaf57 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -143,10 +143,6 @@ static const struct imxi2c_platform_data moboard_i2c1_data __initconst = {
 	.bitrate = 100000,
 };
 
-static const struct spi_imx_master moboard_spi1_pdata __initconst = {
-	.num_chipselect	= 3,
-};
-
 static struct regulator_consumer_supply sdhc_consumers[] = {
 	{
 		.dev_name = "imx31-mmc.0",
@@ -287,10 +283,6 @@ static struct spi_board_info moboard_spi_board_info[] __initdata = {
 	},
 };
 
-static const struct spi_imx_master moboard_spi2_pdata __initconst = {
-	.num_chipselect	= 2,
-};
-
 #define SDHC1_CD IOMUX_TO_GPIO(MX31_PIN_ATA_CS0)
 #define SDHC1_WP IOMUX_TO_GPIO(MX31_PIN_ATA_CS1)
 
@@ -514,8 +506,8 @@ static void __init mx31moboard_init(void)
 	imx31_add_imx_i2c0(&moboard_i2c0_data);
 	imx31_add_imx_i2c1(&moboard_i2c1_data);
 
-	imx31_add_spi_imx1(&moboard_spi1_pdata);
-	imx31_add_spi_imx2(&moboard_spi2_pdata);
+	imx31_add_spi_imx1(NULL);
+	imx31_add_spi_imx2(NULL);
 
 	mx31moboard_init_cam();
 
diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c
index 2e28e1b5cddf..27a3678e0658 100644
--- a/arch/arm/mach-imx/mach-pca100.c
+++ b/arch/arm/mach-imx/mach-pca100.c
@@ -14,6 +14,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 
@@ -188,11 +189,19 @@ static struct spi_board_info pca100_spi_board_info[] __initdata = {
 	},
 };
 
-static int pca100_spi_cs[] = {SPI1_SS0, SPI1_SS1};
-
-static const struct spi_imx_master pca100_spi0_data __initconst = {
-	.chipselect	= pca100_spi_cs,
-	.num_chipselect = ARRAY_SIZE(pca100_spi_cs),
+static struct gpiod_lookup_table pca100_spi0_gpiod_table = {
+	.dev_id = "imx27-cspi.0", /* Actual device name for spi0 */
+	.table = {
+		/*
+		 * The i.MX27 has the i.MX21 GPIO controller, port D is
+		 * bank 3 and thus named "imx21-gpio.3".
+		 * SPI1_SS0 is GPIO_PORTD + 28
+		 * SPI1_SS1 is GPIO_PORTD + 27
+		 */
+		GPIO_LOOKUP_IDX("imx21-gpio.3", 28, "cs", 0, GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP_IDX("imx21-gpio.3", 27, "cs", 1, GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static void pca100_ac97_warm_reset(struct snd_ac97 *ac97)
@@ -362,7 +371,7 @@ static void __init pca100_init(void)
 	mxc_gpio_mode(GPIO_PORTD | 27 | GPIO_GPIO | GPIO_IN);
 	spi_register_board_info(pca100_spi_board_info,
 				ARRAY_SIZE(pca100_spi_board_info));
-	imx27_add_spi_imx0(&pca100_spi0_data);
+	imx27_add_spi_imx0(&pca100_spi0_gpiod_table);
 
 	imx27_add_imx_fb(&pca100_fb_data);
 
diff --git a/arch/arm/mach-imx/mach-pcm037_eet.c b/arch/arm/mach-imx/mach-pcm037_eet.c
index 51f5142920cf..8b0e03a595c1 100644
--- a/arch/arm/mach-imx/mach-pcm037_eet.c
+++ b/arch/arm/mach-imx/mach-pcm037_eet.c
@@ -52,11 +52,6 @@ static struct spi_board_info pcm037_spi_dev[] = {
 	},
 };
 
-/* Platform Data for MXC CSPI */
-static const struct spi_imx_master pcm037_spi1_pdata __initconst = {
-	.num_chipselect = 2,
-};
-
 /* GPIO-keys input device */
 static struct gpio_keys_button pcm037_gpio_keys[] = {
 	{
@@ -163,7 +158,7 @@ int __init pcm037_eet_init_devices(void)
 
 	/* SPI */
 	spi_register_board_info(pcm037_spi_dev, ARRAY_SIZE(pcm037_spi_dev));
-	imx31_add_spi_imx0(&pcm037_spi1_pdata);
+	imx31_add_spi_imx0(NULL);
 
 	imx_add_gpio_keys(&pcm037_gpio_keys_platform_data);
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 1552b28b9515..38b44446c947 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -11,7 +11,6 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -19,11 +18,9 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/dma-imx.h>
-#include <linux/platform_data/spi-imx.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
@@ -224,20 +221,6 @@ static int lpspi_unprepare_xfer_hardware(struct spi_controller *controller)
 	return 0;
 }
 
-static int fsl_lpspi_prepare_message(struct spi_controller *controller,
-				     struct spi_message *msg)
-{
-	struct fsl_lpspi_data *fsl_lpspi =
-					spi_controller_get_devdata(controller);
-	struct spi_device *spi = msg->spi;
-	int gpio = fsl_lpspi->chipselect[spi->chip_select];
-
-	if (gpio_is_valid(gpio))
-		gpio_direction_output(gpio, spi->mode & SPI_CS_HIGH ? 0 : 1);
-
-	return 0;
-}
-
 static void fsl_lpspi_write_tx_fifo(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u8 txfifo_cnt;
@@ -831,13 +814,10 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
 
 static int fsl_lpspi_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	struct fsl_lpspi_data *fsl_lpspi;
 	struct spi_controller *controller;
-	struct spi_imx_master *lpspi_platform_info =
-		dev_get_platdata(&pdev->dev);
 	struct resource *res;
-	int i, ret, irq;
+	int ret, irq;
 	u32 temp;
 	bool is_slave;
 
@@ -867,6 +847,8 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	controller->dev.of_node = pdev->dev.of_node;
 	controller->bus_num = pdev->id;
 	controller->slave_abort = fsl_lpspi_slave_abort;
+	if (!fsl_lpspi->is_slave)
+		controller->use_gpio_descriptors = true;
 
 	ret = devm_spi_register_controller(&pdev->dev, controller);
 	if (ret < 0) {
@@ -874,29 +856,6 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 		goto out_controller_put;
 	}
 
-	if (!fsl_lpspi->is_slave) {
-		for (i = 0; i < controller->num_chipselect; i++) {
-			int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
-
-			if (!gpio_is_valid(cs_gpio) && lpspi_platform_info)
-				cs_gpio = lpspi_platform_info->chipselect[i];
-
-			fsl_lpspi->chipselect[i] = cs_gpio;
-			if (!gpio_is_valid(cs_gpio))
-				continue;
-
-			ret = devm_gpio_request(&pdev->dev,
-						fsl_lpspi->chipselect[i],
-						DRIVER_NAME);
-			if (ret) {
-				dev_err(&pdev->dev, "can't get cs gpios\n");
-				goto out_controller_put;
-			}
-		}
-		controller->cs_gpios = fsl_lpspi->chipselect;
-		controller->prepare_message = fsl_lpspi_prepare_message;
-	}
-
 	init_completion(&fsl_lpspi->xfer_done);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 2b8d339f1936..fdc25f549378 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -8,7 +8,6 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -21,10 +20,9 @@
 #include <linux/types.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
+#include <linux/property.h>
 
 #include <linux/platform_data/dma-imx.h>
-#include <linux/platform_data/spi-imx.h>
 
 #define DRIVER_NAME "spi_imx"
 
@@ -723,7 +721,7 @@ static int mx31_prepare_transfer(struct spi_imx_data *spi_imx,
 		reg |= MX31_CSPICTRL_POL;
 	if (spi->mode & SPI_CS_HIGH)
 		reg |= MX31_CSPICTRL_SSPOL;
-	if (!gpio_is_valid(spi->cs_gpio))
+	if (!spi->cs_gpiod)
 		reg |= (spi->chip_select) <<
 			(is_imx35_cspi(spi_imx) ? MX35_CSPICTRL_CS_SHIFT :
 						  MX31_CSPICTRL_CS_SHIFT);
@@ -824,7 +822,7 @@ static int mx21_prepare_transfer(struct spi_imx_data *spi_imx,
 		reg |= MX21_CSPICTRL_POL;
 	if (spi->mode & SPI_CS_HIGH)
 		reg |= MX21_CSPICTRL_SSPOL;
-	if (!gpio_is_valid(spi->cs_gpio))
+	if (!spi->cs_gpiod)
 		reg |= spi->chip_select << MX21_CSPICTRL_CS_SHIFT;
 
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
@@ -1056,20 +1054,6 @@ static const struct of_device_id spi_imx_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, spi_imx_dt_ids);
 
-static void spi_imx_chipselect(struct spi_device *spi, int is_active)
-{
-	int active = is_active != BITBANG_CS_INACTIVE;
-	int dev_is_lowactive = !(spi->mode & SPI_CS_HIGH);
-
-	if (spi->mode & SPI_NO_CS)
-		return;
-
-	if (!gpio_is_valid(spi->cs_gpio))
-		return;
-
-	gpio_set_value(spi->cs_gpio, dev_is_lowactive ^ active);
-}
-
 static void spi_imx_set_burst_len(struct spi_imx_data *spi_imx, int n_bits)
 {
 	u32 ctrl;
@@ -1533,15 +1517,6 @@ static int spi_imx_setup(struct spi_device *spi)
 	dev_dbg(&spi->dev, "%s: mode %d, %u bpw, %d hz\n", __func__,
 		 spi->mode, spi->bits_per_word, spi->max_speed_hz);
 
-	if (spi->mode & SPI_NO_CS)
-		return 0;
-
-	if (gpio_is_valid(spi->cs_gpio))
-		gpio_direction_output(spi->cs_gpio,
-				      spi->mode & SPI_CS_HIGH ? 0 : 1);
-
-	spi_imx_chipselect(spi, BITBANG_CS_INACTIVE);
-
 	return 0;
 }
 
@@ -1599,20 +1574,14 @@ static int spi_imx_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *of_id =
 			of_match_device(spi_imx_dt_ids, &pdev->dev);
-	struct spi_imx_master *mxc_platform_info =
-			dev_get_platdata(&pdev->dev);
 	struct spi_master *master;
 	struct spi_imx_data *spi_imx;
 	struct resource *res;
-	int i, ret, irq, spi_drctl;
+	int ret, irq, spi_drctl;
 	const struct spi_imx_devtype_data *devtype_data = of_id ? of_id->data :
 		(struct spi_imx_devtype_data *)pdev->id_entry->driver_data;
 	bool slave_mode;
-
-	if (!np && !mxc_platform_info) {
-		dev_err(&pdev->dev, "can't get the platform data\n");
-		return -EINVAL;
-	}
+	u32 val;
 
 	slave_mode = devtype_data->has_slavemode &&
 			of_property_read_bool(np, "spi-slave");
@@ -1635,6 +1604,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 	master->bus_num = np ? -1 : pdev->id;
+	master->use_gpio_descriptors = true;
 
 	spi_imx = spi_master_get_devdata(master);
 	spi_imx->bitbang.master = master;
@@ -1643,28 +1613,17 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	spi_imx->devtype_data = devtype_data;
 
-	/* Get number of chip selects, either platform data or OF */
-	if (mxc_platform_info) {
-		master->num_chipselect = mxc_platform_info->num_chipselect;
-		if (mxc_platform_info->chipselect) {
-			master->cs_gpios = devm_kcalloc(&master->dev,
-				master->num_chipselect, sizeof(int),
-				GFP_KERNEL);
-			if (!master->cs_gpios)
-				return -ENOMEM;
-
-			for (i = 0; i < master->num_chipselect; i++)
-				master->cs_gpios[i] = mxc_platform_info->chipselect[i];
-		}
-	} else {
-		u32 num_cs;
-
-		if (!of_property_read_u32(np, "num-cs", &num_cs))
-			master->num_chipselect = num_cs;
-		/* If not preset, default value of 1 is used */
-	}
+	/*
+	 * Get number of chip selects from device properties. This can be
+	 * coming from device tree or boardfiles, if it is not defined,
+	 * a default value of 3 chip selects will be used, as all the legacy
+	 * board files have <= 3 chip selects.
+	 */
+	if (!device_property_read_u32(&pdev->dev, "num-cs", &val))
+		master->num_chipselect = val;
+	else
+		master->num_chipselect = 3;
 
-	spi_imx->bitbang.chipselect = spi_imx_chipselect;
 	spi_imx->bitbang.setup_transfer = spi_imx_setupxfer;
 	spi_imx->bitbang.txrx_bufs = spi_imx_transfer;
 	spi_imx->bitbang.master->setup = spi_imx_setup;
@@ -1749,31 +1708,12 @@ static int spi_imx_probe(struct platform_device *pdev)
 		goto out_clk_put;
 	}
 
-	/* Request GPIO CS lines, if any */
-	if (!spi_imx->slave_mode && master->cs_gpios) {
-		for (i = 0; i < master->num_chipselect; i++) {
-			if (!gpio_is_valid(master->cs_gpios[i]))
-				continue;
-
-			ret = devm_gpio_request(&pdev->dev,
-						master->cs_gpios[i],
-						DRIVER_NAME);
-			if (ret) {
-				dev_err(&pdev->dev, "Can't get CS GPIO %i\n",
-					master->cs_gpios[i]);
-				goto out_spi_bitbang;
-			}
-		}
-	}
-
 	dev_info(&pdev->dev, "probed\n");
 
 	clk_disable(spi_imx->clk_ipg);
 	clk_disable(spi_imx->clk_per);
 	return ret;
 
-out_spi_bitbang:
-	spi_bitbang_stop(&spi_imx->bitbang);
 out_clk_put:
 	clk_disable_unprepare(spi_imx->clk_ipg);
 out_put_per:
diff --git a/include/linux/platform_data/spi-imx.h b/include/linux/platform_data/spi-imx.h
deleted file mode 100644
index 328f670d10bd..000000000000
--- a/include/linux/platform_data/spi-imx.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef __MACH_SPI_H_
-#define __MACH_SPI_H_
-
-/*
- * struct spi_imx_master - device.platform_data for SPI controller devices.
- * @chipselect: Array of chipselects for this master or NULL.  Numbers >= 0
- *              mean GPIO pins, -ENOENT means internal CSPI chipselect
- *              matching the position in the array.  E.g., if chipselect[1] =
- *              -ENOENT then a SPI slave using chip select 1 will use the
- *              native SS1 line of the CSPI.  Omitting the array will use
- *              all native chip selects.
-
- *              Normally you want to use gpio based chip selects as the CSPI
- *              module tries to be intelligent about when to assert the
- *              chipselect:  The CSPI module deasserts the chipselect once it
- *              runs out of input data.  The other problem is that it is not
- *              possible to mix between high active and low active chipselects
- *              on one single bus using the internal chipselects.
- *              Unfortunately, on some SoCs, Freescale decided to put some
- *              chipselects on dedicated pins which are not usable as gpios,
- *              so we have to support the internal chipselects.
- *
- * @num_chipselect: If @chipselect is specified, ARRAY_SIZE(chipselect),
- *                  otherwise the number of native chip selects.
- */
-struct spi_imx_master {
-	int	*chipselect;
-	int	num_chipselect;
-};
-
-#endif /* __MACH_SPI_H_*/
-- 
cgit v1.2.3


From 5a2798ab32ba2952cfe25701ee460bccbd434c75 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 11 Jul 2020 23:53:23 +0200
Subject: bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros

Adding support to generate .BTF_ids section that will hold BTF
ID lists for verifier.

Adding macros that will help to define lists of BTF ID values
placed in .BTF_ids section. They are initially filled with zeros
(during compilation) and resolved later during the linking phase
by resolve_btfids tool.

Following defines list of one BTF ID value:

  BTF_ID_LIST(bpf_skb_output_btf_ids)
  BTF_ID(struct, sk_buff)

It also defines following variable to access the list:

  extern u32 bpf_skb_output_btf_ids[];

The BTF_ID_UNUSED macro defines 4 zero bytes. It's used when we
want to define 'unused' entry in BTF_ID_LIST, like:

  BTF_ID_LIST(bpf_skb_output_btf_ids)
  BTF_ID(struct, sk_buff)
  BTF_ID_UNUSED
  BTF_ID(struct, task_struct)

Suggested-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200711215329.41165-4-jolsa@kernel.org
---
 include/asm-generic/vmlinux.lds.h |  4 ++
 include/linux/btf_ids.h           | 87 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)
 create mode 100644 include/linux/btf_ids.h

(limited to 'include/linux')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index db600ef218d7..0be2ee265931 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -641,6 +641,10 @@
 		__start_BTF = .;					\
 		*(.BTF)							\
 		__stop_BTF = .;						\
+	}								\
+	. = ALIGN(4);							\
+	.BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) {			\
+		*(.BTF_ids)						\
 	}
 #else
 #define BTF
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
new file mode 100644
index 000000000000..fe019774f8a7
--- /dev/null
+++ b/include/linux/btf_ids.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_BTF_IDS_H
+#define _LINUX_BTF_IDS_H
+
+#include <linux/compiler.h> /* for __PASTE */
+
+/*
+ * Following macros help to define lists of BTF IDs placed
+ * in .BTF_ids section. They are initially filled with zeros
+ * (during compilation) and resolved later during the
+ * linking phase by resolve_btfids tool.
+ *
+ * Any change in list layout must be reflected in resolve_btfids
+ * tool logic.
+ */
+
+#define BTF_IDS_SECTION ".BTF_ids"
+
+#define ____BTF_ID(symbol)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".local " #symbol " ;                          \n"	\
+".type  " #symbol ", @object;                  \n"	\
+".size  " #symbol ", 4;                        \n"	\
+#symbol ":                                     \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+#define __BTF_ID(symbol) \
+	____BTF_ID(symbol)
+
+#define __ID(prefix) \
+	__PASTE(prefix, __COUNTER__)
+
+/*
+ * The BTF_ID defines unique symbol for each ID pointing
+ * to 4 zero bytes.
+ */
+#define BTF_ID(prefix, name) \
+	__BTF_ID(__ID(__BTF_ID__##prefix##__##name##__))
+
+/*
+ * The BTF_ID_LIST macro defines pure (unsorted) list
+ * of BTF IDs, with following layout:
+ *
+ * BTF_ID_LIST(list1)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ *
+ * list1:
+ * __BTF_ID__type1__name1__1:
+ * .zero 4
+ * __BTF_ID__type2__name2__2:
+ * .zero 4
+ *
+ */
+#define __BTF_ID_LIST(name)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".local " #name ";                             \n"	\
+#name ":;                                      \n"	\
+".popsection;                                  \n");	\
+
+#define BTF_ID_LIST(name)				\
+__BTF_ID_LIST(name)					\
+extern u32 name[];
+
+/*
+ * The BTF_ID_UNUSED macro defines 4 zero bytes.
+ * It's used when we want to define 'unused' entry
+ * in BTF_ID_LIST, like:
+ *
+ *   BTF_ID_LIST(bpf_skb_output_btf_ids)
+ *   BTF_ID(struct, sk_buff)
+ *   BTF_ID_UNUSED
+ *   BTF_ID(struct, task_struct)
+ */
+
+#define BTF_ID_UNUSED					\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+
+#endif
-- 
cgit v1.2.3


From 6659061045cc93f609e100b128f30581e5f012e9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 10 Jun 2020 08:20:05 -0700
Subject: fs: Move __scm_install_fd() to __receive_fd()

In preparation for users of the "install a received file" logic outside
of net/ (pidfd and seccomp), relocate and rename __scm_install_fd() from
net/core/scm.c to __receive_fd() in fs/file.c, and provide a wrapper
named receive_fd_user(), as future patches will change the interface
to __receive_fd().

Additionally add a comment to fd_install() as a counterpoint to how
__receive_fd() interacts with fput().

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Dmitry Kadashev <dkadashev@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Ido Schimmel <idosch@idosch.org>
Cc: Ioana Ciornei <ioana.ciornei@nxp.com>
Cc: linux-fsdevel@vger.kernel.org
Cc: netdev@vger.kernel.org
Reviewed-by: Sargun Dhillon <sargun@sargun.me>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/file.c            | 45 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/file.h |  8 ++++++++
 include/net/scm.h    |  1 -
 net/compat.c         |  2 +-
 net/core/scm.c       | 27 +--------------------------
 5 files changed, 55 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index abb8b7081d7a..0cd598cab476 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -18,6 +18,7 @@
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <net/sock.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -613,6 +614,10 @@ void __fd_install(struct files_struct *files, unsigned int fd,
 	rcu_read_unlock_sched();
 }
 
+/*
+ * This consumes the "file" refcount, so callers should treat it
+ * as if they had called fput(file).
+ */
 void fd_install(unsigned int fd, struct file *file)
 {
 	__fd_install(current->files, fd, file);
@@ -931,6 +936,46 @@ out_unlock:
 	return err;
 }
 
+/**
+ * __receive_fd() - Install received file into file descriptor table
+ *
+ * @file: struct file that was received from another process
+ * @ufd: __user pointer to write new fd number to
+ * @o_flags: the O_* flags to apply to the new fd entry
+ *
+ * Installs a received file into the file descriptor table, with appropriate
+ * checks and count updates. Writes the fd number to userspace.
+ *
+ * This helper handles its own reference counting of the incoming
+ * struct file.
+ *
+ * Returns -ve on error.
+ */
+int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+{
+	int new_fd;
+	int error;
+
+	error = security_file_receive(file);
+	if (error)
+		return error;
+
+	new_fd = get_unused_fd_flags(o_flags);
+	if (new_fd < 0)
+		return new_fd;
+
+	error = put_user(new_fd, ufd);
+	if (error) {
+		put_unused_fd(new_fd);
+		return error;
+	}
+
+	/* Bump the sock usage counts, if any. */
+	__receive_sock(file);
+	fd_install(new_fd, get_file(file));
+	return 0;
+}
+
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/include/linux/file.h b/include/linux/file.h
index 122f80084a3e..b14ff2ffd0bd 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -91,6 +91,14 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
+extern int __receive_fd(struct file *file, int __user *ufd,
+			unsigned int o_flags);
+static inline int receive_fd_user(struct file *file, int __user *ufd,
+				  unsigned int o_flags)
+{
+	return __receive_fd(file, ufd, o_flags);
+}
+
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
 
diff --git a/include/net/scm.h b/include/net/scm.h
index 581a94d6c613..1ce365f4c256 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -37,7 +37,6 @@ struct scm_cookie {
 #endif
 };
 
-int __scm_install_fd(struct file *file, int __user *ufd, unsigned int o_flags);
 void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm);
 void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm);
 int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm);
diff --git a/net/compat.c b/net/compat.c
index 27d477fdcaa0..e74cd3dae8b0 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -298,7 +298,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 	int err = 0, i;
 
 	for (i = 0; i < fdmax; i++) {
-		err = __scm_install_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err)
 			break;
 	}
diff --git a/net/core/scm.c b/net/core/scm.c
index 44f03213dcab..67c166a7820d 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -280,31 +280,6 @@ void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_inter
 }
 EXPORT_SYMBOL(put_cmsg_scm_timestamping);
 
-int __scm_install_fd(struct file *file, int __user *ufd, unsigned int o_flags)
-{
-	int new_fd;
-	int error;
-
-	error = security_file_receive(file);
-	if (error)
-		return error;
-
-	new_fd = get_unused_fd_flags(o_flags);
-	if (new_fd < 0)
-		return new_fd;
-
-	error = put_user(new_fd, ufd);
-	if (error) {
-		put_unused_fd(new_fd);
-		return error;
-	}
-
-	/* Bump the sock usage counts, if any. */
-	__receive_sock(file);
-	fd_install(new_fd, get_file(file));
-	return 0;
-}
-
 static int scm_max_fds(struct msghdr *msg)
 {
 	if (msg->msg_controllen <= sizeof(struct cmsghdr))
@@ -331,7 +306,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	}
 
 	for (i = 0; i < fdmax; i++) {
-		err = __scm_install_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err)
 			break;
 	}
-- 
cgit v1.2.3


From deefa7f3505ae2fb6a7cb75f50134b65a1dd1494 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 10 Jun 2020 20:47:45 -0700
Subject: fs: Add receive_fd() wrapper for __receive_fd()

For both pidfd and seccomp, the __user pointer is not used. Update
__receive_fd() to make writing to ufd optional via a NULL check. However,
for the receive_fd_user() wrapper, ufd is NULL checked so an -EFAULT
can be returned to avoid changing the SCM_RIGHTS interface behavior. Add
new wrapper receive_fd() for pidfd and seccomp that does not use the ufd
argument. For the new helper, the allocated fd needs to be returned on
success. Update the existing callers to handle it.

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Sargun Dhillon <sargun@sargun.me>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/file.c            | 17 ++++++++++-------
 include/linux/file.h |  7 +++++++
 net/compat.c         |  2 +-
 net/core/scm.c       |  2 +-
 4 files changed, 19 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 0cd598cab476..56d96d5c0c9f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -944,12 +944,13 @@ out_unlock:
  * @o_flags: the O_* flags to apply to the new fd entry
  *
  * Installs a received file into the file descriptor table, with appropriate
- * checks and count updates. Writes the fd number to userspace.
+ * checks and count updates. Optionally writes the fd number to userspace, if
+ * @ufd is non-NULL.
  *
  * This helper handles its own reference counting of the incoming
  * struct file.
  *
- * Returns -ve on error.
+ * Returns newly install fd or -ve on error.
  */
 int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 {
@@ -964,16 +965,18 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	if (new_fd < 0)
 		return new_fd;
 
-	error = put_user(new_fd, ufd);
-	if (error) {
-		put_unused_fd(new_fd);
-		return error;
+	if (ufd) {
+		error = put_user(new_fd, ufd);
+		if (error) {
+			put_unused_fd(new_fd);
+			return error;
+		}
 	}
 
 	/* Bump the sock usage counts, if any. */
 	__receive_sock(file);
 	fd_install(new_fd, get_file(file));
-	return 0;
+	return new_fd;
 }
 
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
diff --git a/include/linux/file.h b/include/linux/file.h
index b14ff2ffd0bd..d9fee9f5c8da 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/posix_types.h>
+#include <linux/errno.h>
 
 struct file;
 
@@ -96,8 +97,14 @@ extern int __receive_fd(struct file *file, int __user *ufd,
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
+	if (ufd == NULL)
+		return -EFAULT;
 	return __receive_fd(file, ufd, o_flags);
 }
+static inline int receive_fd(struct file *file, unsigned int o_flags)
+{
+	return __receive_fd(file, NULL, o_flags);
+}
 
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
diff --git a/net/compat.c b/net/compat.c
index e74cd3dae8b0..dc7ddbc2b15e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -299,7 +299,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 
 	for (i = 0; i < fdmax; i++) {
 		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
-		if (err)
+		if (err < 0)
 			break;
 	}
 
diff --git a/net/core/scm.c b/net/core/scm.c
index 67c166a7820d..8156d4fb8a39 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -307,7 +307,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 
 	for (i = 0; i < fdmax; i++) {
 		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
-		if (err)
+		if (err < 0)
 			break;
 	}
 
-- 
cgit v1.2.3


From 173817151b15d5a72a9bef1d2df7e6e7f6750f2e Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 10 Jun 2020 08:46:58 -0700
Subject: fs: Expand __receive_fd() to accept existing fd

Expand __receive_fd() with support for replace_fd() for the coming seccomp
"addfd" ioctl(). Add new wrapper receive_fd_replace() for the new behavior
and update existing wrappers to retain old behavior.

Thanks to Colin Ian King <colin.king@canonical.com> for pointing out an
uninitialized variable exposure in an earlier version of this patch.

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dmitry Kadashev <dkadashev@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Sargun Dhillon <sargun@sargun.me>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/file.c            | 25 +++++++++++++++++++------
 include/linux/file.h | 10 +++++++---
 2 files changed, 26 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 56d96d5c0c9f..4fb111735d1d 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -939,6 +939,7 @@ out_unlock:
 /**
  * __receive_fd() - Install received file into file descriptor table
  *
+ * @fd: fd to install into (if negative, a new fd will be allocated)
  * @file: struct file that was received from another process
  * @ufd: __user pointer to write new fd number to
  * @o_flags: the O_* flags to apply to the new fd entry
@@ -952,7 +953,7 @@ out_unlock:
  *
  * Returns newly install fd or -ve on error.
  */
-int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags)
 {
 	int new_fd;
 	int error;
@@ -961,21 +962,33 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	if (error)
 		return error;
 
-	new_fd = get_unused_fd_flags(o_flags);
-	if (new_fd < 0)
-		return new_fd;
+	if (fd < 0) {
+		new_fd = get_unused_fd_flags(o_flags);
+		if (new_fd < 0)
+			return new_fd;
+	} else {
+		new_fd = fd;
+	}
 
 	if (ufd) {
 		error = put_user(new_fd, ufd);
 		if (error) {
-			put_unused_fd(new_fd);
+			if (fd < 0)
+				put_unused_fd(new_fd);
 			return error;
 		}
 	}
 
+	if (fd < 0) {
+		fd_install(new_fd, get_file(file));
+	} else {
+		error = replace_fd(new_fd, file, o_flags);
+		if (error)
+			return error;
+	}
+
 	/* Bump the sock usage counts, if any. */
 	__receive_sock(file);
-	fd_install(new_fd, get_file(file));
 	return new_fd;
 }
 
diff --git a/include/linux/file.h b/include/linux/file.h
index d9fee9f5c8da..225982792fa2 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -92,18 +92,22 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
-extern int __receive_fd(struct file *file, int __user *ufd,
+extern int __receive_fd(int fd, struct file *file, int __user *ufd,
 			unsigned int o_flags);
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
 	if (ufd == NULL)
 		return -EFAULT;
-	return __receive_fd(file, ufd, o_flags);
+	return __receive_fd(-1, file, ufd, o_flags);
 }
 static inline int receive_fd(struct file *file, unsigned int o_flags)
 {
-	return __receive_fd(file, NULL, o_flags);
+	return __receive_fd(-1, file, NULL, o_flags);
+}
+static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags)
+{
+	return __receive_fd(fd, file, NULL, o_flags);
 }
 
 extern void flush_delayed_fput(void);
-- 
cgit v1.2.3


From c1326210477ecc06c53221f0005c64419aba30d6 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:20 +0000
Subject: nfs,nfsd: NFSv4.2 extended attribute protocol definitions

Add definitions for the new operations, errors and flags as defined
in RFC 8276 (File System Extended Attributes in NFSv4).

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/nfs4.h      | 20 ++++++++++++++++++++
 include/uapi/linux/nfs4.h |  3 +++
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 4dba3c948932..e6ca9d1d2e76 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -150,6 +150,12 @@ enum nfs_opnum4 {
 	OP_WRITE_SAME = 70,
 	OP_CLONE = 71,
 
+	/* xattr support (RFC8726) */
+	OP_GETXATTR                = 72,
+	OP_SETXATTR                = 73,
+	OP_LISTXATTRS              = 74,
+	OP_REMOVEXATTR             = 75,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -280,6 +286,10 @@ enum nfsstat4 {
 	NFS4ERR_WRONG_LFS = 10092,
 	NFS4ERR_BADLABEL = 10093,
 	NFS4ERR_OFFLOAD_NO_REQS = 10094,
+
+	/* xattr (RFC8276) */
+	NFS4ERR_NOXATTR        = 10095,
+	NFS4ERR_XATTR2BIG      = 10096,
 };
 
 static inline bool seqid_mutating_err(u32 err)
@@ -452,6 +462,7 @@ enum change_attr_type4 {
 #define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 #define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
+#define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
@@ -700,4 +711,13 @@ struct nl4_server {
 		struct nfs42_netaddr	nl4_addr; /* NL4_NETADDR */
 	} u;
 };
+
+/*
+ * Options for setxattr. These match the flags for setxattr(2).
+ */
+enum nfs4_setxattr_options {
+	SETXATTR4_EITHER	= 0,
+	SETXATTR4_CREATE	= 1,
+	SETXATTR4_REPLACE	= 2,
+};
 #endif
diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h
index 8572930cf5b0..bf197e99b98f 100644
--- a/include/uapi/linux/nfs4.h
+++ b/include/uapi/linux/nfs4.h
@@ -33,6 +33,9 @@
 #define NFS4_ACCESS_EXTEND      0x0008
 #define NFS4_ACCESS_DELETE      0x0010
 #define NFS4_ACCESS_EXECUTE     0x0020
+#define NFS4_ACCESS_XAREAD      0x0040
+#define NFS4_ACCESS_XAWRITE     0x0080
+#define NFS4_ACCESS_XALIST      0x0100
 
 #define NFS4_FH_PERSISTENT		0x0000
 #define NFS4_FH_NOEXPIRE_WITH_OPEN	0x0001
-- 
cgit v1.2.3


From 08b5d5014a27e717826999ad20e394a8811aae92 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:18 +0000
Subject: xattr: break delegations in {set,remove}xattr

set/removexattr on an exported filesystem should break NFS delegations.
This is true in general, but also for the upcoming support for
RFC 8726 (NFSv4 extended attribute support). Make sure that they do.

Additionally, they need to grow a _locked variant, since callers might
call this with i_rwsem held (like the NFS server code).

Cc: stable@vger.kernel.org # v4.9+
Cc: linux-fsdevel@vger.kernel.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/xattr.c            | 84 ++++++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/xattr.h |  2 ++
 2 files changed, 79 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/xattr.c b/fs/xattr.c
index 91608d9bfc6a..95f38f57347f 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 	return error;
 }
 
-
+/**
+ * __vfs_setxattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - xattr name to set
+ *  @value - value to set @name to
+ *  @size - size of @value
+ *  @flags - flags to pass into filesystem operations
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		size_t size, int flags)
+__vfs_setxattr_locked(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_setxattr(dentry, name, value, size, flags);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
+
+int
+vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
+		size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_setxattr_locked(dentry, name, value, size, flags,
+	    &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
@@ -378,8 +415,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name)
 }
 EXPORT_SYMBOL(__vfs_removexattr);
 
+/**
+ * __vfs_removexattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - name of xattr to remove
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_removexattr(struct dentry *dentry, const char *name)
+__vfs_removexattr_locked(struct dentry *dentry, const char *name,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -388,11 +435,14 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_removexattr(dentry, name);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_removexattr(dentry, name);
 
 	if (!error) {
@@ -401,12 +451,32 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	}
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
+
+int
+vfs_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_removexattr_locked(dentry, name, &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_removexattr);
 
-
 /*
  * Extended attribute SET operations
  */
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 47eaa34f8761..a2f3cd02653c 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -51,8 +51,10 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
 int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int);
 int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int);
+int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **);
 int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
 int __vfs_removexattr(struct dentry *, const char *);
+int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **);
 int vfs_removexattr(struct dentry *, const char *);
 
 ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
-- 
cgit v1.2.3


From cab8d289c5ad541a5351a651d95c4086b7f84d7c Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:19 +0000
Subject: xattr: add a function to check if a namespace is supported

Add a function that checks is an extended attribute namespace is
supported for an inode, meaning that a handler must be present
for either the whole namespace, or at least one synthetic
xattr in the namespace.

To be used by the nfs server code when being queried for extended
attributes support.

Cc: linux-fsdevel@vger.kernel.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/xattr.c            | 27 +++++++++++++++++++++++++++
 include/linux/xattr.h |  2 ++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/fs/xattr.c b/fs/xattr.c
index 95f38f57347f..386b45676d7e 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -134,6 +134,33 @@ xattr_permission(struct inode *inode, const char *name, int mask)
 	return inode_permission(inode, mask);
 }
 
+/*
+ * Look for any handler that deals with the specified namespace.
+ */
+int
+xattr_supported_namespace(struct inode *inode, const char *prefix)
+{
+	const struct xattr_handler **handlers = inode->i_sb->s_xattr;
+	const struct xattr_handler *handler;
+	size_t preflen;
+
+	if (!(inode->i_opflags & IOP_XATTR)) {
+		if (unlikely(is_bad_inode(inode)))
+			return -EIO;
+		return -EOPNOTSUPP;
+	}
+
+	preflen = strlen(prefix);
+
+	for_each_xattr_handler(handlers, handler) {
+		if (!strncmp(xattr_prefix(handler), prefix, preflen))
+			return 0;
+	}
+
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(xattr_supported_namespace);
+
 int
 __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
 	       const void *value, size_t size, int flags)
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index a2f3cd02653c..fac75810d9d3 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -61,6 +61,8 @@ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_siz
 ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
 			   char **xattr_value, size_t size, gfp_t flags);
 
+int xattr_supported_namespace(struct inode *inode, const char *prefix);
+
 static inline const char *xattr_prefix(const struct xattr_handler *handler)
 {
 	return handler->prefix ?: handler->name;
-- 
cgit v1.2.3


From 23e50fe3a5e6045a573c69d4b0e3d78aa6183323 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:26 +0000
Subject: nfsd: implement the xattr functions and en/decode logic

Implement the main entry points for the *XATTR operations.

Add functions to calculate the reply size for the user extended attribute
operations, and implement the XDR encode / decode logic for these
operations.

Add the user extended attributes operations to nfsd4_ops.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c   | 120 ++++++++++++++
 fs/nfsd/nfs4xdr.c    | 450 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nfs4.h |   2 +-
 3 files changed, 571 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 841aad772798..a527da3d8052 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2097,6 +2097,68 @@ out:
 }
 #endif /* CONFIG_NFSD_PNFS */
 
+static __be32
+nfsd4_getxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	       union nfsd4_op_u *u)
+{
+	struct nfsd4_getxattr *getxattr = &u->getxattr;
+
+	return nfsd_getxattr(rqstp, &cstate->current_fh,
+			     getxattr->getxa_name, &getxattr->getxa_buf,
+			     &getxattr->getxa_len);
+}
+
+static __be32
+nfsd4_setxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	struct nfsd4_setxattr *setxattr = &u->setxattr;
+	__be32 ret;
+
+	if (opens_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	ret = nfsd_setxattr(rqstp, &cstate->current_fh, setxattr->setxa_name,
+			    setxattr->setxa_buf, setxattr->setxa_len,
+			    setxattr->setxa_flags);
+
+	if (!ret)
+		set_change_info(&setxattr->setxa_cinfo, &cstate->current_fh);
+
+	return ret;
+}
+
+static __be32
+nfsd4_listxattrs(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	/*
+	 * Get the entire list, then copy out only the user attributes
+	 * in the encode function.
+	 */
+	return nfsd_listxattr(rqstp, &cstate->current_fh,
+			     &u->listxattrs.lsxa_buf, &u->listxattrs.lsxa_len);
+}
+
+static __be32
+nfsd4_removexattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	struct nfsd4_removexattr *removexattr = &u->removexattr;
+	__be32 ret;
+
+	if (opens_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	ret = nfsd_removexattr(rqstp, &cstate->current_fh,
+	    removexattr->rmxa_name);
+
+	if (!ret)
+		set_change_info(&removexattr->rmxa_cinfo, &cstate->current_fh);
+
+	return ret;
+}
+
 /*
  * NULL call.
  */
@@ -2706,6 +2768,42 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 	return (op_encode_hdr_size + 3) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp,
+				       struct nfsd4_op *op)
+{
+	u32 maxcount, rlen;
+
+	maxcount = svc_max_payload(rqstp);
+	rlen = min_t(u32, XATTR_SIZE_MAX, maxcount);
+
+	return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp,
+				       struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + op_encode_change_info_maxsz)
+		* sizeof(__be32);
+}
+static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp,
+					 struct nfsd4_op *op)
+{
+	u32 maxcount, rlen;
+
+	maxcount = svc_max_payload(rqstp);
+	rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount);
+
+	return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp,
+					  struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + op_encode_change_info_maxsz)
+		* sizeof(__be32);
+}
+
+
 static const struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = nfsd4_access,
@@ -3087,6 +3185,28 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_COPY_NOTIFY",
 		.op_rsize_bop = nfsd4_copy_notify_rsize,
 	},
+	[OP_GETXATTR] = {
+		.op_func = nfsd4_getxattr,
+		.op_name = "OP_GETXATTR",
+		.op_rsize_bop = nfsd4_getxattr_rsize,
+	},
+	[OP_SETXATTR] = {
+		.op_func = nfsd4_setxattr,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_SETXATTR",
+		.op_rsize_bop = nfsd4_setxattr_rsize,
+	},
+	[OP_LISTXATTRS] = {
+		.op_func = nfsd4_listxattrs,
+		.op_name = "OP_LISTXATTRS",
+		.op_rsize_bop = nfsd4_listxattrs_rsize,
+	},
+	[OP_REMOVEXATTR] = {
+		.op_func = nfsd4_removexattr,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_REMOVEXATTR",
+		.op_rsize_bop = nfsd4_removexattr_rsize,
+	},
 };
 
 /**
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 48806b493eba..8bacc0ceae19 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -41,6 +41,8 @@
 #include <linux/pagemap.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/addr.h>
+#include <linux/xattr.h>
+#include <uapi/linux/xattr.h>
 
 #include "idmap.h"
 #include "acl.h"
@@ -1877,6 +1879,208 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 	DECODE_TAIL;
 }
 
+/*
+ * XDR data that is more than PAGE_SIZE in size is normally part of a
+ * read or write. However, the size of extended attributes is limited
+ * by the maximum request size, and then further limited by the underlying
+ * filesystem limits. This can exceed PAGE_SIZE (currently, XATTR_SIZE_MAX
+ * is 64k). Since there is no kvec- or page-based interface to xattrs,
+ * and we're not dealing with contiguous pages, we need to do some copying.
+ */
+
+/*
+ * Decode data into buffer. Uses head and pages constructed by
+ * svcxdr_construct_vector.
+ */
+static __be32
+nfsd4_vbuf_from_vector(struct nfsd4_compoundargs *argp, struct kvec *head,
+		       struct page **pages, char **bufp, u32 buflen)
+{
+	char *tmp, *dp;
+	u32 len;
+
+	if (buflen <= head->iov_len) {
+		/*
+		 * We're in luck, the head has enough space. Just return
+		 * the head, no need for copying.
+		 */
+		*bufp = head->iov_base;
+		return 0;
+	}
+
+	tmp = svcxdr_tmpalloc(argp, buflen);
+	if (tmp == NULL)
+		return nfserr_jukebox;
+
+	dp = tmp;
+	memcpy(dp, head->iov_base, head->iov_len);
+	buflen -= head->iov_len;
+	dp += head->iov_len;
+
+	while (buflen > 0) {
+		len = min_t(u32, buflen, PAGE_SIZE);
+		memcpy(dp, page_address(*pages), len);
+
+		buflen -= len;
+		dp += len;
+		pages++;
+	}
+
+	*bufp = tmp;
+	return 0;
+}
+
+/*
+ * Get a user extended attribute name from the XDR buffer.
+ * It will not have the "user." prefix, so prepend it.
+ * Lastly, check for nul characters in the name.
+ */
+static __be32
+nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep)
+{
+	DECODE_HEAD;
+	char *name, *sp, *dp;
+	u32 namelen, cnt;
+
+	READ_BUF(4);
+	namelen = be32_to_cpup(p++);
+
+	if (namelen > (XATTR_NAME_MAX - XATTR_USER_PREFIX_LEN))
+		return nfserr_nametoolong;
+
+	if (namelen == 0)
+		goto xdr_error;
+
+	READ_BUF(namelen);
+
+	name = svcxdr_tmpalloc(argp, namelen + XATTR_USER_PREFIX_LEN + 1);
+	if (!name)
+		return nfserr_jukebox;
+
+	memcpy(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
+
+	/*
+	 * Copy the extended attribute name over while checking for 0
+	 * characters.
+	 */
+	sp = (char *)p;
+	dp = name + XATTR_USER_PREFIX_LEN;
+	cnt = namelen;
+
+	while (cnt-- > 0) {
+		if (*sp == '\0')
+			goto xdr_error;
+		*dp++ = *sp++;
+	}
+	*dp = '\0';
+
+	*namep = name;
+
+	DECODE_TAIL;
+}
+
+/*
+ * A GETXATTR op request comes without a length specifier. We just set the
+ * maximum length for the reply based on XATTR_SIZE_MAX and the maximum
+ * channel reply size. nfsd_getxattr will probe the length of the xattr,
+ * check it against getxa_len, and allocate + return the value.
+ */
+static __be32
+nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp,
+		      struct nfsd4_getxattr *getxattr)
+{
+	__be32 status;
+	u32 maxcount;
+
+	status = nfsd4_decode_xattr_name(argp, &getxattr->getxa_name);
+	if (status)
+		return status;
+
+	maxcount = svc_max_payload(argp->rqstp);
+	maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount);
+
+	getxattr->getxa_len = maxcount;
+
+	return status;
+}
+
+static __be32
+nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp,
+		      struct nfsd4_setxattr *setxattr)
+{
+	DECODE_HEAD;
+	u32 flags, maxcount, size;
+	struct kvec head;
+	struct page **pagelist;
+
+	READ_BUF(4);
+	flags = be32_to_cpup(p++);
+
+	if (flags > SETXATTR4_REPLACE)
+		return nfserr_inval;
+	setxattr->setxa_flags = flags;
+
+	status = nfsd4_decode_xattr_name(argp, &setxattr->setxa_name);
+	if (status)
+		return status;
+
+	maxcount = svc_max_payload(argp->rqstp);
+	maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount);
+
+	READ_BUF(4);
+	size = be32_to_cpup(p++);
+	if (size > maxcount)
+		return nfserr_xattr2big;
+
+	setxattr->setxa_len = size;
+	if (size > 0) {
+		status = svcxdr_construct_vector(argp, &head, &pagelist, size);
+		if (status)
+			return status;
+
+		status = nfsd4_vbuf_from_vector(argp, &head, pagelist,
+		    &setxattr->setxa_buf, size);
+	}
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp,
+			struct nfsd4_listxattrs *listxattrs)
+{
+	DECODE_HEAD;
+	u32 maxcount;
+
+	READ_BUF(12);
+	p = xdr_decode_hyper(p, &listxattrs->lsxa_cookie);
+
+	/*
+	 * If the cookie  is too large to have even one user.x attribute
+	 * plus trailing '\0' left in a maximum size buffer, it's invalid.
+	 */
+	if (listxattrs->lsxa_cookie >=
+	    (XATTR_LIST_MAX / (XATTR_USER_PREFIX_LEN + 2)))
+		return nfserr_badcookie;
+
+	maxcount = be32_to_cpup(p++);
+	if (maxcount < 8)
+		/* Always need at least 2 words (length and one character) */
+		return nfserr_inval;
+
+	maxcount = min(maxcount, svc_max_payload(argp->rqstp));
+	listxattrs->lsxa_maxcount = maxcount;
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp,
+			 struct nfsd4_removexattr *removexattr)
+{
+	return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name);
+}
+
 static __be32
 nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
 {
@@ -1973,6 +2177,11 @@ static const nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_CLONE]		= (nfsd4_dec)nfsd4_decode_clone,
+	/* RFC 8276 extended atributes operations */
+	[OP_GETXATTR]		= (nfsd4_dec)nfsd4_decode_getxattr,
+	[OP_SETXATTR]		= (nfsd4_dec)nfsd4_decode_setxattr,
+	[OP_LISTXATTRS]		= (nfsd4_dec)nfsd4_decode_listxattrs,
+	[OP_REMOVEXATTR]	= (nfsd4_dec)nfsd4_decode_removexattr,
 };
 
 static inline bool
@@ -4458,6 +4667,241 @@ nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
 	return nfserr;
 }
 
+/*
+ * Encode kmalloc-ed buffer in to XDR stream.
+ */
+static int
+nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen)
+{
+	u32 cplen;
+	__be32 *p;
+
+	cplen = min_t(unsigned long, buflen,
+		      ((void *)xdr->end - (void *)xdr->p));
+	p = xdr_reserve_space(xdr, cplen);
+	if (!p)
+		return nfserr_resource;
+
+	memcpy(p, buf, cplen);
+	buf += cplen;
+	buflen -= cplen;
+
+	while (buflen) {
+		cplen = min_t(u32, buflen, PAGE_SIZE);
+		p = xdr_reserve_space(xdr, cplen);
+		if (!p)
+			return nfserr_resource;
+
+		memcpy(p, buf, cplen);
+
+		if (cplen < PAGE_SIZE) {
+			/*
+			 * We're done, with a length that wasn't page
+			 * aligned, so possibly not word aligned. Pad
+			 * any trailing bytes with 0.
+			 */
+			xdr_encode_opaque_fixed(p, NULL, cplen);
+			break;
+		}
+
+		buflen -= PAGE_SIZE;
+		buf += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static __be32
+nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
+		      struct nfsd4_getxattr *getxattr)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p, err;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+
+	*p = cpu_to_be32(getxattr->getxa_len);
+
+	if (getxattr->getxa_len == 0)
+		return 0;
+
+	err = nfsd4_vbuf_to_stream(xdr, getxattr->getxa_buf,
+				    getxattr->getxa_len);
+
+	kvfree(getxattr->getxa_buf);
+
+	return err;
+}
+
+static __be32
+nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
+		      struct nfsd4_setxattr *setxattr)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 20);
+	if (!p)
+		return nfserr_resource;
+
+	encode_cinfo(p, &setxattr->setxa_cinfo);
+
+	return 0;
+}
+
+/*
+ * See if there are cookie values that can be rejected outright.
+ */
+static __be32
+nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs,
+				u32 *offsetp)
+{
+	u64 cookie = listxattrs->lsxa_cookie;
+
+	/*
+	 * If the cookie is larger than the maximum number we can fit
+	 * in either the buffer we just got back from vfs_listxattr, or,
+	 * XDR-encoded, in the return buffer, it's invalid.
+	 */
+	if (cookie > (listxattrs->lsxa_len) / (XATTR_USER_PREFIX_LEN + 2))
+		return nfserr_badcookie;
+
+	if (cookie > (listxattrs->lsxa_maxcount /
+		      (XDR_QUADLEN(XATTR_USER_PREFIX_LEN + 2) + 4)))
+		return nfserr_badcookie;
+
+	*offsetp = (u32)cookie;
+	return 0;
+}
+
+static __be32
+nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
+			struct nfsd4_listxattrs *listxattrs)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	u32 cookie_offset, count_offset, eof;
+	u32 left, xdrleft, slen, count;
+	u32 xdrlen, offset;
+	u64 cookie;
+	char *sp;
+	__be32 status;
+	__be32 *p;
+	u32 nuser;
+
+	eof = 1;
+
+	status = nfsd4_listxattr_validate_cookie(listxattrs, &offset);
+	if (status)
+		goto out;
+
+	/*
+	 * Reserve space for the cookie and the name array count. Record
+	 * the offsets to save them later.
+	 */
+	cookie_offset = xdr->buf->len;
+	count_offset = cookie_offset + 8;
+	p = xdr_reserve_space(xdr, 12);
+	if (!p) {
+		status = nfserr_resource;
+		goto out;
+	}
+
+	count = 0;
+	left = listxattrs->lsxa_len;
+	sp = listxattrs->lsxa_buf;
+	nuser = 0;
+
+	xdrleft = listxattrs->lsxa_maxcount;
+
+	while (left > 0 && xdrleft > 0) {
+		slen = strlen(sp);
+
+		/*
+		 * Check if this a user. attribute, skip it if not.
+		 */
+		if (strncmp(sp, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+			goto contloop;
+
+		slen -= XATTR_USER_PREFIX_LEN;
+		xdrlen = 4 + ((slen + 3) & ~3);
+		if (xdrlen > xdrleft) {
+			if (count == 0) {
+				/*
+				 * Can't even fit the first attribute name.
+				 */
+				status = nfserr_toosmall;
+				goto out;
+			}
+			eof = 0;
+			goto wreof;
+		}
+
+		left -= XATTR_USER_PREFIX_LEN;
+		sp += XATTR_USER_PREFIX_LEN;
+		if (nuser++ < offset)
+			goto contloop;
+
+
+		p = xdr_reserve_space(xdr, xdrlen);
+		if (!p) {
+			status = nfserr_resource;
+			goto out;
+		}
+
+		p = xdr_encode_opaque(p, sp, slen);
+
+		xdrleft -= xdrlen;
+		count++;
+contloop:
+		sp += slen + 1;
+		left -= slen + 1;
+	}
+
+	/*
+	 * If there were user attributes to copy, but we didn't copy
+	 * any, the offset was too large (e.g. the cookie was invalid).
+	 */
+	if (nuser > 0 && count == 0) {
+		status = nfserr_badcookie;
+		goto out;
+	}
+
+wreof:
+	p = xdr_reserve_space(xdr, 4);
+	if (!p) {
+		status = nfserr_resource;
+		goto out;
+	}
+	*p = cpu_to_be32(eof);
+
+	cookie = offset + count;
+
+	write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &cookie, 8);
+	count = htonl(count);
+	write_bytes_to_xdr_buf(xdr->buf, count_offset, &count, 4);
+out:
+	if (listxattrs->lsxa_len)
+		kvfree(listxattrs->lsxa_buf);
+	return status;
+}
+
+static __be32
+nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr,
+			 struct nfsd4_removexattr *removexattr)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 20);
+	if (!p)
+		return nfserr_resource;
+
+	p = encode_cinfo(p, &removexattr->rmxa_cinfo);
+	return 0;
+}
+
 typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *);
 
 /*
@@ -4547,6 +4991,12 @@ static const nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_CLONE]		= (nfsd4_enc)nfsd4_encode_noop,
+
+	/* RFC 8276 extended atributes operations */
+	[OP_GETXATTR]		= (nfsd4_enc)nfsd4_encode_getxattr,
+	[OP_SETXATTR]		= (nfsd4_enc)nfsd4_encode_setxattr,
+	[OP_LISTXATTRS]		= (nfsd4_enc)nfsd4_encode_listxattrs,
+	[OP_REMOVEXATTR]	= (nfsd4_enc)nfsd4_encode_removexattr,
 };
 
 /*
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e6ca9d1d2e76..33ebe476428e 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -165,7 +165,7 @@ Needs to be updated if more operations are defined in future.*/
 #define FIRST_NFS4_OP	OP_ACCESS
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_CLONE
+#define LAST_NFS42_OP	OP_REMOVEXATTR
 #define LAST_NFS4_OP	LAST_NFS42_OP
 
 enum nfsstat4 {
-- 
cgit v1.2.3


From c65b326b1eb983bca35ed43d0e453d1b15705f10 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 25 Mar 2020 14:41:46 -0400
Subject: svcrdma: Make svc_rdma_send_error_msg() a global function

Prepare for svc_rdma_send_error_msg() to be invoked from another
source file.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h       |  4 ++++
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 28 +++++++++++++++++++---------
 2 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 7ed82625dc0b..1579f7a14ab4 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -195,6 +195,10 @@ extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_recv_ctxt *rctxt,
 				  struct xdr_buf *xdr);
+extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
+				    struct svc_rdma_send_ctxt *sctxt,
+				    struct svc_rdma_recv_ctxt *rctxt,
+				    int status);
 extern int svc_rdma_sendto(struct svc_rqst *);
 extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
 				 unsigned int length);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index fb548b548c4b..57041298fe4f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -804,16 +804,25 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 	return svc_rdma_send(rdma, &sctxt->sc_send_wr);
 }
 
-/* Given the client-provided Write and Reply chunks, the server was not
- * able to form a complete reply. Return an RDMA_ERROR message so the
- * client can retire this RPC transaction.
- *
- * Remote Invalidation is skipped for simplicity.
+/**
+ * svc_rdma_send_error_msg - Send an RPC/RDMA v1 error response
+ * @rdma: controlling transport context
+ * @sctxt: Send context for the response
+ * @rctxt: Receive context for incoming bad message
+ * @status: negative errno indicating error that occurred
+ *
+ * Given the client-provided Read, Write, and Reply chunks, the
+ * server was not able to parse the Call or form a complete Reply.
+ * Return an RDMA_ERROR message so the client can retire the RPC
+ * transaction.
+ *
+ * The caller does not have to release @sctxt. It is released by
+ * Send completion, or by this function on error.
  */
-static void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
-				    struct svc_rdma_send_ctxt *sctxt,
-				    struct svc_rdma_recv_ctxt *rctxt,
-				    int status)
+void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
+			     struct svc_rdma_send_ctxt *sctxt,
+			     struct svc_rdma_recv_ctxt *rctxt,
+			     int status)
 {
 	__be32 *rdma_argp = rctxt->rc_recv_buf;
 	__be32 *p;
@@ -852,6 +861,7 @@ static void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 		trace_svcrdma_err_chunk(*rdma_argp);
 	}
 
+	/* Remote Invalidation is skipped for simplicity. */
 	sctxt->sc_send_wr.num_sge = 1;
 	sctxt->sc_send_wr.opcode = IB_WR_SEND;
 	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
-- 
cgit v1.2.3


From 0b8dc1b69995cbd81c2c9a2f1730c46cce085f62 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 18 May 2020 11:34:47 -0400
Subject: svcrdma: Remove declarations for functions long removed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pavane pour une infante défunte.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 1579f7a14ab4..d28ca1b6f2eb 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -204,10 +204,6 @@ extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
 				 unsigned int length);
 
 /* svc_rdma_transport.c */
-extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
-extern void svc_sq_reap(struct svcxprt_rdma *);
-extern void svc_rq_reap(struct svcxprt_rdma *);
-
 extern struct svc_xprt_class svc_rdma_class;
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 extern struct svc_xprt_class svc_rdma_bc_class;
-- 
cgit v1.2.3


From 07e9a6325a35fb9655f7b52e2b9dc632da6eef51 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sat, 28 Mar 2020 13:43:22 -0400
Subject: SUNRPC: Add helpers for decoding list discriminators symbolically

Use these helpers in a few spots to demonstrate their use.

The remaining open-coded discriminator checks in rpcrdma will be
addressed in subsequent patches.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/xdr.h              | 26 ++++++++++++++++++++++++++
 net/sunrpc/xprtrdma/rpc_rdma.c          | 12 ++++++------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 17 ++++++++---------
 3 files changed, 40 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 22c207b2425f..5a6a81b7cd9f 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -474,6 +474,32 @@ xdr_stream_encode_uint32_array(struct xdr_stream *xdr,
 	return ret;
 }
 
+/**
+ * xdr_item_is_absent - symbolically handle XDR discriminators
+ * @p: pointer to undecoded discriminator
+ *
+ * Return values:
+ *   %true if the following XDR item is absent
+ *   %false if the following XDR item is present
+ */
+static inline bool xdr_item_is_absent(const __be32 *p)
+{
+	return *p == xdr_zero;
+}
+
+/**
+ * xdr_item_is_present - symbolically handle XDR discriminators
+ * @p: pointer to undecoded discriminator
+ *
+ * Return values:
+ *   %true if the following XDR item is present
+ *   %false if the following XDR item is absent
+ */
+static inline bool xdr_item_is_present(const __be32 *p)
+{
+	return *p != xdr_zero;
+}
+
 /**
  * xdr_stream_decode_u32 - Decode a 32-bit integer
  * @xdr: pointer to xdr_stream
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 935bbef2f7be..feecd1f55f18 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1133,11 +1133,11 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	p = xdr_inline_decode(xdr, 0);
 
 	/* Chunk lists */
-	if (*p++ != xdr_zero)
+	if (xdr_item_is_present(p++))
 		return false;
-	if (*p++ != xdr_zero)
+	if (xdr_item_is_present(p++))
 		return false;
-	if (*p++ != xdr_zero)
+	if (xdr_item_is_present(p++))
 		return false;
 
 	/* RPC header */
@@ -1215,7 +1215,7 @@ static int decode_read_list(struct xdr_stream *xdr)
 	p = xdr_inline_decode(xdr, sizeof(*p));
 	if (unlikely(!p))
 		return -EIO;
-	if (unlikely(*p != xdr_zero))
+	if (unlikely(xdr_item_is_present(p)))
 		return -EIO;
 	return 0;
 }
@@ -1234,7 +1234,7 @@ static int decode_write_list(struct xdr_stream *xdr, u32 *length)
 		p = xdr_inline_decode(xdr, sizeof(*p));
 		if (unlikely(!p))
 			return -EIO;
-		if (*p == xdr_zero)
+		if (xdr_item_is_absent(p))
 			break;
 		if (!first)
 			return -EIO;
@@ -1256,7 +1256,7 @@ static int decode_reply_chunk(struct xdr_stream *xdr, u32 *length)
 		return -EIO;
 
 	*length = 0;
-	if (*p != xdr_zero)
+	if (xdr_item_is_present(p))
 		if (decode_write_chunk(xdr, length))
 			return -EIO;
 	return 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c072ce61b393..5e78067889f3 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -419,7 +419,7 @@ static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
 
 	len = 0;
 	first = true;
-	while (*p != xdr_zero) {
+	while (xdr_item_is_present(p)) {
 		p = xdr_inline_decode(&rctxt->rc_stream,
 				      rpcrdma_readseg_maxsz * sizeof(*p));
 		if (!p)
@@ -500,7 +500,7 @@ static bool xdr_check_write_list(struct svc_rdma_recv_ctxt *rctxt)
 	if (!p)
 		return false;
 	rctxt->rc_write_list = p;
-	while (*p != xdr_zero) {
+	while (xdr_item_is_present(p)) {
 		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_WRITE_CHUNK))
 			return false;
 		++chcount;
@@ -532,12 +532,11 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	rctxt->rc_reply_chunk = p;
-	if (*p != xdr_zero) {
+	rctxt->rc_reply_chunk = NULL;
+	if (xdr_item_is_present(p)) {
 		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_SPECIAL_CHUNK))
 			return false;
-	} else {
-		rctxt->rc_reply_chunk = NULL;
+		rctxt->rc_reply_chunk = p;
 	}
 	return true;
 }
@@ -568,7 +567,7 @@ static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
 	p += rpcrdma_fixed_maxsz;
 
 	/* Read list */
-	while (*p++ != xdr_zero) {
+	while (xdr_item_is_present(p++)) {
 		p++;	/* position */
 		if (inv_rkey == xdr_zero)
 			inv_rkey = *p;
@@ -578,7 +577,7 @@ static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
 	}
 
 	/* Write list */
-	while (*p++ != xdr_zero) {
+	while (xdr_item_is_present(p++)) {
 		segcount = be32_to_cpup(p++);
 		for (i = 0; i < segcount; i++) {
 			if (inv_rkey == xdr_zero)
@@ -590,7 +589,7 @@ static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
 	}
 
 	/* Reply chunk */
-	if (*p++ != xdr_zero) {
+	if (xdr_item_is_present(p++)) {
 		segcount = be32_to_cpup(p++);
 		for (i = 0; i < segcount; i++) {
 			if (inv_rkey == xdr_zero)
-- 
cgit v1.2.3


From f60a08697d28b138c73b14c3204947bc8e637197 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 29 Mar 2020 16:44:13 -0400
Subject: svcrdma: Add common XDR decoders for RDMA and Read segments

Clean up: De-duplicate some code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/rpc_rdma.h          | 37 ++++++++++++++++++++++++++++++++
 net/sunrpc/xprtrdma/frwr_ops.c           |  1 -
 net/sunrpc/xprtrdma/rpc_rdma.c           |  5 +----
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  |  4 +---
 net/sunrpc/xprtrdma/svc_rdma_rw.c        | 37 ++++++++++++++------------------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c    |  5 +----
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  1 -
 7 files changed, 56 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index 320c672d84de..db50380f64f4 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -124,4 +124,41 @@ rpcrdma_decode_buffer_size(u8 val)
 	return ((unsigned int)val + 1) << 10;
 }
 
+/**
+ * xdr_decode_rdma_segment - Decode contents of an RDMA segment
+ * @p: Pointer to the undecoded RDMA segment
+ * @handle: Upon return, the RDMA handle
+ * @length: Upon return, the RDMA length
+ * @offset: Upon return, the RDMA offset
+ *
+ * Return value:
+ *   Pointer to the XDR item that follows the RDMA segment
+ */
+static inline __be32 *xdr_decode_rdma_segment(__be32 *p, u32 *handle,
+					      u32 *length, u64 *offset)
+{
+	*handle = be32_to_cpup(p++);
+	*length = be32_to_cpup(p++);
+	return xdr_decode_hyper(p, offset);
+}
+
+/**
+ * xdr_decode_read_segment - Decode contents of a Read segment
+ * @p: Pointer to the undecoded Read segment
+ * @position: Upon return, the segment's position
+ * @handle: Upon return, the RDMA handle
+ * @length: Upon return, the RDMA length
+ * @offset: Upon return, the RDMA offset
+ *
+ * Return value:
+ *   Pointer to the XDR item that follows the Read segment
+ */
+static inline __be32 *xdr_decode_read_segment(__be32 *p, u32 *position,
+					      u32 *handle, u32 *length,
+					      u64 *offset)
+{
+	*position = be32_to_cpup(p++);
+	return xdr_decode_rdma_segment(p, handle, length, offset);
+}
+
 #endif				/* _LINUX_SUNRPC_RPC_RDMA_H */
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index b647562a26dd..7f94c9a19fd3 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -40,7 +40,6 @@
  * New MRs are created on demand.
  */
 
-#include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/svc_rdma.h>
 
 #include "xprt_rdma.h"
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index feecd1f55f18..5461f01eeca6 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1176,10 +1176,7 @@ static int decode_rdma_segment(struct xdr_stream *xdr, u32 *length)
 	if (unlikely(!p))
 		return -EIO;
 
-	handle = be32_to_cpup(p++);
-	*length = be32_to_cpup(p++);
-	xdr_decode_hyper(p, &offset);
-
+	xdr_decode_rdma_segment(p, &handle, length, &offset);
 	trace_xprtrdma_decode_seg(handle, *length, offset);
 	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 5e78067889f3..c0587d3cd389 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -466,9 +466,7 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
 		if (!p)
 			return false;
 
-		handle = be32_to_cpup(p++);
-		length = be32_to_cpup(p++);
-		xdr_decode_hyper(p, &offset);
+		xdr_decode_rdma_segment(p, &handle, &length, &offset);
 		trace_svcrdma_decode_wseg(handle, length, offset);
 
 		total += length;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 83806fa94def..2038b1b286dd 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -7,6 +7,7 @@
 
 #include <rdma/rw.h>
 
+#include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/svc_rdma.h>
 
@@ -441,34 +442,32 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 	seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
 	do {
 		unsigned int write_len;
-		u32 seg_length, seg_handle;
-		u64 seg_offset;
+		u32 handle, length;
+		u64 offset;
 
 		if (info->wi_seg_no >= info->wi_nsegs)
 			goto out_overflow;
 
-		seg_handle = be32_to_cpup(seg);
-		seg_length = be32_to_cpup(seg + 1);
-		xdr_decode_hyper(seg + 2, &seg_offset);
-		seg_offset += info->wi_seg_off;
+		xdr_decode_rdma_segment(seg, &handle, &length, &offset);
+		offset += info->wi_seg_off;
 
-		write_len = min(remaining, seg_length - info->wi_seg_off);
+		write_len = min(remaining, length - info->wi_seg_off);
 		ctxt = svc_rdma_get_rw_ctxt(rdma,
 					    (write_len >> PAGE_SHIFT) + 2);
 		if (!ctxt)
 			return -ENOMEM;
 
 		constructor(info, write_len, ctxt);
-		ret = svc_rdma_rw_ctx_init(rdma, ctxt, seg_offset, seg_handle,
+		ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, handle,
 					   DMA_TO_DEVICE);
 		if (ret < 0)
 			return -EIO;
 
-		trace_svcrdma_send_wseg(seg_handle, write_len, seg_offset);
+		trace_svcrdma_send_wseg(handle, write_len, offset);
 
 		list_add(&ctxt->rw_list, &cc->cc_rwctxts);
 		cc->cc_sqecount += ret;
-		if (write_len == seg_length - info->wi_seg_off) {
+		if (write_len == length - info->wi_seg_off) {
 			seg += 4;
 			info->wi_seg_no++;
 			info->wi_seg_off = 0;
@@ -689,21 +688,17 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
 	ret = -EINVAL;
 	info->ri_chunklen = 0;
 	while (*p++ != xdr_zero && be32_to_cpup(p++) == info->ri_position) {
-		u32 rs_handle, rs_length;
-		u64 rs_offset;
+		u32 handle, length;
+		u64 offset;
 
-		rs_handle = be32_to_cpup(p++);
-		rs_length = be32_to_cpup(p++);
-		p = xdr_decode_hyper(p, &rs_offset);
-
-		ret = svc_rdma_build_read_segment(info, rqstp,
-						  rs_handle, rs_length,
-						  rs_offset);
+		p = xdr_decode_rdma_segment(p, &handle, &length, &offset);
+		ret = svc_rdma_build_read_segment(info, rqstp, handle, length,
+						  offset);
 		if (ret < 0)
 			break;
 
-		trace_svcrdma_send_rseg(rs_handle, rs_length, rs_offset);
-		info->ri_chunklen += rs_length;
+		trace_svcrdma_send_rseg(handle, length, offset);
+		info->ri_chunklen += length;
 	}
 
 	return ret;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index f985f548346a..a78f1d22e9bb 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -106,7 +106,6 @@
 #include <rdma/rdma_cm.h>
 
 #include <linux/sunrpc/debug.h>
-#include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/svc_rdma.h>
 
 #include "xprt_rdma.h"
@@ -375,9 +374,7 @@ static ssize_t svc_rdma_encode_write_segment(__be32 *src,
 	if (!p)
 		return -EMSGSIZE;
 
-	handle = be32_to_cpup(src++);
-	length = be32_to_cpup(src++);
-	xdr_decode_hyper(src, &offset);
+	xdr_decode_rdma_segment(src, &handle, &length, &offset);
 
 	*p++ = cpu_to_be32(handle);
 	if (*remaining < length) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index d38be57b00ed..3da7901a49e6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -55,7 +55,6 @@
 
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/debug.h>
-#include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/svc_rdma.h>
 
-- 
cgit v1.2.3


From 379c3bc6b4eb989ee37c4ce8ab403719e06fe35f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Apr 2020 15:32:14 -0400
Subject: svcrdma: Add common XDR encoders for RDMA and Read segments

Clean up: De-duplicate some code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/rpc_rdma.h       | 37 +++++++++++++++++++++++++++++++++++
 net/sunrpc/xprtrdma/rpc_rdma.c        | 14 +++----------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c |  4 +---
 3 files changed, 41 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index db50380f64f4..4af31bbc8802 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -124,6 +124,43 @@ rpcrdma_decode_buffer_size(u8 val)
 	return ((unsigned int)val + 1) << 10;
 }
 
+/**
+ * xdr_encode_rdma_segment - Encode contents of an RDMA segment
+ * @p: Pointer into a send buffer
+ * @handle: The RDMA handle to encode
+ * @length: The RDMA length to encode
+ * @offset: The RDMA offset to encode
+ *
+ * Return value:
+ *   Pointer to the XDR position that follows the encoded RDMA segment
+ */
+static inline __be32 *xdr_encode_rdma_segment(__be32 *p, u32 handle,
+					      u32 length, u64 offset)
+{
+	*p++ = cpu_to_be32(handle);
+	*p++ = cpu_to_be32(length);
+	return xdr_encode_hyper(p, offset);
+}
+
+/**
+ * xdr_encode_read_segment - Encode contents of a Read segment
+ * @p: Pointer into a send buffer
+ * @position: The position to encode
+ * @handle: The RDMA handle to encode
+ * @length: The RDMA length to encode
+ * @offset: The RDMA offset to encode
+ *
+ * Return value:
+ *   Pointer to the XDR position that follows the encoded Read segment
+ */
+static inline __be32 *xdr_encode_read_segment(__be32 *p, u32 position,
+					      u32 handle, u32 length,
+					      u64 offset)
+{
+	*p++ = cpu_to_be32(position);
+	return xdr_encode_rdma_segment(p, handle, length, offset);
+}
+
 /**
  * xdr_decode_rdma_segment - Decode contents of an RDMA segment
  * @p: Pointer to the undecoded RDMA segment
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 5461f01eeca6..73ed51893175 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -275,14 +275,6 @@ out:
 	return n;
 }
 
-static void
-xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mr *mr)
-{
-	*iptr++ = cpu_to_be32(mr->mr_handle);
-	*iptr++ = cpu_to_be32(mr->mr_length);
-	xdr_encode_hyper(iptr, mr->mr_offset);
-}
-
 static int
 encode_rdma_segment(struct xdr_stream *xdr, struct rpcrdma_mr *mr)
 {
@@ -292,7 +284,7 @@ encode_rdma_segment(struct xdr_stream *xdr, struct rpcrdma_mr *mr)
 	if (unlikely(!p))
 		return -EMSGSIZE;
 
-	xdr_encode_rdma_segment(p, mr);
+	xdr_encode_rdma_segment(p, mr->mr_handle, mr->mr_length, mr->mr_offset);
 	return 0;
 }
 
@@ -307,8 +299,8 @@ encode_read_segment(struct xdr_stream *xdr, struct rpcrdma_mr *mr,
 		return -EMSGSIZE;
 
 	*p++ = xdr_one;			/* Item present */
-	*p++ = cpu_to_be32(position);
-	xdr_encode_rdma_segment(p, mr);
+	xdr_encode_read_segment(p, position, mr->mr_handle, mr->mr_length,
+				mr->mr_offset);
 	return 0;
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index a78f1d22e9bb..38d8f0ee35ec 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -376,7 +376,6 @@ static ssize_t svc_rdma_encode_write_segment(__be32 *src,
 
 	xdr_decode_rdma_segment(src, &handle, &length, &offset);
 
-	*p++ = cpu_to_be32(handle);
 	if (*remaining < length) {
 		/* segment only partly filled */
 		length = *remaining;
@@ -385,8 +384,7 @@ static ssize_t svc_rdma_encode_write_segment(__be32 *src,
 		/* entire segment was consumed */
 		*remaining -= length;
 	}
-	*p++ = cpu_to_be32(length);
-	xdr_encode_hyper(p, offset);
+	xdr_encode_rdma_segment(p, handle, length, offset);
 
 	trace_svcrdma_encode_wseg(handle, length, offset);
 	return len;
-- 
cgit v1.2.3


From f7bd657b55e3484cadc37a6439de23d2fd703bd6 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 19 May 2020 09:30:32 -0400
Subject: svcrdma: Introduce infrastructure to support completion IDs

The goal is to replace CQE kernel memory addresses in completion-
related tracepoints.

Each completion ID matches an incoming Send or Receive completion
to a Completion Queue and to a previous ib_post_*(). The ID can
then be displayed in an error message or recorded in a trace
record.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/rpc_rdma_cid.h | 24 +++++++++++++++++++++
 include/trace/events/rpcrdma.h      | 43 +++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 include/linux/sunrpc/rpc_rdma_cid.h

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/rpc_rdma_cid.h b/include/linux/sunrpc/rpc_rdma_cid.h
new file mode 100644
index 000000000000..be24ab2baa6a
--- /dev/null
+++ b/include/linux/sunrpc/rpc_rdma_cid.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#ifndef RPC_RDMA_CID_H
+#define RPC_RDMA_CID_H
+
+/*
+ * The rpc_rdma_cid struct records completion ID information. A
+ * completion ID matches an incoming Send or Receive completion
+ * to a Completion Queue and to a previous ib_post_*(). The ID
+ * can then be displayed in an error message or recorded in a
+ * trace record.
+ *
+ * This struct is shared between the server and client RPC/RDMA
+ * transport implementations.
+ */
+struct rpc_rdma_cid {
+	u32			ci_queue_id;
+	int			ci_completion_id;
+};
+
+#endif	/* RPC_RDMA_CID_H */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 0eff80dee066..70ab989aa3b7 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -11,6 +11,7 @@
 #define _TRACE_RPCRDMA_H
 
 #include <linux/scatterlist.h>
+#include <linux/sunrpc/rpc_rdma_cid.h>
 #include <linux/tracepoint.h>
 #include <trace/events/rdma.h>
 
@@ -18,6 +19,48 @@
  ** Event classes
  **/
 
+DECLARE_EVENT_CLASS(rpcrdma_completion_class,
+	TP_PROTO(
+		const struct ib_wc *wc,
+		const struct rpc_rdma_cid *cid
+	),
+
+	TP_ARGS(wc, cid),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(unsigned long, status)
+		__field(unsigned int, vendor_err)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->status = wc->status;
+		if (wc->status)
+			__entry->vendor_err = wc->vendor_err;
+		else
+			__entry->vendor_err = 0;
+	),
+
+	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)",
+		__entry->cq_id, __entry->completion_id,
+		rdma_show_wc_status(__entry->status),
+		__entry->status, __entry->vendor_err
+	)
+);
+
+#define DEFINE_COMPLETION_EVENT(name)					\
+		DEFINE_EVENT(rpcrdma_completion_class, name,		\
+				TP_PROTO(				\
+					const struct ib_wc *wc,		\
+					const struct rpc_rdma_cid *cid	\
+				),					\
+				TP_ARGS(wc, cid))
+
+DEFINE_COMPLETION_EVENT(dummy);
+
 DECLARE_EVENT_CLASS(xprtrdma_reply_event,
 	TP_PROTO(
 		const struct rpcrdma_rep *rep
-- 
cgit v1.2.3


From 9b3bcf8c5c134038e30624db5b57992ae50b80a9 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 29 Apr 2020 16:22:26 -0400
Subject: svcrdma: Introduce Receive completion IDs

Set up a completion ID in each svc_rdma_recv_ctxt. The ID is used
to match an incoming Receive completion to a transport and to a
previous ib_post_recv().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  4 +++
 include/trace/events/rpcrdma.h          | 51 +++++++++++++--------------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 15 ++++++++--
 3 files changed, 36 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index d28ca1b6f2eb..c3c1e46f510f 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -46,6 +46,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/rpc_rdma.h>
+#include <linux/sunrpc/rpc_rdma_cid.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
 
@@ -109,6 +110,8 @@ struct svcxprt_rdma {
 	struct work_struct   sc_work;
 
 	struct llist_head    sc_recv_ctxts;
+
+	atomic_t	     sc_completion_ids;
 };
 /* sc_flags */
 #define RDMAXPRT_CONN_PENDING	3
@@ -129,6 +132,7 @@ struct svc_rdma_recv_ctxt {
 	struct list_head	rc_list;
 	struct ib_recv_wr	rc_recv_wr;
 	struct ib_cqe		rc_cqe;
+	struct rpc_rdma_cid	rc_cid;
 	struct ib_sge		rc_recv_sge;
 	void			*rc_recv_buf;
 	struct xdr_buf		rc_arg;
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 70ab989aa3b7..a0330a557e34 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -59,8 +59,6 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 				),					\
 				TP_ARGS(wc, cid))
 
-DEFINE_COMPLETION_EVENT(dummy);
-
 DECLARE_EVENT_CLASS(xprtrdma_reply_event,
 	TP_PROTO(
 		const struct rpcrdma_rep *rep
@@ -1849,57 +1847,48 @@ DEFINE_SENDCOMP_EVENT(send);
 
 TRACE_EVENT(svcrdma_post_recv,
 	TP_PROTO(
-		const struct ib_recv_wr *wr,
-		int status
+		const struct svc_rdma_recv_ctxt *ctxt
 	),
 
-	TP_ARGS(wr, status),
+	TP_ARGS(ctxt),
 
 	TP_STRUCT__entry(
-		__field(const void *, cqe)
-		__field(int, status)
+		__field(u32, cq_id)
+		__field(int, completion_id)
 	),
 
 	TP_fast_assign(
-		__entry->cqe = wr->wr_cqe;
-		__entry->status = status;
+		__entry->cq_id = ctxt->rc_cid.ci_queue_id;
+		__entry->completion_id = ctxt->rc_cid.ci_completion_id;
 	),
 
-	TP_printk("cqe=%p status=%d",
-		__entry->cqe, __entry->status
+	TP_printk("cq.id=%d cid=%d",
+		__entry->cq_id, __entry->completion_id
 	)
 );
 
-TRACE_EVENT(svcrdma_wc_receive,
+DEFINE_COMPLETION_EVENT(svcrdma_wc_receive);
+
+TRACE_EVENT(svcrdma_rq_post_err,
 	TP_PROTO(
-		const struct ib_wc *wc
+		const struct svcxprt_rdma *rdma,
+		int status
 	),
 
-	TP_ARGS(wc),
+	TP_ARGS(rdma, status),
 
 	TP_STRUCT__entry(
-		__field(const void *, cqe)
-		__field(u32, byte_len)
-		__field(unsigned int, status)
-		__field(u32, vendor_err)
+		__field(int, status)
+		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
-		__entry->cqe = wc->wr_cqe;
-		__entry->status = wc->status;
-		if (wc->status) {
-			__entry->byte_len = 0;
-			__entry->vendor_err = wc->vendor_err;
-		} else {
-			__entry->byte_len = wc->byte_len;
-			__entry->vendor_err = 0;
-		}
+		__entry->status = status;
+		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("cqe=%p byte_len=%u status=%s (%u/0x%x)",
-		__entry->cqe, __entry->byte_len,
-		rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
+	TP_printk("addr=%s status=%d",
+		__get_str(addr), __entry->status
 	)
 );
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c0587d3cd389..e6d7401232d2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -117,6 +117,13 @@ svc_rdma_next_recv_ctxt(struct list_head *list)
 					rc_list);
 }
 
+static void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma,
+				   struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_rq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
 static struct svc_rdma_recv_ctxt *
 svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
@@ -135,6 +142,8 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 	if (ib_dma_mapping_error(rdma->sc_pd->device, addr))
 		goto fail2;
 
+	svc_rdma_recv_cid_init(rdma, &ctxt->rc_cid);
+
 	ctxt->rc_recv_wr.next = NULL;
 	ctxt->rc_recv_wr.wr_cqe = &ctxt->rc_cqe;
 	ctxt->rc_recv_wr.sg_list = &ctxt->rc_recv_sge;
@@ -249,13 +258,14 @@ static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
 	int ret;
 
 	svc_xprt_get(&rdma->sc_xprt);
+	trace_svcrdma_post_recv(ctxt);
 	ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL);
-	trace_svcrdma_post_recv(&ctxt->rc_recv_wr, ret);
 	if (ret)
 		goto err_post;
 	return 0;
 
 err_post:
+	trace_svcrdma_rq_post_err(rdma, ret);
 	svc_rdma_recv_ctxt_put(rdma, ctxt);
 	svc_xprt_put(&rdma->sc_xprt);
 	return ret;
@@ -309,11 +319,10 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_recv_ctxt *ctxt;
 
-	trace_svcrdma_wc_receive(wc);
-
 	/* WARNING: Only wc->wr_cqe and wc->status are reliable */
 	ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe);
 
+	trace_svcrdma_wc_receive(wc, &ctxt->rc_cid);
 	if (wc->status != IB_WC_SUCCESS)
 		goto flushed;
 
-- 
cgit v1.2.3


From 3ac56c2fb166fea25974d8c48bb4a72ee298361b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 30 Apr 2020 13:47:07 -0400
Subject: svcrdma: Introduce Send completion IDs

Set up a completion ID in each svc_rdma_send_ctxt. The ID is used
to match an incoming Send completion to a transport and to a
previous ib_post_send().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h       |  2 ++
 include/trace/events/rpcrdma.h        |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 15 ++++++++++++---
 3 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c3c1e46f510f..c91e00bc937e 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -151,6 +151,8 @@ struct svc_rdma_recv_ctxt {
 
 struct svc_rdma_send_ctxt {
 	struct list_head	sc_list;
+	struct rpc_rdma_cid	sc_cid;
+
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index df49ae5d447b..782a4d826a4b 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1863,7 +1863,7 @@ TRACE_EVENT(svcrdma_post_send,
 	)
 );
 
-DEFINE_SENDCOMP_EVENT(send);
+DEFINE_COMPLETION_EVENT(svcrdma_wc_send);
 
 TRACE_EVENT(svcrdma_post_recv,
 	TP_PROTO(
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 38d8f0ee35ec..c720dcf56231 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -122,6 +122,13 @@ svc_rdma_next_send_ctxt(struct list_head *list)
 					sc_list);
 }
 
+static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma,
+				   struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
 static struct svc_rdma_send_ctxt *
 svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
@@ -144,6 +151,8 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 	if (ib_dma_mapping_error(rdma->sc_pd->device, addr))
 		goto fail2;
 
+	svc_rdma_send_cid_init(rdma, &ctxt->sc_cid);
+
 	ctxt->sc_send_wr.next = NULL;
 	ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe;
 	ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
@@ -268,14 +277,14 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct svcxprt_rdma *rdma = cq->cq_context;
 	struct ib_cqe *cqe = wc->wr_cqe;
-	struct svc_rdma_send_ctxt *ctxt;
+	struct svc_rdma_send_ctxt *ctxt =
+		container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe);
 
-	trace_svcrdma_wc_send(wc);
+	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
 
 	atomic_inc(&rdma->sc_sq_avail);
 	wake_up(&rdma->sc_send_wait);
 
-	ctxt = container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe);
 	svc_rdma_send_ctxt_put(rdma, ctxt);
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
-- 
cgit v1.2.3


From 17f70f8dd52be3723250d21093403bb3a9f2162f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 29 Apr 2020 11:05:33 -0400
Subject: svcrdma: Record send_ctxt completion ID in trace_svcrdma_post_send()

First, refactor: Dereference the svc_rdma_send_ctxt inside
svc_rdma_send() instead of at every call site.

Then, it can be passed into trace_svcrdma_post_send() to get the
proper completion ID.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h            |  3 ++-
 include/trace/events/rpcrdma.h             | 18 +++++++++++-------
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_sendto.c      | 11 ++++++-----
 4 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c91e00bc937e..9dc3a3b88391 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -196,7 +196,8 @@ extern struct svc_rdma_send_ctxt *
 		svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma);
 extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_send_ctxt *ctxt);
-extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr);
+extern int svc_rdma_send(struct svcxprt_rdma *rdma,
+			 struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_recv_ctxt *rctxt,
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 782a4d826a4b..aeeba9188ed5 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1839,27 +1839,31 @@ DECLARE_EVENT_CLASS(svcrdma_sendcomp_event,
 
 TRACE_EVENT(svcrdma_post_send,
 	TP_PROTO(
-		const struct ib_send_wr *wr
+		const struct svc_rdma_send_ctxt *ctxt
 	),
 
-	TP_ARGS(wr),
+	TP_ARGS(ctxt),
 
 	TP_STRUCT__entry(
-		__field(const void *, cqe)
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, num_sge)
 		__field(u32, inv_rkey)
 	),
 
 	TP_fast_assign(
-		__entry->cqe = wr->wr_cqe;
+		const struct ib_send_wr *wr = &ctxt->sc_send_wr;
+
+		__entry->cq_id = ctxt->sc_cid.ci_queue_id;
+		__entry->completion_id = ctxt->sc_cid.ci_completion_id;
 		__entry->num_sge = wr->num_sge;
 		__entry->inv_rkey = (wr->opcode == IB_WR_SEND_WITH_INV) ?
 					wr->ex.invalidate_rkey : 0;
 	),
 
-	TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x",
-		__entry->cqe, __entry->num_sge,
-		__entry->inv_rkey
+	TP_printk("cq_id=%u cid=%d num_sge=%u inv_rkey=0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->num_sge, __entry->inv_rkey
 	)
 );
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 1ee73f7cf931..5e7c4ba9e147 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -87,7 +87,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	 */
 	get_page(virt_to_page(rqst->rq_buffer));
 	ctxt->sc_send_wr.opcode = IB_WR_SEND;
-	return svc_rdma_send(rdma, &ctxt->sc_send_wr);
+	return svc_rdma_send(rdma, ctxt);
 }
 
 /* Server-side transport endpoint wants a whole page for its send
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c720dcf56231..73d46e8cdc16 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -298,13 +298,14 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 /**
  * svc_rdma_send - Post a single Send WR
  * @rdma: transport on which to post the WR
- * @wr: prepared Send WR to post
+ * @ctxt: send ctxt with a Send WR ready to post
  *
  * Returns zero the Send WR was posted successfully. Otherwise, a
  * negative errno is returned.
  */
-int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr)
+int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
 {
+	struct ib_send_wr *wr = &ctxt->sc_send_wr;
 	int ret;
 
 	might_sleep();
@@ -330,7 +331,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr)
 		}
 
 		svc_xprt_get(&rdma->sc_xprt);
-		trace_svcrdma_post_send(wr);
+		trace_svcrdma_post_send(ctxt);
 		ret = ib_post_send(rdma->sc_qp, wr, NULL);
 		if (ret)
 			break;
@@ -805,7 +806,7 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 	} else {
 		sctxt->sc_send_wr.opcode = IB_WR_SEND;
 	}
-	return svc_rdma_send(rdma, &sctxt->sc_send_wr);
+	return svc_rdma_send(rdma, sctxt);
 }
 
 /**
@@ -869,7 +870,7 @@ void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 	sctxt->sc_send_wr.num_sge = 1;
 	sctxt->sc_send_wr.opcode = IB_WR_SEND;
 	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
-	if (svc_rdma_send(rdma, &sctxt->sc_send_wr))
+	if (svc_rdma_send(rdma, sctxt))
 		goto put_ctxt;
 	return;
 
-- 
cgit v1.2.3


From 9a67fcc8f3fd1e294922f28f20003c31d7f6cfeb Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:38:53 +0000
Subject: nfs: add client side only definitions for user xattrs

Add client-side only definitions for user extended
attributes (RFC8276). These are the access bits
as used by the client code, and the CLNT procedure
number definition.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/nfs4.h   | 5 +++++
 include/linux/nfs_fs.h | 3 +++
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e6ca9d1d2e76..db13026ac7d1 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -553,6 +553,11 @@ enum {
 	NFSPROC4_CLNT_LAYOUTERROR,
 
 	NFSPROC4_CLNT_COPY_NOTIFY,
+
+	NFSPROC4_CLNT_GETXATTR,
+	NFSPROC4_CLNT_SETXATTR,
+	NFSPROC4_CLNT_LISTXATTRS,
+	NFSPROC4_CLNT_REMOVEXATTR,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 6ee9119acc5d..b743988fcbd0 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -212,6 +212,9 @@ struct nfs4_copy_state {
 #define NFS_ACCESS_EXTEND      0x0008
 #define NFS_ACCESS_DELETE      0x0010
 #define NFS_ACCESS_EXECUTE     0x0020
+#define NFS_ACCESS_XAREAD      0x0040
+#define NFS_ACCESS_XAWRITE     0x0080
+#define NFS_ACCESS_XALIST      0x0100
 
 /*
  * Cache validity bit flags
-- 
cgit v1.2.3


From 04a5da690e8f2da23c2ac940f2921e3aa622db82 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:38:54 +0000
Subject: NFSv4.2: define limits and sizes for user xattr handling

Set limits for extended attributes (attribute value size and listxattr
buffer size), based on the fs-independent limits (XATTR_*_MAX).

Define the maximum XDR sizes for the RFC 8276 XATTR operations.
In the case of operations that carry a larger payload (SETXATTR,
GETXATTR, LISTXATTR), these exclude that payload, which is added
as separate pages, like other operations do.

Define, much like for read and write operations, the maximum overhead
sizes for get/set/listxattr, and use them to limit the maximum payload
size for those operations, in combination with the channel attributes.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c           | 19 ++++++++++--
 fs/nfs/nfs42.h            | 16 ++++++++++
 fs/nfs/nfs42xdr.c         | 74 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h          |  6 ++++
 fs/nfs/nfs4client.c       | 31 ++++++++++++++++++++
 include/linux/nfs_fs_sb.h |  5 ++++
 6 files changed, 149 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f1ff3076e4a4..055040bf1a8e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -50,6 +50,7 @@
 #include "nfs.h"
 #include "netns.h"
 #include "sysfs.h"
+#include "nfs42.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -749,7 +750,7 @@ error:
 static void nfs_server_set_fsinfo(struct nfs_server *server,
 				  struct nfs_fsinfo *fsinfo)
 {
-	unsigned long max_rpc_payload;
+	unsigned long max_rpc_payload, raw_max_rpc_payload;
 
 	/* Work out a lot of parameters */
 	if (server->rsize == 0)
@@ -762,7 +763,9 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax)
 		server->wsize = nfs_block_size(fsinfo->wtmax, NULL);
 
-	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
+	raw_max_rpc_payload = rpc_max_payload(server->client);
+	max_rpc_payload = nfs_block_size(raw_max_rpc_payload, NULL);
+
 	if (server->rsize > max_rpc_payload)
 		server->rsize = max_rpc_payload;
 	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
@@ -795,6 +798,18 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	server->clone_blksize = fsinfo->clone_blksize;
 	/* We're airborne Set socket buffersize */
 	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
+
+#ifdef CONFIG_NFS_V4_2
+	/*
+	 * Defaults until limited by the session parameters.
+	 */
+	server->gxasize = min_t(unsigned int, raw_max_rpc_payload,
+				XATTR_SIZE_MAX);
+	server->sxasize = min_t(unsigned int, raw_max_rpc_payload,
+				XATTR_SIZE_MAX);
+	server->lxasize = min_t(unsigned int, raw_max_rpc_payload,
+				nfs42_listxattr_xdrsize(XATTR_LIST_MAX));
+#endif
 }
 
 /*
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index c891af949886..51de8ddc7d88 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -6,6 +6,8 @@
 #ifndef __LINUX_FS_NFS_NFS4_2_H
 #define __LINUX_FS_NFS_NFS4_2_H
 
+#include <linux/xattr.h>
+
 /*
  * FIXME:  four LAYOUTSTATS calls per compound at most! Do we need to support
  * more? Need to consider not to pre-alloc too much for a compound.
@@ -36,5 +38,19 @@ static inline bool nfs42_files_from_same_server(struct file *in,
 	return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
 					       c_out->cl_serverowner);
 }
+
+/*
+ * Maximum XDR buffer size needed for a listxattr buffer of buflen size.
+ *
+ * The upper boundary is a buffer with all 1-byte sized attribute names.
+ * They would be 7 bytes long in the eventual buffer ("user.x\0"), and
+ * 8 bytes long XDR-encoded.
+ *
+ * Include the trailing eof word as well.
+ */
+static inline u32 nfs42_listxattr_xdrsize(u32 buflen)
+{
+	return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4;
+}
 #endif /* CONFIG_NFS_V4_2 */
 #endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index c03f3246d6c5..6712daa9d85b 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -169,6 +169,80 @@
 					 decode_clone_maxsz + \
 					 decode_getattr_maxsz)
 
+#ifdef CONFIG_NFS_V4_2
+/* Not limited by NFS itself, limited by the generic xattr code */
+#define nfs4_xattr_name_maxsz   XDR_QUADLEN(XATTR_NAME_MAX)
+
+#define encode_getxattr_maxsz   (op_encode_hdr_maxsz + 1 + \
+				 nfs4_xattr_name_maxsz)
+#define decode_getxattr_maxsz   (op_decode_hdr_maxsz + 1 + 1)
+#define encode_setxattr_maxsz   (op_encode_hdr_maxsz + \
+				 1 + nfs4_xattr_name_maxsz + 1)
+#define decode_setxattr_maxsz   (op_decode_hdr_maxsz + decode_change_info_maxsz)
+#define encode_listxattrs_maxsz  (op_encode_hdr_maxsz + 2 + 1)
+#define decode_listxattrs_maxsz  (op_decode_hdr_maxsz + 2 + 1 + 1)
+#define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \
+				  nfs4_xattr_name_maxsz)
+#define decode_removexattr_maxsz (op_decode_hdr_maxsz + \
+				  decode_change_info_maxsz)
+
+#define NFS4_enc_getxattr_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_getxattr_maxsz)
+#define NFS4_dec_getxattr_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_getxattr_maxsz)
+#define NFS4_enc_setxattr_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_setxattr_maxsz)
+#define NFS4_dec_setxattr_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_setxattr_maxsz)
+#define NFS4_enc_listxattrs_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_listxattrs_maxsz)
+#define NFS4_dec_listxattrs_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_listxattrs_maxsz)
+#define NFS4_enc_removexattr_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_removexattr_maxsz)
+#define NFS4_dec_removexattr_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_removexattr_maxsz)
+
+/*
+ * These values specify the maximum amount of data that is not
+ * associated with the extended attribute name or extended
+ * attribute list in the SETXATTR, GETXATTR and LISTXATTR
+ * respectively.
+ */
+const u32 nfs42_maxsetxattr_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
+					compound_encode_hdr_maxsz +
+					encode_sequence_maxsz +
+					encode_putfh_maxsz + 1 +
+					nfs4_xattr_name_maxsz)
+					* XDR_UNIT);
+
+const u32 nfs42_maxgetxattr_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
+					compound_decode_hdr_maxsz +
+					decode_sequence_maxsz +
+					decode_putfh_maxsz + 1) * XDR_UNIT);
+
+const u32 nfs42_maxlistxattrs_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
+					compound_decode_hdr_maxsz +
+					decode_sequence_maxsz +
+					decode_putfh_maxsz + 3) * XDR_UNIT);
+#endif
+
 static void encode_fallocate(struct xdr_stream *xdr,
 			     const struct nfs42_falloc_args *args)
 {
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 2b7f6dcd2eb8..526b3e70d57c 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -557,6 +557,12 @@ static inline void nfs4_unregister_sysctl(void)
 /* nfs4xdr.c */
 extern const struct rpc_procinfo nfs4_procedures[];
 
+#ifdef CONFIG_NFS_V4_2
+extern const u32 nfs42_maxsetxattr_overhead;
+extern const u32 nfs42_maxgetxattr_overhead;
+extern const u32 nfs42_maxlistxattrs_overhead;
+#endif
+
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 0bd77cc1f639..c41cbd86612c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -992,6 +992,36 @@ static void nfs4_session_limit_rwsize(struct nfs_server *server)
 #endif /* CONFIG_NFS_V4_1 */
 }
 
+/*
+ * Limit xattr sizes using the channel attributes.
+ */
+static void nfs4_session_limit_xasize(struct nfs_server *server)
+{
+#ifdef CONFIG_NFS_V4_2
+	struct nfs4_session *sess;
+	u32 server_gxa_sz;
+	u32 server_sxa_sz;
+	u32 server_lxa_sz;
+
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+
+	sess = server->nfs_client->cl_session;
+
+	server_gxa_sz = sess->fc_attrs.max_resp_sz - nfs42_maxgetxattr_overhead;
+	server_sxa_sz = sess->fc_attrs.max_rqst_sz - nfs42_maxsetxattr_overhead;
+	server_lxa_sz = sess->fc_attrs.max_resp_sz -
+	    nfs42_maxlistxattrs_overhead;
+
+	if (server->gxasize > server_gxa_sz)
+		server->gxasize = server_gxa_sz;
+	if (server->sxasize > server_sxa_sz)
+		server->sxasize = server_sxa_sz;
+	if (server->lxasize > server_lxa_sz)
+		server->lxasize = server_lxa_sz;
+#endif
+}
+
 static int nfs4_server_common_setup(struct nfs_server *server,
 		struct nfs_fh *mntfh, bool auth_probe)
 {
@@ -1039,6 +1069,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 		goto out;
 
 	nfs4_session_limit_rwsize(server);
+	nfs4_session_limit_xasize(server);
 
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 465fa98258a3..128e01acb4ca 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -163,6 +163,11 @@ struct nfs_server {
 	unsigned int		dtsize;		/* readdir size */
 	unsigned short		port;		/* "port=" setting */
 	unsigned int		bsize;		/* server block size */
+#ifdef CONFIG_NFS_V4_2
+	unsigned int		gxasize;	/* getxattr size */
+	unsigned int		sxasize;	/* setxattr size */
+	unsigned int		lxasize;	/* listxattr size */
+#endif
 	unsigned int		acregmin;	/* attr cache timeouts */
 	unsigned int		acregmax;
 	unsigned int		acdirmin;
-- 
cgit v1.2.3


From b78ef845c35dbae25e57b598901a65b13d940c81 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:38:55 +0000
Subject: NFSv4.2: query the server for extended attribute support

Query the server for extended attribute support, and record it
as the NFS_CAP_XATTR flag in the server capabilities.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c           |  3 +++
 fs/nfs/nfs4proc.c         |  3 ++-
 fs/nfs/nfs4xdr.c          | 25 +++++++++++++++++++++++++
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   |  1 +
 5 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 055040bf1a8e..4b8cc93913f7 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -809,6 +809,9 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 				XATTR_SIZE_MAX);
 	server->lxasize = min_t(unsigned int, raw_max_rpc_payload,
 				nfs42_listxattr_xdrsize(XATTR_LIST_MAX));
+
+	if (fsinfo->xattr_support)
+		server->caps |= NFS_CAP_XATTR;
 #endif
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e32717fd1169..64e081459327 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -256,6 +256,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD1_FS_LAYOUT_TYPES,
 			FATTR4_WORD2_LAYOUT_BLKSIZE
 			| FATTR4_WORD2_CLONE_BLKSIZE
+			| FATTR4_WORD2_XATTR_SUPPORT
 };
 
 const u32 nfs4_fs_locations_bitmap[3] = {
@@ -3740,7 +3741,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 
 #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
 #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
-#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_MODE_UMASK - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_XATTR_SUPPORT - 1UL)
 
 static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 47817ef0aadb..9e1b07640e9a 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4201,6 +4201,26 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
+static int decode_attr_xattrsupport(struct xdr_stream *xdr, uint32_t *bitmap,
+				    uint32_t *res)
+{
+	__be32 *p;
+
+	*res = 0;
+	if (unlikely(bitmap[2] & (FATTR4_WORD2_XATTR_SUPPORT - 1U)))
+		return -EIO;
+	if (likely(bitmap[2] & FATTR4_WORD2_XATTR_SUPPORT)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_XATTR_SUPPORT;
+	}
+	dprintk("%s: XATTR support=%s\n", __func__,
+		*res == 0 ? "false" : "true");
+	return 0;
+}
+
 static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
 {
 	unsigned int attrwords = XDR_QUADLEN(attrlen);
@@ -4855,6 +4875,11 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	if (status)
 		goto xdr_error;
 
+	status = decode_attr_xattrsupport(xdr, bitmap,
+					  &fsinfo->xattr_support);
+	if (status)
+		goto xdr_error;
+
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
 	dprintk("%s: xdr returned %d!\n", __func__, -status);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 128e01acb4ca..7eae72a8762e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -286,5 +286,6 @@ struct nfs_server {
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
+#define NFS_CAP_XATTR		(1U << 28)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 5fd0a9ef425f..dee9b1cfa972 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -150,6 +150,7 @@ struct nfs_fsinfo {
 	__u32			layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */
 	__u32			blksize; /* preferred pnfs io block size */
 	__u32			clone_blksize; /* granularity of a CLONE operation */
+	__u32			xattr_support; /* User xattrs supported */
 };
 
 struct nfs_fsstat {
-- 
cgit v1.2.3


From 3e1f02123fba086d32dfd5729e6f4e2b54654acc Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:38:56 +0000
Subject: NFSv4.2: add client side XDR handling for extended attributes

Define the argument and response structures that will be used for
RFC 8276 extended attribute RPC calls, and implement the necessary
functions to encode/decode the extended attribute operations.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42xdr.c       | 368 +++++++++++++++++++++++++++++++++++++++++++++++-
 fs/nfs/nfs4xdr.c        |   6 +
 include/linux/nfs_xdr.h |  59 +++++++-
 3 files changed, 430 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 6712daa9d85b..cc50085e151c 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -169,7 +169,6 @@
 					 decode_clone_maxsz + \
 					 decode_getattr_maxsz)
 
-#ifdef CONFIG_NFS_V4_2
 /* Not limited by NFS itself, limited by the generic xattr code */
 #define nfs4_xattr_name_maxsz   XDR_QUADLEN(XATTR_NAME_MAX)
 
@@ -241,7 +240,6 @@ const u32 nfs42_maxlistxattrs_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 					compound_decode_hdr_maxsz +
 					decode_sequence_maxsz +
 					decode_putfh_maxsz + 3) * XDR_UNIT);
-#endif
 
 static void encode_fallocate(struct xdr_stream *xdr,
 			     const struct nfs42_falloc_args *args)
@@ -407,6 +405,210 @@ static void encode_layouterror(struct xdr_stream *xdr,
 	encode_device_error(xdr, &args->errors[0]);
 }
 
+static void encode_setxattr(struct xdr_stream *xdr,
+			    const struct nfs42_setxattrargs *arg,
+			    struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	BUILD_BUG_ON(XATTR_CREATE != SETXATTR4_CREATE);
+	BUILD_BUG_ON(XATTR_REPLACE != SETXATTR4_REPLACE);
+
+	encode_op_hdr(xdr, OP_SETXATTR, decode_setxattr_maxsz, hdr);
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(arg->xattr_flags);
+	encode_string(xdr, strlen(arg->xattr_name), arg->xattr_name);
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(arg->xattr_len);
+	if (arg->xattr_len)
+		xdr_write_pages(xdr, arg->xattr_pages, 0, arg->xattr_len);
+}
+
+static int decode_setxattr(struct xdr_stream *xdr,
+			   struct nfs4_change_info *cinfo)
+{
+	int status;
+
+	status = decode_op_hdr(xdr, OP_SETXATTR);
+	if (status)
+		goto out;
+	status = decode_change_info(xdr, cinfo);
+out:
+	return status;
+}
+
+
+static void encode_getxattr(struct xdr_stream *xdr, const char *name,
+			    struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_GETXATTR, decode_getxattr_maxsz, hdr);
+	encode_string(xdr, strlen(name), name);
+}
+
+static int decode_getxattr(struct xdr_stream *xdr,
+			   struct nfs42_getxattrres *res,
+			   struct rpc_rqst *req)
+{
+	int status;
+	__be32 *p;
+	u32 len, rdlen;
+
+	status = decode_op_hdr(xdr, OP_GETXATTR);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	len = be32_to_cpup(p);
+	if (len > req->rq_rcv_buf.page_len)
+		return -ERANGE;
+
+	res->xattr_len = len;
+
+	if (len > 0) {
+		rdlen = xdr_read_pages(xdr, len);
+		if (rdlen < len)
+			return -EIO;
+	}
+
+	return 0;
+}
+
+static void encode_removexattr(struct xdr_stream *xdr, const char *name,
+			       struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_REMOVEXATTR, decode_removexattr_maxsz, hdr);
+	encode_string(xdr, strlen(name), name);
+}
+
+
+static int decode_removexattr(struct xdr_stream *xdr,
+			   struct nfs4_change_info *cinfo)
+{
+	int status;
+
+	status = decode_op_hdr(xdr, OP_REMOVEXATTR);
+	if (status)
+		goto out;
+
+	status = decode_change_info(xdr, cinfo);
+out:
+	return status;
+}
+
+static void encode_listxattrs(struct xdr_stream *xdr,
+			     const struct nfs42_listxattrsargs *arg,
+			     struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr);
+
+	p = reserve_space(xdr, 12);
+	if (unlikely(!p))
+		return;
+
+	p = xdr_encode_hyper(p, arg->cookie);
+	/*
+	 * RFC 8276 says to specify the full max length of the LISTXATTRS
+	 * XDR reply. Count is set to the XDR length of the names array
+	 * plus the EOF marker. So, add the cookie and the names count.
+	 */
+	*p = cpu_to_be32(arg->count + 8 + 4);
+}
+
+static int decode_listxattrs(struct xdr_stream *xdr,
+			    struct nfs42_listxattrsres *res)
+{
+	int status;
+	__be32 *p;
+	u32 count, len, ulen;
+	size_t left, copied;
+	char *buf;
+
+	status = decode_op_hdr(xdr, OP_LISTXATTRS);
+	if (status) {
+		/*
+		 * Special case: for LISTXATTRS, NFS4ERR_TOOSMALL
+		 * should be translated to ERANGE.
+		 */
+		if (status == -ETOOSMALL)
+			status = -ERANGE;
+		goto out;
+	}
+
+	p = xdr_inline_decode(xdr, 8);
+	if (unlikely(!p))
+		return -EIO;
+
+	xdr_decode_hyper(p, &res->cookie);
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	left = res->xattr_len;
+	buf = res->xattr_buf;
+
+	count = be32_to_cpup(p);
+	copied = 0;
+
+	/*
+	 * We have asked for enough room to encode the maximum number
+	 * of possible attribute names, so everything should fit.
+	 *
+	 * But, don't rely on that assumption. Just decode entries
+	 * until they don't fit anymore, just in case the server did
+	 * something odd.
+	 */
+	while (count--) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
+
+		len = be32_to_cpup(p);
+		if (len > (XATTR_NAME_MAX - XATTR_USER_PREFIX_LEN)) {
+			status = -ERANGE;
+			goto out;
+		}
+
+		p = xdr_inline_decode(xdr, len);
+		if (unlikely(!p))
+			return -EIO;
+
+		ulen = len + XATTR_USER_PREFIX_LEN + 1;
+		if (buf) {
+			if (ulen > left) {
+				status = -ERANGE;
+				goto out;
+			}
+
+			memcpy(buf, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
+			memcpy(buf + XATTR_USER_PREFIX_LEN, p, len);
+
+			buf[ulen - 1] = 0;
+			buf += ulen;
+			left -= ulen;
+		}
+		copied += ulen;
+	}
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	res->eof = be32_to_cpup(p);
+	res->copied = copied;
+
+out:
+	if (status == -ERANGE && res->xattr_len == XATTR_LIST_MAX)
+		status = -E2BIG;
+
+	return status;
+}
+
 /*
  * Encode ALLOCATE request
  */
@@ -1062,4 +1264,166 @@ out:
 	return status;
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs4_xdr_enc_setxattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+				  const void *data)
+{
+	const struct nfs42_setxattrargs *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_setxattr(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_setxattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+				 void *data)
+{
+	struct nfs42_setxattrres *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, req);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+
+	status = decode_setxattr(xdr, &res->cinfo);
+out:
+	return status;
+}
+
+static void nfs4_xdr_enc_getxattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+				  const void *data)
+{
+	const struct nfs42_getxattrargs *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+	size_t plen;
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_getxattr(xdr, args->xattr_name, &hdr);
+
+	plen = args->xattr_len ? args->xattr_len : XATTR_SIZE_MAX;
+
+	rpc_prepare_reply_pages(req, args->xattr_pages, 0, plen,
+	    hdr.replen);
+	req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
+
+	encode_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_getxattr(struct rpc_rqst *rqstp,
+				 struct xdr_stream *xdr, void *data)
+{
+	struct nfs42_getxattrres *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_getxattr(xdr, res, rqstp);
+out:
+	return status;
+}
+
+static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req,
+				    struct xdr_stream *xdr, const void *data)
+{
+	const struct nfs42_listxattrsargs *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_listxattrs(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count,
+	    hdr.replen);
+	req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
+
+	encode_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_listxattrs(struct rpc_rqst *rqstp,
+				   struct xdr_stream *xdr, void *data)
+{
+	struct nfs42_listxattrsres *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_set_scratch_buffer(xdr, page_address(res->scratch), PAGE_SIZE);
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_listxattrs(xdr, res);
+out:
+	return status;
+}
+
+static void nfs4_xdr_enc_removexattr(struct rpc_rqst *req,
+				     struct xdr_stream *xdr, const void *data)
+{
+	const struct nfs42_removexattrargs *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_removexattr(xdr, args->xattr_name, &hdr);
+	encode_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_removexattr(struct rpc_rqst *req,
+				    struct xdr_stream *xdr, void *data)
+{
+	struct nfs42_removexattrres *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, req);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+
+	status = decode_removexattr(xdr, &res->cinfo);
+out:
+	return status;
+}
+#endif
 #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 9e1b07640e9a..388ac520b104 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7481,6 +7481,8 @@ static struct {
 	{ NFS4ERR_SYMLINK,	-ELOOP		},
 	{ NFS4ERR_OP_ILLEGAL,	-EOPNOTSUPP	},
 	{ NFS4ERR_DEADLOCK,	-EDEADLK	},
+	{ NFS4ERR_NOXATTR,	-ENODATA	},
+	{ NFS4ERR_XATTR2BIG,	-E2BIG		},
 	{ -1,			-EIO		}
 };
 
@@ -7609,6 +7611,10 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC42(LAYOUTERROR,	enc_layouterror,	dec_layouterror),
+	PROC42(GETXATTR,	enc_getxattr,		dec_getxattr),
+	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
+	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
+	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index dee9b1cfa972..9408f3252c8e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1498,7 +1498,64 @@ struct nfs42_seek_res {
 	u32	sr_eof;
 	u64	sr_offset;
 };
-#endif
+
+struct nfs42_setxattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+	u32				xattr_flags;
+	size_t				xattr_len;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_setxattrres {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs4_change_info		cinfo;
+};
+
+struct nfs42_getxattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+	size_t				xattr_len;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_getxattrres {
+	struct nfs4_sequence_res	seq_res;
+	size_t				xattr_len;
+};
+
+struct nfs42_listxattrsargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	u32				count;
+	u64				cookie;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_listxattrsres {
+	struct nfs4_sequence_res	seq_res;
+	struct page			*scratch;
+	void				*xattr_buf;
+	size_t				xattr_len;
+	u64				cookie;
+	bool				eof;
+	size_t				copied;
+};
+
+struct nfs42_removexattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+};
+
+struct nfs42_removexattrres {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs4_change_info		cinfo;
+};
+
+#endif /* CONFIG_NFS_V4_2 */
 
 struct nfs_page;
 
-- 
cgit v1.2.3


From d2ae4f8b21c111bb795c557588d89dccd005828d Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:38:57 +0000
Subject: nfs: define nfs_access_get_cached function

The only consumer of nfs_access_get_cached_rcu and nfs_access_cached
calls these static functions in order to first try RCU access, and
then locked access.

Combine them in to a single function, and call that. Make this function
available to the rest of the NFS code.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c           | 20 ++++++++++++++++----
 include/linux/nfs_fs.h |  2 ++
 2 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 5a331da5f55a..f04fc0f7843b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2460,7 +2460,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co
 	return NULL;
 }
 
-static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
+static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_access_entry *cache;
@@ -2533,6 +2533,20 @@ out:
 	return err;
 }
 
+int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct
+nfs_access_entry *res, bool may_block)
+{
+	int status;
+
+	status = nfs_access_get_cached_rcu(inode, cred, res);
+	if (status != 0)
+		status = nfs_access_get_cached_locked(inode, cred, res,
+		    may_block);
+
+	return status;
+}
+EXPORT_SYMBOL_GPL(nfs_access_get_cached);
+
 static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -2647,9 +2661,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
 
 	trace_nfs_access_enter(inode);
 
-	status = nfs_access_get_cached_rcu(inode, cred, &cache);
-	if (status != 0)
-		status = nfs_access_get_cached(inode, cred, &cache, may_block);
+	status = nfs_access_get_cached(inode, cred, &cache, may_block);
 	if (status == 0)
 		goto out_cached;
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b743988fcbd0..714b577dce19 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -493,6 +493,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh,
 			struct nfs_fattr *fattr, struct nfs4_label *label);
 extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags);
 extern void nfs_access_zap_cache(struct inode *inode);
+extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res,
+				 bool may_block);
 
 /*
  * linux/fs/nfs/symlink.c
-- 
cgit v1.2.3


From 0f44da51aeef9c974ea744c0d9e24d54eec4e94c Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:00 +0000
Subject: nfs: define and use the NFS_INO_INVALID_XATTR flag

Define the NFS_INO_INVALID_XATTR flag, to be used for the NFSv4.2 xattr
cache, and use it where appropriate.

No functional change as yet.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c         | 7 ++++++-
 fs/nfs/nfs4proc.c      | 3 ++-
 fs/nfs/nfstrace.h      | 3 ++-
 include/linux/nfs_fs.h | 1 +
 4 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0bf1f835de01..629af798dfc9 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -204,7 +204,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 			flags &= ~NFS_INO_INVALID_OTHER;
 		flags &= ~(NFS_INO_INVALID_CHANGE
 				| NFS_INO_INVALID_SIZE
-				| NFS_INO_REVAL_PAGECACHE);
+				| NFS_INO_REVAL_PAGECACHE
+				| NFS_INO_INVALID_XATTR);
 	}
 
 	if (inode->i_mapping->nrpages == 0)
@@ -542,6 +543,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 			inode->i_gid = fattr->gid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+		if (nfs_server_capable(inode, NFS_CAP_XATTR))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -1375,6 +1378,8 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode_set_iversion_raw(inode, fattr->change_attr);
 		if (S_ISDIR(inode->i_mode))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
+		else if (nfs_server_capable(inode, NFS_CAP_XATTR))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
 	}
 	/* If we have atomic WCC data, we may update some attributes */
 	ts = inode->i_ctime;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6540071cb228..0d123fe0a423 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1183,7 +1183,8 @@ nfs4_update_changeattr_locked(struct inode *inode,
 
 		if (cinfo->before != inode_peek_iversion_raw(inode))
 			nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
-						NFS_INO_INVALID_ACL;
+						NFS_INO_INVALID_ACL |
+						NFS_INO_INVALID_XATTR;
 	}
 	inode_set_iversion_raw(inode, cinfo->after);
 	nfsi->read_cache_jiffies = timestamp;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 547cec79899f..5a59dcdce0b2 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -59,7 +59,8 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
 			{ NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \
 			{ NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \
 			{ NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \
-			{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" })
+			{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \
+			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" })
 
 TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
 TRACE_DEFINE_ENUM(NFS_INO_STALE);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 714b577dce19..943ee750d68c 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -234,6 +234,7 @@ struct nfs4_copy_state {
 #define NFS_INO_DATA_INVAL_DEFER	\
 				BIT(13)		/* Deferred cache invalidation */
 #define NFS_INO_INVALID_BLOCKS	BIT(14)         /* cached blocks are invalid */
+#define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
-- 
cgit v1.2.3


From 95ad37f90c338e3fd4abf61cecfe02b6f3e080f0 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 23 Jun 2020 22:39:04 +0000
Subject: NFSv4.2: add client side xattr caching.

Implement client side caching for NFSv4.2 extended attributes. The cache
is a per-inode hashtable, with name/value entries. There is one special
entry for the listxattr cache.

NFS inodes have a pointer to a cache structure. The cache structure is
allocated on demand, freed when the cache is invalidated.

Memory shrinkers keep the size in check. Large entries (> PAGE_SIZE)
are collected by a separate shrinker, and freed more aggressively
than others.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/Makefile             |    2 +-
 fs/nfs/inode.c              |    9 +-
 fs/nfs/nfs42proc.c          |   12 +
 fs/nfs/nfs42xattr.c         | 1083 +++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h            |   22 +
 fs/nfs/nfs4proc.c           |   42 +-
 fs/nfs/nfs4super.c          |   10 +
 include/linux/nfs_fs.h      |    6 +
 include/uapi/linux/nfs_fs.h |    1 +
 9 files changed, 1179 insertions(+), 8 deletions(-)
 create mode 100644 fs/nfs/nfs42xattr.c

(limited to 'include/linux')

diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 2433c3e03cfa..22d11fdc6deb 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -30,7 +30,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
 nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
-nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
+nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o nfs42xattr.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 629af798dfc9..10048eed485d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -193,6 +193,7 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
 
 	return nfs_check_cache_invalid_not_delegated(inode, flags);
 }
+EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
 
 static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
@@ -234,11 +235,13 @@ static void nfs_zap_caches_locked(struct inode *inode)
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR
 					| NFS_INO_REVAL_PAGECACHE);
 	} else
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR
 					| NFS_INO_REVAL_PAGECACHE);
 	nfs_zap_label_cache_locked(nfsi);
 }
@@ -1897,7 +1900,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if (!(have_writers || have_delegation)) {
 				invalid |= NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
-					| NFS_INO_INVALID_ACL;
+					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR;
 				/* Force revalidate of all attributes */
 				save_cache_validity |= NFS_INO_INVALID_CTIME
 					| NFS_INO_INVALID_MTIME
@@ -2100,6 +2104,9 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
 #if IS_ENABLED(CONFIG_NFS_V4)
 	nfsi->nfs4_acl = NULL;
 #endif /* CONFIG_NFS_V4 */
+#ifdef CONFIG_NFS_V4_2
+	nfsi->xattr_cache = NULL;
+#endif
 	return &nfsi->vfs_inode;
 }
 EXPORT_SYMBOL_GPL(nfs_alloc_inode);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 8c2e52bc986a..e200522469af 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -1182,6 +1182,18 @@ static ssize_t _nfs42_proc_getxattr(struct inode *inode, const char *name,
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * Normally, the caching is done one layer up, but for successful
+	 * RPCS, always cache the result here, even if the caller was
+	 * just querying the length, or if the reply was too big for
+	 * the caller. This avoids a second RPC in the case of the
+	 * common query-alloc-retrieve cycle for xattrs.
+	 *
+	 * Note that xattr_len is always capped to XATTR_SIZE_MAX.
+	 */
+
+	nfs4_xattr_cache_add(inode, name, NULL, pages, res.xattr_len);
+
 	if (buflen) {
 		if (res.xattr_len > buflen)
 			return -ERANGE;
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
new file mode 100644
index 000000000000..23fdab977a2a
--- /dev/null
+++ b/fs/nfs/nfs42xattr.c
@@ -0,0 +1,1083 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2019, 2020 Amazon.com, Inc. or its affiliates. All rights reserved.
+ *
+ * User extended attribute client side cache functions.
+ *
+ * Author: Frank van der Linden <fllinden@amazon.com>
+ */
+#include <linux/errno.h>
+#include <linux/nfs_fs.h>
+#include <linux/hashtable.h>
+#include <linux/refcount.h>
+#include <uapi/linux/xattr.h>
+
+#include "nfs4_fs.h"
+#include "internal.h"
+
+/*
+ * User extended attributes client side caching is implemented by having
+ * a cache structure attached to NFS inodes. This structure is allocated
+ * when needed, and freed when the cache is zapped.
+ *
+ * The cache structure contains as hash table of entries, and a pointer
+ * to a special-cased entry for the listxattr cache.
+ *
+ * Accessing and allocating / freeing the caches is done via reference
+ * counting. The cache entries use a similar refcounting scheme.
+ *
+ * This makes freeing a cache, both from the shrinker and from the
+ * zap cache path, easy. It also means that, in current use cases,
+ * the large majority of inodes will not waste any memory, as they
+ * will never have any user extended attributes assigned to them.
+ *
+ * Attribute entries are hashed in to a simple hash table. They are
+ * also part of an LRU.
+ *
+ * There are three shrinkers.
+ *
+ * Two shrinkers deal with the cache entries themselves: one for
+ * large entries (> PAGE_SIZE), and one for smaller entries. The
+ * shrinker for the larger entries works more aggressively than
+ * those for the smaller entries.
+ *
+ * The other shrinker frees the cache structures themselves.
+ */
+
+/*
+ * 64 buckets is a good default. There is likely no reasonable
+ * workload that uses more than even 64 user extended attributes.
+ * You can certainly add a lot more - but you get what you ask for
+ * in those circumstances.
+ */
+#define NFS4_XATTR_HASH_SIZE	64
+
+#define NFSDBG_FACILITY	NFSDBG_XATTRCACHE
+
+struct nfs4_xattr_cache;
+struct nfs4_xattr_entry;
+
+struct nfs4_xattr_bucket {
+	spinlock_t lock;
+	struct hlist_head hlist;
+	struct nfs4_xattr_cache *cache;
+	bool draining;
+};
+
+struct nfs4_xattr_cache {
+	struct kref ref;
+	spinlock_t hash_lock;	/* protects hashtable and lru */
+	struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE];
+	struct list_head lru;
+	struct list_head dispose;
+	atomic_long_t nent;
+	spinlock_t listxattr_lock;
+	struct inode *inode;
+	struct nfs4_xattr_entry *listxattr;
+	struct work_struct work;
+};
+
+struct nfs4_xattr_entry {
+	struct kref ref;
+	struct hlist_node hnode;
+	struct list_head lru;
+	struct list_head dispose;
+	char *xattr_name;
+	void *xattr_value;
+	size_t xattr_size;
+	struct nfs4_xattr_bucket *bucket;
+	uint32_t flags;
+};
+
+#define	NFS4_XATTR_ENTRY_EXTVAL	0x0001
+
+/*
+ * LRU list of NFS inodes that have xattr caches.
+ */
+static struct list_lru nfs4_xattr_cache_lru;
+static struct list_lru nfs4_xattr_entry_lru;
+static struct list_lru nfs4_xattr_large_entry_lru;
+
+static struct kmem_cache *nfs4_xattr_cache_cachep;
+
+static struct workqueue_struct *nfs4_xattr_cache_wq;
+
+/*
+ * Hashing helper functions.
+ */
+static void
+nfs4_xattr_hash_init(struct nfs4_xattr_cache *cache)
+{
+	unsigned int i;
+
+	for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) {
+		INIT_HLIST_HEAD(&cache->buckets[i].hlist);
+		spin_lock_init(&cache->buckets[i].lock);
+		cache->buckets[i].cache = cache;
+		cache->buckets[i].draining = false;
+	}
+}
+
+/*
+ * Locking order:
+ * 1. inode i_lock or bucket lock
+ * 2. list_lru lock (taken by list_lru_* functions)
+ */
+
+/*
+ * Wrapper functions to add a cache entry to the right LRU.
+ */
+static bool
+nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry)
+{
+	struct list_lru *lru;
+
+	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
+	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
+
+	return list_lru_add(lru, &entry->lru);
+}
+
+static bool
+nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
+{
+	struct list_lru *lru;
+
+	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
+	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
+
+	return list_lru_del(lru, &entry->lru);
+}
+
+/*
+ * This function allocates cache entries. They are the normal
+ * extended attribute name/value pairs, but may also be a listxattr
+ * cache. Those allocations use the same entry so that they can be
+ * treated as one by the memory shrinker.
+ *
+ * xattr cache entries are allocated together with names. If the
+ * value fits in to one page with the entry structure and the name,
+ * it will also be part of the same allocation (kmalloc). This is
+ * expected to be the vast majority of cases. Larger allocations
+ * have a value pointer that is allocated separately by kvmalloc.
+ *
+ * Parameters:
+ *
+ * @name:  Name of the extended attribute. NULL for listxattr cache
+ *         entry.
+ * @value: Value of attribute, or listxattr cache. NULL if the
+ *         value is to be copied from pages instead.
+ * @pages: Pages to copy the value from, if not NULL. Passed in to
+ *	   make it easier to copy the value after an RPC, even if
+ *	   the value will not be passed up to application (e.g.
+ *	   for a 'query' getxattr with NULL buffer).
+ * @len:   Length of the value. Can be 0 for zero-length attribues.
+ *         @value and @pages will be NULL if @len is 0.
+ */
+static struct nfs4_xattr_entry *
+nfs4_xattr_alloc_entry(const char *name, const void *value,
+		       struct page **pages, size_t len)
+{
+	struct nfs4_xattr_entry *entry;
+	void *valp;
+	char *namep;
+	size_t alloclen, slen;
+	char *buf;
+	uint32_t flags;
+
+	BUILD_BUG_ON(sizeof(struct nfs4_xattr_entry) +
+	    XATTR_NAME_MAX + 1 > PAGE_SIZE);
+
+	alloclen = sizeof(struct nfs4_xattr_entry);
+	if (name != NULL) {
+		slen = strlen(name) + 1;
+		alloclen += slen;
+	} else
+		slen = 0;
+
+	if (alloclen + len <= PAGE_SIZE) {
+		alloclen += len;
+		flags = 0;
+	} else {
+		flags = NFS4_XATTR_ENTRY_EXTVAL;
+	}
+
+	buf = kmalloc(alloclen, GFP_KERNEL_ACCOUNT | GFP_NOFS);
+	if (buf == NULL)
+		return NULL;
+	entry = (struct nfs4_xattr_entry *)buf;
+
+	if (name != NULL) {
+		namep = buf + sizeof(struct nfs4_xattr_entry);
+		memcpy(namep, name, slen);
+	} else {
+		namep = NULL;
+	}
+
+
+	if (flags & NFS4_XATTR_ENTRY_EXTVAL) {
+		valp = kvmalloc(len, GFP_KERNEL_ACCOUNT | GFP_NOFS);
+		if (valp == NULL) {
+			kfree(buf);
+			return NULL;
+		}
+	} else if (len != 0) {
+		valp = buf + sizeof(struct nfs4_xattr_entry) + slen;
+	} else
+		valp = NULL;
+
+	if (valp != NULL) {
+		if (value != NULL)
+			memcpy(valp, value, len);
+		else
+			_copy_from_pages(valp, pages, 0, len);
+	}
+
+	entry->flags = flags;
+	entry->xattr_value = valp;
+	kref_init(&entry->ref);
+	entry->xattr_name = namep;
+	entry->xattr_size = len;
+	entry->bucket = NULL;
+	INIT_LIST_HEAD(&entry->lru);
+	INIT_LIST_HEAD(&entry->dispose);
+	INIT_HLIST_NODE(&entry->hnode);
+
+	return entry;
+}
+
+static void
+nfs4_xattr_free_entry(struct nfs4_xattr_entry *entry)
+{
+	if (entry->flags & NFS4_XATTR_ENTRY_EXTVAL)
+		kvfree(entry->xattr_value);
+	kfree(entry);
+}
+
+static void
+nfs4_xattr_free_entry_cb(struct kref *kref)
+{
+	struct nfs4_xattr_entry *entry;
+
+	entry = container_of(kref, struct nfs4_xattr_entry, ref);
+
+	if (WARN_ON(!list_empty(&entry->lru)))
+		return;
+
+	nfs4_xattr_free_entry(entry);
+}
+
+static void
+nfs4_xattr_free_cache_cb(struct kref *kref)
+{
+	struct nfs4_xattr_cache *cache;
+	int i;
+
+	cache = container_of(kref, struct nfs4_xattr_cache, ref);
+
+	for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) {
+		if (WARN_ON(!hlist_empty(&cache->buckets[i].hlist)))
+			return;
+		cache->buckets[i].draining = false;
+	}
+
+	cache->listxattr = NULL;
+
+	kmem_cache_free(nfs4_xattr_cache_cachep, cache);
+
+}
+
+static struct nfs4_xattr_cache *
+nfs4_xattr_alloc_cache(void)
+{
+	struct nfs4_xattr_cache *cache;
+
+	cache = kmem_cache_alloc(nfs4_xattr_cache_cachep,
+	    GFP_KERNEL_ACCOUNT | GFP_NOFS);
+	if (cache == NULL)
+		return NULL;
+
+	kref_init(&cache->ref);
+	atomic_long_set(&cache->nent, 0);
+
+	return cache;
+}
+
+/*
+ * Set the listxattr cache, which is a special-cased cache entry.
+ * The special value ERR_PTR(-ESTALE) is used to indicate that
+ * the cache is being drained - this prevents a new listxattr
+ * cache from being added to what is now a stale cache.
+ */
+static int
+nfs4_xattr_set_listcache(struct nfs4_xattr_cache *cache,
+			 struct nfs4_xattr_entry *new)
+{
+	struct nfs4_xattr_entry *old;
+	int ret = 1;
+
+	spin_lock(&cache->listxattr_lock);
+
+	old = cache->listxattr;
+
+	if (old == ERR_PTR(-ESTALE)) {
+		ret = 0;
+		goto out;
+	}
+
+	cache->listxattr = new;
+	if (new != NULL && new != ERR_PTR(-ESTALE))
+		nfs4_xattr_entry_lru_add(new);
+
+	if (old != NULL) {
+		nfs4_xattr_entry_lru_del(old);
+		kref_put(&old->ref, nfs4_xattr_free_entry_cb);
+	}
+out:
+	spin_unlock(&cache->listxattr_lock);
+
+	return ret;
+}
+
+/*
+ * Unlink a cache from its parent inode, clearing out an invalid
+ * cache. Must be called with i_lock held.
+ */
+static struct nfs4_xattr_cache *
+nfs4_xattr_cache_unlink(struct inode *inode)
+{
+	struct nfs_inode *nfsi;
+	struct nfs4_xattr_cache *oldcache;
+
+	nfsi = NFS_I(inode);
+
+	oldcache = nfsi->xattr_cache;
+	if (oldcache != NULL) {
+		list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru);
+		oldcache->inode = NULL;
+	}
+	nfsi->xattr_cache = NULL;
+	nfsi->cache_validity &= ~NFS_INO_INVALID_XATTR;
+
+	return oldcache;
+
+}
+
+/*
+ * Discard a cache. Usually called by a worker, since walking all
+ * the entries can take up some cycles that we don't want to waste
+ * in the I/O path. Can also be called from the shrinker callback.
+ *
+ * The cache is dead, it has already been unlinked from its inode,
+ * and no longer appears on the cache LRU list.
+ *
+ * Mark all buckets as draining, so that no new entries are added. This
+ * could still happen in the unlikely, but possible case that another
+ * thread had grabbed a reference before it was unlinked from the inode,
+ * and is still holding it for an add operation.
+ *
+ * Remove all entries from the LRU lists, so that there is no longer
+ * any way to 'find' this cache. Then, remove the entries from the hash
+ * table.
+ *
+ * At that point, the cache will remain empty and can be freed when the final
+ * reference drops, which is very likely the kref_put at the end of
+ * this function, or the one called immediately afterwards in the
+ * shrinker callback.
+ */
+static void
+nfs4_xattr_discard_cache(struct nfs4_xattr_cache *cache)
+{
+	unsigned int i;
+	struct nfs4_xattr_entry *entry;
+	struct nfs4_xattr_bucket *bucket;
+	struct hlist_node *n;
+
+	nfs4_xattr_set_listcache(cache, ERR_PTR(-ESTALE));
+
+	for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) {
+		bucket = &cache->buckets[i];
+
+		spin_lock(&bucket->lock);
+		bucket->draining = true;
+		hlist_for_each_entry_safe(entry, n, &bucket->hlist, hnode) {
+			nfs4_xattr_entry_lru_del(entry);
+			hlist_del_init(&entry->hnode);
+			kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+		}
+		spin_unlock(&bucket->lock);
+	}
+
+	atomic_long_set(&cache->nent, 0);
+
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+}
+
+static void
+nfs4_xattr_discard_cache_worker(struct work_struct *work)
+{
+	struct nfs4_xattr_cache *cache = container_of(work,
+	    struct nfs4_xattr_cache, work);
+
+	nfs4_xattr_discard_cache(cache);
+}
+
+static void
+nfs4_xattr_reap_cache(struct nfs4_xattr_cache *cache)
+{
+	queue_work(nfs4_xattr_cache_wq, &cache->work);
+}
+
+/*
+ * Get a referenced copy of the cache structure. Avoid doing allocs
+ * while holding i_lock. Which means that we do some optimistic allocation,
+ * and might have to free the result in rare cases.
+ *
+ * This function only checks the NFS_INO_INVALID_XATTR cache validity bit
+ * and acts accordingly, replacing the cache when needed. For the read case
+ * (!add), this means that the caller must make sure that the cache
+ * is valid before caling this function. getxattr and listxattr call
+ * revalidate_inode to do this. The attribute cache timeout (for the
+ * non-delegated case) is expected to be dealt with in the revalidate
+ * call.
+ */
+
+static struct nfs4_xattr_cache *
+nfs4_xattr_get_cache(struct inode *inode, int add)
+{
+	struct nfs_inode *nfsi;
+	struct nfs4_xattr_cache *cache, *oldcache, *newcache;
+
+	nfsi = NFS_I(inode);
+
+	cache = oldcache = NULL;
+
+	spin_lock(&inode->i_lock);
+
+	if (nfsi->cache_validity & NFS_INO_INVALID_XATTR)
+		oldcache = nfs4_xattr_cache_unlink(inode);
+	else
+		cache = nfsi->xattr_cache;
+
+	if (cache != NULL)
+		kref_get(&cache->ref);
+
+	spin_unlock(&inode->i_lock);
+
+	if (add && cache == NULL) {
+		newcache = NULL;
+
+		cache = nfs4_xattr_alloc_cache();
+		if (cache == NULL)
+			goto out;
+
+		spin_lock(&inode->i_lock);
+		if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) {
+			/*
+			 * The cache was invalidated again. Give up,
+			 * since what we want to enter is now likely
+			 * outdated anyway.
+			 */
+			spin_unlock(&inode->i_lock);
+			kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+			cache = NULL;
+			goto out;
+		}
+
+		/*
+		 * Check if someone beat us to it.
+		 */
+		if (nfsi->xattr_cache != NULL) {
+			newcache = nfsi->xattr_cache;
+			kref_get(&newcache->ref);
+		} else {
+			kref_get(&cache->ref);
+			nfsi->xattr_cache = cache;
+			cache->inode = inode;
+			list_lru_add(&nfs4_xattr_cache_lru, &cache->lru);
+		}
+
+		spin_unlock(&inode->i_lock);
+
+		/*
+		 * If there was a race, throw away the cache we just
+		 * allocated, and use the new one allocated by someone
+		 * else.
+		 */
+		if (newcache != NULL) {
+			kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+			cache = newcache;
+		}
+	}
+
+out:
+	/*
+	 * Discarding an old cache is done via a workqueue.
+	 */
+	if (oldcache != NULL)
+		nfs4_xattr_reap_cache(oldcache);
+
+	return cache;
+}
+
+static inline struct nfs4_xattr_bucket *
+nfs4_xattr_hash_bucket(struct nfs4_xattr_cache *cache, const char *name)
+{
+	return &cache->buckets[jhash(name, strlen(name), 0) &
+	    (ARRAY_SIZE(cache->buckets) - 1)];
+}
+
+static struct nfs4_xattr_entry *
+nfs4_xattr_get_entry(struct nfs4_xattr_bucket *bucket, const char *name)
+{
+	struct nfs4_xattr_entry *entry;
+
+	entry = NULL;
+
+	hlist_for_each_entry(entry, &bucket->hlist, hnode) {
+		if (!strcmp(entry->xattr_name, name))
+			break;
+	}
+
+	return entry;
+}
+
+static int
+nfs4_xattr_hash_add(struct nfs4_xattr_cache *cache,
+		    struct nfs4_xattr_entry *entry)
+{
+	struct nfs4_xattr_bucket *bucket;
+	struct nfs4_xattr_entry *oldentry = NULL;
+	int ret = 1;
+
+	bucket = nfs4_xattr_hash_bucket(cache, entry->xattr_name);
+	entry->bucket = bucket;
+
+	spin_lock(&bucket->lock);
+
+	if (bucket->draining) {
+		ret = 0;
+		goto out;
+	}
+
+	oldentry = nfs4_xattr_get_entry(bucket, entry->xattr_name);
+	if (oldentry != NULL) {
+		hlist_del_init(&oldentry->hnode);
+		nfs4_xattr_entry_lru_del(oldentry);
+	} else {
+		atomic_long_inc(&cache->nent);
+	}
+
+	hlist_add_head(&entry->hnode, &bucket->hlist);
+	nfs4_xattr_entry_lru_add(entry);
+
+out:
+	spin_unlock(&bucket->lock);
+
+	if (oldentry != NULL)
+		kref_put(&oldentry->ref, nfs4_xattr_free_entry_cb);
+
+	return ret;
+}
+
+static void
+nfs4_xattr_hash_remove(struct nfs4_xattr_cache *cache, const char *name)
+{
+	struct nfs4_xattr_bucket *bucket;
+	struct nfs4_xattr_entry *entry;
+
+	bucket = nfs4_xattr_hash_bucket(cache, name);
+
+	spin_lock(&bucket->lock);
+
+	entry = nfs4_xattr_get_entry(bucket, name);
+	if (entry != NULL) {
+		hlist_del_init(&entry->hnode);
+		nfs4_xattr_entry_lru_del(entry);
+		atomic_long_dec(&cache->nent);
+	}
+
+	spin_unlock(&bucket->lock);
+
+	if (entry != NULL)
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+}
+
+static struct nfs4_xattr_entry *
+nfs4_xattr_hash_find(struct nfs4_xattr_cache *cache, const char *name)
+{
+	struct nfs4_xattr_bucket *bucket;
+	struct nfs4_xattr_entry *entry;
+
+	bucket = nfs4_xattr_hash_bucket(cache, name);
+
+	spin_lock(&bucket->lock);
+
+	entry = nfs4_xattr_get_entry(bucket, name);
+	if (entry != NULL)
+		kref_get(&entry->ref);
+
+	spin_unlock(&bucket->lock);
+
+	return entry;
+}
+
+/*
+ * Entry point to retrieve an entry from the cache.
+ */
+ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name, char *buf,
+			 ssize_t buflen)
+{
+	struct nfs4_xattr_cache *cache;
+	struct nfs4_xattr_entry *entry;
+	ssize_t ret;
+
+	cache = nfs4_xattr_get_cache(inode, 0);
+	if (cache == NULL)
+		return -ENOENT;
+
+	ret = 0;
+	entry = nfs4_xattr_hash_find(cache, name);
+
+	if (entry != NULL) {
+		dprintk("%s: cache hit '%s', len %lu\n", __func__,
+		    entry->xattr_name, (unsigned long)entry->xattr_size);
+		if (buflen == 0) {
+			/* Length probe only */
+			ret = entry->xattr_size;
+		} else if (buflen < entry->xattr_size)
+			ret = -ERANGE;
+		else {
+			memcpy(buf, entry->xattr_value, entry->xattr_size);
+			ret = entry->xattr_size;
+		}
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+	} else {
+		dprintk("%s: cache miss '%s'\n", __func__, name);
+		ret = -ENOENT;
+	}
+
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+
+	return ret;
+}
+
+/*
+ * Retrieve a cached list of xattrs from the cache.
+ */
+ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf, ssize_t buflen)
+{
+	struct nfs4_xattr_cache *cache;
+	struct nfs4_xattr_entry *entry;
+	ssize_t ret;
+
+	cache = nfs4_xattr_get_cache(inode, 0);
+	if (cache == NULL)
+		return -ENOENT;
+
+	spin_lock(&cache->listxattr_lock);
+
+	entry = cache->listxattr;
+
+	if (entry != NULL && entry != ERR_PTR(-ESTALE)) {
+		if (buflen == 0) {
+			/* Length probe only */
+			ret = entry->xattr_size;
+		} else if (entry->xattr_size > buflen)
+			ret = -ERANGE;
+		else {
+			memcpy(buf, entry->xattr_value, entry->xattr_size);
+			ret = entry->xattr_size;
+		}
+	} else {
+		ret = -ENOENT;
+	}
+
+	spin_unlock(&cache->listxattr_lock);
+
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+
+	return ret;
+}
+
+/*
+ * Add an xattr to the cache.
+ *
+ * This also invalidates the xattr list cache.
+ */
+void nfs4_xattr_cache_add(struct inode *inode, const char *name,
+			  const char *buf, struct page **pages, ssize_t buflen)
+{
+	struct nfs4_xattr_cache *cache;
+	struct nfs4_xattr_entry *entry;
+
+	dprintk("%s: add '%s' len %lu\n", __func__,
+	    name, (unsigned long)buflen);
+
+	cache = nfs4_xattr_get_cache(inode, 1);
+	if (cache == NULL)
+		return;
+
+	entry = nfs4_xattr_alloc_entry(name, buf, pages, buflen);
+	if (entry == NULL)
+		goto out;
+
+	(void)nfs4_xattr_set_listcache(cache, NULL);
+
+	if (!nfs4_xattr_hash_add(cache, entry))
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+
+out:
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+}
+
+
+/*
+ * Remove an xattr from the cache.
+ *
+ * This also invalidates the xattr list cache.
+ */
+void nfs4_xattr_cache_remove(struct inode *inode, const char *name)
+{
+	struct nfs4_xattr_cache *cache;
+
+	dprintk("%s: remove '%s'\n", __func__, name);
+
+	cache = nfs4_xattr_get_cache(inode, 0);
+	if (cache == NULL)
+		return;
+
+	(void)nfs4_xattr_set_listcache(cache, NULL);
+	nfs4_xattr_hash_remove(cache, name);
+
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+}
+
+/*
+ * Cache listxattr output, replacing any possible old one.
+ */
+void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf,
+			       ssize_t buflen)
+{
+	struct nfs4_xattr_cache *cache;
+	struct nfs4_xattr_entry *entry;
+
+	cache = nfs4_xattr_get_cache(inode, 1);
+	if (cache == NULL)
+		return;
+
+	entry = nfs4_xattr_alloc_entry(NULL, buf, NULL, buflen);
+	if (entry == NULL)
+		goto out;
+
+	/*
+	 * This is just there to be able to get to bucket->cache,
+	 * which is obviously the same for all buckets, so just
+	 * use bucket 0.
+	 */
+	entry->bucket = &cache->buckets[0];
+
+	if (!nfs4_xattr_set_listcache(cache, entry))
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+
+out:
+	kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+}
+
+/*
+ * Zap the entire cache. Called when an inode is evicted.
+ */
+void nfs4_xattr_cache_zap(struct inode *inode)
+{
+	struct nfs4_xattr_cache *oldcache;
+
+	spin_lock(&inode->i_lock);
+	oldcache = nfs4_xattr_cache_unlink(inode);
+	spin_unlock(&inode->i_lock);
+
+	if (oldcache)
+		nfs4_xattr_discard_cache(oldcache);
+}
+
+/*
+ * The entry LRU is shrunk more aggressively than the cache LRU,
+ * by settings @seeks to 1.
+ *
+ * Cache structures are freed only when they've become empty, after
+ * pruning all but one entry.
+ */
+
+static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink,
+					    struct shrink_control *sc);
+static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink,
+					    struct shrink_control *sc);
+static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink,
+					   struct shrink_control *sc);
+static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink,
+					   struct shrink_control *sc);
+
+static struct shrinker nfs4_xattr_cache_shrinker = {
+	.count_objects	= nfs4_xattr_cache_count,
+	.scan_objects	= nfs4_xattr_cache_scan,
+	.seeks		= DEFAULT_SEEKS,
+	.flags		= SHRINKER_MEMCG_AWARE,
+};
+
+static struct shrinker nfs4_xattr_entry_shrinker = {
+	.count_objects	= nfs4_xattr_entry_count,
+	.scan_objects	= nfs4_xattr_entry_scan,
+	.seeks		= DEFAULT_SEEKS,
+	.batch		= 512,
+	.flags		= SHRINKER_MEMCG_AWARE,
+};
+
+static struct shrinker nfs4_xattr_large_entry_shrinker = {
+	.count_objects	= nfs4_xattr_entry_count,
+	.scan_objects	= nfs4_xattr_entry_scan,
+	.seeks		= 1,
+	.batch		= 512,
+	.flags		= SHRINKER_MEMCG_AWARE,
+};
+
+static enum lru_status
+cache_lru_isolate(struct list_head *item,
+	struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
+{
+	struct list_head *dispose = arg;
+	struct inode *inode;
+	struct nfs4_xattr_cache *cache = container_of(item,
+	    struct nfs4_xattr_cache, lru);
+
+	if (atomic_long_read(&cache->nent) > 1)
+		return LRU_SKIP;
+
+	/*
+	 * If a cache structure is on the LRU list, we know that
+	 * its inode is valid. Try to lock it to break the link.
+	 * Since we're inverting the lock order here, only try.
+	 */
+	inode = cache->inode;
+
+	if (!spin_trylock(&inode->i_lock))
+		return LRU_SKIP;
+
+	kref_get(&cache->ref);
+
+	cache->inode = NULL;
+	NFS_I(inode)->xattr_cache = NULL;
+	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_XATTR;
+	list_lru_isolate(lru, &cache->lru);
+
+	spin_unlock(&inode->i_lock);
+
+	list_add_tail(&cache->dispose, dispose);
+	return LRU_REMOVED;
+}
+
+static unsigned long
+nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	LIST_HEAD(dispose);
+	unsigned long freed;
+	struct nfs4_xattr_cache *cache;
+
+	freed = list_lru_shrink_walk(&nfs4_xattr_cache_lru, sc,
+	    cache_lru_isolate, &dispose);
+	while (!list_empty(&dispose)) {
+		cache = list_first_entry(&dispose, struct nfs4_xattr_cache,
+		    dispose);
+		list_del_init(&cache->dispose);
+		nfs4_xattr_discard_cache(cache);
+		kref_put(&cache->ref, nfs4_xattr_free_cache_cb);
+	}
+
+	return freed;
+}
+
+
+static unsigned long
+nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	unsigned long count;
+
+	count = list_lru_count(&nfs4_xattr_cache_lru);
+	return vfs_pressure_ratio(count);
+}
+
+static enum lru_status
+entry_lru_isolate(struct list_head *item,
+	struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
+{
+	struct list_head *dispose = arg;
+	struct nfs4_xattr_bucket *bucket;
+	struct nfs4_xattr_cache *cache;
+	struct nfs4_xattr_entry *entry = container_of(item,
+	    struct nfs4_xattr_entry, lru);
+
+	bucket = entry->bucket;
+	cache = bucket->cache;
+
+	/*
+	 * Unhook the entry from its parent (either a cache bucket
+	 * or a cache structure if it's a listxattr buf), so that
+	 * it's no longer found. Then add it to the isolate list,
+	 * to be freed later.
+	 *
+	 * In both cases, we're reverting lock order, so use
+	 * trylock and skip the entry if we can't get the lock.
+	 */
+	if (entry->xattr_name != NULL) {
+		/* Regular cache entry */
+		if (!spin_trylock(&bucket->lock))
+			return LRU_SKIP;
+
+		kref_get(&entry->ref);
+
+		hlist_del_init(&entry->hnode);
+		atomic_long_dec(&cache->nent);
+		list_lru_isolate(lru, &entry->lru);
+
+		spin_unlock(&bucket->lock);
+	} else {
+		/* Listxattr cache entry */
+		if (!spin_trylock(&cache->listxattr_lock))
+			return LRU_SKIP;
+
+		kref_get(&entry->ref);
+
+		cache->listxattr = NULL;
+		list_lru_isolate(lru, &entry->lru);
+
+		spin_unlock(&cache->listxattr_lock);
+	}
+
+	list_add_tail(&entry->dispose, dispose);
+	return LRU_REMOVED;
+}
+
+static unsigned long
+nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	LIST_HEAD(dispose);
+	unsigned long freed;
+	struct nfs4_xattr_entry *entry;
+	struct list_lru *lru;
+
+	lru = (shrink == &nfs4_xattr_large_entry_shrinker) ?
+	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
+
+	freed = list_lru_shrink_walk(lru, sc, entry_lru_isolate, &dispose);
+
+	while (!list_empty(&dispose)) {
+		entry = list_first_entry(&dispose, struct nfs4_xattr_entry,
+		    dispose);
+		list_del_init(&entry->dispose);
+
+		/*
+		 * Drop two references: the one that we just grabbed
+		 * in entry_lru_isolate, and the one that was set
+		 * when the entry was first allocated.
+		 */
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+		kref_put(&entry->ref, nfs4_xattr_free_entry_cb);
+	}
+
+	return freed;
+}
+
+static unsigned long
+nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	unsigned long count;
+	struct list_lru *lru;
+
+	lru = (shrink == &nfs4_xattr_large_entry_shrinker) ?
+	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
+
+	count = list_lru_count(lru);
+	return vfs_pressure_ratio(count);
+}
+
+
+static void nfs4_xattr_cache_init_once(void *p)
+{
+	struct nfs4_xattr_cache *cache = (struct nfs4_xattr_cache *)p;
+
+	spin_lock_init(&cache->listxattr_lock);
+	atomic_long_set(&cache->nent, 0);
+	nfs4_xattr_hash_init(cache);
+	cache->listxattr = NULL;
+	INIT_WORK(&cache->work, nfs4_xattr_discard_cache_worker);
+	INIT_LIST_HEAD(&cache->lru);
+	INIT_LIST_HEAD(&cache->dispose);
+}
+
+int __init nfs4_xattr_cache_init(void)
+{
+	int ret = 0;
+
+	nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache",
+	    sizeof(struct nfs4_xattr_cache), 0,
+	    (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+	    nfs4_xattr_cache_init_once);
+	if (nfs4_xattr_cache_cachep == NULL)
+		return -ENOMEM;
+
+	ret = list_lru_init_memcg(&nfs4_xattr_large_entry_lru,
+	    &nfs4_xattr_large_entry_shrinker);
+	if (ret)
+		goto out4;
+
+	ret = list_lru_init_memcg(&nfs4_xattr_entry_lru,
+	    &nfs4_xattr_entry_shrinker);
+	if (ret)
+		goto out3;
+
+	ret = list_lru_init_memcg(&nfs4_xattr_cache_lru,
+	    &nfs4_xattr_cache_shrinker);
+	if (ret)
+		goto out2;
+
+	nfs4_xattr_cache_wq = alloc_workqueue("nfs4_xattr", WQ_MEM_RECLAIM, 0);
+	if (nfs4_xattr_cache_wq == NULL)
+		goto out1;
+
+	ret = register_shrinker(&nfs4_xattr_cache_shrinker);
+	if (ret)
+		goto out0;
+
+	ret = register_shrinker(&nfs4_xattr_entry_shrinker);
+	if (ret)
+		goto out;
+
+	ret = register_shrinker(&nfs4_xattr_large_entry_shrinker);
+	if (!ret)
+		return 0;
+
+	unregister_shrinker(&nfs4_xattr_entry_shrinker);
+out:
+	unregister_shrinker(&nfs4_xattr_cache_shrinker);
+out0:
+	destroy_workqueue(nfs4_xattr_cache_wq);
+out1:
+	list_lru_destroy(&nfs4_xattr_cache_lru);
+out2:
+	list_lru_destroy(&nfs4_xattr_entry_lru);
+out3:
+	list_lru_destroy(&nfs4_xattr_large_entry_lru);
+out4:
+	kmem_cache_destroy(nfs4_xattr_cache_cachep);
+
+	return ret;
+}
+
+void nfs4_xattr_cache_exit(void)
+{
+	unregister_shrinker(&nfs4_xattr_entry_shrinker);
+	unregister_shrinker(&nfs4_xattr_cache_shrinker);
+	list_lru_destroy(&nfs4_xattr_entry_lru);
+	list_lru_destroy(&nfs4_xattr_cache_lru);
+	kmem_cache_destroy(nfs4_xattr_cache_cachep);
+	destroy_workqueue(nfs4_xattr_cache_wq);
+}
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 2fa9e4ea98d2..7e16a586f3fc 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -626,12 +626,34 @@ static inline bool nfs4_state_match_open_stateid_other(const struct nfs4_state *
 		nfs4_stateid_match_other(&state->open_stateid, stateid);
 }
 
+/* nfs42xattr.c */
+#ifdef CONFIG_NFS_V4_2
+extern int __init nfs4_xattr_cache_init(void);
+extern void nfs4_xattr_cache_exit(void);
+extern void nfs4_xattr_cache_add(struct inode *inode, const char *name,
+				 const char *buf, struct page **pages,
+				 ssize_t buflen);
+extern void nfs4_xattr_cache_remove(struct inode *inode, const char *name);
+extern ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name,
+				char *buf, ssize_t buflen);
+extern void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf,
+				      ssize_t buflen);
+extern ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf,
+				     ssize_t buflen);
+extern void nfs4_xattr_cache_zap(struct inode *inode);
 #else
+static inline void nfs4_xattr_cache_zap(struct inode *inode)
+{
+}
+#endif /* CONFIG_NFS_V4_2 */
+
+#else /* CONFIG_NFS_V4 */
 
 #define nfs4_close_state(a, b) do { } while (0)
 #define nfs4_close_sync(a, b) do { } while (0)
 #define nfs4_state_protect(a, b, c, d) do { } while (0)
 #define nfs4_state_protect_write(a, b, c, d) do { } while (0)
 
+
 #endif /* CONFIG_NFS_V4 */
 #endif /* __LINUX_FS_NFS_NFS4_FS.H */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 92a07956f07b..f670ff64b31e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7448,6 +7448,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler,
 				    size_t buflen, int flags)
 {
 	struct nfs_access_entry cache;
+	int ret;
 
 	if (!nfs_server_capable(inode, NFS_CAP_XATTR))
 		return -EOPNOTSUPP;
@@ -7466,10 +7467,17 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler,
 			return -EACCES;
 	}
 
-	if (buf == NULL)
-		return nfs42_proc_removexattr(inode, key);
-	else
-		return nfs42_proc_setxattr(inode, key, buf, buflen, flags);
+	if (buf == NULL) {
+		ret = nfs42_proc_removexattr(inode, key);
+		if (!ret)
+			nfs4_xattr_cache_remove(inode, key);
+	} else {
+		ret = nfs42_proc_setxattr(inode, key, buf, buflen, flags);
+		if (!ret)
+			nfs4_xattr_cache_add(inode, key, buf, NULL, buflen);
+	}
+
+	return ret;
 }
 
 static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
@@ -7477,6 +7485,7 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
 				    const char *key, void *buf, size_t buflen)
 {
 	struct nfs_access_entry cache;
+	ssize_t ret;
 
 	if (!nfs_server_capable(inode, NFS_CAP_XATTR))
 		return -EOPNOTSUPP;
@@ -7486,7 +7495,17 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
 			return -EACCES;
 	}
 
-	return nfs42_proc_getxattr(inode, key, buf, buflen);
+	ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	if (ret)
+		return ret;
+
+	ret = nfs4_xattr_cache_get(inode, key, buf, buflen);
+	if (ret >= 0 || (ret < 0 && ret != -ENOENT))
+		return ret;
+
+	ret = nfs42_proc_getxattr(inode, key, buf, buflen);
+
+	return ret;
 }
 
 static ssize_t
@@ -7494,7 +7513,7 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
 {
 	u64 cookie;
 	bool eof;
-	int ret, size;
+	ssize_t ret, size;
 	char *buf;
 	size_t buflen;
 	struct nfs_access_entry cache;
@@ -7507,6 +7526,14 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
 			return 0;
 	}
 
+	ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	if (ret)
+		return ret;
+
+	ret = nfs4_xattr_cache_list(inode, list, list_len);
+	if (ret >= 0 || (ret < 0 && ret != -ENOENT))
+		return ret;
+
 	cookie = 0;
 	eof = false;
 	buflen = list_len ? list_len : XATTR_LIST_MAX;
@@ -7526,6 +7553,9 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
 		size += ret;
 	}
 
+	if (list_len)
+		nfs4_xattr_cache_set_list(inode, list, size);
+
 	return size;
 }
 
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 1475f932d7da..0c1ab846b83d 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -69,6 +69,7 @@ static void nfs4_evict_inode(struct inode *inode)
 	pnfs_destroy_layout(NFS_I(inode));
 	/* First call standard NFS clear_inode() code */
 	nfs_clear_inode(inode);
+	nfs4_xattr_cache_zap(inode);
 }
 
 struct nfs_referral_count {
@@ -268,6 +269,12 @@ static int __init init_nfs_v4(void)
 	if (err)
 		goto out1;
 
+#ifdef CONFIG_NFS_V4_2
+	err = nfs4_xattr_cache_init();
+	if (err)
+		goto out2;
+#endif
+
 	err = nfs4_register_sysctl();
 	if (err)
 		goto out2;
@@ -288,6 +295,9 @@ static void __exit exit_nfs_v4(void)
 	nfs4_pnfs_v3_ds_connect_unload();
 
 	unregister_nfs_version(&nfs_v4);
+#ifdef CONFIG_NFS_V4_2
+	nfs4_xattr_cache_exit();
+#endif
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
 	nfs_dns_resolver_destroy();
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 943ee750d68c..a2c6455ea3fa 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -102,6 +102,8 @@ struct nfs_delegation;
 
 struct posix_acl;
 
+struct nfs4_xattr_cache;
+
 /*
  * nfs fs inode data in memory
  */
@@ -188,6 +190,10 @@ struct nfs_inode {
 	struct fscache_cookie	*fscache;
 #endif
 	struct inode		vfs_inode;
+
+#ifdef CONFIG_NFS_V4_2
+	struct nfs4_xattr_cache *xattr_cache;
+#endif
 };
 
 struct nfs4_copy_state {
diff --git a/include/uapi/linux/nfs_fs.h b/include/uapi/linux/nfs_fs.h
index 7bcc8cd6831d..3afe3767c55d 100644
--- a/include/uapi/linux/nfs_fs.h
+++ b/include/uapi/linux/nfs_fs.h
@@ -56,6 +56,7 @@
 #define NFSDBG_PNFS		0x1000
 #define NFSDBG_PNFS_LD		0x2000
 #define NFSDBG_STATE		0x4000
+#define NFSDBG_XATTRCACHE	0x8000
 #define NFSDBG_ALL		0xFFFF
 
 
-- 
cgit v1.2.3


From 4a3107f61f1ce2c8ccd4dde8ae655ae3f2996f35 Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <rnayak@codeaurora.org>
Date: Tue, 14 Jul 2020 11:01:49 +0530
Subject: tty: serial: qcom-geni-serial: Drop the icc bw votes in suspend for
 console

When using the geni-serial as console, its important to be
able to hit the lowest possible power state in suspend,
even with no_console_suspend.
The only thing that prevents it today on platforms like the sc7180
is the interconnect BW votes, which we certainly don't need when
the system is in suspend. So in the suspend handler mark them as
ACTIVE_ONLY (0x3) and on resume switch them back to the ALWAYS tag (0x7)

Signed-off-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Akash Asthana <akashast@codeaurora.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1594704709-26072-1-git-send-email-rnayak@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/soc/qcom/qcom-geni-se.c       |  9 +++++++++
 drivers/tty/serial/qcom_geni_serial.c | 16 +++++++++++++++-
 include/linux/qcom-geni-se.h          |  1 +
 3 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index e2a0ba278b6b..355d503b7008 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -771,6 +771,15 @@ int geni_icc_set_bw(struct geni_se *se)
 }
 EXPORT_SYMBOL(geni_icc_set_bw);
 
+void geni_icc_set_tag(struct geni_se *se, u32 tag)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++)
+		icc_set_tag(se->icc_paths[i].path, tag);
+}
+EXPORT_SYMBOL(geni_icc_set_tag);
+
 /* To do: Replace this by icc_bulk_enable once it's implemented in ICC core */
 int geni_icc_enable(struct geni_se *se)
 {
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 583d903321b5..07b7b6b05b8b 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1505,16 +1505,30 @@ static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev)
 	struct uart_port *uport = &port->uport;
 	struct qcom_geni_private_data *private_data = uport->private_data;
 
+	/*
+	 * This is done so we can hit the lowest possible state in suspend
+	 * even with no_console_suspend
+	 */
+	if (uart_console(uport)) {
+		geni_icc_set_tag(&port->se, 0x3);
+		geni_icc_set_bw(&port->se);
+	}
 	return uart_suspend_port(private_data->drv, uport);
 }
 
 static int __maybe_unused qcom_geni_serial_sys_resume(struct device *dev)
 {
+	int ret;
 	struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
 	struct uart_port *uport = &port->uport;
 	struct qcom_geni_private_data *private_data = uport->private_data;
 
-	return uart_resume_port(private_data->drv, uport);
+	ret = uart_resume_port(private_data->drv, uport);
+	if (uart_console(uport)) {
+		geni_icc_set_tag(&port->se, 0x7);
+		geni_icc_set_bw(&port->se);
+	}
+	return ret;
 }
 
 static const struct dev_pm_ops qcom_geni_serial_pm_ops = {
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index afa511ef1457..8f385fbe5a0e 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -454,6 +454,7 @@ void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len);
 int geni_icc_get(struct geni_se *se, const char *icc_ddr);
 
 int geni_icc_set_bw(struct geni_se *se);
+void geni_icc_set_tag(struct geni_se *se, u32 tag);
 
 int geni_icc_enable(struct geni_se *se);
 
-- 
cgit v1.2.3


From b330966f79fb4fdc49183f58db113303695a750f Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 14 Jul 2020 14:45:41 +0200
Subject: fuse: reject options on reconfigure via fsconfig(2)

Previous patch changed handling of remount/reconfigure to ignore all
options, including those that are unknown to the fuse kernel fs.  This was
done for backward compatibility, but this likely only affects the old
mount(2) API.

The new fsconfig(2) based reconfiguration could possibly be improved.  This
would make the new API less of a drop in replacement for the old, OTOH this
is a good chance to get rid of some weirdnesses in the old API.

Several other behaviors might make sense:

 1) unknown options are rejected, known options are ignored

 2) unknown options are rejected, known options are rejected if the value
 is changed, allowed otherwise

 3) all options are rejected

Prior to the backward compatibility fix to ignore all options all known
options were accepted (1), even if they change the value of a mount
parameter; fuse_reconfigure() does not look at the config values set by
fuse_parse_param().

To fix that we'd need to verify that the value provided is the same as set
in the initial configuration (2).  The major drawback is that this is much
more complex than just rejecting all attempts at changing options (3);
i.e. all options signify initial configuration values and don't make sense
on reconfigure.

This patch opts for (3) with the rationale that no mount options are
reconfigurable in fuse.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/inode.c            | 16 ++++++++++------
 fs/namespace.c             |  1 +
 include/linux/fs_context.h |  1 +
 3 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index ba201bf5ffad..bba747520e9b 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -477,12 +477,16 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	struct fuse_fs_context *ctx = fc->fs_private;
 	int opt;
 
-	/*
-	 * Ignore options coming from mount(MS_REMOUNT) for backward
-	 * compatibility.
-	 */
-	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)
-		return 0;
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		/*
+		 * Ignore options coming from mount(MS_REMOUNT) for backward
+		 * compatibility.
+		 */
+		if (fc->oldapi)
+			return 0;
+
+		return invalfc(fc, "No changes allowed in reconfigure");
+	}
 
 	opt = fs_parse(fc, fuse_fs_parameters, param, &result);
 	if (opt < 0)
diff --git a/fs/namespace.c b/fs/namespace.c
index f30ed401cc6d..4a0f600a3328 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2603,6 +2603,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
 	if (IS_ERR(fc))
 		return PTR_ERR(fc);
 
+	fc->oldapi = true;
 	err = parse_monolithic_mount_data(fc, data);
 	if (!err) {
 		down_write(&sb->s_umount);
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index 5f24fcbfbfb4..37e1e8f7f08d 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -109,6 +109,7 @@ struct fs_context {
 	enum fs_context_phase	phase:8;	/* The phase the context is in */
 	bool			need_free:1;	/* Need to call ops->free() */
 	bool			global:1;	/* Goes into &init_user_ns */
+	bool			oldapi:1;	/* Coming from mount(2) */
 };
 
 struct fs_context_operations {
-- 
cgit v1.2.3


From afb0367a80553e795e7ad055299096544454f3f6 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 14 Jul 2020 14:56:25 +0200
Subject: PM: domains: Restore comment indentation for
 generic_pm_domain.child_links

The rename of generic_pm_domain.slave_links to
generic_pm_domain.child_links accidentally dropped the TAB to align the
member's comment.  Re-add the lost TAB to restore indentation.

Fixes: 8d87ae48ced2dffd ("PM: domains: Fix up terminology with parent/child")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
[ rjw: Minor subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_domain.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 574a1fadb1e5..ee11502a575b 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -96,7 +96,7 @@ struct generic_pm_domain {
 	struct dev_pm_domain domain;	/* PM domain operations */
 	struct list_head gpd_list_node;	/* Node in the global PM domains list */
 	struct list_head parent_links;	/* Links with PM domain as a parent */
-	struct list_head child_links;/* Links with PM domain as a child */
+	struct list_head child_links;	/* Links with PM domain as a child */
 	struct list_head dev_list;	/* List of devices */
 	struct dev_power_governor *gov;
 	struct work_struct power_off_work;
-- 
cgit v1.2.3


From 567f6a6eba0c09e5f502e0290e57651befa8aacb Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Tue, 14 Jul 2020 14:39:25 +0200
Subject: dma-direct: provide function to check physical memory area validity

dma_coherent_ok() checks if a physical memory area fits a device's DMA
constraints.

Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h | 1 +
 kernel/dma/direct.c        | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 5184735a0fe8..ab2e20cba951 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -69,6 +69,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 u64 dma_direct_get_required_mask(struct device *dev);
 gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 				  u64 *phys_mask);
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 95866b647581..67f060b86a73 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -70,7 +70,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
-- 
cgit v1.2.3


From 4c5e2bba30e49b970a0fd07b43e0b7a3b5fd5ea7 Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <p.yadav@ti.com>
Date: Wed, 24 Jun 2020 00:00:14 +0530
Subject: spi: spi-mem: allow specifying whether an op is DTR or not

Each phase is given a separate 'dtr' field so mixed protocols like
4S-4D-4D can be supported.

Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20200623183030.26591-2-p.yadav@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mem.c       | 3 +++
 include/linux/spi/spi-mem.h | 8 ++++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 9a86cc27fcc0..93e255287ab9 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -156,6 +156,9 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 				   op->data.dir == SPI_MEM_DATA_OUT))
 		return false;
 
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index af9ff2f0f1b2..e3dcb956bf61 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -71,9 +71,11 @@ enum spi_mem_data_dir {
  * struct spi_mem_op - describes a SPI memory operation
  * @cmd.buswidth: number of IO lines used to transmit the command
  * @cmd.opcode: operation opcode
+ * @cmd.dtr: whether the command opcode should be sent in DTR mode or not
  * @addr.nbytes: number of address bytes to send. Can be zero if the operation
  *		 does not need to send an address
  * @addr.buswidth: number of IO lines used to transmit the address cycles
+ * @addr.dtr: whether the address should be sent in DTR mode or not
  * @addr.val: address value. This value is always sent MSB first on the bus.
  *	      Note that only @addr.nbytes are taken into account in this
  *	      address value, so users should make sure the value fits in the
@@ -81,7 +83,9 @@ enum spi_mem_data_dir {
  * @dummy.nbytes: number of dummy bytes to send after an opcode or address. Can
  *		  be zero if the operation does not require dummy bytes
  * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes
+ * @dummy.dtr: whether the dummy bytes should be sent in DTR mode or not
  * @data.buswidth: number of IO lanes used to send/receive the data
+ * @data.dtr: whether the data should be sent in DTR mode or not
  * @data.dir: direction of the transfer
  * @data.nbytes: number of data bytes to send/receive. Can be zero if the
  *		 operation does not involve transferring data
@@ -91,22 +95,26 @@ enum spi_mem_data_dir {
 struct spi_mem_op {
 	struct {
 		u8 buswidth;
+		u8 dtr : 1;
 		u8 opcode;
 	} cmd;
 
 	struct {
 		u8 nbytes;
 		u8 buswidth;
+		u8 dtr : 1;
 		u64 val;
 	} addr;
 
 	struct {
 		u8 nbytes;
 		u8 buswidth;
+		u8 dtr : 1;
 	} dummy;
 
 	struct {
 		u8 buswidth;
+		u8 dtr : 1;
 		enum spi_mem_data_dir dir;
 		unsigned int nbytes;
 		union {
-- 
cgit v1.2.3


From caf72df48be32c39f74287976ae843501ae06949 Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <p.yadav@ti.com>
Date: Wed, 24 Jun 2020 00:00:15 +0530
Subject: spi: spi-mem: allow specifying a command's extension

In xSPI mode, flashes expect 2-byte opcodes. The second byte is called
the "command extension". There can be 3 types of extensions in xSPI:
repeat, invert, and hex. When the extension type is "repeat", the same
opcode is sent twice. When it is "invert", the second byte is the
inverse of the opcode. When it is "hex" an additional opcode byte based
is sent with the command whose value can be anything.

So, make opcode a 16-bit value and add a 'nbytes', similar to how
multiple address widths are handled.

Some places use sizeof(op->cmd.opcode). Replace them with op->cmd.nbytes

The spi-mxic and spi-zynq-qspi drivers directly use op->cmd.opcode as a
buffer. Now that opcode is a 2-byte field, this can result in different
behaviour depending on if the machine is little endian or big endian.
Extract the opcode in a local 1-byte variable and use that as the buffer
instead. Both these drivers would reject multi-byte opcodes in their
supports_op() hook anyway, so we only need to worry about single-byte
opcodes for now.

The above two changes are put in this commit to keep the series
bisectable.

Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20200623183030.26591-3-p.yadav@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mem.c       | 13 +++++++------
 drivers/spi/spi-mtk-nor.c   |  4 ++--
 drivers/spi/spi-mxic.c      |  3 ++-
 drivers/spi/spi-zynq-qspi.c | 11 ++++++-----
 include/linux/spi/spi-mem.h |  6 +++++-
 5 files changed, 22 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 93e255287ab9..ef53290b7d24 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -159,6 +159,9 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
 		return false;
 
+	if (op->cmd.nbytes != 1)
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
@@ -173,7 +176,7 @@ static bool spi_mem_buswidth_is_valid(u8 buswidth)
 
 static int spi_mem_check_op(const struct spi_mem_op *op)
 {
-	if (!op->cmd.buswidth)
+	if (!op->cmd.buswidth || !op->cmd.nbytes)
 		return -EINVAL;
 
 	if ((op->addr.nbytes && !op->addr.buswidth) ||
@@ -309,8 +312,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 			return ret;
 	}
 
-	tmpbufsize = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		     op->dummy.nbytes;
+	tmpbufsize = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 	/*
 	 * Allocate a buffer to transmit the CMD, ADDR cycles with kmalloc() so
@@ -325,7 +327,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 	tmpbuf[0] = op->cmd.opcode;
 	xfers[xferpos].tx_buf = tmpbuf;
-	xfers[xferpos].len = sizeof(op->cmd.opcode);
+	xfers[xferpos].len = op->cmd.nbytes;
 	xfers[xferpos].tx_nbits = op->cmd.buswidth;
 	spi_message_add_tail(&xfers[xferpos], &msg);
 	xferpos++;
@@ -427,8 +429,7 @@ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 		return ctlr->mem_ops->adjust_op_size(mem, op);
 
 	if (!ctlr->mem_ops || !ctlr->mem_ops->exec_op) {
-		len = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		      op->dummy.nbytes;
+		len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 		if (len > spi_max_transfer_size(mem->spi))
 			return -EINVAL;
diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c
index 7bc302b50396..d5f393871619 100644
--- a/drivers/spi/spi-mtk-nor.c
+++ b/drivers/spi/spi-mtk-nor.c
@@ -195,7 +195,7 @@ static int mtk_nor_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 		}
 	}
 
-	len = MTK_NOR_PRG_MAX_SIZE - sizeof(op->cmd.opcode) - op->addr.nbytes -
+	len = MTK_NOR_PRG_MAX_SIZE - op->cmd.nbytes - op->addr.nbytes -
 	      op->dummy.nbytes;
 	if (op->data.nbytes > len)
 		op->data.nbytes = len;
@@ -219,7 +219,7 @@ static bool mtk_nor_supports_op(struct spi_mem *mem,
 			       (op->dummy.buswidth == 0) &&
 			       (op->data.buswidth == 1);
 	}
-	len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 	if ((len > MTK_NOR_PRG_MAX_SIZE) ||
 	    ((op->data.nbytes) && (len == MTK_NOR_PRG_MAX_SIZE)))
 		return false;
diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c
index 69491f3a515d..8c630acb0110 100644
--- a/drivers/spi/spi-mxic.c
+++ b/drivers/spi/spi-mxic.c
@@ -356,6 +356,7 @@ static int mxic_spi_mem_exec_op(struct spi_mem *mem,
 	int nio = 1, i, ret;
 	u32 ss_ctrl;
 	u8 addr[8];
+	u8 opcode = op->cmd.opcode;
 
 	ret = mxic_spi_set_freq(mxic, mem->spi->max_speed_hz);
 	if (ret)
@@ -393,7 +394,7 @@ static int mxic_spi_mem_exec_op(struct spi_mem *mem,
 	writel(readl(mxic->regs + HC_CFG) | HC_CFG_MAN_CS_ASSERT,
 	       mxic->regs + HC_CFG);
 
-	ret = mxic_spi_data_xfer(mxic, &op->cmd.opcode, NULL, 1);
+	ret = mxic_spi_data_xfer(mxic, &opcode, NULL, 1);
 	if (ret)
 		goto out;
 
diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
index 17641157354d..bbf3d90561f5 100644
--- a/drivers/spi/spi-zynq-qspi.c
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -527,20 +527,21 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem,
 	struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master);
 	int err = 0, i;
 	u8 *tmpbuf;
+	u8 opcode = op->cmd.opcode;
 
 	dev_dbg(xqspi->dev, "cmd:%#x mode:%d.%d.%d.%d\n",
-		op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth,
+		opcode, op->cmd.buswidth, op->addr.buswidth,
 		op->dummy.buswidth, op->data.buswidth);
 
 	zynq_qspi_chipselect(mem->spi, true);
 	zynq_qspi_config_op(xqspi, mem->spi);
 
-	if (op->cmd.opcode) {
+	if (op->cmd.nbytes) {
 		reinit_completion(&xqspi->data_completion);
-		xqspi->txbuf = (u8 *)&op->cmd.opcode;
+		xqspi->txbuf = &opcode;
 		xqspi->rxbuf = NULL;
-		xqspi->tx_bytes = sizeof(op->cmd.opcode);
-		xqspi->rx_bytes = sizeof(op->cmd.opcode);
+		xqspi->tx_bytes = op->cmd.nbytes;
+		xqspi->rx_bytes = op->cmd.nbytes;
 		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
 		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
 				ZYNQ_QSPI_IXR_RXTX_MASK);
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index e3dcb956bf61..159463cc659c 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -17,6 +17,7 @@
 	{							\
 		.buswidth = __buswidth,				\
 		.opcode = __opcode,				\
+		.nbytes = 1,					\
 	}
 
 #define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth)		\
@@ -69,6 +70,8 @@ enum spi_mem_data_dir {
 
 /**
  * struct spi_mem_op - describes a SPI memory operation
+ * @cmd.nbytes: number of opcode bytes (only 1 or 2 are valid). The opcode is
+ *		sent MSB-first.
  * @cmd.buswidth: number of IO lines used to transmit the command
  * @cmd.opcode: operation opcode
  * @cmd.dtr: whether the command opcode should be sent in DTR mode or not
@@ -94,9 +97,10 @@ enum spi_mem_data_dir {
  */
 struct spi_mem_op {
 	struct {
+		u8 nbytes;
 		u8 buswidth;
 		u8 dtr : 1;
-		u8 opcode;
+		u16 opcode;
 	} cmd;
 
 	struct {
-- 
cgit v1.2.3


From 079ef53673f2e3b3ee1728800311f20f28eed4f7 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 14 Jul 2020 12:25:33 +0200
Subject: bpf: Fix build for disabled CONFIG_DEBUG_INFO_BTF option

Stephen reported following linker warnings on powerpc build:

  ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids'
  ld: warning: orphan section `.BTF_ids' from `kernel/bpf/btf.o' being placed in section `.BTF_ids'
  ld: warning: orphan section `.BTF_ids' from `kernel/bpf/stackmap.o' being placed in section `.BTF_ids'
  ld: warning: orphan section `.BTF_ids' from `net/core/filter.o' being placed in section `.BTF_ids'
  ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids'

It's because we generated .BTF_ids section even when
CONFIG_DEBUG_INFO_BTF is not enabled. Fixing this by
generating empty btf_id arrays for this case.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/bpf/20200714102534.299280-1-jolsa@kernel.org
---
 include/linux/btf_ids.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index fe019774f8a7..b3c73db9587c 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -3,6 +3,8 @@
 #ifndef _LINUX_BTF_IDS_H
 #define _LINUX_BTF_IDS_H
 
+#ifdef CONFIG_DEBUG_INFO_BTF
+
 #include <linux/compiler.h> /* for __PASTE */
 
 /*
@@ -83,5 +85,12 @@ asm(							\
 ".zero 4                                       \n"	\
 ".popsection;                                  \n");
 
+#else
+
+#define BTF_ID_LIST(name) static u32 name[5];
+#define BTF_ID(prefix, name)
+#define BTF_ID_UNUSED
+
+#endif /* CONFIG_DEBUG_INFO_BTF */
 
 #endif
-- 
cgit v1.2.3


From 11bb2f7a45909f4f64afe471875672ae1b84a380 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 14 Jul 2020 12:25:34 +0200
Subject: bpf: Fix cross build for CONFIG_DEBUG_INFO_BTF option

Stephen and 0-DAY CI Kernel Test Service reported broken cross build
for arm (arm-linux-gnueabi-gcc (GCC) 9.3.0), with following output:

   /tmp/ccMS5uth.s: Assembler messages:
   /tmp/ccMS5uth.s:69: Error: unrecognized symbol type ""
   /tmp/ccMS5uth.s:82: Error: unrecognized symbol type ""

Having '@object' for .type  diretive is  wrong because '@' is comment
character for some architectures. Using STT_OBJECT instead that should
work everywhere.

Also using HOST* variables to build resolve_btfids so it's properly
build in crossbuilds (stolen from objtool's Makefile).

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/bpf/20200714102534.299280-2-jolsa@kernel.org
---
 include/linux/btf_ids.h           |  2 +-
 tools/bpf/resolve_btfids/Makefile | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index b3c73db9587c..1cdb56950ffe 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -23,7 +23,7 @@
 asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
 ".local " #symbol " ;                          \n"	\
-".type  " #symbol ", @object;                  \n"	\
+".type  " #symbol ", STT_OBJECT;               \n"	\
 ".size  " #symbol ", 4;                        \n"	\
 #symbol ":                                     \n"	\
 ".zero 4                                       \n"	\
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 948378ca73d4..a88cd4426398 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -16,6 +16,20 @@ else
   MAKEFLAGS=--no-print-directory
 endif
 
+# always use the host compiler
+ifneq ($(LLVM),)
+HOSTAR  ?= llvm-ar
+HOSTCC  ?= clang
+HOSTLD  ?= ld.lld
+else
+HOSTAR  ?= ar
+HOSTCC  ?= gcc
+HOSTLD  ?= ld
+endif
+AR       = $(HOSTAR)
+CC       = $(HOSTCC)
+LD       = $(HOSTLD)
+
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
 
 LIBBPF_SRC := $(srctree)/tools/lib/bpf/
-- 
cgit v1.2.3


From 59679d9933ab897d197297eaf37e5b3788c052a5 Mon Sep 17 00:00:00 2001
From: He Zhe <zhe.he@windriver.com>
Date: Mon, 6 Jul 2020 17:52:24 +0800
Subject: freezer: Add unsafe version of
 freezable_schedule_timeout_interruptible() for NFS

commit 0688e64bc600 ("NFS: Allow signal interruption of
NFS4ERR_DELAYed operations") introduces nfs4_delay_interruptible
which also needs an _unsafe version to avoid the following call
trace for the same reason explained in commit 416ad3c9c006 ("freezer:
add unsafe versions of freezable helpers for NFS")

CPU: 4 PID: 3968 Comm: rm Tainted: G W 5.8.0-rc4 #1
Hardware name: Marvell OcteonTX CN96XX board (DT)
Call trace:
dump_backtrace+0x0/0x1dc
show_stack+0x20/0x30
dump_stack+0xdc/0x150
debug_check_no_locks_held+0x98/0xa0
nfs4_delay_interruptible+0xd8/0x120
nfs4_handle_exception+0x130/0x170
nfs4_proc_rmdir+0x8c/0x220
nfs_rmdir+0xa4/0x360
vfs_rmdir.part.0+0x6c/0x1b0
do_rmdir+0x18c/0x210
__arm64_sys_unlinkat+0x64/0x7c
el0_svc_common.constprop.0+0x7c/0x110
do_el0_svc+0x24/0xa0
el0_sync_handler+0x13c/0x1b8
el0_sync+0x158/0x180

Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 fs/nfs/nfs4proc.c       |  2 +-
 include/linux/freezer.h | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e32717fd1169..15ecfa474e37 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -414,7 +414,7 @@ static int nfs4_delay_interruptible(long *timeout)
 {
 	might_sleep();
 
-	freezable_schedule_timeout_interruptible(nfs4_update_delay(timeout));
+	freezable_schedule_timeout_interruptible_unsafe(nfs4_update_delay(timeout));
 	if (!signal_pending(current))
 		return 0;
 	return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 21f5aa0b217f..27828145ca09 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -207,6 +207,17 @@ static inline long freezable_schedule_timeout_interruptible(long timeout)
 	return __retval;
 }
 
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout)
+{
+	long __retval;
+
+	freezer_do_not_count();
+	__retval = schedule_timeout_interruptible(timeout);
+	freezer_count_unsafe();
+	return __retval;
+}
+
 /* Like schedule_timeout_killable(), but should not block the freezer. */
 static inline long freezable_schedule_timeout_killable(long timeout)
 {
@@ -285,6 +296,9 @@ static inline void set_freezable(void) {}
 #define freezable_schedule_timeout_interruptible(timeout)		\
 	schedule_timeout_interruptible(timeout)
 
+#define freezable_schedule_timeout_interruptible_unsafe(timeout)	\
+	schedule_timeout_interruptible(timeout)
+
 #define freezable_schedule_timeout_killable(timeout)			\
 	schedule_timeout_killable(timeout)
 
-- 
cgit v1.2.3


From 43364ef1a12a4236b7956b076649ddd080764cd1 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Tue, 14 Jul 2020 09:34:49 +0200
Subject: bridge: mrp: Extend bridge interface

This patch adds a new flag(BR_MRP_LOST_IN_CONT) to the net bridge
ports. This bit will be set when the port lost the continuity of
MRP_InTest frames.

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index b3a8d3054af0..6479a38e52fa 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -49,6 +49,7 @@ struct br_ip_list {
 #define BR_ISOLATED		BIT(16)
 #define BR_MRP_AWARE		BIT(17)
 #define BR_MRP_LOST_CONT	BIT(18)
+#define BR_MRP_LOST_IN_CONT	BIT(19)
 
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
-- 
cgit v1.2.3


From 7cf97b12545503992020796c74bd84078eb39299 Mon Sep 17 00:00:00 2001
From: Sargun Dhillon <sargun@sargun.me>
Date: Tue, 2 Jun 2020 18:10:43 -0700
Subject: seccomp: Introduce addfd ioctl to seccomp user notifier

The current SECCOMP_RET_USER_NOTIF API allows for syscall supervision over
an fd. It is often used in settings where a supervising task emulates
syscalls on behalf of a supervised task in userspace, either to further
restrict the supervisee's syscall abilities or to circumvent kernel
enforced restrictions the supervisor deems safe to lift (e.g. actually
performing a mount(2) for an unprivileged container).

While SECCOMP_RET_USER_NOTIF allows for the interception of any syscall,
only a certain subset of syscalls could be correctly emulated. Over the
last few development cycles, the set of syscalls which can't be emulated
has been reduced due to the addition of pidfd_getfd(2). With this we are
now able to, for example, intercept syscalls that require the supervisor
to operate on file descriptors of the supervisee such as connect(2).

However, syscalls that cause new file descriptors to be installed can not
currently be correctly emulated since there is no way for the supervisor
to inject file descriptors into the supervisee. This patch adds a
new addfd ioctl to remove this restriction by allowing the supervisor to
install file descriptors into the intercepted task. By implementing this
feature via seccomp the supervisor effectively instructs the supervisee
to install a set of file descriptors into its own file descriptor table
during the intercepted syscall. This way it is possible to intercept
syscalls such as open() or accept(), and install (or replace, like
dup2(2)) the supervisor's resulting fd into the supervisee. One
replacement use-case would be to redirect the stdout and stderr of a
supervisee into log file descriptors opened by the supervisor.

The ioctl handling is based on the discussions[1] of how Extensible
Arguments should interact with ioctls. Instead of building size into
the addfd structure, make it a function of the ioctl command (which
is how sizes are normally passed to ioctls). To support forward and
backward compatibility, just mask out the direction and size, and match
everything. The size (and any future direction) checks are done along
with copy_struct_from_user() logic.

As a note, the seccomp_notif_addfd structure is laid out based on 8-byte
alignment without requiring packing as there have been packing issues
with uapi highlighted before[2][3]. Although we could overload the
newfd field and use -1 to indicate that it is not to be used, doing
so requires changing the size of the fd field, and introduces struct
packing complexity.

[1]: https://lore.kernel.org/lkml/87o8w9bcaf.fsf@mid.deneb.enyo.de/
[2]: https://lore.kernel.org/lkml/a328b91d-fd8f-4f27-b3c2-91a9c45f18c0@rasmusvillemoes.dk/
[3]: https://lore.kernel.org/lkml/20200612104629.GA15814@ircssh-2.c.rugged-nimbus-611.internal

Cc: Christoph Hellwig <hch@lst.de>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: Jann Horn <jannh@google.com>
Cc: Robert Sesek <rsesek@google.com>
Cc: Chris Palmer <palmer@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Suggested-by: Matt Denton <mpdenton@google.com>
Link: https://lore.kernel.org/r/20200603011044.7972-4-sargun@sargun.me
Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Reviewed-by: Will Drewry <wad@chromium.org>
Co-developed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/seccomp.h      |   4 +
 include/uapi/linux/seccomp.h |  22 ++++++
 kernel/seccomp.c             | 175 ++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 199 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index babcd6c02d09..881c90b6aa25 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -10,6 +10,10 @@
 					 SECCOMP_FILTER_FLAG_NEW_LISTENER | \
 					 SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
 
+/* sizeof() the first published struct seccomp_notif_addfd */
+#define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24
+#define SECCOMP_NOTIFY_ADDFD_SIZE_LATEST SECCOMP_NOTIFY_ADDFD_SIZE_VER0
+
 #ifdef CONFIG_SECCOMP
 
 #include <linux/thread_info.h>
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 965290f7dcc2..6ba18b82a02e 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -113,6 +113,25 @@ struct seccomp_notif_resp {
 	__u32 flags;
 };
 
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
+
+/**
+ * struct seccomp_notif_addfd
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: The O_* flags the remote FD should have applied
+ */
+struct seccomp_notif_addfd {
+	__u64 id;
+	__u32 flags;
+	__u32 srcfd;
+	__u32 newfd;
+	__u32 newfd_flags;
+};
+
 #define SECCOMP_IOC_MAGIC		'!'
 #define SECCOMP_IO(nr)			_IO(SECCOMP_IOC_MAGIC, nr)
 #define SECCOMP_IOR(nr, type)		_IOR(SECCOMP_IOC_MAGIC, nr, type)
@@ -124,5 +143,8 @@ struct seccomp_notif_resp {
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
 #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3, \
+						struct seccomp_notif_addfd)
 
 #endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 866a432cd746..3ee59ce0a323 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -87,10 +87,42 @@ struct seccomp_knotif {
 	long val;
 	u32 flags;
 
-	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
+	/*
+	 * Signals when this has changed states, such as the listener
+	 * dying, a new seccomp addfd message, or changing to REPLIED
+	 */
 	struct completion ready;
 
 	struct list_head list;
+
+	/* outstanding addfd requests */
+	struct list_head addfd;
+};
+
+/**
+ * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages
+ *
+ * @file: A reference to the file to install in the other task
+ * @fd: The fd number to install it at. If the fd number is -1, it means the
+ *      installing process should allocate the fd as normal.
+ * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
+ *         is allowed.
+ * @ret: The return value of the installing process. It is set to the fd num
+ *       upon success (>= 0).
+ * @completion: Indicates that the installing process has completed fd
+ *              installation, or gone away (either due to successful
+ *              reply, or signal)
+ *
+ */
+struct seccomp_kaddfd {
+	struct file *file;
+	int fd;
+	unsigned int flags;
+
+	/* To only be set on reply */
+	int ret;
+	struct completion completion;
+	struct list_head list;
 };
 
 /**
@@ -793,6 +825,17 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }
 
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+{
+	/*
+	 * Remove the notification, and reset the list pointers, indicating
+	 * that it has been handled.
+	 */
+	list_del_init(&addfd->list);
+	addfd->ret = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
+	complete(&addfd->completion);
+}
+
 static int seccomp_do_user_notification(int this_syscall,
 					struct seccomp_filter *match,
 					const struct seccomp_data *sd)
@@ -801,6 +844,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	u32 flags = 0;
 	long ret = 0;
 	struct seccomp_knotif n = {};
+	struct seccomp_kaddfd *addfd, *tmp;
 
 	mutex_lock(&match->notify_lock);
 	err = -ENOSYS;
@@ -813,6 +857,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	n.id = seccomp_next_notify_id(match);
 	init_completion(&n.ready);
 	list_add(&n.list, &match->notif->notifications);
+	INIT_LIST_HEAD(&n.addfd);
 
 	up(&match->notif->request);
 	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
@@ -821,17 +866,34 @@ static int seccomp_do_user_notification(int this_syscall,
 	/*
 	 * This is where we wait for a reply from userspace.
 	 */
+wait:
 	err = wait_for_completion_interruptible(&n.ready);
 	mutex_lock(&match->notify_lock);
 	if (err == 0) {
+		/* Check if we were woken up by a addfd message */
+		addfd = list_first_entry_or_null(&n.addfd,
+						 struct seccomp_kaddfd, list);
+		if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) {
+			seccomp_handle_addfd(addfd);
+			mutex_unlock(&match->notify_lock);
+			goto wait;
+		}
 		ret = n.val;
 		err = n.error;
 		flags = n.flags;
 	}
 
+	/* If there were any pending addfd calls, clear them out */
+	list_for_each_entry_safe(addfd, tmp, &n.addfd, list) {
+		/* The process went away before we got a chance to handle it */
+		addfd->ret = -ESRCH;
+		list_del_init(&addfd->list);
+		complete(&addfd->completion);
+	}
+
 	/*
 	 * Note that it's possible the listener died in between the time when
-	 * we were notified of a respons (or a signal) and when we were able to
+	 * we were notified of a response (or a signal) and when we were able to
 	 * re-acquire the lock, so only delete from the list if the
 	 * notification actually exists.
 	 *
@@ -1069,6 +1131,11 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		knotif->error = -ENOSYS;
 		knotif->val = 0;
 
+		/*
+		 * We do not need to wake up any pending addfd messages, as
+		 * the notifier will do that for us, as this just looks
+		 * like a standard reply.
+		 */
 		complete(&knotif->ready);
 	}
 
@@ -1233,12 +1300,109 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 	return ret;
 }
 
+static long seccomp_notify_addfd(struct seccomp_filter *filter,
+				 struct seccomp_notif_addfd __user *uaddfd,
+				 unsigned int size)
+{
+	struct seccomp_notif_addfd addfd;
+	struct seccomp_knotif *knotif;
+	struct seccomp_kaddfd kaddfd;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0);
+	BUILD_BUG_ON(sizeof(addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST);
+
+	if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE)
+		return -EINVAL;
+
+	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+	if (ret)
+		return ret;
+
+	if (addfd.newfd_flags & ~O_CLOEXEC)
+		return -EINVAL;
+
+	if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+		return -EINVAL;
+
+	if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
+		return -EINVAL;
+
+	kaddfd.file = fget(addfd.srcfd);
+	if (!kaddfd.file)
+		return -EBADF;
+
+	kaddfd.flags = addfd.newfd_flags;
+	kaddfd.fd = (addfd.flags & SECCOMP_ADDFD_FLAG_SETFD) ?
+		    addfd.newfd : -1;
+	init_completion(&kaddfd.completion);
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		goto out;
+
+	knotif = find_notification(filter, addfd.id);
+	if (!knotif) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	/*
+	 * We do not want to allow for FD injection to occur before the
+	 * notification has been picked up by a userspace handler, or after
+	 * the notification has been replied to.
+	 */
+	if (knotif->state != SECCOMP_NOTIFY_SENT) {
+		ret = -EINPROGRESS;
+		goto out_unlock;
+	}
+
+	list_add(&kaddfd.list, &knotif->addfd);
+	complete(&knotif->ready);
+	mutex_unlock(&filter->notify_lock);
+
+	/* Now we wait for it to be processed or be interrupted */
+	ret = wait_for_completion_interruptible(&kaddfd.completion);
+	if (ret == 0) {
+		/*
+		 * We had a successful completion. The other side has already
+		 * removed us from the addfd queue, and
+		 * wait_for_completion_interruptible has a memory barrier upon
+		 * success that lets us read this value directly without
+		 * locking.
+		 */
+		ret = kaddfd.ret;
+		goto out;
+	}
+
+	mutex_lock(&filter->notify_lock);
+	/*
+	 * Even though we were woken up by a signal and not a successful
+	 * completion, a completion may have happened in the mean time.
+	 *
+	 * We need to check again if the addfd request has been handled,
+	 * and if not, we will remove it from the queue.
+	 */
+	if (list_empty(&kaddfd.list))
+		ret = kaddfd.ret;
+	else
+		list_del(&kaddfd.list);
+
+out_unlock:
+	mutex_unlock(&filter->notify_lock);
+out:
+	fput(kaddfd.file);
+
+	return ret;
+}
+
 static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 				 unsigned long arg)
 {
 	struct seccomp_filter *filter = file->private_data;
 	void __user *buf = (void __user *)arg;
 
+	/* Fixed-size ioctls */
 	switch (cmd) {
 	case SECCOMP_IOCTL_NOTIF_RECV:
 		return seccomp_notify_recv(filter, buf);
@@ -1247,6 +1411,13 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
+	}
+
+	/* Extensible Argument ioctls */
+#define EA_IOCTL(cmd)	((cmd) & ~(IOC_INOUT | IOCSIZE_MASK))
+	switch (EA_IOCTL(cmd)) {
+	case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD):
+		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 4550569bd779f25398503ad5556f8dc7c1f216c2 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 1 Jul 2020 02:43:53 +0800
Subject: soundwire: stream: add helper to startup/shutdown streams

To handle streams at the dailink level, expose two helpers that will
be called from machine drivers.

Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200630184356.24939-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/driver-api/soundwire/stream.rst | 11 ++-
 drivers/soundwire/stream.c                    | 98 +++++++++++++++++++++++++++
 include/linux/soundwire/sdw.h                 |  2 +
 3 files changed, 110 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/soundwire/stream.rst b/Documentation/driver-api/soundwire/stream.rst
index 1b386076402c..8858cea7bfe0 100644
--- a/Documentation/driver-api/soundwire/stream.rst
+++ b/Documentation/driver-api/soundwire/stream.rst
@@ -293,6 +293,10 @@ per stream. From ASoC DPCM framework, this stream state maybe linked to
 
   int sdw_alloc_stream(char * stream_name);
 
+The SoundWire core provides a sdw_startup_stream() helper function,
+typically called during a dailink .startup() callback, which performs
+stream allocation and sets the stream pointer for all DAIs
+connected to a stream.
 
 SDW_STREAM_CONFIGURED
 ~~~~~~~~~~~~~~~~~~~~~
@@ -509,7 +513,12 @@ In .shutdown() the data structure maintaining stream state are freed up.
 
   void sdw_release_stream(struct sdw_stream_runtime * stream);
 
-Not Supported
+The SoundWire core provides a sdw_shutdown_stream() helper function,
+typically called during a dailink .shutdown() callback, which clears
+the stream pointer for all DAIS connected to a stream and releases the
+memory allocated for the stream.
+
+  Not Supported
 =============
 
 1. A single port with multiple channels supported cannot be used between two
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index a9a72574b34a..6bc2ff29c202 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
+#include <sound/soc.h>
 #include "bus.h"
 
 /*
@@ -1826,3 +1827,100 @@ state_err:
 	return ret;
 }
 EXPORT_SYMBOL(sdw_deprepare_stream);
+
+static int set_stream(struct snd_pcm_substream *substream,
+		      struct sdw_stream_runtime *sdw_stream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *dai;
+	int ret = 0;
+	int i;
+
+	/* Set stream pointer on all DAIs */
+	for_each_rtd_dais(rtd, i, dai) {
+		ret = snd_soc_dai_set_sdw_stream(dai, sdw_stream, substream->stream);
+		if (ret < 0) {
+			dev_err(rtd->dev, "failed to set stream pointer on dai %s", dai->name);
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_startup_stream() - Startup SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
+ */
+int sdw_startup_stream(void *sdw_substream)
+{
+	struct snd_pcm_substream *substream = sdw_substream;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct sdw_stream_runtime *sdw_stream;
+	char *name;
+	int ret;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		name = kasprintf(GFP_KERNEL, "%s-Playback", substream->name);
+	else
+		name = kasprintf(GFP_KERNEL, "%s-Capture", substream->name);
+
+	if (!name)
+		return -ENOMEM;
+
+	sdw_stream = sdw_alloc_stream(name);
+	if (!sdw_stream) {
+		dev_err(rtd->dev, "alloc stream failed for substream DAI %s", substream->name);
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = set_stream(substream, sdw_stream);
+	if (ret < 0)
+		goto release_stream;
+	return 0;
+
+release_stream:
+	sdw_release_stream(sdw_stream);
+	set_stream(substream, NULL);
+error:
+	kfree(name);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_startup_stream);
+
+/**
+ * sdw_shutdown_stream() - Shutdown SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
+ */
+void sdw_shutdown_stream(void *sdw_substream)
+{
+	struct snd_pcm_substream *substream = sdw_substream;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct sdw_stream_runtime *sdw_stream;
+	struct snd_soc_dai *dai;
+
+	/* Find stream from first CPU DAI */
+	dai = asoc_rtd_to_cpu(rtd, 0);
+
+	sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream);
+
+	if (!sdw_stream) {
+		dev_err(rtd->dev, "no stream found for DAI %s", dai->name);
+		return;
+	}
+
+	/* release memory */
+	kfree(sdw_stream->name);
+	sdw_release_stream(sdw_stream);
+
+	/* clear DAI data */
+	set_stream(substream, NULL);
+}
+EXPORT_SYMBOL(sdw_shutdown_stream);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 64c9314cb903..4057adf7f049 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -955,10 +955,12 @@ int sdw_stream_remove_master(struct sdw_bus *bus,
 		struct sdw_stream_runtime *stream);
 int sdw_stream_remove_slave(struct sdw_slave *slave,
 		struct sdw_stream_runtime *stream);
+int sdw_startup_stream(void *sdw_substream);
 int sdw_prepare_stream(struct sdw_stream_runtime *stream);
 int sdw_enable_stream(struct sdw_stream_runtime *stream);
 int sdw_disable_stream(struct sdw_stream_runtime *stream);
 int sdw_deprepare_stream(struct sdw_stream_runtime *stream);
+void sdw_shutdown_stream(void *sdw_substream);
 int sdw_bus_prep_clk_stop(struct sdw_bus *bus);
 int sdw_bus_clk_stop(struct sdw_bus *bus);
 int sdw_bus_exit_clk_stop(struct sdw_bus *bus);
-- 
cgit v1.2.3


From 58eeba0bdb52afe5c18ce2a760ca9fe2901943e9 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Tue, 14 Jul 2020 15:01:53 +0300
Subject: lib/string_helpers: Introduce string_upper() and string_lower()
 helpers

Provide the helpers for string conversions to upper and lower cases.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/string_helpers.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index c28955132234..86f150c2a6b6 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_STRING_HELPERS_H_
 #define _LINUX_STRING_HELPERS_H_
 
+#include <linux/ctype.h>
 #include <linux/types.h>
 
 struct file;
@@ -75,6 +76,20 @@ static inline int string_escape_str_any_np(const char *src, char *dst,
 	return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, only);
 }
 
+static inline void string_upper(char *dst, const char *src)
+{
+	do {
+		*dst++ = toupper(*src);
+	} while (*src++);
+}
+
+static inline void string_lower(char *dst, const char *src)
+{
+	do {
+		*dst++ = tolower(*src);
+	} while (*src++);
+}
+
 char *kstrdup_quotable(const char *src, gfp_t gfp);
 char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp);
 char *kstrdup_quotable_file(struct file *file, gfp_t gfp);
-- 
cgit v1.2.3


From 13e52e63a4462e2bd0ef249fb535a599ea158725 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Tue, 14 Jul 2020 15:01:58 +0300
Subject: platform_data/mlxreg: Add support for complex attributes

Add new field 'regnum' to the structure 'mlxreg_core_data' to specify
the number of registers occupied by multi-register attribute.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/platform_data/mlxreg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index b8da8aef2446..a2adc3ad45f2 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -80,6 +80,7 @@ struct mlxreg_hotplug_device {
  * @hpdev - hotplug device data;
  * @health_cntr: dynamic device health indication counter;
  * @attached: true if device has been attached after good health indication;
+ * @regnum: number of registers occupied by multi-register attribute;
  */
 struct mlxreg_core_data {
 	char label[MLXREG_CORE_LABEL_MAX_SIZE];
@@ -92,6 +93,7 @@ struct mlxreg_core_data {
 	struct mlxreg_hotplug_device hpdev;
 	u8 health_cntr;
 	bool attached;
+	u8 regnum;
 };
 
 /**
-- 
cgit v1.2.3


From 17727a3b4879324818ea6f2ebc3f68432173ce24 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Tue, 14 Jul 2020 15:02:02 +0300
Subject: platform_data/mlxreg: Add presence register field for FAN devices

Add new field 'reg_prsnt' to the structure 'mlxreg_core_data' to
provide the number FAN drawers equpped within the system. The purpose
is to allow mapping between FAN drawers and FAN rotors (tachometer),
since FAN drawer can be eqipped with a few rotors.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/platform_data/mlxreg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index a2adc3ad45f2..9cffa9a64ab3 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -75,6 +75,7 @@ struct mlxreg_hotplug_device {
  * @mask: attribute access mask;
  * @bit: attribute effective bit;
  * @capability: attribute capability register;
+ * @reg_prsnt: attribute presence register;
  * @mode: access mode;
  * @np - pointer to node platform associated with attribute;
  * @hpdev - hotplug device data;
@@ -88,6 +89,7 @@ struct mlxreg_core_data {
 	u32 mask;
 	u32 bit;
 	u32 capability;
+	u32 reg_prsnt;
 	umode_t	mode;
 	struct device_node *np;
 	struct mlxreg_hotplug_device hpdev;
-- 
cgit v1.2.3


From a8209dd42a60dca0fd15bc73d19fc4009e704c17 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 15 Jul 2020 05:37:43 +0800
Subject: soundwire: sdw.h: fix PRBS/Static_1 swapped definitions

Table 110 "Port Data Modes" of the SoundWire 1.2 specification lists
PRBS as b01 and Static_1 as b11. The existing headers swapped the two
values, fix.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200714213744.24674-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 4057adf7f049..6452bac957b3 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -152,19 +152,19 @@ enum sdw_data_direction {
  *
  * @SDW_PORT_DATA_MODE_NORMAL: Normal data mode where audio data is received
  * and transmitted.
+ * @SDW_PORT_DATA_MODE_PRBS: Test mode which uses a PRBS generator to produce
+ * a pseudo random data pattern that is transferred
+ * @SDW_PORT_DATA_MODE_STATIC_0: Simple test mode which uses static value of
+ * logic 0. The encoding will result in no signal transitions
  * @SDW_PORT_DATA_MODE_STATIC_1: Simple test mode which uses static value of
  * logic 1. The encoding will result in signal transitions at every bitslot
  * owned by this Port
- * @SDW_PORT_DATA_MODE_STATIC_0: Simple test mode which uses static value of
- * logic 0. The encoding will result in no signal transitions
- * @SDW_PORT_DATA_MODE_PRBS: Test mode which uses a PRBS generator to produce
- * a pseudo random data pattern that is transferred
  */
 enum sdw_port_data_mode {
 	SDW_PORT_DATA_MODE_NORMAL = 0,
-	SDW_PORT_DATA_MODE_STATIC_1 = 1,
+	SDW_PORT_DATA_MODE_PRBS = 1,
 	SDW_PORT_DATA_MODE_STATIC_0 = 2,
-	SDW_PORT_DATA_MODE_PRBS = 3,
+	SDW_PORT_DATA_MODE_STATIC_1 = 3,
 };
 
 /*
-- 
cgit v1.2.3


From 9256686898881b0694fe6af2c3283b69677838de Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 15 Jul 2020 05:37:44 +0800
Subject: soundwire: sdw.h: fix indentation

Not sure how this went undetected for years.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200714213744.24674-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 6452bac957b3..76052f12c9f7 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -88,10 +88,10 @@ enum sdw_slave_status {
  * @SDW_CLK_POST_DEPREPARE: post clock stop de-prepare
  */
 enum sdw_clk_stop_type {
-	       SDW_CLK_PRE_PREPARE = 0,
-	       SDW_CLK_POST_PREPARE,
-	       SDW_CLK_PRE_DEPREPARE,
-	       SDW_CLK_POST_DEPREPARE,
+	SDW_CLK_PRE_PREPARE = 0,
+	SDW_CLK_POST_PREPARE,
+	SDW_CLK_PRE_DEPREPARE,
+	SDW_CLK_POST_DEPREPARE,
 };
 
 /**
-- 
cgit v1.2.3


From 71d734103edfa2b4c6657578a3082ee0e51d767e Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@techsingularity.net>
Date: Wed, 8 Jul 2020 14:11:36 +0300
Subject: fsnotify: Rearrange fast path to minimise overhead when there is no
 watcher

The fsnotify paths are trivial to hit even when there are no watchers and
they are surprisingly expensive. For example, every successful vfs_write()
hits fsnotify_modify which calls both fsnotify_parent and fsnotify unless
FMODE_NONOTIFY is set which is an internal flag invisible to userspace.
As it stands, fsnotify_parent is a guaranteed functional call even if there
are no watchers and fsnotify() does a substantial amount of unnecessary
work before it checks if there are any watchers. A perf profile showed
that applying mnt->mnt_fsnotify_mask in fnotify() was almost half of the
total samples taken in that function during a test. This patch rearranges
the fast paths to reduce the amount of work done when there are no
watchers.

The test motivating this was "perf bench sched messaging --pipe". Despite
the fact the pipes are anonymous, fsnotify is still called a lot and
the overhead is noticeable even though it's completely pointless. It's
likely the overhead is negligible for real IO so this is an extreme
example. This is a comparison of hackbench using processes and pipes on
a 1-socket machine with 8 CPU threads without fanotify watchers.

                              5.7.0                  5.7.0
                            vanilla      fastfsnotify-v1r1
Amean     1       0.4837 (   0.00%)      0.4630 *   4.27%*
Amean     3       1.5447 (   0.00%)      1.4557 (   5.76%)
Amean     5       2.6037 (   0.00%)      2.4363 (   6.43%)
Amean     7       3.5987 (   0.00%)      3.4757 (   3.42%)
Amean     12      5.8267 (   0.00%)      5.6983 (   2.20%)
Amean     18      8.4400 (   0.00%)      8.1327 (   3.64%)
Amean     24     11.0187 (   0.00%)     10.0290 *   8.98%*
Amean     30     13.1013 (   0.00%)     12.8510 (   1.91%)
Amean     32     13.9190 (   0.00%)     13.2410 (   4.87%)

                       5.7.0       5.7.0
                     vanilla fastfsnotify-v1r1
Duration User         157.05      152.79
Duration System      1279.98     1219.32
Duration Elapsed      182.81      174.52

This is showing that the latencies are improved by roughly 2-9%. The
variability is not shown but some of these results are within the noise
as this workload heavily overloads the machine. That said, the system CPU
usage is reduced by quite a bit so it makes sense to avoid the overhead
even if it is a bit tricky to detect at times. A perf profile of just 1
group of tasks showed that 5.14% of samples taken were in either fsnotify()
or fsnotify_parent(). With the patch, 2.8% of samples were in fsnotify,
mostly function entry and the initial check for watchers.  The check for
watchers is complicated enough that inlining it may be controversial.

[Amir] Slightly simplify with mnt_or_sb_mask => marks_mask

Link: https://lore.kernel.org/r/20200708111156.24659-1-amir73il@gmail.com
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fsnotify.c             | 27 +++++++++++++++------------
 include/linux/fsnotify.h         | 10 ++++++++++
 include/linux/fsnotify_backend.h |  4 ++--
 3 files changed, 27 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 72d332ce8e12..d59a58d10b84 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -143,7 +143,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 }
 
 /* Notify this dentry's parent about a child's events. */
-int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 		    int data_type)
 {
 	struct dentry *parent;
@@ -174,7 +174,7 @@ int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(fsnotify_parent);
+EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
 static int send_to_group(struct inode *to_tell,
 			 __u32 mask, const void *data,
@@ -315,17 +315,11 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	struct fsnotify_iter_info iter_info = {};
 	struct super_block *sb = to_tell->i_sb;
 	struct mount *mnt = NULL;
-	__u32 mnt_or_sb_mask = sb->s_fsnotify_mask;
 	int ret = 0;
-	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+	__u32 test_mask, marks_mask;
 
-	if (path) {
+	if (path)
 		mnt = real_mount(path->mnt);
-		mnt_or_sb_mask |= mnt->mnt_fsnotify_mask;
-	}
-	/* An event "on child" is not intended for a mount/sb mark */
-	if (mask & FS_EVENT_ON_CHILD)
-		mnt_or_sb_mask = 0;
 
 	/*
 	 * Optimization: srcu_read_lock() has a memory barrier which can
@@ -337,13 +331,22 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	if (!to_tell->i_fsnotify_marks && !sb->s_fsnotify_marks &&
 	    (!mnt || !mnt->mnt_fsnotify_marks))
 		return 0;
+
+	/* An event "on child" is not intended for a mount/sb mark */
+	marks_mask = to_tell->i_fsnotify_mask;
+	if (!(mask & FS_EVENT_ON_CHILD)) {
+		marks_mask |= sb->s_fsnotify_mask;
+		if (mnt)
+			marks_mask |= mnt->mnt_fsnotify_mask;
+	}
+
 	/*
 	 * if this is a modify event we may need to clear the ignored masks
 	 * otherwise return if neither the inode nor the vfsmount/sb care about
 	 * this type of event.
 	 */
-	if (!(mask & FS_MODIFY) &&
-	    !(test_mask & (to_tell->i_fsnotify_mask | mnt_or_sb_mask)))
+	test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+	if (!(mask & FS_MODIFY) && !(test_mask & marks_mask))
 		return 0;
 
 	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 5ab28f6c7d26..508f6bb0b06b 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -44,6 +44,16 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
 }
 
+/* Notify this dentry's parent about a child's events. */
+static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
+				  const void *data, int data_type)
+{
+	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+		return 0;
+
+	return __fsnotify_parent(dentry, mask, data, data_type);
+}
+
 /*
  * Simple wrappers to consolidate calls fsnotify_parent()/fsnotify() when
  * an event is on a file/dentry.
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index f0c506405b54..1626fa7d10ff 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -379,7 +379,7 @@ struct fsnotify_mark {
 /* main fsnotify call to send events */
 extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
 		    int data_type, const struct qstr *name, u32 cookie);
-extern int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 			   int data_type);
 extern void __fsnotify_inode_delete(struct inode *inode);
 extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
@@ -541,7 +541,7 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
 	return 0;
 }
 
-static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
+static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask,
 				  const void *data, int data_type)
 {
 	return 0;
-- 
cgit v1.2.3


From 8635764bcf0f109933b593d79ac2247b1e863d0a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 15 Jul 2020 10:52:03 +0800
Subject: netpoll: Remove unused inline function netpoll_netdev_init()

commit d565b0a1a9b6 ("net: Add Generic Receive Offload infrastructure")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index f47af135bd56..e6a2d72e0dc7 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -102,9 +102,6 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi)
 static inline void netpoll_poll_unlock(void *have)
 {
 }
-static inline void netpoll_netdev_init(struct net_device *dev)
-{
-}
 static inline bool netpoll_tx_running(struct net_device *dev)
 {
 	return false;
-- 
cgit v1.2.3


From ded071f475cb5b67fda412f88fd5fd4d9c27916c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 14 Jul 2020 21:56:58 -0700
Subject: usb: linux/usb.h: drop duplicated word in comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20200715045701.22949-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index c28fc391444a..20c555db4621 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -341,7 +341,7 @@ struct usb_interface_cache {
  * @interface: array of pointers to usb_interface structures, one for each
  *	interface in the configuration.  The number of interfaces is stored
  *	in desc.bNumInterfaces.  These pointers are valid only while the
- *	the configuration is active.
+ *	configuration is active.
  * @intf_cache: array of pointers to usb_interface_cache structures, one
  *	for each interface in the configuration.  These structures exist
  *	for the entire life of the device.
-- 
cgit v1.2.3


From c76ae34b5af22497b660f6baeed182869c24e411 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 14 Jul 2020 21:57:00 -0700
Subject: usb: linux/usb/pd_vdo.h: drop duplicated word in comment

Drop the doubled word "all" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20200715045701.22949-3-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/pd_vdo.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h
index 35b8e15efaa0..68bdc4e2f5a9 100644
--- a/include/linux/usb/pd_vdo.h
+++ b/include/linux/usb/pd_vdo.h
@@ -249,7 +249,7 @@
  * SVDM Discover SVIDs request -> response
  *
  * Request is properly formatted VDM Header with discover SVIDs command.
- * Response is a set of SVIDs of all all supported SVIDs with all zero's to
+ * Response is a set of SVIDs of all supported SVIDs with all zero's to
  * mark the end of SVIDs.  If more than 12 SVIDs are supported command SHOULD be
  * repeated.
  */
-- 
cgit v1.2.3


From 4e28335f2b442662148f9803f3e7e053e6074815 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 14 Jul 2020 21:57:01 -0700
Subject: usb: linux/usb/serial.h: drop duplicated word in comment

Drop the doubled word "set" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20200715045701.22949-4-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/serial.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 14cac4a1ae8f..315cfc6f99a9 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -213,7 +213,7 @@ struct usb_serial_endpoints {
  *	Return 0 to continue on with the initialization sequence.  Anything
  *	else will abort it.
  * @attach: pointer to the driver's attach function.
- *	This will be called when the struct usb_serial structure is fully set
+ *	This will be called when the struct usb_serial structure is fully
  *	set up.  Do any local initialization of the device, or any private
  *	memory structure allocation at this point in time.
  * @disconnect: pointer to the driver's disconnect function.  This will be
-- 
cgit v1.2.3


From e4dfa8029925f6200f6ab2db5a25d86fd082e9cf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 14 Jul 2020 21:56:59 -0700
Subject: usb: linux/usb/gadget.h: fix duplicated word in comment

Change the doubled word "in" to "be in" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20200715045701.22949-2-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/gadget.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 298b334e2951..52ce1f6b8f83 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -731,7 +731,7 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver);
  * it will first disconnect().  The driver is also requested
  * to unbind() and clean up any device state, before this procedure
  * finally returns.  It's expected that the unbind() functions
- * will in in exit sections, so may not be linked in some kernels.
+ * will be in exit sections, so may not be linked in some kernels.
  */
 int usb_gadget_unregister_driver(struct usb_gadget_driver *driver);
 
-- 
cgit v1.2.3


From c738fbabb0ff62d0f9a9572e56e65d05a1b34c6a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 8 Jul 2020 14:11:37 +0300
Subject: fsnotify: fold fsnotify() call into fsnotify_parent()

All (two) callers of fsnotify_parent() also call fsnotify() to notify
the child inode. Move the second fsnotify() call into fsnotify_parent().

This will allow more flexibility in making decisions about which of the
two event falvors should be sent.

Using 'goto notify_child' in the inline helper seems a bit strange, but
it mimics the code in __fsnotify_parent() for clarity and the goto
pattern will become less strage after following patches are applied.

Link: https://lore.kernel.org/r/20200708111156.24659-2-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fsnotify.c     | 27 ++++++++++++++++++---------
 include/linux/fsnotify.h | 33 +++++++++++++--------------------
 2 files changed, 31 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index d59a58d10b84..30628a72ca01 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -142,16 +142,20 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 }
 
-/* Notify this dentry's parent about a child's events. */
+/*
+ * Notify this dentry's parent about a child's events with child name info
+ * if parent is watching.
+ * Notify also the child without name info if child inode is watching.
+ */
 int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
-		    int data_type)
+		      int data_type)
 {
 	struct dentry *parent;
 	struct inode *p_inode;
 	int ret = 0;
 
 	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
-		return 0;
+		goto notify_child;
 
 	parent = dget_parent(dentry);
 	p_inode = parent->d_inode;
@@ -161,18 +165,23 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 	} else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
 		struct name_snapshot name;
 
-		/* we are notifying a parent so come up with the new mask which
-		 * specifies these are events which came from a child. */
-		mask |= FS_EVENT_ON_CHILD;
-
+		/*
+		 * We are notifying a parent, so set a flag in mask to inform
+		 * backend that event has information about a child entry.
+		 */
 		take_dentry_name_snapshot(&name, dentry);
-		ret = fsnotify(p_inode, mask, data, data_type, &name.name, 0);
+		ret = fsnotify(p_inode, mask | FS_EVENT_ON_CHILD, data,
+			       data_type, &name.name, 0);
 		release_dentry_name_snapshot(&name);
 	}
 
 	dput(parent);
 
-	return ret;
+	if (ret)
+		return ret;
+
+notify_child:
+	return fsnotify(d_inode(dentry), mask, data, data_type, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 508f6bb0b06b..316c9b820517 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -48,44 +48,37 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 				  const void *data, int data_type)
 {
+	struct inode *inode = d_inode(dentry);
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
 	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
-		return 0;
+		goto notify_child;
 
 	return __fsnotify_parent(dentry, mask, data, data_type);
+
+notify_child:
+	return fsnotify(inode, mask, data, data_type, NULL, 0);
 }
 
 /*
- * Simple wrappers to consolidate calls fsnotify_parent()/fsnotify() when
- * an event is on a file/dentry.
+ * Simple wrappers to consolidate calls to fsnotify_parent() when an event
+ * is on a file/dentry.
  */
 static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 {
-	struct inode *inode = d_inode(dentry);
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	fsnotify_parent(dentry, mask, inode, FSNOTIFY_EVENT_INODE);
-	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE);
 }
 
 static inline int fsnotify_file(struct file *file, __u32 mask)
 {
 	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
-	int ret;
 
 	if (file->f_mode & FMODE_NONOTIFY)
 		return 0;
 
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	ret = fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
-	if (ret)
-		return ret;
-
-	return fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
+	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
 /* Simple call site for access decisions */
-- 
cgit v1.2.3


From cbcf47adc8aadbcaa741391ccfd96f764b50be7e Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 8 Jul 2020 14:11:38 +0300
Subject: fsnotify: return non const from fsnotify_data_inode()

Return non const inode pointer from fsnotify_data_inode().
None of the fsnotify hooks pass const inode pointer as data and
callers often need to cast to a non const pointer.

Link: https://lore.kernel.org/r/20200708111156.24659-3-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c    | 2 +-
 include/linux/fsnotify_backend.h | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 85eda539b35f..d9fc83dd994a 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -341,7 +341,7 @@ static struct inode *fanotify_fid_inode(struct inode *to_tell, u32 event_mask,
 	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
 		return to_tell;
 
-	return (struct inode *)fsnotify_data_inode(data, data_type);
+	return fsnotify_data_inode(data, data_type);
 }
 
 struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 1626fa7d10ff..97300f3b8ff0 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -220,12 +220,11 @@ enum fsnotify_data_type {
 	FSNOTIFY_EVENT_INODE,
 };
 
-static inline const struct inode *fsnotify_data_inode(const void *data,
-						      int data_type)
+static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 {
 	switch (data_type) {
 	case FSNOTIFY_EVENT_INODE:
-		return data;
+		return (struct inode *)data;
 	case FSNOTIFY_EVENT_PATH:
 		return d_inode(((const struct path *)data)->dentry);
 	default:
-- 
cgit v1.2.3


From e15864f8ea05b24071b07300459ae7e511d0b938 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Tue, 14 Jul 2020 23:18:23 +0200
Subject: block: add max_open_zones to blk-sysfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new max_open_zones definition in the sysfs documentation.
This definition will be common for all devices utilizing the zoned block
device support in the kernel.

Export max open zones according to this new definition for NVMe Zoned
Namespace devices, ZAC ATA devices (which are treated as SCSI devices by
the kernel), and ZBC SCSI devices.

Add the new max_open_zones member to struct request_queue, rather
than as a queue limit, since this property cannot be split across stacking
drivers.

Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Javier González <javier@javigon.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/ABI/testing/sysfs-block |  9 +++++++++
 Documentation/block/queue-sysfs.rst   |  7 +++++++
 block/blk-sysfs.c                     | 15 +++++++++++++++
 drivers/nvme/host/zns.c               |  1 +
 drivers/scsi/sd_zbc.c                 |  4 ++++
 include/linux/blkdev.h                | 25 +++++++++++++++++++++++++
 6 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index ed8c14f161ee..f151d9cf90de 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -273,6 +273,15 @@ Description:
 		device ("host-aware" or "host-managed" zone model). For regular
 		block devices, the value is always 0.
 
+What:		/sys/block/<disk>/queue/max_open_zones
+Date:		July 2020
+Contact:	Niklas Cassel <niklas.cassel@wdc.com>
+Description:
+		For zoned block devices (zoned attribute indicating
+		"host-managed" or "host-aware"), the sum of zones belonging to
+		any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN,
+		is limited by this value. If this value is 0, there is no limit.
+
 What:		/sys/block/<disk>/queue/chunk_sectors
 Date:		September 2016
 Contact:	Hannes Reinecke <hare@suse.com>
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index 6a8513af9201..f01cf8530ae4 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -117,6 +117,13 @@ Maximum number of elements in a DMA scatter/gather list with integrity
 data that will be submitted by the block layer core to the associated
 block driver.
 
+max_open_zones (RO)
+-------------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), the sum of zones belonging to any of the zone states:
+EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
+If this value is 0, there is no limit.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index be67952e7be2..414f04579d77 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -306,6 +306,11 @@ static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_nr_zones(q), page);
 }
 
+static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_open_zones(q), page);
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -668,6 +673,11 @@ static struct queue_sysfs_entry queue_nr_zones_entry = {
 	.show = queue_nr_zones_show,
 };
 
+static struct queue_sysfs_entry queue_max_open_zones_entry = {
+	.attr = {.name = "max_open_zones", .mode = 0444 },
+	.show = queue_max_open_zones_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
@@ -766,6 +776,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nonrot_entry.attr,
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
+	&queue_max_open_zones_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -793,6 +804,10 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
 		(!q->mq_ops || !q->mq_ops->timeout))
 			return 0;
 
+	if (attr == &queue_max_open_zones_entry.attr &&
+	    !blk_queue_is_zoned(q))
+		return 0;
+
 	return attr->mode;
 }
 
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 04e5b991c00c..3d80b9cf6bfc 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -96,6 +96,7 @@ int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
 
 	q->limits.zoned = BLK_ZONED_HM;
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
 free_data:
 	kfree(id);
 	return status;
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 183a20720da9..aa3564139b40 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -717,6 +717,10 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	/* The drive satisfies the kernel restrictions: set it up */
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
+	if (sdkp->zones_max_open == U32_MAX)
+		blk_queue_max_open_zones(q, 0);
+	else
+		blk_queue_max_open_zones(q, sdkp->zones_max_open);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index de7adc59b993..c8beb8bbdb08 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -513,6 +513,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+	unsigned int		max_open_zones;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
@@ -722,6 +723,17 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return true;
 	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
 }
+
+static inline void blk_queue_max_open_zones(struct request_queue *q,
+		unsigned int max_open_zones)
+{
+	q->max_open_zones = max_open_zones;
+}
+
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return q->max_open_zones;
+}
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
@@ -737,6 +749,10 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 {
 	return 0;
 }
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -1519,6 +1535,15 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_open_zones(q);
+	return 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
-- 
cgit v1.2.3


From 659bf827ba8f1183b714341d8a1d4b1e446178d9 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Tue, 14 Jul 2020 23:18:24 +0200
Subject: block: add max_active_zones to blk-sysfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new max_active zones definition in the sysfs documentation.
This definition will be common for all devices utilizing the zoned block
device support in the kernel.

Export max_active_zones according to this new definition for NVMe Zoned
Namespace devices, ZAC ATA devices (which are treated as SCSI devices by
the kernel), and ZBC SCSI devices.

Add the new max_active_zones member to struct request_queue, rather
than as a queue limit, since this property cannot be split across stacking
drivers.

For SCSI devices, even though max active zones is not part of the ZBC/ZAC
spec, export max_active_zones as 0, signifying "no limit".

Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Javier González <javier@javigon.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/ABI/testing/sysfs-block |  9 +++++++++
 Documentation/block/queue-sysfs.rst   |  7 +++++++
 block/blk-sysfs.c                     | 14 +++++++++++++-
 drivers/nvme/host/zns.c               |  1 +
 drivers/scsi/sd_zbc.c                 |  1 +
 include/linux/blkdev.h                | 25 +++++++++++++++++++++++++
 6 files changed, 56 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index f151d9cf90de..2322eb748b38 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -273,6 +273,15 @@ Description:
 		device ("host-aware" or "host-managed" zone model). For regular
 		block devices, the value is always 0.
 
+What:		/sys/block/<disk>/queue/max_active_zones
+Date:		July 2020
+Contact:	Niklas Cassel <niklas.cassel@wdc.com>
+Description:
+		For zoned block devices (zoned attribute indicating
+		"host-managed" or "host-aware"), the sum of zones belonging to
+		any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED,
+		is limited by this value. If this value is 0, there is no limit.
+
 What:		/sys/block/<disk>/queue/max_open_zones
 Date:		July 2020
 Contact:	Niklas Cassel <niklas.cassel@wdc.com>
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index f01cf8530ae4..f261a5c84170 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -117,6 +117,13 @@ Maximum number of elements in a DMA scatter/gather list with integrity
 data that will be submitted by the block layer core to the associated
 block driver.
 
+max_active_zones (RO)
+---------------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), the sum of zones belonging to any of the zone states:
+EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
+If this value is 0, there is no limit.
+
 max_open_zones (RO)
 -------------------
 For zoned block devices (zoned attribute indicating "host-managed" or
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 414f04579d77..7dda709f3ccb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -311,6 +311,11 @@ static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_max_open_zones(q), page);
 }
 
+static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_active_zones(q), page);
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -678,6 +683,11 @@ static struct queue_sysfs_entry queue_max_open_zones_entry = {
 	.show = queue_max_open_zones_show,
 };
 
+static struct queue_sysfs_entry queue_max_active_zones_entry = {
+	.attr = {.name = "max_active_zones", .mode = 0444 },
+	.show = queue_max_active_zones_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
@@ -777,6 +787,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
 	&queue_max_open_zones_entry.attr,
+	&queue_max_active_zones_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -804,7 +815,8 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
 		(!q->mq_ops || !q->mq_ops->timeout))
 			return 0;
 
-	if (attr == &queue_max_open_zones_entry.attr &&
+	if ((attr == &queue_max_open_zones_entry.attr ||
+	     attr == &queue_max_active_zones_entry.attr) &&
 	    !blk_queue_is_zoned(q))
 		return 0;
 
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 3d80b9cf6bfc..57cfd78731fb 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -97,6 +97,7 @@ int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
 	q->limits.zoned = BLK_ZONED_HM;
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
+	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
 free_data:
 	kfree(id);
 	return status;
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index aa3564139b40..d8b2c49d645b 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -721,6 +721,7 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 		blk_queue_max_open_zones(q, 0);
 	else
 		blk_queue_max_open_zones(q, sdkp->zones_max_open);
+	blk_queue_max_active_zones(q, 0);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c8beb8bbdb08..285b59cfc064 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -514,6 +514,7 @@ struct request_queue {
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
@@ -734,6 +735,17 @@ static inline unsigned int queue_max_open_zones(const struct request_queue *q)
 {
 	return q->max_open_zones;
 }
+
+static inline void blk_queue_max_active_zones(struct request_queue *q,
+		unsigned int max_active_zones)
+{
+	q->max_active_zones = max_active_zones;
+}
+
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return q->max_active_zones;
+}
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
@@ -753,6 +765,10 @@ static inline unsigned int queue_max_open_zones(const struct request_queue *q)
 {
 	return 0;
 }
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -1544,6 +1560,15 @@ static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_active_zones(q);
+	return 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
-- 
cgit v1.2.3


From 1a8f0886a6008c98a926bdeca49f2ef33015a491 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Thu, 9 Jul 2020 10:48:35 +0530
Subject: powerpc/perf/hv-24x7: Add cpu hotplug support

Patch here adds cpu hotplug functions to hv_24x7 pmu.
A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE" enum
is added.

The online callback function updates the cpumask only if its
empty. As the primary intention of adding hotplug support
is to designate a CPU to make HCALL to collect the
counter data.

The offline function test and clear corresponding cpu in a cpumask
and update cpumask to any other active cpu.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200709051836.723765-2-kjain@linux.ibm.com
---
 arch/powerpc/perf/hv-24x7.c | 46 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 47 insertions(+)

(limited to 'include/linux')

diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index db213eb7cb02..93b4700dcf8c 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -31,6 +31,8 @@ static int interface_version;
 /* Whether we have to aggregate result data for some domains. */
 static bool aggregate_result_elements;
 
+static cpumask_t hv_24x7_cpumask;
+
 static bool domain_is_valid(unsigned domain)
 {
 	switch (domain) {
@@ -1641,6 +1643,45 @@ static struct pmu h_24x7_pmu = {
 	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
+static int ppc_hv_24x7_cpu_online(unsigned int cpu)
+{
+	if (cpumask_empty(&hv_24x7_cpumask))
+		cpumask_set_cpu(cpu, &hv_24x7_cpumask);
+
+	return 0;
+}
+
+static int ppc_hv_24x7_cpu_offline(unsigned int cpu)
+{
+	int target;
+
+	/* Check if exiting cpu is used for collecting 24x7 events */
+	if (!cpumask_test_and_clear_cpu(cpu, &hv_24x7_cpumask))
+		return 0;
+
+	/* Find a new cpu to collect 24x7 events */
+	target = cpumask_last(cpu_active_mask);
+
+	if (target < 0 || target >= nr_cpu_ids) {
+		pr_err("hv_24x7: CPU hotplug init failed\n");
+		return -1;
+	}
+
+	/* Migrate 24x7 events to the new target */
+	cpumask_set_cpu(target, &hv_24x7_cpumask);
+	perf_pmu_migrate_context(&h_24x7_pmu, cpu, target);
+
+	return 0;
+}
+
+static int hv_24x7_cpu_hotplug_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
+			  "perf/powerpc/hv_24x7:online",
+			  ppc_hv_24x7_cpu_online,
+			  ppc_hv_24x7_cpu_offline);
+}
+
 static int hv_24x7_init(void)
 {
 	int r;
@@ -1685,6 +1726,11 @@ static int hv_24x7_init(void)
 	if (r)
 		return r;
 
+	/* init cpuhotplug */
+	r = hv_24x7_cpu_hotplug_init();
+	if (r)
+		return r;
+
 	r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
 	if (r)
 		return r;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 191772d4a4d7..a2710e654b64 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -181,6 +181,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
+	CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-- 
cgit v1.2.3


From 0d80b76184ac9f2dfb939e39ad1f961fc006b99d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 09:42:38 -0700
Subject: net: qed: drop duplicate words in comments

Drop doubled word "the" in two comments.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/qed/qed_chain.h | 2 +-
 include/linux/qed/qed_if.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 92cdc79e5019..7071dc92b4e2 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -130,7 +130,7 @@ struct qed_chain {
 	} pbl_sp;
 
 	/* Address of first page of the chain - the address is required
-	 * for fastpath operation [consume/produce] but only for the the SINGLE
+	 * for fastpath operation [consume/produce] but only for the SINGLE
 	 * flavour which isn't considered fastpath [== SPQ].
 	 */
 	void *p_virt_addr;
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 90e1060da02b..8a6e3ad436d1 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -498,7 +498,7 @@ struct qed_fcoe_pf_params {
 	u8 bdq_pbl_num_entries[2];
 };
 
-/* Most of the the parameters below are described in the FW iSCSI / TCP HSI */
+/* Most of the parameters below are described in the FW iSCSI / TCP HSI */
 struct qed_iscsi_pf_params {
 	u64 glbl_q_params_addr;
 	u64 bdq_pbl_base_addr[3];
-- 
cgit v1.2.3


From 2ff17117e60572d6974c766d6b1a225ec7d68795 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 09:42:39 -0700
Subject: net: skbuff.h: drop duplicate words in comments

Drop doubled words in several comments.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0c0377fc00c2..6a82d4a8229e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1328,7 +1328,7 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
 			   void *target_container);
 
 /* Gets a skb connection tracking info, ctinfo map should be a
- * a map of mapsize to translate enum ip_conntrack_info states
+ * map of mapsize to translate enum ip_conntrack_info states
  * to user states.
  */
 void
@@ -3812,7 +3812,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb)
  * must call this function to return the skb back to the stack with a
  * timestamp.
  *
- * @skb: clone of the the original outgoing packet
+ * @skb: clone of the original outgoing packet
  * @hwtstamps: hardware time stamps
  *
  */
-- 
cgit v1.2.3


From 158e89639166461e225a855bce6e3ee6cd8bb1c0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 09:42:40 -0700
Subject: net: wimax: fix duplicate words in comments

Drop doubled words in two comments.
Fix a spello/typo.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/wimax/debug.h | 4 ++--
 include/net/wimax.h         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h
index 4dd2c1cea6a9..cdae052bcdcd 100644
--- a/include/linux/wimax/debug.h
+++ b/include/linux/wimax/debug.h
@@ -184,8 +184,8 @@ do {									\
 
 
 /*
- * CPP sintatic sugar to generate A_B like symbol names when one of
- * the arguments is a a preprocessor #define.
+ * CPP syntactic sugar to generate A_B like symbol names when one of
+ * the arguments is a preprocessor #define.
  */
 #define __D_PASTE__(varname, modulename) varname##_##modulename
 #define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename))
diff --git a/include/net/wimax.h b/include/net/wimax.h
index 24ba7e89c26c..f6e31d2f47aa 100644
--- a/include/net/wimax.h
+++ b/include/net/wimax.h
@@ -28,7 +28,7 @@
  *
  * USAGE
  *
- * Embed a `struct wimax_dev` at the beginning of the the device's
+ * Embed a `struct wimax_dev` at the beginning of the device's
  * private structure, initialize and register it. For details, see
  * `struct wimax_dev`s documentation.
  *
-- 
cgit v1.2.3


From 59632b220f2d61df274ed3a14a204e941051fdad Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 09:42:46 -0700
Subject: net: ipv6: drop duplicate word in comment

Drop the doubled word "by" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ipv6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 2cb445a8fc9e..8d8f877e7f81 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -223,7 +223,7 @@ struct ipv6_pinfo {
 
 	/*
 	 * Packed in 16bits.
-	 * Omit one shift by by putting the signed field at MSB.
+	 * Omit one shift by putting the signed field at MSB.
 	 */
 #if defined(__BIG_ENDIAN_BITFIELD)
 	__s16			hop_limit:9;
-- 
cgit v1.2.3


From 1dcb6c36a5ebac46099b6363ccf8f4e7563d51e2 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Tue, 14 Jul 2020 21:28:32 -0700
Subject: net/mlx5: Support setting access rights of dma addresses

mlx5_fill_page_frag_array() is used to populate dma addresses to
resources that require it, such as QPs, RQs etc. When the resource is
used, PA list permissions are ignored. For resources that use MTT list,
the user is required to provide the access rights. Subsequent patches
use resources that require MTT lists, so modify API and implementation
to support that.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 11 +++++++++--
 include/linux/mlx5/driver.h                     |  1 +
 include/linux/mlx5/mlx5_ifc.h                   |  6 ++++++
 3 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 42198e64a7f4..8db4b5f0f963 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -299,11 +299,18 @@ void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas)
 }
 EXPORT_SYMBOL_GPL(mlx5_fill_page_array);
 
-void mlx5_fill_page_frag_array(struct mlx5_frag_buf *buf, __be64 *pas)
+void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm)
 {
 	int i;
 
+	WARN_ON(perm & 0xfc);
 	for (i = 0; i < buf->npages; i++)
-		pas[i] = cpu_to_be64(buf->frags[i].map);
+		pas[i] = cpu_to_be64(buf->frags[i].map | perm);
+}
+EXPORT_SYMBOL_GPL(mlx5_fill_page_frag_array_perm);
+
+void mlx5_fill_page_frag_array(struct mlx5_frag_buf *buf, __be64 *pas)
+{
+	mlx5_fill_page_frag_array_perm(buf, pas, 0);
 }
 EXPORT_SYMBOL_GPL(mlx5_fill_page_frag_array);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 13c0e4556eda..f2557d7e1355 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -971,6 +971,7 @@ void mlx5_register_debugfs(void);
 void mlx5_unregister_debugfs(void);
 
 void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
+void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3786888cb1ba..5890e5c9da77 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10653,4 +10653,10 @@ struct mlx5_ifc_tls_progress_params_bits {
 	u8         hw_offset_record_number[0x18];
 };
 
+enum {
+	MLX5_MTT_PERM_READ	= 1 << 0,
+	MLX5_MTT_PERM_WRITE	= 1 << 1,
+	MLX5_MTT_PERM_RW	= MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE,
+};
+
 #endif /* MLX5_IFC_H */
-- 
cgit v1.2.3


From 2a913f23447ce7ef2a4dcaaa230ff43116cf5249 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Tue, 14 Jul 2020 21:28:33 -0700
Subject: net/mlx5: Add VDPA interface type to supported enumerations

VDPA is a new interface that will be added in subsequent patches. It
uses mlx5 core devices and resources. Add an interface type for it.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/driver.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f2557d7e1355..5ecc48831ae8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1054,6 +1054,7 @@ enum {
 enum {
 	MLX5_INTERFACE_PROTOCOL_IB  = 0,
 	MLX5_INTERFACE_PROTOCOL_ETH = 1,
+	MLX5_INTERFACE_PROTOCOL_VDPA = 2,
 };
 
 struct mlx5_interface {
-- 
cgit v1.2.3


From 8a06a79b0aa811eee6d56b3cfc738c5d08b0dc74 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Tue, 14 Jul 2020 21:28:34 -0700
Subject: net/mlx5: Add interface changes required for VDPA

Rename mlx5_ifc_device_virtio_emulation_cap_bits to
mlx5_ifc_virtio_emulation_cap_bits to match names produced by the
tools producing these auto generated files.

In addition missing capabilities that will be required by VDPA
implementation.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/device.h   |   4 +-
 include/linux/mlx5/mlx5_ifc.h | 112 ++++++++++++++++++++++++++++++++++++------
 2 files changed, 100 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 57db125e5802..2aacf9a8ee4d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1361,11 +1361,11 @@ enum mlx5_qcam_feature_groups {
 	MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap)
 
 #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\
-	MLX5_GET(device_virtio_emulation_cap, \
+	MLX5_GET(virtio_emulation_cap, \
 		(mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
 
 #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\
-	MLX5_GET64(device_virtio_emulation_cap, \
+	MLX5_GET64(virtio_emulation_cap, \
 		(mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
 
 #define MLX5_CAP_IPSEC(mdev, cap)\
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5890e5c9da77..435ab47d5362 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -93,6 +93,7 @@ enum {
 
 enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
+	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
 	MLX5_OBJ_TYPE_PSV = 0xff03,
@@ -981,17 +982,40 @@ struct mlx5_ifc_device_event_cap_bits {
 	u8         user_unaffiliated_events[4][0x40];
 };
 
-struct mlx5_ifc_device_virtio_emulation_cap_bits {
-	u8         reserved_at_0[0x20];
+struct mlx5_ifc_virtio_emulation_cap_bits {
+	u8         desc_tunnel_offload_type[0x1];
+	u8         eth_frame_offload_type[0x1];
+	u8         virtio_version_1_0[0x1];
+	u8         device_features_bits_mask[0xd];
+	u8         event_mode[0x8];
+	u8         virtio_queue_type[0x8];
 
-	u8         reserved_at_20[0x13];
+	u8         max_tunnel_desc[0x10];
+	u8         reserved_at_30[0x3];
 	u8         log_doorbell_stride[0x5];
 	u8         reserved_at_38[0x3];
 	u8         log_doorbell_bar_size[0x5];
 
 	u8         doorbell_bar_offset[0x40];
 
-	u8         reserved_at_80[0x780];
+	u8         max_emulated_devices[0x8];
+	u8         max_num_virtio_queues[0x18];
+
+	u8         reserved_at_a0[0x60];
+
+	u8         umem_1_buffer_param_a[0x20];
+
+	u8         umem_1_buffer_param_b[0x20];
+
+	u8         umem_2_buffer_param_a[0x20];
+
+	u8         umem_2_buffer_param_b[0x20];
+
+	u8         umem_3_buffer_param_a[0x20];
+
+	u8         umem_3_buffer_param_b[0x20];
+
+	u8         reserved_at_1c0[0x640];
 };
 
 enum {
@@ -1216,7 +1240,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
-	u8         reserved_at_d0[0xb];
+	u8         reserved_at_d0[0x9];
+	u8         virtio_net_device_emualtion_manager[0x1];
+	u8         virtio_blk_device_emualtion_manager[0x1];
 	u8         log_max_cq[0x5];
 
 	u8         log_max_eq_sz[0x8];
@@ -2952,7 +2978,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_fpga_cap_bits fpga_cap;
 	struct mlx5_ifc_tls_cap_bits tls_cap;
 	struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
-	struct mlx5_ifc_device_virtio_emulation_cap_bits virtio_emulation_cap;
+	struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -3298,15 +3324,18 @@ struct mlx5_ifc_scheduling_context_bits {
 };
 
 struct mlx5_ifc_rqtc_bits {
-	u8         reserved_at_0[0xa0];
+	u8    reserved_at_0[0xa0];
 
-	u8         reserved_at_a0[0x10];
-	u8         rqt_max_size[0x10];
+	u8    reserved_at_a0[0x5];
+	u8    list_q_type[0x3];
+	u8    reserved_at_a8[0x8];
+	u8    rqt_max_size[0x10];
 
-	u8         reserved_at_c0[0x10];
-	u8         rqt_actual_size[0x10];
+	u8    rq_vhca_id_format[0x1];
+	u8    reserved_at_c1[0xf];
+	u8    rqt_actual_size[0x10];
 
-	u8         reserved_at_e0[0x6a0];
+	u8    reserved_at_e0[0x6a0];
 
 	struct mlx5_ifc_rq_num_bits rq_num[];
 };
@@ -7084,7 +7113,7 @@ struct mlx5_ifc_destroy_mkey_out_bits {
 
 struct mlx5_ifc_destroy_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
@@ -7782,7 +7811,7 @@ struct mlx5_ifc_create_mkey_out_bits {
 
 struct mlx5_ifc_create_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
@@ -10312,6 +10341,40 @@ struct mlx5_ifc_create_umem_in_bits {
 	struct mlx5_ifc_umem_bits  umem;
 };
 
+struct mlx5_ifc_create_umem_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         umem_id[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_destroy_umem_in_bits {
+	u8        opcode[0x10];
+	u8        uid[0x10];
+
+	u8        reserved_at_20[0x10];
+	u8        op_mod[0x10];
+
+	u8        reserved_at_40[0x8];
+	u8        umem_id[0x18];
+
+	u8        reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_destroy_umem_out_bits {
+	u8        status[0x8];
+	u8        reserved_at_8[0x18];
+
+	u8        syndrome[0x20];
+
+	u8        reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_create_uctx_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
@@ -10324,6 +10387,18 @@ struct mlx5_ifc_create_uctx_in_bits {
 	struct mlx5_ifc_uctx_bits  uctx;
 };
 
+struct mlx5_ifc_create_uctx_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_destroy_uctx_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
@@ -10337,6 +10412,15 @@ struct mlx5_ifc_destroy_uctx_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_destroy_uctx_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8          reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_create_sw_icm_in_bits {
 	struct mlx5_ifc_general_obj_in_cmd_hdr_bits   hdr;
 	struct mlx5_ifc_sw_icm_bits		      sw_icm;
-- 
cgit v1.2.3


From a5e6f964bb2c613933de58a35ddfa306128ba004 Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Fri, 10 Jul 2020 17:00:03 +0900
Subject: rtc: cleanup obsolete comment about struct rtc_class_ops

Commit ea369ea6d828 ("rtc: remove .open() and .release()") removes
open/release callback from struct rtc_class_ops.

Also commit 80d4bb515b78 ("RTC: Cleanup rtc_class_ops->irq_set_state")
and commit 696160fec162 ("RTC: Cleanup rtc_class_ops->irq_set_freq()")
removes irq callbacks.

So, just remove related comments so that readers will not be confused.

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200710080003.7986-1-misono.tomohiro@jp.fujitsu.com
---
 include/linux/rtc.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index bba3db3f7efa..22d1575e4991 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -55,10 +55,6 @@ extern struct class *rtc_class;
  *
  * The (current) exceptions are mostly filesystem hooks:
  *   - the proc() hook for procfs
- *   - non-ioctl() chardev hooks:  open(), release()
- *
- * REVISIT those periodic irq calls *do* have ops_lock when they're
- * issued through ioctl() ...
  */
 struct rtc_class_ops {
 	int (*ioctl)(struct device *, unsigned int, unsigned long);
-- 
cgit v1.2.3


From 2eb27c11937ee9984c04b75d213a737291c5f58c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 9 Jul 2020 23:20:39 -0700
Subject: crypto: algapi - add NEED_FALLBACK to INHERITED_FLAGS

CRYPTO_ALG_NEED_FALLBACK is handled inconsistently.  When it's requested
to be clear, some templates propagate that request to child algorithms,
while others don't.

It's apparently desired for NEED_FALLBACK to be propagated, to avoid
deadlocks where a module tries to load itself while it's being
initialized, and to avoid unnecessarily complex fallback chains where we
have e.g. cbc-aes-$driver falling back to cbc(aes-$driver) where
aes-$driver itself falls back to aes-generic, instead of cbc-aes-$driver
simply falling back to cbc(aes-generic).  There have been a number of
fixes to this effect:

commit 89027579bc6c ("crypto: xts - Propagate NEED_FALLBACK bit")
commit d2c2a85cfe82 ("crypto: ctr - Propagate NEED_FALLBACK bit")
commit e6c2e65c70a6 ("crypto: cbc - Propagate NEED_FALLBACK bit")

But it seems that other templates can have the same problems too.

To avoid this whack-a-mole, just add NEED_FALLBACK to INHERITED_FLAGS so
that it's always inherited.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ctr.c            | 2 --
 crypto/skcipher.c       | 2 --
 crypto/xts.c            | 2 --
 include/crypto/algapi.h | 3 ++-
 include/linux/crypto.h  | 4 ++--
 5 files changed, 4 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/ctr.c b/crypto/ctr.c
index ae8d88c715d6..c39fcffba27f 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -265,8 +265,6 @@ static int crypto_rfc3686_create(struct crypto_template *tmpl,
 	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask);
 	if (err)
 		return err;
-	mask |= crypto_requires_off(crypto_get_attr_type(tb),
-				    CRYPTO_ALG_NEED_FALLBACK);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 3b93a74ad124..467af525848a 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -943,8 +943,6 @@ struct skcipher_instance *skcipher_alloc_instance_simple(
 	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask);
 	if (err)
 		return ERR_PTR(err);
-	mask |= crypto_requires_off(crypto_get_attr_type(tb),
-				    CRYPTO_ALG_NEED_FALLBACK);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
diff --git a/crypto/xts.c b/crypto/xts.c
index 35a30610569b..9a7adab6c3e1 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -340,8 +340,6 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask);
 	if (err)
 		return err;
-	mask |= crypto_requires_off(crypto_get_attr_type(tb),
-				    CRYPTO_ALG_NEED_FALLBACK);
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index da64c37482b4..22cf4d80959f 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -245,7 +245,8 @@ static inline u32 crypto_requires_off(struct crypto_attr_type *algt, u32 off)
  * template), these are the flags that should always be set on the "outer"
  * algorithm if any "inner" algorithm has them set.
  */
-#define CRYPTO_ALG_INHERITED_FLAGS	CRYPTO_ALG_ASYNC
+#define CRYPTO_ALG_INHERITED_FLAGS	\
+	(CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK)
 
 /*
  * Given the type and mask that specify the flags restrictions on a template
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 7cd2d00f0a05..f73f0b51e1cd 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -60,8 +60,8 @@
 #define CRYPTO_ALG_ASYNC		0x00000080
 
 /*
- * Set this bit if and only if the algorithm requires another algorithm of
- * the same type to handle corner cases.
+ * Set if the algorithm (or an algorithm which it uses) requires another
+ * algorithm of the same type to handle corner cases.
  */
 #define CRYPTO_ALG_NEED_FALLBACK	0x00000100
 
-- 
cgit v1.2.3


From fbb6cda44190d72aa5199d728797aabc6d2ed816 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 9 Jul 2020 23:20:40 -0700
Subject: crypto: algapi - introduce the flag CRYPTO_ALG_ALLOCATES_MEMORY

Introduce a new algorithm flag CRYPTO_ALG_ALLOCATES_MEMORY.  If this
flag is set, then the driver allocates memory in its request routine.
Such drivers are not suitable for disk encryption because GFP_ATOMIC
allocation can fail anytime (causing random I/O errors) and GFP_KERNEL
allocation can recurse into the block layer, causing a deadlock.

For now, this flag is only implemented for some algorithm types.  We
also assume some usage constraints for it to be meaningful, since there
are lots of edge cases the crypto API allows (e.g., misaligned or
fragmented scatterlists) that mean that nearly any crypto algorithm can
allocate memory in some case.  See the comment for details.

Also add this flag to CRYPTO_ALG_INHERITED_FLAGS so that when a template
is instantiated, this flag is set on the template instance if it is set
on any algorithm the instance uses.

Based on a patch by Mikulas Patocka <mpatocka@redhat.com>
(https://lore.kernel.org/r/alpine.LRH.2.02.2006301414580.30526@file01.intranet.prod.int.rdu2.redhat.com).

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/algapi.h |  3 ++-
 include/linux/crypto.h  | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 22cf4d80959f..143d884d65c7 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -246,7 +246,8 @@ static inline u32 crypto_requires_off(struct crypto_attr_type *algt, u32 off)
  * algorithm if any "inner" algorithm has them set.
  */
 #define CRYPTO_ALG_INHERITED_FLAGS	\
-	(CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK)
+	(CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK |	\
+	 CRYPTO_ALG_ALLOCATES_MEMORY)
 
 /*
  * Given the type and mask that specify the flags restrictions on a template
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index f73f0b51e1cd..ef90e07c9635 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -100,6 +100,38 @@
  */
 #define CRYPTO_NOLOAD			0x00008000
 
+/*
+ * The algorithm may allocate memory during request processing, i.e. during
+ * encryption, decryption, or hashing.  Users can request an algorithm with this
+ * flag unset if they can't handle memory allocation failures.
+ *
+ * This flag is currently only implemented for algorithms of type "skcipher",
+ * "aead", "ahash", "shash", and "cipher".  Algorithms of other types might not
+ * have this flag set even if they allocate memory.
+ *
+ * In some edge cases, algorithms can allocate memory regardless of this flag.
+ * To avoid these cases, users must obey the following usage constraints:
+ *    skcipher:
+ *	- The IV buffer and all scatterlist elements must be aligned to the
+ *	  algorithm's alignmask.
+ *	- If the data were to be divided into chunks of size
+ *	  crypto_skcipher_walksize() (with any remainder going at the end), no
+ *	  chunk can cross a page boundary or a scatterlist element boundary.
+ *    aead:
+ *	- The IV buffer and all scatterlist elements must be aligned to the
+ *	  algorithm's alignmask.
+ *	- The first scatterlist element must contain all the associated data,
+ *	  and its pages must be !PageHighMem.
+ *	- If the plaintext/ciphertext were to be divided into chunks of size
+ *	  crypto_aead_walksize() (with the remainder going at the end), no chunk
+ *	  can cross a page boundary or a scatterlist element boundary.
+ *    ahash:
+ *	- The result buffer must be aligned to the algorithm's alignmask.
+ *	- crypto_ahash_finup() must not be used unless the algorithm implements
+ *	  ->finup() natively.
+ */
+#define CRYPTO_ALG_ALLOCATES_MEMORY	0x00010000
+
 /*
  * Transform masks and values (for crt_flags).
  */
-- 
cgit v1.2.3


From c04011fe8cbd80af1be6e12b53193bf3846750d7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 08:47:43 +0200
Subject: fs: add a vfs_fchown helper

Add a helper for struct file based chown operations.  To be used by
the initramfs code soon.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/open.c          | 29 +++++++++++++++++------------
 include/linux/fs.h |  2 ++
 2 files changed, 19 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/open.c b/fs/open.c
index 6cd48a61cda3..103c66309bee 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -740,23 +740,28 @@ SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group
 			   AT_SYMLINK_NOFOLLOW);
 }
 
+int vfs_fchown(struct file *file, uid_t user, gid_t group)
+{
+	int error;
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+	audit_file(file);
+	error = chown_common(&file->f_path, user, group);
+	mnt_drop_write_file(file);
+	return error;
+}
+
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group)
 {
 	struct fd f = fdget(fd);
 	int error = -EBADF;
 
-	if (!f.file)
-		goto out;
-
-	error = mnt_want_write_file(f.file);
-	if (error)
-		goto out_fput;
-	audit_file(f.file);
-	error = chown_common(&f.file->f_path, user, group);
-	mnt_drop_write_file(f.file);
-out_fput:
-	fdput(f);
-out:
+	if (f.file) {
+		error = vfs_fchown(f.file, user, group);
+		fdput(f);
+	}
 	return error;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5abba86107d..0ddd64ca0b45 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1744,6 +1744,8 @@ int vfs_mkobj(struct dentry *, umode_t,
 		int (*f)(struct dentry *, umode_t, void *),
 		void *);
 
+int vfs_fchown(struct file *file, uid_t user, gid_t group);
+
 extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
 #ifdef CONFIG_COMPAT
-- 
cgit v1.2.3


From 9e96c8c0e94eea2f69a9705f5d0f51928ea26c17 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 08:55:05 +0200
Subject: fs: add a vfs_fchmod helper

Add a helper for struct file based chmode operations.  To be used by
the initramfs code soon.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/open.c          | 9 +++++++--
 include/linux/fs.h | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/open.c b/fs/open.c
index 103c66309bee..75166f071d28 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -602,14 +602,19 @@ out_unlock:
 	return error;
 }
 
+int vfs_fchmod(struct file *file, umode_t mode)
+{
+	audit_file(file);
+	return chmod_common(&file->f_path, mode);
+}
+
 int ksys_fchmod(unsigned int fd, umode_t mode)
 {
 	struct fd f = fdget(fd);
 	int err = -EBADF;
 
 	if (f.file) {
-		audit_file(f.file);
-		err = chmod_common(&f.file->f_path, mode);
+		err = vfs_fchmod(f.file, mode);
 		fdput(f);
 	}
 	return err;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0ddd64ca0b45..635086726f20 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1745,6 +1745,7 @@ int vfs_mkobj(struct dentry *, umode_t,
 		void *);
 
 int vfs_fchown(struct file *file, uid_t user, gid_t group);
+int vfs_fchmod(struct file *file, umode_t mode);
 
 extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
-- 
cgit v1.2.3


From 4f5b246b37e024955c0fcca0c7f5952089052d1d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 7 Jun 2020 16:18:59 +0200
Subject: md: move the early init autodetect code to drivers/md/

Just like the NFS and CIFS root code this better lives with the
driver it is tightly integrated with.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/md/Makefile         |   3 +
 drivers/md/md-autodetect.c  | 315 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/raid/detect.h |   8 ++
 init/Makefile               |   1 -
 init/do_mounts.c            |   1 +
 init/do_mounts.h            |  10 --
 init/do_mounts_md.c         | 304 ------------------------------------------
 7 files changed, 327 insertions(+), 315 deletions(-)
 create mode 100644 drivers/md/md-autodetect.c
 delete mode 100644 init/do_mounts_md.c

(limited to 'include/linux')

diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 31840f95cd40..6d3e234dc46a 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -43,6 +43,9 @@ obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_MD_CLUSTER)	+= md-cluster.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
+ifeq ($(CONFIG_BLK_DEV_MD),y)
+obj-y				+= md-autodetect.o
+endif
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
 obj-$(CONFIG_DM_UNSTRIPED)	+= dm-unstripe.o
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
new file mode 100644
index 000000000000..fe806f7b9759
--- /dev/null
+++ b/drivers/md/md-autodetect.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/syscalls.h>
+#include <linux/mount.h>
+#include <linux/major.h>
+#include <linux/delay.h>
+#include <linux/raid/detect.h>
+#include <linux/raid/md_u.h>
+#include <linux/raid/md_p.h>
+
+/*
+ * When md (and any require personalities) are compiled into the kernel
+ * (not a module), arrays can be assembles are boot time using with AUTODETECT
+ * where specially marked partitions are registered with md_autodetect_dev(),
+ * and with MD_BOOT where devices to be collected are given on the boot line
+ * with md=.....
+ * The code for that is here.
+ */
+
+#ifdef CONFIG_MD_AUTODETECT
+static int __initdata raid_noautodetect;
+#else
+static int __initdata raid_noautodetect=1;
+#endif
+static int __initdata raid_autopart;
+
+static struct {
+	int minor;
+	int partitioned;
+	int level;
+	int chunk;
+	char *device_names;
+} md_setup_args[256] __initdata;
+
+static int md_setup_ents __initdata;
+
+/*
+ * Parse the command-line parameters given our kernel, but do not
+ * actually try to invoke the MD device now; that is handled by
+ * md_setup_drive after the low-level disk drivers have initialised.
+ *
+ * 27/11/1999: Fixed to work correctly with the 2.3 kernel (which
+ *             assigns the task of parsing integer arguments to the
+ *             invoked program now).  Added ability to initialise all
+ *             the MD devices (by specifying multiple "md=" lines)
+ *             instead of just one.  -- KTK
+ * 18May2000: Added support for persistent-superblock arrays:
+ *             md=n,0,factor,fault,device-list   uses RAID0 for device n
+ *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
+ *             md=n,device-list      reads a RAID superblock from the devices
+ *             elements in device-list are read by name_to_kdev_t so can be
+ *             a hex number or something like /dev/hda1 /dev/sdb
+ * 2001-06-03: Dave Cinege <dcinege@psychosis.com>
+ *		Shifted name_to_kdev_t() and related operations to md_set_drive()
+ *		for later execution. Rewrote section to make devfs compatible.
+ */
+static int __init md_setup(char *str)
+{
+	int minor, level, factor, fault, partitioned = 0;
+	char *pername = "";
+	char *str1;
+	int ent;
+
+	if (*str == 'd') {
+		partitioned = 1;
+		str++;
+	}
+	if (get_option(&str, &minor) != 2) {	/* MD Number */
+		printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
+		return 0;
+	}
+	str1 = str;
+	for (ent=0 ; ent< md_setup_ents ; ent++)
+		if (md_setup_args[ent].minor == minor &&
+		    md_setup_args[ent].partitioned == partitioned) {
+			printk(KERN_WARNING "md: md=%s%d, Specified more than once. "
+			       "Replacing previous definition.\n", partitioned?"d":"", minor);
+			break;
+		}
+	if (ent >= ARRAY_SIZE(md_setup_args)) {
+		printk(KERN_WARNING "md: md=%s%d - too many md initialisations\n", partitioned?"d":"", minor);
+		return 0;
+	}
+	if (ent >= md_setup_ents)
+		md_setup_ents++;
+	switch (get_option(&str, &level)) {	/* RAID level */
+	case 2: /* could be 0 or -1.. */
+		if (level == 0 || level == LEVEL_LINEAR) {
+			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
+					get_option(&str, &fault) != 2) {
+				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
+				return 0;
+			}
+			md_setup_args[ent].level = level;
+			md_setup_args[ent].chunk = 1 << (factor+12);
+			if (level ==  LEVEL_LINEAR)
+				pername = "linear";
+			else
+				pername = "raid0";
+			break;
+		}
+		/* FALL THROUGH */
+	case 1: /* the first device is numeric */
+		str = str1;
+		/* FALL THROUGH */
+	case 0:
+		md_setup_args[ent].level = LEVEL_NONE;
+		pername="super-block";
+	}
+
+	printk(KERN_INFO "md: Will configure md%d (%s) from %s, below.\n",
+		minor, pername, str);
+	md_setup_args[ent].device_names = str;
+	md_setup_args[ent].partitioned = partitioned;
+	md_setup_args[ent].minor = minor;
+
+	return 1;
+}
+
+static inline int create_dev(char *name, dev_t dev)
+{
+	ksys_unlink(name);
+	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
+}
+
+static void __init md_setup_drive(void)
+{
+	int minor, i, ent, partitioned;
+	dev_t dev;
+	dev_t devices[MD_SB_DISKS+1];
+
+	for (ent = 0; ent < md_setup_ents ; ent++) {
+		int fd;
+		int err = 0;
+		char *devname;
+		mdu_disk_info_t dinfo;
+		char name[16];
+
+		minor = md_setup_args[ent].minor;
+		partitioned = md_setup_args[ent].partitioned;
+		devname = md_setup_args[ent].device_names;
+
+		sprintf(name, "/dev/md%s%d", partitioned?"_d":"", minor);
+		if (partitioned)
+			dev = MKDEV(mdp_major, minor << MdpMinorShift);
+		else
+			dev = MKDEV(MD_MAJOR, minor);
+		create_dev(name, dev);
+		for (i = 0; i < MD_SB_DISKS && devname != NULL; i++) {
+			struct kstat stat;
+			char *p;
+			char comp_name[64];
+
+			p = strchr(devname, ',');
+			if (p)
+				*p++ = 0;
+
+			dev = name_to_dev_t(devname);
+			if (strncmp(devname, "/dev/", 5) == 0)
+				devname += 5;
+			snprintf(comp_name, 63, "/dev/%s", devname);
+			if (vfs_stat(comp_name, &stat) == 0 &&
+			    S_ISBLK(stat.mode))
+				dev = new_decode_dev(stat.rdev);
+			if (!dev) {
+				printk(KERN_WARNING "md: Unknown device name: %s\n", devname);
+				break;
+			}
+
+			devices[i] = dev;
+
+			devname = p;
+		}
+		devices[i] = 0;
+
+		if (!i)
+			continue;
+
+		printk(KERN_INFO "md: Loading md%s%d: %s\n",
+			partitioned ? "_d" : "", minor,
+			md_setup_args[ent].device_names);
+
+		fd = ksys_open(name, 0, 0);
+		if (fd < 0) {
+			printk(KERN_ERR "md: open failed - cannot start "
+					"array %s\n", name);
+			continue;
+		}
+		if (ksys_ioctl(fd, SET_ARRAY_INFO, 0) == -EBUSY) {
+			printk(KERN_WARNING
+			       "md: Ignoring md=%d, already autodetected. (Use raid=noautodetect)\n",
+			       minor);
+			ksys_close(fd);
+			continue;
+		}
+
+		if (md_setup_args[ent].level != LEVEL_NONE) {
+			/* non-persistent */
+			mdu_array_info_t ainfo;
+			ainfo.level = md_setup_args[ent].level;
+			ainfo.size = 0;
+			ainfo.nr_disks =0;
+			ainfo.raid_disks =0;
+			while (devices[ainfo.raid_disks])
+				ainfo.raid_disks++;
+			ainfo.md_minor =minor;
+			ainfo.not_persistent = 1;
+
+			ainfo.state = (1 << MD_SB_CLEAN);
+			ainfo.layout = 0;
+			ainfo.chunk_size = md_setup_args[ent].chunk;
+			err = ksys_ioctl(fd, SET_ARRAY_INFO, (long)&ainfo);
+			for (i = 0; !err && i <= MD_SB_DISKS; i++) {
+				dev = devices[i];
+				if (!dev)
+					break;
+				dinfo.number = i;
+				dinfo.raid_disk = i;
+				dinfo.state = (1<<MD_DISK_ACTIVE)|(1<<MD_DISK_SYNC);
+				dinfo.major = MAJOR(dev);
+				dinfo.minor = MINOR(dev);
+				err = ksys_ioctl(fd, ADD_NEW_DISK,
+						 (long)&dinfo);
+			}
+		} else {
+			/* persistent */
+			for (i = 0; i <= MD_SB_DISKS; i++) {
+				dev = devices[i];
+				if (!dev)
+					break;
+				dinfo.major = MAJOR(dev);
+				dinfo.minor = MINOR(dev);
+				ksys_ioctl(fd, ADD_NEW_DISK, (long)&dinfo);
+			}
+		}
+		if (!err)
+			err = ksys_ioctl(fd, RUN_ARRAY, 0);
+		if (err)
+			printk(KERN_WARNING "md: starting md%d failed\n", minor);
+		else {
+			/* reread the partition table.
+			 * I (neilb) and not sure why this is needed, but I cannot
+			 * boot a kernel with devfs compiled in from partitioned md
+			 * array without it
+			 */
+			ksys_close(fd);
+			fd = ksys_open(name, 0, 0);
+			ksys_ioctl(fd, BLKRRPART, 0);
+		}
+		ksys_close(fd);
+	}
+}
+
+static int __init raid_setup(char *str)
+{
+	int len, pos;
+
+	len = strlen(str) + 1;
+	pos = 0;
+
+	while (pos < len) {
+		char *comma = strchr(str+pos, ',');
+		int wlen;
+		if (comma)
+			wlen = (comma-str)-pos;
+		else	wlen = (len-1)-pos;
+
+		if (!strncmp(str, "noautodetect", wlen))
+			raid_noautodetect = 1;
+		if (!strncmp(str, "autodetect", wlen))
+			raid_noautodetect = 0;
+		if (strncmp(str, "partitionable", wlen)==0)
+			raid_autopart = 1;
+		if (strncmp(str, "part", wlen)==0)
+			raid_autopart = 1;
+		pos += wlen+1;
+	}
+	return 1;
+}
+
+__setup("raid=", raid_setup);
+__setup("md=", md_setup);
+
+static void __init autodetect_raid(void)
+{
+	int fd;
+
+	/*
+	 * Since we don't want to detect and use half a raid array, we need to
+	 * wait for the known devices to complete their probing
+	 */
+	printk(KERN_INFO "md: Waiting for all devices to be available before autodetect\n");
+	printk(KERN_INFO "md: If you don't use raid, use raid=noautodetect\n");
+
+	wait_for_device_probe();
+
+	fd = ksys_open("/dev/md0", 0, 0);
+	if (fd >= 0) {
+		ksys_ioctl(fd, RAID_AUTORUN, raid_autopart);
+		ksys_close(fd);
+	}
+}
+
+void __init md_run_setup(void)
+{
+	create_dev("/dev/md0", MKDEV(MD_MAJOR, 0));
+
+	if (raid_noautodetect)
+		printk(KERN_INFO "md: Skipping autodetection of RAID arrays. (raid=autodetect will force)\n");
+	else
+		autodetect_raid();
+	md_setup_drive();
+}
diff --git a/include/linux/raid/detect.h b/include/linux/raid/detect.h
index 37dd3f40cd31..1f029a71c3ef 100644
--- a/include/linux/raid/detect.h
+++ b/include/linux/raid/detect.h
@@ -1,3 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 void md_autodetect_dev(dev_t dev);
+
+#ifdef CONFIG_BLK_DEV_MD
+void md_run_setup(void);
+#else
+static inline void md_run_setup(void)
+{
+}
+#endif
diff --git a/init/Makefile b/init/Makefile
index 57499b1ff471..6bc37f64b361 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -18,7 +18,6 @@ obj-y                          += init_task.o
 mounts-y			:= do_mounts.o
 mounts-$(CONFIG_BLK_DEV_RAM)	+= do_mounts_rd.o
 mounts-$(CONFIG_BLK_DEV_INITRD)	+= do_mounts_initrd.o
-mounts-$(CONFIG_BLK_DEV_MD)	+= do_mounts_md.o
 
 # dependencies on generated files need to be listed explicitly
 $(obj)/version.o: include/generated/compile.h
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 29d326b6c29d..1a4dfa17fb28 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -23,6 +23,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
 #include <linux/nfs_mount.h>
+#include <linux/raid/detect.h>
 #include <uapi/linux/mount.h>
 
 #include "do_mounts.h"
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 7513d1c14d13..50d6c8941e15 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -41,13 +41,3 @@ bool __init initrd_load(void);
 static inline bool initrd_load(void) { return false; }
 
 #endif
-
-#ifdef CONFIG_BLK_DEV_MD
-
-void md_run_setup(void);
-
-#else
-
-static inline void md_run_setup(void) {}
-
-#endif
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
deleted file mode 100644
index 359363e85ccd..000000000000
--- a/init/do_mounts_md.c
+++ /dev/null
@@ -1,304 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/delay.h>
-#include <linux/raid/md_u.h>
-#include <linux/raid/md_p.h>
-
-#include "do_mounts.h"
-
-/*
- * When md (and any require personalities) are compiled into the kernel
- * (not a module), arrays can be assembles are boot time using with AUTODETECT
- * where specially marked partitions are registered with md_autodetect_dev(),
- * and with MD_BOOT where devices to be collected are given on the boot line
- * with md=.....
- * The code for that is here.
- */
-
-#ifdef CONFIG_MD_AUTODETECT
-static int __initdata raid_noautodetect;
-#else
-static int __initdata raid_noautodetect=1;
-#endif
-static int __initdata raid_autopart;
-
-static struct {
-	int minor;
-	int partitioned;
-	int level;
-	int chunk;
-	char *device_names;
-} md_setup_args[256] __initdata;
-
-static int md_setup_ents __initdata;
-
-/*
- * Parse the command-line parameters given our kernel, but do not
- * actually try to invoke the MD device now; that is handled by
- * md_setup_drive after the low-level disk drivers have initialised.
- *
- * 27/11/1999: Fixed to work correctly with the 2.3 kernel (which
- *             assigns the task of parsing integer arguments to the
- *             invoked program now).  Added ability to initialise all
- *             the MD devices (by specifying multiple "md=" lines)
- *             instead of just one.  -- KTK
- * 18May2000: Added support for persistent-superblock arrays:
- *             md=n,0,factor,fault,device-list   uses RAID0 for device n
- *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
- *             md=n,device-list      reads a RAID superblock from the devices
- *             elements in device-list are read by name_to_kdev_t so can be
- *             a hex number or something like /dev/hda1 /dev/sdb
- * 2001-06-03: Dave Cinege <dcinege@psychosis.com>
- *		Shifted name_to_kdev_t() and related operations to md_set_drive()
- *		for later execution. Rewrote section to make devfs compatible.
- */
-static int __init md_setup(char *str)
-{
-	int minor, level, factor, fault, partitioned = 0;
-	char *pername = "";
-	char *str1;
-	int ent;
-
-	if (*str == 'd') {
-		partitioned = 1;
-		str++;
-	}
-	if (get_option(&str, &minor) != 2) {	/* MD Number */
-		printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
-		return 0;
-	}
-	str1 = str;
-	for (ent=0 ; ent< md_setup_ents ; ent++)
-		if (md_setup_args[ent].minor == minor &&
-		    md_setup_args[ent].partitioned == partitioned) {
-			printk(KERN_WARNING "md: md=%s%d, Specified more than once. "
-			       "Replacing previous definition.\n", partitioned?"d":"", minor);
-			break;
-		}
-	if (ent >= ARRAY_SIZE(md_setup_args)) {
-		printk(KERN_WARNING "md: md=%s%d - too many md initialisations\n", partitioned?"d":"", minor);
-		return 0;
-	}
-	if (ent >= md_setup_ents)
-		md_setup_ents++;
-	switch (get_option(&str, &level)) {	/* RAID level */
-	case 2: /* could be 0 or -1.. */
-		if (level == 0 || level == LEVEL_LINEAR) {
-			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
-					get_option(&str, &fault) != 2) {
-				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
-				return 0;
-			}
-			md_setup_args[ent].level = level;
-			md_setup_args[ent].chunk = 1 << (factor+12);
-			if (level ==  LEVEL_LINEAR)
-				pername = "linear";
-			else
-				pername = "raid0";
-			break;
-		}
-		/* FALL THROUGH */
-	case 1: /* the first device is numeric */
-		str = str1;
-		/* FALL THROUGH */
-	case 0:
-		md_setup_args[ent].level = LEVEL_NONE;
-		pername="super-block";
-	}
-
-	printk(KERN_INFO "md: Will configure md%d (%s) from %s, below.\n",
-		minor, pername, str);
-	md_setup_args[ent].device_names = str;
-	md_setup_args[ent].partitioned = partitioned;
-	md_setup_args[ent].minor = minor;
-
-	return 1;
-}
-
-static void __init md_setup_drive(void)
-{
-	int minor, i, ent, partitioned;
-	dev_t dev;
-	dev_t devices[MD_SB_DISKS+1];
-
-	for (ent = 0; ent < md_setup_ents ; ent++) {
-		int fd;
-		int err = 0;
-		char *devname;
-		mdu_disk_info_t dinfo;
-		char name[16];
-
-		minor = md_setup_args[ent].minor;
-		partitioned = md_setup_args[ent].partitioned;
-		devname = md_setup_args[ent].device_names;
-
-		sprintf(name, "/dev/md%s%d", partitioned?"_d":"", minor);
-		if (partitioned)
-			dev = MKDEV(mdp_major, minor << MdpMinorShift);
-		else
-			dev = MKDEV(MD_MAJOR, minor);
-		create_dev(name, dev);
-		for (i = 0; i < MD_SB_DISKS && devname != NULL; i++) {
-			struct kstat stat;
-			char *p;
-			char comp_name[64];
-
-			p = strchr(devname, ',');
-			if (p)
-				*p++ = 0;
-
-			dev = name_to_dev_t(devname);
-			if (strncmp(devname, "/dev/", 5) == 0)
-				devname += 5;
-			snprintf(comp_name, 63, "/dev/%s", devname);
-			if (vfs_stat(comp_name, &stat) == 0 &&
-			    S_ISBLK(stat.mode))
-				dev = new_decode_dev(stat.rdev);
-			if (!dev) {
-				printk(KERN_WARNING "md: Unknown device name: %s\n", devname);
-				break;
-			}
-
-			devices[i] = dev;
-
-			devname = p;
-		}
-		devices[i] = 0;
-
-		if (!i)
-			continue;
-
-		printk(KERN_INFO "md: Loading md%s%d: %s\n",
-			partitioned ? "_d" : "", minor,
-			md_setup_args[ent].device_names);
-
-		fd = ksys_open(name, 0, 0);
-		if (fd < 0) {
-			printk(KERN_ERR "md: open failed - cannot start "
-					"array %s\n", name);
-			continue;
-		}
-		if (ksys_ioctl(fd, SET_ARRAY_INFO, 0) == -EBUSY) {
-			printk(KERN_WARNING
-			       "md: Ignoring md=%d, already autodetected. (Use raid=noautodetect)\n",
-			       minor);
-			ksys_close(fd);
-			continue;
-		}
-
-		if (md_setup_args[ent].level != LEVEL_NONE) {
-			/* non-persistent */
-			mdu_array_info_t ainfo;
-			ainfo.level = md_setup_args[ent].level;
-			ainfo.size = 0;
-			ainfo.nr_disks =0;
-			ainfo.raid_disks =0;
-			while (devices[ainfo.raid_disks])
-				ainfo.raid_disks++;
-			ainfo.md_minor =minor;
-			ainfo.not_persistent = 1;
-
-			ainfo.state = (1 << MD_SB_CLEAN);
-			ainfo.layout = 0;
-			ainfo.chunk_size = md_setup_args[ent].chunk;
-			err = ksys_ioctl(fd, SET_ARRAY_INFO, (long)&ainfo);
-			for (i = 0; !err && i <= MD_SB_DISKS; i++) {
-				dev = devices[i];
-				if (!dev)
-					break;
-				dinfo.number = i;
-				dinfo.raid_disk = i;
-				dinfo.state = (1<<MD_DISK_ACTIVE)|(1<<MD_DISK_SYNC);
-				dinfo.major = MAJOR(dev);
-				dinfo.minor = MINOR(dev);
-				err = ksys_ioctl(fd, ADD_NEW_DISK,
-						 (long)&dinfo);
-			}
-		} else {
-			/* persistent */
-			for (i = 0; i <= MD_SB_DISKS; i++) {
-				dev = devices[i];
-				if (!dev)
-					break;
-				dinfo.major = MAJOR(dev);
-				dinfo.minor = MINOR(dev);
-				ksys_ioctl(fd, ADD_NEW_DISK, (long)&dinfo);
-			}
-		}
-		if (!err)
-			err = ksys_ioctl(fd, RUN_ARRAY, 0);
-		if (err)
-			printk(KERN_WARNING "md: starting md%d failed\n", minor);
-		else {
-			/* reread the partition table.
-			 * I (neilb) and not sure why this is needed, but I cannot
-			 * boot a kernel with devfs compiled in from partitioned md
-			 * array without it
-			 */
-			ksys_close(fd);
-			fd = ksys_open(name, 0, 0);
-			ksys_ioctl(fd, BLKRRPART, 0);
-		}
-		ksys_close(fd);
-	}
-}
-
-static int __init raid_setup(char *str)
-{
-	int len, pos;
-
-	len = strlen(str) + 1;
-	pos = 0;
-
-	while (pos < len) {
-		char *comma = strchr(str+pos, ',');
-		int wlen;
-		if (comma)
-			wlen = (comma-str)-pos;
-		else	wlen = (len-1)-pos;
-
-		if (!strncmp(str, "noautodetect", wlen))
-			raid_noautodetect = 1;
-		if (!strncmp(str, "autodetect", wlen))
-			raid_noautodetect = 0;
-		if (strncmp(str, "partitionable", wlen)==0)
-			raid_autopart = 1;
-		if (strncmp(str, "part", wlen)==0)
-			raid_autopart = 1;
-		pos += wlen+1;
-	}
-	return 1;
-}
-
-__setup("raid=", raid_setup);
-__setup("md=", md_setup);
-
-static void __init autodetect_raid(void)
-{
-	int fd;
-
-	/*
-	 * Since we don't want to detect and use half a raid array, we need to
-	 * wait for the known devices to complete their probing
-	 */
-	printk(KERN_INFO "md: Waiting for all devices to be available before autodetect\n");
-	printk(KERN_INFO "md: If you don't use raid, use raid=noautodetect\n");
-
-	wait_for_device_probe();
-
-	fd = ksys_open("/dev/md0", 0, 0);
-	if (fd >= 0) {
-		ksys_ioctl(fd, RAID_AUTORUN, raid_autopart);
-		ksys_close(fd);
-	}
-}
-
-void __init md_run_setup(void)
-{
-	create_dev("/dev/md0", MKDEV(MD_MAJOR, 0));
-
-	if (raid_noautodetect)
-		printk(KERN_INFO "md: Skipping autodetection of RAID arrays. (raid=autodetect will force)\n");
-	else
-		autodetect_raid();
-	md_setup_drive();
-}
-- 
cgit v1.2.3


From 1a6a050620e496abf42749a2e1d3882645cc053f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 7 Jun 2020 16:33:01 +0200
Subject: md: remove the kernel version of md_u.h

mdp_major can just move to drivers/md/md.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/md/md.h           |  1 +
 include/linux/raid/md_u.h | 13 -------------
 2 files changed, 1 insertion(+), 13 deletions(-)
 delete mode 100644 include/linux/raid/md_u.h

(limited to 'include/linux')

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 37315a3f28e9..6f8fff77ce10 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -801,6 +801,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
 
+extern int mdp_major;
 void md_autostart_arrays(int part);
 
 #endif /* _MD_MD_H */
diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h
deleted file mode 100644
index 8dfec085a20e..000000000000
--- a/include/linux/raid/md_u.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
-   md_u.h : user <=> kernel API between Linux raidtools and RAID drivers
-          Copyright (C) 1998 Ingo Molnar
-	  
-*/
-#ifndef _MD_U_H
-#define _MD_U_H
-
-#include <uapi/linux/raid/md_u.h>
-
-extern int mdp_major;
-#endif 
-- 
cgit v1.2.3


From d3fa60d7bfdc9a0ff1a524bdef96b3db1fd62022 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jul 2020 09:45:11 +0200
Subject: dma-mapping: move the remaining DMA API calls out of line

For a long time the DMA API has been implemented inline in dma-mapping.h,
but the function bodies can be quite large.  Move them all out of line.

This also removes all the dma_direct_* exports as those are just
implementation details and should never be used by drivers directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 include/linux/dma-direct.h  |  58 +++++++++++
 include/linux/dma-mapping.h | 247 ++++----------------------------------------
 kernel/dma/direct.c         |   9 --
 kernel/dma/mapping.c        | 164 +++++++++++++++++++++++++++++
 4 files changed, 244 insertions(+), 234 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index ab2e20cba951..2b045c509146 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -87,4 +87,62 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir);
+void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+size_t dma_direct_max_mapping_size(struct device *dev);
+
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index a33ed3954ed4..bd0a6f5ee445 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -188,73 +188,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
-static inline bool dma_is_direct(const struct dma_map_ops *ops)
-{
-	return likely(!ops);
-}
-
-/*
- * All the dma_direct_* declarations are here just for the indirect call bypass,
- * and must not be used directly drivers!
- */
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-}
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-size_t dma_direct_max_mapping_size(struct device *dev);
-
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 
@@ -271,164 +204,6 @@ static inline void set_dma_ops(struct device *dev,
 	dev->dma_ops = dma_ops;
 }
 
-static inline dma_addr_t dma_map_page_attrs(struct device *dev,
-		struct page *page, size_t offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
-	else
-		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	debug_dma_map_page(dev, page, offset, size, dir, addr);
-
-	return addr;
-}
-
-static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_unmap_page(dev, addr, size, dir, attrs);
-	else if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir);
-}
-
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	int ents;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
-	else
-		ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-				      int nents, enum dma_data_direction dir,
-				      unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_is_direct(ops))
-		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
-	else if (ops->unmap_sg)
-		ops->unmap_sg(dev, sg, nents, dir, attrs);
-}
-
-static inline dma_addr_t dma_map_resource(struct device *dev,
-					  phys_addr_t phys_addr,
-					  size_t size,
-					  enum dma_data_direction dir,
-					  unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr = DMA_MAPPING_ERROR;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	/* Don't allow RAM to be mapped */
-	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
-		return DMA_MAPPING_ERROR;
-
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (ops->map_resource)
-		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
-
-	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
-	return addr;
-}
-
-static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
-				      size_t size, enum dma_data_direction dir,
-				      unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (!dma_is_direct(ops) && ops->unmap_resource)
-		ops->unmap_resource(dev, addr, size, dir, attrs);
-	debug_dma_unmap_resource(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-					   size_t size,
-					   enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-	else if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr, size, dir);
-	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t addr, size_t size,
-					      enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_device(dev, addr, size, dir);
-	else if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr, size, dir);
-	debug_dma_sync_single_for_device(dev, addr, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-
-}
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -439,6 +214,28 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs);
+dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir);
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir);
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir);
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir);
 void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t flag, unsigned long attrs);
 void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 67f060b86a73..e545d14fccee 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -315,7 +315,6 @@ void dma_direct_sync_single_for_device(struct device *dev,
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_device(paddr, size, dir);
 }
-EXPORT_SYMBOL(dma_direct_sync_single_for_device);
 
 void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
@@ -335,7 +334,6 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 					dir);
 	}
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
 #endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
@@ -354,7 +352,6 @@ void dma_direct_sync_single_for_cpu(struct device *dev,
 	if (unlikely(is_swiotlb_buffer(paddr)))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
 }
-EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);
 
 void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
@@ -376,7 +373,6 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_cpu_all();
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
 
 void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
@@ -389,7 +385,6 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 	if (unlikely(is_swiotlb_buffer(phys)))
 		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
 }
-EXPORT_SYMBOL(dma_direct_unmap_page);
 
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
@@ -401,7 +396,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
 			     attrs);
 }
-EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
@@ -428,7 +422,6 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		arch_sync_dma_for_device(phys, size, dir);
 	return dma_addr;
 }
-EXPORT_SYMBOL(dma_direct_map_page);
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
@@ -450,7 +443,6 @@ out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
 	return 0;
 }
-EXPORT_SYMBOL(dma_direct_map_sg);
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
@@ -467,7 +459,6 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 
 	return dma_addr;
 }
-EXPORT_SYMBOL(dma_direct_map_resource);
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index a8c18c9a796f..b53953024512 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -105,6 +105,170 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 }
 EXPORT_SYMBOL(dmam_alloc_attrs);
 
+static inline bool dma_is_direct(const struct dma_map_ops *ops)
+{
+	return likely(!ops);
+}
+
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	else
+		addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	debug_dma_map_page(dev, page, offset, size, dir, addr);
+
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_page_attrs);
+
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_page_attrs);
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	int ents;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
+	else
+		ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+EXPORT_SYMBOL(dma_map_sg_attrs);
+
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (dma_is_direct(ops))
+		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
+	else if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+EXPORT_SYMBOL(dma_unmap_sg_attrs);
+
+dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr = DMA_MAPPING_ERROR;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	/* Don't allow RAM to be mapped */
+	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
+		return DMA_MAPPING_ERROR;
+
+	if (dma_is_direct(ops))
+		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
+	else if (ops->map_resource)
+		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
+
+	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_resource);
+
+void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (!dma_is_direct(ops) && ops->unmap_resource)
+		ops->unmap_resource(dev, addr, size, dir, attrs);
+	debug_dma_unmap_resource(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_resource);
+
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+	else if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_cpu);
+
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		dma_direct_sync_single_for_device(dev, addr, size, dir);
+	else if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_device);
+
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_is_direct(ops))
+		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_device);
+
 /*
  * Create scatter-list for the already allocated DMA buffer.
  */
-- 
cgit v1.2.3


From b4174173005972f8f6497883d08d87e0aba1b604 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jul 2020 09:47:08 +0200
Subject: dma-mapping: inline the fast path dma-direct calls

Inline the single page map/unmap/sync dma-direct calls into the now
out of line generic wrappers.  This restores the behavior of a single
function call that we had before moving the generic calls out of line.
Besides the dma-mapping callers there are just a few callers in IOMMU
drivers that have a bypass mode, and more of those are going to be
switched to the generic bypass soon.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 include/linux/dma-direct.h | 92 ++++++++++++++++++++++++++++++++++------------
 kernel/dma/direct.c        | 65 --------------------------------
 2 files changed, 69 insertions(+), 88 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 2b045c509146..5a3ce2a24794 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -1,10 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Internals of the DMA direct mapping implementation.  Only for use by the
+ * DMA mapping code and IOMMU drivers.
+ */
 #ifndef _LINUX_DMA_DIRECT_H
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
+#include <linux/swiotlb.h>
 
 extern unsigned int zone_dma_bits;
 
@@ -87,25 +93,17 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs);
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs);
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
 #else
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
 static inline void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -115,34 +113,82 @@ static inline void dma_direct_sync_sg_for_device(struct device *dev,
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
 void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
 #else
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-}
 static inline void dma_direct_unmap_sg(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
 		unsigned long attrs)
 {
 }
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
 static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
 }
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
 }
-#endif
 
-size_t dma_direct_max_mapping_size(struct device *dev);
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index e545d14fccee..bb0041e99659 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -10,11 +10,9 @@
 #include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
-#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -304,18 +302,6 @@ void dma_direct_free(struct device *dev, size_t size,
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-
 void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -339,20 +325,6 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-}
-
 void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -374,18 +346,6 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu_all();
 }
 
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = dma_to_phys(dev, addr);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
-
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
@@ -398,31 +358,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 }
 #endif
 
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
-	}
-
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-- 
cgit v1.2.3


From 9216477449f33cdbc9c9a99d49f500b7fbb81702 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 14 Jul 2020 15:56:38 +0200
Subject: bpf: cpumap: Add the possibility to attach an eBPF program to cpumap

Introduce the capability to attach an eBPF program to cpumap entries.
The idea behind this feature is to add the possibility to define on
which CPU run the eBPF program if the underlying hw does not support
RSS. Current supported verdicts are XDP_DROP and XDP_PASS.

This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu
sample available in the kernel tree to identify possible performance
regressions. Results show there are no observable differences in
packet-per-second:

$./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1
rx: 354.8 Kpps
rx: 356.0 Kpps
rx: 356.8 Kpps
rx: 356.3 Kpps
rx: 356.6 Kpps
rx: 356.6 Kpps
rx: 356.7 Kpps
rx: 355.8 Kpps
rx: 356.8 Kpps
rx: 356.8 Kpps

Co-developed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/5c9febdf903d810b3415732e5cd98491d7d9067a.1594734381.git.lorenzo@kernel.org
---
 include/linux/bpf.h            |   6 ++
 include/net/xdp.h              |   5 ++
 include/trace/events/xdp.h     |  14 +++--
 include/uapi/linux/bpf.h       |   5 ++
 kernel/bpf/cpumap.c            | 121 ++++++++++++++++++++++++++++++++++++-----
 net/core/dev.c                 |   9 +++
 tools/include/uapi/linux/bpf.h |   5 ++
 7 files changed, 148 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c67c88ad35f8..54ad426dbea1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1272,6 +1272,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_flush(void);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+bool cpu_map_prog_allowed(struct bpf_map *map);
 
 /* Return map's numa specified by userspace */
 static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
@@ -1432,6 +1433,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 	return 0;
 }
 
+static inline bool cpu_map_prog_allowed(struct bpf_map *map)
+{
+	return false;
+}
+
 static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
 				enum bpf_prog_type type)
 {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 5b383c450858..83b9e0142b52 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -98,6 +98,11 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+struct xdp_cpumap_stats {
+	unsigned int pass;
+	unsigned int drop;
+};
+
 /* Clear kernel pointers in xdp_frame */
 static inline void xdp_scrub_frame(struct xdp_frame *frame)
 {
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index b73d3e141323..e2c99f5bee39 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -177,9 +177,9 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 TRACE_EVENT(xdp_cpumap_kthread,
 
 	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
-		 int sched),
+		 int sched, struct xdp_cpumap_stats *xdp_stats),
 
-	TP_ARGS(map_id, processed, drops, sched),
+	TP_ARGS(map_id, processed, drops, sched, xdp_stats),
 
 	TP_STRUCT__entry(
 		__field(int, map_id)
@@ -188,6 +188,8 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__field(unsigned int, drops)
 		__field(unsigned int, processed)
 		__field(int, sched)
+		__field(unsigned int, xdp_pass)
+		__field(unsigned int, xdp_drop)
 	),
 
 	TP_fast_assign(
@@ -197,16 +199,20 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__entry->drops		= drops;
 		__entry->processed	= processed;
 		__entry->sched	= sched;
+		__entry->xdp_pass	= xdp_stats->pass;
+		__entry->xdp_drop	= xdp_stats->drop;
 	),
 
 	TP_printk("kthread"
 		  " cpu=%d map_id=%d action=%s"
 		  " processed=%u drops=%u"
-		  " sched=%d",
+		  " sched=%d"
+		  " xdp_pass=%u xdp_drop=%u",
 		  __entry->cpu, __entry->map_id,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->processed, __entry->drops,
-		  __entry->sched)
+		  __entry->sched,
+		  __entry->xdp_pass, __entry->xdp_drop)
 );
 
 TRACE_EVENT(xdp_cpumap_enqueue,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 109623527358..c010b57fce3f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -227,6 +227,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
 	BPF_CGROUP_INET_SOCK_RELEASE,
+	BPF_XDP_CPUMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3856,6 +3857,10 @@ struct bpf_devmap_val {
  */
 struct bpf_cpumap_val {
 	__u32 qsize;	/* queue size to remote target CPU */
+	union {
+		int   fd;	/* prog fd on map write */
+		__u32 id;	/* prog id on map read */
+	} bpf_prog;
 };
 
 enum sk_action {
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index ff48dc00e8d0..b3a8aea81ee5 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -63,6 +63,7 @@ struct bpf_cpu_map_entry {
 	struct task_struct *kthread;
 
 	struct bpf_cpumap_val value;
+	struct bpf_prog *prog;
 
 	atomic_t refcnt; /* Control when this struct can be free'ed */
 	struct rcu_head rcu;
@@ -82,6 +83,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq);
 
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
+	u32 value_size = attr->value_size;
 	struct bpf_cpu_map *cmap;
 	int err = -ENOMEM;
 	u64 cost;
@@ -92,7 +94,9 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    (value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
+	     value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) ||
+	    attr->map_flags & ~BPF_F_NUMA_NODE)
 		return ERR_PTR(-EINVAL);
 
 	cmap = kzalloc(sizeof(*cmap), GFP_USER);
@@ -214,6 +218,8 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 {
 	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		if (rcpu->prog)
+			bpf_prog_put(rcpu->prog);
 		/* The queue should be empty at this point */
 		__cpu_map_ring_cleanup(rcpu->queue);
 		ptr_ring_cleanup(rcpu->queue, NULL);
@@ -222,6 +228,62 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
+				    void **frames, int n,
+				    struct xdp_cpumap_stats *stats)
+{
+	struct xdp_rxq_info rxq;
+	struct xdp_buff xdp;
+	int i, nframes = 0;
+
+	if (!rcpu->prog)
+		return n;
+
+	rcu_read_lock();
+
+	xdp_set_return_frame_no_direct();
+	xdp.rxq = &rxq;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		u32 act;
+		int err;
+
+		rxq.dev = xdpf->dev_rx;
+		rxq.mem = xdpf->mem;
+		/* TODO: report queue_index to xdp_rxq_info */
+
+		xdp_convert_frame_to_buff(xdpf, &xdp);
+
+		act = bpf_prog_run_xdp(rcpu->prog, &xdp);
+		switch (act) {
+		case XDP_PASS:
+			err = xdp_update_frame_from_buff(&xdp, xdpf);
+			if (err < 0) {
+				xdp_return_frame(xdpf);
+				stats->drop++;
+			} else {
+				frames[nframes++] = xdpf;
+				stats->pass++;
+			}
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+			/* fallthrough */
+		case XDP_DROP:
+			xdp_return_frame(xdpf);
+			stats->drop++;
+			break;
+		}
+	}
+
+	xdp_clear_return_frame_no_direct();
+
+	rcu_read_unlock();
+
+	return nframes;
+}
+
 #define CPUMAP_BATCH 8
 
 static int cpu_map_kthread_run(void *data)
@@ -236,11 +298,12 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
 		unsigned int drops = 0, sched = 0;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		int i, n, m;
+		int i, n, m, nframes;
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -261,8 +324,8 @@ static int cpu_map_kthread_run(void *data)
 		 * kthread CPU pinned. Lockless access to ptr_ring
 		 * consume side valid as no-resize allowed of queue.
 		 */
-		n = __ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
-
+		n = __ptr_ring_consume_batched(rcpu->queue, frames,
+					       CPUMAP_BATCH);
 		for (i = 0; i < n; i++) {
 			void *f = frames[i];
 			struct page *page = virt_to_page(f);
@@ -274,15 +337,19 @@ static int cpu_map_kthread_run(void *data)
 			prefetchw(page);
 		}
 
-		m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs);
-		if (unlikely(m == 0)) {
-			for (i = 0; i < n; i++)
-				skbs[i] = NULL; /* effect: xdp_return_frame */
-			drops = n;
+		/* Support running another XDP prog on this CPU */
+		nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
+		if (nframes) {
+			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
+			if (unlikely(m == 0)) {
+				for (i = 0; i < nframes; i++)
+					skbs[i] = NULL; /* effect: xdp_return_frame */
+				drops += nframes;
+			}
 		}
 
 		local_bh_disable();
-		for (i = 0; i < n; i++) {
+		for (i = 0; i < nframes; i++) {
 			struct xdp_frame *xdpf = frames[i];
 			struct sk_buff *skb = skbs[i];
 			int ret;
@@ -299,7 +366,7 @@ static int cpu_map_kthread_run(void *data)
 				drops++;
 		}
 		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
@@ -309,13 +376,38 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
+bool cpu_map_prog_allowed(struct bpf_map *map)
+{
+	return map->map_type == BPF_MAP_TYPE_CPUMAP &&
+	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
+}
+
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+{
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	rcpu->value.bpf_prog.id = prog->aux->id;
+	rcpu->prog = prog;
+
+	return 0;
+}
+
 static struct bpf_cpu_map_entry *
 __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
 {
+	int numa, err, i, fd = value->bpf_prog.fd;
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	struct xdp_bulk_queue *bq;
-	int numa, err, i;
 
 	/* Have map->numa_node, but choose node of redirect target CPU */
 	numa = cpu_to_node(cpu);
@@ -357,6 +449,9 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
 	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
 	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
 
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+		goto free_ptr_ring;
+
 	/* Make sure kthread runs on a single CPU */
 	kthread_bind(rcpu->kthread, cpu);
 	wake_up_process(rcpu->kthread);
diff --git a/net/core/dev.c b/net/core/dev.c
index b61075828358..b820527f0a8d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5448,6 +5448,8 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
 			if (dev_map_can_have_prog(new->aux->used_maps[i]))
 				return -EINVAL;
+			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+				return -EINVAL;
 		}
 	}
 
@@ -8875,6 +8877,13 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_CPUMAP) {
+			NL_SET_ERR_MSG(extack,
+				       "BPF_XDP_CPUMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 109623527358..c010b57fce3f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -227,6 +227,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
 	BPF_CGROUP_INET_SOCK_RELEASE,
+	BPF_XDP_CPUMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3856,6 +3857,10 @@ struct bpf_devmap_val {
  */
 struct bpf_cpumap_val {
 	__u32 qsize;	/* queue size to remote target CPU */
+	union {
+		int   fd;	/* prog fd on map write */
+		__u32 id;	/* prog id on map read */
+	} bpf_prog;
 };
 
 enum sk_action {
-- 
cgit v1.2.3


From ecbe6bc0003bfd5bf8581cb679cae0eb944432cb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 16 Jul 2020 16:33:09 +0200
Subject: block: use bd_prepare_to_claim directly in the loop driver

The arcane magic in bd_start_claiming is only needed to be able to claim
a block_device that hasn't been fully set up.  Switch the loop driver
that claims from the ioctl path with a fully set up struct block_device
to just use the much simpler bd_prepare_to_claim directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c   | 7 +++----
 fs/block_dev.c         | 9 +++++----
 include/linux/blkdev.h | 3 ++-
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a943207705dd..d18160146226 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1090,11 +1090,10 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bd_start_claiming(bdev, loop_configure);
-		if (IS_ERR(claimed_bdev)) {
-			error = PTR_ERR(claimed_bdev);
+		claimed_bdev = bdev->bd_contains;
+		error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure);
+		if (error)
 			goto out_putf;
-		}
 	}
 
 	error = mutex_lock_killable(&loop_ctl_mutex);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b7b2ee4b288a..ee80bd81af74 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1027,8 +1027,8 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-static int bd_prepare_to_claim(struct block_device *bdev,
-			       struct block_device *whole, void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
+		void *holder)
 {
 retry:
 	spin_lock(&bdev_lock);
@@ -1055,6 +1055,7 @@ retry:
 	spin_unlock(&bdev_lock);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
 
 static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
 {
@@ -1100,7 +1101,8 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
  * Pointer to the block device containing @bdev on success, ERR_PTR()
  * value on failure.
  */
-struct block_device *bd_start_claiming(struct block_device *bdev, void *holder)
+static struct block_device *bd_start_claiming(struct block_device *bdev,
+		void *holder)
 {
 	struct gendisk *disk;
 	struct block_device *whole;
@@ -1141,7 +1143,6 @@ struct block_device *bd_start_claiming(struct block_device *bdev, void *holder)
 
 	return whole;
 }
-EXPORT_SYMBOL(bd_start_claiming);
 
 static void bd_clear_claiming(struct block_device *whole, void *holder)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 71173a1ffa8b..06995b96e946 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1919,7 +1919,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 		void *holder);
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-struct block_device *bd_start_claiming(struct block_device *bdev, void *holder);
+int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
+		void *holder);
 void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 		void *holder);
 void blkdev_put(struct block_device *bdev, fmode_t mode);
-- 
cgit v1.2.3


From aecfd220b223043475fa515aa563249f683fcd04 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 3 Jun 2020 13:28:45 -0700
Subject: x86/mm/numa: Remove uninitialized_var() usage

Using uninitialized_var() is dangerous as it papers over real bugs[1]
(or can in the future), and suppresses unrelated compiler warnings (e.g.
"unused variable"). If the compiler thinks it is uninitialized, either
simply initialize the variable or make compiler changes. As a precursor
to removing[2] this[3] macro[4], refactor code to avoid its need.

The original reason for its use here was to work around the #ifdef
being the only place the variable was used. This is better expressed
using IS_ENABLED() and a new code block where the variable can be used
unconditionally.

[1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/
[2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/
[3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/
[4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/

Fixes: 1e01979c8f50 ("x86, numa: Implement pfn -> nid mapping granularity check")
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/x86/mm/numa.c                | 18 +++++++++---------
 include/linux/page-flags-layout.h |  4 +++-
 2 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 8ee952038c80..b05f45e5e8e2 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -543,7 +543,6 @@ static void __init numa_clear_kernel_node_hotplug(void)
 
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
-	unsigned long uninitialized_var(pfn_align);
 	int i, nid;
 
 	/* Account for nodes with cpus and no memory */
@@ -571,15 +570,16 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	 * If sections array is gonna be used for pfn -> nid mapping, check
 	 * whether its granularity is fine enough.
 	 */
-#ifdef NODE_NOT_IN_PAGE_FLAGS
-	pfn_align = node_map_pfn_alignment();
-	if (pfn_align && pfn_align < PAGES_PER_SECTION) {
-		printk(KERN_WARNING "Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
-		       PFN_PHYS(pfn_align) >> 20,
-		       PFN_PHYS(PAGES_PER_SECTION) >> 20);
-		return -EINVAL;
+	if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) {
+		unsigned long pfn_align = node_map_pfn_alignment();
+
+		if (pfn_align && pfn_align < PAGES_PER_SECTION) {
+			pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
+				PFN_PHYS(pfn_align) >> 20,
+				PFN_PHYS(PAGES_PER_SECTION) >> 20);
+			return -EINVAL;
+		}
 	}
-#endif
 	if (!numa_meminfo_cover_memory(mi))
 		return -EINVAL;
 
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index 71283739ffd2..e200eef6a7fd 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -98,9 +98,11 @@
 /*
  * We are going to use the flags for the page to node mapping if its in
  * there.  This includes the case where there is no node, so it is implicit.
+ * Note that this #define MUST have a value so that it can be tested with
+ * the IS_ENABLED() macro.
  */
 #if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
-#define NODE_NOT_IN_PAGE_FLAGS
+#define NODE_NOT_IN_PAGE_FLAGS 1
 #endif
 
 #if defined(CONFIG_NUMA_BALANCING) && LAST_CPUPID_WIDTH == 0
-- 
cgit v1.2.3


From 63a0895d960aa3d3653ef0ecad5bd8579388f14b Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 3 Jun 2020 13:09:38 -0700
Subject: compiler: Remove uninitialized_var() macro

Using uninitialized_var() is dangerous as it papers over real bugs[1]
(or can in the future), and suppresses unrelated compiler warnings
(e.g. "unused variable"). If the compiler thinks it is uninitialized,
either simply initialize the variable or make compiler changes.

As recommended[2] by[3] Linus[4], remove the macro. With the recent
change to disable -Wmaybe-uninitialized in v5.7 in commit 78a5255ffb6a
("Stop the ad-hoc games with -Wno-maybe-initialized"), this is likely
the best time to make this treewide change.

[1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/
[2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/
[3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/
[4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Bart van Assche <bvanassche@acm.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/compiler-clang.h | 2 --
 include/linux/compiler-gcc.h   | 6 ------
 tools/include/linux/compiler.h | 2 --
 tools/virtio/linux/kernel.h    | 2 --
 4 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 5e55302e3bf6..8a072d00e688 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -5,8 +5,6 @@
 
 /* Compiler specific definitions for Clang compiler */
 
-#define uninitialized_var(x) x = *(&(x))
-
 /* same as gcc, this was present in clang-2.6 so we can assume it works
  * with any version that can compile the kernel
  */
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 1c74464c80c6..4099ac8b7f10 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -59,12 +59,6 @@
 	(typeof(ptr)) (__ptr + (off));					\
 })
 
-/*
- * A trick to suppress uninitialized variable warning without generating any
- * code
- */
-#define uninitialized_var(x) x = x
-
 #ifdef CONFIG_RETPOLINE
 #define __noretpoline __attribute__((__indirect_branch__("keep")))
 #endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 9f9002734e19..2f2f4082225e 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -111,8 +111,6 @@
 # define noinline
 #endif
 
-#define uninitialized_var(x) x = *(&(x))
-
 #include <linux/types.h>
 
 /*
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index caab980211a6..315e85cabeda 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -110,8 +110,6 @@ static inline void free_page(unsigned long addr)
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
 
-#define uninitialized_var(x) x = x
-
 # ifndef likely
 #  define likely(x)	(__builtin_expect(!!(x), 1))
 # endif
-- 
cgit v1.2.3


From 5be542e945cb39a2457aa2cfe8b84aac95ef0f2d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 16 Jul 2020 16:36:50 +1000
Subject: lockdep: Move list.h inclusion into lockdep.h

Currently lockdep_types.h includes list.h without actually using any
of its macros or functions.  All it needs are the type definitions
which were moved into types.h long ago.  This potentially causes
inclusion loops because both are included by many core header
files.

This patch moves the list.h inclusion into lockdep.h.  Note that
we could probably remove it completely but that could potentially
result in compile failures should any end users not include list.h
directly and also be unlucky enough to not get list.h via some other
header file.

Reported-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Petr Mladek <pmladek@suse.com>
Link: https://lkml.kernel.org/r/20200716063649.GA23065@gondor.apana.org.au
---
 include/linux/lockdep.h       | 1 +
 include/linux/lockdep_types.h | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index fd04b9e96091..7aafba0ddcf9 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -22,6 +22,7 @@ extern int lock_stat;
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
+#include <linux/list.h>
 #include <linux/debug_locks.h>
 #include <linux/stacktrace.h>
 
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 7b9350624577..bb35b449f533 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -32,8 +32,6 @@ enum lockdep_wait_type {
 
 #ifdef CONFIG_LOCKDEP
 
-#include <linux/list.h>
-
 /*
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
-- 
cgit v1.2.3


From a9232dc5607dbada801f2fe83ea307cda762969a Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sat, 11 Jul 2020 17:59:54 +0300
Subject: rwsem: fix commas in initialisation

Leading comma prevents arbitrary reordering of initialisation clauses.
The whole point of C99 initialisation is to allow any such reordering.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200711145954.GA1178171@localhost.localdomain
---
 include/linux/rwsem.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 7e5b2a4eb560..25e3fde85617 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -60,39 +60,39 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 }
 
 #define RWSEM_UNLOCKED_VALUE		0L
-#define __RWSEM_INIT_COUNT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
+#define __RWSEM_COUNT_INIT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
 
 /* Common initializer macros and functions */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __RWSEM_DEP_MAP_INIT(lockname)			\
-	, .dep_map = {					\
+	.dep_map = {					\
 		.name = #lockname,			\
 		.wait_type_inner = LD_WAIT_SLEEP,	\
-	}
+	},
 #else
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
 #ifdef CONFIG_DEBUG_RWSEMS
-# define __DEBUG_RWSEM_INITIALIZER(lockname) , .magic = &lockname
+# define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname,
 #else
-# define __DEBUG_RWSEM_INITIALIZER(lockname)
+# define __RWSEM_DEBUG_INIT(lockname)
 #endif
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED
+#define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED,
 #else
 #define __RWSEM_OPT_INIT(lockname)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
-	{ __RWSEM_INIT_COUNT(name),				\
+	{ __RWSEM_COUNT_INIT(name),				\
 	  .owner = ATOMIC_LONG_INIT(0),				\
-	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
-	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
-	  __DEBUG_RWSEM_INITIALIZER(name)			\
+	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\
+	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
+	  __RWSEM_DEBUG_INIT(name)				\
 	  __RWSEM_DEP_MAP_INIT(name) }
 
 #define DECLARE_RWSEM(name) \
-- 
cgit v1.2.3


From 6611561a7a7ef925294353a4c2124bdb66eb831c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:30:12 -0700
Subject: regmap: fix duplicated word in <linux/regmap.h>

Change doubled word "be" to "to be".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/7ef41bfc-de3e-073a-8746-0b3fdf7628c0@infradead.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regmap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e3817c097791..1970ed59d49f 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -275,7 +275,7 @@ typedef void (*regmap_unlock)(void *);
  *			readable if it belongs to one of the ranges specified
  *			by rd_noinc_table).
  * @disable_locking: This regmap is either protected by external means or
- *                   is guaranteed not be be accessed from multiple threads.
+ *                   is guaranteed not to be accessed from multiple threads.
  *                   Don't use any locking mechanisms.
  * @lock:	  Optional lock callback (overrides regmap's default lock
  *		  function, based on spinlock or mutex).
-- 
cgit v1.2.3


From 9a6ad1ad71fbc5a52617e016a3608d71b91f62e8 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Mon, 18 Nov 2019 14:30:20 +0200
Subject: net/mlx5: Accel, Add core IPsec support for the Connect-X family

This to set the base for downstream patches to support
the new IPsec implementation of the Connect-X family.

Following modifications made:
- Remove accel layer dependency from MLX5_FPGA_IPSEC.
- Introduce accel_ipsec_ops, each IPsec device will
  have to support these ops.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.c  | 103 +++++++++++++++------
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.h  |  45 +++++----
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   |   4 +-
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c   |  51 ++++++----
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.h   |  37 ++------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   9 +-
 include/linux/mlx5/accel.h                         |   6 +-
 include/linux/mlx5/driver.h                        |   3 +
 8 files changed, 154 insertions(+), 104 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index 8a4985d8cbfe..628c8887f086 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -31,37 +31,83 @@
  *
  */
 
-#ifdef CONFIG_MLX5_FPGA_IPSEC
-
 #include <linux/mlx5/device.h>
 
 #include "accel/ipsec.h"
 #include "mlx5_core.h"
 #include "fpga/ipsec.h"
 
+void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
+{
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mlx5_fpga_ipsec_ops(mdev);
+	int err = 0;
+
+	if (!ipsec_ops || !ipsec_ops->init) {
+		mlx5_core_dbg(mdev, "IPsec ops is not supported\n");
+		return;
+	}
+
+	err = ipsec_ops->init(mdev);
+	if (err) {
+		mlx5_core_warn_once(mdev, "Failed to start IPsec device, err = %d\n", err);
+		return;
+	}
+
+	mdev->ipsec_ops = ipsec_ops;
+}
+
+void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
+{
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->cleanup)
+		return;
+
+	ipsec_ops->cleanup(mdev);
+}
+
 u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev)
 {
-	return mlx5_fpga_ipsec_device_caps(mdev);
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->device_caps)
+		return 0;
+
+	return ipsec_ops->device_caps(mdev);
 }
 EXPORT_SYMBOL_GPL(mlx5_accel_ipsec_device_caps);
 
 unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev)
 {
-	return mlx5_fpga_ipsec_counters_count(mdev);
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->counters_count)
+		return -EOPNOTSUPP;
+
+	return ipsec_ops->counters_count(mdev);
 }
 
 int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 				   unsigned int count)
 {
-	return mlx5_fpga_ipsec_counters_read(mdev, counters, count);
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->counters_read)
+		return -EOPNOTSUPP;
+
+	return ipsec_ops->counters_read(mdev, counters, count);
 }
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle)
 {
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	__be32 saddr[4] = {}, daddr[4] = {};
 
+	if (!ipsec_ops || !ipsec_ops->create_hw_context)
+		return  ERR_PTR(-EOPNOTSUPP);
+
 	if (!xfrm->attrs.is_ipv6) {
 		saddr[3] = xfrm->attrs.saddr.a4;
 		daddr[3] = xfrm->attrs.daddr.a4;
@@ -70,29 +116,18 @@ void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 		memcpy(daddr, xfrm->attrs.daddr.a6, sizeof(daddr));
 	}
 
-	return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr,
-					     daddr, xfrm->attrs.spi,
-					     xfrm->attrs.is_ipv6, sa_handle);
+	return ipsec_ops->create_hw_context(mdev, xfrm, saddr, daddr, xfrm->attrs.spi,
+					    xfrm->attrs.is_ipv6, sa_handle);
 }
 
-void mlx5_accel_esp_free_hw_context(void *context)
+void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context)
 {
-	mlx5_fpga_ipsec_delete_sa_ctx(context);
-}
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 
-int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	return mlx5_fpga_ipsec_init(mdev);
-}
-
-void mlx5_accel_ipsec_build_fs_cmds(void)
-{
-	mlx5_fpga_ipsec_build_fs_cmds();
-}
+	if (!ipsec_ops || !ipsec_ops->free_hw_context)
+		return;
 
-void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-	mlx5_fpga_ipsec_cleanup(mdev);
+	ipsec_ops->free_hw_context(context);
 }
 
 struct mlx5_accel_esp_xfrm *
@@ -100,9 +135,13 @@ mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs,
 			   u32 flags)
 {
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	struct mlx5_accel_esp_xfrm *xfrm;
 
-	xfrm = mlx5_fpga_esp_create_xfrm(mdev, attrs, flags);
+	if (!ipsec_ops || !ipsec_ops->esp_create_xfrm)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	xfrm = ipsec_ops->esp_create_xfrm(mdev, attrs, flags);
 	if (IS_ERR(xfrm))
 		return xfrm;
 
@@ -113,15 +152,23 @@ EXPORT_SYMBOL_GPL(mlx5_accel_esp_create_xfrm);
 
 void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 {
-	mlx5_fpga_esp_destroy_xfrm(xfrm);
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->esp_destroy_xfrm)
+		return;
+
+	ipsec_ops->esp_destroy_xfrm(xfrm);
 }
 EXPORT_SYMBOL_GPL(mlx5_accel_esp_destroy_xfrm);
 
 int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			       const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	return mlx5_fpga_esp_modify_xfrm(xfrm, attrs);
+	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
+
+	if (!ipsec_ops || !ipsec_ops->esp_modify_xfrm)
+		return -EOPNOTSUPP;
+
+	return ipsec_ops->esp_modify_xfrm(xfrm, attrs);
 }
 EXPORT_SYMBOL_GPL(mlx5_accel_esp_modify_xfrm);
-
-#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
index e89747674712..fbb9c5415d53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
@@ -37,7 +37,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_FPGA_IPSEC
+#ifdef CONFIG_MLX5_ACCEL
 
 #define MLX5_IPSEC_DEV(mdev) (mlx5_accel_ipsec_device_caps(mdev) & \
 			      MLX5_ACCEL_IPSEC_CAP_DEVICE)
@@ -49,12 +49,30 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle);
-void mlx5_accel_esp_free_hw_context(void *context);
+void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context);
 
-int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
-void mlx5_accel_ipsec_build_fs_cmds(void);
+void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
 void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
 
+struct mlx5_accel_ipsec_ops {
+	u32 (*device_caps)(struct mlx5_core_dev *mdev);
+	unsigned int (*counters_count)(struct mlx5_core_dev *mdev);
+	int (*counters_read)(struct mlx5_core_dev *mdev, u64 *counters, unsigned int count);
+	void* (*create_hw_context)(struct mlx5_core_dev *mdev,
+				   struct mlx5_accel_esp_xfrm *xfrm,
+				   const __be32 saddr[4], const __be32 daddr[4],
+				   const __be32 spi, bool is_ipv6, u32 *sa_handle);
+	void (*free_hw_context)(void *context);
+	int (*init)(struct mlx5_core_dev *mdev);
+	void (*cleanup)(struct mlx5_core_dev *mdev);
+	struct mlx5_accel_esp_xfrm* (*esp_create_xfrm)(struct mlx5_core_dev *mdev,
+						       const struct mlx5_accel_esp_xfrm_attrs *attrs,
+						       u32 flags);
+	int (*esp_modify_xfrm)(struct mlx5_accel_esp_xfrm *xfrm,
+			       const struct mlx5_accel_esp_xfrm_attrs *attrs);
+	void (*esp_destroy_xfrm)(struct mlx5_accel_esp_xfrm *xfrm);
+};
+
 #else
 
 #define MLX5_IPSEC_DEV(mdev) false
@@ -67,23 +85,12 @@ mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 	return NULL;
 }
 
-static inline void mlx5_accel_esp_free_hw_context(void *context)
-{
-}
-
-static inline int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
+static inline void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context) {}
 
-static inline void mlx5_accel_ipsec_build_fs_cmds(void)
-{
-}
+static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
 
-static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-}
+static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
 
-#endif
+#endif /* CONFIG_MLX5_ACCEL */
 
 #endif	/* __MLX5_ACCEL_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index bc55c82b55ba..8d797cd56e26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -342,7 +342,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 	goto out;
 
 err_hw_ctx:
-	mlx5_accel_esp_free_hw_context(sa_entry->hw_context);
+	mlx5_accel_esp_free_hw_context(priv->mdev, sa_entry->hw_context);
 err_xfrm:
 	mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm);
 err_sa_entry:
@@ -372,7 +372,7 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 
 	if (sa_entry->hw_context) {
 		flush_workqueue(sa_entry->ipsec->wq);
-		mlx5_accel_esp_free_hw_context(sa_entry->hw_context);
+		mlx5_accel_esp_free_hw_context(sa_entry->xfrm->mdev, sa_entry->hw_context);
 		mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index b463787d6ca1..cc67366495b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -359,7 +359,7 @@ u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	return ret;
 }
 
-unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev)
+static unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 
@@ -370,8 +370,8 @@ unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev)
 			number_of_ipsec_counters);
 }
 
-int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				  unsigned int counters_count)
+static int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
+					 unsigned int counters_count)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 	unsigned int i;
@@ -665,12 +665,10 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
 	return true;
 }
 
-void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
-				    struct mlx5_accel_esp_xfrm *accel_xfrm,
-				    const __be32 saddr[4],
-				    const __be32 daddr[4],
-				    const __be32 spi, bool is_ipv6,
-				    u32 *sa_handle)
+static void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
+					   struct mlx5_accel_esp_xfrm *accel_xfrm,
+					   const __be32 saddr[4], const __be32 daddr[4],
+					   const __be32 spi, bool is_ipv6, u32 *sa_handle)
 {
 	struct mlx5_fpga_ipsec_sa_ctx *sa_ctx;
 	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
@@ -862,7 +860,7 @@ mlx5_fpga_ipsec_release_sa_ctx(struct mlx5_fpga_ipsec_sa_ctx *sa_ctx)
 	mutex_unlock(&fipsec->sa_hash_lock);
 }
 
-void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
+static void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
 {
 	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
 			((struct mlx5_fpga_ipsec_sa_ctx *)context)->fpga_xfrm;
@@ -1264,7 +1262,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flo
 	}
 }
 
-int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev)
+static int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_fpga_conn_attr init_attr = {0};
 	struct mlx5_fpga_device *fdev = mdev->fpga;
@@ -1346,7 +1344,7 @@ static void destroy_rules_rb(struct rb_root *root)
 	}
 }
 
-void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev)
+static void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 
@@ -1451,7 +1449,7 @@ mlx5_fpga_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
 	return 0;
 }
 
-struct mlx5_accel_esp_xfrm *
+static struct mlx5_accel_esp_xfrm *
 mlx5_fpga_esp_create_xfrm(struct mlx5_core_dev *mdev,
 			  const struct mlx5_accel_esp_xfrm_attrs *attrs,
 			  u32 flags)
@@ -1479,7 +1477,7 @@ mlx5_fpga_esp_create_xfrm(struct mlx5_core_dev *mdev,
 	return &fpga_xfrm->accel_xfrm;
 }
 
-void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
+static void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 {
 	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
 			container_of(xfrm, struct mlx5_fpga_esp_xfrm,
@@ -1488,8 +1486,8 @@ void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 	kfree(fpga_xfrm);
 }
 
-int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			      const struct mlx5_accel_esp_xfrm_attrs *attrs)
+static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
+				     const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = xfrm->mdev;
 	struct mlx5_fpga_device *fdev = mdev->fpga;
@@ -1560,3 +1558,24 @@ change_sw_xfrm_attrs:
 	mutex_unlock(&fpga_xfrm->lock);
 	return err;
 }
+
+static const struct mlx5_accel_ipsec_ops fpga_ipsec_ops = {
+	.device_caps = mlx5_fpga_ipsec_device_caps,
+	.counters_count = mlx5_fpga_ipsec_counters_count,
+	.counters_read = mlx5_fpga_ipsec_counters_read,
+	.create_hw_context = mlx5_fpga_ipsec_create_sa_ctx,
+	.free_hw_context = mlx5_fpga_ipsec_delete_sa_ctx,
+	.init = mlx5_fpga_ipsec_init,
+	.cleanup = mlx5_fpga_ipsec_cleanup,
+	.esp_create_xfrm = mlx5_fpga_esp_create_xfrm,
+	.esp_modify_xfrm = mlx5_fpga_esp_modify_xfrm,
+	.esp_destroy_xfrm = mlx5_fpga_esp_destroy_xfrm,
+};
+
+const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev)
+{
+	if (!mlx5_fpga_is_ipsec_device(mdev))
+		return NULL;
+
+	return &fpga_ipsec_ops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
index 9ba637f0f0f2..db88eb4c49e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
@@ -38,44 +38,23 @@
 #include "fs_cmd.h"
 
 #ifdef CONFIG_MLX5_FPGA_IPSEC
+const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev);
 u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev);
-unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev);
-int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				  unsigned int counters_count);
-
-void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
-				    struct mlx5_accel_esp_xfrm *accel_xfrm,
-				    const __be32 saddr[4],
-				    const __be32 daddr[4],
-				    const __be32 spi, bool is_ipv6,
-				    u32 *sa_handle);
-void mlx5_fpga_ipsec_delete_sa_ctx(void *context);
-
-int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev);
-void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev);
-void mlx5_fpga_ipsec_build_fs_cmds(void);
-
-struct mlx5_accel_esp_xfrm *
-mlx5_fpga_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			  const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			  u32 flags);
-void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
-int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			      const struct mlx5_accel_esp_xfrm_attrs *attrs);
-
 const struct mlx5_flow_cmds *
 mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type);
+void mlx5_fpga_ipsec_build_fs_cmds(void);
 #else
-static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
+static inline
+const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev)
+{ return NULL; }
+static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; }
 static inline const struct mlx5_flow_cmds *
 mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type)
 {
 	return mlx5_fs_cmd_get_default(type);
 }
 
+static inline void mlx5_fpga_ipsec_build_fs_cmds(void) {};
+
 #endif /* CONFIG_MLX5_FPGA_IPSEC */
 #endif	/* __MLX5_FPGA_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 8b658908f044..e32d46c33701 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1089,11 +1089,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fpga_start;
 	}
 
-	err = mlx5_accel_ipsec_init(dev);
-	if (err) {
-		mlx5_core_err(dev, "IPSec device start failed %d\n", err);
-		goto err_ipsec_start;
-	}
+	mlx5_accel_ipsec_init(dev);
 
 	err = mlx5_accel_tls_init(dev);
 	if (err) {
@@ -1135,7 +1131,6 @@ err_fs:
 	mlx5_accel_tls_cleanup(dev);
 err_tls_start:
 	mlx5_accel_ipsec_cleanup(dev);
-err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
 err_fpga_start:
 	mlx5_rsc_dump_cleanup(dev);
@@ -1628,7 +1623,7 @@ static int __init init(void)
 	get_random_bytes(&sw_owner_id, sizeof(sw_owner_id));
 
 	mlx5_core_verify_params();
-	mlx5_accel_ipsec_build_fs_cmds();
+	mlx5_fpga_ipsec_build_fs_cmds();
 	mlx5_register_debugfs();
 
 	err = pci_register_driver(&mlx5_core_driver);
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 96ebaa94a92e..dacf69516002 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -126,7 +126,7 @@ enum mlx5_accel_ipsec_cap {
 	MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN	= 1 << 7,
 };
 
-#ifdef CONFIG_MLX5_FPGA_IPSEC
+#ifdef CONFIG_MLX5_ACCEL
 
 u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev);
 
@@ -152,5 +152,5 @@ static inline int
 mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; }
 
-#endif
-#endif
+#endif /* CONFIG_MLX5_ACCEL */
+#endif /* __MLX5_ACCEL_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1e6ca716635a..6a97ad601991 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -707,6 +707,9 @@ struct mlx5_core_dev {
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
+#endif
+#ifdef CONFIG_MLX5_ACCEL
+	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 #endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
-- 
cgit v1.2.3


From 78fb6122fa2b6b55fafee1b32cd94913ad72f8a4 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Wed, 8 Apr 2020 20:09:05 -0500
Subject: net/mlx5: Add IPsec related Flow steering entry's fields

Add FTE actions IPsec ENCRYPT/DECRYPT
Add ipsec_obj_id field in FTE
Add new action field MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/fs.h       |  5 ++++-
 include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++--
 2 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 6c5aa0a21425..92d991d93757 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -207,7 +207,10 @@ struct mlx5_flow_act {
 	u32 action;
 	struct mlx5_modify_hdr  *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
-	uintptr_t esp_id;
+	union {
+		u32 ipsec_obj_id;
+		uintptr_t esp_id;
+	};
 	u32 flags;
 	struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH];
 	struct ib_counters *counters;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 791766e15d5c..9e64710bc54f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -416,7 +416,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   table_miss_action_domain[0x1];
 	u8         termination_table[0x1];
 	u8         reformat_and_fwd_to_table[0x1];
-	u8         reserved_at_1a[0x6];
+	u8         reserved_at_1a[0x2];
+	u8         ipsec_encrypt[0x1];
+	u8         ipsec_decrypt[0x1];
+	u8         reserved_at_1e[0x2];
+
 	u8         termination_table_raw_traffic[0x1];
 	u8         reserved_at_21[0x1];
 	u8         log_max_ft_size[0x6];
@@ -2965,6 +2969,8 @@ enum {
 	MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100,
 	MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2  = 0x400,
 	MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800,
+	MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000,
+	MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000,
 };
 
 enum {
@@ -3006,7 +3012,8 @@ struct mlx5_ifc_flow_context_bits {
 
 	struct mlx5_ifc_vlan_bits push_vlan_2;
 
-	u8         reserved_at_120[0xe0];
+	u8         ipsec_obj_id[0x20];
+	u8         reserved_at_140[0xc0];
 
 	struct mlx5_ifc_fte_match_param_bits match_value;
 
@@ -5752,6 +5759,7 @@ enum {
 	MLX5_ACTION_IN_FIELD_METADATA_REG_C_7  = 0x58,
 	MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM   = 0x59,
 	MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM   = 0x5B,
+	MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME    = 0x5D,
 };
 
 struct mlx5_ifc_alloc_modify_header_context_out_bits {
-- 
cgit v1.2.3


From 2ae3de10abfe0be40c9d93ebc2f429b969abf008 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:30:48 -0700
Subject: spi: fix duplicated word in <linux/spi/spi.h>

Change doubled word "as" to "as a".

Change "Return: Return:" in kernel-doc notation to have only one
"Return:".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: linux-spi@vger.kernel.org
Link: https://lore.kernel.org/r/40354d64-be71-3952-a980-63a76a278145@infradead.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 5fcf5da13fdb..f8b721fcd5c6 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -971,7 +971,7 @@ struct spi_transfer {
  * each represented by a struct spi_transfer.  The sequence is "atomic"
  * in the sense that no other spi_message may use that SPI bus until that
  * sequence completes.  On some systems, many such sequences can execute as
- * as single programmed DMA transfer.  On all systems, these messages are
+ * a single programmed DMA transfer.  On all systems, these messages are
  * queued, and might complete after transactions to other devices.  Messages
  * sent to a given spi_device are always executed in FIFO order.
  *
@@ -1234,7 +1234,7 @@ extern int spi_bus_unlock(struct spi_controller *ctlr);
  *
  * For more specific semantics see spi_sync().
  *
- * Return: Return: zero on success, else a negative error code.
+ * Return: zero on success, else a negative error code.
  */
 static inline int
 spi_sync_transfer(struct spi_device *spi, struct spi_transfer *xfers,
-- 
cgit v1.2.3


From e2e5c55eed8023ecfbf4c9b623ef7dec343d1845 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Tue, 14 Jul 2020 13:50:27 -0600
Subject: remoteproc: Add new RPROC_DETACHED state

Add a new RPROC_DETACHED state to take into account scenarios
where the remoteproc core needs to attach to a remote processor
that is booted by another entity.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Link: https://lore.kernel.org/r/20200714195035.1426873-2-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_sysfs.c | 1 +
 include/linux/remoteproc.h            | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index 52b871327b55..264759713934 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -72,6 +72,7 @@ static const char * const rproc_state_string[] = {
 	[RPROC_RUNNING]		= "running",
 	[RPROC_CRASHED]		= "crashed",
 	[RPROC_DELETED]		= "deleted",
+	[RPROC_DETACHED]	= "detached",
 	[RPROC_LAST]		= "invalid",
 };
 
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index e7b7bab8b235..21182ad2d059 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -400,6 +400,8 @@ struct rproc_ops {
  * @RPROC_RUNNING:	device is up and running
  * @RPROC_CRASHED:	device has crashed; need to start recovery
  * @RPROC_DELETED:	device is deleted
+ * @RPROC_DETACHED:	device has been booted by another entity and waiting
+ *			for the core to attach to it
  * @RPROC_LAST:		just keep this one at the end
  *
  * Please note that the values of these states are used as indices
@@ -414,7 +416,8 @@ enum rproc_state {
 	RPROC_RUNNING	= 2,
 	RPROC_CRASHED	= 3,
 	RPROC_DELETED	= 4,
-	RPROC_LAST	= 5,
+	RPROC_DETACHED	= 5,
+	RPROC_LAST	= 6,
 };
 
 /**
-- 
cgit v1.2.3


From a6a4f2857524007848f7957af432cddb4d43b593 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Tue, 14 Jul 2020 13:50:28 -0600
Subject: remoteproc: Add new attach() remoteproc operation

Add an new attach() operation in order to properly deal with
scenarios where the remoteproc core needs to attach to a
remote processor that has been booted by another entity.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Link: https://lore.kernel.org/r/20200714195035.1426873-3-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_internal.h | 8 ++++++++
 include/linux/remoteproc.h               | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h
index 4ba7cb59d3e8..fc710866f8ce 100644
--- a/drivers/remoteproc/remoteproc_internal.h
+++ b/drivers/remoteproc/remoteproc_internal.h
@@ -79,6 +79,14 @@ static inline int rproc_unprepare_device(struct rproc *rproc)
 	return 0;
 }
 
+static inline int rproc_attach_device(struct rproc *rproc)
+{
+	if (rproc->ops->attach)
+		return rproc->ops->attach(rproc);
+
+	return 0;
+}
+
 static inline
 int rproc_fw_sanity_check(struct rproc *rproc, const struct firmware *fw)
 {
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 21182ad2d059..bf6a310ba870 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -359,6 +359,7 @@ enum rsc_handling_status {
  * @unprepare:	unprepare device after stop
  * @start:	power on the device and boot it
  * @stop:	power off the device
+ * @attach:	attach to a device that his already powered up
  * @kick:	kick a virtqueue (virtqueue id given as a parameter)
  * @da_to_va:	optional platform hook to perform address translations
  * @parse_fw:	parse firmware to extract information (e.g. resource table)
@@ -379,6 +380,7 @@ struct rproc_ops {
 	int (*unprepare)(struct rproc *rproc);
 	int (*start)(struct rproc *rproc);
 	int (*stop)(struct rproc *rproc);
+	int (*attach)(struct rproc *rproc);
 	void (*kick)(struct rproc *rproc, int vqid);
 	void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len);
 	int (*parse_fw)(struct rproc *rproc, const struct firmware *fw);
-- 
cgit v1.2.3


From 4a4dca1941fedc1b02635ff0b4ed51b9857d0382 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Tue, 14 Jul 2020 13:50:35 -0600
Subject: remoteproc: Properly handle firmware name when attaching

This patch prevents the firmware image name from being displayed when
the remoteproc core is attaching to a remote processor. This is needed
needed since there is no guarantee about the nature of the firmware
image that is loaded by the external entity.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Link: https://lore.kernel.org/r/20200714195035.1426873-10-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_core.c  | 18 ++++++++++++++++++
 drivers/remoteproc/remoteproc_sysfs.c | 16 ++++++++++++++--
 include/linux/remoteproc.h            |  2 ++
 3 files changed, 34 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 565778ccb39c..1b52004655ab 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1627,6 +1627,14 @@ static int rproc_stop(struct rproc *rproc, bool crashed)
 
 	rproc->state = RPROC_OFFLINE;
 
+	/*
+	 * The remote processor has been stopped and is now offline, which means
+	 * that the next time it is brought back online the remoteproc core will
+	 * be responsible to load its firmware.  As such it is no longer
+	 * autonomous.
+	 */
+	rproc->autonomous = false;
+
 	dev_info(dev, "stopped remote processor %s\n", rproc->name);
 
 	return 0;
@@ -2145,6 +2153,16 @@ int rproc_add(struct rproc *rproc)
 	/* create debugfs entries */
 	rproc_create_debug_dir(rproc);
 
+	/*
+	 * Remind ourselves the remote processor has been attached to rather
+	 * than booted by the remoteproc core.  This is important because the
+	 * RPROC_DETACHED state will be lost as soon as the remote processor
+	 * has been attached to.  Used in firmware_show() and reset in
+	 * rproc_stop().
+	 */
+	if (rproc->state == RPROC_DETACHED)
+		rproc->autonomous = true;
+
 	/* if rproc is marked always-on, request it to boot */
 	if (rproc->auto_boot) {
 		ret = rproc_trigger_auto_boot(rproc);
diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index 264759713934..eea514cec50e 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -15,8 +15,20 @@ static ssize_t firmware_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	struct rproc *rproc = to_rproc(dev);
-
-	return sprintf(buf, "%s\n", rproc->firmware);
+	const char *firmware = rproc->firmware;
+
+	/*
+	 * If the remote processor has been started by an external
+	 * entity we have no idea of what image it is running.  As such
+	 * simply display a generic string rather then rproc->firmware.
+	 *
+	 * Here we rely on the autonomous flag because a remote processor
+	 * may have been attached to and currently in a running state.
+	 */
+	if (rproc->autonomous)
+		firmware = "unknown";
+
+	return sprintf(buf, "%s\n", firmware);
 }
 
 /* Change firmware name via sysfs */
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index bf6a310ba870..cf5e31556780 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -491,6 +491,7 @@ struct rproc_dump_segment {
  * @table_sz: size of @cached_table
  * @has_iommu: flag to indicate if remote processor is behind an MMU
  * @auto_boot: flag to indicate if remote processor should be auto-started
+ * @autonomous: true if an external entity has booted the remote processor
  * @dump_segments: list of segments in the firmware
  * @nb_vdev: number of vdev currently handled by rproc
  */
@@ -524,6 +525,7 @@ struct rproc {
 	size_t table_sz;
 	bool has_iommu;
 	bool auto_boot;
+	bool autonomous;
 	struct list_head dump_segments;
 	int nb_vdev;
 	u8 elf_class;
-- 
cgit v1.2.3


From 9c8ebd8b82da89c2484594b61d66288d24983348 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 17 Jul 2020 04:33:34 +0300
Subject: dmaengine: Add support for repeating transactions

DMA engines used with displays perform 2D interleaved transfers to read
framebuffers from memory and feed the data to the display engine. As the
same framebuffer can be displayed for multiple frames, the DMA
transactions need to be repeated until a new framebuffer replaces the
current one. This feature is implemented natively by some DMA engines
that have the ability to repeat transactions and switch to a new
transaction at the end of a transfer without any race condition or frame
loss.

This patch implements support for this feature in the DMA engine API. A
new DMA_PREP_REPEAT transaction flag allows DMA clients to instruct the
DMA channel to repeat the transaction automatically until one or more
new transactions are issued on the channel (or until all active DMA
transfers are explicitly terminated with the dmaengine_terminate_*()
functions). A new DMA_REPEAT transaction type is also added for DMA
engine drivers to report their support of the DMA_PREP_REPEAT flag.

A new DMA_PREP_LOAD_EOT transaction flag is also introduced (with a
corresponding DMA_LOAD_EOT capability bit), as requested during the
review of v4. The flag instructs the DMA channel that the transaction
being queued should replace the active repeated transaction when the
latter terminates (at End Of Transaction). Not setting the flag will
result in the active repeated transaction to continue being repeated,
and the new transaction being silently ignored.

The DMA_PREP_REPEAT flag is currently supported for interleaved
transactions only. Its usage can easily be extended to cover more
transaction types simply by adding an appropriate check in the
corresponding dmaengine_prep_*() function.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20200717013337.24122-3-laurent.pinchart@ideasonboard.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/driver-api/dmaengine/client.rst   |  4 +-
 Documentation/driver-api/dmaengine/provider.rst | 49 +++++++++++++++++++++++++
 include/linux/dmaengine.h                       | 17 +++++++++
 3 files changed, 69 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dmaengine/client.rst b/Documentation/driver-api/dmaengine/client.rst
index 2104830a99ae..41938aa2bdeb 100644
--- a/Documentation/driver-api/dmaengine/client.rst
+++ b/Documentation/driver-api/dmaengine/client.rst
@@ -86,7 +86,9 @@ The details of these operations are:
   - interleaved_dma: This is common to Slave as well as M2M clients. For slave
     address of devices' fifo could be already known to the driver.
     Various types of operations could be expressed by setting
-    appropriate values to the 'dma_interleaved_template' members.
+    appropriate values to the 'dma_interleaved_template' members. Cyclic
+    interleaved DMA transfers are also possible if supported by the channel by
+    setting the DMA_PREP_REPEAT transfer flag.
 
   A non-NULL return of this transfer API represents a "descriptor" for
   the given transaction.
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 56e5833e8a07..f896acccdfee 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -239,6 +239,27 @@ Currently, the types available are:
     want to transfer a portion of uncompressed data directly to the
     display to print it
 
+- DMA_REPEAT
+
+  - The device supports repeated transfers. A repeated transfer, indicated by
+    the DMA_PREP_REPEAT transfer flag, is similar to a cyclic transfer in that
+    it gets automatically repeated when it ends, but can additionally be
+    replaced by the client.
+
+  - This feature is limited to interleaved transfers, this flag should thus not
+    be set if the DMA_INTERLEAVE flag isn't set. This limitation is based on
+    the current needs of DMA clients, support for additional transfer types
+    should be added in the future if and when the need arises.
+
+- DMA_LOAD_EOT
+
+  - The device supports replacing repeated transfers at end of transfer (EOT)
+    by queuing a new transfer with the DMA_PREP_LOAD_EOT flag set.
+
+  - Support for replacing a currently running transfer at another point (such
+    as end of burst instead of end of transfer) will be added in the future
+    based on DMA clients needs, if and when the need arises.
+
 These various types will also affect how the source and destination
 addresses change over time.
 
@@ -531,6 +552,34 @@ DMA_CTRL_REUSE
     writes for which the descriptor should be in different format from
     normal data descriptors.
 
+- DMA_PREP_REPEAT
+
+  - If set, the transfer will be automatically repeated when it ends until a
+    new transfer is queued on the same channel with the DMA_PREP_LOAD_EOT flag.
+    If the next transfer to be queued on the channel does not have the
+    DMA_PREP_LOAD_EOT flag set, the current transfer will be repeated until the
+    client terminates all transfers.
+
+  - This flag is only supported if the channel reports the DMA_REPEAT
+    capability.
+
+- DMA_PREP_LOAD_EOT
+
+  - If set, the transfer will replace the transfer currently being executed at
+    the end of the transfer.
+
+  - This is the default behaviour for non-repeated transfers, specifying
+    DMA_PREP_LOAD_EOT for non-repeated transfers will thus make no difference.
+
+  - When using repeated transfers, DMA clients will usually need to set the
+    DMA_PREP_LOAD_EOT flag on all transfers, otherwise the channel will keep
+    repeating the last repeated transfer and ignore the new transfers being
+    queued. Failure to set DMA_PREP_LOAD_EOT will appear as if the channel was
+    stuck on the previous transfer.
+
+  - This flag is only supported if the channel reports the DMA_LOAD_EOT
+    capability.
+
 General Design Notes
 ====================
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index e1c03339918f..328e3aca7f51 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -61,6 +61,8 @@ enum dma_transaction_type {
 	DMA_SLAVE,
 	DMA_CYCLIC,
 	DMA_INTERLEAVE,
+	DMA_REPEAT,
+	DMA_LOAD_EOT,
 /* last transaction type for creation of the capabilities mask */
 	DMA_TX_TYPE_END,
 };
@@ -176,6 +178,16 @@ struct dma_interleaved_template {
  * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command
  *  data and the descriptor should be in different format from normal
  *  data descriptors.
+ * @DMA_PREP_REPEAT: tell the driver that the transaction shall be automatically
+ *  repeated when it ends until a transaction is issued on the same channel
+ *  with the DMA_PREP_LOAD_EOT flag set. This flag is only applicable to
+ *  interleaved transactions and is ignored for all other transaction types.
+ * @DMA_PREP_LOAD_EOT: tell the driver that the transaction shall replace any
+ *  active repeated (as indicated by DMA_PREP_REPEAT) transaction when the
+ *  repeated transaction ends. Not setting this flag when the previously queued
+ *  transaction is marked with DMA_PREP_REPEAT will cause the new transaction
+ *  to never be processed and stay in the issued queue forever. The flag is
+ *  ignored if the previous transaction is not a repeated transaction.
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
@@ -186,6 +198,8 @@ enum dma_ctrl_flags {
 	DMA_PREP_FENCE = (1 << 5),
 	DMA_CTRL_REUSE = (1 << 6),
 	DMA_PREP_CMD = (1 << 7),
+	DMA_PREP_REPEAT = (1 << 8),
+	DMA_PREP_LOAD_EOT = (1 << 9),
 };
 
 /**
@@ -980,6 +994,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
 {
 	if (!chan || !chan->device || !chan->device->device_prep_interleaved_dma)
 		return NULL;
+	if (flags & DMA_PREP_REPEAT &&
+	    !test_bit(DMA_REPEAT, chan->device->cap_mask.bits))
+		return NULL;
 
 	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
 }
-- 
cgit v1.2.3


From ecdef9f459ad24bf987267df6c25967819016707 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Fri, 17 Jul 2020 10:42:29 +0800
Subject: block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd
 numbers

Currently REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are defined as
even numbers 6 and 8, such zone reset bios are treated as READ bios by
bio_data_dir(), which is obviously misleading.

The macro bio_data_dir() is defined in include/linux/bio.h as,
 55 #define bio_data_dir(bio) \
 56         (op_is_write(bio_op(bio)) ? WRITE : READ)

And op_is_write() is defined in include/linux/blk_types.h as,
397 static inline bool op_is_write(unsigned int op)
398 {
399         return (op & 1);
400 }

The convention of op_is_write() is when there is data transfer then the
op code should be odd number, and treat as a write op. bio_data_dir()
treats all bio direction as READ if op_is_write() reports false, and
WRITE if op_is_write() reports true.

Because REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are even numbers,
although they don't transfer data but reporting them as READ bio by
bio_data_dir() is misleading and might be wrong. Because these two
commands will reset the writer pointers of the resetting zones, and all
content after the reset write pointer will be invalid and unaccessible,
obviously they are not READ bios in any means.

This patch changes REQ_OP_ZONE_RESET from 6 to 15, and changes
REQ_OP_ZONE_RESET_ALL from 8 to 17. Now bios with these two op code
can be treated as WRITE by bio_data_dir(). Although they don't transfer
data, now we keep them consistent with REQ_OP_DISCARD and
REQ_OP_WRITE_ZEROES with the ituition that they change on-media content
and should be WRITE request.

Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Jens Axboe <axboe@fb.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Shaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 07facaf62b72..4ecf4fed171f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -327,12 +327,8 @@ enum req_opf {
 	REQ_OP_DISCARD		= 3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= 5,
-	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= 6,
 	/* write the same sector many times */
 	REQ_OP_WRITE_SAME	= 7,
-	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
 	/* Open a zone */
@@ -343,6 +339,10 @@ enum req_opf {
 	REQ_OP_ZONE_FINISH	= 12,
 	/* write data at the current zone write pointer */
 	REQ_OP_ZONE_APPEND	= 13,
+	/* reset a zone write pointer */
+	REQ_OP_ZONE_RESET	= 15,
+	/* reset all the zone present on the device */
+	REQ_OP_ZONE_RESET_ALL	= 17,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
-- 
cgit v1.2.3


From 767598d447aa46411289c5808b0e45e20a1823b4 Mon Sep 17 00:00:00 2001
From: Sowjanya Komatineni <skomatineni@nvidia.com>
Date: Tue, 14 Jul 2020 21:20:51 -0700
Subject: gpu: host1x: mipi: Update tegra_mipi_request() to be node based

Tegra CSI driver need a separate MIPI device for each channel as
calibration of corresponding MIPI pads for each channel should
happen independently.

So, this patch updates tegra_mipi_request() API to add a device_node
pointer argument to allow creating mipi device for specific device
node rather than a device.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dsi.c | 2 +-
 drivers/gpu/host1x/mipi.c   | 4 ++--
 include/linux/host1x.h      | 3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 38beab9ab4f8..3c09e290632c 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1618,7 +1618,7 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 	if (IS_ERR(dsi->regs))
 		return PTR_ERR(dsi->regs);
 
-	dsi->mipi = tegra_mipi_request(&pdev->dev);
+	dsi->mipi = tegra_mipi_request(&pdev->dev, pdev->dev.of_node);
 	if (IS_ERR(dsi->mipi))
 		return PTR_ERR(dsi->mipi);
 
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index e00809d996a2..762d349ad00f 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -206,9 +206,9 @@ static int tegra_mipi_power_down(struct tegra_mipi *mipi)
 	return 0;
 }
 
-struct tegra_mipi_device *tegra_mipi_request(struct device *device)
+struct tegra_mipi_device *tegra_mipi_request(struct device *device,
+					     struct device_node *np)
 {
-	struct device_node *np = device->of_node;
 	struct tegra_mipi_device *dev;
 	struct of_phandle_args args;
 	int err;
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index a3a568bf9686..9e678412778c 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -328,7 +328,8 @@ int host1x_client_resume(struct host1x_client *client);
 
 struct tegra_mipi_device;
 
-struct tegra_mipi_device *tegra_mipi_request(struct device *device);
+struct tegra_mipi_device *tegra_mipi_request(struct device *device,
+					     struct device_node *np);
 void tegra_mipi_free(struct tegra_mipi_device *device);
 int tegra_mipi_enable(struct tegra_mipi_device *device);
 int tegra_mipi_disable(struct tegra_mipi_device *device);
-- 
cgit v1.2.3


From b3f1b760710f2acfc04abefc09358c26a75e7e89 Mon Sep 17 00:00:00 2001
From: Sowjanya Komatineni <skomatineni@nvidia.com>
Date: Tue, 14 Jul 2020 21:20:53 -0700
Subject: gpu: host1x: mipi: Split tegra_mipi_calibrate() and tegra_mipi_wait()

SW can trigger MIPI pads calibration any time after power on
but calibration results will be latched and applied to the pads
by MIPI CAL unit only when the link is in LP-11 state and then
status register will be updated.

For CSI, trigger of pads calibration happen during CSI stream
enable where CSI receiver is kept ready prior to sensor or CSI
transmitter stream start.

So, pads may not be in LP-11 at this time and waiting for the
calibration to be done immediate after calibration start will
result in timeout.

This patch splits tegra_mipi_calibrate() and tegra_mipi_wait()
so triggering for calibration and waiting for it to complete can
happen at different stages.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dsi.c |  7 ++++++-
 drivers/gpu/host1x/mipi.c   | 17 +++++++++++++----
 include/linux/host1x.h      |  1 +
 3 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 3c09e290632c..3820e8dff14b 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -670,6 +670,7 @@ static int tegra_dsi_pad_enable(struct tegra_dsi *dsi)
 static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
 {
 	u32 value;
+	int err;
 
 	/*
 	 * XXX Is this still needed? The module reset is deasserted right
@@ -693,7 +694,11 @@ static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
 		DSI_PAD_PREEMP_PD(0x03) | DSI_PAD_PREEMP_PU(0x3);
 	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_3);
 
-	return tegra_mipi_calibrate(dsi->mipi);
+	err = tegra_mipi_calibrate(dsi->mipi);
+	if (err < 0)
+		return err;
+
+	return tegra_mipi_wait(dsi->mipi);
 }
 
 static void tegra_dsi_set_timeout(struct tegra_dsi *dsi, unsigned long bclk,
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index 259e70c47a38..e606464aa43c 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -293,18 +293,29 @@ int tegra_mipi_disable(struct tegra_mipi_device *dev)
 }
 EXPORT_SYMBOL(tegra_mipi_disable);
 
-static int tegra_mipi_wait(struct tegra_mipi *mipi)
+int tegra_mipi_wait(struct tegra_mipi_device *device)
 {
+	struct tegra_mipi *mipi = device->mipi;
 	void __iomem *status_reg = mipi->regs + (MIPI_CAL_STATUS << 2);
 	u32 value;
 	int err;
 
+	err = clk_enable(device->mipi->clk);
+	if (err < 0)
+		return err;
+
+	mutex_lock(&device->mipi->lock);
+
 	err = readl_relaxed_poll_timeout(status_reg, value,
 					 !(value & MIPI_CAL_STATUS_ACTIVE) &&
 					 (value & MIPI_CAL_STATUS_DONE), 50,
 					 250000);
+	mutex_unlock(&device->mipi->lock);
+	clk_disable(device->mipi->clk);
+
 	return err;
 }
+EXPORT_SYMBOL(tegra_mipi_wait);
 
 int tegra_mipi_calibrate(struct tegra_mipi_device *device)
 {
@@ -370,12 +381,10 @@ int tegra_mipi_calibrate(struct tegra_mipi_device *device)
 	value |= MIPI_CAL_CTRL_START;
 	tegra_mipi_writel(device->mipi, value, MIPI_CAL_CTRL);
 
-	err = tegra_mipi_wait(device->mipi);
-
 	mutex_unlock(&device->mipi->lock);
 	clk_disable(device->mipi->clk);
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(tegra_mipi_calibrate);
 
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 9e678412778c..20c885d0bddc 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -334,5 +334,6 @@ void tegra_mipi_free(struct tegra_mipi_device *device);
 int tegra_mipi_enable(struct tegra_mipi_device *device);
 int tegra_mipi_disable(struct tegra_mipi_device *device);
 int tegra_mipi_calibrate(struct tegra_mipi_device *device);
+int tegra_mipi_wait(struct tegra_mipi_device *device);
 
 #endif
-- 
cgit v1.2.3


From ab91e7a6da7eeb8aa54843748652c186daee43eb Mon Sep 17 00:00:00 2001
From: He Zhe <zhe.he@windriver.com>
Date: Mon, 6 Jul 2020 17:52:24 +0800
Subject: freezer: Add unsafe versions of
 freezable_schedule_timeout_interruptible for NFS

commit 0688e64bc600 ("NFS: Allow signal interruption of NFS4ERR_DELAYed operations")
introduces nfs4_delay_interruptible which also needs an _unsafe version to
avoid the following call trace for the same reason explained in
commit 416ad3c9c006 ("freezer: add unsafe versions of freezable helpers for NFS")

CPU: 4 PID: 3968 Comm: rm Tainted: G W 5.8.0-rc4 #1
Hardware name: Marvell OcteonTX CN96XX board (DT)
Call trace:
dump_backtrace+0x0/0x1dc
show_stack+0x20/0x30
dump_stack+0xdc/0x150
debug_check_no_locks_held+0x98/0xa0
nfs4_delay_interruptible+0xd8/0x120
nfs4_handle_exception+0x130/0x170
nfs4_proc_rmdir+0x8c/0x220
nfs_rmdir+0xa4/0x360
vfs_rmdir.part.0+0x6c/0x1b0
do_rmdir+0x18c/0x210
__arm64_sys_unlinkat+0x64/0x7c
el0_svc_common.constprop.0+0x7c/0x110
do_el0_svc+0x24/0xa0
el0_sync_handler+0x13c/0x1b8
el0_sync+0x158/0x180

Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c       |  2 +-
 include/linux/freezer.h | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f670ff64b31e..113e0d6dd3d3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -416,7 +416,7 @@ static int nfs4_delay_interruptible(long *timeout)
 {
 	might_sleep();
 
-	freezable_schedule_timeout_interruptible(nfs4_update_delay(timeout));
+	freezable_schedule_timeout_interruptible_unsafe(nfs4_update_delay(timeout));
 	if (!signal_pending(current))
 		return 0;
 	return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 21f5aa0b217f..27828145ca09 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -207,6 +207,17 @@ static inline long freezable_schedule_timeout_interruptible(long timeout)
 	return __retval;
 }
 
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout)
+{
+	long __retval;
+
+	freezer_do_not_count();
+	__retval = schedule_timeout_interruptible(timeout);
+	freezer_count_unsafe();
+	return __retval;
+}
+
 /* Like schedule_timeout_killable(), but should not block the freezer. */
 static inline long freezable_schedule_timeout_killable(long timeout)
 {
@@ -285,6 +296,9 @@ static inline void set_freezable(void) {}
 #define freezable_schedule_timeout_interruptible(timeout)		\
 	schedule_timeout_interruptible(timeout)
 
+#define freezable_schedule_timeout_interruptible_unsafe(timeout)	\
+	schedule_timeout_interruptible(timeout)
+
 #define freezable_schedule_timeout_killable(timeout)			\
 	schedule_timeout_killable(timeout)
 
-- 
cgit v1.2.3


From e506addeff844237d60545ef4f6141de21471caf Mon Sep 17 00:00:00 2001
From: Miguel Rodríguez Pérez <miguel@det.uvigo.gal>
Date: Wed, 15 Jul 2020 20:40:57 +0200
Subject: net: cdc_ether: export usbnet_cdc_update_filter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This makes the function available to other drivers, like cdc_ncm.

Signed-off-by: Miguel Rodríguez Pérez <miguel@det.uvigo.gal>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 3 ++-
 include/linux/usb/usbnet.h  | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 2afe258e3648..8c1d61c2cbac 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -63,7 +63,7 @@ static const u8 mbm_guid[16] = {
 	0xa6, 0x07, 0xc0, 0xff, 0xcb, 0x7e, 0x39, 0x2a,
 };
 
-static void usbnet_cdc_update_filter(struct usbnet *dev)
+void usbnet_cdc_update_filter(struct usbnet *dev)
 {
 	struct net_device	*net = dev->net;
 
@@ -90,6 +90,7 @@ static void usbnet_cdc_update_filter(struct usbnet *dev)
 			USB_CTRL_SET_TIMEOUT
 		);
 }
+EXPORT_SYMBOL_GPL(usbnet_cdc_update_filter);
 
 /* probes control interface, claims data interface, collects the bulk
  * endpoints, activates data interface (if needed), maybe sets MTU.
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index b0bff3083278..3a856963a363 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -207,6 +207,7 @@ struct cdc_state {
 	struct usb_interface		*data;
 };
 
+extern void usbnet_cdc_update_filter(struct usbnet *dev);
 extern int usbnet_generic_cdc_bind(struct usbnet *, struct usb_interface *);
 extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf);
 extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *);
-- 
cgit v1.2.3


From 1ea2b748b5eb4f9b6c8f66d098f1277afb724336 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Wed, 15 Jul 2020 20:40:58 +0200
Subject: net: usbnet: export usbnet_set_rx_mode()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This function can be reused by other usbnet minidrivers.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 3 ++-
 include/linux/usb/usbnet.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 5ec97def3513..e45935a5856a 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1108,12 +1108,13 @@ static void __handle_link_change(struct usbnet *dev)
 	clear_bit(EVENT_LINK_CHANGE, &dev->flags);
 }
 
-static void usbnet_set_rx_mode(struct net_device *net)
+void usbnet_set_rx_mode(struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 
 	usbnet_defer_kevent(dev, EVENT_SET_RX_MODE);
 }
+EXPORT_SYMBOL_GPL(usbnet_set_rx_mode);
 
 static void __handle_set_rx_mode(struct usbnet *dev)
 {
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 3a856963a363..2e4f7721fc4e 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -274,6 +274,7 @@ extern int usbnet_set_link_ksettings(struct net_device *net,
 extern u32 usbnet_get_link(struct net_device *net);
 extern u32 usbnet_get_msglevel(struct net_device *);
 extern void usbnet_set_msglevel(struct net_device *, u32);
+extern void usbnet_set_rx_mode(struct net_device *net);
 extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *);
 extern int usbnet_nway_reset(struct net_device *net);
 
-- 
cgit v1.2.3


From d9473cbfb0c5cbb279dfdeaec780934729537d27 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Tue, 14 Jul 2020 14:04:41 -0600
Subject: remoteproc: Make function rproc_resource_cleanup() public

Make function rproc_resource_cleanup() public so that it can be
used by platform drivers when allocating resources to be used by
a detached remote processor.

Acked-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200714200445.1427257-8-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_core.c | 3 ++-
 include/linux/remoteproc.h           | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 1b52004655ab..6fa9f75754b3 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1274,7 +1274,7 @@ static void rproc_coredump_cleanup(struct rproc *rproc)
  * This function will free all resources acquired for @rproc, and it
  * is called whenever @rproc either shuts down or fails to boot.
  */
-static void rproc_resource_cleanup(struct rproc *rproc)
+void rproc_resource_cleanup(struct rproc *rproc)
 {
 	struct rproc_mem_entry *entry, *tmp;
 	struct rproc_debug_trace *trace, *ttmp;
@@ -1318,6 +1318,7 @@ static void rproc_resource_cleanup(struct rproc *rproc)
 
 	rproc_coredump_cleanup(rproc);
 }
+EXPORT_SYMBOL(rproc_resource_cleanup);
 
 static int rproc_start(struct rproc *rproc, const struct firmware *fw)
 {
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index cf5e31556780..7c0567029f7c 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -610,6 +610,7 @@ void rproc_put(struct rproc *rproc);
 int rproc_add(struct rproc *rproc);
 int rproc_del(struct rproc *rproc);
 void rproc_free(struct rproc *rproc);
+void rproc_resource_cleanup(struct rproc *rproc);
 
 struct rproc *devm_rproc_alloc(struct device *dev, const char *name,
 			       const struct rproc_ops *ops,
-- 
cgit v1.2.3


From 7f5f81406e2b36785f1e25fe5209edd9dd3610d7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:37:25 -0700
Subject: rhashtable: drop duplicated word in <linux/rhashtable.h>

Drop the doubled word "be" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 70ebef866cc8..d3432ee65de7 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -33,7 +33,7 @@
  * of two or more hash tables when the rhashtable is being resized.
  * The end of the chain is marked with a special nulls marks which has
  * the least significant bit set but otherwise stores the address of
- * the hash bucket.  This allows us to be be sure we've found the end
+ * the hash bucket.  This allows us to be sure we've found the end
  * of the right list.
  * The value stored in the hash bucket has BIT(0) used as a lock bit.
  * This bit must be atomically set before any changes are made to
-- 
cgit v1.2.3


From ef45fe470e1e5410db4af87abc5d5055427945ac Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Mon, 1 Jun 2020 13:12:05 -0700
Subject: blk-cgroup: show global disk stats in root cgroup io.stat

In order to improve consistency and usability in cgroup stat accounting,
we would like to support the root cgroup's io.stat.

Since the root cgroup has processes doing io even if the system has no
explicitly created cgroups, we need to be careful to avoid overhead in
that case.  For that reason, the rstat algorithms don't handle the root
cgroup, so just turning the file on wouldn't give correct statistics.

To get around this, we simulate flushing the iostat struct by filling it
out directly from global disk stats. The result is a root cgroup io.stat
file consistent with both /proc/diskstats and io.stat.

Note that in order to collect the disk stats, we needed to iterate over
devices. To facilitate that, we had to change the linkage of a disk_type
to external so that it can be used from blk-cgroup.c to iterate over
disks.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Boris Burkov <boris@bur.io>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/admin-guide/cgroup-v2.rst |  3 +-
 block/blk-cgroup.c                      | 57 +++++++++++++++++++++++++++++++--
 block/genhd.c                           |  4 +--
 include/linux/genhd.h                   |  1 +
 4 files changed, 58 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index ce3e05e41724..2d7c5907e0ce 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1483,8 +1483,7 @@ IO Interface Files
 ~~~~~~~~~~~~~~~~~~
 
   io.stat
-	A read-only nested-keyed file which exists on non-root
-	cgroups.
+	A read-only nested-keyed file.
 
 	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
 	The following nested keys are defined.
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 696d28151c9a..619a79b51068 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -782,12 +782,66 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 	rcu_read_unlock();
 }
 
+/*
+ * The rstat algorithms intentionally don't handle the root cgroup to avoid
+ * incurring overhead when no cgroups are defined. For that reason,
+ * cgroup_rstat_flush in blkcg_print_stat does not actually fill out the
+ * iostat in the root cgroup's blkcg_gq.
+ *
+ * However, we would like to re-use the printing code between the root and
+ * non-root cgroups to the extent possible. For that reason, we simulate
+ * flushing the root cgroup's stats by explicitly filling in the iostat
+ * with disk level statistics.
+ */
+static void blkcg_fill_root_iostats(void)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct hd_struct *part = disk_get_part(disk, 0);
+		struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue);
+		struct blkg_iostat tmp;
+		int cpu;
+
+		memset(&tmp, 0, sizeof(tmp));
+		for_each_possible_cpu(cpu) {
+			struct disk_stats *cpu_dkstats;
+
+			cpu_dkstats = per_cpu_ptr(part->dkstats, cpu);
+			tmp.ios[BLKG_IOSTAT_READ] +=
+				cpu_dkstats->ios[STAT_READ];
+			tmp.ios[BLKG_IOSTAT_WRITE] +=
+				cpu_dkstats->ios[STAT_WRITE];
+			tmp.ios[BLKG_IOSTAT_DISCARD] +=
+				cpu_dkstats->ios[STAT_DISCARD];
+			// convert sectors to bytes
+			tmp.bytes[BLKG_IOSTAT_READ] +=
+				cpu_dkstats->sectors[STAT_READ] << 9;
+			tmp.bytes[BLKG_IOSTAT_WRITE] +=
+				cpu_dkstats->sectors[STAT_WRITE] << 9;
+			tmp.bytes[BLKG_IOSTAT_DISCARD] +=
+				cpu_dkstats->sectors[STAT_DISCARD] << 9;
+
+			u64_stats_update_begin(&blkg->iostat.sync);
+			blkg_iostat_set(&blkg->iostat.cur, &tmp);
+			u64_stats_update_end(&blkg->iostat.sync);
+		}
+	}
+}
+
 static int blkcg_print_stat(struct seq_file *sf, void *v)
 {
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct blkcg_gq *blkg;
 
-	cgroup_rstat_flush(blkcg->css.cgroup);
+	if (!seq_css(sf)->parent)
+		blkcg_fill_root_iostats();
+	else
+		cgroup_rstat_flush(blkcg->css.cgroup);
+
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
@@ -876,7 +930,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
-		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = blkcg_print_stat,
 	},
 	{ }	/* terminate */
diff --git a/block/genhd.c b/block/genhd.c
index c42a49f2f537..8b1e9f48957c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -38,8 +38,6 @@ static struct kobject *block_depr;
 static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
-static const struct device_type disk_type;
-
 static void disk_check_events(struct disk_events *ev,
 			      unsigned int *clearing_ptr);
 static void disk_alloc_events(struct gendisk *disk);
@@ -1587,7 +1585,7 @@ static char *block_devnode(struct device *dev, umode_t *mode,
 	return NULL;
 }
 
-static const struct device_type disk_type = {
+const struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 31a54072ffd6..4ab853461dff 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -24,6 +24,7 @@
 #define disk_to_dev(disk)	(&(disk)->part0.__dev)
 #define part_to_dev(part)	(&((part)->__dev))
 
+extern const struct device_type disk_type;
 extern struct device_type part_type;
 extern struct class block_class;
 
-- 
cgit v1.2.3


From ce3aa9cc5109363099b7c4ac82e2c9768afcaf31 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 17 Jul 2020 12:35:22 +0200
Subject: bpf, netns: Handle multiple link attachments

Extend the BPF netns link callbacks to rebuild (grow/shrink) or update the
prog_array at given position when link gets attached/updated/released.

This let's us lift the limit of having just one link attached for the new
attach type introduced by subsequent patch.

No functional changes intended.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200717103536.397595-2-jakub@cloudflare.com
---
 include/linux/bpf.h        |  3 ++
 kernel/bpf/core.c          | 55 ++++++++++++++++++++++++++++
 kernel/bpf/net_namespace.c | 90 +++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 139 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 54ad426dbea1..c8c9eabcd106 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -928,6 +928,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 
 void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
 				struct bpf_prog *old_prog);
+int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index);
+int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
+			     struct bpf_prog *prog);
 int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9df4cc9a2907..7be02e555ab9 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1958,6 +1958,61 @@ void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
 		}
 }
 
+/**
+ * bpf_prog_array_delete_safe_at() - Replaces the program at the given
+ *                                   index into the program array with
+ *                                   a dummy no-op program.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to replace
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the the position of the program to replace.
+ *
+ * Return:
+ * * 0		- Success
+ * * -EINVAL	- Invalid index value. Must be a non-negative integer.
+ * * -ENOENT	- Index out of range
+ */
+int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index)
+{
+	return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog);
+}
+
+/**
+ * bpf_prog_array_update_at() - Updates the program at the given index
+ *                              into the program array.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to update
+ * @prog: the program to insert into the array
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the position of the program to update.
+ *
+ * Return:
+ * * 0		- Success
+ * * -EINVAL	- Invalid index value. Must be a non-negative integer.
+ * * -ENOENT	- Index out of range
+ */
+int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
+			     struct bpf_prog *prog)
+{
+	struct bpf_prog_array_item *item;
+
+	if (unlikely(index < 0))
+		return -EINVAL;
+
+	for (item = array->items; item->prog; item++) {
+		if (item->prog == &dummy_bpf_prog.prog)
+			continue;
+		if (!index) {
+			WRITE_ONCE(item->prog, prog);
+			return 0;
+		}
+		index--;
+	}
+	return -ENOENT;
+}
+
 int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 310241ca7991..e9c8e26ac8f2 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -36,12 +36,50 @@ static void netns_bpf_run_array_detach(struct net *net,
 	bpf_prog_array_free(run_array);
 }
 
+static int link_index(struct net *net, enum netns_bpf_attach_type type,
+		      struct bpf_netns_link *link)
+{
+	struct bpf_netns_link *pos;
+	int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		if (pos == link)
+			return i;
+		i++;
+	}
+	return -ENOENT;
+}
+
+static int link_count(struct net *net, enum netns_bpf_attach_type type)
+{
+	struct list_head *pos;
+	int i = 0;
+
+	list_for_each(pos, &net->bpf.links[type])
+		i++;
+	return i;
+}
+
+static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type,
+			    struct bpf_prog_array *prog_array)
+{
+	struct bpf_netns_link *pos;
+	unsigned int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		prog_array->items[i].prog = pos->link.prog;
+		i++;
+	}
+}
+
 static void bpf_netns_link_release(struct bpf_link *link)
 {
 	struct bpf_netns_link *net_link =
 		container_of(link, struct bpf_netns_link, link);
 	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct bpf_prog_array *old_array, *new_array;
 	struct net *net;
+	int cnt, idx;
 
 	mutex_lock(&netns_bpf_mutex);
 
@@ -53,9 +91,27 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	if (!net)
 		goto out_unlock;
 
-	netns_bpf_run_array_detach(net, type);
+	/* Remember link position in case of safe delete */
+	idx = link_index(net, type, net_link);
 	list_del(&net_link->node);
 
+	cnt = link_count(net, type);
+	if (!cnt) {
+		netns_bpf_run_array_detach(net, type);
+		goto out_unlock;
+	}
+
+	old_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+	if (!new_array) {
+		WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx));
+		goto out_unlock;
+	}
+	fill_prog_array(net, type, new_array);
+	rcu_assign_pointer(net->bpf.run_array[type], new_array);
+	bpf_prog_array_free(old_array);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 }
@@ -77,7 +133,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 	enum netns_bpf_attach_type type = net_link->netns_type;
 	struct bpf_prog_array *run_array;
 	struct net *net;
-	int ret = 0;
+	int idx, ret;
 
 	if (old_prog && old_prog != link->prog)
 		return -EPERM;
@@ -95,7 +151,10 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 
 	run_array = rcu_dereference_protected(net->bpf.run_array[type],
 					      lockdep_is_held(&netns_bpf_mutex));
-	WRITE_ONCE(run_array->items[0].prog, new_prog);
+	idx = link_index(net, type, net_link);
+	ret = bpf_prog_array_update_at(run_array, idx, new_prog);
+	if (ret)
+		goto out_unlock;
 
 	old_prog = xchg(&link->prog, new_prog);
 	bpf_prog_put(old_prog);
@@ -309,18 +368,28 @@ int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 	return ret;
 }
 
+static int netns_bpf_max_progs(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
 static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 				 enum netns_bpf_attach_type type)
 {
 	struct bpf_netns_link *net_link =
 		container_of(link, struct bpf_netns_link, link);
 	struct bpf_prog_array *run_array;
-	int err;
+	int cnt, err;
 
 	mutex_lock(&netns_bpf_mutex);
 
-	/* Allow attaching only one prog or link for now */
-	if (!list_empty(&net->bpf.links[type])) {
+	cnt = link_count(net, type);
+	if (cnt >= netns_bpf_max_progs(type)) {
 		err = -E2BIG;
 		goto out_unlock;
 	}
@@ -341,16 +410,19 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	if (err)
 		goto out_unlock;
 
-	run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+	run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL);
 	if (!run_array) {
 		err = -ENOMEM;
 		goto out_unlock;
 	}
-	run_array->items[0].prog = link->prog;
-	rcu_assign_pointer(net->bpf.run_array[type], run_array);
 
 	list_add_tail(&net_link->node, &net->bpf.links[type]);
 
+	fill_prog_array(net, type, run_array);
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 	return err;
-- 
cgit v1.2.3


From e9ddbb7707ff5891616240026062b8c1e29864ca Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 17 Jul 2020 12:35:23 +0200
Subject: bpf: Introduce SK_LOOKUP program type with a dedicated attach point

Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type
BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer
when looking up a listening socket for a new connection request for
connection oriented protocols, or when looking up an unconnected socket for
a packet for connection-less protocols.

When called, SK_LOOKUP BPF program can select a socket that will receive
the packet. This serves as a mechanism to overcome the limits of what
bind() API allows to express. Two use-cases driving this work are:

 (1) steer packets destined to an IP range, on fixed port to a socket

     192.0.2.0/24, port 80 -> NGINX socket

 (2) steer packets destined to an IP address, on any port to a socket

     198.51.100.1, any port -> L7 proxy socket

In its run-time context program receives information about the packet that
triggered the socket lookup. Namely IP version, L4 protocol identifier, and
address 4-tuple. Context can be further extended to include ingress
interface identifier.

To select a socket BPF program fetches it from a map holding socket
references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...)
helper to record the selection. Transport layer then uses the selected
socket as a result of socket lookup.

In its basic form, SK_LOOKUP acts as a filter and hence must return either
SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should
look for a socket to receive the packet, or use the one selected by the
program if available, while SK_DROP informs the transport layer that the
lookup should fail.

This patch only enables the user to attach an SK_LOOKUP program to a
network namespace. Subsequent patches hook it up to run on local delivery
path in ipv4 and ipv6 stacks.

Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com
---
 include/linux/bpf-netns.h  |   3 +
 include/linux/bpf.h        |   1 +
 include/linux/bpf_types.h  |   2 +
 include/linux/filter.h     |  17 +++++
 include/uapi/linux/bpf.h   |  77 +++++++++++++++++++
 kernel/bpf/net_namespace.c |   5 ++
 kernel/bpf/syscall.c       |   9 +++
 kernel/bpf/verifier.c      |  13 +++-
 net/core/filter.c          | 180 +++++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py |   9 ++-
 10 files changed, 312 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 47d5b0c708c9..722f799c1a2e 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -8,6 +8,7 @@
 enum netns_bpf_attach_type {
 	NETNS_BPF_INVALID = -1,
 	NETNS_BPF_FLOW_DISSECTOR = 0,
+	NETNS_BPF_SK_LOOKUP,
 	MAX_NETNS_BPF_ATTACH_TYPE
 };
 
@@ -17,6 +18,8 @@ to_netns_bpf_attach_type(enum bpf_attach_type attach_type)
 	switch (attach_type) {
 	case BPF_FLOW_DISSECTOR:
 		return NETNS_BPF_FLOW_DISSECTOR;
+	case BPF_SK_LOOKUP:
+		return NETNS_BPF_SK_LOOKUP;
 	default:
 		return NETNS_BPF_INVALID;
 	}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c8c9eabcd106..adb16bdc5f0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -249,6 +249,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
+	ARG_PTR_TO_SOCKET_OR_NULL,	/* pointer to bpf_sock (fullsock) or NULL */
 	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a18ae82a298a..a52a5688418e 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
 #ifdef CONFIG_INET
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
 	      struct sk_reuseport_md, struct sk_reuseport_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup,
+	      struct bpf_sk_lookup, struct bpf_sk_lookup_kern)
 #endif
 #if defined(CONFIG_BPF_JIT)
 BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0b0144752d78..fa1ea12ad2cd 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1278,4 +1278,21 @@ struct bpf_sockopt_kern {
 	s32		retval;
 };
 
+struct bpf_sk_lookup_kern {
+	u16		family;
+	u16		protocol;
+	struct {
+		__be32 saddr;
+		__be32 daddr;
+	} v4;
+	struct {
+		const struct in6_addr *saddr;
+		const struct in6_addr *daddr;
+	} v6;
+	__be16		sport;
+	u16		dport;
+	struct sock	*selected_sk;
+	bool		no_reuseport;
+};
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7ac3992dacfe..54d0c886e3ba 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -189,6 +189,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_STRUCT_OPS,
 	BPF_PROG_TYPE_EXT,
 	BPF_PROG_TYPE_LSM,
+	BPF_PROG_TYPE_SK_LOOKUP,
 };
 
 enum bpf_attach_type {
@@ -228,6 +229,7 @@ enum bpf_attach_type {
 	BPF_XDP_DEVMAP,
 	BPF_CGROUP_INET_SOCK_RELEASE,
 	BPF_XDP_CPUMAP,
+	BPF_SK_LOOKUP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3069,6 +3071,10 @@ union bpf_attr {
  *
  * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
  *	Description
+ *		Helper is overloaded depending on BPF program type. This
+ *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
+ *		**BPF_PROG_TYPE_SCHED_ACT** programs.
+ *
  *		Assign the *sk* to the *skb*. When combined with appropriate
  *		routing configuration to receive the packet towards the socket,
  *		will cause *skb* to be delivered to the specified socket.
@@ -3094,6 +3100,56 @@ union bpf_attr {
  *		**-ESOCKTNOSUPPORT** if the socket type is not supported
  *		(reuseport).
  *
+ * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Helper is overloaded depending on BPF program type. This
+ *		description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
+ *
+ *		Select the *sk* as a result of a socket lookup.
+ *
+ *		For the operation to succeed passed socket must be compatible
+ *		with the packet description provided by the *ctx* object.
+ *
+ *		L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must
+ *		be an exact match. While IP family (**AF_INET** or
+ *		**AF_INET6**) must be compatible, that is IPv6 sockets
+ *		that are not v6-only can be selected for IPv4 packets.
+ *
+ *		Only TCP listeners and UDP unconnected sockets can be
+ *		selected. *sk* can also be NULL to reset any previous
+ *		selection.
+ *
+ *		*flags* argument can combination of following values:
+ *
+ *		* **BPF_SK_LOOKUP_F_REPLACE** to override the previous
+ *		  socket selection, potentially done by a BPF program
+ *		  that ran before us.
+ *
+ *		* **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip
+ *		  load-balancing within reuseport group for the socket
+ *		  being selected.
+ *
+ *		On success *ctx->sk* will point to the selected socket.
+ *
+ *	Return
+ *		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EAFNOSUPPORT** if socket family (*sk->family*) is
+ *		  not compatible with packet family (*ctx->family*).
+ *
+ *		* **-EEXIST** if socket has been already selected,
+ *		  potentially by another program, and
+ *		  **BPF_SK_LOOKUP_F_REPLACE** flag was not specified.
+ *
+ *		* **-EINVAL** if unsupported flags were specified.
+ *
+ *		* **-EPROTOTYPE** if socket L4 protocol
+ *		  (*sk->protocol*) doesn't match packet protocol
+ *		  (*ctx->protocol*).
+ *
+ *		* **-ESOCKTNOSUPPORT** if socket is not in allowed
+ *		  state (TCP listening or UDP unconnected).
+ *
  * u64 bpf_ktime_get_boot_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
@@ -3607,6 +3663,12 @@ enum {
 	BPF_RINGBUF_HDR_SZ		= 8,
 };
 
+/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */
+enum {
+	BPF_SK_LOOKUP_F_REPLACE		= (1ULL << 0),
+	BPF_SK_LOOKUP_F_NO_REUSEPORT	= (1ULL << 1),
+};
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -4349,4 +4411,19 @@ struct bpf_pidns_info {
 	__u32 pid;
 	__u32 tgid;
 };
+
+/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
+struct bpf_sk_lookup {
+	__bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+
+	__u32 family;		/* Protocol family (AF_INET, AF_INET6) */
+	__u32 protocol;		/* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
+	__u32 remote_ip4;	/* Network byte order */
+	__u32 remote_ip6[4];	/* Network byte order */
+	__u32 remote_port;	/* Network byte order */
+	__u32 local_ip4;	/* Network byte order */
+	__u32 local_ip6[4];	/* Network byte order */
+	__u32 local_port;	/* Host byte order */
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index e9c8e26ac8f2..38b368bccda2 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -373,6 +373,8 @@ static int netns_bpf_max_progs(enum netns_bpf_attach_type type)
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
 		return 1;
+	case NETNS_BPF_SK_LOOKUP:
+		return 64;
 	default:
 		return 0;
 	}
@@ -403,6 +405,9 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	case NETNS_BPF_FLOW_DISSECTOR:
 		err = flow_dissector_bpf_prog_attach_check(net, link->prog);
 		break;
+	case NETNS_BPF_SK_LOOKUP:
+		err = 0; /* nothing to check */
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7ea9dfbebd8c..d07417d17712 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2022,6 +2022,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		if (expected_attach_type == BPF_SK_LOOKUP)
+			return 0;
+		return -EINVAL;
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
@@ -2756,6 +2760,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		if (!capable(CAP_NET_ADMIN))
@@ -2817,6 +2822,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
 	case BPF_TRACE_ITER:
 		return BPF_PROG_TYPE_TRACING;
+	case BPF_SK_LOOKUP:
+		return BPF_PROG_TYPE_SK_LOOKUP;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -2953,6 +2960,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
 	case BPF_FLOW_DISSECTOR:
+	case BPF_SK_LOOKUP:
 		return netns_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
@@ -3891,6 +3899,7 @@ static int link_create(union bpf_attr *attr)
 		ret = tracing_bpf_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
 	default:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3c1efc9d08fd..9a6703bc3f36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3878,10 +3878,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			}
 			meta->ref_obj_id = reg->ref_obj_id;
 		}
-	} else if (arg_type == ARG_PTR_TO_SOCKET) {
+	} else if (arg_type == ARG_PTR_TO_SOCKET ||
+		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
 		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
+		if (!(register_is_null(reg) &&
+		      arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) {
+			if (type != expected_type)
+				goto err_type;
+		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
@@ -7354,6 +7358,9 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return -ENOTSUPP;
 		}
 		break;
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		range = tnum_range(SK_DROP, SK_PASS);
+		break;
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
 		 * depends on the to-be-replaced kernel func or bpf program.
diff --git a/net/core/filter.c b/net/core/filter.c
index bdd2382e655d..d099436b3ff5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9229,6 +9229,186 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
 
 const struct bpf_prog_ops sk_reuseport_prog_ops = {
 };
+
+BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
+	   struct sock *, sk, u64, flags)
+{
+	if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE |
+			       BPF_SK_LOOKUP_F_NO_REUSEPORT)))
+		return -EINVAL;
+	if (unlikely(sk && sk_is_refcounted(sk)))
+		return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */
+	if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED))
+		return -ESOCKTNOSUPPORT; /* reject connected sockets */
+
+	/* Check if socket is suitable for packet L3/L4 protocol */
+	if (sk && sk->sk_protocol != ctx->protocol)
+		return -EPROTOTYPE;
+	if (sk && sk->sk_family != ctx->family &&
+	    (sk->sk_family == AF_INET || ipv6_only_sock(sk)))
+		return -EAFNOSUPPORT;
+
+	if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE))
+		return -EEXIST;
+
+	/* Select socket as lookup result */
+	ctx->selected_sk = sk;
+	ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_assign_proto = {
+	.func		= bpf_sk_lookup_assign,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_SOCKET_OR_NULL,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
+	case BPF_FUNC_sk_assign:
+		return &bpf_sk_lookup_assign_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
+static bool sk_lookup_is_valid_access(int off, int size,
+				      enum bpf_access_type type,
+				      const struct bpf_prog *prog,
+				      struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= sizeof(struct bpf_sk_lookup))
+		return false;
+	if (off % size != 0)
+		return false;
+	if (type != BPF_READ)
+		return false;
+
+	switch (off) {
+	case offsetof(struct bpf_sk_lookup, sk):
+		info->reg_type = PTR_TO_SOCKET_OR_NULL;
+		return size == sizeof(__u64);
+
+	case bpf_ctx_range(struct bpf_sk_lookup, family):
+	case bpf_ctx_range(struct bpf_sk_lookup, protocol):
+	case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4):
+	case bpf_ctx_range(struct bpf_sk_lookup, local_ip4):
+	case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]):
+	case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
+	case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
+	case bpf_ctx_range(struct bpf_sk_lookup, local_port):
+		bpf_ctx_record_field_size(info, sizeof(__u32));
+		return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32));
+
+	default:
+		return false;
+	}
+}
+
+static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type,
+					const struct bpf_insn *si,
+					struct bpf_insn *insn_buf,
+					struct bpf_prog *prog,
+					u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct bpf_sk_lookup, sk):
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sk_lookup_kern, selected_sk));
+		break;
+
+	case offsetof(struct bpf_sk_lookup, family):
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     family, 2, target_size));
+		break;
+
+	case offsetof(struct bpf_sk_lookup, protocol):
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     protocol, 2, target_size));
+		break;
+
+	case offsetof(struct bpf_sk_lookup, remote_ip4):
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     v4.saddr, 4, target_size));
+		break;
+
+	case offsetof(struct bpf_sk_lookup, local_ip4):
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     v4.daddr, 4, target_size));
+		break;
+
+	case bpf_ctx_range_till(struct bpf_sk_lookup,
+				remote_ip6[0], remote_ip6[3]): {
+#if IS_ENABLED(CONFIG_IPV6)
+		int off = si->off;
+
+		off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]);
+		off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sk_lookup_kern, v6.saddr));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
+	}
+	case bpf_ctx_range_till(struct bpf_sk_lookup,
+				local_ip6[0], local_ip6[3]): {
+#if IS_ENABLED(CONFIG_IPV6)
+		int off = si->off;
+
+		off -= offsetof(struct bpf_sk_lookup, local_ip6[0]);
+		off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sk_lookup_kern, v6.daddr));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
+	}
+	case offsetof(struct bpf_sk_lookup, remote_port):
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     sport, 2, target_size));
+		break;
+
+	case offsetof(struct bpf_sk_lookup, local_port):
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+				      bpf_target_off(struct bpf_sk_lookup_kern,
+						     dport, 2, target_size));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+const struct bpf_prog_ops sk_lookup_prog_ops = {
+};
+
+const struct bpf_verifier_ops sk_lookup_verifier_ops = {
+	.get_func_proto		= sk_lookup_func_proto,
+	.is_valid_access	= sk_lookup_is_valid_access,
+	.convert_ctx_access	= sk_lookup_convert_ctx_access,
+};
+
 #endif /* CONFIG_INET */
 
 DEFINE_BPF_DISPATCHER(xdp)
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6843376733df..5bfa448b4704 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -404,6 +404,7 @@ class PrinterHelpers(Printer):
 
     type_fwds = [
             'struct bpf_fib_lookup',
+            'struct bpf_sk_lookup',
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
             'struct bpf_pidns_info',
@@ -450,6 +451,7 @@ class PrinterHelpers(Printer):
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
             'struct bpf_pidns_info',
+            'struct bpf_sk_lookup',
             'struct bpf_sock',
             'struct bpf_sock_addr',
             'struct bpf_sock_ops',
@@ -487,6 +489,11 @@ class PrinterHelpers(Printer):
             'struct sk_msg_buff': 'struct sk_msg_md',
             'struct xdp_buff': 'struct xdp_md',
     }
+    # Helpers overloaded for different context types.
+    overloaded_helpers = [
+        'bpf_get_socket_cookie',
+        'bpf_sk_assign',
+    ]
 
     def print_header(self):
         header = '''\
@@ -543,7 +550,7 @@ class PrinterHelpers(Printer):
         for i, a in enumerate(proto['args']):
             t = a['type']
             n = a['name']
-            if proto['name'] == 'bpf_get_socket_cookie' and i == 0:
+            if proto['name'] in self.overloaded_helpers and i == 0:
                     t = 'void'
                     n = 'ctx'
             one_arg = '{}{}'.format(comma, self.map_type(t))
-- 
cgit v1.2.3


From 1559b4aa1db443096af493c7d621dc156054babe Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 17 Jul 2020 12:35:25 +0200
Subject: inet: Run SK_LOOKUP BPF program on socket lookup

Run a BPF program before looking up a listening socket on the receive path.
Program selects a listening socket to yield as result of socket lookup by
calling bpf_sk_assign() helper and returning SK_PASS code. Program can
revert its decision by assigning a NULL socket with bpf_sk_assign().

Alternatively, BPF program can also fail the lookup by returning with
SK_DROP, or let the lookup continue as usual with SK_PASS on return, when
no socket has been selected with bpf_sk_assign().

This lets the user match packets with listening sockets freely at the last
possible point on the receive path, where we know that packets are destined
for local delivery after undergoing policing, filtering, and routing.

With BPF code selecting the socket, directing packets destined to an IP
range or to a port range to a single socket becomes possible.

In case multiple programs are attached, they are run in series in the order
in which they were attached. The end result is determined from return codes
of all the programs according to following rules:

 1. If any program returned SK_PASS and selected a valid socket, the socket
    is used as result of socket lookup.
 2. If more than one program returned SK_PASS and selected a socket,
    last selection takes effect.
 3. If any program returned SK_DROP, and no program returned SK_PASS and
    selected a socket, socket lookup fails with -ECONNREFUSED.
 4. If all programs returned SK_PASS and none of them selected a socket,
    socket lookup continues to htable-based lookup.

Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
---
 include/linux/filter.h     | 91 ++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/net_namespace.c | 32 +++++++++++++++-
 net/core/filter.c          |  3 ++
 net/ipv4/inet_hashtables.c | 31 ++++++++++++++++
 4 files changed, 156 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index fa1ea12ad2cd..c4f54c216347 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1295,4 +1295,95 @@ struct bpf_sk_lookup_kern {
 	bool		no_reuseport;
 };
 
+extern struct static_key_false bpf_sk_lookup_enabled;
+
+/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup.
+ *
+ * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and
+ * SK_DROP. Their meaning is as follows:
+ *
+ *  SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result
+ *  SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup
+ *  SK_DROP                           : terminate lookup with -ECONNREFUSED
+ *
+ * This macro aggregates return values and selected sockets from
+ * multiple BPF programs according to following rules in order:
+ *
+ *  1. If any program returned SK_PASS and a non-NULL ctx.selected_sk,
+ *     macro result is SK_PASS and last ctx.selected_sk is used.
+ *  2. If any program returned SK_DROP return value,
+ *     macro result is SK_DROP.
+ *  3. Otherwise result is SK_PASS and ctx.selected_sk is NULL.
+ *
+ * Caller must ensure that the prog array is non-NULL, and that the
+ * array as well as the programs it contains remain valid.
+ */
+#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func)			\
+	({								\
+		struct bpf_sk_lookup_kern *_ctx = &(ctx);		\
+		struct bpf_prog_array_item *_item;			\
+		struct sock *_selected_sk = NULL;			\
+		bool _no_reuseport = false;				\
+		struct bpf_prog *_prog;					\
+		bool _all_pass = true;					\
+		u32 _ret;						\
+									\
+		migrate_disable();					\
+		_item = &(array)->items[0];				\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			/* restore most recent selection */		\
+			_ctx->selected_sk = _selected_sk;		\
+			_ctx->no_reuseport = _no_reuseport;		\
+									\
+			_ret = func(_prog, _ctx);			\
+			if (_ret == SK_PASS && _ctx->selected_sk) {	\
+				/* remember last non-NULL socket */	\
+				_selected_sk = _ctx->selected_sk;	\
+				_no_reuseport = _ctx->no_reuseport;	\
+			} else if (_ret == SK_DROP && _all_pass) {	\
+				_all_pass = false;			\
+			}						\
+			_item++;					\
+		}							\
+		_ctx->selected_sk = _selected_sk;			\
+		_ctx->no_reuseport = _no_reuseport;			\
+		migrate_enable();					\
+		_all_pass || _selected_sk ? SK_PASS : SK_DROP;		\
+	 })
+
+static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
+					const __be32 saddr, const __be16 sport,
+					const __be32 daddr, const u16 dport,
+					struct sock **psk)
+{
+	struct bpf_prog_array *run_array;
+	struct sock *selected_sk = NULL;
+	bool no_reuseport = false;
+
+	rcu_read_lock();
+	run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]);
+	if (run_array) {
+		struct bpf_sk_lookup_kern ctx = {
+			.family		= AF_INET,
+			.protocol	= protocol,
+			.v4.saddr	= saddr,
+			.v4.daddr	= daddr,
+			.sport		= sport,
+			.dport		= dport,
+		};
+		u32 act;
+
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		if (act == SK_PASS) {
+			selected_sk = ctx.selected_sk;
+			no_reuseport = ctx.no_reuseport;
+		} else {
+			selected_sk = ERR_PTR(-ECONNREFUSED);
+		}
+	}
+	rcu_read_unlock();
+	*psk = selected_sk;
+	return no_reuseport;
+}
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 38b368bccda2..4e1bcaa2c3cb 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -25,6 +25,28 @@ struct bpf_netns_link {
 /* Protects updates to netns_bpf */
 DEFINE_MUTEX(netns_bpf_mutex);
 
+static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_dec(&bpf_sk_lookup_enabled);
+		break;
+	default:
+		break;
+	}
+}
+
+static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_inc(&bpf_sk_lookup_enabled);
+		break;
+	default:
+		break;
+	}
+}
+
 /* Must be called with netns_bpf_mutex held. */
 static void netns_bpf_run_array_detach(struct net *net,
 				       enum netns_bpf_attach_type type)
@@ -91,6 +113,9 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	if (!net)
 		goto out_unlock;
 
+	/* Mark attach point as unused */
+	netns_bpf_attach_type_unneed(type);
+
 	/* Remember link position in case of safe delete */
 	idx = link_index(net, type, net_link);
 	list_del(&net_link->node);
@@ -428,6 +453,9 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 					lockdep_is_held(&netns_bpf_mutex));
 	bpf_prog_array_free(run_array);
 
+	/* Mark attach point as used */
+	netns_bpf_attach_type_need(type);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 	return err;
@@ -503,8 +531,10 @@ static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
 	mutex_lock(&netns_bpf_mutex);
 	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
 		netns_bpf_run_array_detach(net, type);
-		list_for_each_entry(net_link, &net->bpf.links[type], node)
+		list_for_each_entry(net_link, &net->bpf.links[type], node) {
 			net_link->net = NULL; /* auto-detach link */
+			netns_bpf_attach_type_unneed(type);
+		}
 		if (net->bpf.progs[type])
 			bpf_prog_put(net->bpf.progs[type]);
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index d099436b3ff5..2bd129b5ae74 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9230,6 +9230,9 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
 const struct bpf_prog_ops sk_reuseport_prog_ops = {
 };
 
+DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled);
+EXPORT_SYMBOL(bpf_sk_lookup_enabled);
+
 BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
 	   struct sock *, sk, u64, flags)
 {
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ab64834837c8..4eb4cd8d20dd 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -299,6 +299,29 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 	return result;
 }
 
+static inline struct sock *inet_lookup_run_bpf(struct net *net,
+					       struct inet_hashinfo *hashinfo,
+					       struct sk_buff *skb, int doff,
+					       __be32 saddr, __be16 sport,
+					       __be32 daddr, u16 hnum)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	if (hashinfo != &tcp_hashinfo)
+		return NULL; /* only TCP is supported */
+
+	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP,
+					    saddr, sport, daddr, hnum, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+
 struct sock *__inet_lookup_listener(struct net *net,
 				    struct inet_hashinfo *hashinfo,
 				    struct sk_buff *skb, int doff,
@@ -310,6 +333,14 @@ struct sock *__inet_lookup_listener(struct net *net,
 	struct sock *result = NULL;
 	unsigned int hash2;
 
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
+					     saddr, sport, daddr, hnum);
+		if (result)
+			goto done;
+	}
+
 	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
 
-- 
cgit v1.2.3


From 1122702f02678597c4f1c7d316365ef502aafe08 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 17 Jul 2020 12:35:27 +0200
Subject: inet6: Run SK_LOOKUP BPF program on socket lookup

Following ipv4 stack changes, run a BPF program attached to netns before
looking up a listening socket. Program can return a listening socket to use
as result of socket lookup, fail the lookup, or take no action.

Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200717103536.397595-7-jakub@cloudflare.com
---
 include/linux/filter.h      | 39 +++++++++++++++++++++++++++++++++++++++
 net/ipv6/inet6_hashtables.c | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index c4f54c216347..8252572db918 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1386,4 +1386,43 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
 	return no_reuseport;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 dport,
+					struct sock **psk)
+{
+	struct bpf_prog_array *run_array;
+	struct sock *selected_sk = NULL;
+	bool no_reuseport = false;
+
+	rcu_read_lock();
+	run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]);
+	if (run_array) {
+		struct bpf_sk_lookup_kern ctx = {
+			.family		= AF_INET6,
+			.protocol	= protocol,
+			.v6.saddr	= saddr,
+			.v6.daddr	= daddr,
+			.sport		= sport,
+			.dport		= dport,
+		};
+		u32 act;
+
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		if (act == SK_PASS) {
+			selected_sk = ctx.selected_sk;
+			no_reuseport = ctx.no_reuseport;
+		} else {
+			selected_sk = ERR_PTR(-ECONNREFUSED);
+		}
+	}
+	rcu_read_unlock();
+	*psk = selected_sk;
+	return no_reuseport;
+}
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 03942eef8ab6..2d3add9e6116 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -21,6 +21,8 @@
 #include <net/ip.h>
 #include <net/sock_reuseport.h>
 
+extern struct inet_hashinfo tcp_hashinfo;
+
 u32 inet6_ehashfn(const struct net *net,
 		  const struct in6_addr *laddr, const u16 lport,
 		  const struct in6_addr *faddr, const __be16 fport)
@@ -159,6 +161,31 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	return result;
 }
 
+static inline struct sock *inet6_lookup_run_bpf(struct net *net,
+						struct inet_hashinfo *hashinfo,
+						struct sk_buff *skb, int doff,
+						const struct in6_addr *saddr,
+						const __be16 sport,
+						const struct in6_addr *daddr,
+						const u16 hnum)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	if (hashinfo != &tcp_hashinfo)
+		return NULL; /* only TCP is supported */
+
+	no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP,
+					    saddr, sport, daddr, hnum, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+
 struct sock *inet6_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
 		struct sk_buff *skb, int doff,
@@ -170,6 +197,14 @@ struct sock *inet6_lookup_listener(struct net *net,
 	struct sock *result = NULL;
 	unsigned int hash2;
 
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
+					      saddr, sport, daddr, hnum);
+		if (result)
+			goto done;
+	}
+
 	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
 
-- 
cgit v1.2.3


From 2be90e914c12bdea70b0bd297d5715ee66eb46d0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 19:51:18 -0700
Subject: dmaengine: linux/dmaengine.h: drop duplicated word in a comment

Drop the doubled word "has" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: dmaengine@vger.kernel.org
Link: https://lore.kernel.org/r/06e64046-ebf1-15db-dbaf-73698de3b493@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 9f9a13a2c01f..883e1e087de5 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -164,7 +164,7 @@ struct dma_interleaved_template {
  * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of
  *  this transaction
  * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client
- *  acknowledges receipt, i.e. has has a chance to establish any dependency
+ *  acknowledges receipt, i.e. has a chance to establish any dependency
  *  chains
  * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q
  * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P
-- 
cgit v1.2.3


From 2f9237d4f6df49b74c51cdac555b0a9979d0c237 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jul 2020 09:30:00 +0200
Subject: dma-mapping: make support for dma ops optional

Avoid the overhead of the dma ops support for tiny builds that only
use the direct mapping.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/alpha/Kconfig               |  1 +
 arch/arm/Kconfig                 |  1 +
 arch/ia64/Kconfig                |  1 +
 arch/mips/Kconfig                |  1 +
 arch/parisc/Kconfig              |  1 +
 arch/powerpc/Kconfig             |  1 +
 arch/s390/Kconfig                |  1 +
 arch/sparc/Kconfig               |  1 +
 arch/x86/Kconfig                 |  1 +
 drivers/infiniband/core/device.c |  6 +++++-
 drivers/iommu/Kconfig            |  2 ++
 drivers/macintosh/macio_asic.c   |  4 ++--
 drivers/misc/mic/Kconfig         |  4 ++++
 drivers/vdpa/Kconfig             |  1 +
 drivers/xen/Kconfig              |  1 +
 include/linux/device.h           |  3 ++-
 include/linux/dma-mapping.h      | 12 +++++++++++-
 kernel/dma/Kconfig               |  4 ++++
 kernel/dma/Makefile              |  3 ++-
 19 files changed, 43 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 10862c5a8c76..9c5f06e8eb9b 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -7,6 +7,7 @@ config ALPHA
 	select ARCH_NO_PREEMPT
 	select ARCH_NO_SG_CHAIN
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select DMA_OPS if PCI
 	select FORCE_PCI if !ALPHA_JENSEN
 	select PCI_DOMAINS if PCI
 	select PCI_SYSCALL if PCI
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2ac74904a3ce..bee35b0187e4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -41,6 +41,7 @@ config ARM
 	select CPU_PM if SUSPEND || CPU_IDLE
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select DMA_DECLARE_COHERENT
+	select DMA_OPS
 	select DMA_REMAP if MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1fa2fe2ef053..5b4ec80bf586 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -192,6 +192,7 @@ config IA64_SGI_UV
 
 config IA64_HP_SBA_IOMMU
 	bool "HP SBA IOMMU support"
+	select DMA_OPS
 	default y
 	help
 	  Say Y here to add support for the SBA IOMMU found on HP zx1 and
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 6fee1a133e9d..8a458105e445 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -367,6 +367,7 @@ config MACH_JAZZ
 	select ARC_PROMLIB
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select DMA_OPS
 	select FW_ARC
 	select FW_ARC32
 	select ARCH_MAY_HAVE_PC_FDC
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 8e4c3708773d..38c1eafc1f1a 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -14,6 +14,7 @@ config PARISC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_NO_SG_CHAIN
 	select ARCH_SUPPORTS_MEMORY_FAILURE
+	select DMA_OPS
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9fa23eb320ff..e9b091d35872 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -151,6 +151,7 @@ config PPC
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select DMA_OPS				if PPC64
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c7d7ede6300c..687fe23f61cc 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -113,6 +113,7 @@ config S390
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
+	select DMA_OPS if PCI
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_AUTOPROBE
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 5bf2dc163540..5db1faaaee31 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -15,6 +15,7 @@ config SPARC
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT if SPARC64 && PCI
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select DMA_OPS
 	select OF
 	select OF_PROMTREE
 	select HAVE_ASM_MODVERSIONS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 883da0abf779..96ab92754158 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -909,6 +909,7 @@ config DMI
 
 config GART_IOMMU
 	bool "Old AMD GART IOMMU support"
+	select DMA_OPS
 	select IOMMU_HELPER
 	select SWIOTLB
 	depends on X86_64 && PCI && AMD_NB
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 905a2beaf885..2927a9d16eaa 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1183,6 +1183,8 @@ static void setup_dma_device(struct ib_device *device)
 	struct device *parent = device->dev.parent;
 
 	WARN_ON_ONCE(device->dma_device);
+
+#ifdef CONFIG_DMA_OPS
 	if (device->dev.dma_ops) {
 		/*
 		 * The caller provided custom DMA operations. Copy the
@@ -1203,7 +1205,9 @@ static void setup_dma_device(struct ib_device *device)
 			else
 				WARN_ON_ONCE(true);
 		}
-	} else {
+	} else
+#endif /* CONFIG_DMA_OPS */
+	{
 		/*
 		 * The caller did not provide custom DMA operations. Use the
 		 * DMA mapping operations of the parent device.
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index b0f308cb7f7c..b622af72448f 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -97,6 +97,7 @@ config OF_IOMMU
 # IOMMU-agnostic DMA-mapping layer
 config IOMMU_DMA
 	bool
+	select DMA_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IRQ_MSI_IOMMU
@@ -183,6 +184,7 @@ config DMAR_TABLE
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64)
+	select DMA_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select NEED_DMA_MAP_STATE
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 92d142d2b75f..49af60bdac92 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -382,7 +382,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	dma_set_max_seg_size(&dev->ofdev.dev, 65536);
 	dma_set_seg_boundary(&dev->ofdev.dev, 0xffffffff);
 
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(CONFIG_DMA_OPS)
 	/* Set the DMA ops to the ones from the PCI device, this could be
 	 * fishy if we didn't know that on PowerMac it's always direct ops
 	 * or iommu ops that will work fine
@@ -391,7 +391,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	 */
 	dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
 	dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops;
-#endif /* CONFIG_PCI */
+#endif /* CONFIG_PCI && CONFIG_DMA_OPS */
 
 #ifdef DEBUG
 	printk("preparing mdev @%p, ofdev @%p, dev @%p, kobj @%p\n",
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 8f201d019f5a..b9bb086785db 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -4,6 +4,7 @@ menu "Intel MIC & related support"
 config INTEL_MIC_BUS
 	tristate "Intel MIC Bus Driver"
 	depends on 64BIT && PCI && X86
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
@@ -19,6 +20,7 @@ config INTEL_MIC_BUS
 config SCIF_BUS
 	tristate "SCIF Bus Driver"
 	depends on 64BIT && PCI && X86
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
@@ -33,6 +35,7 @@ config SCIF_BUS
 
 config VOP_BUS
 	tristate "VOP Bus Driver"
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the VOP Bus, such as CONFIG_INTEL_MIC_HOST
@@ -49,6 +52,7 @@ config INTEL_MIC_HOST
 	tristate "Intel MIC Host Driver"
 	depends on 64BIT && PCI && X86
 	depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
+	select DMA_OPS
 	help
 	  This enables Host Driver support for the Intel Many Integrated
 	  Core (MIC) family of PCIe form factor coprocessor devices that
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 3e1ceb8e9f2b..d93a69b12f81 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -11,6 +11,7 @@ if VDPA
 config VDPA_SIM
 	tristate "vDPA device simulator"
 	depends on RUNTIME_TESTING_MENU && HAS_DMA
+	select DMA_OPS
 	select VHOST_RING
 	default n
 	help
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 727f11eb46b2..1d339ef92422 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -179,6 +179,7 @@ config XEN_GRANT_DMA_ALLOC
 
 config SWIOTLB_XEN
 	def_bool y
+	select DMA_OPS
 	select SWIOTLB
 
 config XEN_PCIDEV_BACKEND
diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..4c4af98321eb 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -568,8 +568,9 @@ struct device {
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	struct list_head	msi_list;
 #endif
-
+#ifdef CONFIG_DMA_OPS
 	const struct dma_map_ops *dma_ops;
+#endif
 	u64		*dma_mask;	/* dma mask (if dma'able device) */
 	u64		coherent_dma_mask;/* Like dma_mask, but for
 					     alloc_coherent mappings as
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index bd0a6f5ee445..39da883c8619 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -191,6 +191,7 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 
+#ifdef CONFIG_DMA_OPS
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 	if (dev->dma_ops)
@@ -203,7 +204,16 @@ static inline void set_dma_ops(struct device *dev,
 {
 	dev->dma_ops = dma_ops;
 }
-
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return NULL;
+}
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+}
+#endif /* CONFIG_DMA_OPS */
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 1da3f44f2565..5cfb2428593a 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -5,6 +5,9 @@ config HAS_DMA
 	depends on !NO_DMA
 	default y
 
+config DMA_OPS
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
@@ -60,6 +63,7 @@ config DMA_NONCOHERENT_CACHE_SYNC
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
+	select DMA_OPS
 
 config SWIOTLB
 	bool
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index 370f63344e9c..32c7c1942bbd 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o dummy.o
+obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o
+obj-$(CONFIG_DMA_OPS)			+= dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
 obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
-- 
cgit v1.2.3


From d35834c64820c7ef397f8a244061d4450720540e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Mar 2020 18:19:30 +0100
Subject: dma-mapping: add a dma_ops_bypass flag to struct device

Several IOMMU drivers have a bypass mode where they can use a direct
mapping if the devices DMA mask is large enough.  Add generic support
to the core dma-mapping code to do that to switch those drivers to
a common solution.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 include/linux/device.h |  8 ++++++
 kernel/dma/Kconfig     |  8 ++++++
 kernel/dma/mapping.c   | 74 +++++++++++++++++++++++++++++++++++---------------
 3 files changed, 68 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 4c4af98321eb..1f71acf37f78 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -523,6 +523,11 @@ struct dev_links_info {
  *		  sync_state() callback.
  * @dma_coherent: this particular device is dma coherent, even if the
  *		architecture supports non-coherent devices.
+ * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the
+ *		streaming DMA operations (->map_* / ->unmap_* / ->sync_*),
+ *		and optionall (if the coherent mask is large enough) also
+ *		for dma allocations.  This flag is managed by the dma ops
+ *		instance from ->dma_supported.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -623,6 +628,9 @@ struct device {
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	bool			dma_coherent:1;
 #endif
+#ifdef CONFIG_DMA_OPS_BYPASS
+	bool			dma_ops_bypass : 1;
+#endif
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 5cfb2428593a..f4770fcfa62b 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -8,6 +8,14 @@ config HAS_DMA
 config DMA_OPS
 	bool
 
+#
+# IOMMU drivers that can bypass the IOMMU code and optionally use the direct
+# mapping fast path should select this option and set the dma_ops_bypass
+# flag in struct device where applicable
+#
+config DMA_OPS_BYPASS
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index b53953024512..0d129421e75f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -105,9 +105,35 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 }
 EXPORT_SYMBOL(dmam_alloc_attrs);
 
-static inline bool dma_is_direct(const struct dma_map_ops *ops)
+static bool dma_go_direct(struct device *dev, dma_addr_t mask,
+		const struct dma_map_ops *ops)
 {
-	return likely(!ops);
+	if (likely(!ops))
+		return true;
+#ifdef CONFIG_DMA_OPS_BYPASS
+	if (dev->dma_ops_bypass)
+		return min_not_zero(mask, dev->bus_dma_limit) >=
+			    dma_direct_get_required_mask(dev);
+#endif
+	return false;
+}
+
+
+/*
+ * Check if the devices uses a direct mapping for streaming DMA operations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_alloc_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, dev->coherent_dma_mask, ops);
+}
+
+static inline bool dma_map_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, *dev->dma_mask, ops);
 }
 
 dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
@@ -118,7 +144,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
@@ -134,7 +160,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_unmap_page(dev, addr, size, dir, attrs);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, addr, size, dir, attrs);
@@ -153,7 +179,7 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
 		ents = ops->map_sg(dev, sg, nents, dir, attrs);
@@ -172,7 +198,7 @@ void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
 	else if (ops->unmap_sg)
 		ops->unmap_sg(dev, sg, nents, dir, attrs);
@@ -191,7 +217,7 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
 	else if (ops->map_resource)
 		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
@@ -207,7 +233,7 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (!dma_is_direct(ops) && ops->unmap_resource)
+	if (!dma_map_direct(dev, ops) && ops->unmap_resource)
 		ops->unmap_resource(dev, addr, size, dir, attrs);
 	debug_dma_unmap_resource(dev, addr, size, dir);
 }
@@ -219,7 +245,7 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 	else if (ops->sync_single_for_cpu)
 		ops->sync_single_for_cpu(dev, addr, size, dir);
@@ -233,7 +259,7 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_single_for_device(dev, addr, size, dir);
 	else if (ops->sync_single_for_device)
 		ops->sync_single_for_device(dev, addr, size, dir);
@@ -247,7 +273,7 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
 	else if (ops->sync_sg_for_cpu)
 		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
@@ -261,7 +287,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
 	else if (ops->sync_sg_for_device)
 		ops->sync_sg_for_device(dev, sg, nelems, dir);
@@ -302,7 +328,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
 				size, attrs);
 	if (!ops->get_sgtable)
@@ -372,7 +398,7 @@ bool dma_can_mmap(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_can_mmap(dev);
 	return ops->mmap != NULL;
 }
@@ -397,7 +423,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
 				attrs);
 	if (!ops->mmap)
@@ -410,7 +436,7 @@ u64 dma_get_required_mask(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_required_mask(dev);
 	if (ops->get_required_mask)
 		return ops->get_required_mask(dev);
@@ -441,7 +467,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)
 		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
@@ -473,7 +499,7 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
 	else if (ops->free)
 		ops->free(dev, size, cpu_addr, dma_handle, attrs);
@@ -484,7 +510,11 @@ int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	/*
+	 * ->dma_supported sets the bypass flag, so we must always call
+	 * into the method here unless the device is truly direct mapped.
+	 */
+	if (!ops)
 		return dma_direct_supported(dev, mask);
 	if (!ops->dma_supported)
 		return 1;
@@ -540,7 +570,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 
 	BUG_ON(!valid_dma_direction(dir));
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		arch_dma_cache_sync(dev, vaddr, size, dir);
 	else if (ops->cache_sync)
 		ops->cache_sync(dev, vaddr, size, dir);
@@ -552,7 +582,7 @@ size_t dma_max_mapping_size(struct device *dev)
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	size_t size = SIZE_MAX;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		size = dma_direct_max_mapping_size(dev);
 	else if (ops && ops->max_mapping_size)
 		size = ops->max_mapping_size(dev);
@@ -565,7 +595,7 @@ bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		return dma_direct_need_sync(dev, dma_addr);
 	return ops->sync_single_for_cpu || ops->sync_single_for_device;
 }
-- 
cgit v1.2.3


From 35694afc92646ac24d7f3ef34a7387876d998fe7 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 1 Jul 2020 08:21:37 +0200
Subject: media: device property: Add a function to test is a fwnode is a graph
 endpoint
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers may need to test if a fwnode is a graph endpoint. To avoid
hand-written solutions that wouldn't work for all fwnode types, add a
new fwnode_graph_is_endpoint() function for this purpose. We don't need
to wire it up to different backends for OF and ACPI for now, as the
implementation can simply be based on checkout the presence of a
remote-endpoint property.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/property.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/property.h b/include/linux/property.h
index 10d03572f52e..9f805c442819 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -389,6 +389,11 @@ struct fwnode_handle *
 fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port,
 			     u32 endpoint);
 
+static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode)
+{
+	return fwnode_property_present(fwnode, "remote-endpoint");
+}
+
 /*
  * Fwnode lookup flags
  *
-- 
cgit v1.2.3


From 124ea650d3072b005457faed69909221c2905a1f Mon Sep 17 00:00:00 2001
From: Adrian Reber <areber@redhat.com>
Date: Sun, 19 Jul 2020 12:04:11 +0200
Subject: capabilities: Introduce CAP_CHECKPOINT_RESTORE

This patch introduces CAP_CHECKPOINT_RESTORE, a new capability facilitating
checkpoint/restore for non-root users.

Over the last years, The CRIU (Checkpoint/Restore In Userspace) team has
been asked numerous times if it is possible to checkpoint/restore a
process as non-root. The answer usually was: 'almost'.

The main blocker to restore a process as non-root was to control the PID
of the restored process. This feature available via the clone3 system
call, or via /proc/sys/kernel/ns_last_pid is unfortunately guarded by
CAP_SYS_ADMIN.

In the past two years, requests for non-root checkpoint/restore have
increased due to the following use cases:
* Checkpoint/Restore in an HPC environment in combination with a
  resource manager distributing jobs where users are always running as
  non-root. There is a desire to provide a way to checkpoint and
  restore long running jobs.
* Container migration as non-root
* We have been in contact with JVM developers who are integrating
  CRIU into a Java VM to decrease the startup time. These
  checkpoint/restore applications are not meant to be running with
  CAP_SYS_ADMIN.

We have seen the following workarounds:
* Use a setuid wrapper around CRIU:
  See https://github.com/FredHutch/slurm-examples/blob/master/checkpointer/lib/checkpointer/checkpointer-suid.c
* Use a setuid helper that writes to ns_last_pid.
  Unfortunately, this helper delegation technique is impossible to use
  with clone3, and is thus prone to races.
  See https://github.com/twosigma/set_ns_last_pid
* Cycle through PIDs with fork() until the desired PID is reached:
  This has been demonstrated to work with cycling rates of 100,000 PIDs/s
  See https://github.com/twosigma/set_ns_last_pid
* Patch out the CAP_SYS_ADMIN check from the kernel
* Run the desired application in a new user and PID namespace to provide
  a local CAP_SYS_ADMIN for controlling PIDs. This technique has limited
  use in typical container environments (e.g., Kubernetes) as /proc is
  typically protected with read-only layers (e.g., /proc/sys) for
  hardening purposes. Read-only layers prevent additional /proc mounts
  (due to proc's SB_I_USERNS_VISIBLE property), making the use of new
  PID namespaces limited as certain applications need access to /proc
  matching their PID namespace.

The introduced capability allows to:
* Control PIDs when the current user is CAP_CHECKPOINT_RESTORE capable
  for the corresponding PID namespace via ns_last_pid/clone3.
* Open files in /proc/pid/map_files when the current user is
  CAP_CHECKPOINT_RESTORE capable in the root namespace, useful for
  recovering files that are unreachable via the file system such as
  deleted files, or memfd files.

See corresponding selftest for an example with clone3().

Signed-off-by: Adrian Reber <areber@redhat.com>
Signed-off-by: Nicolas Viennot <Nicolas.Viennot@twosigma.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200719100418.2112740-2-areber@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/capability.h          | 6 ++++++
 include/uapi/linux/capability.h     | 9 ++++++++-
 security/selinux/include/classmap.h | 5 +++--
 3 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/capability.h b/include/linux/capability.h
index b4345b38a6be..1e7fe311cabe 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -261,6 +261,12 @@ static inline bool bpf_capable(void)
 	return capable(CAP_BPF) || capable(CAP_SYS_ADMIN);
 }
 
+static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns)
+{
+	return ns_capable(ns, CAP_CHECKPOINT_RESTORE) ||
+		ns_capable(ns, CAP_SYS_ADMIN);
+}
+
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
 
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 48ff0757ae5e..395dd0df8d08 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -408,7 +408,14 @@ struct vfs_ns_cap_data {
  */
 #define CAP_BPF			39
 
-#define CAP_LAST_CAP         CAP_BPF
+
+/* Allow checkpoint/restore related operations */
+/* Allow PID selection during clone3() */
+/* Allow writing to ns_last_pid */
+
+#define CAP_CHECKPOINT_RESTORE	40
+
+#define CAP_LAST_CAP         CAP_CHECKPOINT_RESTORE
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 98e1513b608a..40cebde62856 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -27,9 +27,10 @@
 	    "audit_control", "setfcap"
 
 #define COMMON_CAP2_PERMS  "mac_override", "mac_admin", "syslog", \
-		"wake_alarm", "block_suspend", "audit_read", "perfmon", "bpf"
+		"wake_alarm", "block_suspend", "audit_read", "perfmon", "bpf", \
+		"checkpoint_restore"
 
-#if CAP_LAST_CAP > CAP_BPF
+#if CAP_LAST_CAP > CAP_CHECKPOINT_RESTORE
 #error New capability defined, please update COMMON_CAP2_PERMS.
 #endif
 
-- 
cgit v1.2.3


From a4872f7a4bc16d6ed831833b4f1ec16df642c367 Mon Sep 17 00:00:00 2001
From: Tim Harvey <tharvey@gateworks.com>
Date: Tue, 9 Jun 2020 07:57:20 -0700
Subject: hwmon: (gsc) add 16bit pre-scaled voltage mode

add a 16-bit pre-scaled voltage mode to adc and clarify that existing
pre-scaled mode is 24bit.

Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/1591714640-10332-3-git-send-email-tharvey@gateworks.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/gsc-hwmon.c               | 8 +++++---
 include/linux/platform_data/gsc_hwmon.h | 3 ++-
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c
index 2137bc65829d..3dfe2ca2f8c8 100644
--- a/drivers/hwmon/gsc-hwmon.c
+++ b/drivers/hwmon/gsc-hwmon.c
@@ -159,7 +159,7 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		return -EOPNOTSUPP;
 	}
 
-	sz = (ch->mode == mode_voltage) ? 3 : 2;
+	sz = (ch->mode == mode_voltage_24bit) ? 3 : 2;
 	ret = regmap_bulk_read(hwmon->regmap, ch->reg, buf, sz);
 	if (ret)
 		return ret;
@@ -186,7 +186,8 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		/* adjust by uV offset */
 		tmp += ch->mvoffset;
 		break;
-	case mode_voltage:
+	case mode_voltage_24bit:
+	case mode_voltage_16bit:
 		/* no adjustment needed */
 		break;
 	}
@@ -336,7 +337,8 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 						     HWMON_T_LABEL;
 			i_temp++;
 			break;
-		case mode_voltage:
+		case mode_voltage_24bit:
+		case mode_voltage_16bit:
 		case mode_voltage_raw:
 			if (i_in == GSC_HWMON_MAX_IN_CH) {
 				dev_err(gsc->dev, "too many input channels\n");
diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h
index ec1611aff863..37a8f554da00 100644
--- a/include/linux/platform_data/gsc_hwmon.h
+++ b/include/linux/platform_data/gsc_hwmon.h
@@ -4,8 +4,9 @@
 
 enum gsc_hwmon_mode {
 	mode_temperature,
-	mode_voltage,
+	mode_voltage_24bit,
 	mode_voltage_raw,
+	mode_voltage_16bit,
 	mode_max,
 };
 
-- 
cgit v1.2.3


From a06d30ae7af492497ffbca6abf1621d508b8fcaa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:10 +0200
Subject: net/atm: remove the atmdev_ops {get, set}sockopt methods

All implementations of these two methods are dummies that always
return -EINVAL.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/eni.c        | 17 -----------------
 drivers/atm/firestream.c |  2 --
 drivers/atm/fore200e.c   | 27 ---------------------------
 drivers/atm/horizon.c    | 40 ----------------------------------------
 drivers/atm/iphase.c     | 16 ----------------
 drivers/atm/lanai.c      |  2 --
 drivers/atm/solos-pci.c  |  2 --
 drivers/atm/zatm.c       | 16 ----------------
 include/linux/atmdev.h   |  9 ---------
 net/atm/common.c         | 14 ++------------
 10 files changed, 2 insertions(+), 143 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 17d47ad03ab7..b3d8e00e7671 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2027,21 +2027,6 @@ static int eni_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 	return dev->phy->ioctl(dev,cmd,arg);
 }
 
-
-static int eni_getsockopt(struct atm_vcc *vcc,int level,int optname,
-    void __user *optval,int optlen)
-{
-	return -EINVAL;
-}
-
-
-static int eni_setsockopt(struct atm_vcc *vcc,int level,int optname,
-    void __user *optval,unsigned int optlen)
-{
-	return -EINVAL;
-}
-
-
 static int eni_send(struct atm_vcc *vcc,struct sk_buff *skb)
 {
 	enum enq_res res;
@@ -2215,8 +2200,6 @@ static const struct atmdev_ops ops = {
 	.open		= eni_open,
 	.close		= eni_close,
 	.ioctl		= eni_ioctl,
-	.getsockopt	= eni_getsockopt,
-	.setsockopt	= eni_setsockopt,
 	.send		= eni_send,
 	.phy_put	= eni_phy_put,
 	.phy_get	= eni_phy_get,
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index cc87004d5e2d..2ca9ec802734 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1277,8 +1277,6 @@ static const struct atmdev_ops ops = {
 	.send =         fs_send,
 	.owner =        THIS_MODULE,
 	/* ioctl:          fs_ioctl, */
-	/* getsockopt:     fs_getsockopt, */
-	/* setsockopt:     fs_setsockopt, */
 	/* change_qos:     fs_change_qos, */
 
 	/* For now implement these internally here... */  
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index f4ad7ce25ae8..a81bc49c14ac 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -1710,31 +1710,6 @@ fore200e_getstats(struct fore200e* fore200e)
     return 0;
 }
 
-
-static int
-fore200e_getsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, int optlen)
-{
-    /* struct fore200e* fore200e = FORE200E_DEV(vcc->dev); */
-
-    DPRINTK(2, "getsockopt %d.%d.%d, level = %d, optname = 0x%x, optval = 0x%p, optlen = %d\n",
-	    vcc->itf, vcc->vpi, vcc->vci, level, optname, optval, optlen);
-
-    return -EINVAL;
-}
-
-
-static int
-fore200e_setsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, unsigned int optlen)
-{
-    /* struct fore200e* fore200e = FORE200E_DEV(vcc->dev); */
-    
-    DPRINTK(2, "setsockopt %d.%d.%d, level = %d, optname = 0x%x, optval = 0x%p, optlen = %d\n",
-	    vcc->itf, vcc->vpi, vcc->vci, level, optname, optval, optlen);
-    
-    return -EINVAL;
-}
-
-
 #if 0 /* currently unused */
 static int
 fore200e_get_oc3(struct fore200e* fore200e, struct oc3_regs* regs)
@@ -3026,8 +3001,6 @@ static const struct atmdev_ops fore200e_ops = {
 	.open       = fore200e_open,
 	.close      = fore200e_close,
 	.ioctl      = fore200e_ioctl,
-	.getsockopt = fore200e_getsockopt,
-	.setsockopt = fore200e_setsockopt,
 	.send       = fore200e_send,
 	.change_qos = fore200e_change_qos,
 	.proc_read  = fore200e_proc_read,
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c
index e5da51f907a2..4f2951cbe69c 100644
--- a/drivers/atm/horizon.c
+++ b/drivers/atm/horizon.c
@@ -2527,46 +2527,6 @@ static void hrz_close (struct atm_vcc * atm_vcc) {
   clear_bit(ATM_VF_ADDR,&atm_vcc->flags);
 }
 
-#if 0
-static int hrz_getsockopt (struct atm_vcc * atm_vcc, int level, int optname,
-			   void *optval, int optlen) {
-  hrz_dev * dev = HRZ_DEV(atm_vcc->dev);
-  PRINTD (DBG_FLOW|DBG_VCC, "hrz_getsockopt");
-  switch (level) {
-    case SOL_SOCKET:
-      switch (optname) {
-//	case SO_BCTXOPT:
-//	  break;
-//	case SO_BCRXOPT:
-//	  break;
-	default:
-	  return -ENOPROTOOPT;
-      };
-      break;
-  }
-  return -EINVAL;
-}
-
-static int hrz_setsockopt (struct atm_vcc * atm_vcc, int level, int optname,
-			   void *optval, unsigned int optlen) {
-  hrz_dev * dev = HRZ_DEV(atm_vcc->dev);
-  PRINTD (DBG_FLOW|DBG_VCC, "hrz_setsockopt");
-  switch (level) {
-    case SOL_SOCKET:
-      switch (optname) {
-//	case SO_BCTXOPT:
-//	  break;
-//	case SO_BCRXOPT:
-//	  break;
-	default:
-	  return -ENOPROTOOPT;
-      };
-      break;
-  }
-  return -EINVAL;
-}
-#endif
-
 #if 0
 static int hrz_ioctl (struct atm_dev * atm_dev, unsigned int cmd, void *arg) {
   hrz_dev * dev = HRZ_DEV(atm_dev);
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 8c7a996d1f16..eef637fd90b3 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -2880,20 +2880,6 @@ static int ia_ioctl(struct atm_dev *dev, unsigned int cmd, void __user *arg)
    return 0;  
 }  
   
-static int ia_getsockopt(struct atm_vcc *vcc, int level, int optname,   
-	void __user *optval, int optlen)  
-{  
-	IF_EVENT(printk(">ia_getsockopt\n");)  
-	return -EINVAL;  
-}  
-  
-static int ia_setsockopt(struct atm_vcc *vcc, int level, int optname,   
-	void __user *optval, unsigned int optlen)  
-{  
-	IF_EVENT(printk(">ia_setsockopt\n");)  
-	return -EINVAL;  
-}  
-  
 static int ia_pkt_tx (struct atm_vcc *vcc, struct sk_buff *skb) {
         IADEV *iadev;
         struct dle *wr_ptr;
@@ -3164,8 +3150,6 @@ static const struct atmdev_ops ops = {
 	.open		= ia_open,  
 	.close		= ia_close,  
 	.ioctl		= ia_ioctl,  
-	.getsockopt	= ia_getsockopt,  
-	.setsockopt	= ia_setsockopt,  
 	.send		= ia_send,  
 	.phy_put	= ia_phy_put,  
 	.phy_get	= ia_phy_get,  
diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c
index 645a6bc1df88..986c1313694c 100644
--- a/drivers/atm/lanai.c
+++ b/drivers/atm/lanai.c
@@ -2537,8 +2537,6 @@ static const struct atmdev_ops ops = {
 	.dev_close	= lanai_dev_close,
 	.open		= lanai_open,
 	.close		= lanai_close,
-	.getsockopt	= NULL,
-	.setsockopt	= NULL,
 	.send		= lanai_send,
 	.phy_put	= NULL,
 	.phy_get	= NULL,
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index b7646ae55942..94fbc3abe60e 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -1179,8 +1179,6 @@ static const struct atmdev_ops fpga_ops = {
 	.open =		popen,
 	.close =	pclose,
 	.ioctl =	NULL,
-	.getsockopt =	NULL,
-	.setsockopt =	NULL,
 	.send =		psend,
 	.send_oam =	NULL,
 	.phy_put =	NULL,
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 57f97b95a453..2788b985edbe 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1515,20 +1515,6 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 	}
 }
 
-
-static int zatm_getsockopt(struct atm_vcc *vcc,int level,int optname,
-    void __user *optval,int optlen)
-{
-	return -EINVAL;
-}
-
-
-static int zatm_setsockopt(struct atm_vcc *vcc,int level,int optname,
-    void __user *optval,unsigned int optlen)
-{
-	return -EINVAL;
-}
-
 static int zatm_send(struct atm_vcc *vcc,struct sk_buff *skb)
 {
 	int error;
@@ -1582,8 +1568,6 @@ static const struct atmdev_ops ops = {
 	.open		= zatm_open,
 	.close		= zatm_close,
 	.ioctl		= zatm_ioctl,
-	.getsockopt	= zatm_getsockopt,
-	.setsockopt	= zatm_setsockopt,
 	.send		= zatm_send,
 	.phy_put	= zatm_phy_put,
 	.phy_get	= zatm_phy_get,
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 8124815eb121..5d5ff2203fa2 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -176,11 +176,6 @@ struct atm_dev {
 #define ATM_OF_IMMED  1		/* Attempt immediate delivery */
 #define ATM_OF_INRATE 2		/* Attempt in-rate delivery */
 
-
-/*
- * ioctl, getsockopt, and setsockopt are optional and can be set to NULL.
- */
-
 struct atmdev_ops { /* only send is required */
 	void (*dev_close)(struct atm_dev *dev);
 	int (*open)(struct atm_vcc *vcc);
@@ -190,10 +185,6 @@ struct atmdev_ops { /* only send is required */
 	int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd,
 			    void __user *arg);
 #endif
-	int (*getsockopt)(struct atm_vcc *vcc,int level,int optname,
-	    void __user *optval,int optlen);
-	int (*setsockopt)(struct atm_vcc *vcc,int level,int optname,
-	    void __user *optval,unsigned int optlen);
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
 	void (*phy_put)(struct atm_dev *dev,unsigned char value,
diff --git a/net/atm/common.c b/net/atm/common.c
index 8575f5d52087..9b28f1fb3c69 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -782,13 +782,8 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
 			vcc->atm_options &= ~ATM_ATMOPT_CLP;
 		return 0;
 	default:
-		if (level == SOL_SOCKET)
-			return -EINVAL;
-		break;
-	}
-	if (!vcc->dev || !vcc->dev->ops->setsockopt)
 		return -EINVAL;
-	return vcc->dev->ops->setsockopt(vcc, level, optname, optval, optlen);
+	}
 }
 
 int vcc_getsockopt(struct socket *sock, int level, int optname,
@@ -826,13 +821,8 @@ int vcc_getsockopt(struct socket *sock, int level, int optname,
 		return copy_to_user(optval, &pvc, sizeof(pvc)) ? -EFAULT : 0;
 	}
 	default:
-		if (level == SOL_SOCKET)
-			return -EINVAL;
-		break;
-	}
-	if (!vcc->dev || !vcc->dev->ops->getsockopt)
 		return -EINVAL;
-	return vcc->dev->ops->getsockopt(vcc, level, optname, optval, len);
+	}
 }
 
 int register_atmdevice_notifier(struct notifier_block *nb)
-- 
cgit v1.2.3


From 4d295e54611509854a12c26f95a6f4430731d614 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:13 +0200
Subject: net: simplify cBPF setsockopt compat handling

Add a helper that copies either a native or compat bpf_fprog from
userspace after verifying the length, and remove the compat setsockopt
handlers that now aren't required.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h |  4 ++--
 include/net/compat.h   |  1 -
 net/compat.c           | 45 +--------------------------------------------
 net/core/filter.c      | 23 +++++++++++++++++++++++
 net/core/sock.c        | 30 ++++++++++--------------------
 net/packet/af_packet.c | 33 ++++-----------------------------
 6 files changed, 40 insertions(+), 96 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0b0144752d78..4d049c8e1fbe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -502,13 +502,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		offsetof(TYPE, MEMBER);						\
 	})
 
-#ifdef CONFIG_COMPAT
 /* A struct sock_filter is architecture independent. */
 struct compat_sock_fprog {
 	u16		len;
 	compat_uptr_t	filter;	/* struct sock_filter * */
 };
-#endif
 
 struct sock_fprog_kern {
 	u16			len;
@@ -1278,4 +1276,6 @@ struct bpf_sockopt_kern {
 	s32		retval;
 };
 
+int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len);
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/compat.h b/include/net/compat.h
index f241666117d8..745db0d605b6 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -61,7 +61,6 @@ int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
 			compat_size_t *len);
 int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
 		      struct sockaddr __user **, struct iovec **);
-struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
 int put_cmsg_compat(struct msghdr*, int, int, int, void *);
 
 int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *,
diff --git a/net/compat.c b/net/compat.c
index 5e3041a2c37d..3e6c2c5ff260 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -335,49 +335,6 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 	__scm_destroy(scm);
 }
 
-/* allocate a 64-bit sock_fprog on the user stack for duration of syscall. */
-struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval)
-{
-	struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval;
-	struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog));
-	struct compat_sock_fprog f32;
-	struct sock_fprog f;
-
-	if (copy_from_user(&f32, fprog32, sizeof(*fprog32)))
-		return NULL;
-	memset(&f, 0, sizeof(f));
-	f.len = f32.len;
-	f.filter = compat_ptr(f32.filter);
-	if (copy_to_user(kfprog, &f, sizeof(struct sock_fprog)))
-		return NULL;
-
-	return kfprog;
-}
-EXPORT_SYMBOL_GPL(get_compat_bpf_fprog);
-
-static int do_set_attach_filter(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int optlen)
-{
-	struct sock_fprog __user *kfprog;
-
-	kfprog = get_compat_bpf_fprog(optval);
-	if (!kfprog)
-		return -EFAULT;
-
-	return sock_setsockopt(sock, level, optname, (char __user *)kfprog,
-			      sizeof(struct sock_fprog));
-}
-
-static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int optlen)
-{
-	if (optname == SO_ATTACH_FILTER ||
-	    optname == SO_ATTACH_REUSEPORT_CBPF)
-		return do_set_attach_filter(sock, level, optname,
-					    optval, optlen);
-	return sock_setsockopt(sock, level, optname, optval, optlen);
-}
-
 static int __compat_sys_setsockopt(int fd, int level, int optname,
 				   char __user *optval, unsigned int optlen)
 {
@@ -396,7 +353,7 @@ static int __compat_sys_setsockopt(int fd, int level, int optname,
 		}
 
 		if (level == SOL_SOCKET)
-			err = compat_sock_setsockopt(sock, level,
+			err = sock_setsockopt(sock, level,
 					optname, optval, optlen);
 		else if (sock->ops->compat_setsockopt)
 			err = sock->ops->compat_setsockopt(sock, level,
diff --git a/net/core/filter.c b/net/core/filter.c
index bdd2382e655d..2bf6624796d8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,6 +77,29 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 
+int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len)
+{
+	if (in_compat_syscall()) {
+		struct compat_sock_fprog f32;
+
+		if (len != sizeof(f32))
+			return -EINVAL;
+		if (copy_from_user(&f32, src, sizeof(f32)))
+			return -EFAULT;
+		memset(dst, 0, sizeof(*dst));
+		dst->len = f32.len;
+		dst->filter = compat_ptr(f32.filter);
+	} else {
+		if (len != sizeof(*dst))
+			return -EINVAL;
+		if (copy_from_user(dst, src, sizeof(*dst)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user);
+
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
  *	@sk: sock associated with &sk_buff
diff --git a/net/core/sock.c b/net/core/sock.c
index 11d6f77dd562..e085df794825 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1059,19 +1059,14 @@ set_sndbuf:
 		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD);
 		break;
 
-	case SO_ATTACH_FILTER:
-		ret = -EINVAL;
-		if (optlen == sizeof(struct sock_fprog)) {
-			struct sock_fprog fprog;
-
-			ret = -EFAULT;
-			if (copy_from_user(&fprog, optval, sizeof(fprog)))
-				break;
+	case SO_ATTACH_FILTER: {
+		struct sock_fprog fprog;
 
+		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		if (!ret)
 			ret = sk_attach_filter(&fprog, sk);
-		}
 		break;
-
+	}
 	case SO_ATTACH_BPF:
 		ret = -EINVAL;
 		if (optlen == sizeof(u32)) {
@@ -1085,19 +1080,14 @@ set_sndbuf:
 		}
 		break;
 
-	case SO_ATTACH_REUSEPORT_CBPF:
-		ret = -EINVAL;
-		if (optlen == sizeof(struct sock_fprog)) {
-			struct sock_fprog fprog;
-
-			ret = -EFAULT;
-			if (copy_from_user(&fprog, optval, sizeof(fprog)))
-				break;
+	case SO_ATTACH_REUSEPORT_CBPF: {
+		struct sock_fprog fprog;
 
+		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		if (!ret)
 			ret = sk_reuseport_attach_filter(&fprog, sk);
-		}
 		break;
-
+	}
 	case SO_ATTACH_REUSEPORT_EBPF:
 		ret = -EINVAL;
 		if (optlen == sizeof(u32)) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 781fee93b7d5..35aee9e98053 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1545,10 +1545,10 @@ static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data,
 
 	if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
-	if (len != sizeof(fprog))
-		return -EINVAL;
-	if (copy_from_user(&fprog, data, len))
-		return -EFAULT;
+
+	ret = copy_bpf_fprog_from_user(&fprog, data, len);
+	if (ret)
+		return ret;
 
 	ret = bpf_prog_create_from_user(&new, &fprog, NULL, false);
 	if (ret)
@@ -4040,28 +4040,6 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	return 0;
 }
 
-
-#ifdef CONFIG_COMPAT
-static int compat_packet_setsockopt(struct socket *sock, int level, int optname,
-				    char __user *optval, unsigned int optlen)
-{
-	struct packet_sock *po = pkt_sk(sock->sk);
-
-	if (level != SOL_PACKET)
-		return -ENOPROTOOPT;
-
-	if (optname == PACKET_FANOUT_DATA &&
-	    po->fanout && po->fanout->type == PACKET_FANOUT_CBPF) {
-		optval = (char __user *)get_compat_bpf_fprog(optval);
-		if (!optval)
-			return -EFAULT;
-		optlen = sizeof(struct sock_fprog);
-	}
-
-	return packet_setsockopt(sock, level, optname, optval, optlen);
-}
-#endif
-
 static int packet_notifier(struct notifier_block *this,
 			   unsigned long msg, void *ptr)
 {
@@ -4549,9 +4527,6 @@ static const struct proto_ops packet_ops = {
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	packet_setsockopt,
 	.getsockopt =	packet_getsockopt,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_packet_setsockopt,
-#endif
 	.sendmsg =	packet_sendmsg,
 	.recvmsg =	packet_recvmsg,
 	.mmap =		packet_mmap,
-- 
cgit v1.2.3


From 8c918ffbbad49454ed26c53eb1b90bf98bb5e394 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:14 +0200
Subject: net: remove compat_sock_common_{get,set}sockopt

Add the compat handling to sock_common_{get,set}sockopt instead,
keyed of in_compat_syscall().  This allow to remove the now unused
->compat_{get,set}sockopt methods from struct proto_ops.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h      |  6 ------
 include/net/sock.h       |  4 ----
 net/core/sock.c          | 30 ++++++------------------------
 net/dccp/ipv4.c          |  4 ----
 net/dccp/ipv6.c          |  2 --
 net/ieee802154/socket.c  |  8 --------
 net/ipv4/af_inet.c       |  6 ------
 net/ipv6/af_inet6.c      |  4 ----
 net/ipv6/ipv6_sockglue.c | 12 ++----------
 net/ipv6/raw.c           |  2 --
 net/l2tp/l2tp_ip.c       |  4 ----
 net/l2tp/l2tp_ip6.c      |  2 --
 net/mptcp/protocol.c     |  6 ------
 net/phonet/socket.c      |  8 --------
 net/sctp/ipv6.c          |  2 --
 net/sctp/protocol.c      |  4 ----
 16 files changed, 8 insertions(+), 96 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/net.h b/include/linux/net.h
index 016a9c5faa34..858ff1d98154 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -165,12 +165,6 @@ struct proto_ops {
 				      int optname, char __user *optval, unsigned int optlen);
 	int		(*getsockopt)(struct socket *sock, int level,
 				      int optname, char __user *optval, int __user *optlen);
-#ifdef CONFIG_COMPAT
-	int		(*compat_setsockopt)(struct socket *sock, int level,
-				      int optname, char __user *optval, unsigned int optlen);
-	int		(*compat_getsockopt)(struct socket *sock, int level,
-				      int optname, char __user *optval, int __user *optlen);
-#endif
 	void		(*show_fdinfo)(struct seq_file *m, struct socket *sock);
 	int		(*sendmsg)   (struct socket *sock, struct msghdr *m,
 				      size_t total_len);
diff --git a/include/net/sock.h b/include/net/sock.h
index 4bf884165148..1fd7cf5fc751 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1744,10 +1744,6 @@ int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			int flags);
 int sock_common_setsockopt(struct socket *sock, int level, int optname,
 				  char __user *optval, unsigned int optlen);
-int compat_sock_common_getsockopt(struct socket *sock, int level,
-		int optname, char __user *optval, int __user *optlen);
-int compat_sock_common_setsockopt(struct socket *sock, int level,
-		int optname, char __user *optval, unsigned int optlen);
 
 void sk_common_release(struct sock *sk);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index e085df794825..018404d17626 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3199,23 +3199,14 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname,
 {
 	struct sock *sk = sock->sk;
 
-	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(sock_common_getsockopt);
-
 #ifdef CONFIG_COMPAT
-int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
-				  char __user *optval, int __user *optlen)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk->sk_prot->compat_getsockopt != NULL)
+	if (in_compat_syscal() && sk->sk_prot->compat_getsockopt)
 		return sk->sk_prot->compat_getsockopt(sk, level, optname,
 						      optval, optlen);
+#endif
 	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
 }
-EXPORT_SYMBOL(compat_sock_common_getsockopt);
-#endif
+EXPORT_SYMBOL(sock_common_getsockopt);
 
 int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			int flags)
@@ -3240,23 +3231,14 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname,
 {
 	struct sock *sk = sock->sk;
 
-	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(sock_common_setsockopt);
-
 #ifdef CONFIG_COMPAT
-int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
-				  char __user *optval, unsigned int optlen)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk->sk_prot->compat_setsockopt != NULL)
+	if (in_compat_syscall() && sk->sk_prot->compat_setsockopt)
 		return sk->sk_prot->compat_setsockopt(sk, level, optname,
 						      optval, optlen);
+#endif
 	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
 }
-EXPORT_SYMBOL(compat_sock_common_setsockopt);
-#endif
+EXPORT_SYMBOL(sock_common_setsockopt);
 
 void sk_common_release(struct sock *sk)
 {
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a7e989919c53..316cc5ac0da7 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -999,10 +999,6 @@ static const struct proto_ops inet_dccp_ops = {
 	.recvmsg	   = sock_common_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 static struct inet_protosw dccp_v4_protosw = {
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 650187d68851..b50f85a72cd5 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1083,8 +1083,6 @@ static const struct proto_ops inet6_dccp_ops = {
 	.sendpage	   = sock_no_sendpage,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index d93d4531aa9b..94ae9662133e 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -423,10 +423,6 @@ static const struct proto_ops ieee802154_raw_ops = {
 	.recvmsg	   = sock_common_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 /* DGRAM Sockets (802.15.4 dataframes) */
@@ -986,10 +982,6 @@ static const struct proto_ops ieee802154_dgram_ops = {
 	.recvmsg	   = sock_common_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 /* Create a socket. Initialise the socket, blank the addresses
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ff141d630bdf..4307503a6f0b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1043,8 +1043,6 @@ const struct proto_ops inet_stream_ops = {
 	.sendpage_locked   = tcp_sendpage_locked,
 	.peek_len	   = tcp_peek_len,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 	.compat_ioctl	   = inet_compat_ioctl,
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
@@ -1073,8 +1071,6 @@ const struct proto_ops inet_dgram_ops = {
 	.sendpage	   = inet_sendpage,
 	.set_peek_off	   = sk_set_peek_off,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 	.compat_ioctl	   = inet_compat_ioctl,
 #endif
 };
@@ -1105,8 +1101,6 @@ static const struct proto_ops inet_sockraw_ops = {
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = inet_sendpage,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 	.compat_ioctl	   = inet_compat_ioctl,
 #endif
 };
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b304b882e031..0306509ab063 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -688,8 +688,6 @@ const struct proto_ops inet6_stream_ops = {
 	.peek_len	   = tcp_peek_len,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
@@ -717,8 +715,6 @@ const struct proto_ops inet6_dgram_ops = {
 	.set_peek_off	   = sk_set_peek_off,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 20576e87a5f7..6ab44ec2c369 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -914,12 +914,8 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
 {
 	int err;
 
-	if (level == SOL_IP && sk->sk_type != SOCK_RAW) {
-		if (udp_prot.compat_setsockopt != NULL)
-			return udp_prot.compat_setsockopt(sk, level, optname,
-							  optval, optlen);
+	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
 		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
-	}
 
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
@@ -1480,12 +1476,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 {
 	int err;
 
-	if (level == SOL_IP && sk->sk_type != SOCK_RAW) {
-		if (udp_prot.compat_getsockopt != NULL)
-			return udp_prot.compat_getsockopt(sk, level, optname,
-							  optval, optlen);
+	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
 		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
-	}
 
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8ef5a7b30524..e23c6b461758 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1378,8 +1378,6 @@ const struct proto_ops inet6_sockraw_ops = {
 	.sendpage	   = sock_no_sendpage,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 955662a6dee7..f8d7412cfb3d 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -638,10 +638,6 @@ static const struct proto_ops l2tp_ip_ops = {
 	.recvmsg	   = sock_common_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 static struct inet_protosw l2tp_ip_protosw = {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 526ed2c24dd5..2cdc0b7a7a43 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -773,8 +773,6 @@ static const struct proto_ops l2tp_ip6_ops = {
 	.sendpage	   = sock_no_sendpage,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index dbe43e0cd734..f0b0b503c262 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2166,10 +2166,6 @@ static const struct proto_ops mptcp_stream_ops = {
 	.recvmsg	   = inet_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = inet_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 static struct inet_protosw mptcp_protosw = {
@@ -2222,8 +2218,6 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.sendpage	   = inet_sendpage,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 76d499f6af9a..87c60f83c180 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -441,10 +441,6 @@ const struct proto_ops phonet_dgram_ops = {
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
 	.getsockopt	= sock_no_getsockopt,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = sock_no_setsockopt,
-	.compat_getsockopt = sock_no_getsockopt,
-#endif
 	.sendmsg	= pn_socket_sendmsg,
 	.recvmsg	= sock_common_recvmsg,
 	.mmap		= sock_no_mmap,
@@ -466,10 +462,6 @@ const struct proto_ops phonet_stream_ops = {
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_common_setsockopt,
 	.getsockopt	= sock_common_getsockopt,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 	.sendmsg	= pn_socket_sendmsg,
 	.recvmsg	= sock_common_recvmsg,
 	.mmap		= sock_no_mmap,
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ccfa0ab3e7f4..ebda31b7747d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1033,8 +1033,6 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.mmap		   = sock_no_mmap,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index cde29f3c7fb3..8d25cc464efd 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1036,10 +1036,6 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.recvmsg	   = inet_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
 };
 
 /* Registration with AF_INET family.  */
-- 
cgit v1.2.3


From 55db9c0e853421fa71cac5e6855898601f78a1f5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:15 +0200
Subject: net: remove compat_sys_{get,set}sockopt

Now that the ->compat_{get,set}sockopt proto_ops methods are gone
there is no good reason left to keep the compat syscalls separate.

This fixes the odd use of unsigned int for the compat_setsockopt
optlen and the missing sock_use_custom_sol_socket.

It would also easily allow running the eBPF hooks for the compat
syscalls, but such a large change in behavior does not belong into
a consolidation patch like this one.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/include/asm/unistd32.h                  |  4 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  4 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  4 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  4 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  4 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  4 +-
 arch/sparc/kernel/sys32.S                          | 12 ++--
 arch/sparc/kernel/syscalls/syscall.tbl             |  4 +-
 arch/x86/entry/syscall_x32.c                       |  7 ++
 arch/x86/entry/syscalls/syscall_32.tbl             |  4 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |  4 +-
 include/linux/compat.h                             |  4 --
 include/linux/syscalls.h                           |  4 ++
 include/uapi/asm-generic/unistd.h                  |  4 +-
 net/compat.c                                       | 79 +---------------------
 net/socket.c                                       | 25 ++++---
 tools/include/uapi/asm-generic/unistd.h            |  4 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  4 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  4 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  4 +-
 20 files changed, 62 insertions(+), 125 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 6d95d0c8bf2f..166e36903110 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -599,9 +599,9 @@ __SYSCALL(__NR_recvfrom, compat_sys_recvfrom)
 #define __NR_shutdown 293
 __SYSCALL(__NR_shutdown, sys_shutdown)
 #define __NR_setsockopt 294
-__SYSCALL(__NR_setsockopt, compat_sys_setsockopt)
+__SYSCALL(__NR_setsockopt, sys_setsockopt)
 #define __NR_getsockopt 295
-__SYSCALL(__NR_getsockopt, compat_sys_getsockopt)
+__SYSCALL(__NR_getsockopt, sys_getsockopt)
 #define __NR_sendmsg 296
 __SYSCALL(__NR_sendmsg, compat_sys_sendmsg)
 #define __NR_recvmsg 297
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f777141f5256..8488b0d0a99e 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -60,8 +60,8 @@
 50	n32	getsockname			sys_getsockname
 51	n32	getpeername			sys_getpeername
 52	n32	socketpair			sys_socketpair
-53	n32	setsockopt			compat_sys_setsockopt
-54	n32	getsockopt			compat_sys_getsockopt
+53	n32	setsockopt			sys_setsockopt
+54	n32	getsockopt			sys_getsockopt
 55	n32	clone				__sys_clone
 56	n32	fork				__sys_fork
 57	n32	execve				compat_sys_execve
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 13280625d312..b20522f813f9 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -184,7 +184,7 @@
 170	o32	connect				sys_connect
 171	o32	getpeername			sys_getpeername
 172	o32	getsockname			sys_getsockname
-173	o32	getsockopt			sys_getsockopt			compat_sys_getsockopt
+173	o32	getsockopt			sys_getsockopt			sys_getsockopt
 174	o32	listen				sys_listen
 175	o32	recv				sys_recv			compat_sys_recv
 176	o32	recvfrom			sys_recvfrom			compat_sys_recvfrom
@@ -192,7 +192,7 @@
 178	o32	send				sys_send
 179	o32	sendmsg				sys_sendmsg			compat_sys_sendmsg
 180	o32	sendto				sys_sendto
-181	o32	setsockopt			sys_setsockopt			compat_sys_setsockopt
+181	o32	setsockopt			sys_setsockopt			sys_setsockopt
 182	o32	shutdown			sys_shutdown
 183	o32	socket				sys_socket
 184	o32	socketpair			sys_socketpair
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 5a758fa6ec52..3494e4fa1a17 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -198,8 +198,8 @@
 178	common	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
 179	common	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
 180	common	chown			sys_chown
-181	common	setsockopt		sys_setsockopt			compat_sys_setsockopt
-182	common	getsockopt		sys_getsockopt			compat_sys_getsockopt
+181	common	setsockopt		sys_setsockopt			sys_setsockopt
+182	common	getsockopt		sys_getsockopt			sys_getsockopt
 183	common	sendmsg			sys_sendmsg			compat_sys_sendmsg
 184	common	recvmsg			sys_recvmsg			compat_sys_recvmsg
 185	common	semop			sys_semop
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index f833a3190822..94eb5b27ef65 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -433,8 +433,8 @@
 336	common	recv				sys_recv			compat_sys_recv
 337	common	recvfrom			sys_recvfrom			compat_sys_recvfrom
 338	common	shutdown			sys_shutdown
-339	common	setsockopt			sys_setsockopt			compat_sys_setsockopt
-340	common	getsockopt			sys_getsockopt			compat_sys_getsockopt
+339	common	setsockopt			sys_setsockopt			sys_setsockopt
+340	common	getsockopt			sys_getsockopt			sys_getsockopt
 341	common	sendmsg				sys_sendmsg			compat_sys_sendmsg
 342	common	recvmsg				sys_recvmsg			compat_sys_recvmsg
 343	32	recvmmsg			sys_recvmmsg_time32		compat_sys_recvmmsg_time32
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index bfdcb7633957..0d63c71fc544 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -372,8 +372,8 @@
 362  common	connect			sys_connect			sys_connect
 363  common	listen			sys_listen			sys_listen
 364  common	accept4			sys_accept4			sys_accept4
-365  common	getsockopt		sys_getsockopt			compat_sys_getsockopt
-366  common	setsockopt		sys_setsockopt			compat_sys_setsockopt
+365  common	getsockopt		sys_getsockopt			sys_getsockopt
+366  common	setsockopt		sys_setsockopt			sys_setsockopt
 367  common	getsockname		sys_getsockname			sys_getsockname
 368  common	getpeername		sys_getpeername			sys_getpeername
 369  common	sendto			sys_sendto			sys_sendto
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index 489ffab918a8..a45f0f31fe51 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -157,22 +157,22 @@ do_sys_shutdown: /* sys_shutdown(int, int) */
 	nop
 	nop
 	nop
-do_sys_setsockopt: /* compat_sys_setsockopt(int, int, int, char *, int) */
+do_sys_setsockopt: /* sys_setsockopt(int, int, int, char *, int) */
 47:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(compat_sys_setsockopt), %g1
+	sethi		%hi(sys_setsockopt), %g1
 48:	ldswa		[%o1 + 0x8] %asi, %o2
 49:	lduwa		[%o1 + 0xc] %asi, %o3
 50:	ldswa		[%o1 + 0x10] %asi, %o4
-	jmpl		%g1 + %lo(compat_sys_setsockopt), %g0
+	jmpl		%g1 + %lo(sys_setsockopt), %g0
 51:	 ldswa		[%o1 + 0x4] %asi, %o1
 	nop
-do_sys_getsockopt: /* compat_sys_getsockopt(int, int, int, u32, u32) */
+do_sys_getsockopt: /* sys_getsockopt(int, int, int, u32, u32) */
 52:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(compat_sys_getsockopt), %g1
+	sethi		%hi(sys_getsockopt), %g1
 53:	ldswa		[%o1 + 0x8] %asi, %o2
 54:	lduwa		[%o1 + 0xc] %asi, %o3
 55:	lduwa		[%o1 + 0x10] %asi, %o4
-	jmpl		%g1 + %lo(compat_sys_getsockopt), %g0
+	jmpl		%g1 + %lo(sys_getsockopt), %g0
 56:	 ldswa		[%o1 + 0x4] %asi, %o1
 	nop
 do_sys_sendmsg: /* compat_sys_sendmsg(int, struct compat_msghdr *, unsigned int) */
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 8004a276cb74..c59b37965add 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -147,7 +147,7 @@
 115	32	getgroups32		sys_getgroups
 116	common	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
 117	common	getrusage		sys_getrusage			compat_sys_getrusage
-118	common	getsockopt		sys_getsockopt			compat_sys_getsockopt
+118	common	getsockopt		sys_getsockopt			sys_getsockopt
 119	common	getcwd			sys_getcwd
 120	common	readv			sys_readv			compat_sys_readv
 121	common	writev			sys_writev			compat_sys_writev
@@ -425,7 +425,7 @@
 352	common	userfaultfd		sys_userfaultfd
 353	common	bind			sys_bind
 354	common	listen			sys_listen
-355	common	setsockopt		sys_setsockopt			compat_sys_setsockopt
+355	common	setsockopt		sys_setsockopt			sys_setsockopt
 356	common	mlock2			sys_mlock2
 357	common	copy_file_range		sys_copy_file_range
 358	common	preadv2			sys_preadv2			compat_sys_preadv2
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 3d8d70d3896c..1583831f61a9 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -8,6 +8,13 @@
 #include <asm/unistd.h>
 #include <asm/syscall.h>
 
+/*
+ * Reuse the 64-bit entry points for the x32 versions that occupy different
+ * slots in the syscall table.
+ */
+#define __x32_sys_getsockopt	__x64_sys_getsockopt
+#define __x32_sys_setsockopt	__x64_sys_setsockopt
+
 #define __SYSCALL_64(nr, sym)
 
 #define __SYSCALL_X32(nr, sym) extern long __x32_##sym(const struct pt_regs *);
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d8f8a1a69ed1..43742a69dba1 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -376,8 +376,8 @@
 362	i386	connect			sys_connect
 363	i386	listen			sys_listen
 364	i386	accept4			sys_accept4
-365	i386	getsockopt		sys_getsockopt			compat_sys_getsockopt
-366	i386	setsockopt		sys_setsockopt			compat_sys_setsockopt
+365	i386	getsockopt		sys_getsockopt			sys_getsockopt
+366	i386	setsockopt		sys_setsockopt			sys_setsockopt
 367	i386	getsockname		sys_getsockname
 368	i386	getpeername		sys_getpeername
 369	i386	sendto			sys_sendto
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 78847b32e137..e008d638e641 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -396,8 +396,8 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
-541	x32	setsockopt		compat_sys_setsockopt
-542	x32	getsockopt		compat_sys_getsockopt
+541	x32	setsockopt		sys_setsockopt
+542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
 545	x32	execveat		compat_sys_execveat
diff --git a/include/linux/compat.h b/include/linux/compat.h
index e90100c0de72..c4255d8a4a8a 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -737,10 +737,6 @@ asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg);
 asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len,
 			    unsigned flags, struct sockaddr __user *addr,
 			    int __user *addrlen);
-asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
-				      char __user *optval, unsigned int optlen);
-asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
-				      char __user *optval, int __user *optlen);
 asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned flags);
 asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b951a87da987..aa46825c6f9d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1424,4 +1424,8 @@ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
 			    unsigned int nsops,
 			    const struct old_timespec32 __user *timeout);
 
+int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
+		int __user *optlen);
+int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
+		int optlen);
 #endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f4a01305d9a6..c8c189a5f0a6 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -606,9 +606,9 @@ __SYSCALL(__NR_sendto, sys_sendto)
 #define __NR_recvfrom 207
 __SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
 #define __NR_setsockopt 208
-__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt)
 #define __NR_getsockopt 209
-__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt)
 #define __NR_shutdown 210
 __SYSCALL(__NR_shutdown, sys_shutdown)
 #define __NR_sendmsg 211
diff --git a/net/compat.c b/net/compat.c
index 3e6c2c5ff260..091875bd6210 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -335,77 +335,6 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 	__scm_destroy(scm);
 }
 
-static int __compat_sys_setsockopt(int fd, int level, int optname,
-				   char __user *optval, unsigned int optlen)
-{
-	int err;
-	struct socket *sock;
-
-	if (optlen > INT_MAX)
-		return -EINVAL;
-
-	sock = sockfd_lookup(fd, &err);
-	if (sock) {
-		err = security_socket_setsockopt(sock, level, optname);
-		if (err) {
-			sockfd_put(sock);
-			return err;
-		}
-
-		if (level == SOL_SOCKET)
-			err = sock_setsockopt(sock, level,
-					optname, optval, optlen);
-		else if (sock->ops->compat_setsockopt)
-			err = sock->ops->compat_setsockopt(sock, level,
-					optname, optval, optlen);
-		else
-			err = sock->ops->setsockopt(sock, level,
-					optname, optval, optlen);
-		sockfd_put(sock);
-	}
-	return err;
-}
-
-COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
-		       char __user *, optval, unsigned int, optlen)
-{
-	return __compat_sys_setsockopt(fd, level, optname, optval, optlen);
-}
-
-static int __compat_sys_getsockopt(int fd, int level, int optname,
-				   char __user *optval,
-				   int __user *optlen)
-{
-	int err;
-	struct socket *sock = sockfd_lookup(fd, &err);
-
-	if (sock) {
-		err = security_socket_getsockopt(sock, level, optname);
-		if (err) {
-			sockfd_put(sock);
-			return err;
-		}
-
-		if (level == SOL_SOCKET)
-			err = sock_getsockopt(sock, level,
-					optname, optval, optlen);
-		else if (sock->ops->compat_getsockopt)
-			err = sock->ops->compat_getsockopt(sock, level,
-					optname, optval, optlen);
-		else
-			err = sock->ops->getsockopt(sock, level,
-					optname, optval, optlen);
-		sockfd_put(sock);
-	}
-	return err;
-}
-
-COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
-		       char __user *, optval, int __user *, optlen)
-{
-	return __compat_sys_getsockopt(fd, level, optname, optval, optlen);
-}
-
 /* Argument list sizes for compat_sys_socketcall */
 #define AL(x) ((x) * sizeof(u32))
 static unsigned char nas[21] = {
@@ -565,13 +494,11 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
 		ret = __sys_shutdown(a0, a1);
 		break;
 	case SYS_SETSOCKOPT:
-		ret = __compat_sys_setsockopt(a0, a1, a[2],
-					      compat_ptr(a[3]), a[4]);
+		ret = __sys_setsockopt(a0, a1, a[2], compat_ptr(a[3]), a[4]);
 		break;
 	case SYS_GETSOCKOPT:
-		ret = __compat_sys_getsockopt(a0, a1, a[2],
-					      compat_ptr(a[3]),
-					      compat_ptr(a[4]));
+		ret = __sys_getsockopt(a0, a1, a[2], compat_ptr(a[3]),
+				       compat_ptr(a[4]));
 		break;
 	case SYS_SENDMSG:
 		ret = __compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
diff --git a/net/socket.c b/net/socket.c
index b79376b17b45..dec345982abb 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2094,9 +2094,8 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
  *	Set a socket option. Because we don't know the option lengths we have
  *	to pass the user mode parameter for the protocols to sort out.
  */
-
-static int __sys_setsockopt(int fd, int level, int optname,
-			    char __user *optval, int optlen)
+int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
+		int optlen)
 {
 	mm_segment_t oldfs = get_fs();
 	char *kernel_optval = NULL;
@@ -2114,8 +2113,10 @@ static int __sys_setsockopt(int fd, int level, int optname,
 	if (err)
 		goto out_put;
 
-	err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
-					     optval, &optlen, &kernel_optval);
+	if (!in_compat_syscall())
+		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
+						     optval, &optlen,
+						     &kernel_optval);
 	if (err < 0)
 		goto out_put;
 	if (err > 0) {
@@ -2154,9 +2155,8 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
  *	Get a socket option. Because we don't know the option lengths we have
  *	to pass a user mode parameter for the protocols to sort out.
  */
-
-static int __sys_getsockopt(int fd, int level, int optname,
-			    char __user *optval, int __user *optlen)
+int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
+		int __user *optlen)
 {
 	int err, fput_needed;
 	struct socket *sock;
@@ -2170,7 +2170,8 @@ static int __sys_getsockopt(int fd, int level, int optname,
 	if (err)
 		goto out_put;
 
-	max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
+	if (!in_compat_syscall())
+		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
 
 	if (level == SOL_SOCKET)
 		err = sock_getsockopt(sock, level, optname, optval, optlen);
@@ -2178,8 +2179,10 @@ static int __sys_getsockopt(int fd, int level, int optname,
 		err = sock->ops->getsockopt(sock, level, optname, optval,
 					    optlen);
 
-	err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval,
-					     optlen, max_optlen, err);
+	if (!in_compat_syscall())
+		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
+						     optval, optlen, max_optlen,
+						     err);
 out_put:
 	fput_light(sock->file, fput_needed);
 	return err;
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f4a01305d9a6..c8c189a5f0a6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -606,9 +606,9 @@ __SYSCALL(__NR_sendto, sys_sendto)
 #define __NR_recvfrom 207
 __SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
 #define __NR_setsockopt 208
-__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt)
 #define __NR_getsockopt 209
-__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt)
 #define __NR_shutdown 210
 __SYSCALL(__NR_shutdown, sys_shutdown)
 #define __NR_sendmsg 211
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 35b61bfc1b1a..b190f2eb2611 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -427,8 +427,8 @@
 336	common	recv				sys_recv			compat_sys_recv
 337	common	recvfrom			sys_recvfrom			compat_sys_recvfrom
 338	common	shutdown			sys_shutdown
-339	common	setsockopt			sys_setsockopt			compat_sys_setsockopt
-340	common	getsockopt			sys_getsockopt			compat_sys_getsockopt
+339	common	setsockopt			sys_setsockopt			sys_setsockopt
+340	common	getsockopt			sys_getsockopt			sys_getsockopt
 341	common	sendmsg				sys_sendmsg			compat_sys_sendmsg
 342	common	recvmsg				sys_recvmsg			compat_sys_recvmsg
 343	32	recvmmsg			sys_recvmmsg_time32		compat_sys_recvmmsg_time32
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index b38d48464368..56ae24b6e4be 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -372,8 +372,8 @@
 362  common	connect			sys_connect			compat_sys_connect
 363  common	listen			sys_listen			sys_listen
 364  common	accept4			sys_accept4			compat_sys_accept4
-365  common	getsockopt		sys_getsockopt			compat_sys_getsockopt
-366  common	setsockopt		sys_setsockopt			compat_sys_setsockopt
+365  common	getsockopt		sys_getsockopt			sys_getsockopt
+366  common	setsockopt		sys_setsockopt			sys_setsockopt
 367  common	getsockname		sys_getsockname			compat_sys_getsockname
 368  common	getpeername		sys_getpeername			compat_sys_getpeername
 369  common	sendto			sys_sendto			compat_sys_sendto
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 78847b32e137..e008d638e641 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -396,8 +396,8 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
-541	x32	setsockopt		compat_sys_setsockopt
-542	x32	getsockopt		compat_sys_getsockopt
+541	x32	setsockopt		sys_setsockopt
+542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
 545	x32	execveat		compat_sys_execveat
-- 
cgit v1.2.3


From 77d4df41d53e5c2af14db26f20fe50da52e382ba Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:20 +0200
Subject: netfilter: remove the compat_{get,set} methods

All instances handle compat sockopts via in_compat_syscall() now, so
remove the compat_{get,set} methods as well as the
compat_nf_{get,set}sockopt wrappers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter.h  | 14 --------------
 net/ipv4/ip_sockglue.c     |  5 ++---
 net/ipv6/ipv6_sockglue.c   |  5 ++---
 net/netfilter/nf_sockopt.c | 42 ------------------------------------------
 4 files changed, 4 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index eb312e7ca36e..711b4d4486f0 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -164,17 +164,9 @@ struct nf_sockopt_ops {
 	int set_optmin;
 	int set_optmax;
 	int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len);
-#ifdef CONFIG_COMPAT
-	int (*compat_set)(struct sock *sk, int optval,
-			void __user *user, unsigned int len);
-#endif
 	int get_optmin;
 	int get_optmax;
 	int (*get)(struct sock *sk, int optval, void __user *user, int *len);
-#ifdef CONFIG_COMPAT
-	int (*compat_get)(struct sock *sk, int optval,
-			void __user *user, int *len);
-#endif
 	/* Use the module struct to lock set/get code in place */
 	struct module *owner;
 };
@@ -350,12 +342,6 @@ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
 		  unsigned int len);
 int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
 		  int *len);
-#ifdef CONFIG_COMPAT
-int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval,
-		char __user *opt, unsigned int len);
-int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval,
-		char __user *opt, int *len);
-#endif
 
 struct flowi;
 struct nf_queue_entry;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 84ec3703c909..95f4248c6fc5 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1446,8 +1446,7 @@ mc_msf_out:
 			optname != IP_IPSEC_POLICY &&
 			optname != IP_XFRM_POLICY &&
 			!ip_mroute_opt(optname))
-		err = compat_nf_setsockopt(sk, PF_INET, optname, optval,
-					   optlen);
+		err = nf_setsockopt(sk, PF_INET, optname, optval, optlen);
 #endif
 	return err;
 }
@@ -1821,7 +1820,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
+		err = nf_getsockopt(sk, PF_INET, optname, optval, &len);
 		if (err >= 0)
 			err = put_user(len, optlen);
 		return err;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 6ab44ec2c369..6adfbdcb7979 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1030,8 +1030,7 @@ mc_msf_out:
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY &&
 	    optname != IPV6_XFRM_POLICY)
-		err = compat_nf_setsockopt(sk, PF_INET6, optname, optval,
-					   optlen);
+		err = nf_setsockopt(sk, PF_INET6, optname, optval, optlen);
 #endif
 	return err;
 }
@@ -1531,7 +1530,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len);
+		err = nf_getsockopt(sk, PF_INET6, optname, optval, &len);
 		if (err >= 0)
 			err = put_user(len, optlen);
 	}
diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c
index 46cb3786e0ec..02870993d335 100644
--- a/net/netfilter/nf_sockopt.c
+++ b/net/netfilter/nf_sockopt.c
@@ -122,45 +122,3 @@ int nf_getsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt,
 	return nf_sockopt(sk, pf, val, opt, len, 1);
 }
 EXPORT_SYMBOL(nf_getsockopt);
-
-#ifdef CONFIG_COMPAT
-static int compat_nf_sockopt(struct sock *sk, u_int8_t pf, int val,
-			     char __user *opt, int *len, int get)
-{
-	struct nf_sockopt_ops *ops;
-	int ret;
-
-	ops = nf_sockopt_find(sk, pf, val, get);
-	if (IS_ERR(ops))
-		return PTR_ERR(ops);
-
-	if (get) {
-		if (ops->compat_get)
-			ret = ops->compat_get(sk, val, opt, len);
-		else
-			ret = ops->get(sk, val, opt, len);
-	} else {
-		if (ops->compat_set)
-			ret = ops->compat_set(sk, val, opt, *len);
-		else
-			ret = ops->set(sk, val, opt, *len);
-	}
-
-	module_put(ops->owner);
-	return ret;
-}
-
-int compat_nf_setsockopt(struct sock *sk, u_int8_t pf,
-		int val, char __user *opt, unsigned int len)
-{
-	return compat_nf_sockopt(sk, pf, val, opt, &len, 0);
-}
-EXPORT_SYMBOL(compat_nf_setsockopt);
-
-int compat_nf_getsockopt(struct sock *sk, u_int8_t pf,
-		int val, char __user *opt, int *len)
-{
-	return compat_nf_sockopt(sk, pf, val, opt, len, 1);
-}
-EXPORT_SYMBOL(compat_nf_getsockopt);
-#endif
-- 
cgit v1.2.3


From c34bc10d2535719ddf77d44ee849f6c7589583ba Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 17 Jul 2020 08:23:21 +0200
Subject: netfilter: remove the compat argument to xt_copy_counters_from_user

Lift the in_compat_syscall() from the callers instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter/x_tables.h | 2 +-
 net/ipv4/netfilter/arp_tables.c    | 3 +--
 net/ipv4/netfilter/ip_tables.c     | 3 +--
 net/ipv6/netfilter/ip6_tables.c    | 3 +--
 net/netfilter/x_tables.c           | 9 ++++-----
 5 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 5da88451853b..b8b943ee7b8b 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -302,7 +302,7 @@ int xt_data_to_user(void __user *dst, const void *src,
 		    int usersize, int size, int aligned_size);
 
 void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
-				 struct xt_counters_info *info, bool compat);
+				 struct xt_counters_info *info);
 struct xt_counters *xt_counters_alloc(unsigned int counters);
 
 struct xt_table *xt_register_table(struct net *net,
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 15807fb4a65f..2c8a4dad39d7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1008,8 +1008,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 	struct arpt_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp,
-					   in_compat_syscall());
+	paddc = xt_copy_counters_from_user(user, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index fbfad38f3979..161901dd1cae 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1163,8 +1163,7 @@ do_add_counters(struct net *net, const void __user *user,
 	struct ipt_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp,
-					   in_compat_syscall());
+	paddc = xt_copy_counters_from_user(user, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 96c48e91e6c7..fd1f8f931231 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1179,8 +1179,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len)
 	struct ip6t_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp,
-					   in_compat_syscall());
+	paddc = xt_copy_counters_from_user(user, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 	t = xt_find_table_lock(net, AF_INET6, tmp.name);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 99a468be4a59..32bab45af7e4 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1033,15 +1033,14 @@ EXPORT_SYMBOL_GPL(xt_check_target);
  * @user: src pointer to userspace memory
  * @len: alleged size of userspace memory
  * @info: where to store the xt_counters_info metadata
- * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel
  *
  * Copies counter meta data from @user and stores it in @info.
  *
  * vmallocs memory to hold the counters, then copies the counter data
  * from @user to the new memory and returns a pointer to it.
  *
- * If @compat is true, @info gets converted automatically to the 64bit
- * representation.
+ * If called from a compat syscall, @info gets converted automatically to the
+ * 64bit representation.
  *
  * The metadata associated with the counters is stored in @info.
  *
@@ -1049,13 +1048,13 @@ EXPORT_SYMBOL_GPL(xt_check_target);
  * If IS_ERR is false, caller has to vfree the pointer.
  */
 void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
-				 struct xt_counters_info *info, bool compat)
+				 struct xt_counters_info *info)
 {
 	void *mem;
 	u64 size;
 
 #ifdef CONFIG_COMPAT
-	if (compat) {
+	if (in_compat_syscall()) {
 		/* structures only differ in size due to alignment */
 		struct compat_xt_counters_info compat_tmp;
 
-- 
cgit v1.2.3


From eba75c587e811d3249c8bd50d22bb2266ccd3c0f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 10 Jul 2020 09:29:02 -0400
Subject: icmp: support rfc 4884

Add setsockopt SOL_IP/IP_RECVERR_4884 to return the offset to an
extension struct if present.

ICMP messages may include an extension structure after the original
datagram. RFC 4884 standardized this behavior. It stores the offset
in words to the extension header in u8 icmphdr.un.reserved[1].

The field is valid only for ICMP types destination unreachable, time
exceeded and parameter problem, if length is at least 128 bytes and
entire packet does not exceed 576 bytes.

Return the offset to the start of the extension struct when reading an
ICMP error from the error queue, if it matches the above constraints.

Do not return the raw u8 field. Return the offset from the start of
the user buffer, in bytes. The kernel does not return the network and
transport headers, so subtract those.

Also validate the headers. Return the offset regardless of validation,
as an invalid extension must still not be misinterpreted as part of
the original datagram. Note that !invalid does not imply valid. If
the extension version does not match, no validation can take place,
for instance.

For backward compatibility, make this optional, set by setsockopt
SOL_IP/IP_RECVERR_RFC4884. For API example and feature test, see
github.com/wdebruij/kerneltools/blob/master/tests/recv_icmp_v2.c

For forward compatibility, reserve only setsockopt value 1, leaving
other bits for additional icmp extensions.

Changes
  v1->v2:
  - convert word offset to byte offset from start of user buffer
    - return in ee_data as u8 may be insufficient
  - define extension struct and object header structs
  - return len only if constraints met
  - if returning len, also validate

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/icmp.h          |  4 +++
 include/net/inet_sock.h       |  1 +
 include/uapi/linux/errqueue.h | 14 ++++++++-
 include/uapi/linux/icmp.h     | 22 ++++++++++++++
 include/uapi/linux/in.h       |  1 +
 net/ipv4/icmp.c               | 71 +++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/ip_sockglue.c        | 12 ++++++++
 7 files changed, 124 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/icmp.h b/include/linux/icmp.h
index 81ca84ce3119..8fc38a34cb20 100644
--- a/include/linux/icmp.h
+++ b/include/linux/icmp.h
@@ -15,6 +15,7 @@
 
 #include <linux/skbuff.h>
 #include <uapi/linux/icmp.h>
+#include <uapi/linux/errqueue.h>
 
 static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb)
 {
@@ -35,4 +36,7 @@ static inline bool icmp_is_err(int type)
 	return false;
 }
 
+void ip_icmp_error_rfc4884(const struct sk_buff *skb,
+			   struct sock_ee_data_rfc4884 *out);
+
 #endif	/* _LINUX_ICMP_H */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a7ce00af6c44..a3702d1d4875 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -225,6 +225,7 @@ struct inet_sock {
 				mc_all:1,
 				nodefrag:1;
 	__u8			bind_address_no_port:1,
+				recverr_rfc4884:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
 						  * and cookie exists so we defer connect
 						  * until first data frame is written
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index ca5cb3e3c6df..3c70e8ac14b8 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -5,6 +5,13 @@
 #include <linux/types.h>
 #include <linux/time_types.h>
 
+/* RFC 4884: return offset to extension struct + validation */
+struct sock_ee_data_rfc4884 {
+	__u16	len;
+	__u8	flags;
+	__u8	reserved;
+};
+
 struct sock_extended_err {
 	__u32	ee_errno;	
 	__u8	ee_origin;
@@ -12,7 +19,10 @@ struct sock_extended_err {
 	__u8	ee_code;
 	__u8	ee_pad;
 	__u32   ee_info;
-	__u32   ee_data;
+	union	{
+		__u32   ee_data;
+		struct sock_ee_data_rfc4884 ee_rfc4884;
+	};
 };
 
 #define SO_EE_ORIGIN_NONE	0
@@ -31,6 +41,8 @@ struct sock_extended_err {
 #define SO_EE_CODE_TXTIME_INVALID_PARAM	1
 #define SO_EE_CODE_TXTIME_MISSED	2
 
+#define SO_EE_RFC4884_FLAG_INVALID	1
+
 /**
  *	struct scm_timestamping - timestamps exposed through cmsg
  *
diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h
index 5589eeb791ca..fb169a50895e 100644
--- a/include/uapi/linux/icmp.h
+++ b/include/uapi/linux/icmp.h
@@ -19,6 +19,7 @@
 #define _UAPI_LINUX_ICMP_H
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 #define ICMP_ECHOREPLY		0	/* Echo Reply			*/
 #define ICMP_DEST_UNREACH	3	/* Destination Unreachable	*/
@@ -95,5 +96,26 @@ struct icmp_filter {
 	__u32		data;
 };
 
+/* RFC 4884 extension struct: one per message */
+struct icmp_ext_hdr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u8		reserved1:4,
+			version:4;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	__u8		version:4,
+			reserved1:4;
+#else
+#error	"Please fix <asm/byteorder.h>"
+#endif
+	__u8		reserved2;
+	__sum16		checksum;
+};
+
+/* RFC 4884 extension object header: one for each object */
+struct icmp_extobj_hdr {
+	__be16		length;
+	__u8		class_num;
+	__u8		class_type;
+};
 
 #endif /* _UAPI_LINUX_ICMP_H */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 8533bf07450f..3d0d8231dc19 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -123,6 +123,7 @@ struct in_addr {
 #define IP_CHECKSUM	23
 #define IP_BIND_ADDRESS_NO_PORT	24
 #define IP_RECVFRAGSIZE	25
+#define IP_RECVERR_RFC4884	26
 
 /* IP_MTU_DISCOVER values */
 #define IP_PMTUDISC_DONT		0	/* Never send DF frames */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e30515f89802..793aebf07c2a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1116,6 +1116,77 @@ error:
 	goto drop;
 }
 
+static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off)
+{
+	struct icmp_extobj_hdr *objh, _objh;
+	struct icmp_ext_hdr *exth, _exth;
+	u16 olen;
+
+	exth = skb_header_pointer(skb, off, sizeof(_exth), &_exth);
+	if (!exth)
+		return false;
+	if (exth->version != 2)
+		return true;
+
+	if (exth->checksum &&
+	    csum_fold(skb_checksum(skb, off, skb->len - off, 0)))
+		return false;
+
+	off += sizeof(_exth);
+	while (off < skb->len) {
+		objh = skb_header_pointer(skb, off, sizeof(_objh), &_objh);
+		if (!objh)
+			return false;
+
+		olen = ntohs(objh->length);
+		if (olen < sizeof(_objh))
+			return false;
+
+		off += olen;
+		if (off > skb->len)
+			return false;
+	}
+
+	return true;
+}
+
+void ip_icmp_error_rfc4884(const struct sk_buff *skb,
+			   struct sock_ee_data_rfc4884 *out)
+{
+	int hlen, off;
+
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		break;
+	default:
+		return;
+	}
+
+	/* outer headers up to inner iph. skb->data is at inner payload */
+	hlen = -skb_transport_offset(skb) - sizeof(struct icmphdr);
+
+	/* per rfc 791: maximum packet length of 576 bytes */
+	if (hlen + skb->len > 576)
+		return;
+
+	/* per rfc 4884: minimal datagram length of 128 bytes */
+	off = icmp_hdr(skb)->un.reserved[1] * sizeof(u32);
+	if (off < 128)
+		return;
+
+	/* kernel has stripped headers: return payload offset in bytes */
+	off -= hlen;
+	if (off + sizeof(struct icmp_ext_hdr) > skb->len)
+		return;
+
+	out->len = off;
+
+	if (!ip_icmp_error_rfc4884_validate(skb, off))
+		out->flags |= SO_EE_RFC4884_FLAG_INVALID;
+}
+
 int icmp_err(struct sk_buff *skb, u32 info)
 {
 	struct iphdr *iph = (struct iphdr *)skb->data;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 86b3b9a7cea3..a5ea02d7a183 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -411,6 +411,9 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 	serr->port = port;
 
 	if (skb_pull(skb, payload - skb->data)) {
+		if (inet_sk(sk)->recverr_rfc4884)
+			ip_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+
 		skb_reset_transport_header(skb);
 		if (sock_queue_err_skb(sk, skb) == 0)
 			return;
@@ -904,6 +907,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_RECVORIGDSTADDR:
 	case IP_CHECKSUM:
 	case IP_RECVFRAGSIZE:
+	case IP_RECVERR_RFC4884:
 		if (optlen >= sizeof(int)) {
 			if (get_user(val, (int __user *) optval))
 				return -EFAULT;
@@ -1063,6 +1067,11 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		if (!val)
 			skb_queue_purge(&sk->sk_error_queue);
 		break;
+	case IP_RECVERR_RFC4884:
+		if (val < 0 || val > 1)
+			goto e_inval;
+		inet->recverr_rfc4884 = !!val;
+		break;
 	case IP_MULTICAST_TTL:
 		if (sk->sk_type == SOCK_STREAM)
 			goto e_inval;
@@ -1611,6 +1620,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVERR:
 		val = inet->recverr;
 		break;
+	case IP_RECVERR_RFC4884:
+		val = inet->recverr_rfc4884;
+		break;
 	case IP_MULTICAST_TTL:
 		val = inet->mc_ttl;
 		break;
-- 
cgit v1.2.3


From c6a8b84da4c28bda61b842a089651c3ec9d89a48 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:36:50 -0700
Subject: modules: linux/moduleparam.h: drop duplicated word in a comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jessica Yu <jeyu@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/moduleparam.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 3ef917ff0964..1ad5aa3b86d9 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -108,7 +108,7 @@ struct kparam_array
  * ".") the kernel commandline parameter.  Note that - is changed to _, so
  * the user can use "foo-bar=1" even for variable "foo_bar".
  *
- * @perm is 0 if the the variable is not to appear in sysfs, or 0444
+ * @perm is 0 if the variable is not to appear in sysfs, or 0444
  * for world-readable, 0644 for root-writable, etc.  Note that if it
  * is writable, you may need to use kernel_param_lock() around
  * accesses (esp. charp, which can be kfreed when it changes).
-- 
cgit v1.2.3


From 1c91b46555aa1dd86331025e62d55d92459e0faf Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:26 +0200
Subject: backlight: backlight: Add backlight_is_blank()

The backlight support has three properties that express the state:
 - power
 - state
 - fb_blank

It is un-documented and easy to get wrong.
Add backlight_is_blank() helper to make it simpler
for drivers to get the check of the state correct.

A lot of drivers also includes checks for fb_blank.
This check is redundant when the state is checked
and thus not needed in this helper function.
But added anyway to avoid introducing subtle bugs
due to the creative use of fb_blank in some drivers.
Introducing this helper will for some drivers results in
added support for fb_blank. This will be a change in
functionality, which will improve the backlight driver.

Rolling out this helper to all relevant backlight drivers
will eliminate almost all accesses to fb_blank.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 56e4580d4f55..56e51ebab740 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -175,6 +175,25 @@ static inline void backlight_put(struct backlight_device *bd)
 		put_device(&bd->dev);
 }
 
+/**
+ * backlight_is_blank - Return true if display is expected to be blank
+ * @bd: the backlight device
+ *
+ * Display is expected to be blank if any of these is true::
+ *
+ *   1) if power in not UNBLANK
+ *   2) if fb_blank is not UNBLANK
+ *   3) if state indicate BLANK or SUSPENDED
+ *
+ * Returns true if display is expected to be blank, false otherwise.
+ */
+static inline bool backlight_is_blank(const struct backlight_device *bd)
+{
+	return bd->props.power != FB_BLANK_UNBLANK ||
+	       bd->props.fb_blank != FB_BLANK_UNBLANK ||
+	       bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK);
+}
+
 extern struct backlight_device *backlight_device_register(const char *name,
 	struct device *dev, void *devdata, const struct backlight_ops *ops,
 	const struct backlight_properties *props);
-- 
cgit v1.2.3


From ca7c20b2132d228ec76df3c96f5d0b5ae3d6f218 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:27 +0200
Subject: backlight: backlight: Improve backlight_ops documentation

Improve the documentation for backlight_ops and adapt it to kernel-doc
style.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 59 ++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 56e51ebab740..4ff60774ae22 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -55,19 +55,66 @@ enum backlight_scale {
 struct backlight_device;
 struct fb_info;
 
+/**
+ * struct backlight_ops - backlight operations
+ *
+ * The backlight operations are specified when the backlight device is registered.
+ */
 struct backlight_ops {
+	/**
+	 * @options: Configure how operations are called from the core.
+	 *
+	 * The options parameter is used to adjust the behaviour of the core.
+	 * Set BL_CORE_SUSPENDRESUME to get the update_status() operation called
+	 * upon suspend and resume.
+	 */
 	unsigned int options;
 
 #define BL_CORE_SUSPENDRESUME	(1 << 0)
 
-	/* Notify the backlight driver some property has changed */
+	/**
+	 * @update_status: Operation called when properties have changed.
+	 *
+	 * Notify the backlight driver some property has changed.
+	 * The update_status operation is protected by the update_lock.
+	 *
+	 * The backlight driver is expected to use backlight_is_blank()
+	 * to check if the display is blanked and set brightness accordingly.
+	 * update_status() is called when any of the properties has changed.
+	 *
+	 * RETURNS:
+	 *
+	 * 0 on success, negative error code if any failure occurred.
+	 */
 	int (*update_status)(struct backlight_device *);
-	/* Return the current backlight brightness (accounting for power,
-	   fb_blank etc.) */
+
+	/**
+	 * @get_brightness: Return the current backlight brightness.
+	 *
+	 * The driver may implement this as a readback from the HW.
+	 * This operation is optional and if not present then the current
+	 * brightness property value is used.
+	 *
+	 * RETURNS:
+	 *
+	 * A brightness value which is 0 or a positive number.
+	 * On failure a negative error code is returned.
+	 */
 	int (*get_brightness)(struct backlight_device *);
-	/* Check if given framebuffer device is the one bound to this backlight;
-	   return 0 if not, !=0 if it is. If NULL, backlight always matches the fb. */
-	int (*check_fb)(struct backlight_device *, struct fb_info *);
+
+	/**
+	 * @check_fb: Check the framebuffer device.
+	 *
+	 * Check if given framebuffer device is the one bound to this backlight.
+	 * This operation is optional and if not implemented it is assumed that the
+	 * fbdev is always the one bound to the backlight.
+	 *
+	 * RETURNS:
+	 *
+	 * If info is NULL or the info matches the fbdev bound to the backlight return true.
+	 * If info does not match the fbdev bound to the backlight return false.
+	 */
+	int (*check_fb)(struct backlight_device *bd, struct fb_info *info);
 };
 
 /* This structure defines all the properties of a backlight */
-- 
cgit v1.2.3


From cabf161335ca9fe695bb87469ed99be881cd08f5 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:28 +0200
Subject: backlight: backlight: Improve backlight_properties documentation

Improve the documentation for backlight_properties and adapt it to
kernel-doc style.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 96 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 85 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 4ff60774ae22..3554aef008ea 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -117,28 +117,102 @@ struct backlight_ops {
 	int (*check_fb)(struct backlight_device *bd, struct fb_info *info);
 };
 
-/* This structure defines all the properties of a backlight */
+/**
+ * struct backlight_properties - backlight properties
+ *
+ * This structure defines all the properties of a backlight.
+ */
 struct backlight_properties {
-	/* Current User requested brightness (0 - max_brightness) */
+	/**
+	 * @brightness: The current brightness requested by the user.
+	 *
+	 * The backlight core makes sure the range is (0 to max_brightness)
+	 * when the brightness is set via the sysfs attribute:
+	 * /sys/class/backlight/<backlight>/brightness.
+	 *
+	 * This value can be set in the backlight_properties passed
+	 * to devm_backlight_device_register() to set a default brightness
+	 * value.
+	 */
 	int brightness;
-	/* Maximal value for brightness (read-only) */
+
+	/**
+	 * @max_brightness: The maximum brightness value.
+	 *
+	 * This value must be set in the backlight_properties passed to
+	 * devm_backlight_device_register() and shall not be modified by the
+	 * driver after registration.
+	 */
 	int max_brightness;
-	/* Current FB Power mode (0: full on, 1..3: power saving
-	   modes; 4: full off), see FB_BLANK_XXX */
+
+	/**
+	 * @power: The current power mode.
+	 *
+	 * User space can configure the power mode using the sysfs
+	 * attribute: /sys/class/backlight/<backlight>/bl_power
+	 * When the power property is updated update_status() is called.
+	 *
+	 * The possible values are: (0: full on, 1 to 3: power saving
+	 * modes; 4: full off), see FB_BLANK_XXX.
+	 *
+	 * When the backlight device is enabled @power is set
+	 * to FB_BLANK_UNBLANK. When the backlight device is disabled
+	 * @power is set to FB_BLANK_POWERDOWN.
+	 */
 	int power;
-	/* FB Blanking active? (values as for power) */
-	/* Due to be removed, please use (state & BL_CORE_FBBLANK) */
+
+	/**
+	 * @fb_blank: The power state from the FBIOBLANK ioctl.
+	 *
+	 * When the FBIOBLANK ioctl is called @fb_blank is set to the
+	 * blank parameter and the update_status() operation is called.
+	 *
+	 * When the backlight device is enabled @fb_blank is set
+	 * to FB_BLANK_UNBLANK. When the backlight device is disabled
+	 * @fb_blank is set to FB_BLANK_POWERDOWN.
+	 *
+	 * Backlight drivers should avoid using this property. It has been
+	 * replaced by state & BL_CORE_FBLANK (although most drivers should
+	 * use backlight_is_blank() as the preferred means to get the blank
+	 * state).
+	 *
+	 * fb_blank is deprecated and will be removed.
+	 */
 	int fb_blank;
-	/* Backlight type */
+
+	/**
+	 * @type: The type of backlight supported.
+	 *
+	 * The backlight type allows userspace to make appropriate
+	 * policy decisions based on the backlight type.
+	 *
+	 * This value must be set in the backlight_properties
+	 * passed to devm_backlight_device_register().
+	 */
 	enum backlight_type type;
-	/* Flags used to signal drivers of state changes */
+
+	/**
+	 * @state: The state of the backlight core.
+	 *
+	 * The state is a bitmask. BL_CORE_FBBLANK is set when the display
+	 * is expected to be blank. BL_CORE_SUSPENDED is set when the
+	 * driver is suspended.
+	 *
+	 * backlight drivers are expected to use backlight_is_blank()
+	 * in their update_status() operation rather than reading the
+	 * state property.
+	 *
+	 * The state is maintained by the core and drivers may not modify it.
+	 */
 	unsigned int state;
-	/* Type of the brightness scale (linear, non-linear, ...) */
-	enum backlight_scale scale;
 
 #define BL_CORE_SUSPENDED	(1 << 0)	/* backlight is suspended */
 #define BL_CORE_FBBLANK		(1 << 1)	/* backlight is under an fb blank event */
 
+	/**
+	 * @scale: The type of the brightness scale.
+	 */
+	enum backlight_scale scale;
 };
 
 struct backlight_device {
-- 
cgit v1.2.3


From 6f10cd124c44eea018672d5852708ca5dca4d06d Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:29 +0200
Subject: backlight: backlight: Improve backlight_device documentation

Improve the documentation for backlight_device and adapt it to
kernel-doc style.

The updated documentation is more strict on how locking is used.
With the update neither update_lock nor ops_lock may be used
outside the backlight core.

This restriction was introduced to keep the locking simple
by keeping it in the core.

It was verified that this documents the current state by renaming
update_lock => bl_update_lock and ops_lock => bl_ops_lock.
The rename did not reveal any uses outside the backlight core.
The rename is NOT part of this patch.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Jingoo Han <jingoohan1@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 72 ++++++++++++++++++++++++++++++++---------------
 1 file changed, 49 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 3554aef008ea..cf9977169fe8 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -14,21 +14,6 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 
-/* Notes on locking:
- *
- * backlight_device->ops_lock is an internal backlight lock protecting the
- * ops pointer and no code outside the core should need to touch it.
- *
- * Access to update_status() is serialised by the update_lock mutex since
- * most drivers seem to need this and historically get it wrong.
- *
- * Most drivers don't need locking on their get_brightness() method.
- * If yours does, you need to implement it in the driver. You can use the
- * update_lock mutex if appropriate.
- *
- * Any other use of the locks below is probably wrong.
- */
-
 enum backlight_update_reason {
 	BACKLIGHT_UPDATE_HOTKEY,
 	BACKLIGHT_UPDATE_SYSFS,
@@ -215,30 +200,71 @@ struct backlight_properties {
 	enum backlight_scale scale;
 };
 
+/**
+ * struct backlight_device - backlight device data
+ *
+ * This structure holds all data required by a backlight device.
+ */
 struct backlight_device {
-	/* Backlight properties */
+	/**
+	 * @props: Backlight properties
+	 */
 	struct backlight_properties props;
 
-	/* Serialise access to update_status method */
+	/**
+	 * @update_lock: The lock used when calling the update_status() operation.
+	 *
+	 * update_lock is an internal backlight lock that serialise access
+	 * to the update_status() operation. The backlight core holds the update_lock
+	 * when calling the update_status() operation. The update_lock shall not
+	 * be used by backlight drivers.
+	 */
 	struct mutex update_lock;
 
-	/* This protects the 'ops' field. If 'ops' is NULL, the driver that
-	   registered this device has been unloaded, and if class_get_devdata()
-	   points to something in the body of that driver, it is also invalid. */
+	/**
+	 * @ops_lock: The lock used around everything related to backlight_ops.
+	 *
+	 * ops_lock is an internal backlight lock that protects the ops pointer
+	 * and is used around all accesses to ops and when the operations are
+	 * invoked. The ops_lock shall not be used by backlight drivers.
+	 */
 	struct mutex ops_lock;
+
+	/**
+	 * @ops: Pointer to the backlight operations.
+	 *
+	 * If ops is NULL, the driver that registered this device has been unloaded,
+	 * and if class_get_devdata() points to something in the body of that driver,
+	 * it is also invalid.
+	 */
 	const struct backlight_ops *ops;
 
-	/* The framebuffer notifier block */
+	/**
+	 * @fb_notif: The framebuffer notifier block
+	 */
 	struct notifier_block fb_notif;
 
-	/* list entry of all registered backlight devices */
+	/**
+	 * @entry: List entry of all registered backlight devices
+	 */
 	struct list_head entry;
 
+	/**
+	 * @dev: Parent device.
+	 */
 	struct device dev;
 
-	/* Multiple framebuffers may share one backlight device */
+	/**
+	 * @fb_bl_on: The state of individual fbdev's.
+	 *
+	 * Multiple fbdev's may share one backlight device. The fb_bl_on
+	 * records the state of the individual fbdev.
+	 */
 	bool fb_bl_on[FB_MAX];
 
+	/**
+	 * @use_count: The number of uses of fb_bl_on.
+	 */
 	int use_count;
 };
 
-- 
cgit v1.2.3


From d160fd4e918da33f5ffbcf005cd95888dbbe4f76 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:30 +0200
Subject: backlight: backlight: Document inline functions in backlight.h

Add documentation for the inline functions in backlight.h

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index cf9977169fe8..99381b5a289d 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -268,6 +268,10 @@ struct backlight_device {
 	int use_count;
 };
 
+/**
+ * backlight_update_status - force an update of the backlight device status
+ * @bd: the backlight device
+ */
 static inline int backlight_update_status(struct backlight_device *bd)
 {
 	int ret = -ENOENT;
@@ -361,6 +365,18 @@ extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned
 
 #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev)
 
+/**
+ * bl_get_data - access devdata
+ * @bl_dev: pointer to backlight device
+ *
+ * When a backlight device is registered the driver has the possibility
+ * to supply a void * devdata. bl_get_data() return a pointer to the
+ * devdata.
+ *
+ * RETURNS:
+ *
+ * pointer to devdata stored while registering the backlight device.
+ */
 static inline void * bl_get_data(struct backlight_device *bl_dev)
 {
 	return dev_get_drvdata(&bl_dev->dev);
-- 
cgit v1.2.3


From 2d15bb47f3331db979bd0a1987812ca1a3ff40c6 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:31 +0200
Subject: backlight: backlight: Document enums in backlight.h

Add kernel-doc documentation for the backlight enums

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 72 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 99381b5a289d..1d56b34ff33c 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -14,26 +14,98 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 
+/**
+ * enum backlight_update_reason - what method was used to update backlight
+ *
+ * A driver indicates the method (reason) used for updating the backlight
+ * when calling backlight_force_update().
+ */
 enum backlight_update_reason {
+	/**
+	 * @BACKLIGHT_UPDATE_HOTKEY: The backlight was updated using a hot-key.
+	 */
 	BACKLIGHT_UPDATE_HOTKEY,
+
+	/**
+	 * @BACKLIGHT_UPDATE_SYSFS: The backlight was updated using sysfs.
+	 */
 	BACKLIGHT_UPDATE_SYSFS,
 };
 
+/**
+ * enum backlight_type - the type of backlight control
+ *
+ * The type of interface used to control the backlight.
+ */
 enum backlight_type {
+	/**
+	 * @BACKLIGHT_RAW:
+	 *
+	 * The backlight is controlled using hardware registers.
+	 */
 	BACKLIGHT_RAW = 1,
+
+	/**
+	 * @BACKLIGHT_PLATFORM:
+	 *
+	 * The backlight is controlled using a platform-specific interface.
+	 */
 	BACKLIGHT_PLATFORM,
+
+	/**
+	 * @BACKLIGHT_FIRMWARE:
+	 *
+	 * The backlight is controlled using a standard firmware interface.
+	 */
 	BACKLIGHT_FIRMWARE,
+
+	/**
+	 * @BACKLIGHT_TYPE_MAX: Number of entries.
+	 */
 	BACKLIGHT_TYPE_MAX,
 };
 
+/**
+ * enum backlight_notification - the type of notification
+ *
+ * The notifications that is used for notification sent to the receiver
+ * that registered notifications using backlight_register_notifier().
+ */
 enum backlight_notification {
+	/**
+	 * @BACKLIGHT_REGISTERED: The backlight device is registered.
+	 */
 	BACKLIGHT_REGISTERED,
+
+	/**
+	 * @BACKLIGHT_UNREGISTERED: The backlight revice is unregistered.
+	 */
 	BACKLIGHT_UNREGISTERED,
 };
 
+/** enum backlight_scale - the type of scale used for brightness values
+ *
+ * The type of scale used for brightness values.
+ */
 enum backlight_scale {
+	/**
+	 * @BACKLIGHT_SCALE_UNKNOWN: The scale is unknown.
+	 */
 	BACKLIGHT_SCALE_UNKNOWN = 0,
+
+	/**
+	 * @BACKLIGHT_SCALE_LINEAR: The scale is linear.
+	 *
+	 * The linear scale will increase brightness the same for each step.
+	 */
 	BACKLIGHT_SCALE_LINEAR,
+
+	/**
+	 * @BACKLIGHT_SCALE_NON_LINEAR: The scale is not linear.
+	 *
+	 * This is often used when the brightness values tries to adjust to
+	 * the relative perception of the eye demanding a non-linear scale.
+	 */
 	BACKLIGHT_SCALE_NON_LINEAR,
 };
 
-- 
cgit v1.2.3


From 7ecdea4a0226f6c5cd0e86859d1b38cf17bc8529 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:32 +0200
Subject: backlight: generic_bl: Remove this driver as it is unused

The backlight_bl driver required initialization using
struct generic_bl_info. As there are no more references
to this struct there is no users left.
So it is safe to delete the driver.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/video/backlight/Kconfig      |   8 ---
 drivers/video/backlight/Makefile     |   1 -
 drivers/video/backlight/generic_bl.c | 110 -----------------------------------
 include/linux/backlight.h            |   9 ---
 4 files changed, 128 deletions(-)
 delete mode 100644 drivers/video/backlight/generic_bl.c

(limited to 'include/linux')

diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 95c546cc8774..87f9fc238d28 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -173,14 +173,6 @@ config BACKLIGHT_EP93XX
 	  To compile this driver as a module, choose M here: the module will
 	  be called ep93xx_bl.
 
-config BACKLIGHT_GENERIC
-	tristate "Generic (aka Sharp Corgi) Backlight Driver"
-	default y
-	help
-	  Say y to enable the generic platform backlight driver previously
-	  known as the Corgi backlight driver. If you have a Sharp Zaurus
-	  SL-C7xx, SL-Cxx00 or SL-6000x say y.
-
 config BACKLIGHT_IPAQ_MICRO
 	tristate "iPAQ microcontroller backlight driver"
 	depends on MFD_IPAQ_MICRO
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index 2072d21b60f7..13463b99f1f9 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -31,7 +31,6 @@ obj-$(CONFIG_BACKLIGHT_CLASS_DEVICE)	+= backlight.o
 obj-$(CONFIG_BACKLIGHT_DA903X)		+= da903x_bl.o
 obj-$(CONFIG_BACKLIGHT_DA9052)		+= da9052_bl.o
 obj-$(CONFIG_BACKLIGHT_EP93XX)		+= ep93xx_bl.o
-obj-$(CONFIG_BACKLIGHT_GENERIC)		+= generic_bl.o
 obj-$(CONFIG_BACKLIGHT_GPIO)		+= gpio_backlight.o
 obj-$(CONFIG_BACKLIGHT_HP680)		+= hp680_bl.o
 obj-$(CONFIG_BACKLIGHT_HP700)		+= jornada720_bl.o
diff --git a/drivers/video/backlight/generic_bl.c b/drivers/video/backlight/generic_bl.c
deleted file mode 100644
index 8fe63dbc8590..000000000000
--- a/drivers/video/backlight/generic_bl.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Generic Backlight Driver
- *
- *  Copyright (c) 2004-2008 Richard Purdie
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mutex.h>
-#include <linux/fb.h>
-#include <linux/backlight.h>
-
-static int genericbl_intensity;
-static struct backlight_device *generic_backlight_device;
-static struct generic_bl_info *bl_machinfo;
-
-static int genericbl_send_intensity(struct backlight_device *bd)
-{
-	int intensity = bd->props.brightness;
-
-	if (bd->props.power != FB_BLANK_UNBLANK)
-		intensity = 0;
-	if (bd->props.state & BL_CORE_FBBLANK)
-		intensity = 0;
-	if (bd->props.state & BL_CORE_SUSPENDED)
-		intensity = 0;
-
-	bl_machinfo->set_bl_intensity(intensity);
-
-	genericbl_intensity = intensity;
-
-	if (bl_machinfo->kick_battery)
-		bl_machinfo->kick_battery();
-
-	return 0;
-}
-
-static int genericbl_get_intensity(struct backlight_device *bd)
-{
-	return genericbl_intensity;
-}
-
-static const struct backlight_ops genericbl_ops = {
-	.options = BL_CORE_SUSPENDRESUME,
-	.get_brightness = genericbl_get_intensity,
-	.update_status  = genericbl_send_intensity,
-};
-
-static int genericbl_probe(struct platform_device *pdev)
-{
-	struct backlight_properties props;
-	struct generic_bl_info *machinfo = dev_get_platdata(&pdev->dev);
-	const char *name = "generic-bl";
-	struct backlight_device *bd;
-
-	bl_machinfo = machinfo;
-	if (!machinfo->limit_mask)
-		machinfo->limit_mask = -1;
-
-	if (machinfo->name)
-		name = machinfo->name;
-
-	memset(&props, 0, sizeof(struct backlight_properties));
-	props.type = BACKLIGHT_RAW;
-	props.max_brightness = machinfo->max_intensity;
-	bd = devm_backlight_device_register(&pdev->dev, name, &pdev->dev,
-					NULL, &genericbl_ops, &props);
-	if (IS_ERR(bd))
-		return PTR_ERR(bd);
-
-	platform_set_drvdata(pdev, bd);
-
-	bd->props.power = FB_BLANK_UNBLANK;
-	bd->props.brightness = machinfo->default_intensity;
-	backlight_update_status(bd);
-
-	generic_backlight_device = bd;
-
-	dev_info(&pdev->dev, "Generic Backlight Driver Initialized.\n");
-	return 0;
-}
-
-static int genericbl_remove(struct platform_device *pdev)
-{
-	struct backlight_device *bd = platform_get_drvdata(pdev);
-
-	bd->props.power = 0;
-	bd->props.brightness = 0;
-	backlight_update_status(bd);
-
-	dev_info(&pdev->dev, "Generic Backlight Driver Unloaded\n");
-	return 0;
-}
-
-static struct platform_driver genericbl_driver = {
-	.probe		= genericbl_probe,
-	.remove		= genericbl_remove,
-	.driver		= {
-		.name	= "generic-bl",
-	},
-};
-
-module_platform_driver(genericbl_driver);
-
-MODULE_AUTHOR("Richard Purdie <rpurdie@rpsys.net>");
-MODULE_DESCRIPTION("Generic Backlight Driver");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 1d56b34ff33c..d0f01dc3b98d 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -454,15 +454,6 @@ static inline void * bl_get_data(struct backlight_device *bl_dev)
 	return dev_get_drvdata(&bl_dev->dev);
 }
 
-struct generic_bl_info {
-	const char *name;
-	int max_intensity;
-	int default_intensity;
-	int limit_mask;
-	void (*set_bl_intensity)(int intensity);
-	void (*kick_battery)(void);
-};
-
 #ifdef CONFIG_OF
 struct backlight_device *of_find_backlight_by_node(struct device_node *node);
 #else
-- 
cgit v1.2.3


From 9c4aa3118bab6f10904b7bc9bc34b501a083751b Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:33 +0200
Subject: backlight: backlight: Drop extern from prototypes

No need to put "extern" in front of prototypes. While touching the
prototypes adjust indent to follow the kernel style.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index d0f01dc3b98d..c1824426fc9e 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -417,23 +417,26 @@ static inline bool backlight_is_blank(const struct backlight_device *bd)
 	       bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK);
 }
 
-extern struct backlight_device *backlight_device_register(const char *name,
-	struct device *dev, void *devdata, const struct backlight_ops *ops,
-	const struct backlight_properties *props);
-extern struct backlight_device *devm_backlight_device_register(
-	struct device *dev, const char *name, struct device *parent,
-	void *devdata, const struct backlight_ops *ops,
-	const struct backlight_properties *props);
-extern void backlight_device_unregister(struct backlight_device *bd);
-extern void devm_backlight_device_unregister(struct device *dev,
-					struct backlight_device *bd);
-extern void backlight_force_update(struct backlight_device *bd,
-				   enum backlight_update_reason reason);
-extern int backlight_register_notifier(struct notifier_block *nb);
-extern int backlight_unregister_notifier(struct notifier_block *nb);
-extern struct backlight_device *backlight_device_get_by_type(enum backlight_type type);
+struct backlight_device *
+backlight_device_register(const char *name, struct device *dev, void *devdata,
+			  const struct backlight_ops *ops,
+			  const struct backlight_properties *props);
+struct backlight_device *
+devm_backlight_device_register(struct device *dev, const char *name,
+			       struct device *parent, void *devdata,
+			       const struct backlight_ops *ops,
+			       const struct backlight_properties *props);
+void backlight_device_unregister(struct backlight_device *bd);
+void devm_backlight_device_unregister(struct device *dev,
+				      struct backlight_device *bd);
+void backlight_force_update(struct backlight_device *bd,
+			    enum backlight_update_reason reason);
+int backlight_register_notifier(struct notifier_block *nb);
+int backlight_unregister_notifier(struct notifier_block *nb);
 struct backlight_device *backlight_device_get_by_name(const char *name);
-extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned long brightness);
+struct backlight_device *backlight_device_get_by_type(enum backlight_type type);
+int backlight_device_set_brightness(struct backlight_device *bd,
+				    unsigned long brightness);
 
 #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev)
 
-- 
cgit v1.2.3


From 2144d00ed0db28c764513080f95e4c49ea9133b0 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:36 +0200
Subject: backlight: backlight: Introduce backlight_get_brightness()

Based on an idea from Emil Velikov, add a helper that checks
backlight_is_blank() and return 0 as brightness if display is blank or
the property value if not.

This allows us to simplify the update_status() implementation
in most of the backlight drivers.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/backlight.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index c1824426fc9e..26e89a8033f5 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -417,6 +417,25 @@ static inline bool backlight_is_blank(const struct backlight_device *bd)
 	       bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK);
 }
 
+/**
+ * backlight_get_brightness - Returns the current brightness value
+ * @bd: the backlight device
+ *
+ * Returns the current brightness value, taking in consideration the current
+ * state. If backlight_is_blank() returns true then return 0 as brightness
+ * otherwise return the current brightness property value.
+ *
+ * Backlight drivers are expected to use this function in their update_status()
+ * operation to get the brightness value.
+ */
+static inline int backlight_get_brightness(const struct backlight_device *bd)
+{
+	if (backlight_is_blank(bd))
+		return 0;
+	else
+		return bd->props.brightness;
+}
+
 struct backlight_device *
 backlight_device_register(const char *name, struct device *dev, void *devdata,
 			  const struct backlight_ops *ops,
-- 
cgit v1.2.3


From 0f6a3256fd810eeca9c56cccafee46359d995138 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:42 +0200
Subject: backlight: backlight: Drop backlight_put()

There are no external users of backlight_put(). Drop it and open code
the two users in backlight.c.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/video/backlight/backlight.c |  7 +++++--
 include/linux/backlight.h           | 10 ----------
 2 files changed, 5 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index 82dc93ca859a..cba8505fef5a 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -718,7 +718,10 @@ EXPORT_SYMBOL(of_find_backlight);
 
 static void devm_backlight_release(void *data)
 {
-	backlight_put(data);
+	struct backlight_device *bd = data;
+
+	if (bd)
+		put_device(&bd->dev);
 }
 
 /**
@@ -746,7 +749,7 @@ struct backlight_device *devm_of_find_backlight(struct device *dev)
 		return bd;
 	ret = devm_add_action(dev, devm_backlight_release, bd);
 	if (ret) {
-		backlight_put(bd);
+		put_device(&bd->dev);
 		return ERR_PTR(ret);
 	}
 	return bd;
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 26e89a8033f5..64f91324c911 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -388,16 +388,6 @@ static inline int backlight_disable(struct backlight_device *bd)
 	return backlight_update_status(bd);
 }
 
-/**
- * backlight_put - Drop backlight reference
- * @bd: the backlight device to put
- */
-static inline void backlight_put(struct backlight_device *bd)
-{
-	if (bd)
-		put_device(&bd->dev);
-}
-
 /**
  * backlight_is_blank - Return true if display is expected to be blank
  * @bd: the backlight device
-- 
cgit v1.2.3


From b6539a11e807c531e51ff7ad9a25c3a1b6ff7340 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 19 Jul 2020 10:07:43 +0200
Subject: backlight: backlight: Make of_find_backlight static

There are no external users of of_find_backlight, as they have all
changed to use the managed version. Make of_find_backlight static to
prevent new external users.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/video/backlight/backlight.c | 18 +-----------------
 include/linux/backlight.h           |  6 ------
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index cba8505fef5a..537fe1b376ad 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -673,22 +673,7 @@ struct backlight_device *of_find_backlight_by_node(struct device_node *node)
 EXPORT_SYMBOL(of_find_backlight_by_node);
 #endif
 
-/**
- * of_find_backlight - Get backlight device
- * @dev: Device
- *
- * This function looks for a property named 'backlight' on the DT node
- * connected to @dev and looks up the backlight device.
- *
- * Call backlight_put() to drop the reference on the backlight device.
- *
- * Returns:
- * A pointer to the backlight device if found.
- * Error pointer -EPROBE_DEFER if the DT property is set, but no backlight
- * device is found.
- * NULL if there's no backlight property.
- */
-struct backlight_device *of_find_backlight(struct device *dev)
+static struct backlight_device *of_find_backlight(struct device *dev)
 {
 	struct backlight_device *bd = NULL;
 	struct device_node *np;
@@ -714,7 +699,6 @@ struct backlight_device *of_find_backlight(struct device *dev)
 
 	return bd;
 }
-EXPORT_SYMBOL(of_find_backlight);
 
 static void devm_backlight_release(void *data)
 {
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 64f91324c911..614653e07e3a 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -477,14 +477,8 @@ of_find_backlight_by_node(struct device_node *node)
 #endif
 
 #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
-struct backlight_device *of_find_backlight(struct device *dev);
 struct backlight_device *devm_of_find_backlight(struct device *dev);
 #else
-static inline struct backlight_device *of_find_backlight(struct device *dev)
-{
-	return NULL;
-}
-
 static inline struct backlight_device *
 devm_of_find_backlight(struct device *dev)
 {
-- 
cgit v1.2.3


From 1b86abc1c645ad5c9c7bf70910cb3ce73939d2d7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 16 Jul 2020 13:11:24 +0800
Subject: sched_clock: Expose struct clock_read_data

In order to support perf_event_mmap_page::cap_time features, an
architecture needs, aside from a userspace readable counter register,
to expose the exact clock data so that userspace can convert the
counter register into a correct timestamp.

Provide struct clock_read_data and two (seqcount) helpers so that
architectures (arm64 in specific) can expose the numbers to userspace.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Link: https://lore.kernel.org/r/20200716051130.4359-2-leo.yan@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/sched_clock.h | 28 ++++++++++++++++++++++++++++
 kernel/time/sched_clock.c   | 41 +++++++++++++----------------------------
 2 files changed, 41 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 0bb04a96a6d4..528718e4ed52 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -6,6 +6,34 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
+	u64 epoch_ns;
+	u64 epoch_cyc;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
+	u32 mult;
+	u32 shift;
+};
+
+extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq);
+extern int sched_clock_read_retry(unsigned int seq);
+
 extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index fa3f800d7d76..0acaadc3156c 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -19,31 +19,6 @@
 
 #include "timekeeping.h"
 
-/**
- * struct clock_read_data - data required to read from sched_clock()
- *
- * @epoch_ns:		sched_clock() value at last update
- * @epoch_cyc:		Clock cycle value at last update.
- * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
- *			clocks.
- * @read_sched_clock:	Current clock source (or dummy source when suspended).
- * @mult:		Multipler for scaled math conversion.
- * @shift:		Shift value for scaled math conversion.
- *
- * Care must be taken when updating this structure; it is read by
- * some very hot code paths. It occupies <=40 bytes and, when combined
- * with the seqcount used to synchronize access, comfortably fits into
- * a 64 byte cache line.
- */
-struct clock_read_data {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 sched_clock_mask;
-	u64 (*read_sched_clock)(void);
-	u32 mult;
-	u32 shift;
-};
-
 /**
  * struct clock_data - all data needed for sched_clock() (including
  *                     registration of a new clock source)
@@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
+struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+{
+	*seq = raw_read_seqcount(&cd.seq);
+	return cd.read_data + (*seq & 1);
+}
+
+int sched_clock_read_retry(unsigned int seq)
+{
+	return read_seqcount_retry(&cd.seq, seq);
+}
+
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
@@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void)
 	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount(&cd.seq);
-		rd = cd.read_data + (seq & 1);
+		rd = sched_clock_read_begin(&seq);
 
 		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
 		      rd->sched_clock_mask;
 		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
-	} while (read_seqcount_retry(&cd.seq, seq));
+	} while (sched_clock_read_retry(seq));
 
 	return res;
 }
-- 
cgit v1.2.3


From 3c8387d234f75887a2d78972ab0f764fe9f756e4 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 22 Jun 2020 10:53:55 +0300
Subject: uuid: remove unused uuid_le_to_bin() definition

There is no more user, so remove it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/uuid.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/uuid.h b/include/linux/uuid.h
index d41b0d3e9474..8cdc0d3567cd 100644
--- a/include/linux/uuid.h
+++ b/include/linux/uuid.h
@@ -98,8 +98,6 @@ int guid_parse(const char *uuid, guid_t *u);
 int uuid_parse(const char *uuid, uuid_t *u);
 
 /* backwards compatibility, don't use in new code */
-#define uuid_le_to_bin(guid, u)	guid_parse(guid, u)
-
 static inline int uuid_le_cmp(const guid_t u1, const guid_t u2)
 {
 	return memcmp(&u1, &u2, sizeof(guid_t));
-- 
cgit v1.2.3


From 4834177e633258fbf3c5754b1220f01c705b79eb Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.microsoft.com>
Date: Thu, 9 Jul 2020 01:19:11 -0500
Subject: ima: Support additional conditionals in the KEXEC_CMDLINE hook
 function

Take the properties of the kexec kernel's inode and the current task
ownership into consideration when matching a KEXEC_CMDLINE operation to
the rules in the IMA policy. This allows for some uniformity when
writing IMA policy rules for KEXEC_KERNEL_CHECK, KEXEC_INITRAMFS_CHECK,
and KEXEC_CMDLINE operations.

Prior to this patch, it was not possible to write a set of rules like
this:

 dont_measure func=KEXEC_KERNEL_CHECK obj_type=foo_t
 dont_measure func=KEXEC_INITRAMFS_CHECK obj_type=foo_t
 dont_measure func=KEXEC_CMDLINE obj_type=foo_t
 measure func=KEXEC_KERNEL_CHECK
 measure func=KEXEC_INITRAMFS_CHECK
 measure func=KEXEC_CMDLINE

The inode information associated with the kernel being loaded by a
kexec_kernel_load(2) syscall can now be included in the decision to
measure or not

Additonally, the uid, euid, and subj_* conditionals can also now be
used in KEXEC_CMDLINE rules. There was no technical reason as to why
those conditionals weren't being considered previously other than
ima_match_rules() didn't have a valid inode to use so it immediately
bailed out for KEXEC_CMDLINE operations rather than going through the
full list of conditional comparisons.

Signed-off-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: kexec@lists.infradead.org
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 include/linux/ima.h                          |  4 ++--
 kernel/kexec_file.c                          |  2 +-
 security/integrity/ima/ima.h                 |  2 +-
 security/integrity/ima/ima_api.c             |  2 +-
 security/integrity/ima/ima_appraise.c        |  2 +-
 security/integrity/ima/ima_asymmetric_keys.c |  2 +-
 security/integrity/ima/ima_main.c            | 23 +++++++++++++++++------
 security/integrity/ima/ima_policy.c          | 17 ++++++-----------
 security/integrity/ima/ima_queue_keys.c      |  2 +-
 9 files changed, 31 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ima.h b/include/linux/ima.h
index 9164e1534ec9..d15100de6cdd 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -25,7 +25,7 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
-extern void ima_kexec_cmdline(const void *buf, int size);
+extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
 
 #ifdef CONFIG_IMA_KEXEC
 extern void ima_add_kexec_buffer(struct kimage *image);
@@ -103,7 +103,7 @@ static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size)
 	return -EOPNOTSUPP;
 }
 
-static inline void ima_kexec_cmdline(const void *buf, int size) {}
+static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {}
 #endif /* CONFIG_IMA */
 
 #ifndef CONFIG_IMA_KEXEC
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index bb05fd52de85..07df431c1f21 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -287,7 +287,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 			goto out;
 		}
 
-		ima_kexec_cmdline(image->cmdline_buf,
+		ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
 				  image->cmdline_buf_len - 1);
 	}
 
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index ea7e77536f3c..576ae2c6d418 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -265,7 +265,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
 			   struct evm_ima_xattr_data *xattr_value,
 			   int xattr_len, const struct modsig *modsig, int pcr,
 			   struct ima_template_desc *template_desc);
-void process_buffer_measurement(const void *buf, int size,
+void process_buffer_measurement(struct inode *inode, const void *buf, int size,
 				const char *eventname, enum ima_hooks func,
 				int pcr, const char *keyring);
 void ima_audit_measurement(struct integrity_iint_cache *iint,
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index bf22de8b7ce0..4f39fb93f278 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -162,7 +162,7 @@ err_out:
 
 /**
  * ima_get_action - appraise & measure decision based on policy.
- * @inode: pointer to inode to measure
+ * @inode: pointer to the inode associated with the object being validated
  * @cred: pointer to credentials structure to validate
  * @secid: secid of the task being validated
  * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXEC,
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index a9649b04b9f1..6c52bf7ea7f0 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -328,7 +328,7 @@ int ima_check_blacklist(struct integrity_iint_cache *iint,
 
 		rc = is_binary_blacklisted(digest, digestsize);
 		if ((rc == -EPERM) && (iint->flags & IMA_MEASURE))
-			process_buffer_measurement(digest, digestsize,
+			process_buffer_measurement(NULL, digest, digestsize,
 						   "blacklisted-hash", NONE,
 						   pcr, NULL);
 	}
diff --git a/security/integrity/ima/ima_asymmetric_keys.c b/security/integrity/ima/ima_asymmetric_keys.c
index aaae80c4e376..1c68c500c26f 100644
--- a/security/integrity/ima/ima_asymmetric_keys.c
+++ b/security/integrity/ima/ima_asymmetric_keys.c
@@ -58,7 +58,7 @@ void ima_post_key_create_or_update(struct key *keyring, struct key *key,
 	 * if the IMA policy is configured to measure a key linked
 	 * to the given keyring.
 	 */
-	process_buffer_measurement(payload, payload_len,
+	process_buffer_measurement(NULL, payload, payload_len,
 				   keyring->description, KEY_CHECK, 0,
 				   keyring->description);
 }
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 8351b2fd48e0..8a91711ca79b 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -726,6 +726,7 @@ int ima_load_data(enum kernel_load_data_id id)
 
 /*
  * process_buffer_measurement - Measure the buffer to ima log.
+ * @inode: inode associated with the object being measured (NULL for KEY_CHECK)
  * @buf: pointer to the buffer that needs to be added to the log.
  * @size: size of buffer(in bytes).
  * @eventname: event name to be used for the buffer entry.
@@ -735,7 +736,7 @@ int ima_load_data(enum kernel_load_data_id id)
  *
  * Based on policy, the buffer is measured into the ima log.
  */
-void process_buffer_measurement(const void *buf, int size,
+void process_buffer_measurement(struct inode *inode, const void *buf, int size,
 				const char *eventname, enum ima_hooks func,
 				int pcr, const char *keyring)
 {
@@ -768,7 +769,7 @@ void process_buffer_measurement(const void *buf, int size,
 	 */
 	if (func) {
 		security_task_getsecid(current, &secid);
-		action = ima_get_action(NULL, current_cred(), secid, 0, func,
+		action = ima_get_action(inode, current_cred(), secid, 0, func,
 					&pcr, &template, keyring);
 		if (!(action & IMA_MEASURE))
 			return;
@@ -823,16 +824,26 @@ out:
 
 /**
  * ima_kexec_cmdline - measure kexec cmdline boot args
+ * @kernel_fd: file descriptor of the kexec kernel being loaded
  * @buf: pointer to buffer
  * @size: size of buffer
  *
  * Buffers can only be measured, not appraised.
  */
-void ima_kexec_cmdline(const void *buf, int size)
+void ima_kexec_cmdline(int kernel_fd, const void *buf, int size)
 {
-	if (buf && size != 0)
-		process_buffer_measurement(buf, size, "kexec-cmdline",
-					   KEXEC_CMDLINE, 0, NULL);
+	struct fd f;
+
+	if (!buf || !size)
+		return;
+
+	f = fdget(kernel_fd);
+	if (!f.file)
+		return;
+
+	process_buffer_measurement(file_inode(f.file), buf, size,
+				   "kexec-cmdline", KEXEC_CMDLINE, 0, NULL);
+	fdput(f);
 }
 
 static int __init init_ima(void)
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index dcd1aaac4ff0..9284055ee13a 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -443,13 +443,9 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode,
 {
 	int i;
 
-	if ((func == KEXEC_CMDLINE) || (func == KEY_CHECK)) {
-		if ((rule->flags & IMA_FUNC) && (rule->func == func)) {
-			if (func == KEY_CHECK)
-				return ima_match_keyring(rule, keyring, cred);
-			return true;
-		}
-		return false;
+	if (func == KEY_CHECK) {
+		return (rule->flags & IMA_FUNC) && (rule->func == func) &&
+		       ima_match_keyring(rule, keyring, cred);
 	}
 	if ((rule->flags & IMA_FUNC) &&
 	    (rule->func != func && func != POST_SETATTR))
@@ -1035,10 +1031,9 @@ static bool ima_validate_rule(struct ima_rule_entry *entry)
 		if (entry->action & ~(MEASURE | DONT_MEASURE))
 			return false;
 
-		if (entry->flags & ~(IMA_FUNC | IMA_PCR))
-			return false;
-
-		if (ima_rule_contains_lsm_cond(entry))
+		if (entry->flags & ~(IMA_FUNC | IMA_FSMAGIC | IMA_UID |
+				     IMA_FOWNER | IMA_FSUUID | IMA_EUID |
+				     IMA_PCR | IMA_FSNAME))
 			return false;
 
 		break;
diff --git a/security/integrity/ima/ima_queue_keys.c b/security/integrity/ima/ima_queue_keys.c
index 56ce24a18b66..69a8626a35c0 100644
--- a/security/integrity/ima/ima_queue_keys.c
+++ b/security/integrity/ima/ima_queue_keys.c
@@ -158,7 +158,7 @@ void ima_process_queued_keys(void)
 
 	list_for_each_entry_safe(entry, tmp, &ima_keys, list) {
 		if (!timer_expired)
-			process_buffer_measurement(entry->payload,
+			process_buffer_measurement(NULL, entry->payload,
 						   entry->payload_len,
 						   entry->keyring_name,
 						   KEY_CHECK, 0,
-- 
cgit v1.2.3


From 3093a479727be194996dbc40f803711af5877be4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 20 Jul 2020 08:12:49 +0200
Subject: block: inherit the zoned characteristics in blk_stack_limits

Lift the code from device mapper into blk_stack_limits to inherity
the stacking limitations.  This ensures we do the right thing for
all stacked zoned block devices.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   |  1 +
 drivers/md/dm-table.c  | 19 -------------------
 include/linux/blkdev.h |  9 ++++++---
 3 files changed, 7 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 9a2c23cd9700..9cddbd736474 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -609,6 +609,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		t->chunk_sectors = min_not_zero(t->chunk_sectors,
 						b->chunk_sectors);
 
+	t->zoned = max(t->zoned, b->zoned);
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 0ea5b7367179..ec5364133cef 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -467,9 +467,6 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       q->limits.logical_block_size,
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
-
-	limits->zoned = blk_queue_zoned_model(q);
-
 	return 0;
 }
 
@@ -1528,22 +1525,6 @@ combine_limits:
 			       dm_device_name(table->md),
 			       (unsigned long long) ti->begin,
 			       (unsigned long long) ti->len);
-
-		/*
-		 * FIXME: this should likely be moved to blk_stack_limits(), would
-		 * also eliminate limits->zoned stacking hack in dm_set_device_limits()
-		 */
-		if (limits->zoned == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
-			/*
-			 * By default, the stacked limits zoned model is set to
-			 * BLK_ZONED_NONE in blk_set_stacking_limits(). Update
-			 * this model using the first target model reported
-			 * that is not BLK_ZONED_NONE. This will be either the
-			 * first target device zoned model or the model reported
-			 * by the target .io_hints.
-			 */
-			limits->zoned = ti_limits.zoned;
-		}
 	}
 
 	/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 63078944909c..9e331a1eb35f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -306,11 +306,14 @@ enum blk_queue_state {
 
 /*
  * Zoned block device models (zoned limit).
+ *
+ * Note: This needs to be ordered from the least to the most severe
+ * restrictions for the inheritance in blk_stack_limits() to work.
  */
 enum blk_zoned_model {
-	BLK_ZONED_NONE,	/* Regular block device */
-	BLK_ZONED_HA,	/* Host-aware zoned block device */
-	BLK_ZONED_HM,	/* Host-managed zoned block device */
+	BLK_ZONED_NONE = 0,	/* Regular block device */
+	BLK_ZONED_HA,		/* Host-aware zoned block device */
+	BLK_ZONED_HM,		/* Host-managed zoned block device */
 };
 
 struct queue_limits {
-- 
cgit v1.2.3


From 9efa82ef2b15d1757dd6cc518988a4506554e893 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 20 Jul 2020 08:12:50 +0200
Subject: block: remove bdev_stack_limits

This function is just a tiny wrapper around blk_stack_limit and has
two callers.  Simplify the stack a bit by open coding it in the two
callers.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 25 ++-----------------------
 drivers/md/dm-table.c  |  3 ++-
 include/linux/blkdev.h |  2 --
 3 files changed, 4 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 9cddbd736474..8c63af772685 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -614,28 +614,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
-/**
- * bdev_stack_limits - adjust queue limits for stacked drivers
- * @t:	the stacking driver limits (top device)
- * @bdev:  the component block_device (bottom)
- * @start:  first data sector within component device
- *
- * Description:
- *    Merges queue limits for a top device and a block_device.  Returns
- *    0 if alignment didn't change.  Returns -1 if adding the bottom
- *    device caused misalignment.
- */
-int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
-		      sector_t start)
-{
-	struct request_queue *bq = bdev_get_queue(bdev);
-
-	start += get_start_sect(bdev);
-
-	return blk_stack_limits(t, &bq->limits, start);
-}
-EXPORT_SYMBOL(bdev_stack_limits);
-
 /**
  * disk_stack_limits - adjust queue limits for stacked drivers
  * @disk:  MD/DM gendisk (top)
@@ -651,7 +629,8 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 {
 	struct request_queue *t = disk->queue;
 
-	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
+	if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
+			get_start_sect(bdev) + (offset >> 9)) < 0) {
 		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
 
 		disk_name(disk, 0, top);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ec5364133cef..aac4c31cfc84 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -458,7 +458,8 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		return 0;
 	}
 
-	if (bdev_stack_limits(limits, bdev, start) < 0)
+	if (blk_stack_limits(limits, &q->limits,
+			get_start_sect(bdev) + start) < 0)
 		DMWARN("%s: adding target device %s caused an alignment inconsistency: "
 		       "physical_block_size=%u, logical_block_size=%u, "
 		       "alignment_offset=%u, start=%llu",
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9e331a1eb35f..54b963109e64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1139,8 +1139,6 @@ extern void blk_set_default_limits(struct queue_limits *lim);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
-			    sector_t offset);
 extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
-- 
cgit v1.2.3


From b9b1a5d71533f2ccd54b810dffdcf0789b30ba9b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 20 Jul 2020 08:12:51 +0200
Subject: block: remove blk_queue_stack_limits

This function is just a tiny wrapper around blk_stack_limits.  Open code
it int the two callers.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c         | 11 -----------
 drivers/block/drbd/drbd_nl.c |  4 ++--
 drivers/nvme/host/core.c     |  3 ++-
 include/linux/blkdev.h       |  1 -
 4 files changed, 4 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 8c63af772685..76a7e03bcd6c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -455,17 +455,6 @@ void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
-/**
- * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
- * @t:	the stacking driver (top)
- * @b:  the underlying device (bottom)
- **/
-void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
-{
-	blk_stack_limits(&t->limits, &b->limits, 0);
-}
-EXPORT_SYMBOL(blk_queue_stack_limits);
-
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index da4a3ebe04ef..d0d9a549b583 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1250,7 +1250,7 @@ static void fixup_discard_if_not_supported(struct request_queue *q)
 
 static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
 {
-	/* Fixup max_write_zeroes_sectors after blk_queue_stack_limits():
+	/* Fixup max_write_zeroes_sectors after blk_stack_limits():
 	 * if we can handle "zeroes" efficiently on the protocol,
 	 * we want to do that, even if our backend does not announce
 	 * max_write_zeroes_sectors itself. */
@@ -1361,7 +1361,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 	decide_on_write_same_support(device, q, b, o, disable_write_same);
 
 	if (b) {
-		blk_queue_stack_limits(q, b);
+		blk_stack_limits(&q->limits, &b->limits, 0);
 
 		if (q->backing_dev_info->ra_pages !=
 		    b->backing_dev_info->ra_pages) {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e9d83b98d79d..aa2b66edba5e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2054,7 +2054,8 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
-		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+		blk_stack_limits(&ns->head->disk->queue->limits,
+				 &ns->queue->limits, 0);
 		nvme_mpath_update_disk_size(ns->head->disk);
 	}
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 54b963109e64..bbdd3cf62038 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1141,7 +1141,6 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
 extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
-extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
-- 
cgit v1.2.3


From 6c4411f14d1afa8ead90cd4cf18a308c43ac6908 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:28:30 -0700
Subject: clk: <linux/clk-provider.h>: drop a duplicated word

Drop the repeated word "not" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: linux-clk@vger.kernel.org
Link: https://lore.kernel.org/r/20200719002830.20319-1-rdunlap@infradead.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/clk-provider.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index bd1ee9039558..6f815be99b77 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -189,7 +189,7 @@ struct clk_duty {
  *              and >= numerator) Return 0 on success, otherwise -EERROR.
  *
  * @init:	Perform platform-specific initialization magic.
- *		This is not not used by any of the basic clock types.
+ *		This is not used by any of the basic clock types.
  *		This callback exist for HW which needs to perform some
  *		initialisation magic for CCF to get an accurate view of the
  *		clock. It may also be used dynamic resource allocation is
-- 
cgit v1.2.3


From a8b7b2d0b3fc965d823e362840e5451e2eb4a71b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 20 Jul 2020 10:10:41 +0200
Subject: sched: sch_api: add missing rcu read lock to silence the warning

In case the qdisc_match_from_root function() is called from non-rcu path
with rtnl mutex held, a suspiciout rcu usage warning appears:

[  241.504354] =============================
[  241.504358] WARNING: suspicious RCU usage
[  241.504366] 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 Not tainted
[  241.504370] -----------------------------
[  241.504378] net/sched/sch_api.c:270 RCU-list traversed in non-reader section!!
[  241.504382]
               other info that might help us debug this:
[  241.504388]
               rcu_scheduler_active = 2, debug_locks = 1
[  241.504394] 1 lock held by tc/1391:
[  241.504398]  #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0
[  241.504431]
               stack backtrace:
[  241.504440] CPU: 0 PID: 1391 Comm: tc Not tainted 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32
[  241.504446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
[  241.504453] Call Trace:
[  241.504465]  dump_stack+0x100/0x184
[  241.504482]  lockdep_rcu_suspicious+0x153/0x15d
[  241.504499]  qdisc_match_from_root+0x293/0x350

Fix this by passing the rtnl held lockdep condition down to
hlist_for_each_entry_rcu()

Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/hashtable.h | 4 ++--
 net/sched/sch_api.c       | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h
index 78b6ea5fa8ba..f6c666730b8c 100644
--- a/include/linux/hashtable.h
+++ b/include/linux/hashtable.h
@@ -173,9 +173,9 @@ static inline void hash_del_rcu(struct hlist_node *node)
  * @member: the name of the hlist_node within the struct
  * @key: the key of the objects to iterate over
  */
-#define hash_for_each_possible_rcu(name, obj, member, key)		\
+#define hash_for_each_possible_rcu(name, obj, member, key, cond...)	\
 	hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\
-		member)
+		member, ## cond)
 
 /**
  * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 11ebba60da3b..2a76a2f5ed88 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -267,7 +267,8 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	    root->handle == handle)
 		return root;
 
-	hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle) {
+	hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle,
+				   lockdep_rtnl_is_held()) {
 		if (q->handle == handle)
 			return q;
 	}
-- 
cgit v1.2.3


From e812916d3278baf03aabf10044661fc3b2848823 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:00 +0300
Subject: linkmode: introduce linkmode_intersects()

Add a new helper to find intersections between Ethtool link modes,
linkmode_intersects(), similar to the other linkmode helpers.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/linkmode.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index c664c27a29a0..f8397f300fcd 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -82,6 +82,12 @@ static inline int linkmode_equal(const unsigned long *src1,
 	return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
+static inline int linkmode_intersects(const unsigned long *src1,
+				      const unsigned long *src2)
+{
+	return bitmap_intersects(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
 static inline int linkmode_subset(const unsigned long *src1,
 				  const unsigned long *src2)
 {
-- 
cgit v1.2.3


From bdb5d8ec47611ca61e168349f233e1dd1ed063f4 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:01 +0300
Subject: qed, qede, qedf: convert link mode from u32 to ETHTOOL_LINK_MODE

Currently qed driver already ran out of 32 bits to store link modes,
and this doesn't allow to add and support more speeds.
Convert custom link mode to generic Ethtool bitmap and definitions
(convenient Phylink shorthands are used for elegance and readability).
This allowed us to drop all conversions/mappings between the driver
and Ethtool.

This involves changes in qede and qedf as well, as they used definitions
from shared "qed_if.h".

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c      | 288 +++++++++++++-----------
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 200 +++++-----------
 drivers/scsi/qedf/qedf_main.c                   |  78 ++++---
 include/linux/qed/qed_if.h                      |  47 +---
 4 files changed, 268 insertions(+), 345 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 4c5f5bd91359..afc4fa3bdcaa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -24,6 +24,7 @@
 #include <linux/qed/qed_ll2_if.h>
 #include <net/devlink.h>
 #include <linux/aer.h>
+#include <linux/phylink.h>
 
 #include "qed.h"
 #include "qed_sriov.h"
@@ -1456,10 +1457,11 @@ static bool qed_can_link_change(struct qed_dev *cdev)
 
 static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 {
-	struct qed_hwfn *hwfn;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sup_caps);
 	struct qed_mcp_link_params *link_params;
+	struct qed_hwfn *hwfn;
 	struct qed_ptt *ptt;
-	u32 sup_caps;
+	u32 as;
 	int rc;
 
 	if (!cdev)
@@ -1482,57 +1484,79 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 		return -EBUSY;
 
 	link_params = qed_mcp_get_link_params(hwfn);
+	if (!link_params)
+		return -ENODATA;
+
 	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_AUTONEG)
 		link_params->speed.autoneg = params->autoneg;
+
 	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS) {
-		link_params->speed.advertised_speeds = 0;
-		sup_caps = QED_LM_1000baseT_Full_BIT |
-			   QED_LM_1000baseKX_Full_BIT |
-			   QED_LM_1000baseX_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G;
-		sup_caps = QED_LM_10000baseT_Full_BIT |
-			   QED_LM_10000baseKR_Full_BIT |
-			   QED_LM_10000baseKX4_Full_BIT |
-			   QED_LM_10000baseR_FEC_BIT |
-			   QED_LM_10000baseCR_Full_BIT |
-			   QED_LM_10000baseSR_Full_BIT |
-			   QED_LM_10000baseLR_Full_BIT |
-			   QED_LM_10000baseLRM_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G;
-		if (params->adv_speeds & QED_LM_20000baseKR2_Full_BIT)
-			link_params->speed.advertised_speeds |=
-				NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G;
-		sup_caps = QED_LM_25000baseKR_Full_BIT |
-			   QED_LM_25000baseCR_Full_BIT |
-			   QED_LM_25000baseSR_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G;
-		sup_caps = QED_LM_40000baseLR4_Full_BIT |
-			   QED_LM_40000baseKR4_Full_BIT |
-			   QED_LM_40000baseCR4_Full_BIT |
-			   QED_LM_40000baseSR4_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-				NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G;
-		sup_caps = QED_LM_50000baseKR2_Full_BIT |
-			   QED_LM_50000baseCR2_Full_BIT |
-			   QED_LM_50000baseSR2_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G;
-		sup_caps = QED_LM_100000baseKR4_Full_BIT |
-			   QED_LM_100000baseSR4_Full_BIT |
-			   QED_LM_100000baseCR4_Full_BIT |
-			   QED_LM_100000baseLR4_ER4_Full_BIT;
-		if (params->adv_speeds & sup_caps)
-			link_params->speed.advertised_speeds |=
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G;
+		as = 0;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 1000baseT_Full);
+		phylink_set(sup_caps, 1000baseKX_Full);
+		phylink_set(sup_caps, 1000baseX_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 10000baseT_Full);
+		phylink_set(sup_caps, 10000baseKR_Full);
+		phylink_set(sup_caps, 10000baseKX4_Full);
+		phylink_set(sup_caps, 10000baseR_FEC);
+		phylink_set(sup_caps, 10000baseCR_Full);
+		phylink_set(sup_caps, 10000baseSR_Full);
+		phylink_set(sup_caps, 10000baseLR_Full);
+		phylink_set(sup_caps, 10000baseLRM_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 20000baseKR2_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 25000baseKR_Full);
+		phylink_set(sup_caps, 25000baseCR_Full);
+		phylink_set(sup_caps, 25000baseSR_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 40000baseLR4_Full);
+		phylink_set(sup_caps, 40000baseKR4_Full);
+		phylink_set(sup_caps, 40000baseCR4_Full);
+		phylink_set(sup_caps, 40000baseSR4_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 50000baseKR2_Full);
+		phylink_set(sup_caps, 50000baseCR2_Full);
+		phylink_set(sup_caps, 50000baseSR2_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G;
+
+		phylink_zero(sup_caps);
+		phylink_set(sup_caps, 100000baseKR4_Full);
+		phylink_set(sup_caps, 100000baseSR4_Full);
+		phylink_set(sup_caps, 100000baseCR4_Full);
+		phylink_set(sup_caps, 100000baseLR4_ER4_Full);
+
+		if (linkmode_intersects(params->adv_speeds, sup_caps))
+			as |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G;
+
+		link_params->speed.advertised_speeds = as;
 	}
+
 	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_FORCED_SPEED)
 		link_params->speed.forced_speed = params->forced_speed;
 	if (params->override_flags & QED_LINK_OVERRIDE_PAUSE_CONFIG) {
@@ -1644,7 +1668,7 @@ static int qed_get_link_data(struct qed_hwfn *hwfn,
 
 static void qed_fill_link_capability(struct qed_hwfn *hwfn,
 				     struct qed_ptt *ptt, u32 capability,
-				     u32 *if_capability)
+				     unsigned long *if_caps)
 {
 	u32 media_type, tcvr_state, tcvr_type;
 	u32 speed_mask, board_cfg;
@@ -1667,113 +1691,117 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn,
 
 	switch (media_type) {
 	case MEDIA_DA_TWINAX:
-		*if_capability |= QED_LM_FIBRE_BIT;
+		phylink_set(if_caps, FIBRE);
+
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G)
-			*if_capability |= QED_LM_20000baseKR2_Full_BIT;
+			phylink_set(if_caps, 20000baseKR2_Full);
+
 		/* For DAC media multiple speed capabilities are supported*/
 		capability = capability & speed_mask;
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G)
-			*if_capability |= QED_LM_1000baseKX_Full_BIT;
+			phylink_set(if_caps, 1000baseKX_Full);
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G)
-			*if_capability |= QED_LM_10000baseCR_Full_BIT;
+			phylink_set(if_caps, 10000baseCR_Full);
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G)
-			*if_capability |= QED_LM_40000baseCR4_Full_BIT;
+			phylink_set(if_caps, 40000baseCR4_Full);
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G)
-			*if_capability |= QED_LM_25000baseCR_Full_BIT;
+			phylink_set(if_caps, 25000baseCR_Full);
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G)
-			*if_capability |= QED_LM_50000baseCR2_Full_BIT;
+			phylink_set(if_caps, 50000baseCR2_Full);
 		if (capability &
-			NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G)
-			*if_capability |= QED_LM_100000baseCR4_Full_BIT;
+		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G)
+			phylink_set(if_caps, 100000baseCR4_Full);
+
 		break;
 	case MEDIA_BASE_T:
-		*if_capability |= QED_LM_TP_BIT;
+		phylink_set(if_caps, TP);
+
 		if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) {
 			if (capability &
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) {
-				*if_capability |= QED_LM_1000baseT_Full_BIT;
-			}
+			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G)
+				phylink_set(if_caps, 1000baseT_Full);
 			if (capability &
-			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) {
-				*if_capability |= QED_LM_10000baseT_Full_BIT;
-			}
+			    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G)
+				phylink_set(if_caps, 10000baseT_Full);
 		}
+
 		if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) {
-			*if_capability |= QED_LM_FIBRE_BIT;
+			phylink_set(if_caps, FIBRE);
+
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET)
-				*if_capability |= QED_LM_1000baseT_Full_BIT;
+				phylink_set(if_caps, 1000baseT_Full);
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET)
-				*if_capability |= QED_LM_10000baseT_Full_BIT;
+				phylink_set(if_caps, 10000baseT_Full);
 		}
+
 		break;
 	case MEDIA_SFP_1G_FIBER:
 	case MEDIA_SFPP_10G_FIBER:
 	case MEDIA_XFP_FIBER:
 	case MEDIA_MODULE_FIBER:
-		*if_capability |= QED_LM_FIBRE_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) {
+		phylink_set(if_caps, FIBRE);
+
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) {
 			if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) ||
 			    (tcvr_type == ETH_TRANSCEIVER_TYPE_1G_SX))
-				*if_capability |= QED_LM_1000baseKX_Full_BIT;
+				phylink_set(if_caps, 1000baseKX_Full);
 		}
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) {
+
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) {
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_SR)
-				*if_capability |= QED_LM_10000baseSR_Full_BIT;
+				phylink_set(if_caps, 10000baseSR_Full);
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_LR)
-				*if_capability |= QED_LM_10000baseLR_Full_BIT;
+				phylink_set(if_caps, 10000baseLR_Full);
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_LRM)
-				*if_capability |= QED_LM_10000baseLRM_Full_BIT;
+				phylink_set(if_caps, 10000baseLRM_Full);
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_ER)
-				*if_capability |= QED_LM_10000baseR_FEC_BIT;
+				phylink_set(if_caps, 10000baseR_FEC);
 		}
+
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G)
-			*if_capability |= QED_LM_20000baseKR2_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) {
+			phylink_set(if_caps, 20000baseKR2_Full);
+
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) {
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_25G_SR)
-				*if_capability |= QED_LM_25000baseSR_Full_BIT;
+				phylink_set(if_caps, 25000baseSR_Full);
 		}
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) {
+
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) {
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_40G_LR4)
-				*if_capability |= QED_LM_40000baseLR4_Full_BIT;
+				phylink_set(if_caps, 40000baseLR4_Full);
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_40G_SR4)
-				*if_capability |= QED_LM_40000baseSR4_Full_BIT;
+				phylink_set(if_caps, 40000baseSR4_Full);
 		}
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G)
-			*if_capability |= QED_LM_50000baseKR2_Full_BIT;
+
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G)
+			phylink_set(if_caps, 50000baseKR2_Full);
+
 		if (capability &
 		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) {
 			if (tcvr_type == ETH_TRANSCEIVER_TYPE_100G_SR4)
-				*if_capability |= QED_LM_100000baseSR4_Full_BIT;
+				phylink_set(if_caps, 100000baseSR4_Full);
 		}
 
 		break;
 	case MEDIA_KR:
-		*if_capability |= QED_LM_Backplane_BIT;
+		phylink_set(if_caps, Backplane);
+
 		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G)
-			*if_capability |= QED_LM_20000baseKR2_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G)
-			*if_capability |= QED_LM_1000baseKX_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G)
-			*if_capability |= QED_LM_10000baseKR_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G)
-			*if_capability |= QED_LM_25000baseKR_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G)
-			*if_capability |= QED_LM_40000baseKR4_Full_BIT;
-		if (capability &
-		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G)
-			*if_capability |= QED_LM_50000baseKR2_Full_BIT;
+			phylink_set(if_caps, 20000baseKR2_Full);
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G)
+			phylink_set(if_caps, 1000baseKX_Full);
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G)
+			phylink_set(if_caps, 10000baseKR_Full);
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G)
+			phylink_set(if_caps, 25000baseKR_Full);
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G)
+			phylink_set(if_caps, 40000baseKR4_Full);
+		if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G)
+			phylink_set(if_caps, 50000baseKR2_Full);
 		if (capability &
 		    NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G)
-			*if_capability |= QED_LM_100000baseKR4_Full_BIT;
+			phylink_set(if_caps, 100000baseKR4_Full);
+
 		break;
 	case MEDIA_UNSPECIFIED:
 	case MEDIA_NOT_PRESENT:
@@ -1806,26 +1834,27 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 
 	/* TODO - at the moment assume supported and advertised speed equal */
 	if (link_caps.default_speed_autoneg)
-		if_link->supported_caps |= QED_LM_Autoneg_BIT;
+		phylink_set(if_link->supported_caps, Autoneg);
 	if (params.pause.autoneg ||
 	    (params.pause.forced_rx && params.pause.forced_tx))
-		if_link->supported_caps |= QED_LM_Asym_Pause_BIT;
+		phylink_set(if_link->supported_caps, Asym_Pause);
 	if (params.pause.autoneg || params.pause.forced_rx ||
 	    params.pause.forced_tx)
-		if_link->supported_caps |= QED_LM_Pause_BIT;
+		phylink_set(if_link->supported_caps, Pause);
+
+	linkmode_copy(if_link->advertised_caps, if_link->supported_caps);
 
-	if_link->advertised_caps = if_link->supported_caps;
 	if (params.speed.autoneg)
-		if_link->advertised_caps |= QED_LM_Autoneg_BIT;
+		phylink_set(if_link->advertised_caps, Autoneg);
 	else
-		if_link->advertised_caps &= ~QED_LM_Autoneg_BIT;
+		phylink_clear(if_link->advertised_caps, Autoneg);
 
 	/* Fill link advertised capability*/
 	qed_fill_link_capability(hwfn, ptt, params.speed.advertised_speeds,
-				 &if_link->advertised_caps);
+				 if_link->advertised_caps);
 	/* Fill link supported capability*/
 	qed_fill_link_capability(hwfn, ptt, link_caps.speed_capabilities,
-				 &if_link->supported_caps);
+				 if_link->supported_caps);
 
 	if (link.link_up)
 		if_link->speed = link.speed;
@@ -1845,30 +1874,29 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 		if_link->pause_config |= QED_LINK_PAUSE_TX_ENABLE;
 
 	/* Link partner capabilities */
-	if (link.partner_adv_speed &
-	    QED_LINK_PARTNER_SPEED_1G_FD)
-		if_link->lp_caps |= QED_LM_1000baseT_Full_BIT;
+
+	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_1G_FD)
+		phylink_set(if_link->lp_caps, 1000baseT_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_10G)
-		if_link->lp_caps |= QED_LM_10000baseKR_Full_BIT;
+		phylink_set(if_link->lp_caps, 10000baseKR_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_20G)
-		if_link->lp_caps |= QED_LM_20000baseKR2_Full_BIT;
+		phylink_set(if_link->lp_caps, 20000baseKR2_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_25G)
-		if_link->lp_caps |= QED_LM_25000baseKR_Full_BIT;
+		phylink_set(if_link->lp_caps, 25000baseKR_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_40G)
-		if_link->lp_caps |= QED_LM_40000baseLR4_Full_BIT;
+		phylink_set(if_link->lp_caps, 40000baseLR4_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_50G)
-		if_link->lp_caps |= QED_LM_50000baseKR2_Full_BIT;
+		phylink_set(if_link->lp_caps, 50000baseKR2_Full);
 	if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_100G)
-		if_link->lp_caps |= QED_LM_100000baseKR4_Full_BIT;
+		phylink_set(if_link->lp_caps, 100000baseKR4_Full);
 
 	if (link.an_complete)
-		if_link->lp_caps |= QED_LM_Autoneg_BIT;
-
+		phylink_set(if_link->lp_caps, Autoneg);
 	if (link.partner_adv_pause)
-		if_link->lp_caps |= QED_LM_Pause_BIT;
+		phylink_set(if_link->lp_caps, Pause);
 	if (link.partner_adv_pause == QED_LINK_PARTNER_ASYMMETRIC_PAUSE ||
 	    link.partner_adv_pause == QED_LINK_PARTNER_BOTH_PAUSE)
-		if_link->lp_caps |= QED_LM_Asym_Pause_BIT;
+		phylink_set(if_link->lp_caps, Asym_Pause);
 
 	if (link_caps.default_eee == QED_MCP_EEE_UNSUPPORTED) {
 		if_link->eee_supported = false;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index d3fc7403d095..0a564b06d697 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -13,6 +13,8 @@
 #include <linux/pci.h>
 #include <linux/capability.h>
 #include <linux/vmalloc.h>
+#include <linux/phylink.h>
+
 #include "qede.h"
 #include "qede_ptp.h"
 
@@ -418,76 +420,10 @@ static int qede_set_priv_flags(struct net_device *dev, u32 flags)
 	return 0;
 }
 
-struct qede_link_mode_mapping {
-	u32 qed_link_mode;
-	u32 ethtool_link_mode;
-};
-
-static const struct qede_link_mode_mapping qed_lm_map[] = {
-	{QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT},
-	{QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT},
-	{QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT},
-	{QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT},
-	{QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT},
-	{QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT},
-	{QED_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT},
-	{QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT},
-	{QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT},
-	{QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT},
-	{QED_LM_10000baseKR_Full_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT},
-	{QED_LM_10000baseKR_Full_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT},
-	{QED_LM_10000baseR_FEC_BIT, ETHTOOL_LINK_MODE_10000baseR_FEC_BIT},
-	{QED_LM_20000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT},
-	{QED_LM_40000baseKR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT},
-	{QED_LM_40000baseCR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT},
-	{QED_LM_40000baseSR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT},
-	{QED_LM_40000baseLR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT},
-	{QED_LM_25000baseCR_Full_BIT, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT},
-	{QED_LM_25000baseKR_Full_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT},
-	{QED_LM_25000baseSR_Full_BIT, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT},
-	{QED_LM_50000baseCR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT},
-	{QED_LM_50000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT},
-	{QED_LM_100000baseKR4_Full_BIT,
-		ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT},
-	{QED_LM_100000baseSR4_Full_BIT,
-		ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT},
-	{QED_LM_100000baseCR4_Full_BIT,
-		ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT},
-	{QED_LM_100000baseLR4_ER4_Full_BIT,
-		ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT},
-	{QED_LM_50000baseSR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT},
-	{QED_LM_1000baseX_Full_BIT, ETHTOOL_LINK_MODE_1000baseX_Full_BIT},
-	{QED_LM_10000baseCR_Full_BIT, ETHTOOL_LINK_MODE_10000baseCR_Full_BIT},
-	{QED_LM_10000baseSR_Full_BIT, ETHTOOL_LINK_MODE_10000baseSR_Full_BIT},
-	{QED_LM_10000baseLR_Full_BIT, ETHTOOL_LINK_MODE_10000baseLR_Full_BIT},
-	{QED_LM_10000baseLRM_Full_BIT, ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT},
-};
-
-#define QEDE_DRV_TO_ETHTOOL_CAPS(caps, lk_ksettings, name)	\
-{								\
-	int i;							\
-								\
-	for (i = 0; i < ARRAY_SIZE(qed_lm_map); i++) {		\
-		if ((caps) & (qed_lm_map[i].qed_link_mode))	\
-			__set_bit(qed_lm_map[i].ethtool_link_mode,\
-				  lk_ksettings->link_modes.name); \
-	}							\
-}
-
-#define QEDE_ETHTOOL_TO_DRV_CAPS(caps, lk_ksettings, name)	\
-{								\
-	int i;							\
-								\
-	for (i = 0; i < ARRAY_SIZE(qed_lm_map); i++) {		\
-		if (test_bit(qed_lm_map[i].ethtool_link_mode,	\
-			     lk_ksettings->link_modes.name))	\
-			caps |= qed_lm_map[i].qed_link_mode;	\
-	}							\
-}
-
 static int qede_get_link_ksettings(struct net_device *dev,
 				   struct ethtool_link_ksettings *cmd)
 {
+	typeof(cmd->link_modes) *link_modes = &cmd->link_modes;
 	struct ethtool_link_settings *base = &cmd->base;
 	struct qede_dev *edev = netdev_priv(dev);
 	struct qed_link_output current_link;
@@ -497,14 +433,9 @@ static int qede_get_link_ksettings(struct net_device *dev,
 	memset(&current_link, 0, sizeof(current_link));
 	edev->ops->common->get_link(edev->cdev, &current_link);
 
-	ethtool_link_ksettings_zero_link_mode(cmd, supported);
-	QEDE_DRV_TO_ETHTOOL_CAPS(current_link.supported_caps, cmd, supported)
-
-	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
-	QEDE_DRV_TO_ETHTOOL_CAPS(current_link.advertised_caps, cmd, advertising)
-
-	ethtool_link_ksettings_zero_link_mode(cmd, lp_advertising);
-	QEDE_DRV_TO_ETHTOOL_CAPS(current_link.lp_caps, cmd, lp_advertising)
+	linkmode_copy(link_modes->supported, current_link.supported_caps);
+	linkmode_copy(link_modes->advertising, current_link.advertised_caps);
+	linkmode_copy(link_modes->lp_advertising, current_link.lp_caps);
 
 	if ((edev->state == QEDE_STATE_OPEN) && (current_link.link_up)) {
 		base->speed = current_link.speed;
@@ -527,10 +458,10 @@ static int qede_set_link_ksettings(struct net_device *dev,
 				   const struct ethtool_link_ksettings *cmd)
 {
 	const struct ethtool_link_settings *base = &cmd->base;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sup_caps);
 	struct qede_dev *edev = netdev_priv(dev);
 	struct qed_link_output current_link;
 	struct qed_link_params params;
-	u32 sup_caps;
 
 	if (!edev->ops || !edev->ops->common->can_link_change(edev->cdev)) {
 		DP_INFO(edev, "Link settings are not allowed to be changed\n");
@@ -542,105 +473,79 @@ static int qede_set_link_ksettings(struct net_device *dev,
 
 	params.override_flags |= QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS;
 	params.override_flags |= QED_LINK_OVERRIDE_SPEED_AUTONEG;
+
 	if (base->autoneg == AUTONEG_ENABLE) {
-		if (!(current_link.supported_caps & QED_LM_Autoneg_BIT)) {
+		if (!phylink_test(current_link.supported_caps, Autoneg)) {
 			DP_INFO(edev, "Auto negotiation is not supported\n");
 			return -EOPNOTSUPP;
 		}
 
 		params.autoneg = true;
 		params.forced_speed = 0;
-		QEDE_ETHTOOL_TO_DRV_CAPS(params.adv_speeds, cmd, advertising)
+
+		linkmode_copy(params.adv_speeds, cmd->link_modes.advertising);
 	} else {		/* forced speed */
 		params.override_flags |= QED_LINK_OVERRIDE_SPEED_FORCED_SPEED;
 		params.autoneg = false;
 		params.forced_speed = base->speed;
+
+		phylink_zero(sup_caps);
+
 		switch (base->speed) {
 		case SPEED_1000:
-			sup_caps = QED_LM_1000baseT_Full_BIT |
-					QED_LM_1000baseKX_Full_BIT |
-					QED_LM_1000baseX_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "1G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 1000baseT_Full);
+			phylink_set(sup_caps, 1000baseKX_Full);
+			phylink_set(sup_caps, 1000baseX_Full);
 			break;
 		case SPEED_10000:
-			sup_caps = QED_LM_10000baseT_Full_BIT |
-					QED_LM_10000baseKR_Full_BIT |
-					QED_LM_10000baseKX4_Full_BIT |
-					QED_LM_10000baseR_FEC_BIT |
-					QED_LM_10000baseCR_Full_BIT |
-					QED_LM_10000baseSR_Full_BIT |
-					QED_LM_10000baseLR_Full_BIT |
-					QED_LM_10000baseLRM_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "10G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 10000baseT_Full);
+			phylink_set(sup_caps, 10000baseKR_Full);
+			phylink_set(sup_caps, 10000baseKX4_Full);
+			phylink_set(sup_caps, 10000baseR_FEC);
+			phylink_set(sup_caps, 10000baseCR_Full);
+			phylink_set(sup_caps, 10000baseSR_Full);
+			phylink_set(sup_caps, 10000baseLR_Full);
+			phylink_set(sup_caps, 10000baseLRM_Full);
 			break;
 		case SPEED_20000:
-			if (!(current_link.supported_caps &
-			    QED_LM_20000baseKR2_Full_BIT)) {
-				DP_INFO(edev, "20G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = QED_LM_20000baseKR2_Full_BIT;
+			phylink_set(sup_caps, 20000baseKR2_Full);
 			break;
 		case SPEED_25000:
-			sup_caps = QED_LM_25000baseKR_Full_BIT |
-					QED_LM_25000baseCR_Full_BIT |
-					QED_LM_25000baseSR_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "25G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 25000baseKR_Full);
+			phylink_set(sup_caps, 25000baseCR_Full);
+			phylink_set(sup_caps, 25000baseSR_Full);
 			break;
 		case SPEED_40000:
-			sup_caps = QED_LM_40000baseLR4_Full_BIT |
-					QED_LM_40000baseKR4_Full_BIT |
-					QED_LM_40000baseCR4_Full_BIT |
-					QED_LM_40000baseSR4_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "40G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 40000baseLR4_Full);
+			phylink_set(sup_caps, 40000baseKR4_Full);
+			phylink_set(sup_caps, 40000baseCR4_Full);
+			phylink_set(sup_caps, 40000baseSR4_Full);
 			break;
 		case SPEED_50000:
-			sup_caps = QED_LM_50000baseKR2_Full_BIT |
-					QED_LM_50000baseCR2_Full_BIT |
-					QED_LM_50000baseSR2_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "50G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 50000baseKR2_Full);
+			phylink_set(sup_caps, 50000baseCR2_Full);
+			phylink_set(sup_caps, 50000baseSR2_Full);
 			break;
 		case SPEED_100000:
-			sup_caps = QED_LM_100000baseKR4_Full_BIT |
-					QED_LM_100000baseSR4_Full_BIT |
-					QED_LM_100000baseCR4_Full_BIT |
-					QED_LM_100000baseLR4_ER4_Full_BIT;
-			if (!(current_link.supported_caps & sup_caps)) {
-				DP_INFO(edev, "100G speed not supported\n");
-				return -EINVAL;
-			}
-			params.adv_speeds = current_link.supported_caps &
-						sup_caps;
+			phylink_set(sup_caps, 100000baseKR4_Full);
+			phylink_set(sup_caps, 100000baseSR4_Full);
+			phylink_set(sup_caps, 100000baseCR4_Full);
+			phylink_set(sup_caps, 100000baseLR4_ER4_Full);
 			break;
 		default:
 			DP_INFO(edev, "Unsupported speed %u\n", base->speed);
 			return -EINVAL;
 		}
+
+		if (!linkmode_intersects(current_link.supported_caps,
+					 sup_caps)) {
+			DP_INFO(edev, "%uG speed not supported\n",
+				base->speed / 1000);
+			return -EINVAL;
+		}
+
+		linkmode_and(params.adv_speeds, current_link.supported_caps,
+			     sup_caps);
 	}
 
 	params.link_up = true;
@@ -1006,13 +911,16 @@ static int qede_set_pauseparam(struct net_device *dev,
 
 	memset(&params, 0, sizeof(params));
 	params.override_flags |= QED_LINK_OVERRIDE_PAUSE_CONFIG;
+
 	if (epause->autoneg) {
-		if (!(current_link.supported_caps & QED_LM_Autoneg_BIT)) {
+		if (!phylink_test(current_link.supported_caps, Autoneg)) {
 			DP_INFO(edev, "autoneg not supported\n");
 			return -EINVAL;
 		}
+
 		params.pause_config |= QED_LINK_PAUSE_AUTONEG_ENABLE;
 	}
+
 	if (epause->rx_pause)
 		params.pause_config |= QED_LINK_PAUSE_RX_ENABLE;
 	if (epause->tx_pause)
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 36b1ca2dadbb..6e77e4908605 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/kthread.h>
+#include <linux/phylink.h>
 #include <scsi/libfc.h>
 #include <scsi/scsi_host.h>
 #include <scsi/fc_frame.h>
@@ -440,6 +441,7 @@ static void qedf_link_recovery(struct work_struct *work)
 static void qedf_update_link_speed(struct qedf_ctx *qedf,
 	struct qed_link_output *link)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sup_caps);
 	struct fc_lport *lport = qedf->lport;
 
 	lport->link_speed = FC_PORTSPEED_UNKNOWN;
@@ -474,40 +476,60 @@ static void qedf_update_link_speed(struct qedf_ctx *qedf,
 	 * Set supported link speed by querying the supported
 	 * capabilities of the link.
 	 */
-	if ((link->supported_caps & QED_LM_10000baseT_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseKX4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseR_FEC_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseCR_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseSR_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseLR_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseLRM_Full_BIT) ||
-	    (link->supported_caps & QED_LM_10000baseKR_Full_BIT)) {
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 10000baseT_Full);
+	phylink_set(sup_caps, 10000baseKX4_Full);
+	phylink_set(sup_caps, 10000baseR_FEC);
+	phylink_set(sup_caps, 10000baseCR_Full);
+	phylink_set(sup_caps, 10000baseSR_Full);
+	phylink_set(sup_caps, 10000baseLR_Full);
+	phylink_set(sup_caps, 10000baseLRM_Full);
+	phylink_set(sup_caps, 10000baseKR_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_10GBIT;
-	}
-	if ((link->supported_caps & QED_LM_25000baseKR_Full_BIT) ||
-	    (link->supported_caps & QED_LM_25000baseCR_Full_BIT) ||
-	    (link->supported_caps & QED_LM_25000baseSR_Full_BIT)) {
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 25000baseKR_Full);
+	phylink_set(sup_caps, 25000baseCR_Full);
+	phylink_set(sup_caps, 25000baseSR_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_25GBIT;
-	}
-	if ((link->supported_caps & QED_LM_40000baseLR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_40000baseKR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_40000baseCR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_40000baseSR4_Full_BIT)) {
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 40000baseLR4_Full);
+	phylink_set(sup_caps, 40000baseKR4_Full);
+	phylink_set(sup_caps, 40000baseCR4_Full);
+	phylink_set(sup_caps, 40000baseSR4_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_40GBIT;
-	}
-	if ((link->supported_caps & QED_LM_50000baseKR2_Full_BIT) ||
-	    (link->supported_caps & QED_LM_50000baseCR2_Full_BIT) ||
-	    (link->supported_caps & QED_LM_50000baseSR2_Full_BIT)) {
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 50000baseKR2_Full);
+	phylink_set(sup_caps, 50000baseCR2_Full);
+	phylink_set(sup_caps, 50000baseSR2_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_50GBIT;
-	}
-	if ((link->supported_caps & QED_LM_100000baseKR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_100000baseSR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_100000baseCR4_Full_BIT) ||
-	    (link->supported_caps & QED_LM_100000baseLR4_ER4_Full_BIT)) {
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 100000baseKR4_Full);
+	phylink_set(sup_caps, 100000baseSR4_Full);
+	phylink_set(sup_caps, 100000baseCR4_Full);
+	phylink_set(sup_caps, 100000baseLR4_ER4_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_100GBIT;
-	}
-	if (link->supported_caps & QED_LM_20000baseKR2_Full_BIT)
+
+	phylink_zero(sup_caps);
+	phylink_set(sup_caps, 20000baseKR2_Full);
+
+	if (linkmode_intersects(link->supported_caps, sup_caps))
 		lport->link_supported_speeds |= FC_PORTSPEED_20GBIT;
+
 	fc_host_supported_speeds(lport->host) = lport->link_supported_speeds;
 }
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 8a6e3ad436d1..f82db1b92d45 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -661,42 +661,6 @@ enum qed_protocol {
 	QED_PROTOCOL_FCOE,
 };
 
-enum qed_link_mode_bits {
-	QED_LM_FIBRE_BIT = BIT(0),
-	QED_LM_Autoneg_BIT = BIT(1),
-	QED_LM_Asym_Pause_BIT = BIT(2),
-	QED_LM_Pause_BIT = BIT(3),
-	QED_LM_1000baseT_Full_BIT = BIT(4),
-	QED_LM_10000baseT_Full_BIT = BIT(5),
-	QED_LM_10000baseKR_Full_BIT = BIT(6),
-	QED_LM_20000baseKR2_Full_BIT = BIT(7),
-	QED_LM_25000baseKR_Full_BIT = BIT(8),
-	QED_LM_40000baseLR4_Full_BIT = BIT(9),
-	QED_LM_50000baseKR2_Full_BIT = BIT(10),
-	QED_LM_100000baseKR4_Full_BIT = BIT(11),
-	QED_LM_TP_BIT = BIT(12),
-	QED_LM_Backplane_BIT = BIT(13),
-	QED_LM_1000baseKX_Full_BIT = BIT(14),
-	QED_LM_10000baseKX4_Full_BIT = BIT(15),
-	QED_LM_10000baseR_FEC_BIT = BIT(16),
-	QED_LM_40000baseKR4_Full_BIT = BIT(17),
-	QED_LM_40000baseCR4_Full_BIT = BIT(18),
-	QED_LM_40000baseSR4_Full_BIT = BIT(19),
-	QED_LM_25000baseCR_Full_BIT = BIT(20),
-	QED_LM_25000baseSR_Full_BIT = BIT(21),
-	QED_LM_50000baseCR2_Full_BIT = BIT(22),
-	QED_LM_100000baseSR4_Full_BIT = BIT(23),
-	QED_LM_100000baseCR4_Full_BIT = BIT(24),
-	QED_LM_100000baseLR4_ER4_Full_BIT = BIT(25),
-	QED_LM_50000baseSR2_Full_BIT = BIT(26),
-	QED_LM_1000baseX_Full_BIT = BIT(27),
-	QED_LM_10000baseCR_Full_BIT = BIT(28),
-	QED_LM_10000baseSR_Full_BIT = BIT(29),
-	QED_LM_10000baseLR_Full_BIT = BIT(30),
-	QED_LM_10000baseLRM_Full_BIT = BIT(31),
-	QED_LM_COUNT = 32
-};
-
 struct qed_link_params {
 	bool	link_up;
 
@@ -708,7 +672,9 @@ struct qed_link_params {
 #define QED_LINK_OVERRIDE_EEE_CONFIG            BIT(5)
 	u32	override_flags;
 	bool	autoneg;
-	u32	adv_speeds;
+
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds);
+
 	u32	forced_speed;
 #define QED_LINK_PAUSE_AUTONEG_ENABLE           BIT(0)
 #define QED_LINK_PAUSE_RX_ENABLE                BIT(1)
@@ -726,10 +692,9 @@ struct qed_link_params {
 struct qed_link_output {
 	bool	link_up;
 
-	/* In QED_LM_* defs */
-	u32	supported_caps;
-	u32	advertised_caps;
-	u32	lp_caps;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps);
 
 	u32	speed;                  /* In Mb/s */
 	u8	duplex;                 /* In DUPLEX defs */
-- 
cgit v1.2.3


From 37237b5b7104f91b519133d7862d1b5169a3ba8e Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:06 +0300
Subject: qed: reformat several structures a bit

Prior to adding new fields and bitfields, reformat the related
structures according to the Linux style (spaces to tabs,
lowercase hex, indentation etc.).

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h | 256 +++++++++++++++---------------
 drivers/net/ethernet/qlogic/qed/qed_mcp.h |  85 +++++-----
 include/linux/qed/qed_if.h                |  64 ++++----
 3 files changed, 205 insertions(+), 200 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index ebc25b34e491..93d33c9cf145 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -11536,34 +11536,35 @@ typedef u32 offsize_t;		/* In DWORDS !!! */
 
 /* PHY configuration */
 struct eth_phy_cfg {
-	u32 speed;
-#define ETH_SPEED_AUTONEG	0
-#define ETH_SPEED_SMARTLINQ	0x8
-
-	u32 pause;
-#define ETH_PAUSE_NONE		0x0
-#define ETH_PAUSE_AUTONEG	0x1
-#define ETH_PAUSE_RX		0x2
-#define ETH_PAUSE_TX		0x4
-
-	u32 adv_speed;
-	u32 loopback_mode;
-#define ETH_LOOPBACK_NONE		(0)
-#define ETH_LOOPBACK_INT_PHY		(1)
-#define ETH_LOOPBACK_EXT_PHY		(2)
-#define ETH_LOOPBACK_EXT		(3)
-#define ETH_LOOPBACK_MAC		(4)
-
-	u32 eee_cfg;
+	u32					speed;
+#define ETH_SPEED_AUTONEG			0x0
+#define ETH_SPEED_SMARTLINQ			0x8
+
+	u32					pause;
+#define ETH_PAUSE_NONE				0x0
+#define ETH_PAUSE_AUTONEG			0x1
+#define ETH_PAUSE_RX				0x2
+#define ETH_PAUSE_TX				0x4
+
+	u32					adv_speed;
+
+	u32					loopback_mode;
+#define ETH_LOOPBACK_NONE			0x0
+#define ETH_LOOPBACK_INT_PHY			0x1
+#define ETH_LOOPBACK_EXT_PHY			0x2
+#define ETH_LOOPBACK_EXT			0x3
+#define ETH_LOOPBACK_MAC			0x4
+
+	u32					eee_cfg;
 #define EEE_CFG_EEE_ENABLED			BIT(0)
 #define EEE_CFG_TX_LPI				BIT(1)
 #define EEE_CFG_ADV_SPEED_1G			BIT(2)
 #define EEE_CFG_ADV_SPEED_10G			BIT(3)
-#define EEE_TX_TIMER_USEC_MASK			(0xfffffff0)
+#define EEE_TX_TIMER_USEC_MASK			0xfffffff0
 #define EEE_TX_TIMER_USEC_OFFSET		4
-#define EEE_TX_TIMER_USEC_BALANCED_TIME		(0xa00)
-#define EEE_TX_TIMER_USEC_AGGRESSIVE_TIME	(0x100)
-#define EEE_TX_TIMER_USEC_LATENCY_TIME		(0x6000)
+#define EEE_TX_TIMER_USEC_BALANCED_TIME		0xa00
+#define EEE_TX_TIMER_USEC_AGGRESSIVE_TIME	0x100
+#define EEE_TX_TIMER_USEC_LATENCY_TIME		0x6000
 
 	u32 feature_config_flags;
 #define ETH_EEE_MODE_ADV_LPI		(1 << 0)
@@ -11895,41 +11896,36 @@ struct public_path {
 };
 
 struct public_port {
-	u32 validity_map;
-
-	u32 link_status;
-#define LINK_STATUS_LINK_UP			0x00000001
-#define LINK_STATUS_SPEED_AND_DUPLEX_MASK	0x0000001e
-#define LINK_STATUS_SPEED_AND_DUPLEX_1000THD	(1 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_1000TFD	(2 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_10G	(3 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_20G	(4 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_40G	(5 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_50G	(6 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_100G	(7 << 1)
-#define LINK_STATUS_SPEED_AND_DUPLEX_25G	(8 << 1)
-
-#define LINK_STATUS_AUTO_NEGOTIATE_ENABLED	0x00000020
-
-#define LINK_STATUS_AUTO_NEGOTIATE_COMPLETE	0x00000040
-#define LINK_STATUS_PARALLEL_DETECTION_USED	0x00000080
-
+	u32						validity_map;
+
+	u32						link_status;
+#define LINK_STATUS_LINK_UP				0x00000001
+#define LINK_STATUS_SPEED_AND_DUPLEX_MASK		0x0000001e
+#define LINK_STATUS_SPEED_AND_DUPLEX_1000THD		(1 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_1000TFD		(2 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_10G		(3 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_20G		(4 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_40G		(5 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_50G		(6 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_100G		(7 << 1)
+#define LINK_STATUS_SPEED_AND_DUPLEX_25G		(8 << 1)
+#define LINK_STATUS_AUTO_NEGOTIATE_ENABLED		0x00000020
+#define LINK_STATUS_AUTO_NEGOTIATE_COMPLETE		0x00000040
+#define LINK_STATUS_PARALLEL_DETECTION_USED		0x00000080
 #define LINK_STATUS_PFC_ENABLED				0x00000100
-#define LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE 0x00000200
-#define LINK_STATUS_LINK_PARTNER_1000THD_CAPABLE 0x00000400
+#define LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE	0x00000200
+#define LINK_STATUS_LINK_PARTNER_1000THD_CAPABLE	0x00000400
 #define LINK_STATUS_LINK_PARTNER_10G_CAPABLE		0x00000800
 #define LINK_STATUS_LINK_PARTNER_20G_CAPABLE		0x00001000
 #define LINK_STATUS_LINK_PARTNER_40G_CAPABLE		0x00002000
 #define LINK_STATUS_LINK_PARTNER_50G_CAPABLE		0x00004000
 #define LINK_STATUS_LINK_PARTNER_100G_CAPABLE		0x00008000
 #define LINK_STATUS_LINK_PARTNER_25G_CAPABLE		0x00010000
-
-#define LINK_STATUS_LINK_PARTNER_FLOW_CONTROL_MASK	0x000C0000
+#define LINK_STATUS_LINK_PARTNER_FLOW_CONTROL_MASK	0x000c0000
 #define LINK_STATUS_LINK_PARTNER_NOT_PAUSE_CAPABLE	(0 << 18)
 #define LINK_STATUS_LINK_PARTNER_SYMMETRIC_PAUSE	(1 << 18)
 #define LINK_STATUS_LINK_PARTNER_ASYMMETRIC_PAUSE	(2 << 18)
 #define LINK_STATUS_LINK_PARTNER_BOTH_PAUSE		(3 << 18)
-
 #define LINK_STATUS_SFP_TX_FAULT			0x00100000
 #define LINK_STATUS_TX_FLOW_CONTROL_ENABLED		0x00200000
 #define LINK_STATUS_RX_FLOW_CONTROL_ENABLED		0x00400000
@@ -12630,49 +12626,49 @@ struct public_drv_mb {
 
 #define FW_MSG_CODE_MDUMP_INVALID_CMD		0x00030000
 
-	u32 fw_mb_param;
-#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
+	u32						fw_mb_param;
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xffff0000
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
-#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK	0x0000FFFF
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK	0x0000ffff
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT	0
 
-	/* get pf rdma protocol command responce */
-#define FW_MB_PARAM_GET_PF_RDMA_NONE		0x0
-#define FW_MB_PARAM_GET_PF_RDMA_ROCE		0x1
-#define FW_MB_PARAM_GET_PF_RDMA_IWARP		0x2
-#define FW_MB_PARAM_GET_PF_RDMA_BOTH		0x3
+	/* Get PF RDMA protocol command response */
+#define FW_MB_PARAM_GET_PF_RDMA_NONE			0x0
+#define FW_MB_PARAM_GET_PF_RDMA_ROCE			0x1
+#define FW_MB_PARAM_GET_PF_RDMA_IWARP			0x2
+#define FW_MB_PARAM_GET_PF_RDMA_BOTH			0x3
 
-/* get MFW feature support response */
-#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ	0x00000001
-#define FW_MB_PARAM_FEATURE_SUPPORT_EEE		0x00000002
-#define FW_MB_PARAM_FEATURE_SUPPORT_VLINK	0x00010000
+	/* Get MFW feature support response */
+#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ		0x00000001
+#define FW_MB_PARAM_FEATURE_SUPPORT_EEE			0x00000002
+#define FW_MB_PARAM_FEATURE_SUPPORT_VLINK		0x00010000
 
-#define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR	(1 << 0)
+#define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR		BIT(0)
 
-#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_MASK   0x00000001
-#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_SHIFT 0
-#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_MASK   0x00000002
-#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_SHIFT 1
-#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_MASK    0x00000004
-#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_SHIFT  2
-#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_MASK    0x00000008
-#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_SHIFT  3
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_MASK	0x00000001
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_SHIFT	0
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_MASK	0x00000002
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_SHIFT	1
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_MASK		0x00000004
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_SHIFT	2
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_MASK		0x00000008
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_SHIFT	3
 
-#define FW_MB_PARAM_PPFID_BITMAP_MASK	0xFF
-#define FW_MB_PARAM_PPFID_BITMAP_SHIFT	0
+#define FW_MB_PARAM_PPFID_BITMAP_MASK			0xff
+#define FW_MB_PARAM_PPFID_BITMAP_SHIFT			0
 
-	u32 drv_pulse_mb;
-#define DRV_PULSE_SEQ_MASK			0x00007fff
-#define DRV_PULSE_SYSTEM_TIME_MASK		0xffff0000
-#define DRV_PULSE_ALWAYS_ALIVE			0x00008000
+	u32						drv_pulse_mb;
+#define DRV_PULSE_SEQ_MASK				0x00007fff
+#define DRV_PULSE_SYSTEM_TIME_MASK			0xffff0000
+#define DRV_PULSE_ALWAYS_ALIVE				0x00008000
 
-	u32 mcp_pulse_mb;
-#define MCP_PULSE_SEQ_MASK			0x00007fff
-#define MCP_PULSE_ALWAYS_ALIVE			0x00008000
-#define MCP_EVENT_MASK				0xffff0000
-#define MCP_EVENT_OTHER_DRIVER_RESET_REQ	0x00010000
+	u32						mcp_pulse_mb;
+#define MCP_PULSE_SEQ_MASK				0x00007fff
+#define MCP_PULSE_ALWAYS_ALIVE				0x00008000
+#define MCP_EVENT_MASK					0xffff0000
+#define MCP_EVENT_OTHER_DRIVER_RESET_REQ		0x00010000
 
-	union drv_union_data union_data;
+	union drv_union_data				union_data;
 };
 
 #define FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET_MASK	0x00ffffff
@@ -13048,24 +13044,27 @@ struct nvm_cfg1_path {
 };
 
 struct nvm_cfg1_port {
-	u32 reserved__m_relocated_to_option_123;
-	u32 reserved__m_relocated_to_option_124;
-	u32 generic_cont0;
-#define NVM_CFG1_PORT_DCBX_MODE_MASK				0x000F0000
+	u32							rel_to_opt123;
+	u32							rel_to_opt124;
+
+	u32							generic_cont0;
+#define NVM_CFG1_PORT_DCBX_MODE_MASK				0x000f0000
 #define NVM_CFG1_PORT_DCBX_MODE_OFFSET				16
 #define NVM_CFG1_PORT_DCBX_MODE_DISABLED			0x0
 #define NVM_CFG1_PORT_DCBX_MODE_IEEE				0x1
 #define NVM_CFG1_PORT_DCBX_MODE_CEE				0x2
 #define NVM_CFG1_PORT_DCBX_MODE_DYNAMIC				0x3
-#define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_MASK		0x00F00000
+#define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_MASK		0x00f00000
 #define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_OFFSET		20
 #define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_ETHERNET	0x1
 #define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_FCOE		0x2
 #define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_ISCSI		0x4
-	u32 pcie_cfg;
-	u32 features;
-	u32 speed_cap_mask;
-#define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_MASK		0x0000FFFF
+
+	u32							pcie_cfg;
+	u32							features;
+
+	u32							speed_cap_mask;
+#define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_MASK		0x0000ffff
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_OFFSET		0
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G		0x1
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G		0x2
@@ -13074,8 +13073,9 @@ struct nvm_cfg1_port {
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G		0x10
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G		0x20
 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G		0x40
-	u32 link_settings;
-#define NVM_CFG1_PORT_DRV_LINK_SPEED_MASK			0x0000000F
+
+	u32							link_settings;
+#define NVM_CFG1_PORT_DRV_LINK_SPEED_MASK			0x0000000f
 #define NVM_CFG1_PORT_DRV_LINK_SPEED_OFFSET			0
 #define NVM_CFG1_PORT_DRV_LINK_SPEED_AUTONEG			0x0
 #define NVM_CFG1_PORT_DRV_LINK_SPEED_1G				0x1
@@ -13091,49 +13091,53 @@ struct nvm_cfg1_port {
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG			0x1
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX			0x2
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX			0x4
-	u32 phy_cfg;
-	u32 mgmt_traffic;
 
-	u32 ext_phy;
+	u32							phy_cfg;
+	u32							mgmt_traffic;
+
+	u32							ext_phy;
 	/* EEE power saving mode */
-#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_MASK		0x00FF0000
+#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_MASK		0x00ff0000
 #define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_OFFSET		16
 #define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_DISABLED		0x0
 #define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_BALANCED		0x1
 #define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_AGGRESSIVE		0x2
 #define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_LOW_LATENCY		0x3
 
-	u32 mba_cfg1;
-	u32 mba_cfg2;
-	u32 vf_cfg;
-	struct nvm_cfg_mac_address lldp_mac_address;
-	u32 led_port_settings;
-	u32 transceiver_00;
-	u32 device_ids;
-	u32 board_cfg;
-#define NVM_CFG1_PORT_PORT_TYPE_MASK                            0x000000FF
-#define NVM_CFG1_PORT_PORT_TYPE_OFFSET                          0
-#define NVM_CFG1_PORT_PORT_TYPE_UNDEFINED                       0x0
-#define NVM_CFG1_PORT_PORT_TYPE_MODULE                          0x1
-#define NVM_CFG1_PORT_PORT_TYPE_BACKPLANE                       0x2
-#define NVM_CFG1_PORT_PORT_TYPE_EXT_PHY                         0x3
-#define NVM_CFG1_PORT_PORT_TYPE_MODULE_SLAVE                    0x4
-	u32 mnm_10g_cap;
-	u32 mnm_10g_ctrl;
-	u32 mnm_10g_misc;
-	u32 mnm_25g_cap;
-	u32 mnm_25g_ctrl;
-	u32 mnm_25g_misc;
-	u32 mnm_40g_cap;
-	u32 mnm_40g_ctrl;
-	u32 mnm_40g_misc;
-	u32 mnm_50g_cap;
-	u32 mnm_50g_ctrl;
-	u32 mnm_50g_misc;
-	u32 mnm_100g_cap;
-	u32 mnm_100g_ctrl;
-	u32 mnm_100g_misc;
-	u32 reserved[116];
+	u32							mba_cfg1;
+	u32							mba_cfg2;
+	u32							vf_cfg;
+	struct nvm_cfg_mac_address				lldp_mac_address;
+	u32							led_port_settings;
+	u32							transceiver_00;
+	u32							device_ids;
+
+	u32							board_cfg;
+#define NVM_CFG1_PORT_PORT_TYPE_MASK				0x000000ff
+#define NVM_CFG1_PORT_PORT_TYPE_OFFSET				0
+#define NVM_CFG1_PORT_PORT_TYPE_UNDEFINED			0x0
+#define NVM_CFG1_PORT_PORT_TYPE_MODULE				0x1
+#define NVM_CFG1_PORT_PORT_TYPE_BACKPLANE			0x2
+#define NVM_CFG1_PORT_PORT_TYPE_EXT_PHY				0x3
+#define NVM_CFG1_PORT_PORT_TYPE_MODULE_SLAVE			0x4
+
+	u32							mnm_10g_cap;
+	u32							mnm_10g_ctrl;
+	u32							mnm_10g_misc;
+	u32							mnm_25g_cap;
+	u32							mnm_25g_ctrl;
+	u32							mnm_25g_misc;
+	u32							mnm_40g_cap;
+	u32							mnm_40g_ctrl;
+	u32							mnm_40g_misc;
+	u32							mnm_50g_cap;
+	u32							mnm_50g_ctrl;
+	u32							mnm_50g_misc;
+	u32							mnm_100g_cap;
+	u32							mnm_100g_ctrl;
+	u32							mnm_100g_misc;
+
+	u32							reserved[116];
 };
 
 struct nvm_cfg1_func {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 63a22a615e94..cf678b6966f8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -34,61 +34,60 @@ enum qed_mcp_eee_mode {
 };
 
 struct qed_mcp_link_params {
-	struct qed_mcp_link_speed_params speed;
-	struct qed_mcp_link_pause_params pause;
-	u32 loopback_mode;
-	struct qed_link_eee_params eee;
+	struct qed_mcp_link_speed_params	speed;
+	struct qed_mcp_link_pause_params	pause;
+	u32					loopback_mode;
+	struct qed_link_eee_params		eee;
 };
 
 struct qed_mcp_link_capabilities {
-	u32 speed_capabilities;
-	bool default_speed_autoneg;
-	enum qed_mcp_eee_mode default_eee;
-	u32 eee_lpi_timer;
-	u8 eee_speed_caps;
+	u32					speed_capabilities;
+	bool					default_speed_autoneg;
+	enum qed_mcp_eee_mode			default_eee;
+	u32					eee_lpi_timer;
+	u8					eee_speed_caps;
 };
 
 struct qed_mcp_link_state {
-	bool    link_up;
-
-	u32	min_pf_rate;
+	bool					link_up;
+	u32					min_pf_rate;
 
 	/* Actual link speed in Mb/s */
-	u32	line_speed;
+	u32					line_speed;
 
 	/* PF max speed in Mb/s, deduced from line_speed
 	 * according to PF max bandwidth configuration.
 	 */
-	u32     speed;
-	bool    full_duplex;
-
-	bool    an;
-	bool    an_complete;
-	bool    parallel_detection;
-	bool    pfc_enabled;
-
-#define QED_LINK_PARTNER_SPEED_1G_HD    BIT(0)
-#define QED_LINK_PARTNER_SPEED_1G_FD    BIT(1)
-#define QED_LINK_PARTNER_SPEED_10G      BIT(2)
-#define QED_LINK_PARTNER_SPEED_20G      BIT(3)
-#define QED_LINK_PARTNER_SPEED_25G      BIT(4)
-#define QED_LINK_PARTNER_SPEED_40G      BIT(5)
-#define QED_LINK_PARTNER_SPEED_50G      BIT(6)
-#define QED_LINK_PARTNER_SPEED_100G     BIT(7)
-	u32     partner_adv_speed;
-
-	bool    partner_tx_flow_ctrl_en;
-	bool    partner_rx_flow_ctrl_en;
-
-#define QED_LINK_PARTNER_SYMMETRIC_PAUSE (1)
-#define QED_LINK_PARTNER_ASYMMETRIC_PAUSE (2)
-#define QED_LINK_PARTNER_BOTH_PAUSE (3)
-	u8      partner_adv_pause;
-
-	bool    sfp_tx_fault;
-	bool    eee_active;
-	u8      eee_adv_caps;
-	u8      eee_lp_adv_caps;
+	u32					speed;
+
+	bool					full_duplex;
+	bool					an;
+	bool					an_complete;
+	bool					parallel_detection;
+	bool					pfc_enabled;
+
+	u32					partner_adv_speed;
+#define QED_LINK_PARTNER_SPEED_1G_HD		BIT(0)
+#define QED_LINK_PARTNER_SPEED_1G_FD		BIT(1)
+#define QED_LINK_PARTNER_SPEED_10G		BIT(2)
+#define QED_LINK_PARTNER_SPEED_20G		BIT(3)
+#define QED_LINK_PARTNER_SPEED_25G		BIT(4)
+#define QED_LINK_PARTNER_SPEED_40G		BIT(5)
+#define QED_LINK_PARTNER_SPEED_50G		BIT(6)
+#define QED_LINK_PARTNER_SPEED_100G		BIT(7)
+
+	bool					partner_tx_flow_ctrl_en;
+	bool					partner_rx_flow_ctrl_en;
+
+	u8					partner_adv_pause;
+#define QED_LINK_PARTNER_SYMMETRIC_PAUSE	0x1
+#define QED_LINK_PARTNER_ASYMMETRIC_PAUSE	0x2
+#define QED_LINK_PARTNER_BOTH_PAUSE		0x3
+
+	bool					sfp_tx_fault;
+	bool					eee_active;
+	u8					eee_adv_caps;
+	u8					eee_lp_adv_caps;
 };
 
 struct qed_mcp_function_info {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f82db1b92d45..dde48f206d0d 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -662,51 +662,53 @@ enum qed_protocol {
 };
 
 struct qed_link_params {
-	bool	link_up;
+	bool					link_up;
 
-#define QED_LINK_OVERRIDE_SPEED_AUTONEG         BIT(0)
-#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS      BIT(1)
-#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED    BIT(2)
-#define QED_LINK_OVERRIDE_PAUSE_CONFIG          BIT(3)
-#define QED_LINK_OVERRIDE_LOOPBACK_MODE         BIT(4)
-#define QED_LINK_OVERRIDE_EEE_CONFIG            BIT(5)
-	u32	override_flags;
-	bool	autoneg;
+	u32					override_flags;
+#define QED_LINK_OVERRIDE_SPEED_AUTONEG		BIT(0)
+#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS	BIT(1)
+#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED	BIT(2)
+#define QED_LINK_OVERRIDE_PAUSE_CONFIG		BIT(3)
+#define QED_LINK_OVERRIDE_LOOPBACK_MODE		BIT(4)
+#define QED_LINK_OVERRIDE_EEE_CONFIG		BIT(5)
 
+	bool					autoneg;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds);
+	u32					forced_speed;
 
-	u32	forced_speed;
-#define QED_LINK_PAUSE_AUTONEG_ENABLE           BIT(0)
-#define QED_LINK_PAUSE_RX_ENABLE                BIT(1)
-#define QED_LINK_PAUSE_TX_ENABLE                BIT(2)
-	u32	pause_config;
-#define QED_LINK_LOOPBACK_NONE                  BIT(0)
-#define QED_LINK_LOOPBACK_INT_PHY               BIT(1)
-#define QED_LINK_LOOPBACK_EXT_PHY               BIT(2)
-#define QED_LINK_LOOPBACK_EXT                   BIT(3)
-#define QED_LINK_LOOPBACK_MAC                   BIT(4)
-	u32	loopback_mode;
-	struct qed_link_eee_params eee;
+	u32					pause_config;
+#define QED_LINK_PAUSE_AUTONEG_ENABLE		BIT(0)
+#define QED_LINK_PAUSE_RX_ENABLE		BIT(1)
+#define QED_LINK_PAUSE_TX_ENABLE		BIT(2)
+
+	u32					loopback_mode;
+#define QED_LINK_LOOPBACK_NONE			BIT(0)
+#define QED_LINK_LOOPBACK_INT_PHY		BIT(1)
+#define QED_LINK_LOOPBACK_EXT_PHY		BIT(2)
+#define QED_LINK_LOOPBACK_EXT			BIT(3)
+#define QED_LINK_LOOPBACK_MAC			BIT(4)
+
+	struct qed_link_eee_params		eee;
 };
 
 struct qed_link_output {
-	bool	link_up;
+	bool					link_up;
 
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps);
 
-	u32	speed;                  /* In Mb/s */
-	u8	duplex;                 /* In DUPLEX defs */
-	u8	port;                   /* In PORT defs */
-	bool	autoneg;
-	u32	pause_config;
+	u32					speed;	   /* In Mb/s */
+	u8					duplex;	   /* In DUPLEX defs */
+	u8					port;	   /* In PORT defs */
+	bool					autoneg;
+	u32					pause_config;
 
 	/* EEE - capability & param */
-	bool eee_supported;
-	bool eee_active;
-	u8 sup_caps;
-	struct qed_link_eee_params eee;
+	bool					eee_supported;
+	bool					eee_active;
+	u8					sup_caps;
+	struct qed_link_eee_params		eee;
 };
 
 struct qed_probe_params {
-- 
cgit v1.2.3


From ae7e69379fd5a87141fd8c7f2efab8e73f2a9f7e Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:07 +0300
Subject: qed: add support for Forward Error Correction

Add all necessary routines for reading supported FEC modes from NVM and
querying FEC control to the MFW (if the running version supports it).

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c  | 54 ++++++++++++++++++++----------
 drivers/net/ethernet/qlogic/qed/qed_hsi.h  | 24 +++++++++++--
 drivers/net/ethernet/qlogic/qed/qed_main.c |  6 ++++
 drivers/net/ethernet/qlogic/qed/qed_mcp.c  | 47 +++++++++++++++++++++-----
 drivers/net/ethernet/qlogic/qed/qed_mcp.h  |  4 +++
 include/linux/qed/qed_if.h                 | 13 +++++++
 6 files changed, 121 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 491a6dbb5d73..d929556247a5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3968,7 +3968,7 @@ unlock_and_exit:
 
 static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities;
+	u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities, fc;
 	u32 nvm_cfg1_offset, mf_mode, addr, generic_cont0, core_cfg;
 	struct qed_mcp_link_capabilities *p_caps;
 	struct qed_mcp_link_params *link;
@@ -4081,16 +4081,38 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_hwfn->mcp_info->link_capabilities.default_speed_autoneg =
 		link->speed.autoneg;
 
-	link_temp &= NVM_CFG1_PORT_DRV_FLOW_CONTROL_MASK;
-	link_temp >>= NVM_CFG1_PORT_DRV_FLOW_CONTROL_OFFSET;
-	link->pause.autoneg = !!(link_temp &
-				 NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG);
-	link->pause.forced_rx = !!(link_temp &
-				   NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX);
-	link->pause.forced_tx = !!(link_temp &
-				   NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX);
+	fc = GET_MFW_FIELD(link_temp, NVM_CFG1_PORT_DRV_FLOW_CONTROL);
+	link->pause.autoneg = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG);
+	link->pause.forced_rx = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX);
+	link->pause.forced_tx = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX);
 	link->loopback_mode = 0;
 
+	if (p_hwfn->mcp_info->capabilities &
+	    FW_MB_PARAM_FEATURE_SUPPORT_FEC_CONTROL) {
+		switch (GET_MFW_FIELD(link_temp,
+				      NVM_CFG1_PORT_FEC_FORCE_MODE)) {
+		case NVM_CFG1_PORT_FEC_FORCE_MODE_NONE:
+			p_caps->fec_default |= QED_FEC_MODE_NONE;
+			break;
+		case NVM_CFG1_PORT_FEC_FORCE_MODE_FIRECODE:
+			p_caps->fec_default |= QED_FEC_MODE_FIRECODE;
+			break;
+		case NVM_CFG1_PORT_FEC_FORCE_MODE_RS:
+			p_caps->fec_default |= QED_FEC_MODE_RS;
+			break;
+		case NVM_CFG1_PORT_FEC_FORCE_MODE_AUTO:
+			p_caps->fec_default |= QED_FEC_MODE_AUTO;
+			break;
+		default:
+			DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
+				   "unknown FEC mode in 0x%08x\n", link_temp);
+		}
+	} else {
+		p_caps->fec_default = QED_FEC_MODE_UNSUPPORTED;
+	}
+
+	link->fec = p_caps->fec_default;
+
 	if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) {
 		link_temp = qed_rd(p_hwfn, p_ptt, port_cfg_addr +
 				   offsetof(struct nvm_cfg1_port, ext_phy));
@@ -4122,14 +4144,12 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_caps->default_eee = QED_MCP_EEE_UNSUPPORTED;
 	}
 
-	DP_VERBOSE(p_hwfn,
-		   NETIF_MSG_LINK,
-		   "Read default link: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, PAUSE AN: 0x%02x EEE: %02x [%08x usec]\n",
-		   link->speed.forced_speed,
-		   link->speed.advertised_speeds,
-		   link->speed.autoneg,
-		   link->pause.autoneg,
-		   p_caps->default_eee, p_caps->eee_lpi_timer);
+	DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
+		   "Read default link: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, PAUSE AN: 0x%02x, EEE: 0x%02x [0x%08x usec], FEC: 0x%02x\n",
+		   link->speed.forced_speed, link->speed.advertised_speeds,
+		   link->speed.autoneg, link->pause.autoneg,
+		   p_caps->default_eee, p_caps->eee_lpi_timer,
+		   p_caps->fec_default);
 
 	if (IS_LEAD_HWFN(p_hwfn)) {
 		struct qed_dev *cdev = p_hwfn->cdev;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 93d33c9cf145..7c1d4efffbff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -11566,8 +11566,15 @@ struct eth_phy_cfg {
 #define EEE_TX_TIMER_USEC_AGGRESSIVE_TIME	0x100
 #define EEE_TX_TIMER_USEC_LATENCY_TIME		0x6000
 
-	u32 feature_config_flags;
-#define ETH_EEE_MODE_ADV_LPI		(1 << 0)
+	u32					deprecated;
+
+	u32					fec_mode;
+#define FEC_FORCE_MODE_MASK			0x000000ff
+#define FEC_FORCE_MODE_OFFSET			0
+#define FEC_FORCE_MODE_NONE			0x00
+#define FEC_FORCE_MODE_FIRECODE			0x01
+#define FEC_FORCE_MODE_RS			0x02
+#define FEC_FORCE_MODE_AUTO			0x07
 };
 
 struct port_mf_cfg {
@@ -11934,6 +11941,11 @@ struct public_port {
 #define LINK_STATUS_MAC_REMOTE_FAULT			0x02000000
 #define LINK_STATUS_UNSUPPORTED_SPD_REQ			0x04000000
 
+#define LINK_STATUS_FEC_MODE_MASK			0x38000000
+#define LINK_STATUS_FEC_MODE_NONE			(0 << 27)
+#define LINK_STATUS_FEC_MODE_FIRECODE_CL74		(1 << 27)
+#define LINK_STATUS_FEC_MODE_RS_CL91			(2 << 27)
+
 	u32 link_status1;
 	u32 ext_phy_fw_version;
 	u32 drv_phy_cfg_addr;
@@ -12553,6 +12565,7 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_MASK		0x0000FFFF
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_OFFSET	0
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE		0x00000002
+#define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_FEC_CONTROL	0x00000004
 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK		0x00010000
 
 /* DRV_MSG_CODE_DEBUG_DATA_SEND parameters */
@@ -12641,6 +12654,7 @@ struct public_drv_mb {
 	/* Get MFW feature support response */
 #define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ		0x00000001
 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE			0x00000002
+#define FW_MB_PARAM_FEATURE_SUPPORT_FEC_CONTROL		0x00000020
 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK		0x00010000
 
 #define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR		BIT(0)
@@ -13091,6 +13105,12 @@ struct nvm_cfg1_port {
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG			0x1
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX			0x2
 #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX			0x4
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_MASK			0x000e0000
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_OFFSET			17
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_NONE			0x0
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_FIRECODE			0x1
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_RS				0x2
+#define NVM_CFG1_PORT_FEC_FORCE_MODE_AUTO			0x7
 
 	u32							phy_cfg;
 	u32							mgmt_traffic;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 2be9ed39c450..91e7cfc544f0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1597,6 +1597,9 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 		memcpy(&link_params->eee, &params->eee,
 		       sizeof(link_params->eee));
 
+	if (params->override_flags & QED_LINK_OVERRIDE_FEC_CONFIG)
+		link_params->fec = params->fec;
+
 	rc = qed_mcp_set_link(hwfn, ptt, params->link_up);
 
 	qed_ptt_release(hwfn, ptt);
@@ -1938,6 +1941,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 	else
 		phylink_clear(if_link->advertised_caps, Autoneg);
 
+	if_link->sup_fec = link_caps.fec_default;
+	if_link->active_fec = params.fec;
+
 	/* Fill link advertised capability */
 	qed_fill_link_capability(hwfn, ptt, params.speed.advertised_speeds,
 				 if_link->advertised_caps);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index b10a92488630..78c0d3a2d164 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1446,6 +1446,25 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn,
 	if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE)
 		qed_mcp_read_eee_config(p_hwfn, p_ptt, p_link);
 
+	if (p_hwfn->mcp_info->capabilities &
+	    FW_MB_PARAM_FEATURE_SUPPORT_FEC_CONTROL) {
+		switch (status & LINK_STATUS_FEC_MODE_MASK) {
+		case LINK_STATUS_FEC_MODE_NONE:
+			p_link->fec_active = QED_FEC_MODE_NONE;
+			break;
+		case LINK_STATUS_FEC_MODE_FIRECODE_CL74:
+			p_link->fec_active = QED_FEC_MODE_FIRECODE;
+			break;
+		case LINK_STATUS_FEC_MODE_RS_CL91:
+			p_link->fec_active = QED_FEC_MODE_RS;
+			break;
+		default:
+			p_link->fec_active = QED_FEC_MODE_AUTO;
+		}
+	} else {
+		p_link->fec_active = QED_FEC_MODE_UNSUPPORTED;
+	}
+
 	qed_link_update(p_hwfn, p_ptt);
 out:
 	spin_unlock_bh(&p_hwfn->mcp_info->link_lock);
@@ -1456,8 +1475,8 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	struct qed_mcp_link_params *params = &p_hwfn->mcp_info->link_input;
 	struct qed_mcp_mb_params mb_params;
 	struct eth_phy_cfg phy_cfg;
+	u32 cmd, fec_bit = 0;
 	int rc = 0;
-	u32 cmd;
 
 	/* Set the shmem configuration according to params */
 	memset(&phy_cfg, 0, sizeof(phy_cfg));
@@ -1489,16 +1508,27 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 				   EEE_TX_TIMER_USEC_MASK;
 	}
 
+	if (p_hwfn->mcp_info->capabilities &
+	    FW_MB_PARAM_FEATURE_SUPPORT_FEC_CONTROL) {
+		if (params->fec & QED_FEC_MODE_NONE)
+			fec_bit |= FEC_FORCE_MODE_NONE;
+		else if (params->fec & QED_FEC_MODE_FIRECODE)
+			fec_bit |= FEC_FORCE_MODE_FIRECODE;
+		else if (params->fec & QED_FEC_MODE_RS)
+			fec_bit |= FEC_FORCE_MODE_RS;
+		else if (params->fec & QED_FEC_MODE_AUTO)
+			fec_bit |= FEC_FORCE_MODE_AUTO;
+
+		SET_MFW_FIELD(phy_cfg.fec_mode, FEC_FORCE_MODE, fec_bit);
+	}
+
 	p_hwfn->b_drv_link_init = b_up;
 
 	if (b_up) {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
-			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, features 0x%08x\n",
-			   phy_cfg.speed,
-			   phy_cfg.pause,
-			   phy_cfg.adv_speed,
-			   phy_cfg.loopback_mode,
-			   phy_cfg.feature_config_flags);
+			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, FEC 0x%08x\n",
+			   phy_cfg.speed, phy_cfg.pause, phy_cfg.adv_speed,
+			   phy_cfg.loopback_mode, phy_cfg.fec_mode);
 	} else {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 			   "Resetting link\n");
@@ -3805,7 +3835,8 @@ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	u32 mcp_resp, mcp_param, features;
 
 	features = DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE |
-		   DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK;
+		   DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK |
+		   DRV_MB_PARAM_FEATURE_SUPPORT_PORT_FEC_CONTROL;
 
 	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_FEATURE_SUPPORT,
 			   features, &mcp_resp, &mcp_param);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index cf678b6966f8..5e50405854e6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -38,11 +38,13 @@ struct qed_mcp_link_params {
 	struct qed_mcp_link_pause_params	pause;
 	u32					loopback_mode;
 	struct qed_link_eee_params		eee;
+	u32					fec;
 };
 
 struct qed_mcp_link_capabilities {
 	u32					speed_capabilities;
 	bool					default_speed_autoneg;
+	u32					fec_default;
 	enum qed_mcp_eee_mode			default_eee;
 	u32					eee_lpi_timer;
 	u8					eee_speed_caps;
@@ -88,6 +90,8 @@ struct qed_mcp_link_state {
 	bool					eee_active;
 	u8					eee_adv_caps;
 	u8					eee_lp_adv_caps;
+
+	u32					fec_active;
 };
 
 struct qed_mcp_function_info {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index dde48f206d0d..f0b4cdc79299 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -661,6 +661,14 @@ enum qed_protocol {
 	QED_PROTOCOL_FCOE,
 };
 
+enum qed_fec_mode {
+	QED_FEC_MODE_NONE			= BIT(0),
+	QED_FEC_MODE_FIRECODE			= BIT(1),
+	QED_FEC_MODE_RS				= BIT(2),
+	QED_FEC_MODE_AUTO			= BIT(3),
+	QED_FEC_MODE_UNSUPPORTED		= BIT(4),
+};
+
 struct qed_link_params {
 	bool					link_up;
 
@@ -671,6 +679,7 @@ struct qed_link_params {
 #define QED_LINK_OVERRIDE_PAUSE_CONFIG		BIT(3)
 #define QED_LINK_OVERRIDE_LOOPBACK_MODE		BIT(4)
 #define QED_LINK_OVERRIDE_EEE_CONFIG		BIT(5)
+#define QED_LINK_OVERRIDE_FEC_CONFIG		BIT(6)
 
 	bool					autoneg;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds);
@@ -689,6 +698,7 @@ struct qed_link_params {
 #define QED_LINK_LOOPBACK_MAC			BIT(4)
 
 	struct qed_link_eee_params		eee;
+	u32					fec;
 };
 
 struct qed_link_output {
@@ -709,6 +719,9 @@ struct qed_link_output {
 	bool					eee_active;
 	u8					sup_caps;
 	struct qed_link_eee_params		eee;
+
+	u32					sup_fec;
+	u32					active_fec;
 };
 
 struct qed_probe_params {
-- 
cgit v1.2.3


From 98e675ec5a92a15f6f8ade41eda883cd39df5712 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:13 +0300
Subject: qed: add missing loopback modes

These modes are relevant only for several boards, but may be reported by
MFW as well as the others.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h  |  5 +++++
 drivers/net/ethernet/qlogic/qed/qed_main.c | 19 +++++++++++++++++++
 include/linux/qed/qed_if.h                 |  5 +++++
 3 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index debc55923251..5b81d5d42397 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -11554,6 +11554,11 @@ struct eth_phy_cfg {
 #define ETH_LOOPBACK_EXT_PHY			0x2
 #define ETH_LOOPBACK_EXT			0x3
 #define ETH_LOOPBACK_MAC			0x4
+#define ETH_LOOPBACK_CNIG_AH_ONLY_0123		0x5
+#define ETH_LOOPBACK_CNIG_AH_ONLY_2301		0x6
+#define ETH_LOOPBACK_PCS_AH_ONLY		0x7
+#define ETH_LOOPBACK_REVERSE_MAC_AH_ONLY	0x8
+#define ETH_LOOPBACK_INT_PHY_FEA_AH_ONLY	0x9
 
 	u32					eee_cfg;
 #define EEE_CFG_EEE_ENABLED			BIT(0)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 91e7cfc544f0..fea155c6ff11 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1587,6 +1587,25 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 		case QED_LINK_LOOPBACK_MAC:
 			link_params->loopback_mode = ETH_LOOPBACK_MAC;
 			break;
+		case QED_LINK_LOOPBACK_CNIG_AH_ONLY_0123:
+			link_params->loopback_mode =
+				ETH_LOOPBACK_CNIG_AH_ONLY_0123;
+			break;
+		case QED_LINK_LOOPBACK_CNIG_AH_ONLY_2301:
+			link_params->loopback_mode =
+				ETH_LOOPBACK_CNIG_AH_ONLY_2301;
+			break;
+		case QED_LINK_LOOPBACK_PCS_AH_ONLY:
+			link_params->loopback_mode = ETH_LOOPBACK_PCS_AH_ONLY;
+			break;
+		case QED_LINK_LOOPBACK_REVERSE_MAC_AH_ONLY:
+			link_params->loopback_mode =
+				ETH_LOOPBACK_REVERSE_MAC_AH_ONLY;
+			break;
+		case QED_LINK_LOOPBACK_INT_PHY_FEA_AH_ONLY:
+			link_params->loopback_mode =
+				ETH_LOOPBACK_INT_PHY_FEA_AH_ONLY;
+			break;
 		default:
 			link_params->loopback_mode = ETH_LOOPBACK_NONE;
 			break;
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f0b4cdc79299..2e780159a5fb 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -696,6 +696,11 @@ struct qed_link_params {
 #define QED_LINK_LOOPBACK_EXT_PHY		BIT(2)
 #define QED_LINK_LOOPBACK_EXT			BIT(3)
 #define QED_LINK_LOOPBACK_MAC			BIT(4)
+#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_0123	BIT(5)
+#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_2301	BIT(6)
+#define QED_LINK_LOOPBACK_PCS_AH_ONLY		BIT(7)
+#define QED_LINK_LOOPBACK_REVERSE_MAC_AH_ONLY	BIT(8)
+#define QED_LINK_LOOPBACK_INT_PHY_FEA_AH_ONLY	BIT(9)
 
 	struct qed_link_eee_params		eee;
 	u32					fec;
-- 
cgit v1.2.3


From 99785a87fc7d27207c7dca0f0fe04386f1981690 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Mon, 20 Jul 2020 21:08:15 +0300
Subject: qed: add support for the extended speed and FEC modes

Add all necessary code (NVM parsing, MFW and Ethtool reports etc.) to
support extended speed and FEC modes.
These new modes are supported by the new boards revisions and newer
MFW versions.

Misc: correct port type for MEDIA_KR.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h      |   1 +
 drivers/net/ethernet/qlogic/qed/qed_dev.c  | 102 ++++++++++-
 drivers/net/ethernet/qlogic/qed/qed_hsi.h  |  85 +++++++++-
 drivers/net/ethernet/qlogic/qed/qed_main.c | 264 +++++++++++++++++++++++++++--
 drivers/net/ethernet/qlogic/qed/qed_mcp.c  |  74 +++++++-
 drivers/net/ethernet/qlogic/qed/qed_mcp.h  |  45 +++++
 include/linux/qed/qed_if.h                 |   1 +
 7 files changed, 547 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 47da4f7d3be2..b2a7b53ee760 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -712,6 +712,7 @@ struct qed_dev {
 #define QED_IS_AH(dev)			((dev)->type == QED_DEV_TYPE_AH)
 #define QED_IS_K2(dev)			QED_IS_AH(dev)
 #define QED_IS_E4(dev)			(QED_IS_BB(dev) || QED_IS_AH(dev))
+#define QED_IS_E5(dev)			((dev)->type == QED_DEV_TYPE_E5)
 
 	u16				vendor_id;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 66a520099c44..6516a1f921da 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3968,8 +3968,9 @@ unlock_and_exit:
 
 static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities, fc;
+	u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities, fld;
 	u32 nvm_cfg1_offset, mf_mode, addr, generic_cont0, core_cfg;
+	struct qed_mcp_link_speed_params *ext_speed;
 	struct qed_mcp_link_capabilities *p_caps;
 	struct qed_mcp_link_params *link;
 
@@ -4026,8 +4027,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	link_temp &= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_MASK;
 	link->speed.advertised_speeds = link_temp;
 
-	link_temp = link->speed.advertised_speeds;
-	p_hwfn->mcp_info->link_capabilities.speed_capabilities = link_temp;
+	p_caps->speed_capabilities = link->speed.advertised_speeds;
 
 	link_temp = qed_rd(p_hwfn, p_ptt,
 			   port_cfg_addr +
@@ -4062,13 +4062,12 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		DP_NOTICE(p_hwfn, "Unknown Speed in 0x%08x\n", link_temp);
 	}
 
-	p_hwfn->mcp_info->link_capabilities.default_speed_autoneg =
-		link->speed.autoneg;
+	p_caps->default_speed_autoneg = link->speed.autoneg;
 
-	fc = GET_MFW_FIELD(link_temp, NVM_CFG1_PORT_DRV_FLOW_CONTROL);
-	link->pause.autoneg = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG);
-	link->pause.forced_rx = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX);
-	link->pause.forced_tx = !!(fc & NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX);
+	fld = GET_MFW_FIELD(link_temp, NVM_CFG1_PORT_DRV_FLOW_CONTROL);
+	link->pause.autoneg = !!(fld & NVM_CFG1_PORT_DRV_FLOW_CONTROL_AUTONEG);
+	link->pause.forced_rx = !!(fld & NVM_CFG1_PORT_DRV_FLOW_CONTROL_RX);
+	link->pause.forced_tx = !!(fld & NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX);
 	link->loopback_mode = 0;
 
 	if (p_hwfn->mcp_info->capabilities &
@@ -4128,6 +4127,91 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_caps->default_eee = QED_MCP_EEE_UNSUPPORTED;
 	}
 
+	if (p_hwfn->mcp_info->capabilities &
+	    FW_MB_PARAM_FEATURE_SUPPORT_EXT_SPEED_FEC_CONTROL) {
+		ext_speed = &link->ext_speed;
+
+		link_temp = qed_rd(p_hwfn, p_ptt,
+				   port_cfg_addr +
+				   offsetof(struct nvm_cfg1_port,
+					    extended_speed));
+
+		fld = GET_MFW_FIELD(link_temp, NVM_CFG1_PORT_EXTENDED_SPEED);
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_AN)
+			ext_speed->autoneg = true;
+
+		ext_speed->forced_speed = 0;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_1G)
+			ext_speed->forced_speed |= QED_EXT_SPEED_1G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_10G)
+			ext_speed->forced_speed |= QED_EXT_SPEED_10G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_20G)
+			ext_speed->forced_speed |= QED_EXT_SPEED_20G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_25G)
+			ext_speed->forced_speed |= QED_EXT_SPEED_25G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_40G)
+			ext_speed->forced_speed |= QED_EXT_SPEED_40G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_50G_R)
+			ext_speed->forced_speed |= QED_EXT_SPEED_50G_R;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_50G_R2)
+			ext_speed->forced_speed |= QED_EXT_SPEED_50G_R2;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_R2)
+			ext_speed->forced_speed |= QED_EXT_SPEED_100G_R2;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_R4)
+			ext_speed->forced_speed |= QED_EXT_SPEED_100G_R4;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_P4)
+			ext_speed->forced_speed |= QED_EXT_SPEED_100G_P4;
+
+		fld = GET_MFW_FIELD(link_temp,
+				    NVM_CFG1_PORT_EXTENDED_SPEED_CAP);
+
+		ext_speed->advertised_speeds = 0;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_RESERVED)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_RES;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_1G)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_1G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_10G)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_10G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_20G)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_20G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_25G)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_25G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_40G)
+			ext_speed->advertised_speeds |= QED_EXT_SPEED_MASK_40G;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_50G_R)
+			ext_speed->advertised_speeds |=
+				QED_EXT_SPEED_MASK_50G_R;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_50G_R2)
+			ext_speed->advertised_speeds |=
+				QED_EXT_SPEED_MASK_50G_R2;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_R2)
+			ext_speed->advertised_speeds |=
+				QED_EXT_SPEED_MASK_100G_R2;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_R4)
+			ext_speed->advertised_speeds |=
+				QED_EXT_SPEED_MASK_100G_R4;
+		if (fld & NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_P4)
+			ext_speed->advertised_speeds |=
+				QED_EXT_SPEED_MASK_100G_P4;
+
+		link_temp = qed_rd(p_hwfn, p_ptt,
+				   port_cfg_addr +
+				   offsetof(struct nvm_cfg1_port,
+					    extended_fec_mode));
+		link->ext_fec_mode = link_temp;
+
+		p_caps->default_ext_speed_caps = ext_speed->advertised_speeds;
+		p_caps->default_ext_speed = ext_speed->forced_speed;
+		p_caps->default_ext_autoneg = ext_speed->autoneg;
+		p_caps->default_ext_fec = link->ext_fec_mode;
+
+		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
+			   "Read default extended link config: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, FEC: 0x%02x\n",
+			   ext_speed->forced_speed,
+			   ext_speed->advertised_speeds, ext_speed->autoneg,
+			   p_caps->default_ext_fec);
+	}
+
 	DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 		   "Read default link: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, PAUSE AN: 0x%02x, EEE: 0x%02x [0x%08x usec], FEC: 0x%02x\n",
 		   link->speed.forced_speed, link->speed.advertised_speeds,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 5b81d5d42397..1af3f65ab862 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -11580,6 +11580,54 @@ struct eth_phy_cfg {
 #define FEC_FORCE_MODE_FIRECODE			0x01
 #define FEC_FORCE_MODE_RS			0x02
 #define FEC_FORCE_MODE_AUTO			0x07
+#define FEC_EXTENDED_MODE_MASK			0xffffff00
+#define FEC_EXTENDED_MODE_OFFSET		8
+#define ETH_EXT_FEC_NONE			0x00000100
+#define ETH_EXT_FEC_10G_NONE			0x00000200
+#define ETH_EXT_FEC_10G_BASE_R			0x00000400
+#define ETH_EXT_FEC_20G_NONE			0x00000800
+#define ETH_EXT_FEC_20G_BASE_R			0x00001000
+#define ETH_EXT_FEC_25G_NONE			0x00002000
+#define ETH_EXT_FEC_25G_BASE_R			0x00004000
+#define ETH_EXT_FEC_25G_RS528			0x00008000
+#define ETH_EXT_FEC_40G_NONE			0x00010000
+#define ETH_EXT_FEC_40G_BASE_R			0x00020000
+#define ETH_EXT_FEC_50G_NONE			0x00040000
+#define ETH_EXT_FEC_50G_BASE_R			0x00080000
+#define ETH_EXT_FEC_50G_RS528			0x00100000
+#define ETH_EXT_FEC_50G_RS544			0x00200000
+#define ETH_EXT_FEC_100G_NONE			0x00400000
+#define ETH_EXT_FEC_100G_BASE_R			0x00800000
+#define ETH_EXT_FEC_100G_RS528			0x01000000
+#define ETH_EXT_FEC_100G_RS544			0x02000000
+
+	u32					extended_speed;
+#define ETH_EXT_SPEED_MASK			0x0000ffff
+#define ETH_EXT_SPEED_OFFSET			0
+#define ETH_EXT_SPEED_AN			0x00000001
+#define ETH_EXT_SPEED_1G			0x00000002
+#define ETH_EXT_SPEED_10G			0x00000004
+#define ETH_EXT_SPEED_20G			0x00000008
+#define ETH_EXT_SPEED_25G			0x00000010
+#define ETH_EXT_SPEED_40G			0x00000020
+#define ETH_EXT_SPEED_50G_BASE_R		0x00000040
+#define ETH_EXT_SPEED_50G_BASE_R2		0x00000080
+#define ETH_EXT_SPEED_100G_BASE_R2		0x00000100
+#define ETH_EXT_SPEED_100G_BASE_R4		0x00000200
+#define ETH_EXT_SPEED_100G_BASE_P4		0x00000400
+#define ETH_EXT_ADV_SPEED_MASK			0xffff0000
+#define ETH_EXT_ADV_SPEED_OFFSET		16
+#define ETH_EXT_ADV_SPEED_RESERVED		0x00010000
+#define ETH_EXT_ADV_SPEED_1G			0x00020000
+#define ETH_EXT_ADV_SPEED_10G			0x00040000
+#define ETH_EXT_ADV_SPEED_20G			0x00080000
+#define ETH_EXT_ADV_SPEED_25G			0x00100000
+#define ETH_EXT_ADV_SPEED_40G			0x00200000
+#define ETH_EXT_ADV_SPEED_50G_BASE_R		0x00400000
+#define ETH_EXT_ADV_SPEED_50G_BASE_R2		0x00800000
+#define ETH_EXT_ADV_SPEED_100G_BASE_R2		0x01000000
+#define ETH_EXT_ADV_SPEED_100G_BASE_R4		0x02000000
+#define ETH_EXT_ADV_SPEED_100G_BASE_P4		0x04000000
 };
 
 struct port_mf_cfg {
@@ -12571,6 +12619,7 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_OFFSET		0
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE			0x00000002
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_FEC_CONTROL		0x00000004
+#define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EXT_SPEED_FEC_CONTROL	0x00000008
 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK			0x00010000
 
 /* DRV_MSG_CODE_DEBUG_DATA_SEND parameters */
@@ -12660,6 +12709,7 @@ struct public_drv_mb {
 #define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ			BIT(0)
 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE				BIT(1)
 #define FW_MB_PARAM_FEATURE_SUPPORT_FEC_CONTROL			BIT(5)
+#define FW_MB_PARAM_FEATURE_SUPPORT_EXT_SPEED_FEC_CONTROL	BIT(6)
 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK			BIT(16)
 
 #define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR			BIT(0)
@@ -13174,7 +13224,40 @@ struct nvm_cfg1_port {
 	u32							mnm_100g_ctrl;
 	u32							mnm_100g_misc;
 
-	u32							reserved[116];
+	u32							temperature;
+	u32							ext_phy_cfg1;
+
+	u32							extended_speed;
+#define NVM_CFG1_PORT_EXTENDED_SPEED_MASK			0x0000ffff
+#define NVM_CFG1_PORT_EXTENDED_SPEED_OFFSET			0
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_AN		0x1
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_1G		0x2
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_10G		0x4
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_20G		0x8
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_25G		0x10
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_40G		0x20
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_50G_R		0x40
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_50G_R2		0x80
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_R2		0x100
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_R4		0x200
+#define NVM_CFG1_PORT_EXTENDED_SPEED_EXTND_SPD_100G_P4		0x400
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_MASK			0xffff0000
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_OFFSET			16
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_RESERVED	0x1
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_1G		0x2
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_10G		0x4
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_20G		0x8
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_25G		0x10
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_40G		0x20
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_50G_R	0x40
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_50G_R2	0x80
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_R2	0x100
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_R4	0x200
+#define NVM_CFG1_PORT_EXTENDED_SPEED_CAP_EXTND_SPD_100G_P4	0x400
+
+	u32							extended_fec_mode;
+
+	u32							reserved[112];
 };
 
 struct nvm_cfg1_func {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 4fe66cf60f24..2558cb680db3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -82,6 +82,85 @@ struct qed_mfw_speed_map {
 	.arr_size	= ARRAY_SIZE(arr),	\
 }
 
+static const u32 qed_mfw_ext_1g[] __initconst = {
+	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+	ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_10g[] __initconst = {
+	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+	ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_20g[] __initconst = {
+	ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_25g[] __initconst = {
+	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_40g[] __initconst = {
+	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_50g_base_r[] __initconst = {
+	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_50g_base_r2[] __initconst = {
+	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_100g_base_r2[] __initconst = {
+	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+};
+
+static const u32 qed_mfw_ext_100g_base_r4[] __initconst = {
+	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+};
+
+static struct qed_mfw_speed_map qed_mfw_ext_maps[] __ro_after_init = {
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_1G, qed_mfw_ext_1g),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_10G, qed_mfw_ext_10g),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_20G, qed_mfw_ext_20g),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_25G, qed_mfw_ext_25g),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_40G, qed_mfw_ext_40g),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_50G_BASE_R,
+			  qed_mfw_ext_50g_base_r),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_50G_BASE_R2,
+			  qed_mfw_ext_50g_base_r2),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_100G_BASE_R2,
+			  qed_mfw_ext_100g_base_r2),
+	QED_MFW_SPEED_MAP(ETH_EXT_ADV_SPEED_100G_BASE_R4,
+			  qed_mfw_ext_100g_base_r4),
+};
+
 static const u32 qed_mfw_legacy_1g[] __initconst = {
 	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
 	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
@@ -158,6 +237,9 @@ static void __init qed_mfw_speed_maps_init(void)
 {
 	u32 i;
 
+	for (i = 0; i < ARRAY_SIZE(qed_mfw_ext_maps); i++)
+		qed_mfw_speed_map_populate(qed_mfw_ext_maps + i);
+
 	for (i = 0; i < ARRAY_SIZE(qed_mfw_legacy_maps); i++)
 		qed_mfw_speed_map_populate(qed_mfw_legacy_maps + i);
 }
@@ -1553,6 +1635,147 @@ static bool qed_can_link_change(struct qed_dev *cdev)
 	return true;
 }
 
+static void qed_set_ext_speed_params(struct qed_mcp_link_params *link_params,
+				     const struct qed_link_params *params)
+{
+	struct qed_mcp_link_speed_params *ext_speed = &link_params->ext_speed;
+	const struct qed_mfw_speed_map *map;
+	u32 i;
+
+	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_AUTONEG)
+		ext_speed->autoneg = !!params->autoneg;
+
+	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS) {
+		ext_speed->advertised_speeds = 0;
+
+		for (i = 0; i < ARRAY_SIZE(qed_mfw_ext_maps); i++) {
+			map = qed_mfw_ext_maps + i;
+
+			if (linkmode_intersects(params->adv_speeds, map->caps))
+				ext_speed->advertised_speeds |= map->mfw_val;
+		}
+	}
+
+	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_FORCED_SPEED) {
+		switch (params->forced_speed) {
+		case SPEED_1000:
+			ext_speed->forced_speed = QED_EXT_SPEED_1G;
+			break;
+		case SPEED_10000:
+			ext_speed->forced_speed = QED_EXT_SPEED_10G;
+			break;
+		case SPEED_20000:
+			ext_speed->forced_speed = QED_EXT_SPEED_20G;
+			break;
+		case SPEED_25000:
+			ext_speed->forced_speed = QED_EXT_SPEED_25G;
+			break;
+		case SPEED_40000:
+			ext_speed->forced_speed = QED_EXT_SPEED_40G;
+			break;
+		case SPEED_50000:
+			ext_speed->forced_speed = QED_EXT_SPEED_50G_R |
+						  QED_EXT_SPEED_50G_R2;
+			break;
+		case SPEED_100000:
+			ext_speed->forced_speed = QED_EXT_SPEED_100G_R2 |
+						  QED_EXT_SPEED_100G_R4 |
+						  QED_EXT_SPEED_100G_P4;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (!(params->override_flags & QED_LINK_OVERRIDE_FEC_CONFIG))
+		return;
+
+	switch (params->forced_speed) {
+	case SPEED_25000:
+		switch (params->fec) {
+		case FEC_FORCE_MODE_NONE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_25G_NONE;
+			break;
+		case FEC_FORCE_MODE_FIRECODE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_25G_BASE_R;
+			break;
+		case FEC_FORCE_MODE_RS:
+			link_params->ext_fec_mode = ETH_EXT_FEC_25G_RS528;
+			break;
+		case FEC_FORCE_MODE_AUTO:
+			link_params->ext_fec_mode = ETH_EXT_FEC_25G_RS528 |
+						    ETH_EXT_FEC_25G_BASE_R |
+						    ETH_EXT_FEC_25G_NONE;
+			break;
+		default:
+			break;
+		}
+
+		break;
+	case SPEED_40000:
+		switch (params->fec) {
+		case FEC_FORCE_MODE_NONE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_40G_NONE;
+			break;
+		case FEC_FORCE_MODE_FIRECODE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_40G_BASE_R;
+			break;
+		case FEC_FORCE_MODE_AUTO:
+			link_params->ext_fec_mode = ETH_EXT_FEC_40G_BASE_R |
+						    ETH_EXT_FEC_40G_NONE;
+			break;
+		default:
+			break;
+		}
+
+		break;
+	case SPEED_50000:
+		switch (params->fec) {
+		case FEC_FORCE_MODE_NONE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_50G_NONE;
+			break;
+		case FEC_FORCE_MODE_FIRECODE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_50G_BASE_R;
+			break;
+		case FEC_FORCE_MODE_RS:
+			link_params->ext_fec_mode = ETH_EXT_FEC_50G_RS528;
+			break;
+		case FEC_FORCE_MODE_AUTO:
+			link_params->ext_fec_mode = ETH_EXT_FEC_50G_RS528 |
+						    ETH_EXT_FEC_50G_BASE_R |
+						    ETH_EXT_FEC_50G_NONE;
+			break;
+		default:
+			break;
+		}
+
+		break;
+	case SPEED_100000:
+		switch (params->fec) {
+		case FEC_FORCE_MODE_NONE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_100G_NONE;
+			break;
+		case FEC_FORCE_MODE_FIRECODE:
+			link_params->ext_fec_mode = ETH_EXT_FEC_100G_BASE_R;
+			break;
+		case FEC_FORCE_MODE_RS:
+			link_params->ext_fec_mode = ETH_EXT_FEC_100G_RS528;
+			break;
+		case FEC_FORCE_MODE_AUTO:
+			link_params->ext_fec_mode = ETH_EXT_FEC_100G_RS528 |
+						    ETH_EXT_FEC_100G_BASE_R |
+						    ETH_EXT_FEC_100G_NONE;
+			break;
+		default:
+			break;
+		}
+
+		break;
+	default:
+		break;
+	}
+}
+
 static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 {
 	struct qed_mcp_link_params *link_params;
@@ -1605,6 +1828,9 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params)
 	if (params->override_flags & QED_LINK_OVERRIDE_SPEED_FORCED_SPEED)
 		speed->forced_speed = params->forced_speed;
 
+	if (qed_mcp_is_ext_speed_supported(hwfn))
+		qed_set_ext_speed_params(link_params, params);
+
 	if (params->override_flags & QED_LINK_OVERRIDE_PAUSE_CONFIG) {
 		if (params->pause_config & QED_LINK_PAUSE_AUTONEG_ENABLE)
 			link_params->pause.autoneg = true;
@@ -1682,7 +1908,6 @@ static int qed_get_port_type(u32 media_type)
 	case MEDIA_SFP_1G_FIBER:
 	case MEDIA_XFP_FIBER:
 	case MEDIA_MODULE_FIBER:
-	case MEDIA_KR:
 		port_type = PORT_FIBRE;
 		break;
 	case MEDIA_DA_TWINAX:
@@ -1691,6 +1916,7 @@ static int qed_get_port_type(u32 media_type)
 	case MEDIA_BASE_T:
 		port_type = PORT_TP;
 		break;
+	case MEDIA_KR:
 	case MEDIA_NOT_PRESENT:
 		port_type = PORT_NONE;
 		break;
@@ -1990,9 +2216,32 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 	if (link.link_up)
 		if_link->link_up = true;
 
-	/* TODO - at the moment assume supported and advertised speed equal */
-	if (link_caps.default_speed_autoneg)
-		phylink_set(if_link->supported_caps, Autoneg);
+	if (IS_PF(hwfn->cdev) && qed_mcp_is_ext_speed_supported(hwfn)) {
+		if (link_caps.default_ext_autoneg)
+			phylink_set(if_link->supported_caps, Autoneg);
+
+		linkmode_copy(if_link->advertised_caps, if_link->supported_caps);
+
+		if (params.ext_speed.autoneg)
+			phylink_set(if_link->advertised_caps, Autoneg);
+		else
+			phylink_clear(if_link->advertised_caps, Autoneg);
+
+		qed_fill_link_capability(hwfn, ptt,
+					 params.ext_speed.advertised_speeds,
+					 if_link->advertised_caps);
+	} else {
+		if (link_caps.default_speed_autoneg)
+			phylink_set(if_link->supported_caps, Autoneg);
+
+		linkmode_copy(if_link->advertised_caps, if_link->supported_caps);
+
+		if (params.speed.autoneg)
+			phylink_set(if_link->advertised_caps, Autoneg);
+		else
+			phylink_clear(if_link->advertised_caps, Autoneg);
+	}
+
 	if (params.pause.autoneg ||
 	    (params.pause.forced_rx && params.pause.forced_tx))
 		phylink_set(if_link->supported_caps, Asym_Pause);
@@ -2000,13 +2249,6 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 	    params.pause.forced_tx)
 		phylink_set(if_link->supported_caps, Pause);
 
-	linkmode_copy(if_link->advertised_caps, if_link->supported_caps);
-
-	if (params.speed.autoneg)
-		phylink_set(if_link->advertised_caps, Autoneg);
-	else
-		phylink_clear(if_link->advertised_caps, Autoneg);
-
 	if_link->sup_fec = link_caps.fec_default;
 	if_link->active_fec = params.fec;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 78c0d3a2d164..988d84564849 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1476,6 +1476,7 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	struct qed_mcp_mb_params mb_params;
 	struct eth_phy_cfg phy_cfg;
 	u32 cmd, fec_bit = 0;
+	u32 val, ext_speed;
 	int rc = 0;
 
 	/* Set the shmem configuration according to params */
@@ -1522,16 +1523,77 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 		SET_MFW_FIELD(phy_cfg.fec_mode, FEC_FORCE_MODE, fec_bit);
 	}
 
+	if (p_hwfn->mcp_info->capabilities &
+	    FW_MB_PARAM_FEATURE_SUPPORT_EXT_SPEED_FEC_CONTROL) {
+		ext_speed = 0;
+		if (params->ext_speed.autoneg)
+			ext_speed |= ETH_EXT_SPEED_AN;
+
+		val = params->ext_speed.forced_speed;
+		if (val & QED_EXT_SPEED_1G)
+			ext_speed |= ETH_EXT_SPEED_1G;
+		if (val & QED_EXT_SPEED_10G)
+			ext_speed |= ETH_EXT_SPEED_10G;
+		if (val & QED_EXT_SPEED_20G)
+			ext_speed |= ETH_EXT_SPEED_20G;
+		if (val & QED_EXT_SPEED_25G)
+			ext_speed |= ETH_EXT_SPEED_25G;
+		if (val & QED_EXT_SPEED_40G)
+			ext_speed |= ETH_EXT_SPEED_40G;
+		if (val & QED_EXT_SPEED_50G_R)
+			ext_speed |= ETH_EXT_SPEED_50G_BASE_R;
+		if (val & QED_EXT_SPEED_50G_R2)
+			ext_speed |= ETH_EXT_SPEED_50G_BASE_R2;
+		if (val & QED_EXT_SPEED_100G_R2)
+			ext_speed |= ETH_EXT_SPEED_100G_BASE_R2;
+		if (val & QED_EXT_SPEED_100G_R4)
+			ext_speed |= ETH_EXT_SPEED_100G_BASE_R4;
+		if (val & QED_EXT_SPEED_100G_P4)
+			ext_speed |= ETH_EXT_SPEED_100G_BASE_P4;
+
+		SET_MFW_FIELD(phy_cfg.extended_speed, ETH_EXT_SPEED,
+			      ext_speed);
+
+		ext_speed = 0;
+
+		val = params->ext_speed.advertised_speeds;
+		if (val & QED_EXT_SPEED_MASK_1G)
+			ext_speed |= ETH_EXT_ADV_SPEED_1G;
+		if (val & QED_EXT_SPEED_MASK_10G)
+			ext_speed |= ETH_EXT_ADV_SPEED_10G;
+		if (val & QED_EXT_SPEED_MASK_20G)
+			ext_speed |= ETH_EXT_ADV_SPEED_20G;
+		if (val & QED_EXT_SPEED_MASK_25G)
+			ext_speed |= ETH_EXT_ADV_SPEED_25G;
+		if (val & QED_EXT_SPEED_MASK_40G)
+			ext_speed |= ETH_EXT_ADV_SPEED_40G;
+		if (val & QED_EXT_SPEED_MASK_50G_R)
+			ext_speed |= ETH_EXT_ADV_SPEED_50G_BASE_R;
+		if (val & QED_EXT_SPEED_MASK_50G_R2)
+			ext_speed |= ETH_EXT_ADV_SPEED_50G_BASE_R2;
+		if (val & QED_EXT_SPEED_MASK_100G_R2)
+			ext_speed |= ETH_EXT_ADV_SPEED_100G_BASE_R2;
+		if (val & QED_EXT_SPEED_MASK_100G_R4)
+			ext_speed |= ETH_EXT_ADV_SPEED_100G_BASE_R4;
+		if (val & QED_EXT_SPEED_MASK_100G_P4)
+			ext_speed |= ETH_EXT_ADV_SPEED_100G_BASE_P4;
+
+		phy_cfg.extended_speed |= ext_speed;
+
+		SET_MFW_FIELD(phy_cfg.fec_mode, FEC_EXTENDED_MODE,
+			      params->ext_fec_mode);
+	}
+
 	p_hwfn->b_drv_link_init = b_up;
 
 	if (b_up) {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
-			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, FEC 0x%08x\n",
+			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, Adv. Speed 0x%08x, Loopback 0x%08x, FEC 0x%08x, Ext. Speed 0x%08x\n",
 			   phy_cfg.speed, phy_cfg.pause, phy_cfg.adv_speed,
-			   phy_cfg.loopback_mode, phy_cfg.fec_mode);
+			   phy_cfg.loopback_mode, phy_cfg.fec_mode,
+			   phy_cfg.extended_speed);
 	} else {
-		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
-			   "Resetting link\n");
+		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK, "Resetting link\n");
 	}
 
 	memset(&mb_params, 0, sizeof(mb_params));
@@ -3838,6 +3900,10 @@ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		   DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK |
 		   DRV_MB_PARAM_FEATURE_SUPPORT_PORT_FEC_CONTROL;
 
+	if (QED_IS_E5(p_hwfn->cdev))
+		features |=
+		    DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EXT_SPEED_FEC_CONTROL;
+
 	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_FEATURE_SUPPORT,
 			   features, &mcp_resp, &mcp_param);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index ea956c43e596..8edb450d0abf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -17,8 +17,31 @@
 
 struct qed_mcp_link_speed_params {
 	bool					autoneg;
+
 	u32					advertised_speeds;
+#define QED_EXT_SPEED_MASK_RES			0x1
+#define QED_EXT_SPEED_MASK_1G			0x2
+#define QED_EXT_SPEED_MASK_10G			0x4
+#define QED_EXT_SPEED_MASK_20G			0x8
+#define QED_EXT_SPEED_MASK_25G			0x10
+#define QED_EXT_SPEED_MASK_40G			0x20
+#define QED_EXT_SPEED_MASK_50G_R		0x40
+#define QED_EXT_SPEED_MASK_50G_R2		0x80
+#define QED_EXT_SPEED_MASK_100G_R2		0x100
+#define QED_EXT_SPEED_MASK_100G_R4		0x200
+#define QED_EXT_SPEED_MASK_100G_P4		0x400
+
 	u32					forced_speed;	   /* In Mb/s */
+#define QED_EXT_SPEED_1G			0x1
+#define QED_EXT_SPEED_10G			0x2
+#define QED_EXT_SPEED_20G			0x4
+#define QED_EXT_SPEED_25G			0x8
+#define QED_EXT_SPEED_40G			0x10
+#define QED_EXT_SPEED_50G_R			0x20
+#define QED_EXT_SPEED_50G_R2			0x40
+#define QED_EXT_SPEED_100G_R2			0x80
+#define QED_EXT_SPEED_100G_R4			0x100
+#define QED_EXT_SPEED_100G_P4			0x200
 };
 
 struct qed_mcp_link_pause_params {
@@ -39,6 +62,9 @@ struct qed_mcp_link_params {
 	u32					loopback_mode;
 	struct qed_link_eee_params		eee;
 	u32					fec;
+
+	struct qed_mcp_link_speed_params	ext_speed;
+	u32					ext_fec_mode;
 };
 
 struct qed_mcp_link_capabilities {
@@ -48,6 +74,11 @@ struct qed_mcp_link_capabilities {
 	enum qed_mcp_eee_mode			default_eee;
 	u32					eee_lpi_timer;
 	u8					eee_speed_caps;
+
+	u32					default_ext_speed_caps;
+	u32					default_ext_autoneg;
+	u32					default_ext_speed;
+	u32					default_ext_fec;
 };
 
 struct qed_mcp_link_state {
@@ -750,6 +781,20 @@ struct qed_drv_tlv_hdr {
 	u8 tlv_flags;
 };
 
+/**
+ * qed_mcp_is_ext_speed_supported() - Check if management firmware supports
+ *                                    extended speeds.
+ * @p_hwfn: HW device data.
+ *
+ * Return: true if supported, false otherwise.
+ */
+static inline bool
+qed_mcp_is_ext_speed_supported(const struct qed_hwfn *p_hwfn)
+{
+	return !!(p_hwfn->mcp_info->capabilities &
+		  FW_MB_PARAM_FEATURE_SUPPORT_EXT_SPEED_FEC_CONTROL);
+}
+
 /**
  * @brief Initialize the interface with the MCP
  *
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 2e780159a5fb..a5c6854343e6 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -594,6 +594,7 @@ enum qed_hw_err_type {
 enum qed_dev_type {
 	QED_DEV_TYPE_BB,
 	QED_DEV_TYPE_AH,
+	QED_DEV_TYPE_E5,
 };
 
 struct qed_dev_info {
-- 
cgit v1.2.3


From 5fbff813a4a328b730cb117027c43a4ae9d8b6c0 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 7 Jul 2020 22:12:05 +0200
Subject: dma-fence: basic lockdep annotations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Design is similar to the lockdep annotations for workers, but with
some twists:

- We use a read-lock for the execution/worker/completion side, so that
  this explicit annotation can be more liberally sprinkled around.
  With read locks lockdep isn't going to complain if the read-side
  isn't nested the same way under all circumstances, so ABBA deadlocks
  are ok. Which they are, since this is an annotation only.

- We're using non-recursive lockdep read lock mode, since in recursive
  read lock mode lockdep does not catch read side hazards. And we
  _very_ much want read side hazards to be caught. For full details of
  this limitation see

  commit e91498589746065e3ae95d9a00b068e525eec34f
  Author: Peter Zijlstra <peterz@infradead.org>
  Date:   Wed Aug 23 13:13:11 2017 +0200

      locking/lockdep/selftests: Add mixed read-write ABBA tests

- To allow nesting of the read-side explicit annotations we explicitly
  keep track of the nesting. lock_is_held() allows us to do that.

- The wait-side annotation is a write lock, and entirely done within
  dma_fence_wait() for everyone by default.

- To be able to freely annotate helper functions I want to make it ok
  to call dma_fence_begin/end_signalling from soft/hardirq context.
  First attempt was using the hardirq locking context for the write
  side in lockdep, but this forces all normal spinlocks nested within
  dma_fence_begin/end_signalling to be spinlocks. That bollocks.

  The approach now is to simple check in_atomic(), and for these cases
  entirely rely on the might_sleep() check in dma_fence_wait(). That
  will catch any wrong nesting against spinlocks from soft/hardirq
  contexts.

The idea here is that every code path that's critical for eventually
signalling a dma_fence should be annotated with
dma_fence_begin/end_signalling. The annotation ideally starts right
after a dma_fence is published (added to a dma_resv, exposed as a
sync_file fd, attached to a drm_syncobj fd, or anything else that
makes the dma_fence visible to other kernel threads), up to and
including the dma_fence_wait(). Examples are irq handlers, the
scheduler rt threads, the tail of execbuf (after the corresponding
fences are visible), any workers that end up signalling dma_fences and
really anything else. Not annotated should be code paths that only
complete fences opportunistically as the gpu progresses, like e.g.
shrinker/eviction code.

The main class of deadlocks this is supposed to catch are:

Thread A:

	mutex_lock(A);
	mutex_unlock(A);

	dma_fence_signal();

Thread B:

	mutex_lock(A);
	dma_fence_wait();
	mutex_unlock(A);

Thread B is blocked on A signalling the fence, but A never gets around
to that because it cannot acquire the lock A.

Note that dma_fence_wait() is allowed to be nested within
dma_fence_begin/end_signalling sections. To allow this to happen the
read lock needs to be upgraded to a write lock, which means that any
other lock is acquired between the dma_fence_begin_signalling() call and
the call to dma_fence_wait(), and still held, this will result in an
immediate lockdep complaint. The only other option would be to not
annotate such calls, defeating the point. Therefore these annotations
cannot be sprinkled over the code entirely mindless to avoid false
positives.

Originally I hope that the cross-release lockdep extensions would
alleviate the need for explicit annotations:

https://lwn.net/Articles/709849/

But there's a few reasons why that's not an option:

- It's not happening in upstream, since it got reverted due to too
  many false positives:

	commit e966eaeeb623f09975ef362c2866fae6f86844f9
	Author: Ingo Molnar <mingo@kernel.org>
	Date:   Tue Dec 12 12:31:16 2017 +0100

	    locking/lockdep: Remove the cross-release locking checks

	    This code (CONFIG_LOCKDEP_CROSSRELEASE=y and CONFIG_LOCKDEP_COMPLETIONS=y),
	    while it found a number of old bugs initially, was also causing too many
	    false positives that caused people to disable lockdep - which is arguably
	    a worse overall outcome.

- cross-release uses the complete() call to annotate the end of
  critical sections, for dma_fence that would be dma_fence_signal().
  But we do not want all dma_fence_signal() calls to be treated as
  critical, since many are opportunistic cleanup of gpu requests. If
  these get stuck there's still the main completion interrupt and
  workers who can unblock everyone. Automatically annotating all
  dma_fence_signal() calls would hence cause false positives.

- cross-release had some educated guesses for when a critical section
  starts, like fresh syscall or fresh work callback. This would again
  cause false positives without explicit annotations, since for
  dma_fence the critical sections only starts when we publish a fence.

- Furthermore there can be cases where a thread never does a
  dma_fence_signal, but is still critical for reaching completion of
  fences. One example would be a scheduler kthread which picks up jobs
  and pushes them into hardware, where the interrupt handler or
  another completion thread calls dma_fence_signal(). But if the
  scheduler thread hangs, then all the fences hang, hence we need to
  manually annotate it. cross-release aimed to solve this by chaining
  cross-release dependencies, but the dependency from scheduler thread
  to the completion interrupt handler goes through hw where
  cross-release code can't observe it.

In short, without manual annotations and careful review of the start
and end of critical sections, cross-relese dependency tracking doesn't
work. We need explicit annotations.

v2: handle soft/hardirq ctx better against write side and dont forget
EXPORT_SYMBOL, drivers can't use this otherwise.

v3: Kerneldoc.

v4: Some spelling fixes from Mika

v5: Amend commit message to explain in detail why cross-release isn't
the solution.

v6: Pull out misplaced .rst hunk.

Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Thomas Hellstrom <thomas.hellstrom@intel.com>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: linux-rdma@vger.kernel.org
Cc: amd-gfx@lists.freedesktop.org
Cc: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200707201229.472834-2-daniel.vetter@ffwll.ch
---
 Documentation/driver-api/dma-buf.rst |   6 ++
 drivers/dma-buf/dma-fence.c          | 161 +++++++++++++++++++++++++++++++++++
 include/linux/dma-fence.h            |  12 +++
 3 files changed, 179 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 7fb7b661febd..05d856131140 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -133,6 +133,12 @@ DMA Fences
 .. kernel-doc:: drivers/dma-buf/dma-fence.c
    :doc: DMA fences overview
 
+DMA Fence Signalling Annotations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/dma-buf/dma-fence.c
+   :doc: fence signalling annotation
+
 DMA Fences Functions Reference
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 656e9ac2d028..0005bc002529 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -110,6 +110,160 @@ u64 dma_fence_context_alloc(unsigned num)
 }
 EXPORT_SYMBOL(dma_fence_context_alloc);
 
+/**
+ * DOC: fence signalling annotation
+ *
+ * Proving correctness of all the kernel code around &dma_fence through code
+ * review and testing is tricky for a few reasons:
+ *
+ * * It is a cross-driver contract, and therefore all drivers must follow the
+ *   same rules for lock nesting order, calling contexts for various functions
+ *   and anything else significant for in-kernel interfaces. But it is also
+ *   impossible to test all drivers in a single machine, hence brute-force N vs.
+ *   N testing of all combinations is impossible. Even just limiting to the
+ *   possible combinations is infeasible.
+ *
+ * * There is an enormous amount of driver code involved. For render drivers
+ *   there's the tail of command submission, after fences are published,
+ *   scheduler code, interrupt and workers to process job completion,
+ *   and timeout, gpu reset and gpu hang recovery code. Plus for integration
+ *   with core mm with have &mmu_notifier, respectively &mmu_interval_notifier,
+ *   and &shrinker. For modesetting drivers there's the commit tail functions
+ *   between when fences for an atomic modeset are published, and when the
+ *   corresponding vblank completes, including any interrupt processing and
+ *   related workers. Auditing all that code, across all drivers, is not
+ *   feasible.
+ *
+ * * Due to how many other subsystems are involved and the locking hierarchies
+ *   this pulls in there is extremely thin wiggle-room for driver-specific
+ *   differences. &dma_fence interacts with almost all of the core memory
+ *   handling through page fault handlers via &dma_resv, dma_resv_lock() and
+ *   dma_resv_unlock(). On the other side it also interacts through all
+ *   allocation sites through &mmu_notifier and &shrinker.
+ *
+ * Furthermore lockdep does not handle cross-release dependencies, which means
+ * any deadlocks between dma_fence_wait() and dma_fence_signal() can't be caught
+ * at runtime with some quick testing. The simplest example is one thread
+ * waiting on a &dma_fence while holding a lock::
+ *
+ *     lock(A);
+ *     dma_fence_wait(B);
+ *     unlock(A);
+ *
+ * while the other thread is stuck trying to acquire the same lock, which
+ * prevents it from signalling the fence the previous thread is stuck waiting
+ * on::
+ *
+ *     lock(A);
+ *     unlock(A);
+ *     dma_fence_signal(B);
+ *
+ * By manually annotating all code relevant to signalling a &dma_fence we can
+ * teach lockdep about these dependencies, which also helps with the validation
+ * headache since now lockdep can check all the rules for us::
+ *
+ *    cookie = dma_fence_begin_signalling();
+ *    lock(A);
+ *    unlock(A);
+ *    dma_fence_signal(B);
+ *    dma_fence_end_signalling(cookie);
+ *
+ * For using dma_fence_begin_signalling() and dma_fence_end_signalling() to
+ * annotate critical sections the following rules need to be observed:
+ *
+ * * All code necessary to complete a &dma_fence must be annotated, from the
+ *   point where a fence is accessible to other threads, to the point where
+ *   dma_fence_signal() is called. Un-annotated code can contain deadlock issues,
+ *   and due to the very strict rules and many corner cases it is infeasible to
+ *   catch these just with review or normal stress testing.
+ *
+ * * &struct dma_resv deserves a special note, since the readers are only
+ *   protected by rcu. This means the signalling critical section starts as soon
+ *   as the new fences are installed, even before dma_resv_unlock() is called.
+ *
+ * * The only exception are fast paths and opportunistic signalling code, which
+ *   calls dma_fence_signal() purely as an optimization, but is not required to
+ *   guarantee completion of a &dma_fence. The usual example is a wait IOCTL
+ *   which calls dma_fence_signal(), while the mandatory completion path goes
+ *   through a hardware interrupt and possible job completion worker.
+ *
+ * * To aid composability of code, the annotations can be freely nested, as long
+ *   as the overall locking hierarchy is consistent. The annotations also work
+ *   both in interrupt and process context. Due to implementation details this
+ *   requires that callers pass an opaque cookie from
+ *   dma_fence_begin_signalling() to dma_fence_end_signalling().
+ *
+ * * Validation against the cross driver contract is implemented by priming
+ *   lockdep with the relevant hierarchy at boot-up. This means even just
+ *   testing with a single device is enough to validate a driver, at least as
+ *   far as deadlocks with dma_fence_wait() against dma_fence_signal() are
+ *   concerned.
+ */
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map	dma_fence_lockdep_map = {
+	.name = "dma_fence_map"
+};
+
+/**
+ * dma_fence_begin_signalling - begin a critical DMA fence signalling section
+ *
+ * Drivers should use this to annotate the beginning of any code section
+ * required to eventually complete &dma_fence by calling dma_fence_signal().
+ *
+ * The end of these critical sections are annotated with
+ * dma_fence_end_signalling().
+ *
+ * Returns:
+ *
+ * Opaque cookie needed by the implementation, which needs to be passed to
+ * dma_fence_end_signalling().
+ */
+bool dma_fence_begin_signalling(void)
+{
+	/* explicitly nesting ... */
+	if (lock_is_held_type(&dma_fence_lockdep_map, 1))
+		return true;
+
+	/* rely on might_sleep check for soft/hardirq locks */
+	if (in_atomic())
+		return true;
+
+	/* ... and non-recursive readlock */
+	lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _RET_IP_);
+
+	return false;
+}
+EXPORT_SYMBOL(dma_fence_begin_signalling);
+
+/**
+ * dma_fence_end_signalling - end a critical DMA fence signalling section
+ *
+ * Closes a critical section annotation opened by dma_fence_begin_signalling().
+ */
+void dma_fence_end_signalling(bool cookie)
+{
+	if (cookie)
+		return;
+
+	lock_release(&dma_fence_lockdep_map, _RET_IP_);
+}
+EXPORT_SYMBOL(dma_fence_end_signalling);
+
+void __dma_fence_might_wait(void)
+{
+	bool tmp;
+
+	tmp = lock_is_held_type(&dma_fence_lockdep_map, 1);
+	if (tmp)
+		lock_release(&dma_fence_lockdep_map, _THIS_IP_);
+	lock_map_acquire(&dma_fence_lockdep_map);
+	lock_map_release(&dma_fence_lockdep_map);
+	if (tmp)
+		lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _THIS_IP_);
+}
+#endif
+
+
 /**
  * dma_fence_signal_locked - signal completion of a fence
  * @fence: the fence to signal
@@ -170,14 +324,19 @@ int dma_fence_signal(struct dma_fence *fence)
 {
 	unsigned long flags;
 	int ret;
+	bool tmp;
 
 	if (!fence)
 		return -EINVAL;
 
+	tmp = dma_fence_begin_signalling();
+
 	spin_lock_irqsave(fence->lock, flags);
 	ret = dma_fence_signal_locked(fence);
 	spin_unlock_irqrestore(fence->lock, flags);
 
+	dma_fence_end_signalling(tmp);
+
 	return ret;
 }
 EXPORT_SYMBOL(dma_fence_signal);
@@ -210,6 +369,8 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
 
 	might_sleep();
 
+	__dma_fence_might_wait();
+
 	trace_dma_fence_wait_start(fence);
 	if (fence->ops->wait)
 		ret = fence->ops->wait(fence, intr, timeout);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 3347c54f3a87..3f288f7db2ef 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -357,6 +357,18 @@ dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep)
 	} while (1);
 }
 
+#ifdef CONFIG_LOCKDEP
+bool dma_fence_begin_signalling(void);
+void dma_fence_end_signalling(bool cookie);
+#else
+static inline bool dma_fence_begin_signalling(void)
+{
+	return true;
+}
+static inline void dma_fence_end_signalling(bool cookie) {}
+static inline void __dma_fence_might_wait(void) {}
+#endif
+
 int dma_fence_signal(struct dma_fence *fence);
 int dma_fence_signal_locked(struct dma_fence *fence);
 signed long dma_fence_default_wait(struct dma_fence *fence,
-- 
cgit v1.2.3


From d0b9a9aef0a18e7ba473d0887e7ebd107ab84fe4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 7 Jul 2020 22:12:06 +0200
Subject: dma-fence: prime lockdep annotations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Two in one go:
- it is allowed to call dma_fence_wait() while holding a
  dma_resv_lock(). This is fundamental to how eviction works with ttm,
  so required.

- it is allowed to call dma_fence_wait() from memory reclaim contexts,
  specifically from shrinker callbacks (which i915 does), and from mmu
  notifier callbacks (which amdgpu does, and which i915 sometimes also
  does, and probably always should, but that's kinda a debate). Also
  for stuff like HMM we really need to be able to do this, or things
  get real dicey.

Consequence is that any critical path necessary to get to a
dma_fence_signal for a fence must never a) call dma_resv_lock nor b)
allocate memory with GFP_KERNEL. Also by implication of
dma_resv_lock(), no userspace faulting allowed. That's some supremely
obnoxious limitations, which is why we need to sprinkle the right
annotations to all relevant paths.

The one big locking context we're leaving out here is mmu notifiers,
added in

commit 23b68395c7c78a764e8963fc15a7cfd318bf187f
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Mon Aug 26 22:14:21 2019 +0200

    mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end

that one covers a lot of other callsites, and it's also allowed to
wait on dma-fences from mmu notifiers. But there's no ready-made
functions exposed to prime this, so I've left it out for now.

v2: Also track against mmu notifier context.

v3: kerneldoc to spec the cross-driver contract. Note that currently
i915 throws in a hard-coded 10s timeout on foreign fences (not sure
why that was done, but it's there), which is why that rule is worded
with SHOULD instead of MUST.

Also some of the mmu_notifier/shrinker rules might surprise SoC
drivers, I haven't fully audited them all. Which is infeasible anyway,
we'll need to run them with lockdep and dma-fence annotations and see
what goes boom.

v4: A spelling fix from Mika

v5: #ifdef for CONFIG_MMU_NOTIFIER. Reported by 0day. Unfortunately
this means lockdep enforcement is slightly inconsistent, it won't spot
GFP_NOIO and GFP_NOFS allocations in the wrong spot if
CONFIG_MMU_NOTIFIER is disabled in the kernel config. Oh well.

v5: Note that only drivers/gpu has a reasonable (or at least
historical) excuse to use dma_fence_wait() from shrinker and mmu
notifier callbacks. Everyone else should either have a better memory
manager model, or better hardware. This reflects discussions with
Jason Gunthorpe.

Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: kernel test robot <lkp@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com> (v4)
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Thomas Hellstrom <thomas.hellstrom@intel.com>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: linux-rdma@vger.kernel.org
Cc: amd-gfx@lists.freedesktop.org
Cc: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200707201229.472834-3-daniel.vetter@ffwll.ch
---
 Documentation/driver-api/dma-buf.rst |  6 +++++
 drivers/dma-buf/dma-fence.c          | 46 ++++++++++++++++++++++++++++++++++++
 drivers/dma-buf/dma-resv.c           |  8 +++++++
 include/linux/dma-fence.h            |  1 +
 4 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 05d856131140..f8f6decde359 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -133,6 +133,12 @@ DMA Fences
 .. kernel-doc:: drivers/dma-buf/dma-fence.c
    :doc: DMA fences overview
 
+DMA Fence Cross-Driver Contract
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/dma-buf/dma-fence.c
+   :doc: fence cross-driver contract
+
 DMA Fence Signalling Annotations
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 0005bc002529..af1d8ea926b3 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -64,6 +64,52 @@ static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1);
  *   &dma_buf.resv pointer.
  */
 
+/**
+ * DOC: fence cross-driver contract
+ *
+ * Since &dma_fence provide a cross driver contract, all drivers must follow the
+ * same rules:
+ *
+ * * Fences must complete in a reasonable time. Fences which represent kernels
+ *   and shaders submitted by userspace, which could run forever, must be backed
+ *   up by timeout and gpu hang recovery code. Minimally that code must prevent
+ *   further command submission and force complete all in-flight fences, e.g.
+ *   when the driver or hardware do not support gpu reset, or if the gpu reset
+ *   failed for some reason. Ideally the driver supports gpu recovery which only
+ *   affects the offending userspace context, and no other userspace
+ *   submissions.
+ *
+ * * Drivers may have different ideas of what completion within a reasonable
+ *   time means. Some hang recovery code uses a fixed timeout, others a mix
+ *   between observing forward progress and increasingly strict timeouts.
+ *   Drivers should not try to second guess timeout handling of fences from
+ *   other drivers.
+ *
+ * * To ensure there's no deadlocks of dma_fence_wait() against other locks
+ *   drivers should annotate all code required to reach dma_fence_signal(),
+ *   which completes the fences, with dma_fence_begin_signalling() and
+ *   dma_fence_end_signalling().
+ *
+ * * Drivers are allowed to call dma_fence_wait() while holding dma_resv_lock().
+ *   This means any code required for fence completion cannot acquire a
+ *   &dma_resv lock. Note that this also pulls in the entire established
+ *   locking hierarchy around dma_resv_lock() and dma_resv_unlock().
+ *
+ * * Drivers are allowed to call dma_fence_wait() from their &shrinker
+ *   callbacks. This means any code required for fence completion cannot
+ *   allocate memory with GFP_KERNEL.
+ *
+ * * Drivers are allowed to call dma_fence_wait() from their &mmu_notifier
+ *   respectively &mmu_interval_notifier callbacks. This means any code required
+ *   for fence completeion cannot allocate memory with GFP_NOFS or GFP_NOIO.
+ *   Only GFP_ATOMIC is permissible, which might fail.
+ *
+ * Note that only GPU drivers have a reasonable excuse for both requiring
+ * &mmu_interval_notifier and &shrinker callbacks at the same time as having to
+ * track asynchronous compute work using &dma_fence. No driver outside of
+ * drivers/gpu should ever call dma_fence_wait() in such contexts.
+ */
+
 static const char *dma_fence_stub_get_name(struct dma_fence *fence)
 {
         return "stub";
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index b45f8514dc82..07f5273207e7 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
+#include <linux/mmu_notifier.h>
 
 /**
  * DOC: Reservation Object Overview
@@ -116,6 +117,13 @@ static int __init dma_resv_lockdep(void)
 	if (ret == -EDEADLK)
 		dma_resv_lock_slow(&obj, &ctx);
 	fs_reclaim_acquire(GFP_KERNEL);
+#ifdef CONFIG_MMU_NOTIFIER
+	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
+	__dma_fence_might_wait();
+	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
+#else
+	__dma_fence_might_wait();
+#endif
 	fs_reclaim_release(GFP_KERNEL);
 	ww_mutex_unlock(&obj.lock);
 	ww_acquire_fini(&ctx);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 3f288f7db2ef..09e23adb351d 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -360,6 +360,7 @@ dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep)
 #ifdef CONFIG_LOCKDEP
 bool dma_fence_begin_signalling(void);
 void dma_fence_end_signalling(bool cookie);
+void __dma_fence_might_wait(void);
 #else
 static inline bool dma_fence_begin_signalling(void)
 {
-- 
cgit v1.2.3


From af0e5f1f47d8b7139ee446bc2367f74e4f034202 Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 1 Jul 2020 21:44:14 +0530
Subject: thermal/drivers/clock_cooling: Remove clock_cooling code

clock_cooling has no in-kernel users. It has never found any use in
drivers as far as I can tell.

Remove the code.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/aa5d5ac2589cf7b14ece882130731b4a916849a6.1593619943.git.amit.kucheria@linaro.org
---
 drivers/thermal/Kconfig         |  10 -
 drivers/thermal/Makefile        |   3 -
 drivers/thermal/clock_cooling.c | 445 ----------------------------------------
 include/linux/clock_cooling.h   |  57 -----
 4 files changed, 515 deletions(-)
 delete mode 100644 drivers/thermal/clock_cooling.c
 delete mode 100644 include/linux/clock_cooling.h

(limited to 'include/linux')

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 07983bef8d6a..13991d68c844 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -190,16 +190,6 @@ config CPU_IDLE_THERMAL
 	  idle cycle.
 endif
 
-config CLOCK_THERMAL
-	bool "Generic clock cooling support"
-	depends on COMMON_CLK
-	depends on PM_OPP
-	help
-	  This entry implements the generic clock cooling mechanism through
-	  frequency clipping. Typically used to cool off co-processors. The
-	  device that is configured to use this cooling mechanism will be
-	  controlled to reduce clock frequency whenever temperature is high.
-
 config DEVFREQ_THERMAL
 	bool "Generic device cooling support"
 	depends on PM_DEVFREQ
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 589f6fb0d381..b8d96d26f9ec 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -25,9 +25,6 @@ thermal_sys-$(CONFIG_THERMAL_GOV_POWER_ALLOCATOR)	+= gov_power_allocator.o
 thermal_sys-$(CONFIG_CPU_FREQ_THERMAL)	+= cpufreq_cooling.o
 thermal_sys-$(CONFIG_CPU_IDLE_THERMAL)	+= cpuidle_cooling.o
 
-# clock cooling
-thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
-
 # devfreq cooling
 thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
 
diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c
deleted file mode 100644
index 56cb1f46a428..000000000000
--- a/drivers/thermal/clock_cooling.c
+++ /dev/null
@@ -1,445 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  drivers/thermal/clock_cooling.c
- *
- *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
- *
- *  Copyright (C) 2013	Texas Instruments Inc.
- *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
- *
- *  Highly based on cpufreq_cooling.c.
- *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
- *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
- */
-#include <linux/clk.h>
-#include <linux/clock_cooling.h>
-#include <linux/cpufreq.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/idr.h>
-#include <linux/mutex.h>
-#include <linux/pm_opp.h>
-#include <linux/slab.h>
-#include <linux/thermal.h>
-
-/**
- * struct clock_cooling_device - data for cooling device with clock
- * @id: unique integer value corresponding to each clock_cooling_device
- *	registered.
- * @dev: struct device pointer to the device being used to cool off using
- *       clock frequencies.
- * @cdev: thermal_cooling_device pointer to keep track of the
- *	registered cooling device.
- * @clk_rate_change_nb: reference to notifier block used to receive clock
- *                      rate changes.
- * @freq_table: frequency table used to keep track of available frequencies.
- * @clock_state: integer value representing the current state of clock
- *	cooling	devices.
- * @clock_val: integer value representing the absolute value of the clipped
- *	frequency.
- * @clk: struct clk reference used to enforce clock limits.
- * @lock: mutex lock to protect this struct.
- *
- * This structure is required for keeping information of each
- * clock_cooling_device registered. In order to prevent corruption of this a
- * mutex @lock is used.
- */
-struct clock_cooling_device {
-	int id;
-	struct device *dev;
-	struct thermal_cooling_device *cdev;
-	struct notifier_block clk_rate_change_nb;
-	struct cpufreq_frequency_table *freq_table;
-	unsigned long clock_state;
-	unsigned long clock_val;
-	struct clk *clk;
-	struct mutex lock; /* lock to protect the content of this struct */
-};
-#define to_clock_cooling_device(x) \
-		container_of(x, struct clock_cooling_device, clk_rate_change_nb)
-static DEFINE_IDA(clock_ida);
-
-/* Below code defines functions to be used for clock as cooling device */
-
-enum clock_cooling_property {
-	GET_LEVEL,
-	GET_FREQ,
-	GET_MAXL,
-};
-
-/**
- * clock_cooling_get_property - fetch a property of interest for a give cpu.
- * @ccdev: clock cooling device reference
- * @input: query parameter
- * @output: query return
- * @property: type of query (frequency, level, max level)
- *
- * This is the common function to
- * 1. get maximum clock cooling states
- * 2. translate frequency to cooling state
- * 3. translate cooling state to frequency
- * Note that the code may be not in good shape
- * but it is written in this way in order to:
- * a) reduce duplicate code as most of the code can be shared.
- * b) make sure the logic is consistent when translating between
- *    cooling states and frequencies.
- *
- * Return: 0 on success, -EINVAL when invalid parameters are passed.
- */
-static int clock_cooling_get_property(struct clock_cooling_device *ccdev,
-				      unsigned long input,
-				      unsigned long *output,
-				      enum clock_cooling_property property)
-{
-	int i;
-	unsigned long max_level = 0, level = 0;
-	unsigned int freq = CPUFREQ_ENTRY_INVALID;
-	int descend = -1;
-	struct cpufreq_frequency_table *pos, *table = ccdev->freq_table;
-
-	if (!output)
-		return -EINVAL;
-
-	if (!table)
-		return -EINVAL;
-
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* get the frequency order */
-		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
-			descend = freq > pos->frequency;
-
-		freq = pos->frequency;
-		max_level++;
-	}
-
-	/* No valid cpu frequency entry */
-	if (max_level == 0)
-		return -EINVAL;
-
-	/* max_level is an index, not a counter */
-	max_level--;
-
-	/* get max level */
-	if (property == GET_MAXL) {
-		*output = max_level;
-		return 0;
-	}
-
-	if (property == GET_FREQ)
-		level = descend ? input : (max_level - input);
-
-	i = 0;
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* now we have a valid frequency entry */
-		freq = pos->frequency;
-
-		if (property == GET_LEVEL && (unsigned int)input == freq) {
-			/* get level by frequency */
-			*output = descend ? i : (max_level - i);
-			return 0;
-		}
-		if (property == GET_FREQ && level == i) {
-			/* get frequency by level */
-			*output = freq;
-			return 0;
-		}
-		i++;
-	}
-
-	return -EINVAL;
-}
-
-/**
- * clock_cooling_get_level - return the cooling level of given clock cooling.
- * @cdev: reference of a thermal cooling device of used as clock cooling device
- * @freq: the frequency of interest
- *
- * This function will match the cooling level corresponding to the
- * requested @freq and return it.
- *
- * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID
- * otherwise.
- */
-unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
-				      unsigned long freq)
-{
-	struct clock_cooling_device *ccdev = cdev->devdata;
-	unsigned long val;
-
-	if (clock_cooling_get_property(ccdev, (unsigned long)freq, &val,
-				       GET_LEVEL))
-		return THERMAL_CSTATE_INVALID;
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(clock_cooling_get_level);
-
-/**
- * clock_cooling_get_frequency - get the absolute value of frequency from level.
- * @ccdev: clock cooling device reference
- * @level: cooling level
- *
- * This function matches cooling level with frequency. Based on a cooling level
- * of frequency, equals cooling state of cpu cooling device, it will return
- * the corresponding frequency.
- *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
- *
- * Return: 0 on error, the corresponding frequency otherwise.
- */
-static unsigned long
-clock_cooling_get_frequency(struct clock_cooling_device *ccdev,
-			    unsigned long level)
-{
-	int ret = 0;
-	unsigned long freq;
-
-	ret = clock_cooling_get_property(ccdev, level, &freq, GET_FREQ);
-	if (ret)
-		return 0;
-
-	return freq;
-}
-
-/**
- * clock_cooling_apply - function to apply frequency clipping.
- * @ccdev: clock_cooling_device pointer containing frequency clipping data.
- * @cooling_state: value of the cooling state.
- *
- * Function used to make sure the clock layer is aware of current thermal
- * limits. The limits are applied by updating the clock rate in case it is
- * higher than the corresponding frequency based on the requested cooling_state.
- *
- * Return: 0 on success, an error code otherwise (-EINVAL in case wrong
- * cooling state).
- */
-static int clock_cooling_apply(struct clock_cooling_device *ccdev,
-			       unsigned long cooling_state)
-{
-	unsigned long clip_freq, cur_freq;
-	int ret = 0;
-
-	/* Here we write the clipping */
-	/* Check if the old cooling action is same as new cooling action */
-	if (ccdev->clock_state == cooling_state)
-		return 0;
-
-	clip_freq = clock_cooling_get_frequency(ccdev, cooling_state);
-	if (!clip_freq)
-		return -EINVAL;
-
-	cur_freq = clk_get_rate(ccdev->clk);
-
-	mutex_lock(&ccdev->lock);
-	ccdev->clock_state = cooling_state;
-	ccdev->clock_val = clip_freq;
-	/* enforce clock level */
-	if (cur_freq > clip_freq)
-		ret = clk_set_rate(ccdev->clk, clip_freq);
-	mutex_unlock(&ccdev->lock);
-
-	return ret;
-}
-
-/**
- * clock_cooling_clock_notifier - notifier callback on clock rate changes.
- * @nb:	struct notifier_block * with callback info.
- * @event: value showing clock event for which this function invoked.
- * @data: callback-specific data
- *
- * Callback to hijack the notification on clock transition.
- * Every time there is a clock change, we intercept all pre change events
- * and block the transition in case the new rate infringes thermal limits.
- *
- * Return: NOTIFY_DONE (success) or NOTIFY_BAD (new_rate > thermal limit).
- */
-static int clock_cooling_clock_notifier(struct notifier_block *nb,
-					unsigned long event, void *data)
-{
-	struct clk_notifier_data *ndata = data;
-	struct clock_cooling_device *ccdev = to_clock_cooling_device(nb);
-
-	switch (event) {
-	case PRE_RATE_CHANGE:
-		/*
-		 * checks on current state
-		 * TODO: current method is not best we can find as it
-		 * allows possibly voltage transitions, in case DVFS
-		 * layer is also hijacking clock pre notifications.
-		 */
-		if (ndata->new_rate > ccdev->clock_val)
-			return NOTIFY_BAD;
-		/* fall through */
-	case POST_RATE_CHANGE:
-	case ABORT_RATE_CHANGE:
-	default:
-		return NOTIFY_DONE;
-	}
-}
-
-/* clock cooling device thermal callback functions are defined below */
-
-/**
- * clock_cooling_get_max_state - callback function to get the max cooling state.
- * @cdev: thermal cooling device pointer.
- * @state: fill this variable with the max cooling state.
- *
- * Callback for the thermal cooling device to return the clock
- * max cooling state.
- *
- * Return: 0 on success, an error code otherwise.
- */
-static int clock_cooling_get_max_state(struct thermal_cooling_device *cdev,
-				       unsigned long *state)
-{
-	struct clock_cooling_device *ccdev = cdev->devdata;
-	unsigned long count = 0;
-	int ret;
-
-	ret = clock_cooling_get_property(ccdev, 0, &count, GET_MAXL);
-	if (!ret)
-		*state = count;
-
-	return ret;
-}
-
-/**
- * clock_cooling_get_cur_state - function to get the current cooling state.
- * @cdev: thermal cooling device pointer.
- * @state: fill this variable with the current cooling state.
- *
- * Callback for the thermal cooling device to return the clock
- * current cooling state.
- *
- * Return: 0 (success)
- */
-static int clock_cooling_get_cur_state(struct thermal_cooling_device *cdev,
-				       unsigned long *state)
-{
-	struct clock_cooling_device *ccdev = cdev->devdata;
-
-	*state = ccdev->clock_state;
-
-	return 0;
-}
-
-/**
- * clock_cooling_set_cur_state - function to set the current cooling state.
- * @cdev: thermal cooling device pointer.
- * @state: set this variable to the current cooling state.
- *
- * Callback for the thermal cooling device to change the clock cooling
- * current cooling state.
- *
- * Return: 0 on success, an error code otherwise.
- */
-static int clock_cooling_set_cur_state(struct thermal_cooling_device *cdev,
-				       unsigned long state)
-{
-	struct clock_cooling_device *clock_device = cdev->devdata;
-
-	return clock_cooling_apply(clock_device, state);
-}
-
-/* Bind clock callbacks to thermal cooling device ops */
-static struct thermal_cooling_device_ops const clock_cooling_ops = {
-	.get_max_state = clock_cooling_get_max_state,
-	.get_cur_state = clock_cooling_get_cur_state,
-	.set_cur_state = clock_cooling_set_cur_state,
-};
-
-/**
- * clock_cooling_register - function to create clock cooling device.
- * @dev: struct device pointer to the device used as clock cooling device.
- * @clock_name: string containing the clock used as cooling mechanism.
- *
- * This interface function registers the clock cooling device with the name
- * "thermal-clock-%x". The cooling device is based on clock frequencies.
- * The struct device is assumed to be capable of DVFS transitions.
- * The OPP layer is used to fetch and fill the available frequencies for
- * the referred device. The ordered frequency table is used to control
- * the clock cooling device cooling states and to limit clock transitions
- * based on the cooling state requested by the thermal framework.
- *
- * Return: a valid struct thermal_cooling_device pointer on success,
- * on failure, it returns a corresponding ERR_PTR().
- */
-struct thermal_cooling_device *
-clock_cooling_register(struct device *dev, const char *clock_name)
-{
-	struct thermal_cooling_device *cdev;
-	struct clock_cooling_device *ccdev = NULL;
-	char dev_name[THERMAL_NAME_LENGTH];
-	int ret = 0;
-
-	ccdev = devm_kzalloc(dev, sizeof(*ccdev), GFP_KERNEL);
-	if (!ccdev)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&ccdev->lock);
-	ccdev->dev = dev;
-	ccdev->clk = devm_clk_get(dev, clock_name);
-	if (IS_ERR(ccdev->clk))
-		return ERR_CAST(ccdev->clk);
-
-	ret = ida_simple_get(&clock_ida, 0, 0, GFP_KERNEL);
-	if (ret < 0)
-		return ERR_PTR(ret);
-	ccdev->id = ret;
-
-	snprintf(dev_name, sizeof(dev_name), "thermal-clock-%d", ccdev->id);
-
-	cdev = thermal_cooling_device_register(dev_name, ccdev,
-					       &clock_cooling_ops);
-	if (IS_ERR(cdev)) {
-		ida_simple_remove(&clock_ida, ccdev->id);
-		return ERR_PTR(-EINVAL);
-	}
-	ccdev->cdev = cdev;
-	ccdev->clk_rate_change_nb.notifier_call = clock_cooling_clock_notifier;
-
-	/* Assuming someone has already filled the opp table for this device */
-	ret = dev_pm_opp_init_cpufreq_table(dev, &ccdev->freq_table);
-	if (ret) {
-		ida_simple_remove(&clock_ida, ccdev->id);
-		return ERR_PTR(ret);
-	}
-	ccdev->clock_state = 0;
-	ccdev->clock_val = clock_cooling_get_frequency(ccdev, 0);
-
-	clk_notifier_register(ccdev->clk, &ccdev->clk_rate_change_nb);
-
-	return cdev;
-}
-EXPORT_SYMBOL_GPL(clock_cooling_register);
-
-/**
- * clock_cooling_unregister - function to remove clock cooling device.
- * @cdev: thermal cooling device pointer.
- *
- * This interface function unregisters the "thermal-clock-%x" cooling device.
- */
-void clock_cooling_unregister(struct thermal_cooling_device *cdev)
-{
-	struct clock_cooling_device *ccdev;
-
-	if (!cdev)
-		return;
-
-	ccdev = cdev->devdata;
-
-	clk_notifier_unregister(ccdev->clk, &ccdev->clk_rate_change_nb);
-	dev_pm_opp_free_cpufreq_table(ccdev->dev, &ccdev->freq_table);
-
-	thermal_cooling_device_unregister(ccdev->cdev);
-	ida_simple_remove(&clock_ida, ccdev->id);
-}
-EXPORT_SYMBOL_GPL(clock_cooling_unregister);
diff --git a/include/linux/clock_cooling.h b/include/linux/clock_cooling.h
deleted file mode 100644
index 4b0a69863656..000000000000
--- a/include/linux/clock_cooling.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  linux/include/linux/clock_cooling.h
- *
- *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
- *
- *  Copyright (C) 2013	Texas Instruments Inc.
- *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
- *
- *  Highly based on cpufreq_cooling.c.
- *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
- *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
- */
-
-#ifndef __CPU_COOLING_H__
-#define __CPU_COOLING_H__
-
-#include <linux/of.h>
-#include <linux/thermal.h>
-#include <linux/cpumask.h>
-
-#ifdef CONFIG_CLOCK_THERMAL
-/**
- * clock_cooling_register - function to create clock cooling device.
- * @dev: struct device pointer to the device used as clock cooling device.
- * @clock_name: string containing the clock used as cooling mechanism.
- */
-struct thermal_cooling_device *
-clock_cooling_register(struct device *dev, const char *clock_name);
-
-/**
- * clock_cooling_unregister - function to remove clock cooling device.
- * @cdev: thermal cooling device pointer.
- */
-void clock_cooling_unregister(struct thermal_cooling_device *cdev);
-
-unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
-				      unsigned long freq);
-#else /* !CONFIG_CLOCK_THERMAL */
-static inline struct thermal_cooling_device *
-clock_cooling_register(struct device *dev, const char *clock_name)
-{
-	return NULL;
-}
-static inline
-void clock_cooling_unregister(struct thermal_cooling_device *cdev)
-{
-}
-static inline
-unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
-				      unsigned long freq)
-{
-	return THERMAL_CSTATE_INVALID;
-}
-#endif	/* CONFIG_CLOCK_THERMAL */
-
-#endif /* __CPU_COOLING_H__ */
-- 
cgit v1.2.3


From e506ea451254ab17e0bf918ca36232fec2a9b10c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 15 Oct 2019 16:29:32 -0700
Subject: compiler.h: Split {READ,WRITE}_ONCE definitions out into rwonce.h

In preparation for allowing architectures to define their own
implementation of the READ_ONCE() macro, move the generic
{READ,WRITE}_ONCE() definitions out of the unwieldy 'linux/compiler.h'
file and into a new 'rwonce.h' header under 'asm-generic'.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/asm-generic/Kbuild    |   1 +
 include/asm-generic/barrier.h |   2 +-
 include/asm-generic/rwonce.h  | 101 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/compiler.h      |  93 +-------------------------------------
 4 files changed, 105 insertions(+), 92 deletions(-)
 create mode 100644 include/asm-generic/rwonce.h

(limited to 'include/linux')

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 44ec80e70518..74b0612601dd 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -45,6 +45,7 @@ mandatory-y += pci.h
 mandatory-y += percpu.h
 mandatory-y += pgalloc.h
 mandatory-y += preempt.h
+mandatory-y += rwonce.h
 mandatory-y += sections.h
 mandatory-y += serial.h
 mandatory-y += shmparam.h
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 2eacaf7d62f6..8116744bb82c 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,7 +13,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/compiler.h>
+#include <asm/rwonce.h>
 
 #ifndef nop
 #define nop()	asm volatile ("nop")
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
new file mode 100644
index 000000000000..87584379da43
--- /dev/null
+++ b/include/asm-generic/rwonce.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
+ *
+ * These two macros will also work on aggregate data types like structs or
+ * unions.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+#ifndef __ASM_GENERIC_RWONCE_H
+#define __ASM_GENERIC_RWONCE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler_types.h>
+#include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+
+#include <asm/barrier.h>
+
+/*
+ * Yes, this permits 64-bit accesses on 32-bit architectures. These will
+ * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
+ * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
+ * (e.g. a virtual address) and a strong prevailing wind.
+ */
+#define compiletime_assert_rwonce_type(t)					\
+	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
+		"Unsupported access size for {READ,WRITE}_ONCE().")
+
+/*
+ * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
+ * atomicity or dependency ordering guarantees. Note that this may result
+ * in tears!
+ */
+#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
+
+#define __READ_ONCE_SCALAR(x)						\
+({									\
+	__unqual_scalar_typeof(x) __x = __READ_ONCE(x);			\
+	smp_read_barrier_depends();					\
+	(typeof(x))__x;							\
+})
+
+#define READ_ONCE(x)							\
+({									\
+	compiletime_assert_rwonce_type(x);				\
+	__READ_ONCE_SCALAR(x);						\
+})
+
+#define __WRITE_ONCE(x, val)						\
+do {									\
+	*(volatile typeof(x) *)&(x) = (val);				\
+} while (0)
+
+#define WRITE_ONCE(x, val)						\
+do {									\
+	compiletime_assert_rwonce_type(x);				\
+	__WRITE_ONCE(x, val);						\
+} while (0)
+
+static __no_sanitize_or_inline
+unsigned long __read_once_word_nocheck(const void *addr)
+{
+	return __READ_ONCE(*(unsigned long *)addr);
+}
+
+/*
+ * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
+ * word from memory atomically but without telling KASAN/KCSAN. This is
+ * usually used by unwinding code when walking the stack of a running process.
+ */
+#define READ_ONCE_NOCHECK(x)						\
+({									\
+	unsigned long __x;						\
+	compiletime_assert(sizeof(x) == sizeof(__x),			\
+		"Unsupported access size for READ_ONCE_NOCHECK().");	\
+	__x = __read_once_word_nocheck(&(x));				\
+	smp_read_barrier_depends();					\
+	(typeof(x))__x;							\
+})
+
+static __no_kasan_or_inline
+unsigned long read_word_at_a_time(const void *addr)
+{
+	kasan_check_read(addr, 1);
+	return *(unsigned long *)addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_GENERIC_RWONCE_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 204e76856435..f075a3df4fe2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -230,28 +230,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
 #endif
 
-/*
- * Prevent the compiler from merging or refetching reads or writes. The
- * compiler is also forbidden from reordering successive instances of
- * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
- * particular ordering. One way to make the compiler aware of ordering is to
- * put the two invocations of READ_ONCE or WRITE_ONCE in different C
- * statements.
- *
- * These two macros will also work on aggregate data types like structs or
- * unions.
- *
- * Their two major use cases are: (1) Mediating communication between
- * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
- * mutilate accesses that either do not require ordering or that interact
- * with an explicit memory barrier or atomic instruction that provides the
- * required ordering.
- */
-#include <asm/barrier.h>
-#include <linux/kasan-checks.h>
-#include <linux/kcsan-checks.h>
-
 /**
  * data_race - mark an expression as containing intentional data races
  *
@@ -272,65 +250,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__v;								\
 })
 
-/*
- * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
- * atomicity or dependency ordering guarantees. Note that this may result
- * in tears!
- */
-#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
-
-#define __READ_ONCE_SCALAR(x)						\
-({									\
-	__unqual_scalar_typeof(x) __x = __READ_ONCE(x);			\
-	smp_read_barrier_depends();					\
-	(typeof(x))__x;							\
-})
-
-#define READ_ONCE(x)							\
-({									\
-	compiletime_assert_rwonce_type(x);				\
-	__READ_ONCE_SCALAR(x);						\
-})
-
-#define __WRITE_ONCE(x, val)						\
-do {									\
-	*(volatile typeof(x) *)&(x) = (val);				\
-} while (0)
-
-#define WRITE_ONCE(x, val)						\
-do {									\
-	compiletime_assert_rwonce_type(x);				\
-	__WRITE_ONCE(x, val);						\
-} while (0)
-
-static __no_sanitize_or_inline
-unsigned long __read_once_word_nocheck(const void *addr)
-{
-	return __READ_ONCE(*(unsigned long *)addr);
-}
-
-/*
- * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
- * word from memory atomically but without telling KASAN/KCSAN. This is
- * usually used by unwinding code when walking the stack of a running process.
- */
-#define READ_ONCE_NOCHECK(x)						\
-({									\
-	unsigned long __x;						\
-	compiletime_assert(sizeof(x) == sizeof(__x),			\
-		"Unsupported access size for READ_ONCE_NOCHECK().");	\
-	__x = __read_once_word_nocheck(&(x));				\
-	smp_read_barrier_depends();					\
-	(typeof(x))__x;							\
-})
-
-static __no_kasan_or_inline
-unsigned long read_word_at_a_time(const void *addr)
-{
-	kasan_check_read(addr, 1);
-	return *(unsigned long *)addr;
-}
-
 #endif /* __KERNEL__ */
 
 /*
@@ -395,16 +314,6 @@ static inline void *offset_to_ptr(const int *off)
 	compiletime_assert(__native_word(t),				\
 		"Need native word sized stores/loads for atomicity.")
 
-/*
- * Yes, this permits 64-bit accesses on 32-bit architectures. These will
- * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
- * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
- * (e.g. a virtual address) and a strong prevailing wind.
- */
-#define compiletime_assert_rwonce_type(t)					\
-	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
-		"Unsupported access size for {READ,WRITE}_ONCE().")
-
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
@@ -414,4 +323,6 @@ static inline void *offset_to_ptr(const int *off)
  */
 #define prevent_tail_call_optimization()	mb()
 
+#include <asm/rwonce.h>
+
 #endif /* __LINUX_COMPILER_H */
-- 
cgit v1.2.3


From 002dff36acfba3476b685a09f78ffb7c452f5951 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 10 Jul 2020 14:49:40 +0100
Subject: asm/rwonce: Don't pull <asm/barrier.h> into 'asm-generic/rwonce.h'

Now that 'smp_read_barrier_depends()' has gone the way of the Norwegian
Blue, drop the inclusion of <asm/barrier.h> in 'asm-generic/rwonce.h'.

This requires fixups to some architecture vdso headers which were
previously relying on 'asm/barrier.h' coming in via 'linux/compiler.h'.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm/include/asm/vdso/gettimeofday.h          | 1 +
 arch/arm64/include/asm/vdso/compat_gettimeofday.h | 1 +
 arch/arm64/include/asm/vdso/gettimeofday.h        | 1 +
 arch/riscv/include/asm/vdso/gettimeofday.h        | 1 +
 include/asm-generic/rwonce.h                      | 2 --
 include/linux/nospec.h                            | 2 ++
 6 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 36dc18553ed8..1b207cf07697 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/errno.h>
 #include <asm/unistd.h>
 #include <asm/vdso/cp15.h>
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index b6907ae78e53..bcf7649999a4 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
 
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index afba6ba332f8..127fa63893e2 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 
 #define VDSO_HAS_CLOCK_GETRES		1
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index c8e818688ec1..3099362d9f26 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -4,6 +4,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/csr.h>
 #include <uapi/linux/time.h>
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
index 3a7f737c77bd..8d0a6280e982 100644
--- a/include/asm-generic/rwonce.h
+++ b/include/asm-generic/rwonce.h
@@ -26,8 +26,6 @@
 #include <linux/kasan-checks.h>
 #include <linux/kcsan-checks.h>
 
-#include <asm/barrier.h>
-
 /*
  * Yes, this permits 64-bit accesses on 32-bit architectures. These will
  * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index 0c5ef54fd416..c1e79f72cd89 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -5,6 +5,8 @@
 
 #ifndef _LINUX_NOSPEC_H
 #define _LINUX_NOSPEC_H
+
+#include <linux/compiler.h>
 #include <asm/barrier.h>
 
 struct task_struct;
-- 
cgit v1.2.3


From c6cd2e011655aead2097273a04350f52429a1a8d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 7 Nov 2019 14:46:59 +0000
Subject: include/linux: Remove smp_read_barrier_depends() from comments

smp_read_barrier_depends() doesn't exist any more, so reword the two
comments that mention it to refer to "dependency ordering" instead.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/percpu-refcount.h | 2 +-
 include/linux/ptr_ring.h        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 22d9d183950d..87d8a38bdea1 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -155,7 +155,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	 * between contaminating the pointer value, meaning that
 	 * READ_ONCE() is required when fetching it.
 	 *
-	 * The smp_read_barrier_depends() implied by READ_ONCE() pairs
+	 * The dependency ordering from the READ_ONCE() pairs
 	 * with smp_store_release() in __percpu_ref_switch_to_percpu().
 	 */
 	percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 417db0a79a62..808f9d3ee546 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -107,7 +107,7 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 		return -ENOSPC;
 
 	/* Make sure the pointer we are storing points to a valid data. */
-	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+	/* Pairs with the dependency ordering in __ptr_ring_consume. */
 	smp_wmb();
 
 	WRITE_ONCE(r->queue[r->producer++], ptr);
-- 
cgit v1.2.3


From eb5c2d4b45e3d2d5d052ea6b8f1463976b1020d5 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 21 Jul 2020 09:54:15 +0100
Subject: compiler.h: Move compiletime_assert() macros into compiler_types.h

The kernel test robot reports that moving READ_ONCE() out into its own
header breaks a W=1 build for parisc, which is relying on the definition
of compiletime_assert() being available:

  | In file included from ./arch/parisc/include/generated/asm/rwonce.h:1,
  |                  from ./include/asm-generic/barrier.h:16,
  |                  from ./arch/parisc/include/asm/barrier.h:29,
  |                  from ./arch/parisc/include/asm/atomic.h:11,
  |                  from ./include/linux/atomic.h:7,
  |                  from kernel/locking/percpu-rwsem.c:2:
  | ./arch/parisc/include/asm/atomic.h: In function 'atomic_read':
  | ./include/asm-generic/rwonce.h:36:2: error: implicit declaration of function 'compiletime_assert' [-Werror=implicit-function-declaration]
  |    36 |  compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \
  |       |  ^~~~~~~~~~~~~~~~~~
  | ./include/asm-generic/rwonce.h:49:2: note: in expansion of macro 'compiletime_assert_rwonce_type'
  |    49 |  compiletime_assert_rwonce_type(x);    \
  |       |  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  | ./arch/parisc/include/asm/atomic.h:73:9: note: in expansion of macro 'READ_ONCE'
  |    73 |  return READ_ONCE((v)->counter);
  |       |         ^~~~~~~~~

Move these macros into compiler_types.h, so that they are available to
READ_ONCE() and friends.

Link: http://lists.infradead.org/pipermail/linux-arm-kernel/2020-July/587094.html
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/compiler.h       | 41 -----------------------------------------
 include/linux/compiler_types.h | 41 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index f075a3df4fe2..59f7194fdf08 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -273,47 +273,6 @@ static inline void *offset_to_ptr(const int *off)
 
 #endif /* __ASSEMBLY__ */
 
-/* Compile time object size, -1 for unknown */
-#ifndef __compiletime_object_size
-# define __compiletime_object_size(obj) -1
-#endif
-#ifndef __compiletime_warning
-# define __compiletime_warning(message)
-#endif
-#ifndef __compiletime_error
-# define __compiletime_error(message)
-#endif
-
-#ifdef __OPTIMIZE__
-# define __compiletime_assert(condition, msg, prefix, suffix)		\
-	do {								\
-		extern void prefix ## suffix(void) __compiletime_error(msg); \
-		if (!(condition))					\
-			prefix ## suffix();				\
-	} while (0)
-#else
-# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
-#endif
-
-#define _compiletime_assert(condition, msg, prefix, suffix) \
-	__compiletime_assert(condition, msg, prefix, suffix)
-
-/**
- * compiletime_assert - break build and emit msg if condition is false
- * @condition: a compile-time constant condition to check
- * @msg:       a message to emit if condition is false
- *
- * In tradition of POSIX assert, this macro will break the build if the
- * supplied condition is *false*, emitting the supplied error message if the
- * compiler has support to do so.
- */
-#define compiletime_assert(condition, msg) \
-	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
-
-#define compiletime_assert_atomic_type(t)				\
-	compiletime_assert(__native_word(t),				\
-		"Need native word sized stores/loads for atomicity.")
-
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index c3bf7710f69a..d9bbb62a3e2a 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -300,6 +300,47 @@ struct ftrace_likely_data {
 	(sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \
 	 sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 
+/* Compile time object size, -1 for unknown */
+#ifndef __compiletime_object_size
+# define __compiletime_object_size(obj) -1
+#endif
+#ifndef __compiletime_warning
+# define __compiletime_warning(message)
+#endif
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
+#ifdef __OPTIMIZE__
+# define __compiletime_assert(condition, msg, prefix, suffix)		\
+	do {								\
+		extern void prefix ## suffix(void) __compiletime_error(msg); \
+		if (!(condition))					\
+			prefix ## suffix();				\
+	} while (0)
+#else
+# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+#endif
+
+#define _compiletime_assert(condition, msg, prefix, suffix) \
+	__compiletime_assert(condition, msg, prefix, suffix)
+
+/**
+ * compiletime_assert - break build and emit msg if condition is false
+ * @condition: a compile-time constant condition to check
+ * @msg:       a message to emit if condition is false
+ *
+ * In tradition of POSIX assert, this macro will break the build if the
+ * supplied condition is *false*, emitting the supplied error message if the
+ * compiler has support to do so.
+ */
+#define compiletime_assert(condition, msg) \
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
+
+#define compiletime_assert_atomic_type(t)				\
+	compiletime_assert(__native_word(t),				\
+		"Need native word sized stores/loads for atomicity.")
+
 /* Helpers for emitting diagnostics in pragmas. */
 #ifndef __diag
 #define __diag(string)
-- 
cgit v1.2.3


From 4a17c441c7cb06ac1e5fd3409a64d8ce78151983 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 16 Jul 2020 23:09:40 +0800
Subject: soundwire: intel: revisit SHIM programming sequences.

Somehow the existing code is not aligned with the steps described in
the documentation, refactor code and make sure the register
programming sequences are correct. Also add missing power-up,
power-down and wake capabilities (the last two are used in follow-up
patches but introduced here for consistency).

Some of the SHIM registers exposed fields that are link specific, and
in addition some of the power-related registers (SPA/CPA) take time to
be updated. Uncontrolled access leads to timeouts or errors. Add a
mutex, shared by all links, so that all accesses to such registers are
serialized, and follow a pattern of read-modify-write.

This includes making sure SHIM_SYNC is programmed only once, before
the first master is powered on. We use a 'shim_mask' field, shared
between all links and protected by a mutex, to deal with power-up and
power-down sequences.

Note that the SYNCPRD value is tied only to the XTAL value and not the
current bus frequency or the frame rate.

BugLink: https://github.com/thesofproject/linux/issues/1555
Signed-off-by: Rander Wang <rander.wang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200716150947.22119-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/intel.c           | 237 ++++++++++++++++++++++++++++++------
 drivers/soundwire/intel.h           |   4 +
 drivers/soundwire/intel_init.c      |   4 +
 include/linux/soundwire/sdw_intel.h |   2 +
 4 files changed, 213 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index 8c7ae07c0fe1..4792613e8e5a 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -46,7 +46,8 @@
 #define SDW_SHIM_LCTL_SPA		BIT(0)
 #define SDW_SHIM_LCTL_CPA		BIT(8)
 
-#define SDW_SHIM_SYNC_SYNCPRD_VAL	0x176F
+#define SDW_SHIM_SYNC_SYNCPRD_VAL_24	(24000 / SDW_CADENCE_GSYNC_KHZ - 1)
+#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4	(38400 / SDW_CADENCE_GSYNC_KHZ - 1)
 #define SDW_SHIM_SYNC_SYNCPRD		GENMASK(14, 0)
 #define SDW_SHIM_SYNC_SYNCCPU		BIT(15)
 #define SDW_SHIM_SYNC_CMDSYNC_MASK	GENMASK(19, 16)
@@ -272,8 +273,46 @@ static int intel_link_power_up(struct sdw_intel *sdw)
 {
 	unsigned int link_id = sdw->instance;
 	void __iomem *shim = sdw->link_res->shim;
+	u32 *shim_mask = sdw->link_res->shim_mask;
+	struct sdw_bus *bus = &sdw->cdns.bus;
+	struct sdw_master_prop *prop = &bus->prop;
 	int spa_mask, cpa_mask;
-	int link_control, ret;
+	int link_control;
+	int ret = 0;
+	u32 syncprd;
+	u32 sync_reg;
+
+	mutex_lock(sdw->link_res->shim_lock);
+
+	/*
+	 * The hardware relies on an internal counter, typically 4kHz,
+	 * to generate the SoundWire SSP - which defines a 'safe'
+	 * synchronization point between commands and audio transport
+	 * and allows for multi link synchronization. The SYNCPRD value
+	 * is only dependent on the oscillator clock provided to
+	 * the IP, so adjust based on _DSD properties reported in DSDT
+	 * tables. The values reported are based on either 24MHz
+	 * (CNL/CML) or 38.4 MHz (ICL/TGL+).
+	 */
+	if (prop->mclk_freq % 6000000)
+		syncprd = SDW_SHIM_SYNC_SYNCPRD_VAL_38_4;
+	else
+		syncprd = SDW_SHIM_SYNC_SYNCPRD_VAL_24;
+
+	if (!*shim_mask) {
+		/* we first need to program the SyncPRD/CPU registers */
+		dev_dbg(sdw->cdns.dev,
+			"%s: first link up, programming SYNCPRD\n", __func__);
+
+		/* set SyncPRD period */
+		sync_reg = intel_readl(shim, SDW_SHIM_SYNC);
+		sync_reg |= (syncprd <<
+			     SDW_REG_SHIFT(SDW_SHIM_SYNC_SYNCPRD));
+
+		/* Set SyncCPU bit */
+		sync_reg |= SDW_SHIM_SYNC_SYNCCPU;
+		intel_writel(shim, SDW_SHIM_SYNC, sync_reg);
+	}
 
 	/* Link power up sequence */
 	link_control = intel_readl(shim, SDW_SHIM_LCTL);
@@ -282,68 +321,180 @@ static int intel_link_power_up(struct sdw_intel *sdw)
 	link_control |=  spa_mask;
 
 	ret = intel_set_bit(shim, SDW_SHIM_LCTL, link_control, cpa_mask);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		dev_err(sdw->cdns.dev, "Failed to power up link: %d\n", ret);
+		goto out;
+	}
+
+	if (!*shim_mask) {
+		/* SyncCPU will change once link is active */
+		ret = intel_wait_bit(shim, SDW_SHIM_SYNC,
+				     SDW_SHIM_SYNC_SYNCCPU, 0);
+		if (ret < 0) {
+			dev_err(sdw->cdns.dev,
+				"Failed to set SHIM_SYNC: %d\n", ret);
+			goto out;
+		}
+	}
+
+	*shim_mask |= BIT(link_id);
 
 	sdw->cdns.link_up = true;
-	return 0;
+out:
+	mutex_unlock(sdw->link_res->shim_lock);
+
+	return ret;
 }
 
-static int intel_shim_init(struct sdw_intel *sdw)
+/* this needs to be called with shim_lock */
+static void intel_shim_glue_to_master_ip(struct sdw_intel *sdw)
 {
 	void __iomem *shim = sdw->link_res->shim;
 	unsigned int link_id = sdw->instance;
-	int sync_reg, ret;
-	u16 ioctl = 0, act = 0;
+	u16 ioctl;
 
-	/* Initialize Shim */
-	ioctl |= SDW_SHIM_IOCTL_BKE;
+	/* Switch to MIP from Glue logic */
+	ioctl = intel_readw(shim,  SDW_SHIM_IOCTL(link_id));
+
+	ioctl &= ~(SDW_SHIM_IOCTL_DOE);
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl |= SDW_SHIM_IOCTL_WPDD;
+	ioctl &= ~(SDW_SHIM_IOCTL_DO);
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl |= SDW_SHIM_IOCTL_DO;
+	ioctl |= (SDW_SHIM_IOCTL_MIF);
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl |= SDW_SHIM_IOCTL_DOE;
+	ioctl &= ~(SDW_SHIM_IOCTL_BKE);
+	ioctl &= ~(SDW_SHIM_IOCTL_COE);
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	/* Switch to MIP from Glue logic */
-	ioctl = intel_readw(shim,  SDW_SHIM_IOCTL(link_id));
+	/* at this point Master IP has full control of the I/Os */
+}
 
-	ioctl &= ~(SDW_SHIM_IOCTL_DOE);
+/* this needs to be called with shim_lock */
+static void intel_shim_master_ip_to_glue(struct sdw_intel *sdw)
+{
+	unsigned int link_id = sdw->instance;
+	void __iomem *shim = sdw->link_res->shim;
+	u16 ioctl;
+
+	/* Glue logic */
+	ioctl = intel_readw(shim, SDW_SHIM_IOCTL(link_id));
+	ioctl |= SDW_SHIM_IOCTL_BKE;
+	ioctl |= SDW_SHIM_IOCTL_COE;
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl &= ~(SDW_SHIM_IOCTL_DO);
+	ioctl &= ~(SDW_SHIM_IOCTL_MIF);
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl |= (SDW_SHIM_IOCTL_MIF);
+	/* at this point Integration Glue has full control of the I/Os */
+}
+
+static int intel_shim_init(struct sdw_intel *sdw, bool clock_stop)
+{
+	void __iomem *shim = sdw->link_res->shim;
+	unsigned int link_id = sdw->instance;
+	int ret = 0;
+	u16 ioctl = 0, act = 0;
+
+	mutex_lock(sdw->link_res->shim_lock);
+
+	/* Initialize Shim */
+	ioctl |= SDW_SHIM_IOCTL_BKE;
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
-	ioctl &= ~(SDW_SHIM_IOCTL_BKE);
-	ioctl &= ~(SDW_SHIM_IOCTL_COE);
+	ioctl |= SDW_SHIM_IOCTL_WPDD;
+	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
 
+	ioctl |= SDW_SHIM_IOCTL_DO;
+	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
+
+	ioctl |= SDW_SHIM_IOCTL_DOE;
 	intel_writew(shim, SDW_SHIM_IOCTL(link_id), ioctl);
+	usleep_range(10, 15);
+
+	intel_shim_glue_to_master_ip(sdw);
 
 	act |= 0x1 << SDW_REG_SHIFT(SDW_SHIM_CTMCTL_DOAIS);
 	act |= SDW_SHIM_CTMCTL_DACTQE;
 	act |= SDW_SHIM_CTMCTL_DODS;
 	intel_writew(shim, SDW_SHIM_CTMCTL(link_id), act);
+	usleep_range(10, 15);
 
-	/* Now set SyncPRD period */
-	sync_reg = intel_readl(shim, SDW_SHIM_SYNC);
-	sync_reg |= (SDW_SHIM_SYNC_SYNCPRD_VAL <<
-			SDW_REG_SHIFT(SDW_SHIM_SYNC_SYNCPRD));
+	mutex_unlock(sdw->link_res->shim_lock);
+
+	return ret;
+}
+
+static void __maybe_unused intel_shim_wake(struct sdw_intel *sdw, bool wake_enable)
+{
+	void __iomem *shim = sdw->link_res->shim;
+	unsigned int link_id = sdw->instance;
+	u16 wake_en, wake_sts;
+
+	mutex_lock(sdw->link_res->shim_lock);
+	wake_en = intel_readw(shim, SDW_SHIM_WAKEEN);
+
+	if (wake_enable) {
+		/* Enable the wakeup */
+		wake_en |= (SDW_SHIM_WAKEEN_ENABLE << link_id);
+		intel_writew(shim, SDW_SHIM_WAKEEN, wake_en);
+	} else {
+		/* Disable the wake up interrupt */
+		wake_en &= ~(SDW_SHIM_WAKEEN_ENABLE << link_id);
+		intel_writew(shim, SDW_SHIM_WAKEEN, wake_en);
+
+		/* Clear wake status */
+		wake_sts = intel_readw(shim, SDW_SHIM_WAKESTS);
+		wake_sts |= (SDW_SHIM_WAKEEN_ENABLE << link_id);
+		intel_writew(shim, SDW_SHIM_WAKESTS_STATUS, wake_sts);
+	}
+	mutex_unlock(sdw->link_res->shim_lock);
+}
+
+static int __maybe_unused intel_link_power_down(struct sdw_intel *sdw)
+{
+	int link_control, spa_mask, cpa_mask;
+	unsigned int link_id = sdw->instance;
+	void __iomem *shim = sdw->link_res->shim;
+	u32 *shim_mask = sdw->link_res->shim_mask;
+	int ret = 0;
+
+	mutex_lock(sdw->link_res->shim_lock);
+
+	intel_shim_master_ip_to_glue(sdw);
+
+	/* Link power down sequence */
+	link_control = intel_readl(shim, SDW_SHIM_LCTL);
+	spa_mask = ~(SDW_SHIM_LCTL_SPA << link_id);
+	cpa_mask = (SDW_SHIM_LCTL_CPA << link_id);
+	link_control &=  spa_mask;
+
+	ret = intel_clear_bit(shim, SDW_SHIM_LCTL, link_control, cpa_mask);
+
+	if (!(*shim_mask & BIT(link_id)))
+		dev_err(sdw->cdns.dev,
+			"%s: Unbalanced power-up/down calls\n", __func__);
+
+	*shim_mask &= ~BIT(link_id);
+
+	mutex_unlock(sdw->link_res->shim_lock);
 
-	/* Set SyncCPU bit */
-	sync_reg |= SDW_SHIM_SYNC_SYNCCPU;
-	ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg,
-			      SDW_SHIM_SYNC_SYNCCPU);
 	if (ret < 0)
-		dev_err(sdw->cdns.dev, "Failed to set sync period: %d\n", ret);
+		return ret;
 
-	return ret;
+	sdw->cdns.link_up = false;
+	return 0;
 }
 
 /*
@@ -566,11 +717,15 @@ static int intel_pre_bank_switch(struct sdw_bus *bus)
 	if (!bus->multi_link)
 		return 0;
 
+	mutex_lock(sdw->link_res->shim_lock);
+
 	/* Read SYNC register */
 	sync_reg = intel_readl(shim, SDW_SHIM_SYNC);
 	sync_reg |= SDW_SHIM_SYNC_CMDSYNC << sdw->instance;
 	intel_writel(shim, SDW_SHIM_SYNC, sync_reg);
 
+	mutex_unlock(sdw->link_res->shim_lock);
+
 	return 0;
 }
 
@@ -585,6 +740,8 @@ static int intel_post_bank_switch(struct sdw_bus *bus)
 	if (!bus->multi_link)
 		return 0;
 
+	mutex_lock(sdw->link_res->shim_lock);
+
 	/* Read SYNC register */
 	sync_reg = intel_readl(shim, SDW_SHIM_SYNC);
 
@@ -596,9 +753,10 @@ static int intel_post_bank_switch(struct sdw_bus *bus)
 	 *
 	 * So, set the SYNCGO bit only if CMDSYNC bit is set for any Master.
 	 */
-	if (!(sync_reg & SDW_SHIM_SYNC_CMDSYNC_MASK))
-		return 0;
-
+	if (!(sync_reg & SDW_SHIM_SYNC_CMDSYNC_MASK)) {
+		ret = 0;
+		goto unlock;
+	}
 	/*
 	 * Set SyncGO bit to synchronously trigger a bank switch for
 	 * all the masters. A write to SYNCGO bit clears CMDSYNC bit for all
@@ -608,6 +766,9 @@ static int intel_post_bank_switch(struct sdw_bus *bus)
 
 	ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg,
 			      SDW_SHIM_SYNC_SYNCGO);
+unlock:
+	mutex_unlock(sdw->link_res->shim_lock);
+
 	if (ret < 0)
 		dev_err(sdw->cdns.dev, "Post bank switch failed: %d\n", ret);
 
@@ -1011,9 +1172,17 @@ static struct sdw_master_ops sdw_intel_ops = {
 
 static int intel_init(struct sdw_intel *sdw)
 {
+	bool clock_stop;
+
 	/* Initialize shim and controller */
 	intel_link_power_up(sdw);
-	intel_shim_init(sdw);
+
+	clock_stop = sdw_cdns_is_clock_stop(&sdw->cdns);
+
+	intel_shim_init(sdw, clock_stop);
+
+	if (clock_stop)
+		return 0;
 
 	return sdw_cdns_init(&sdw->cdns);
 }
diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h
index 694117370ac3..d6bdd4d63e08 100644
--- a/drivers/soundwire/intel.h
+++ b/drivers/soundwire/intel.h
@@ -15,6 +15,8 @@
  * @irq: Interrupt line
  * @ops: Shim callback ops
  * @dev: device implementing hw_params and free callbacks
+ * @shim_lock: mutex to handle access to shared SHIM registers
+ * @shim_mask: global pointer to check SHIM register initialization
  */
 struct sdw_intel_link_res {
 	struct platform_device *pdev;
@@ -25,6 +27,8 @@ struct sdw_intel_link_res {
 	int irq;
 	const struct sdw_intel_ops *ops;
 	struct device *dev;
+	struct mutex *shim_lock; /* protect shared registers */
+	u32 *shim_mask;
 };
 
 struct sdw_intel {
diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c
index 3f2e884b4f6d..f50a93130d12 100644
--- a/drivers/soundwire/intel_init.c
+++ b/drivers/soundwire/intel_init.c
@@ -180,6 +180,7 @@ static struct sdw_intel_ctx
 	ctx->mmio_base = res->mmio_base;
 	ctx->link_mask = res->link_mask;
 	ctx->handle = res->handle;
+	mutex_init(&ctx->shim_lock);
 
 	link = ctx->links;
 	link_mask = ctx->link_mask;
@@ -201,6 +202,9 @@ static struct sdw_intel_ctx
 		link->ops = res->ops;
 		link->dev = res->dev;
 
+		link->shim_lock = &ctx->shim_lock;
+		link->shim_mask = &ctx->shim_mask;
+
 		memset(&pdevinfo, 0, sizeof(pdevinfo));
 
 		pdevinfo.parent = res->parent;
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index 979b41b5dcb4..120ffddc03d2 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -115,6 +115,7 @@ struct sdw_intel_slave_id {
  * links
  * @link_list: list to handle interrupts across all links
  * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers.
+ * @shim_mask: flags to track initialization of SHIM shared registers
  */
 struct sdw_intel_ctx {
 	int count;
@@ -126,6 +127,7 @@ struct sdw_intel_ctx {
 	struct sdw_intel_slave_id *ids;
 	struct list_head link_list;
 	struct mutex shim_lock; /* lock for access to shared SHIM registers */
+	u32 shim_mask;
 };
 
 /**
-- 
cgit v1.2.3


From b2dcfefc43f783c4462f30507f78b7bb093ee8df Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 15 Jul 2020 20:41:26 -0700
Subject: usb: typec: tcpm: Support bist test data mode for compliance

TCPM supports BIST carried mode. PD compliance tests require
BIST Test Data to be supported as well.

Introducing set_bist_data callback to signal tcpc driver for
configuring the port controller hardware to enable/disable
BIST Test Data mode.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200716034128.1251728-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 11 +++++++++++
 include/linux/usb/tcpm.h      |  2 ++
 2 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a6d4b03ec250..a04f6c18b11a 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -2748,6 +2748,11 @@ static void tcpm_detach(struct tcpm_port *port)
 	if (!port->attached)
 		return;
 
+	if (port->tcpc->set_bist_data) {
+		tcpm_log(port, "disable BIST MODE TESTDATA");
+		port->tcpc->set_bist_data(port->tcpc, false);
+	}
+
 	if (tcpm_port_is_disconnected(port))
 		port->hard_reset_count = 0;
 
@@ -3557,6 +3562,12 @@ static void run_state_machine(struct tcpm_port *port)
 		case BDO_MODE_CARRIER2:
 			tcpm_pd_transmit(port, TCPC_TX_BIST_MODE_2, NULL);
 			break;
+		case BDO_MODE_TESTDATA:
+			if (port->tcpc->set_bist_data) {
+				tcpm_log(port, "Enable BIST MODE TESTDATA");
+				port->tcpc->set_bist_data(port->tcpc, true);
+			}
+			break;
 		default:
 			break;
 		}
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index e7979c01c351..89f58760cf48 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -79,6 +79,7 @@ enum tcpm_transmit_type {
  * @try_role:	Optional; called to set a preferred role
  * @pd_transmit:Called to transmit PD message
  * @mux:	Pointer to multiplexer data
+ * @set_bist_data: Turn on/off bist data mode for compliance testing
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -103,6 +104,7 @@ struct tcpc_dev {
 	int (*try_role)(struct tcpc_dev *dev, int role);
 	int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type,
 			   const struct pd_message *msg);
+	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
 };
 
 struct tcpm_port;
-- 
cgit v1.2.3


From 6e1c2241f4cecfc21f26f44179d04217c8390338 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 15 Jul 2020 20:41:28 -0700
Subject: usb: typec: tcpm: Stay in BIST mode till hardreset or unattached
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Port starts to toggle when transitioning to unattached state.
This is incorrect while in BIST mode.

6.4.3.1 BIST Carrier Mode
Upon receipt of a BIST Message, with a BIST Carrier Mode BIST Data Object,
the UUT Shall send out a continuous string of BMC encoded alternating "1"s
and “0”s. The UUT Shall exit the Continuous BIST Mode within
tBISTContMode of this Continuous BIST Mode being enabled(see
Section 6.6.7.2).

6.4.3.2 BIST Test Data
Upon receipt of a BIST Message, with a BIST Test Data BIST Data Object,
the UUT Shall return a GoodCRC Message and Shall enter a test mode in which
it sends no further Messages except for GoodCRC Messages in response to
received Messages. See Section 5.9.2 for the definition of the Test Data
Frame. The test Shall be ended by sending Hard Reset Signaling to reset the
UUT.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200716034128.1251728-3-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 7 +++++--
 include/linux/usb/pd.h        | 1 +
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a04f6c18b11a..ff1cbd2147ca 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3561,6 +3561,8 @@ static void run_state_machine(struct tcpm_port *port)
 		switch (BDO_MODE_MASK(port->bist_request)) {
 		case BDO_MODE_CARRIER2:
 			tcpm_pd_transmit(port, TCPC_TX_BIST_MODE_2, NULL);
+			tcpm_set_state(port, unattached_state(port),
+				       PD_T_BIST_CONT_MODE);
 			break;
 		case BDO_MODE_TESTDATA:
 			if (port->tcpc->set_bist_data) {
@@ -3571,8 +3573,6 @@ static void run_state_machine(struct tcpm_port *port)
 		default:
 			break;
 		}
-		/* Always switch to unattached state */
-		tcpm_set_state(port, unattached_state(port), 0);
 		break;
 	case GET_STATUS_SEND:
 		tcpm_pd_send_control(port, PD_CTRL_GET_STATUS);
@@ -3962,6 +3962,9 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 static void _tcpm_pd_hard_reset(struct tcpm_port *port)
 {
 	tcpm_log_force(port, "Received hard reset");
+	if (port->bist_request == BDO_MODE_TESTDATA && port->tcpc->set_bist_data)
+		port->tcpc->set_bist_data(port->tcpc, false);
+
 	/*
 	 * If we keep receiving hard reset requests, executing the hard reset
 	 * must have failed. Revert to error recovery if that happens.
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index a665d7f21142..b6c233e79bd4 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -483,4 +483,5 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_N_CAPS_COUNT		(PD_T_NO_RESPONSE / PD_T_SEND_SOURCE_CAP)
 #define PD_N_HARD_RESET_COUNT	2
 
+#define PD_T_BIST_CONT_MODE	50 /* 30 - 60 ms */
 #endif /* __LINUX_USB_PD_H */
-- 
cgit v1.2.3


From ffeb1e9e897b8d36b197275592d121c96d3bdb95 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Sun, 19 Jul 2020 18:09:10 +0200
Subject: USB: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Link: https://lore.kernel.org/r/20200719160910.60018-1-grandmaster@al2klimov.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/gadget_hid.rst   |  2 +-
 Documentation/usb/gadget_multi.rst | 10 +++++-----
 Documentation/usb/linux.inf        |  2 +-
 drivers/usb/cdns3/cdns3-ti.c       |  2 +-
 drivers/usb/common/debug.c         |  2 +-
 drivers/usb/host/max3421-hcd.c     |  6 +++---
 drivers/usb/misc/Kconfig           |  4 ++--
 include/linux/usb/phy_companion.h  |  2 +-
 8 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/usb/gadget_hid.rst b/Documentation/usb/gadget_hid.rst
index 098d563040cc..e623416de4f1 100644
--- a/Documentation/usb/gadget_hid.rst
+++ b/Documentation/usb/gadget_hid.rst
@@ -11,7 +11,7 @@ and HID reports can be sent/received through I/O on the
 /dev/hidgX character devices.
 
 For more details about HID, see the developer page on
-http://www.usb.org/developers/hidpage/
+https://www.usb.org/developers/hidpage/
 
 Configuration
 =============
diff --git a/Documentation/usb/gadget_multi.rst b/Documentation/usb/gadget_multi.rst
index 9806b55af301..3a22c1b2f39e 100644
--- a/Documentation/usb/gadget_multi.rst
+++ b/Documentation/usb/gadget_multi.rst
@@ -142,7 +142,7 @@ Footnotes
 =========
 
 [1] Remote Network Driver Interface Specification,
-[[http://msdn.microsoft.com/en-us/library/ee484414.aspx]].
+[[https://msdn.microsoft.com/en-us/library/ee484414.aspx]].
 
 [2] Communications Device Class Abstract Control Model, spec for this
 and other USB classes can be found at
@@ -150,9 +150,9 @@ and other USB classes can be found at
 
 [3] CDC Ethernet Control Model.
 
-[4] [[http://msdn.microsoft.com/en-us/library/ff537109(v=VS.85).aspx]]
+[4] [[https://msdn.microsoft.com/en-us/library/ff537109(v=VS.85).aspx]]
 
-[5] [[http://msdn.microsoft.com/en-us/library/ff539234(v=VS.85).aspx]]
+[5] [[https://msdn.microsoft.com/en-us/library/ff539234(v=VS.85).aspx]]
 
 [6] To put it in some other nice words, Windows failed to respond to
 any user input.
@@ -160,6 +160,6 @@ any user input.
 [7] You may find [[http://www.cygnal.org/ubb/Forum9/HTML/001050.html]]
 useful.
 
-[8] http://www.nirsoft.net/utils/usb_devices_view.html
+[8] https://www.nirsoft.net/utils/usb_devices_view.html
 
-[9] [[http://msdn.microsoft.com/en-us/library/ff570620.aspx]]
+[9] [[https://msdn.microsoft.com/en-us/library/ff570620.aspx]]
diff --git a/Documentation/usb/linux.inf b/Documentation/usb/linux.inf
index 4ffa715b0ae8..c569ac6bec58 100644
--- a/Documentation/usb/linux.inf
+++ b/Documentation/usb/linux.inf
@@ -1,5 +1,5 @@
 ; Based on template INF file found at
-;    <http://msdn.microsoft.com/en-us/library/ff570620.aspx>
+;    <https://msdn.microsoft.com/en-us/library/ff570620.aspx>
 ; which was:
 ;    Copyright (c) Microsoft Corporation
 ; and released under the MLPL as found at:
diff --git a/drivers/usb/cdns3/cdns3-ti.c b/drivers/usb/cdns3/cdns3-ti.c
index e701ab56b0a7..90e246601537 100644
--- a/drivers/usb/cdns3/cdns3-ti.c
+++ b/drivers/usb/cdns3/cdns3-ti.c
@@ -2,7 +2,7 @@
 /**
  * cdns3-ti.c - TI specific Glue layer for Cadence USB Controller
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #include <linux/bits.h>
diff --git a/drivers/usb/common/debug.c b/drivers/usb/common/debug.c
index 54c8f984c7b4..ba849c7bc5c7 100644
--- a/drivers/usb/common/debug.c
+++ b/drivers/usb/common/debug.c
@@ -2,7 +2,7 @@
 /*
  * Common USB debugging functions
  *
- * Copyright (C) 2010-2011 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2010-2011 Texas Instruments Incorporated - https://www.ti.com
  *
  * Authors: Felipe Balbi <balbi@ti.com>,
  *	    Sebastian Andrzej Siewior <bigeasy@linutronix.de>
diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index 05828c0ab7de..0894f6caccb2 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -11,9 +11,9 @@
  *
  * Based on:
  *	o MAX3421E datasheet
- *		http://datasheets.maximintegrated.com/en/ds/MAX3421E.pdf
+ *		https://datasheets.maximintegrated.com/en/ds/MAX3421E.pdf
  *	o MAX3421E Programming Guide
- *		http://www.hdl.co.jp/ftpdata/utl-001/AN3785.pdf
+ *		https://www.hdl.co.jp/ftpdata/utl-001/AN3785.pdf
  *	o gadget/dummy_hcd.c
  *		For USB HCD implementation.
  *	o Arduino MAX3421 driver
@@ -317,7 +317,7 @@ static const int hrsl_to_error[] = {
 };
 
 /*
- * See http://www.beyondlogic.org/usbnutshell/usb4.shtml#Control for a
+ * See https://www.beyondlogic.org/usbnutshell/usb4.shtml#Control for a
  * reasonable overview of how control transfers use the the IN/OUT
  * tokens.
  */
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index 4e48f8eed168..6818ea689cd9 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -78,7 +78,7 @@ config USB_CYPRESS_CY7C63
 	  driver supports the pre-programmed devices (incl. firmware)
 	  by AK Modul-Bus Computer GmbH.
 
-	  Please see: http://www.ak-modul-bus.de/stat/mikrocontroller.html
+	  Please see: https://www.ak-modul-bus.de/stat/mikrocontroller.html
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called cypress_cy7c63.
@@ -106,7 +106,7 @@ config USB_IDMOUSE
 	  This driver creates an entry "/dev/idmouseX" or "/dev/usb/idmouseX",
 	  which can be used by, e.g.,"cat /dev/idmouse0 > fingerprint.pnm".
 
-	  See also <http://www.fs.tum.de/~echtler/idmouse/>.
+	  See also <https://www.fs.tum.de/~echtler/idmouse/>.
 
 config USB_FTDI_ELAN
 	tristate "Elan PCMCIA CardBus Adapter USB Client"
diff --git a/include/linux/usb/phy_companion.h b/include/linux/usb/phy_companion.h
index 407f530061cd..263196f05015 100644
--- a/include/linux/usb/phy_companion.h
+++ b/include/linux/usb/phy_companion.h
@@ -2,7 +2,7 @@
 /*
  * phy-companion.h -- phy companion to indicate the comparator part of PHY
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
-- 
cgit v1.2.3


From 9746c9be0bb5860592e048468b37974be4c59d44 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 11 Jul 2020 06:45:36 -0500
Subject: exec: Remove unnecessary spaces from binfmts.h

The general convention in the linux kernel is to define a pointer
member as "type *name".  The declaration of struct linux_binprm has
several pointer defined as "type * name".  Update them to the
form of "type *name" for consistency.

Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lkml.kernel.org/r/87v9iq6x9x.fsf@x220.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/binfmts.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 7c27d7b57871..eb5cb8df5485 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -45,15 +45,15 @@ struct linux_binprm {
 #ifdef __alpha__
 	unsigned int taso:1;
 #endif
-	struct file * executable; /* Executable to pass to the interpreter */
-	struct file * interpreter;
-	struct file * file;
+	struct file *executable; /* Executable to pass to the interpreter */
+	struct file *interpreter;
+	struct file *file;
 	struct cred *cred;	/* new credentials */
 	int unsafe;		/* how unsafe this exec is (mask of LSM_UNSAFE_*) */
 	unsigned int per_clear;	/* bits to clear in current->personality */
 	int argc, envc;
-	const char * filename;	/* Name of binary as seen by procps */
-	const char * interp;	/* Name of the binary really executed. Most
+	const char *filename;	/* Name of binary as seen by procps */
+	const char *interp;	/* Name of the binary really executed. Most
 				   of the time same as filename, but could be
 				   different for binfmt_{misc,script} */
 	unsigned interp_flags;
-- 
cgit v1.2.3


From 60d9ad1d1d7f15964d23f6e71a7adcf1bde0e18e Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 11 Jul 2020 08:16:15 -0500
Subject: exec: Move initialization of bprm->filename into alloc_bprm

Currently it is necessary for the usermode helper code and the code
that launches init to use set_fs so that pages coming from the kernel
look like they are coming from userspace.

To allow that usage of set_fs to be removed cleanly the argument
copying from userspace needs to happen earlier.  Move the computation
of bprm->filename and possible allocation of a name in the case
of execveat into alloc_bprm to make that possible.

The exectuable name, the arguments, and the environment are
copied into the new usermode stack which is stored in bprm
until exec passes the point of no return.

As the executable name is copied first onto the usermode stack
it needs to be known.  As there are no dependencies to computing
the executable name, compute it early in alloc_bprm.

As an implementation detail if the filename needs to be generated
because it embeds a file descriptor store that filename in a new field
bprm->fdpath, and free it in free_bprm.  Previously this was done in
an independent variable pathbuf.  I have renamed pathbuf fdpath
because fdpath is more suggestive of what kind of path is in the
variable.  I moved fdpath into struct linux_binprm because it is
tightly tied to the other variables in struct linux_binprm, and as
such is needed to allow the call alloc_binprm to move.

Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lkml.kernel.org/r/87k0z66x8f.fsf@x220.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/exec.c               | 61 ++++++++++++++++++++++++++-----------------------
 include/linux/binfmts.h |  1 +
 2 files changed, 34 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index 526156d6461d..7e8af27dd199 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1557,15 +1557,37 @@ static void free_bprm(struct linux_binprm *bprm)
 	/* If a binfmt changed the interp, free it. */
 	if (bprm->interp != bprm->filename)
 		kfree(bprm->interp);
+	kfree(bprm->fdpath);
 	kfree(bprm);
 }
 
-static struct linux_binprm *alloc_bprm(void)
+static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
 {
 	struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	int retval = -ENOMEM;
 	if (!bprm)
-		return ERR_PTR(-ENOMEM);
+		goto out;
+
+	if (fd == AT_FDCWD || filename->name[0] == '/') {
+		bprm->filename = filename->name;
+	} else {
+		if (filename->name[0] == '\0')
+			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd);
+		else
+			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s",
+						  fd, filename->name);
+		if (!bprm->fdpath)
+			goto out_free;
+
+		bprm->filename = bprm->fdpath;
+	}
+	bprm->interp = bprm->filename;
 	return bprm;
+
+out_free:
+	free_bprm(bprm);
+out:
+	return ERR_PTR(retval);
 }
 
 int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
@@ -1831,7 +1853,6 @@ static int do_execveat_common(int fd, struct filename *filename,
 			      struct user_arg_ptr envp,
 			      int flags)
 {
-	char *pathbuf = NULL;
 	struct linux_binprm *bprm;
 	struct file *file;
 	struct files_struct *displaced;
@@ -1856,7 +1877,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * further execve() calls fail. */
 	current->flags &= ~PF_NPROC_EXCEEDED;
 
-	bprm = alloc_bprm();
+	bprm = alloc_bprm(fd, filename);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -1881,28 +1902,14 @@ static int do_execveat_common(int fd, struct filename *filename,
 	sched_exec();
 
 	bprm->file = file;
-	if (fd == AT_FDCWD || filename->name[0] == '/') {
-		bprm->filename = filename->name;
-	} else {
-		if (filename->name[0] == '\0')
-			pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd);
-		else
-			pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s",
-					    fd, filename->name);
-		if (!pathbuf) {
-			retval = -ENOMEM;
-			goto out_unmark;
-		}
-		/*
-		 * Record that a name derived from an O_CLOEXEC fd will be
-		 * inaccessible after exec. Relies on having exclusive access to
-		 * current->files (due to unshare_files above).
-		 */
-		if (close_on_exec(fd, rcu_dereference_raw(current->files->fdt)))
-			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
-		bprm->filename = pathbuf;
-	}
-	bprm->interp = bprm->filename;
+	/*
+	 * Record that a name derived from an O_CLOEXEC fd will be
+	 * inaccessible after exec. Relies on having exclusive access to
+	 * current->files (due to unshare_files above).
+	 */
+	if (bprm->fdpath &&
+	    close_on_exec(fd, rcu_dereference_raw(current->files->fdt)))
+		bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
 
 	retval = bprm_mm_init(bprm);
 	if (retval)
@@ -1941,7 +1948,6 @@ static int do_execveat_common(int fd, struct filename *filename,
 	acct_update_integrals(current);
 	task_numa_free(current, false);
 	free_bprm(bprm);
-	kfree(pathbuf);
 	putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
@@ -1970,7 +1976,6 @@ out_files:
 		reset_files_struct(displaced);
 out_free:
 	free_bprm(bprm);
-	kfree(pathbuf);
 
 out_ret:
 	putname(filename);
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index eb5cb8df5485..8e9e1b0c8eb8 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -56,6 +56,7 @@ struct linux_binprm {
 	const char *interp;	/* Name of the binary really executed. Most
 				   of the time same as filename, but could be
 				   different for binfmt_{misc,script} */
+	const char *fdpath;	/* generated filename for execveat */
 	unsigned interp_flags;
 	int execfd;		/* File descriptor of the executable */
 	unsigned long loader, exec;
-- 
cgit v1.2.3


From be619f7f063a49c656f620a46af4f8ea3e759e91 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 13 Jul 2020 12:06:48 -0500
Subject: exec: Implement kernel_execve

To allow the kernel not to play games with set_fs to call exec
implement kernel_execve.  The function kernel_execve takes pointers
into kernel memory and copies the values pointed to onto the new
userspace stack.

The calls with arguments from kernel space of do_execve are replaced
with calls to kernel_execve.

The calls do_execve and do_execveat are made static as there are now
no callers outside of exec.

The comments that mention do_execve are updated to refer to
kernel_execve or execve depending on the circumstances.  In addition
to correcting the comments, this makes it easy to grep for do_execve
and verify it is not used.

Inspired-by: https://lkml.kernel.org/r/20200627072704.2447163-1-hch@lst.de
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/87wo365ikj.fsf@x220.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/x86/entry/entry_32.S      |  2 +-
 arch/x86/entry/entry_64.S      |  2 +-
 arch/x86/kernel/unwind_frame.c |  2 +-
 fs/exec.c                      | 88 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/binfmts.h        |  9 +----
 init/main.c                    |  4 +-
 kernel/umh.c                   |  6 +--
 security/tomoyo/common.h       |  2 +-
 security/tomoyo/domain.c       |  4 +-
 security/tomoyo/tomoyo.c       |  4 +-
 10 files changed, 100 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 024d7d276cd4..8f4e085ee06d 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -854,7 +854,7 @@ SYM_CODE_START(ret_from_fork)
 	CALL_NOSPEC ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
-	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * calling kernel_execve().  Exit to userspace to complete the execve()
 	 * syscall.
 	 */
 	movl	$0, PT_EAX(%esp)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d2a00c97e53f..73c7e255256b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -293,7 +293,7 @@ SYM_CODE_START(ret_from_fork)
 	CALL_NOSPEC rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
-	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * calling kernel_execve().  Exit to userspace to complete the execve()
 	 * syscall.
 	 */
 	movq	$0, RAX(%rsp)
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 722a85f3b2dd..e40b4942157f 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -275,7 +275,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		 * This user_mode() check is slightly broader than a PF_KTHREAD
 		 * check because it also catches the awkward situation where a
 		 * newly forked kthread transitions into a user task by calling
-		 * do_execve(), which eventually clears PF_KTHREAD.
+		 * kernel_execve(), which eventually clears PF_KTHREAD.
 		 */
 		if (!user_mode(regs))
 			goto the_end;
diff --git a/fs/exec.c b/fs/exec.c
index f8135dc149b3..3698252719a3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -448,6 +448,23 @@ static int count(struct user_arg_ptr argv, int max)
 	return i;
 }
 
+static int count_strings_kernel(const char *const *argv)
+{
+	int i;
+
+	if (!argv)
+		return 0;
+
+	for (i = 0; argv[i]; ++i) {
+		if (i >= MAX_ARG_STRINGS)
+			return -E2BIG;
+		if (fatal_signal_pending(current))
+			return -ERESTARTNOHAND;
+		cond_resched();
+	}
+	return i;
+}
+
 static int bprm_stack_limits(struct linux_binprm *bprm)
 {
 	unsigned long limit, ptr_size;
@@ -624,6 +641,20 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
 }
 EXPORT_SYMBOL(copy_string_kernel);
 
+static int copy_strings_kernel(int argc, const char *const *argv,
+			       struct linux_binprm *bprm)
+{
+	while (argc-- > 0) {
+		int ret = copy_string_kernel(argv[argc], bprm);
+		if (ret < 0)
+			return ret;
+		if (fatal_signal_pending(current))
+			return -ERESTARTNOHAND;
+		cond_resched();
+	}
+	return 0;
+}
+
 #ifdef CONFIG_MMU
 
 /*
@@ -1991,7 +2022,60 @@ out_ret:
 	return retval;
 }
 
-int do_execve(struct filename *filename,
+int kernel_execve(const char *kernel_filename,
+		  const char *const *argv, const char *const *envp)
+{
+	struct filename *filename;
+	struct linux_binprm *bprm;
+	int fd = AT_FDCWD;
+	int retval;
+
+	filename = getname_kernel(kernel_filename);
+	if (IS_ERR(filename))
+		return PTR_ERR(filename);
+
+	bprm = alloc_bprm(fd, filename);
+	if (IS_ERR(bprm)) {
+		retval = PTR_ERR(bprm);
+		goto out_ret;
+	}
+
+	retval = count_strings_kernel(argv);
+	if (retval < 0)
+		goto out_free;
+	bprm->argc = retval;
+
+	retval = count_strings_kernel(envp);
+	if (retval < 0)
+		goto out_free;
+	bprm->envc = retval;
+
+	retval = bprm_stack_limits(bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = copy_string_kernel(bprm->filename, bprm);
+	if (retval < 0)
+		goto out_free;
+	bprm->exec = bprm->p;
+
+	retval = copy_strings_kernel(bprm->envc, envp, bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = copy_strings_kernel(bprm->argc, argv, bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = bprm_execve(bprm, fd, filename, 0);
+out_free:
+	free_bprm(bprm);
+out_ret:
+	putname(filename);
+	return retval;
+}
+
+static int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
 	const char __user *const __user *__envp)
 {
@@ -2000,7 +2084,7 @@ int do_execve(struct filename *filename,
 	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
 }
 
-int do_execveat(int fd, struct filename *filename,
+static int do_execveat(int fd, struct filename *filename,
 		const char __user *const __user *__argv,
 		const char __user *const __user *__envp,
 		int flags)
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 8e9e1b0c8eb8..0571701ab1c5 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -135,12 +135,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm);
 extern void set_binfmt(struct linux_binfmt *new);
 extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
 
-extern int do_execve(struct filename *,
-		     const char __user * const __user *,
-		     const char __user * const __user *);
-extern int do_execveat(int, struct filename *,
-		       const char __user * const __user *,
-		       const char __user * const __user *,
-		       int);
+int kernel_execve(const char *filename,
+		  const char *const *argv, const char *const *envp);
 
 #endif /* _LINUX_BINFMTS_H */
diff --git a/init/main.c b/init/main.c
index 0ead83e86b5a..78ccec5c28f3 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1329,9 +1329,7 @@ static int run_init_process(const char *init_filename)
 	pr_debug("  with environment:\n");
 	for (p = envp_init; *p; p++)
 		pr_debug("    %s\n", *p);
-	return do_execve(getname_kernel(init_filename),
-		(const char __user *const __user *)argv_init,
-		(const char __user *const __user *)envp_init);
+	return kernel_execve(init_filename, argv_init, envp_init);
 }
 
 static int try_to_run_init_process(const char *init_filename)
diff --git a/kernel/umh.c b/kernel/umh.c
index 6ca2096298b9..a25433f9cd9a 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -98,9 +98,9 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
-	retval = do_execve(getname_kernel(sub_info->path),
-			   (const char __user *const __user *)sub_info->argv,
-			   (const char __user *const __user *)sub_info->envp);
+	retval = kernel_execve(sub_info->path,
+			       (const char *const *)sub_info->argv,
+			       (const char *const *)sub_info->envp);
 out:
 	sub_info->retval = retval;
 	/*
diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
index 050473df5809..85246b9df7ca 100644
--- a/security/tomoyo/common.h
+++ b/security/tomoyo/common.h
@@ -425,7 +425,7 @@ struct tomoyo_request_info {
 	struct tomoyo_obj_info *obj;
 	/*
 	 * For holding parameters specific to execve() request.
-	 * NULL if not dealing do_execve().
+	 * NULL if not dealing execve().
 	 */
 	struct tomoyo_execve *ee;
 	struct tomoyo_domain_info *domain;
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 7869d6a9980b..53b3e1f5f227 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -767,7 +767,7 @@ retry:
 
 	/*
 	 * Check for domain transition preference if "file execute" matched.
-	 * If preference is given, make do_execve() fail if domain transition
+	 * If preference is given, make execve() fail if domain transition
 	 * has failed, for domain transition preference should be used with
 	 * destination domain defined.
 	 */
@@ -810,7 +810,7 @@ force_reset_domain:
 		snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>",
 			 candidate->name);
 		/*
-		 * Make do_execve() fail if domain transition across namespaces
+		 * Make execve() fail if domain transition across namespaces
 		 * has failed.
 		 */
 		reject_on_transition_failure = true;
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index f9adddc42ac8..1f3cd432d830 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -93,7 +93,7 @@ static int tomoyo_bprm_check_security(struct linux_binprm *bprm)
 	struct tomoyo_task *s = tomoyo_task(current);
 
 	/*
-	 * Execute permission is checked against pathname passed to do_execve()
+	 * Execute permission is checked against pathname passed to execve()
 	 * using current domain.
 	 */
 	if (!s->old_domain_info) {
@@ -307,7 +307,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
  */
 static int tomoyo_file_open(struct file *f)
 {
-	/* Don't check read permission here if called from do_execve(). */
+	/* Don't check read permission here if called from execve(). */
 	if (current->in_execve)
 		return 0;
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
-- 
cgit v1.2.3


From d061cd734f1a59798574b50188b14b49e95a54d3 Mon Sep 17 00:00:00 2001
From: Mike Leach <mike.leach@linaro.org>
Date: Thu, 16 Jul 2020 11:57:40 -0600
Subject: coresight: Fix comment in main header file

Comment for an elemnt in the coresight_device structure appears to have
been corrupted and makes no sense. Fix this before making further changes.

Signed-off-by: Mike Leach <mike.leach@linaro.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200716175746.3338735-12-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/coresight.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index e3e9f0e3a878..84dc695e87d4 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -179,7 +179,8 @@ struct coresight_sysfs_link {
  * @enable:	'true' if component is currently part of an active path.
  * @activated:	'true' only if a _sink_ has been activated.  A sink can be
  *		activated but not yet enabled.  Enabling for a _sink_
- *		appens when a source has been selected for that it.
+ *		happens when a source has been selected and a path is enabled
+ *		from source to that sink.
  * @ea:		Device attribute for sink representation under PMU directory.
  * @ect_dev:	Associated cross trigger device. Not part of the trace data
  *		path or connections.
-- 
cgit v1.2.3


From 0336bdfd7354edfa3db0e01675b5df224516e3e9 Mon Sep 17 00:00:00 2001
From: Mike Leach <mike.leach@linaro.org>
Date: Thu, 16 Jul 2020 11:57:43 -0600
Subject: coresight: Add default sink selection to CoreSight base

Adds a method to select a suitable sink connected to a given source.

In cases where no sink is defined, the coresight_find_default_sink
routine can search from a given source, through the child connections
until a suitable sink is found.

The suitability is defined in by the sink coresight_dev_subtype on the
CoreSight device, and the distance from the source by counting
connections.

Higher value subtype is preferred - where these are equal, shorter
distance from source is used as a tie-break.

This allows for default sink to be discovered were none is specified
(e.g. perf command line)

Signed-off-by: Mike Leach <mike.leach@linaro.org>
Suggested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200716175746.3338735-15-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight-priv.h |   2 +
 drivers/hwtracing/coresight/coresight.c      | 166 +++++++++++++++++++++++++++
 include/linux/coresight.h                    |   3 +
 3 files changed, 171 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 36c943ae94d5..f2dc625ea585 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -150,6 +150,8 @@ int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data);
 struct coresight_device *coresight_get_sink(struct list_head *path);
 struct coresight_device *coresight_get_enabled_sink(bool reset);
 struct coresight_device *coresight_get_sink_by_id(u32 id);
+struct coresight_device *
+coresight_find_default_sink(struct coresight_device *csdev);
 struct list_head *coresight_build_path(struct coresight_device *csdev,
 				       struct coresight_device *sink);
 void coresight_release_path(struct list_head *path);
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index f3efbb3b2b4d..e9c90f2de34a 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -769,6 +769,171 @@ void coresight_release_path(struct list_head *path)
 	path = NULL;
 }
 
+/* return true if the device is a suitable type for a default sink */
+static inline bool coresight_is_def_sink_type(struct coresight_device *csdev)
+{
+	/* sink & correct subtype */
+	if (((csdev->type == CORESIGHT_DEV_TYPE_SINK) ||
+	     (csdev->type == CORESIGHT_DEV_TYPE_LINKSINK)) &&
+	    (csdev->subtype.sink_subtype >= CORESIGHT_DEV_SUBTYPE_SINK_BUFFER))
+		return true;
+	return false;
+}
+
+/**
+ * coresight_select_best_sink - return the best sink for use as default from
+ * the two provided.
+ *
+ * @sink:	current best sink.
+ * @depth:      search depth where current sink was found.
+ * @new_sink:	new sink for comparison with current sink.
+ * @new_depth:  search depth where new sink was found.
+ *
+ * Sinks prioritised according to coresight_dev_subtype_sink, with only
+ * subtypes CORESIGHT_DEV_SUBTYPE_SINK_BUFFER or higher being used.
+ *
+ * Where two sinks of equal priority are found, the sink closest to the
+ * source is used (smallest search depth).
+ *
+ * return @new_sink & update @depth if better than @sink, else return @sink.
+ */
+static struct coresight_device *
+coresight_select_best_sink(struct coresight_device *sink, int *depth,
+			   struct coresight_device *new_sink, int new_depth)
+{
+	bool update = false;
+
+	if (!sink) {
+		/* first found at this level */
+		update = true;
+	} else if (new_sink->subtype.sink_subtype >
+		   sink->subtype.sink_subtype) {
+		/* found better sink */
+		update = true;
+	} else if ((new_sink->subtype.sink_subtype ==
+		    sink->subtype.sink_subtype) &&
+		   (*depth > new_depth)) {
+		/* found same but closer sink */
+		update = true;
+	}
+
+	if (update)
+		*depth = new_depth;
+	return update ? new_sink : sink;
+}
+
+/**
+ * coresight_find_sink - recursive function to walk trace connections from
+ * source to find a suitable default sink.
+ *
+ * @csdev: source / current device to check.
+ * @depth: [in] search depth of calling dev, [out] depth of found sink.
+ *
+ * This will walk the connection path from a source (ETM) till a suitable
+ * sink is encountered and return that sink to the original caller.
+ *
+ * If current device is a plain sink return that & depth, otherwise recursively
+ * call child connections looking for a sink. Select best possible using
+ * coresight_select_best_sink.
+ *
+ * return best sink found, or NULL if not found at this node or child nodes.
+ */
+static struct coresight_device *
+coresight_find_sink(struct coresight_device *csdev, int *depth)
+{
+	int i, curr_depth = *depth + 1, found_depth = 0;
+	struct coresight_device *found_sink = NULL;
+
+	if (coresight_is_def_sink_type(csdev)) {
+		found_depth = curr_depth;
+		found_sink = csdev;
+		if (csdev->type == CORESIGHT_DEV_TYPE_SINK)
+			goto return_def_sink;
+		/* look past LINKSINK for something better */
+	}
+
+	/*
+	 * Not a sink we want - or possible child sink may be better.
+	 * recursively explore each port found on this element.
+	 */
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		struct coresight_device *child_dev, *sink = NULL;
+		int child_depth = curr_depth;
+
+		child_dev = csdev->pdata->conns[i].child_dev;
+		if (child_dev)
+			sink = coresight_find_sink(child_dev, &child_depth);
+
+		if (sink)
+			found_sink = coresight_select_best_sink(found_sink,
+								&found_depth,
+								sink,
+								child_depth);
+	}
+
+return_def_sink:
+	/* return found sink and depth */
+	if (found_sink)
+		*depth = found_depth;
+	return found_sink;
+}
+
+/**
+ * coresight_find_default_sink: Find a sink suitable for use as a
+ * default sink.
+ *
+ * @csdev: starting source to find a connected sink.
+ *
+ * Walks connections graph looking for a suitable sink to enable for the
+ * supplied source. Uses CoreSight device subtypes and distance from source
+ * to select the best sink.
+ *
+ * If a sink is found, then the default sink for this device is set and
+ * will be automatically used in future.
+ *
+ * Used in cases where the CoreSight user (perf / sysfs) has not selected a
+ * sink.
+ */
+struct coresight_device *
+coresight_find_default_sink(struct coresight_device *csdev)
+{
+	int depth = 0;
+
+	/* look for a default sink if we have not found for this device */
+	if (!csdev->def_sink)
+		csdev->def_sink = coresight_find_sink(csdev, &depth);
+	return csdev->def_sink;
+}
+
+static int coresight_remove_sink_ref(struct device *dev, void *data)
+{
+	struct coresight_device *sink = data;
+	struct coresight_device *source = to_coresight_device(dev);
+
+	if (source->def_sink == sink)
+		source->def_sink = NULL;
+	return 0;
+}
+
+/**
+ * coresight_clear_default_sink: Remove all default sink references to the
+ * supplied sink.
+ *
+ * If supplied device is a sink, then check all the bus devices and clear
+ * out all the references to this sink from the coresight_device def_sink
+ * parameter.
+ *
+ * @csdev: coresight sink - remove references to this from all sources.
+ */
+static void coresight_clear_default_sink(struct coresight_device *csdev)
+{
+	if ((csdev->type == CORESIGHT_DEV_TYPE_SINK) ||
+	    (csdev->type == CORESIGHT_DEV_TYPE_LINKSINK)) {
+		bus_for_each_dev(&coresight_bustype, NULL, csdev,
+				 coresight_remove_sink_ref);
+	}
+}
+
 /** coresight_validate_source - make sure a source has the right credentials
  *  @csdev:	the device structure for a source.
  *  @function:	the function this was called from.
@@ -1358,6 +1523,7 @@ void coresight_unregister(struct coresight_device *csdev)
 	etm_perf_del_symlink_sink(csdev);
 	/* Remove references of that device in the topology */
 	coresight_remove_conns(csdev);
+	coresight_clear_default_sink(csdev);
 	coresight_release_platform_data(csdev, csdev->pdata);
 	device_unregister(&csdev->dev);
 }
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 84dc695e87d4..58fffdecdbfd 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -48,6 +48,7 @@ enum coresight_dev_subtype_sink {
 	CORESIGHT_DEV_SUBTYPE_SINK_NONE,
 	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
 	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+	CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM,
 };
 
 enum coresight_dev_subtype_link {
@@ -182,6 +183,7 @@ struct coresight_sysfs_link {
  *		happens when a source has been selected and a path is enabled
  *		from source to that sink.
  * @ea:		Device attribute for sink representation under PMU directory.
+ * @def_sink:	cached reference to default sink found for this device.
  * @ect_dev:	Associated cross trigger device. Not part of the trace data
  *		path or connections.
  * @nr_links:   number of sysfs links created to other components from this
@@ -200,6 +202,7 @@ struct coresight_device {
 	/* sink specific fields */
 	bool activated;	/* true only if a sink is part of a path */
 	struct dev_ext_attribute *ea;
+	struct coresight_device *def_sink;
 	/* cross trigger handling */
 	struct coresight_device *ect_dev;
 	/* sysfs links between components */
-- 
cgit v1.2.3


From 5c9fa16e8abd342ce04dc830c1ebb2a03abf6c05 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Fri, 3 Jul 2020 11:19:57 +1000
Subject: powerpc/64s: Remove PROT_SAO support

ISA v3.1 does not support the SAO storage control attribute required to
implement PROT_SAO. PROT_SAO was used by specialised system software
(Lx86) that has been discontinued for about 7 years, and is not thought
to be used elsewhere, so removal should not cause problems.

We rather remove it than keep support for older processors, because
live migrating guest partitions to newer processors may not be possible
if SAO is in use (or worse allowed with silent races).

- PROT_SAO stays in the uapi header so code using it would still build.
- arch_validate_prot() is removed, the generic version rejects PROT_SAO
  so applications would get a failure at mmap() time.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Drop KVM change for the time being]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200703011958.1166620-3-npiggin@gmail.com
---
 arch/powerpc/include/asm/book3s/64/pgtable.h  |  8 +++--
 arch/powerpc/include/asm/cputable.h           | 10 +++----
 arch/powerpc/include/asm/mman.h               | 26 +++--------------
 arch/powerpc/include/asm/nohash/64/pgtable.h  |  2 --
 arch/powerpc/include/uapi/asm/mman.h          |  2 +-
 arch/powerpc/kernel/dt_cpu_ftrs.c             |  2 +-
 arch/powerpc/mm/book3s64/hash_utils.c         |  2 --
 include/linux/mm.h                            |  2 --
 include/trace/events/mmflags.h                |  2 --
 mm/ksm.c                                      |  4 ---
 tools/testing/selftests/powerpc/mm/.gitignore |  1 -
 tools/testing/selftests/powerpc/mm/Makefile   |  4 +--
 tools/testing/selftests/powerpc/mm/prot_sao.c | 42 ---------------------------
 13 files changed, 17 insertions(+), 90 deletions(-)
 delete mode 100644 tools/testing/selftests/powerpc/mm/prot_sao.c

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 495fc0ccb453..6de56c3b33c4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -20,9 +20,13 @@
 #define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
 #define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
-#define _PAGE_SAO		0x00010 /* Strong access order */
+
+#define _PAGE_CACHE_CTL		0x00030 /* Bits for the folowing cache modes */
+			/*	No bits set is normal cacheable memory */
+			/*	0x00010 unused, is SAO bit on radix POWER9 */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
 #define _PAGE_TOLERANT		0x00030 /* tolerant memory, cache inhibited */
+
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
 /*
@@ -824,8 +828,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	return hash__set_pte_at(mm, addr, ptep, pte, percpu);
 }
 
-#define _PAGE_CACHE_CTL	(_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
-
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
 {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index dd0a2e77a695..a461c3300804 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -191,7 +191,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
 #define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
-#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
+// Free					LONG_ASM_CONST(0x0000000008000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
@@ -435,7 +435,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
 	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
@@ -444,7 +444,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_DSCR | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
@@ -455,7 +455,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_DSCR | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
@@ -473,7 +473,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_DSCR | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 4ba303ea27f5..7c07728af300 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -13,38 +13,20 @@
 #include <linux/pkeys.h>
 #include <asm/cpu_has_feature.h>
 
+#ifdef CONFIG_PPC_MEM_KEYS
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
-#ifdef CONFIG_PPC_MEM_KEYS
-	return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
-#else
-	return ((prot & PROT_SAO) ? VM_SAO : 0);
-#endif
+	return pkey_to_vmflag_bits(pkey);
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-#ifdef CONFIG_PPC_MEM_KEYS
-	return (vm_flags & VM_SAO) ?
-		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
-		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
-#else
-	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
-#endif
+	return __pgprot(vmflag_to_pte_pkey_bits(vm_flags));
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-
-static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
-{
-	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
-		return false;
-	if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
-		return false;
-	return true;
-}
-#define arch_validate_prot arch_validate_prot
+#endif
 
 #endif /* CONFIG_PPC64 */
 #endif	/* _ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 6cb8aa357191..59ee9fa4ae09 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -82,8 +82,6 @@
  */
 #include <asm/nohash/pte-book3e.h>
 
-#define _PAGE_SAO	0
-
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
 
 /*
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index c0c737215b00..3a700351feca 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -11,7 +11,7 @@
 #include <asm-generic/mman-common.h>
 
 
-#define PROT_SAO	0x10		/* Strong Access Ordering */
+#define PROT_SAO	0x10		/* Unsupported since v5.9 */
 
 #define MAP_RENAME      MAP_ANONYMOUS   /* In SunOS terminology */
 #define MAP_NORESERVE   0x40            /* don't reserve swap pages */
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 554bec785f6a..9aa8537f7da2 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -622,7 +622,7 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
 	{"no-execute", feat_enable, 0},
-	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+	/* strong-access-ordering is unused */
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
 	{"coprocessor-icswx", feat_enable, 0},
 	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 9dfb0ceed5e3..6f9f346a5f65 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -232,8 +232,6 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		rflags |= HPTE_R_I;
 	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
-	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
-		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
 	else
 		/*
 		 * Add memory coherence if cache inhibited is not set
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc7b87310c10..6c8333d6c991 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -317,8 +317,6 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
-#elif defined(CONFIG_PPC)
-# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
 # define VM_GROWSUP	VM_ARCH_1
 #elif defined(CONFIG_IA64)
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5fb752034386..939092dbcb8b 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -114,8 +114,6 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 
 #if defined(CONFIG_X86)
 #define __VM_ARCH_SPECIFIC_1 {VM_PAT,     "pat"           }
-#elif defined(CONFIG_PPC)
-#define __VM_ARCH_SPECIFIC_1 {VM_SAO,     "sao"           }
 #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64)
 #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP,	"growsup"	}
 #elif !defined(CONFIG_MMU)
diff --git a/mm/ksm.c b/mm/ksm.c
index 4102034cd55a..d1cfa18689b5 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2452,10 +2452,6 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (vma_is_dax(vma))
 			return 0;
 
-#ifdef VM_SAO
-		if (*vm_flags & VM_SAO)
-			return 0;
-#endif
 #ifdef VM_SPARC_ADI
 		if (*vm_flags & VM_SPARC_ADI)
 			return 0;
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 8f841f925baa..8d041f508a51 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,7 +2,6 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
-prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index f9fa0ba7435c..5a86d59441dc 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot
 TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
@@ -12,8 +12,6 @@ include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
 
-$(OUTPUT)/prot_sao: ../utils.c
-
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
deleted file mode 100644
index e2eed65b7735..000000000000
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ /dev/null
@@ -1,42 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2016, Michael Ellerman, IBM Corp.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/mman.h>
-
-#include <asm/cputable.h>
-
-#include "utils.h"
-
-#define SIZE (64 * 1024)
-
-int test_prot_sao(void)
-{
-	char *p;
-
-	/* 2.06 or later should support SAO */
-	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
-
-	/*
-	 * Ensure we can ask for PROT_SAO.
-	 * We can't really verify that it does the right thing, but at least we
-	 * confirm the kernel will accept it.
-	 */
-	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
-		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-	FAIL_IF(p == MAP_FAILED);
-
-	/* Write to the mapping, to at least cause a fault */
-	memset(p, 0xaa, SIZE);
-
-	return 0;
-}
-
-int main(void)
-{
-	return test_harness(test_prot_sao, "prot-sao");
-}
-- 
cgit v1.2.3


From f1d9b23cabc61e58509164c3c3132556476491d2 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Mon, 13 Jul 2020 15:51:59 -0400
Subject: audit: purge audit_log_string from the intra-kernel audit API

audit_log_string() was inteded to be an internal audit function and
since there are only two internal uses, remove them.  Purge all external
uses of it by restructuring code to use an existing audit_log_format()
or using audit_log_format().

Please see the upstream issue
https://github.com/linux-audit/audit-kernel/issues/84

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h     |  5 -----
 kernel/audit.c            |  4 ++--
 security/apparmor/audit.c | 10 ++++------
 security/apparmor/file.c  | 25 +++++++------------------
 security/apparmor/ipc.c   | 46 +++++++++++++++++++++++-----------------------
 security/apparmor/net.c   | 14 ++++++++------
 security/lsm_audit.c      |  4 ++--
 7 files changed, 46 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 523f77494847..b3d859831a31 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -694,9 +694,4 @@ static inline bool audit_loginuid_set(struct task_struct *tsk)
 	return uid_valid(audit_get_loginuid(tsk));
 }
 
-static inline void audit_log_string(struct audit_buffer *ab, const char *buf)
-{
-	audit_log_n_string(ab, buf, strlen(buf));
-}
-
 #endif
diff --git a/kernel/audit.c b/kernel/audit.c
index 8c201f414226..a2f3e34aa724 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -2080,13 +2080,13 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
 	/* We will allow 11 spaces for ' (deleted)' to be appended */
 	pathname = kmalloc(PATH_MAX+11, ab->gfp_mask);
 	if (!pathname) {
-		audit_log_string(ab, "<no_memory>");
+		audit_log_format(ab, "\"<no_memory>\"");
 		return;
 	}
 	p = d_path(path, pathname, PATH_MAX+11);
 	if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
 		/* FIXME: can we save some information here? */
-		audit_log_string(ab, "<too_long>");
+		audit_log_format(ab, "\"<too_long>\"");
 	} else
 		audit_log_untrustedstring(ab, p);
 	kfree(pathname);
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index 597732503815..f7e97c7e80f3 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -57,18 +57,16 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 	struct common_audit_data *sa = ca;
 
 	if (aa_g_audit_header) {
-		audit_log_format(ab, "apparmor=");
-		audit_log_string(ab, aa_audit_type[aad(sa)->type]);
+		audit_log_format(ab, "apparmor=\"%s\"",
+				 aa_audit_type[aad(sa)->type]);
 	}
 
 	if (aad(sa)->op) {
-		audit_log_format(ab, " operation=");
-		audit_log_string(ab, aad(sa)->op);
+		audit_log_format(ab, " operation=\"%s\"", aad(sa)->op);
 	}
 
 	if (aad(sa)->info) {
-		audit_log_format(ab, " info=");
-		audit_log_string(ab, aad(sa)->info);
+		audit_log_format(ab, " info=\"%s\"", aad(sa)->info);
 		if (aad(sa)->error)
 			audit_log_format(ab, " error=%d", aad(sa)->error);
 	}
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
index 9a2d14b7c9f8..92acf9a49405 100644
--- a/security/apparmor/file.c
+++ b/security/apparmor/file.c
@@ -34,20 +34,6 @@ static u32 map_mask_to_chr_mask(u32 mask)
 	return m;
 }
 
-/**
- * audit_file_mask - convert mask to permission string
- * @buffer: buffer to write string to (NOT NULL)
- * @mask: permission mask to convert
- */
-static void audit_file_mask(struct audit_buffer *ab, u32 mask)
-{
-	char str[10];
-
-	aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs,
-			    map_mask_to_chr_mask(mask));
-	audit_log_string(ab, str);
-}
-
 /**
  * file_audit_cb - call back for file specific audit fields
  * @ab: audit_buffer  (NOT NULL)
@@ -57,14 +43,17 @@ static void file_audit_cb(struct audit_buffer *ab, void *va)
 {
 	struct common_audit_data *sa = va;
 	kuid_t fsuid = current_fsuid();
+	char str[10];
 
 	if (aad(sa)->request & AA_AUDIT_FILE_MASK) {
-		audit_log_format(ab, " requested_mask=");
-		audit_file_mask(ab, aad(sa)->request);
+		aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs,
+				    map_mask_to_chr_mask(aad(sa)->request));
+		audit_log_format(ab, " requested_mask=\"%s\"", str);
 	}
 	if (aad(sa)->denied & AA_AUDIT_FILE_MASK) {
-		audit_log_format(ab, " denied_mask=");
-		audit_file_mask(ab, aad(sa)->denied);
+		aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs,
+				    map_mask_to_chr_mask(aad(sa)->denied));
+		audit_log_format(ab, " denied_mask=\"%s\"", str);
 	}
 	if (aad(sa)->request & AA_AUDIT_FILE_MASK) {
 		audit_log_format(ab, " fsuid=%d",
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
index 4ecedffbdd33..fe36d112aad9 100644
--- a/security/apparmor/ipc.c
+++ b/security/apparmor/ipc.c
@@ -20,25 +20,23 @@
 
 /**
  * audit_ptrace_mask - convert mask to permission string
- * @buffer: buffer to write string to (NOT NULL)
  * @mask: permission mask to convert
+ *
+ * Returns: pointer to static string
  */
-static void audit_ptrace_mask(struct audit_buffer *ab, u32 mask)
+static const char *audit_ptrace_mask(u32 mask)
 {
 	switch (mask) {
 	case MAY_READ:
-		audit_log_string(ab, "read");
-		break;
+		return "read";
 	case MAY_WRITE:
-		audit_log_string(ab, "trace");
-		break;
+		return "trace";
 	case AA_MAY_BE_READ:
-		audit_log_string(ab, "readby");
-		break;
+		return "readby";
 	case AA_MAY_BE_TRACED:
-		audit_log_string(ab, "tracedby");
-		break;
+		return "tracedby";
 	}
+	return "";
 }
 
 /* call back to audit ptrace fields */
@@ -47,12 +45,12 @@ static void audit_ptrace_cb(struct audit_buffer *ab, void *va)
 	struct common_audit_data *sa = va;
 
 	if (aad(sa)->request & AA_PTRACE_PERM_MASK) {
-		audit_log_format(ab, " requested_mask=");
-		audit_ptrace_mask(ab, aad(sa)->request);
+		audit_log_format(ab, " requested_mask=\"%s\"",
+				 audit_ptrace_mask(aad(sa)->request));
 
 		if (aad(sa)->denied & AA_PTRACE_PERM_MASK) {
-			audit_log_format(ab, " denied_mask=");
-			audit_ptrace_mask(ab, aad(sa)->denied);
+			audit_log_format(ab, " denied_mask=\"%s\"",
+					 audit_ptrace_mask(aad(sa)->denied));
 		}
 	}
 	audit_log_format(ab, " peer=");
@@ -142,16 +140,18 @@ static inline int map_signal_num(int sig)
 }
 
 /**
- * audit_file_mask - convert mask to permission string
- * @buffer: buffer to write string to (NOT NULL)
+ * audit_signal_mask - convert mask to permission string
  * @mask: permission mask to convert
+ *
+ * Returns: pointer to static string
  */
-static void audit_signal_mask(struct audit_buffer *ab, u32 mask)
+static const char *audit_signal_mask(u32 mask)
 {
 	if (mask & MAY_READ)
-		audit_log_string(ab, "receive");
+		return "receive";
 	if (mask & MAY_WRITE)
-		audit_log_string(ab, "send");
+		return "send";
+	return "";
 }
 
 /**
@@ -164,11 +164,11 @@ static void audit_signal_cb(struct audit_buffer *ab, void *va)
 	struct common_audit_data *sa = va;
 
 	if (aad(sa)->request & AA_SIGNAL_PERM_MASK) {
-		audit_log_format(ab, " requested_mask=");
-		audit_signal_mask(ab, aad(sa)->request);
+		audit_log_format(ab, " requested_mask=\"%s\"",
+				 audit_signal_mask(aad(sa)->request));
 		if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) {
-			audit_log_format(ab, " denied_mask=");
-			audit_signal_mask(ab, aad(sa)->denied);
+			audit_log_format(ab, " denied_mask=\"%s\"",
+					 audit_signal_mask(aad(sa)->denied));
 		}
 	}
 	if (aad(sa)->signal == SIGUNKNOWN)
diff --git a/security/apparmor/net.c b/security/apparmor/net.c
index d8afc39f663a..fa0e85568450 100644
--- a/security/apparmor/net.c
+++ b/security/apparmor/net.c
@@ -72,16 +72,18 @@ void audit_net_cb(struct audit_buffer *ab, void *va)
 {
 	struct common_audit_data *sa = va;
 
-	audit_log_format(ab, " family=");
 	if (address_family_names[sa->u.net->family])
-		audit_log_string(ab, address_family_names[sa->u.net->family]);
+		audit_log_format(ab, " family=\"%s\"",
+				 address_family_names[sa->u.net->family]);
 	else
-		audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family);
-	audit_log_format(ab, " sock_type=");
+		audit_log_format(ab, " family=\"unknown(%d)\"",
+				 sa->u.net->family);
 	if (sock_type_names[aad(sa)->net.type])
-		audit_log_string(ab, sock_type_names[aad(sa)->net.type]);
+		audit_log_format(ab, " sock_type=\"%s\"",
+				 sock_type_names[aad(sa)->net.type]);
 	else
-		audit_log_format(ab, "\"unknown(%d)\"", aad(sa)->net.type);
+		audit_log_format(ab, " sock_type=\"unknown(%d)\"",
+				 aad(sa)->net.type);
 	audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol);
 
 	if (aad(sa)->request & NET_PERMS_MASK) {
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 7c555621c2bd..53d0d183db8f 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -432,8 +432,8 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 				 a->u.ibendport->port);
 		break;
 	case LSM_AUDIT_DATA_LOCKDOWN:
-		audit_log_format(ab, " lockdown_reason=");
-		audit_log_string(ab, lockdown_reasons[a->u.reason]);
+		audit_log_format(ab, " lockdown_reason=\"%s\"",
+				 lockdown_reasons[a->u.reason]);
 		break;
 	} /* switch (a->type) */
 }
-- 
cgit v1.2.3


From 98cc1b93724aa85bd828269855d48d884c702726 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Mon, 20 Jul 2020 15:43:57 -0500
Subject: power_supply: Add additional health properties to the header

Add HEALTH_WARM, HEALTH_COOL and HEALTH_HOT to the health enum.

HEALTH_WARM, HEALTH_COOL, and HEALTH_HOT properties are taken
from JEITA specification JISC8712:2015

Acked-by: Andrew F. Davis <afd@ti.com>
Tested-by: Guru Das Srinagesh <gurus@codeaurora.org>
Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 Documentation/ABI/testing/sysfs-class-power | 3 ++-
 drivers/power/supply/power_supply_sysfs.c   | 3 +++
 include/linux/power_supply.h                | 3 +++
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 216d61a22f1e..40213c73bc9c 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -205,7 +205,8 @@ Description:
 		Valid values: "Unknown", "Good", "Overheat", "Dead",
 			      "Over voltage", "Unspecified failure", "Cold",
 			      "Watchdog timer expire", "Safety timer expire",
-			      "Over current", "Calibration required"
+			      "Over current", "Calibration required", "Warm",
+			      "Cool", "Hot"
 
 What:		/sys/class/power_supply/<supply_name>/precharge_current
 Date:		June 2017
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index af0cad253f52..b903cb4dca2b 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -101,6 +101,9 @@ static const char * const POWER_SUPPLY_HEALTH_TEXT[] = {
 	[POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE]   = "Safety timer expire",
 	[POWER_SUPPLY_HEALTH_OVERCURRENT]	    = "Over current",
 	[POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED]  = "Calibration required",
+	[POWER_SUPPLY_HEALTH_WARM]		    = "Warm",
+	[POWER_SUPPLY_HEALTH_COOL]		    = "Cool",
+	[POWER_SUPPLY_HEALTH_HOT]		    = "Hot",
 };
 
 static const char * const POWER_SUPPLY_TECHNOLOGY_TEXT[] = {
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index ac1345a48ad0..b5ee35d3c304 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -62,6 +62,9 @@ enum {
 	POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE,
 	POWER_SUPPLY_HEALTH_OVERCURRENT,
 	POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED,
+	POWER_SUPPLY_HEALTH_WARM,
+	POWER_SUPPLY_HEALTH_COOL,
+	POWER_SUPPLY_HEALTH_HOT,
 };
 
 enum {
-- 
cgit v1.2.3


From bc4f0548f683a3d53359cef15f088d2d5bb4bc39 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 20 Jul 2020 09:33:58 -0700
Subject: bpf: Compute bpf_skc_to_*() helper socket btf ids at build time

Currently, socket types (struct tcp_sock, udp_sock, etc.)
used by bpf_skc_to_*() helpers are computed when vmlinux_btf
is first built in the kernel.

Commit 5a2798ab32ba
("bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros")
implemented a mechanism to compute btf_ids at kernel build
time which can simplify kernel implementation and reduce
runtime overhead by removing in-kernel btf_id calculation.
This patch did exactly this, removing in-kernel btf_id
computation and utilizing build-time btf_id computation.

If CONFIG_DEBUG_INFO_BTF is not defined, BTF_ID_LIST will
define an array with size of 5, which is not enough for
btf_sock_ids. So define its own static array if
CONFIG_DEBUG_INFO_BTF is not defined.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200720163358.1393023-1-yhs@fb.com
---
 include/linux/bpf.h |  4 ----
 kernel/bpf/btf.c    |  1 -
 net/core/filter.c   | 49 ++++++++++++++++++-------------------------------
 3 files changed, 18 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index adb16bdc5f0a..1df1c0fd3f28 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1541,7 +1541,6 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
-void init_btf_sock_ids(struct btf *btf);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1567,9 +1566,6 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
-static inline void init_btf_sock_ids(struct btf *btf)
-{
-}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 03d6d43bb1d6..315cde73421b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3672,7 +3672,6 @@ struct btf *btf_parse_vmlinux(void)
 		goto errout;
 
 	bpf_struct_ops_init(btf, log);
-	init_btf_sock_ids(btf);
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
diff --git a/net/core/filter.c b/net/core/filter.c
index 2bd129b5ae74..5a65fb4b95ff 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9426,19 +9426,19 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog)
  * sock_common as the first argument in its memory layout.
  */
 #define BTF_SOCK_TYPE_xxx \
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, "inet_sock")			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, "inet_connection_sock")	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, "inet_request_sock")	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, "inet_timewait_sock")	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, "request_sock")		\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, "sock")			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, "sock_common")		\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, "tcp_sock")			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, "tcp_request_sock")	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, "tcp_timewait_sock")	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, "tcp6_sock")			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, "udp_sock")			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, "udp6_sock")
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock)				\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
 
 enum {
 #define BTF_SOCK_TYPE(name, str) name,
@@ -9447,26 +9447,13 @@ BTF_SOCK_TYPE_xxx
 MAX_BTF_SOCK_TYPE,
 };
 
-static int btf_sock_ids[MAX_BTF_SOCK_TYPE];
-
-#ifdef CONFIG_BPF_SYSCALL
-static const char *bpf_sock_types[] = {
-#define BTF_SOCK_TYPE(name, str) str,
+#ifdef CONFIG_DEBUG_INFO_BTF
+BTF_ID_LIST(btf_sock_ids)
+#define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type)
 BTF_SOCK_TYPE_xxx
 #undef BTF_SOCK_TYPE
-};
-
-void init_btf_sock_ids(struct btf *btf)
-{
-	int i, btf_id;
-
-	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) {
-		btf_id = btf_find_by_name_kind(btf, bpf_sock_types[i],
-					       BTF_KIND_STRUCT);
-		if (btf_id > 0)
-			btf_sock_ids[i] = btf_id;
-	}
-}
+#else
+static u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
 static bool check_arg_btf_id(u32 btf_id, u32 arg)
-- 
cgit v1.2.3


From 0f12e584b241285cf60a6227f3771fa444cfcf76 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 20 Jul 2020 09:34:01 -0700
Subject: bpf: Add BTF_ID_LIST_GLOBAL in btf_ids.h

Existing BTF_ID_LIST used a local static variable
to store btf_ids. This patch provided a new macro
BTF_ID_LIST_GLOBAL to store btf_ids in a global
variable which can be shared among multiple files.

The existing BTF_ID_LIST is still retained.
Two reasons. First, BTF_ID_LIST is also used to build
btf_ids for helper arguments which typically
is an array of 5. Since typically different
helpers have different signature, it makes
little sense to share them. Second, some
current computed btf_ids are indeed local.
If later those btf_ids are shared between
different files, they can use BTF_ID_LIST_GLOBAL then.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Link: https://lore.kernel.org/bpf/20200720163401.1393159-1-yhs@fb.com
---
 include/linux/btf_ids.h                            | 10 +++++--
 tools/include/linux/btf_ids.h                      | 10 +++++--
 .../selftests/bpf/prog_tests/resolve_btfids.c      | 33 ++++++++++++++++------
 3 files changed, 39 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 1cdb56950ffe..77ab45baa095 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -57,17 +57,20 @@ asm(							\
  * .zero 4
  *
  */
-#define __BTF_ID_LIST(name)				\
+#define __BTF_ID_LIST(name, scope)			\
 asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
-".local " #name ";                             \n"	\
+"." #scope " " #name ";                        \n"	\
 #name ":;                                      \n"	\
 ".popsection;                                  \n");	\
 
 #define BTF_ID_LIST(name)				\
-__BTF_ID_LIST(name)					\
+__BTF_ID_LIST(name, local)				\
 extern u32 name[];
 
+#define BTF_ID_LIST_GLOBAL(name)			\
+__BTF_ID_LIST(name, globl)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -90,6 +93,7 @@ asm(							\
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
+#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 1cdb56950ffe..77ab45baa095 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -57,17 +57,20 @@ asm(							\
  * .zero 4
  *
  */
-#define __BTF_ID_LIST(name)				\
+#define __BTF_ID_LIST(name, scope)			\
 asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
-".local " #name ";                             \n"	\
+"." #scope " " #name ";                        \n"	\
 #name ":;                                      \n"	\
 ".popsection;                                  \n");	\
 
 #define BTF_ID_LIST(name)				\
-__BTF_ID_LIST(name)					\
+__BTF_ID_LIST(name, local)				\
 extern u32 name[];
 
+#define BTF_ID_LIST_GLOBAL(name)			\
+__BTF_ID_LIST(name, globl)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -90,6 +93,7 @@ asm(							\
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
+#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index 22d83bba4e91..3b127cab4864 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -28,7 +28,17 @@ struct symbol test_symbols[] = {
 	{ "func",    BTF_KIND_FUNC,    -1 },
 };
 
-BTF_ID_LIST(test_list)
+BTF_ID_LIST(test_list_local)
+BTF_ID_UNUSED
+BTF_ID(typedef, S)
+BTF_ID(typedef, T)
+BTF_ID(typedef, U)
+BTF_ID(struct,  S)
+BTF_ID(union,   U)
+BTF_ID(func,    func)
+
+extern __u32 test_list_global[];
+BTF_ID_LIST_GLOBAL(test_list_global)
 BTF_ID_UNUSED
 BTF_ID(typedef, S)
 BTF_ID(typedef, T)
@@ -94,18 +104,25 @@ static int resolve_symbols(void)
 
 int test_resolve_btfids(void)
 {
-	unsigned int i;
+	__u32 *test_list, *test_lists[] = { test_list_local, test_list_global };
+	unsigned int i, j;
 	int ret = 0;
 
 	if (resolve_symbols())
 		return -1;
 
-	/* Check BTF_ID_LIST(test_list) IDs */
-	for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) {
-		ret = CHECK(test_list[i] != test_symbols[i].id,
-			    "id_check",
-			    "wrong ID for %s (%d != %d)\n", test_symbols[i].name,
-			    test_list[i], test_symbols[i].id);
+	/* Check BTF_ID_LIST(test_list_local) and
+	 * BTF_ID_LIST_GLOBAL(test_list_global) IDs
+	 */
+	for (j = 0; j < ARRAY_SIZE(test_lists); j++) {
+		test_list = test_lists[j];
+		for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) {
+			ret = CHECK(test_list[i] != test_symbols[i].id,
+				    "id_check",
+				    "wrong ID for %s (%d != %d)\n",
+				    test_symbols[i].name,
+				    test_list[i], test_symbols[i].id);
+		}
 	}
 
 	return ret;
-- 
cgit v1.2.3


From fce557bcef119a1bc5ab3cb02678cf454bcaf424 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 20 Jul 2020 09:34:02 -0700
Subject: bpf: Make btf_sock_ids global

tcp and udp bpf_iter can reuse some socket ids in
btf_sock_ids, so make it global.

I put the extern definition in btf_ids.h as a central
place so it can be easily discovered by developers.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200720163402.1393427-1-yhs@fb.com
---
 include/linux/btf_ids.h       | 30 ++++++++++++++++++++++++++++++
 net/core/filter.c             | 30 ++----------------------------
 tools/include/linux/btf_ids.h | 30 ++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 77ab45baa095..4867d549e3c1 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -97,4 +97,34 @@ asm(							\
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
+#ifdef CONFIG_NET
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock)				\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+extern u32 btf_sock_ids[];
+#endif
+
 #endif
diff --git a/net/core/filter.c b/net/core/filter.c
index 5a65fb4b95ff..654c346b7d91 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9421,39 +9421,13 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog)
 	bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog);
 }
 
-/* Define a list of socket types which can be the argument for
- * skc_to_*_sock() helpers. All these sockets should have
- * sock_common as the first argument in its memory layout.
- */
-#define BTF_SOCK_TYPE_xxx \
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock)	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock)	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock)	\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock)				\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common)		\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock)		\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
-
-enum {
-#define BTF_SOCK_TYPE(name, str) name,
-BTF_SOCK_TYPE_xxx
-#undef BTF_SOCK_TYPE
-MAX_BTF_SOCK_TYPE,
-};
-
 #ifdef CONFIG_DEBUG_INFO_BTF
-BTF_ID_LIST(btf_sock_ids)
+BTF_ID_LIST_GLOBAL(btf_sock_ids)
 #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type)
 BTF_SOCK_TYPE_xxx
 #undef BTF_SOCK_TYPE
 #else
-static u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
+u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
 static bool check_arg_btf_id(u32 btf_id, u32 arg)
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 77ab45baa095..4867d549e3c1 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -97,4 +97,34 @@ asm(							\
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
+#ifdef CONFIG_NET
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock)				\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+extern u32 btf_sock_ids[];
+#endif
+
 #endif
-- 
cgit v1.2.3


From 951cf368bcb11d6f817709660cf5cd914072c36f Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 20 Jul 2020 09:34:03 -0700
Subject: bpf: net: Use precomputed btf_id for bpf iterators

One additional field btf_id is added to struct
bpf_ctx_arg_aux to store the precomputed btf_ids.
The btf_id is computed at build time with
BTF_ID_LIST or BTF_ID_LIST_GLOBAL macro definitions.
All existing bpf iterators are changed to used
pre-compute btf_ids.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200720163403.1393551-1-yhs@fb.com
---
 include/linux/bpf.h      |  1 +
 kernel/bpf/btf.c         |  5 +++--
 kernel/bpf/map_iter.c    |  7 ++++++-
 kernel/bpf/task_iter.c   | 12 ++++++++++--
 net/ipv4/tcp_ipv4.c      |  4 +++-
 net/ipv4/udp.c           |  4 +++-
 net/ipv6/route.c         |  7 ++++++-
 net/netlink/af_netlink.c |  7 ++++++-
 8 files changed, 38 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1df1c0fd3f28..bae557ff2da8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -668,6 +668,7 @@ struct bpf_jit_poke_descriptor {
 struct bpf_ctx_arg_aux {
 	u32 offset;
 	enum bpf_reg_type reg_type;
+	u32 btf_id;
 };
 
 struct bpf_prog_aux {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 315cde73421b..ee36b7f60936 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3817,16 +3817,17 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		return true;
 
 	/* this is a pointer to another type */
-	info->reg_type = PTR_TO_BTF_ID;
 	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
 		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
 
 		if (ctx_arg_info->offset == off) {
 			info->reg_type = ctx_arg_info->reg_type;
-			break;
+			info->btf_id = ctx_arg_info->btf_id;
+			return true;
 		}
 	}
 
+	info->reg_type = PTR_TO_BTF_ID;
 	if (tgt_prog) {
 		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
 		if (ret > 0) {
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index c69071e334bf..8a7af11b411f 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -4,6 +4,7 @@
 #include <linux/fs.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/btf_ids.h>
 
 struct bpf_iter_seq_map_info {
 	u32 mid;
@@ -81,7 +82,10 @@ static const struct seq_operations bpf_map_seq_ops = {
 	.show	= bpf_map_seq_show,
 };
 
-static const struct bpf_iter_reg bpf_map_reg_info = {
+BTF_ID_LIST(btf_bpf_map_id)
+BTF_ID(struct, bpf_map)
+
+static struct bpf_iter_reg bpf_map_reg_info = {
 	.target			= "bpf_map",
 	.seq_ops		= &bpf_map_seq_ops,
 	.init_seq_private	= NULL,
@@ -96,6 +100,7 @@ static const struct bpf_iter_reg bpf_map_reg_info = {
 
 static int __init bpf_map_iter_init(void)
 {
+	bpf_map_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_map_id;
 	return bpf_iter_reg_target(&bpf_map_reg_info);
 }
 
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 4dbf2b6035f8..2feecf095609 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/fdtable.h>
 #include <linux/filter.h>
+#include <linux/btf_ids.h>
 
 struct bpf_iter_seq_task_common {
 	struct pid_namespace *ns;
@@ -312,7 +313,11 @@ static const struct seq_operations task_file_seq_ops = {
 	.show	= task_file_seq_show,
 };
 
-static const struct bpf_iter_reg task_reg_info = {
+BTF_ID_LIST(btf_task_file_ids)
+BTF_ID(struct, task_struct)
+BTF_ID(struct, file)
+
+static struct bpf_iter_reg task_reg_info = {
 	.target			= "task",
 	.seq_ops		= &task_seq_ops,
 	.init_seq_private	= init_seq_pidns,
@@ -325,7 +330,7 @@ static const struct bpf_iter_reg task_reg_info = {
 	},
 };
 
-static const struct bpf_iter_reg task_file_reg_info = {
+static struct bpf_iter_reg task_file_reg_info = {
 	.target			= "task_file",
 	.seq_ops		= &task_file_seq_ops,
 	.init_seq_private	= init_seq_pidns,
@@ -344,10 +349,13 @@ static int __init task_iter_init(void)
 {
 	int ret;
 
+	task_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
 	ret = bpf_iter_reg_target(&task_reg_info);
 	if (ret)
 		return ret;
 
+	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
+	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
 	return bpf_iter_reg_target(&task_file_reg_info);
 }
 late_initcall(task_iter_init);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 116c11a0aaed..a7f1b41482f8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -76,6 +76,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/inetdevice.h>
+#include <linux/btf_ids.h>
 
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
@@ -2954,7 +2955,7 @@ static void bpf_iter_fini_tcp(void *priv_data)
 	bpf_iter_fini_seq_net(priv_data);
 }
 
-static const struct bpf_iter_reg tcp_reg_info = {
+static struct bpf_iter_reg tcp_reg_info = {
 	.target			= "tcp",
 	.seq_ops		= &bpf_iter_tcp_seq_ops,
 	.init_seq_private	= bpf_iter_init_tcp,
@@ -2969,6 +2970,7 @@ static const struct bpf_iter_reg tcp_reg_info = {
 
 static void __init bpf_iter_register(void)
 {
+	tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON];
 	if (bpf_iter_reg_target(&tcp_reg_info))
 		pr_warn("Warning: could not register bpf iterator tcp\n");
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b738c63d7a77..b5231ab350e0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -106,6 +106,7 @@
 #include <net/xfrm.h>
 #include <trace/events/udp.h>
 #include <linux/static_key.h>
+#include <linux/btf_ids.h>
 #include <trace/events/skb.h>
 #include <net/busy_poll.h>
 #include "udp_impl.h"
@@ -3232,7 +3233,7 @@ static void bpf_iter_fini_udp(void *priv_data)
 	bpf_iter_fini_seq_net(priv_data);
 }
 
-static const struct bpf_iter_reg udp_reg_info = {
+static struct bpf_iter_reg udp_reg_info = {
 	.target			= "udp",
 	.seq_ops		= &bpf_iter_udp_seq_ops,
 	.init_seq_private	= bpf_iter_init_udp,
@@ -3247,6 +3248,7 @@ static const struct bpf_iter_reg udp_reg_info = {
 
 static void __init bpf_iter_register(void)
 {
+	udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP];
 	if (bpf_iter_reg_target(&udp_reg_info))
 		pr_warn("Warning: could not register bpf iterator udp\n");
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 427b81cbc164..33f5efbad0a9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -61,6 +61,7 @@
 #include <net/l3mdev.h>
 #include <net/ip.h>
 #include <linux/uaccess.h>
+#include <linux/btf_ids.h>
 
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
@@ -6423,7 +6424,10 @@ void __init ip6_route_init_special_entries(void)
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
 DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt)
 
-static const struct bpf_iter_reg ipv6_route_reg_info = {
+BTF_ID_LIST(btf_fib6_info_id)
+BTF_ID(struct, fib6_info)
+
+static struct bpf_iter_reg ipv6_route_reg_info = {
 	.target			= "ipv6_route",
 	.seq_ops		= &ipv6_route_seq_ops,
 	.init_seq_private	= bpf_iter_init_seq_net,
@@ -6438,6 +6442,7 @@ static const struct bpf_iter_reg ipv6_route_reg_info = {
 
 static int __init bpf_iter_register(void)
 {
+	ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id;
 	return bpf_iter_reg_target(&ipv6_route_reg_info);
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4f2c3b14ddbf..3cd58f0c2de4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -60,6 +60,7 @@
 #include <linux/genetlink.h>
 #include <linux/net_namespace.h>
 #include <linux/nospec.h>
+#include <linux/btf_ids.h>
 
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -2803,7 +2804,10 @@ static const struct rhashtable_params netlink_rhashtable_params = {
 };
 
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
-static const struct bpf_iter_reg netlink_reg_info = {
+BTF_ID_LIST(btf_netlink_sock_id)
+BTF_ID(struct, netlink_sock)
+
+static struct bpf_iter_reg netlink_reg_info = {
 	.target			= "netlink",
 	.seq_ops		= &netlink_seq_ops,
 	.init_seq_private	= bpf_iter_init_seq_net,
@@ -2818,6 +2822,7 @@ static const struct bpf_iter_reg netlink_reg_info = {
 
 static int __init bpf_iter_register(void)
 {
+	netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id;
 	return bpf_iter_reg_target(&netlink_reg_info);
 }
 #endif
-- 
cgit v1.2.3


From 76abf9cea6c8215ea45b9359f11f0e30127c544a Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Thu, 16 Jul 2020 15:20:33 -0700
Subject: remoteproc: Pass size and offset as arguments to segment dump
 function

Change the segment dump API signature to include size and offset
arguments. Refactor the qcom_q6v5_mss driver to use these
arguments while copying the segment. Doing this lays the ground
work for "inline" coredump functionality being added in the next
patch.

Tested-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Link: https://lore.kernel.org/r/1594938035-7327-4-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/qcom_q6v5_mss.c       | 10 +++++-----
 drivers/remoteproc/remoteproc_coredump.c |  5 +++--
 include/linux/remoteproc.h               |  5 +++--
 3 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 1ee809b772ff..a3c412a3f143 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -1202,7 +1202,7 @@ out:
 
 static void qcom_q6v5_dump_segment(struct rproc *rproc,
 				   struct rproc_dump_segment *segment,
-				   void *dest)
+				   void *dest, size_t cp_offset, size_t size)
 {
 	int ret = 0;
 	struct q6v5 *qproc = rproc->priv;
@@ -1222,16 +1222,16 @@ static void qcom_q6v5_dump_segment(struct rproc *rproc,
 	}
 
 	if (!ret)
-		ptr = ioremap_wc(qproc->mpss_phys + offset, segment->size);
+		ptr = ioremap_wc(qproc->mpss_phys + offset + cp_offset, size);
 
 	if (ptr) {
-		memcpy(dest, ptr, segment->size);
+		memcpy(dest, ptr, size);
 		iounmap(ptr);
 	} else {
-		memset(dest, 0xff, segment->size);
+		memset(dest, 0xff, size);
 	}
 
-	qproc->current_dump_size += segment->size;
+	qproc->current_dump_size += size;
 
 	/* Reclaim mba after copying segments */
 	if (qproc->current_dump_size == qproc->total_dump_size) {
diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index ded02442374a..390f563ec019 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -72,7 +72,8 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc,
 				      dma_addr_t da, size_t size,
 				      void (*dumpfn)(struct rproc *rproc,
 						     struct rproc_dump_segment *segment,
-						     void *dest),
+						     void *dest, size_t offset,
+						     size_t size),
 				      void *priv)
 {
 	struct rproc_dump_segment *segment;
@@ -183,7 +184,7 @@ void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_align(class, phdr, 0);
 
 		if (segment->dump) {
-			segment->dump(rproc, segment, data + offset);
+			segment->dump(rproc, segment, data + offset, 0, segment->size);
 		} else {
 			ptr = rproc_da_to_va(rproc, segment->da, segment->size);
 			if (!ptr) {
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 7c0567029f7c..5dab13b6baae 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -456,7 +456,7 @@ struct rproc_dump_segment {
 
 	void *priv;
 	void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment,
-		     void *dest);
+		     void *dest, size_t offset, size_t size);
 	loff_t offset;
 };
 
@@ -638,7 +638,8 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc,
 				      dma_addr_t da, size_t size,
 				      void (*dumpfn)(struct rproc *rproc,
 						     struct rproc_dump_segment *segment,
-						     void *dest),
+						     void *dest, size_t offset,
+						     size_t size),
 				      void *priv);
 int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine);
 
-- 
cgit v1.2.3


From c97319881c9116dc7c56dd30115567b4078c4ba6 Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Thu, 16 Jul 2020 15:20:34 -0700
Subject: remoteproc: Add inline coredump functionality

The current coredump implementation uses vmalloc area to copy
all the segments. But this might put strain on low memory targets
as the firmware size sometimes is in tens of MBs. The situation
becomes worse if there are multiple remote processors undergoing
recovery at the same time. This patch adds inline coredump
functionality that avoids extra memory usage. This requires
recovery to be halted until data is read by userspace and free
function is called.

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Tested-by: Sibi Sankar <sibis@codeaurora.org>
Link: https://lore.kernel.org/r/1594938035-7327-5-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_coredump.c | 156 +++++++++++++++++++++++++++----
 include/linux/remoteproc.h               |  16 ++++
 2 files changed, 154 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index 390f563ec019..bb15a29038e8 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2020, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/completion.h>
 #include <linux/devcoredump.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -12,6 +13,12 @@
 #include "remoteproc_internal.h"
 #include "remoteproc_elf_helpers.h"
 
+struct rproc_coredump_state {
+	struct rproc *rproc;
+	void *header;
+	struct completion dump_done;
+};
+
 /**
  * rproc_coredump_cleanup() - clean up dump_segments list
  * @rproc: the remote processor handle
@@ -115,12 +122,110 @@ int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine)
 }
 EXPORT_SYMBOL(rproc_coredump_set_elf_info);
 
+static void rproc_coredump_free(void *data)
+{
+	struct rproc_coredump_state *dump_state = data;
+
+	vfree(dump_state->header);
+	complete(&dump_state->dump_done);
+}
+
+static void *rproc_coredump_find_segment(loff_t user_offset,
+					 struct list_head *segments,
+					 size_t *data_left)
+{
+	struct rproc_dump_segment *segment;
+
+	list_for_each_entry(segment, segments, node) {
+		if (user_offset < segment->size) {
+			*data_left = segment->size - user_offset;
+			return segment;
+		}
+		user_offset -= segment->size;
+	}
+
+	*data_left = 0;
+	return NULL;
+}
+
+static void rproc_copy_segment(struct rproc *rproc, void *dest,
+			       struct rproc_dump_segment *segment,
+			       size_t offset, size_t size)
+{
+	void *ptr;
+
+	if (segment->dump) {
+		segment->dump(rproc, segment, dest, offset, size);
+	} else {
+		ptr = rproc_da_to_va(rproc, segment->da + offset, size);
+		if (!ptr) {
+			dev_err(&rproc->dev,
+				"invalid copy request for segment %pad with offset %zu and size %zu)\n",
+				&segment->da, offset, size);
+			memset(dest, 0xff, size);
+		} else {
+			memcpy(dest, ptr, size);
+		}
+	}
+}
+
+static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count,
+				   void *data, size_t header_sz)
+{
+	size_t seg_data, bytes_left = count;
+	ssize_t copy_sz;
+	struct rproc_dump_segment *seg;
+	struct rproc_coredump_state *dump_state = data;
+	struct rproc *rproc = dump_state->rproc;
+	void *elfcore = dump_state->header;
+
+	/* Copy the vmalloc'ed header first. */
+	if (offset < header_sz) {
+		copy_sz = memory_read_from_buffer(buffer, count, &offset,
+						  elfcore, header_sz);
+
+		return copy_sz;
+	}
+
+	/*
+	 * Find out the segment memory chunk to be copied based on offset.
+	 * Keep copying data until count bytes are read.
+	 */
+	while (bytes_left) {
+		seg = rproc_coredump_find_segment(offset - header_sz,
+						  &rproc->dump_segments,
+						  &seg_data);
+		/* EOF check */
+		if (!seg) {
+			dev_info(&rproc->dev, "Ramdump done, %lld bytes read",
+				 offset);
+			break;
+		}
+
+		copy_sz = min_t(size_t, bytes_left, seg_data);
+
+		rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data,
+				   copy_sz);
+
+		offset += copy_sz;
+		buffer += copy_sz;
+		bytes_left -= copy_sz;
+	}
+
+	return count - bytes_left;
+}
+
 /**
  * rproc_coredump() - perform coredump
  * @rproc:	rproc handle
  *
  * This function will generate an ELF header for the registered segments
- * and create a devcoredump device associated with rproc.
+ * and create a devcoredump device associated with rproc. Based on the
+ * coredump configuration this function will directly copy the segments
+ * from device memory to userspace or copy segments from device memory to
+ * a separate buffer, which can then be read by userspace.
+ * The first approach avoids using extra vmalloc memory. But it will stall
+ * recovery flow until dump is read by userspace.
  */
 void rproc_coredump(struct rproc *rproc)
 {
@@ -130,11 +235,13 @@ void rproc_coredump(struct rproc *rproc)
 	size_t data_size;
 	size_t offset;
 	void *data;
-	void *ptr;
 	u8 class = rproc->elf_class;
 	int phnum = 0;
+	struct rproc_coredump_state dump_state;
+	enum rproc_dump_mechanism dump_conf = rproc->dump_conf;
 
-	if (list_empty(&rproc->dump_segments))
+	if (list_empty(&rproc->dump_segments) ||
+	    dump_conf == RPROC_COREDUMP_DISABLED)
 		return;
 
 	if (class == ELFCLASSNONE) {
@@ -144,7 +251,14 @@ void rproc_coredump(struct rproc *rproc)
 
 	data_size = elf_size_of_hdr(class);
 	list_for_each_entry(segment, &rproc->dump_segments, node) {
-		data_size += elf_size_of_phdr(class) + segment->size;
+		/*
+		 * For default configuration buffer includes headers & segments.
+		 * For inline dump buffer just includes headers as segments are
+		 * directly read from device memory.
+		 */
+		data_size += elf_size_of_phdr(class);
+		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+			data_size += segment->size;
 
 		phnum++;
 	}
@@ -183,23 +297,29 @@ void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X);
 		elf_phdr_set_p_align(class, phdr, 0);
 
-		if (segment->dump) {
-			segment->dump(rproc, segment, data + offset, 0, segment->size);
-		} else {
-			ptr = rproc_da_to_va(rproc, segment->da, segment->size);
-			if (!ptr) {
-				dev_err(&rproc->dev,
-					"invalid coredump segment (%pad, %zu)\n",
-					&segment->da, segment->size);
-				memset(data + offset, 0xff, segment->size);
-			} else {
-				memcpy(data + offset, ptr, segment->size);
-			}
-		}
+		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+			rproc_copy_segment(rproc, data + offset, segment, 0,
+					   segment->size);
 
 		offset += elf_phdr_get_p_filesz(class, phdr);
 		phdr += elf_size_of_phdr(class);
 	}
+	if (dump_conf == RPROC_COREDUMP_DEFAULT) {
+		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
+		return;
+	}
+
+	/* Initialize the dump state struct to be used by rproc_coredump_read */
+	dump_state.rproc = rproc;
+	dump_state.header = data;
+	init_completion(&dump_state.dump_done);
+
+	dev_coredumpm(&rproc->dev, NULL, &dump_state, data_size, GFP_KERNEL,
+		      rproc_coredump_read, rproc_coredump_free);
 
-	dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
+	/*
+	 * Wait until the dump is read and free is called. Data is freed
+	 * by devcoredump framework automatically after 5 minutes.
+	 */
+	wait_for_completion(&dump_state.dump_done);
 }
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 5dab13b6baae..0e8d2ff575b4 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -439,6 +439,20 @@ enum rproc_crash_type {
 	RPROC_FATAL_ERROR,
 };
 
+/**
+ * enum rproc_dump_mechanism - Coredump options for core
+ * @RPROC_COREDUMP_DEFAULT:	Copy dump to separate buffer and carry on with
+				recovery
+ * @RPROC_COREDUMP_INLINE:	Read segments directly from device memory. Stall
+				recovery until all segments are read
+ * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
+ */
+enum rproc_dump_mechanism {
+	RPROC_COREDUMP_DEFAULT,
+	RPROC_COREDUMP_INLINE,
+	RPROC_COREDUMP_DISABLED,
+};
+
 /**
  * struct rproc_dump_segment - segment info from ELF header
  * @node:	list node related to the rproc segment list
@@ -471,6 +485,7 @@ struct rproc_dump_segment {
  * @dev: virtual device for refcounting and common remoteproc behavior
  * @power: refcount of users who need this rproc powered up
  * @state: state of the device
+ * @dump_conf: Currently selected coredump configuration
  * @lock: lock which protects concurrent manipulations of the rproc
  * @dbg_dir: debugfs directory of this rproc device
  * @traces: list of trace buffers
@@ -505,6 +520,7 @@ struct rproc {
 	struct device dev;
 	atomic_t power;
 	unsigned int state;
+	enum rproc_dump_mechanism dump_conf;
 	struct mutex lock;
 	struct dentry *dbg_dir;
 	struct list_head traces;
-- 
cgit v1.2.3


From 53aab92dec447f93489e07924e310d605a389dea Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 21 Jul 2020 10:17:16 -0700
Subject: Input: synaptics-rmi4 - drop a duplicated word

Drop the repeated word "to" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20200719003131.21050-1-rdunlap@infradead.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/rmi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/rmi.h b/include/linux/rmi.h
index 7b22366d0065..8ed37f93f3c8 100644
--- a/include/linux/rmi.h
+++ b/include/linux/rmi.h
@@ -206,7 +206,7 @@ struct rmi_device_platform_data_spi {
  *
  * @reset_delay_ms - after issuing a reset command to the touch sensor, the
  * driver waits a few milliseconds to give the firmware a chance to
- * to re-initialize.  You can override the default wait period here.
+ * re-initialize.  You can override the default wait period here.
  * @irq: irq associated with the attn gpio line, or negative
  */
 struct rmi_device_platform_data {
-- 
cgit v1.2.3


From 1571e700fd610c39e8b50b0110b1ee9badb2fe6a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Jul 2020 12:04:36 +0100
Subject: net: phylink: in-band pause mode advertisement update for PCS

Re-code the pause in-band advertisement update in light of the addition
of PCS support, so that we perform the minimum required; only the PCS
configuration function needs to be called in this case, followed by the
request to trigger a restart of negotiation if the programmed
advertisement changed.

We need to change the pcs_config() signature to pass whether resolved
pause should be passed to the MAC for setups such as mvneta and mvpp2
where doing so overrides the MAC manual flow controls.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 55 +++++++++++++++++++++++++++++++++++++++++++----
 include/linux/phylink.h   |  7 ++++--
 2 files changed, 56 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 452d509803ca..84a426401102 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -441,7 +441,9 @@ static void phylink_pcs_config(struct phylink *pl, bool force_restart,
 	if (pl->pcs_ops && pl->pcs_ops->pcs_config(pl->config,
 						   pl->cur_link_an_mode,
 						   state->interface,
-						   state->advertising))
+						   state->advertising,
+						   !!(pl->link_config.pause &
+						      MLO_PAUSE_AN)))
 		restart = true;
 
 	phylink_mac_config(pl, state);
@@ -450,6 +452,49 @@ static void phylink_pcs_config(struct phylink *pl, bool force_restart,
 		phylink_mac_pcs_an_restart(pl);
 }
 
+/*
+ * Reconfigure for a change of inband advertisement.
+ * If we have a separate PCS, we only need to call its pcs_config() method,
+ * and then restart AN if it indicates something changed. Otherwise, we do
+ * the full MAC reconfiguration.
+ */
+static int phylink_change_inband_advert(struct phylink *pl)
+{
+	int ret;
+
+	if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state))
+		return 0;
+
+	if (!pl->pcs_ops) {
+		/* Legacy method */
+		phylink_mac_config(pl, &pl->link_config);
+		phylink_mac_pcs_an_restart(pl);
+		return 0;
+	}
+
+	phylink_dbg(pl, "%s: mode=%s/%s adv=%*pb pause=%02x\n", __func__,
+		    phylink_an_mode_str(pl->cur_link_an_mode),
+		    phy_modes(pl->link_config.interface),
+		    __ETHTOOL_LINK_MODE_MASK_NBITS, pl->link_config.advertising,
+		    pl->link_config.pause);
+
+	/* Modern PCS-based method; update the advert at the PCS, and
+	 * restart negotiation if the pcs_config() helper indicates that
+	 * the programmed advertisement has changed.
+	 */
+	ret = pl->pcs_ops->pcs_config(pl->config, pl->cur_link_an_mode,
+				      pl->link_config.interface,
+				      pl->link_config.advertising,
+				      !!(pl->link_config.pause & MLO_PAUSE_AN));
+	if (ret < 0)
+		return ret;
+
+	if (ret > 0)
+		phylink_mac_pcs_an_restart(pl);
+
+	return 0;
+}
+
 static void phylink_mac_pcs_get_state(struct phylink *pl,
 				      struct phylink_link_state *state)
 {
@@ -1524,9 +1569,11 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 
 	config->pause = pause_state;
 
-	if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED,
-				     &pl->phylink_disable_state))
-		phylink_pcs_config(pl, true, &pl->link_config);
+	/* Update our in-band advertisement, triggering a renegotiation if
+	 * the advertisement changed.
+	 */
+	if (!pl->phydev)
+		phylink_change_inband_advert(pl);
 
 	mutex_unlock(&pl->state_mutex);
 
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index b32b8b45421b..d9913d8e6b91 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -286,7 +286,8 @@ struct phylink_pcs_ops {
 			      struct phylink_link_state *state);
 	int (*pcs_config)(struct phylink_config *config, unsigned int mode,
 			  phy_interface_t interface,
-			  const unsigned long *advertising);
+			  const unsigned long *advertising,
+			  bool permit_pause_to_mac);
 	void (*pcs_an_restart)(struct phylink_config *config);
 	void (*pcs_link_up)(struct phylink_config *config, unsigned int mode,
 			    phy_interface_t interface, int speed, int duplex);
@@ -317,9 +318,11 @@ void pcs_get_state(struct phylink_config *config,
  * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
  * @interface: interface mode to be used
  * @advertising: adertisement ethtool link mode mask
+ * @permit_pause_to_mac: permit forwarding pause resolution to MAC
  *
  * Configure the PCS for the operating mode, the interface mode, and set
- * the advertisement mask.
+ * the advertisement mask. @permit_pause_to_mac indicates whether the
+ * hardware may forward the pause mode resolution to the MAC.
  *
  * When operating in %MLO_AN_INBAND, inband should always be enabled,
  * otherwise inband should be disabled.
-- 
cgit v1.2.3


From b7ad14c2fe2d4b2abee491e3adfa3d0123aa2d8c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Jul 2020 12:04:41 +0100
Subject: net: phylink: re-implement interface configuration with PCS

With PCS support, how we implement interface reconfiguration (or other
major reconfiguration) is not up to the job; we end up reconfiguring
the PCS for an interface change while the link could potentially be up.
In order to solve this, add two additional MAC methods for major
configuration, one to prepare for the change, and one to finish the
change.

This allows mvneta and mvpp2 to shutdown what they require prior to the
MAC and PCS configuration calls, and then restart as appropriate.

This impacts ksettings_set(), which now needs to identify whether the
change is a minor tweak to the advertisement masks or whether the
interface mode has changed, and call the appropriate function for that
update.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 75 ++++++++++++++++++++++++++++++++---------------
 include/linux/phylink.h   | 48 ++++++++++++++++++++++++++++++
 2 files changed, 100 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 84a426401102..d554a0fbb4f3 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -433,23 +433,47 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl)
 	}
 }
 
-static void phylink_pcs_config(struct phylink *pl, bool force_restart,
-			       const struct phylink_link_state *state)
+static void phylink_major_config(struct phylink *pl, bool restart,
+				  const struct phylink_link_state *state)
 {
-	bool restart = force_restart;
+	int err;
+
+	phylink_dbg(pl, "major config %s\n", phy_modes(state->interface));
 
-	if (pl->pcs_ops && pl->pcs_ops->pcs_config(pl->config,
-						   pl->cur_link_an_mode,
-						   state->interface,
-						   state->advertising,
-						   !!(pl->link_config.pause &
-						      MLO_PAUSE_AN)))
-		restart = true;
+	if (pl->mac_ops->mac_prepare) {
+		err = pl->mac_ops->mac_prepare(pl->config, pl->cur_link_an_mode,
+					       state->interface);
+		if (err < 0) {
+			phylink_err(pl, "mac_prepare failed: %pe\n",
+				    ERR_PTR(err));
+			return;
+		}
+	}
 
 	phylink_mac_config(pl, state);
 
+	if (pl->pcs_ops) {
+		err = pl->pcs_ops->pcs_config(pl->config, pl->cur_link_an_mode,
+					      state->interface,
+					      state->advertising,
+					      !!(pl->link_config.pause &
+						 MLO_PAUSE_AN));
+		if (err < 0)
+			phylink_err(pl, "pcs_config failed: %pe\n",
+				    ERR_PTR(err));
+		if (err > 0)
+			restart = true;
+	}
 	if (restart)
 		phylink_mac_pcs_an_restart(pl);
+
+	if (pl->mac_ops->mac_finish) {
+		err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode,
+					      state->interface);
+		if (err < 0)
+			phylink_err(pl, "mac_prepare failed: %pe\n",
+				    ERR_PTR(err));
+	}
 }
 
 /*
@@ -555,7 +579,7 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
 	link_state.link = false;
 
 	phylink_apply_manual_flow(pl, &link_state);
-	phylink_pcs_config(pl, force_restart, &link_state);
+	phylink_major_config(pl, force_restart, &link_state);
 }
 
 static const char *phylink_pause_to_str(int pause)
@@ -674,7 +698,7 @@ static void phylink_resolve(struct work_struct *w)
 				phylink_link_down(pl);
 				cur_link_state = false;
 			}
-			phylink_pcs_config(pl, false, &link_state);
+			phylink_major_config(pl, false, &link_state);
 			pl->link_config.interface = link_state.interface;
 		} else if (!pl->pcs_ops) {
 			/* The interface remains unchanged, only the speed,
@@ -1450,21 +1474,26 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 		return -EINVAL;
 
 	mutex_lock(&pl->state_mutex);
-	linkmode_copy(pl->link_config.advertising, config.advertising);
-	pl->link_config.interface = config.interface;
 	pl->link_config.speed = config.speed;
 	pl->link_config.duplex = config.duplex;
 	pl->link_config.an_enabled = config.an_enabled;
 
-	if (pl->cur_link_an_mode == MLO_AN_INBAND &&
-	    !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) {
-		/* If in 802.3z mode, this updates the advertisement.
-		 *
-		 * If we are in SGMII mode without a PHY, there is no
-		 * advertisement; the only thing we have is the pause
-		 * modes which can only come from a PHY.
-		 */
-		phylink_pcs_config(pl, true, &pl->link_config);
+	if (pl->link_config.interface != config.interface) {
+		/* The interface changed, e.g. 1000base-X <-> 2500base-X */
+		/* We need to force the link down, then change the interface */
+		if (pl->old_link_state) {
+			phylink_link_down(pl);
+			pl->old_link_state = false;
+		}
+		if (!test_bit(PHYLINK_DISABLE_STOPPED,
+			      &pl->phylink_disable_state))
+			phylink_major_config(pl, false, &config);
+		pl->link_config.interface = config.interface;
+		linkmode_copy(pl->link_config.advertising, config.advertising);
+	} else if (!linkmode_equal(pl->link_config.advertising,
+				   config.advertising)) {
+		linkmode_copy(pl->link_config.advertising, config.advertising);
+		phylink_change_inband_advert(pl);
 	}
 	mutex_unlock(&pl->state_mutex);
 
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index d9913d8e6b91..2f1315f32113 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -76,7 +76,9 @@ struct phylink_config {
  * struct phylink_mac_ops - MAC operations structure.
  * @validate: Validate and update the link configuration.
  * @mac_pcs_get_state: Read the current link state from the hardware.
+ * @mac_prepare: prepare for a major reconfiguration of the interface.
  * @mac_config: configure the MAC for the selected mode and state.
+ * @mac_finish: finish a major reconfiguration of the interface.
  * @mac_an_restart: restart 802.3z BaseX autonegotiation.
  * @mac_link_down: take the link down.
  * @mac_link_up: allow the link to come up.
@@ -89,8 +91,12 @@ struct phylink_mac_ops {
 			 struct phylink_link_state *state);
 	void (*mac_pcs_get_state)(struct phylink_config *config,
 				  struct phylink_link_state *state);
+	int (*mac_prepare)(struct phylink_config *config, unsigned int mode,
+			   phy_interface_t iface);
 	void (*mac_config)(struct phylink_config *config, unsigned int mode,
 			   const struct phylink_link_state *state);
+	int (*mac_finish)(struct phylink_config *config, unsigned int mode,
+			  phy_interface_t iface);
 	void (*mac_an_restart)(struct phylink_config *config);
 	void (*mac_link_down)(struct phylink_config *config, unsigned int mode,
 			      phy_interface_t interface);
@@ -145,6 +151,31 @@ void validate(struct phylink_config *config, unsigned long *supported,
 void mac_pcs_get_state(struct phylink_config *config,
 		       struct phylink_link_state *state);
 
+/**
+ * mac_prepare() - prepare to change the PHY interface mode
+ * @config: a pointer to a &struct phylink_config.
+ * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
+ * @iface: interface mode to switch to
+ *
+ * phylink will call this method at the beginning of a full initialisation
+ * of the link, which includes changing the interface mode or at initial
+ * startup time. It may be called for the current mode. The MAC driver
+ * should perform whatever actions are required, e.g. disabling the
+ * Serdes PHY.
+ *
+ * This will be the first call in the sequence:
+ * - mac_prepare()
+ * - mac_config()
+ * - pcs_config()
+ * - possible pcs_an_restart()
+ * - mac_finish()
+ *
+ * Returns zero on success, or negative errno on failure which will be
+ * reported to the kernel log.
+ */
+int mac_prepare(struct phylink_config *config, unsigned int mode,
+		phy_interface_t iface);
+
 /**
  * mac_config() - configure the MAC for the selected mode and state
  * @config: a pointer to a &struct phylink_config.
@@ -220,6 +251,23 @@ void mac_pcs_get_state(struct phylink_config *config,
 void mac_config(struct phylink_config *config, unsigned int mode,
 		const struct phylink_link_state *state);
 
+/**
+ * mac_finish() - finish a to change the PHY interface mode
+ * @config: a pointer to a &struct phylink_config.
+ * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
+ * @iface: interface mode to switch to
+ *
+ * phylink will call this if it called mac_prepare() to allow the MAC to
+ * complete any necessary steps after the MAC and PCS have been configured
+ * for the @mode and @iface. E.g. a MAC driver may wish to re-enable the
+ * Serdes PHY here if it was previously disabled by mac_prepare().
+ *
+ * Returns zero on success, or negative errno on failure which will be
+ * reported to the kernel log.
+ */
+int mac_finish(struct phylink_config *config, unsigned int mode,
+		phy_interface_t iface);
+
 /**
  * mac_an_restart() - restart 802.3z BaseX autonegotiation
  * @config: a pointer to a &struct phylink_config.
-- 
cgit v1.2.3


From 7137e18f6f889a67046d5004e1690a32d7d2108d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Jul 2020 12:04:46 +0100
Subject: net: phylink: add struct phylink_pcs

Add a way for MAC PCS to have private data while keeping independence
from struct phylink_config, which is used for the MAC itself. We need
this independence as we will have stand-alone code for PCS that is
independent of the MAC.  Introduce struct phylink_pcs, which is
designed to be embedded in a driver private data structure.

This structure does not include a mdio_device as there are PCS
implementations such as the Marvell DSA and network drivers where this
is not necessary.

Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 34 ++++++++++++++++++++++++++--------
 include/linux/phylink.h   | 45 ++++++++++++++++++++++++++++++---------------
 2 files changed, 56 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index d554a0fbb4f3..b57cd2142786 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -43,6 +43,7 @@ struct phylink {
 	const struct phylink_mac_ops *mac_ops;
 	const struct phylink_pcs_ops *pcs_ops;
 	struct phylink_config *config;
+	struct phylink_pcs *pcs;
 	struct device *dev;
 	unsigned int old_link_state:1;
 
@@ -427,7 +428,7 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl)
 	    phy_interface_mode_is_8023z(pl->link_config.interface) &&
 	    phylink_autoneg_inband(pl->cur_link_an_mode)) {
 		if (pl->pcs_ops)
-			pl->pcs_ops->pcs_an_restart(pl->config);
+			pl->pcs_ops->pcs_an_restart(pl->pcs);
 		else
 			pl->mac_ops->mac_an_restart(pl->config);
 	}
@@ -453,7 +454,7 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 	phylink_mac_config(pl, state);
 
 	if (pl->pcs_ops) {
-		err = pl->pcs_ops->pcs_config(pl->config, pl->cur_link_an_mode,
+		err = pl->pcs_ops->pcs_config(pl->pcs, pl->cur_link_an_mode,
 					      state->interface,
 					      state->advertising,
 					      !!(pl->link_config.pause &
@@ -506,7 +507,7 @@ static int phylink_change_inband_advert(struct phylink *pl)
 	 * restart negotiation if the pcs_config() helper indicates that
 	 * the programmed advertisement has changed.
 	 */
-	ret = pl->pcs_ops->pcs_config(pl->config, pl->cur_link_an_mode,
+	ret = pl->pcs_ops->pcs_config(pl->pcs, pl->cur_link_an_mode,
 				      pl->link_config.interface,
 				      pl->link_config.advertising,
 				      !!(pl->link_config.pause & MLO_PAUSE_AN));
@@ -533,7 +534,7 @@ static void phylink_mac_pcs_get_state(struct phylink *pl,
 	state->link = 1;
 
 	if (pl->pcs_ops)
-		pl->pcs_ops->pcs_get_state(pl->config, state);
+		pl->pcs_ops->pcs_get_state(pl->pcs, state);
 	else
 		pl->mac_ops->mac_pcs_get_state(pl->config, state);
 }
@@ -604,7 +605,7 @@ static void phylink_link_up(struct phylink *pl,
 	pl->cur_interface = link_state.interface;
 
 	if (pl->pcs_ops && pl->pcs_ops->pcs_link_up)
-		pl->pcs_ops->pcs_link_up(pl->config, pl->cur_link_an_mode,
+		pl->pcs_ops->pcs_link_up(pl->pcs, pl->cur_link_an_mode,
 					 pl->cur_interface,
 					 link_state.speed, link_state.duplex);
 
@@ -863,11 +864,26 @@ struct phylink *phylink_create(struct phylink_config *config,
 }
 EXPORT_SYMBOL_GPL(phylink_create);
 
-void phylink_add_pcs(struct phylink *pl, const struct phylink_pcs_ops *ops)
+/**
+ * phylink_set_pcs() - set the current PCS for phylink to use
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ * @pcs: a pointer to the &struct phylink_pcs
+ *
+ * Bind the MAC PCS to phylink.  This may be called after phylink_create(),
+ * in mac_prepare() or mac_config() methods if it is desired to dynamically
+ * change the PCS.
+ *
+ * Please note that there are behavioural changes with the mac_config()
+ * callback if a PCS is present (denoting a newer setup) so removing a PCS
+ * is not supported, and if a PCS is going to be used, it must be registered
+ * by calling phylink_set_pcs() at the latest in the first mac_config() call.
+ */
+void phylink_set_pcs(struct phylink *pl, struct phylink_pcs *pcs)
 {
-	pl->pcs_ops = ops;
+	pl->pcs = pcs;
+	pl->pcs_ops = pcs->ops;
 }
-EXPORT_SYMBOL_GPL(phylink_add_pcs);
+EXPORT_SYMBOL_GPL(phylink_set_pcs);
 
 /**
  * phylink_destroy() - cleanup and destroy the phylink instance
@@ -1212,6 +1228,8 @@ void phylink_start(struct phylink *pl)
 		break;
 	case MLO_AN_INBAND:
 		poll |= pl->config->pcs_poll;
+		if (pl->pcs)
+			poll |= pl->pcs->poll;
 		break;
 	}
 	if (poll)
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 2f1315f32113..057f78263a46 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -321,6 +321,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy,
 		 int speed, int duplex, bool tx_pause, bool rx_pause);
 #endif
 
+struct phylink_pcs_ops;
+
+/**
+ * struct phylink_pcs - PHYLINK PCS instance
+ * @ops: a pointer to the &struct phylink_pcs_ops structure
+ * @poll: poll the PCS for link changes
+ *
+ * This structure is designed to be embedded within the PCS private data,
+ * and will be passed between phylink and the PCS.
+ */
+struct phylink_pcs {
+	const struct phylink_pcs_ops *ops;
+	bool poll;
+};
+
 /**
  * struct phylink_pcs_ops - MAC PCS operations structure.
  * @pcs_get_state: read the current MAC PCS link state from the hardware.
@@ -330,21 +345,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy,
  *               (where necessary).
  */
 struct phylink_pcs_ops {
-	void (*pcs_get_state)(struct phylink_config *config,
+	void (*pcs_get_state)(struct phylink_pcs *pcs,
 			      struct phylink_link_state *state);
-	int (*pcs_config)(struct phylink_config *config, unsigned int mode,
+	int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode,
 			  phy_interface_t interface,
 			  const unsigned long *advertising,
 			  bool permit_pause_to_mac);
-	void (*pcs_an_restart)(struct phylink_config *config);
-	void (*pcs_link_up)(struct phylink_config *config, unsigned int mode,
+	void (*pcs_an_restart)(struct phylink_pcs *pcs);
+	void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int mode,
 			    phy_interface_t interface, int speed, int duplex);
 };
 
 #if 0 /* For kernel-doc purposes only. */
 /**
  * pcs_get_state() - Read the current inband link state from the hardware
- * @config: a pointer to a &struct phylink_config.
+ * @pcs: a pointer to a &struct phylink_pcs.
  * @state: a pointer to a &struct phylink_link_state.
  *
  * Read the current inband link state from the MAC PCS, reporting the
@@ -357,12 +372,12 @@ struct phylink_pcs_ops {
  * When present, this overrides mac_pcs_get_state() in &struct
  * phylink_mac_ops.
  */
-void pcs_get_state(struct phylink_config *config,
+void pcs_get_state(struct phylink_pcs *pcs,
 		   struct phylink_link_state *state);
 
 /**
  * pcs_config() - Configure the PCS mode and advertisement
- * @config: a pointer to a &struct phylink_config.
+ * @pcs: a pointer to a &struct phylink_pcs.
  * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
  * @interface: interface mode to be used
  * @advertising: adertisement ethtool link mode mask
@@ -382,21 +397,21 @@ void pcs_get_state(struct phylink_config *config,
  *
  * For most 10GBASE-R, there is no advertisement.
  */
-int (*pcs_config)(struct phylink_config *config, unsigned int mode,
-		  phy_interface_t interface, const unsigned long *advertising);
+int pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+	       phy_interface_t interface, const unsigned long *advertising);
 
 /**
  * pcs_an_restart() - restart 802.3z BaseX autonegotiation
- * @config: a pointer to a &struct phylink_config.
+ * @pcs: a pointer to a &struct phylink_pcs.
  *
  * When PCS ops are present, this overrides mac_an_restart() in &struct
  * phylink_mac_ops.
  */
-void (*pcs_an_restart)(struct phylink_config *config);
+void pcs_an_restart(struct phylink_pcs *pcs);
 
 /**
  * pcs_link_up() - program the PCS for the resolved link configuration
- * @config: a pointer to a &struct phylink_config.
+ * @pcs: a pointer to a &struct phylink_pcs.
  * @mode: link autonegotiation mode
  * @interface: link &typedef phy_interface_t mode
  * @speed: link speed
@@ -407,14 +422,14 @@ void (*pcs_an_restart)(struct phylink_config *config);
  * mode without in-band AN needs to be manually configured for the link
  * and duplex setting. Otherwise, this should be a no-op.
  */
-void (*pcs_link_up)(struct phylink_config *config, unsigned int mode,
-		    phy_interface_t interface, int speed, int duplex);
+void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+		 phy_interface_t interface, int speed, int duplex);
 #endif
 
 struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *,
 			       phy_interface_t iface,
 			       const struct phylink_mac_ops *mac_ops);
-void phylink_add_pcs(struct phylink *, const struct phylink_pcs_ops *ops);
+void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs);
 void phylink_destroy(struct phylink *);
 
 int phylink_connect_phy(struct phylink *, struct phy_device *);
-- 
cgit v1.2.3


From 93eaceb0fcf87b7f70924f9da3ec27e3c73be53d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Jul 2020 12:04:51 +0100
Subject: net: phylink: add interface to configure clause 22 PCS PHY

Add an interface to configure the advertisement for a clause 22 PCS
PHY, and set the AN enable flag in the BMCR appropriately.

Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  3 +++
 2 files changed, 40 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b57cd2142786..32b4bd6a5b55 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2442,6 +2442,43 @@ int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs,
 }
 EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_set_advertisement);
 
+/**
+ * phylink_mii_c22_pcs_config() - configure clause 22 PCS
+ * @pcs: a pointer to a &struct mdio_device.
+ * @mode: link autonegotiation mode
+ * @interface: the PHY interface mode being configured
+ * @advertising: the ethtool advertisement mask
+ *
+ * Configure a Clause 22 PCS PHY with the appropriate negotiation
+ * parameters for the @mode, @interface and @advertising parameters.
+ * Returns negative error number on failure, zero if the advertisement
+ * has not changed, or positive if there is a change.
+ */
+int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode,
+			       phy_interface_t interface,
+			       const unsigned long *advertising)
+{
+	bool changed;
+	u16 bmcr;
+	int ret;
+
+	ret = phylink_mii_c22_pcs_set_advertisement(pcs, interface,
+						    advertising);
+	if (ret < 0)
+		return ret;
+
+	changed = ret > 0;
+
+	bmcr = mode == MLO_AN_INBAND ? BMCR_ANENABLE : 0;
+	ret = mdiobus_modify(pcs->bus, pcs->addr, MII_BMCR,
+			     BMCR_ANENABLE, bmcr);
+	if (ret < 0)
+		return ret;
+
+	return changed ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_config);
+
 /**
  * phylink_mii_c22_pcs_an_restart() - restart 802.3z autonegotiation
  * @pcs: a pointer to a &struct mdio_device.
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 057f78263a46..1aad2aea4610 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -478,6 +478,9 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs,
 int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs,
 					  phy_interface_t interface,
 					  const unsigned long *advertising);
+int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode,
+			       phy_interface_t interface,
+			       const unsigned long *advertising);
 void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs);
 
 void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs,
-- 
cgit v1.2.3


From ab673b987488c4fab7a0bc4824a48211f9d910e3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 21 Jul 2020 15:59:19 -0700
Subject: fscrypt: use smp_load_acquire() for ->i_crypt_info

Normally smp_store_release() or cmpxchg_release() is paired with
smp_load_acquire().  Sometimes smp_load_acquire() can be replaced with
the more lightweight READ_ONCE().  However, for this to be safe, all the
published memory must only be accessed in a way that involves the
pointer itself.  This may not be the case if allocating the object also
involves initializing a static or global variable, for example.

fscrypt_info includes various sub-objects which are internal to and are
allocated by other kernel subsystems such as keyrings and crypto.  So by
using READ_ONCE() for ->i_crypt_info, we're relying on internal
implementation details of these other kernel subsystems.

Remove this fragile assumption by using smp_load_acquire() instead.

(Note: I haven't seen any real-world problems here.  This change is just
fixing the code to be guaranteed correct and less fragile.)

Fixes: e37a784d8b6a ("fscrypt: use READ_ONCE() to access ->i_crypt_info")
Link: https://lore.kernel.org/r/20200721225920.114347-5-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/keysetup.c    | 12 +++++++++++-
 fs/crypto/policy.c      |  4 ++--
 include/linux/fscrypt.h | 29 ++++++++++++++++++++++++-----
 3 files changed, 37 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 7f85fc645602..fea6226afc2b 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -518,7 +518,17 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	if (res)
 		goto out;
 
+	/*
+	 * Multiple tasks may race to set ->i_crypt_info, so use
+	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
+	 * fscrypt_get_info().  I.e., here we publish ->i_crypt_info with a
+	 * RELEASE barrier so that other tasks can ACQUIRE it.
+	 */
 	if (cmpxchg_release(&inode->i_crypt_info, NULL, crypt_info) == NULL) {
+		/*
+		 * We won the race and set ->i_crypt_info to our crypt_info.
+		 * Now link it into the master key's inode list.
+		 */
 		if (master_key) {
 			struct fscrypt_master_key *mk =
 				master_key->payload.data[0];
@@ -589,7 +599,7 @@ EXPORT_SYMBOL(fscrypt_free_inode);
  */
 int fscrypt_drop_inode(struct inode *inode)
 {
-	const struct fscrypt_info *ci = READ_ONCE(inode->i_crypt_info);
+	const struct fscrypt_info *ci = fscrypt_get_info(inode);
 	const struct fscrypt_master_key *mk;
 
 	/*
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 8e667aadf271..2d73fd39ad96 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -352,7 +352,7 @@ static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy)
 	union fscrypt_context ctx;
 	int ret;
 
-	ci = READ_ONCE(inode->i_crypt_info);
+	ci = fscrypt_get_info(inode);
 	if (ci) {
 		/* key available, use the cached policy */
 		*policy = ci->ci_policy;
@@ -641,7 +641,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	if (res < 0)
 		return res;
 
-	ci = READ_ONCE(parent->i_crypt_info);
+	ci = fscrypt_get_info(parent);
 	if (ci == NULL)
 		return -ENOKEY;
 
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index bb257411365f..991ff8575d0e 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -74,10 +74,15 @@ struct fscrypt_operations {
 			    struct request_queue **devs);
 };
 
-static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
 {
-	/* pairs with cmpxchg_release() in fscrypt_get_encryption_info() */
-	return READ_ONCE(inode->i_crypt_info) != NULL;
+	/*
+	 * Pairs with the cmpxchg_release() in fscrypt_get_encryption_info().
+	 * I.e., another task may publish ->i_crypt_info concurrently, executing
+	 * a RELEASE barrier.  We need to use smp_load_acquire() here to safely
+	 * ACQUIRE the memory the other task published.
+	 */
+	return smp_load_acquire(&inode->i_crypt_info);
 }
 
 /**
@@ -234,9 +239,9 @@ static inline void fscrypt_set_ops(struct super_block *sb,
 }
 #else  /* !CONFIG_FS_ENCRYPTION */
 
-static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
 {
-	return false;
+	return NULL;
 }
 
 static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
@@ -619,6 +624,20 @@ static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode)
 	       !__fscrypt_inode_uses_inline_crypto(inode);
 }
 
+/**
+ * fscrypt_has_encryption_key() - check whether an inode has had its key set up
+ * @inode: the inode to check
+ *
+ * Return: %true if the inode has had its encryption key set up, else %false.
+ *
+ * Usually this should be preceded by fscrypt_get_encryption_info() to try to
+ * set up the key first.
+ */
+static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+{
+	return fscrypt_get_info(inode) != NULL;
+}
+
 /**
  * fscrypt_require_key() - require an inode's encryption key
  * @inode: the inode we need the key for
-- 
cgit v1.2.3


From f3db0bed458314a835ccef5ccb130270c5b2cf04 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 21 Jul 2020 15:59:20 -0700
Subject: fs-verity: use smp_load_acquire() for ->i_verity_info

Normally smp_store_release() or cmpxchg_release() is paired with
smp_load_acquire().  Sometimes smp_load_acquire() can be replaced with
the more lightweight READ_ONCE().  However, for this to be safe, all the
published memory must only be accessed in a way that involves the
pointer itself.  This may not be the case if allocating the object also
involves initializing a static or global variable, for example.

fsverity_info::tree_params.hash_alg->tfm is a crypto_ahash object that's
internal to and is allocated by the crypto subsystem.  So by using
READ_ONCE() for ->i_verity_info, we're relying on internal
implementation details of the crypto subsystem.

Remove this fragile assumption by using smp_load_acquire() instead.

Also fix the cmpxchg logic to correctly execute an ACQUIRE barrier when
losing the cmpxchg race, since cmpxchg doesn't guarantee a memory
barrier on failure.

(Note: I haven't seen any real-world problems here.  This change is just
fixing the code to be guaranteed correct and less fragile.)

Fixes: fd2d1acfcadf ("fs-verity: add the hook for file ->open()")
Link: https://lore.kernel.org/r/20200721225920.114347-6-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/verity/open.c         | 15 ++++++++++++---
 include/linux/fsverity.h |  9 +++++++--
 2 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/verity/open.c b/fs/verity/open.c
index d007db0c9304..bfe0280c14e4 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -221,11 +221,20 @@ out:
 void fsverity_set_info(struct inode *inode, struct fsverity_info *vi)
 {
 	/*
-	 * Multiple processes may race to set ->i_verity_info, so use cmpxchg.
-	 * This pairs with the READ_ONCE() in fsverity_get_info().
+	 * Multiple tasks may race to set ->i_verity_info, so use
+	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
+	 * fsverity_get_info().  I.e., here we publish ->i_verity_info with a
+	 * RELEASE barrier so that other tasks can ACQUIRE it.
 	 */
-	if (cmpxchg(&inode->i_verity_info, NULL, vi) != NULL)
+	if (cmpxchg_release(&inode->i_verity_info, NULL, vi) != NULL) {
+		/* Lost the race, so free the fsverity_info we allocated. */
 		fsverity_free_info(vi);
+		/*
+		 * Afterwards, the caller may access ->i_verity_info directly,
+		 * so make sure to ACQUIRE the winning fsverity_info.
+		 */
+		(void)fsverity_get_info(inode);
+	}
 }
 
 void fsverity_free_info(struct fsverity_info *vi)
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index 78201a6d35f6..c1144a450392 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -115,8 +115,13 @@ struct fsverity_operations {
 
 static inline struct fsverity_info *fsverity_get_info(const struct inode *inode)
 {
-	/* pairs with the cmpxchg() in fsverity_set_info() */
-	return READ_ONCE(inode->i_verity_info);
+	/*
+	 * Pairs with the cmpxchg_release() in fsverity_set_info().
+	 * I.e., another task may publish ->i_verity_info concurrently,
+	 * executing a RELEASE barrier.  We need to use smp_load_acquire() here
+	 * to safely ACQUIRE the memory the other task published.
+	 */
+	return smp_load_acquire(&inode->i_verity_info);
 }
 
 /* enable.c */
-- 
cgit v1.2.3


From 58877d347b58c9e971112df5eb311c13bb0acb28 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 2 Jul 2020 14:52:11 +0200
Subject: sched: Better document ttwu()

Dave hit the problem fixed by commit:

  b6e13e85829f ("sched/core: Fix ttwu() race")

and failed to understand much of the code involved. Per his request a
few comments to (hopefully) clarify things.

Requested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200702125211.GQ4800@hirez.programming.kicks-ass.net
---
 include/linux/sched.h |  12 ++--
 kernel/sched/core.c   | 188 +++++++++++++++++++++++++++++++++++++++++++-------
 kernel/sched/sched.h  |  10 +++
 3 files changed, 179 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 12b10ce51a08..5033813fecd5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -154,24 +154,24 @@ struct task_group;
  *
  *   for (;;) {
  *	set_current_state(TASK_UNINTERRUPTIBLE);
- *	if (!need_sleep)
- *		break;
+ *	if (CONDITION)
+ *	   break;
  *
  *	schedule();
  *   }
  *   __set_current_state(TASK_RUNNING);
  *
  * If the caller does not need such serialisation (because, for instance, the
- * condition test and condition change and wakeup are under the same lock) then
+ * CONDITION test and condition change and wakeup are under the same lock) then
  * use __set_current_state().
  *
  * The above is typically ordered against the wakeup, which does:
  *
- *   need_sleep = false;
+ *   CONDITION = 1;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * where wake_up_state() executes a full memory barrier before accessing the
- * task state.
+ * where wake_up_state()/try_to_wake_up() executes a full memory barrier before
+ * accessing p->state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 08d02ce26b71..12db8fbd9c97 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -79,6 +79,100 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+
+/*
+ * Serialization rules:
+ *
+ * Lock order:
+ *
+ *   p->pi_lock
+ *     rq->lock
+ *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
+ *
+ *  rq1->lock
+ *    rq2->lock  where: rq1 < rq2
+ *
+ * Regular state:
+ *
+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
+ * always looks at the local rq data structures to find the most elegible task
+ * to run next.
+ *
+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
+ * the local CPU to avoid bouncing the runqueue state around [ see
+ * ttwu_queue_wakelist() ]
+ *
+ * Task wakeup, specifically wakeups that involve migration, are horribly
+ * complicated to avoid having to take two rq->locks.
+ *
+ * Special state:
+ *
+ * System-calls and anything external will use task_rq_lock() which acquires
+ * both p->pi_lock and rq->lock. As a consequence the state they change is
+ * stable while holding either lock:
+ *
+ *  - sched_setaffinity()/
+ *    set_cpus_allowed_ptr():	p->cpus_ptr, p->nr_cpus_allowed
+ *  - set_user_nice():		p->se.load, p->*prio
+ *  - __sched_setscheduler():	p->sched_class, p->policy, p->*prio,
+ *				p->se.load, p->rt_priority,
+ *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
+ *  - sched_setnuma():		p->numa_preferred_nid
+ *  - sched_move_task()/
+ *    cpu_cgroup_fork():	p->sched_task_group
+ *  - uclamp_update_active()	p->uclamp*
+ *
+ * p->state <- TASK_*:
+ *
+ *   is changed locklessly using set_current_state(), __set_current_state() or
+ *   set_special_state(), see their respective comments, or by
+ *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
+ *   concurrent self.
+ *
+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
+ *
+ *   is set by activate_task() and cleared by deactivate_task(), under
+ *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   ON_RQ_MIGRATING state is used for migration without holding both
+ *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
+ *
+ * p->on_cpu <- { 0, 1 }:
+ *
+ *   is set by prepare_task() and cleared by finish_task() such that it will be
+ *   set before p is scheduled-in and cleared after p is scheduled-out, both
+ *   under rq->lock. Non-zero indicates the task is running on its CPU.
+ *
+ *   [ The astute reader will observe that it is possible for two tasks on one
+ *     CPU to have ->on_cpu = 1 at the same time. ]
+ *
+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
+ *
+ *  - Don't call set_task_cpu() on a blocked task:
+ *
+ *    We don't care what CPU we're not running on, this simplifies hotplug,
+ *    the CPU assignment of blocked tasks isn't required to be valid.
+ *
+ *  - for try_to_wake_up(), called under p->pi_lock:
+ *
+ *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
+ *
+ *  - for migration called under rq->lock:
+ *    [ see task_on_rq_migrating() in task_rq_lock() ]
+ *
+ *    o move_queued_task()
+ *    o detach_task()
+ *
+ *  - for migration called under double_rq_lock():
+ *
+ *    o __migrate_swap_task()
+ *    o push_rt_task() / pull_rt_task()
+ *    o push_dl_task() / pull_dl_task()
+ *    o dl_task_offline_migration()
+ *
+ */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -1543,8 +1637,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
+	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
 
@@ -1552,8 +1645,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 
 	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
-	enqueue_task(rq, p, 0);
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -2318,12 +2410,31 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 }
 
 /*
- * Called in case the task @p isn't fully descheduled from its runqueue,
- * in this case we must do a remote wakeup. Its a 'light' wakeup though,
- * since all we need to do is flip p->state to TASK_RUNNING, since
- * the task is still ->on_rq.
+ * Consider @p being inside a wait loop:
+ *
+ *   for (;;) {
+ *      set_current_state(TASK_UNINTERRUPTIBLE);
+ *
+ *      if (CONDITION)
+ *         break;
+ *
+ *      schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * between set_current_state() and schedule(). In this case @p is still
+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
+ * an atomic manner.
+ *
+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
+ * then schedule() must still happen and p->state can be changed to
+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
+ * need to do a full wakeup with enqueue.
+ *
+ * Returns: %true when the wakeup is done,
+ *          %false otherwise.
  */
-static int ttwu_remote(struct task_struct *p, int wake_flags)
+static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -2464,6 +2575,14 @@ static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 
 	return false;
 }
+
+#else /* !CONFIG_SMP */
+
+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2471,10 +2590,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
-#if defined(CONFIG_SMP)
 	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
-#endif
 
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
@@ -2530,8 +2647,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * migration. However the means are completely different as there is no lock
  * chain to provide order. Instead we do:
  *
- *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_load_acquire(!X->on_cpu)
+ *   1) smp_store_release(X->on_cpu, 0)   -- finish_task()
+ *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
  *
  * Example:
  *
@@ -2571,15 +2688,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * If (@state & @p->state) @p->state = TASK_RUNNING.
+ * Conceptually does:
+ *
+ *   If (@state & @p->state) @p->state = TASK_RUNNING.
  *
  * If the task was not queued/runnable, also place it back on a runqueue.
  *
- * Atomic against schedule() which would dequeue a task, also see
- * set_current_state().
+ * This function is atomic against schedule() which would dequeue the task.
+ *
+ * It issues a full memory barrier before accessing @p->state, see the comment
+ * with set_current_state().
+ *
+ * Uses p->pi_lock to serialize against concurrent wake-ups.
  *
- * This function executes a full memory barrier before accessing the task
- * state; see set_current_state().
+ * Relies on p->pi_lock stabilizing:
+ *  - p->sched_class
+ *  - p->cpus_ptr
+ *  - p->sched_task_group
+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
+ *
+ * Tries really hard to only take one task_rq(p)->lock for performance.
+ * Takes rq->lock in:
+ *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
+ *  - ttwu_queue()       -- new rq, for enqueue of the task;
+ *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
+ *
+ * As a consequence we race really badly with just about everything. See the
+ * many memory barriers and their comments for details.
  *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
@@ -2595,7 +2730,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
-		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
 		 * In particular:
@@ -2616,8 +2751,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
-	 * reordered with p->state check below. This pairs with mb() in
-	 * set_current_state() the waiting thread does.
+	 * reordered with p->state check below. This pairs with smp_store_mb()
+	 * in set_current_state() that the waiting thread does.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
@@ -2652,7 +2787,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -3222,8 +3357,10 @@ static inline void prepare_task(struct task_struct *next)
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
+	 *
+	 * See the ttwu() WF_ON_CPU case and its ordering comment.
 	 */
-	next->on_cpu = 1;
+	WRITE_ONCE(next->on_cpu, 1);
 #endif
 }
 
@@ -3231,8 +3368,9 @@ static inline void finish_task(struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
+	 * This must be the very last reference to @prev from this CPU. After
+	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
+	 * must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
 	 * In particular, the load of prev->state in finish_task_switch() must
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 65b72e0487bf..9f33c77258ea 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1203,6 +1203,16 @@ struct rq_flags {
 #endif
 };
 
+/*
+ * Lockdep annotation that avoids accidental unlocks; it's like a
+ * sticky/continuous lockdep_assert_held().
+ *
+ * This avoids code that has access to 'struct rq *rq' (basically everything in
+ * the scheduler) from accidentally unlocking the rq if they do not also have a
+ * copy of the (on-stack) 'struct rq_flags rf'.
+ *
+ * Also see Documentation/locking/lockdep-design.rst.
+ */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	rf->cookie = lockdep_pin_lock(&rq->lock);
-- 
cgit v1.2.3


From 46132e3ac58cb2ee48051ed80bffc0070ad59b2e Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Wed, 1 Jul 2020 14:34:18 -0400
Subject: sched: nohz: stop passing around unused "ticks" parameter.

The "ticks" parameter was added in commit 0f004f5a696a ("sched: Cure more
NO_HZ load average woes") since calc_global_nohz() was called and needed
the "ticks" argument.

But in commit c308b56b5398 ("sched: Fix nohz load accounting -- again!")
it became unused as the function calc_global_nohz() dropped using "ticks".

Fixes: c308b56b5398 ("sched: Fix nohz load accounting -- again!")
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593628458-32290-1-git-send-email-paul.gortmaker@windriver.com
---
 include/linux/sched/loadavg.h | 2 +-
 kernel/sched/loadavg.c        | 2 +-
 kernel/time/timekeeping.c     | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 4859bea47a7b..83ec54b65e79 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -43,6 +43,6 @@ extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-extern void calc_global_load(unsigned long ticks);
+extern void calc_global_load(void);
 
 #endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index de22da666ac7..d2a655643a02 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -347,7 +347,7 @@ static inline void calc_global_nohz(void) { }
  *
  * Called from the global timer code.
  */
-void calc_global_load(unsigned long ticks)
+void calc_global_load(void)
 {
 	unsigned long sample_window;
 	long active, delta;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d20d489841c8..63a632f9896c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2193,7 +2193,7 @@ EXPORT_SYMBOL(ktime_get_coarse_ts64);
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	calc_global_load(ticks);
+	calc_global_load();
 }
 
 /**
-- 
cgit v1.2.3


From e0078e2eb8620079d988f150ba02a4ce9b5a946a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:30:31 -0700
Subject: linux/sched/mm.h: drop duplicated words in comments

Drop doubled words "to" and "that".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/927ea8d8-3f6c-9b65-4c2b-63ab4bd59ef1@infradead.org
---
 include/linux/sched/mm.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a98604ea76f1..6be66f52a2ad 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -23,7 +23,7 @@ extern struct mm_struct *mm_alloc(void);
  * will still exist later on and mmget_not_zero() has to be used before
  * accessing it.
  *
- * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * This is a preferred way to pin @mm for a longer/unbounded amount
  * of time.
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
@@ -232,7 +232,7 @@ static inline unsigned int memalloc_noio_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_noio_save call.
  */
 static inline void memalloc_noio_restore(unsigned int flags)
@@ -263,7 +263,7 @@ static inline unsigned int memalloc_nofs_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_nofs_save call.
  */
 static inline void memalloc_nofs_restore(unsigned int flags)
-- 
cgit v1.2.3


From 25980c7a79af42f2daa73e2f475ebf4cbac8253e Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Sun, 12 Jul 2020 17:59:15 +0100
Subject: arch_topology, sched/core: Cleanup thermal pressure definition

The following commit:

  14533a16c46d ("thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code")

moved the definition of arch_set_thermal_pressure() to sched/core.c, but
kept its declaration in linux/arch_topology.h. When building e.g. an x86
kernel with CONFIG_SCHED_THERMAL_PRESSURE=y, cpufreq_cooling.c ends up
getting the declaration of arch_set_thermal_pressure() from
include/linux/arch_topology.h, which is somewhat awkward.

On top of this, sched/core.c unconditionally defines
o The thermal_pressure percpu variable
o arch_set_thermal_pressure()

while arch_scale_thermal_pressure() does nothing unless redefined by the
architecture.

arch_*() functions are meant to be defined by architectures, so revert the
aforementioned commit and re-implement it in a way that keeps
arch_set_thermal_pressure() architecture-definable, and doesn't define the
thermal pressure percpu variable for kernels that don't need
it (CONFIG_SCHED_THERMAL_PRESSURE=n).

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200712165917.9168-2-valentin.schneider@arm.com
---
 arch/arm/include/asm/topology.h   |  3 ++-
 arch/arm64/include/asm/topology.h |  3 ++-
 drivers/base/arch_topology.c      | 11 +++++++++++
 include/linux/arch_topology.h     |  4 ++--
 include/linux/sched/topology.h    |  7 +++++++
 kernel/sched/core.c               | 11 -----------
 6 files changed, 24 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 435aba289fc5..e0593cf095d0 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -16,8 +16,9 @@
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #else
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 0cc835ddfcd1..e042f6527981 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -34,8 +34,9 @@ void topology_scale_freq_tick(void);
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #include <asm-generic/topology.h>
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 4d0a0038b476..75f72d684294 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -54,6 +54,17 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 	per_cpu(cpu_scale, cpu) = capacity;
 }
 
+DEFINE_PER_CPU(unsigned long, thermal_pressure);
+
+void topology_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{
+	int cpu;
+
+	for_each_cpu(cpu, cpus)
+		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
+}
+
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,
 				 char *buf)
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 0566cb3314ef..69b1dabe39dc 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -39,8 +39,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu)
 	return per_cpu(thermal_pressure, cpu);
 }
 
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure);
+void topology_set_thermal_pressure(const struct cpumask *cpus,
+				   unsigned long th_pressure);
 
 struct cpu_topology {
 	int thread_id;
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index fb11091129b3..764222d637b7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -232,6 +232,13 @@ unsigned long arch_scale_thermal_pressure(int cpu)
 }
 #endif
 
+#ifndef arch_set_thermal_pressure
+static __always_inline
+void arch_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{ }
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 12db8fbd9c97..bd8e5211d31f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3869,17 +3869,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
-DEFINE_PER_CPU(unsigned long, thermal_pressure);
-
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure)
-{
-	int cpu;
-
-	for_each_cpu(cpu, cpus)
-		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
-}
-
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
-- 
cgit v1.2.3


From c2127e14c127de2775feefdfb1444e30a129a59f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:30:27 -0700
Subject: perf: <linux/perf_event.h>: drop a duplicated word

Drop the repeated word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200719003027.20798-1-rdunlap@infradead.org
---
 include/linux/perf_event.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3b22db08b6fb..0edd257a5916 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -366,7 +366,7 @@ struct pmu {
 	 * ->stop() with PERF_EF_UPDATE will read the counter and update
 	 *  period/count values like ->read() would.
 	 *
-	 * ->start() with PERF_EF_RELOAD will reprogram the the counter
+	 * ->start() with PERF_EF_RELOAD will reprogram the counter
 	 *  value, must be preceded by a ->stop() with PERF_EF_UPDATE.
 	 */
 	void (*start)			(struct perf_event *event, int flags);
-- 
cgit v1.2.3


From aca7ed091117d9b4ce499855c383119afb2819a2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:38:15 -0700
Subject: i2c: drop duplicated word in the header file

Drop the doubled word "be" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index b8b8963f8bb9..ee328cf80bd9 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -56,7 +56,7 @@ struct property_entry;
  * on a bus (or read from them). Apart from two basic transfer functions to
  * transmit one message at a time, a more complex version can be used to
  * transmit an arbitrary number of messages without interruption.
- * @count must be be less than 64k since msg.len is u16.
+ * @count must be less than 64k since msg.len is u16.
  */
 int i2c_transfer_buffer_flags(const struct i2c_client *client,
 			      char *buf, int count, u16 flags);
-- 
cgit v1.2.3


From df746b3f079c31db7350b282c86e9004fa1a88df Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Jul 2020 16:23:33 -0500
Subject: misc: rtsx: Remove unused pcie_cap

There are no more uses of struct rtsx_pcr.pcie_cap.  Remove it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200721212336.1159079-3-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtsx_pcr.c | 1 -
 include/linux/rtsx_pci.h           | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 6d76929f31f5..0c0f1dd6f00f 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1253,7 +1253,6 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 		rtsx_pci_write_register(pcr, RTS5228_LDO1_CFG1, RTS5228_LDO1_SR_TIME_MASK,
 				RTS5228_LDO1_SR_0_5);
 
-	pcr->pcie_cap = pci_find_capability(pcr->pci, PCI_CAP_ID_EXP);
 	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
 
 	rtsx_pci_enable_bus_int(pcr);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 27a6ea82aeea..4ff7b221f36e 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1166,7 +1166,6 @@ struct rtsx_hw_param {
 struct rtsx_pcr {
 	struct pci_dev			*pci;
 	unsigned int			id;
-	int				pcie_cap;
 	struct rtsx_cr_option	option;
 	struct rtsx_hw_param hw_param;
 
-- 
cgit v1.2.3


From 22bf3251d7b7da0339f41ec27f2c3d4e0ec02255 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Jul 2020 16:23:34 -0500
Subject: misc: rtsx: Remove rtsx_pci_read/write_config() wrappers

rtsx_pci_read_config_dword() and similar wrappers around the PCI config
accessors add very little value, and they obscure the fact that often we
are accessing standard PCI registers that should be coordinated with the
PCI core.

Remove the wrappers and use the PCI config accessors directly.  No
functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200721212336.1159079-4-helgaas@kernel.org
[ fixed up some other instances as original patch was based on old tree - gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtl8411.c  |  8 +++++---
 drivers/misc/cardreader/rts5209.c  |  5 +++--
 drivers/misc/cardreader/rts5227.c  |  5 +++--
 drivers/misc/cardreader/rts5228.c  |  8 +++++---
 drivers/misc/cardreader/rts5229.c  |  5 +++--
 drivers/misc/cardreader/rts5249.c  | 12 +++++++-----
 drivers/misc/cardreader/rts5260.c  | 10 ++++++----
 drivers/misc/cardreader/rts5261.c  | 19 +++++++++++--------
 drivers/misc/cardreader/rtsx_pcr.c |  2 +-
 include/linux/rtsx_pci.h           | 12 ------------
 10 files changed, 44 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rtl8411.c b/drivers/misc/cardreader/rtl8411.c
index 489ebe907688..a07674ed0596 100644
--- a/drivers/misc/cardreader/rtl8411.c
+++ b/drivers/misc/cardreader/rtl8411.c
@@ -37,10 +37,11 @@ static int rtl8411b_is_qfn48(struct rtsx_pcr *pcr)
 
 static void rtl8411_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg1 = 0;
 	u8 reg3 = 0;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg1);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg1);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg1);
 
 	if (!rtsx_vendor_setting_valid(reg1))
@@ -52,16 +53,17 @@ static void rtl8411_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->card_drive_sel &= 0x3F;
 	pcr->card_drive_sel |= rtsx_reg_to_card_drive_sel(reg1);
 
-	rtsx_pci_read_config_byte(pcr, PCR_SETTING_REG3, &reg3);
+	pci_read_config_byte(pdev, PCR_SETTING_REG3, &reg3);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG3, reg3);
 	pcr->sd30_drive_sel_3v3 = rtl8411_reg_to_sd30_drive_sel_3v3(reg3);
 }
 
 static void rtl8411b_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg = 0;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg))
diff --git a/drivers/misc/cardreader/rts5209.c b/drivers/misc/cardreader/rts5209.c
index 659056164b21..39a6a7ecc32e 100644
--- a/drivers/misc/cardreader/rts5209.c
+++ b/drivers/misc/cardreader/rts5209.c
@@ -23,9 +23,10 @@ static u8 rts5209_get_ic_version(struct rtsx_pcr *pcr)
 
 static void rts5209_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (rts5209_vendor_setting1_valid(reg)) {
@@ -34,7 +35,7 @@ static void rts5209_fetch_vendor_settings(struct rtsx_pcr *pcr)
 		pcr->aspm_en = rts5209_reg_to_aspm(reg);
 	}
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 
 	if (rts5209_vendor_setting2_valid(reg)) {
diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c
index 3a9467aaa435..f5f392ddf3d6 100644
--- a/drivers/misc/cardreader/rts5227.c
+++ b/drivers/misc/cardreader/rts5227.c
@@ -56,9 +56,10 @@ static void rts5227_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 
 static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg))
@@ -69,7 +70,7 @@ static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->card_drive_sel &= 0x3F;
 	pcr->card_drive_sel |= rtsx_reg_to_card_drive_sel(reg);
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 	pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg);
 	if (rtsx_reg_check_reverse_socket(reg))
diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
index 99aff7cd0a93..448929829de4 100644
--- a/drivers/misc/cardreader/rts5228.c
+++ b/drivers/misc/cardreader/rts5228.c
@@ -60,9 +60,11 @@ static void rts5228_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 
 static void rtsx5228_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
+
 	/* 0x724~0x727 */
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg)) {
@@ -73,7 +75,7 @@ static void rtsx5228_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->aspm_en = rtsx_reg_to_aspm(reg);
 
 	/* 0x814~0x817 */
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 
 	pcr->rtd3_en = rtsx_reg_to_rtd3(reg);
@@ -380,7 +382,7 @@ static void rts5228_init_from_cfg(struct rtsx_pcr *pcr)
 	u32 lval;
 	struct rtsx_cr_option *option = &pcr->option;
 
-	rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_REG1, &lval);
+	pci_read_config_dword(pcr->pci, PCR_ASPM_SETTING_REG1, &lval);
 
 
 	if (0 == (lval & 0x0F))
diff --git a/drivers/misc/cardreader/rts5229.c b/drivers/misc/cardreader/rts5229.c
index 9f080a32ef50..89e6f124ca5c 100644
--- a/drivers/misc/cardreader/rts5229.c
+++ b/drivers/misc/cardreader/rts5229.c
@@ -23,9 +23,10 @@ static u8 rts5229_get_ic_version(struct rtsx_pcr *pcr)
 
 static void rts5229_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg))
@@ -37,7 +38,7 @@ static void rts5229_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->card_drive_sel &= 0x3F;
 	pcr->card_drive_sel |= rtsx_reg_to_card_drive_sel(reg);
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 	pcr->sd30_drive_sel_3v3 =
 		map_sd_drive(rtsx_reg_to_sd30_drive_sel_3v3(reg));
diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index 6c6c9e95a29f..665472d05993 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -55,9 +55,10 @@ static void rts5249_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 
 static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg)) {
@@ -70,7 +71,7 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->card_drive_sel &= 0x3F;
 	pcr->card_drive_sel |= rtsx_reg_to_card_drive_sel(reg);
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 	pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg);
 	if (rtsx_reg_check_reverse_socket(reg))
@@ -93,14 +94,15 @@ static void rtsx_base_force_power_down(struct rtsx_pcr *pcr, u8 pm_state)
 
 static void rts5249_init_from_cfg(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	struct rtsx_cr_option *option = &(pcr->option);
 	u32 lval;
 
 	if (CHK_PCI_PID(pcr, PID_524A))
-		rtsx_pci_read_config_dword(pcr,
+		pci_read_config_dword(pdev,
 			PCR_ASPM_SETTING_REG1, &lval);
 	else
-		rtsx_pci_read_config_dword(pcr,
+		pci_read_config_dword(pdev,
 			PCR_ASPM_SETTING_REG2, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
@@ -118,7 +120,7 @@ static void rts5249_init_from_cfg(struct rtsx_pcr *pcr)
 	if (option->ltr_en) {
 		u16 val;
 
-		pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
+		pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
 		if (val & PCI_EXP_DEVCTL2_LTR_EN) {
 			option->ltr_enabled = true;
 			option->ltr_active = true;
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index 7a9dbb778e84..0e806dd7ad08 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -64,9 +64,10 @@ static void rts5260_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 
 static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	if (!rtsx_vendor_setting_valid(reg)) {
@@ -79,7 +80,7 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
 	pcr->card_drive_sel &= 0x3F;
 	pcr->card_drive_sel |= rtsx_reg_to_card_drive_sel(reg);
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 	pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg);
 	if (rtsx_reg_check_reverse_socket(reg))
@@ -496,10 +497,11 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr)
 
 static void rts5260_init_from_cfg(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	struct rtsx_cr_option *option = &pcr->option;
 	u32 lval;
 
-	rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_5260, &lval);
+	pci_read_config_dword(pdev, PCR_ASPM_SETTING_5260, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
@@ -518,7 +520,7 @@ static void rts5260_init_from_cfg(struct rtsx_pcr *pcr)
 	if (option->ltr_en) {
 		u16 val;
 
-		pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
+		pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
 		if (val & PCI_EXP_DEVCTL2_LTR_EN) {
 			option->ltr_enabled = true;
 			option->ltr_active = true;
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 195822ec858e..4f30637ee4ac 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -59,9 +59,11 @@ static void rts5261_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 
 static void rtsx5261_fetch_vendor_settings(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 reg;
+
 	/* 0x814~0x817 */
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
 
 	if (!rts5261_vendor_setting_valid(reg)) {
@@ -76,7 +78,7 @@ static void rtsx5261_fetch_vendor_settings(struct rtsx_pcr *pcr)
 		pcr->flags |= PCR_REVERSE_SOCKET;
 
 	/* 0x724~0x727 */
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
 
 	pcr->aspm_en = rts5261_reg_to_aspm(reg);
@@ -361,6 +363,7 @@ static void rts5261_process_ocp(struct rtsx_pcr *pcr)
 
 static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	int retval;
 	u32 lval, i;
 	u8 valid, efuse_valid, tmp;
@@ -386,8 +389,7 @@ static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
 
 	if (efuse_valid == 0) {
-		retval = rtsx_pci_read_config_dword(pcr,
-			PCR_SETTING_REG2, &lval);
+		retval = pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval);
 		if (retval != 0)
 			pcr_dbg(pcr, "read 0x814 DW fail\n");
 		pcr_dbg(pcr, "DW from 0x814: 0x%x\n", lval);
@@ -399,9 +401,9 @@ static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 		REG_EFUSE_POR, 0);
 	pcr_dbg(pcr, "Disable efuse por!\n");
 
-	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &lval);
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval);
 	lval = lval & 0x00FFFFFF;
-	retval = rtsx_pci_write_config_dword(pcr, PCR_SETTING_REG2, lval);
+	retval = pci_write_config_dword(pdev, PCR_SETTING_REG2, lval);
 	if (retval != 0)
 		pcr_dbg(pcr, "write config fail\n");
 
@@ -410,10 +412,11 @@ static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 
 static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
 	u32 lval;
 	struct rtsx_cr_option *option = &pcr->option;
 
-	rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_REG1, &lval);
+	pci_read_config_dword(pdev, PCR_ASPM_SETTING_REG1, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
@@ -439,7 +442,7 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
 	if (option->ltr_en) {
 		u16 val;
 
-		pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
+		pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
 		if (val & PCI_EXP_DEVCTL2_LTR_EN) {
 			option->ltr_enabled = true;
 			option->ltr_active = true;
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 0c0f1dd6f00f..2fc6b938e999 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1350,7 +1350,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	pcie_capability_write_word(pdev, PCI_EXP_LNKCTL,
 				   PCI_EXP_LNKCTL_CLKREQ_EN);
 	/* Enter L1 when host tx idle */
-	rtsx_pci_write_config_byte(pcr, 0x70F, 0x5B);
+	pci_write_config_byte(pdev, 0x70F, 0x5B);
 
 	if (pcr->ops->extra_init_hw) {
 		err = pcr->ops->extra_init_hw(pcr);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 4ff7b221f36e..b93573c3c5fc 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -99,18 +99,6 @@
 #define rtsx_pci_readb(pcr, reg) \
 	ioread8((pcr)->remap_addr + reg)
 
-#define rtsx_pci_read_config_byte(pcr, where, val) \
-	pci_read_config_byte((pcr)->pci, where, val)
-
-#define rtsx_pci_write_config_byte(pcr, where, val) \
-	pci_write_config_byte((pcr)->pci, where, val)
-
-#define rtsx_pci_read_config_dword(pcr, where, val) \
-	pci_read_config_dword((pcr)->pci, where, val)
-
-#define rtsx_pci_write_config_dword(pcr, where, val) \
-	pci_write_config_dword((pcr)->pci, where, val)
-
 #define STATE_TRANS_NONE		0
 #define STATE_TRANS_CMD			1
 #define STATE_TRANS_BUF			2
-- 
cgit v1.2.3


From ed86a9877d05b99088a409a7603828b818a433dc Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Jul 2020 16:23:35 -0500
Subject: misc: rtsx: Find L1 PM Substates capability instead of hard-coding

Instead of hard-coding the location of the L1 PM Substates capability based
on the Device ID, search for it in the extended capabilities list.  This
works for any device, as long as it implements the L1 PM Substates
capability correctly, so it doesn't require maintenance as new devices are
added.  No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200721212336.1159079-5-helgaas@kernel.org
[ minor addition due to differences in my tree - gregkh]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rts5228.c |  7 ++++++-
 drivers/misc/cardreader/rts5249.c | 12 ++++++------
 drivers/misc/cardreader/rts5260.c |  7 ++++++-
 drivers/misc/cardreader/rts5261.c |  7 ++++++-
 include/linux/rtsx_pci.h          |  4 ----
 5 files changed, 24 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
index 448929829de4..f5716c631104 100644
--- a/drivers/misc/cardreader/rts5228.c
+++ b/drivers/misc/cardreader/rts5228.c
@@ -379,11 +379,16 @@ static void rts5228_process_ocp(struct rtsx_pcr *pcr)
 
 static void rts5228_init_from_cfg(struct rtsx_pcr *pcr)
 {
+	struct pci_dev *pdev = pcr->pci;
+	int l1ss;
 	u32 lval;
 	struct rtsx_cr_option *option = &pcr->option;
 
-	pci_read_config_dword(pcr->pci, PCR_ASPM_SETTING_REG1, &lval);
+	l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!l1ss)
+		return;
 
+	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
 	if (0 == (lval & 0x0F))
 		rtsx_pci_enable_oobs_polling(pcr);
diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index 665472d05993..1b8149e806c1 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -95,15 +95,15 @@ static void rtsx_base_force_power_down(struct rtsx_pcr *pcr, u8 pm_state)
 static void rts5249_init_from_cfg(struct rtsx_pcr *pcr)
 {
 	struct pci_dev *pdev = pcr->pci;
+	int l1ss;
 	struct rtsx_cr_option *option = &(pcr->option);
 	u32 lval;
 
-	if (CHK_PCI_PID(pcr, PID_524A))
-		pci_read_config_dword(pdev,
-			PCR_ASPM_SETTING_REG1, &lval);
-	else
-		pci_read_config_dword(pdev,
-			PCR_ASPM_SETTING_REG2, &lval);
+	l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!l1ss)
+		return;
+
+	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index 0e806dd7ad08..ebf77643cc90 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -498,10 +498,15 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr)
 static void rts5260_init_from_cfg(struct rtsx_pcr *pcr)
 {
 	struct pci_dev *pdev = pcr->pci;
+	int l1ss;
 	struct rtsx_cr_option *option = &pcr->option;
 	u32 lval;
 
-	pci_read_config_dword(pdev, PCR_ASPM_SETTING_5260, &lval);
+	l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!l1ss)
+		return;
+
+	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 4f30637ee4ac..4b6e3fe4a007 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -413,10 +413,15 @@ static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
 {
 	struct pci_dev *pdev = pcr->pci;
+	int l1ss;
 	u32 lval;
 	struct rtsx_cr_option *option = &pcr->option;
 
-	pci_read_config_dword(pdev, PCR_ASPM_SETTING_REG1, &lval);
+	l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!l1ss)
+		return;
+
+	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
 	if (lval & ASPM_L1_1_EN_MASK)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index b93573c3c5fc..f146ca413f38 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1037,10 +1037,6 @@
 #define   PHY_DIG1E_RX_EN_KEEP		0x0001
 #define PHY_DUM_REG			0x1F
 
-#define PCR_ASPM_SETTING_REG1		0x160
-#define PCR_ASPM_SETTING_REG2		0x168
-#define PCR_ASPM_SETTING_5260		0x178
-
 #define PCR_SETTING_REG1		0x724
 #define PCR_SETTING_REG2		0x814
 #define PCR_SETTING_REG3		0x747
-- 
cgit v1.2.3


From 7a4462a96777b64b22412f782de226c90290bf75 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Jul 2020 16:23:36 -0500
Subject: misc: rtsx: Use standard PCI definitions

When reading registers defined by the PCIe spec, use the names already
defined by the PCI core.  This makes maintenance of the PCI core and
drivers easier.  No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200721212336.1159079-6-helgaas@kernel.org
[ additional replacements due to changes in my tree - gregkh ]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rts5228.c | 8 ++++----
 drivers/misc/cardreader/rts5249.c | 8 ++++----
 drivers/misc/cardreader/rts5260.c | 8 ++++----
 drivers/misc/cardreader/rts5261.c | 8 ++++----
 include/linux/rtsx_pci.h          | 5 -----
 5 files changed, 16 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
index f5716c631104..28feab1449ab 100644
--- a/drivers/misc/cardreader/rts5228.c
+++ b/drivers/misc/cardreader/rts5228.c
@@ -395,22 +395,22 @@ static void rts5228_init_from_cfg(struct rtsx_pcr *pcr)
 	else
 		rtsx_pci_disable_oobs_polling(pcr);
 
-	if (lval & ASPM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
 	else
 		rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
 
-	if (lval & ASPM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
 		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
 	else
 		rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
 
-	if (lval & PM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
 		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
 	else
 		rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
 
-	if (lval & PM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
 		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
 	else
 		rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index 1b8149e806c1..941b3d77f1e9 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -105,16 +105,16 @@ static void rts5249_init_from_cfg(struct rtsx_pcr *pcr)
 
 	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
-	if (lval & ASPM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
 
-	if (lval & ASPM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
 		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
 
-	if (lval & PM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
 		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
 
-	if (lval & PM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
 		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
 
 	if (option->ltr_en) {
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index ebf77643cc90..b9f66b1384a6 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -508,16 +508,16 @@ static void rts5260_init_from_cfg(struct rtsx_pcr *pcr)
 
 	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
-	if (lval & ASPM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
 
-	if (lval & ASPM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
 		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
 
-	if (lval & PM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
 		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
 
-	if (lval & PM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
 		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
 
 	rts5260_pwr_saving_setting(pcr);
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 4b6e3fe4a007..471961487ff8 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -423,22 +423,22 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
 
 	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
 
-	if (lval & ASPM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
 		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
 	else
 		rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
 
-	if (lval & ASPM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
 		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
 	else
 		rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
 
-	if (lval & PM_L1_1_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
 		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
 	else
 		rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
 
-	if (lval & PM_L1_2_EN_MASK)
+	if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
 		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
 	else
 		rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index f146ca413f38..745f5e73f99a 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1083,11 +1083,6 @@ struct pcr_ops {
 
 enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
 
-#define ASPM_L1_1_EN_MASK		BIT(3)
-#define ASPM_L1_2_EN_MASK		BIT(2)
-#define PM_L1_1_EN_MASK		BIT(1)
-#define PM_L1_2_EN_MASK		BIT(0)
-
 #define ASPM_L1_1_EN			BIT(0)
 #define ASPM_L1_2_EN			BIT(1)
 #define PM_L1_1_EN				BIT(2)
-- 
cgit v1.2.3


From 55d5d3b46b08a4dc0b05343d24640744e7430ed7 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Thu, 16 Jul 2020 13:19:56 -0500
Subject: leds: multicolor: Introduce a multicolor class definition

Introduce a multicolor class that groups colored LEDs
within a LED node.

The multicolor class groups monochrome LEDs and allows controlling two
aspects of the final combined color: hue and lightness. The former is
controlled via the intensity file and the latter is controlled
via brightness file.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Acked-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
[squashed leds: multicolor: Fix camel case in documentation in]
---
 .../ABI/testing/sysfs-class-led-multicolor         |  35 ++++
 Documentation/leds/index.rst                       |   1 +
 Documentation/leds/leds-class-multicolor.rst       |  86 +++++++++
 drivers/leds/Kconfig                               |  10 +
 drivers/leds/Makefile                              |   1 +
 drivers/leds/led-class-multicolor.c                | 203 +++++++++++++++++++++
 include/linux/led-class-multicolor.h               | 121 ++++++++++++
 7 files changed, 457 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-class-led-multicolor
 create mode 100644 Documentation/leds/leds-class-multicolor.rst
 create mode 100644 drivers/leds/led-class-multicolor.c
 create mode 100644 include/linux/led-class-multicolor.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-led-multicolor b/Documentation/ABI/testing/sysfs-class-led-multicolor
new file mode 100644
index 000000000000..eeeddcbdbbe3
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-led-multicolor
@@ -0,0 +1,35 @@
+What:		/sys/class/leds/<led>/brightness
+Date:		March 2020
+KernelVersion:	5.9
+Contact:	Dan Murphy <dmurphy@ti.com>
+Description:	read/write
+		Writing to this file will update all LEDs within the group to a
+		calculated percentage of what each color LED intensity is set
+		to. The percentage is calculated for each grouped LED via the
+		equation below:
+
+		led_brightness = brightness * multi_intensity/max_brightness
+
+		For additional details please refer to
+		Documentation/leds/leds-class-multicolor.rst.
+
+		The value of the LED is from 0 to
+		/sys/class/leds/<led>/max_brightness.
+
+What:		/sys/class/leds/<led>/multi_index
+Date:		March 2020
+KernelVersion:	5.9
+Contact:	Dan Murphy <dmurphy@ti.com>
+Description:	read
+		The multi_index array, when read, will output the LED colors
+		as an array of strings as they are indexed in the
+		multi_intensity file.
+
+What:		/sys/class/leds/<led>/multi_intensity
+Date:		March 2020
+KernelVersion:	5.9
+Contact:	Dan Murphy <dmurphy@ti.com>
+Description:	read/write
+		This file contains array of integers. Order of components is
+		described by the multi_index array. The maximum intensity should
+		not exceed /sys/class/leds/<led>/max_brightness.
diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst
index 060f4e485897..bc70c6aa7138 100644
--- a/Documentation/leds/index.rst
+++ b/Documentation/leds/index.rst
@@ -9,6 +9,7 @@ LEDs
 
    leds-class
    leds-class-flash
+   leds-class-multicolor
    ledtrig-oneshot
    ledtrig-transient
    ledtrig-usbport
diff --git a/Documentation/leds/leds-class-multicolor.rst b/Documentation/leds/leds-class-multicolor.rst
new file mode 100644
index 000000000000..c57b98bfd387
--- /dev/null
+++ b/Documentation/leds/leds-class-multicolor.rst
@@ -0,0 +1,86 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================
+Multicolor LED handling under Linux
+====================================
+
+Description
+===========
+The multicolor class groups monochrome LEDs and allows controlling two
+aspects of the final combined color: hue and lightness. The former is
+controlled via the multi_intensity array file and the latter is controlled
+via brightness file.
+
+Multicolor Class Control
+========================
+The multicolor class presents files that groups the colors as indexes in an
+array.  These files are children under the LED parent node created by the
+led_class framework.  The led_class framework is documented in led-class.rst
+within this documentation directory.
+
+Each colored LED will be indexed under the multi_* files. The order of the
+colors will be arbitrary. The multi_index file can be read to determine the
+color name to indexed value.
+
+The multi_index file is an array that contains the string list of the colors as
+they are defined in each multi_* array file.
+
+The multi_intensity is an array that can be read or written to for the
+individual color intensities.  All elements within this array must be written in
+order for the color LED intensities to be updated.
+
+Directory Layout Example
+========================
+root:/sys/class/leds/multicolor:status# ls -lR
+-rw-r--r--    1 root     root          4096 Oct 19 16:16 brightness
+-r--r--r--    1 root     root          4096 Oct 19 16:16 max_brightness
+-r--r--r--    1 root     root          4096 Oct 19 16:16 multi_index
+-rw-r--r--    1 root     root          4096 Oct 19 16:16 multi_intensity
+
+Multicolor Class Brightness Control
+===================================
+The brightness level for each LED is calculated based on the color LED
+intensity setting divided by the global max_brightness setting multiplied by
+the requested brightness.
+
+led_brightness = brightness * multi_intensity/max_brightness
+
+Example:
+A user first writes the multi_intensity file with the brightness levels
+for each LED that are necessary to achieve a certain color output from a
+multicolor LED group.
+
+cat /sys/class/leds/multicolor:status/multi_index
+green blue red
+
+echo 43 226 138 > /sys/class/leds/multicolor:status/multi_intensity
+
+red -
+	intensity = 138
+	max_brightness = 255
+green -
+	intensity = 43
+	max_brightness = 255
+blue -
+	intensity = 226
+	max_brightness = 255
+
+The user can control the brightness of that multicolor LED group by writing the
+global 'brightness' control.  Assuming a max_brightness of 255 the user
+may want to dim the LED color group to half.  The user would write a value of
+128 to the global brightness file then the values written to each LED will be
+adjusted base on this value.
+
+cat /sys/class/leds/multicolor:status/max_brightness
+255
+echo 128 > /sys/class/leds/multicolor:status/brightness
+
+adjusted_red_value = 128 * 138/255 = 69
+adjusted_green_value = 128 * 43/255 = 21
+adjusted_blue_value = 128 * 226/255 = 113
+
+Reading the global brightness file will return the current brightness value of
+the color LED group.
+
+cat /sys/class/leds/multicolor:status/brightness
+128
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index ed943140e1fd..1de6e8e264a0 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -30,6 +30,16 @@ config LEDS_CLASS_FLASH
 	  for the flash related features of a LED device. It can be built
 	  as a module.
 
+config LEDS_CLASS_MULTICOLOR
+	tristate "LED Multicolor Class Support"
+	depends on LEDS_CLASS
+	help
+	  This option enables the multicolor LED sysfs class in /sys/class/leds.
+	  It wraps LED class and adds multicolor LED specific sysfs attributes
+	  and kernel internal API to it. You'll need this to provide support
+	  for multicolor LEDs that are grouped together. This class is not
+	  intended for single color LEDs. It can be built as a module.
+
 config LEDS_BRIGHTNESS_HW_CHANGED
 	bool "LED Class brightness_hw_changed attribute support"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index d6b8a792c936..d684bc76d2b2 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -4,6 +4,7 @@
 obj-$(CONFIG_NEW_LEDS)			+= led-core.o
 obj-$(CONFIG_LEDS_CLASS)		+= led-class.o
 obj-$(CONFIG_LEDS_CLASS_FLASH)		+= led-class-flash.o
+obj-$(CONFIG_LEDS_CLASS_MULTICOLOR)	+= led-class-multicolor.o
 obj-$(CONFIG_LEDS_TRIGGERS)		+= led-triggers.o
 
 # LED Platform Drivers (keep this sorted, M-| sort)
diff --git a/drivers/leds/led-class-multicolor.c b/drivers/leds/led-class-multicolor.c
new file mode 100644
index 000000000000..e317408583df
--- /dev/null
+++ b/drivers/leds/led-class-multicolor.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+// LED Multicolor class interface
+// Copyright (C) 2019-20 Texas Instruments Incorporated - http://www.ti.com/
+// Author: Dan Murphy <dmurphy@ti.com>
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/led-class-multicolor.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include "leds.h"
+
+int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev,
+				 enum led_brightness brightness)
+{
+	struct led_classdev *led_cdev = &mcled_cdev->led_cdev;
+	int i;
+
+	for (i = 0; i < mcled_cdev->num_colors; i++)
+		mcled_cdev->subled_info[i].brightness = brightness *
+					mcled_cdev->subled_info[i].intensity /
+					led_cdev->max_brightness;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(led_mc_calc_color_components);
+
+static ssize_t multi_intensity_store(struct device *dev,
+				struct device_attribute *intensity_attr,
+				const char *buf, size_t size)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev_mc *mcled_cdev = lcdev_to_mccdev(led_cdev);
+	int nrchars, offset = 0;
+	int intensity_value[LED_COLOR_ID_MAX];
+	int i;
+	ssize_t ret;
+
+	mutex_lock(&led_cdev->led_access);
+
+	for (i = 0; i < mcled_cdev->num_colors; i++) {
+		ret = sscanf(buf + offset, "%i%n",
+			     &intensity_value[i], &nrchars);
+		if (ret != 1) {
+			ret = -EINVAL;
+			goto err_out;
+		}
+		offset += nrchars;
+	}
+
+	offset++;
+	if (offset < size) {
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	for (i = 0; i < mcled_cdev->num_colors; i++)
+		mcled_cdev->subled_info[i].intensity = intensity_value[i];
+
+	led_set_brightness(led_cdev, led_cdev->brightness);
+	ret = size;
+err_out:
+	mutex_unlock(&led_cdev->led_access);
+	return ret;
+}
+
+static ssize_t multi_intensity_show(struct device *dev,
+			      struct device_attribute *intensity_attr,
+			      char *buf)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev_mc *mcled_cdev = lcdev_to_mccdev(led_cdev);
+	int len = 0;
+	int i;
+
+	for (i = 0; i < mcled_cdev->num_colors; i++) {
+		len += sprintf(buf + len, "%d",
+			       mcled_cdev->subled_info[i].intensity);
+		if (i < mcled_cdev->num_colors - 1)
+			len += sprintf(buf + len, " ");
+	}
+
+	buf[len++] = '\n';
+	return len;
+}
+static DEVICE_ATTR_RW(multi_intensity);
+
+static ssize_t multi_index_show(struct device *dev,
+			      struct device_attribute *multi_index_attr,
+			      char *buf)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev_mc *mcled_cdev = lcdev_to_mccdev(led_cdev);
+	int len = 0;
+	int index;
+	int i;
+
+	for (i = 0; i < mcled_cdev->num_colors; i++) {
+		index = mcled_cdev->subled_info[i].color_index;
+		len += sprintf(buf + len, "%s", led_colors[index]);
+		if (i < mcled_cdev->num_colors - 1)
+			len += sprintf(buf + len, " ");
+	}
+
+	buf[len++] = '\n';
+	return len;
+}
+static DEVICE_ATTR_RO(multi_index);
+
+static struct attribute *led_multicolor_attrs[] = {
+	&dev_attr_multi_intensity.attr,
+	&dev_attr_multi_index.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(led_multicolor);
+
+int led_classdev_multicolor_register_ext(struct device *parent,
+				     struct led_classdev_mc *mcled_cdev,
+				     struct led_init_data *init_data)
+{
+	struct led_classdev *led_cdev;
+
+	if (!mcled_cdev)
+		return -EINVAL;
+
+	if (mcled_cdev->num_colors <= 0)
+		return -EINVAL;
+
+	if (mcled_cdev->num_colors > LED_COLOR_ID_MAX)
+		return -EINVAL;
+
+	led_cdev = &mcled_cdev->led_cdev;
+	mcled_cdev->led_cdev.groups = led_multicolor_groups;
+
+	return led_classdev_register_ext(parent, led_cdev, init_data);
+}
+EXPORT_SYMBOL_GPL(led_classdev_multicolor_register_ext);
+
+void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev)
+{
+	if (!mcled_cdev)
+		return;
+
+	led_classdev_unregister(&mcled_cdev->led_cdev);
+}
+EXPORT_SYMBOL_GPL(led_classdev_multicolor_unregister);
+
+static void devm_led_classdev_multicolor_release(struct device *dev, void *res)
+{
+	led_classdev_multicolor_unregister(*(struct led_classdev_mc **)res);
+}
+
+int devm_led_classdev_multicolor_register_ext(struct device *parent,
+					     struct led_classdev_mc *mcled_cdev,
+					     struct led_init_data *init_data)
+{
+	struct led_classdev_mc **dr;
+	int ret;
+
+	dr = devres_alloc(devm_led_classdev_multicolor_release,
+			  sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	ret = led_classdev_multicolor_register_ext(parent, mcled_cdev,
+						   init_data);
+	if (ret) {
+		devres_free(dr);
+		return ret;
+	}
+
+	*dr = mcled_cdev;
+	devres_add(parent, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_led_classdev_multicolor_register_ext);
+
+static int devm_led_classdev_multicolor_match(struct device *dev,
+					      void *res, void *data)
+{
+	struct led_classdev_mc **p = res;
+
+	if (WARN_ON(!p || !*p))
+		return 0;
+
+	return *p == data;
+}
+
+void devm_led_classdev_multicolor_unregister(struct device *dev,
+					     struct led_classdev_mc *mcled_cdev)
+{
+	WARN_ON(devres_release(dev,
+			       devm_led_classdev_multicolor_release,
+			       devm_led_classdev_multicolor_match, mcled_cdev));
+}
+EXPORT_SYMBOL_GPL(devm_led_classdev_multicolor_unregister);
+
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
+MODULE_DESCRIPTION("Multicolor LED class interface");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h
new file mode 100644
index 000000000000..5116f9a866cc
--- /dev/null
+++ b/include/linux/led-class-multicolor.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* LED Multicolor class interface
+ * Copyright (C) 2019-20 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+#ifndef _LINUX_MULTICOLOR_LEDS_H_INCLUDED
+#define _LINUX_MULTICOLOR_LEDS_H_INCLUDED
+
+#include <linux/leds.h>
+#include <dt-bindings/leds/common.h>
+
+struct mc_subled {
+	unsigned int color_index;
+	unsigned int brightness;
+	unsigned int intensity;
+	unsigned int channel;
+};
+
+struct led_classdev_mc {
+	/* led class device */
+	struct led_classdev led_cdev;
+	unsigned int num_colors;
+
+	struct mc_subled *subled_info;
+};
+
+static inline struct led_classdev_mc *lcdev_to_mccdev(
+						struct led_classdev *led_cdev)
+{
+	return container_of(led_cdev, struct led_classdev_mc, led_cdev);
+}
+
+#if IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR)
+/**
+ * led_classdev_multicolor_register_ext - register a new object of led_classdev
+ *				      class with support for multicolor LEDs
+ * @parent: the multicolor LED to register
+ * @mcled_cdev: the led_classdev_mc structure for this device
+ * @init_data: the LED class multicolor device initialization data
+ *
+ * Returns: 0 on success or negative error value on failure
+ */
+int led_classdev_multicolor_register_ext(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev,
+					    struct led_init_data *init_data);
+
+static inline int led_classdev_multicolor_register(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev)
+{
+	return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL);
+}
+
+/**
+ * led_classdev_multicolor_unregister - unregisters an object of led_classdev
+ *					class with support for multicolor LEDs
+ * @mcled_cdev: the multicolor LED to unregister
+ *
+ * Unregister a previously registered via led_classdev_multicolor_register
+ * object
+ */
+void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev);
+
+/* Calculate brightness for the monochrome LED cluster */
+int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev,
+				 enum led_brightness brightness);
+
+int devm_led_classdev_multicolor_register_ext(struct device *parent,
+					  struct led_classdev_mc *mcled_cdev,
+					  struct led_init_data *init_data);
+
+static inline int devm_led_classdev_multicolor_register(struct device *parent,
+				     struct led_classdev_mc *mcled_cdev)
+{
+	return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev,
+							 NULL);
+}
+
+void devm_led_classdev_multicolor_unregister(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev);
+#else
+
+static inline int led_classdev_multicolor_register_ext(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev,
+					    struct led_init_data *init_data)
+{
+	return -EINVAL;
+}
+
+static inline int led_classdev_multicolor_register(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev)
+{
+	return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL);
+}
+
+static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {};
+static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev,
+					       enum led_brightness brightness)
+{
+	return -EINVAL;
+}
+
+static inline int devm_led_classdev_multicolor_register_ext(struct device *parent,
+					  struct led_classdev_mc *mcled_cdev,
+					  struct led_init_data *init_data)
+{
+	return -EINVAL;
+}
+
+static inline int devm_led_classdev_multicolor_register(struct device *parent,
+					     struct led_classdev_mc *mcled_cdev)
+{
+	return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev,
+							 NULL);
+}
+
+static inline void devm_led_classdev_multicolor_unregister(struct device *parent,
+					    struct led_classdev_mc *mcled_cdev)
+{};
+
+#endif  /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */
+#endif	/* _LINUX_MULTICOLOR_LEDS_H_INCLUDED */
-- 
cgit v1.2.3


From 92a81562e695628086acb92f95090ab09d9b9ec0 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Thu, 16 Jul 2020 13:20:01 -0500
Subject: leds: lp55xx: Add multicolor framework support to lp55xx

Add multicolor framework support for the lp55xx family.

Acked-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/Kconfig                      |  11 +-
 drivers/leds/leds-lp5521.c                |  14 ++-
 drivers/leds/leds-lp5523.c                |  14 ++-
 drivers/leds/leds-lp5562.c                |  13 ++-
 drivers/leds/leds-lp55xx-common.c         | 177 ++++++++++++++++++++++++++----
 drivers/leds/leds-lp55xx-common.h         |  14 ++-
 drivers/leds/leds-lp8501.c                |  14 ++-
 include/linux/platform_data/leds-lp55xx.h |   7 ++
 8 files changed, 212 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 1de6e8e264a0..b9002850b5fa 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -386,7 +386,8 @@ config LEDS_LP3952
 
 config LEDS_LP55XX_COMMON
 	tristate "Common Driver for TI/National LP5521/5523/55231/5562/8501"
-	depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562 || LEDS_LP8501
+	depends on LEDS_CLASS_MULTICOLOR || !LEDS_CLASS_MULTICOLOR
+	depends on OF
 	select FW_LOADER
 	select FW_LOADER_USER_HELPER
 	help
@@ -396,7 +397,7 @@ config LEDS_LP55XX_COMMON
 config LEDS_LP5521
 	tristate "LED Support for N.S. LP5521 LED driver chip"
 	depends on LEDS_CLASS && I2C
-	select LEDS_LP55XX_COMMON
+	depends on LEDS_LP55XX_COMMON
 	help
 	  If you say yes here you get support for the National Semiconductor
 	  LP5521 LED driver. It is 3 channel chip with programmable engines.
@@ -406,7 +407,7 @@ config LEDS_LP5521
 config LEDS_LP5523
 	tristate "LED Support for TI/National LP5523/55231 LED driver chip"
 	depends on LEDS_CLASS && I2C
-	select LEDS_LP55XX_COMMON
+	depends on LEDS_LP55XX_COMMON
 	help
 	  If you say yes here you get support for TI/National Semiconductor
 	  LP5523/55231 LED driver.
@@ -417,7 +418,7 @@ config LEDS_LP5523
 config LEDS_LP5562
 	tristate "LED Support for TI LP5562 LED driver chip"
 	depends on LEDS_CLASS && I2C
-	select LEDS_LP55XX_COMMON
+	depends on LEDS_LP55XX_COMMON
 	help
 	  If you say yes here you get support for TI LP5562 LED driver.
 	  It is 4 channels chip with programmable engines.
@@ -427,7 +428,7 @@ config LEDS_LP5562
 config LEDS_LP8501
 	tristate "LED Support for TI LP8501 LED driver chip"
 	depends on LEDS_CLASS && I2C
-	select LEDS_LP55XX_COMMON
+	depends on LEDS_LP55XX_COMMON
 	help
 	  If you say yes here you get support for TI LP8501 LED driver.
 	  It is 9 channel chip with programmable engines.
diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index 6d2163c0f625..6ff81d6be789 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -505,9 +505,16 @@ static int lp5521_probe(struct i2c_client *client,
 	struct lp55xx_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct device_node *np = client->dev.of_node;
 
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->cfg = &lp5521_cfg;
+
 	if (!pdata) {
 		if (np) {
-			pdata = lp55xx_of_populate_pdata(&client->dev, np);
+			pdata = lp55xx_of_populate_pdata(&client->dev, np,
+							 chip);
 			if (IS_ERR(pdata))
 				return PTR_ERR(pdata);
 		} else {
@@ -516,10 +523,6 @@ static int lp5521_probe(struct i2c_client *client,
 		}
 	}
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
-
 	led = devm_kcalloc(&client->dev,
 			pdata->num_channels, sizeof(*led), GFP_KERNEL);
 	if (!led)
@@ -527,7 +530,6 @@ static int lp5521_probe(struct i2c_client *client,
 
 	chip->cl = client;
 	chip->pdata = pdata;
-	chip->cfg = &lp5521_cfg;
 
 	mutex_init(&chip->lock);
 
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index cb550cf19e14..bb97549007d7 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -873,9 +873,16 @@ static int lp5523_probe(struct i2c_client *client,
 	struct lp55xx_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct device_node *np = client->dev.of_node;
 
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->cfg = &lp5523_cfg;
+
 	if (!pdata) {
 		if (np) {
-			pdata = lp55xx_of_populate_pdata(&client->dev, np);
+			pdata = lp55xx_of_populate_pdata(&client->dev, np,
+							 chip);
 			if (IS_ERR(pdata))
 				return PTR_ERR(pdata);
 		} else {
@@ -884,10 +891,6 @@ static int lp5523_probe(struct i2c_client *client,
 		}
 	}
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
-
 	led = devm_kcalloc(&client->dev,
 			pdata->num_channels, sizeof(*led), GFP_KERNEL);
 	if (!led)
@@ -895,7 +898,6 @@ static int lp5523_probe(struct i2c_client *client,
 
 	chip->cl = client;
 	chip->pdata = pdata;
-	chip->cfg = &lp5523_cfg;
 
 	mutex_init(&chip->lock);
 
diff --git a/drivers/leds/leds-lp5562.c b/drivers/leds/leds-lp5562.c
index 1c94422408b0..7ecdd199d7ef 100644
--- a/drivers/leds/leds-lp5562.c
+++ b/drivers/leds/leds-lp5562.c
@@ -520,9 +520,16 @@ static int lp5562_probe(struct i2c_client *client,
 	struct lp55xx_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct device_node *np = client->dev.of_node;
 
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->cfg = &lp5562_cfg;
+
 	if (!pdata) {
 		if (np) {
-			pdata = lp55xx_of_populate_pdata(&client->dev, np);
+			pdata = lp55xx_of_populate_pdata(&client->dev, np,
+							 chip);
 			if (IS_ERR(pdata))
 				return PTR_ERR(pdata);
 		} else {
@@ -531,9 +538,6 @@ static int lp5562_probe(struct i2c_client *client,
 		}
 	}
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
 
 	led = devm_kcalloc(&client->dev,
 			pdata->num_channels, sizeof(*led), GFP_KERNEL);
@@ -542,7 +546,6 @@ static int lp5562_probe(struct i2c_client *client,
 
 	chip->cl = client;
 	chip->pdata = pdata;
-	chip->cfg = &lp5562_cfg;
 
 	mutex_init(&chip->lock);
 
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 243c749ebda5..af14e2b2d577 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -34,6 +34,11 @@ static struct lp55xx_led *dev_to_lp55xx_led(struct device *dev)
 	return cdev_to_lp55xx_led(dev_get_drvdata(dev));
 }
 
+static struct lp55xx_led *mcled_cdev_to_led(struct led_classdev_mc *mc_cdev)
+{
+	return container_of(mc_cdev, struct lp55xx_led, mc_cdev);
+}
+
 static void lp55xx_reset_device(struct lp55xx_chip *chip)
 {
 	struct lp55xx_device_config *cfg = chip->cfg;
@@ -129,6 +134,18 @@ static struct attribute *lp55xx_led_attrs[] = {
 };
 ATTRIBUTE_GROUPS(lp55xx_led);
 
+static int lp55xx_set_mc_brightness(struct led_classdev *cdev,
+				    enum led_brightness brightness)
+{
+	struct led_classdev_mc *mc_dev = lcdev_to_mccdev(cdev);
+	struct lp55xx_led *led = mcled_cdev_to_led(mc_dev);
+	struct lp55xx_device_config *cfg = led->chip->cfg;
+
+	led_mc_calc_color_components(&led->mc_cdev, brightness);
+	return cfg->multicolor_brightness_fn(led);
+
+}
+
 static int lp55xx_set_brightness(struct led_classdev *cdev,
 			     enum led_brightness brightness)
 {
@@ -145,9 +162,12 @@ static int lp55xx_init_led(struct lp55xx_led *led,
 	struct lp55xx_platform_data *pdata = chip->pdata;
 	struct lp55xx_device_config *cfg = chip->cfg;
 	struct device *dev = &chip->cl->dev;
+	int max_channel = cfg->max_channel;
+	struct mc_subled *mc_led_info;
+	struct led_classdev *led_cdev;
 	char name[32];
+	int i, j = 0;
 	int ret;
-	int max_channel = cfg->max_channel;
 
 	if (chan >= max_channel) {
 		dev_err(dev, "invalid channel: %d / %d\n", chan, max_channel);
@@ -157,10 +177,43 @@ static int lp55xx_init_led(struct lp55xx_led *led,
 	if (pdata->led_config[chan].led_current == 0)
 		return 0;
 
+	if (pdata->led_config[chan].name) {
+		led->cdev.name = pdata->led_config[chan].name;
+	} else {
+		snprintf(name, sizeof(name), "%s:channel%d",
+			pdata->label ? : chip->cl->name, chan);
+		led->cdev.name = name;
+	}
+
+	if (pdata->led_config[chan].num_colors > 1) {
+		mc_led_info = devm_kcalloc(dev,
+					   pdata->led_config[chan].num_colors,
+					   sizeof(*mc_led_info), GFP_KERNEL);
+		if (!mc_led_info)
+			return -ENOMEM;
+
+		led_cdev = &led->mc_cdev.led_cdev;
+		led_cdev->name = led->cdev.name;
+		led_cdev->brightness_set_blocking = lp55xx_set_mc_brightness;
+		led->mc_cdev.num_colors = pdata->led_config[chan].num_colors;
+		for (i = 0; i < led->mc_cdev.num_colors; i++) {
+			mc_led_info[i].color_index =
+				pdata->led_config[chan].color_id[i];
+			mc_led_info[i].channel =
+					pdata->led_config[chan].output_num[i];
+			j++;
+		}
+
+		led->mc_cdev.subled_info = mc_led_info;
+	} else {
+		led->cdev.brightness_set_blocking = lp55xx_set_brightness;
+	}
+
+	led->cdev.groups = lp55xx_led_groups;
+	led->cdev.default_trigger = pdata->led_config[chan].default_trigger;
 	led->led_current = pdata->led_config[chan].led_current;
 	led->max_current = pdata->led_config[chan].max_current;
 	led->chan_nr = pdata->led_config[chan].chan_nr;
-	led->cdev.default_trigger = pdata->led_config[chan].default_trigger;
 
 	if (led->chan_nr >= max_channel) {
 		dev_err(dev, "Use channel numbers between 0 and %d\n",
@@ -168,18 +221,11 @@ static int lp55xx_init_led(struct lp55xx_led *led,
 		return -EINVAL;
 	}
 
-	led->cdev.brightness_set_blocking = lp55xx_set_brightness;
-	led->cdev.groups = lp55xx_led_groups;
-
-	if (pdata->led_config[chan].name) {
-		led->cdev.name = pdata->led_config[chan].name;
-	} else {
-		snprintf(name, sizeof(name), "%s:channel%d",
-			pdata->label ? : chip->cl->name, chan);
-		led->cdev.name = name;
-	}
+	if (pdata->led_config[chan].num_colors > 1)
+		ret = devm_led_classdev_multicolor_register(dev, &led->mc_cdev);
+	else
+		ret = devm_led_classdev_register(dev, &led->cdev);
 
-	ret = devm_led_classdev_register(dev, &led->cdev);
 	if (ret) {
 		dev_err(dev, "led register err: %d\n", ret);
 		return ret;
@@ -515,14 +561,105 @@ void lp55xx_unregister_sysfs(struct lp55xx_chip *chip)
 }
 EXPORT_SYMBOL_GPL(lp55xx_unregister_sysfs);
 
+static int lp55xx_parse_common_child(struct device_node *np,
+				     struct lp55xx_led_config *cfg,
+				     int led_number, int *chan_nr)
+{
+	int ret;
+
+	of_property_read_string(np, "chan-name",
+				&cfg[led_number].name);
+	of_property_read_u8(np, "led-cur",
+			    &cfg[led_number].led_current);
+	of_property_read_u8(np, "max-cur",
+			    &cfg[led_number].max_current);
+
+	ret = of_property_read_u32(np, "reg", chan_nr);
+	if (ret)
+		return ret;
+
+	if (*chan_nr < 0 || *chan_nr > cfg->max_channel)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int lp55xx_parse_multi_led_child(struct device_node *child,
+					 struct lp55xx_led_config *cfg,
+					 int child_number, int color_number)
+{
+	int chan_nr, color_id, ret;
+
+	ret = lp55xx_parse_common_child(child, cfg, child_number, &chan_nr);
+	if (ret)
+		return ret;
+
+	ret = of_property_read_u32(child, "color", &color_id);
+	if (ret)
+		return ret;
+
+	cfg[child_number].color_id[color_number] = color_id;
+	cfg[child_number].output_num[color_number] = chan_nr;
+
+	return 0;
+}
+
+static int lp55xx_parse_multi_led(struct device_node *np,
+				  struct lp55xx_led_config *cfg,
+				  int child_number)
+{
+	struct device_node *child;
+	int num_colors = 0, ret;
+
+	for_each_child_of_node(np, child) {
+		ret = lp55xx_parse_multi_led_child(child, cfg, child_number,
+						   num_colors);
+		if (ret)
+			return ret;
+		num_colors++;
+	}
+
+	cfg[child_number].num_colors = num_colors;
+
+	return 0;
+}
+
+static int lp55xx_parse_logical_led(struct device_node *np,
+				   struct lp55xx_led_config *cfg,
+				   int child_number)
+{
+	int led_color, ret;
+	int chan_nr = 0;
+
+	cfg[child_number].default_trigger =
+		of_get_property(np, "linux,default-trigger", NULL);
+
+	ret = of_property_read_u32(np, "color", &led_color);
+	if (ret)
+		return ret;
+
+	if (led_color == LED_COLOR_ID_MULTI)
+		return lp55xx_parse_multi_led(np, cfg, child_number);
+
+	ret =  lp55xx_parse_common_child(np, cfg, child_number, &chan_nr);
+	if (ret < 0)
+		return ret;
+
+	cfg[child_number].chan_nr = chan_nr;
+
+	return ret;
+}
+
 struct lp55xx_platform_data *lp55xx_of_populate_pdata(struct device *dev,
-						      struct device_node *np)
+						      struct device_node *np,
+						      struct lp55xx_chip *chip)
 {
 	struct device_node *child;
 	struct lp55xx_platform_data *pdata;
 	struct lp55xx_led_config *cfg;
 	int num_channels;
 	int i = 0;
+	int ret;
 
 	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
@@ -540,16 +677,12 @@ struct lp55xx_platform_data *lp55xx_of_populate_pdata(struct device *dev,
 
 	pdata->led_config = &cfg[0];
 	pdata->num_channels = num_channels;
+	cfg->max_channel = chip->cfg->max_channel;
 
 	for_each_child_of_node(np, child) {
-		cfg[i].chan_nr = i;
-
-		of_property_read_string(child, "chan-name", &cfg[i].name);
-		of_property_read_u8(child, "led-cur", &cfg[i].led_current);
-		of_property_read_u8(child, "max-cur", &cfg[i].max_current);
-		cfg[i].default_trigger =
-			of_get_property(child, "linux,default-trigger", NULL);
-
+		ret = lp55xx_parse_logical_led(child, cfg, i);
+		if (ret)
+			return ERR_PTR(-EINVAL);
 		i++;
 	}
 
diff --git a/drivers/leds/leds-lp55xx-common.h b/drivers/leds/leds-lp55xx-common.h
index b9b1041e8143..2f38c5b33830 100644
--- a/drivers/leds/leds-lp55xx-common.h
+++ b/drivers/leds/leds-lp55xx-common.h
@@ -12,6 +12,8 @@
 #ifndef _LEDS_LP55XX_COMMON_H
 #define _LEDS_LP55XX_COMMON_H
 
+#include <linux/led-class-multicolor.h>
+
 enum lp55xx_engine_index {
 	LP55XX_ENGINE_INVALID,
 	LP55XX_ENGINE_1,
@@ -93,6 +95,7 @@ struct lp55xx_reg {
  * @max_channel        : Maximum number of channels
  * @post_init_device   : Chip specific initialization code
  * @brightness_fn      : Brightness function
+ * @multicolor_brightness_fn : Multicolor brightness function
  * @set_led_current    : LED current set function
  * @firmware_cb        : Call function when the firmware is loaded
  * @run_engine         : Run internal engine for pattern
@@ -106,9 +109,12 @@ struct lp55xx_device_config {
 	/* define if the device has specific initialization process */
 	int (*post_init_device) (struct lp55xx_chip *chip);
 
-	/* access brightness register */
+	/* set LED brightness */
 	int (*brightness_fn)(struct lp55xx_led *led);
 
+	/* set multicolor LED brightness */
+	int (*multicolor_brightness_fn)(struct lp55xx_led *led);
+
 	/* current setting function */
 	void (*set_led_current) (struct lp55xx_led *led, u8 led_current);
 
@@ -159,6 +165,8 @@ struct lp55xx_chip {
  * struct lp55xx_led
  * @chan_nr         : Channel number
  * @cdev            : LED class device
+ * @mc_cdev         : Multi color class device
+ * @color_components: Multi color LED map information
  * @led_current     : Current setting at each led channel
  * @max_current     : Maximun current at each led channel
  * @brightness      : Brightness value
@@ -167,6 +175,7 @@ struct lp55xx_chip {
 struct lp55xx_led {
 	int chan_nr;
 	struct led_classdev cdev;
+	struct led_classdev_mc mc_cdev;
 	u8 led_current;
 	u8 max_current;
 	u8 brightness;
@@ -196,6 +205,7 @@ extern void lp55xx_unregister_sysfs(struct lp55xx_chip *chip);
 
 /* common device tree population function */
 extern struct lp55xx_platform_data
-*lp55xx_of_populate_pdata(struct device *dev, struct device_node *np);
+*lp55xx_of_populate_pdata(struct device *dev, struct device_node *np,
+			  struct lp55xx_chip *chip);
 
 #endif /* _LEDS_LP55XX_COMMON_H */
diff --git a/drivers/leds/leds-lp8501.c b/drivers/leds/leds-lp8501.c
index a58019cdb8c3..ac2c31db4a65 100644
--- a/drivers/leds/leds-lp8501.c
+++ b/drivers/leds/leds-lp8501.c
@@ -308,9 +308,16 @@ static int lp8501_probe(struct i2c_client *client,
 	struct lp55xx_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct device_node *np = client->dev.of_node;
 
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->cfg = &lp8501_cfg;
+
 	if (!pdata) {
 		if (np) {
-			pdata = lp55xx_of_populate_pdata(&client->dev, np);
+			pdata = lp55xx_of_populate_pdata(&client->dev, np,
+							 chip);
 			if (IS_ERR(pdata))
 				return PTR_ERR(pdata);
 		} else {
@@ -319,10 +326,6 @@ static int lp8501_probe(struct i2c_client *client,
 		}
 	}
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
-
 	led = devm_kcalloc(&client->dev,
 			pdata->num_channels, sizeof(*led), GFP_KERNEL);
 	if (!led)
@@ -330,7 +333,6 @@ static int lp8501_probe(struct i2c_client *client,
 
 	chip->cl = client;
 	chip->pdata = pdata;
-	chip->cfg = &lp8501_cfg;
 
 	mutex_init(&chip->lock);
 
diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h
index 00492d6ff018..3441064713a3 100644
--- a/include/linux/platform_data/leds-lp55xx.h
+++ b/include/linux/platform_data/leds-lp55xx.h
@@ -13,18 +13,25 @@
 #define _LEDS_LP55XX_H
 
 #include <linux/gpio/consumer.h>
+#include <linux/led-class-multicolor.h>
 
 /* Clock configuration */
 #define LP55XX_CLOCK_AUTO	0
 #define LP55XX_CLOCK_INT	1
 #define LP55XX_CLOCK_EXT	2
 
+#define LP55XX_MAX_GROUPED_CHAN	4
+
 struct lp55xx_led_config {
 	const char *name;
 	const char *default_trigger;
 	u8 chan_nr;
 	u8 led_current; /* mA x10, 0 if led is not connected */
 	u8 max_current;
+	int num_colors;
+	unsigned int max_channel;
+	int color_id[LED_COLOR_ID_MAX];
+	int output_num[LED_COLOR_ID_MAX];
 };
 
 struct lp55xx_predef_pattern {
-- 
cgit v1.2.3


From 93690cdf3060c61dfce813121d0bfc055e7fa30d Mon Sep 17 00:00:00 2001
From: Marek Behún <marek.behun@nic.cz>
Date: Thu, 16 Jul 2020 19:17:28 +0200
Subject: leds: trigger: add support for LED-private device triggers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some LED controllers may come with an internal HW triggering mechanism
for the LED and the ability to switch between SW control and the
internal HW control. This includes most PHYs, various ethernet switches,
the Turris Omnia LED controller or AXP20X PMIC.

This adds support for registering such triggers.

This code is based on work by Pavel Machek <pavel@ucw.cz> and
Ondřej Jirman <megous@megous.com>.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Acked-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/led-triggers.c | 26 ++++++++++++++++++++------
 include/linux/leds.h        | 10 ++++++++++
 2 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 0836bf7631ea..91da90cfb11d 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -27,6 +27,12 @@ LIST_HEAD(trigger_list);
 
  /* Used by LED Class */
 
+static inline bool
+trigger_relevant(struct led_classdev *led_cdev, struct led_trigger *trig)
+{
+	return !trig->trigger_type || trig->trigger_type == led_cdev->trigger_type;
+}
+
 ssize_t led_trigger_write(struct file *filp, struct kobject *kobj,
 			  struct bin_attribute *bin_attr, char *buf,
 			  loff_t pos, size_t count)
@@ -50,7 +56,7 @@ ssize_t led_trigger_write(struct file *filp, struct kobject *kobj,
 
 	down_read(&triggers_list_lock);
 	list_for_each_entry(trig, &trigger_list, next_trig) {
-		if (sysfs_streq(buf, trig->name)) {
+		if (sysfs_streq(buf, trig->name) && trigger_relevant(led_cdev, trig)) {
 			down_write(&led_cdev->trigger_lock);
 			led_trigger_set(led_cdev, trig);
 			up_write(&led_cdev->trigger_lock);
@@ -93,8 +99,12 @@ static int led_trigger_format(char *buf, size_t size,
 				       led_cdev->trigger ? "none" : "[none]");
 
 	list_for_each_entry(trig, &trigger_list, next_trig) {
-		bool hit = led_cdev->trigger &&
-			!strcmp(led_cdev->trigger->name, trig->name);
+		bool hit;
+
+		if (!trigger_relevant(led_cdev, trig))
+			continue;
+
+		hit = led_cdev->trigger && !strcmp(led_cdev->trigger->name, trig->name);
 
 		len += led_trigger_snprintf(buf + len, size - len,
 					    " %s%s%s", hit ? "[" : "",
@@ -243,7 +253,8 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 	down_read(&triggers_list_lock);
 	down_write(&led_cdev->trigger_lock);
 	list_for_each_entry(trig, &trigger_list, next_trig) {
-		if (!strcmp(led_cdev->default_trigger, trig->name)) {
+		if (!strcmp(led_cdev->default_trigger, trig->name) &&
+		    trigger_relevant(led_cdev, trig)) {
 			led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER;
 			led_trigger_set(led_cdev, trig);
 			break;
@@ -280,7 +291,9 @@ int led_trigger_register(struct led_trigger *trig)
 	down_write(&triggers_list_lock);
 	/* Make sure the trigger's name isn't already in use */
 	list_for_each_entry(_trig, &trigger_list, next_trig) {
-		if (!strcmp(_trig->name, trig->name)) {
+		if (!strcmp(_trig->name, trig->name) &&
+		    (trig->trigger_type == _trig->trigger_type ||
+		     !trig->trigger_type || !_trig->trigger_type)) {
 			up_write(&triggers_list_lock);
 			return -EEXIST;
 		}
@@ -294,7 +307,8 @@ int led_trigger_register(struct led_trigger *trig)
 	list_for_each_entry(led_cdev, &leds_list, node) {
 		down_write(&led_cdev->trigger_lock);
 		if (!led_cdev->trigger && led_cdev->default_trigger &&
-			    !strcmp(led_cdev->default_trigger, trig->name)) {
+		    !strcmp(led_cdev->default_trigger, trig->name) &&
+		    trigger_relevant(led_cdev, trig)) {
 			led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER;
 			led_trigger_set(led_cdev, trig);
 		}
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 2451962d1ec5..6a8d6409c993 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -57,6 +57,10 @@ struct led_init_data {
 	bool devname_mandatory;
 };
 
+struct led_hw_trigger_type {
+	int dummy;
+};
+
 struct led_classdev {
 	const char		*name;
 	enum led_brightness	 brightness;
@@ -141,6 +145,9 @@ struct led_classdev {
 	void			*trigger_data;
 	/* true if activated - deactivate routine uses it to do cleanup */
 	bool			activated;
+
+	/* LEDs that have private triggers have this set */
+	struct led_hw_trigger_type	*trigger_type;
 #endif
 
 #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
@@ -345,6 +352,9 @@ struct led_trigger {
 	int		(*activate)(struct led_classdev *led_cdev);
 	void		(*deactivate)(struct led_classdev *led_cdev);
 
+	/* LED-private triggers have this set */
+	struct led_hw_trigger_type *trigger_type;
+
 	/* LEDs under control by this trigger (for simple triggers) */
 	rwlock_t	  leddev_list_lock;
 	struct list_head  led_cdevs;
-- 
cgit v1.2.3


From 2cf2f4f546f1dea54b63302a7eb28d1fe15f1e28 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:31 +0300
Subject: qed: reformat "qed_chain.h" a bit

Reformat structs and macros definitions a bit prior to making functional
changes.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_chain.h | 126 ++++++++++++++++++++++--------------------
 1 file changed, 66 insertions(+), 60 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 7071dc92b4e2..087073517c09 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -26,9 +26,9 @@ enum qed_chain_mode {
 };
 
 enum qed_chain_use_mode {
-	QED_CHAIN_USE_TO_PRODUCE,		/* Chain starts empty */
-	QED_CHAIN_USE_TO_CONSUME,		/* Chain starts full */
-	QED_CHAIN_USE_TO_CONSUME_PRODUCE,	/* Chain starts empty */
+	QED_CHAIN_USE_TO_PRODUCE,			/* Chain starts empty */
+	QED_CHAIN_USE_TO_CONSUME,			/* Chain starts full */
+	QED_CHAIN_USE_TO_CONSUME_PRODUCE,		/* Chain starts empty */
 };
 
 enum qed_chain_cnt_type {
@@ -40,84 +40,86 @@ enum qed_chain_cnt_type {
 };
 
 struct qed_chain_next {
-	struct regpair	next_phys;
-	void		*next_virt;
+	struct regpair					next_phys;
+	void						*next_virt;
 };
 
 struct qed_chain_pbl_u16 {
-	u16 prod_page_idx;
-	u16 cons_page_idx;
+	u16						prod_page_idx;
+	u16						cons_page_idx;
 };
 
 struct qed_chain_pbl_u32 {
-	u32 prod_page_idx;
-	u32 cons_page_idx;
+	u32						prod_page_idx;
+	u32						cons_page_idx;
 };
 
 struct qed_chain_ext_pbl {
-	dma_addr_t p_pbl_phys;
-	void *p_pbl_virt;
+	dma_addr_t					p_pbl_phys;
+	void						*p_pbl_virt;
 };
 
 struct qed_chain_u16 {
 	/* Cyclic index of next element to produce/consme */
-	u16 prod_idx;
-	u16 cons_idx;
+	u16						prod_idx;
+	u16						cons_idx;
 };
 
 struct qed_chain_u32 {
 	/* Cyclic index of next element to produce/consme */
-	u32 prod_idx;
-	u32 cons_idx;
+	u32						prod_idx;
+	u32						cons_idx;
 };
 
 struct addr_tbl_entry {
-	void *virt_addr;
-	dma_addr_t dma_map;
+	void						*virt_addr;
+	dma_addr_t					dma_map;
 };
 
 struct qed_chain {
-	/* fastpath portion of the chain - required for commands such
+	/* Fastpath portion of the chain - required for commands such
 	 * as produce / consume.
 	 */
+
 	/* Point to next element to produce/consume */
-	void *p_prod_elem;
-	void *p_cons_elem;
+	void						*p_prod_elem;
+	void						*p_cons_elem;
 
 	/* Fastpath portions of the PBL [if exists] */
+
 	struct {
 		/* Table for keeping the virtual and physical addresses of the
 		 * chain pages, respectively to the physical addresses
 		 * in the pbl table.
 		 */
-		struct addr_tbl_entry *pp_addr_tbl;
+		struct addr_tbl_entry			*pp_addr_tbl;
 
 		union {
-			struct qed_chain_pbl_u16 u16;
-			struct qed_chain_pbl_u32 u32;
-		} c;
-	} pbl;
+			struct qed_chain_pbl_u16	u16;
+			struct qed_chain_pbl_u32	u32;
+		}					c;
+	}						pbl;
 
 	union {
-		struct qed_chain_u16 chain16;
-		struct qed_chain_u32 chain32;
-	} u;
+		struct qed_chain_u16			chain16;
+		struct qed_chain_u32			chain32;
+	}						u;
 
 	/* Capacity counts only usable elements */
-	u32 capacity;
-	u32 page_cnt;
+	u32						capacity;
+	u32						page_cnt;
 
-	enum qed_chain_mode mode;
+	enum qed_chain_mode				mode;
 
 	/* Elements information for fast calculations */
-	u16 elem_per_page;
-	u16 elem_per_page_mask;
-	u16 elem_size;
-	u16 next_page_mask;
-	u16 usable_per_page;
-	u8 elem_unusable;
+	u16						elem_per_page;
+	u16						elem_per_page_mask;
+	u16						elem_size;
+	u16						next_page_mask;
+	u16						usable_per_page;
+	u8						elem_unusable;
 
-	u8 cnt_type;
+	u8						cnt_type;
 
 	/* Slowpath of the chain - required for initialization and destruction,
 	 * but isn't involved in regular functionality.
@@ -125,43 +127,47 @@ struct qed_chain {
 
 	/* Base address of a pre-allocated buffer for pbl */
 	struct {
-		dma_addr_t p_phys_table;
-		void *p_virt_table;
-	} pbl_sp;
+		dma_addr_t				p_phys_table;
+		void					*p_virt_table;
+	}						pbl_sp;
 
 	/* Address of first page of the chain - the address is required
 	 * for fastpath operation [consume/produce] but only for the SINGLE
 	 * flavour which isn't considered fastpath [== SPQ].
 	 */
-	void *p_virt_addr;
-	dma_addr_t p_phys_addr;
+	void						*p_virt_addr;
+	dma_addr_t					p_phys_addr;
 
 	/* Total number of elements [for entire chain] */
-	u32 size;
+	u32						size;
 
-	u8 intended_use;
+	u8						intended_use;
 
-	bool b_external_pbl;
+	bool						b_external_pbl;
 };
 
-#define QED_CHAIN_PBL_ENTRY_SIZE        (8)
-#define QED_CHAIN_PAGE_SIZE             (0x1000)
-#define ELEMS_PER_PAGE(elem_size)       (QED_CHAIN_PAGE_SIZE / (elem_size))
+#define QED_CHAIN_PBL_ENTRY_SIZE			8
+#define QED_CHAIN_PAGE_SIZE				0x1000
+
+#define ELEMS_PER_PAGE(elem_size)					     \
+	(QED_CHAIN_PAGE_SIZE / (elem_size))
 
-#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode)	 \
-	(((mode) == QED_CHAIN_MODE_NEXT_PTR) ?		 \
-	 (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / \
-		   (elem_size))) : 0)
+#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode)			     \
+	(((mode) == QED_CHAIN_MODE_NEXT_PTR) ?				     \
+	 (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) :     \
+	 0)
 
-#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \
-	((u32)(ELEMS_PER_PAGE(elem_size) -     \
-	       UNUSABLE_ELEMS_PER_PAGE(elem_size, mode)))
+#define USABLE_ELEMS_PER_PAGE(elem_size, mode)				     \
+	((u32)(ELEMS_PER_PAGE(elem_size) -				     \
+	       UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode))))
 
-#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \
-	DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode))
+#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode)			     \
+	DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode)))
 
-#define is_chain_u16(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16)
-#define is_chain_u32(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32)
+#define is_chain_u16(p)							     \
+	((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16)
+#define is_chain_u32(p)							     \
+	((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32)
 
 /* Accessors */
 static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain)
-- 
cgit v1.2.3


From 9b6ee3cf95d322ab02e9927f5b08ebc870ca9f1f Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:35 +0300
Subject: qed: sanitize PBL chains allocation

PBL chain elements are actually DMA addresses stored in __le64, but
currently their size is hardcoded to 8, and DMA addresses are assigned
via cast to variable-sized dma_addr_t without any bitwise conversions.
Change the type of pbl_virt array to match the actual one, add a new
field to store the size of allocated DMA memory and sanitize elements
assignment.

Misc: give more logic names to the members of qed_chain::pbl_sp embedded
struct.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_chain.c       | 21 ++++++++++-----------
 drivers/net/ethernet/qlogic/qed/qed_sp_commands.c |  4 ++--
 include/linux/qed/qed_chain.h                     | 16 ++++++++--------
 3 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_chain.c b/drivers/net/ethernet/qlogic/qed/qed_chain.c
index 917b783433f7..a9ff15b9d8c0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_chain.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_chain.c
@@ -49,7 +49,7 @@ static void qed_chain_free_pbl(struct qed_dev *cdev, struct qed_chain *chain)
 {
 	struct device *dev = &cdev->pdev->dev;
 	struct addr_tbl_entry *entry;
-	u32 pbl_size, i;
+	u32 i;
 
 	if (!chain->pbl.pp_addr_tbl)
 		return;
@@ -63,11 +63,10 @@ static void qed_chain_free_pbl(struct qed_dev *cdev, struct qed_chain *chain)
 				  entry->dma_map);
 	}
 
-	pbl_size = chain->page_cnt * QED_CHAIN_PBL_ENTRY_SIZE;
-
 	if (!chain->b_external_pbl)
-		dma_free_coherent(dev, pbl_size, chain->pbl_sp.p_virt_table,
-				  chain->pbl_sp.p_phys_table);
+		dma_free_coherent(dev, chain->pbl_sp.table_size,
+				  chain->pbl_sp.table_virt,
+				  chain->pbl_sp.table_phys);
 
 	vfree(chain->pbl.pp_addr_tbl);
 	chain->pbl.pp_addr_tbl = NULL;
@@ -190,7 +189,7 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain,
 	struct device *dev = &cdev->pdev->dev;
 	struct addr_tbl_entry *addr_tbl;
 	dma_addr_t phys, pbl_phys;
-	void *pbl_virt;
+	__le64 *pbl_virt;
 	u32 page_cnt, i;
 	size_t size;
 	void *virt;
@@ -214,7 +213,7 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain,
 
 		chain->b_external_pbl = true;
 	} else {
-		size = array_size(page_cnt, QED_CHAIN_PBL_ENTRY_SIZE);
+		size = array_size(page_cnt, sizeof(*pbl_virt));
 		if (unlikely(size == SIZE_MAX))
 			return -EOVERFLOW;
 
@@ -225,8 +224,9 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain,
 	if (!pbl_virt)
 		return -ENOMEM;
 
-	chain->pbl_sp.p_virt_table = pbl_virt;
-	chain->pbl_sp.p_phys_table = pbl_phys;
+	chain->pbl_sp.table_virt = pbl_virt;
+	chain->pbl_sp.table_phys = pbl_phys;
+	chain->pbl_sp.table_size = size;
 
 	for (i = 0; i < page_cnt; i++) {
 		virt = dma_alloc_coherent(dev, QED_CHAIN_PAGE_SIZE, &phys,
@@ -240,8 +240,7 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain,
 		}
 
 		/* Fill the PBL table with the physical address of the page */
-		*(dma_addr_t *)pbl_virt = phys;
-		pbl_virt += QED_CHAIN_PBL_ENTRY_SIZE;
+		pbl_virt[i] = cpu_to_le64(phys);
 
 		/* Keep the virtual address of the page */
 		addr_tbl[i].virt_addr = virt;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 8142f5669b26..aa71adcf31ee 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -366,11 +366,11 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
 
 	/* Place EQ address in RAMROD */
 	DMA_REGPAIR_LE(p_ramrod->event_ring_pbl_addr,
-		       p_hwfn->p_eq->chain.pbl_sp.p_phys_table);
+		       qed_chain_get_pbl_phys(&p_hwfn->p_eq->chain));
 	page_cnt = (u8)qed_chain_get_page_cnt(&p_hwfn->p_eq->chain);
 	p_ramrod->event_ring_num_pages = page_cnt;
 	DMA_REGPAIR_LE(p_ramrod->consolid_q_pbl_addr,
-		       p_hwfn->p_consq->chain.pbl_sp.p_phys_table);
+		       qed_chain_get_pbl_phys(&p_hwfn->p_consq->chain));
 
 	qed_tunn_set_pf_start_params(p_hwfn, p_tunn, &p_ramrod->tunnel_config);
 
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 087073517c09..265e0b671a5c 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -127,8 +127,9 @@ struct qed_chain {
 
 	/* Base address of a pre-allocated buffer for pbl */
 	struct {
-		dma_addr_t				p_phys_table;
-		void					*p_virt_table;
+		__le64					*table_virt;
+		dma_addr_t				table_phys;
+		size_t					table_size;
 	}						pbl_sp;
 
 	/* Address of first page of the chain - the address is required
@@ -146,7 +147,6 @@ struct qed_chain {
 	bool						b_external_pbl;
 };
 
-#define QED_CHAIN_PBL_ENTRY_SIZE			8
 #define QED_CHAIN_PAGE_SIZE				0x1000
 
 #define ELEMS_PER_PAGE(elem_size)					     \
@@ -236,7 +236,7 @@ static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain)
 
 static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain)
 {
-	return p_chain->pbl_sp.p_phys_table;
+	return p_chain->pbl_sp.table_phys;
 }
 
 /**
@@ -527,8 +527,8 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain,
 	p_chain->capacity = p_chain->usable_per_page * page_cnt;
 	p_chain->size = p_chain->elem_per_page * page_cnt;
 
-	p_chain->pbl_sp.p_phys_table = 0;
-	p_chain->pbl_sp.p_virt_table = NULL;
+	p_chain->pbl_sp.table_phys = 0;
+	p_chain->pbl_sp.table_virt = NULL;
 	p_chain->pbl.pp_addr_tbl = NULL;
 }
 
@@ -569,8 +569,8 @@ static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain,
 					  dma_addr_t p_phys_pbl,
 					  struct addr_tbl_entry *pp_addr_tbl)
 {
-	p_chain->pbl_sp.p_phys_table = p_phys_pbl;
-	p_chain->pbl_sp.p_virt_table = p_virt_pbl;
+	p_chain->pbl_sp.table_phys = p_phys_pbl;
+	p_chain->pbl_sp.table_virt = p_virt_pbl;
 	p_chain->pbl.pp_addr_tbl = pp_addr_tbl;
 }
 
-- 
cgit v1.2.3


From 5e776d8016119e13c27fbb6e87c9e1fd6f8b2a75 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:36 +0300
Subject: qed: move chain initialization inlines next to allocation functions

qed_chain_init*() are used in one file/place on "cold" path only, so they
can be uninlined and moved next to the call sites.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_chain.c |  47 ++++++++++++
 include/linux/qed/qed_chain.h               | 112 ----------------------------
 2 files changed, 47 insertions(+), 112 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_chain.c b/drivers/net/ethernet/qlogic/qed/qed_chain.c
index a9ff15b9d8c0..b60ec3e4654c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_chain.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_chain.c
@@ -7,6 +7,53 @@
 
 #include "qed_dev_api.h"
 
+static void qed_chain_init_params(struct qed_chain *chain,
+				  u32 page_cnt, u8 elem_size,
+				  enum qed_chain_use_mode intended_use,
+				  enum qed_chain_mode mode,
+				  enum qed_chain_cnt_type cnt_type)
+{
+	memset(chain, 0, sizeof(*chain));
+
+	chain->elem_size = elem_size;
+	chain->intended_use = intended_use;
+	chain->mode = mode;
+	chain->cnt_type = cnt_type;
+
+	chain->elem_per_page = ELEMS_PER_PAGE(elem_size);
+	chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode);
+	chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode);
+
+	chain->elem_per_page_mask = chain->elem_per_page - 1;
+	chain->next_page_mask = chain->usable_per_page &
+				chain->elem_per_page_mask;
+
+	chain->page_cnt = page_cnt;
+	chain->capacity = chain->usable_per_page * page_cnt;
+	chain->size = chain->elem_per_page * page_cnt;
+}
+
+static void qed_chain_init_next_ptr_elem(const struct qed_chain *chain,
+					 void *virt_curr, void *virt_next,
+					 dma_addr_t phys_next)
+{
+	struct qed_chain_next *next;
+	u32 size;
+
+	size = chain->elem_size * chain->usable_per_page;
+	next = virt_curr + size;
+
+	DMA_REGPAIR_LE(next->next_phys, phys_next);
+	next->next_virt = virt_next;
+}
+
+static void qed_chain_init_mem(struct qed_chain *chain, void *virt_addr,
+			       dma_addr_t phys_addr)
+{
+	chain->p_virt_addr = virt_addr;
+	chain->p_phys_addr = phys_addr;
+}
+
 static void qed_chain_free_next_ptr(struct qed_dev *cdev,
 				    struct qed_chain *chain)
 {
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 265e0b671a5c..a0d83095dc73 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -490,118 +490,6 @@ static inline void qed_chain_reset(struct qed_chain *p_chain)
 	}
 }
 
-/**
- * @brief qed_chain_init - Initalizes a basic chain struct
- *
- * @param p_chain
- * @param p_virt_addr
- * @param p_phys_addr	physical address of allocated buffer's beginning
- * @param page_cnt	number of pages in the allocated buffer
- * @param elem_size	size of each element in the chain
- * @param intended_use
- * @param mode
- */
-static inline void qed_chain_init_params(struct qed_chain *p_chain,
-					 u32 page_cnt,
-					 u8 elem_size,
-					 enum qed_chain_use_mode intended_use,
-					 enum qed_chain_mode mode,
-					 enum qed_chain_cnt_type cnt_type)
-{
-	/* chain fixed parameters */
-	p_chain->p_virt_addr = NULL;
-	p_chain->p_phys_addr = 0;
-	p_chain->elem_size	= elem_size;
-	p_chain->intended_use = (u8)intended_use;
-	p_chain->mode		= mode;
-	p_chain->cnt_type = (u8)cnt_type;
-
-	p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size);
-	p_chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode);
-	p_chain->elem_per_page_mask = p_chain->elem_per_page - 1;
-	p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode);
-	p_chain->next_page_mask = (p_chain->usable_per_page &
-				   p_chain->elem_per_page_mask);
-
-	p_chain->page_cnt = page_cnt;
-	p_chain->capacity = p_chain->usable_per_page * page_cnt;
-	p_chain->size = p_chain->elem_per_page * page_cnt;
-
-	p_chain->pbl_sp.table_phys = 0;
-	p_chain->pbl_sp.table_virt = NULL;
-	p_chain->pbl.pp_addr_tbl = NULL;
-}
-
-/**
- * @brief qed_chain_init_mem -
- *
- * Initalizes a basic chain struct with its chain buffers
- *
- * @param p_chain
- * @param p_virt_addr	virtual address of allocated buffer's beginning
- * @param p_phys_addr	physical address of allocated buffer's beginning
- *
- */
-static inline void qed_chain_init_mem(struct qed_chain *p_chain,
-				      void *p_virt_addr, dma_addr_t p_phys_addr)
-{
-	p_chain->p_virt_addr = p_virt_addr;
-	p_chain->p_phys_addr = p_phys_addr;
-}
-
-/**
- * @brief qed_chain_init_pbl_mem -
- *
- * Initalizes a basic chain struct with its pbl buffers
- *
- * @param p_chain
- * @param p_virt_pbl	pointer to a pre allocated side table which will hold
- *                      virtual page addresses.
- * @param p_phys_pbl	pointer to a pre-allocated side table which will hold
- *                      physical page addresses.
- * @param pp_virt_addr_tbl
- *                      pointer to a pre-allocated side table which will hold
- *                      the virtual addresses of the chain pages.
- *
- */
-static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain,
-					  void *p_virt_pbl,
-					  dma_addr_t p_phys_pbl,
-					  struct addr_tbl_entry *pp_addr_tbl)
-{
-	p_chain->pbl_sp.table_phys = p_phys_pbl;
-	p_chain->pbl_sp.table_virt = p_virt_pbl;
-	p_chain->pbl.pp_addr_tbl = pp_addr_tbl;
-}
-
-/**
- * @brief qed_chain_init_next_ptr_elem -
- *
- * Initalizes a next pointer element
- *
- * @param p_chain
- * @param p_virt_curr	virtual address of a chain page of which the next
- *                      pointer element is initialized
- * @param p_virt_next	virtual address of the next chain page
- * @param p_phys_next	physical address of the next chain page
- *
- */
-static inline void
-qed_chain_init_next_ptr_elem(struct qed_chain *p_chain,
-			     void *p_virt_curr,
-			     void *p_virt_next, dma_addr_t p_phys_next)
-{
-	struct qed_chain_next *p_next;
-	u32 size;
-
-	size = p_chain->elem_size * p_chain->usable_per_page;
-	p_next = (struct qed_chain_next *)((u8 *)p_virt_curr + size);
-
-	DMA_REGPAIR_LE(p_next->next_phys, p_phys_next);
-
-	p_next->next_virt = p_virt_next;
-}
-
 /**
  * @brief qed_chain_get_last_elem -
  *
-- 
cgit v1.2.3


From b6db3f71c976ea92361dbc7ebfb65db666ac9f02 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:38 +0300
Subject: qed: simplify chain allocation with init params struct

To simplify qed_chain_alloc() prototype and call sites, introduce struct
qed_chain_init_params to specify chain params, and pass a pointer to
filled struct to the actual qed_chain_alloc() instead of a long list
of separate arguments.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/qedr/main.c             | 20 +++---
 drivers/infiniband/hw/qedr/verbs.c            | 95 +++++++++++++--------------
 drivers/net/ethernet/qlogic/qed/qed_chain.c   | 80 ++++++++++++----------
 drivers/net/ethernet/qlogic/qed/qed_dev_api.h | 32 +--------
 drivers/net/ethernet/qlogic/qed/qed_iscsi.c   | 39 +++++------
 drivers/net/ethernet/qlogic/qed/qed_ll2.c     | 44 +++++++------
 drivers/net/ethernet/qlogic/qed/qed_spq.c     | 90 +++++++++++++++----------
 drivers/net/ethernet/qlogic/qede/qede_main.c  | 45 ++++++-------
 include/linux/qed/qed_chain.h                 | 21 ++++--
 include/linux/qed/qed_if.h                    |  9 +--
 10 files changed, 242 insertions(+), 233 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index ccaedfd53e49..b1de8d608e4d 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -346,9 +346,14 @@ static void qedr_free_resources(struct qedr_dev *dev)
 
 static int qedr_alloc_resources(struct qedr_dev *dev)
 {
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.elem_size	= sizeof(struct regpair *),
+	};
 	struct qedr_cnq *cnq;
 	__le16 *cons_pi;
-	u16 n_entries;
 	int i, rc;
 
 	dev->sgid_tbl = kcalloc(QEDR_MAX_SGID, sizeof(union ib_gid),
@@ -382,7 +387,9 @@ static int qedr_alloc_resources(struct qedr_dev *dev)
 	dev->sb_start = dev->ops->rdma_get_start_sb(dev->cdev);
 
 	/* Allocate CNQ PBLs */
-	n_entries = min_t(u32, QED_RDMA_MAX_CNQ_SIZE, QEDR_ROCE_MAX_CNQ_SIZE);
+	params.num_elems = min_t(u32, QED_RDMA_MAX_CNQ_SIZE,
+				 QEDR_ROCE_MAX_CNQ_SIZE);
+
 	for (i = 0; i < dev->num_cnq; i++) {
 		cnq = &dev->cnq_array[i];
 
@@ -391,13 +398,8 @@ static int qedr_alloc_resources(struct qedr_dev *dev)
 		if (rc)
 			goto err3;
 
-		rc = dev->ops->common->chain_alloc(dev->cdev,
-						   QED_CHAIN_USE_TO_CONSUME,
-						   QED_CHAIN_MODE_PBL,
-						   QED_CHAIN_CNT_TYPE_U16,
-						   n_entries,
-						   sizeof(struct regpair *),
-						   &cnq->pbl, NULL);
+		rc = dev->ops->common->chain_alloc(dev->cdev, &cnq->pbl,
+						   &params);
 		if (rc)
 			goto err4;
 
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 9b9e80266367..6737895a0d68 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -891,6 +891,12 @@ int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		udata, struct qedr_ucontext, ibucontext);
 	struct qed_rdma_destroy_cq_out_params destroy_oparams;
 	struct qed_rdma_destroy_cq_in_params destroy_iparams;
+	struct qed_chain_init_params chain_params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U32,
+		.elem_size	= sizeof(union rdma_cqe),
+	};
 	struct qedr_dev *dev = get_qedr_dev(ibdev);
 	struct qed_rdma_create_cq_in_params params;
 	struct qedr_create_cq_ureq ureq = {};
@@ -917,6 +923,7 @@ int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 	chain_entries = qedr_align_cq_entries(entries);
 	chain_entries = min_t(int, chain_entries, QEDR_MAX_CQES);
+	chain_params.num_elems = chain_entries;
 
 	/* calc db offset. user will add DPI base, kernel will add db addr */
 	db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_UCM_RDMA_CQ_CONS_32BIT);
@@ -951,13 +958,8 @@ int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	} else {
 		cq->cq_type = QEDR_CQ_TYPE_KERNEL;
 
-		rc = dev->ops->common->chain_alloc(dev->cdev,
-						   QED_CHAIN_USE_TO_CONSUME,
-						   QED_CHAIN_MODE_PBL,
-						   QED_CHAIN_CNT_TYPE_U32,
-						   chain_entries,
-						   sizeof(union rdma_cqe),
-						   &cq->pbl, NULL);
+		rc = dev->ops->common->chain_alloc(dev->cdev, &cq->pbl,
+						   &chain_params);
 		if (rc)
 			goto err0;
 
@@ -1446,6 +1448,12 @@ static int qedr_alloc_srq_kernel_params(struct qedr_srq *srq,
 					struct ib_srq_init_attr *init_attr)
 {
 	struct qedr_srq_hwq_info *hw_srq = &srq->hw_srq;
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U32,
+		.elem_size	= QEDR_SRQ_WQE_ELEM_SIZE,
+	};
 	dma_addr_t phy_prod_pair_addr;
 	u32 num_elems;
 	void *va;
@@ -1464,13 +1472,9 @@ static int qedr_alloc_srq_kernel_params(struct qedr_srq *srq,
 	hw_srq->virt_prod_pair_addr = va;
 
 	num_elems = init_attr->attr.max_wr * RDMA_MAX_SRQ_WQE_SIZE;
-	rc = dev->ops->common->chain_alloc(dev->cdev,
-					   QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-					   QED_CHAIN_MODE_PBL,
-					   QED_CHAIN_CNT_TYPE_U32,
-					   num_elems,
-					   QEDR_SRQ_WQE_ELEM_SIZE,
-					   &hw_srq->pbl, NULL);
+	params.num_elems = num_elems;
+
+	rc = dev->ops->common->chain_alloc(dev->cdev, &hw_srq->pbl, &params);
 	if (rc)
 		goto err0;
 
@@ -1901,29 +1905,28 @@ qedr_roce_create_kernel_qp(struct qedr_dev *dev,
 			   u32 n_sq_elems, u32 n_rq_elems)
 {
 	struct qed_rdma_create_qp_out_params out_params;
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U32,
+	};
 	int rc;
 
-	rc = dev->ops->common->chain_alloc(dev->cdev,
-					   QED_CHAIN_USE_TO_PRODUCE,
-					   QED_CHAIN_MODE_PBL,
-					   QED_CHAIN_CNT_TYPE_U32,
-					   n_sq_elems,
-					   QEDR_SQE_ELEMENT_SIZE,
-					   &qp->sq.pbl, NULL);
+	params.intended_use = QED_CHAIN_USE_TO_PRODUCE;
+	params.num_elems = n_sq_elems;
+	params.elem_size = QEDR_SQE_ELEMENT_SIZE;
 
+	rc = dev->ops->common->chain_alloc(dev->cdev, &qp->sq.pbl, &params);
 	if (rc)
 		return rc;
 
 	in_params->sq_num_pages = qed_chain_get_page_cnt(&qp->sq.pbl);
 	in_params->sq_pbl_ptr = qed_chain_get_pbl_phys(&qp->sq.pbl);
 
-	rc = dev->ops->common->chain_alloc(dev->cdev,
-					   QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-					   QED_CHAIN_MODE_PBL,
-					   QED_CHAIN_CNT_TYPE_U32,
-					   n_rq_elems,
-					   QEDR_RQE_ELEMENT_SIZE,
-					   &qp->rq.pbl, NULL);
+	params.intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE;
+	params.elem_size = n_rq_elems;
+	params.elem_size = QEDR_RQE_ELEMENT_SIZE;
+
+	rc = dev->ops->common->chain_alloc(dev->cdev, &qp->rq.pbl, &params);
 	if (rc)
 		return rc;
 
@@ -1949,7 +1952,10 @@ qedr_iwarp_create_kernel_qp(struct qedr_dev *dev,
 			    u32 n_sq_elems, u32 n_rq_elems)
 {
 	struct qed_rdma_create_qp_out_params out_params;
-	struct qed_chain_ext_pbl ext_pbl;
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U32,
+	};
 	int rc;
 
 	in_params->sq_num_pages = QED_CHAIN_PAGE_CNT(n_sq_elems,
@@ -1966,31 +1972,24 @@ qedr_iwarp_create_kernel_qp(struct qedr_dev *dev,
 		return -EINVAL;
 
 	/* Now we allocate the chain */
-	ext_pbl.p_pbl_virt = out_params.sq_pbl_virt;
-	ext_pbl.p_pbl_phys = out_params.sq_pbl_phys;
 
-	rc = dev->ops->common->chain_alloc(dev->cdev,
-					   QED_CHAIN_USE_TO_PRODUCE,
-					   QED_CHAIN_MODE_PBL,
-					   QED_CHAIN_CNT_TYPE_U32,
-					   n_sq_elems,
-					   QEDR_SQE_ELEMENT_SIZE,
-					   &qp->sq.pbl, &ext_pbl);
+	params.intended_use = QED_CHAIN_USE_TO_PRODUCE;
+	params.num_elems = n_sq_elems;
+	params.elem_size = QEDR_SQE_ELEMENT_SIZE;
+	params.ext_pbl_virt = out_params.sq_pbl_virt;
+	params.ext_pbl_phys = out_params.sq_pbl_phys;
 
+	rc = dev->ops->common->chain_alloc(dev->cdev, &qp->sq.pbl, &params);
 	if (rc)
 		goto err;
 
-	ext_pbl.p_pbl_virt = out_params.rq_pbl_virt;
-	ext_pbl.p_pbl_phys = out_params.rq_pbl_phys;
-
-	rc = dev->ops->common->chain_alloc(dev->cdev,
-					   QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-					   QED_CHAIN_MODE_PBL,
-					   QED_CHAIN_CNT_TYPE_U32,
-					   n_rq_elems,
-					   QEDR_RQE_ELEMENT_SIZE,
-					   &qp->rq.pbl, &ext_pbl);
+	params.intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE;
+	params.num_elems = n_rq_elems;
+	params.elem_size = QEDR_RQE_ELEMENT_SIZE;
+	params.ext_pbl_virt = out_params.rq_pbl_virt;
+	params.ext_pbl_phys = out_params.rq_pbl_phys;
 
+	rc = dev->ops->common->chain_alloc(dev->cdev, &qp->rq.pbl, &params);
 	if (rc)
 		goto err;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_chain.c b/drivers/net/ethernet/qlogic/qed/qed_chain.c
index 6effee3b50f4..a68ee4b3dbbc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_chain.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_chain.c
@@ -7,23 +7,22 @@
 
 #include "qed_dev_api.h"
 
-static void qed_chain_init_params(struct qed_chain *chain,
-				  u32 page_cnt, u8 elem_size,
-				  enum qed_chain_use_mode intended_use,
-				  enum qed_chain_mode mode,
-				  enum qed_chain_cnt_type cnt_type,
-				  const struct qed_chain_ext_pbl *ext_pbl)
+static void qed_chain_init(struct qed_chain *chain,
+			   const struct qed_chain_init_params *params,
+			   u32 page_cnt)
 {
 	memset(chain, 0, sizeof(*chain));
 
-	chain->elem_size = elem_size;
-	chain->intended_use = intended_use;
-	chain->mode = mode;
-	chain->cnt_type = cnt_type;
+	chain->elem_size = params->elem_size;
+	chain->intended_use = params->intended_use;
+	chain->mode = params->mode;
+	chain->cnt_type = params->cnt_type;
 
-	chain->elem_per_page = ELEMS_PER_PAGE(elem_size);
-	chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode);
-	chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode);
+	chain->elem_per_page = ELEMS_PER_PAGE(params->elem_size);
+	chain->usable_per_page = USABLE_ELEMS_PER_PAGE(params->elem_size,
+						       params->mode);
+	chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(params->elem_size,
+						       params->mode);
 
 	chain->elem_per_page_mask = chain->elem_per_page - 1;
 	chain->next_page_mask = chain->usable_per_page &
@@ -33,9 +32,9 @@ static void qed_chain_init_params(struct qed_chain *chain,
 	chain->capacity = chain->usable_per_page * page_cnt;
 	chain->size = chain->elem_per_page * page_cnt;
 
-	if (ext_pbl && ext_pbl->p_pbl_virt) {
-		chain->pbl_sp.table_virt = ext_pbl->p_pbl_virt;
-		chain->pbl_sp.table_phys = ext_pbl->p_pbl_phys;
+	if (params->ext_pbl_virt) {
+		chain->pbl_sp.table_virt = params->ext_pbl_virt;
+		chain->pbl_sp.table_phys = params->ext_pbl_phys;
 
 		chain->b_external_pbl = true;
 	}
@@ -154,10 +153,16 @@ void qed_chain_free(struct qed_dev *cdev, struct qed_chain *chain)
 
 static int
 qed_chain_alloc_sanity_check(struct qed_dev *cdev,
-			     enum qed_chain_cnt_type cnt_type,
-			     size_t elem_size, u32 page_cnt)
+			     const struct qed_chain_init_params *params,
+			     u32 page_cnt)
 {
-	u64 chain_size = ELEMS_PER_PAGE(elem_size) * page_cnt;
+	u64 chain_size;
+
+	chain_size = ELEMS_PER_PAGE(params->elem_size);
+	chain_size *= page_cnt;
+
+	if (!chain_size)
+		return -EINVAL;
 
 	/* The actual chain size can be larger than the maximal possible value
 	 * after rounding up the requested elements number to pages, and after
@@ -165,7 +170,7 @@ qed_chain_alloc_sanity_check(struct qed_dev *cdev,
 	 * The size of a "u16" chain can be (U16_MAX + 1) since the chain
 	 * size/capacity fields are of u32 type.
 	 */
-	switch (cnt_type) {
+	switch (params->cnt_type) {
 	case QED_CHAIN_CNT_TYPE_U16:
 		if (chain_size > U16_MAX + 1)
 			break;
@@ -298,37 +303,42 @@ alloc_pages:
 	return 0;
 }
 
-int qed_chain_alloc(struct qed_dev *cdev,
-		    enum qed_chain_use_mode intended_use,
-		    enum qed_chain_mode mode,
-		    enum qed_chain_cnt_type cnt_type,
-		    u32 num_elems,
-		    size_t elem_size,
-		    struct qed_chain *chain,
-		    struct qed_chain_ext_pbl *ext_pbl)
+/**
+ * qed_chain_alloc() - Allocate and initialize a chain.
+ *
+ * @cdev: Main device structure.
+ * @chain: Chain to be processed.
+ * @params: Chain initialization parameters.
+ *
+ * Return: 0 on success, negative errno otherwise.
+ */
+int qed_chain_alloc(struct qed_dev *cdev, struct qed_chain *chain,
+		    struct qed_chain_init_params *params)
 {
 	u32 page_cnt;
 	int rc;
 
-	if (mode == QED_CHAIN_MODE_SINGLE)
+	if (params->mode == QED_CHAIN_MODE_SINGLE)
 		page_cnt = 1;
 	else
-		page_cnt = QED_CHAIN_PAGE_CNT(num_elems, elem_size, mode);
+		page_cnt = QED_CHAIN_PAGE_CNT(params->num_elems,
+					      params->elem_size,
+					      params->mode);
 
-	rc = qed_chain_alloc_sanity_check(cdev, cnt_type, elem_size, page_cnt);
+	rc = qed_chain_alloc_sanity_check(cdev, params, page_cnt);
 	if (rc) {
 		DP_NOTICE(cdev,
 			  "Cannot allocate a chain with the given arguments:\n");
 		DP_NOTICE(cdev,
 			  "[use_mode %d, mode %d, cnt_type %d, num_elems %d, elem_size %zu]\n",
-			  intended_use, mode, cnt_type, num_elems, elem_size);
+			  params->intended_use, params->mode, params->cnt_type,
+			  params->num_elems, params->elem_size);
 		return rc;
 	}
 
-	qed_chain_init_params(chain, page_cnt, elem_size, intended_use, mode,
-			      cnt_type, ext_pbl);
+	qed_chain_init(chain, params, page_cnt);
 
-	switch (mode) {
+	switch (params->mode) {
 	case QED_CHAIN_MODE_NEXT_PTR:
 		rc = qed_chain_alloc_next_ptr(cdev, chain);
 		break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index 395d4932c262..d3c1f3879be8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -254,35 +254,9 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 		       dma_addr_t dest_addr,
 		       u32 size_in_dwords, struct qed_dmae_params *p_params);
 
-/**
- * @brief qed_chain_alloc - Allocate and initialize a chain
- *
- * @param p_hwfn
- * @param intended_use
- * @param mode
- * @param num_elems
- * @param elem_size
- * @param p_chain
- * @param ext_pbl - a possible external PBL
- *
- * @return int
- */
-int
-qed_chain_alloc(struct qed_dev *cdev,
-		enum qed_chain_use_mode intended_use,
-		enum qed_chain_mode mode,
-		enum qed_chain_cnt_type cnt_type,
-		u32 num_elems,
-		size_t elem_size,
-		struct qed_chain *p_chain, struct qed_chain_ext_pbl *ext_pbl);
-
-/**
- * @brief qed_chain_free - Free chain DMA memory
- *
- * @param p_hwfn
- * @param p_chain
- */
-void qed_chain_free(struct qed_dev *cdev, struct qed_chain *p_chain);
+int qed_chain_alloc(struct qed_dev *cdev, struct qed_chain *chain,
+		    struct qed_chain_init_params *params);
+void qed_chain_free(struct qed_dev *cdev, struct qed_chain *chain);
 
 /**
  * @@brief qed_fw_l2_queue - Get absolute L2 queue ID
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 25d2c882d7ac..4eae4ee3538f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -684,9 +684,13 @@ nomem:
 static int qed_iscsi_allocate_connection(struct qed_hwfn *p_hwfn,
 					 struct qed_iscsi_conn **p_out_conn)
 {
-	u16 uhq_num_elements = 0, xhq_num_elements = 0, r2tq_num_elements = 0;
 	struct scsi_terminate_extra_params *p_q_cnts = NULL;
 	struct qed_iscsi_pf_params *p_params = NULL;
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+	};
 	struct tcp_upload_params *p_tcp = NULL;
 	struct qed_iscsi_conn *p_conn = NULL;
 	int rc = 0;
@@ -727,34 +731,25 @@ static int qed_iscsi_allocate_connection(struct qed_hwfn *p_hwfn,
 		goto nomem_upload_param;
 	p_conn->tcp_upload_params_virt_addr = p_tcp;
 
-	r2tq_num_elements = p_params->num_r2tq_pages_in_ring *
-			    QED_CHAIN_PAGE_SIZE / 0x80;
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_PBL,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     r2tq_num_elements, 0x80, &p_conn->r2tq, NULL);
+	params.num_elems = p_params->num_r2tq_pages_in_ring *
+			   QED_CHAIN_PAGE_SIZE / sizeof(struct iscsi_wqe);
+	params.elem_size = sizeof(struct iscsi_wqe);
+
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->r2tq, &params);
 	if (rc)
 		goto nomem_r2tq;
 
-	uhq_num_elements = p_params->num_uhq_pages_in_ring *
+	params.num_elems = p_params->num_uhq_pages_in_ring *
 			   QED_CHAIN_PAGE_SIZE / sizeof(struct iscsi_uhqe);
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_PBL,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     uhq_num_elements,
-			     sizeof(struct iscsi_uhqe), &p_conn->uhq, NULL);
+	params.elem_size = sizeof(struct iscsi_uhqe);
+
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->uhq, &params);
 	if (rc)
 		goto nomem_uhq;
 
-	xhq_num_elements = uhq_num_elements;
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_PBL,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     xhq_num_elements,
-			     sizeof(struct iscsi_xhqe), &p_conn->xhq, NULL);
+	params.elem_size = sizeof(struct iscsi_xhqe);
+
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->xhq, &params);
 	if (rc)
 		goto nomem;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 6f4aec339cd4..0452b728c527 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1125,6 +1125,12 @@ static int
 qed_ll2_acquire_connection_rx(struct qed_hwfn *p_hwfn,
 			      struct qed_ll2_info *p_ll2_info)
 {
+	struct qed_chain_init_params params = {
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= p_ll2_info->input.rx_num_desc,
+	};
+	struct qed_dev *cdev = p_hwfn->cdev;
 	struct qed_ll2_rx_packet *p_descq;
 	u32 capacity;
 	int rc = 0;
@@ -1132,13 +1138,10 @@ qed_ll2_acquire_connection_rx(struct qed_hwfn *p_hwfn,
 	if (!p_ll2_info->input.rx_num_desc)
 		goto out;
 
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_NEXT_PTR,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     p_ll2_info->input.rx_num_desc,
-			     sizeof(struct core_rx_bd),
-			     &p_ll2_info->rx_queue.rxq_chain, NULL);
+	params.mode = QED_CHAIN_MODE_NEXT_PTR;
+	params.elem_size = sizeof(struct core_rx_bd);
+
+	rc = qed_chain_alloc(cdev, &p_ll2_info->rx_queue.rxq_chain, &params);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "Failed to allocate ll2 rxq chain\n");
 		goto out;
@@ -1154,13 +1157,10 @@ qed_ll2_acquire_connection_rx(struct qed_hwfn *p_hwfn,
 	}
 	p_ll2_info->rx_queue.descq_array = p_descq;
 
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_PBL,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     p_ll2_info->input.rx_num_desc,
-			     sizeof(struct core_rx_fast_path_cqe),
-			     &p_ll2_info->rx_queue.rcq_chain, NULL);
+	params.mode = QED_CHAIN_MODE_PBL;
+	params.elem_size = sizeof(struct core_rx_fast_path_cqe);
+
+	rc = qed_chain_alloc(cdev, &p_ll2_info->rx_queue.rcq_chain, &params);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "Failed to allocate ll2 rcq chain\n");
 		goto out;
@@ -1177,6 +1177,13 @@ out:
 static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 					 struct qed_ll2_info *p_ll2_info)
 {
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= p_ll2_info->input.tx_num_desc,
+		.elem_size	= sizeof(struct core_tx_bd),
+	};
 	struct qed_ll2_tx_packet *p_descq;
 	u32 desc_size;
 	u32 capacity;
@@ -1185,13 +1192,8 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 	if (!p_ll2_info->input.tx_num_desc)
 		goto out;
 
-	rc = qed_chain_alloc(p_hwfn->cdev,
-			     QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-			     QED_CHAIN_MODE_PBL,
-			     QED_CHAIN_CNT_TYPE_U16,
-			     p_ll2_info->input.tx_num_desc,
-			     sizeof(struct core_tx_bd),
-			     &p_ll2_info->tx_queue.txq_chain, NULL);
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_ll2_info->tx_queue.txq_chain,
+			     &params);
 	if (rc)
 		goto out;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 92ab029789e5..0bc1a0aeb56e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -382,22 +382,26 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 
 int qed_eq_alloc(struct qed_hwfn *p_hwfn, u16 num_elem)
 {
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= num_elem,
+		.elem_size	= sizeof(union event_ring_element),
+	};
 	struct qed_eq *p_eq;
+	int ret;
 
 	/* Allocate EQ struct */
 	p_eq = kzalloc(sizeof(*p_eq), GFP_KERNEL);
 	if (!p_eq)
 		return -ENOMEM;
 
-	/* Allocate and initialize EQ chain*/
-	if (qed_chain_alloc(p_hwfn->cdev,
-			    QED_CHAIN_USE_TO_PRODUCE,
-			    QED_CHAIN_MODE_PBL,
-			    QED_CHAIN_CNT_TYPE_U16,
-			    num_elem,
-			    sizeof(union event_ring_element),
-			    &p_eq->chain, NULL))
+	ret = qed_chain_alloc(p_hwfn->cdev, &p_eq->chain, &params);
+	if (ret) {
+		DP_NOTICE(p_hwfn, "Failed to allocate EQ chain\n");
 		goto eq_allocate_fail;
+	}
 
 	/* register EQ completion on the SP SB */
 	qed_int_register_cb(p_hwfn, qed_eq_completion,
@@ -408,7 +412,8 @@ int qed_eq_alloc(struct qed_hwfn *p_hwfn, u16 num_elem)
 
 eq_allocate_fail:
 	kfree(p_eq);
-	return -ENOMEM;
+
+	return ret;
 }
 
 void qed_eq_setup(struct qed_hwfn *p_hwfn)
@@ -529,33 +534,40 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 
 int qed_spq_alloc(struct qed_hwfn *p_hwfn)
 {
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_SINGLE,
+		.intended_use	= QED_CHAIN_USE_TO_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.elem_size	= sizeof(struct slow_path_element),
+	};
+	struct qed_dev *cdev = p_hwfn->cdev;
 	struct qed_spq_entry *p_virt = NULL;
 	struct qed_spq *p_spq = NULL;
 	dma_addr_t p_phys = 0;
 	u32 capacity;
+	int ret;
 
 	/* SPQ struct */
 	p_spq = kzalloc(sizeof(struct qed_spq), GFP_KERNEL);
 	if (!p_spq)
 		return -ENOMEM;
 
-	/* SPQ ring  */
-	if (qed_chain_alloc(p_hwfn->cdev,
-			    QED_CHAIN_USE_TO_PRODUCE,
-			    QED_CHAIN_MODE_SINGLE,
-			    QED_CHAIN_CNT_TYPE_U16,
-			    0,   /* N/A when the mode is SINGLE */
-			    sizeof(struct slow_path_element),
-			    &p_spq->chain, NULL))
-		goto spq_allocate_fail;
+	/* SPQ ring */
+	ret = qed_chain_alloc(cdev, &p_spq->chain, &params);
+	if (ret) {
+		DP_NOTICE(p_hwfn, "Failed to allocate SPQ chain\n");
+		goto spq_chain_alloc_fail;
+	}
 
 	/* allocate and fill the SPQ elements (incl. ramrod data list) */
 	capacity = qed_chain_get_capacity(&p_spq->chain);
-	p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+	ret = -ENOMEM;
+
+	p_virt = dma_alloc_coherent(&cdev->pdev->dev,
 				    capacity * sizeof(struct qed_spq_entry),
 				    &p_phys, GFP_KERNEL);
 	if (!p_virt)
-		goto spq_allocate_fail;
+		goto spq_alloc_fail;
 
 	p_spq->p_virt = p_virt;
 	p_spq->p_phys = p_phys;
@@ -563,10 +575,12 @@ int qed_spq_alloc(struct qed_hwfn *p_hwfn)
 
 	return 0;
 
-spq_allocate_fail:
-	qed_chain_free(p_hwfn->cdev, &p_spq->chain);
+spq_alloc_fail:
+	qed_chain_free(cdev, &p_spq->chain);
+spq_chain_alloc_fail:
 	kfree(p_spq);
-	return -ENOMEM;
+
+	return ret;
 }
 
 void qed_spq_free(struct qed_hwfn *p_hwfn)
@@ -967,30 +981,40 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+#define QED_SPQ_CONSQ_ELEM_SIZE		0x80
+
 int qed_consq_alloc(struct qed_hwfn *p_hwfn)
 {
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= QED_CHAIN_PAGE_SIZE / QED_SPQ_CONSQ_ELEM_SIZE,
+		.elem_size	= QED_SPQ_CONSQ_ELEM_SIZE,
+	};
 	struct qed_consq *p_consq;
+	int ret;
 
 	/* Allocate ConsQ struct */
 	p_consq = kzalloc(sizeof(*p_consq), GFP_KERNEL);
 	if (!p_consq)
 		return -ENOMEM;
 
-	/* Allocate and initialize EQ chain*/
-	if (qed_chain_alloc(p_hwfn->cdev,
-			    QED_CHAIN_USE_TO_PRODUCE,
-			    QED_CHAIN_MODE_PBL,
-			    QED_CHAIN_CNT_TYPE_U16,
-			    QED_CHAIN_PAGE_SIZE / 0x80,
-			    0x80, &p_consq->chain, NULL))
-		goto consq_allocate_fail;
+	/* Allocate and initialize ConsQ chain */
+	ret = qed_chain_alloc(p_hwfn->cdev, &p_consq->chain, &params);
+	if (ret) {
+		DP_NOTICE(p_hwfn, "Failed to allocate ConsQ chain");
+		goto consq_alloc_fail;
+	}
 
 	p_hwfn->p_consq = p_consq;
+
 	return 0;
 
-consq_allocate_fail:
+consq_alloc_fail:
 	kfree(p_consq);
-	return -ENOMEM;
+
+	return ret;
 }
 
 void qed_consq_setup(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 6f2171dc0dea..b5a95f165520 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1442,6 +1442,11 @@ static void qede_set_tpa_param(struct qede_rx_queue *rxq)
 /* This function allocates all memory needed per Rx queue */
 static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 {
+	struct qed_chain_init_params params = {
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= RX_RING_SIZE,
+	};
+	struct qed_dev *cdev = edev->cdev;
 	int i, rc, size;
 
 	rxq->num_rx_buffers = edev->q_num_rx_buffers;
@@ -1477,24 +1482,20 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 	}
 
 	/* Allocate FW Rx ring  */
-	rc = edev->ops->common->chain_alloc(edev->cdev,
-					    QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-					    QED_CHAIN_MODE_NEXT_PTR,
-					    QED_CHAIN_CNT_TYPE_U16,
-					    RX_RING_SIZE,
-					    sizeof(struct eth_rx_bd),
-					    &rxq->rx_bd_ring, NULL);
+	params.mode = QED_CHAIN_MODE_NEXT_PTR;
+	params.intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE;
+	params.elem_size = sizeof(struct eth_rx_bd);
+
+	rc = edev->ops->common->chain_alloc(cdev, &rxq->rx_bd_ring, &params);
 	if (rc)
 		goto err;
 
 	/* Allocate FW completion ring */
-	rc = edev->ops->common->chain_alloc(edev->cdev,
-					    QED_CHAIN_USE_TO_CONSUME,
-					    QED_CHAIN_MODE_PBL,
-					    QED_CHAIN_CNT_TYPE_U16,
-					    RX_RING_SIZE,
-					    sizeof(union eth_rx_cqe),
-					    &rxq->rx_comp_ring, NULL);
+	params.mode = QED_CHAIN_MODE_PBL;
+	params.intended_use = QED_CHAIN_USE_TO_CONSUME;
+	params.elem_size = sizeof(union eth_rx_cqe);
+
+	rc = edev->ops->common->chain_alloc(cdev, &rxq->rx_comp_ring, &params);
 	if (rc)
 		goto err;
 
@@ -1531,7 +1532,13 @@ static void qede_free_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 /* This function allocates all memory needed per Tx queue */
 static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
-	union eth_tx_bd_types *p_virt;
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+		.num_elems	= edev->q_num_tx_buffers,
+		.elem_size	= sizeof(union eth_tx_bd_types),
+	};
 	int size, rc;
 
 	txq->num_tx_buffers = edev->q_num_tx_buffers;
@@ -1549,13 +1556,7 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 			goto err;
 	}
 
-	rc = edev->ops->common->chain_alloc(edev->cdev,
-					    QED_CHAIN_USE_TO_CONSUME_PRODUCE,
-					    QED_CHAIN_MODE_PBL,
-					    QED_CHAIN_CNT_TYPE_U16,
-					    txq->num_tx_buffers,
-					    sizeof(*p_virt),
-					    &txq->tx_pbl, NULL);
+	rc = edev->ops->common->chain_alloc(edev->cdev, &txq->tx_pbl, &params);
 	if (rc)
 		goto err;
 
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index a0d83095dc73..f5cfee0934e5 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -54,11 +54,6 @@ struct qed_chain_pbl_u32 {
 	u32						cons_page_idx;
 };
 
-struct qed_chain_ext_pbl {
-	dma_addr_t					p_pbl_phys;
-	void						*p_pbl_virt;
-};
-
 struct qed_chain_u16 {
 	/* Cyclic index of next element to produce/consme */
 	u16						prod_idx;
@@ -119,7 +114,7 @@ struct qed_chain {
 	u16						usable_per_page;
 	u8						elem_unusable;
 
-	u8						cnt_type;
+	enum qed_chain_cnt_type				cnt_type;
 
 	/* Slowpath of the chain - required for initialization and destruction,
 	 * but isn't involved in regular functionality.
@@ -142,11 +137,23 @@ struct qed_chain {
 	/* Total number of elements [for entire chain] */
 	u32						size;
 
-	u8						intended_use;
+	enum qed_chain_use_mode				intended_use;
 
 	bool						b_external_pbl;
 };
 
+struct qed_chain_init_params {
+	enum qed_chain_mode				mode;
+	enum qed_chain_use_mode				intended_use;
+	enum qed_chain_cnt_type				cnt_type;
+
+	u32						num_elems;
+	size_t						elem_size;
+
+	void						*ext_pbl_virt;
+	dma_addr_t					ext_pbl_phys;
+};
+
 #define QED_CHAIN_PAGE_SIZE				0x1000
 
 #define ELEMS_PER_PAGE(elem_size)					     \
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index a5c6854343e6..cd6a5c7e56eb 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -948,13 +948,8 @@ struct qed_common_ops {
 					 u8 dp_level);
 
 	int		(*chain_alloc)(struct qed_dev *cdev,
-				       enum qed_chain_use_mode intended_use,
-				       enum qed_chain_mode mode,
-				       enum qed_chain_cnt_type cnt_type,
-				       u32 num_elems,
-				       size_t elem_size,
-				       struct qed_chain *p_chain,
-				       struct qed_chain_ext_pbl *ext_pbl);
+				       struct qed_chain *chain,
+				       struct qed_chain_init_params *params);
 
 	void		(*chain_free)(struct qed_dev *cdev,
 				      struct qed_chain *p_chain);
-- 
cgit v1.2.3


From 155065866bc36f20061c55fd2ca287a466911b16 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:39 +0300
Subject: qed: add support for different page sizes for chains

Extend current infrastructure to store chain page size in a struct
and use it in all functions instead of fixed QED_CHAIN_PAGE_SIZE.
Its value remains the default one, but can be overridden in
qed_chain_init_params before chain allocation.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/qedr/verbs.c          |  2 ++
 drivers/net/ethernet/qlogic/qed/qed_chain.c | 28 ++++++++++++++++++----------
 include/linux/qed/qed_chain.h               | 21 +++++++++++++--------
 3 files changed, 33 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 6737895a0d68..49b8a43e3fa2 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1960,9 +1960,11 @@ qedr_iwarp_create_kernel_qp(struct qedr_dev *dev,
 
 	in_params->sq_num_pages = QED_CHAIN_PAGE_CNT(n_sq_elems,
 						     QEDR_SQE_ELEMENT_SIZE,
+						     QED_CHAIN_PAGE_SIZE,
 						     QED_CHAIN_MODE_PBL);
 	in_params->rq_num_pages = QED_CHAIN_PAGE_CNT(n_rq_elems,
 						     QEDR_RQE_ELEMENT_SIZE,
+						     QED_CHAIN_PAGE_SIZE,
 						     QED_CHAIN_MODE_PBL);
 
 	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_chain.c b/drivers/net/ethernet/qlogic/qed/qed_chain.c
index a68ee4b3dbbc..f8efd36d66e0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_chain.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_chain.c
@@ -18,8 +18,10 @@ static void qed_chain_init(struct qed_chain *chain,
 	chain->mode = params->mode;
 	chain->cnt_type = params->cnt_type;
 
-	chain->elem_per_page = ELEMS_PER_PAGE(params->elem_size);
+	chain->elem_per_page = ELEMS_PER_PAGE(params->elem_size,
+					      params->page_size);
 	chain->usable_per_page = USABLE_ELEMS_PER_PAGE(params->elem_size,
+						       params->page_size,
 						       params->mode);
 	chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(params->elem_size,
 						       params->mode);
@@ -28,6 +30,7 @@ static void qed_chain_init(struct qed_chain *chain,
 	chain->next_page_mask = chain->usable_per_page &
 				chain->elem_per_page_mask;
 
+	chain->page_size = params->page_size;
 	chain->page_cnt = page_cnt;
 	chain->capacity = chain->usable_per_page * page_cnt;
 	chain->size = chain->elem_per_page * page_cnt;
@@ -82,7 +85,7 @@ static void qed_chain_free_next_ptr(struct qed_dev *cdev,
 		virt_next = next->next_virt;
 		phys_next = HILO_DMA_REGPAIR(next->next_phys);
 
-		dma_free_coherent(dev, QED_CHAIN_PAGE_SIZE, virt, phys);
+		dma_free_coherent(dev, chain->page_size, virt, phys);
 
 		virt = virt_next;
 		phys = phys_next;
@@ -95,7 +98,7 @@ static void qed_chain_free_single(struct qed_dev *cdev,
 	if (!chain->p_virt_addr)
 		return;
 
-	dma_free_coherent(&cdev->pdev->dev, QED_CHAIN_PAGE_SIZE,
+	dma_free_coherent(&cdev->pdev->dev, chain->page_size,
 			  chain->p_virt_addr, chain->p_phys_addr);
 }
 
@@ -113,7 +116,7 @@ static void qed_chain_free_pbl(struct qed_dev *cdev, struct qed_chain *chain)
 		if (!entry->virt_addr)
 			break;
 
-		dma_free_coherent(dev, QED_CHAIN_PAGE_SIZE, entry->virt_addr,
+		dma_free_coherent(dev, chain->page_size, entry->virt_addr,
 				  entry->dma_map);
 	}
 
@@ -158,7 +161,7 @@ qed_chain_alloc_sanity_check(struct qed_dev *cdev,
 {
 	u64 chain_size;
 
-	chain_size = ELEMS_PER_PAGE(params->elem_size);
+	chain_size = ELEMS_PER_PAGE(params->elem_size, params->page_size);
 	chain_size *= page_cnt;
 
 	if (!chain_size)
@@ -201,7 +204,7 @@ static int qed_chain_alloc_next_ptr(struct qed_dev *cdev,
 	u32 i;
 
 	for (i = 0; i < chain->page_cnt; i++) {
-		virt = dma_alloc_coherent(dev, QED_CHAIN_PAGE_SIZE, &phys,
+		virt = dma_alloc_coherent(dev, chain->page_size, &phys,
 					  GFP_KERNEL);
 		if (!virt)
 			return -ENOMEM;
@@ -232,7 +235,7 @@ static int qed_chain_alloc_single(struct qed_dev *cdev,
 	dma_addr_t phys;
 	void *virt;
 
-	virt = dma_alloc_coherent(&cdev->pdev->dev, QED_CHAIN_PAGE_SIZE,
+	virt = dma_alloc_coherent(&cdev->pdev->dev, chain->page_size,
 				  &phys, GFP_KERNEL);
 	if (!virt)
 		return -ENOMEM;
@@ -282,7 +285,7 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain)
 
 alloc_pages:
 	for (i = 0; i < page_cnt; i++) {
-		virt = dma_alloc_coherent(dev, QED_CHAIN_PAGE_SIZE, &phys,
+		virt = dma_alloc_coherent(dev, chain->page_size, &phys,
 					  GFP_KERNEL);
 		if (!virt)
 			return -ENOMEM;
@@ -318,11 +321,15 @@ int qed_chain_alloc(struct qed_dev *cdev, struct qed_chain *chain,
 	u32 page_cnt;
 	int rc;
 
+	if (!params->page_size)
+		params->page_size = QED_CHAIN_PAGE_SIZE;
+
 	if (params->mode == QED_CHAIN_MODE_SINGLE)
 		page_cnt = 1;
 	else
 		page_cnt = QED_CHAIN_PAGE_CNT(params->num_elems,
 					      params->elem_size,
+					      params->page_size,
 					      params->mode);
 
 	rc = qed_chain_alloc_sanity_check(cdev, params, page_cnt);
@@ -330,9 +337,10 @@ int qed_chain_alloc(struct qed_dev *cdev, struct qed_chain *chain,
 		DP_NOTICE(cdev,
 			  "Cannot allocate a chain with the given arguments:\n");
 		DP_NOTICE(cdev,
-			  "[use_mode %d, mode %d, cnt_type %d, num_elems %d, elem_size %zu]\n",
+			  "[use_mode %d, mode %d, cnt_type %d, num_elems %d, elem_size %zu, page_size %u]\n",
 			  params->intended_use, params->mode, params->cnt_type,
-			  params->num_elems, params->elem_size);
+			  params->num_elems, params->elem_size,
+			  params->page_size);
 		return rc;
 	}
 
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index f5cfee0934e5..8a96c361cc19 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -11,6 +11,7 @@
 #include <asm/byteorder.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/qed/common_hsi.h>
 
@@ -120,6 +121,8 @@ struct qed_chain {
 	 * but isn't involved in regular functionality.
 	 */
 
+	u32						page_size;
+
 	/* Base address of a pre-allocated buffer for pbl */
 	struct {
 		__le64					*table_virt;
@@ -147,6 +150,7 @@ struct qed_chain_init_params {
 	enum qed_chain_use_mode				intended_use;
 	enum qed_chain_cnt_type				cnt_type;
 
+	u32						page_size;
 	u32						num_elems;
 	size_t						elem_size;
 
@@ -154,22 +158,23 @@ struct qed_chain_init_params {
 	dma_addr_t					ext_pbl_phys;
 };
 
-#define QED_CHAIN_PAGE_SIZE				0x1000
+#define QED_CHAIN_PAGE_SIZE				SZ_4K
 
-#define ELEMS_PER_PAGE(elem_size)					     \
-	(QED_CHAIN_PAGE_SIZE / (elem_size))
+#define ELEMS_PER_PAGE(elem_size, page_size)				     \
+	((page_size) / (elem_size))
 
 #define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode)			     \
 	(((mode) == QED_CHAIN_MODE_NEXT_PTR) ?				     \
 	 (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) :     \
 	 0)
 
-#define USABLE_ELEMS_PER_PAGE(elem_size, mode)				     \
-	((u32)(ELEMS_PER_PAGE(elem_size) -				     \
+#define USABLE_ELEMS_PER_PAGE(elem_size, page_size, mode)		     \
+	((u32)(ELEMS_PER_PAGE((elem_size), (page_size)) -		     \
 	       UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode))))
 
-#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode)			     \
-	DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode)))
+#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, page_size, mode)	     \
+	DIV_ROUND_UP((elem_cnt),					     \
+		     USABLE_ELEMS_PER_PAGE((elem_size), (page_size), (mode)))
 
 #define is_chain_u16(p)							     \
 	((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16)
@@ -604,7 +609,7 @@ static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain)
 
 	for (i = 0; i < page_cnt; i++)
 		memset(p_chain->pbl.pp_addr_tbl[i].virt_addr, 0,
-		       QED_CHAIN_PAGE_SIZE);
+		       p_chain->page_size);
 }
 
 #endif
-- 
cgit v1.2.3


From f2aefd20b02d83b8565c867c38eedd88853967e9 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:40 +0300
Subject: qed: optimize common chain accessors

Constify chain pointers and refactor qed_chain_get_elem_left{,u32}() a bit.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_chain.h | 60 ++++++++++++++++++++++++-------------------
 1 file changed, 33 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 8a96c361cc19..434479e2ab65 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -182,73 +182,79 @@ struct qed_chain_init_params {
 	((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32)
 
 /* Accessors */
-static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain)
+
+static inline u16 qed_chain_get_prod_idx(const struct qed_chain *chain)
+{
+	return chain->u.chain16.prod_idx;
+}
+
+static inline u16 qed_chain_get_cons_idx(const struct qed_chain *chain)
 {
-	return p_chain->u.chain16.prod_idx;
+	return chain->u.chain16.cons_idx;
 }
 
-static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain)
+static inline u32 qed_chain_get_prod_idx_u32(const struct qed_chain *chain)
 {
-	return p_chain->u.chain16.cons_idx;
+	return chain->u.chain32.prod_idx;
 }
 
-static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain)
+static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain)
 {
-	return p_chain->u.chain32.cons_idx;
+	return chain->u.chain32.cons_idx;
 }
 
-static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
+static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain)
 {
-	u16 elem_per_page = p_chain->elem_per_page;
-	u32 prod = p_chain->u.chain16.prod_idx;
-	u32 cons = p_chain->u.chain16.cons_idx;
+	u32 prod = qed_chain_get_prod_idx(chain);
+	u32 cons = qed_chain_get_cons_idx(chain);
+	u16 elem_per_page = chain->elem_per_page;
 	u16 used;
 
 	if (prod < cons)
 		prod += (u32)U16_MAX + 1;
 
 	used = (u16)(prod - cons);
-	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= prod / elem_per_page - cons / elem_per_page;
+	if (chain->mode == QED_CHAIN_MODE_NEXT_PTR)
+		used -= (u16)(prod / elem_per_page - cons / elem_per_page);
 
-	return (u16)(p_chain->capacity - used);
+	return (u16)(chain->capacity - used);
 }
 
-static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain)
+static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain)
 {
-	u16 elem_per_page = p_chain->elem_per_page;
-	u64 prod = p_chain->u.chain32.prod_idx;
-	u64 cons = p_chain->u.chain32.cons_idx;
+	u64 prod = qed_chain_get_prod_idx_u32(chain);
+	u64 cons = qed_chain_get_cons_idx_u32(chain);
+	u16 elem_per_page = chain->elem_per_page;
 	u32 used;
 
 	if (prod < cons)
 		prod += (u64)U32_MAX + 1;
 
 	used = (u32)(prod - cons);
-	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
+	if (chain->mode == QED_CHAIN_MODE_NEXT_PTR)
 		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
 
-	return p_chain->capacity - used;
+	return chain->capacity - used;
 }
 
-static inline u16 qed_chain_get_usable_per_page(struct qed_chain *p_chain)
+static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain)
 {
-	return p_chain->usable_per_page;
+	return chain->usable_per_page;
 }
 
-static inline u8 qed_chain_get_unusable_per_page(struct qed_chain *p_chain)
+static inline u8 qed_chain_get_unusable_per_page(const struct qed_chain *chain)
 {
-	return p_chain->elem_unusable;
+	return chain->elem_unusable;
 }
 
-static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain)
+static inline u32 qed_chain_get_page_cnt(const struct qed_chain *chain)
 {
-	return p_chain->page_cnt;
+	return chain->page_cnt;
 }
 
-static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain)
+static inline dma_addr_t qed_chain_get_pbl_phys(const struct qed_chain *chain)
 {
-	return p_chain->pbl_sp.table_phys;
+	return chain->pbl_sp.table_phys;
 }
 
 /**
-- 
cgit v1.2.3


From be0cec6ffd686364bbba2796bbe5eee2fad18181 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@marvell.com>
Date: Thu, 23 Jul 2020 01:10:41 +0300
Subject: qed: introduce qed_chain_get_elem_used{,u32}()

Add reverse-variants of qed_chain_get_elem_left{,u32}() to be able to
know current chain occupation. They will be used in the upcoming qede
XDP_REDIRECT code.
They share most of the logics with the mentioned ones, so were reused
to collapse the latters.

Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_chain.h | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 434479e2ab65..4d58dc8943f0 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -203,7 +203,7 @@ static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain)
 	return chain->u.chain32.cons_idx;
 }
 
-static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain)
+static inline u16 qed_chain_get_elem_used(const struct qed_chain *chain)
 {
 	u32 prod = qed_chain_get_prod_idx(chain);
 	u32 cons = qed_chain_get_cons_idx(chain);
@@ -217,10 +217,15 @@ static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain)
 	if (chain->mode == QED_CHAIN_MODE_NEXT_PTR)
 		used -= (u16)(prod / elem_per_page - cons / elem_per_page);
 
-	return (u16)(chain->capacity - used);
+	return used;
 }
 
-static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain)
+static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain)
+{
+	return (u16)(chain->capacity - qed_chain_get_elem_used(chain));
+}
+
+static inline u32 qed_chain_get_elem_used_u32(const struct qed_chain *chain)
 {
 	u64 prod = qed_chain_get_prod_idx_u32(chain);
 	u64 cons = qed_chain_get_cons_idx_u32(chain);
@@ -234,7 +239,12 @@ static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain)
 	if (chain->mode == QED_CHAIN_MODE_NEXT_PTR)
 		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
 
-	return chain->capacity - used;
+	return used;
+}
+
+static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain)
+{
+	return chain->capacity - qed_chain_get_elem_used_u32(chain);
 }
 
 static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain)
-- 
cgit v1.2.3


From bd25b4886ddcebec92591f298ce2ce345d7f2ea9 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 14 Jul 2020 16:13:51 -0400
Subject: padata: remove start function

padata_start() is only used right after pcrypt allocates an instance
with all possible CPUs, when PADATA_INVALID can't happen, so there's no
need for a separate "start" step.  It can be done during allocation to
save text, make using padata easier, and avoid unneeded calls in the
future.

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/pcrypt.c        |  3 ---
 include/linux/padata.h |  1 -
 kernel/padata.c        | 26 +-------------------------
 3 files changed, 1 insertion(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index cbc383a1a3fe..fb9127ec5357 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -355,9 +355,6 @@ static int __init pcrypt_init(void)
 	if (err)
 		goto err_deinit_pencrypt;
 
-	padata_start(pencrypt);
-	padata_start(pdecrypt);
-
 	return crypto_register_template(&pcrypt_tmpl);
 
 err_deinit_pencrypt:
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 7302efff5e65..20294cddc739 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -204,6 +204,5 @@ extern void padata_do_serial(struct padata_priv *padata);
 extern void __init padata_do_multithreaded(struct padata_mt_job *job);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
-extern int padata_start(struct padata_instance *pinst);
 extern void padata_stop(struct padata_instance *pinst);
 #endif
diff --git a/kernel/padata.c b/kernel/padata.c
index 4373f7adaa40..931762316612 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -789,30 +789,6 @@ out:
 }
 EXPORT_SYMBOL(padata_set_cpumask);
 
-/**
- * padata_start - start the parallel processing
- *
- * @pinst: padata instance to start
- *
- * Return: 0 on success or negative error code
- */
-int padata_start(struct padata_instance *pinst)
-{
-	int err = 0;
-
-	mutex_lock(&pinst->lock);
-
-	if (pinst->flags & PADATA_INVALID)
-		err = -EINVAL;
-
-	__padata_start(pinst);
-
-	mutex_unlock(&pinst->lock);
-
-	return err;
-}
-EXPORT_SYMBOL(padata_start);
-
 /**
  * padata_stop - stop the parallel processing
  *
@@ -1100,7 +1076,7 @@ static struct padata_instance *padata_alloc(const char *name,
 	if (padata_setup_cpumasks(pinst))
 		goto err_free_rcpumask_cbcpu;
 
-	pinst->flags = 0;
+	__padata_start(pinst);
 
 	kobject_init(&pinst->kobj, &padata_attr_type);
 	mutex_init(&pinst->lock);
-- 
cgit v1.2.3


From 350ef051d4edd884e8dea0be9f3685b4b32142fb Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 14 Jul 2020 16:13:52 -0400
Subject: padata: remove stop function

padata_stop() has two callers and is unnecessary in both cases.  When
pcrypt calls it before padata_free(), it's being unloaded so there are
no outstanding padata jobs[0].  When __padata_free() calls it, it's
either along the same path or else pcrypt initialization failed, which
of course means there are also no outstanding jobs.

Removing it simplifies padata and saves text.

[0] https://lore.kernel.org/linux-crypto/20191119225017.mjrak2fwa5vccazl@gondor.apana.org.au/

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/core-api/padata.rst | 16 ++--------------
 crypto/pcrypt.c                   | 12 +++---------
 include/linux/padata.h            |  1 -
 kernel/padata.c                   | 14 --------------
 4 files changed, 5 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/padata.rst b/Documentation/core-api/padata.rst
index 0830e5b0e821..771d50330e5b 100644
--- a/Documentation/core-api/padata.rst
+++ b/Documentation/core-api/padata.rst
@@ -31,18 +31,7 @@ padata_instance structure for overall control of how jobs are to be run::
 
 'name' simply identifies the instance.
 
-There are functions for enabling and disabling the instance::
-
-    int padata_start(struct padata_instance *pinst);
-    void padata_stop(struct padata_instance *pinst);
-
-These functions are setting or clearing the "PADATA_INIT" flag; if that flag is
-not set, other functions will refuse to work.  padata_start() returns zero on
-success (flag set) or -EINVAL if the padata cpumask contains no active CPU
-(flag not set).  padata_stop() clears the flag and blocks until the padata
-instance is unused.
-
-Finally, complete padata initialization by allocating a padata_shell::
+Then, complete padata initialization by allocating a padata_shell::
 
    struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
 
@@ -155,11 +144,10 @@ submitted.
 Destroying
 ----------
 
-Cleaning up a padata instance predictably involves calling the three free
+Cleaning up a padata instance predictably involves calling the two free
 functions that correspond to the allocation in reverse::
 
     void padata_free_shell(struct padata_shell *ps);
-    void padata_stop(struct padata_instance *pinst);
     void padata_free(struct padata_instance *pinst);
 
 It is the user's responsibility to ensure all outstanding jobs are complete
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index fb9127ec5357..2d4ac9d44902 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -327,12 +327,6 @@ static int pcrypt_init_padata(struct padata_instance **pinst, const char *name)
 	return ret;
 }
 
-static void pcrypt_fini_padata(struct padata_instance *pinst)
-{
-	padata_stop(pinst);
-	padata_free(pinst);
-}
-
 static struct crypto_template pcrypt_tmpl = {
 	.name = "pcrypt",
 	.create = pcrypt_create,
@@ -358,7 +352,7 @@ static int __init pcrypt_init(void)
 	return crypto_register_template(&pcrypt_tmpl);
 
 err_deinit_pencrypt:
-	pcrypt_fini_padata(pencrypt);
+	padata_free(pencrypt);
 err_unreg_kset:
 	kset_unregister(pcrypt_kset);
 err:
@@ -369,8 +363,8 @@ static void __exit pcrypt_exit(void)
 {
 	crypto_unregister_template(&pcrypt_tmpl);
 
-	pcrypt_fini_padata(pencrypt);
-	pcrypt_fini_padata(pdecrypt);
+	padata_free(pencrypt);
+	padata_free(pdecrypt);
 
 	kset_unregister(pcrypt_kset);
 }
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 20294cddc739..7d53208b43da 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -204,5 +204,4 @@ extern void padata_do_serial(struct padata_priv *padata);
 extern void __init padata_do_multithreaded(struct padata_mt_job *job);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
-extern void padata_stop(struct padata_instance *pinst);
 #endif
diff --git a/kernel/padata.c b/kernel/padata.c
index 931762316612..8f55e717ba50 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -789,19 +789,6 @@ out:
 }
 EXPORT_SYMBOL(padata_set_cpumask);
 
-/**
- * padata_stop - stop the parallel processing
- *
- * @pinst: padata instance to stop
- */
-void padata_stop(struct padata_instance *pinst)
-{
-	mutex_lock(&pinst->lock);
-	__padata_stop(pinst);
-	mutex_unlock(&pinst->lock);
-}
-EXPORT_SYMBOL(padata_stop);
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
@@ -883,7 +870,6 @@ static void __padata_free(struct padata_instance *pinst)
 
 	WARN_ON(!list_empty(&pinst->pslist));
 
-	padata_stop(pinst);
 	free_cpumask_var(pinst->rcpumask.cbcpu);
 	free_cpumask_var(pinst->rcpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.pcpu);
-- 
cgit v1.2.3


From d69e037bcc4a7e31fdd40ae416aa1bd768dd7d99 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 14 Jul 2020 16:13:54 -0400
Subject: padata: remove effective cpumasks from the instance

A padata instance has effective cpumasks that store the user-supplied
masks ANDed with the online mask, but this middleman is unnecessary.
parallel_data keeps the same information around.  Removing this saves
text and code churn in future changes.

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/padata.h |  2 --
 kernel/padata.c        | 30 +++---------------------------
 2 files changed, 3 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 7d53208b43da..a941b96b7119 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -167,7 +167,6 @@ struct padata_mt_job {
  * @serial_wq: The workqueue used for serial work.
  * @pslist: List of padata_shell objects attached to this instance.
  * @cpumask: User supplied cpumasks for parallel and serial works.
- * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask.
  * @kobj: padata instance kernel object.
  * @lock: padata instance lock.
  * @flags: padata flags.
@@ -179,7 +178,6 @@ struct padata_instance {
 	struct workqueue_struct		*serial_wq;
 	struct list_head		pslist;
 	struct padata_cpumask		cpumask;
-	struct padata_cpumask		rcpumask;
 	struct kobject                   kobj;
 	struct mutex			 lock;
 	u8				 flags;
diff --git a/kernel/padata.c b/kernel/padata.c
index 27f90a3c4dc6..4f0a57e5738c 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -571,13 +571,8 @@ static void padata_init_pqueues(struct parallel_data *pd)
 static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 {
 	struct padata_instance *pinst = ps->pinst;
-	const struct cpumask *cbcpumask;
-	const struct cpumask *pcpumask;
 	struct parallel_data *pd;
 
-	cbcpumask = pinst->rcpumask.cbcpu;
-	pcpumask = pinst->rcpumask.pcpu;
-
 	pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
 	if (!pd)
 		goto err;
@@ -597,8 +592,8 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
 		goto err_free_pcpu;
 
-	cpumask_copy(pd->cpumask.pcpu, pcpumask);
-	cpumask_copy(pd->cpumask.cbcpu, cbcpumask);
+	cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask);
+	cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask);
 
 	padata_init_pqueues(pd);
 	padata_init_squeues(pd);
@@ -668,12 +663,6 @@ static int padata_replace(struct padata_instance *pinst)
 
 	pinst->flags |= PADATA_RESET;
 
-	cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu,
-		    cpu_online_mask);
-
-	cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu,
-		    cpu_online_mask);
-
 	list_for_each_entry(ps, &pinst->pslist, list) {
 		err = padata_replace_one(ps);
 		if (err)
@@ -856,8 +845,6 @@ static void __padata_free(struct padata_instance *pinst)
 
 	WARN_ON(!list_empty(&pinst->pslist));
 
-	free_cpumask_var(pinst->rcpumask.cbcpu);
-	free_cpumask_var(pinst->rcpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
 	destroy_workqueue(pinst->serial_wq);
@@ -1033,20 +1020,13 @@ static struct padata_instance *padata_alloc(const char *name,
 	    !padata_validate_cpumask(pinst, cbcpumask))
 		goto err_free_masks;
 
-	if (!alloc_cpumask_var(&pinst->rcpumask.pcpu, GFP_KERNEL))
-		goto err_free_masks;
-	if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL))
-		goto err_free_rcpumask_pcpu;
-
 	INIT_LIST_HEAD(&pinst->pslist);
 
 	cpumask_copy(pinst->cpumask.pcpu, pcpumask);
 	cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
-	cpumask_and(pinst->rcpumask.pcpu, pcpumask, cpu_online_mask);
-	cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask);
 
 	if (padata_setup_cpumasks(pinst))
-		goto err_free_rcpumask_cbcpu;
+		goto err_free_masks;
 
 	__padata_start(pinst);
 
@@ -1064,10 +1044,6 @@ static struct padata_instance *padata_alloc(const char *name,
 
 	return pinst;
 
-err_free_rcpumask_cbcpu:
-	free_cpumask_var(pinst->rcpumask.cbcpu);
-err_free_rcpumask_pcpu:
-	free_cpumask_var(pinst->rcpumask.pcpu);
 err_free_masks:
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
-- 
cgit v1.2.3


From 3f257191d31d5eaf154ebdb696efc238837ddd51 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 14 Jul 2020 16:13:55 -0400
Subject: padata: fold padata_alloc_possible() into padata_alloc()

There's no reason to have two interfaces when there's only one caller.
Removing _possible saves text and simplifies future changes.

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/core-api/padata.rst |  2 +-
 crypto/pcrypt.c                   |  2 +-
 include/linux/padata.h            |  2 +-
 kernel/padata.c                   | 33 +++++----------------------------
 4 files changed, 8 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/padata.rst b/Documentation/core-api/padata.rst
index 771d50330e5b..35175710b43c 100644
--- a/Documentation/core-api/padata.rst
+++ b/Documentation/core-api/padata.rst
@@ -27,7 +27,7 @@ padata_instance structure for overall control of how jobs are to be run::
 
     #include <linux/padata.h>
 
-    struct padata_instance *padata_alloc_possible(const char *name);
+    struct padata_instance *padata_alloc(const char *name);
 
 'name' simply identifies the instance.
 
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 2d4ac9d44902..d569c7ed6c80 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -316,7 +316,7 @@ static int pcrypt_init_padata(struct padata_instance **pinst, const char *name)
 {
 	int ret = -ENOMEM;
 
-	*pinst = padata_alloc_possible(name);
+	*pinst = padata_alloc(name);
 	if (!*pinst)
 		return ret;
 
diff --git a/include/linux/padata.h b/include/linux/padata.h
index a941b96b7119..070a7d43e8af 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -192,7 +192,7 @@ extern void __init padata_init(void);
 static inline void __init padata_init(void) {}
 #endif
 
-extern struct padata_instance *padata_alloc_possible(const char *name);
+extern struct padata_instance *padata_alloc(const char *name);
 extern void padata_free(struct padata_instance *pinst);
 extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
 extern void padata_free_shell(struct padata_shell *ps);
diff --git a/kernel/padata.c b/kernel/padata.c
index 4f0a57e5738c..1c0b97891edb 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -979,18 +979,12 @@ static struct kobj_type padata_attr_type = {
 };
 
 /**
- * padata_alloc - allocate and initialize a padata instance and specify
- *                cpumasks for serial and parallel workers.
- *
+ * padata_alloc - allocate and initialize a padata instance
  * @name: used to identify the instance
- * @pcpumask: cpumask that will be used for padata parallelization
- * @cbcpumask: cpumask that will be used for padata serialization
  *
  * Return: new instance on success, NULL on error
  */
-static struct padata_instance *padata_alloc(const char *name,
-					    const struct cpumask *pcpumask,
-					    const struct cpumask *cbcpumask)
+struct padata_instance *padata_alloc(const char *name)
 {
 	struct padata_instance *pinst;
 
@@ -1016,14 +1010,11 @@ static struct padata_instance *padata_alloc(const char *name,
 		free_cpumask_var(pinst->cpumask.pcpu);
 		goto err_free_serial_wq;
 	}
-	if (!padata_validate_cpumask(pinst, pcpumask) ||
-	    !padata_validate_cpumask(pinst, cbcpumask))
-		goto err_free_masks;
 
 	INIT_LIST_HEAD(&pinst->pslist);
 
-	cpumask_copy(pinst->cpumask.pcpu, pcpumask);
-	cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
+	cpumask_copy(pinst->cpumask.pcpu, cpu_possible_mask);
+	cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask);
 
 	if (padata_setup_cpumasks(pinst))
 		goto err_free_masks;
@@ -1057,21 +1048,7 @@ err_free_inst:
 err:
 	return NULL;
 }
-
-/**
- * padata_alloc_possible - Allocate and initialize padata instance.
- *                         Use the cpu_possible_mask for serial and
- *                         parallel workers.
- *
- * @name: used to identify the instance
- *
- * Return: new instance on success, NULL on error
- */
-struct padata_instance *padata_alloc_possible(const char *name)
-{
-	return padata_alloc(name, cpu_possible_mask, cpu_possible_mask);
-}
-EXPORT_SYMBOL(padata_alloc_possible);
+EXPORT_SYMBOL(padata_alloc);
 
 /**
  * padata_free - free a padata instance
-- 
cgit v1.2.3


From f601c725a6ac072608f47083e7c8115a3f504f95 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 14 Jul 2020 16:13:56 -0400
Subject: padata: remove padata_parallel_queue

Only its reorder field is actually used now, so remove the struct and
embed @reorder directly in parallel_data.

No functional change, just a cleanup.

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/padata.h | 15 ++-------------
 kernel/padata.c        | 46 ++++++++++++++++++++--------------------------
 2 files changed, 22 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 070a7d43e8af..a433f13fc4bf 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -66,17 +66,6 @@ struct padata_serial_queue {
        struct parallel_data *pd;
 };
 
-/**
- * struct padata_parallel_queue - The percpu padata parallel queue
- *
- * @reorder: List to wait for reordering after parallel processing.
- * @num_obj: Number of objects that are processed by this cpu.
- */
-struct padata_parallel_queue {
-       struct padata_list    reorder;
-       atomic_t              num_obj;
-};
-
 /**
  * struct padata_cpumask - The cpumasks for the parallel/serial workers
  *
@@ -93,7 +82,7 @@ struct padata_cpumask {
  * that depends on the cpumask in use.
  *
  * @ps: padata_shell object.
- * @pqueue: percpu padata queues used for parallelization.
+ * @reorder_list: percpu reorder lists
  * @squeue: percpu padata queues used for serialuzation.
  * @refcnt: Number of objects holding a reference on this parallel_data.
  * @seq_nr: Sequence number of the parallelized data object.
@@ -105,7 +94,7 @@ struct padata_cpumask {
  */
 struct parallel_data {
 	struct padata_shell		*ps;
-	struct padata_parallel_queue	__percpu *pqueue;
+	struct padata_list		__percpu *reorder_list;
 	struct padata_serial_queue	__percpu *squeue;
 	atomic_t			refcnt;
 	unsigned int			seq_nr;
diff --git a/kernel/padata.c b/kernel/padata.c
index 1c0b97891edb..16cb894dc272 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -250,13 +250,11 @@ EXPORT_SYMBOL(padata_do_parallel);
 static struct padata_priv *padata_find_next(struct parallel_data *pd,
 					    bool remove_object)
 {
-	struct padata_parallel_queue *next_queue;
 	struct padata_priv *padata;
 	struct padata_list *reorder;
 	int cpu = pd->cpu;
 
-	next_queue = per_cpu_ptr(pd->pqueue, cpu);
-	reorder = &next_queue->reorder;
+	reorder = per_cpu_ptr(pd->reorder_list, cpu);
 
 	spin_lock(&reorder->lock);
 	if (list_empty(&reorder->list)) {
@@ -291,7 +289,7 @@ static void padata_reorder(struct parallel_data *pd)
 	int cb_cpu;
 	struct padata_priv *padata;
 	struct padata_serial_queue *squeue;
-	struct padata_parallel_queue *next_queue;
+	struct padata_list *reorder;
 
 	/*
 	 * We need to ensure that only one cpu can work on dequeueing of
@@ -339,9 +337,8 @@ static void padata_reorder(struct parallel_data *pd)
 	 */
 	smp_mb();
 
-	next_queue = per_cpu_ptr(pd->pqueue, pd->cpu);
-	if (!list_empty(&next_queue->reorder.list) &&
-	    padata_find_next(pd, false))
+	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
+	if (!list_empty(&reorder->list) && padata_find_next(pd, false))
 		queue_work(pinst->serial_wq, &pd->reorder_work);
 }
 
@@ -401,17 +398,16 @@ void padata_do_serial(struct padata_priv *padata)
 {
 	struct parallel_data *pd = padata->pd;
 	int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr);
-	struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue,
-							   hashed_cpu);
+	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
 	struct padata_priv *cur;
 
-	spin_lock(&pqueue->reorder.lock);
+	spin_lock(&reorder->lock);
 	/* Sort in ascending order of sequence number. */
-	list_for_each_entry_reverse(cur, &pqueue->reorder.list, list)
+	list_for_each_entry_reverse(cur, &reorder->list, list)
 		if (cur->seq_nr < padata->seq_nr)
 			break;
 	list_add(&padata->list, &cur->list);
-	spin_unlock(&pqueue->reorder.lock);
+	spin_unlock(&reorder->lock);
 
 	/*
 	 * Ensure the addition to the reorder list is ordered correctly
@@ -553,17 +549,15 @@ static void padata_init_squeues(struct parallel_data *pd)
 	}
 }
 
-/* Initialize all percpu queues used by parallel workers */
-static void padata_init_pqueues(struct parallel_data *pd)
+/* Initialize per-CPU reorder lists */
+static void padata_init_reorder_list(struct parallel_data *pd)
 {
 	int cpu;
-	struct padata_parallel_queue *pqueue;
+	struct padata_list *list;
 
 	for_each_cpu(cpu, pd->cpumask.pcpu) {
-		pqueue = per_cpu_ptr(pd->pqueue, cpu);
-
-		__padata_list_init(&pqueue->reorder);
-		atomic_set(&pqueue->num_obj, 0);
+		list = per_cpu_ptr(pd->reorder_list, cpu);
+		__padata_list_init(list);
 	}
 }
 
@@ -577,13 +571,13 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	if (!pd)
 		goto err;
 
-	pd->pqueue = alloc_percpu(struct padata_parallel_queue);
-	if (!pd->pqueue)
+	pd->reorder_list = alloc_percpu(struct padata_list);
+	if (!pd->reorder_list)
 		goto err_free_pd;
 
 	pd->squeue = alloc_percpu(struct padata_serial_queue);
 	if (!pd->squeue)
-		goto err_free_pqueue;
+		goto err_free_reorder_list;
 
 	pd->ps = ps;
 
@@ -595,7 +589,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask);
 	cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask);
 
-	padata_init_pqueues(pd);
+	padata_init_reorder_list(pd);
 	padata_init_squeues(pd);
 	pd->seq_nr = -1;
 	atomic_set(&pd->refcnt, 1);
@@ -609,8 +603,8 @@ err_free_pcpu:
 	free_cpumask_var(pd->cpumask.pcpu);
 err_free_squeue:
 	free_percpu(pd->squeue);
-err_free_pqueue:
-	free_percpu(pd->pqueue);
+err_free_reorder_list:
+	free_percpu(pd->reorder_list);
 err_free_pd:
 	kfree(pd);
 err:
@@ -621,7 +615,7 @@ static void padata_free_pd(struct parallel_data *pd)
 {
 	free_cpumask_var(pd->cpumask.pcpu);
 	free_cpumask_var(pd->cpumask.cbcpu);
-	free_percpu(pd->pqueue);
+	free_percpu(pd->reorder_list);
 	free_percpu(pd->squeue);
 	kfree(pd);
 }
-- 
cgit v1.2.3


From 34ec0aa62b40e55bcd5f41b89494242c38556f30 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:29:43 -0700
Subject: misc: mic: <linux/mic_bus.h>: drop a duplicated word

Drop the repeated word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20200719002943.20624-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mic_bus.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h
index 491156a2359f..e99c789424e0 100644
--- a/include/linux/mic_bus.h
+++ b/include/linux/mic_bus.h
@@ -6,7 +6,7 @@
  *
  * Intel MIC Bus driver.
  *
- * This implementation is very similar to the the virtio bus driver
+ * This implementation is very similar to the virtio bus driver
  * implementation @ include/linux/virtio.h.
  */
 #ifndef _MIC_BUS_H_
-- 
cgit v1.2.3


From c1e18d4fb9590268105e724444792656fcb3927d Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Mon, 15 Jun 2020 22:35:21 +0200
Subject: platform/chrome: cros_ec_proto: Do not export cros_ec_cmd_xfer()

Now that all the remaining users of cros_ec_cmd_xfer() has been removed,
make this function private to the cros_ec_proto module.

Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
---
 drivers/platform/chrome/cros_ec_proto.c     | 5 ++---
 include/linux/platform_data/cros_ec_proto.h | 3 ---
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index 3e745e0fe092..11a2db7cd0f7 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -496,8 +496,8 @@ EXPORT_SYMBOL(cros_ec_query_all);
  *
  * Return: 0 on success or negative error code.
  */
-int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
-		     struct cros_ec_command *msg)
+static int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+			    struct cros_ec_command *msg)
 {
 	int ret;
 
@@ -541,7 +541,6 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
 
 	return ret;
 }
-EXPORT_SYMBOL(cros_ec_cmd_xfer);
 
 /**
  * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC.
diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index 383243326676..4a415ae851ef 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -216,9 +216,6 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
 int cros_ec_check_result(struct cros_ec_device *ec_dev,
 			 struct cros_ec_command *msg);
 
-int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
-		     struct cros_ec_command *msg);
-
 int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
 			    struct cros_ec_command *msg);
 
-- 
cgit v1.2.3


From bf9b82b7fe4d3c7d4d432ef80b4299c9b6b4a1f8 Mon Sep 17 00:00:00 2001
From: Garrit Franke <garritfranke@gmail.com>
Date: Thu, 16 Jul 2020 22:31:01 +0200
Subject: kobject: remove unused KOBJ_MAX action

The loop in libb/kobj_uevent.c that checked for KOBBJ_MAX is no longer
present, we do a much more sane ARRAY_SIZE() check instead. See
5c5daf657cb5 ("Driver core: exclude kobject_uevent.c for
!CONFIG_HOTPLUG").

Signed-off-by: Garrit Franke <garritfranke@gmail.com>
Link: https://lore.kernel.org/r/20200716203100.7959-1-garritfranke@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/kobject.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 6cba088bee24..ea30529fba08 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -59,7 +59,6 @@ enum kobject_action {
 	KOBJ_OFFLINE,
 	KOBJ_BIND,
 	KOBJ_UNBIND,
-	KOBJ_MAX
 };
 
 struct kobject {
-- 
cgit v1.2.3


From 8fc3ed3a474d76cd76dd0a154ea904373e9a5530 Mon Sep 17 00:00:00 2001
From: Colton Lewis <colton.w.lewis@protonmail.com>
Date: Thu, 23 Jul 2020 09:58:28 +0000
Subject: gpio: Correct kernel-doc inconsistency

Fix kernel-doc comment to match parameter name change "chip" to "gc"
in gpiochip_add_data function.

Signed-off-by: Colton Lewis <colton.w.lewis@protonmail.com>
Link: https://lore.kernel.org/r/20200723095658.234668-1-colton.w.lewis@protonmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/driver.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index db82451776fc..6e9f1826ecd7 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -497,25 +497,25 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 /**
  * gpiochip_add_data() - register a gpio_chip
- * @gc: the chip to register, with chip->base initialized
+ * @gc: the chip to register, with gc->base initialized
  * @data: driver-private data associated with this chip
  *
  * Context: potentially before irqs will work
  *
  * When gpiochip_add_data() is called very early during boot, so that GPIOs
- * can be freely used, the chip->parent device must be registered before
+ * can be freely used, the gc->parent device must be registered before
  * the gpio framework's arch_initcall().  Otherwise sysfs initialization
  * for GPIOs will fail rudely.
  *
  * gpiochip_add_data() must only be called after gpiolib initialization,
  * ie after core_initcall().
  *
- * If chip->base is negative, this requests dynamic assignment of
+ * If gc->base is negative, this requests dynamic assignment of
  * a range of valid GPIOs.
  *
  * Returns:
  * A negative errno if the chip can't be registered, such as because the
- * chip->base is invalid or already associated with a different chip.
+ * gc->base is invalid or already associated with a different chip.
  * Otherwise it returns zero as a success code.
  */
 #ifdef CONFIG_LOCKDEP
-- 
cgit v1.2.3


From a3b7a581823857fab4fae71be9d1c830af78a766 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 17 Jul 2020 18:47:58 +0300
Subject: bus: fsl-mc: add missing device types

The MC bus has different types of devices that can be discovered on the
bus. Add the missing device types.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Link: https://lore.kernel.org/r/20200717154800.17169-2-ioana.ciornei@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c | 30 ++++++++++++++++++++++++++++++
 include/linux/fsl/mc.h          | 30 ++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 40526da5c6a6..ee1873438e97 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -201,6 +201,31 @@ struct device_type fsl_mc_bus_dpseci_type = {
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpseci_type);
 
+struct device_type fsl_mc_bus_dpdmux_type = {
+	.name = "fsl_mc_bus_dpdmux"
+};
+EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmux_type);
+
+struct device_type fsl_mc_bus_dpdcei_type = {
+	.name = "fsl_mc_bus_dpdcei"
+};
+EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdcei_type);
+
+struct device_type fsl_mc_bus_dpaiop_type = {
+	.name = "fsl_mc_bus_dpaiop"
+};
+EXPORT_SYMBOL_GPL(fsl_mc_bus_dpaiop_type);
+
+struct device_type fsl_mc_bus_dpci_type = {
+	.name = "fsl_mc_bus_dpci"
+};
+EXPORT_SYMBOL_GPL(fsl_mc_bus_dpci_type);
+
+struct device_type fsl_mc_bus_dpdmai_type = {
+	.name = "fsl_mc_bus_dpdmai"
+};
+EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmai_type);
+
 static struct device_type *fsl_mc_get_device_type(const char *type)
 {
 	static const struct {
@@ -217,6 +242,11 @@ static struct device_type *fsl_mc_get_device_type(const char *type)
 		{ &fsl_mc_bus_dpmac_type, "dpmac" },
 		{ &fsl_mc_bus_dprtc_type, "dprtc" },
 		{ &fsl_mc_bus_dpseci_type, "dpseci" },
+		{ &fsl_mc_bus_dpdmux_type, "dpdmux" },
+		{ &fsl_mc_bus_dpdcei_type, "dpdcei" },
+		{ &fsl_mc_bus_dpaiop_type, "dpaiop" },
+		{ &fsl_mc_bus_dpci_type, "dpci" },
+		{ &fsl_mc_bus_dpdmai_type, "dpdmai" },
 		{ NULL, NULL }
 	};
 	int i;
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 2b5f8366dbe1..cdb03aca2aef 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -433,6 +433,11 @@ extern struct device_type fsl_mc_bus_dpmcp_type;
 extern struct device_type fsl_mc_bus_dpmac_type;
 extern struct device_type fsl_mc_bus_dprtc_type;
 extern struct device_type fsl_mc_bus_dpseci_type;
+extern struct device_type fsl_mc_bus_dpdmux_type;
+extern struct device_type fsl_mc_bus_dpdcei_type;
+extern struct device_type fsl_mc_bus_dpaiop_type;
+extern struct device_type fsl_mc_bus_dpci_type;
+extern struct device_type fsl_mc_bus_dpdmai_type;
 
 static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev)
 {
@@ -454,6 +459,11 @@ static inline bool is_fsl_mc_bus_dpsw(const struct fsl_mc_device *mc_dev)
 	return mc_dev->dev.type == &fsl_mc_bus_dpsw_type;
 }
 
+static inline bool is_fsl_mc_bus_dpdmux(const struct fsl_mc_device *mc_dev)
+{
+	return mc_dev->dev.type == &fsl_mc_bus_dpdmux_type;
+}
+
 static inline bool is_fsl_mc_bus_dpbp(const struct fsl_mc_device *mc_dev)
 {
 	return mc_dev->dev.type == &fsl_mc_bus_dpbp_type;
@@ -484,6 +494,26 @@ static inline bool is_fsl_mc_bus_dpseci(const struct fsl_mc_device *mc_dev)
 	return mc_dev->dev.type == &fsl_mc_bus_dpseci_type;
 }
 
+static inline bool is_fsl_mc_bus_dpdcei(const struct fsl_mc_device *mc_dev)
+{
+	return mc_dev->dev.type == &fsl_mc_bus_dpdcei_type;
+}
+
+static inline bool is_fsl_mc_bus_dpaiop(const struct fsl_mc_device *mc_dev)
+{
+	return mc_dev->dev.type == &fsl_mc_bus_dpaiop_type;
+}
+
+static inline bool is_fsl_mc_bus_dpci(const struct fsl_mc_device *mc_dev)
+{
+	return mc_dev->dev.type == &fsl_mc_bus_dpci_type;
+}
+
+static inline bool is_fsl_mc_bus_dpdmai(const struct fsl_mc_device *mc_dev)
+{
+	return mc_dev->dev.type == &fsl_mc_bus_dpdmai_type;
+}
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 9a872def598195d2de4a4a74e17804142e2aa78e Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Fri, 17 Jul 2020 18:47:59 +0300
Subject: bus: fsl-mc: use raw spin lock to serialize mc cmds

Replace the spinlock that serializes the MC commands with a raw
spinlock. This is needed for the RT kernel because there are MC
commands sent in interrupt context.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Link: https://lore.kernel.org/r/20200717154800.17169-3-ioana.ciornei@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/mc-io.c  | 2 +-
 drivers/bus/fsl-mc/mc-sys.c | 4 ++--
 include/linux/fsl/mc.h      | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/mc-io.c b/drivers/bus/fsl-mc/mc-io.c
index 6ae48ad80409..a30b53f1d87d 100644
--- a/drivers/bus/fsl-mc/mc-io.c
+++ b/drivers/bus/fsl-mc/mc-io.c
@@ -82,7 +82,7 @@ int __must_check fsl_create_mc_io(struct device *dev,
 	mc_io->portal_phys_addr = mc_portal_phys_addr;
 	mc_io->portal_size = mc_portal_size;
 	if (flags & FSL_MC_IO_ATOMIC_CONTEXT_PORTAL)
-		spin_lock_init(&mc_io->spinlock);
+		raw_spin_lock_init(&mc_io->spinlock);
 	else
 		mutex_init(&mc_io->mutex);
 
diff --git a/drivers/bus/fsl-mc/mc-sys.c b/drivers/bus/fsl-mc/mc-sys.c
index 3221a7fbaf0a..85a0225db522 100644
--- a/drivers/bus/fsl-mc/mc-sys.c
+++ b/drivers/bus/fsl-mc/mc-sys.c
@@ -251,7 +251,7 @@ int mc_send_command(struct fsl_mc_io *mc_io, struct fsl_mc_command *cmd)
 		return -EINVAL;
 
 	if (mc_io->flags & FSL_MC_IO_ATOMIC_CONTEXT_PORTAL)
-		spin_lock_irqsave(&mc_io->spinlock, irq_flags);
+		raw_spin_lock_irqsave(&mc_io->spinlock, irq_flags);
 	else
 		mutex_lock(&mc_io->mutex);
 
@@ -287,7 +287,7 @@ int mc_send_command(struct fsl_mc_io *mc_io, struct fsl_mc_command *cmd)
 	error = 0;
 common_exit:
 	if (mc_io->flags & FSL_MC_IO_ATOMIC_CONTEXT_PORTAL)
-		spin_unlock_irqrestore(&mc_io->spinlock, irq_flags);
+		raw_spin_unlock_irqrestore(&mc_io->spinlock, irq_flags);
 	else
 		mutex_unlock(&mc_io->mutex);
 
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index cdb03aca2aef..a428c61ead6e 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -339,7 +339,7 @@ struct fsl_mc_io {
 		 * This field is only meaningful if the
 		 * FSL_MC_IO_ATOMIC_CONTEXT_PORTAL flag is set
 		 */
-		spinlock_t spinlock;	/* serializes mc_send_command() */
+		raw_spinlock_t spinlock; /* serializes mc_send_command() */
 	};
 };
 
-- 
cgit v1.2.3


From 5df96f2b9f58a5d2dc1f30fe7de75e197f2c25f2 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Thu, 23 Jul 2020 10:42:09 -0400
Subject: dm integrity: fix integrity recalculation that is improperly skipped

Commit adc0daad366b62ca1bce3e2958a40b0b71a8b8b3 ("dm: report suspended
device during destroy") broke integrity recalculation.

The problem is dm_suspended() returns true not only during suspend,
but also during resume. So this race condition could occur:
1. dm_integrity_resume calls queue_work(ic->recalc_wq, &ic->recalc_work)
2. integrity_recalc (&ic->recalc_work) preempts the current thread
3. integrity_recalc calls if (unlikely(dm_suspended(ic->ti))) goto unlock_ret;
4. integrity_recalc exits and no recalculating is done.

To fix this race condition, add a function dm_post_suspending that is
only true during the postsuspend phase and use it instead of
dm_suspended().

Signed-off-by: Mikulas Patocka <mpatocka redhat com>
Fixes: adc0daad366b ("dm: report suspended device during destroy")
Cc: stable vger kernel org # v4.18+
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-integrity.c     |  4 ++--
 drivers/md/dm.c               | 17 +++++++++++++++++
 include/linux/device-mapper.h |  1 +
 3 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 81dc5ff08909..a83a1de1e03f 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2420,7 +2420,7 @@ static void integrity_writer(struct work_struct *w)
 	unsigned prev_free_sectors;
 
 	/* the following test is not needed, but it tests the replay code */
-	if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
+	if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev)
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
@@ -2481,7 +2481,7 @@ static void integrity_recalc(struct work_struct *w)
 
 next_chunk:
 
-	if (unlikely(dm_suspended(ic->ti)))
+	if (unlikely(dm_post_suspending(ic->ti)))
 		goto unlock_ret;
 
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 52449afd58eb..5b9de2f71bb0 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -143,6 +143,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_DEFERRED_REMOVE 6
 #define DMF_SUSPENDED_INTERNALLY 7
+#define DMF_POST_SUSPENDING 8
 
 #define DM_NUMA_NODE NUMA_NO_NODE
 static int dm_numa_node = DM_NUMA_NODE;
@@ -2408,6 +2409,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		set_bit(DMF_SUSPENDED, &md->flags);
+		set_bit(DMF_POST_SUSPENDING, &md->flags);
 		dm_table_postsuspend_targets(map);
 	}
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
@@ -2766,7 +2768,9 @@ retry:
 	if (r)
 		goto out_unlock;
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 
 out_unlock:
 	mutex_unlock(&md->suspend_lock);
@@ -2863,7 +2867,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
 			    DMF_SUSPENDED_INTERNALLY);
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 }
 
 static void __dm_internal_resume(struct mapped_device *md)
@@ -3024,6 +3030,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+static int dm_post_suspending_md(struct mapped_device *md)
+{
+	return test_bit(DMF_POST_SUSPENDING, &md->flags);
+}
+
 int dm_suspended_internally_md(struct mapped_device *md)
 {
 	return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
@@ -3040,6 +3051,12 @@ int dm_suspended(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_suspended);
 
+int dm_post_suspending(struct dm_target *ti)
+{
+	return dm_post_suspending_md(dm_table_get_md(ti->table));
+}
+EXPORT_SYMBOL_GPL(dm_post_suspending);
+
 int dm_noflush_suspending(struct dm_target *ti)
 {
 	return __noflush_suspending(dm_table_get_md(ti->table));
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8750f2dc5613..73dec4b5d5be 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -426,6 +426,7 @@ const char *dm_device_name(struct mapped_device *md);
 int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
 struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
+int dm_post_suspending(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
-- 
cgit v1.2.3


From 76be93fc0702322179bb0ea87295d820ee46ad14 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 23 Jul 2020 12:00:06 -0700
Subject: tcp: allow at most one TLP probe per flight

Previously TLP may send multiple probes of new data in one
flight. This happens when the sender is cwnd limited. After the
initial TLP containing new data is sent, the sender receives another
ACK that acks partial inflight.  It may re-arm another TLP timer
to send more, if no further ACK returns before the next TLP timeout
(PTO) expires. The sender may send in theory a large amount of TLP
until send queue is depleted. This only happens if the sender sees
such irregular uncommon ACK pattern. But it is generally undesirable
behavior during congestion especially.

The original TLP design restrict only one TLP probe per inflight as
published in "Reducing Web Latency: the Virtue of Gentle Aggression",
SIGCOMM 2013. This patch changes TLP to send at most one probe
per inflight.

Note that if the sender is app-limited, TLP retransmits old data
and did not have this issue.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  6 ++++--
 net/ipv4/tcp_input.c  | 11 ++++++-----
 net/ipv4/tcp_output.c | 13 ++++++++-----
 3 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 9aac824c523c..a1bbaa1c1a3a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -220,7 +220,9 @@ struct tcp_sock {
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
-	u8	dup_ack_counter;
+	u8	dup_ack_counter:2,
+		tlp_retrans:1,	/* TLP is a retransmission */
+		unused:5;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -243,7 +245,7 @@ struct tcp_sock {
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
 		syn_smc:1;	/* SYN includes SMC */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
 	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9615e72656d1..518f04355fbf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3488,10 +3488,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 	}
 }
 
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -3500,7 +3498,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (before(ack, tp->tlp_high_seq))
 		return;
 
-	if (flag & FLAG_DSACKING_ACK) {
+	if (!tp->tlp_retrans) {
+		/* TLP of new data has been acknowledged */
+		tp->tlp_high_seq = 0;
+	} else if (flag & FLAG_DSACKING_ACK) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5f5b2f0b0e60..0bc05d68cd74 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2624,6 +2624,11 @@ void tcp_send_loss_probe(struct sock *sk)
 	int pcount;
 	int mss = tcp_current_mss(sk);
 
+	/* At most one outstanding TLP */
+	if (tp->tlp_high_seq)
+		goto rearm_timer;
+
+	tp->tlp_retrans = 0;
 	skb = tcp_send_head(sk);
 	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
 		pcount = tp->packets_out;
@@ -2641,10 +2646,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		return;
 	}
 
-	/* At most one outstanding TLP retransmission. */
-	if (tp->tlp_high_seq)
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2666,10 +2667,12 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (__tcp_retransmit_skb(sk, skb, 1))
 		goto rearm_timer;
 
+	tp->tlp_retrans = 1;
+
+probe_sent:
 	/* Record snd_nxt for loss detection. */
 	tp->tlp_high_seq = tp->snd_nxt;
 
-probe_sent:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
 	/* Reset s.t. tcp_rearm_rto will restart timer from now */
 	inet_csk(sk)->icsk_pending = 0;
-- 
cgit v1.2.3


From 7f3d176f5f7e3f0477bf82df0f600fcddcdcc4e4 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.microsoft.com>
Date: Fri, 10 Jul 2020 14:29:55 -0500
Subject: tpm: Require that all digests are present in TCG_PCR_EVENT2
 structures

Require that the TCG_PCR_EVENT2.digests.count value strictly matches the
value of TCG_EfiSpecIdEvent.numberOfAlgorithms in the event field of the
TCG_PCClientPCREvent event log header. Also require that
TCG_EfiSpecIdEvent.numberOfAlgorithms is non-zero.

The TCG PC Client Platform Firmware Profile Specification section 9.1
(Family "2.0", Level 00 Revision 1.04) states:

 For each Hash algorithm enumerated in the TCG_PCClientPCREvent entry,
 there SHALL be a corresponding digest in all TCG_PCR_EVENT2 structures.
 Note: This includes EV_NO_ACTION events which do not extend the PCR.

Section 9.4.5.1 provides this description of
TCG_EfiSpecIdEvent.numberOfAlgorithms:

 The number of Hash algorithms in the digestSizes field. This field MUST
 be set to a value of 0x01 or greater.

Enforce these restrictions, as required by the above specification, in
order to better identify and ignore invalid sequences of bytes at the
end of an otherwise valid TPM2 event log. Firmware doesn't always have
the means necessary to inform the kernel of the actual event log size so
the kernel's event log parsing code should be stringent when parsing the
event log for resiliency against firmware bugs. This is true, for
example, when firmware passes the event log to the kernel via a reserved
memory region described in device tree.

POWER and some ARM systems use the "linux,sml-base" and "linux,sml-size"
device tree properties to describe the memory region used to pass the
event log from firmware to the kernel. Unfortunately, the
"linux,sml-size" property describes the size of the entire reserved
memory region rather than the size of the event long within the memory
region and the event log format does not include information describing
the size of the event log.

tpm_read_log_of(), in drivers/char/tpm/eventlog/of.c, is where the
"linux,sml-size" property is used. At the end of that function,
log->bios_event_log_end is pointing at the end of the reserved memory
region. That's typically 0x10000 bytes offset from "linux,sml-base",
depending on what's defined in the device tree source.

The firmware event log only fills a portion of those 0x10000 bytes and
the rest of the memory region should be zeroed out by firmware. Even in
the case of a properly zeroed bytes in the remainder of the memory
region, the only thing allowing the kernel's event log parser to detect
the end of the event log is the following conditional in
__calc_tpm2_event_size():

        if (event_type == 0 && event_field->event_size == 0)
                size = 0;

If that wasn't there, __calc_tpm2_event_size() would think that a 16
byte sequence of zeroes, following an otherwise valid event log, was
a valid event.

However, problems can occur if a single bit is set in the offset
corresponding to either the TCG_PCR_EVENT2.eventType or
TCG_PCR_EVENT2.eventSize fields, after the last valid event log entry.
This could confuse the parser into thinking that an additional entry is
present in the event log and exposing this invalid entry to userspace in
the /sys/kernel/security/tpm0/binary_bios_measurements file. Such
problems have been seen if firmware does not fully zero the memory
region upon a warm reboot.

This patch significantly raises the bar on how difficult it is for
stale/invalid memory to confuse the kernel's event log parser but
there's still, ultimately, a reliance on firmware to properly initialize
the remainder of the memory region reserved for the event log as the
parser cannot be expected to detect a stale but otherwise properly
formatted firmware event log entry.

Fixes: fd5c78694f3f ("tpm: fix handling of the TPM 2.0 event logs")
Signed-off-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 include/linux/tpm_eventlog.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 64356b199e94..739ba9a03ec1 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -211,9 +211,16 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 
 	efispecid = (struct tcg_efi_specid_event_head *)event_header->event;
 
-	/* Check if event is malformed. */
+	/*
+	 * Perform validation of the event in order to identify malformed
+	 * events. This function may be asked to parse arbitrary byte sequences
+	 * immediately following a valid event log. The caller expects this
+	 * function to recognize that the byte sequence is not a valid event
+	 * and to return an event size of 0.
+	 */
 	if (memcmp(efispecid->signature, TCG_SPECID_SIG,
-		   sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) {
+		   sizeof(TCG_SPECID_SIG)) ||
+	    !efispecid->num_algs || count != efispecid->num_algs) {
 		size = 0;
 		goto out;
 	}
-- 
cgit v1.2.3


From 6c4e79d99e6f42b79040f1a33cd4018f5425030b Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Fri, 3 Jul 2020 01:55:59 +0300
Subject: tpm: Unify the mismatching TPM space buffer sizes

The size of the buffers for storing context's and sessions can vary from
arch to arch as PAGE_SIZE can be anything between 4 kB and 256 kB (the
maximum for PPC64). Define a fixed buffer size set to 16 kB. This should be
enough for most use with three handles (that is how many we allow at the
moment). Parametrize the buffer size while doing this, so that it is easier
to revisit this later on if required.

Cc: stable@vger.kernel.org
Reported-by: Stefan Berger <stefanb@linux.ibm.com>
Fixes: 745b361e989a ("tpm: infrastructure for TPM spaces")
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Stefan Berger <stefanb@linux.ibm.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-chip.c   |  9 ++-------
 drivers/char/tpm/tpm.h        |  5 ++++-
 drivers/char/tpm/tpm2-space.c | 26 ++++++++++++++++----------
 drivers/char/tpm/tpmrm-dev.c  |  2 +-
 include/linux/tpm.h           |  1 +
 5 files changed, 24 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 8c77e88012e9..ddaeceb7e109 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -386,13 +386,8 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev,
 	chip->cdev.owner = THIS_MODULE;
 	chip->cdevs.owner = THIS_MODULE;
 
-	chip->work_space.context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.context_buf) {
-		rc = -ENOMEM;
-		goto out;
-	}
-	chip->work_space.session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.session_buf) {
+	rc = tpm2_init_space(&chip->work_space, TPM2_SPACE_BUFFER_SIZE);
+	if (rc) {
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 0fbcede241ea..947d1db0a5cc 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -59,6 +59,9 @@ enum tpm_addr {
 
 #define TPM_TAG_RQU_COMMAND 193
 
+/* TPM2 specific constants. */
+#define TPM2_SPACE_BUFFER_SIZE		16384 /* 16 kB */
+
 struct	stclear_flags_t {
 	__be16	tag;
 	u8	deactivated;
@@ -228,7 +231,7 @@ unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
 int tpm2_probe(struct tpm_chip *chip);
 int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip);
 int tpm2_find_cc(struct tpm_chip *chip, u32 cc);
-int tpm2_init_space(struct tpm_space *space);
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size);
 void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space);
 void tpm2_flush_space(struct tpm_chip *chip);
 int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd,
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 982d341d8837..784b8b3cb903 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -38,18 +38,21 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	}
 }
 
-int tpm2_init_space(struct tpm_space *space)
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size)
 {
-	space->context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->context_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!space->context_buf)
 		return -ENOMEM;
 
-	space->session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->session_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (space->session_buf == NULL) {
 		kfree(space->context_buf);
+		/* Prevent caller getting a dangling pointer. */
+		space->context_buf = NULL;
 		return -ENOMEM;
 	}
 
+	space->buf_size = buf_size;
 	return 0;
 }
 
@@ -311,8 +314,10 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd,
 	       sizeof(space->context_tbl));
 	memcpy(&chip->work_space.session_tbl, &space->session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(chip->work_space.context_buf, space->context_buf, PAGE_SIZE);
-	memcpy(chip->work_space.session_buf, space->session_buf, PAGE_SIZE);
+	memcpy(chip->work_space.context_buf, space->context_buf,
+	       space->buf_size);
+	memcpy(chip->work_space.session_buf, space->session_buf,
+	       space->buf_size);
 
 	rc = tpm2_load_space(chip);
 	if (rc) {
@@ -492,7 +497,7 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->context_tbl[i],
-				       space->context_buf, PAGE_SIZE,
+				       space->context_buf, space->buf_size,
 				       &offset);
 		if (rc == -ENOENT) {
 			space->context_tbl[i] = 0;
@@ -509,9 +514,8 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->session_tbl[i],
-				       space->session_buf, PAGE_SIZE,
+				       space->session_buf, space->buf_size,
 				       &offset);
-
 		if (rc == -ENOENT) {
 			/* handle error saving session, just forget it */
 			space->session_tbl[i] = 0;
@@ -557,8 +561,10 @@ int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space,
 	       sizeof(space->context_tbl));
 	memcpy(&space->session_tbl, &chip->work_space.session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(space->context_buf, chip->work_space.context_buf, PAGE_SIZE);
-	memcpy(space->session_buf, chip->work_space.session_buf, PAGE_SIZE);
+	memcpy(space->context_buf, chip->work_space.context_buf,
+	       space->buf_size);
+	memcpy(space->session_buf, chip->work_space.session_buf,
+	       space->buf_size);
 
 	return 0;
 out:
diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c
index 7a0a7051a06f..eef0fb06ea83 100644
--- a/drivers/char/tpm/tpmrm-dev.c
+++ b/drivers/char/tpm/tpmrm-dev.c
@@ -21,7 +21,7 @@ static int tpmrm_open(struct inode *inode, struct file *file)
 	if (priv == NULL)
 		return -ENOMEM;
 
-	rc = tpm2_init_space(&priv->space);
+	rc = tpm2_init_space(&priv->space, TPM2_SPACE_BUFFER_SIZE);
 	if (rc) {
 		kfree(priv);
 		return -ENOMEM;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 03e9b184411b..8f4ff39f51e7 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -96,6 +96,7 @@ struct tpm_space {
 	u8 *context_buf;
 	u32 session_tbl[3];
 	u8 *session_buf;
+	u32 buf_size;
 };
 
 struct tpm_bios_log {
-- 
cgit v1.2.3


From 5f77d6ca5ca74e4b4a5e2e010f7ff50c45dea326 Mon Sep 17 00:00:00 2001
From: Liu Yi L <yi.l.liu@intel.com>
Date: Fri, 24 Jul 2020 09:49:14 +0800
Subject: iommu/vt-d: Enforce PASID devTLB field mask

Set proper masks to avoid invalid input spillover to reserved bits.

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200724014925.15523-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/intel-iommu.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 3e8fa1c7a1e6..311117b50e93 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -381,8 +381,8 @@ enum {
 
 #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
-#define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
-#define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
+#define QI_DEV_EIOTLB_GLOB(g)	((u64)(g) & 0x1)
+#define QI_DEV_EIOTLB_PASID(p)	((u64)((p) & 0xfffff) << 32)
 #define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
 #define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \
-- 
cgit v1.2.3


From 78df6c86f0691f5b6e325006aeb470de443351ea Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
Date: Fri, 24 Jul 2020 09:49:15 +0800
Subject: iommu/vt-d: Remove global page support in devTLB flush

Global pages support is removed from VT-d spec 3.0 for dev TLB
invalidation. This patch is to remove the bits for vSVA. Similar change
already made for the native SVA. See the link below.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/linux-iommu/20190830142919.GE11578@8bytes.org/T/
Link: https://lore.kernel.org/r/20200724014925.15523-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/dmar.c  | 4 +---
 drivers/iommu/intel/iommu.c | 4 ++--
 include/linux/intel-iommu.h | 3 +--
 3 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 683b812c5c47..9be08b9400ee 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1438,8 +1438,7 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 
 /* PASID-based device IOTLB Invalidate */
 void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
-			      u32 pasid,  u16 qdep, u64 addr,
-			      unsigned int size_order, u64 granu)
+			      u32 pasid,  u16 qdep, u64 addr, unsigned int size_order)
 {
 	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
 	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
@@ -1447,7 +1446,6 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
 		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
 		QI_DEV_IOTLB_PFSID(pfsid);
-	desc.qw1 = QI_DEV_EIOTLB_GLOB(granu);
 
 	/*
 	 * If S bit is 0, we only flush a single page. If S bit is set,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index d759e7234e98..bdd1e7d81178 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -5474,7 +5474,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 						info->pfsid, pasid,
 						info->ats_qdep,
 						inv_info->addr_info.addr,
-						size, granu);
+						size);
 			break;
 		case IOMMU_CACHE_INV_TYPE_DEV_IOTLB:
 			if (info->ats_enabled)
@@ -5482,7 +5482,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 						info->pfsid, pasid,
 						info->ats_qdep,
 						inv_info->addr_info.addr,
-						size, granu);
+						size);
 			else
 				pr_warn_ratelimited("Passdown device IOTLB flush w/o ATS!\n");
 			break;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 311117b50e93..c7a8aae36771 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -381,7 +381,6 @@ enum {
 
 #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
-#define QI_DEV_EIOTLB_GLOB(g)	((u64)(g) & 0x1)
 #define QI_DEV_EIOTLB_PASID(p)	((u64)((p) & 0xfffff) << 32)
 #define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
 #define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
@@ -705,7 +704,7 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 
 void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			      u32 pasid, u16 qdep, u64 addr,
-			      unsigned int size_order, u64 granu);
+			      unsigned int size_order);
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
 			  int pasid);
 
-- 
cgit v1.2.3


From dd6692f1b883bac46036000a1e3a0b3785f89e87 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 24 Jul 2020 09:49:21 +0800
Subject: iommu/vt-d: Refactor device_to_iommu() helper

It is refactored in two ways:

- Make it global so that it could be used in other files.

- Make bus/devfn optional so that callers could ignore these two returned
values when they only want to get the coresponding iommu pointer.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20200724014925.15523-9-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 55 +++++++++++++--------------------------------
 drivers/iommu/intel/svm.c   |  8 +++----
 include/linux/intel-iommu.h |  3 +--
 3 files changed, 21 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0a4831532442..ce8458e8119c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -778,16 +778,16 @@ is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
 	return false;
 }
 
-static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
+	struct pci_dev *pdev = NULL;
 	struct intel_iommu *iommu;
 	struct device *tmp;
-	struct pci_dev *pdev = NULL;
 	u16 segment = 0;
 	int i;
 
-	if (iommu_dummy(dev))
+	if (!dev || iommu_dummy(dev))
 		return NULL;
 
 	if (dev_is_pci(dev)) {
@@ -818,8 +818,10 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 				if (pdev && pdev->is_virtfn)
 					goto got_pdev;
 
-				*bus = drhd->devices[i].bus;
-				*devfn = drhd->devices[i].devfn;
+				if (bus && devfn) {
+					*bus = drhd->devices[i].bus;
+					*devfn = drhd->devices[i].devfn;
+				}
 				goto out;
 			}
 
@@ -829,8 +831,10 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 
 		if (pdev && drhd->include_all) {
 		got_pdev:
-			*bus = pdev->bus->number;
-			*devfn = pdev->devfn;
+			if (bus && devfn) {
+				*bus = pdev->bus->number;
+				*devfn = pdev->devfn;
+			}
 			goto out;
 		}
 	}
@@ -5146,11 +5150,10 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 			      struct device *dev)
 {
 	int ret;
-	u8 bus, devfn;
 	unsigned long flags;
 	struct intel_iommu *iommu;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		return -ENODEV;
 
@@ -5236,9 +5239,8 @@ static int prepare_domain_attach_device(struct iommu_domain *domain,
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu;
 	int addr_width;
-	u8 bus, devfn;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		return -ENODEV;
 
@@ -5668,9 +5670,8 @@ static bool intel_iommu_capable(enum iommu_cap cap)
 static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 {
 	struct intel_iommu *iommu;
-	u8 bus, devfn;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		return ERR_PTR(-ENODEV);
 
@@ -5683,9 +5684,8 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 static void intel_iommu_release_device(struct device *dev)
 {
 	struct intel_iommu *iommu;
-	u8 bus, devfn;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		return;
 
@@ -5835,37 +5835,14 @@ static struct iommu_group *intel_iommu_device_group(struct device *dev)
 	return generic_device_group(dev);
 }
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
-struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
-{
-	struct intel_iommu *iommu;
-	u8 bus, devfn;
-
-	if (iommu_dummy(dev)) {
-		dev_warn(dev,
-			 "No IOMMU translation for device; cannot enable SVM\n");
-		return NULL;
-	}
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if ((!iommu)) {
-		dev_err(dev, "No IOMMU for device; cannot enable SVM\n");
-		return NULL;
-	}
-
-	return iommu;
-}
-#endif /* CONFIG_INTEL_IOMMU_SVM */
-
 static int intel_iommu_enable_auxd(struct device *dev)
 {
 	struct device_domain_info *info;
 	struct intel_iommu *iommu;
 	unsigned long flags;
-	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu || dmar_disabled)
 		return -EINVAL;
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index d386853121a2..65d2327dcd0d 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -231,7 +231,7 @@ static LIST_HEAD(global_svm_list);
 int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			  struct iommu_gpasid_bind_data *data)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct dmar_domain *dmar_domain;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
@@ -369,7 +369,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 
 int intel_svm_unbind_gpasid(struct device *dev, int pasid)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
 	int ret = -EINVAL;
@@ -426,7 +426,7 @@ static int
 intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
 		  struct mm_struct *mm, struct intel_svm_dev **sd)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct device_domain_info *info;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm = NULL;
@@ -604,7 +604,7 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid)
 	struct intel_svm *svm;
 	int ret = -EINVAL;
 
-	iommu = intel_svm_device_to_iommu(dev);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		goto out;
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index c7a8aae36771..a57ffbcc84c7 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -727,6 +727,7 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
 struct dmar_domain *find_domain(struct device *dev);
 struct device_domain_info *get_domain_info(struct device *dev);
+struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 extern void intel_svm_check(struct intel_iommu *iommu);
@@ -765,8 +766,6 @@ struct intel_svm {
 	struct list_head devs;
 	struct list_head list;
 };
-
-extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev);
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
 #endif
-- 
cgit v1.2.3


From 8b73712115ebd603b75876f7d96d59e41d9107ad Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 24 Jul 2020 09:49:24 +0800
Subject: iommu/vt-d: Add page response ops support

After page requests are handled, software must respond to the device
which raised the page request with the result. This is done through
the iommu ops.page_response if the request was reported to outside of
vendor iommu driver through iommu_report_device_fault(). This adds the
VT-d implementation of page_response ops.

Co-developed-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Co-developed-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20200724014925.15523-12-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c |  1 +
 drivers/iommu/intel/svm.c   | 99 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/intel-iommu.h |  3 ++
 3 files changed, 103 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ce8458e8119c..1cb3a2a050c3 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -6067,6 +6067,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.sva_bind		= intel_svm_bind,
 	.sva_unbind		= intel_svm_unbind,
 	.sva_get_pasid		= intel_svm_get_pasid,
+	.page_response		= intel_svm_page_response,
 #endif
 };
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 140114ab1375..85ce8daa3177 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -1078,3 +1078,102 @@ int intel_svm_get_pasid(struct iommu_sva *sva)
 
 	return pasid;
 }
+
+int intel_svm_page_response(struct device *dev,
+			    struct iommu_fault_event *evt,
+			    struct iommu_page_response *msg)
+{
+	struct iommu_fault_page_request *prm;
+	struct intel_svm_dev *sdev = NULL;
+	struct intel_svm *svm = NULL;
+	struct intel_iommu *iommu;
+	bool private_present;
+	bool pasid_present;
+	bool last_page;
+	u8 bus, devfn;
+	int ret = 0;
+	u16 sid;
+
+	if (!dev || !dev_is_pci(dev))
+		return -ENODEV;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	if (!msg || !evt)
+		return -EINVAL;
+
+	mutex_lock(&pasid_mutex);
+
+	prm = &evt->fault.prm;
+	sid = PCI_DEVID(bus, devfn);
+	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	if (!pasid_present) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (prm->pasid == 0 || prm->pasid >= PASID_MAX) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = pasid_to_svm_sdev(dev, prm->pasid, &svm, &sdev);
+	if (ret || !sdev) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/*
+	 * For responses from userspace, need to make sure that the
+	 * pasid has been bound to its mm.
+	 */
+	if (svm->flags & SVM_FLAG_GUEST_MODE) {
+		struct mm_struct *mm;
+
+		mm = get_task_mm(current);
+		if (!mm) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (mm != svm->mm) {
+			ret = -ENODEV;
+			mmput(mm);
+			goto out;
+		}
+
+		mmput(mm);
+	}
+
+	/*
+	 * Per VT-d spec. v3.0 ch7.7, system software must respond
+	 * with page group response if private data is present (PDP)
+	 * or last page in group (LPIG) bit is set. This is an
+	 * additional VT-d requirement beyond PCI ATS spec.
+	 */
+	if (last_page || private_present) {
+		struct qi_desc desc;
+
+		desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
+				QI_PGRP_PASID_P(pasid_present) |
+				QI_PGRP_PDP(private_present) |
+				QI_PGRP_RESP_CODE(msg->code) |
+				QI_PGRP_RESP_TYPE;
+		desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
+		desc.qw2 = 0;
+		desc.qw3 = 0;
+		if (private_present)
+			memcpy(&desc.qw2, prm->private_data,
+			       sizeof(prm->private_data));
+
+		qi_submit_sync(iommu, &desc, 1, 0);
+	}
+out:
+	mutex_unlock(&pasid_mutex);
+	return ret;
+}
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index a57ffbcc84c7..9ff5e340948b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -740,6 +740,9 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
 				 void *drvdata);
 void intel_svm_unbind(struct iommu_sva *handle);
 int intel_svm_get_pasid(struct iommu_sva *handle);
+int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
+			    struct iommu_page_response *msg);
+
 struct svm_dev_ops;
 
 struct intel_svm_dev {
-- 
cgit v1.2.3


From 75c88143f3b879664cc5bf68b91854c1a98f5e5b Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:20 +0300
Subject: clk: at91: clk-master: add master clock support for SAMA7G5

Add master clock support (MCK1..4) for SAMA7G5. SAMA7G5's PMC has
multiple master clocks feeding different subsystems. One of them
feeds image subsystem and is changeable based on image subsystem
needs.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-13-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-master.c | 310 +++++++++++++++++++++++++++++++++++++++++-
 drivers/clk/at91/pmc.h        |   7 +
 include/linux/clk/at91_pmc.h  |   1 +
 3 files changed, 313 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index 88d545b1698c..bd0d8a69a2cf 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -17,30 +17,49 @@
 #define MASTER_DIV_SHIFT	8
 #define MASTER_DIV_MASK		0x3
 
+#define PMC_MCR			0x30
+#define PMC_MCR_ID_MSK		GENMASK(3, 0)
+#define PMC_MCR_CMD		BIT(7)
+#define PMC_MCR_DIV		GENMASK(10, 8)
+#define PMC_MCR_CSS		GENMASK(20, 16)
+#define PMC_MCR_CSS_SHIFT	(16)
+#define PMC_MCR_EN		BIT(28)
+
+#define PMC_MCR_ID(x)		((x) & PMC_MCR_ID_MSK)
+
+#define MASTER_MAX_ID		4
+
 #define to_clk_master(hw) container_of(hw, struct clk_master, hw)
 
 struct clk_master {
 	struct clk_hw hw;
 	struct regmap *regmap;
+	spinlock_t *lock;
 	const struct clk_master_layout *layout;
 	const struct clk_master_characteristics *characteristics;
+	u32 *mux_table;
 	u32 mckr;
+	int chg_pid;
+	u8 id;
+	u8 parent;
+	u8 div;
 };
 
-static inline bool clk_master_ready(struct regmap *regmap)
+static inline bool clk_master_ready(struct clk_master *master)
 {
+	unsigned int bit = master->id ? AT91_PMC_MCKXRDY : AT91_PMC_MCKRDY;
 	unsigned int status;
 
-	regmap_read(regmap, AT91_PMC_SR, &status);
+	regmap_read(master->regmap, AT91_PMC_SR, &status);
 
-	return !!(status & AT91_PMC_MCKRDY);
+	return !!(status & bit);
 }
 
 static int clk_master_prepare(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
 
-	while (!clk_master_ready(master->regmap))
+	while (!clk_master_ready(master))
 		cpu_relax();
 
 	return 0;
@@ -50,7 +69,7 @@ static int clk_master_is_prepared(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
 
-	return clk_master_ready(master->regmap);
+	return clk_master_ready(master);
 }
 
 static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
@@ -143,6 +162,287 @@ at91_clk_register_master(struct regmap *regmap,
 	return hw;
 }
 
+static unsigned long
+clk_sama7g5_master_recalc_rate(struct clk_hw *hw,
+			       unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+
+	return DIV_ROUND_CLOSEST_ULL(parent_rate, (1 << master->div));
+}
+
+static void clk_sama7g5_master_best_diff(struct clk_rate_request *req,
+					 struct clk_hw *parent,
+					 unsigned long parent_rate,
+					 long *best_rate,
+					 long *best_diff,
+					 u32 div)
+{
+	unsigned long tmp_rate, tmp_diff;
+
+	if (div == MASTER_PRES_MAX)
+		tmp_rate = parent_rate / 3;
+	else
+		tmp_rate = parent_rate >> div;
+
+	tmp_diff = abs(req->rate - tmp_rate);
+
+	if (*best_diff < 0 || *best_diff >= tmp_diff) {
+		*best_rate = tmp_rate;
+		*best_diff = tmp_diff;
+		req->best_parent_rate = parent_rate;
+		req->best_parent_hw = parent;
+	}
+}
+
+static int clk_sama7g5_master_determine_rate(struct clk_hw *hw,
+					     struct clk_rate_request *req)
+{
+	struct clk_master *master = to_clk_master(hw);
+	struct clk_rate_request req_parent = *req;
+	struct clk_hw *parent;
+	long best_rate = LONG_MIN, best_diff = LONG_MIN;
+	unsigned long parent_rate;
+	unsigned int div, i;
+
+	/* First: check the dividers of MCR. */
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		parent = clk_hw_get_parent_by_index(hw, i);
+		if (!parent)
+			continue;
+
+		parent_rate = clk_hw_get_rate(parent);
+		if (!parent_rate)
+			continue;
+
+		for (div = 0; div < MASTER_PRES_MAX + 1; div++) {
+			clk_sama7g5_master_best_diff(req, parent, parent_rate,
+						     &best_rate, &best_diff,
+						     div);
+			if (!best_diff)
+				break;
+		}
+
+		if (!best_diff)
+			break;
+	}
+
+	/* Second: try to request rate form changeable parent. */
+	if (master->chg_pid < 0)
+		goto end;
+
+	parent = clk_hw_get_parent_by_index(hw, master->chg_pid);
+	if (!parent)
+		goto end;
+
+	for (div = 0; div < MASTER_PRES_MAX + 1; div++) {
+		if (div == MASTER_PRES_MAX)
+			req_parent.rate = req->rate * 3;
+		else
+			req_parent.rate = req->rate << div;
+
+		if (__clk_determine_rate(parent, &req_parent))
+			continue;
+
+		clk_sama7g5_master_best_diff(req, parent, req_parent.rate,
+					     &best_rate, &best_diff, div);
+
+		if (!best_diff)
+			break;
+	}
+
+end:
+	pr_debug("MCK: %s, best_rate = %ld, parent clk: %s @ %ld\n",
+		 __func__, best_rate,
+		 __clk_get_name((req->best_parent_hw)->clk),
+		req->best_parent_rate);
+
+	if (best_rate < 0)
+		return -EINVAL;
+
+	req->rate = best_rate;
+
+	return 0;
+}
+
+static u8 clk_sama7g5_master_get_parent(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	u8 index;
+
+	spin_lock_irqsave(master->lock, flags);
+	index = clk_mux_val_to_index(&master->hw, master->mux_table, 0,
+				     master->parent);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return index;
+}
+
+static int clk_sama7g5_master_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+
+	if (index >= clk_hw_get_num_parents(hw))
+		return -EINVAL;
+
+	spin_lock_irqsave(master->lock, flags);
+	master->parent = clk_mux_index_to_val(master->mux_table, 0, index);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static int clk_sama7g5_master_enable(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	unsigned int val, cparent;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, PMC_MCR_ID(master->id));
+	regmap_read(master->regmap, PMC_MCR, &val);
+	regmap_update_bits(master->regmap, PMC_MCR,
+			   PMC_MCR_EN | PMC_MCR_CSS | PMC_MCR_DIV |
+			   PMC_MCR_CMD | PMC_MCR_ID_MSK,
+			   PMC_MCR_EN | (master->parent << PMC_MCR_CSS_SHIFT) |
+			   (master->div << MASTER_DIV_SHIFT) |
+			   PMC_MCR_CMD | PMC_MCR_ID(master->id));
+
+	cparent = (val & PMC_MCR_CSS) >> PMC_MCR_CSS_SHIFT;
+
+	/* Wait here only if parent is being changed. */
+	while ((cparent != master->parent) && !clk_master_ready(master))
+		cpu_relax();
+
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static void clk_sama7g5_master_disable(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_update_bits(master->regmap, PMC_MCR,
+			   PMC_MCR_EN | PMC_MCR_CMD | PMC_MCR_ID_MSK,
+			   PMC_MCR_CMD | PMC_MCR_ID(master->id));
+
+	spin_unlock_irqrestore(master->lock, flags);
+}
+
+static int clk_sama7g5_master_is_enabled(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	unsigned int val;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_read(master->regmap, PMC_MCR, &val);
+
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return !!(val & PMC_MCR_EN);
+}
+
+static int clk_sama7g5_master_set_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long div, flags;
+
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if ((div > (1 << (MASTER_PRES_MAX - 1))) || (div & (div - 1)))
+		return -EINVAL;
+
+	if (div == 3)
+		div = MASTER_PRES_MAX;
+	else
+		div = ffs(div) - 1;
+
+	spin_lock_irqsave(master->lock, flags);
+	master->div = div;
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops sama7g5_master_ops = {
+	.enable = clk_sama7g5_master_enable,
+	.disable = clk_sama7g5_master_disable,
+	.is_enabled = clk_sama7g5_master_is_enabled,
+	.recalc_rate = clk_sama7g5_master_recalc_rate,
+	.determine_rate = clk_sama7g5_master_determine_rate,
+	.set_rate = clk_sama7g5_master_set_rate,
+	.get_parent = clk_sama7g5_master_get_parent,
+	.set_parent = clk_sama7g5_master_set_parent,
+};
+
+struct clk_hw * __init
+at91_clk_sama7g5_register_master(struct regmap *regmap,
+				 const char *name, int num_parents,
+				 const char **parent_names,
+				 u32 *mux_table,
+				 spinlock_t *lock, u8 id,
+				 bool critical, int chg_pid)
+{
+	struct clk_master *master;
+	struct clk_hw *hw;
+	struct clk_init_data init;
+	unsigned long flags;
+	unsigned int val;
+	int ret;
+
+	if (!name || !num_parents || !parent_names || !mux_table ||
+	    !lock || id > MASTER_MAX_ID)
+		return ERR_PTR(-EINVAL);
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &sama7g5_master_ops;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+	if (chg_pid >= 0)
+		init.flags |= CLK_SET_RATE_PARENT;
+	if (critical)
+		init.flags |= CLK_IS_CRITICAL;
+
+	master->hw.init = &init;
+	master->regmap = regmap;
+	master->id = id;
+	master->chg_pid = chg_pid;
+	master->lock = lock;
+	master->mux_table = mux_table;
+
+	spin_lock_irqsave(master->lock, flags);
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_read(master->regmap, PMC_MCR, &val);
+	master->parent = (val & PMC_MCR_CSS) >> PMC_MCR_CSS_SHIFT;
+	master->div = (val & PMC_MCR_DIV) >> MASTER_DIV_SHIFT;
+	spin_unlock_irqrestore(master->lock, flags);
+
+	hw = &master->hw;
+	ret = clk_hw_register(NULL, &master->hw);
+	if (ret) {
+		kfree(master);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+}
+
 const struct clk_master_layout at91rm9200_master_layout = {
 	.mask = 0x31F,
 	.pres_shift = 2,
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 2bfe1405f9f8..29d150feaa46 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -154,6 +154,13 @@ at91_clk_register_master(struct regmap *regmap, const char *name,
 			 const struct clk_master_layout *layout,
 			 const struct clk_master_characteristics *characteristics);
 
+struct clk_hw * __init
+at91_clk_sama7g5_register_master(struct regmap *regmap,
+				 const char *name, int num_parents,
+				 const char **parent_names, u32 *mux_table,
+				 spinlock_t *lock, u8 id, bool critical,
+				 int chg_pid);
+
 struct clk_hw * __init
 at91_clk_register_peripheral(struct regmap *regmap, const char *name,
 			     const char *parent_name, u32 id);
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 49a53a137610..77d6dabc4c3c 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -174,6 +174,7 @@
 #define		AT91_PMC_MOSCRCS	(1 << 17)		/* Main On-Chip RC [some SAM9] */
 #define		AT91_PMC_CFDEV		(1 << 18)		/* Clock Failure Detector Event [some SAM9] */
 #define		AT91_PMC_GCKRDY		(1 << 24)		/* Generated Clocks */
+#define		AT91_PMC_MCKXRDY	(1 << 26)		/* Master Clock x [x=1..4] Ready Status */
 #define	AT91_PMC_IMR		0x6c			/* Interrupt Mask Register */
 
 #define AT91_PMC_FSMR		0x70		/* Fast Startup Mode Register */
-- 
cgit v1.2.3


From 0416824edca1cdcb6e00e6f909423bf0fc529eef Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:23 +0300
Subject: clk: at91: add macro for pll ids mask

Add macro for PLL IDs mask.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-16-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/clk/at91_pmc.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 77d6dabc4c3c..dc5e85f124e0 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -59,6 +59,7 @@
 #define AT91_PMC_PLL_UPDT		0x1C		/* PMC PLL update register [for SAM9X60] */
 #define		AT91_PMC_PLL_UPDT_UPDATE	(1 << 8)	/* Update PLL settings */
 #define		AT91_PMC_PLL_UPDT_ID		(1 << 0)	/* PLL ID */
+#define		AT91_PMC_PLL_UPDT_ID_MSK	(0xf)		/* PLL ID mask */
 #define		AT91_PMC_PLL_UPDT_STUPTIM	(0xff << 16)	/* Startup time */
 
 #define	AT91_CKGR_MOR		0x20			/* Main Oscillator Register [not on SAM9RL] */
-- 
cgit v1.2.3


From ef396df99251b848596c717b63ff4fe74a941193 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:25 +0300
Subject: clk: at91: clk-utmi: add utmi support for sama7g5

Add UTMI support for SAMA7G5. SAMA7G5's UTMI control is done via
XTALF register. Values written at bits 2..0 in this register
correspond to the on board crystal oscillator frequency.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-18-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-utmi.c  | 103 ++++++++++++++++++++++++++++++++++++++++---
 drivers/clk/at91/pmc.h       |   4 ++
 include/linux/clk/at91_pmc.h |   2 +
 3 files changed, 104 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index f1ef4e1f41a9..df9f3fc3b6a6 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -120,9 +120,11 @@ static const struct clk_ops utmi_ops = {
 	.recalc_rate = clk_utmi_recalc_rate,
 };
 
-struct clk_hw * __init
-at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
-		       const char *name, const char *parent_name)
+static struct clk_hw * __init
+at91_clk_register_utmi_internal(struct regmap *regmap_pmc,
+				struct regmap *regmap_sfr,
+				const char *name, const char *parent_name,
+				const struct clk_ops *ops, unsigned long flags)
 {
 	struct clk_utmi *utmi;
 	struct clk_hw *hw;
@@ -134,10 +136,10 @@ at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &utmi_ops;
+	init.ops = ops;
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
-	init.flags = CLK_SET_RATE_GATE;
+	init.flags = flags;
 
 	utmi->hw.init = &init;
 	utmi->regmap_pmc = regmap_pmc;
@@ -152,3 +154,94 @@ at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 
 	return hw;
 }
+
+struct clk_hw * __init
+at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
+		       const char *name, const char *parent_name)
+{
+	return at91_clk_register_utmi_internal(regmap_pmc, regmap_sfr, name,
+			parent_name, &utmi_ops, CLK_SET_RATE_GATE);
+}
+
+static int clk_utmi_sama7g5_prepare(struct clk_hw *hw)
+{
+	struct clk_utmi *utmi = to_clk_utmi(hw);
+	struct clk_hw *hw_parent;
+	unsigned long parent_rate;
+	unsigned int val;
+
+	hw_parent = clk_hw_get_parent(hw);
+	parent_rate = clk_hw_get_rate(hw_parent);
+
+	switch (parent_rate) {
+	case 16000000:
+		val = 0;
+		break;
+	case 20000000:
+		val = 2;
+		break;
+	case 24000000:
+		val = 3;
+		break;
+	case 32000000:
+		val = 5;
+		break;
+	default:
+		pr_err("UTMICK: unsupported main_xtal rate\n");
+		return -EINVAL;
+	}
+
+	regmap_write(utmi->regmap_pmc, AT91_PMC_XTALF, val);
+
+	return 0;
+
+}
+
+static int clk_utmi_sama7g5_is_prepared(struct clk_hw *hw)
+{
+	struct clk_utmi *utmi = to_clk_utmi(hw);
+	struct clk_hw *hw_parent;
+	unsigned long parent_rate;
+	unsigned int val;
+
+	hw_parent = clk_hw_get_parent(hw);
+	parent_rate = clk_hw_get_rate(hw_parent);
+
+	regmap_read(utmi->regmap_pmc, AT91_PMC_XTALF, &val);
+	switch (val & 0x7) {
+	case 0:
+		if (parent_rate == 16000000)
+			return 1;
+		break;
+	case 2:
+		if (parent_rate == 20000000)
+			return 1;
+		break;
+	case 3:
+		if (parent_rate == 24000000)
+			return 1;
+		break;
+	case 5:
+		if (parent_rate == 32000000)
+			return 1;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct clk_ops sama7g5_utmi_ops = {
+	.prepare = clk_utmi_sama7g5_prepare,
+	.is_prepared = clk_utmi_sama7g5_is_prepared,
+	.recalc_rate = clk_utmi_recalc_rate,
+};
+
+struct clk_hw * __init
+at91_clk_sama7g5_register_utmi(struct regmap *regmap_pmc, const char *name,
+			       const char *parent_name)
+{
+	return at91_clk_register_utmi_internal(regmap_pmc, NULL, name,
+			parent_name, &sama7g5_utmi_ops, 0);
+}
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 6340b9be8205..7b86affc6d7c 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -236,6 +236,10 @@ struct clk_hw * __init
 at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 		       const char *name, const char *parent_name);
 
+struct clk_hw * __init
+at91_clk_sama7g5_register_utmi(struct regmap *regmap, const char *name,
+			       const char *parent_name);
+
 #ifdef CONFIG_PM
 void pmc_register_id(u8 id);
 void pmc_register_pck(u8 pck);
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index dc5e85f124e0..a4f82e836a7c 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -137,6 +137,8 @@
 #define			AT91_PMC_PLLADIV2_ON		(1 << 12)
 #define		AT91_PMC_H32MXDIV	BIT(24)
 
+#define AT91_PMC_XTALF		0x34			/* Main XTAL Frequency Register [SAMA7G5 only] */
+
 #define	AT91_PMC_USB		0x38			/* USB Clock Register [some SAM9 only] */
 #define		AT91_PMC_USBS		(0x1 <<  0)		/* USB OHCI Input clock selection */
 #define			AT91_PMC_USBS_PLLA		(0 << 0)
-- 
cgit v1.2.3


From d19e789f068b3d633cbac430764962f404198022 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 24 Jul 2020 13:50:25 +0200
Subject: compiler.h: Move instrumentation_begin()/end() to new
 <linux/instrumentation.h> header

Linus pointed out that compiler.h - which is a key header that gets included in every
single one of the 28,000+ kernel files during a kernel build - was bloated in:

  655389666643: ("vmlinux.lds.h: Create section for protection against instrumentation")

Linus noted:

 > I have pulled this, but do we really want to add this to a header file
 > that is _so_ core that it gets included for basically every single
 > file built?
 >
 > I don't even see those instrumentation_begin/end() things used
 > anywhere right now.
 >
 > It seems excessive. That 53 lines is maybe not a lot, but it pushed
 > that header file to over 12kB, and while it's mostly comments, it's
 > extra IO and parsing basically for _every_ single file compiled in the
 > kernel.
 >
 > For what appears to be absolutely zero upside right now, and I really
 > don't see why this should be in such a core header file!

Move these primitives into a new header: <linux/instrumentation.h>, and include that
header in the headers that make use of it.

Unfortunately one of these headers is asm-generic/bug.h, which does get included
in a lot of places, similarly to compiler.h. So the de-bloating effect isn't as
good as we'd like it to be - but at least the interfaces are defined separately.

No change to functionality intended.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200604071921.GA1361070@gmail.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 arch/x86/include/asm/bug.h       |  1 +
 include/asm-generic/bug.h        |  1 +
 include/linux/compiler.h         | 53 -------------------------------------
 include/linux/context_tracking.h |  2 ++
 include/linux/instrumentation.h  | 57 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 61 insertions(+), 53 deletions(-)
 create mode 100644 include/linux/instrumentation.h

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 028189575560..297fa12e7e27 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_BUG_H
 
 #include <linux/stringify.h>
+#include <linux/instrumentation.h>
 
 /*
  * Despite that some emulators terminate on UD2, we use it for WARN().
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index c94e33ae3e7b..18b0f4eee8cb 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BUG_H
 
 #include <linux/compiler.h>
+#include <linux/instrumentation.h>
 
 #define CUT_HERE		"------------[ cut here ]------------\n"
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 204e76856435..681894bfde99 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -120,65 +120,12 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Annotate a C jump table to allow objtool to follow the code flow */
 #define __annotate_jump_table __section(.rodata..c_jump_table)
 
-#ifdef CONFIG_DEBUG_ENTRY
-/* Begin/end of an instrumentation safe region */
-#define instrumentation_begin() ({					\
-	asm volatile("%c0: nop\n\t"						\
-		     ".pushsection .discard.instr_begin\n\t"		\
-		     ".long %c0b - .\n\t"				\
-		     ".popsection\n\t" : : "i" (__COUNTER__));		\
-})
-
-/*
- * Because instrumentation_{begin,end}() can nest, objtool validation considers
- * _begin() a +1 and _end() a -1 and computes a sum over the instructions.
- * When the value is greater than 0, we consider instrumentation allowed.
- *
- * There is a problem with code like:
- *
- * noinstr void foo()
- * {
- *	instrumentation_begin();
- *	...
- *	if (cond) {
- *		instrumentation_begin();
- *		...
- *		instrumentation_end();
- *	}
- *	bar();
- *	instrumentation_end();
- * }
- *
- * If instrumentation_end() would be an empty label, like all the other
- * annotations, the inner _end(), which is at the end of a conditional block,
- * would land on the instruction after the block.
- *
- * If we then consider the sum of the !cond path, we'll see that the call to
- * bar() is with a 0-value, even though, we meant it to happen with a positive
- * value.
- *
- * To avoid this, have _end() be a NOP instruction, this ensures it will be
- * part of the condition block and does not escape.
- */
-#define instrumentation_end() ({					\
-	asm volatile("%c0: nop\n\t"					\
-		     ".pushsection .discard.instr_end\n\t"		\
-		     ".long %c0b - .\n\t"				\
-		     ".popsection\n\t" : : "i" (__COUNTER__));		\
-})
-#endif /* CONFIG_DEBUG_ENTRY */
-
 #else
 #define annotate_reachable()
 #define annotate_unreachable()
 #define __annotate_jump_table
 #endif
 
-#ifndef instrumentation_begin
-#define instrumentation_begin()		do { } while(0)
-#define instrumentation_end()		do { } while(0)
-#endif
-
 #ifndef ASM_UNREACHABLE
 # define ASM_UNREACHABLE
 #endif
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 981b880d5b60..d53cd331c4dd 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -5,6 +5,8 @@
 #include <linux/sched.h>
 #include <linux/vtime.h>
 #include <linux/context_tracking_state.h>
+#include <linux/instrumentation.h>
+
 #include <asm/ptrace.h>
 
 
diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h
new file mode 100644
index 000000000000..93e2ad67fc10
--- /dev/null
+++ b/include/linux/instrumentation.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_INSTRUMENTATION_H
+#define __LINUX_INSTRUMENTATION_H
+
+#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION)
+
+/* Begin/end of an instrumentation safe region */
+#define instrumentation_begin() ({					\
+	asm volatile("%c0: nop\n\t"						\
+		     ".pushsection .discard.instr_begin\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+
+/*
+ * Because instrumentation_{begin,end}() can nest, objtool validation considers
+ * _begin() a +1 and _end() a -1 and computes a sum over the instructions.
+ * When the value is greater than 0, we consider instrumentation allowed.
+ *
+ * There is a problem with code like:
+ *
+ * noinstr void foo()
+ * {
+ *	instrumentation_begin();
+ *	...
+ *	if (cond) {
+ *		instrumentation_begin();
+ *		...
+ *		instrumentation_end();
+ *	}
+ *	bar();
+ *	instrumentation_end();
+ * }
+ *
+ * If instrumentation_end() would be an empty label, like all the other
+ * annotations, the inner _end(), which is at the end of a conditional block,
+ * would land on the instruction after the block.
+ *
+ * If we then consider the sum of the !cond path, we'll see that the call to
+ * bar() is with a 0-value, even though, we meant it to happen with a positive
+ * value.
+ *
+ * To avoid this, have _end() be a NOP instruction, this ensures it will be
+ * part of the condition block and does not escape.
+ */
+#define instrumentation_end() ({					\
+	asm volatile("%c0: nop\n\t"					\
+		     ".pushsection .discard.instr_end\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+#else
+# define instrumentation_begin()	do { } while(0)
+# define instrumentation_end()		do { } while(0)
+#endif
+
+#endif /* __LINUX_INSTRUMENTATION_H */
-- 
cgit v1.2.3


From f34ce7a7018c2f71d78fc7f512f6daf01e487114 Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Fri, 12 Jun 2020 11:39:55 +0800
Subject: iommu: Add gfp parameter to io_pgtable_ops->map()

Now the ARM page tables are always allocated by GFP_ATOMIC parameter,
but the iommu_ops->map() function has been added a gfp_t parameter by
commit 781ca2de89ba ("iommu: Add gfp parameter to iommu_ops::map"),
thus io_pgtable_ops->map() should use the gfp parameter passed from
iommu_ops->map() to allocate page pages, which can avoid wasting the
memory allocators atomic pools for some non-atomic contexts.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/3093df4cb95497aaf713fca623ce4ecebb197c2e.1591930156.git.baolin.wang@linux.alibaba.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c |  2 +-
 drivers/iommu/arm-smmu-v3.c             |  2 +-
 drivers/iommu/arm-smmu.c                |  2 +-
 drivers/iommu/io-pgtable-arm-v7s.c      | 18 +++++++++---------
 drivers/iommu/io-pgtable-arm.c          | 18 +++++++++---------
 drivers/iommu/ipmmu-vmsa.c              |  2 +-
 drivers/iommu/msm_iommu.c               |  2 +-
 drivers/iommu/mtk_iommu.c               |  2 +-
 drivers/iommu/qcom_iommu.c              |  2 +-
 include/linux/io-pgtable.h              |  2 +-
 10 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index ed28aeba6d59..5a39eee8cf83 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -262,7 +262,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 		while (len) {
 			size_t pgsize = get_pgsize(iova | paddr, len);
 
-			ops->map(ops, iova, paddr, pgsize, prot);
+			ops->map(ops, iova, paddr, pgsize, prot, GFP_KERNEL);
 			iova += pgsize;
 			paddr += pgsize;
 			len -= pgsize;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index f578677a5c41..7b59f06b3913 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2850,7 +2850,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 	if (!ops)
 		return -ENODEV;
 
-	return ops->map(ops, iova, paddr, size, prot);
+	return ops->map(ops, iova, paddr, size, prot, gfp);
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705..dc1d2535798a 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1227,7 +1227,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 		return -ENODEV;
 
 	arm_smmu_rpm_get(smmu);
-	ret = ops->map(ops, iova, paddr, size, prot);
+	ret = ops->map(ops, iova, paddr, size, prot, gfp);
 	arm_smmu_rpm_put(smmu);
 
 	return ret;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 4272fe4e17f4..a688f22cbe3b 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -470,7 +470,7 @@ static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table,
 
 static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 			 phys_addr_t paddr, size_t size, int prot,
-			 int lvl, arm_v7s_iopte *ptep)
+			 int lvl, arm_v7s_iopte *ptep, gfp_t gfp)
 {
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_v7s_iopte pte, *cptep;
@@ -491,7 +491,7 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_v7s_alloc_table(lvl + 1, GFP_ATOMIC, data);
+		cptep = __arm_v7s_alloc_table(lvl + 1, gfp, data);
 		if (!cptep)
 			return -ENOMEM;
 
@@ -512,11 +512,11 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 	}
 
 	/* Rinse, repeat */
-	return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep);
+	return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp);
 }
 
 static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable *iop = &data->iop;
@@ -530,7 +530,7 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 		    paddr >= (1ULL << data->iop.cfg.oas)))
 		return -ERANGE;
 
-	ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd);
+	ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd, gfp);
 	/*
 	 * Synchronise all PTE updates for the new mapping before there's
 	 * a chance for anything to kick off a table walk for the new iova.
@@ -922,12 +922,12 @@ static int __init arm_v7s_do_selftests(void)
 		if (ops->map(ops, iova, iova, size, IOMMU_READ |
 						    IOMMU_WRITE |
 						    IOMMU_NOEXEC |
-						    IOMMU_CACHE))
+						    IOMMU_CACHE, GFP_KERNEL))
 			return __FAIL(ops);
 
 		/* Overlapping mappings */
 		if (!ops->map(ops, iova, iova + size, size,
-			      IOMMU_READ | IOMMU_NOEXEC))
+			      IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL))
 			return __FAIL(ops);
 
 		if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
@@ -946,7 +946,7 @@ static int __init arm_v7s_do_selftests(void)
 			return __FAIL(ops);
 
 		/* Remap of partial unmap */
-		if (ops->map(ops, iova_start + size, size, size, IOMMU_READ))
+		if (ops->map(ops, iova_start + size, size, size, IOMMU_READ, GFP_KERNEL))
 			return __FAIL(ops);
 
 		if (ops->iova_to_phys(ops, iova_start + size + 42)
@@ -967,7 +967,7 @@ static int __init arm_v7s_do_selftests(void)
 			return __FAIL(ops);
 
 		/* Remap full block */
-		if (ops->map(ops, iova, iova, size, IOMMU_WRITE))
+		if (ops->map(ops, iova, iova, size, IOMMU_WRITE, GFP_KERNEL))
 			return __FAIL(ops);
 
 		if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 04fbd4bf0ff9..4a5a7b083a9b 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -355,7 +355,7 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table,
 
 static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 			  phys_addr_t paddr, size_t size, arm_lpae_iopte prot,
-			  int lvl, arm_lpae_iopte *ptep)
+			  int lvl, arm_lpae_iopte *ptep, gfp_t gfp)
 {
 	arm_lpae_iopte *cptep, pte;
 	size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
@@ -376,7 +376,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_lpae_alloc_pages(tblsz, GFP_ATOMIC, cfg);
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
 		if (!cptep)
 			return -ENOMEM;
 
@@ -396,7 +396,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	}
 
 	/* Rinse, repeat */
-	return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep);
+	return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp);
 }
 
 static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
@@ -461,7 +461,7 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 }
 
 static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
-			phys_addr_t paddr, size_t size, int iommu_prot)
+			phys_addr_t paddr, size_t size, int iommu_prot, gfp_t gfp)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
@@ -483,7 +483,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
-	ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep);
+	ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep, gfp);
 	/*
 	 * Synchronise all PTE updates for the new mapping before there's
 	 * a chance for anything to kick off a table walk for the new iova.
@@ -1178,12 +1178,12 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 			if (ops->map(ops, iova, iova, size, IOMMU_READ |
 							    IOMMU_WRITE |
 							    IOMMU_NOEXEC |
-							    IOMMU_CACHE))
+							    IOMMU_CACHE, GFP_KERNEL))
 				return __FAIL(ops, i);
 
 			/* Overlapping mappings */
 			if (!ops->map(ops, iova, iova + size, size,
-				      IOMMU_READ | IOMMU_NOEXEC))
+				      IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL))
 				return __FAIL(ops, i);
 
 			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
@@ -1198,7 +1198,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 			return __FAIL(ops, i);
 
 		/* Remap of partial unmap */
-		if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ))
+		if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ, GFP_KERNEL))
 			return __FAIL(ops, i);
 
 		if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
@@ -1216,7 +1216,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 				return __FAIL(ops, i);
 
 			/* Remap full block */
-			if (ops->map(ops, iova, iova, size, IOMMU_WRITE))
+			if (ops->map(ops, iova, iova, size, IOMMU_WRITE, GFP_KERNEL))
 				return __FAIL(ops, i);
 
 			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 4c2972f3153b..87475b2f7ef1 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -687,7 +687,7 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
 	if (!domain)
 		return -ENODEV;
 
-	return domain->iop->map(domain->iop, iova, paddr, size, prot);
+	return domain->iop->map(domain->iop, iova, paddr, size, prot, gfp);
 }
 
 static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index f773cc85f311..3615cd6241c4 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -491,7 +491,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	int ret;
 
 	spin_lock_irqsave(&priv->pgtlock, flags);
-	ret = priv->iop->map(priv->iop, iova, pa, len, prot);
+	ret = priv->iop->map(priv->iop, iova, pa, len, prot, GFP_ATOMIC);
 	spin_unlock_irqrestore(&priv->pgtlock, flags);
 
 	return ret;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 2be96f1cdbd2..b7b16414a217 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -397,7 +397,7 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 		paddr |= BIT_ULL(32);
 
 	/* Synchronize with the tlb_lock */
-	return dom->iop->map(dom->iop, iova, paddr, size, prot);
+	return dom->iop->map(dom->iop, iova, paddr, size, prot, gfp);
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c3e1fbd1988c..cfcfd7553b30 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -441,7 +441,7 @@ static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
 		return -ENODEV;
 
 	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
-	ret = ops->map(ops, iova, paddr, size, prot);
+	ret = ops->map(ops, iova, paddr, size, prot, GFP_ATOMIC);
 	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
 	return ret;
 }
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 53d53c6c2be9..23285ba645db 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -155,7 +155,7 @@ struct io_pgtable_cfg {
  */
 struct io_pgtable_ops {
 	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
+		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
 	size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
 			size_t size, struct iommu_iotlb_gather *gather);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
-- 
cgit v1.2.3


From b1012ca8dc4f9b1a1fe8e2cb1590dd6d43ea3849 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Thu, 23 Jul 2020 09:34:37 +0800
Subject: iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu

The VT-d spec requires (10.4.4 Global Command Register, TE field) that:

Hardware implementations supporting DMA draining must drain any in-flight
DMA read/write requests queued within the Root-Complex before completing
the translation enable command and reflecting the status of the command
through the TES field in the Global Status register.

Unfortunately, some integrated graphic devices fail to do so after some
kind of power state transition. As the result, the system might stuck in
iommu_disable_translation(), waiting for the completion of TE transition.

This provides a quirk list for those devices and skips TE disabling if
the qurik hits.

Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208363
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=206571
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Koba Ko <koba.ko@canonical.com>
Tested-by: Jun Miao <jun.miao@windriver.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200723013437.2268-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/dmar.c  |  1 +
 drivers/iommu/intel/iommu.c | 27 +++++++++++++++++++++++++++
 include/linux/dmar.h        |  1 +
 include/linux/intel-iommu.h |  2 ++
 4 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index f6cbe3f95c8d..93e6345f3414 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1102,6 +1102,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 
 	drhd->iommu = iommu;
+	iommu->drhd = drhd;
 
 	return 0;
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index b3faf99457a6..0c2d582ff8cd 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -356,6 +356,7 @@ static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int iommu_identity_mapping;
 static int intel_no_bounce;
+static int iommu_skip_te_disable;
 
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
@@ -1633,6 +1634,10 @@ static void iommu_disable_translation(struct intel_iommu *iommu)
 	u32 sts;
 	unsigned long flag;
 
+	if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated &&
+	    (cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap)))
+		return;
+
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	iommu->gcmd &= ~DMA_GCMD_TE;
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
@@ -4043,6 +4048,7 @@ static void __init init_no_remapping_devices(void)
 
 		/* This IOMMU has *only* gfx devices. Either bypass it or
 		   set the gfx_mapped flag, as appropriate */
+		drhd->gfx_dedicated = 1;
 		if (!dmar_map_gfx) {
 			drhd->ignored = 1;
 			for_each_active_dev_scope(drhd->devices,
@@ -6170,6 +6176,27 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_g
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
 
+static void quirk_igfx_skip_te_disable(struct pci_dev *dev)
+{
+	unsigned short ver;
+
+	if (!IS_GFX_DEVICE(dev))
+		return;
+
+	ver = (dev->device >> 8) & 0xff;
+	if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
+	    ver != 0x4e && ver != 0x8a && ver != 0x98 &&
+	    ver != 0x9a)
+		return;
+
+	if (risky_device(dev))
+		return;
+
+	pci_info(dev, "Skip IOMMU disabling for graphics\n");
+	iommu_skip_te_disable = 1;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable);
+
 /* On Tylersburg chipsets, some BIOSes have been known to enable the
    ISOCH DMAR unit for the Azalia sound device, but not give it any
    TLB entries, which causes it to deadlock. Check for that.  We do
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d7bf029df737..65565820328a 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -48,6 +48,7 @@ struct dmar_drhd_unit {
 	u16	segment;		/* PCI domain		*/
 	u8	ignored:1; 		/* ignore drhd		*/
 	u8	include_all:1;
+	u8	gfx_dedicated:1;	/* graphic dedicated	*/
 	struct intel_iommu *iommu;
 };
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 9ff5e340948b..b1ed2f25f7c0 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -599,6 +599,8 @@ struct intel_iommu {
 	struct iommu_device iommu;  /* IOMMU core code handle */
 	int		node;
 	u32		flags;      /* Software defined flags */
+
+	struct dmar_drhd_unit *drhd;
 };
 
 /* PCI domain-device relationship */
-- 
cgit v1.2.3


From 6823ecabf03031d610a6c5afe7ed4b4fd659a99f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jul 2020 23:59:55 +0200
Subject: seccomp: Provide stub for __secure_computing()

To avoid #ifdeffery in the upcoming generic syscall entry work code provide
a stub for __secure_computing() as this is preferred over
secure_computing() because the TIF flag is already evaluated.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200722220519.404974280@linutronix.de
---
 include/linux/seccomp.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 4192369b8418..03d28c32ad01 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -61,6 +61,7 @@ struct seccomp_filter { };
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 static inline int secure_computing(void) { return 0; }
+static inline int __secure_computing(void) { return 0; }
 #else
 static inline void secure_computing_strict(int this_syscall) { return; }
 #endif
-- 
cgit v1.2.3


From 142781e108b13b2b0e8f035cfb5bfbbc8f14d887 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jul 2020 23:59:56 +0200
Subject: entry: Provide generic syscall entry functionality

On syscall entry certain work needs to be done:

   - Establish state (lockdep, context tracking, tracing)
   - Conditional work (ptrace, seccomp, audit...)

This code is needlessly duplicated and  different in all
architectures.

Provide a generic version based on the x86 implementation which has all the
RCU and instrumentation bits right.

As interrupt/exception entry from user space needs parts of the same
functionality, provide a function for this as well.

syscall_enter_from_user_mode() and irqentry_enter_from_user_mode() must be
called right after the low level ASM entry. The calling code must be
non-instrumentable. After the functions returns state is correct and the
subsequent functions can be instrumented.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200722220519.513463269@linutronix.de
---
 arch/Kconfig                 |   3 ++
 include/linux/entry-common.h | 121 +++++++++++++++++++++++++++++++++++++++++++
 kernel/Makefile              |   1 +
 kernel/entry/Makefile        |  12 +++++
 kernel/entry/common.c        |  88 +++++++++++++++++++++++++++++++
 5 files changed, 225 insertions(+)
 create mode 100644 include/linux/entry-common.h
 create mode 100644 kernel/entry/Makefile
 create mode 100644 kernel/entry/common.c

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 8cc35dc556c7..852a527f418f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -27,6 +27,9 @@ config HAVE_IMA_KEXEC
 config HOTPLUG_SMT
 	bool
 
+config GENERIC_ENTRY
+       bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
new file mode 100644
index 000000000000..42fc8e4632bb
--- /dev/null
+++ b/include/linux/entry-common.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_ENTRYCOMMON_H
+#define __LINUX_ENTRYCOMMON_H
+
+#include <linux/tracehook.h>
+#include <linux/syscalls.h>
+#include <linux/seccomp.h>
+#include <linux/sched.h>
+
+#include <asm/entry-common.h>
+
+/*
+ * Define dummy _TIF work flags if not defined by the architecture or for
+ * disabled functionality.
+ */
+#ifndef _TIF_SYSCALL_EMU
+# define _TIF_SYSCALL_EMU		(0)
+#endif
+
+#ifndef _TIF_SYSCALL_TRACEPOINT
+# define _TIF_SYSCALL_TRACEPOINT	(0)
+#endif
+
+#ifndef _TIF_SECCOMP
+# define _TIF_SECCOMP			(0)
+#endif
+
+#ifndef _TIF_SYSCALL_AUDIT
+# define _TIF_SYSCALL_AUDIT		(0)
+#endif
+
+/*
+ * TIF flags handled in syscall_enter_from_usermode()
+ */
+#ifndef ARCH_SYSCALL_ENTER_WORK
+# define ARCH_SYSCALL_ENTER_WORK	(0)
+#endif
+
+#define SYSCALL_ENTER_WORK						\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP |	\
+	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
+	 ARCH_SYSCALL_ENTER_WORK)
+
+/**
+ * arch_check_user_regs - Architecture specific sanity check for user mode regs
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Defaults to an empty implementation. Can be replaced by architecture
+ * specific code.
+ *
+ * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
+ * section. Use __always_inline so the compiler cannot push it out of line
+ * and make it instrumentable.
+ */
+static __always_inline void arch_check_user_regs(struct pt_regs *regs);
+
+#ifndef arch_check_user_regs
+static __always_inline void arch_check_user_regs(struct pt_regs *regs) {}
+#endif
+
+/**
+ * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry()
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Returns: 0 on success or an error code to skip the syscall.
+ *
+ * Defaults to tracehook_report_syscall_entry(). Can be replaced by
+ * architecture specific code.
+ *
+ * Invoked from syscall_enter_from_user_mode()
+ */
+static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs);
+
+#ifndef arch_syscall_enter_tracehook
+static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs)
+{
+	return tracehook_report_syscall_entry(regs);
+}
+#endif
+
+/**
+ * syscall_enter_from_user_mode - Check and handle work before invoking
+ *				 a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and the subsequent functions can be
+ * instrumented.
+ *
+ * Returns: The original or a modified syscall number
+ *
+ * If the returned syscall number is -1 then the syscall should be
+ * skipped. In this case the caller may invoke syscall_set_error() or
+ * syscall_set_return_value() first.  If neither of those are called and -1
+ * is returned, then the syscall will fail with ENOSYS.
+ *
+ * The following functionality is handled here:
+ *
+ *  1) Establish state (lockdep, RCU (context tracking), tracing)
+ *  2) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
+ *     __secure_computing(), trace_sys_enter()
+ *  3) Invocation of audit_syscall_entry()
+ */
+long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
+
+/**
+ * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from architecture specific entry code with interrupts disabled.
+ * Can only be called when the interrupt entry came from user mode. The
+ * calling code must be non-instrumentable.  When the function returns all
+ * state is correct and the subsequent functions can be instrumented.
+ *
+ * The function establishes state (lockdep, RCU (context tracking), tracing)
+ */
+void irqentry_enter_from_user_mode(struct pt_regs *regs);
+
+#endif
diff --git a/kernel/Makefile b/kernel/Makefile
index f3218bc5ec69..fde2000d0d0d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -48,6 +48,7 @@ obj-y += irq/
 obj-y += rcu/
 obj-y += livepatch/
 obj-y += dma/
+obj-y += entry/
 
 obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
new file mode 100644
index 000000000000..c207d202bf3a
--- /dev/null
+++ b/kernel/entry/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Prevent the noinstr section from being pestered by sanitizer and other goodies
+# as long as these things cannot be disabled per function.
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
+CFLAGS_common.o		+= -fno-stack-protector
+
+obj-$(CONFIG_GENERIC_ENTRY) += common.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
new file mode 100644
index 000000000000..1d636dee2fec
--- /dev/null
+++ b/kernel/entry/common.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_check_user_regs(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+				unsigned long ti_work)
+{
+	long ret = 0;
+
+	/* Handle ptrace */
+	if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+		ret = arch_syscall_enter_tracehook(regs);
+		if (ret || (ti_work & _TIF_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (ti_work & _TIF_SECCOMP) {
+		ret = __secure_computing(NULL);
+		if (ret == -1L)
+			return ret;
+	}
+
+	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall);
+
+	syscall_enter_audit(regs, syscall);
+
+	return ret ? : syscall;
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	unsigned long ti_work;
+
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+
+	local_irq_enable();
+	ti_work = READ_ONCE(current_thread_info()->flags);
+	if (ti_work & SYSCALL_ENTER_WORK)
+		syscall = syscall_trace_enter(regs, syscall, ti_work);
+	instrumentation_end();
+
+	return syscall;
+}
+
+noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+}
-- 
cgit v1.2.3


From a9f3a74a29af095f3e1b89e9176f8127912ae0f0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jul 2020 23:59:57 +0200
Subject: entry: Provide generic syscall exit function

Like syscall entry all architectures have similar and pointlessly different
code to handle pending work before returning from a syscall to user space.

  1) One-time syscall exit work:
      - rseq syscall exit
      - audit
      - syscall tracing
      - tracehook (single stepping)

  2) Preparatory work
      - Exit to user mode loop (common TIF handling).
      - Architecture specific one time work arch_exit_to_user_mode_prepare()
      - Address limit and lockdep checks

  3) Final transition (lockdep, tracing, context tracking, RCU). Invokes
     arch_exit_to_user_mode() to handle e.g. speculation mitigations

Provide a generic version based on the x86 code which has all the RCU and
instrumentation protections right.

Provide a variant for interrupt return to user mode as well which shares
the above #2 and #3 work items.

After syscall_exit_to_user_mode() and irqentry_exit_to_user_mode() the
architecture code just has to return to user space. The code after
returning from these functions must not be instrumented.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200722220519.613977173@linutronix.de
---
 include/linux/entry-common.h | 189 +++++++++++++++++++++++++++++++++++++++++++
 kernel/entry/common.c        | 169 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 358 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 42fc8e4632bb..c4a57be9cde4 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -29,6 +29,14 @@
 # define _TIF_SYSCALL_AUDIT		(0)
 #endif
 
+#ifndef _TIF_PATCH_PENDING
+# define _TIF_PATCH_PENDING		(0)
+#endif
+
+#ifndef _TIF_UPROBE
+# define _TIF_UPROBE			(0)
+#endif
+
 /*
  * TIF flags handled in syscall_enter_from_usermode()
  */
@@ -41,6 +49,29 @@
 	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
 	 ARCH_SYSCALL_ENTER_WORK)
 
+/*
+ * TIF flags handled in syscall_exit_to_user_mode()
+ */
+#ifndef ARCH_SYSCALL_EXIT_WORK
+# define ARCH_SYSCALL_EXIT_WORK		(0)
+#endif
+
+#define SYSCALL_EXIT_WORK						\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
+	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
+
+/*
+ * TIF flags handled in exit_to_user_mode_loop()
+ */
+#ifndef ARCH_EXIT_TO_USER_MODE_WORK
+# define ARCH_EXIT_TO_USER_MODE_WORK		(0)
+#endif
+
+#define EXIT_TO_USER_MODE_WORK						\
+	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING |			\
+	 ARCH_EXIT_TO_USER_MODE_WORK)
+
 /**
  * arch_check_user_regs - Architecture specific sanity check for user mode regs
  * @regs:	Pointer to currents pt_regs
@@ -105,6 +136,149 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
  */
 long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
 
+/**
+ * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Defaults to local_irq_enable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
+
+#ifndef local_irq_enable_exit_to_user
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
+{
+	local_irq_enable();
+}
+#endif
+
+/**
+ * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
+ *
+ * Defaults to local_irq_disable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_disable_exit_to_user(void);
+
+#ifndef local_irq_disable_exit_to_user
+static inline void local_irq_disable_exit_to_user(void)
+{
+	local_irq_disable();
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
+ *				 to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_loop() with interrupt enabled
+ *
+ * Defaults to NOOP. Can be supplied by architecture specific code.
+ */
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_work
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_prepare - Architecture specific preparation for
+ *				    exit to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ */
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_prepare
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode - Architecture specific final work before
+ *			    exit to user mode.
+ *
+ * Invoked from exit_to_user_mode() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ *
+ * This needs to be __always_inline because it is non-instrumentable code
+ * invoked after context tracking switched to user mode.
+ *
+ * An architecture implementation must not do anything complex, no locking
+ * etc. The main purpose is for speculation mitigations.
+ */
+static __always_inline void arch_exit_to_user_mode(void);
+
+#ifndef arch_exit_to_user_mode
+static __always_inline void arch_exit_to_user_mode(void) { }
+#endif
+
+/**
+ * arch_do_signal -  Architecture specific signal delivery function
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from exit_to_user_mode_loop().
+ */
+void arch_do_signal(struct pt_regs *regs);
+
+/**
+ * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()
+ * @regs:	Pointer to currents pt_regs
+ * @step:	Indicator for single step
+ *
+ * Defaults to tracehook_report_syscall_exit(). Can be replaced by
+ * architecture specific code.
+ *
+ * Invoked from syscall_exit_to_user_mode()
+ */
+static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step);
+
+#ifndef arch_syscall_exit_tracehook
+static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
+{
+	tracehook_report_syscall_exit(regs, step);
+}
+#endif
+
+/**
+ * syscall_exit_to_user_mode - Handle work before returning to user mode
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked with interrupts enabled and fully valid regs. Returns with all
+ * work handled, interrupts disabled such that the caller can immediately
+ * switch to user mode. Called from architecture specific syscall and ret
+ * from fork code.
+ *
+ * The call order is:
+ *  1) One-time syscall exit work:
+ *	- rseq syscall exit
+ *      - audit
+ *	- syscall tracing
+ *	- tracehook (single stepping)
+ *
+ *  2) Preparatory work
+ *	- Exit to user mode loop (common TIF handling). Invokes
+ *	  arch_exit_to_user_mode_work() for architecture specific TIF work
+ *	- Architecture specific one time work arch_exit_to_user_mode_prepare()
+ *	- Address limit and lockdep checks
+ *
+ *  3) Final transition (lockdep, tracing, context tracking, RCU). Invokes
+ *     arch_exit_to_user_mode() to handle e.g. speculation mitigations
+ */
+void syscall_exit_to_user_mode(struct pt_regs *regs);
+
 /**
  * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
  * @regs:	Pointer to currents pt_regs
@@ -118,4 +292,19 @@ long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
  */
 void irqentry_enter_from_user_mode(struct pt_regs *regs);
 
+/**
+ * irqentry_exit_to_user_mode - Interrupt exit work
+ * @regs:	Pointer to current's pt_regs
+ *
+ * Invoked with interrupts disbled and fully valid regs. Returns with all
+ * work handled, interrupts disabled such that the caller can immediately
+ * switch to user mode. Called from architecture specific interrupt
+ * handling code.
+ *
+ * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
+ * Interrupt exit is not invoking #1 which is the syscall specific one time
+ * work.
+ */
+void irqentry_exit_to_user_mode(struct pt_regs *regs);
+
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 1d636dee2fec..0a051bb91a56 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -2,6 +2,8 @@
 
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
+#include <linux/livepatch.h>
+#include <linux/audit.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -82,7 +84,174 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 	return syscall;
 }
 
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.
+ * 4) Tell lockdep that interrupts are enabled
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/* Workaround to allow gradual conversion of architecture code */
+void __weak arch_do_signal(struct pt_regs *regs) { }
+
+static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+					    unsigned long ti_work)
+{
+	/*
+	 * Before returning to user space ensure that all pending work
+	 * items have been completed.
+	 */
+	while (ti_work & EXIT_TO_USER_MODE_WORK) {
+
+		local_irq_enable_exit_to_user(ti_work);
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		if (ti_work & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
+		if (ti_work & _TIF_SIGPENDING)
+			arch_do_signal(regs);
+
+		if (ti_work & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+			rseq_handle_notify_resume(NULL, regs);
+		}
+
+		/* Architecture specific TIF work */
+		arch_exit_to_user_mode_work(regs, ti_work);
+
+		/*
+		 * Disable interrupts and reevaluate the work flags as they
+		 * might have changed while interrupts and preemption was
+		 * enabled above.
+		 */
+		local_irq_disable_exit_to_user();
+		ti_work = READ_ONCE(current_thread_info()->flags);
+	}
+
+	/* Return the latest work state for arch_exit_to_user_mode() */
+	return ti_work;
+}
+
+static void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
+
+	lockdep_assert_irqs_disabled();
+
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that the address limit is intact and no locks are held */
+	addr_limit_user_check();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+#ifndef _TIF_SINGLESTEP
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return false;
+}
+#else
+/*
+ * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_usermode().
+ */
+#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
+
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+}
+#endif
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	bool step;
+
+	audit_syscall_exit(regs);
+
+	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(ti_work);
+	if (step || ti_work & _TIF_SYSCALL_TRACE)
+		arch_syscall_exit_tracehook(regs, step);
+}
+
+/*
+ * Syscall specific exit to user mode preparation. Runs with interrupts
+ * enabled.
+ */
+static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_syscall(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
+		syscall_exit_work(regs, cached_flags);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	syscall_exit_to_user_mode_prepare(regs);
+	local_irq_disable_exit_to_user();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 }
+
+noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
-- 
cgit v1.2.3


From a5497bab5f72dce38a259a53fd3ac1239a7ecf40 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jul 2020 23:59:58 +0200
Subject: entry: Provide generic interrupt entry/exit code

Like the syscall entry/exit code interrupt/exception entry after the real
low level ASM bits should not be different accross architectures.

Provide a generic version based on the x86 code.

irqentry_enter() is called after the low level entry code and
irqentry_exit() must be invoked right before returning to the low level
code which just contains the actual return logic. The code before
irqentry_enter() and irqentry_exit() must not be instrumented. Code after
irqentry_enter() and before irqentry_exit() can be instrumented.

irqentry_enter() invokes irqentry_enter_from_user_mode() if the
interrupt/exception came from user mode. If if entered from kernel mode it
handles the kernel mode variant of establishing state for lockdep, RCU and
tracing depending on the kernel context it interrupted (idle, non-idle).

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200722220519.723703209@linutronix.de
---
 include/linux/entry-common.h |  62 +++++++++++++++++++++++
 kernel/entry/common.c        | 117 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 179 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index c4a57be9cde4..efebbffcd5cc 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -307,4 +307,66 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs);
  */
 void irqentry_exit_to_user_mode(struct pt_regs *regs);
 
+#ifndef irqentry_state
+typedef struct irqentry_state {
+	bool	exit_rcu;
+} irqentry_state_t;
+#endif
+
+/**
+ * irqentry_enter - Handle state tracking on ordinary interrupt entries
+ * @regs:	Pointer to pt_regs of interrupted context
+ *
+ * Invokes:
+ *  - lockdep irqflag state tracking as low level ASM entry disabled
+ *    interrupts.
+ *
+ *  - Context tracking if the exception hit user mode.
+ *
+ *  - The hardirq tracer to keep the state consistent as low level ASM
+ *    entry disabled interrupts.
+ *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
+ * invoked on entry and rcu_irq_exit() on exit.
+ *
+ * Avoiding the rcu_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking rcu_irq_enter() without undoing it.
+ *
+ * For user mode entries irqentry_enter_from_user_mode() is invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: An opaque object that must be passed to idtentry_exit()
+ */
+irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
+ *
+ * Conditional reschedule with additional sanity checks.
+ */
+void irqentry_exit_cond_resched(void);
+
+/**
+ * irqentry_exit - Handle return from exception that used irqentry_enter()
+ * @regs:	Pointer to pt_regs (exception entry regs)
+ * @state:	Return value from matching call to irqentry_enter()
+ *
+ * Depending on the return target (kernel/user) this runs the necessary
+ * preemption and work checks if possible and reguired and returns to
+ * the caller with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to irqentry_enter().
+ */
+void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
+
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 0a051bb91a56..495f5c051b03 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -255,3 +255,120 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_end();
 	exit_to_user_mode();
 }
+
+irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs)
+{
+	irqentry_state_t ret = {
+		.exit_rcu = false,
+	};
+
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+		return ret;
+	}
+
+	/*
+	 * If this entry hit the idle task invoke rcu_irq_enter() whether
+	 * RCU is watching or not.
+	 *
+	 * Interupts can nest when the first interrupt invokes softirq
+	 * processing on return which enables interrupts.
+	 *
+	 * Scheduler ticks in the idle task can mark quiescent state and
+	 * terminate a grace period, if and only if the timer interrupt is
+	 * not nested into another interrupt.
+	 *
+	 * Checking for __rcu_is_watching() here would prevent the nesting
+	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
+	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
+	 * assume that it is the first interupt and eventually claim
+	 * quiescient state and end grace periods prematurely.
+	 *
+	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
+	 * consistent.
+	 *
+	 * TINY_RCU does not support EQS, so let the compiler eliminate
+	 * this part when enabled.
+	 */
+	if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+		/*
+		 * If RCU is not watching then the same careful
+		 * sequence vs. lockdep and tracing is required
+		 * as in irq_enter_from_user_mode().
+		 */
+		lockdep_hardirqs_off(CALLER_ADDR0);
+		rcu_irq_enter();
+		instrumentation_begin();
+		trace_hardirqs_off_finish();
+		instrumentation_end();
+
+		ret.exit_rcu = true;
+		return ret;
+	}
+
+	/*
+	 * If RCU is watching then RCU only wants to check whether it needs
+	 * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
+	 * already contains a warning when RCU is not watching, so no point
+	 * in having another one here.
+	 */
+	instrumentation_begin();
+	rcu_irq_enter_check_tick();
+	/* Use the combo lockdep/tracing function */
+	trace_hardirqs_off();
+	instrumentation_end();
+
+	return ret;
+}
+
+void irqentry_exit_cond_resched(void)
+{
+	if (!preempt_count()) {
+		/* Sanity check RCU and thread stack */
+		rcu_irq_exit_check_preempt();
+		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+			WARN_ON_ONCE(!on_thread_stack());
+		if (need_resched())
+			preempt_schedule_irq();
+	}
+}
+
+void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
+{
+	lockdep_assert_irqs_disabled();
+
+	/* Check whether this returns to user mode */
+	if (user_mode(regs)) {
+		irqentry_exit_to_user_mode(regs);
+	} else if (!regs_irqs_disabled(regs)) {
+		/*
+		 * If RCU was not watching on entry this needs to be done
+		 * carefully and needs the same ordering of lockdep/tracing
+		 * and RCU as the return to user mode path.
+		 */
+		if (state.exit_rcu) {
+			instrumentation_begin();
+			/* Tell the tracer that IRET will enable interrupts */
+			trace_hardirqs_on_prepare();
+			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			instrumentation_end();
+			rcu_irq_exit();
+			lockdep_hardirqs_on(CALLER_ADDR0);
+			return;
+		}
+
+		instrumentation_begin();
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			irqentry_exit_cond_resched();
+		/* Covers both tracing and lockdep */
+		trace_hardirqs_on();
+		instrumentation_end();
+	} else {
+		/*
+		 * IRQ flags state is correct already. Just tell RCU if it
+		 * was not watching on entry.
+		 */
+		if (state.exit_rcu)
+			rcu_irq_exit();
+	}
+}
-- 
cgit v1.2.3


From 935ace2fb5cc49ae88bd1f1735ddc51cdc2ebfb3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jul 2020 23:59:59 +0200
Subject: entry: Provide infrastructure for work before transitioning to guest
 mode

Entering a guest is similar to exiting to user space. Pending work like
handling signals, rescheduling, task work etc. needs to be handled before
that.

Provide generic infrastructure to avoid duplication of the same handling
code all over the place.

The transfer to guest mode handling is different from the exit to usermode
handling, e.g. vs. rseq and live patching, so a separate function is used.

The initial list of work items handled is:

    TIF_SIGPENDING, TIF_NEED_RESCHED, TIF_NOTIFY_RESUME

Architecture specific TIF flags can be added via defines in the
architecture specific include files.

The calling convention is also different from the syscall/interrupt entry
functions as KVM invokes this from the outer vcpu_run() loop with
interrupts and preemption enabled. To prevent missing a pending work item
it invokes a check for pending TIF work from interrupt disabled code right
before transitioning to guest mode. The lockdep, RCU and tracing state
handling is also done directly around the switch to and from guest mode.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200722220519.833296398@linutronix.de
---
 include/linux/entry-kvm.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kvm_host.h  |  8 +++++
 kernel/entry/Makefile     |  3 +-
 kernel/entry/kvm.c        | 51 ++++++++++++++++++++++++++++++
 virt/kvm/Kconfig          |  3 ++
 5 files changed, 144 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/entry-kvm.h
 create mode 100644 kernel/entry/kvm.c

(limited to 'include/linux')

diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
new file mode 100644
index 000000000000..0cef17afb41a
--- /dev/null
+++ b/include/linux/entry-kvm.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_ENTRYKVM_H
+#define __LINUX_ENTRYKVM_H
+
+#include <linux/entry-common.h>
+
+/* Transfer to guest mode work */
+#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
+
+#ifndef ARCH_XFER_TO_GUEST_MODE_WORK
+# define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
+#endif
+
+#define XFER_TO_GUEST_MODE_WORK					\
+	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |			\
+	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
+
+struct kvm_vcpu;
+
+/**
+ * arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest
+ *					 mode work handling function.
+ * @vcpu:	Pointer to current's VCPU data
+ * @ti_work:	Cached TIF flags gathered in xfer_to_guest_mode_handle_work()
+ *
+ * Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be
+ * replaced by architecture specific code.
+ */
+static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
+						      unsigned long ti_work);
+
+#ifndef arch_xfer_to_guest_mode_work
+static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
+						      unsigned long ti_work)
+{
+	return 0;
+}
+#endif
+
+/**
+ * xfer_to_guest_mode_handle_work - Check and handle pending work which needs
+ *				    to be handled before going to guest mode
+ * @vcpu:	Pointer to current's VCPU data
+ *
+ * Returns: 0 or an error code
+ */
+int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
+
+/**
+ * __xfer_to_guest_mode_work_pending - Check if work is pending
+ *
+ * Returns: True if work pending, False otherwise.
+ *
+ * Bare variant of xfer_to_guest_mode_work_pending(). Can be called from
+ * interrupt enabled code for racy quick checks with care.
+ */
+static inline bool __xfer_to_guest_mode_work_pending(void)
+{
+	unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
+
+	return !!(ti_work & XFER_TO_GUEST_MODE_WORK);
+}
+
+/**
+ * xfer_to_guest_mode_work_pending - Check if work is pending which needs to be
+ *				     handled before returning to guest mode
+ *
+ * Returns: True if work pending, False otherwise.
+ *
+ * Has to be invoked with interrupts disabled before the transition to
+ * guest mode.
+ */
+static inline bool xfer_to_guest_mode_work_pending(void)
+{
+	lockdep_assert_irqs_disabled();
+	return __xfer_to_guest_mode_work_pending();
+}
+#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
+
+#endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d564855243d8..ac83e9c1d82c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1439,4 +1439,12 @@ int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
 				uintptr_t data, const char *name,
 				struct task_struct **thread_ptr);
 
+#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
+static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
+{
+	vcpu->run->exit_reason = KVM_EXIT_INTR;
+	vcpu->stat.signal_exits++;
+}
+#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
+
 #endif
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
index c207d202bf3a..34c8a3f1c735 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -9,4 +9,5 @@ KCOV_INSTRUMENT := n
 CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_common.o		+= -fno-stack-protector
 
-obj-$(CONFIG_GENERIC_ENTRY) += common.o
+obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o
+obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
new file mode 100644
index 000000000000..eb1a8a4c867c
--- /dev/null
+++ b/kernel/entry/kvm.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/entry-kvm.h>
+#include <linux/kvm_host.h>
+
+static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
+{
+	do {
+		int ret;
+
+		if (ti_work & _TIF_SIGPENDING) {
+			kvm_handle_signal_exit(vcpu);
+			return -EINTR;
+		}
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(NULL);
+		}
+
+		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
+		if (ret)
+			return ret;
+
+		ti_work = READ_ONCE(current_thread_info()->flags);
+	} while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched());
+	return 0;
+}
+
+int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu)
+{
+	unsigned long ti_work;
+
+	/*
+	 * This is invoked from the outer guest loop with interrupts and
+	 * preemption enabled.
+	 *
+	 * KVM invokes xfer_to_guest_mode_work_pending() with interrupts
+	 * disabled in the inner loop before going into guest mode. No need
+	 * to disable interrupts here.
+	 */
+	ti_work = READ_ONCE(current_thread_info()->flags);
+	if (!(ti_work & XFER_TO_GUEST_MODE_WORK))
+		return 0;
+
+	return xfer_to_guest_mode_work(vcpu, ti_work);
+}
+EXPORT_SYMBOL_GPL(xfer_to_guest_mode_handle_work);
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index aad9284c043a..1c37ccd5d402 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -60,3 +60,6 @@ config HAVE_KVM_VCPU_RUN_PID_CHANGE
 
 config HAVE_KVM_NO_POLL
        bool
+
+config KVM_XFER_TO_GUEST_WORK
+       bool
-- 
cgit v1.2.3


From 3f9a7a13fe4cb6e119e4e4745fbf975d30bfac9b Mon Sep 17 00:00:00 2001
From: Ashok Raj <ashok.raj@intel.com>
Date: Thu, 23 Jul 2020 15:37:29 -0700
Subject: PCI/ATS: Add pci_pri_supported() to check device or associated PF

For SR-IOV, the PF PRI is shared between the PF and any associated VFs, and
the PRI Capability is allowed for PFs but not for VFs.  Searching for the
PRI Capability on a VF always fails, even if its associated PF supports
PRI.

Add pci_pri_supported() to check whether device or its associated PF
supports PRI.

[bhelgaas: commit log, avoid "!!"]
Fixes: b16d0cb9e2fc ("iommu/vt-d: Always enable PASID/PRI PCI capabilities before ATS")
Link: https://lore.kernel.org/r/1595543849-19692-1-git-send-email-ashok.raj@intel.com
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Cc: stable@vger.kernel.org	# v4.4+
---
 drivers/iommu/intel/iommu.c |  2 +-
 drivers/pci/ats.c           | 15 +++++++++++++++
 include/linux/pci-ats.h     |  4 ++++
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 9129663a7406..5552e7d5d2b1 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2554,7 +2554,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 			}
 
 			if (info->ats_supported && ecap_prs(iommu->ecap) &&
-			    pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI))
+			    pci_pri_supported(pdev))
 				info->pri_supported = 1;
 		}
 	}
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index b761c1f72f67..647e097530a8 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -325,6 +325,21 @@ int pci_prg_resp_pasid_required(struct pci_dev *pdev)
 
 	return pdev->pasid_required;
 }
+
+/**
+ * pci_pri_supported - Check if PRI is supported.
+ * @pdev: PCI device structure
+ *
+ * Returns true if PRI capability is present, false otherwise.
+ */
+bool pci_pri_supported(struct pci_dev *pdev)
+{
+	/* VFs share the PF PRI */
+	if (pci_physfn(pdev)->pri_cap)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(pci_pri_supported);
 #endif /* CONFIG_PCI_PRI */
 
 #ifdef CONFIG_PCI_PASID
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index f75c307f346d..df54cd5b15db 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -28,6 +28,10 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs);
 void pci_disable_pri(struct pci_dev *pdev);
 int pci_reset_pri(struct pci_dev *pdev);
 int pci_prg_resp_pasid_required(struct pci_dev *pdev);
+bool pci_pri_supported(struct pci_dev *pdev);
+#else
+static inline bool pci_pri_supported(struct pci_dev *pdev)
+{ return false; }
 #endif /* CONFIG_PCI_PRI */
 
 #ifdef CONFIG_PCI_PASID
-- 
cgit v1.2.3


From e5ebffe18e5add85acb23c7a0f74509749967204 Mon Sep 17 00:00:00 2001
From: Jim Cromie <jim.cromie@gmail.com>
Date: Sun, 19 Jul 2020 17:10:45 -0600
Subject: dyndbg: rename __verbose section to __dyndbg

dyndbg populates its callsite info into __verbose section, change that
to a more specific and descriptive name, __dyndbg.

Also, per checkpatch:
  simplify __attribute(..) to __section(__dyndbg) declaration.

and 1 spelling fix, decriptor

Acked-by: <jbaron@akamai.com>
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
Link: https://lore.kernel.org/r/20200719231058.1586423-6-jim.cromie@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/asm-generic/vmlinux.lds.h |  6 +++---
 include/linux/dynamic_debug.h     |  4 ++--
 kernel/module.c                   |  2 +-
 lib/dynamic_debug.c               | 12 ++++++------
 4 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index db600ef218d7..05af5cef1ad6 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -320,9 +320,9 @@
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
 	. = ALIGN(8);							\
-	__start___verbose = .;						\
-	KEEP(*(__verbose))                                              \
-	__stop___verbose = .;						\
+	__start___dyndbg = .;						\
+	KEEP(*(__dyndbg))						\
+	__stop___dyndbg = .;						\
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index abcd5fde30eb..aa9ff9e1c0b3 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -80,7 +80,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 
 #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt)		\
 	static struct _ddebug  __aligned(8)			\
-	__attribute__((section("__verbose"))) name = {		\
+	__section(__dyndbg) name = {				\
 		.modname = KBUILD_MODNAME,			\
 		.function = __func__,				\
 		.filename = __FILE__,				\
@@ -133,7 +133,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 
 /*
  * "Factory macro" for generating a call to func, guarded by a
- * DYNAMIC_DEBUG_BRANCH. The dynamic debug decriptor will be
+ * DYNAMIC_DEBUG_BRANCH. The dynamic debug descriptor will be
  * initialized using the fmt argument. The function will be called with
  * the address of the descriptor as first argument, followed by all
  * the varargs. Note that fmt is repeated in invocations of this
diff --git a/kernel/module.c b/kernel/module.c
index aa183c9ac0a2..e7b4ff7e4fd0 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3237,7 +3237,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	if (section_addr(info, "__obsparm"))
 		pr_warn("%s: Ignoring obsolete parameters\n", mod->name);
 
-	info->debug = section_objs(info, "__verbose",
+	info->debug = section_objs(info, "__dyndbg",
 				   sizeof(*info->debug), &info->num_debug);
 
 	return 0;
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c97872cffc8e..66c0bdf06ce7 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -39,8 +39,8 @@
 
 #include <rdma/ib_verbs.h>
 
-extern struct _ddebug __start___verbose[];
-extern struct _ddebug __stop___verbose[];
+extern struct _ddebug __start___dyndbg[];
+extern struct _ddebug __stop___dyndbg[];
 
 struct ddebug_table {
 	struct list_head link;
@@ -1019,7 +1019,7 @@ static int __init dynamic_debug_init(void)
 	int n = 0, entries = 0, modct = 0;
 	int verbose_bytes = 0;
 
-	if (&__start___verbose == &__stop___verbose) {
+	if (&__start___dyndbg == &__stop___dyndbg) {
 		if (IS_ENABLED(CONFIG_DYNAMIC_DEBUG)) {
 			pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
 			return 1;
@@ -1028,10 +1028,10 @@ static int __init dynamic_debug_init(void)
 		ddebug_init_success = 1;
 		return 0;
 	}
-	iter = __start___verbose;
+	iter = __start___dyndbg;
 	modname = iter->modname;
 	iter_start = iter;
-	for (; iter < __stop___verbose; iter++) {
+	for (; iter < __stop___dyndbg; iter++) {
 		entries++;
 		verbose_bytes += strlen(iter->modname) + strlen(iter->function)
 			+ strlen(iter->filename) + strlen(iter->format);
@@ -1054,7 +1054,7 @@ static int __init dynamic_debug_init(void)
 	ddebug_init_success = 1;
 	vpr_info("%d modules, %d entries and %d bytes in ddebug tables, %d bytes in (readonly) verbose section\n",
 		 modct, entries, (int)(modct * sizeof(struct ddebug_table)),
-		 verbose_bytes + (int)(__stop___verbose - __start___verbose));
+		 verbose_bytes + (int)(__stop___dyndbg - __start___dyndbg));
 
 	/* apply ddebug_query boot param, dont unload tables on err */
 	if (ddebug_setup_string[0] != '\0') {
-- 
cgit v1.2.3


From dd6f843a9fca8f225c86fee5f50da429c369c045 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 18 Jul 2020 11:32:51 +0300
Subject: tasks: add put_task_struct_many()

put_task_struct_many() is as put_task_struct() but puts several
references at once. Useful to batching it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched/task.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 38359071236a..1301077f9c24 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -126,6 +126,12 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
+static inline void put_task_struct_many(struct task_struct *t, int nr)
+{
+	if (refcount_sub_and_test(nr, &t->usage))
+		__put_task_struct(t);
+}
+
 void put_task_struct_rcu_user(struct task_struct *task);
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
-- 
cgit v1.2.3


From 042dd05bddbd84e6a52b337a65d1994003c9b9bb Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Thu, 4 Jun 2020 08:49:38 +0300
Subject: RDMA/mlx5: ConnectX-7 new capabilities to set relaxed ordering by UMR

Up to ConnectX-7 setting mkey relaxed ordering read/write attributes
by UMR is not supported. ConnectX-7 supports this option, which is
indicated by two new HCA capabilities - relaxed_ordering_write_umr
and relaxed_ordering_read_umr.

Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 435ab47d5362..0257329431e8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1240,7 +1240,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
-	u8         reserved_at_d0[0x9];
+	u8         relaxed_ordering_write_umr[0x1];
+	u8         relaxed_ordering_read_umr[0x1];
+	u8         reserved_at_d2[0x7];
 	u8         virtio_net_device_emualtion_manager[0x1];
 	u8         virtio_blk_device_emualtion_manager[0x1];
 	u8         log_max_cq[0x5];
-- 
cgit v1.2.3


From 3bef735ad7b7d987069181e7b58588043cbd1509 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@mykernel.net>
Date: Thu, 23 Jul 2020 21:15:14 -0700
Subject: vfs/xattr: mm/shmem: kernfs: release simple xattr entry in a right
 way

After commit fdc85222d58e ("kernfs: kvmalloc xattr value instead of
kmalloc"), simple xattr entry is allocated with kvmalloc() instead of
kmalloc(), so we should release it with kvfree() instead of kfree().

Fixes: fdc85222d58e ("kernfs: kvmalloc xattr value instead of kmalloc")
Signed-off-by: Chengguang Xu <cgxu519@mykernel.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Daniel Xu <dxu@dxuuu.xyz>
Cc: Chris Down <chris@chrisdown.name>
Cc: Andreas Dilger <adilger@dilger.ca>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>	[5.7]
Link: http://lkml.kernel.org/r/20200704051608.15043-1-cgxu519@mykernel.net
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xattr.h | 3 ++-
 mm/shmem.c            | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 47eaa34f8761..c5afaf8ca7a2 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/mm.h>
 #include <uapi/linux/xattr.h>
 
 struct inode;
@@ -94,7 +95,7 @@ static inline void simple_xattrs_free(struct simple_xattrs *xattrs)
 
 	list_for_each_entry_safe(xattr, node, &xattrs->head, list) {
 		kfree(xattr->name);
-		kfree(xattr);
+		kvfree(xattr);
 	}
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index a0dbe62f8042..b2abca3f7f33 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3178,7 +3178,7 @@ static int shmem_initxattrs(struct inode *inode,
 		new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len,
 					  GFP_KERNEL);
 		if (!new_xattr->name) {
-			kfree(new_xattr);
+			kvfree(new_xattr);
 			return -ENOMEM;
 		}
 
-- 
cgit v1.2.3


From e0b3e0b1a04367fc15c07f44e78361545b55357c Mon Sep 17 00:00:00 2001
From: "Michael J. Ruhl" <michael.j.ruhl@intel.com>
Date: Thu, 23 Jul 2020 21:15:46 -0700
Subject: io-mapping: indicate mapping failure

The !ATOMIC_IOMAP version of io_maping_init_wc will always return
success, even when the ioremap fails.

Since the ATOMIC_IOMAP version returns NULL when the init fails, and
callers check for a NULL return on error this is unexpected.

During a device probe, where the ioremap failed, a crash can look like
this:

    BUG: unable to handle page fault for address: 0000000000210000
     #PF: supervisor write access in kernel mode
     #PF: error_code(0x0002) - not-present page
     Oops: 0002 [#1] PREEMPT SMP
     CPU: 0 PID: 177 Comm:
     RIP: 0010:fill_page_dma [i915]
       gen8_ppgtt_create [i915]
       i915_ppgtt_create [i915]
       intel_gt_init [i915]
       i915_gem_init [i915]
       i915_driver_probe [i915]
       pci_device_probe
       really_probe
       driver_probe_device

The remap failure occurred much earlier in the probe.  If it had been
propagated, the driver would have exited with an error.

Return NULL on ioremap failure.

[akpm@linux-foundation.org: detect ioremap_wc() errors earlier]

Fixes: cafaf14a5d8f ("io-mapping: Always create a struct to hold metadata about the io-mapping")
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200721171936.81563-1-michael.j.ruhl@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/io-mapping.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 0beaa3eba155..c75e4d3d8833 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -107,9 +107,12 @@ io_mapping_init_wc(struct io_mapping *iomap,
 		   resource_size_t base,
 		   unsigned long size)
 {
+	iomap->iomem = ioremap_wc(base, size);
+	if (!iomap->iomem)
+		return NULL;
+
 	iomap->base = base;
 	iomap->size = size;
-	iomap->iomem = ioremap_wc(base, size);
 #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */
 	iomap->prot = pgprot_noncached_wc(PAGE_KERNEL);
 #elif defined(pgprot_writecombine)
-- 
cgit v1.2.3


From 0c2a34937f7e4c4776bb261114c475392da2355c Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 30 Jun 2020 18:24:40 +0200
Subject: i2c: revert "i2c: core: Allow drivers to disable i2c-core irq
 mapping"

This manually reverts commit d1d84bb95364ed604015c2b788caaf3dbca0262f.
The only user has gone two years ago with commit 589edb56b424 ("ACPI /
scan: Create platform device for INT33FE ACPI nodes") and no new user
has showed up. Remove and hope we will never need it again.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c | 6 +++---
 include/linux/i2c.h         | 3 ---
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 26f03a14a478..dc43242a85ba 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -319,11 +319,9 @@ static int i2c_device_probe(struct device *dev)
 	if (!client)
 		return 0;
 
-	driver = to_i2c_driver(dev->driver);
-
 	client->irq = client->init_irq;
 
-	if (!client->irq && !driver->disable_i2c_core_irq_mapping) {
+	if (!client->irq) {
 		int irq = -ENOENT;
 
 		if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
@@ -349,6 +347,8 @@ static int i2c_device_probe(struct device *dev)
 		client->irq = irq;
 	}
 
+	driver = to_i2c_driver(dev->driver);
+
 	/*
 	 * An I2C ID table is not mandatory, if and only if, a suitable OF
 	 * or ACPI ID table is supplied for the probing device.
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index b8b8963f8bb9..098405df431f 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -231,7 +231,6 @@ enum i2c_alert_protocol {
  * @detect: Callback for device detection
  * @address_list: The I2C addresses to probe (for detect)
  * @clients: List of detected clients we created (for i2c-core use only)
- * @disable_i2c_core_irq_mapping: Tell the i2c-core to not do irq-mapping
  *
  * The driver.owner field should be set to the module owner of this driver.
  * The driver.name field should be set to the name of this driver.
@@ -290,8 +289,6 @@ struct i2c_driver {
 	int (*detect)(struct i2c_client *client, struct i2c_board_info *info);
 	const unsigned short *address_list;
 	struct list_head clients;
-
-	bool disable_i2c_core_irq_mapping;
 };
 #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver)
 
-- 
cgit v1.2.3


From 43148b1cab44dbabf91cb70749ef3f9b24592e91 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 24 Jul 2020 14:19:12 -0700
Subject: soc: ti: k3-ringacc: add request pair of rings api.

Add new API k3_ringacc_request_rings_pair() to request pair of rings at
once, as in the most cases Rings are used with DMA channels, which need to
request pair of rings - one to feed DMA with descriptors (TX/RX FDQ) and
one to receive completions (RX/TX CQ). This will allow to simplify Ringacc
API users.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/k3-ringacc.c       | 24 ++++++++++++++++++++++++
 include/linux/soc/ti/k3-ringacc.h |  4 ++++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c
index 3d8e11079ede..c9f022037942 100644
--- a/drivers/soc/ti/k3-ringacc.c
+++ b/drivers/soc/ti/k3-ringacc.c
@@ -322,6 +322,30 @@ error:
 }
 EXPORT_SYMBOL_GPL(k3_ringacc_request_ring);
 
+int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
+				  int fwd_id, int compl_id,
+				  struct k3_ring **fwd_ring,
+				  struct k3_ring **compl_ring)
+{
+	int ret = 0;
+
+	if (!fwd_ring || !compl_ring)
+		return -EINVAL;
+
+	*fwd_ring = k3_ringacc_request_ring(ringacc, fwd_id, 0);
+	if (!(*fwd_ring))
+		return -ENODEV;
+
+	*compl_ring = k3_ringacc_request_ring(ringacc, compl_id, 0);
+	if (!(*compl_ring)) {
+		k3_ringacc_ring_free(*fwd_ring);
+		ret = -ENODEV;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(k3_ringacc_request_rings_pair);
+
 static void k3_ringacc_ring_reset_sci(struct k3_ring *ring)
 {
 	struct k3_ringacc *ringacc = ring->parent;
diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h
index 26f73df0a524..7ac115432fa1 100644
--- a/include/linux/soc/ti/k3-ringacc.h
+++ b/include/linux/soc/ti/k3-ringacc.h
@@ -107,6 +107,10 @@ struct k3_ringacc *of_k3_ringacc_get_by_phandle(struct device_node *np,
 struct k3_ring *k3_ringacc_request_ring(struct k3_ringacc *ringacc,
 					int id, u32 flags);
 
+int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
+				  int fwd_id, int compl_id,
+				  struct k3_ring **fwd_ring,
+				  struct k3_ring **compl_ring);
 /**
  * k3_ringacc_ring_reset - ring reset
  * @ring: pointer on Ring
-- 
cgit v1.2.3


From 2ea17d504a0ee9b357a5fd2bde257c2ec37ceca7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 24 Jul 2020 14:42:03 -0700
Subject: soc: ti/ti_sci_protocol.h: drop a duplicated word + clarify

Drop the repeated word "an" in a comment.
Insert "and" between "source" and "destination" as is done a few
lines earlier.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 include/linux/soc/ti/ti_sci_protocol.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 9531ec823298..6c728dad8c10 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -226,8 +226,8 @@ struct ti_sci_rm_core_ops {
  *			and destination
  * @set_event_map:	Set an Event based peripheral irq to Interrupt
  *			Aggregator.
- * @free_irq:		Free an an IRQ route between the requested source
- *			destination.
+ * @free_irq:		Free an IRQ route between the requested source
+ *			and destination.
  * @free_event_map:	Free an event based peripheral irq to Interrupt
  *			Aggregator.
  */
-- 
cgit v1.2.3


From a6df49f4224324dd8588f6a0d9cff53cd61a196b Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Fri, 24 Jul 2020 14:43:48 -0700
Subject: firmware: ti_sci: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt | 2 +-
 drivers/firmware/ti_sci.c                                              | 2 +-
 drivers/firmware/ti_sci.h                                              | 2 +-
 drivers/irqchip/irq-ti-sci-inta.c                                      | 2 +-
 drivers/irqchip/irq-ti-sci-intr.c                                      | 2 +-
 drivers/reset/reset-ti-sci.c                                           | 2 +-
 include/linux/soc/ti/ti_sci_inta_msi.h                                 | 2 +-
 include/linux/soc/ti/ti_sci_protocol.h                                 | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
index 1a8718f8855d..178fca08278f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
@@ -55,7 +55,7 @@ Required Properties:
 			corresponds to a range of host irqs.
 
 For more details on TISCI IRQ resource management refer:
-http://downloads.ti.com/tisci/esd/latest/2_tisci_msgs/rm/rm_irq.html
+https://downloads.ti.com/tisci/esd/latest/2_tisci_msgs/rm/rm_irq.html
 
 Example:
 --------
diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 4126be9e3216..53cee17d0115 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments System Control Interface Protocol Driver
  *
- * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/
  *	Nishanth Menon
  */
 
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index f0d068c03944..57cd04062994 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -6,7 +6,7 @@
  * The system works in a message response protocol
  * See: http://processors.wiki.ti.com/index.php/TISCI for details
  *
- * Copyright (C)  2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C)  2015-2016 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef __TI_SCI_H
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index 7e3ebf6ed2cd..85de19fe9b6e 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments' K3 Interrupt Aggregator irqchip driver
  *
- * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/
  *	Lokesh Vutla <lokeshvutla@ti.com>
  */
 
diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c
index 59d51a20bbd8..5ea148faf2ab 100644
--- a/drivers/irqchip/irq-ti-sci-intr.c
+++ b/drivers/irqchip/irq-ti-sci-intr.c
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments' K3 Interrupt Router irqchip driver
  *
- * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/
  *	Lokesh Vutla <lokeshvutla@ti.com>
  */
 
diff --git a/drivers/reset/reset-ti-sci.c b/drivers/reset/reset-ti-sci.c
index bf68729ab729..b799aefad547 100644
--- a/drivers/reset/reset-ti-sci.c
+++ b/drivers/reset/reset-ti-sci.c
@@ -1,7 +1,7 @@
 /*
  * Texas Instrument's System Control Interface (TI-SCI) reset driver
  *
- * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h
index 11fb5048f5f6..e3aa8b14612e 100644
--- a/include/linux/soc/ti/ti_sci_inta_msi.h
+++ b/include/linux/soc/ti/ti_sci_inta_msi.h
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments' K3 TI SCI INTA MSI helper
  *
- * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/
  *	Lokesh Vutla <lokeshvutla@ti.com>
  */
 
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 6c728dad8c10..49c5d29cd33c 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments System Control Interface Protocol
  *
- * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/
  *	Nishanth Menon
  */
 
-- 
cgit v1.2.3


From 0cb09aff9d49d92305c3969fc84b785117412968 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Thu, 23 Jul 2020 01:03:00 +0300
Subject: net/flow_dissector: add packet hash dissection

Retreive a hash value from the SKB and store it
in the dissector key for future matching.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h       |  4 ++++
 include/net/flow_dissector.h |  9 +++++++++
 net/core/flow_dissector.c    | 17 +++++++++++++++++
 3 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6a82d4a8229e..fa817a105517 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1342,6 +1342,10 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 			     struct flow_dissector *flow_dissector,
 			     void *target_container);
 
+void skb_flow_dissect_hash(const struct sk_buff *skb,
+			   struct flow_dissector *flow_dissector,
+			   void *target_container);
+
 static inline __u32 skb_get_hash(struct sk_buff *skb)
 {
 	if (!skb->l4_hash && !skb->sw_hash)
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 4b6e36288ddd..cc10b10dc3a1 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -243,6 +243,14 @@ struct flow_dissector_key_ct {
 	u32	ct_labels[4];
 };
 
+/**
+ * struct flow_dissector_key_hash:
+ * @hash: hash value
+ */
+struct flow_dissector_key_hash {
+	u32 hash;
+};
+
 enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -271,6 +279,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
 	FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
 	FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
+	FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 142a8824f0a8..29806eb765cf 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -383,6 +383,23 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
+void skb_flow_dissect_hash(const struct sk_buff *skb,
+			   struct flow_dissector *flow_dissector,
+			   void *target_container)
+{
+	struct flow_dissector_key_hash *key;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH))
+		return;
+
+	key = skb_flow_dissector_target(flow_dissector,
+					FLOW_DISSECTOR_KEY_HASH,
+					target_container);
+
+	key->hash = skb_get_hash_raw(skb);
+}
+EXPORT_SYMBOL(skb_flow_dissect_hash);
+
 static enum flow_dissect_ret
 __skb_flow_dissect_mpls(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-- 
cgit v1.2.3


From ba423fdaa589d972473083defedf9e862626d268 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:46 +0200
Subject: net: add a new sockptr_t type

Add a uptr_t type that can hold a pointer to either a user or kernel
memory region, and simply helpers to copy to and from it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockptr.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 104 insertions(+)
 create mode 100644 include/linux/sockptr.h

(limited to 'include/linux')

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
new file mode 100644
index 000000000000..700856e13ea0
--- /dev/null
+++ b/include/linux/sockptr.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 Christoph Hellwig.
+ *
+ * Support for "universal" pointers that can point to either kernel or userspace
+ * memory.
+ */
+#ifndef _LINUX_SOCKPTR_H
+#define _LINUX_SOCKPTR_H
+
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+typedef struct {
+	union {
+		void		*kernel;
+		void __user	*user;
+	};
+	bool		is_kernel : 1;
+} sockptr_t;
+
+static inline bool sockptr_is_kernel(sockptr_t sockptr)
+{
+	return sockptr.is_kernel;
+}
+
+static inline sockptr_t KERNEL_SOCKPTR(void *p)
+{
+	return (sockptr_t) { .kernel = p, .is_kernel = true };
+}
+
+static inline sockptr_t USER_SOCKPTR(void __user *p)
+{
+	return (sockptr_t) { .user = p };
+}
+
+static inline bool sockptr_is_null(sockptr_t sockptr)
+{
+	return !sockptr.user && !sockptr.kernel;
+}
+
+static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
+{
+	if (!sockptr_is_kernel(src))
+		return copy_from_user(dst, src.user, size);
+	memcpy(dst, src.kernel, size);
+	return 0;
+}
+
+static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size)
+{
+	if (!sockptr_is_kernel(dst))
+		return copy_to_user(dst.user, src, size);
+	memcpy(dst.kernel, src, size);
+	return 0;
+}
+
+static inline void *memdup_sockptr(sockptr_t src, size_t len)
+{
+	void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
+
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+	if (copy_from_sockptr(p, src, len)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+	return p;
+}
+
+static inline void *memdup_sockptr_nul(sockptr_t src, size_t len)
+{
+	char *p = kmalloc_track_caller(len + 1, GFP_KERNEL);
+
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+	if (copy_from_sockptr(p, src, len)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+	p[len] = '\0';
+	return p;
+}
+
+static inline void sockptr_advance(sockptr_t sockptr, size_t len)
+{
+	if (sockptr_is_kernel(sockptr))
+		sockptr.kernel += len;
+	else
+		sockptr.user += len;
+}
+
+static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count)
+{
+	if (sockptr_is_kernel(src)) {
+		size_t len = min(strnlen(src.kernel, count - 1) + 1, count);
+
+		memcpy(dst, src.kernel, len);
+		return len;
+	}
+	return strncpy_from_user(dst, src.user, count);
+}
+
+#endif /* _LINUX_SOCKPTR_H */
-- 
cgit v1.2.3


From b1ea9ff6aff2deae84eccaf0a07cd14912669680 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:47 +0200
Subject: net: switch copy_bpf_fprog_from_user to sockptr_t

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h | 3 ++-
 net/core/filter.c      | 6 +++---
 net/core/sock.c        | 6 ++++--
 net/packet/af_packet.c | 4 ++--
 4 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1c6b6d982bf4..d07a6e973a7d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -20,6 +20,7 @@
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
+#include <linux/sockptr.h>
 #include <crypto/sha.h>
 
 #include <net/sch_generic.h>
@@ -1276,7 +1277,7 @@ struct bpf_sockopt_kern {
 	s32		retval;
 };
 
-int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len);
+int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
 
 struct bpf_sk_lookup_kern {
 	u16		family;
diff --git a/net/core/filter.c b/net/core/filter.c
index 3fa16b8c0d61..29e3455122f7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,14 +77,14 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 
-int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len)
+int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
 	if (in_compat_syscall()) {
 		struct compat_sock_fprog f32;
 
 		if (len != sizeof(f32))
 			return -EINVAL;
-		if (copy_from_user(&f32, src, sizeof(f32)))
+		if (copy_from_sockptr(&f32, src, sizeof(f32)))
 			return -EFAULT;
 		memset(dst, 0, sizeof(*dst));
 		dst->len = f32.len;
@@ -92,7 +92,7 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len)
 	} else {
 		if (len != sizeof(*dst))
 			return -EINVAL;
-		if (copy_from_user(dst, src, sizeof(*dst)))
+		if (copy_from_sockptr(dst, src, sizeof(*dst)))
 			return -EFAULT;
 	}
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 6da54eac2b34..71fc7e4ddd06 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1063,7 +1063,8 @@ set_sndbuf:
 	case SO_ATTACH_FILTER: {
 		struct sock_fprog fprog;
 
-		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		ret = copy_bpf_fprog_from_user(&fprog, USER_SOCKPTR(optval),
+					       optlen);
 		if (!ret)
 			ret = sk_attach_filter(&fprog, sk);
 		break;
@@ -1084,7 +1085,8 @@ set_sndbuf:
 	case SO_ATTACH_REUSEPORT_CBPF: {
 		struct sock_fprog fprog;
 
-		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		ret = copy_bpf_fprog_from_user(&fprog, USER_SOCKPTR(optval),
+					       optlen);
 		if (!ret)
 			ret = sk_reuseport_attach_filter(&fprog, sk);
 		break;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c240fb5de3f0..d8d4f78f78e4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1536,7 +1536,7 @@ static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new)
 	}
 }
 
-static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data,
+static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data,
 				unsigned int len)
 {
 	struct bpf_prog *new;
@@ -1584,7 +1584,7 @@ static int fanout_set_data(struct packet_sock *po, char __user *data,
 {
 	switch (po->fanout->type) {
 	case PACKET_FANOUT_CBPF:
-		return fanout_set_data_cbpf(po, data, len);
+		return fanout_set_data_cbpf(po, USER_SOCKPTR(data), len);
 	case PACKET_FANOUT_EBPF:
 		return fanout_set_data_ebpf(po, data, len);
 	default:
-- 
cgit v1.2.3


From ab214d1bf8c7ef1ed7af803a72491cb29edfa8f5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:53 +0200
Subject: netfilter: switch xt_copy_counters to sockptr_t

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter/x_tables.h |  4 ++--
 net/ipv4/netfilter/arp_tables.c    |  7 +++----
 net/ipv4/netfilter/ip_tables.c     |  7 +++----
 net/ipv6/netfilter/ip6_tables.c    |  6 +++---
 net/netfilter/x_tables.c           | 20 ++++++++++----------
 5 files changed, 21 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index b8b943ee7b8b..5deb099d156d 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -301,8 +301,8 @@ int xt_target_to_user(const struct xt_entry_target *t,
 int xt_data_to_user(void __user *dst, const void *src,
 		    int usersize, int size, int aligned_size);
 
-void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
-				 struct xt_counters_info *info);
+void *xt_copy_counters(sockptr_t arg, unsigned int len,
+		       struct xt_counters_info *info);
 struct xt_counters *xt_counters_alloc(unsigned int counters);
 
 struct xt_table *xt_register_table(struct net *net,
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 2c8a4dad39d7..6d24b686c7f0 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -996,8 +996,7 @@ static int do_replace(struct net *net, const void __user *user,
 	return ret;
 }
 
-static int do_add_counters(struct net *net, const void __user *user,
-			   unsigned int len)
+static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 {
 	unsigned int i;
 	struct xt_counters_info tmp;
@@ -1008,7 +1007,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 	struct arpt_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp);
+	paddc = xt_copy_counters(arg, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 
@@ -1420,7 +1419,7 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned
 		break;
 
 	case ARPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), user, len);
+		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
 		break;
 
 	default:
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 161901dd1cae..4697d09c98dc 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1151,8 +1151,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 }
 
 static int
-do_add_counters(struct net *net, const void __user *user,
-		unsigned int len)
+do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 {
 	unsigned int i;
 	struct xt_counters_info tmp;
@@ -1163,7 +1162,7 @@ do_add_counters(struct net *net, const void __user *user,
 	struct ipt_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp);
+	paddc = xt_copy_counters(arg, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 
@@ -1629,7 +1628,7 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		break;
 
 	case IPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), user, len);
+		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
 		break;
 
 	default:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index fd1f8f931231..a787aba30e2d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1168,7 +1168,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 }
 
 static int
-do_add_counters(struct net *net, const void __user *user, unsigned int len)
+do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 {
 	unsigned int i;
 	struct xt_counters_info tmp;
@@ -1179,7 +1179,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len)
 	struct ip6t_entry *iter;
 	unsigned int addend;
 
-	paddc = xt_copy_counters_from_user(user, len, &tmp);
+	paddc = xt_copy_counters(arg, len, &tmp);
 	if (IS_ERR(paddc))
 		return PTR_ERR(paddc);
 	t = xt_find_table_lock(net, AF_INET6, tmp.name);
@@ -1637,7 +1637,7 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		break;
 
 	case IP6T_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), user, len);
+		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
 		break;
 
 	default:
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 32bab45af7e4..b97eb4b538fd 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1028,9 +1028,9 @@ int xt_check_target(struct xt_tgchk_param *par,
 EXPORT_SYMBOL_GPL(xt_check_target);
 
 /**
- * xt_copy_counters_from_user - copy counters and metadata from userspace
+ * xt_copy_counters - copy counters and metadata from a sockptr_t
  *
- * @user: src pointer to userspace memory
+ * @arg: src sockptr
  * @len: alleged size of userspace memory
  * @info: where to store the xt_counters_info metadata
  *
@@ -1047,8 +1047,8 @@ EXPORT_SYMBOL_GPL(xt_check_target);
  * Return: returns pointer that caller has to test via IS_ERR().
  * If IS_ERR is false, caller has to vfree the pointer.
  */
-void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
-				 struct xt_counters_info *info)
+void *xt_copy_counters(sockptr_t arg, unsigned int len,
+		       struct xt_counters_info *info)
 {
 	void *mem;
 	u64 size;
@@ -1062,12 +1062,12 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
 			return ERR_PTR(-EINVAL);
 
 		len -= sizeof(compat_tmp);
-		if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
+		if (copy_from_sockptr(&compat_tmp, arg, sizeof(compat_tmp)) != 0)
 			return ERR_PTR(-EFAULT);
 
 		memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1);
 		info->num_counters = compat_tmp.num_counters;
-		user += sizeof(compat_tmp);
+		sockptr_advance(arg, sizeof(compat_tmp));
 	} else
 #endif
 	{
@@ -1075,10 +1075,10 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
 			return ERR_PTR(-EINVAL);
 
 		len -= sizeof(*info);
-		if (copy_from_user(info, user, sizeof(*info)) != 0)
+		if (copy_from_sockptr(info, arg, sizeof(*info)) != 0)
 			return ERR_PTR(-EFAULT);
 
-		user += sizeof(*info);
+		sockptr_advance(arg, sizeof(*info));
 	}
 	info->name[sizeof(info->name) - 1] = '\0';
 
@@ -1092,13 +1092,13 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
 	if (!mem)
 		return ERR_PTR(-ENOMEM);
 
-	if (copy_from_user(mem, user, len) == 0)
+	if (copy_from_sockptr(mem, arg, len) == 0)
 		return mem;
 
 	vfree(mem);
 	return ERR_PTR(-EFAULT);
 }
-EXPORT_SYMBOL_GPL(xt_copy_counters_from_user);
+EXPORT_SYMBOL_GPL(xt_copy_counters);
 
 #ifdef CONFIG_COMPAT
 int xt_compat_target_offset(const struct xt_target *target)
-- 
cgit v1.2.3


From c2f12630c60ff33a9cafd221646053fc10ec59b6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:54 +0200
Subject: netfilter: switch nf_setsockopt to sockptr_t

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter.h       |  6 ++++--
 net/bridge/netfilter/ebtables.c | 37 +++++++++++++++++--------------------
 net/decnet/af_decnet.c          |  3 ++-
 net/ipv4/ip_sockglue.c          |  3 ++-
 net/ipv4/netfilter/arp_tables.c | 28 ++++++++++++++--------------
 net/ipv4/netfilter/ip_tables.c  | 24 ++++++++++++------------
 net/ipv6/ipv6_sockglue.c        |  3 ++-
 net/ipv6/netfilter/ip6_tables.c | 24 ++++++++++++------------
 net/netfilter/ipvs/ip_vs_ctl.c  |  4 ++--
 net/netfilter/nf_sockopt.c      |  2 +-
 10 files changed, 68 insertions(+), 66 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 711b4d4486f0..0101747de549 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -13,6 +13,7 @@
 #include <linux/static_key.h>
 #include <linux/netfilter_defs.h>
 #include <linux/netdevice.h>
+#include <linux/sockptr.h>
 #include <net/net_namespace.h>
 
 static inline int NF_DROP_GETERR(int verdict)
@@ -163,7 +164,8 @@ struct nf_sockopt_ops {
 	/* Non-inclusive ranges: use 0/0/NULL to never get called. */
 	int set_optmin;
 	int set_optmax;
-	int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len);
+	int (*set)(struct sock *sk, int optval, sockptr_t arg,
+		   unsigned int len);
 	int get_optmin;
 	int get_optmax;
 	int (*get)(struct sock *sk, int optval, void __user *user, int *len);
@@ -338,7 +340,7 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
 }
 
 /* Call setsockopt() */
-int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
+int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt,
 		  unsigned int len);
 int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
 		  int *len);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 12f8929667bf..d35173e803d3 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1063,14 +1063,13 @@ free_counterstmp:
 }
 
 /* replace the table */
-static int do_replace(struct net *net, const void __user *user,
-		      unsigned int len)
+static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret, countersize;
 	struct ebt_table_info *newinfo;
 	struct ebt_replace tmp;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	if (len != sizeof(tmp) + tmp.entries_size)
@@ -1286,12 +1285,11 @@ free_tmp:
 	return ret;
 }
 
-static int update_counters(struct net *net, const void __user *user,
-			    unsigned int len)
+static int update_counters(struct net *net, sockptr_t arg, unsigned int len)
 {
 	struct ebt_replace hlp;
 
-	if (copy_from_user(&hlp, user, sizeof(hlp)))
+	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
 	if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter))
@@ -2079,7 +2077,7 @@ static int compat_copy_entries(unsigned char *data, unsigned int size_user,
 
 
 static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl,
-					    void __user *user, unsigned int len)
+					     sockptr_t arg, unsigned int len)
 {
 	struct compat_ebt_replace tmp;
 	int i;
@@ -2087,7 +2085,7 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl,
 	if (len < sizeof(tmp))
 		return -EINVAL;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)))
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)))
 		return -EFAULT;
 
 	if (len != sizeof(tmp) + tmp.entries_size)
@@ -2114,8 +2112,7 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl,
 	return 0;
 }
 
-static int compat_do_replace(struct net *net, void __user *user,
-			     unsigned int len)
+static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret, i, countersize, size64;
 	struct ebt_table_info *newinfo;
@@ -2123,10 +2120,10 @@ static int compat_do_replace(struct net *net, void __user *user,
 	struct ebt_entries_buf_state state;
 	void *entries_tmp;
 
-	ret = compat_copy_ebt_replace_from_user(&tmp, user, len);
+	ret = compat_copy_ebt_replace_from_user(&tmp, arg, len);
 	if (ret) {
 		/* try real handler in case userland supplied needed padding */
-		if (ret == -EINVAL && do_replace(net, user, len) == 0)
+		if (ret == -EINVAL && do_replace(net, arg, len) == 0)
 			ret = 0;
 		return ret;
 	}
@@ -2217,17 +2214,17 @@ out_unlock:
 	goto free_entries;
 }
 
-static int compat_update_counters(struct net *net, void __user *user,
+static int compat_update_counters(struct net *net, sockptr_t arg,
 				  unsigned int len)
 {
 	struct compat_ebt_replace hlp;
 
-	if (copy_from_user(&hlp, user, sizeof(hlp)))
+	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
 	/* try real handler in case userland supplied needed padding */
 	if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter))
-		return update_counters(net, user, len);
+		return update_counters(net, arg, len);
 
 	return do_update_counters(net, hlp.name, compat_ptr(hlp.counters),
 				  hlp.num_counters, len);
@@ -2368,7 +2365,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
-static int do_ebt_set_ctl(struct sock *sk, int cmd, void __user *user,
+static int do_ebt_set_ctl(struct sock *sk, int cmd, sockptr_t arg,
 		unsigned int len)
 {
 	struct net *net = sock_net(sk);
@@ -2381,18 +2378,18 @@ static int do_ebt_set_ctl(struct sock *sk, int cmd, void __user *user,
 	case EBT_SO_SET_ENTRIES:
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
-			ret = compat_do_replace(net, user, len);
+			ret = compat_do_replace(net, arg, len);
 		else
 #endif
-			ret = do_replace(net, user, len);
+			ret = do_replace(net, arg, len);
 		break;
 	case EBT_SO_SET_COUNTERS:
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
-			ret = compat_update_counters(net, user, len);
+			ret = compat_update_counters(net, arg, len);
 		else
 #endif
-			ret = update_counters(net, user, len);
+			ret = update_counters(net, arg, len);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 7d7ae2dd69b8..7d51ab608fb3 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1332,7 +1332,8 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != DSO_LINKINFO &&
 	    optname != DSO_STREAM && optname != DSO_SEQPACKET)
-		err = nf_setsockopt(sk, PF_DECnet, optname, optval, optlen);
+		err = nf_setsockopt(sk, PF_DECnet, optname,
+				    USER_SOCKPTR(optval), optlen);
 #endif
 
 	return err;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index da933f99b5d5..42befbf12846 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1422,7 +1422,8 @@ int ip_setsockopt(struct sock *sk, int level,
 			optname != IP_IPSEC_POLICY &&
 			optname != IP_XFRM_POLICY &&
 			!ip_mroute_opt(optname))
-		err = nf_setsockopt(sk, PF_INET, optname, optval, optlen);
+		err = nf_setsockopt(sk, PF_INET, optname, USER_SOCKPTR(optval),
+				    optlen);
 #endif
 	return err;
 }
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6d24b686c7f0..f5b26ef17820 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+
 /*
  * Packet matching code for ARP packets.
  *
@@ -947,8 +947,7 @@ static int __do_replace(struct net *net, const char *name,
 	return ret;
 }
 
-static int do_replace(struct net *net, const void __user *user,
-		      unsigned int len)
+static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct arpt_replace tmp;
@@ -956,7 +955,7 @@ static int do_replace(struct net *net, const void __user *user,
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -972,8 +971,8 @@ static int do_replace(struct net *net, const void __user *user,
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
-			   tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1244,8 +1243,7 @@ out_unlock:
 	return ret;
 }
 
-static int compat_do_replace(struct net *net, void __user *user,
-			     unsigned int len)
+static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct compat_arpt_replace tmp;
@@ -1253,7 +1251,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -1269,7 +1267,8 @@ static int compat_do_replace(struct net *net, void __user *user,
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1401,7 +1400,8 @@ static int compat_get_entries(struct net *net,
 }
 #endif
 
-static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
+static int do_arpt_set_ctl(struct sock *sk, int cmd, sockptr_t arg,
+		unsigned int len)
 {
 	int ret;
 
@@ -1412,14 +1412,14 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned
 	case ARPT_SO_SET_REPLACE:
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
-			ret = compat_do_replace(sock_net(sk), user, len);
+			ret = compat_do_replace(sock_net(sk), arg, len);
 		else
 #endif
-			ret = do_replace(sock_net(sk), user, len);
+			ret = do_replace(sock_net(sk), arg, len);
 		break;
 
 	case ARPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
+		ret = do_add_counters(sock_net(sk), arg, len);
 		break;
 
 	default:
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4697d09c98dc..f2a9680303d8 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1102,7 +1102,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 }
 
 static int
-do_replace(struct net *net, const void __user *user, unsigned int len)
+do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct ipt_replace tmp;
@@ -1110,7 +1110,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -1126,8 +1126,8 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
-			   tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1484,7 +1484,7 @@ out_unlock:
 }
 
 static int
-compat_do_replace(struct net *net, void __user *user, unsigned int len)
+compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct compat_ipt_replace tmp;
@@ -1492,7 +1492,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -1508,8 +1508,8 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
-			   tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1610,7 +1610,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
 #endif
 
 static int
-do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
+do_ipt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len)
 {
 	int ret;
 
@@ -1621,14 +1621,14 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	case IPT_SO_SET_REPLACE:
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
-			ret = compat_do_replace(sock_net(sk), user, len);
+			ret = compat_do_replace(sock_net(sk), arg, len);
 		else
 #endif
-			ret = do_replace(sock_net(sk), user, len);
+			ret = do_replace(sock_net(sk), arg, len);
 		break;
 
 	case IPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
+		ret = do_add_counters(sock_net(sk), arg, len);
 		break;
 
 	default:
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 56a74707c617..85892b35cff7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -996,7 +996,8 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY &&
 			optname != IPV6_XFRM_POLICY)
-		err = nf_setsockopt(sk, PF_INET6, optname, optval, optlen);
+		err = nf_setsockopt(sk, PF_INET6, optname, USER_SOCKPTR(optval),
+				    optlen);
 #endif
 	return err;
 }
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index a787aba30e2d..1d52957a413f 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1119,7 +1119,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 }
 
 static int
-do_replace(struct net *net, const void __user *user, unsigned int len)
+do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct ip6t_replace tmp;
@@ -1127,7 +1127,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 	void *loc_cpu_entry;
 	struct ip6t_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -1143,8 +1143,8 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
-			   tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1493,7 +1493,7 @@ out_unlock:
 }
 
 static int
-compat_do_replace(struct net *net, void __user *user, unsigned int len)
+compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 {
 	int ret;
 	struct compat_ip6t_replace tmp;
@@ -1501,7 +1501,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 	void *loc_cpu_entry;
 	struct ip6t_entry *iter;
 
-	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
+	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
 	/* overflow check */
@@ -1517,8 +1517,8 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
-			   tmp.size) != 0) {
+	sockptr_advance(arg, sizeof(tmp));
+	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1619,7 +1619,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
 #endif
 
 static int
-do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
+do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len)
 {
 	int ret;
 
@@ -1630,14 +1630,14 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	case IP6T_SO_SET_REPLACE:
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
-			ret = compat_do_replace(sock_net(sk), user, len);
+			ret = compat_do_replace(sock_net(sk), arg, len);
 		else
 #endif
-			ret = do_replace(sock_net(sk), user, len);
+			ret = do_replace(sock_net(sk), arg, len);
 		break;
 
 	case IP6T_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(sock_net(sk), USER_SOCKPTR(user), len);
+		ret = do_add_counters(sock_net(sk), arg, len);
 		break;
 
 	default:
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 4af83f466dfc..bcac316addab 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2434,7 +2434,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 }
 
 static int
-do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
+do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
 {
 	struct net *net = sock_net(sk);
 	int ret;
@@ -2458,7 +2458,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		return -EINVAL;
 	}
 
-	if (copy_from_user(arg, user, len) != 0)
+	if (copy_from_sockptr(arg, ptr, len) != 0)
 		return -EFAULT;
 
 	/* Handle daemons since they have another lock */
diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c
index 90469b1f628a..34afcd03b6f6 100644
--- a/net/netfilter/nf_sockopt.c
+++ b/net/netfilter/nf_sockopt.c
@@ -89,7 +89,7 @@ out:
 	return ops;
 }
 
-int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt,
+int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, sockptr_t opt,
 		  unsigned int len)
 {
 	struct nf_sockopt_ops *ops;
-- 
cgit v1.2.3


From b03afaa82ece13b2a008f0e3a7127bead578e3e6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:55 +0200
Subject: bpfilter: switch bpfilter_ip_set_sockopt to sockptr_t

This is mostly to prepare for cleaning up the callers, as bpfilter by
design can't handle kernel pointers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpfilter.h     | 6 +++---
 net/bpfilter/bpfilter_kern.c | 6 +++---
 net/ipv4/bpfilter/sockopt.c  | 8 ++++----
 net/ipv4/ip_sockglue.c       | 3 ++-
 4 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index 9b114c718a76..2ae3c8e1d83c 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -4,9 +4,10 @@
 
 #include <uapi/linux/bpfilter.h>
 #include <linux/usermode_driver.h>
+#include <linux/sockptr.h>
 
 struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
 			    unsigned int optlen);
 int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
 			    int __user *optlen);
@@ -16,8 +17,7 @@ struct bpfilter_umh_ops {
 	struct umd_info info;
 	/* since ip_getsockopt() can run in parallel, serialize access to umh */
 	struct mutex lock;
-	int (*sockopt)(struct sock *sk, int optname,
-		       char __user *optval,
+	int (*sockopt)(struct sock *sk, int optname, sockptr_t optval,
 		       unsigned int optlen, bool is_set);
 	int (*start)(void);
 };
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 00540457e5f4..f580c3344cb3 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -60,17 +60,17 @@ stop:
 }
 
 static int bpfilter_process_sockopt(struct sock *sk, int optname,
-				    char __user *optval, unsigned int optlen,
+				    sockptr_t optval, unsigned int optlen,
 				    bool is_set)
 {
 	struct mbox_request req = {
 		.is_set		= is_set,
 		.pid		= current->pid,
 		.cmd		= optname,
-		.addr		= (uintptr_t)optval,
+		.addr		= (uintptr_t)optval.user,
 		.len		= optlen,
 	};
-	if (uaccess_kernel()) {
+	if (uaccess_kernel() || sockptr_is_kernel(optval)) {
 		pr_err("kernel access not supported\n");
 		return -EFAULT;
 	}
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 9063c6767d34..1b34cb9a7708 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -21,8 +21,7 @@ void bpfilter_umh_cleanup(struct umd_info *info)
 }
 EXPORT_SYMBOL_GPL(bpfilter_umh_cleanup);
 
-static int bpfilter_mbox_request(struct sock *sk, int optname,
-				 char __user *optval,
+static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
 				 unsigned int optlen, bool is_set)
 {
 	int err;
@@ -52,7 +51,7 @@ out:
 	return err;
 }
 
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
 			    unsigned int optlen)
 {
 	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
@@ -66,7 +65,8 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
-	return bpfilter_mbox_request(sk, optname, optval, len, false);
+	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
+				     false);
 }
 
 static int __init bpfilter_sockopt_init(void)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 42befbf12846..36f746e01741 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1414,7 +1414,8 @@ int ip_setsockopt(struct sock *sk, int level,
 #if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
 	    optname < BPFILTER_IPT_SET_MAX)
-		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
+		err = bpfilter_ip_set_sockopt(sk, optname, USER_SOCKPTR(optval),
+					      optlen);
 #endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
-- 
cgit v1.2.3


From 01ccb5b48f08f59ca3746d59221f4990aec1b194 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:56 +0200
Subject: net/ipv4: switch ip_mroute_setsockopt to sockptr_t

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute.h |  5 +++--
 net/ipv4/ip_sockglue.c |  3 ++-
 net/ipv4/ipmr.c        | 14 +++++++-------
 3 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 9a36fad9e068..6cbbfe94348c 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -8,6 +8,7 @@
 #include <net/fib_notifier.h>
 #include <uapi/linux/mroute.h>
 #include <linux/mroute_base.h>
+#include <linux/sockptr.h>
 
 #ifdef CONFIG_IP_MROUTE
 static inline int ip_mroute_opt(int opt)
@@ -15,7 +16,7 @@ static inline int ip_mroute_opt(int opt)
 	return opt >= MRT_BASE && opt <= MRT_MAX;
 }
 
-int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
+int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
 int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
 int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
 int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
@@ -23,7 +24,7 @@ int ip_mr_init(void);
 bool ipmr_rule_default(const struct fib_rule *rule);
 #else
 static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
-				       char __user *optval, unsigned int optlen)
+				       sockptr_t optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 36f746e01741..ac495b0cff8f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -925,7 +925,8 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	if (optname == IP_ROUTER_ALERT)
 		return ip_ra_control(sk, val ? 1 : 0, NULL);
 	if (ip_mroute_opt(optname))
-		return ip_mroute_setsockopt(sk, optname, optval, optlen);
+		return ip_mroute_setsockopt(sk, optname, USER_SOCKPTR(optval),
+					    optlen);
 
 	err = 0;
 	if (needs_rtnl)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 678639c01e48..cdf3a40f9ff5 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1341,7 +1341,7 @@ static void mrtsock_destruct(struct sock *sk)
  * MOSPF/PIM router set up we can clean this up.
  */
 
-int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
+int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 			 unsigned int optlen)
 {
 	struct net *net = sock_net(sk);
@@ -1413,7 +1413,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (copy_from_user(&vif, optval, sizeof(vif))) {
+		if (copy_from_sockptr(&vif, optval, sizeof(vif))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1441,7 +1441,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (copy_from_user(&mfc, optval, sizeof(mfc))) {
+		if (copy_from_sockptr(&val, optval, sizeof(val))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1459,7 +1459,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (get_user(val, (int __user *)optval)) {
+		if (copy_from_sockptr(&val, optval, sizeof(val))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1471,7 +1471,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (get_user(val, (int __user *)optval)) {
+		if (copy_from_sockptr(&val, optval, sizeof(val))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1486,7 +1486,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (get_user(val, (int __user *)optval)) {
+		if (copy_from_sockptr(&val, optval, sizeof(val))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1508,7 +1508,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			ret = -EINVAL;
 			break;
 		}
-		if (get_user(uval, (u32 __user *)optval)) {
+		if (copy_from_sockptr(&uval, optval, sizeof(uval))) {
 			ret = -EFAULT;
 			break;
 		}
-- 
cgit v1.2.3


From b43c6153132c92745317f92174af84f57b160b76 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:08:59 +0200
Subject: net/ipv6: switch ip6_mroute_setsockopt to sockptr_t

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute6.h  |  8 ++++----
 net/ipv6/ip6mr.c         | 17 +++++++++--------
 net/ipv6/ipv6_sockglue.c |  3 ++-
 3 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index c4a45859f586..bc351a85ce9b 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -8,6 +8,7 @@
 #include <net/net_namespace.h>
 #include <uapi/linux/mroute6.h>
 #include <linux/mroute_base.h>
+#include <linux/sockptr.h>
 #include <net/fib_rules.h>
 
 #ifdef CONFIG_IPV6_MROUTE
@@ -25,7 +26,7 @@ static inline int ip6_mroute_opt(int opt)
 struct sock;
 
 #ifdef CONFIG_IPV6_MROUTE
-extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
+extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
 extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
 extern int ip6_mr_input(struct sk_buff *skb);
 extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg);
@@ -33,9 +34,8 @@ extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *ar
 extern int ip6_mr_init(void);
 extern void ip6_mr_cleanup(void);
 #else
-static inline
-int ip6_mroute_setsockopt(struct sock *sock,
-			  int optname, char __user *optval, unsigned int optlen)
+static inline int ip6_mroute_setsockopt(struct sock *sock, int optname,
+		sockptr_t optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 1f4d20e97c07..06b0d2c329b9 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1629,7 +1629,8 @@ EXPORT_SYMBOL(mroute6_is_socket);
  *	MOSPF/PIM router set up we can clean this up.
  */
 
-int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen)
+int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
+			  unsigned int optlen)
 {
 	int ret, parent = 0;
 	struct mif6ctl vif;
@@ -1665,7 +1666,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	case MRT6_ADD_MIF:
 		if (optlen < sizeof(vif))
 			return -EINVAL;
-		if (copy_from_user(&vif, optval, sizeof(vif)))
+		if (copy_from_sockptr(&vif, optval, sizeof(vif)))
 			return -EFAULT;
 		if (vif.mif6c_mifi >= MAXMIFS)
 			return -ENFILE;
@@ -1678,7 +1679,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	case MRT6_DEL_MIF:
 		if (optlen < sizeof(mifi_t))
 			return -EINVAL;
-		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
+		if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
 		ret = mif6_delete(mrt, mifi, 0, NULL);
@@ -1697,7 +1698,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	case MRT6_DEL_MFC_PROXY:
 		if (optlen < sizeof(mfc))
 			return -EINVAL;
-		if (copy_from_user(&mfc, optval, sizeof(mfc)))
+		if (copy_from_sockptr(&mfc, optval, sizeof(mfc)))
 			return -EFAULT;
 		if (parent == 0)
 			parent = mfc.mf6cc_parent;
@@ -1718,7 +1719,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 		if (optlen != sizeof(flags))
 			return -EINVAL;
-		if (get_user(flags, (int __user *)optval))
+		if (copy_from_sockptr(&flags, optval, sizeof(flags)))
 			return -EFAULT;
 		rtnl_lock();
 		mroute_clean_tables(mrt, flags);
@@ -1735,7 +1736,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 		if (optlen != sizeof(v))
 			return -EINVAL;
-		if (get_user(v, (int __user *)optval))
+		if (copy_from_sockptr(&v, optval, sizeof(v)))
 			return -EFAULT;
 		mrt->mroute_do_assert = v;
 		return 0;
@@ -1748,7 +1749,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 		if (optlen != sizeof(v))
 			return -EINVAL;
-		if (get_user(v, (int __user *)optval))
+		if (copy_from_sockptr(&v, optval, sizeof(v)))
 			return -EFAULT;
 		v = !!v;
 		rtnl_lock();
@@ -1769,7 +1770,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 		if (optlen != sizeof(u32))
 			return -EINVAL;
-		if (get_user(v, (u32 __user *)optval))
+		if (copy_from_sockptr(&v, optval, sizeof(v)))
 			return -EFAULT;
 		/* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */
 		if (v != RT_TABLE_DEFAULT && v >= 100000000)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 85892b35cff7..119dfaf5f4bb 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -337,7 +337,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	valbool = (val != 0);
 
 	if (ip6_mroute_opt(optname))
-		return ip6_mroute_setsockopt(sk, optname, optval, optlen);
+		return ip6_mroute_setsockopt(sk, optname, USER_SOCKPTR(optval),
+					     optlen);
 
 	if (needs_rtnl)
 		rtnl_lock();
-- 
cgit v1.2.3


From a7b75c5a8c41445f33efb663887ff5f5c3b4454b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:09:07 +0200
Subject: net: pass a sockptr_t into ->setsockopt

Rework the remaining setsockopt code to pass a sockptr_t instead of a
plain user pointer.  This removes the last remaining set_fs(KERNEL_DS)
outside of architecture specific code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org> [ieee802154]
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c                           |  7 +++---
 drivers/crypto/chelsio/chtls/chtls_main.c | 18 +++++++-------
 drivers/isdn/mISDN/socket.c               |  4 ++--
 include/linux/net.h                       |  4 +++-
 include/net/inet_connection_sock.h        |  3 ++-
 include/net/ip.h                          |  2 +-
 include/net/ipv6.h                        |  4 ++--
 include/net/sctp/structs.h                |  2 +-
 include/net/sock.h                        |  4 ++--
 include/net/tcp.h                         |  4 ++--
 net/atm/common.c                          |  6 ++---
 net/atm/common.h                          |  2 +-
 net/atm/pvc.c                             |  2 +-
 net/atm/svc.c                             |  6 ++---
 net/ax25/af_ax25.c                        |  6 ++---
 net/bluetooth/hci_sock.c                  |  8 +++----
 net/bluetooth/l2cap_sock.c                | 22 ++++++++---------
 net/bluetooth/rfcomm/sock.c               | 12 ++++++----
 net/bluetooth/sco.c                       |  6 ++---
 net/caif/caif_socket.c                    |  8 +++----
 net/can/j1939/socket.c                    | 12 +++++-----
 net/can/raw.c                             | 16 ++++++-------
 net/core/sock.c                           |  2 +-
 net/dccp/dccp.h                           |  2 +-
 net/dccp/proto.c                          | 20 ++++++++--------
 net/decnet/af_decnet.c                    | 16 +++++++------
 net/ieee802154/socket.c                   |  6 ++---
 net/ipv4/ip_sockglue.c                    | 13 ++++-------
 net/ipv4/raw.c                            |  8 +++----
 net/ipv4/tcp.c                            |  5 ++--
 net/ipv4/udp.c                            |  6 ++---
 net/ipv4/udp_impl.h                       |  4 ++--
 net/ipv6/ipv6_sockglue.c                  | 10 ++++----
 net/ipv6/raw.c                            | 10 ++++----
 net/ipv6/udp.c                            |  6 ++---
 net/ipv6/udp_impl.h                       |  4 ++--
 net/iucv/af_iucv.c                        |  4 ++--
 net/kcm/kcmsock.c                         |  6 ++---
 net/l2tp/l2tp_ppp.c                       |  4 ++--
 net/llc/af_llc.c                          |  4 ++--
 net/mptcp/protocol.c                      | 12 ++++------
 net/netlink/af_netlink.c                  |  4 ++--
 net/netrom/af_netrom.c                    |  4 ++--
 net/nfc/llcp_sock.c                       |  6 ++---
 net/packet/af_packet.c                    | 39 ++++++++++++++++---------------
 net/phonet/pep.c                          |  4 ++--
 net/rds/af_rds.c                          | 30 +++++++++++-------------
 net/rds/rdma.c                            | 14 +++++------
 net/rds/rds.h                             |  6 ++---
 net/rose/af_rose.c                        |  4 ++--
 net/rxrpc/af_rxrpc.c                      |  8 +++----
 net/rxrpc/ar-internal.h                   |  4 ++--
 net/rxrpc/key.c                           |  9 ++++---
 net/sctp/socket.c                         |  4 ++--
 net/smc/af_smc.c                          |  4 ++--
 net/socket.c                              | 23 ++++++------------
 net/tipc/socket.c                         |  8 +++----
 net/tls/tls_main.c                        | 17 +++++++-------
 net/vmw_vsock/af_vsock.c                  |  4 ++--
 net/x25/af_x25.c                          |  4 ++--
 net/xdp/xsk.c                             |  8 +++----
 61 files changed, 246 insertions(+), 258 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 29f71428520b..892242a42c3e 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -197,8 +197,7 @@ unlock:
 	return err;
 }
 
-static int alg_setkey(struct sock *sk, char __user *ukey,
-		      unsigned int keylen)
+static int alg_setkey(struct sock *sk, sockptr_t ukey, unsigned int keylen)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type = ask->type;
@@ -210,7 +209,7 @@ static int alg_setkey(struct sock *sk, char __user *ukey,
 		return -ENOMEM;
 
 	err = -EFAULT;
-	if (copy_from_user(key, ukey, keylen))
+	if (copy_from_sockptr(key, ukey, keylen))
 		goto out;
 
 	err = type->setkey(ask->private, key, keylen);
@@ -222,7 +221,7 @@ out:
 }
 
 static int alg_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index d98b89d0fa6e..c3058dcdb33c 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -488,7 +488,7 @@ static int chtls_getsockopt(struct sock *sk, int level, int optname,
 }
 
 static int do_chtls_setsockopt(struct sock *sk, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct tls_crypto_info *crypto_info, tmp_crypto_info;
 	struct chtls_sock *csk;
@@ -498,12 +498,12 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 
 	csk = rcu_dereference_sk_user_data(sk);
 
-	if (!optval || optlen < sizeof(*crypto_info)) {
+	if (sockptr_is_null(optval) || optlen < sizeof(*crypto_info)) {
 		rc = -EINVAL;
 		goto out;
 	}
 
-	rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info));
+	rc = copy_from_sockptr(&tmp_crypto_info, optval, sizeof(*crypto_info));
 	if (rc) {
 		rc = -EFAULT;
 		goto out;
@@ -525,8 +525,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 		/* Obtain version and type from previous copy */
 		crypto_info[0] = tmp_crypto_info;
 		/* Now copy the following data */
-		rc = copy_from_user((char *)crypto_info + sizeof(*crypto_info),
-				optval + sizeof(*crypto_info),
+		sockptr_advance(optval, sizeof(*crypto_info));
+		rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info),
+				optval,
 				sizeof(struct tls12_crypto_info_aes_gcm_128)
 				- sizeof(*crypto_info));
 
@@ -541,8 +542,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 	}
 	case TLS_CIPHER_AES_GCM_256: {
 		crypto_info[0] = tmp_crypto_info;
-		rc = copy_from_user((char *)crypto_info + sizeof(*crypto_info),
-				    optval + sizeof(*crypto_info),
+		sockptr_advance(optval, sizeof(*crypto_info));
+		rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info),
+				    optval,
 				sizeof(struct tls12_crypto_info_aes_gcm_256)
 				- sizeof(*crypto_info));
 
@@ -565,7 +567,7 @@ out:
 }
 
 static int chtls_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, unsigned int optlen)
+			    sockptr_t optval, unsigned int optlen)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 1b2b91479107..2835daae9e9f 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -401,7 +401,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 }
 
 static int data_sock_setsockopt(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int len)
+				sockptr_t optval, unsigned int len)
 {
 	struct sock *sk = sock->sk;
 	int err = 0, opt = 0;
@@ -414,7 +414,7 @@ static int data_sock_setsockopt(struct socket *sock, int level, int optname,
 
 	switch (optname) {
 	case MISDN_TIME_STAMP:
-		if (get_user(opt, (int __user *)optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(int))) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/include/linux/net.h b/include/linux/net.h
index 858ff1d98154..d48ff1180879 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/once.h>
 #include <linux/fs.h>
+#include <linux/sockptr.h>
 
 #include <uapi/linux/net.h>
 
@@ -162,7 +163,8 @@ struct proto_ops {
 	int		(*listen)    (struct socket *sock, int len);
 	int		(*shutdown)  (struct socket *sock, int flags);
 	int		(*setsockopt)(struct socket *sock, int level,
-				      int optname, char __user *optval, unsigned int optlen);
+				      int optname, sockptr_t optval,
+				      unsigned int optlen);
 	int		(*getsockopt)(struct socket *sock, int level,
 				      int optname, char __user *optval, int __user *optlen);
 	void		(*show_fdinfo)(struct seq_file *m, struct socket *sock);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 157c60cca0ca..1e209ce7d1bd 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -16,6 +16,7 @@
 #include <linux/timer.h>
 #include <linux/poll.h>
 #include <linux/kernel.h>
+#include <linux/sockptr.h>
 
 #include <net/inet_sock.h>
 #include <net/request_sock.h>
@@ -45,7 +46,7 @@ struct inet_connection_sock_af_ops {
 	u16	    net_frag_header_len;
 	u16	    sockaddr_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
-				  char __user *optval, unsigned int optlen);
+				  sockptr_t optval, unsigned int optlen);
 	int	    (*getsockopt)(struct sock *sk, int level, int optname,
 				  char __user *optval, int __user *optlen);
 	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
diff --git a/include/net/ip.h b/include/net/ip.h
index d66ad3a95220..b09c48d862cc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -722,7 +722,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
-int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
+int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		  int __user *optlen);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4c9d89b5d732..bd1f396cc9c7 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1084,8 +1084,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
  *	socket options (ipv6_sockglue.c)
  */
 
-int ipv6_setsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, unsigned int optlen);
+int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		    unsigned int optlen);
 int ipv6_getsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, int __user *optlen);
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 233bbf7df5d6..b33f1aefad09 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -431,7 +431,7 @@ struct sctp_af {
 	int		(*setsockopt)	(struct sock *sk,
 					 int level,
 					 int optname,
-					 char __user *optval,
+					 sockptr_t optval,
 					 unsigned int optlen);
 	int		(*getsockopt)	(struct sock *sk,
 					 int level,
diff --git a/include/net/sock.h b/include/net/sock.h
index bfb2fe2fc368..2cc3ba667908 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1141,7 +1141,7 @@ struct proto {
 	void			(*destroy)(struct sock *sk);
 	void			(*shutdown)(struct sock *sk, int how);
 	int			(*setsockopt)(struct sock *sk, int level,
-					int optname, char __user *optval,
+					int optname, sockptr_t optval,
 					unsigned int optlen);
 	int			(*getsockopt)(struct sock *sk, int level,
 					int optname, char __user *optval,
@@ -1734,7 +1734,7 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname,
 int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			int flags);
 int sock_common_setsockopt(struct socket *sock, int level, int optname,
-				  char __user *optval, unsigned int optlen);
+			   sockptr_t optval, unsigned int optlen);
 
 void sk_common_release(struct sock *sk);
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e3c8e1d82021..e0c35d56091f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -399,8 +399,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
-int tcp_setsockopt(struct sock *sk, int level, int optname,
-		   char __user *optval, unsigned int optlen);
+int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);
 void tcp_syn_ack_timeout(const struct request_sock *req);
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
diff --git a/net/atm/common.c b/net/atm/common.c
index 9b28f1fb3c69..84367b844b14 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -745,7 +745,7 @@ static int check_qos(const struct atm_qos *qos)
 }
 
 int vcc_setsockopt(struct socket *sock, int level, int optname,
-		   char __user *optval, unsigned int optlen)
+		   sockptr_t optval, unsigned int optlen)
 {
 	struct atm_vcc *vcc;
 	unsigned long value;
@@ -760,7 +760,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
 	{
 		struct atm_qos qos;
 
-		if (copy_from_user(&qos, optval, sizeof(qos)))
+		if (copy_from_sockptr(&qos, optval, sizeof(qos)))
 			return -EFAULT;
 		error = check_qos(&qos);
 		if (error)
@@ -774,7 +774,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
 		return 0;
 	}
 	case SO_SETCLP:
-		if (get_user(value, (unsigned long __user *)optval))
+		if (copy_from_sockptr(&value, optval, sizeof(value)))
 			return -EFAULT;
 		if (value)
 			vcc->atm_options |= ATM_ATMOPT_CLP;
diff --git a/net/atm/common.h b/net/atm/common.h
index 5850649068bb..a1e56e8de698 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -21,7 +21,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
 int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_setsockopt(struct socket *sock, int level, int optname,
-		   char __user *optval, unsigned int optlen);
+		   sockptr_t optval, unsigned int optlen);
 int vcc_getsockopt(struct socket *sock, int level, int optname,
 		   char __user *optval, int __user *optlen);
 void vcc_process_recv_queue(struct atm_vcc *vcc);
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 02bd2a436bdf..53e7d3f39e26 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -63,7 +63,7 @@ static int pvc_connect(struct socket *sock, struct sockaddr *sockaddr,
 }
 
 static int pvc_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	int error;
diff --git a/net/atm/svc.c b/net/atm/svc.c
index ba144d035e3d..4a02bcaad279 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -451,7 +451,7 @@ int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos)
 }
 
 static int svc_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct atm_vcc *vcc = ATM_SD(sock);
@@ -464,7 +464,7 @@ static int svc_setsockopt(struct socket *sock, int level, int optname,
 			error = -EINVAL;
 			goto out;
 		}
-		if (copy_from_user(&vcc->sap, optval, optlen)) {
+		if (copy_from_sockptr(&vcc->sap, optval, optlen)) {
 			error = -EFAULT;
 			goto out;
 		}
@@ -475,7 +475,7 @@ static int svc_setsockopt(struct socket *sock, int level, int optname,
 			error = -EINVAL;
 			goto out;
 		}
-		if (get_user(value, (int __user *)optval)) {
+		if (copy_from_sockptr(&value, optval, sizeof(int))) {
 			error = -EFAULT;
 			goto out;
 		}
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fd91cd34f25e..17bf31a89692 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -528,7 +528,7 @@ ax25_cb *ax25_create_cb(void)
  */
 
 static int ax25_setsockopt(struct socket *sock, int level, int optname,
-	char __user *optval, unsigned int optlen)
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	ax25_cb *ax25;
@@ -543,7 +543,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(unsigned int))
 		return -EINVAL;
 
-	if (get_user(opt, (unsigned int __user *)optval))
+	if (copy_from_sockptr(&opt, optval, sizeof(unsigned int)))
 		return -EFAULT;
 
 	lock_sock(sk);
@@ -640,7 +640,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 
 		memset(devname, 0, sizeof(devname));
 
-		if (copy_from_user(devname, optval, optlen)) {
+		if (copy_from_sockptr(devname, optval, optlen)) {
 			res = -EFAULT;
 			break;
 		}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index caf38a8ea6a8..d5eff27d5b1e 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1842,7 +1842,7 @@ drop:
 }
 
 static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
-			       char __user *optval, unsigned int len)
+			       sockptr_t optval, unsigned int len)
 {
 	struct hci_ufilter uf = { .opcode = 0 };
 	struct sock *sk = sock->sk;
@@ -1862,7 +1862,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
 
 	switch (optname) {
 	case HCI_DATA_DIR:
-		if (get_user(opt, (int __user *)optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
 			err = -EFAULT;
 			break;
 		}
@@ -1874,7 +1874,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case HCI_TIME_STAMP:
-		if (get_user(opt, (int __user *)optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
 			err = -EFAULT;
 			break;
 		}
@@ -1896,7 +1896,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
 		}
 
 		len = min_t(unsigned int, len, sizeof(uf));
-		if (copy_from_user(&uf, optval, len)) {
+		if (copy_from_sockptr(&uf, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a995d2c51fa7..a3d104123f38 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -703,7 +703,7 @@ static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu)
 }
 
 static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
-				     char __user *optval, unsigned int optlen)
+				     sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
@@ -736,7 +736,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
 		opts.txwin_size = chan->tx_win;
 
 		len = min_t(unsigned int, sizeof(opts), optlen);
-		if (copy_from_user((char *) &opts, optval, len)) {
+		if (copy_from_sockptr(&opts, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
@@ -782,7 +782,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
 		break;
 
 	case L2CAP_LM:
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -859,7 +859,7 @@ static int l2cap_set_mode(struct l2cap_chan *chan, u8 mode)
 }
 
 static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
-				 char __user *optval, unsigned int optlen)
+				 sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
@@ -891,7 +891,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		sec.level = BT_SECURITY_LOW;
 
 		len = min_t(unsigned int, sizeof(sec), optlen);
-		if (copy_from_user((char *) &sec, optval, len)) {
+		if (copy_from_sockptr(&sec, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
@@ -939,7 +939,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -954,7 +954,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_FLUSHABLE:
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -990,7 +990,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		pwr.force_active = BT_POWER_FORCE_ACTIVE_ON;
 
 		len = min_t(unsigned int, sizeof(pwr), optlen);
-		if (copy_from_user((char *) &pwr, optval, len)) {
+		if (copy_from_sockptr(&pwr, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
@@ -1002,7 +1002,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_CHANNEL_POLICY:
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -1050,7 +1050,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u16 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u16))) {
 			err = -EFAULT;
 			break;
 		}
@@ -1081,7 +1081,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u8 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u8))) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index df14eebe80da..dba4ea0e1b0d 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -644,7 +644,8 @@ static int rfcomm_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	return len;
 }
 
-static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen)
+static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname,
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	int err = 0;
@@ -656,7 +657,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u
 
 	switch (optname) {
 	case RFCOMM_LM:
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -685,7 +686,8 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u
 	return err;
 }
 
-static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
+static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname,
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct bt_security sec;
@@ -713,7 +715,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c
 		sec.level = BT_SECURITY_LOW;
 
 		len = min_t(unsigned int, sizeof(sec), optlen);
-		if (copy_from_user((char *) &sec, optval, len)) {
+		if (copy_from_sockptr(&sec, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
@@ -732,7 +734,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index c8c3d38cdc7b..37260baf7150 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -791,7 +791,7 @@ static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 }
 
 static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	int len, err = 0;
@@ -810,7 +810,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -831,7 +831,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
 		voice.setting = sco_pi(sk)->setting;
 
 		len = min_t(unsigned int, sizeof(voice), optlen);
-		if (copy_from_user((char *)&voice, optval, len)) {
+		if (copy_from_sockptr(&voice, optval, len)) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index b94ecd931002..3ad0a1df6712 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -669,8 +669,8 @@ out_err:
 	return sent ? : err;
 }
 
-static int setsockopt(struct socket *sock,
-		      int lvl, int opt, char __user *ov, unsigned int ol)
+static int setsockopt(struct socket *sock, int lvl, int opt, sockptr_t ov,
+		unsigned int ol)
 {
 	struct sock *sk = sock->sk;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -685,7 +685,7 @@ static int setsockopt(struct socket *sock,
 			return -EINVAL;
 		if (lvl != SOL_CAIF)
 			goto bad_sol;
-		if (copy_from_user(&linksel, ov, sizeof(int)))
+		if (copy_from_sockptr(&linksel, ov, sizeof(int)))
 			return -EINVAL;
 		lock_sock(&(cf_sk->sk));
 		cf_sk->conn_req.link_selector = linksel;
@@ -699,7 +699,7 @@ static int setsockopt(struct socket *sock,
 			return -ENOPROTOOPT;
 		lock_sock(&(cf_sk->sk));
 		if (ol > sizeof(cf_sk->conn_req.param.data) ||
-			copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) {
+		    copy_from_sockptr(&cf_sk->conn_req.param.data, ov, ol)) {
 			release_sock(&cf_sk->sk);
 			return -EINVAL;
 		}
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index f7587428febd..78ff9b3f1d40 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -627,14 +627,14 @@ static int j1939_sk_release(struct socket *sock)
 	return 0;
 }
 
-static int j1939_sk_setsockopt_flag(struct j1939_sock *jsk, char __user *optval,
+static int j1939_sk_setsockopt_flag(struct j1939_sock *jsk, sockptr_t optval,
 				    unsigned int optlen, int flag)
 {
 	int tmp;
 
 	if (optlen != sizeof(tmp))
 		return -EINVAL;
-	if (copy_from_user(&tmp, optval, optlen))
+	if (copy_from_sockptr(&tmp, optval, optlen))
 		return -EFAULT;
 	lock_sock(&jsk->sk);
 	if (tmp)
@@ -646,7 +646,7 @@ static int j1939_sk_setsockopt_flag(struct j1939_sock *jsk, char __user *optval,
 }
 
 static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct j1939_sock *jsk = j1939_sk(sk);
@@ -658,7 +658,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
 
 	switch (optname) {
 	case SO_J1939_FILTER:
-		if (optval) {
+		if (!sockptr_is_null(optval)) {
 			struct j1939_filter *f;
 			int c;
 
@@ -670,7 +670,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
 				return -EINVAL;
 
 			count = optlen / sizeof(*filters);
-			filters = memdup_user(optval, optlen);
+			filters = memdup_sockptr(optval, optlen);
 			if (IS_ERR(filters))
 				return PTR_ERR(filters);
 
@@ -703,7 +703,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
 	case SO_J1939_SEND_PRIO:
 		if (optlen != sizeof(tmp))
 			return -EINVAL;
-		if (copy_from_user(&tmp, optval, optlen))
+		if (copy_from_sockptr(&tmp, optval, optlen))
 			return -EFAULT;
 		if (tmp < 0 || tmp > 7)
 			return -EDOM;
diff --git a/net/can/raw.c b/net/can/raw.c
index 59c039d73c6d..94a9405658dc 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -485,7 +485,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 
 static int raw_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro = raw_sk(sk);
@@ -511,11 +511,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 
 		if (count > 1) {
 			/* filter does not fit into dfilter => alloc space */
-			filter = memdup_user(optval, optlen);
+			filter = memdup_sockptr(optval, optlen);
 			if (IS_ERR(filter))
 				return PTR_ERR(filter);
 		} else if (count == 1) {
-			if (copy_from_user(&sfilter, optval, sizeof(sfilter)))
+			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
 				return -EFAULT;
 		}
 
@@ -568,7 +568,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(err_mask))
 			return -EINVAL;
 
-		if (copy_from_user(&err_mask, optval, optlen))
+		if (copy_from_sockptr(&err_mask, optval, optlen))
 			return -EFAULT;
 
 		err_mask &= CAN_ERR_MASK;
@@ -607,7 +607,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->loopback))
 			return -EINVAL;
 
-		if (copy_from_user(&ro->loopback, optval, optlen))
+		if (copy_from_sockptr(&ro->loopback, optval, optlen))
 			return -EFAULT;
 
 		break;
@@ -616,7 +616,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->recv_own_msgs))
 			return -EINVAL;
 
-		if (copy_from_user(&ro->recv_own_msgs, optval, optlen))
+		if (copy_from_sockptr(&ro->recv_own_msgs, optval, optlen))
 			return -EFAULT;
 
 		break;
@@ -625,7 +625,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->fd_frames))
 			return -EINVAL;
 
-		if (copy_from_user(&ro->fd_frames, optval, optlen))
+		if (copy_from_sockptr(&ro->fd_frames, optval, optlen))
 			return -EFAULT;
 
 		break;
@@ -634,7 +634,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->join_filters))
 			return -EINVAL;
 
-		if (copy_from_user(&ro->join_filters, optval, optlen))
+		if (copy_from_sockptr(&ro->join_filters, optval, optlen))
 			return -EFAULT;
 
 		break;
diff --git a/net/core/sock.c b/net/core/sock.c
index 1444d7d53ba2..2c5dd1397775 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3211,7 +3211,7 @@ EXPORT_SYMBOL(sock_common_recvmsg);
  *	Set socket options on an inet socket.
  */
 int sock_common_setsockopt(struct socket *sock, int level, int optname,
-			   char __user *optval, unsigned int optlen)
+			   sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 434eea91b767..9cc9d1ee6cdb 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -295,7 +295,7 @@ int dccp_disconnect(struct sock *sk, int flags);
 int dccp_getsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, int __user *optlen);
 int dccp_setsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, unsigned int optlen);
+		    sockptr_t optval, unsigned int optlen);
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9e453611107f..2e9e8449698f 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -411,7 +411,7 @@ out:
 EXPORT_SYMBOL_GPL(dccp_ioctl);
 
 static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
-				   char __user *optval, unsigned int optlen)
+				   sockptr_t optval, unsigned int optlen)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_service_list *sl = NULL;
@@ -426,9 +426,9 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
 			return -ENOMEM;
 
 		sl->dccpsl_nr = optlen / sizeof(u32) - 1;
-		if (copy_from_user(sl->dccpsl_list,
-				   optval + sizeof(service),
-				   optlen - sizeof(service)) ||
+		sockptr_advance(optval, sizeof(service));
+		if (copy_from_sockptr(sl->dccpsl_list, optval,
+				      optlen - sizeof(service)) ||
 		    dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
 			kfree(sl);
 			return -EFAULT;
@@ -482,7 +482,7 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
 }
 
 static int dccp_setsockopt_ccid(struct sock *sk, int type,
-				char __user *optval, unsigned int optlen)
+				sockptr_t optval, unsigned int optlen)
 {
 	u8 *val;
 	int rc = 0;
@@ -490,7 +490,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type,
 	if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
 		return -EINVAL;
 
-	val = memdup_user(optval, optlen);
+	val = memdup_sockptr(optval, optlen);
 	if (IS_ERR(val))
 		return PTR_ERR(val);
 
@@ -507,7 +507,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type,
 }
 
 static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
-		char __user *optval, unsigned int optlen)
+		sockptr_t optval, unsigned int optlen)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	int val, err = 0;
@@ -529,7 +529,7 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
 	if (optlen < (int)sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	if (optname == DCCP_SOCKOPT_SERVICE)
@@ -572,8 +572,8 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
 	return err;
 }
 
-int dccp_setsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, unsigned int optlen)
+int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		    unsigned int optlen)
 {
 	if (level != SOL_DCCP)
 		return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 7d51ab608fb3..3b53d766789d 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -150,7 +150,8 @@ static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE];
 static struct hlist_head dn_wild_sk;
 static atomic_long_t decnet_memory_allocated;
 
-static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags);
+static int __dn_setsockopt(struct socket *sock, int level, int optname,
+		sockptr_t optval, unsigned int optlen, int flags);
 static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags);
 
 static struct hlist_head *dn_find_list(struct sock *sk)
@@ -1320,7 +1321,8 @@ out:
 	return err;
 }
 
-static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
+static int dn_setsockopt(struct socket *sock, int level, int optname,
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	int err;
@@ -1332,14 +1334,14 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != DSO_LINKINFO &&
 	    optname != DSO_STREAM && optname != DSO_SEQPACKET)
-		err = nf_setsockopt(sk, PF_DECnet, optname,
-				    USER_SOCKPTR(optval), optlen);
+		err = nf_setsockopt(sk, PF_DECnet, optname, optval, optlen);
 #endif
 
 	return err;
 }
 
-static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, unsigned int optlen, int flags)
+static int __dn_setsockopt(struct socket *sock, int level, int optname,
+		sockptr_t optval, unsigned int optlen, int flags)
 {
 	struct	sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
@@ -1355,13 +1357,13 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us
 	} u;
 	int err;
 
-	if (optlen && !optval)
+	if (optlen && sockptr_is_null(optval))
 		return -EINVAL;
 
 	if (optlen > sizeof(u))
 		return -EINVAL;
 
-	if (copy_from_user(&u, optval, optlen))
+	if (copy_from_sockptr(&u, optval, optlen))
 		return -EFAULT;
 
 	switch (optname) {
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 94ae9662133e..a45a0401adc5 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -382,7 +382,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname,
 }
 
 static int raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	return -EOPNOTSUPP;
 }
@@ -872,7 +872,7 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname,
 }
 
 static int dgram_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, unsigned int optlen)
+			    sockptr_t optval, unsigned int optlen)
 {
 	struct dgram_sock *ro = dgram_sk(sk);
 	struct net *net = sock_net(sk);
@@ -882,7 +882,7 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	lock_sock(sk);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f7f1507b89fe..8dc027e54c5b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1401,21 +1401,19 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 }
 
-int ip_setsockopt(struct sock *sk, int level,
-		int optname, char __user *optval, unsigned int optlen)
+int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		unsigned int optlen)
 {
 	int err;
 
 	if (level != SOL_IP)
 		return -ENOPROTOOPT;
 
-	err = do_ip_setsockopt(sk, level, optname, USER_SOCKPTR(optval),
-			       optlen);
+	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
 #if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
 	    optname < BPFILTER_IPT_SET_MAX)
-		err = bpfilter_ip_set_sockopt(sk, optname, USER_SOCKPTR(optval),
-					      optlen);
+		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
 #endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
@@ -1423,8 +1421,7 @@ int ip_setsockopt(struct sock *sk, int level,
 			optname != IP_IPSEC_POLICY &&
 			optname != IP_XFRM_POLICY &&
 			!ip_mroute_opt(optname))
-		err = nf_setsockopt(sk, PF_INET, optname, USER_SOCKPTR(optval),
-				    optlen);
+		err = nf_setsockopt(sk, PF_INET, optname, optval, optlen);
 #endif
 	return err;
 }
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2a57d633b31e..6fd4330287c2 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -809,11 +809,11 @@ static int raw_sk_init(struct sock *sk)
 	return 0;
 }
 
-static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
+static int raw_seticmpfilter(struct sock *sk, sockptr_t optval, int optlen)
 {
 	if (optlen > sizeof(struct icmp_filter))
 		optlen = sizeof(struct icmp_filter);
-	if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
+	if (copy_from_sockptr(&raw_sk(sk)->filter, optval, optlen))
 		return -EFAULT;
 	return 0;
 }
@@ -838,7 +838,7 @@ out:	return ret;
 }
 
 static int do_raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			     sockptr_t optval, unsigned int optlen)
 {
 	if (optname == ICMP_FILTER) {
 		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
@@ -850,7 +850,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname,
 }
 
 static int raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	if (level != SOL_RAW)
 		return ip_setsockopt(sk, level, optname, optval, optlen);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 71cbc61c335f..27de9380ed14 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3323,7 +3323,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	return err;
 }
 
-int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
+int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -3331,8 +3331,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
 	if (level != SOL_TCP)
 		return icsk->icsk_af_ops->setsockopt(sk, level, optname,
 						     optval, optlen);
-	return do_tcp_setsockopt(sk, level, optname, USER_SOCKPTR(optval),
-				 optlen);
+	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
 }
 EXPORT_SYMBOL(tcp_setsockopt);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c6cb2d09dbc7..5a6a2f6d86b9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2703,12 +2703,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 }
 EXPORT_SYMBOL(udp_lib_setsockopt);
 
-int udp_setsockopt(struct sock *sk, int level, int optname,
-		   char __user *optval, unsigned int optlen)
+int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		   unsigned int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
 		return udp_lib_setsockopt(sk, level, optname,
-					  USER_SOCKPTR(optval), optlen,
+					  optval, optlen,
 					  udp_push_pending_frames);
 	return ip_setsockopt(sk, level, optname, optval, optlen);
 }
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index ab313702c87f..2878d8285caf 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -12,8 +12,8 @@ int __udp4_lib_err(struct sk_buff *, u32, struct udp_table *);
 int udp_v4_get_port(struct sock *sk, unsigned short snum);
 void udp_v4_rehash(struct sock *sk);
 
-int udp_setsockopt(struct sock *sk, int level, int optname,
-		   char __user *optval, unsigned int optlen);
+int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		   unsigned int optlen);
 int udp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index dcd000a5a9b1..d2282f5c9760 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -980,8 +980,8 @@ e_inval:
 	return -EINVAL;
 }
 
-int ipv6_setsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, unsigned int optlen)
+int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		    unsigned int optlen)
 {
 	int err;
 
@@ -991,14 +991,12 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
-	err = do_ipv6_setsockopt(sk, level, optname, USER_SOCKPTR(optval),
-				 optlen);
+	err = do_ipv6_setsockopt(sk, level, optname, optval, optlen);
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY &&
 			optname != IPV6_XFRM_POLICY)
-		err = nf_setsockopt(sk, PF_INET6, optname, USER_SOCKPTR(optval),
-				    optlen);
+		err = nf_setsockopt(sk, PF_INET6, optname, optval, optlen);
 #endif
 	return err;
 }
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 594e01ad670a..874f01cd7aec 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -972,13 +972,13 @@ do_confirm:
 }
 
 static int rawv6_seticmpfilter(struct sock *sk, int level, int optname,
-			       char __user *optval, int optlen)
+			       sockptr_t optval, int optlen)
 {
 	switch (optname) {
 	case ICMPV6_FILTER:
 		if (optlen > sizeof(struct icmp6_filter))
 			optlen = sizeof(struct icmp6_filter);
-		if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen))
+		if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen))
 			return -EFAULT;
 		return 0;
 	default:
@@ -1015,12 +1015,12 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname,
 
 
 static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct raw6_sock *rp = raw6_sk(sk);
 	int val;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
 	switch (optname) {
@@ -1062,7 +1062,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
 }
 
 static int rawv6_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			    sockptr_t optval, unsigned int optlen)
 {
 	switch (level) {
 	case SOL_RAW:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2df1e6c9d7cb..15818e18655d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1618,12 +1618,12 @@ void udpv6_destroy_sock(struct sock *sk)
 /*
  *	Socket option code for UDP
  */
-int udpv6_setsockopt(struct sock *sk, int level, int optname,
-		     char __user *optval, unsigned int optlen)
+int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		     unsigned int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
 		return udp_lib_setsockopt(sk, level, optname,
-					  USER_SOCKPTR(optval), optlen,
+					  optval, optlen,
 					  udp_v6_push_pending_frames);
 	return ipv6_setsockopt(sk, level, optname, optval, optlen);
 }
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 30dfb6f1b762..b2fcc46c1630 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -17,8 +17,8 @@ void udp_v6_rehash(struct sock *sk);
 
 int udpv6_getsockopt(struct sock *sk, int level, int optname,
 		     char __user *optval, int __user *optlen);
-int udpv6_setsockopt(struct sock *sk, int level, int optname,
-		     char __user *optval, unsigned int optlen);
+int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		     unsigned int optlen);
 int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
 int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		  int flags, int *addr_len);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ee0add15497d..6ee9851ac7c6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1494,7 +1494,7 @@ static int iucv_sock_release(struct socket *sock)
 
 /* getsockopt and setsockopt */
 static int iucv_sock_setsockopt(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int optlen)
+				sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
@@ -1507,7 +1507,7 @@ static int iucv_sock_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *) optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	rc = 0;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 56fac24a627a..56dad9565bc9 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1265,7 +1265,7 @@ static void kcm_recv_enable(struct kcm_sock *kcm)
 }
 
 static int kcm_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct kcm_sock *kcm = kcm_sk(sock->sk);
 	int val, valbool;
@@ -1277,8 +1277,8 @@ static int kcm_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *)optval))
-		return -EINVAL;
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
+		return -EFAULT;
 
 	valbool = val ? 1 : 0;
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index e58fe7e3b884..4389df66af35 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1242,7 +1242,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
  * session or the special tunnel type.
  */
 static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct l2tp_session *session;
@@ -1256,7 +1256,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	err = -ENOTCONN;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 6140a3e46c26..7180979114e4 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1053,7 +1053,7 @@ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd,
  *	Set various connection specific parameters.
  */
 static int llc_ui_setsockopt(struct socket *sock, int level, int optname,
-			     char __user *optval, unsigned int optlen)
+			     sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
@@ -1063,7 +1063,7 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname,
 	lock_sock(sk);
 	if (unlikely(level != SOL_LLC || optlen != sizeof(int)))
 		goto out;
-	rc = get_user(opt, (int __user *)optval);
+	rc = copy_from_sockptr(&opt, optval, sizeof(opt));
 	if (rc)
 		goto out;
 	rc = -EINVAL;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7246847efa90..2891ae8a1028 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1632,7 +1632,7 @@ static void mptcp_destroy(struct sock *sk)
 }
 
 static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
-				       char __user *optval, unsigned int optlen)
+				       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct socket *ssock;
@@ -1648,8 +1648,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 			return -EINVAL;
 		}
 
-		ret = sock_setsockopt(ssock, SOL_SOCKET, optname,
-				      USER_SOCKPTR(optval), optlen);
+		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);
 		if (ret == 0) {
 			if (optname == SO_REUSEPORT)
 				sk->sk_reuseport = ssock->sk->sk_reuseport;
@@ -1660,12 +1659,11 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 		return ret;
 	}
 
-	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
-			       USER_SOCKPTR(optval), optlen);
+	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
 }
 
 static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
 	int ret = -EOPNOTSUPP;
@@ -1692,7 +1690,7 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 }
 
 static int mptcp_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, unsigned int optlen)
+			    sockptr_t optval, unsigned int optlen)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sock *ssk;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3cd58f0c2de4..d8921b833744 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1621,7 +1621,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk,
 }
 
 static int netlink_setsockopt(struct socket *sock, int level, int optname,
-			      char __user *optval, unsigned int optlen)
+			      sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -1632,7 +1632,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		return -ENOPROTOOPT;
 
 	if (optlen >= sizeof(int) &&
-	    get_user(val, (unsigned int __user *)optval))
+	    copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
 	switch (optname) {
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index f90ef6934b8f..6d16e1ab1a8a 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -294,7 +294,7 @@ void nr_destroy_socket(struct sock *sk)
  */
 
 static int nr_setsockopt(struct socket *sock, int level, int optname,
-	char __user *optval, unsigned int optlen)
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct nr_sock *nr = nr_sk(sk);
@@ -306,7 +306,7 @@ static int nr_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(unsigned int))
 		return -EINVAL;
 
-	if (get_user(opt, (unsigned int __user *)optval))
+	if (copy_from_sockptr(&opt, optval, sizeof(unsigned int)))
 		return -EFAULT;
 
 	switch (optname) {
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 6da1e2334bb6..d257ed3b732a 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -218,7 +218,7 @@ error:
 }
 
 static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname,
-			       char __user *optval, unsigned int optlen)
+			       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk);
@@ -241,7 +241,7 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
@@ -263,7 +263,7 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d8d4f78f78e4..0b8160d1a6e0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1558,7 +1558,7 @@ static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data,
 	return 0;
 }
 
-static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
+static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data,
 				unsigned int len)
 {
 	struct bpf_prog *new;
@@ -1568,7 +1568,7 @@ static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
 		return -EPERM;
 	if (len != sizeof(fd))
 		return -EINVAL;
-	if (copy_from_user(&fd, data, len))
+	if (copy_from_sockptr(&fd, data, len))
 		return -EFAULT;
 
 	new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER);
@@ -1579,12 +1579,12 @@ static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
 	return 0;
 }
 
-static int fanout_set_data(struct packet_sock *po, char __user *data,
+static int fanout_set_data(struct packet_sock *po, sockptr_t data,
 			   unsigned int len)
 {
 	switch (po->fanout->type) {
 	case PACKET_FANOUT_CBPF:
-		return fanout_set_data_cbpf(po, USER_SOCKPTR(data), len);
+		return fanout_set_data_cbpf(po, data, len);
 	case PACKET_FANOUT_EBPF:
 		return fanout_set_data_ebpf(po, data, len);
 	default:
@@ -3652,7 +3652,8 @@ static void packet_flush_mclist(struct sock *sk)
 }
 
 static int
-packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
+packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
+		  unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
@@ -3672,7 +3673,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EINVAL;
 		if (len > sizeof(mreq))
 			len = sizeof(mreq);
-		if (copy_from_user(&mreq, optval, len))
+		if (copy_from_sockptr(&mreq, optval, len))
 			return -EFAULT;
 		if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address)))
 			return -EINVAL;
@@ -3703,7 +3704,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (optlen < len) {
 			ret = -EINVAL;
 		} else {
-			if (copy_from_user(&req_u.req, optval, len))
+			if (copy_from_sockptr(&req_u.req, optval, len))
 				ret = -EFAULT;
 			else
 				ret = packet_set_ring(sk, &req_u, 0,
@@ -3718,7 +3719,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		pkt_sk(sk)->copy_thresh = val;
@@ -3730,7 +3731,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 		switch (val) {
 		case TPACKET_V1:
@@ -3756,7 +3757,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 		if (val > INT_MAX)
 			return -EINVAL;
@@ -3776,7 +3777,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		lock_sock(sk);
@@ -3795,7 +3796,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen < sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		lock_sock(sk);
@@ -3809,7 +3810,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen < sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		lock_sock(sk);
@@ -3825,7 +3826,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EINVAL;
 		if (optlen < sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		lock_sock(sk);
@@ -3844,7 +3845,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		po->tp_tstamp = val;
@@ -3856,7 +3857,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		return fanout_add(sk, val & 0xffff, val >> 16);
@@ -3874,7 +3875,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 		if (val < 0 || val > 1)
 			return -EINVAL;
@@ -3888,7 +3889,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		lock_sock(sk);
@@ -3907,7 +3908,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (copy_from_user(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
 			return -EFAULT;
 
 		po->xmit = val ? packet_direct_xmit : dev_queue_xmit;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 4577e43cb777..e47d09aca4af 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -975,7 +975,7 @@ static int pep_init(struct sock *sk)
 }
 
 static int pep_setsockopt(struct sock *sk, int level, int optname,
-				char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct pep_sock *pn = pep_sk(sk);
 	int val = 0, err = 0;
@@ -983,7 +983,7 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_PNPIPE)
 		return -ENOPROTOOPT;
 	if (optlen >= sizeof(int)) {
-		if (get_user(val, (int __user *) optval))
+		if (copy_from_sockptr(&val, optval, sizeof(int)))
 			return -EFAULT;
 	}
 
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 1a5bf3fa4578..b239120dd9ca 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -290,8 +290,7 @@ static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
-static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
-			      int len)
+static int rds_cancel_sent_to(struct rds_sock *rs, sockptr_t optval, int len)
 {
 	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
@@ -308,14 +307,15 @@ static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
 		goto out;
 	} else if (len < sizeof(struct sockaddr_in6)) {
 		/* Assume IPv4 */
-		if (copy_from_user(&sin, optval, sizeof(struct sockaddr_in))) {
+		if (copy_from_sockptr(&sin, optval,
+				sizeof(struct sockaddr_in))) {
 			ret = -EFAULT;
 			goto out;
 		}
 		ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr);
 		sin6.sin6_port = sin.sin_port;
 	} else {
-		if (copy_from_user(&sin6, optval,
+		if (copy_from_sockptr(&sin6, optval,
 				   sizeof(struct sockaddr_in6))) {
 			ret = -EFAULT;
 			goto out;
@@ -327,21 +327,20 @@ out:
 	return ret;
 }
 
-static int rds_set_bool_option(unsigned char *optvar, char __user *optval,
+static int rds_set_bool_option(unsigned char *optvar, sockptr_t optval,
 			       int optlen)
 {
 	int value;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
-	if (get_user(value, (int __user *) optval))
+	if (copy_from_sockptr(&value, optval, sizeof(int)))
 		return -EFAULT;
 	*optvar = !!value;
 	return 0;
 }
 
-static int rds_cong_monitor(struct rds_sock *rs, char __user *optval,
-			    int optlen)
+static int rds_cong_monitor(struct rds_sock *rs, sockptr_t optval, int optlen)
 {
 	int ret;
 
@@ -358,8 +357,7 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval,
 	return ret;
 }
 
-static int rds_set_transport(struct rds_sock *rs, char __user *optval,
-			     int optlen)
+static int rds_set_transport(struct rds_sock *rs, sockptr_t optval, int optlen)
 {
 	int t_type;
 
@@ -369,7 +367,7 @@ static int rds_set_transport(struct rds_sock *rs, char __user *optval,
 	if (optlen != sizeof(int))
 		return -EINVAL;
 
-	if (copy_from_user(&t_type, (int __user *)optval, sizeof(t_type)))
+	if (copy_from_sockptr(&t_type, optval, sizeof(t_type)))
 		return -EFAULT;
 
 	if (t_type < 0 || t_type >= RDS_TRANS_COUNT)
@@ -380,7 +378,7 @@ static int rds_set_transport(struct rds_sock *rs, char __user *optval,
 	return rs->rs_transport ? 0 : -ENOPROTOOPT;
 }
 
-static int rds_enable_recvtstamp(struct sock *sk, char __user *optval,
+static int rds_enable_recvtstamp(struct sock *sk, sockptr_t optval,
 				 int optlen, int optname)
 {
 	int val, valbool;
@@ -388,7 +386,7 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval,
 	if (optlen != sizeof(int))
 		return -EFAULT;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	valbool = val ? 1 : 0;
@@ -404,7 +402,7 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval,
 	return 0;
 }
 
-static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval,
+static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval,
 				  int optlen)
 {
 	struct rds_rx_trace_so trace;
@@ -413,7 +411,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval,
 	if (optlen != sizeof(struct rds_rx_trace_so))
 		return -EFAULT;
 
-	if (copy_from_user(&trace, optval, sizeof(trace)))
+	if (copy_from_sockptr(&trace, optval, sizeof(trace)))
 		return -EFAULT;
 
 	if (trace.rx_traces > RDS_MSG_RX_DGRAM_TRACE_MAX)
@@ -432,7 +430,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval,
 }
 
 static int rds_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
 	int ret;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index a7ae11846cd7..ccdd304eae0a 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -353,21 +353,20 @@ out:
 	return ret;
 }
 
-int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen)
+int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen)
 {
 	struct rds_get_mr_args args;
 
 	if (optlen != sizeof(struct rds_get_mr_args))
 		return -EINVAL;
 
-	if (copy_from_user(&args, (struct rds_get_mr_args __user *)optval,
-			   sizeof(struct rds_get_mr_args)))
+	if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_args)))
 		return -EFAULT;
 
 	return __rds_rdma_map(rs, &args, NULL, NULL, NULL);
 }
 
-int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
+int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen)
 {
 	struct rds_get_mr_for_dest_args args;
 	struct rds_get_mr_args new_args;
@@ -375,7 +374,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
 	if (optlen != sizeof(struct rds_get_mr_for_dest_args))
 		return -EINVAL;
 
-	if (copy_from_user(&args, (struct rds_get_mr_for_dest_args __user *)optval,
+	if (copy_from_sockptr(&args, optval,
 			   sizeof(struct rds_get_mr_for_dest_args)))
 		return -EFAULT;
 
@@ -394,7 +393,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
 /*
  * Free the MR indicated by the given R_Key
  */
-int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen)
+int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen)
 {
 	struct rds_free_mr_args args;
 	struct rds_mr *mr;
@@ -403,8 +402,7 @@ int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen)
 	if (optlen != sizeof(struct rds_free_mr_args))
 		return -EINVAL;
 
-	if (copy_from_user(&args, (struct rds_free_mr_args __user *)optval,
-			   sizeof(struct rds_free_mr_args)))
+	if (copy_from_sockptr(&args, optval, sizeof(struct rds_free_mr_args)))
 		return -EFAULT;
 
 	/* Special case - a null cookie means flush all unused MRs */
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 106e862996b9..d35d1fc39807 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -924,9 +924,9 @@ int rds_send_pong(struct rds_conn_path *cp, __be16 dport);
 
 /* rdma.c */
 void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
-int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen);
-int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen);
-int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen);
+int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen);
+int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen);
+int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen);
 void rds_rdma_drop_keys(struct rds_sock *rs);
 int rds_rdma_extra_size(struct rds_rdma_args *args,
 			struct rds_iov_vector *iov);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index ce85656ac9c1..cf7d974e0f61 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -365,7 +365,7 @@ void rose_destroy_socket(struct sock *sk)
  */
 
 static int rose_setsockopt(struct socket *sock, int level, int optname,
-	char __user *optval, unsigned int optlen)
+		sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
@@ -377,7 +377,7 @@ static int rose_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(opt, (int __user *)optval))
+	if (copy_from_sockptr(&opt, optval, sizeof(int)))
 		return -EFAULT;
 
 	switch (optname) {
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index cd7d0d204c74..e6725a6de015 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -588,7 +588,7 @@ EXPORT_SYMBOL(rxrpc_sock_set_min_security_level);
  * set RxRPC socket options
  */
 static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
-			    char __user *optval, unsigned int optlen)
+			    sockptr_t optval, unsigned int optlen)
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	unsigned int min_sec_level;
@@ -639,8 +639,8 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			ret = -EISCONN;
 			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
-			ret = get_user(min_sec_level,
-				       (unsigned int __user *) optval);
+			ret = copy_from_sockptr(&min_sec_level, optval,
+				       sizeof(unsigned int));
 			if (ret < 0)
 				goto error;
 			ret = -EINVAL;
@@ -658,7 +658,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			if (rx->sk.sk_state != RXRPC_SERVER_BOUND2)
 				goto error;
 			ret = -EFAULT;
-			if (copy_from_user(service_upgrade, optval,
+			if (copy_from_sockptr(service_upgrade, optval,
 					   sizeof(service_upgrade)) != 0)
 				goto error;
 			ret = -EINVAL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 9a2139ebd67d..6d29a3603a3e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -909,8 +909,8 @@ extern const struct rxrpc_security rxrpc_no_security;
 extern struct key_type key_type_rxrpc;
 extern struct key_type key_type_rxrpc_s;
 
-int rxrpc_request_key(struct rxrpc_sock *, char __user *, int);
-int rxrpc_server_keyring(struct rxrpc_sock *, char __user *, int);
+int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int);
+int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int);
 int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t,
 			      u32);
 
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 0c98313dd7a8..94c3df392651 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -896,7 +896,7 @@ static void rxrpc_describe(const struct key *key, struct seq_file *m)
 /*
  * grab the security key for a socket
  */
-int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen)
+int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
 {
 	struct key *key;
 	char *description;
@@ -906,7 +906,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen)
 	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
 		return -EINVAL;
 
-	description = memdup_user_nul(optval, optlen);
+	description = memdup_sockptr_nul(optval, optlen);
 	if (IS_ERR(description))
 		return PTR_ERR(description);
 
@@ -926,8 +926,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen)
 /*
  * grab the security keyring for a server socket
  */
-int rxrpc_server_keyring(struct rxrpc_sock *rx, char __user *optval,
-			 int optlen)
+int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
 {
 	struct key *key;
 	char *description;
@@ -937,7 +936,7 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, char __user *optval,
 	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
 		return -EINVAL;
 
-	description = memdup_user_nul(optval, optlen);
+	description = memdup_sockptr_nul(optval, optlen);
 	if (IS_ERR(description))
 		return PTR_ERR(description);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9a767f359718..144808dfea9e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4429,7 +4429,7 @@ out:
  *   optlen  - the size of the buffer.
  */
 static int sctp_setsockopt(struct sock *sk, int level, int optname,
-			   char __user *optval, unsigned int optlen)
+			   sockptr_t optval, unsigned int optlen)
 {
 	void *kopt = NULL;
 	int retval = 0;
@@ -4449,7 +4449,7 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	}
 
 	if (optlen > 0) {
-		kopt = memdup_user(optval, optlen);
+		kopt = memdup_sockptr(optval, optlen);
 		if (IS_ERR(kopt))
 			return PTR_ERR(kopt);
 	}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9711c9e0e515..4ac1d4de6676 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1731,7 +1731,7 @@ out:
 }
 
 static int smc_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct smc_sock *smc;
@@ -1754,7 +1754,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(int)))
 		return -EFAULT;
 
 	lock_sock(sk);
diff --git a/net/socket.c b/net/socket.c
index c97f83d879ae..e44b8ac47f6f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2094,10 +2094,10 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
  *	Set a socket option. Because we don't know the option lengths we have
  *	to pass the user mode parameter for the protocols to sort out.
  */
-int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
+int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 		int optlen)
 {
-	mm_segment_t oldfs = get_fs();
+	sockptr_t optval = USER_SOCKPTR(user_optval);
 	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
@@ -2115,7 +2115,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 
 	if (!in_compat_syscall())
 		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
-						     optval, &optlen,
+						     user_optval, &optlen,
 						     &kernel_optval);
 	if (err < 0)
 		goto out_put;
@@ -2124,25 +2124,16 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 		goto out_put;
 	}
 
-	if (kernel_optval) {
-		set_fs(KERNEL_DS);
-		optval = (char __user __force *)kernel_optval;
-	}
-
+	if (kernel_optval)
+		optval = KERNEL_SOCKPTR(kernel_optval);
 	if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock))
-		err = sock_setsockopt(sock, level, optname,
-				      USER_SOCKPTR(optval), optlen);
+		err = sock_setsockopt(sock, level, optname, optval, optlen);
 	else if (unlikely(!sock->ops->setsockopt))
 		err = -EOPNOTSUPP;
 	else
 		err = sock->ops->setsockopt(sock, level, optname, optval,
 					    optlen);
-
-	if (kernel_optval) {
-		set_fs(oldfs);
-		kfree(kernel_optval);
-	}
-
+	kfree(kernel_optval);
 out_put:
 	fput_light(sock->file, fput_needed);
 	return err;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index fc388cef6471..07419f36116a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3103,7 +3103,7 @@ static int tipc_sk_leave(struct tipc_sock *tsk)
  * Returns 0 on success, errno otherwise
  */
 static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
-			   char __user *ov, unsigned int ol)
+			   sockptr_t ov, unsigned int ol)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
@@ -3124,17 +3124,17 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 	case TIPC_NODELAY:
 		if (ol < sizeof(value))
 			return -EINVAL;
-		if (get_user(value, (u32 __user *)ov))
+		if (copy_from_sockptr(&value, ov, sizeof(u32)))
 			return -EFAULT;
 		break;
 	case TIPC_GROUP_JOIN:
 		if (ol < sizeof(mreq))
 			return -EINVAL;
-		if (copy_from_user(&mreq, ov, sizeof(mreq)))
+		if (copy_from_sockptr(&mreq, ov, sizeof(mreq)))
 			return -EFAULT;
 		break;
 	default:
-		if (ov || ol)
+		if (!sockptr_is_null(ov) || ol)
 			return -EINVAL;
 	}
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index ec10041c6b7d..d77f7d821130 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -450,7 +450,7 @@ static int tls_getsockopt(struct sock *sk, int level, int optname,
 	return do_tls_getsockopt(sk, optname, optval, optlen);
 }
 
-static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
+static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 				  unsigned int optlen, int tx)
 {
 	struct tls_crypto_info *crypto_info;
@@ -460,7 +460,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 	int rc = 0;
 	int conf;
 
-	if (!optval || (optlen < sizeof(*crypto_info))) {
+	if (sockptr_is_null(optval) || (optlen < sizeof(*crypto_info))) {
 		rc = -EINVAL;
 		goto out;
 	}
@@ -479,7 +479,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 		goto out;
 	}
 
-	rc = copy_from_user(crypto_info, optval, sizeof(*crypto_info));
+	rc = copy_from_sockptr(crypto_info, optval, sizeof(*crypto_info));
 	if (rc) {
 		rc = -EFAULT;
 		goto err_crypto_info;
@@ -522,8 +522,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 		goto err_crypto_info;
 	}
 
-	rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info),
-			    optlen - sizeof(*crypto_info));
+	sockptr_advance(optval, sizeof(*crypto_info));
+	rc = copy_from_sockptr(crypto_info + 1, optval,
+			       optlen - sizeof(*crypto_info));
 	if (rc) {
 		rc = -EFAULT;
 		goto err_crypto_info;
@@ -579,8 +580,8 @@ out:
 	return rc;
 }
 
-static int do_tls_setsockopt(struct sock *sk, int optname,
-			     char __user *optval, unsigned int optlen)
+static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval,
+			     unsigned int optlen)
 {
 	int rc = 0;
 
@@ -600,7 +601,7 @@ static int do_tls_setsockopt(struct sock *sk, int optname,
 }
 
 static int tls_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index df204c6761c4..27bbcfad9c17 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1517,7 +1517,7 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk,
 static int vsock_stream_setsockopt(struct socket *sock,
 				   int level,
 				   int optname,
-				   char __user *optval,
+				   sockptr_t optval,
 				   unsigned int optlen)
 {
 	int err;
@@ -1535,7 +1535,7 @@ static int vsock_stream_setsockopt(struct socket *sock,
 			err = -EINVAL;			  \
 			goto exit;			  \
 		}					  \
-		if (copy_from_user(&_v, optval, sizeof(_v)) != 0) {	\
+		if (copy_from_sockptr(&_v, optval, sizeof(_v)) != 0) {	\
 			err = -EFAULT;					\
 			goto exit;					\
 		}							\
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index d5b09bbff375..0bbb283f23c9 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -431,7 +431,7 @@ void x25_destroy_socket_from_timer(struct sock *sk)
  */
 
 static int x25_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	int opt;
 	struct sock *sk = sock->sk;
@@ -445,7 +445,7 @@ static int x25_setsockopt(struct socket *sock, int level, int optname,
 		goto out;
 
 	rc = -EFAULT;
-	if (get_user(opt, (int __user *)optval))
+	if (copy_from_sockptr(&opt, optval, sizeof(int)))
 		goto out;
 
 	if (opt)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 26e3bba8c204..2e94a7e94671 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -702,7 +702,7 @@ struct xdp_umem_reg_v1 {
 };
 
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
@@ -720,7 +720,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(entries))
 			return -EINVAL;
-		if (copy_from_user(&entries, optval, sizeof(entries)))
+		if (copy_from_sockptr(&entries, optval, sizeof(entries)))
 			return -EFAULT;
 
 		mutex_lock(&xs->mutex);
@@ -747,7 +747,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		else if (optlen < sizeof(mr))
 			mr_size = sizeof(struct xdp_umem_reg_v1);
 
-		if (copy_from_user(&mr, optval, mr_size))
+		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;
 
 		mutex_lock(&xs->mutex);
@@ -774,7 +774,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		struct xsk_queue **q;
 		int entries;
 
-		if (copy_from_user(&entries, optval, sizeof(entries)))
+		if (copy_from_sockptr(&entries, optval, sizeof(entries)))
 			return -EFAULT;
 
 		mutex_lock(&xs->mutex);
-- 
cgit v1.2.3


From 6d04fe15f78acdf8e32329e208552e226f7a8ae6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:09:08 +0200
Subject: net: optimize the sockptr_t for unified kernel/user address spaces

For architectures like x86 and arm64 we don't need the separate bit to
indicate that a pointer is a kernel pointer as the address spaces are
unified.  That way the sockptr_t can be reduced to a union of two
pointers, which leads to nicer calling conventions.

The only caveat is that we need to check that users don't pass in kernel
address and thus gain access to kernel memory.  Thus the USER_SOCKPTR
helper is replaced with a init_user_sockptr function that does this check
and returns an error if it fails.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockptr.h     | 32 ++++++++++++++++++++++++++++++--
 net/ipv4/bpfilter/sockopt.c | 14 ++++++++------
 net/socket.c                |  6 +++++-
 3 files changed, 43 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 700856e13ea0..7d5cdb2b30b5 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -8,9 +8,34 @@
 #ifndef _LINUX_SOCKPTR_H
 #define _LINUX_SOCKPTR_H
 
+#include <linux/compiler.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+typedef union {
+	void		*kernel;
+	void __user	*user;
+} sockptr_t;
+
+static inline bool sockptr_is_kernel(sockptr_t sockptr)
+{
+	return (unsigned long)sockptr.kernel >= TASK_SIZE;
+}
+
+static inline sockptr_t KERNEL_SOCKPTR(void *p)
+{
+	return (sockptr_t) { .kernel = p };
+}
+
+static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p)
+{
+	if ((unsigned long)p >= TASK_SIZE)
+		return -EFAULT;
+	sp->user = p;
+	return 0;
+}
+#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 typedef struct {
 	union {
 		void		*kernel;
@@ -29,10 +54,13 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p)
 	return (sockptr_t) { .kernel = p, .is_kernel = true };
 }
 
-static inline sockptr_t USER_SOCKPTR(void __user *p)
+static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p)
 {
-	return (sockptr_t) { .user = p };
+	sp->user = p;
+	sp->is_kernel = false;
+	return 0;
 }
+#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
 static inline bool sockptr_is_null(sockptr_t sockptr)
 {
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 1b34cb9a7708..94f18d2352d0 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -57,16 +57,18 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
 	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
 }
 
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen)
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname,
+			    char __user *user_optval, int __user *optlen)
 {
-	int len;
+	sockptr_t optval;
+	int err, len;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
-
-	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
-				     false);
+	err = init_user_sockptr(&optval, user_optval);
+	if (err)
+		return err;
+	return bpfilter_mbox_request(sk, optname, optval, len, false);
 }
 
 static int __init bpfilter_sockopt_init(void)
diff --git a/net/socket.c b/net/socket.c
index e44b8ac47f6f..94ca4547cd7c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2097,7 +2097,7 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
 int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 		int optlen)
 {
-	sockptr_t optval = USER_SOCKPTR(user_optval);
+	sockptr_t optval;
 	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
@@ -2105,6 +2105,10 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 	if (optlen < 0)
 		return -EINVAL;
 
+	err = init_user_sockptr(&optval, user_optval);
+	if (err)
+		return err;
+
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		return err;
-- 
cgit v1.2.3


From 178c49d9f9a4b5ade00c93480d714708fe971e24 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 24 Jul 2020 09:03:09 -0400
Subject: icmp: prepare rfc 4884 for ipv6

The RFC 4884 spec is largely the same between IPv4 and IPv6.
Factor out the IPv4 specific parts in preparation for IPv6 support:

- icmp types supported

- icmp header size, and thus offset to original datagram start

- datagram length field offset in icmp(6)hdr.

- datagram length field word size: 4B for IPv4, 8B for IPv6.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/icmp.h   |  3 ++-
 net/ipv4/icmp.c        | 17 ++++-------------
 net/ipv4/ip_sockglue.c | 14 +++++++++++++-
 3 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/icmp.h b/include/linux/icmp.h
index 8fc38a34cb20..0af4d210ee31 100644
--- a/include/linux/icmp.h
+++ b/include/linux/icmp.h
@@ -37,6 +37,7 @@ static inline bool icmp_is_err(int type)
 }
 
 void ip_icmp_error_rfc4884(const struct sk_buff *skb,
-			   struct sock_ee_data_rfc4884 *out);
+			   struct sock_ee_data_rfc4884 *out,
+			   int thlen, int off);
 
 #endif	/* _LINUX_ICMP_H */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8d2654cdbd77..7498c58460a1 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1151,24 +1151,15 @@ static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off)
 }
 
 void ip_icmp_error_rfc4884(const struct sk_buff *skb,
-			   struct sock_ee_data_rfc4884 *out)
+			   struct sock_ee_data_rfc4884 *out,
+			   int thlen, int off)
 {
-	int hlen, off;
-
-	switch (icmp_hdr(skb)->type) {
-	case ICMP_DEST_UNREACH:
-	case ICMP_TIME_EXCEEDED:
-	case ICMP_PARAMETERPROB:
-		break;
-	default:
-		return;
-	}
+	int hlen;
 
 	/* original datagram headers: end of icmph to payload (skb->data) */
-	hlen = -skb_transport_offset(skb) - sizeof(struct icmphdr);
+	hlen = -skb_transport_offset(skb) - thlen;
 
 	/* per rfc 4884: minimal datagram length of 128 bytes */
-	off = icmp_hdr(skb)->un.reserved[1] * sizeof(u32);
 	if (off < 128 || off < hlen)
 		return;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8dc027e54c5b..d2c223554ff7 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -390,6 +390,18 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 	return 0;
 }
 
+static void ipv4_icmp_error_rfc4884(const struct sk_buff *skb,
+				    struct sock_ee_data_rfc4884 *out)
+{
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip_icmp_error_rfc4884(skb, out, sizeof(struct icmphdr),
+				      icmp_hdr(skb)->un.reserved[1] * 4);
+	}
+}
+
 void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		   __be16 port, u32 info, u8 *payload)
 {
@@ -413,7 +425,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 
 	if (skb_pull(skb, payload - skb->data)) {
 		if (inet_sk(sk)->recverr_rfc4884)
-			ip_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+			ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
 
 		skb_reset_transport_header(skb);
 		if (sock_queue_err_skb(sk, skb) == 0)
-- 
cgit v1.2.3


From 01370434df85eb76ecb1527a4466013c4aca2436 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 24 Jul 2020 09:03:10 -0400
Subject: icmp6: support rfc 4884

Extend the rfc 4884 read interface introduced for ipv4 in
commit eba75c587e81 ("icmp: support rfc 4884") to ipv6.

Add socket option SOL_IPV6/IPV6_RECVERR_RFC4884.

Changes v1->v2:
  - make ipv6_icmp_error_rfc4884 static (file scope)

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h        |  1 +
 include/uapi/linux/icmpv6.h |  1 +
 include/uapi/linux/in6.h    |  1 +
 net/ipv4/icmp.c             |  1 +
 net/ipv6/datagram.c         | 16 ++++++++++++++++
 net/ipv6/ipv6_sockglue.c    | 12 ++++++++++++
 6 files changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 8d8f877e7f81..a44789d027cc 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -283,6 +283,7 @@ struct ipv6_pinfo {
 				autoflowlabel:1,
 				autoflowlabel_set:1,
 				mc_all:1,
+				recverr_rfc4884:1,
 				rtalert_isolate:1;
 	__u8			min_hopcount;
 	__u8			tclass;
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index 2622b5a3e616..c1661febc2dc 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -68,6 +68,7 @@ struct icmp6hdr {
 #define icmp6_mtu		icmp6_dataun.un_data32[0]
 #define icmp6_unused		icmp6_dataun.un_data32[0]
 #define icmp6_maxdelay		icmp6_dataun.un_data16[0]
+#define icmp6_datagram_len	icmp6_dataun.un_data8[0]
 #define icmp6_router		icmp6_dataun.u_nd_advt.router
 #define icmp6_solicited		icmp6_dataun.u_nd_advt.solicited
 #define icmp6_override		icmp6_dataun.u_nd_advt.override
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 9f2273a08356..5ad396a57eb3 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -179,6 +179,7 @@ struct in6_flowlabel_req {
 #define IPV6_LEAVE_ANYCAST	28
 #define IPV6_MULTICAST_ALL	29
 #define IPV6_ROUTER_ALERT_ISOLATE	30
+#define IPV6_RECVERR_RFC4884	31
 
 /* IPV6_MTU_DISCOVER values */
 #define IPV6_PMTUDISC_DONT		0
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7498c58460a1..cf36f955bfe6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1173,6 +1173,7 @@ void ip_icmp_error_rfc4884(const struct sk_buff *skb,
 	if (!ip_icmp_error_rfc4884_validate(skb, off))
 		out->flags |= SO_EE_RFC4884_FLAG_INVALID;
 }
+EXPORT_SYMBOL_GPL(ip_icmp_error_rfc4884);
 
 int icmp_err(struct sk_buff *skb, u32 info)
 {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 390bedde21a5..cc8ad7ddecda 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -19,6 +19,7 @@
 #include <linux/route.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/icmp.h>
 
 #include <net/ipv6.h>
 #include <net/ndisc.h>
@@ -284,6 +285,17 @@ int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only);
 
+static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb,
+				    struct sock_ee_data_rfc4884 *out)
+{
+	switch (icmp6_hdr(skb)->icmp6_type) {
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_DEST_UNREACH:
+		ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr),
+				      icmp6_hdr(skb)->icmp6_datagram_len * 8);
+	}
+}
+
 void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		     __be16 port, u32 info, u8 *payload)
 {
@@ -313,6 +325,10 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 	serr->port = port;
 
 	__skb_pull(skb, payload - skb->data);
+
+	if (inet6_sk(sk)->recverr_rfc4884)
+		ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+
 	skb_reset_transport_header(skb);
 
 	if (sock_queue_err_skb(sk, skb))
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d2282f5c9760..20c740976334 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -965,6 +965,14 @@ done:
 		np->rxopt.bits.recvfragsize = valbool;
 		retv = 0;
 		break;
+	case IPV6_RECVERR_RFC4884:
+		if (optlen < sizeof(int))
+			goto e_inval;
+		if (val < 0 || val > 1)
+			goto e_inval;
+		np->recverr_rfc4884 = valbool;
+		retv = 0;
+		break;
 	}
 
 	release_sock(sk);
@@ -1439,6 +1447,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		val = np->rtalert_isolate;
 		break;
 
+	case IPV6_RECVERR_RFC4884:
+		val = np->recverr_rfc4884;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
-- 
cgit v1.2.3


From 0f206514749be9988a083ca364b889a7fcff7f78 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 10 Jul 2020 00:20:08 -0700
Subject: scsi: firmware: qcom_scm: Add support for programming inline crypto
 keys

Add support for the Inline Crypto Engine (ICE) key programming interface
that's needed for the ufs-qcom driver to use inline encryption on
Snapdragon SoCs.  This interface consists of two SCM calls: one to program
a key into a keyslot, and one to invalidate a keyslot.

Although the UFS specification defines a standard way to do this, on these
SoCs the Linux kernel isn't permitted to access the needed crypto
configuration registers directly; these SCM calls must be used instead.

Link: https://lore.kernel.org/r/20200710072013.177481-2-ebiggers@kernel.org
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/firmware/qcom_scm.c | 101 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/firmware/qcom_scm.h |   4 ++
 include/linux/qcom_scm.h    |  19 +++++++++
 3 files changed, 124 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 0e7233a20f34..1a8eb1b42b1e 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -923,6 +923,107 @@ int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size)
 }
 EXPORT_SYMBOL(qcom_scm_ocmem_unlock);
 
+/**
+ * qcom_scm_ice_available() - Is the ICE key programming interface available?
+ *
+ * Return: true iff the SCM calls wrapped by qcom_scm_ice_invalidate_key() and
+ *	   qcom_scm_ice_set_key() are available.
+ */
+bool qcom_scm_ice_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES,
+					    QCOM_SCM_ES_INVALIDATE_ICE_KEY) &&
+		__qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES,
+					     QCOM_SCM_ES_CONFIG_SET_ICE_KEY);
+}
+EXPORT_SYMBOL(qcom_scm_ice_available);
+
+/**
+ * qcom_scm_ice_invalidate_key() - Invalidate an inline encryption key
+ * @index: the keyslot to invalidate
+ *
+ * The UFSHCI standard defines a standard way to do this, but it doesn't work on
+ * these SoCs; only this SCM call does.
+ *
+ * Return: 0 on success; -errno on failure.
+ */
+int qcom_scm_ice_invalidate_key(u32 index)
+{
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_ES,
+		.cmd = QCOM_SCM_ES_INVALIDATE_ICE_KEY,
+		.arginfo = QCOM_SCM_ARGS(1),
+		.args[0] = index,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+
+	return qcom_scm_call(__scm->dev, &desc, NULL);
+}
+EXPORT_SYMBOL(qcom_scm_ice_invalidate_key);
+
+/**
+ * qcom_scm_ice_set_key() - Set an inline encryption key
+ * @index: the keyslot into which to set the key
+ * @key: the key to program
+ * @key_size: the size of the key in bytes
+ * @cipher: the encryption algorithm the key is for
+ * @data_unit_size: the encryption data unit size, i.e. the size of each
+ *		    individual plaintext and ciphertext.  Given in 512-byte
+ *		    units, e.g. 1 = 512 bytes, 8 = 4096 bytes, etc.
+ *
+ * Program a key into a keyslot of Qualcomm ICE (Inline Crypto Engine), where it
+ * can then be used to encrypt/decrypt UFS I/O requests inline.
+ *
+ * The UFSHCI standard defines a standard way to do this, but it doesn't work on
+ * these SoCs; only this SCM call does.
+ *
+ * Return: 0 on success; -errno on failure.
+ */
+int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size,
+			 enum qcom_scm_ice_cipher cipher, u32 data_unit_size)
+{
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_ES,
+		.cmd = QCOM_SCM_ES_CONFIG_SET_ICE_KEY,
+		.arginfo = QCOM_SCM_ARGS(5, QCOM_SCM_VAL, QCOM_SCM_RW,
+					 QCOM_SCM_VAL, QCOM_SCM_VAL,
+					 QCOM_SCM_VAL),
+		.args[0] = index,
+		.args[2] = key_size,
+		.args[3] = cipher,
+		.args[4] = data_unit_size,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+	void *keybuf;
+	dma_addr_t key_phys;
+	int ret;
+
+	/*
+	 * 'key' may point to vmalloc()'ed memory, but we need to pass a
+	 * physical address that's been properly flushed.  The sanctioned way to
+	 * do this is by using the DMA API.  But as is best practice for crypto
+	 * keys, we also must wipe the key after use.  This makes kmemdup() +
+	 * dma_map_single() not clearly correct, since the DMA API can use
+	 * bounce buffers.  Instead, just use dma_alloc_coherent().  Programming
+	 * keys is normally rare and thus not performance-critical.
+	 */
+
+	keybuf = dma_alloc_coherent(__scm->dev, key_size, &key_phys,
+				    GFP_KERNEL);
+	if (!keybuf)
+		return -ENOMEM;
+	memcpy(keybuf, key, key_size);
+	desc.args[1] = key_phys;
+
+	ret = qcom_scm_call(__scm->dev, &desc, NULL);
+
+	memzero_explicit(keybuf, key_size);
+
+	dma_free_coherent(__scm->dev, key_size, keybuf, key_phys);
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_ice_set_key);
+
 /**
  * qcom_scm_hdcp_available() - Check if secure environment supports HDCP.
  *
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index d9ed670da222..38ea614d29fe 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -103,6 +103,10 @@ extern int scm_legacy_call(struct device *dev, const struct qcom_scm_desc *desc,
 #define QCOM_SCM_OCMEM_LOCK_CMD		0x01
 #define QCOM_SCM_OCMEM_UNLOCK_CMD	0x02
 
+#define QCOM_SCM_SVC_ES			0x10	/* Enterprise Security */
+#define QCOM_SCM_ES_INVALIDATE_ICE_KEY	0x03
+#define QCOM_SCM_ES_CONFIG_SET_ICE_KEY	0x04
+
 #define QCOM_SCM_SVC_HDCP		0x11
 #define QCOM_SCM_HDCP_INVOKE		0x01
 
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 3d6a24697761..2e1193a3fb5f 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -44,6 +44,13 @@ enum qcom_scm_sec_dev_id {
 	QCOM_SCM_ICE_DEV_ID     = 20,
 };
 
+enum qcom_scm_ice_cipher {
+	QCOM_SCM_ICE_CIPHER_AES_128_XTS = 0,
+	QCOM_SCM_ICE_CIPHER_AES_128_CBC = 1,
+	QCOM_SCM_ICE_CIPHER_AES_256_XTS = 3,
+	QCOM_SCM_ICE_CIPHER_AES_256_CBC = 4,
+};
+
 #define QCOM_SCM_VMID_HLOS       0x3
 #define QCOM_SCM_VMID_MSS_MSA    0xF
 #define QCOM_SCM_VMID_WLAN       0x18
@@ -88,6 +95,12 @@ extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset,
 extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset,
 				 u32 size);
 
+extern bool qcom_scm_ice_available(void);
+extern int qcom_scm_ice_invalidate_key(u32 index);
+extern int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size,
+				enum qcom_scm_ice_cipher cipher,
+				u32 data_unit_size);
+
 extern bool qcom_scm_hdcp_available(void);
 extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 			     u32 *resp);
@@ -138,6 +151,12 @@ static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset,
 static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id,
 		u32 offset, u32 size) { return -ENODEV; }
 
+static inline bool qcom_scm_ice_available(void) { return false; }
+static inline int qcom_scm_ice_invalidate_key(u32 index) { return -ENODEV; }
+static inline int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size,
+				       enum qcom_scm_ice_cipher cipher,
+				       u32 data_unit_size) { return -ENODEV; }
+
 static inline bool qcom_scm_hdcp_available(void) { return false; }
 static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 		u32 *resp) { return -ENODEV; }
-- 
cgit v1.2.3


From 2d38dbf89a06d0f689daec9842c5d3295c49777f Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 24 Jul 2020 14:36:22 -0700
Subject: test_firmware: Test platform fw loading on non-EFI systems

On non-EFI systems, it wasn't possible to test the platform firmware
loader because it will have never set "checked_fw" during __init.
Instead, allow the test code to override this check. Additionally split
the declarations into a private header file so it there is greater
enforcement of the symbol visibility.

Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform")
Cc: stable@vger.kernel.org
Acked-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200724213640.389191-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 ++++++++++++++++-----
 drivers/firmware/efi/embedded-firmware.h | 19 +++++++++++++++++++
 include/linux/efi_embedded_fw.h          | 13 -------------
 lib/test_firmware.c                      |  5 +++++
 4 files changed, 40 insertions(+), 18 deletions(-)
 create mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index a1b199de9006..0fb03cd0a5a2 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,11 +14,22 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
+#include "embedded-firmware.h"
+
+#ifdef CONFIG_TEST_FIRMWARE
+# define EFI_EMBEDDED_FW_VISIBILITY
+#else
+# define EFI_EMBEDDED_FW_VISIBILITY static
+#endif
+
+EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
+EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
+
 /* Exported for use by lib/test_firmware.c only */
-LIST_HEAD(efi_embedded_fw_list);
+#ifdef CONFIG_TEST_FIRMWARE
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-
-static bool checked_for_fw;
+EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
+#endif
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -119,14 +130,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	checked_for_fw = true;
+	efi_embedded_fw_checked = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!checked_for_fw) {
+	if (!efi_embedded_fw_checked) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
new file mode 100644
index 000000000000..34113316d068
--- /dev/null
+++ b/drivers/firmware/efi/embedded-firmware.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
+#define _EFI_EMBEDDED_FW_INTERNAL_H_
+
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they only in separate header for use by lib/test_firmware.c.
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+
+#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 57eac5241303..4ad5db9f5312 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,19 +7,6 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they are in this header for use by lib/test_firmware.c only!
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-extern struct list_head efi_embedded_fw_list;
-
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 9fee2b93a8d1..62af792e151c 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,6 +489,7 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -501,6 +502,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -513,6 +515,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -530,6 +534,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From 92fe2aa859f52ce6aa595ca97fec110dc7100e63 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 20 Jul 2020 15:07:30 -0700
Subject: libnvdimm: Validate command family indices

The ND_CMD_CALL format allows for a general passthrough of passlisted
commands targeting a given command set. However there is no validation
of the family index relative to what the bus supports.

- Update the NFIT bus implementation (the only one that supports
  ND_CMD_CALL passthrough) to also passlist the valid set of command
  family indices.

- Update the generic __nd_ioctl() path to validate that field on behalf
  of all implementations.

Fixes: 31eca76ba2fc ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism")
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 drivers/acpi/nfit/core.c   | 11 +++++++++--
 drivers/acpi/nfit/nfit.h   |  1 -
 drivers/nvdimm/bus.c       | 16 ++++++++++++++++
 include/linux/libnvdimm.h  |  2 ++
 include/uapi/linux/ndctl.h |  4 ++++
 5 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 7c138a4edc03..1f72ce1a782b 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1823,6 +1823,7 @@ static void populate_shutdown_status(struct nfit_mem *nfit_mem)
 static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, u32 device_handle)
 {
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
 	struct acpi_device *adev, *adev_dimm;
 	struct device *dev = acpi_desc->dev;
 	unsigned long dsm_mask, label_mask;
@@ -1834,6 +1835,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	/* nfit test assumes 1:1 relationship between commands and dsms */
 	nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en;
 	nfit_mem->family = NVDIMM_FAMILY_INTEL;
+	set_bit(NVDIMM_FAMILY_INTEL, &nd_desc->dimm_family_mask);
 
 	if (dcr->valid_fields & ACPI_NFIT_CONTROL_MFG_INFO_VALID)
 		sprintf(nfit_mem->id, "%04x-%02x-%04x-%08x",
@@ -1886,10 +1888,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	 * Note, that checking for function0 (bit0) tells us if any commands
 	 * are reachable through this GUID.
 	 */
+	clear_bit(NVDIMM_FAMILY_INTEL, &nd_desc->dimm_family_mask);
 	for (i = 0; i <= NVDIMM_FAMILY_MAX; i++)
-		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
+		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) {
+			set_bit(i, &nd_desc->dimm_family_mask);
 			if (family < 0 || i == default_dsm_family)
 				family = i;
+		}
 
 	/* limit the supported commands to those that are publicly documented */
 	nfit_mem->family = family;
@@ -2153,6 +2158,9 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 
 	nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
 	nd_desc->bus_dsm_mask = acpi_desc->bus_nfit_cmd_force_en;
+	set_bit(ND_CMD_CALL, &nd_desc->cmd_mask);
+	set_bit(NVDIMM_BUS_FAMILY_NFIT, &nd_desc->bus_family_mask);
+
 	adev = to_acpi_dev(acpi_desc);
 	if (!adev)
 		return;
@@ -2160,7 +2168,6 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++)
 		if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
 			set_bit(i, &nd_desc->cmd_mask);
-	set_bit(ND_CMD_CALL, &nd_desc->cmd_mask);
 
 	dsm_mask =
 		(1 << ND_CMD_ARS_CAP) |
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index f5525f8bb770..5c5e7ebba8dc 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -33,7 +33,6 @@
 		| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
 		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
-#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV
 #define NVDIMM_CMD_MAX 31
 
 #define NVDIMM_STANDARD_CMDMASK \
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 09087c38fabd..955265656b96 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -1037,9 +1037,25 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		dimm_name = "bus";
 	}
 
+	/* Validate command family support against bus declared support */
 	if (cmd == ND_CMD_CALL) {
+		unsigned long *mask;
+
 		if (copy_from_user(&pkg, p, sizeof(pkg)))
 			return -EFAULT;
+
+		if (nvdimm) {
+			if (pkg.nd_family > NVDIMM_FAMILY_MAX)
+				return -EINVAL;
+			mask = &nd_desc->dimm_family_mask;
+		} else {
+			if (pkg.nd_family > NVDIMM_BUS_FAMILY_MAX)
+				return -EINVAL;
+			mask = &nd_desc->bus_family_mask;
+		}
+
+		if (!test_bit(pkg.nd_family, mask))
+			return -EINVAL;
 	}
 
 	if (!desc ||
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 18da4059be09..bd39a2cf7972 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -78,6 +78,8 @@ struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
 	unsigned long bus_dsm_mask;
 	unsigned long cmd_mask;
+	unsigned long dimm_family_mask;
+	unsigned long bus_family_mask;
 	struct module *module;
 	char *provider_name;
 	struct device_node *of_node;
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index 0e09dc5cec19..e9468b9332bd 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -245,6 +245,10 @@ struct nd_cmd_pkg {
 #define NVDIMM_FAMILY_MSFT 3
 #define NVDIMM_FAMILY_HYPERV 4
 #define NVDIMM_FAMILY_PAPR 5
+#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_PAPR
+
+#define NVDIMM_BUS_FAMILY_NFIT 0
+#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_NFIT
 
 #define ND_IOCTL_CALL			_IOWR(ND_IOCTL, ND_CMD_CALL,\
 					struct nd_cmd_pkg)
-- 
cgit v1.2.3


From d46e6a2176f8edf7030db34aeb54a4f016fabe0a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 20 Jul 2020 15:07:35 -0700
Subject: ACPI: NFIT: Move bus_dsm_mask out of generic nvdimm_bus_descriptor

DSMs are strictly an ACPI mechanism, evict the bus_dsm_mask concept from
the generic 'struct nvdimm_bus_descriptor' object.

As a side effect the test facility ->bus_nfit_cmd_force_en is no longer
necessary. The test infrastructure can communicate that information
directly in ->bus_dsm_mask.

Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 drivers/acpi/nfit/core.c         |  8 ++++----
 drivers/acpi/nfit/nfit.h         |  2 +-
 include/linux/libnvdimm.h        |  1 -
 tools/testing/nvdimm/test/nfit.c | 16 ++++++++--------
 4 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 1f72ce1a782b..9fdd655bdf0e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -478,7 +478,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 
 		cmd_name = nvdimm_bus_cmd_name(cmd);
 		cmd_mask = nd_desc->cmd_mask;
-		dsm_mask = nd_desc->bus_dsm_mask;
+		dsm_mask = acpi_desc->bus_dsm_mask;
 		desc = nd_cmd_bus_desc(cmd);
 		guid = to_nfit_uuid(NFIT_DEV_BUS);
 		handle = adev->handle;
@@ -1238,8 +1238,9 @@ static ssize_t bus_dsm_mask_show(struct device *dev,
 {
 	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%#lx\n", nd_desc->bus_dsm_mask);
+	return sprintf(buf, "%#lx\n", acpi_desc->bus_dsm_mask);
 }
 static struct device_attribute dev_attr_bus_dsm_mask =
 		__ATTR(dsm_mask, 0444, bus_dsm_mask_show, NULL);
@@ -2157,7 +2158,6 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	int i;
 
 	nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
-	nd_desc->bus_dsm_mask = acpi_desc->bus_nfit_cmd_force_en;
 	set_bit(ND_CMD_CALL, &nd_desc->cmd_mask);
 	set_bit(NVDIMM_BUS_FAMILY_NFIT, &nd_desc->bus_family_mask);
 
@@ -2180,7 +2180,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 		(1 << NFIT_CMD_ARS_INJECT_GET);
 	for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
 		if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
-			set_bit(i, &nd_desc->bus_dsm_mask);
+			set_bit(i, &acpi_desc->bus_dsm_mask);
 }
 
 static ssize_t range_index_show(struct device *dev,
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 5c5e7ebba8dc..da097149d94d 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -237,7 +237,7 @@ struct acpi_nfit_desc {
 	unsigned long scrub_flags;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
-	unsigned long bus_nfit_cmd_force_en;
+	unsigned long bus_dsm_mask;
 	unsigned int platform_cap;
 	unsigned int scrub_tmo;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index bd39a2cf7972..ad9898ece7d3 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -76,7 +76,6 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 struct device_node;
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
-	unsigned long bus_dsm_mask;
 	unsigned long cmd_mask;
 	unsigned long dimm_family_mask;
 	unsigned long bus_family_mask;
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a8ee5c4d41eb..a59174ba1d2a 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -2507,10 +2507,10 @@ static void nfit_test0_setup(struct nfit_test *t)
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_CALL, &acpi_desc->bus_cmd_force_en);
-	set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_nfit_cmd_force_en);
-	set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_nfit_cmd_force_en);
-	set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_nfit_cmd_force_en);
-	set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_nfit_cmd_force_en);
+	set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_dsm_mask);
+	set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_dsm_mask);
+	set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_dsm_mask);
+	set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_dsm_mask);
 	set_bit(ND_INTEL_FW_GET_INFO, &acpi_desc->dimm_cmd_force_en);
 	set_bit(ND_INTEL_FW_START_UPDATE, &acpi_desc->dimm_cmd_force_en);
 	set_bit(ND_INTEL_FW_SEND_DATA, &acpi_desc->dimm_cmd_force_en);
@@ -2731,11 +2731,11 @@ static int nfit_ctl_test(struct device *dev)
 			.module = THIS_MODULE,
 			.provider_name = "ACPI.NFIT",
 			.ndctl = acpi_nfit_ctl,
-			.bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA
-				| 1UL << NFIT_CMD_ARS_INJECT_SET
-				| 1UL << NFIT_CMD_ARS_INJECT_CLEAR
-				| 1UL << NFIT_CMD_ARS_INJECT_GET,
 		},
+		.bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA
+			| 1UL << NFIT_CMD_ARS_INJECT_SET
+			| 1UL << NFIT_CMD_ARS_INJECT_CLEAR
+			| 1UL << NFIT_CMD_ARS_INJECT_GET,
 		.dev = &adev->dev,
 	};
 
-- 
cgit v1.2.3


From 60d360acddc54344409a710af07c561e025f13f5 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 20 Jul 2020 15:08:07 -0700
Subject: driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW}

A common pattern for using plain DEVICE_ATTR() instead of
DEVICE_ATTR_RO() and DEVICE_ATTR_RW() is for attributes that want to
limit read to only root.  I.e. many users of DEVICE_ATTR() are
specifying 0400 or 0600 for permissions.

Given the expectation that CAP_SYS_ADMIN is needed to access these
sensitive attributes add an explicit helper with the _ADMIN_ identifier
for DEVICE_ATTR_ADMIN_{RO,RW}.

Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 include/linux/device.h | 4 ++++
 include/linux/sysfs.h  | 7 +++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 15460a5ac024..d7c2570368fa 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -128,8 +128,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
 		__ATTR_PREALLOC(_name, _mode, _show, _store)
 #define DEVICE_ATTR_RW(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
+#define DEVICE_ATTR_ADMIN_RW(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600)
 #define DEVICE_ATTR_RO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
+#define DEVICE_ATTR_ADMIN_RO(_name) \
+	struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400)
 #define DEVICE_ATTR_WO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
 #define DEVICE_ULONG_ATTR(_name, _mode, _var) \
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 86067dbe7745..34e84122f635 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -123,6 +123,13 @@ struct attribute_group {
 	.show	= _name##_show,						\
 }
 
+#define __ATTR_RW_MODE(_name, _mode) {					\
+	.attr	= { .name = __stringify(_name),				\
+		    .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
+	.show	= _name##_show,						\
+	.store	= _name##_store,					\
+}
+
 #define __ATTR_WO(_name) {						\
 	.attr	= { .name = __stringify(_name), .mode = 0200 },		\
 	.store	= _name##_store,					\
-- 
cgit v1.2.3


From a228a64fc1e4428e2b96dc68e9ad3c447095c9e7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 1 Jul 2020 18:10:18 -0700
Subject: bpf: Add bpf_prog iterator

It's mostly a copy paste of commit 6086d29def80 ("bpf: Add bpf_map iterator")
that is use to implement bpf_seq_file opreations to traverse all bpf programs.

v1->v2: Tweak to use build time btf_id

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h    |   1 +
 kernel/bpf/Makefile    |   2 +-
 kernel/bpf/prog_iter.c | 103 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c   |  19 +++++++++
 4 files changed, 124 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/prog_iter.c

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bae557ff2da8..72221aea1c60 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1117,6 +1117,7 @@ int  generic_map_delete_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,
 			      union bpf_attr __user *uattr);
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
+struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1131a921e1a6..e6eb9c0402da 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -2,7 +2,7 @@
 obj-y := core.o
 CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
diff --git a/kernel/bpf/prog_iter.c b/kernel/bpf/prog_iter.c
new file mode 100644
index 000000000000..6541b577d69f
--- /dev/null
+++ b/kernel/bpf/prog_iter.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+#include <linux/btf_ids.h>
+
+struct bpf_iter_seq_prog_info {
+	u32 prog_id;
+};
+
+static void *bpf_prog_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_prog_info *info = seq->private;
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_get_curr_or_next(&info->prog_id);
+	if (!prog)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return prog;
+}
+
+static void *bpf_prog_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_prog_info *info = seq->private;
+
+	++*pos;
+	++info->prog_id;
+	bpf_prog_put((struct bpf_prog *)v);
+	return bpf_prog_get_curr_or_next(&info->prog_id);
+}
+
+struct bpf_iter__bpf_prog {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_prog *, prog);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_prog, struct bpf_iter_meta *meta, struct bpf_prog *prog)
+
+static int __bpf_prog_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter__bpf_prog ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.meta = &meta;
+	ctx.prog = v;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	return ret;
+}
+
+static int bpf_prog_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_prog_seq_show(seq, v, false);
+}
+
+static void bpf_prog_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_prog_seq_show(seq, v, true);
+	else
+		bpf_prog_put((struct bpf_prog *)v);
+}
+
+static const struct seq_operations bpf_prog_seq_ops = {
+	.start	= bpf_prog_seq_start,
+	.next	= bpf_prog_seq_next,
+	.stop	= bpf_prog_seq_stop,
+	.show	= bpf_prog_seq_show,
+};
+
+BTF_ID_LIST(btf_bpf_prog_id)
+BTF_ID(struct, bpf_prog)
+
+static struct bpf_iter_reg bpf_prog_reg_info = {
+	.target			= "bpf_prog",
+	.seq_ops		= &bpf_prog_seq_ops,
+	.init_seq_private	= NULL,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_prog_info),
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_prog, prog),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+};
+
+static int __init bpf_prog_iter_init(void)
+{
+	bpf_prog_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_prog_id;
+	return bpf_iter_reg_target(&bpf_prog_reg_info);
+}
+
+late_initcall(bpf_prog_iter_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d07417d17712..ee290b1f2d9e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3044,6 +3044,25 @@ again:
 	return map;
 }
 
+struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id)
+{
+	struct bpf_prog *prog;
+
+	spin_lock_bh(&prog_idr_lock);
+again:
+	prog = idr_get_next(&prog_idr, id);
+	if (prog) {
+		prog = bpf_prog_inc_not_zero(prog);
+		if (IS_ERR(prog)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&prog_idr_lock);
+
+	return prog;
+}
+
 #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
 
 struct bpf_prog *bpf_prog_by_id(u32 id)
-- 
cgit v1.2.3


From 14fc6bd6b79c430f615500d0fe6cea4722110db8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Jul 2020 11:41:09 -0700
Subject: bpf: Refactor bpf_iter_reg to have separate seq_info member

There is no functionality change for this patch.
Struct bpf_iter_reg is used to register a bpf_iter target,
which includes information for both prog_load, link_create
and seq_file creation.

This patch puts fields related seq_file creation into
a different structure. This will be useful for map
elements iterator where one iterator covers different
map types and different map types may have different
seq_ops, init/fini private_data function and
private_data size.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
---
 include/linux/bpf.h      | 17 ++++++++++-------
 kernel/bpf/bpf_iter.c    | 12 ++++++------
 kernel/bpf/map_iter.c    |  8 ++++++--
 kernel/bpf/prog_iter.c   |  8 ++++++--
 kernel/bpf/task_iter.c   | 16 ++++++++++++----
 net/ipv4/tcp_ipv4.c      |  8 ++++++--
 net/ipv4/udp.c           |  8 ++++++--
 net/ipv6/route.c         |  8 ++++++--
 net/netlink/af_netlink.c |  8 ++++++--
 9 files changed, 64 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 72221aea1c60..127067f71fd4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -37,6 +37,15 @@ struct seq_operations;
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 
+typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
+typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
+struct bpf_iter_seq_info {
+	const struct seq_operations *seq_ops;
+	bpf_iter_init_seq_priv_t init_seq_private;
+	bpf_iter_fini_seq_priv_t fini_seq_private;
+	u32 seq_priv_size;
+};
+
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
@@ -1189,18 +1198,12 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
 	extern int bpf_iter_ ## target(args);			\
 	int __init bpf_iter_ ## target(args) { return 0; }
 
-typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
-typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
-
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
-	const struct seq_operations *seq_ops;
-	bpf_iter_init_seq_priv_t init_seq_private;
-	bpf_iter_fini_seq_priv_t fini_seq_private;
-	u32 seq_priv_size;
 	u32 ctx_arg_info_size;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
+	const struct bpf_iter_seq_info *seq_info;
 };
 
 struct bpf_iter_meta {
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index dd612b80b9fe..5b2387d6aa1f 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -218,8 +218,8 @@ static int iter_release(struct inode *inode, struct file *file)
 	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
 				 target_private);
 
-	if (iter_priv->tinfo->reg_info->fini_seq_private)
-		iter_priv->tinfo->reg_info->fini_seq_private(seq->private);
+	if (iter_priv->tinfo->reg_info->seq_info->fini_seq_private)
+		iter_priv->tinfo->reg_info->seq_info->fini_seq_private(seq->private);
 
 	bpf_prog_put(iter_priv->prog);
 	seq->private = iter_priv;
@@ -433,16 +433,16 @@ static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
 
 	tinfo = link->tinfo;
 	total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) +
-			   tinfo->reg_info->seq_priv_size;
-	priv_data = __seq_open_private(file, tinfo->reg_info->seq_ops,
+			   tinfo->reg_info->seq_info->seq_priv_size;
+	priv_data = __seq_open_private(file, tinfo->reg_info->seq_info->seq_ops,
 				       total_priv_dsize);
 	if (!priv_data) {
 		err = -ENOMEM;
 		goto release_prog;
 	}
 
-	if (tinfo->reg_info->init_seq_private) {
-		err = tinfo->reg_info->init_seq_private(priv_data->target_private);
+	if (tinfo->reg_info->seq_info->init_seq_private) {
+		err = tinfo->reg_info->seq_info->init_seq_private(priv_data->target_private);
 		if (err)
 			goto release_seq_file;
 	}
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 5926c76d854e..1a69241fb1e2 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -81,17 +81,21 @@ static const struct seq_operations bpf_map_seq_ops = {
 BTF_ID_LIST(btf_bpf_map_id)
 BTF_ID(struct, bpf_map)
 
-static struct bpf_iter_reg bpf_map_reg_info = {
-	.target			= "bpf_map",
+static const struct bpf_iter_seq_info bpf_map_seq_info = {
 	.seq_ops		= &bpf_map_seq_ops,
 	.init_seq_private	= NULL,
 	.fini_seq_private	= NULL,
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_map_info),
+};
+
+static struct bpf_iter_reg bpf_map_reg_info = {
+	.target			= "bpf_map",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map, map),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &bpf_map_seq_info,
 };
 
 static int __init bpf_map_iter_init(void)
diff --git a/kernel/bpf/prog_iter.c b/kernel/bpf/prog_iter.c
index 6541b577d69f..53a73c841c13 100644
--- a/kernel/bpf/prog_iter.c
+++ b/kernel/bpf/prog_iter.c
@@ -81,17 +81,21 @@ static const struct seq_operations bpf_prog_seq_ops = {
 BTF_ID_LIST(btf_bpf_prog_id)
 BTF_ID(struct, bpf_prog)
 
-static struct bpf_iter_reg bpf_prog_reg_info = {
-	.target			= "bpf_prog",
+static const struct bpf_iter_seq_info bpf_prog_seq_info = {
 	.seq_ops		= &bpf_prog_seq_ops,
 	.init_seq_private	= NULL,
 	.fini_seq_private	= NULL,
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_prog_info),
+};
+
+static struct bpf_iter_reg bpf_prog_reg_info = {
+	.target			= "bpf_prog",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_prog, prog),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &bpf_prog_seq_info,
 };
 
 static int __init bpf_prog_iter_init(void)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 1039e52ebd8b..6d9cd23869bf 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -319,25 +319,32 @@ BTF_ID_LIST(btf_task_file_ids)
 BTF_ID(struct, task_struct)
 BTF_ID(struct, file)
 
-static struct bpf_iter_reg task_reg_info = {
-	.target			= "task",
+static const struct bpf_iter_seq_info task_seq_info = {
 	.seq_ops		= &task_seq_ops,
 	.init_seq_private	= init_seq_pidns,
 	.fini_seq_private	= fini_seq_pidns,
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_info),
+};
+
+static struct bpf_iter_reg task_reg_info = {
+	.target			= "task",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task, task),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &task_seq_info,
 };
 
-static struct bpf_iter_reg task_file_reg_info = {
-	.target			= "task_file",
+static const struct bpf_iter_seq_info task_file_seq_info = {
 	.seq_ops		= &task_file_seq_ops,
 	.init_seq_private	= init_seq_pidns,
 	.fini_seq_private	= fini_seq_pidns,
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_file_info),
+};
+
+static struct bpf_iter_reg task_file_reg_info = {
+	.target			= "task_file",
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task_file, task),
@@ -345,6 +352,7 @@ static struct bpf_iter_reg task_file_reg_info = {
 		{ offsetof(struct bpf_iter__task_file, file),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &task_file_seq_info,
 };
 
 static int __init task_iter_init(void)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f8913923a6c0..cb288fdcf2ca 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2947,17 +2947,21 @@ static void bpf_iter_fini_tcp(void *priv_data)
 	bpf_iter_fini_seq_net(priv_data);
 }
 
-static struct bpf_iter_reg tcp_reg_info = {
-	.target			= "tcp",
+static const struct bpf_iter_seq_info tcp_seq_info = {
 	.seq_ops		= &bpf_iter_tcp_seq_ops,
 	.init_seq_private	= bpf_iter_init_tcp,
 	.fini_seq_private	= bpf_iter_fini_tcp,
 	.seq_priv_size		= sizeof(struct tcp_iter_state),
+};
+
+static struct bpf_iter_reg tcp_reg_info = {
+	.target			= "tcp",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__tcp, sk_common),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &tcp_seq_info,
 };
 
 static void __init bpf_iter_register(void)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0fb5e4ea133f..1bc50ec2caef 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3208,17 +3208,21 @@ static void bpf_iter_fini_udp(void *priv_data)
 	bpf_iter_fini_seq_net(priv_data);
 }
 
-static struct bpf_iter_reg udp_reg_info = {
-	.target			= "udp",
+static const struct bpf_iter_seq_info udp_seq_info = {
 	.seq_ops		= &bpf_iter_udp_seq_ops,
 	.init_seq_private	= bpf_iter_init_udp,
 	.fini_seq_private	= bpf_iter_fini_udp,
 	.seq_priv_size		= sizeof(struct udp_iter_state),
+};
+
+static struct bpf_iter_reg udp_reg_info = {
+	.target			= "udp",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__udp, udp_sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &udp_seq_info,
 };
 
 static void __init bpf_iter_register(void)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 33f5efbad0a9..8bfc57b0802a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6427,17 +6427,21 @@ DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *r
 BTF_ID_LIST(btf_fib6_info_id)
 BTF_ID(struct, fib6_info)
 
-static struct bpf_iter_reg ipv6_route_reg_info = {
-	.target			= "ipv6_route",
+static const struct bpf_iter_seq_info ipv6_route_seq_info = {
 	.seq_ops		= &ipv6_route_seq_ops,
 	.init_seq_private	= bpf_iter_init_seq_net,
 	.fini_seq_private	= bpf_iter_fini_seq_net,
 	.seq_priv_size		= sizeof(struct ipv6_route_iter),
+};
+
+static struct bpf_iter_reg ipv6_route_reg_info = {
+	.target			= "ipv6_route",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__ipv6_route, rt),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &ipv6_route_seq_info,
 };
 
 static int __init bpf_iter_register(void)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d8921b833744..b5f30d7d30d0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2807,17 +2807,21 @@ static const struct rhashtable_params netlink_rhashtable_params = {
 BTF_ID_LIST(btf_netlink_sock_id)
 BTF_ID(struct, netlink_sock)
 
-static struct bpf_iter_reg netlink_reg_info = {
-	.target			= "netlink",
+static const struct bpf_iter_seq_info netlink_seq_info = {
 	.seq_ops		= &netlink_seq_ops,
 	.init_seq_private	= bpf_iter_init_seq_net,
 	.fini_seq_private	= bpf_iter_fini_seq_net,
 	.seq_priv_size		= sizeof(struct nl_seq_iter),
+};
+
+static struct bpf_iter_reg netlink_reg_info = {
+	.target			= "netlink",
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__netlink, sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},
+	.seq_info		= &netlink_seq_info,
 };
 
 static int __init bpf_iter_register(void)
-- 
cgit v1.2.3


From f9c792729581bd8b8473af163e8ab426c2c61d89 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Jul 2020 11:41:10 -0700
Subject: bpf: Refactor to provide aux info to bpf_iter_init_seq_priv_t

This patch refactored target bpf_iter_init_seq_priv_t callback
function to accept additional information. This will be needed
in later patches for map element targets since a particular
map should be passed to traverse elements for that particular
map. In the future, other information may be passed to target
as well, e.g., pid, cgroup id, etc. to customize the iterator.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com
---
 fs/proc/proc_net.c      | 2 +-
 include/linux/bpf.h     | 7 ++++++-
 include/linux/proc_fs.h | 3 ++-
 kernel/bpf/bpf_iter.c   | 2 +-
 kernel/bpf/task_iter.c  | 2 +-
 net/ipv4/tcp_ipv4.c     | 4 ++--
 net/ipv4/udp.c          | 4 ++--
 7 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index dba63b2429f0..ed8a6306990c 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -98,7 +98,7 @@ static const struct proc_ops proc_net_seq_ops = {
 	.proc_release	= seq_release_net,
 };
 
-int bpf_iter_init_seq_net(void *priv_data)
+int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux)
 {
 #ifdef CONFIG_NET_NS
 	struct seq_net_private *p = priv_data;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 127067f71fd4..ef52717336cf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -33,11 +33,13 @@ struct btf;
 struct btf_type;
 struct exception_table_entry;
 struct seq_operations;
+struct bpf_iter_aux_info;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 
-typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
+typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
+					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
 struct bpf_iter_seq_info {
 	const struct seq_operations *seq_ops;
@@ -1198,6 +1200,9 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
 	extern int bpf_iter_ ## target(args);			\
 	int __init bpf_iter_ ## target(args) { return 0; }
 
+struct bpf_iter_aux_info {
+};
+
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index d1eed1b43651..2df965cd0974 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -133,7 +133,8 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 						    void *data);
 extern struct pid *tgid_pidfd_to_pid(const struct file *file);
 
-extern int bpf_iter_init_seq_net(void *priv_data);
+struct bpf_iter_aux_info;
+extern int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux);
 extern void bpf_iter_fini_seq_net(void *priv_data);
 
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 5b2387d6aa1f..8fa94cb1b5a0 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -442,7 +442,7 @@ static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
 	}
 
 	if (tinfo->reg_info->seq_info->init_seq_private) {
-		err = tinfo->reg_info->seq_info->init_seq_private(priv_data->target_private);
+		err = tinfo->reg_info->seq_info->init_seq_private(priv_data->target_private, NULL);
 		if (err)
 			goto release_seq_file;
 	}
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 6d9cd23869bf..232df29793e9 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -293,7 +293,7 @@ static void task_file_seq_stop(struct seq_file *seq, void *v)
 	}
 }
 
-static int init_seq_pidns(void *priv_data)
+static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux)
 {
 	struct bpf_iter_seq_task_common *common = priv_data;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cb288fdcf2ca..5084333b5ab6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2921,7 +2921,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
 DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta,
 		     struct sock_common *sk_common, uid_t uid)
 
-static int bpf_iter_init_tcp(void *priv_data)
+static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux)
 {
 	struct tcp_iter_state *st = priv_data;
 	struct tcp_seq_afinfo *afinfo;
@@ -2933,7 +2933,7 @@ static int bpf_iter_init_tcp(void *priv_data)
 
 	afinfo->family = AF_UNSPEC;
 	st->bpf_seq_afinfo = afinfo;
-	ret = bpf_iter_init_seq_net(priv_data);
+	ret = bpf_iter_init_seq_net(priv_data, aux);
 	if (ret)
 		kfree(afinfo);
 	return ret;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1bc50ec2caef..7ce31beccfc2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3181,7 +3181,7 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = {
 DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
 		     struct udp_sock *udp_sk, uid_t uid, int bucket)
 
-static int bpf_iter_init_udp(void *priv_data)
+static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
 {
 	struct udp_iter_state *st = priv_data;
 	struct udp_seq_afinfo *afinfo;
@@ -3194,7 +3194,7 @@ static int bpf_iter_init_udp(void *priv_data)
 	afinfo->family = AF_UNSPEC;
 	afinfo->udp_table = &udp_table;
 	st->bpf_seq_afinfo = afinfo;
-	ret = bpf_iter_init_seq_net(priv_data);
+	ret = bpf_iter_init_seq_net(priv_data, aux);
 	if (ret)
 		kfree(afinfo);
 	return ret;
-- 
cgit v1.2.3


From afbf21dce668ef59482037596eaffbe5041e094c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Jul 2020 11:41:11 -0700
Subject: bpf: Support readonly/readwrite buffers in verifier

Readonly and readwrite buffer register states
are introduced. Totally four states,
PTR_TO_RDONLY_BUF[_OR_NULL] and PTR_TO_RDWR_BUF[_OR_NULL]
are supported. As suggested by their respective
names, PTR_TO_RDONLY_BUF[_OR_NULL] are for
readonly buffers and PTR_TO_RDWR_BUF[_OR_NULL]
for read/write buffers.

These new register states will be used
by later bpf map element iterator.

New register states share some similarity to
PTR_TO_TP_BUFFER as it will calculate accessed buffer
size during verification time. The accessed buffer
size will be later compared to other metrics during
later attach/link_create time.

Similar to reg_state PTR_TO_BTF_ID_OR_NULL in bpf
iterator programs, PTR_TO_RDONLY_BUF_OR_NULL or
PTR_TO_RDWR_BUF_OR_NULL reg_types can be set at
prog->aux->bpf_ctx_arg_aux, and bpf verifier will
retrieve the values during btf_ctx_access().
Later bpf map element iterator implementation
will show how such information will be assigned
during target registeration time.

The verifier is also enhanced such that PTR_TO_RDONLY_BUF
can be passed to ARG_PTR_TO_MEM[_OR_NULL] helper argument, and
PTR_TO_RDWR_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] or
ARG_PTR_TO_UNINIT_MEM.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184111.590274-1-yhs@fb.com
---
 include/linux/bpf.h   |  6 ++++
 kernel/bpf/btf.c      | 13 ++++++++
 kernel/bpf/verifier.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 104 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ef52717336cf..f9c4bb08f616 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -353,6 +353,10 @@ enum bpf_reg_type {
 	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
+	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
+	PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
+	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
+	PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -694,6 +698,8 @@ struct bpf_prog_aux {
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
 	u32 ctx_arg_info_size;
+	u32 max_rdonly_access;
+	u32 max_rdwr_access;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
 	struct bpf_prog *linked_prog;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ee36b7f60936..0fd6bb62be3a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3806,6 +3806,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			btf_kind_str[BTF_INFO_KIND(t->info)]);
 		return false;
 	}
+
+	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
+	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
+		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+
+		if (ctx_arg_info->offset == off &&
+		    (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
+		     ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+			info->reg_type = ctx_arg_info->reg_type;
+			return true;
+		}
+	}
+
 	if (t->type == 0)
 		/* This is a pointer to void.
 		 * It is the same as scalar from the verifier safety pov.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9a6703bc3f36..8d6979db48d8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -409,7 +409,9 @@ static bool reg_type_may_be_null(enum bpf_reg_type type)
 	       type == PTR_TO_SOCK_COMMON_OR_NULL ||
 	       type == PTR_TO_TCP_SOCK_OR_NULL ||
 	       type == PTR_TO_BTF_ID_OR_NULL ||
-	       type == PTR_TO_MEM_OR_NULL;
+	       type == PTR_TO_MEM_OR_NULL ||
+	       type == PTR_TO_RDONLY_BUF_OR_NULL ||
+	       type == PTR_TO_RDWR_BUF_OR_NULL;
 }
 
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
@@ -503,6 +505,10 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
 	[PTR_TO_MEM]		= "mem",
 	[PTR_TO_MEM_OR_NULL]	= "mem_or_null",
+	[PTR_TO_RDONLY_BUF]	= "rdonly_buf",
+	[PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
+	[PTR_TO_RDWR_BUF]	= "rdwr_buf",
+	[PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
 };
 
 static char slot_type_char[] = {
@@ -2173,6 +2179,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
 	case PTR_TO_BTF_ID_OR_NULL:
+	case PTR_TO_RDONLY_BUF:
+	case PTR_TO_RDONLY_BUF_OR_NULL:
+	case PTR_TO_RDWR_BUF:
+	case PTR_TO_RDWR_BUF_OR_NULL:
 		return true;
 	default:
 		return false;
@@ -3052,14 +3062,15 @@ int check_ctx_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_tp_buffer_access(struct bpf_verifier_env *env,
-				  const struct bpf_reg_state *reg,
-				  int regno, int off, int size)
+static int __check_buffer_access(struct bpf_verifier_env *env,
+				 const char *buf_info,
+				 const struct bpf_reg_state *reg,
+				 int regno, int off, int size)
 {
 	if (off < 0) {
 		verbose(env,
-			"R%d invalid tracepoint buffer access: off=%d, size=%d",
-			regno, off, size);
+			"R%d invalid %s buffer access: off=%d, size=%d",
+			regno, buf_info, off, size);
 		return -EACCES;
 	}
 	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
@@ -3071,12 +3082,45 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env,
 			regno, off, tn_buf);
 		return -EACCES;
 	}
+
+	return 0;
+}
+
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg,
+				  int regno, int off, int size)
+{
+	int err;
+
+	err = __check_buffer_access(env, "tracepoint", reg, regno, off, size);
+	if (err)
+		return err;
+
 	if (off + size > env->prog->aux->max_tp_access)
 		env->prog->aux->max_tp_access = off + size;
 
 	return 0;
 }
 
+static int check_buffer_access(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg,
+			       int regno, int off, int size,
+			       bool zero_size_allowed,
+			       const char *buf_info,
+			       u32 *max_access)
+{
+	int err;
+
+	err = __check_buffer_access(env, buf_info, reg, regno, off, size);
+	if (err)
+		return err;
+
+	if (off + size > *max_access)
+		*max_access = off + size;
+
+	return 0;
+}
+
 /* BPF architecture zero extends alu32 ops into 64-bit registesr */
 static void zext_32_to_64(struct bpf_reg_state *reg)
 {
@@ -3427,6 +3471,23 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (reg->type == CONST_PTR_TO_MAP) {
 		err = check_ptr_to_map_access(env, regs, regno, off, size, t,
 					      value_regno);
+	} else if (reg->type == PTR_TO_RDONLY_BUF) {
+		if (t == BPF_WRITE) {
+			verbose(env, "R%d cannot write into %s\n",
+				regno, reg_type_str[reg->type]);
+			return -EACCES;
+		}
+		err = check_buffer_access(env, reg, regno, off, size, "rdonly",
+					  false,
+					  &env->prog->aux->max_rdonly_access);
+		if (!err && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_RDWR_BUF) {
+		err = check_buffer_access(env, reg, regno, off, size, "rdwr",
+					  false,
+					  &env->prog->aux->max_rdwr_access);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
@@ -3668,6 +3729,18 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		return check_mem_region_access(env, regno, reg->off,
 					       access_size, reg->mem_size,
 					       zero_size_allowed);
+	case PTR_TO_RDONLY_BUF:
+		if (meta && meta->raw_mode)
+			return -EACCES;
+		return check_buffer_access(env, reg, regno, reg->off,
+					   access_size, zero_size_allowed,
+					   "rdonly",
+					   &env->prog->aux->max_rdonly_access);
+	case PTR_TO_RDWR_BUF:
+		return check_buffer_access(env, reg, regno, reg->off,
+					   access_size, zero_size_allowed,
+					   "rdwr",
+					   &env->prog->aux->max_rdwr_access);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
@@ -3933,6 +4006,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		else if (!type_is_pkt_pointer(type) &&
 			 type != PTR_TO_MAP_VALUE &&
 			 type != PTR_TO_MEM &&
+			 type != PTR_TO_RDONLY_BUF &&
+			 type != PTR_TO_RDWR_BUF &&
 			 type != expected_type)
 			goto err_type;
 		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
@@ -6806,6 +6881,10 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 			reg->type = PTR_TO_BTF_ID;
 		} else if (reg->type == PTR_TO_MEM_OR_NULL) {
 			reg->type = PTR_TO_MEM;
+		} else if (reg->type == PTR_TO_RDONLY_BUF_OR_NULL) {
+			reg->type = PTR_TO_RDONLY_BUF;
+		} else if (reg->type == PTR_TO_RDWR_BUF_OR_NULL) {
+			reg->type = PTR_TO_RDWR_BUF;
 		}
 		if (is_null) {
 			/* We don't need id and ref_obj_id from this point
-- 
cgit v1.2.3


From a5cbe05a6673b85bed2a63ffcfea6a96c6410cff Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Jul 2020 11:41:12 -0700
Subject: bpf: Implement bpf iterator for map elements

The bpf iterator for map elements are implemented.
The bpf program will receive four parameters:
  bpf_iter_meta *meta: the meta data
  bpf_map *map:        the bpf_map whose elements are traversed
  void *key:           the key of one element
  void *value:         the value of the same element

Here, meta and map pointers are always valid, and
key has register type PTR_TO_RDONLY_BUF_OR_NULL and
value has register type PTR_TO_RDWR_BUF_OR_NULL.
The kernel will track the access range of key and value
during verification time. Later, these values will be compared
against the values in the actual map to ensure all accesses
are within range.

A new field iter_seq_info is added to bpf_map_ops which
is used to add map type specific information, i.e., seq_ops,
init/fini seq_file func and seq_file private data size.
Subsequent patches will have actual implementation
for bpf_map_ops->iter_seq_info.

In user space, BPF_ITER_LINK_MAP_FD needs to be
specified in prog attr->link_create.flags, which indicates
that attr->link_create.target_fd is a map_fd.
The reason for such an explicit flag is for possible
future cases where one bpf iterator may allow more than
one possible customization, e.g., pid and cgroup id for
task_file.

Current kernel internal implementation only allows
the target to register at most one required bpf_iter_link_info.
To support the above case, optional bpf_iter_link_info's
are needed, the target can be extended to register such link
infos, and user provided link_info needs to match one of
target supported ones.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com
---
 include/linux/bpf.h            | 16 ++++++++
 include/uapi/linux/bpf.h       |  7 ++++
 kernel/bpf/bpf_iter.c          | 85 ++++++++++++++++++++++++++++++++++--------
 kernel/bpf/map_iter.c          | 30 ++++++++++++++-
 tools/include/uapi/linux/bpf.h |  7 ++++
 5 files changed, 128 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f9c4bb08f616..4175cf1f4665 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -107,6 +107,9 @@ struct bpf_map_ops {
 	/* BTF name and id of struct allocated by map_alloc */
 	const char * const map_btf_name;
 	int *map_btf_id;
+
+	/* bpf_iter info used to open a seq_file */
+	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
 struct bpf_map_memory {
@@ -1207,12 +1210,18 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
 	int __init bpf_iter_ ## target(args) { return 0; }
 
 struct bpf_iter_aux_info {
+	struct bpf_map *map;
 };
 
+typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog,
+				       struct bpf_iter_aux_info *aux);
+
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
+	bpf_iter_check_target_t check_target;
 	u32 ctx_arg_info_size;
+	enum bpf_iter_link_info req_linfo;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
 };
@@ -1223,6 +1232,13 @@ struct bpf_iter_meta {
 	u64 seq_num;
 };
 
+struct bpf_iter__bpf_map_elem {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+	__bpf_md_ptr(void *, key);
+	__bpf_md_ptr(void *, value);
+};
+
 int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 54d0c886e3ba..828c2f6438f2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -246,6 +246,13 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
+enum bpf_iter_link_info {
+	BPF_ITER_LINK_UNSPEC = 0,
+	BPF_ITER_LINK_MAP_FD = 1,
+
+	MAX_BPF_ITER_LINK_INFO,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 8fa94cb1b5a0..363b9cafc2d8 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -14,11 +14,13 @@ struct bpf_iter_target_info {
 
 struct bpf_iter_link {
 	struct bpf_link link;
+	struct bpf_iter_aux_info aux;
 	struct bpf_iter_target_info *tinfo;
 };
 
 struct bpf_iter_priv_data {
 	struct bpf_iter_target_info *tinfo;
+	const struct bpf_iter_seq_info *seq_info;
 	struct bpf_prog *prog;
 	u64 session_id;
 	u64 seq_num;
@@ -35,7 +37,8 @@ static DEFINE_MUTEX(link_mutex);
 /* incremented on every opened seq_file */
 static atomic64_t session_id;
 
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
+			    const struct bpf_iter_seq_info *seq_info);
 
 static void bpf_iter_inc_seq_num(struct seq_file *seq)
 {
@@ -199,11 +202,25 @@ done:
 	return copied;
 }
 
+static const struct bpf_iter_seq_info *
+__get_seq_info(struct bpf_iter_link *link)
+{
+	const struct bpf_iter_seq_info *seq_info;
+
+	if (link->aux.map) {
+		seq_info = link->aux.map->ops->iter_seq_info;
+		if (seq_info)
+			return seq_info;
+	}
+
+	return link->tinfo->reg_info->seq_info;
+}
+
 static int iter_open(struct inode *inode, struct file *file)
 {
 	struct bpf_iter_link *link = inode->i_private;
 
-	return prepare_seq_file(file, link);
+	return prepare_seq_file(file, link, __get_seq_info(link));
 }
 
 static int iter_release(struct inode *inode, struct file *file)
@@ -218,8 +235,8 @@ static int iter_release(struct inode *inode, struct file *file)
 	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
 				 target_private);
 
-	if (iter_priv->tinfo->reg_info->seq_info->fini_seq_private)
-		iter_priv->tinfo->reg_info->seq_info->fini_seq_private(seq->private);
+	if (iter_priv->seq_info->fini_seq_private)
+		iter_priv->seq_info->fini_seq_private(seq->private);
 
 	bpf_prog_put(iter_priv->prog);
 	seq->private = iter_priv;
@@ -318,6 +335,11 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
 
 static void bpf_iter_link_release(struct bpf_link *link)
 {
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+
+	if (iter_link->aux.map)
+		bpf_map_put_with_uref(iter_link->aux.map);
 }
 
 static void bpf_iter_link_dealloc(struct bpf_link *link)
@@ -370,14 +392,13 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_iter_target_info *tinfo;
+	struct bpf_iter_aux_info aux = {};
 	struct bpf_iter_link *link;
+	u32 prog_btf_id, target_fd;
 	bool existed = false;
-	u32 prog_btf_id;
+	struct bpf_map *map;
 	int err;
 
-	if (attr->link_create.target_fd || attr->link_create.flags)
-		return -EINVAL;
-
 	prog_btf_id = prog->aux->attach_btf_id;
 	mutex_lock(&targets_mutex);
 	list_for_each_entry(tinfo, &targets, list) {
@@ -390,6 +411,13 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (!existed)
 		return -ENOENT;
 
+	/* Make sure user supplied flags are target expected. */
+	target_fd = attr->link_create.target_fd;
+	if (attr->link_create.flags != tinfo->reg_info->req_linfo)
+		return -EINVAL;
+	if (!attr->link_create.flags && target_fd)
+		return -EINVAL;
+
 	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
 	if (!link)
 		return -ENOMEM;
@@ -403,21 +431,45 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		return err;
 	}
 
+	if (tinfo->reg_info->req_linfo == BPF_ITER_LINK_MAP_FD) {
+		map = bpf_map_get_with_uref(target_fd);
+		if (IS_ERR(map)) {
+			err = PTR_ERR(map);
+			goto cleanup_link;
+		}
+
+		aux.map = map;
+		err = tinfo->reg_info->check_target(prog, &aux);
+		if (err) {
+			bpf_map_put_with_uref(map);
+			goto cleanup_link;
+		}
+
+		link->aux.map = map;
+	}
+
 	return bpf_link_settle(&link_primer);
+
+cleanup_link:
+	bpf_link_cleanup(&link_primer);
+	return err;
 }
 
 static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
 			  struct bpf_iter_target_info *tinfo,
+			  const struct bpf_iter_seq_info *seq_info,
 			  struct bpf_prog *prog)
 {
 	priv_data->tinfo = tinfo;
+	priv_data->seq_info = seq_info;
 	priv_data->prog = prog;
 	priv_data->session_id = atomic64_inc_return(&session_id);
 	priv_data->seq_num = 0;
 	priv_data->done_stop = false;
 }
 
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
+			    const struct bpf_iter_seq_info *seq_info)
 {
 	struct bpf_iter_priv_data *priv_data;
 	struct bpf_iter_target_info *tinfo;
@@ -433,21 +485,21 @@ static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
 
 	tinfo = link->tinfo;
 	total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) +
-			   tinfo->reg_info->seq_info->seq_priv_size;
-	priv_data = __seq_open_private(file, tinfo->reg_info->seq_info->seq_ops,
+			   seq_info->seq_priv_size;
+	priv_data = __seq_open_private(file, seq_info->seq_ops,
 				       total_priv_dsize);
 	if (!priv_data) {
 		err = -ENOMEM;
 		goto release_prog;
 	}
 
-	if (tinfo->reg_info->seq_info->init_seq_private) {
-		err = tinfo->reg_info->seq_info->init_seq_private(priv_data->target_private, NULL);
+	if (seq_info->init_seq_private) {
+		err = seq_info->init_seq_private(priv_data->target_private, &link->aux);
 		if (err)
 			goto release_seq_file;
 	}
 
-	init_seq_meta(priv_data, tinfo, prog);
+	init_seq_meta(priv_data, tinfo, seq_info, prog);
 	seq = file->private_data;
 	seq->private = priv_data->target_private;
 
@@ -463,6 +515,7 @@ release_prog:
 
 int bpf_iter_new_fd(struct bpf_link *link)
 {
+	struct bpf_iter_link *iter_link;
 	struct file *file;
 	unsigned int flags;
 	int err, fd;
@@ -481,8 +534,8 @@ int bpf_iter_new_fd(struct bpf_link *link)
 		goto free_fd;
 	}
 
-	err = prepare_seq_file(file,
-			       container_of(link, struct bpf_iter_link, link));
+	iter_link = container_of(link, struct bpf_iter_link, link);
+	err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link));
 	if (err)
 		goto free_file;
 
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 1a69241fb1e2..8a1f9b3355d0 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -98,10 +98,38 @@ static struct bpf_iter_reg bpf_map_reg_info = {
 	.seq_info		= &bpf_map_seq_info,
 };
 
+static int bpf_iter_check_map(struct bpf_prog *prog,
+			      struct bpf_iter_aux_info *aux)
+{
+	return -EINVAL;
+}
+
+DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
+		     struct bpf_map *map, void *key, void *value)
+
+static const struct bpf_iter_reg bpf_map_elem_reg_info = {
+	.target			= "bpf_map_elem",
+	.check_target		= bpf_iter_check_map,
+	.req_linfo		= BPF_ITER_LINK_MAP_FD,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_map_elem, key),
+		  PTR_TO_RDONLY_BUF_OR_NULL },
+		{ offsetof(struct bpf_iter__bpf_map_elem, value),
+		  PTR_TO_RDWR_BUF_OR_NULL },
+	},
+};
+
 static int __init bpf_map_iter_init(void)
 {
+	int ret;
+
 	bpf_map_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_map_id;
-	return bpf_iter_reg_target(&bpf_map_reg_info);
+	ret = bpf_iter_reg_target(&bpf_map_reg_info);
+	if (ret)
+		return ret;
+
+	return bpf_iter_reg_target(&bpf_map_elem_reg_info);
 }
 
 late_initcall(bpf_map_iter_init);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 54d0c886e3ba..828c2f6438f2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -246,6 +246,13 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
+enum bpf_iter_link_info {
+	BPF_ITER_LINK_UNSPEC = 0,
+	BPF_ITER_LINK_MAP_FD = 1,
+
+	MAX_BPF_ITER_LINK_INFO,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
-- 
cgit v1.2.3


From 7b04d6d60fcfb5b2200ffebb9cfb90927bdfeec7 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 23 Jul 2020 11:06:44 -0700
Subject: bpf: Separate bpf_get_[stack|stackid] for perf events BPF

Calling get_perf_callchain() on perf_events from PEBS entries may cause
unwinder errors. To fix this issue, the callchain is fetched early. Such
perf_events are marked with __PERF_SAMPLE_CALLCHAIN_EARLY.

Similarly, calling bpf_get_[stack|stackid] on perf_events from PEBS may
also cause unwinder errors. To fix this, add separate version of these
two helpers, bpf_get_[stack|stackid]_pe. These two hepers use callchain in
bpf_perf_event_data_kern->data->callchain.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723180648.1429892-2-songliubraving@fb.com
---
 include/linux/bpf.h      |   2 +
 kernel/bpf/stackmap.c    | 184 ++++++++++++++++++++++++++++++++++++++++++-----
 kernel/trace/bpf_trace.c |   4 +-
 3 files changed, 170 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4175cf1f4665..8357be349133 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1675,6 +1675,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
 extern const struct bpf_func_proto bpf_get_task_stack_proto;
+extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
+extern const struct bpf_func_proto bpf_get_stack_proto_pe;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 48d8e739975f..5beb2f8c23da 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
 #include <linux/elf.h>
@@ -387,11 +388,10 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
 #endif
 }
 
-BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
-	   u64, flags)
+static long __bpf_get_stackid(struct bpf_map *map,
+			      struct perf_callchain_entry *trace, u64 flags)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
-	struct perf_callchain_entry *trace;
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
 	u32 max_depth = map->value_size / stack_map_data_size(map);
 	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
@@ -399,21 +399,9 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	u32 hash, id, trace_nr, trace_len;
 	bool user = flags & BPF_F_USER_STACK;
-	bool kernel = !user;
 	u64 *ips;
 	bool hash_matches;
 
-	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
-			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
-		return -EINVAL;
-
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
-
-	if (unlikely(!trace))
-		/* couldn't fetch the stack trace */
-		return -EFAULT;
-
 	/* get_perf_callchain() guarantees that trace->nr >= init_nr
 	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
 	 */
@@ -478,6 +466,30 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	return id;
 }
 
+BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
+	   u64, flags)
+{
+	u32 max_depth = map->value_size / stack_map_data_size(map);
+	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
+	bool user = flags & BPF_F_USER_STACK;
+	struct perf_callchain_entry *trace;
+	bool kernel = !user;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+
+	if (unlikely(!trace))
+		/* couldn't fetch the stack trace */
+		return -EFAULT;
+
+	return __bpf_get_stackid(map, trace, flags);
+}
+
 const struct bpf_func_proto bpf_get_stackid_proto = {
 	.func		= bpf_get_stackid,
 	.gpl_only	= true,
@@ -487,7 +499,77 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static __u64 count_kernel_ip(struct perf_callchain_entry *trace)
+{
+	__u64 nr_kernel = 0;
+
+	while (nr_kernel < trace->nr) {
+		if (trace->ip[nr_kernel] == PERF_CONTEXT_USER)
+			break;
+		nr_kernel++;
+	}
+	return nr_kernel;
+}
+
+BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_map *, map, u64, flags)
+{
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	__u64 nr_kernel;
+	int ret;
+
+	/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return bpf_get_stackid((unsigned long)(ctx->regs),
+				       (unsigned long) map, flags, 0, 0);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		return -EFAULT;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		ret = __bpf_get_stackid(map, trace, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			return -EFAULT;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		ret = __bpf_get_stackid(map, trace, flags);
+	}
+	return ret;
+}
+
+const struct bpf_func_proto bpf_get_stackid_proto_pe = {
+	.func		= bpf_get_stackid_pe,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    struct perf_callchain_entry *trace_in,
 			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
@@ -520,7 +602,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
 
-	if (kernel && task)
+	if (trace_in)
+		trace = trace_in;
+	else if (kernel && task)
 		trace = get_callchain_entry_for_task(task, init_nr);
 	else
 		trace = get_perf_callchain(regs, init_nr, kernel, user,
@@ -556,7 +640,7 @@ clear:
 BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	   u64, flags)
 {
-	return __bpf_get_stack(regs, NULL, buf, size, flags);
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
 }
 
 const struct bpf_func_proto bpf_get_stack_proto = {
@@ -574,7 +658,7 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 {
 	struct pt_regs *regs = task_pt_regs(task);
 
-	return __bpf_get_stack(regs, task, buf, size, flags);
+	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
 }
 
 BTF_ID_LIST(bpf_get_task_stack_btf_ids)
@@ -591,6 +675,70 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.btf_id		= bpf_get_task_stack_btf_ids,
 };
 
+BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
+	   void *, buf, u32, size, u64, flags)
+{
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	int err = -EINVAL;
+	__u64 nr_kernel;
+
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return __bpf_get_stack(ctx->regs, NULL, NULL, buf, size, flags);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_USER_BUILD_ID)))
+		goto clear;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	err = -EFAULT;
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		goto clear;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		err = __bpf_get_stack(ctx->regs, NULL, trace, buf,
+				      size, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			goto clear;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		err = __bpf_get_stack(ctx->regs, NULL, trace, buf,
+				      size, flags);
+	}
+	return err;
+
+clear:
+	memset(buf, 0, size);
+	return err;
+
+}
+
+const struct bpf_func_proto bpf_get_stack_proto_pe = {
+	.func		= bpf_get_stack_pe,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3cc0dcb60ca2..cb91ef902cc4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1411,9 +1411,9 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
-		return &bpf_get_stackid_proto_tp;
+		return &bpf_get_stackid_proto_pe;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto_tp;
+		return &bpf_get_stack_proto_pe;
 	case BPF_FUNC_perf_prog_read_value:
 		return &bpf_perf_prog_read_value_proto;
 	case BPF_FUNC_read_branch_records:
-- 
cgit v1.2.3


From 5d99cb2c86775b4780c02a339a9578bf9471ead9 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 23 Jul 2020 11:06:45 -0700
Subject: bpf: Fail PERF_EVENT_IOC_SET_BPF when bpf_get_[stack|stackid] cannot
 work

bpf_get_[stack|stackid] on perf_events with precise_ip uses callchain
attached to perf_sample_data. If this callchain is not presented, do not
allow attaching BPF program that calls bpf_get_[stack|stackid] to this
event.

In the error case, -EPROTO is returned so that libbpf can identify this
error and print proper hint message.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723180648.1429892-3-songliubraving@fb.com
---
 include/linux/filter.h |  3 ++-
 kernel/bpf/verifier.c  |  3 +++
 kernel/events/core.c   | 18 ++++++++++++++++++
 3 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index d07a6e973a7d..0a355b005bf4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -533,7 +533,8 @@ struct bpf_prog {
 				is_func:1,	/* program is a bpf function */
 				kprobe_override:1, /* Do we override a kprobe? */
 				has_callchain_buf:1, /* callchain buffer allocated? */
-				enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */
+				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
+				call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	enum bpf_attach_type	expected_attach_type; /* For some prog types */
 	u32			len;		/* Number of filter blocks */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8d6979db48d8..cd14e70f2d07 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4962,6 +4962,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		env->prog->has_callchain_buf = true;
 	}
 
+	if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
+		env->prog->call_get_stack = true;
+
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 856d98c36f56..ddcfd2fb5cc5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9544,6 +9544,24 @@ static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
+	if (event->attr.precise_ip &&
+	    prog->call_get_stack &&
+	    (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY) ||
+	     event->attr.exclude_callchain_kernel ||
+	     event->attr.exclude_callchain_user)) {
+		/*
+		 * On perf_event with precise_ip, calling bpf_get_stack()
+		 * may trigger unwinder warnings and occasional crashes.
+		 * bpf_get_[stack|stackid] works around this issue by using
+		 * callchain attached to perf_sample_data. If the
+		 * perf_event does not full (kernel and user) callchain
+		 * attached to perf_sample_data, do not allow attaching BPF
+		 * program that calls bpf_get_[stack|stackid].
+		 */
+		bpf_prog_put(prog);
+		return -EPROTO;
+	}
+
 	event->prog = prog;
 	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
 	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
-- 
cgit v1.2.3


From 7d9c3427894fe70d1347b4820476bf37736d2ff0 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Thu, 23 Jul 2020 23:47:43 -0500
Subject: bpf: Make cgroup storages shared between programs on the same cgroup

This change comes in several parts:

One, the restriction that the CGROUP_STORAGE map can only be used
by one program is removed. This results in the removal of the field
'aux' in struct bpf_cgroup_storage_map, and removal of relevant
code associated with the field, and removal of now-noop functions
bpf_free_cgroup_storage and bpf_cgroup_storage_release.

Second, we permit a key of type u64 as the key to the map.
Providing such a key type indicates that the map should ignore
attach type when comparing map keys. However, for simplicity newly
linked storage will still have the attach type at link time in
its key struct. cgroup_storage_check_btf is adapted to accept
u64 as the type of the key.

Third, because the storages are now shared, the storages cannot
be unconditionally freed on program detach. There could be two
ways to solve this issue:
* A. Reference count the usage of the storages, and free when the
     last program is detached.
* B. Free only when the storage is impossible to be referred to
     again, i.e. when either the cgroup_bpf it is attached to, or
     the map itself, is freed.
Option A has the side effect that, when the user detach and
reattach a program, whether the program gets a fresh storage
depends on whether there is another program attached using that
storage. This could trigger races if the user is multi-threaded,
and since nondeterminism in data races is evil, go with option B.

The both the map and the cgroup_bpf now tracks their associated
storages, and the storage unlink and free are removed from
cgroup_bpf_detach and added to cgroup_bpf_release and
cgroup_storage_map_free. The latter also new holds the cgroup_mutex
to prevent any races with the former.

Fourth, on attach, we reuse the old storage if the key already
exists in the map, via cgroup_storage_lookup. If the storage
does not exist yet, we create a new one, and publish it at the
last step in the attach process. This does not create a race
condition because for the whole attach the cgroup_mutex is held.
We keep track of an array of new storages that was allocated
and if the process fails only the new storages would get freed.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/d5401c6106728a00890401190db40020a1f84ff1.1595565795.git.zhuyifei@google.com
---
 include/linux/bpf-cgroup.h |  12 ++-
 kernel/bpf/cgroup.c        |  67 ++++++++------
 kernel/bpf/core.c          |  12 ---
 kernel/bpf/local_storage.c | 216 ++++++++++++++++++++++++---------------------
 4 files changed, 164 insertions(+), 143 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 2c6f26670acc..64f367044e25 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -46,7 +46,8 @@ struct bpf_cgroup_storage {
 	};
 	struct bpf_cgroup_storage_map *map;
 	struct bpf_cgroup_storage_key key;
-	struct list_head list;
+	struct list_head list_map;
+	struct list_head list_cg;
 	struct rb_node node;
 	struct rcu_head rcu;
 };
@@ -78,6 +79,9 @@ struct cgroup_bpf {
 	struct list_head progs[MAX_BPF_ATTACH_TYPE];
 	u32 flags[MAX_BPF_ATTACH_TYPE];
 
+	/* list of cgroup shared storages */
+	struct list_head storages;
+
 	/* temp storage for effective prog array used by prog_attach/detach */
 	struct bpf_prog_array *inactive;
 
@@ -161,6 +165,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage
 		this_cpu_write(bpf_cgroup_storage[stype], storage[stype]);
 }
 
+struct bpf_cgroup_storage *
+cgroup_storage_lookup(struct bpf_cgroup_storage_map *map,
+		      void *key, bool locked);
 struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
 					enum bpf_cgroup_storage_type stype);
 void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage);
@@ -169,7 +176,6 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 			     enum bpf_attach_type type);
 void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
 int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map);
-void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map);
 
 int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
@@ -383,8 +389,6 @@ static inline void bpf_cgroup_storage_set(
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {}
 static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux,
 					    struct bpf_map *map) { return 0; }
-static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux,
-					      struct bpf_map *map) {}
 static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
 	struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; }
 static inline void bpf_cgroup_storage_free(
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac53102e244a..957cce1d5168 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -37,17 +37,34 @@ static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[])
 }
 
 static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[],
-				     struct bpf_prog *prog)
+				     struct bpf_cgroup_storage *new_storages[],
+				     enum bpf_attach_type type,
+				     struct bpf_prog *prog,
+				     struct cgroup *cgrp)
 {
 	enum bpf_cgroup_storage_type stype;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_map *map;
+
+	key.cgroup_inode_id = cgroup_id(cgrp);
+	key.attach_type = type;
 
 	for_each_cgroup_storage_type(stype) {
+		map = prog->aux->cgroup_storage[stype];
+		if (!map)
+			continue;
+
+		storages[stype] = cgroup_storage_lookup((void *)map, &key, false);
+		if (storages[stype])
+			continue;
+
 		storages[stype] = bpf_cgroup_storage_alloc(prog, stype);
 		if (IS_ERR(storages[stype])) {
-			storages[stype] = NULL;
-			bpf_cgroup_storages_free(storages);
+			bpf_cgroup_storages_free(new_storages);
 			return -ENOMEM;
 		}
+
+		new_storages[stype] = storages[stype];
 	}
 
 	return 0;
@@ -63,7 +80,7 @@ static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[],
 }
 
 static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
-				     struct cgroup* cgrp,
+				     struct cgroup *cgrp,
 				     enum bpf_attach_type attach_type)
 {
 	enum bpf_cgroup_storage_type stype;
@@ -72,14 +89,6 @@ static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
 		bpf_cgroup_storage_link(storages[stype], cgrp, attach_type);
 }
 
-static void bpf_cgroup_storages_unlink(struct bpf_cgroup_storage *storages[])
-{
-	enum bpf_cgroup_storage_type stype;
-
-	for_each_cgroup_storage_type(stype)
-		bpf_cgroup_storage_unlink(storages[stype]);
-}
-
 /* Called when bpf_cgroup_link is auto-detached from dying cgroup.
  * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It
  * doesn't free link memory, which will eventually be done by bpf_link's
@@ -101,22 +110,23 @@ static void cgroup_bpf_release(struct work_struct *work)
 	struct cgroup *p, *cgrp = container_of(work, struct cgroup,
 					       bpf.release_work);
 	struct bpf_prog_array *old_array;
+	struct list_head *storages = &cgrp->bpf.storages;
+	struct bpf_cgroup_storage *storage, *stmp;
+
 	unsigned int type;
 
 	mutex_lock(&cgroup_mutex);
 
 	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
 		struct list_head *progs = &cgrp->bpf.progs[type];
-		struct bpf_prog_list *pl, *tmp;
+		struct bpf_prog_list *pl, *pltmp;
 
-		list_for_each_entry_safe(pl, tmp, progs, node) {
+		list_for_each_entry_safe(pl, pltmp, progs, node) {
 			list_del(&pl->node);
 			if (pl->prog)
 				bpf_prog_put(pl->prog);
 			if (pl->link)
 				bpf_cgroup_link_auto_detach(pl->link);
-			bpf_cgroup_storages_unlink(pl->storage);
-			bpf_cgroup_storages_free(pl->storage);
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
@@ -126,6 +136,11 @@ static void cgroup_bpf_release(struct work_struct *work)
 		bpf_prog_array_free(old_array);
 	}
 
+	list_for_each_entry_safe(storage, stmp, storages, list_cg) {
+		bpf_cgroup_storage_unlink(storage);
+		bpf_cgroup_storage_free(storage);
+	}
+
 	mutex_unlock(&cgroup_mutex);
 
 	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
@@ -290,6 +305,8 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
 	for (i = 0; i < NR; i++)
 		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
 
+	INIT_LIST_HEAD(&cgrp->bpf.storages);
+
 	for (i = 0; i < NR; i++)
 		if (compute_effective_progs(cgrp, i, &arrays[i]))
 			goto cleanup;
@@ -422,7 +439,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
-	struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
 	struct bpf_prog_list *pl;
 	int err;
 
@@ -455,17 +472,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (IS_ERR(pl))
 		return PTR_ERR(pl);
 
-	if (bpf_cgroup_storages_alloc(storage, prog ? : link->link.prog))
+	if (bpf_cgroup_storages_alloc(storage, new_storage, type,
+				      prog ? : link->link.prog, cgrp))
 		return -ENOMEM;
 
 	if (pl) {
 		old_prog = pl->prog;
-		bpf_cgroup_storages_unlink(pl->storage);
-		bpf_cgroup_storages_assign(old_storage, pl->storage);
 	} else {
 		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
 		if (!pl) {
-			bpf_cgroup_storages_free(storage);
+			bpf_cgroup_storages_free(new_storage);
 			return -ENOMEM;
 		}
 		list_add_tail(&pl->node, progs);
@@ -480,12 +496,11 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (err)
 		goto cleanup;
 
-	bpf_cgroup_storages_free(old_storage);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 	else
 		static_branch_inc(&cgroup_bpf_enabled_key);
-	bpf_cgroup_storages_link(pl->storage, cgrp, type);
+	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
 
 cleanup:
@@ -493,9 +508,7 @@ cleanup:
 		pl->prog = old_prog;
 		pl->link = NULL;
 	}
-	bpf_cgroup_storages_free(pl->storage);
-	bpf_cgroup_storages_assign(pl->storage, old_storage);
-	bpf_cgroup_storages_link(pl->storage, cgrp, type);
+	bpf_cgroup_storages_free(new_storage);
 	if (!old_prog) {
 		list_del(&pl->node);
 		kfree(pl);
@@ -679,8 +692,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
-	bpf_cgroup_storages_unlink(pl->storage);
-	bpf_cgroup_storages_free(pl->storage);
 	kfree(pl);
 	if (list_empty(progs))
 		/* last program was detached, reset flags to zero */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7be02e555ab9..bde93344164d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2097,24 +2097,12 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 								     : 0;
 }
 
-static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux)
-{
-	enum bpf_cgroup_storage_type stype;
-
-	for_each_cgroup_storage_type(stype) {
-		if (!aux->cgroup_storage[stype])
-			continue;
-		bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]);
-	}
-}
-
 void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len)
 {
 	struct bpf_map *map;
 	u32 i;
 
-	bpf_free_cgroup_storage(aux);
 	for (i = 0; i < len; i++) {
 		map = used_maps[i];
 		if (map->ops->map_poke_untrack)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 51bd5a8cb01b..3b2c70197d78 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -9,6 +9,8 @@
 #include <linux/slab.h>
 #include <uapi/linux/btf.h>
 
+#include "../cgroup/cgroup-internal.h"
+
 DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
 
 #ifdef CONFIG_CGROUP_BPF
@@ -20,7 +22,6 @@ struct bpf_cgroup_storage_map {
 	struct bpf_map map;
 
 	spinlock_t lock;
-	struct bpf_prog_aux *aux;
 	struct rb_root root;
 	struct list_head list;
 };
@@ -30,24 +31,41 @@ static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
 	return container_of(map, struct bpf_cgroup_storage_map, map);
 }
 
-static int bpf_cgroup_storage_key_cmp(
-	const struct bpf_cgroup_storage_key *key1,
-	const struct bpf_cgroup_storage_key *key2)
+static bool attach_type_isolated(const struct bpf_map *map)
 {
-	if (key1->cgroup_inode_id < key2->cgroup_inode_id)
-		return -1;
-	else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
-		return 1;
-	else if (key1->attach_type < key2->attach_type)
-		return -1;
-	else if (key1->attach_type > key2->attach_type)
-		return 1;
+	return map->key_size == sizeof(struct bpf_cgroup_storage_key);
+}
+
+static int bpf_cgroup_storage_key_cmp(const struct bpf_cgroup_storage_map *map,
+				      const void *_key1, const void *_key2)
+{
+	if (attach_type_isolated(&map->map)) {
+		const struct bpf_cgroup_storage_key *key1 = _key1;
+		const struct bpf_cgroup_storage_key *key2 = _key2;
+
+		if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+			return -1;
+		else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+			return 1;
+		else if (key1->attach_type < key2->attach_type)
+			return -1;
+		else if (key1->attach_type > key2->attach_type)
+			return 1;
+	} else {
+		const __u64 *cgroup_inode_id1 = _key1;
+		const __u64 *cgroup_inode_id2 = _key2;
+
+		if (*cgroup_inode_id1 < *cgroup_inode_id2)
+			return -1;
+		else if (*cgroup_inode_id1 > *cgroup_inode_id2)
+			return 1;
+	}
 	return 0;
 }
 
-static struct bpf_cgroup_storage *cgroup_storage_lookup(
-	struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
-	bool locked)
+struct bpf_cgroup_storage *
+cgroup_storage_lookup(struct bpf_cgroup_storage_map *map,
+		      void *key, bool locked)
 {
 	struct rb_root *root = &map->root;
 	struct rb_node *node;
@@ -61,7 +79,7 @@ static struct bpf_cgroup_storage *cgroup_storage_lookup(
 
 		storage = container_of(node, struct bpf_cgroup_storage, node);
 
-		switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+		switch (bpf_cgroup_storage_key_cmp(map, key, &storage->key)) {
 		case -1:
 			node = node->rb_left;
 			break;
@@ -93,7 +111,7 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
 		this = container_of(*new, struct bpf_cgroup_storage, node);
 
 		parent = *new;
-		switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+		switch (bpf_cgroup_storage_key_cmp(map, &storage->key, &this->key)) {
 		case -1:
 			new = &((*new)->rb_left);
 			break;
@@ -111,10 +129,9 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
 	return 0;
 }
 
-static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 
 	storage = cgroup_storage_lookup(map, key, false);
@@ -124,17 +141,13 @@ static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
 	return &READ_ONCE(storage->buf)->data[0];
 }
 
-static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
 				      void *value, u64 flags)
 {
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	struct bpf_storage_buffer *new;
 
-	if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST)))
-		return -EINVAL;
-
-	if (unlikely(flags & BPF_NOEXIST))
+	if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST)))
 		return -EINVAL;
 
 	if (unlikely((flags & BPF_F_LOCK) &&
@@ -167,11 +180,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
 	return 0;
 }
 
-int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
 				   void *value)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu, off = 0;
 	u32 size;
@@ -197,11 +209,10 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
 	return 0;
 }
 
-int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
+int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
 				     void *value, u64 map_flags)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu, off = 0;
 	u32 size;
@@ -232,12 +243,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
 	return 0;
 }
 
-static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key,
 				       void *_next_key)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
-	struct bpf_cgroup_storage_key *next = _next_key;
 	struct bpf_cgroup_storage *storage;
 
 	spin_lock_bh(&map->lock);
@@ -250,17 +259,23 @@ static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
 		if (!storage)
 			goto enoent;
 
-		storage = list_next_entry(storage, list);
+		storage = list_next_entry(storage, list_map);
 		if (!storage)
 			goto enoent;
 	} else {
 		storage = list_first_entry(&map->list,
-					 struct bpf_cgroup_storage, list);
+					 struct bpf_cgroup_storage, list_map);
 	}
 
 	spin_unlock_bh(&map->lock);
-	next->attach_type = storage->key.attach_type;
-	next->cgroup_inode_id = storage->key.cgroup_inode_id;
+
+	if (attach_type_isolated(&map->map)) {
+		struct bpf_cgroup_storage_key *next = _next_key;
+		*next = storage->key;
+	} else {
+		__u64 *next = _next_key;
+		*next = storage->key.cgroup_inode_id;
+	}
 	return 0;
 
 enoent:
@@ -275,7 +290,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	struct bpf_map_memory mem;
 	int ret;
 
-	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) &&
+	    attr->key_size != sizeof(__u64))
 		return ERR_PTR(-EINVAL);
 
 	if (attr->value_size == 0)
@@ -318,6 +334,17 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 static void cgroup_storage_map_free(struct bpf_map *_map)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct list_head *storages = &map->list;
+	struct bpf_cgroup_storage *storage, *stmp;
+
+	mutex_lock(&cgroup_mutex);
+
+	list_for_each_entry_safe(storage, stmp, storages, list_map) {
+		bpf_cgroup_storage_unlink(storage);
+		bpf_cgroup_storage_free(storage);
+	}
+
+	mutex_unlock(&cgroup_mutex);
 
 	WARN_ON(!RB_EMPTY_ROOT(&map->root));
 	WARN_ON(!list_empty(&map->list));
@@ -335,49 +362,63 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
 {
-	struct btf_member *m;
-	u32 offset, size;
-
-	/* Key is expected to be of struct bpf_cgroup_storage_key type,
-	 * which is:
-	 * struct bpf_cgroup_storage_key {
-	 *	__u64	cgroup_inode_id;
-	 *	__u32	attach_type;
-	 * };
-	 */
+	if (attach_type_isolated(map)) {
+		struct btf_member *m;
+		u32 offset, size;
+
+		/* Key is expected to be of struct bpf_cgroup_storage_key type,
+		 * which is:
+		 * struct bpf_cgroup_storage_key {
+		 *	__u64	cgroup_inode_id;
+		 *	__u32	attach_type;
+		 * };
+		 */
+
+		/*
+		 * Key_type must be a structure with two fields.
+		 */
+		if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
+		    BTF_INFO_VLEN(key_type->info) != 2)
+			return -EINVAL;
+
+		/*
+		 * The first field must be a 64 bit integer at 0 offset.
+		 */
+		m = (struct btf_member *)(key_type + 1);
+		size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
+		if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
+			return -EINVAL;
+
+		/*
+		 * The second field must be a 32 bit integer at 64 bit offset.
+		 */
+		m++;
+		offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
+		size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
+		if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
+			return -EINVAL;
+	} else {
+		u32 int_data;
 
-	/*
-	 * Key_type must be a structure with two fields.
-	 */
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
-	    BTF_INFO_VLEN(key_type->info) != 2)
-		return -EINVAL;
+		/*
+		 * Key is expected to be u64, which stores the cgroup_inode_id
+		 */
 
-	/*
-	 * The first field must be a 64 bit integer at 0 offset.
-	 */
-	m = (struct btf_member *)(key_type + 1);
-	size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
-	if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
-		return -EINVAL;
+		if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+			return -EINVAL;
 
-	/*
-	 * The second field must be a 32 bit integer at 64 bit offset.
-	 */
-	m++;
-	offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
-	size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
-	if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
-		return -EINVAL;
+		int_data = *(u32 *)(key_type + 1);
+		if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data))
+			return -EINVAL;
+	}
 
 	return 0;
 }
 
-static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
+static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key,
 					 struct seq_file *m)
 {
 	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu;
 
@@ -426,38 +467,13 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map)
 {
 	enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
-	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	int ret = -EBUSY;
-
-	spin_lock_bh(&map->lock);
 
-	if (map->aux && map->aux != aux)
-		goto unlock;
 	if (aux->cgroup_storage[stype] &&
 	    aux->cgroup_storage[stype] != _map)
-		goto unlock;
+		return -EBUSY;
 
-	map->aux = aux;
 	aux->cgroup_storage[stype] = _map;
-	ret = 0;
-unlock:
-	spin_unlock_bh(&map->lock);
-
-	return ret;
-}
-
-void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map)
-{
-	enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
-	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-
-	spin_lock_bh(&map->lock);
-	if (map->aux == aux) {
-		WARN_ON(aux->cgroup_storage[stype] != _map);
-		map->aux = NULL;
-		aux->cgroup_storage[stype] = NULL;
-	}
-	spin_unlock_bh(&map->lock);
+	return 0;
 }
 
 static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages)
@@ -578,7 +594,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 
 	spin_lock_bh(&map->lock);
 	WARN_ON(cgroup_storage_insert(map, storage));
-	list_add(&storage->list, &map->list);
+	list_add(&storage->list_map, &map->list);
+	list_add(&storage->list_cg, &cgroup->bpf.storages);
 	spin_unlock_bh(&map->lock);
 }
 
@@ -596,7 +613,8 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
 	root = &map->root;
 	rb_erase(&storage->node, root);
 
-	list_del(&storage->list);
+	list_del(&storage->list_map);
+	list_del(&storage->list_cg);
 	spin_unlock_bh(&map->lock);
 }
 
-- 
cgit v1.2.3


From 6cc7d1e8e9e06d45f9d1a39a5f465288d7cd8f9a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:54 -0700
Subject: bpf: Make bpf_link API available indepently of CONFIG_BPF_SYSCALL

Similarly to bpf_prog, make bpf_link and related generic API available
unconditionally to make it easier to have bpf_link support in various parts of
the kernel. Stub out init/prime/settle/cleanup and inc/put APIs.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-2-andriin@fb.com
---
 include/linux/bpf.h | 81 ++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 55 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8357be349133..40c5e206ecf2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -781,6 +781,32 @@ struct bpf_array_aux {
 	struct work_struct work;
 };
 
+struct bpf_link {
+	atomic64_t refcnt;
+	u32 id;
+	enum bpf_link_type type;
+	const struct bpf_link_ops *ops;
+	struct bpf_prog *prog;
+	struct work_struct work;
+};
+
+struct bpf_link_ops {
+	void (*release)(struct bpf_link *link);
+	void (*dealloc)(struct bpf_link *link);
+	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
+			   struct bpf_prog *old_prog);
+	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
+	int (*fill_link_info)(const struct bpf_link *link,
+			      struct bpf_link_info *info);
+};
+
+struct bpf_link_primer {
+	struct bpf_link *link;
+	struct file *file;
+	int fd;
+	u32 id;
+};
+
 struct bpf_struct_ops_value;
 struct btf_type;
 struct btf_member;
@@ -1164,32 +1190,6 @@ static inline bool bpf_bypass_spec_v4(void)
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
-struct bpf_link {
-	atomic64_t refcnt;
-	u32 id;
-	enum bpf_link_type type;
-	const struct bpf_link_ops *ops;
-	struct bpf_prog *prog;
-	struct work_struct work;
-};
-
-struct bpf_link_primer {
-	struct bpf_link *link;
-	struct file *file;
-	int fd;
-	u32 id;
-};
-
-struct bpf_link_ops {
-	void (*release)(struct bpf_link *link);
-	void (*dealloc)(struct bpf_link *link);
-	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
-			   struct bpf_prog *old_prog);
-	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
-	int (*fill_link_info)(const struct bpf_link *link,
-			      struct bpf_link_info *info);
-};
-
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
 int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
@@ -1401,6 +1401,35 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
 {
 }
 
+static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+				 const struct bpf_link_ops *ops,
+				 struct bpf_prog *prog)
+{
+}
+
+static inline int bpf_link_prime(struct bpf_link *link,
+				 struct bpf_link_primer *primer)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bpf_link_settle(struct bpf_link_primer *primer)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void bpf_link_cleanup(struct bpf_link_primer *primer)
+{
+}
+
+static inline void bpf_link_inc(struct bpf_link *link)
+{
+}
+
+static inline void bpf_link_put(struct bpf_link *link)
+{
+}
+
 static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 7f0a838254bdd9114b978ef2541a6ce330307e9e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:55 -0700
Subject: bpf, xdp: Maintain info on attached XDP BPF programs in net_device

Instead of delegating to drivers, maintain information about which BPF
programs are attached in which XDP modes (generic/skb, driver, or hardware)
locally in net_device. This effectively obsoletes XDP_QUERY_PROG command.

Such re-organization simplifies existing code already. But it also allows to
further add bpf_link-based XDP attachments without drivers having to know
about any of this at all, which seems like a good setup.
XDP_SETUP_PROG/XDP_SETUP_PROG_HW are just low-level commands to driver to
install/uninstall active BPF program. All the higher-level concerns about
prog/link interaction will be contained within generic driver-agnostic logic.

All the XDP_QUERY_PROG calls to driver in dev_xdp_uninstall() were removed.
It's not clear for me why dev_xdp_uninstall() were passing previous prog_flags
when resetting installed programs. That seems unnecessary, plus most drivers
don't populate prog_flags anyways. Having XDP_SETUP_PROG vs XDP_SETUP_PROG_HW
should be enough of an indicator of what is required of driver to correctly
reset active BPF program. dev_xdp_uninstall() is also generalized as an
iteration over all three supported mode.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-3-andriin@fb.com
---
 include/linux/netdevice.h |  17 ++++-
 net/core/dev.c            | 158 ++++++++++++++++++++++++++--------------------
 net/core/rtnetlink.c      |   5 +-
 3 files changed, 105 insertions(+), 75 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ac2cd3f49aba..cad44b40c776 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -889,6 +889,17 @@ struct netlink_ext_ack;
 struct xdp_umem;
 struct xdp_dev_bulk_queue;
 
+enum bpf_xdp_mode {
+	XDP_MODE_SKB = 0,
+	XDP_MODE_DRV = 1,
+	XDP_MODE_HW = 2,
+	__MAX_XDP_MODE
+};
+
+struct bpf_xdp_entity {
+	struct bpf_prog *prog;
+};
+
 struct netdev_bpf {
 	enum bpf_netdev_command command;
 	union {
@@ -2142,6 +2153,9 @@ struct net_device {
 #endif
 	const struct udp_tunnel_nic_info	*udp_tunnel_nic_info;
 	struct udp_tunnel_nic	*udp_tunnel_nic;
+
+	/* protected by rtnl_lock */
+	struct bpf_xdp_entity	xdp_state[__MAX_XDP_MODE];
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -3817,8 +3831,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags);
-u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
-		    enum bpf_netdev_command cmd);
+u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index fe2e387eed29..bf38fde667e9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8716,84 +8716,103 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
-u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
-		    enum bpf_netdev_command cmd)
+static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
 {
-	struct netdev_bpf xdp;
+	if (flags & XDP_FLAGS_HW_MODE)
+		return XDP_MODE_HW;
+	if (flags & XDP_FLAGS_DRV_MODE)
+		return XDP_MODE_DRV;
+	return XDP_MODE_SKB;
+}
 
-	if (!bpf_op)
-		return 0;
+static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
+{
+	switch (mode) {
+	case XDP_MODE_SKB:
+		return generic_xdp_install;
+	case XDP_MODE_DRV:
+	case XDP_MODE_HW:
+		return dev->netdev_ops->ndo_bpf;
+	default:
+		return NULL;
+	};
+}
 
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = cmd;
+static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
+				     enum bpf_xdp_mode mode)
+{
+	return dev->xdp_state[mode].prog;
+}
+
+u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
+{
+	struct bpf_prog *prog = dev_xdp_prog(dev, mode);
 
-	/* Query must always succeed. */
-	WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG);
+	return prog ? prog->aux->id : 0;
+}
 
-	return xdp.prog_id;
+static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
+			     struct bpf_prog *prog)
+{
+	dev->xdp_state[mode].prog = prog;
 }
 
-static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
-			   struct netlink_ext_ack *extack, u32 flags,
-			   struct bpf_prog *prog)
+static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
+			   bpf_op_t bpf_op, struct netlink_ext_ack *extack,
+			   u32 flags, struct bpf_prog *prog)
 {
-	bool non_hw = !(flags & XDP_FLAGS_HW_MODE);
-	struct bpf_prog *prev_prog = NULL;
 	struct netdev_bpf xdp;
 	int err;
 
-	if (non_hw) {
-		prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op,
-							   XDP_QUERY_PROG));
-		if (IS_ERR(prev_prog))
-			prev_prog = NULL;
-	}
-
 	memset(&xdp, 0, sizeof(xdp));
-	if (flags & XDP_FLAGS_HW_MODE)
-		xdp.command = XDP_SETUP_PROG_HW;
-	else
-		xdp.command = XDP_SETUP_PROG;
+	xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG;
 	xdp.extack = extack;
 	xdp.flags = flags;
 	xdp.prog = prog;
 
+	/* Drivers assume refcnt is already incremented (i.e, prog pointer is
+	 * "moved" into driver), so they don't increment it on their own, but
+	 * they do decrement refcnt when program is detached or replaced.
+	 * Given net_device also owns link/prog, we need to bump refcnt here
+	 * to prevent drivers from underflowing it.
+	 */
+	if (prog)
+		bpf_prog_inc(prog);
 	err = bpf_op(dev, &xdp);
-	if (!err && non_hw)
-		bpf_prog_change_xdp(prev_prog, prog);
+	if (err) {
+		if (prog)
+			bpf_prog_put(prog);
+		return err;
+	}
 
-	if (prev_prog)
-		bpf_prog_put(prev_prog);
+	if (mode != XDP_MODE_HW)
+		bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog);
 
-	return err;
+	return 0;
 }
 
 static void dev_xdp_uninstall(struct net_device *dev)
 {
-	struct netdev_bpf xdp;
-	bpf_op_t ndo_bpf;
+	struct bpf_prog *prog;
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
 
-	/* Remove generic XDP */
-	WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL));
+	ASSERT_RTNL();
 
-	/* Remove from the driver */
-	ndo_bpf = dev->netdev_ops->ndo_bpf;
-	if (!ndo_bpf)
-		return;
+	for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) {
+		prog = dev_xdp_prog(dev, mode);
+		if (!prog)
+			continue;
 
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = XDP_QUERY_PROG;
-	WARN_ON(ndo_bpf(dev, &xdp));
-	if (xdp.prog_id)
-		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
-					NULL));
+		bpf_op = dev_xdp_bpf_op(dev, mode);
+		if (!bpf_op)
+			continue;
 
-	/* Remove HW offload */
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = XDP_QUERY_PROG_HW;
-	if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
-		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
-					NULL));
+		WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
+
+		bpf_prog_put(prog);
+		dev_xdp_set_prog(dev, mode, NULL);
+	}
 }
 
 /**
@@ -8810,29 +8829,22 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	enum bpf_netdev_command query;
+	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
+	bool offload = mode == XDP_MODE_HW;
 	u32 prog_id, expected_id = 0;
-	bpf_op_t bpf_op, bpf_chk;
 	struct bpf_prog *prog;
-	bool offload;
+	bpf_op_t bpf_op;
 	int err;
 
 	ASSERT_RTNL();
 
-	offload = flags & XDP_FLAGS_HW_MODE;
-	query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
-
-	bpf_op = bpf_chk = ops->ndo_bpf;
-	if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) {
+	bpf_op = dev_xdp_bpf_op(dev, mode);
+	if (!bpf_op) {
 		NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode");
 		return -EOPNOTSUPP;
 	}
-	if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
-		bpf_op = generic_xdp_install;
-	if (bpf_op == bpf_chk)
-		bpf_chk = generic_xdp_install;
 
-	prog_id = __dev_xdp_query(dev, bpf_op, query);
+	prog_id = dev_xdp_prog_id(dev, mode);
 	if (flags & XDP_FLAGS_REPLACE) {
 		if (expected_fd >= 0) {
 			prog = bpf_prog_get_type_dev(expected_fd,
@@ -8850,8 +8862,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		}
 	}
 	if (fd >= 0) {
-		if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
-			NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
+		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
+					       ? XDP_MODE_DRV : XDP_MODE_SKB;
+
+		if (!offload && dev_xdp_prog_id(dev, other_mode)) {
+			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
 
@@ -8866,7 +8881,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return PTR_ERR(prog);
 
 		if (!offload && bpf_prog_is_dev_bound(prog->aux)) {
-			NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported");
+			NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported");
 			bpf_prog_put(prog);
 			return -EINVAL;
 		}
@@ -8895,11 +8910,14 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		prog = NULL;
 	}
 
-	err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
-	if (err < 0 && prog)
+	err = dev_xdp_install(dev, mode, bpf_op, extack, flags, prog);
+	if (err < 0 && prog) {
 		bpf_prog_put(prog);
+		return err;
+	}
+	dev_xdp_set_prog(dev, mode, prog);
 
-	return err;
+	return 0;
 }
 
 /**
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 85a4b0101f76..58c484a28395 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1416,13 +1416,12 @@ static u32 rtnl_xdp_prog_skb(struct net_device *dev)
 
 static u32 rtnl_xdp_prog_drv(struct net_device *dev)
 {
-	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
+	return dev_xdp_prog_id(dev, XDP_MODE_DRV);
 }
 
 static u32 rtnl_xdp_prog_hw(struct net_device *dev)
 {
-	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
-			       XDP_QUERY_PROG_HW);
+	return dev_xdp_prog_id(dev, XDP_MODE_HW);
 }
 
 static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
-- 
cgit v1.2.3


From aa8d3a716b59db6c1ad6c68fb8aa05e31980da60 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:57 -0700
Subject: bpf, xdp: Add bpf_link-based XDP attachment API

Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through
BPF_LINK_CREATE command.

bpf_xdp_link is mutually exclusive with direct BPF program attachment,
previous BPF program should be detached prior to attempting to create a new
bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it
can't be replaced by other BPF program attachment or link attachment. It will
be detached only when the last BPF link FD is closed.

bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to
how other BPF links behave (cgroup, flow_dissector). At that point bpf_link
will become defunct, but won't be destroyed until last FD is closed.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-5-andriin@fb.com
---
 include/linux/netdevice.h |   4 ++
 include/uapi/linux/bpf.h  |   7 +-
 kernel/bpf/syscall.c      |   5 ++
 net/core/dev.c            | 169 ++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 178 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cad44b40c776..7d3c412fcfe5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -888,6 +888,7 @@ struct bpf_prog_offload_ops;
 struct netlink_ext_ack;
 struct xdp_umem;
 struct xdp_dev_bulk_queue;
+struct bpf_xdp_link;
 
 enum bpf_xdp_mode {
 	XDP_MODE_SKB = 0,
@@ -898,6 +899,7 @@ enum bpf_xdp_mode {
 
 struct bpf_xdp_entity {
 	struct bpf_prog *prog;
+	struct bpf_xdp_link *link;
 };
 
 struct netdev_bpf {
@@ -3831,7 +3833,9 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags);
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
+
 int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 828c2f6438f2..87823fb9c123 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -230,6 +230,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET_SOCK_RELEASE,
 	BPF_XDP_CPUMAP,
 	BPF_SK_LOOKUP,
+	BPF_XDP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -242,6 +243,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
 	BPF_LINK_TYPE_NETNS = 5,
+	BPF_LINK_TYPE_XDP = 6,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -614,7 +616,10 @@ union bpf_attr {
 
 	struct { /* struct used by BPF_LINK_CREATE command */
 		__u32		prog_fd;	/* eBPF program to attach */
-		__u32		target_fd;	/* object to attach to */
+		union {
+			__u32		target_fd;	/* object to attach to */
+			__u32		target_ifindex; /* target ifindex */
+		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 	} link_create;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ee290b1f2d9e..0e8c88db7e7a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2824,6 +2824,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_TRACING;
 	case BPF_SK_LOOKUP:
 		return BPF_PROG_TYPE_SK_LOOKUP;
+	case BPF_XDP:
+		return BPF_PROG_TYPE_XDP;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -3921,6 +3923,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
+	case BPF_PROG_TYPE_XDP:
+		ret = bpf_xdp_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index 521ce031ee35..e24248f3d675 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8716,6 +8716,12 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
+struct bpf_xdp_link {
+	struct bpf_link link;
+	struct net_device *dev; /* protected by rtnl_lock, no refcnt held */
+	int flags;
+};
+
 static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
 {
 	if (flags & XDP_FLAGS_HW_MODE)
@@ -8738,9 +8744,19 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 	};
 }
 
+static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
+					 enum bpf_xdp_mode mode)
+{
+	return dev->xdp_state[mode].link;
+}
+
 static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
 				     enum bpf_xdp_mode mode)
 {
+	struct bpf_xdp_link *link = dev_xdp_link(dev, mode);
+
+	if (link)
+		return link->link.prog;
 	return dev->xdp_state[mode].prog;
 }
 
@@ -8751,9 +8767,17 @@ u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 	return prog ? prog->aux->id : 0;
 }
 
+static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode,
+			     struct bpf_xdp_link *link)
+{
+	dev->xdp_state[mode].link = link;
+	dev->xdp_state[mode].prog = NULL;
+}
+
 static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
 			     struct bpf_prog *prog)
 {
+	dev->xdp_state[mode].link = NULL;
 	dev->xdp_state[mode].prog = prog;
 }
 
@@ -8793,6 +8817,7 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 
 static void dev_xdp_uninstall(struct net_device *dev)
 {
+	struct bpf_xdp_link *link;
 	struct bpf_prog *prog;
 	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
@@ -8810,14 +8835,20 @@ static void dev_xdp_uninstall(struct net_device *dev)
 
 		WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
 
-		bpf_prog_put(prog);
-		dev_xdp_set_prog(dev, mode, NULL);
+		/* auto-detach link from net device */
+		link = dev_xdp_link(dev, mode);
+		if (link)
+			link->dev = NULL;
+		else
+			bpf_prog_put(prog);
+
+		dev_xdp_set_link(dev, mode, NULL);
 	}
 }
 
 static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack,
-			  struct bpf_prog *new_prog, struct bpf_prog *old_prog,
-			  u32 flags)
+			  struct bpf_xdp_link *link, struct bpf_prog *new_prog,
+			  struct bpf_prog *old_prog, u32 flags)
 {
 	struct bpf_prog *cur_prog;
 	enum bpf_xdp_mode mode;
@@ -8826,6 +8857,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 
 	ASSERT_RTNL();
 
+	/* either link or prog attachment, never both */
+	if (link && (new_prog || old_prog))
+		return -EINVAL;
+	/* link supports only XDP mode flags */
+	if (link && (flags & ~XDP_FLAGS_MODES)) {
+		NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment");
+		return -EINVAL;
+	}
 	/* just one XDP mode bit should be set, zero defaults to SKB mode */
 	if (hweight32(flags & XDP_FLAGS_MODES) > 1) {
 		NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
@@ -8838,7 +8877,18 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 	}
 
 	mode = dev_xdp_mode(flags);
+	/* can't replace attached link */
+	if (dev_xdp_link(dev, mode)) {
+		NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
+		return -EBUSY;
+	}
+
 	cur_prog = dev_xdp_prog(dev, mode);
+	/* can't replace attached prog with link */
+	if (link && cur_prog) {
+		NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link");
+		return -EBUSY;
+	}
 	if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) {
 		NL_SET_ERR_MSG(extack, "Active program does not match expected");
 		return -EEXIST;
@@ -8848,6 +8898,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EBUSY;
 	}
 
+	/* put effective new program into new_prog */
+	if (link)
+		new_prog = link->link.prog;
+
 	if (new_prog) {
 		bool offload = mode == XDP_MODE_HW;
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
@@ -8884,13 +8938,116 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			return err;
 	}
 
-	dev_xdp_set_prog(dev, mode, new_prog);
+	if (link)
+		dev_xdp_set_link(dev, mode, link);
+	else
+		dev_xdp_set_prog(dev, mode, new_prog);
 	if (cur_prog)
 		bpf_prog_put(cur_prog);
 
 	return 0;
 }
 
+static int dev_xdp_attach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags);
+}
+
+static int dev_xdp_detach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
+
+	ASSERT_RTNL();
+
+	mode = dev_xdp_mode(link->flags);
+	if (dev_xdp_link(dev, mode) != link)
+		return -EINVAL;
+
+	bpf_op = dev_xdp_bpf_op(dev, mode);
+	WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
+	dev_xdp_set_link(dev, mode, NULL);
+	return 0;
+}
+
+static void bpf_xdp_link_release(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	rtnl_lock();
+
+	/* if racing with net_device's tear down, xdp_link->dev might be
+	 * already NULL, in which case link was already auto-detached
+	 */
+	if (xdp_link->dev)
+		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+
+	rtnl_unlock();
+}
+
+static void bpf_xdp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	kfree(xdp_link);
+}
+
+static const struct bpf_link_ops bpf_xdp_link_lops = {
+	.release = bpf_xdp_link_release,
+	.dealloc = bpf_xdp_link_dealloc,
+};
+
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_link_primer link_primer;
+	struct bpf_xdp_link *link;
+	struct net_device *dev;
+	int err, fd;
+
+	dev = dev_get_by_index(net, attr->link_create.target_ifindex);
+	if (!dev)
+		return -EINVAL;
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out_put_dev;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
+	link->dev = dev;
+	link->flags = attr->link_create.flags;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_dev;
+	}
+
+	rtnl_lock();
+	err = dev_xdp_attach_link(dev, NULL, link);
+	rtnl_unlock();
+
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_dev;
+	}
+
+	fd = bpf_link_settle(&link_primer);
+	/* link itself doesn't hold dev's refcnt to not complicate shutdown */
+	dev_put(dev);
+	return fd;
+
+out_put_dev:
+	dev_put(dev);
+	return err;
+}
+
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
@@ -8927,7 +9084,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		}
 	}
 
-	err = dev_xdp_attach(dev, extack, new_prog, old_prog, flags);
+	err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags);
 
 err_out:
 	if (err && new_prog)
-- 
cgit v1.2.3


From e8407fdeb9a6866784e249881f6c786a0835faba Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:46:02 -0700
Subject: bpf, xdp: Remove XDP_QUERY_PROG and XDP_QUERY_PROG_HW XDP commands

Now that BPF program/link management is centralized in generic net_device
code, kernel code never queries program id from drivers, so
XDP_QUERY_PROG/XDP_QUERY_PROG_HW commands are unnecessary.

This patch removes all the implementations of those commands in kernel, along
the xdp_attachment_query().

This patch was compile-tested on allyesconfig.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-10-andriin@fb.com
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c       |  6 ------
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c      |  4 ----
 drivers/net/ethernet/cavium/thunder/nicvf_main.c   |  3 ---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c   |  5 -----
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  3 ---
 drivers/net/ethernet/intel/ice/ice_main.c          |  3 ---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  4 ----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c  |  6 ------
 drivers/net/ethernet/marvell/mvneta.c              |  5 -----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c    |  3 ---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     | 24 ----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 18 ----------------
 .../net/ethernet/netronome/nfp/nfp_net_common.c    |  4 ----
 drivers/net/ethernet/qlogic/qede/qede_filter.c     |  3 ---
 drivers/net/ethernet/sfc/efx.c                     |  5 -----
 drivers/net/ethernet/socionext/netsec.c            |  3 ---
 drivers/net/ethernet/ti/cpsw_priv.c                |  3 ---
 drivers/net/hyperv/netvsc_bpf.c                    | 21 +------------------
 drivers/net/netdevsim/bpf.c                        |  4 ----
 drivers/net/netdevsim/netdevsim.h                  |  2 +-
 drivers/net/tun.c                                  | 15 --------------
 drivers/net/veth.c                                 | 15 --------------
 drivers/net/virtio_net.c                           | 17 ---------------
 drivers/net/xen-netfront.c                         | 21 -------------------
 include/linux/netdevice.h                          |  8 --------
 include/net/xdp.h                                  |  2 --
 net/core/dev.c                                     |  4 ----
 net/core/xdp.c                                     |  9 --------
 28 files changed, 2 insertions(+), 218 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6478c1e0d137..2a6c9725e092 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -576,15 +576,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
  */
 static int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
 {
-	struct ena_adapter *adapter = netdev_priv(netdev);
-
 	switch (bpf->command) {
 	case XDP_SETUP_PROG:
 		return ena_xdp_set(netdev, bpf);
-	case XDP_QUERY_PROG:
-		bpf->prog_id = adapter->xdp_bpf_prog ?
-			adapter->xdp_bpf_prog->aux->id : 0;
-		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 5e3b4a3b69ea..2704a4709bc7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -330,10 +330,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
-	case XDP_QUERY_PROG:
-		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
-		rc = 0;
-		break;
 	default:
 		rc = -EINVAL;
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 2ba0ce115e63..1c6163934e20 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1906,9 +1906,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 9b4028c0e34c..17f6bcafc944 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2077,14 +2077,9 @@ out_err:
 
 static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct dpaa2_eth_priv *priv = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return setup_xdp(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
-		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dadbfb3d2a2b..d8315811cbdf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12923,9 +12923,6 @@ static int i40e_xdp(struct net_device *dev,
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
 					   xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 16a4096bb780..231f4b6e93d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2292,9 +2292,6 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return ice_xsk_umem_setup(vsi, xdp->xsk.umem,
 					  xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 4d898ff21a46..6f32b1706ab9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10190,10 +10190,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = adapter->xdp_prog ?
-			adapter->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 6e9a397db583..a6267569bfa9 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4502,15 +4502,9 @@ static int ixgbevf_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct ixgbevf_adapter *adapter = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = adapter->xdp_prog ?
-			       adapter->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 2c9277e73cef..6e3f9e2f883b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4442,14 +4442,9 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 
 static int mvneta_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct mvneta_port *pp = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mvneta_xdp_setup(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = pp->xdp_prog ? pp->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 6a3f356640a0..cd5e9d60307e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4656,9 +4656,6 @@ static int mvpp2_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mvpp2_xdp_setup(port, xdp);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = port->xdp_prog ? port->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2b8608f8f0a9..106513f772c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2802,35 +2802,11 @@ unlock_out:
 	return err;
 }
 
-static u32 mlx4_xdp_query(struct net_device *dev)
-{
-	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_dev *mdev = priv->mdev;
-	const struct bpf_prog *xdp_prog;
-	u32 prog_id = 0;
-
-	if (!priv->tx_ring_num[TX_XDP])
-		return prog_id;
-
-	mutex_lock(&mdev->state_lock);
-	xdp_prog = rcu_dereference_protected(
-		priv->rx_ring[0]->xdp_prog,
-		lockdep_is_held(&mdev->state_lock));
-	if (xdp_prog)
-		prog_id = xdp_prog->aux->id;
-	mutex_unlock(&mdev->state_lock);
-
-	return prog_id;
-}
-
 static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx4_xdp_set(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = mlx4_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d5d8b28bcd8..aa4fb503dac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4518,29 +4518,11 @@ unlock:
 	return err;
 }
 
-static u32 mlx5e_xdp_query(struct net_device *dev)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	u32 prog_id = 0;
-
-	mutex_lock(&priv->state_lock);
-	xdp_prog = priv->channels.params.xdp_prog;
-	if (xdp_prog)
-		prog_id = xdp_prog->aux->id;
-	mutex_unlock(&priv->state_lock);
-
-	return prog_id;
-}
-
 static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx5e_xdp_set(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = mlx5e_xdp_query(dev);
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 44608873d3d9..39ee23e8c0bf 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3614,10 +3614,6 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
 		return nfp_net_xdp_setup_hw(nn, xdp);
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&nn->xdp, xdp);
-	case XDP_QUERY_PROG_HW:
-		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b7d0b6ccebd3..f961f65d9372 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1045,9 +1045,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index f16b4f236031..d60acaa3879d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -653,15 +653,10 @@ static int efx_xdp_setup_prog(struct efx_nic *efx, struct bpf_prog *prog)
 static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct efx_nic *efx = netdev_priv(dev);
-	struct bpf_prog *xdp_prog;
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return efx_xdp_setup_prog(efx, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp_prog = rtnl_dereference(efx->xdp_prog);
-		xdp->prog_id = xdp_prog ? xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 0f366cc50b74..25db667fa879 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1811,9 +1811,6 @@ static int netsec_xdp(struct net_device *ndev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return netsec_xdp_setup(priv, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index a399f3659346..d6d7a7d9c7ad 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1286,9 +1286,6 @@ int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
 	case XDP_SETUP_PROG:
 		return cpsw_xdp_prog_setup(priv, bpf);
 
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&priv->xdpi, bpf);
-
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
index 8e4141552423..440486d9c999 100644
--- a/drivers/net/hyperv/netvsc_bpf.c
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -163,16 +163,6 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog)
 	return ret;
 }
 
-static u32 netvsc_xdp_query(struct netvsc_device *nvdev)
-{
-	struct bpf_prog *prog = netvsc_xdp_get(nvdev);
-
-	if (prog)
-		return prog->aux->id;
-
-	return 0;
-}
-
 int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	struct net_device_context *ndevctx = netdev_priv(dev);
@@ -182,12 +172,7 @@ int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	int ret;
 
 	if (!nvdev || nvdev->destroy) {
-		if (bpf->command == XDP_QUERY_PROG) {
-			bpf->prog_id = 0;
-			return 0; /* Query must always succeed */
-		} else {
-			return -ENODEV;
-		}
+		return -ENODEV;
 	}
 
 	switch (bpf->command) {
@@ -208,10 +193,6 @@ int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 		return ret;
 
-	case XDP_QUERY_PROG:
-		bpf->prog_id = netvsc_xdp_query(nvdev);
-		return 0;
-
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 0b362b8dac17..2e90512f3bbe 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -551,10 +551,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	ASSERT_RTNL();
 
 	switch (bpf->command) {
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&ns->xdp, bpf);
-	case XDP_QUERY_PROG_HW:
-		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index d164052e0393..284f7092241d 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -121,7 +121,7 @@ static inline void nsim_bpf_uninit(struct netdevsim *ns)
 
 static inline int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
-	return bpf->command == XDP_QUERY_PROG ? 0 : -EOPNOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int nsim_bpf_disable_tc(struct netdevsim *ns)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7adeb91bd368..061bebe25cb1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1184,26 +1184,11 @@ static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 }
 
-static u32 tun_xdp_query(struct net_device *dev)
-{
-	struct tun_struct *tun = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-
-	xdp_prog = rtnl_dereference(tun->xdp_prog);
-	if (xdp_prog)
-		return xdp_prog->aux->id;
-
-	return 0;
-}
-
 static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return tun_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = tun_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index b594f03eeddb..e56cd562a664 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1198,26 +1198,11 @@ err:
 	return err;
 }
 
-static u32 veth_xdp_query(struct net_device *dev)
-{
-	struct veth_priv *priv = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-
-	xdp_prog = priv->_xdp_prog;
-	if (xdp_prog)
-		return xdp_prog->aux->id;
-
-	return 0;
-}
-
 static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return veth_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = veth_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ba38765dc490..6fa8fe5ef160 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2490,28 +2490,11 @@ err:
 	return err;
 }
 
-static u32 virtnet_xdp_query(struct net_device *dev)
-{
-	struct virtnet_info *vi = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	int i;
-
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		xdp_prog = rtnl_dereference(vi->rq[i].xdp_prog);
-		if (xdp_prog)
-			return xdp_prog->aux->id;
-	}
-	return 0;
-}
-
 static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = virtnet_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a63e550c370e..458be6882b98 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1480,32 +1480,11 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 }
 
-static u32 xennet_xdp_query(struct net_device *dev)
-{
-	unsigned int num_queues = dev->real_num_tx_queues;
-	struct netfront_info *np = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	struct netfront_queue *queue;
-	unsigned int i;
-
-	for (i = 0; i < num_queues; ++i) {
-		queue = &np->queues[i];
-		xdp_prog = rtnl_dereference(queue->xdp_prog);
-		if (xdp_prog)
-			return xdp_prog->aux->id;
-	}
-
-	return 0;
-}
-
 static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return xennet_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = xennet_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7d3c412fcfe5..1046763cd0dc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -876,8 +876,6 @@ enum bpf_netdev_command {
 	 */
 	XDP_SETUP_PROG,
 	XDP_SETUP_PROG_HW,
-	XDP_QUERY_PROG,
-	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
@@ -911,12 +909,6 @@ struct netdev_bpf {
 			struct bpf_prog *prog;
 			struct netlink_ext_ack *extack;
 		};
-		/* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
-		struct {
-			u32 prog_id;
-			/* flags with which program was installed */
-			u32 prog_flags;
-		};
 		/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
 		struct {
 			struct bpf_offloaded_map *offmap;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index dbe9c60797e1..3814fb631d52 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -240,8 +240,6 @@ struct xdp_attachment_info {
 };
 
 struct netdev_bpf;
-int xdp_attachment_query(struct xdp_attachment_info *info,
-			 struct netdev_bpf *bpf);
 bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 			     struct netdev_bpf *bpf);
 void xdp_attachment_setup(struct xdp_attachment_info *info,
diff --git a/net/core/dev.c b/net/core/dev.c
index 82ce0920b172..a2a57988880a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5468,10 +5468,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		}
 		break;
 
-	case XDP_QUERY_PROG:
-		xdp->prog_id = old ? old->aux->id : 0;
-		break;
-
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 3c45f99e26d5..48aba933a5a8 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -400,15 +400,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem)
 }
 EXPORT_SYMBOL_GPL(__xdp_release_frame);
 
-int xdp_attachment_query(struct xdp_attachment_info *info,
-			 struct netdev_bpf *bpf)
-{
-	bpf->prog_id = info->prog ? info->prog->aux->id : 0;
-	bpf->prog_flags = info->prog ? info->flags : 0;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xdp_attachment_query);
-
 bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 			     struct netdev_bpf *bpf)
 {
-- 
cgit v1.2.3


From 3135f5b73592988af0eb1b11ccbb72a8667be201 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 26 Jul 2020 18:14:43 +0200
Subject: entry: Correct __secure_computing() stub

The original version of that used secure_computing() which has no
arguments. Review requested to switch to __secure_computing() which has
one. The function name was correct, but no argument added and of course
compiling without SECCOMP was deemed overrated.

Add the missing function argument.

Fixes: 6823ecabf030 ("seccomp: Provide stub for __secure_computing()")
Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/seccomp.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 03d28c32ad01..51f234b6d28f 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -58,10 +58,11 @@ static inline int seccomp_mode(struct seccomp *s)
 
 struct seccomp { };
 struct seccomp_filter { };
+struct seccomp_data;
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 static inline int secure_computing(void) { return 0; }
-static inline int __secure_computing(void) { return 0; }
+static inline int __secure_computing(const struct seccomp_data *sd) { return 0; }
 #else
 static inline void secure_computing_strict(int this_syscall) { return; }
 #endif
-- 
cgit v1.2.3


From ab92ffd5f6ac3ebd4a7650ef906702ab86127b45 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:30:01 -0700
Subject: power: fix duplicated words in bq2415x_charger.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop the doubled word "for".
Change "It it" to "If it".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: linux-pm@vger.kernel.org
Acked-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 include/linux/power/bq2415x_charger.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/power/bq2415x_charger.h b/include/linux/power/bq2415x_charger.h
index 4ca08321e251..f3c267f2a467 100644
--- a/include/linux/power/bq2415x_charger.h
+++ b/include/linux/power/bq2415x_charger.h
@@ -14,8 +14,8 @@
  * value is -1 then default chip value (specified in datasheet) will be
  * used.
  *
- * Value resistor_sense is needed for for configuring charge and
- * termination current. It it is less or equal to zero, configuring charge
+ * Value resistor_sense is needed for configuring charge and
+ * termination current. If it is less or equal to zero, configuring charge
  * and termination current will not be possible.
  *
  * For automode support is needed to provide name of power supply device
-- 
cgit v1.2.3


From a070bdbbb06d7787ec7844a4f1e059cf8b55205d Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Sun, 26 Jul 2020 01:23:37 +0200
Subject: gpio: regmap: fix type clash

GPIO_REGMAP_ADDR_ZERO() cast to unsigned long but the actual config
parameters are unsigned int. We use unsigned int here because that is
the type which is used by the underlying regmap.

Fixes: ebe363197e52 ("gpio: add a reusable generic gpio_chip using regmap")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20200725232337.27581-1-michael@walle.cc
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/regmap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h
index 4c1e6b34e824..ad76f3d0a6ba 100644
--- a/include/linux/gpio/regmap.h
+++ b/include/linux/gpio/regmap.h
@@ -8,7 +8,7 @@ struct gpio_regmap;
 struct irq_domain;
 struct regmap;
 
-#define GPIO_REGMAP_ADDR_ZERO ((unsigned long)(-1))
+#define GPIO_REGMAP_ADDR_ZERO ((unsigned int)(-1))
 #define GPIO_REGMAP_ADDR(addr) ((addr) ? : GPIO_REGMAP_ADDR_ZERO)
 
 /**
-- 
cgit v1.2.3


From 6d4c4479f80141a2a24ac798a86942b1225206df Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Tue, 30 Jun 2020 21:41:26 +0800
Subject: irqchip/gic-v3: Remove unused register definition

[maz: The GICv3 spec has evolved quite a bit since the draft the Linux
driver was written against, and some register definitions are simply gone]

As per the GICv3 specification, GIC{D,R}_SEIR are not assigned and the
locations (0x0068) are actually Reserved. GICR_MOV{LPI,ALL}R are two IMP
DEF registers and might be defined by some specific micro-architecture.

As they're not used anywhere in the kernel, just drop all of them.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
[maz: added context explaination]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200630134126.880-1-yuzenghui@huawei.com
---
 include/linux/irqchip/arm-gic-v3.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 6c36b6cc3edf..f6d092fdb93d 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -19,7 +19,6 @@
 #define GICD_CLRSPI_NSR			0x0048
 #define GICD_SETSPI_SR			0x0050
 #define GICD_CLRSPI_SR			0x0058
-#define GICD_SEIR			0x0068
 #define GICD_IGROUPR			0x0080
 #define GICD_ISENABLER			0x0100
 #define GICD_ICENABLER			0x0180
@@ -119,14 +118,11 @@
 #define GICR_WAKER			0x0014
 #define GICR_SETLPIR			0x0040
 #define GICR_CLRLPIR			0x0048
-#define GICR_SEIR			GICD_SEIR
 #define GICR_PROPBASER			0x0070
 #define GICR_PENDBASER			0x0078
 #define GICR_INVLPIR			0x00A0
 #define GICR_INVALLR			0x00B0
 #define GICR_SYNCR			0x00C0
-#define GICR_MOVLPIR			0x0100
-#define GICR_MOVALLR			0x0110
 #define GICR_IDREGS			GICD_IDREGS
 #define GICR_PIDR2			GICD_PIDR2
 
-- 
cgit v1.2.3


From b7640d765dbbde794c49198c9851f6026fb6e43e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:28:53 -0700
Subject: irqchip: irq-bcm2836.h: drop a duplicated word

Drop the repeated word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200719002853.20419-1-rdunlap@infradead.org
---
 include/linux/irqchip/irq-bcm2836.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/irqchip/irq-bcm2836.h b/include/linux/irqchip/irq-bcm2836.h
index f224d6f9e550..ac5719d8f56b 100644
--- a/include/linux/irqchip/irq-bcm2836.h
+++ b/include/linux/irqchip/irq-bcm2836.h
@@ -30,7 +30,7 @@
  */
 #define LOCAL_MAILBOX_INT_CONTROL0	0x050
 /*
- * The CPU's interrupt status register.  Bits are defined by the the
+ * The CPU's interrupt status register.  Bits are defined by the
  * LOCAL_IRQ_* bits below.
  */
 #define LOCAL_IRQ_PENDING0		0x060
-- 
cgit v1.2.3


From f8410e626569324cfe831aaecc0504cafc12b471 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 17 Jul 2020 17:06:34 -0700
Subject: irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH
 helper macros

Compiling an irqchip driver as a platform driver needs to bunch of
things to be done right:
- Making sure the parent domain is initialized first
- Making sure the device can't be unbound from sysfs
- Disallowing module unload if it's built as a module
- Finding the parent node
- Etc.

Instead of trying to make sure all future irqchip platform drivers get
this right, provide boilerplate macros that take care of all of this.

An example use would look something like this. Where acme_foo_init and
acme_bar_init are similar to what would be passed to IRQCHIP_DECLARE.

IRQCHIP_PLATFORM_DRIVER_BEGIN(acme_irq)
IRQCHIP_MATCH("acme,foo", acme_foo_init)
IRQCHIP_MATCH("acme,bar", acme_bar_init)
IRQCHIP_PLATFORM_DRIVER_END(acme_irq)

Signed-off-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: John Stultz <john.stultz@linaro.org>
Link: https://lore.kernel.org/r/20200718000637.3632841-2-saravanak@google.com
---
 drivers/irqchip/irqchip.c | 29 +++++++++++++++++++++++++++++
 include/linux/irqchip.h   | 23 +++++++++++++++++++++++
 2 files changed, 52 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index 2b35e68bea82..1bb0e36c2bf3 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -10,8 +10,10 @@
 
 #include <linux/acpi.h>
 #include <linux/init.h>
+#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/irqchip.h>
+#include <linux/platform_device.h>
 
 /*
  * This special of_device_id is the sentinel at the end of the
@@ -29,3 +31,30 @@ void __init irqchip_init(void)
 	of_irq_init(__irqchip_of_table);
 	acpi_probe_device_table(irqchip);
 }
+
+int platform_irqchip_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *par_np = of_irq_find_parent(np);
+	of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev);
+
+	if (!irq_init_cb)
+		return -EINVAL;
+
+	if (par_np == np)
+		par_np = NULL;
+
+	/*
+	 * If there's a parent interrupt controller and  none of the parent irq
+	 * domains have been registered, that means the parent interrupt
+	 * controller has not been initialized yet.  it's not time for this
+	 * interrupt controller to initialize. So, defer probe of this
+	 * interrupt controller. The actual initialization callback of this
+	 * interrupt controller can check for specific domains as necessary.
+	 */
+	if (par_np && !irq_find_matching_host(np, DOMAIN_BUS_ANY))
+		return -EPROBE_DEFER;
+
+	return irq_init_cb(np, par_np);
+}
+EXPORT_SYMBOL_GPL(platform_irqchip_probe);
diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index 447f22880a69..8e754d8b8155 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -13,6 +13,7 @@
 
 #include <linux/acpi.h>
 #include <linux/of.h>
+#include <linux/platform_device.h>
 
 /*
  * This macro must be used by the different irqchip drivers to declare
@@ -26,6 +27,28 @@
  */
 #define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn)
 
+extern int platform_irqchip_probe(struct platform_device *pdev);
+
+#define IRQCHIP_PLATFORM_DRIVER_BEGIN(drv_name) \
+static const struct of_device_id drv_name##_irqchip_match_table[] = {
+
+#define IRQCHIP_MATCH(compat, fn) { .compatible = compat, .data = fn },
+
+#define IRQCHIP_PLATFORM_DRIVER_END(drv_name)				\
+	{},								\
+};									\
+MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table);		\
+static struct platform_driver drv_name##_driver = {		\
+	.probe  = platform_irqchip_probe,				\
+	.driver = {							\
+		.name = #drv_name,					\
+		.owner = THIS_MODULE,					\
+		.of_match_table = drv_name##_irqchip_match_table,	\
+		.suppress_bind_attrs = true,				\
+	},								\
+};									\
+builtin_platform_driver(drv_name##_driver)
+
 /*
  * This macro must be used by the different irqchip drivers to declare
  * the association between their version and their initialization function.
-- 
cgit v1.2.3


From 762a21fd45e056e9ccd2ef5787b4ee0c5af9bec8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 26 Jul 2020 11:12:36 +0100
Subject: irqchip: Fix IRQCHIP_PLATFORM_DRIVER_* compilation by including
 module.h

The newly introduced IRQCHIP_PLATFORM_DRIVER_* macros expand into
module-related macros, but do so without including module.h.
Depending on the driver and/or architecture, this happens to work,
or not.

Unconditionnaly include linux/module.h to sort it out.

Fixes: f3b5e608ed6d ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros")
Reported-by: kernel test robot <lkp@intel.com>
Cc: Saravana Kannan <saravanak@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irqchip.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index 8e754d8b8155..67351aac65ef 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -12,6 +12,7 @@
 #define _LINUX_IRQCHIP_H
 
 #include <linux/acpi.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 
-- 
cgit v1.2.3


From b4a461e72bcb28a512bbdd29a4cb70aede2d68d3 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 21 Jul 2020 16:22:48 +1000
Subject: printk: Make linux/printk.h self-contained

As it stands if you include printk.h by itself it will fail to
compile because it requires definitions from ratelimit.h.  However,
simply including ratelimit.h from printk.h does not work due to
inclusion loops involving sched.h and kernel.h.

This patch solves this by moving bits from ratelimit.h into a new
header file which can then be included by printk.h without any
worries about header loops.

The build bot then revealed some intriguing failures arising out
of this patch.  On s390 there is an inclusion loop with asm/bug.h
and linux/kernel.h that triggers a compile failure, because kernel.h
will cause asm-generic/bug.h to be included before s390's own
asm/bug.h has finished processing.  This has been fixed by not
including kernel.h in arch/s390/include/asm/bug.h.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Petr Mladek <pmladek@suse.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Link: https://lore.kernel.org/r/20200721062248.GA18383@gondor.apana.org.au
---
 arch/s390/include/asm/bug.h     |  2 +-
 include/linux/printk.h          |  1 +
 include/linux/ratelimit.h       | 36 +---------------------------------
 include/linux/ratelimit_types.h | 43 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 46 insertions(+), 36 deletions(-)
 create mode 100644 include/linux/ratelimit_types.h

(limited to 'include/linux')

diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 7725f8006fdf..0b25f28351ed 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_S390_BUG_H
 #define _ASM_S390_BUG_H
 
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 
 #ifdef CONFIG_BUG
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fc8f03c54543..34c1a7be3e01 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -7,6 +7,7 @@
 #include <linux/kern_levels.h>
 #include <linux/linkage.h>
 #include <linux/cache.h>
+#include <linux/ratelimit_types.h>
 
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 8ddf79e9207a..b17e0cd0a30c 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -2,41 +2,10 @@
 #ifndef _LINUX_RATELIMIT_H
 #define _LINUX_RATELIMIT_H
 
-#include <linux/param.h>
+#include <linux/ratelimit_types.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 
-#define DEFAULT_RATELIMIT_INTERVAL	(5 * HZ)
-#define DEFAULT_RATELIMIT_BURST		10
-
-/* issue num suppressed message on exit */
-#define RATELIMIT_MSG_ON_RELEASE	BIT(0)
-
-struct ratelimit_state {
-	raw_spinlock_t	lock;		/* protect the state */
-
-	int		interval;
-	int		burst;
-	int		printed;
-	int		missed;
-	unsigned long	begin;
-	unsigned long	flags;
-};
-
-#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
-		.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
-		.interval	= interval_init,			\
-		.burst		= burst_init,				\
-	}
-
-#define RATELIMIT_STATE_INIT_DISABLED					\
-	RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST)
-
-#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
-									\
-	struct ratelimit_state name =					\
-		RATELIMIT_STATE_INIT(name, interval_init, burst_init)	\
-
 static inline void ratelimit_state_init(struct ratelimit_state *rs,
 					int interval, int burst)
 {
@@ -73,9 +42,6 @@ ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags)
 
 extern struct ratelimit_state printk_ratelimit_state;
 
-extern int ___ratelimit(struct ratelimit_state *rs, const char *func);
-#define __ratelimit(state) ___ratelimit(state, __func__)
-
 #ifdef CONFIG_PRINTK
 
 #define WARN_ON_RATELIMIT(condition, state)	({		\
diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h
new file mode 100644
index 000000000000..b676aa419eef
--- /dev/null
+++ b/include/linux/ratelimit_types.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RATELIMIT_TYPES_H
+#define _LINUX_RATELIMIT_TYPES_H
+
+#include <linux/bits.h>
+#include <linux/param.h>
+#include <linux/spinlock_types.h>
+
+#define DEFAULT_RATELIMIT_INTERVAL	(5 * HZ)
+#define DEFAULT_RATELIMIT_BURST		10
+
+/* issue num suppressed message on exit */
+#define RATELIMIT_MSG_ON_RELEASE	BIT(0)
+
+struct ratelimit_state {
+	raw_spinlock_t	lock;		/* protect the state */
+
+	int		interval;
+	int		burst;
+	int		printed;
+	int		missed;
+	unsigned long	begin;
+	unsigned long	flags;
+};
+
+#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
+		.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
+		.interval	= interval_init,			\
+		.burst		= burst_init,				\
+	}
+
+#define RATELIMIT_STATE_INIT_DISABLED					\
+	RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST)
+
+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
+									\
+	struct ratelimit_state name =					\
+		RATELIMIT_STATE_INIT(name, interval_init, burst_init)	\
+
+extern int ___ratelimit(struct ratelimit_state *rs, const char *func);
+#define __ratelimit(state) ___ratelimit(state, __func__)
+
+#endif /* _LINUX_RATELIMIT_TYPES_H */
-- 
cgit v1.2.3


From d97758e048e5fe91c7d8ff9ce5f030ee88d92161 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:58:41 +0300
Subject: dmaengine: Introduce min burst length capability

Some hardware aside from default 0/1 may have greater minimum burst
transactions length constraints. Here we introduce the DMA device
and slave capability, which if required can be initialized by the DMA
engine driver with the device-specific value.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200723005848.31907-4-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 1 +
 include/linux/dmaengine.h | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 2b06a7a8629d..2f1a7c0c5446 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -592,6 +592,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->src_addr_widths = device->src_addr_widths;
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
+	caps->min_burst = device->min_burst;
 	caps->max_burst = device->max_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 883e1e087de5..7d6e2aa26980 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -467,6 +467,7 @@ enum dma_residue_granularity {
  *	Since the enum dma_transfer_direction is not defined as bit flag for
  *	each type, the dma controller should set BIT(<TYPE>) and same
  *	should be checked by controller as well
+ * @min_burst: min burst capability per-transfer
  * @max_burst: max burst capability per-transfer
  * @cmd_pause: true, if pause is supported (i.e. for reading residue or
  *	       for resume later)
@@ -480,6 +481,7 @@ struct dma_slave_caps {
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
 	u32 directions;
+	u32 min_burst;
 	u32 max_burst;
 	bool cmd_pause;
 	bool cmd_resume;
@@ -771,6 +773,7 @@ struct dma_filter {
  *	Since the enum dma_transfer_direction is not defined as bit flag for
  *	each type, the dma controller should set BIT(<TYPE>) and same
  *	should be checked by controller as well
+ * @min_burst: min burst capability per-transfer
  * @max_burst: max burst capability per-transfer
  * @residue_granularity: granularity of the transfer residue reported
  *	by tx_status
@@ -841,6 +844,7 @@ struct dma_device {
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
 	u32 directions;
+	u32 min_burst;
 	u32 max_burst;
 	bool descriptor_reuse;
 	enum dma_residue_granularity residue_granularity;
-- 
cgit v1.2.3


From b1b40b8fe7e8fb26e33bad1766ce322d2c63a6c7 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:58:42 +0300
Subject: dmaengine: Introduce max SG burst capability

Some devices may lack the support of the hardware accelerated SG list
entries automatic walking through and execution. In this case a burden of
the SG list traversal and DMA engine re-initialization lies on the
DMA engine driver (normally implemented by using a DMA transfer completion
IRQ to recharge the DMA device with a next SG list entry). But such
solution may not be suitable for some DMA consumers. In particular SPI
devices need both Tx and Rx DMA channels work synchronously in order
to avoid the Rx FIFO overflow. In case if Rx DMA channel is paused for
some time while the Tx DMA channel works implicitly pulling data into the
Rx FIFO, the later will be eventually overflown, which will cause the data
loss. So if SG list entries aren't automatically fetched by the DMA
engine, but are one-by-one manually selected for execution in the
ISRs/deferred work/etc., such problem will eventually happen due to the
non-deterministic latencies of the service execution.

In order to let the DMA consumer know about the DMA device capabilities
regarding the hardware accelerated SG list traversal we introduce the
max_sg_burst capability. It is supposed to be initialized by the DMA engine
driver with 0 if there is no limitation of the number of SG entries
atomically executed and with non-zero value if there is such constraints,
so the upper limit is determined by the number set to the property.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200723005848.31907-5-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 1 +
 include/linux/dmaengine.h | 8 ++++++++
 2 files changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 2f1a7c0c5446..8177f78faeda 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -594,6 +594,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->directions = device->directions;
 	caps->min_burst = device->min_burst;
 	caps->max_burst = device->max_burst;
+	caps->max_sg_burst = device->max_sg_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
 	caps->cmd_pause = !!device->device_pause;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 7d6e2aa26980..4cbe09e66db2 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -469,6 +469,9 @@ enum dma_residue_granularity {
  *	should be checked by controller as well
  * @min_burst: min burst capability per-transfer
  * @max_burst: max burst capability per-transfer
+ * @max_sg_burst: max number of SG list entries executed in a single burst
+ *	DMA tansaction with no software intervention for reinitialization.
+ *	Zero value means unlimited number of entries.
  * @cmd_pause: true, if pause is supported (i.e. for reading residue or
  *	       for resume later)
  * @cmd_resume: true, if resume is supported
@@ -483,6 +486,7 @@ struct dma_slave_caps {
 	u32 directions;
 	u32 min_burst;
 	u32 max_burst;
+	u32 max_sg_burst;
 	bool cmd_pause;
 	bool cmd_resume;
 	bool cmd_terminate;
@@ -775,6 +779,9 @@ struct dma_filter {
  *	should be checked by controller as well
  * @min_burst: min burst capability per-transfer
  * @max_burst: max burst capability per-transfer
+ * @max_sg_burst: max number of SG list entries executed in a single burst
+ *	DMA tansaction with no software intervention for reinitialization.
+ *	Zero value means unlimited number of entries.
  * @residue_granularity: granularity of the transfer residue reported
  *	by tx_status
  * @device_alloc_chan_resources: allocate resources and return the
@@ -846,6 +853,7 @@ struct dma_device {
 	u32 directions;
 	u32 min_burst;
 	u32 max_burst;
+	u32 max_sg_burst;
 	bool descriptor_reuse;
 	enum dma_residue_granularity residue_granularity;
 
-- 
cgit v1.2.3


From 3b6d694eb3eebd86ec44a119e730943ac8e03a6b Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:58:43 +0300
Subject: dmaengine: Introduce DMA-device device_caps callback

There are DMA devices (like ours version of Synopsys DW DMAC) which have
DMA capabilities non-uniformly redistributed between the device channels.
In order to provide a way of exposing the channel-specific parameters to
the DMA engine consumers, we introduce a new DMA-device callback. In case
if provided it gets called from the dma_get_slave_caps() method and is
able to override the generic DMA-device capabilities.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200723005848.31907-6-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 10 ++++++++++
 include/linux/dmaengine.h |  4 ++++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 8177f78faeda..a53e71d2bbd4 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -601,6 +601,16 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->cmd_resume = !!device->device_resume;
 	caps->cmd_terminate = !!device->device_terminate_all;
 
+	/*
+	 * DMA engine device might be configured with non-uniformly
+	 * distributed slave capabilities per device channels. In this
+	 * case the corresponding driver may provide the device_caps
+	 * callback to override the generic capabilities with
+	 * channel-specific ones.
+	 */
+	if (device->device_caps)
+		device->device_caps(chan, caps);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dma_get_slave_caps);
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 4cbe09e66db2..d718671bfd25 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -801,6 +801,8 @@ struct dma_filter {
  *	be called after period_len bytes have been transferred.
  * @device_prep_interleaved_dma: Transfer expression in a generic way.
  * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address
+ * @device_caps: May be used to override the generic DMA slave capabilities
+ *	with per-channel specific ones
  * @device_config: Pushes a new configuration to a channel, return 0 or an error
  *	code
  * @device_pause: Pauses any transfer happening on a channel. Returns
@@ -901,6 +903,8 @@ struct dma_device {
 		struct dma_chan *chan, dma_addr_t dst, u64 data,
 		unsigned long flags);
 
+	void (*device_caps)(struct dma_chan *chan,
+			    struct dma_slave_caps *caps);
 	int (*device_config)(struct dma_chan *chan,
 			     struct dma_slave_config *config);
 	int (*device_pause)(struct dma_chan *chan);
-- 
cgit v1.2.3


From 585d35451e94b2e1b0bf59ef55d3b4a1c8ab3d77 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:58:46 +0300
Subject: dmaengine: dw: Initialize min and max burst DMA device capability

According to the DW APB DMAC data book the minimum burst transaction
length is 1 and it's true for any version of the controller since
isn't parametrised in the coreAssembler so can't be changed at the
IP-core synthesis stage. The maximum burst transaction can vary from
channel to channel and from controller to controller depending on a
IP-core parameter the system engineer activated during the IP-core
synthesis. Let's initialise both min_burst and max_burst members of the
DMA controller descriptor with extreme values so the DMA clients could
use them to properly optimize the DMA requests. The channels and
controller-specific max_burst length initialization will be introduced
by the follow-up patches.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200723005848.31907-9-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw/core.c                | 2 ++
 include/linux/platform_data/dma-dw.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index fb95920c429e..afe5a2e465af 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1223,6 +1223,8 @@ int do_dma_probe(struct dw_dma_chip *chip)
 	dw->dma.device_issue_pending = dwc_issue_pending;
 
 	/* DMA capabilities */
+	dw->dma.min_burst = DW_DMA_MIN_BURST;
+	dw->dma.max_burst = DW_DMA_MAX_BURST;
 	dw->dma.src_addr_widths = DW_DMA_BUSWIDTHS;
 	dw->dma.dst_addr_widths = DW_DMA_BUSWIDTHS;
 	dw->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index f3eaf9ec00a1..369e41e9dcc9 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -12,6 +12,8 @@
 
 #define DW_DMA_MAX_NR_MASTERS	4
 #define DW_DMA_MAX_NR_CHANNELS	8
+#define DW_DMA_MIN_BURST	1
+#define DW_DMA_MAX_BURST	256
 
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
-- 
cgit v1.2.3


From ca7f2851712e7072e8f327882dc4bdaaae3a8079 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:58:47 +0300
Subject: dmaengine: dw: Introduce max burst length hw config

IP core of the DW DMA controller may be synthesized with different
max burst length of the transfers per each channel. According to Synopsis
having the fixed maximum burst transactions length may provide some
performance gain. At the same time setting up the source and destination
multi size exceeding the max burst length limitation may cause a serious
problems. In our case the DMA transaction just hangs up. In order to fix
this lets introduce the max burst length platform config of the DW DMA
controller device and don't let the DMA channels configuration code
exceed the burst length hardware limitation.

Note the maximum burst length parameter can be detected either in runtime
from the DWC parameter registers or from the dedicated DT property.
Depending on the IP core configuration the maximum value can vary from
channel to channel so by overriding the channel slave max_burst capability
we make sure a DMA consumer will get the channel-specific max burst
length.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200723005848.31907-10-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw/core.c                | 16 ++++++++++++++++
 drivers/dma/dw/of.c                  |  5 +++++
 drivers/dma/dw/regs.h                |  2 ++
 include/linux/platform_data/dma-dw.h |  3 +++
 4 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index afe5a2e465af..588b9bae827c 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -791,6 +791,11 @@ static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
 
+	dwc->dma_sconfig.src_maxburst =
+		clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst);
+	dwc->dma_sconfig.dst_maxburst =
+		clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst);
+
 	dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst);
 	dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst);
 
@@ -1049,6 +1054,13 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
+static void dwc_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+
+	caps->max_burst = dwc->max_burst;
+}
+
 int do_dma_probe(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
@@ -1189,9 +1201,12 @@ int do_dma_probe(struct dw_dma_chip *chip)
 			dwc->nollp =
 				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0 ||
 				(dwc_params >> DWC_PARAMS_HC_LLP & 0x1) == 1;
+			dwc->max_burst =
+				(0x4 << (dwc_params >> DWC_PARAMS_MSIZE & 0x7));
 		} else {
 			dwc->block_size = pdata->block_size;
 			dwc->nollp = !pdata->multi_block[i];
+			dwc->max_burst = pdata->max_burst[i] ?: DW_DMA_MAX_BURST;
 		}
 	}
 
@@ -1214,6 +1229,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
 	dw->dma.device_prep_dma_memcpy = dwc_prep_dma_memcpy;
 	dw->dma.device_prep_slave_sg = dwc_prep_slave_sg;
 
+	dw->dma.device_caps = dwc_caps;
 	dw->dma.device_config = dwc_config;
 	dw->dma.device_pause = dwc_pause;
 	dw->dma.device_resume = dwc_resume;
diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
index 9e27831dee32..1474b3817ef4 100644
--- a/drivers/dma/dw/of.c
+++ b/drivers/dma/dw/of.c
@@ -98,6 +98,11 @@ struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
 			pdata->multi_block[tmp] = 1;
 	}
 
+	if (of_property_read_u32_array(np, "snps,max-burst-len", pdata->max_burst,
+				       nr_channels)) {
+		memset32(pdata->max_burst, DW_DMA_MAX_BURST, nr_channels);
+	}
+
 	if (!of_property_read_u32(np, "snps,dma-protection-control", &tmp)) {
 		if (tmp > CHAN_PROTCTL_MASK)
 			return NULL;
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 1ab840b06e79..76654bd13c1a 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -126,6 +126,7 @@ struct dw_dma_regs {
 /* Bitfields in DWC_PARAMS */
 #define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
 #define DWC_PARAMS_HC_LLP	13		/* set LLP register to zero */
+#define DWC_PARAMS_MSIZE	16		/* max group transaction size */
 
 /* bursts size */
 enum dw_dma_msize {
@@ -284,6 +285,7 @@ struct dw_dma_chan {
 	/* hardware configuration */
 	unsigned int		block_size;
 	bool			nollp;
+	u32			max_burst;
 
 	/* custom slave configuration */
 	struct dw_dma_slave	dws;
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index 369e41e9dcc9..4f681df85c27 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -44,6 +44,8 @@ struct dw_dma_slave {
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(in bytes, power of 2)
  * @multi_block: Multi block transfers supported by hardware per channel.
+ * @max_burst: Maximum value of burst transaction size supported by hardware
+ *	       per channel (in units of CTL.SRC_TR_WIDTH/CTL.DST_TR_WIDTH).
  * @protctl: Protection control signals setting per channel.
  */
 struct dw_dma_platform_data {
@@ -58,6 +60,7 @@ struct dw_dma_platform_data {
 	unsigned char	nr_masters;
 	unsigned char	data_width[DW_DMA_MAX_NR_MASTERS];
 	unsigned char	multi_block[DW_DMA_MAX_NR_CHANNELS];
+	u32		max_burst[DW_DMA_MAX_NR_CHANNELS];
 #define CHAN_PROTCTL_PRIVILEGED		BIT(0)
 #define CHAN_PROTCTL_BUFFERABLE		BIT(1)
 #define CHAN_PROTCTL_CACHEABLE		BIT(2)
-- 
cgit v1.2.3


From 6bd0dffa1a6e19e73964ae47c964f57c625cce05 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Jul 2020 16:08:44 +0300
Subject: dmaengine: dw: Don't include unneeded header to platform data header

Including device.h is too much for the dma-dw.h platform data header.
Replace it with the headers of which dma-dw.h is direct user.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200721130844.64162-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/platform_data/dma-dw.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index 4f681df85c27..fbbeb2f6189b 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -8,13 +8,16 @@
 #ifndef _PLATFORM_DATA_DMA_DW_H
 #define _PLATFORM_DATA_DMA_DW_H
 
-#include <linux/device.h>
+#include <linux/bits.h>
+#include <linux/types.h>
 
 #define DW_DMA_MAX_NR_MASTERS	4
 #define DW_DMA_MAX_NR_CHANNELS	8
 #define DW_DMA_MIN_BURST	1
 #define DW_DMA_MAX_BURST	256
 
+struct device;
+
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
  *
-- 
cgit v1.2.3


From 280c7f95f858b103e62d84cae2d5ed9f5cf54d41 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 27 Jul 2020 12:14:28 +0200
Subject: Revert "test_firmware: Test platform fw loading on non-EFI systems"

This reverts commit 2d38dbf89a06d0f689daec9842c5d3295c49777f as it broke
the build in linux-next

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 2d38dbf89a06 ("test_firmware: Test platform fw loading on non-EFI systems")
Cc: stable@vger.kernel.org
Cc: Scott Branden <scott.branden@broadcom.com>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200727165539.0e8797ab@canb.auug.org.au
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 +++++----------------
 drivers/firmware/efi/embedded-firmware.h | 19 -------------------
 include/linux/efi_embedded_fw.h          | 13 +++++++++++++
 lib/test_firmware.c                      |  5 -----
 4 files changed, 18 insertions(+), 40 deletions(-)
 delete mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index 0fb03cd0a5a2..a1b199de9006 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,22 +14,11 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
-#include "embedded-firmware.h"
-
-#ifdef CONFIG_TEST_FIRMWARE
-# define EFI_EMBEDDED_FW_VISIBILITY
-#else
-# define EFI_EMBEDDED_FW_VISIBILITY static
-#endif
-
-EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
-EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
-
 /* Exported for use by lib/test_firmware.c only */
-#ifdef CONFIG_TEST_FIRMWARE
+LIST_HEAD(efi_embedded_fw_list);
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
-#endif
+
+static bool checked_for_fw;
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -130,14 +119,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	efi_embedded_fw_checked = true;
+	checked_for_fw = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!efi_embedded_fw_checked) {
+	if (!checked_for_fw) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
deleted file mode 100644
index 34113316d068..000000000000
--- a/drivers/firmware/efi/embedded-firmware.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
-#define _EFI_EMBEDDED_FW_INTERNAL_H_
-
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they only in separate header for use by lib/test_firmware.c.
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-extern struct list_head efi_embedded_fw_list;
-extern bool efi_embedded_fw_checked;
-
-#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 4ad5db9f5312..57eac5241303 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,6 +7,19 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they are in this header for use by lib/test_firmware.c only!
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+extern struct list_head efi_embedded_fw_list;
+
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 62af792e151c..9fee2b93a8d1 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,7 +489,6 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
-#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -502,7 +501,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
-	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -515,8 +513,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
-	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
-	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -534,7 +530,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
-	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From 7a82e97a11b91a78e9da06ab3f70545953c07b5c Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Thu, 16 Jul 2020 14:42:48 +0200
Subject: PM: core: introduce pm_ptr() macro

This macro is analogous to the infamous of_match_ptr(). If CONFIG_PM
is enabled, this macro will resolve to its argument, otherwise to NULL.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 121c104a4090..1f227c518db3 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -374,6 +374,12 @@ const struct dev_pm_ops name = { \
 	SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
 }
 
+#ifdef CONFIG_PM
+#define pm_ptr(_ptr) (_ptr)
+#else
+#define pm_ptr(_ptr) NULL
+#endif
+
 /*
  * PM_EVENT_ messages
  *
-- 
cgit v1.2.3


From 756a64ce349cf2646c60456b110f7f1756bb8699 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Thu, 16 Jul 2020 14:42:49 +0200
Subject: PM: Make *_DEV_PM_OPS macros use __maybe_unused

This way, when the dev_pm_ops instance is not referenced anywhere, it
will simply be dropped by the compiler without a warning.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 1f227c518db3..a30a4b54df52 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -351,7 +351,7 @@ struct dev_pm_ops {
  * to RAM and hibernation.
  */
 #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
-const struct dev_pm_ops name = { \
+const struct dev_pm_ops __maybe_unused name = { \
 	SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
 }
 
@@ -369,7 +369,7 @@ const struct dev_pm_ops name = { \
  * .runtime_resume(), respectively (and analogously for hibernation).
  */
 #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
-const struct dev_pm_ops name = { \
+const struct dev_pm_ops __maybe_unused name = { \
 	SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \
 	SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
 }
-- 
cgit v1.2.3


From 0585c1c06a550c2a606c33ad45954892245512f6 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 27 Jul 2020 17:29:38 +0800
Subject: ACPI: Use valid link to the ACPI specification

Currently, acpi.info is an invalid link to access ACPI specification,
the new valid link is https://uefi.org/specifications.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/hwmon/acpi_power_meter.rst      | 2 +-
 drivers/acpi/Kconfig                          | 3 +--
 include/linux/tboot.h                         | 2 +-
 tools/power/cpupower/man/cpupower-idle-info.1 | 2 +-
 4 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/hwmon/acpi_power_meter.rst b/Documentation/hwmon/acpi_power_meter.rst
index 4a0941ade0ca..8628c1161015 100644
--- a/Documentation/hwmon/acpi_power_meter.rst
+++ b/Documentation/hwmon/acpi_power_meter.rst
@@ -9,7 +9,7 @@ Supported systems:
 
     Prefix: 'power_meter'
 
-    Datasheet: http://acpi.info/, section 10.4.
+    Datasheet: https://uefi.org/specifications, section 10.4.
 
 Author: Darrick J. Wong
 
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ce2730d61a8f..7428cd2f9f6d 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -40,8 +40,7 @@ menuconfig ACPI
 	  the UEFI Forum and any UEFI member can join the ASWG and contribute
 	  to the ACPI specification.
 	  The specification is available at:
-	  <http://www.acpi.info>
-	  <http://www.uefi.org/acpi/specs>
+	  <https://uefi.org/specifications>
 
 if ACPI
 
diff --git a/include/linux/tboot.h b/include/linux/tboot.h
index c7e424766360..5146d2574e85 100644
--- a/include/linux/tboot.h
+++ b/include/linux/tboot.h
@@ -44,7 +44,7 @@ struct tboot_acpi_generic_address {
 
 /*
  * combines Sx info from FADT and FACS tables per ACPI 2.0+ spec
- * (http://www.acpi.info/)
+ * (https://uefi.org/specifications)
  */
 struct tboot_acpi_sleep_info {
 	struct tboot_acpi_generic_address pm1a_cnt_blk;
diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1
index 80a1311fa747..20b6345c53ad 100644
--- a/tools/power/cpupower/man/cpupower-idle-info.1
+++ b/tools/power/cpupower/man/cpupower-idle-info.1
@@ -75,7 +75,7 @@ By default only values of core zero are displayed. How to display settings of
 other cores is described in the cpupower(1) manpage in the \-\-cpu option
 section.
 .SH REFERENCES
-http://www.acpi.info/spec.htm
+https://uefi.org/specifications
 .SH "FILES"
 .nf
 \fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP
-- 
cgit v1.2.3


From 8365a898fe53f85529566501d3b3d88640b3975e Mon Sep 17 00:00:00 2001
From: Sumeet Pawnikar <sumeet.r.pawnikar@intel.com>
Date: Thu, 16 Jul 2020 23:14:55 +0530
Subject: powercap: Add Power Limit4 support

Modern Intel Mobile platforms support power limit4 (PL4), which is
the SoC package level maximum power limit (in Watts). It can be used
to preemptively limits potential SoC power to prevent power spikes
from tripping the power adapter and battery over-current protection.
This patch enables this feature by exposing package level peak power
capping control to userspace via RAPL sysfs interface. With this,
application like DTPF can modify PL4 power limit, the similar way
of other package power limit (PL1).
As this feature is not tested on previous generations, here it is
enabled only for the platform that has been verified to work,
for safety concerns.

Signed-off-by: Sumeet Pawnikar <sumeet.r.pawnikar@intel.com>
Co-developed-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Reviewed-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Tested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/powercap/powercap.rst | 15 ++++++---
 drivers/powercap/intel_rapl_common.c      | 54 +++++++++++++++++++++++++++++--
 drivers/powercap/intel_rapl_msr.c         | 15 +++++++++
 include/linux/intel_rapl.h                |  5 ++-
 4 files changed, 81 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/powercap/powercap.rst b/Documentation/power/powercap/powercap.rst
index 7ae3b44c7624..e75d12596dac 100644
--- a/Documentation/power/powercap/powercap.rst
+++ b/Documentation/power/powercap/powercap.rst
@@ -167,11 +167,13 @@ For example::
 package-0
 ---------
 
-The Intel RAPL technology allows two constraints, short term and long term,
-with two different time windows to be applied to each power zone.  Thus for
-each zone there are 2 attributes representing the constraint names, 2 power
-limits and 2 attributes representing the sizes of the time windows. Such that,
-constraint_j_* attributes correspond to the jth constraint (j = 0,1).
+Depending on different power zones, the Intel RAPL technology allows
+one or multiple constraints like short term, long term and peak power,
+with different time windows to be applied to each power zone.
+All the zones contain attributes representing the constraint names,
+power limits and the sizes of the time windows. Note that time window
+is not applicable to peak power. Here, constraint_j_* attributes
+correspond to the jth constraint (j = 0,1,2).
 
 For example::
 
@@ -181,6 +183,9 @@ For example::
 	constraint_1_name
 	constraint_1_power_limit_uw
 	constraint_1_time_window_us
+	constraint_2_name
+	constraint_2_power_limit_uw
+	constraint_2_time_window_us
 
 Power Zone Attributes
 =====================
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index b739ce4f390d..6f55aaef8afc 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -39,6 +39,8 @@
 #define POWER_HIGH_LOCK         BIT_ULL(63)
 #define POWER_LOW_LOCK          BIT(31)
 
+#define POWER_LIMIT4_MASK		0x1FFF
+
 #define TIME_WINDOW1_MASK       (0x7FULL<<17)
 #define TIME_WINDOW2_MASK       (0x7FULL<<49)
 
@@ -82,6 +84,7 @@ enum unit_type {
 
 static const char pl1_name[] = "long_term";
 static const char pl2_name[] = "short_term";
+static const char pl4_name[] = "peak_power";
 
 #define power_zone_to_rapl_domain(_zone) \
 	container_of(_zone, struct rapl_domain, power_zone)
@@ -338,6 +341,9 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		rapl_write_data_raw(rd, POWER_LIMIT2, power_limit);
 		break;
+	case PL4_ENABLE:
+		rapl_write_data_raw(rd, POWER_LIMIT4, power_limit);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -372,6 +378,9 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		prim = POWER_LIMIT2;
 		break;
+	case PL4_ENABLE:
+		prim = POWER_LIMIT4;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -441,6 +450,13 @@ static int get_time_window(struct powercap_zone *power_zone, int cid,
 	case PL2_ENABLE:
 		ret = rapl_read_data_raw(rd, TIME_WINDOW2, true, &val);
 		break;
+	case PL4_ENABLE:
+		/*
+		 * Time window parameter is not applicable for PL4 entry
+		 * so assigining '0' as default value.
+		 */
+		val = 0;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -484,6 +500,9 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	case PL2_ENABLE:
 		prim = MAX_POWER;
 		break;
+	case PL4_ENABLE:
+		prim = MAX_POWER;
+		break;
 	default:
 		put_online_cpus();
 		return -EINVAL;
@@ -493,6 +512,10 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	else
 		*data = val;
 
+	/* As a generalization rule, PL4 would be around two times PL2. */
+	if (rd->rpl[id].prim_id == PL4_ENABLE)
+		*data = *data * 2;
+
 	put_online_cpus();
 
 	return ret;
@@ -525,12 +548,22 @@ static void rapl_init_domains(struct rapl_package *rp)
 		rd->id = i;
 		rd->rpl[0].prim_id = PL1_ENABLE;
 		rd->rpl[0].name = pl1_name;
-		/* some domain may support two power limits */
-		if (rp->priv->limits[i] == 2) {
+
+		/*
+		 * The PL2 power domain is applicable for limits two
+		 * and limits three
+		 */
+		if (rp->priv->limits[i] >= 2) {
 			rd->rpl[1].prim_id = PL2_ENABLE;
 			rd->rpl[1].name = pl2_name;
 		}
 
+		/* Enable PL4 domain if the total power limits are three */
+		if (rp->priv->limits[i] == 3) {
+			rd->rpl[2].prim_id = PL4_ENABLE;
+			rd->rpl[2].name = pl4_name;
+		}
+
 		for (j = 0; j < RAPL_DOMAIN_REG_MAX; j++)
 			rd->regs[j] = rp->priv->regs[i][j];
 
@@ -599,6 +632,8 @@ static struct rapl_primitive_info rpi[] = {
 			    RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0),
 	PRIMITIVE_INFO_INIT(POWER_LIMIT2, POWER_LIMIT2_MASK, 32,
 			    RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0),
+	PRIMITIVE_INFO_INIT(POWER_LIMIT4, POWER_LIMIT4_MASK, 0,
+				RAPL_DOMAIN_REG_PL4, POWER_UNIT, 0),
 	PRIMITIVE_INFO_INIT(FW_LOCK, POWER_LOW_LOCK, 31,
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(PL1_ENABLE, POWER_LIMIT1_ENABLE, 15,
@@ -609,6 +644,8 @@ static struct rapl_primitive_info rpi[] = {
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(PL2_CLAMP, POWER_LIMIT2_CLAMP, 48,
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
+	PRIMITIVE_INFO_INIT(PL4_ENABLE, POWER_LIMIT4_MASK, 0,
+				RAPL_DOMAIN_REG_PL4, ARBITRARY_UNIT, 0),
 	PRIMITIVE_INFO_INIT(TIME_WINDOW1, TIME_WINDOW1_MASK, 17,
 			    RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0),
 	PRIMITIVE_INFO_INIT(TIME_WINDOW2, TIME_WINDOW2_MASK, 49,
@@ -1273,6 +1310,7 @@ void rapl_remove_package(struct rapl_package *rp)
 		if (find_nr_power_limit(rd) > 1) {
 			rapl_write_data_raw(rd, PL2_ENABLE, 0);
 			rapl_write_data_raw(rd, PL2_CLAMP, 0);
+			rapl_write_data_raw(rd, PL4_ENABLE, 0);
 		}
 		if (rd->id == RAPL_DOMAIN_PACKAGE) {
 			rd_package = rd;
@@ -1381,6 +1419,13 @@ static void power_limit_state_save(void)
 				if (ret)
 					rd->rpl[i].last_power_limit = 0;
 				break;
+			case PL4_ENABLE:
+				ret = rapl_read_data_raw(rd,
+						 POWER_LIMIT4, true,
+						 &rd->rpl[i].last_power_limit);
+				if (ret)
+					rd->rpl[i].last_power_limit = 0;
+				break;
 			}
 		}
 	}
@@ -1411,6 +1456,11 @@ static void power_limit_state_restore(void)
 					rapl_write_data_raw(rd, POWER_LIMIT2,
 					    rd->rpl[i].last_power_limit);
 				break;
+			case PL4_ENABLE:
+				if (rd->rpl[i].last_power_limit)
+					rapl_write_data_raw(rd, POWER_LIMIT4,
+					    rd->rpl[i].last_power_limit);
+				break;
 			}
 		}
 	}
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index d5487965bdfe..d2a2627507a9 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -28,6 +28,7 @@
 
 /* Local defines */
 #define MSR_PLATFORM_POWER_LIMIT	0x0000065C
+#define MSR_VR_CURRENT_CONFIG		0x00000601
 
 /* private data for RAPL MSR Interface */
 static struct rapl_if_priv rapl_msr_priv = {
@@ -123,13 +124,27 @@ static int rapl_msr_write_raw(int cpu, struct reg_action *ra)
 	return ra->err;
 }
 
+/* List of verified CPUs. */
+static const struct x86_cpu_id pl4_support_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_TIGERLAKE_L, X86_FEATURE_ANY },
+	{}
+};
+
 static int rapl_msr_probe(struct platform_device *pdev)
 {
+	const struct x86_cpu_id *id = x86_match_cpu(pl4_support_ids);
 	int ret;
 
 	rapl_msr_priv.read_raw = rapl_msr_read_raw;
 	rapl_msr_priv.write_raw = rapl_msr_write_raw;
 
+	if (id) {
+		rapl_msr_priv.limits[RAPL_DOMAIN_PACKAGE] = 3;
+		rapl_msr_priv.regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_PL4] =
+			MSR_VR_CURRENT_CONFIG;
+		pr_info("PL4 support detected.\n");
+	}
+
 	rapl_msr_priv.control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
 	if (IS_ERR(rapl_msr_priv.control_type)) {
 		pr_debug("failed to register powercap control_type.\n");
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index efb3ce892c20..3582176a1eca 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -29,6 +29,7 @@ enum rapl_domain_reg_id {
 	RAPL_DOMAIN_REG_PERF,
 	RAPL_DOMAIN_REG_POLICY,
 	RAPL_DOMAIN_REG_INFO,
+	RAPL_DOMAIN_REG_PL4,
 	RAPL_DOMAIN_REG_MAX,
 };
 
@@ -38,12 +39,14 @@ enum rapl_primitives {
 	ENERGY_COUNTER,
 	POWER_LIMIT1,
 	POWER_LIMIT2,
+	POWER_LIMIT4,
 	FW_LOCK,
 
 	PL1_ENABLE,		/* power limit 1, aka long term */
 	PL1_CLAMP,		/* allow frequency to go below OS request */
 	PL2_ENABLE,		/* power limit 2, aka short term, instantaneous */
 	PL2_CLAMP,
+	PL4_ENABLE,		/* power limit 4, aka max peak power */
 
 	TIME_WINDOW1,		/* long term */
 	TIME_WINDOW2,		/* short term */
@@ -65,7 +68,7 @@ struct rapl_domain_data {
 	unsigned long timestamp;
 };
 
-#define NR_POWER_LIMITS (2)
+#define NR_POWER_LIMITS (3)
 struct rapl_power_limit {
 	struct powercap_zone_constraint *constraint;
 	int prim_id;		/* primitive ID used to enable */
-- 
cgit v1.2.3


From cfd97f94d036bf36122fa19d075c5741347aa178 Mon Sep 17 00:00:00 2001
From: Colton Lewis <colton.w.lewis@protonmail.com>
Date: Sat, 25 Jul 2020 05:02:57 +0000
Subject: spi: correct kernel-doc inconsistency

Silence documentation build warnings by correcting kernel-doc comment
for spi_transfer struct.

Signed-off-by: Colton Lewis <colton.w.lewis@protonmail.com>
Link: https://lore.kernel.org/r/20200725050242.279548-1-colton.w.lewis@protonmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index f8b721fcd5c6..99380c0825db 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -329,6 +329,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	every chipselect is connected to a slave.
  * @dma_alignment: SPI controller constraint on DMA buffers alignment.
  * @mode_bits: flags understood by this controller driver
+ * @buswidth_override_bits: flags to override for this controller driver
  * @bits_per_word_mask: A mask indicating which values of bits_per_word are
  *	supported by the driver. Bit n indicates that a bits_per_word n+1 is
  *	supported. If set, the SPI core will reject any transfer with an
@@ -846,12 +847,7 @@ extern void spi_res_release(struct spi_controller *ctlr,
  *	processed the word, i.e. the "pre" timestamp should be taken before
  *	transmitting the "pre" word, and the "post" timestamp after receiving
  *	transmit confirmation from the controller for the "post" word.
- * @timestamped_pre: Set by the SPI controller driver to denote it has acted
- *	upon the @ptp_sts request. Not set when the SPI core has taken care of
- *	the task. SPI device drivers are free to print a warning if this comes
- *	back unset and they need the better resolution.
- * @timestamped_post: See above. The reason why both exist is that these
- *	booleans are also used to keep state in the core SPI logic.
+ * @timestamped: true if the transfer has been timestamped
  * @error: Error status logged by spi controller driver.
  *
  * SPI transfers always write the same number of bytes as they read.
-- 
cgit v1.2.3


From 2224635938814fc63004e30f7c41943812bd6f1c Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Thu, 16 Jul 2020 13:52:47 +0300
Subject: RDMA/mlx5: Use MLX5_SET macro instead of local structure

Use generic mlx5 structure defined in mlx5_ifc.h to represent ConnectX
device data structures instead of using structure defined specifically for
mlx5_ib module.

Link: https://lore.kernel.org/r/20200716105248.1423452-3-leon@kernel.org
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  9 ---------
 drivers/infiniband/hw/mlx5/wr.c      | 26 ++++++++++++++++----------
 include/linux/mlx5/device.h          |  1 -
 3 files changed, 16 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 5dbe3eb0d9cb..d9dfe38f4160 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1423,15 +1423,6 @@ static inline void init_query_mad(struct ib_smp *mad)
 	mad->method	   = IB_MGMT_METHOD_GET;
 }
 
-static inline u8 convert_access(int acc)
-{
-	return (acc & IB_ACCESS_REMOTE_ATOMIC ? MLX5_PERM_ATOMIC       : 0) |
-	       (acc & IB_ACCESS_REMOTE_WRITE  ? MLX5_PERM_REMOTE_WRITE : 0) |
-	       (acc & IB_ACCESS_REMOTE_READ   ? MLX5_PERM_REMOTE_READ  : 0) |
-	       (acc & IB_ACCESS_LOCAL_WRITE   ? MLX5_PERM_LOCAL_WRITE  : 0) |
-	       MLX5_PERM_LOCAL_READ;
-}
-
 static inline int is_qp1(enum ib_qp_type qp_type)
 {
 	return qp_type == MLX5_IB_QPT_HW_GSI;
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index 2c6df1c43b55..e58ecb46f8e3 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -383,20 +383,26 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg,
 
 	memset(seg, 0, sizeof(*seg));
 	if (wr->send_flags & MLX5_IB_SEND_UMR_DISABLE_MR)
-		seg->status = MLX5_MKEY_STATUS_FREE;
-
-	seg->flags = convert_access(umrwr->access_flags);
+		MLX5_SET(mkc, seg, free, 1);
+
+	MLX5_SET(mkc, seg, a,
+		 !!(umrwr->access_flags & IB_ACCESS_REMOTE_ATOMIC));
+	MLX5_SET(mkc, seg, rw,
+		 !!(umrwr->access_flags & IB_ACCESS_REMOTE_WRITE));
+	MLX5_SET(mkc, seg, rr, !!(umrwr->access_flags & IB_ACCESS_REMOTE_READ));
+	MLX5_SET(mkc, seg, lw, !!(umrwr->access_flags & IB_ACCESS_LOCAL_WRITE));
+	MLX5_SET(mkc, seg, lr, 1);
 	if (umrwr->pd)
-		seg->flags_pd = cpu_to_be32(to_mpd(umrwr->pd)->pdn);
+		MLX5_SET(mkc, seg, pd, to_mpd(umrwr->pd)->pdn);
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION &&
 	    !umrwr->length)
-		seg->flags_pd |= cpu_to_be32(MLX5_MKEY_LEN64);
+		MLX5_SET(mkc, seg, length64, 1);
 
-	seg->start_addr = cpu_to_be64(umrwr->virt_addr);
-	seg->len = cpu_to_be64(umrwr->length);
-	seg->log2_page_size = umrwr->page_shift;
-	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff00 |
-				       mlx5_mkey_variant(umrwr->mkey));
+	MLX5_SET64(mkc, seg, start_addr, umrwr->virt_addr);
+	MLX5_SET64(mkc, seg, len, umrwr->length);
+	MLX5_SET(mkc, seg, log_page_size, umrwr->page_shift);
+	MLX5_SET(mkc, seg, qpn, 0xffffff);
+	MLX5_SET(mkc, seg, mkey_7_0, mlx5_mkey_variant(umrwr->mkey));
 }
 
 static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 2aacf9a8ee4d..d184b579617f 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1007,7 +1007,6 @@ enum {
 	MLX5_MKEY_REMOTE_INVAL	= 1 << 24,
 	MLX5_MKEY_FLAG_SYNC_UMR = 1 << 29,
 	MLX5_MKEY_BSF_EN	= 1 << 30,
-	MLX5_MKEY_LEN64		= 1 << 31,
 };
 
 struct mlx5_mkey_seg {
-- 
cgit v1.2.3


From 896ec9735336f5adb576d372ed7e411bce2fc74c Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Thu, 16 Jul 2020 13:52:48 +0300
Subject: RDMA/mlx5: Set mkey relaxed ordering by UMR with ConnectX-7

Up to ConnectX-7 UMR is not used when user passes relaxed ordering access
flag. ConnectX-7 supports setting relaxed ordering read/write mkey
attribute by UMR, indicated by new HCA capabilities.

With ConnectX-7 driver uses UMR when user set relaxed ordering access
flag, in contrast to previous silicon models. Specifically it includes
setting relvant flags of mkey context mask in UMR control segment, and
relaxed ordering write and read flags in UMR mkey context segment.

Link: https://lore.kernel.org/r/20200716105248.1423452-4-leon@kernel.org
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  9 ++++++--
 drivers/infiniband/hw/mlx5/wr.c      | 44 ++++++++++++++++++++++++++++--------
 include/linux/mlx5/device.h          |  4 +++-
 3 files changed, 45 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index d9dfe38f4160..cdd04b3d7d51 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1524,8 +1524,13 @@ static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
 		return false;
 
 	if (access_flags & IB_ACCESS_RELAXED_ORDERING &&
-	    (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write) ||
-	     MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read)))
+	    MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write) &&
+	    !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write_umr))
+		return false;
+
+	if (access_flags & IB_ACCESS_RELAXED_ORDERING &&
+	     MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) &&
+	     !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr))
 		return false;
 
 	return true;
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index e58ecb46f8e3..4d4f8c22b3e6 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -263,7 +263,9 @@ static __be64 get_umr_update_translation_mask(void)
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_access_mask(int atomic)
+static __be64 get_umr_update_access_mask(int atomic,
+					 int relaxed_ordering_write,
+					 int relaxed_ordering_read)
 {
 	u64 result;
 
@@ -275,6 +277,12 @@ static __be64 get_umr_update_access_mask(int atomic)
 	if (atomic)
 		result |= MLX5_MKEY_MASK_A;
 
+	if (relaxed_ordering_write)
+		result |= MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE;
+
+	if (relaxed_ordering_read)
+		result |= MLX5_MKEY_MASK_RELAXED_ORDERING_READ;
+
 	return cpu_to_be64(result);
 }
 
@@ -289,17 +297,28 @@ static __be64 get_umr_update_pd_mask(void)
 
 static int umr_check_mkey_mask(struct mlx5_ib_dev *dev, u64 mask)
 {
-	if ((mask & MLX5_MKEY_MASK_PAGE_SIZE &&
-	     MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled)) ||
-	    (mask & MLX5_MKEY_MASK_A &&
-	     MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled)))
+	if (mask & MLX5_MKEY_MASK_PAGE_SIZE &&
+	    MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled))
+		return -EPERM;
+
+	if (mask & MLX5_MKEY_MASK_A &&
+	    MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled))
+		return -EPERM;
+
+	if (mask & MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE &&
+	    !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write_umr))
+		return -EPERM;
+
+	if (mask & MLX5_MKEY_MASK_RELAXED_ORDERING_READ &&
+	    !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr))
 		return -EPERM;
+
 	return 0;
 }
 
 static int set_reg_umr_segment(struct mlx5_ib_dev *dev,
 			       struct mlx5_wqe_umr_ctrl_seg *umr,
-			       const struct ib_send_wr *wr, int atomic)
+			       const struct ib_send_wr *wr)
 {
 	const struct mlx5_umr_wr *umrwr = umr_wr(wr);
 
@@ -325,7 +344,10 @@ static int set_reg_umr_segment(struct mlx5_ib_dev *dev,
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION)
 		umr->mkey_mask |= get_umr_update_translation_mask();
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS) {
-		umr->mkey_mask |= get_umr_update_access_mask(atomic);
+		umr->mkey_mask |= get_umr_update_access_mask(
+			!!(MLX5_CAP_GEN(dev->mdev, atomic)),
+			!!(MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write_umr)),
+			!!(MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr)));
 		umr->mkey_mask |= get_umr_update_pd_mask();
 	}
 	if (wr->send_flags & MLX5_IB_SEND_UMR_ENABLE_MR)
@@ -392,6 +414,11 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg,
 	MLX5_SET(mkc, seg, rr, !!(umrwr->access_flags & IB_ACCESS_REMOTE_READ));
 	MLX5_SET(mkc, seg, lw, !!(umrwr->access_flags & IB_ACCESS_LOCAL_WRITE));
 	MLX5_SET(mkc, seg, lr, 1);
+	MLX5_SET(mkc, seg, relaxed_ordering_write,
+		 !!(umrwr->access_flags & IB_ACCESS_RELAXED_ORDERING));
+	MLX5_SET(mkc, seg, relaxed_ordering_read,
+		 !!(umrwr->access_flags & IB_ACCESS_RELAXED_ORDERING));
+
 	if (umrwr->pd)
 		MLX5_SET(mkc, seg, pd, to_mpd(umrwr->pd)->pdn);
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION &&
@@ -1230,8 +1257,7 @@ static int handle_qpt_reg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 
 	qp->sq.wr_data[idx] = MLX5_IB_WR_UMR;
 	(*ctrl)->imm = cpu_to_be32(umr_wr(wr)->mkey);
-	err = set_reg_umr_segment(dev, *seg, wr,
-				  !!(MLX5_CAP_GEN(dev->mdev, atomic)));
+	err = set_reg_umr_segment(dev, *seg, wr);
 	if (unlikely(err))
 		goto out;
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index d184b579617f..4d3376e20f5e 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -276,7 +276,9 @@ enum {
 	MLX5_MKEY_MASK_RW		= 1ull << 20,
 	MLX5_MKEY_MASK_A		= 1ull << 21,
 	MLX5_MKEY_MASK_SMALL_FENCE	= 1ull << 23,
-	MLX5_MKEY_MASK_FREE		= 1ull << 29,
+	MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE	= 1ull << 25,
+	MLX5_MKEY_MASK_FREE			= 1ull << 29,
+	MLX5_MKEY_MASK_RELAXED_ORDERING_READ	= 1ull << 47,
 };
 
 enum {
-- 
cgit v1.2.3


From f0c7baca180046824e07fc5f1326e83a8fd150c7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 24 Jul 2020 22:44:41 +0200
Subject: genirq/affinity: Make affinity setting if activated opt-in

John reported that on a RK3288 system the perf per CPU interrupts are all
affine to CPU0 and provided the analysis:

 "It looks like what happens is that because the interrupts are not per-CPU
  in the hardware, armpmu_request_irq() calls irq_force_affinity() while
  the interrupt is deactivated and then request_irq() with IRQF_PERCPU |
  IRQF_NOBALANCING.

  Now when irq_startup() runs with IRQ_STARTUP_NORMAL, it calls
  irq_setup_affinity() which returns early because IRQF_PERCPU and
  IRQF_NOBALANCING are set, leaving the interrupt on its original CPU."

This was broken by the recent commit which blocked interrupt affinity
setting in hardware before activation of the interrupt. While this works in
general, it does not work for this particular case. As contrary to the
initial analysis not all interrupt chip drivers implement an activate
callback, the safe cure is to make the deferred interrupt affinity setting
at activation time opt-in.

Implement the necessary core logic and make the two irqchip implementations
for which this is required opt-in. In hindsight this would have been the
right thing to do, but ...

Fixes: baedb87d1b53 ("genirq/affinity: Handle affinity setting on inactive interrupts correctly")
Reported-by: John Keeping <john@metanate.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marc Zyngier <maz@kernel.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/87blk4tzgm.fsf@nanos.tec.linutronix.de
---
 arch/x86/kernel/apic/vector.c    |  4 ++++
 drivers/irqchip/irq-gic-v3-its.c |  5 ++++-
 include/linux/irq.h              | 13 +++++++++++++
 kernel/irq/manage.c              |  6 +++++-
 4 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 7649da2478d8..dae32d948bf2 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -560,6 +560,10 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		 * as that can corrupt the affinity move state.
 		 */
 		irqd_set_handle_enforce_irqctx(irqd);
+
+		/* Don't invoke affinity setter on deactivated interrupts */
+		irqd_set_affinity_on_activate(irqd);
+
 		/*
 		 * Legacy vectors are already assigned when the IOAPIC
 		 * takes them over. They stay on the same vector. This is
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index beac4caefad9..103d850b5595 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3523,6 +3523,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	msi_alloc_info_t *info = args;
 	struct its_device *its_dev = info->scratchpad[0].ptr;
 	struct its_node *its = its_dev->its;
+	struct irq_data *irqd;
 	irq_hw_number_t hwirq;
 	int err;
 	int i;
@@ -3542,7 +3543,9 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
 					      hwirq + i, &its_irq_chip, its_dev);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
+		irqd = irq_get_irq_data(virq + i);
+		irqd_set_single_target(irqd);
+		irqd_set_affinity_on_activate(irqd);
 		pr_debug("ID:%d pID:%d vID:%d\n",
 			 (int)(hwirq + i - its_dev->event_map.lpi_base),
 			 (int)(hwirq + i), virq + i);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8d5bc2c237d7..1b7f4dfee35b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -213,6 +213,8 @@ struct irq_data {
  *				  required
  * IRQD_HANDLE_ENFORCE_IRQCTX	- Enforce that handle_irq_*() is only invoked
  *				  from actual interrupt context.
+ * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
+ *				  irq_chip::irq_set_affinity() when deactivated.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -237,6 +239,7 @@ enum {
 	IRQD_CAN_RESERVE		= (1 << 26),
 	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
 	IRQD_HANDLE_ENFORCE_IRQCTX	= (1 << 28),
+	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -421,6 +424,16 @@ static inline bool irqd_msi_nomask_quirk(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK;
 }
 
+static inline void irqd_set_affinity_on_activate(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;
+}
+
+static inline bool irqd_affinity_on_activate(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE;
+}
+
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 2a9fec53e159..48c38e09c673 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -320,12 +320,16 @@ static bool irq_set_affinity_deactivated(struct irq_data *data,
 	struct irq_desc *desc = irq_data_to_desc(data);
 
 	/*
+	 * Handle irq chips which can handle affinity only in activated
+	 * state correctly
+	 *
 	 * If the interrupt is not yet activated, just store the affinity
 	 * mask and do not call the chip driver at all. On activation the
 	 * driver has to make sure anyway that the interrupt is in a
 	 * useable state so startup works.
 	 */
-	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data))
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
+	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
 		return false;
 
 	cpumask_copy(desc->irq_common_data.affinity, mask);
-- 
cgit v1.2.3


From 229f5879facf96e5640c0385f62b8cb5f27b8a43 Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Wed, 22 Jul 2020 16:33:05 +0530
Subject: linux/kernel.h: Add PTR_ALIGN_DOWN macro

Add a macro for aligning down a pointer. This is useful to get an
aligned register address when a device allows only word access and
doesn't allow half word or byte access.

Link: https://lore.kernel.org/r/20200722110317.4744-4-kishon@ti.com
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
---
 include/linux/kernel.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 82d91547d122..7339a00c895e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -34,6 +34,7 @@
 #define ALIGN_DOWN(x, a)	__ALIGN_KERNEL((x) - ((a) - 1), (a))
 #define __ALIGN_MASK(x, mask)	__ALIGN_KERNEL_MASK((x), (mask))
 #define PTR_ALIGN(p, a)		((typeof(p))ALIGN((unsigned long)(p), (a)))
+#define PTR_ALIGN_DOWN(p, a)	((typeof(p))ALIGN_DOWN((unsigned long)(p), (a)))
 #define IS_ALIGNED(x, a)		(((x) & ((typeof(x))(a) - 1)) == 0)
 
 /* generic data direction definitions */
-- 
cgit v1.2.3


From b54cecf5e2293d15620f7b3f8d1bf486243d5643 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Sun, 7 Jun 2020 12:10:40 +0300
Subject: fsnotify: pass dir argument to handle_event() callback

The 'inode' argument to handle_event(), sometimes referred to as
'to_tell' is somewhat obsolete.
It is a remnant from the times when a group could only have an inode mark
associated with an event.

We now pass an iter_info array to the callback, with all marks associated
with an event.

Most backends ignore this argument, with two exceptions:
1. dnotify uses it for sanity check that event is on directory
2. fanotify uses it to report fid of directory on directory entry
   modification events

Remove the 'inode' argument and add a 'dir' argument.
The callback function signature is deliberately changed, because
the meaning of the argument has changed and the arguments have
been documented.

The 'dir' argument is set to when 'file_name' is specified and it is
referring to the directory that the 'file_name' entry belongs to.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/nfsd/filecache.c                  |  6 +++---
 fs/notify/dnotify/dnotify.c          |  8 ++++----
 fs/notify/fanotify/fanotify.c        | 23 +++++++++++------------
 fs/notify/fsnotify.c                 | 26 ++++++++++++--------------
 fs/notify/inotify/inotify.h          |  6 +++---
 fs/notify/inotify/inotify_fsnotify.c |  7 +++----
 fs/notify/inotify/inotify_user.c     |  4 ++--
 include/linux/fsnotify_backend.h     | 16 +++++++++++++---
 kernel/audit_fsnotify.c              | 10 +++++-----
 kernel/audit_tree.c                  |  6 +++---
 kernel/audit_watch.c                 |  6 +++---
 11 files changed, 62 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ace8e5c30952..bbc7892d2928 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -598,9 +598,9 @@ static struct notifier_block nfsd_file_lease_notifier = {
 };
 
 static int
-nfsd_file_fsnotify_handle_event(struct fsnotify_group *group,
-				struct inode *to_tell,
-				u32 mask, const void *data, int data_type,
+nfsd_file_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
+				const void *data, int data_type,
+				struct inode *dir,
 				const struct qstr *file_name, u32 cookie,
 				struct fsnotify_iter_info *iter_info)
 {
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 7a42c2ebe28d..2d2eadfb5186 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -70,9 +70,9 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
  * destroy the dnotify struct if it was not registered to receive multiple
  * events.
  */
-static int dnotify_handle_event(struct fsnotify_group *group,
-				struct inode *inode,
-				u32 mask, const void *data, int data_type,
+static int dnotify_handle_event(struct fsnotify_group *group, u32 mask,
+				const void *data, int data_type,
+				struct inode *dir,
 				const struct qstr *file_name, u32 cookie,
 				struct fsnotify_iter_info *iter_info)
 {
@@ -84,7 +84,7 @@ static int dnotify_handle_event(struct fsnotify_group *group,
 	__u32 test_mask = mask & ~FS_EVENT_ON_CHILD;
 
 	/* not a dir, dnotify doesn't care */
-	if (!S_ISDIR(inode->i_mode))
+	if (!dir && !(mask & FS_ISDIR))
 		return 0;
 
 	if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 41f5fc9a8f19..e417c64c365b 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -335,11 +335,11 @@ out:
  * FS_ATTRIB reports the child inode even if reported on a watched parent.
  * FS_CREATE reports the modified dir inode and not the created inode.
  */
-static struct inode *fanotify_fid_inode(struct inode *to_tell, u32 event_mask,
-					const void *data, int data_type)
+static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
+					int data_type, struct inode *dir)
 {
 	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
-		return to_tell;
+		return dir;
 
 	return fsnotify_data_inode(data, data_type);
 }
@@ -416,14 +416,14 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
 }
 
 static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
-						   struct inode *inode, u32 mask,
-						   const void *data, int data_type,
+						   u32 mask, const void *data,
+						   int data_type, struct inode *dir,
 						   const struct qstr *file_name,
 						   __kernel_fsid_t *fsid)
 {
 	struct fanotify_event *event = NULL;
 	gfp_t gfp = GFP_KERNEL_ACCOUNT;
-	struct inode *id = fanotify_fid_inode(inode, mask, data, data_type);
+	struct inode *id = fanotify_fid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
 
 	/*
@@ -507,9 +507,9 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	return fsid;
 }
 
-static int fanotify_handle_event(struct fsnotify_group *group,
-				 struct inode *inode,
-				 u32 mask, const void *data, int data_type,
+static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
+				 const void *data, int data_type,
+				 struct inode *dir,
 				 const struct qstr *file_name, u32 cookie,
 				 struct fsnotify_iter_info *iter_info)
 {
@@ -546,8 +546,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	if (!mask)
 		return 0;
 
-	pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
-		 mask);
+	pr_debug("%s: group=%p mask=%x\n", __func__, group, mask);
 
 	if (fanotify_is_perm_event(mask)) {
 		/*
@@ -565,7 +564,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 			return 0;
 	}
 
-	event = fanotify_alloc_event(group, inode, mask, data, data_type,
+	event = fanotify_alloc_event(group, mask, data, data_type, dir,
 				     file_name, &fsid);
 	ret = -ENOMEM;
 	if (unlikely(!event)) {
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 30628a72ca01..c4ac4d13e10f 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -185,11 +185,9 @@ notify_child:
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
-static int send_to_group(struct inode *to_tell,
-			 __u32 mask, const void *data,
-			 int data_is, u32 cookie,
-			 const struct qstr *file_name,
-			 struct fsnotify_iter_info *iter_info)
+static int send_to_group(__u32 mask, const void *data, int data_type,
+			 struct inode *dir, const struct qstr *file_name,
+			 u32 cookie, struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_group *group = NULL;
 	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
@@ -225,15 +223,14 @@ static int send_to_group(struct inode *to_tell,
 		}
 	}
 
-	pr_debug("%s: group=%p to_tell=%p mask=%x marks_mask=%x marks_ignored_mask=%x"
-		 " data=%p data_is=%d cookie=%d\n",
-		 __func__, group, to_tell, mask, marks_mask, marks_ignored_mask,
-		 data, data_is, cookie);
+	pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
+		 __func__, group, mask, marks_mask, marks_ignored_mask,
+		 data, data_type, dir, cookie);
 
 	if (!(test_mask & marks_mask & ~marks_ignored_mask))
 		return 0;
 
-	return group->ops->handle_event(group, to_tell, mask, data, data_is,
+	return group->ops->handle_event(group, mask, data, data_type, dir,
 					file_name, cookie, iter_info);
 }
 
@@ -317,12 +314,13 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
  * out to all of the registered fsnotify_group.  Those groups can then use the
  * notification event in whatever means they feel necessary.
  */
-int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
+int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type,
 	     const struct qstr *file_name, u32 cookie)
 {
-	const struct path *path = fsnotify_data_path(data, data_is);
+	const struct path *path = fsnotify_data_path(data, data_type);
 	struct fsnotify_iter_info iter_info = {};
 	struct super_block *sb = to_tell->i_sb;
+	struct inode *dir = file_name ? to_tell : NULL;
 	struct mount *mnt = NULL;
 	int ret = 0;
 	__u32 test_mask, marks_mask;
@@ -375,8 +373,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	 * That's why this traversal is so complicated...
 	 */
 	while (fsnotify_iter_select_report_types(&iter_info)) {
-		ret = send_to_group(to_tell, mask, data, data_is, cookie,
-				    file_name, &iter_info);
+		ret = send_to_group(mask, data, data_type, dir, file_name,
+				    cookie, &iter_info);
 
 		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
 			goto out;
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 3f246f7b8a92..4327d0e9c364 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -24,9 +24,9 @@ static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse)
 
 extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 					   struct fsnotify_group *group);
-extern int inotify_handle_event(struct fsnotify_group *group,
-				struct inode *inode,
-				u32 mask, const void *data, int data_type,
+extern int inotify_handle_event(struct fsnotify_group *group, u32 mask,
+				const void *data, int data_type,
+				struct inode *dir,
 				const struct qstr *file_name, u32 cookie,
 				struct fsnotify_iter_info *iter_info);
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 9b481460a2dc..dfd455798a1b 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -55,9 +55,8 @@ static int inotify_merge(struct list_head *list,
 	return event_compare(last_event, event);
 }
 
-int inotify_handle_event(struct fsnotify_group *group,
-			 struct inode *inode,
-			 u32 mask, const void *data, int data_type,
+int inotify_handle_event(struct fsnotify_group *group, u32 mask,
+			 const void *data, int data_type, struct inode *dir,
 			 const struct qstr *file_name, u32 cookie,
 			 struct fsnotify_iter_info *iter_info)
 {
@@ -82,7 +81,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 		alloc_len += len + 1;
 	}
 
-	pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
+	pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark,
 		 mask);
 
 	i_mark = container_of(inode_mark, struct inotify_inode_mark,
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index f88bbcc9efeb..5385d5817dd9 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -490,8 +490,8 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 					   fsn_mark);
 
 	/* Queue ignore event for the watch */
-	inotify_handle_event(group, NULL, FS_IN_IGNORED, NULL,
-			     FSNOTIFY_EVENT_NONE, NULL, 0, &iter_info);
+	inotify_handle_event(group, FS_IN_IGNORED, NULL, FSNOTIFY_EVENT_NONE,
+			     NULL, NULL, 0, &iter_info);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 97300f3b8ff0..0de130cbf72d 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -108,6 +108,17 @@ struct mem_cgroup;
  * these operations for each relevant group.
  *
  * handle_event - main call for a group to handle an fs event
+ * @group:	group to notify
+ * @mask:	event type and flags
+ * @data:	object that event happened on
+ * @data_type:	type of object for fanotify_data_XXX() accessors
+ * @dir:	optional directory associated with event -
+ *		if @file_name is not NULL, this is the directory that
+ *		@file_name is relative to
+ * @file_name:	optional file name associated with event
+ * @cookie:	inotify rename cookie
+ * @iter_info:	array of marks from this group that are interested in the event
+ *
  * free_group_priv - called when a group refcnt hits 0 to clean up the private union
  * freeing_mark - called when a mark is being destroyed for some reason.  The group
  * 		MUST be holding a reference on each mark and that reference must be
@@ -115,9 +126,8 @@ struct mem_cgroup;
  * 		userspace messages that marks have been removed.
  */
 struct fsnotify_ops {
-	int (*handle_event)(struct fsnotify_group *group,
-			    struct inode *inode,
-			    u32 mask, const void *data, int data_type,
+	int (*handle_event)(struct fsnotify_group *group, u32 mask,
+			    const void *data, int data_type, struct inode *dir,
 			    const struct qstr *file_name, u32 cookie,
 			    struct fsnotify_iter_info *iter_info);
 	void (*free_group_priv)(struct fsnotify_group *group);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 3596448bfdab..30ca239285a3 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -152,11 +152,11 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark)
 }
 
 /* Update mark data in audit rules based on fsnotify events. */
-static int audit_mark_handle_event(struct fsnotify_group *group,
-				    struct inode *to_tell,
-				    u32 mask, const void *data, int data_type,
-				    const struct qstr *dname, u32 cookie,
-				    struct fsnotify_iter_info *iter_info)
+static int audit_mark_handle_event(struct fsnotify_group *group, u32 mask,
+				   const void *data, int data_type,
+				   struct inode *dir,
+				   const struct qstr *dname, u32 cookie,
+				   struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct audit_fsnotify_mark *audit_mark;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e49c912f862d..2ce2ac1ce100 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -1037,9 +1037,9 @@ static void evict_chunk(struct audit_chunk *chunk)
 		audit_schedule_prune();
 }
 
-static int audit_tree_handle_event(struct fsnotify_group *group,
-				   struct inode *to_tell,
-				   u32 mask, const void *data, int data_type,
+static int audit_tree_handle_event(struct fsnotify_group *group, u32 mask,
+				   const void *data, int data_type,
+				   struct inode *dir,
 				   const struct qstr *file_name, u32 cookie,
 				   struct fsnotify_iter_info *iter_info)
 {
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index e09c551ae52d..61fd601f1edf 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -464,9 +464,9 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 }
 
 /* Update watch data in audit rules based on fsnotify events. */
-static int audit_watch_handle_event(struct fsnotify_group *group,
-				    struct inode *to_tell,
-				    u32 mask, const void *data, int data_type,
+static int audit_watch_handle_event(struct fsnotify_group *group, u32 mask,
+				    const void *data, int data_type,
+				    struct inode *dir,
 				    const struct qstr *dname, u32 cookie,
 				    struct fsnotify_iter_info *iter_info)
 {
-- 
cgit v1.2.3


From 8be23aec0ee151de731626d5578973fde25b2285 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sat, 25 Jul 2020 16:07:36 +0200
Subject: i2c: also convert placeholder function to return errno

All i2c_new_device-alike functions return ERR_PTR these days, but this
fallback function was missed.

Fixes: 2dea645ffc21 ("i2c: acpi: Return error pointers from i2c_acpi_new_device()")
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
[wsa: changed from 'ENOSYS' to 'ENODEV']
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index ee328cf80bd9..4e7714c88f95 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -1001,7 +1001,7 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev)
 static inline struct i2c_client *i2c_acpi_new_device(struct device *dev,
 					int index, struct i2c_board_info *info)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle)
 {
-- 
cgit v1.2.3


From b4e9c9549f62329d2412f899635fddc5212b9cd4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 1 Jun 2020 19:42:40 -0400
Subject: introduction of regset ->get() wrappers, switching ELF coredumps to
 those

Two new helpers: given a process and regset, dump into a buffer.
regset_get() takes a buffer and size, regset_get_alloc() takes size
and allocates a buffer.

Return value in both cases is the amount of data actually dumped in
case of success or -E...  on error.

In both cases the size is capped by regset->n * regset->size, so
->get() is called with offset 0 and size no more than what regset
expects.

binfmt_elf.c callers of ->get() are switched to using those; the other
caller (copy_regset_to_user()) will need some preparations to switch.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/binfmt_elf.c        | 54 ++++++++++++++++++++++++--------------------------
 include/linux/regset.h |  9 +++++++++
 kernel/Makefile        |  2 +-
 kernel/regset.c        | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 90 insertions(+), 29 deletions(-)
 create mode 100644 kernel/regset.c

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 9fe3b51c116a..e922a6abdca8 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1821,7 +1821,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 				 long signr, size_t *total)
 {
 	unsigned int i;
-	unsigned int regset0_size = regset_size(t->task, &view->regsets[0]);
+	int regset0_size;
 
 	/*
 	 * NT_PRSTATUS is the one special case, because the regset data
@@ -1830,8 +1830,10 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	 * We assume that regset 0 is NT_PRSTATUS.
 	 */
 	fill_prstatus(&t->prstatus, t->task, signr);
-	(void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset0_size,
-				    &t->prstatus.pr_reg, NULL);
+	regset0_size = regset_get(t->task, &view->regsets[0],
+		   sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg);
+	if (regset0_size < 0)
+		return 0;
 
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
 		  PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus);
@@ -1846,32 +1848,28 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	 */
 	for (i = 1; i < view->n; ++i) {
 		const struct user_regset *regset = &view->regsets[i];
+		int note_type = regset->core_note_type;
+		bool is_fpreg = note_type == NT_PRFPREG;
+		void *data;
+		int ret;
+
 		do_thread_regset_writeback(t->task, regset);
-		if (regset->core_note_type && regset->get &&
-		    (!regset->active || regset->active(t->task, regset) > 0)) {
-			int ret;
-			size_t size = regset_size(t->task, regset);
-			void *data = kzalloc(size, GFP_KERNEL);
-			if (unlikely(!data))
-				return 0;
-			ret = regset->get(t->task, regset,
-					  0, size, data, NULL);
-			if (unlikely(ret))
-				kfree(data);
-			else {
-				if (regset->core_note_type != NT_PRFPREG)
-					fill_note(&t->notes[i], "LINUX",
-						  regset->core_note_type,
-						  size, data);
-				else {
-					SET_PR_FPVALID(&t->prstatus,
-							1, regset0_size);
-					fill_note(&t->notes[i], "CORE",
-						  NT_PRFPREG, size, data);
-				}
-				*total += notesize(&t->notes[i]);
-			}
-		}
+		if (!note_type) // not for coredumps
+			continue;
+		if (regset->active && regset->active(t->task, regset) <= 0)
+			continue;
+
+		ret = regset_get_alloc(t->task, regset, ~0U, &data);
+		if (ret < 0)
+			continue;
+
+		if (is_fpreg)
+			SET_PR_FPVALID(&t->prstatus, 1, regset0_size);
+
+		fill_note(&t->notes[i], is_fpreg ? "CORE" : "LINUX",
+			  note_type, ret, data);
+
+		*total += notesize(&t->notes[i]);
 	}
 
 	return 1;
diff --git a/include/linux/regset.h b/include/linux/regset.h
index 46d6ae68c455..968a032922d5 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -353,6 +353,15 @@ static inline int user_regset_copyin_ignore(unsigned int *pos,
 	return 0;
 }
 
+extern int regset_get(struct task_struct *target,
+		      const struct user_regset *regset,
+		      unsigned int size, void *data);
+
+extern int regset_get_alloc(struct task_struct *target,
+			    const struct user_regset *regset,
+			    unsigned int size,
+			    void **data);
+
 /**
  * copy_regset_to_user - fetch a thread's user_regset data into user memory
  * @target:	thread to be examined
diff --git a/kernel/Makefile b/kernel/Makefile
index f3218bc5ec69..e6e03380a0f1 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    extable.o params.o \
 	    kthread.o sys_ni.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
-	    async.o range.o smpboot.o ucount.o
+	    async.o range.o smpboot.o ucount.o regset.o
 
 obj-$(CONFIG_MODULES) += kmod.o
 obj-$(CONFIG_MULTIUSER) += groups.o
diff --git a/kernel/regset.c b/kernel/regset.c
new file mode 100644
index 000000000000..6b39fa0993ec
--- /dev/null
+++ b/kernel/regset.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/regset.h>
+
+static int __regset_get(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int size,
+			void **data)
+{
+	void *p = *data, *to_free = NULL;
+	int res;
+
+	if (!regset->get)
+		return -EOPNOTSUPP;
+	if (size > regset->n * regset->size)
+		size = regset->n * regset->size;
+	if (!p) {
+		to_free = p = kzalloc(size, GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+	}
+	res = regset->get(target, regset, 0, size, p, NULL);
+	if (unlikely(res < 0)) {
+		kfree(to_free);
+		return res;
+	}
+	*data = p;
+	if (regset->get_size) { // arm64-only kludge, will go away
+		unsigned max_size = regset->get_size(target, regset);
+		if (size > max_size)
+			size = max_size;
+	}
+	return size;
+}
+
+int regset_get(struct task_struct *target,
+	       const struct user_regset *regset,
+	       unsigned int size,
+	       void *data)
+{
+	return __regset_get(target, regset, size, &data);
+}
+EXPORT_SYMBOL(regset_get);
+
+int regset_get_alloc(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int size,
+		     void **data)
+{
+	*data = NULL;
+	return __regset_get(target, regset, size, data);
+}
+EXPORT_SYMBOL(regset_get_alloc);
-- 
cgit v1.2.3


From 1e6b57d6421f0343dd11619612e5ff8930cddf38 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 11 Jun 2020 11:11:32 -0400
Subject: unexport linux/elfcore.h

It's unusable from userland - it uses elf_gregset_t, which is not
provided by exported headers.  glibc has it in sys/procfs.h, but
the same file defines struct elf_prstatus, so linux/elfcore.h can't
be included once sys/procfs.h has been pulled.  Same goes for uclibc
and dietlibc simply doesn't have elf_gregset_t defined anywhere.

IOW, no userland source is including that thing.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/elfcore.h      |  69 +++++++++++++++++++++++++++--
 include/uapi/linux/elfcore.h | 101 -------------------------------------------
 scripts/headers_install.sh   |   1 -
 usr/include/Makefile         |   1 -
 4 files changed, 66 insertions(+), 106 deletions(-)
 delete mode 100644 include/uapi/linux/elfcore.h

(limited to 'include/linux')

diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 4cad0e784b28..96ab215dad2d 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -5,12 +5,75 @@
 #include <linux/user.h>
 #include <linux/bug.h>
 #include <linux/sched/task_stack.h>
-
-#include <asm/elf.h>
-#include <uapi/linux/elfcore.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+#include <linux/time.h>
+#include <linux/ptrace.h>
+#include <linux/fs.h>
+#include <linux/elf.h>
 
 struct coredump_params;
 
+struct elf_siginfo
+{
+	int	si_signo;			/* signal number */
+	int	si_code;			/* extra code */
+	int	si_errno;			/* errno */
+};
+
+/*
+ * Definitions to generate Intel SVR4-like core files.
+ * These mostly have the same names as the SVR4 types with "elf_"
+ * tacked on the front to prevent clashes with linux definitions,
+ * and the typedef forms have been avoided.  This is mostly like
+ * the SVR4 structure, but more Linuxy, with things that Linux does
+ * not support and which gdb doesn't really use excluded.
+ */
+struct elf_prstatus
+{
+	struct elf_siginfo pr_info;	/* Info associated with signal */
+	short	pr_cursig;		/* Current signal */
+	unsigned long pr_sigpend;	/* Set of pending signals */
+	unsigned long pr_sighold;	/* Set of held signals */
+	pid_t	pr_pid;
+	pid_t	pr_ppid;
+	pid_t	pr_pgrp;
+	pid_t	pr_sid;
+	struct __kernel_old_timeval pr_utime;	/* User time */
+	struct __kernel_old_timeval pr_stime;	/* System time */
+	struct __kernel_old_timeval pr_cutime;	/* Cumulative user time */
+	struct __kernel_old_timeval pr_cstime;	/* Cumulative system time */
+	elf_gregset_t pr_reg;	/* GP registers */
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	/* When using FDPIC, the loadmap addresses need to be communicated
+	 * to GDB in order for GDB to do the necessary relocations.  The
+	 * fields (below) used to communicate this information are placed
+	 * immediately after ``pr_reg'', so that the loadmap addresses may
+	 * be viewed as part of the register set if so desired.
+	 */
+	unsigned long pr_exec_fdpic_loadmap;
+	unsigned long pr_interp_fdpic_loadmap;
+#endif
+	int pr_fpvalid;		/* True if math co-processor being used.  */
+};
+
+#define ELF_PRARGSZ	(80)	/* Number of chars for args */
+
+struct elf_prpsinfo
+{
+	char	pr_state;	/* numeric process state */
+	char	pr_sname;	/* char for pr_state */
+	char	pr_zomb;	/* zombie */
+	char	pr_nice;	/* nice val */
+	unsigned long pr_flag;	/* flags */
+	__kernel_uid_t	pr_uid;
+	__kernel_gid_t	pr_gid;
+	pid_t	pr_pid, pr_ppid, pr_pgrp, pr_sid;
+	/* Lots missing */
+	char	pr_fname[16];	/* filename of executable */
+	char	pr_psargs[ELF_PRARGSZ];	/* initial part of arg list */
+};
+
 static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
 {
 #ifdef ELF_CORE_COPY_REGS
diff --git a/include/uapi/linux/elfcore.h b/include/uapi/linux/elfcore.h
deleted file mode 100644
index baf03562306d..000000000000
--- a/include/uapi/linux/elfcore.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_ELFCORE_H
-#define _UAPI_LINUX_ELFCORE_H
-
-#include <linux/types.h>
-#include <linux/signal.h>
-#include <linux/time.h>
-#include <linux/ptrace.h>
-#include <linux/elf.h>
-#include <linux/fs.h>
-
-struct elf_siginfo
-{
-	int	si_signo;			/* signal number */
-	int	si_code;			/* extra code */
-	int	si_errno;			/* errno */
-};
-
-
-#ifndef __KERNEL__
-typedef elf_greg_t greg_t;
-typedef elf_gregset_t gregset_t;
-typedef elf_fpregset_t fpregset_t;
-typedef elf_fpxregset_t fpxregset_t;
-#define NGREG ELF_NGREG
-#endif
-
-/*
- * Definitions to generate Intel SVR4-like core files.
- * These mostly have the same names as the SVR4 types with "elf_"
- * tacked on the front to prevent clashes with linux definitions,
- * and the typedef forms have been avoided.  This is mostly like
- * the SVR4 structure, but more Linuxy, with things that Linux does
- * not support and which gdb doesn't really use excluded.
- * Fields present but not used are marked with "XXX".
- */
-struct elf_prstatus
-{
-#if 0
-	long	pr_flags;	/* XXX Process flags */
-	short	pr_why;		/* XXX Reason for process halt */
-	short	pr_what;	/* XXX More detailed reason */
-#endif
-	struct elf_siginfo pr_info;	/* Info associated with signal */
-	short	pr_cursig;		/* Current signal */
-	unsigned long pr_sigpend;	/* Set of pending signals */
-	unsigned long pr_sighold;	/* Set of held signals */
-#if 0
-	struct sigaltstack pr_altstack;	/* Alternate stack info */
-	struct sigaction pr_action;	/* Signal action for current sig */
-#endif
-	pid_t	pr_pid;
-	pid_t	pr_ppid;
-	pid_t	pr_pgrp;
-	pid_t	pr_sid;
-	struct __kernel_old_timeval pr_utime;	/* User time */
-	struct __kernel_old_timeval pr_stime;	/* System time */
-	struct __kernel_old_timeval pr_cutime;	/* Cumulative user time */
-	struct __kernel_old_timeval pr_cstime;	/* Cumulative system time */
-#if 0
-	long	pr_instr;		/* Current instruction */
-#endif
-	elf_gregset_t pr_reg;	/* GP registers */
-#ifdef CONFIG_BINFMT_ELF_FDPIC
-	/* When using FDPIC, the loadmap addresses need to be communicated
-	 * to GDB in order for GDB to do the necessary relocations.  The
-	 * fields (below) used to communicate this information are placed
-	 * immediately after ``pr_reg'', so that the loadmap addresses may
-	 * be viewed as part of the register set if so desired.
-	 */
-	unsigned long pr_exec_fdpic_loadmap;
-	unsigned long pr_interp_fdpic_loadmap;
-#endif
-	int pr_fpvalid;		/* True if math co-processor being used.  */
-};
-
-#define ELF_PRARGSZ	(80)	/* Number of chars for args */
-
-struct elf_prpsinfo
-{
-	char	pr_state;	/* numeric process state */
-	char	pr_sname;	/* char for pr_state */
-	char	pr_zomb;	/* zombie */
-	char	pr_nice;	/* nice val */
-	unsigned long pr_flag;	/* flags */
-	__kernel_uid_t	pr_uid;
-	__kernel_gid_t	pr_gid;
-	pid_t	pr_pid, pr_ppid, pr_pgrp, pr_sid;
-	/* Lots missing */
-	char	pr_fname[16];	/* filename of executable */
-	char	pr_psargs[ELF_PRARGSZ];	/* initial part of arg list */
-};
-
-#ifndef __KERNEL__
-typedef struct elf_prstatus prstatus_t;
-typedef struct elf_prpsinfo prpsinfo_t;
-#define PRARGSZ ELF_PRARGSZ 
-#endif
-
-
-#endif /* _UAPI_LINUX_ELFCORE_H */
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index 955cf3aedf21..9314247bb222 100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -86,7 +86,6 @@ arch/x86/include/uapi/asm/auxvec.h:CONFIG_X86_64
 arch/x86/include/uapi/asm/mman.h:CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 include/uapi/asm-generic/fcntl.h:CONFIG_64BIT
 include/uapi/linux/atmdev.h:CONFIG_COMPAT
-include/uapi/linux/elfcore.h:CONFIG_BINFMT_ELF_FDPIC
 include/uapi/linux/eventpoll.h:CONFIG_PM_SLEEP
 include/uapi/linux/hw_breakpoint.h:CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
 include/uapi/linux/pktcdvd.h:CONFIG_CDROM_PKTCDVD_WCACHE
diff --git a/usr/include/Makefile b/usr/include/Makefile
index 55362f3ab393..f6b3c85d900e 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -28,7 +28,6 @@ no-header-test += linux/am437x-vpfe.h
 no-header-test += linux/android/binder.h
 no-header-test += linux/android/binderfs.h
 no-header-test += linux/coda.h
-no-header-test += linux/elfcore.h
 no-header-test += linux/errqueue.h
 no-header-test += linux/fsmap.h
 no-header-test += linux/hdlc/ioctl.h
-- 
cgit v1.2.3


From 16aead81018ca404efe9bd928786824e7168151f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 14 Jun 2020 09:52:06 -0400
Subject: take fdpic-related parts of elf_prstatus out

The only architecture where we might end up using both is arm,
and there we definitely don't want fdpic-related fields in
elf_prstatus - coredump layout of ELF binaries should not
depend upon having the kernel built with the support of ELF_FDPIC
ones.  Just move the fdpic-modified variant into binfmt_elf_fdpic.c
(and call it elf_prstatus_fdpic there)

[name stolen from nico]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/binfmt_elf_fdpic.c          | 32 +++++++++++++++++++++++++++++---
 include/linux/elfcore-compat.h |  4 ----
 include/linux/elfcore.h        | 10 ----------
 3 files changed, 29 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 0f45521b237c..6e13d8bea32d 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1189,6 +1189,32 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
  */
 #ifdef CONFIG_ELF_CORE
 
+struct elf_prstatus_fdpic
+{
+	struct elf_siginfo pr_info;	/* Info associated with signal */
+	short	pr_cursig;		/* Current signal */
+	unsigned long pr_sigpend;	/* Set of pending signals */
+	unsigned long pr_sighold;	/* Set of held signals */
+	pid_t	pr_pid;
+	pid_t	pr_ppid;
+	pid_t	pr_pgrp;
+	pid_t	pr_sid;
+	struct __kernel_old_timeval pr_utime;	/* User time */
+	struct __kernel_old_timeval pr_stime;	/* System time */
+	struct __kernel_old_timeval pr_cutime;	/* Cumulative user time */
+	struct __kernel_old_timeval pr_cstime;	/* Cumulative system time */
+	elf_gregset_t pr_reg;	/* GP registers */
+	/* When using FDPIC, the loadmap addresses need to be communicated
+	 * to GDB in order for GDB to do the necessary relocations.  The
+	 * fields (below) used to communicate this information are placed
+	 * immediately after ``pr_reg'', so that the loadmap addresses may
+	 * be viewed as part of the register set if so desired.
+	 */
+	unsigned long pr_exec_fdpic_loadmap;
+	unsigned long pr_interp_fdpic_loadmap;
+	int pr_fpvalid;		/* True if math co-processor being used.  */
+};
+
 /*
  * Decide whether a segment is worth dumping; default is yes to be
  * sure (missing info is worse than too much; etc).
@@ -1345,7 +1371,7 @@ static inline void fill_note(struct memelfnote *note, const char *name, int type
  * fill up all the fields in prstatus from the given task struct, except
  * registers which need to be filled up separately.
  */
-static void fill_prstatus(struct elf_prstatus *prstatus,
+static void fill_prstatus(struct elf_prstatus_fdpic *prstatus,
 			  struct task_struct *p, long signr)
 {
 	prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
@@ -1428,7 +1454,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 struct elf_thread_status
 {
 	struct list_head list;
-	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
+	struct elf_prstatus_fdpic prstatus;	/* NT_PRSTATUS */
 	elf_fpregset_t fpu;		/* NT_PRFPREG */
 	struct task_struct *thread;
 #ifdef ELF_CORE_COPY_XFPREGS
@@ -1562,7 +1588,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	loff_t offset = 0, dataoff;
 	int numnote;
 	struct memelfnote *notes = NULL;
-	struct elf_prstatus *prstatus = NULL;	/* NT_PRSTATUS */
+	struct elf_prstatus_fdpic *prstatus = NULL;	/* NT_PRSTATUS */
 	struct elf_prpsinfo *psinfo = NULL;	/* NT_PRPSINFO */
  	LIST_HEAD(thread_list);
  	struct list_head *t;
diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h
index 7a37f4ce9fd2..10485f0c9740 100644
--- a/include/linux/elfcore-compat.h
+++ b/include/linux/elfcore-compat.h
@@ -32,10 +32,6 @@ struct compat_elf_prstatus
 	struct old_timeval32		pr_cutime;
 	struct old_timeval32		pr_cstime;
 	compat_elf_gregset_t		pr_reg;
-#ifdef CONFIG_BINFMT_ELF_FDPIC
-	compat_ulong_t			pr_exec_fdpic_loadmap;
-	compat_ulong_t			pr_interp_fdpic_loadmap;
-#endif
 	compat_int_t			pr_fpvalid;
 };
 
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 96ab215dad2d..adb8ee89f3fd 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -44,16 +44,6 @@ struct elf_prstatus
 	struct __kernel_old_timeval pr_cutime;	/* Cumulative user time */
 	struct __kernel_old_timeval pr_cstime;	/* Cumulative system time */
 	elf_gregset_t pr_reg;	/* GP registers */
-#ifdef CONFIG_BINFMT_ELF_FDPIC
-	/* When using FDPIC, the loadmap addresses need to be communicated
-	 * to GDB in order for GDB to do the necessary relocations.  The
-	 * fields (below) used to communicate this information are placed
-	 * immediately after ``pr_reg'', so that the loadmap addresses may
-	 * be viewed as part of the register set if so desired.
-	 */
-	unsigned long pr_exec_fdpic_loadmap;
-	unsigned long pr_interp_fdpic_loadmap;
-#endif
 	int pr_fpvalid;		/* True if math co-processor being used.  */
 };
 
-- 
cgit v1.2.3


From 7a896028adcfbff4552e6748e8fc8d06036c132c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 13 Jun 2020 00:23:31 -0400
Subject: kill elf_fpxregs_t

all uses are conditional upon ELF_CORE_COPY_XFPREGS, which has not
been defined on any architecture since 2010

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/include/asm/elf.h    |  2 --
 arch/powerpc/include/asm/elf.h |  2 --
 arch/x86/include/asm/elf.h     |  2 --
 fs/binfmt_elf.c                | 30 ------------------------------
 fs/binfmt_elf_fdpic.c          | 28 ----------------------------
 include/linux/elfcore.h        |  7 -------
 6 files changed, 71 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h
index c70bb9c11f52..6629301a2620 100644
--- a/arch/ia64/include/asm/elf.h
+++ b/arch/ia64/include/asm/elf.h
@@ -179,8 +179,6 @@ extern void ia64_init_addr_space (void);
 #define ELF_AR_SSD_OFFSET  (56 * sizeof(elf_greg_t))
 #define ELF_AR_END_OFFSET  (57 * sizeof(elf_greg_t))
 
-typedef unsigned long elf_fpxregset_t;
-
 typedef unsigned long elf_greg_t;
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 57c229a86f08..53ed2ca40151 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -53,8 +53,6 @@ static inline void ppc_elf_core_copy_regs(elf_gregset_t elf_regs,
 }
 #define ELF_CORE_COPY_REGS(gregs, regs) ppc_elf_core_copy_regs(gregs, regs);
 
-typedef elf_vrregset_t elf_fpxregset_t;
-
 /* ELF_HWCAP yields a mask that user programs can use to figure out what
    instruction set this cpu supports.  This could be done in userspace,
    but it's not easy, and we've already done it here.  */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 452beed7892b..b9a5d488f1a5 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -21,8 +21,6 @@ typedef struct user_i387_struct elf_fpregset_t;
 
 #ifdef __i386__
 
-typedef struct user_fxsr_struct elf_fpxregset_t;
-
 #define R_386_NONE	0
 #define R_386_32	1
 #define R_386_PC32	2
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e922a6abdca8..13d053982dd7 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2038,9 +2038,6 @@ struct elf_thread_status
 	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
 	elf_fpregset_t fpu;		/* NT_PRFPREG */
 	struct task_struct *thread;
-#ifdef ELF_CORE_COPY_XFPREGS
-	elf_fpxregset_t xfpu;		/* ELF_CORE_XFPREG_TYPE */
-#endif
 	struct memelfnote notes[3];
 	int num_notes;
 };
@@ -2071,15 +2068,6 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
 		t->num_notes++;
 		sz += notesize(&t->notes[1]);
 	}
-
-#ifdef ELF_CORE_COPY_XFPREGS
-	if (elf_core_copy_task_xfpregs(p, &t->xfpu)) {
-		fill_note(&t->notes[2], "LINUX", ELF_CORE_XFPREG_TYPE,
-			  sizeof(t->xfpu), &t->xfpu);
-		t->num_notes++;
-		sz += notesize(&t->notes[2]);
-	}
-#endif	
 	return sz;
 }
 
@@ -2090,9 +2078,6 @@ struct elf_note_info {
 	struct elf_prpsinfo *psinfo;	/* NT_PRPSINFO */
 	struct list_head thread_list;
 	elf_fpregset_t *fpu;
-#ifdef ELF_CORE_COPY_XFPREGS
-	elf_fpxregset_t *xfpu;
-#endif
 	user_siginfo_t csigdata;
 	int thread_status_size;
 	int numnote;
@@ -2116,11 +2101,6 @@ static int elf_note_info_init(struct elf_note_info *info)
 	info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
 	if (!info->fpu)
 		return 0;
-#ifdef ELF_CORE_COPY_XFPREGS
-	info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
-	if (!info->xfpu)
-		return 0;
-#endif
 	return 1;
 }
 
@@ -2184,13 +2164,6 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 	if (info->prstatus->pr_fpvalid)
 		fill_note(info->notes + info->numnote++,
 			  "CORE", NT_PRFPREG, sizeof(*info->fpu), info->fpu);
-#ifdef ELF_CORE_COPY_XFPREGS
-	if (elf_core_copy_task_xfpregs(current, info->xfpu))
-		fill_note(info->notes + info->numnote++,
-			  "LINUX", ELF_CORE_XFPREG_TYPE,
-			  sizeof(*info->xfpu), info->xfpu);
-#endif
-
 	return 1;
 }
 
@@ -2243,9 +2216,6 @@ static void free_note_info(struct elf_note_info *info)
 	kfree(info->psinfo);
 	kfree(info->notes);
 	kfree(info->fpu);
-#ifdef ELF_CORE_COPY_XFPREGS
-	kfree(info->xfpu);
-#endif
 }
 
 #endif
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 6e13d8bea32d..a6ee92137529 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1457,9 +1457,6 @@ struct elf_thread_status
 	struct elf_prstatus_fdpic prstatus;	/* NT_PRSTATUS */
 	elf_fpregset_t fpu;		/* NT_PRFPREG */
 	struct task_struct *thread;
-#ifdef ELF_CORE_COPY_XFPREGS
-	elf_fpxregset_t xfpu;		/* ELF_CORE_XFPREG_TYPE */
-#endif
 	struct memelfnote notes[3];
 	int num_notes;
 };
@@ -1491,15 +1488,6 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
 		t->num_notes++;
 		sz += notesize(&t->notes[1]);
 	}
-
-#ifdef ELF_CORE_COPY_XFPREGS
-	if (elf_core_copy_task_xfpregs(p, &t->xfpu)) {
-		fill_note(&t->notes[2], "LINUX", ELF_CORE_XFPREG_TYPE,
-			  sizeof(t->xfpu), &t->xfpu);
-		t->num_notes++;
-		sz += notesize(&t->notes[2]);
-	}
-#endif
 	return sz;
 }
 
@@ -1593,9 +1581,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
  	LIST_HEAD(thread_list);
  	struct list_head *t;
 	elf_fpregset_t *fpu = NULL;
-#ifdef ELF_CORE_COPY_XFPREGS
-	elf_fpxregset_t *xfpu = NULL;
-#endif
 	int thread_status_size = 0;
 	elf_addr_t *auxv;
 	struct elf_phdr *phdr4note = NULL;
@@ -1634,11 +1619,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	fpu = kmalloc(sizeof(*fpu), GFP_KERNEL);
 	if (!fpu)
 		goto end_coredump;
-#ifdef ELF_CORE_COPY_XFPREGS
-	xfpu = kmalloc(sizeof(*xfpu), GFP_KERNEL);
-	if (!xfpu)
-		goto end_coredump;
-#endif
 
 	for (ct = current->mm->core_state->dumper.next;
 					ct; ct = ct->next) {
@@ -1703,11 +1683,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	     elf_core_copy_task_fpregs(current, cprm->regs, fpu)))
 		fill_note(notes + numnote++,
 			  "CORE", NT_PRFPREG, sizeof(*fpu), fpu);
-#ifdef ELF_CORE_COPY_XFPREGS
-	if (elf_core_copy_task_xfpregs(current, xfpu))
-		fill_note(notes + numnote++,
-			  "LINUX", ELF_CORE_XFPREG_TYPE, sizeof(*xfpu), xfpu);
-#endif
 
 	offset += sizeof(*elf);				/* Elf header */
 	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
@@ -1828,9 +1803,6 @@ end_coredump:
 	kfree(notes);
 	kfree(fpu);
 	kfree(shdr4extnum);
-#ifdef ELF_CORE_COPY_XFPREGS
-	kfree(xfpu);
-#endif
 	return has_dumped;
 #undef NUM_NOTES
 }
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index adb8ee89f3fd..46c3d691f677 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -104,13 +104,6 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg
 #endif
 }
 
-#ifdef ELF_CORE_COPY_XFPREGS
-static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregset_t *xfpu)
-{
-	return ELF_CORE_COPY_XFPREGS(t, xfpu);
-}
-#endif
-
 /*
  * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out
  * extra segments containing the gate DSO contents.  Dumping its
-- 
cgit v1.2.3


From dc12d7968f9c9540494deb1285854b18ca4465ec Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 17 Feb 2020 12:25:14 -0500
Subject: copy_regset_to_user(): do all copyout at once.

Turn copy_regset_to_user() into regset_get_alloc() + copy_to_user().
Now all ->get() calls have a kernel buffer as destination.

Note that we'd already eliminated the callers of copy_regset_to_user()
with non-zero offset; now that argument is simply unused.

Uninlined, while we are at it.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/regset.h | 29 ++++-------------------------
 kernel/regset.c        | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/regset.h b/include/linux/regset.h
index 968a032922d5..af57c1db1924 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -362,31 +362,10 @@ extern int regset_get_alloc(struct task_struct *target,
 			    unsigned int size,
 			    void **data);
 
-/**
- * copy_regset_to_user - fetch a thread's user_regset data into user memory
- * @target:	thread to be examined
- * @view:	&struct user_regset_view describing user thread machine state
- * @setno:	index in @view->regsets
- * @offset:	offset into the regset data, in bytes
- * @size:	amount of data to copy, in bytes
- * @data:	user-mode pointer to copy into
- */
-static inline int copy_regset_to_user(struct task_struct *target,
-				      const struct user_regset_view *view,
-				      unsigned int setno,
-				      unsigned int offset, unsigned int size,
-				      void __user *data)
-{
-	const struct user_regset *regset = &view->regsets[setno];
-
-	if (!regset->get)
-		return -EOPNOTSUPP;
-
-	if (!access_ok(data, size))
-		return -EFAULT;
-
-	return regset->get(target, regset, offset, size, NULL, data);
-}
+extern int copy_regset_to_user(struct task_struct *target,
+			       const struct user_regset_view *view,
+			       unsigned int setno, unsigned int offset,
+			       unsigned int size, void __user *data);
 
 /**
  * copy_regset_from_user - store into thread's user_regset data from user memory
diff --git a/kernel/regset.c b/kernel/regset.c
index 6b39fa0993ec..0a610983ce43 100644
--- a/kernel/regset.c
+++ b/kernel/regset.c
@@ -52,3 +52,29 @@ int regset_get_alloc(struct task_struct *target,
 	return __regset_get(target, regset, size, data);
 }
 EXPORT_SYMBOL(regset_get_alloc);
+
+/**
+ * copy_regset_to_user - fetch a thread's user_regset data into user memory
+ * @target:	thread to be examined
+ * @view:	&struct user_regset_view describing user thread machine state
+ * @setno:	index in @view->regsets
+ * @offset:	offset into the regset data, in bytes
+ * @size:	amount of data to copy, in bytes
+ * @data:	user-mode pointer to copy into
+ */
+int copy_regset_to_user(struct task_struct *target,
+			const struct user_regset_view *view,
+			unsigned int setno,
+			unsigned int offset, unsigned int size,
+			void __user *data)
+{
+	const struct user_regset *regset = &view->regsets[setno];
+	void *buf;
+	int ret;
+
+	ret = regset_get_alloc(target, regset, size, &buf);
+	if (ret > 0)
+		ret = copy_to_user(data, buf, ret) ? -EFAULT : 0;
+	kfree(buf);
+	return ret;
+}
-- 
cgit v1.2.3


From 7717cb9bdd0421faa432a4e0d499fdba6e2394c8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 20 Feb 2020 20:48:16 -0500
Subject: regset: new method and helpers for it

->regset_get() takes task+regset+buffer, returns the amount of free space
left in the buffer on success and -E... on error.

buffer is represented as struct membuf - a pair of (kernel) pointer
and amount of space left

Primitives for writing to such:
	* membuf_write(buf, data, size)
	* membuf_zero(buf, size)
	* membuf_store(buf, value)

These are implemented as inlines (in case of membuf_store - a macro).
All writes are sequential; they become no-ops when there's no space
left.  Return value of all primitives is the amount of space left
after the operation, so they can be used as return values of ->regset_get().

Example of use:

// stores pt_regs of task + 64 bytes worth of zeroes + 32bit PID of task
int foo_get(struct task_struct *task, const struct regset *regset,
	    struct membuf to)
{
	membuf_write(&to, task_pt_regs(task), sizeof(struct pt_regs));
	membuf_zero(&to, 64);
	return membuf_store(&to, (u32)task_tgid_vnr(task));
}

regset_get()/regset_get_alloc() taught to use that thing if present.
By the end of the series all users of ->get() will be converted;
then ->get() and ->get_size() can go.

Note that unlike ->get() this thing always starts at offset 0 and,
since it only writes to kernel buffer, can't fail on copyout.
It can, of course, fail for other reasons, but those tend to
be less numerous.

The caller guarantees that the buffer size won't be bigger than
regset->n * regset->size.  That simplifies life for quite a few
instances.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/regset.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/regset.c        | 12 +++++++++++-
 2 files changed, 62 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/regset.h b/include/linux/regset.h
index af57c1db1924..f6125a7d949d 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -17,6 +17,52 @@
 struct task_struct;
 struct user_regset;
 
+struct membuf {
+	void *p;
+	size_t left;
+};
+
+static inline int membuf_zero(struct membuf *s, size_t size)
+{
+	if (s->left) {
+		if (size > s->left)
+			size = s->left;
+		memset(s->p, 0, size);
+		s->p += size;
+		s->left -= size;
+	}
+	return s->left;
+}
+
+static inline int membuf_write(struct membuf *s, const void *v, size_t size)
+{
+	if (s->left) {
+		if (size > s->left)
+			size = s->left;
+		memcpy(s->p, v, size);
+		s->p += size;
+		s->left -= size;
+	}
+	return s->left;
+}
+
+/* current s->p must be aligned for v; v must be a scalar */
+#define membuf_store(s, v)				\
+({							\
+	struct membuf *__s = (s);			\
+        if (__s->left) {				\
+		typeof(v) __v = (v);			\
+		size_t __size = sizeof(__v);		\
+		if (unlikely(__size > __s->left)) {	\
+			__size = __s->left;		\
+			memcpy(__s->p, &__v, __size);	\
+		} else {				\
+			*(typeof(__v + 0) *)__s->p = __v;	\
+		}					\
+		__s->p += __size;			\
+		__s->left -= __size;			\
+	}						\
+	__s->left;})
 
 /**
  * user_regset_active_fn - type of @active function in &struct user_regset
@@ -57,6 +103,10 @@ typedef int user_regset_get_fn(struct task_struct *target,
 			       unsigned int pos, unsigned int count,
 			       void *kbuf, void __user *ubuf);
 
+typedef int user_regset_get2_fn(struct task_struct *target,
+			       const struct user_regset *regset,
+			       struct membuf to);
+
 /**
  * user_regset_set_fn - type of @set function in &struct user_regset
  * @target:	thread being examined
@@ -186,6 +236,7 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
  */
 struct user_regset {
 	user_regset_get_fn		*get;
+	user_regset_get2_fn		*regset_get;
 	user_regset_set_fn		*set;
 	user_regset_active_fn		*active;
 	user_regset_writeback_fn	*writeback;
diff --git a/kernel/regset.c b/kernel/regset.c
index 0a610983ce43..eaeaefbbd39e 100644
--- a/kernel/regset.c
+++ b/kernel/regset.c
@@ -11,7 +11,7 @@ static int __regset_get(struct task_struct *target,
 	void *p = *data, *to_free = NULL;
 	int res;
 
-	if (!regset->get)
+	if (!regset->get && !regset->regset_get)
 		return -EOPNOTSUPP;
 	if (size > regset->n * regset->size)
 		size = regset->n * regset->size;
@@ -20,6 +20,16 @@ static int __regset_get(struct task_struct *target,
 		if (!p)
 			return -ENOMEM;
 	}
+	if (regset->regset_get) {
+		res = regset->regset_get(target, regset,
+				   (struct membuf){.p = p, .left = size});
+		if (res < 0) {
+			kfree(to_free);
+			return res;
+		}
+		*data = p;
+		return size - res;
+	}
 	res = regset->get(target, regset, 0, size, p, NULL);
 	if (unlikely(res < 0)) {
 		kfree(to_free);
-- 
cgit v1.2.3


From 1e6986c9db21265bac1435a344b4446c51a3f4d8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 16 Jun 2020 15:34:20 -0400
Subject: regset: kill ->get()

no instances left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/regset.h | 22 ----------------------
 kernel/regset.c        | 24 +++++-------------------
 2 files changed, 5 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/regset.h b/include/linux/regset.h
index f6125a7d949d..2a4a555b1617 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -82,27 +82,6 @@ static inline int membuf_write(struct membuf *s, const void *v, size_t size)
 typedef int user_regset_active_fn(struct task_struct *target,
 				  const struct user_regset *regset);
 
-/**
- * user_regset_get_fn - type of @get function in &struct user_regset
- * @target:	thread being examined
- * @regset:	regset being examined
- * @pos:	offset into the regset data to access, in bytes
- * @count:	amount of data to copy, in bytes
- * @kbuf:	if not %NULL, a kernel-space pointer to copy into
- * @ubuf:	if @kbuf is %NULL, a user-space pointer to copy into
- *
- * Fetch register values.  Return %0 on success; -%EIO or -%ENODEV
- * are usual failure returns.  The @pos and @count values are in
- * bytes, but must be properly aligned.  If @kbuf is non-null, that
- * buffer is used and @ubuf is ignored.  If @kbuf is %NULL, then
- * ubuf gives a userland pointer to access directly, and an -%EFAULT
- * return value is possible.
- */
-typedef int user_regset_get_fn(struct task_struct *target,
-			       const struct user_regset *regset,
-			       unsigned int pos, unsigned int count,
-			       void *kbuf, void __user *ubuf);
-
 typedef int user_regset_get2_fn(struct task_struct *target,
 			       const struct user_regset *regset,
 			       struct membuf to);
@@ -235,7 +214,6 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
  * omitted when there is an @active function and it returns zero.
  */
 struct user_regset {
-	user_regset_get_fn		*get;
 	user_regset_get2_fn		*regset_get;
 	user_regset_set_fn		*set;
 	user_regset_active_fn		*active;
diff --git a/kernel/regset.c b/kernel/regset.c
index eaeaefbbd39e..586823786f39 100644
--- a/kernel/regset.c
+++ b/kernel/regset.c
@@ -11,7 +11,7 @@ static int __regset_get(struct task_struct *target,
 	void *p = *data, *to_free = NULL;
 	int res;
 
-	if (!regset->get && !regset->regset_get)
+	if (!regset->regset_get)
 		return -EOPNOTSUPP;
 	if (size > regset->n * regset->size)
 		size = regset->n * regset->size;
@@ -20,28 +20,14 @@ static int __regset_get(struct task_struct *target,
 		if (!p)
 			return -ENOMEM;
 	}
-	if (regset->regset_get) {
-		res = regset->regset_get(target, regset,
-				   (struct membuf){.p = p, .left = size});
-		if (res < 0) {
-			kfree(to_free);
-			return res;
-		}
-		*data = p;
-		return size - res;
-	}
-	res = regset->get(target, regset, 0, size, p, NULL);
-	if (unlikely(res < 0)) {
+	res = regset->regset_get(target, regset,
+			   (struct membuf){.p = p, .left = size});
+	if (res < 0) {
 		kfree(to_free);
 		return res;
 	}
 	*data = p;
-	if (regset->get_size) { // arm64-only kludge, will go away
-		unsigned max_size = regset->get_size(target, regset);
-		if (size > max_size)
-			size = max_size;
-	}
-	return size;
+	return size - res;
 }
 
 int regset_get(struct task_struct *target,
-- 
cgit v1.2.3


From c522401e0656b51e6a65ec112489cb078801aa9c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 17 Jun 2020 09:57:08 -0400
Subject: regset(): kill ->get_size()

not used anymore

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/kernel/ptrace.c | 13 -------------
 include/linux/regset.h     | 48 +---------------------------------------------
 2 files changed, 1 insertion(+), 60 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 902d987fdd35..5bf737d38b26 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -740,18 +740,6 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header)
 	return ALIGN(header->size, SVE_VQ_BYTES);
 }
 
-static unsigned int sve_get_size(struct task_struct *target,
-				 const struct user_regset *regset)
-{
-	struct user_sve_header header;
-
-	if (!system_supports_sve())
-		return 0;
-
-	sve_init_header_from_task(&header, target);
-	return sve_size_from_header(&header);
-}
-
 static int sve_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   struct membuf to)
@@ -1130,7 +1118,6 @@ static const struct user_regset aarch64_regsets[] = {
 		.align = SVE_VQ_BYTES,
 		.regset_get = sve_get,
 		.set = sve_set,
-		.get_size = sve_get_size,
 	},
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
diff --git a/include/linux/regset.h b/include/linux/regset.h
index 2a4a555b1617..6b951a27bcaf 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -132,28 +132,6 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
 				     const struct user_regset *regset,
 				     int immediate);
 
-/**
- * user_regset_get_size_fn - type of @get_size function in &struct user_regset
- * @target:	thread being examined
- * @regset:	regset being examined
- *
- * This call is optional; usually the pointer is %NULL.
- *
- * When provided, this function must return the current size of regset
- * data, as observed by the @get function in &struct user_regset.  The
- * value returned must be a multiple of @size.  The returned size is
- * required to be valid only until the next time (if any) @regset is
- * modified for @target.
- *
- * This function is intended for dynamically sized regsets.  A regset
- * that is statically sized does not need to implement it.
- *
- * This function should not be called directly: instead, callers should
- * call regset_size() to determine the current size of a regset.
- */
-typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
-					     const struct user_regset *regset);
-
 /**
  * struct user_regset - accessible thread CPU state
  * @n:			Number of slots (registers).
@@ -165,7 +143,6 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
  * @set:		Function to store values.
  * @active:		Function to report if regset is active, or %NULL.
  * @writeback:		Function to write data back to user memory, or %NULL.
- * @get_size:		Function to return the regset's size, or %NULL.
  *
  * This data structure describes a machine resource we call a register set.
  * This is part of the state of an individual thread, not necessarily
@@ -173,12 +150,7 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
  * similar slots, given by @n.  Each slot is @size bytes, and aligned to
  * @align bytes (which is at least @size).  For dynamically-sized
  * regsets, @n must contain the maximum possible number of slots for the
- * regset, and @get_size must point to a function that returns the
- * current regset size.
- *
- * Callers that need to know only the current size of the regset and do
- * not care about its internal structure should call regset_size()
- * instead of inspecting @n or calling @get_size.
+ * regset.
  *
  * For backward compatibility, the @get and @set methods must pad to, or
  * accept, @n * @size bytes, even if the current regset size is smaller.
@@ -218,7 +190,6 @@ struct user_regset {
 	user_regset_set_fn		*set;
 	user_regset_active_fn		*active;
 	user_regset_writeback_fn	*writeback;
-	user_regset_get_size_fn		*get_size;
 	unsigned int			n;
 	unsigned int 			size;
 	unsigned int 			align;
@@ -422,21 +393,4 @@ static inline int copy_regset_from_user(struct task_struct *target,
 	return regset->set(target, regset, offset, size, NULL, data);
 }
 
-/**
- * regset_size - determine the current size of a regset
- * @target:	thread to be examined
- * @regset:	regset to be examined
- *
- * Note that the returned size is valid only until the next time
- * (if any) @regset is modified for @target.
- */
-static inline unsigned int regset_size(struct task_struct *target,
-				       const struct user_regset *regset)
-{
-	if (!regset->get_size)
-		return regset->n * regset->size;
-	else
-		return regset->get_size(target, regset);
-}
-
 #endif	/* <linux/regset.h> */
-- 
cgit v1.2.3


From ce327e1c54119179066d6f3573a28001febc9265 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 17 Jun 2020 13:40:03 -0400
Subject: regset: kill user_regset_copyout{,_zero}()

no callers left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/regset.h | 67 --------------------------------------------------
 1 file changed, 67 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/regset.h b/include/linux/regset.h
index 6b951a27bcaf..c3403f328257 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -238,44 +238,6 @@ struct user_regset_view {
  */
 const struct user_regset_view *task_user_regset_view(struct task_struct *tsk);
 
-
-/*
- * These are helpers for writing regset get/set functions in arch code.
- * Because @start_pos and @end_pos are always compile-time constants,
- * these are inlined into very little code though they look large.
- *
- * Use one or more calls sequentially for each chunk of regset data stored
- * contiguously in memory.  Call with constants for @start_pos and @end_pos,
- * giving the range of byte positions in the regset that data corresponds
- * to; @end_pos can be -1 if this chunk is at the end of the regset layout.
- * Each call updates the arguments to point past its chunk.
- */
-
-static inline int user_regset_copyout(unsigned int *pos, unsigned int *count,
-				      void **kbuf,
-				      void __user **ubuf, const void *data,
-				      const int start_pos, const int end_pos)
-{
-	if (*count == 0)
-		return 0;
-	BUG_ON(*pos < start_pos);
-	if (end_pos < 0 || *pos < end_pos) {
-		unsigned int copy = (end_pos < 0 ? *count
-				     : min(*count, end_pos - *pos));
-		data += *pos - start_pos;
-		if (*kbuf) {
-			memcpy(*kbuf, data, copy);
-			*kbuf += copy;
-		} else if (__copy_to_user(*ubuf, data, copy))
-			return -EFAULT;
-		else
-			*ubuf += copy;
-		*pos += copy;
-		*count -= copy;
-	}
-	return 0;
-}
-
 static inline int user_regset_copyin(unsigned int *pos, unsigned int *count,
 				     const void **kbuf,
 				     const void __user **ubuf, void *data,
@@ -301,35 +263,6 @@ static inline int user_regset_copyin(unsigned int *pos, unsigned int *count,
 	return 0;
 }
 
-/*
- * These two parallel the two above, but for portions of a regset layout
- * that always read as all-zero or for which writes are ignored.
- */
-static inline int user_regset_copyout_zero(unsigned int *pos,
-					   unsigned int *count,
-					   void **kbuf, void __user **ubuf,
-					   const int start_pos,
-					   const int end_pos)
-{
-	if (*count == 0)
-		return 0;
-	BUG_ON(*pos < start_pos);
-	if (end_pos < 0 || *pos < end_pos) {
-		unsigned int copy = (end_pos < 0 ? *count
-				     : min(*count, end_pos - *pos));
-		if (*kbuf) {
-			memset(*kbuf, 0, copy);
-			*kbuf += copy;
-		} else if (clear_user(*ubuf, copy))
-			return -EFAULT;
-		else
-			*ubuf += copy;
-		*pos += copy;
-		*count -= copy;
-	}
-	return 0;
-}
-
 static inline int user_regset_copyin_ignore(unsigned int *pos,
 					    unsigned int *count,
 					    const void **kbuf,
-- 
cgit v1.2.3


From 6414e9b09ffd197803f8e86ce2fafdaf1de4e8e4 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 12 Jul 2020 20:09:52 -0700
Subject: fs: define inode flags using bit numbers

Define the VFS inode flags using bit numbers instead of hardcoding
powers of 2, which has become unwieldy now that we're up to 65536.

No change in the actual values.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6c4ab4dc1cd7..9bf7a32f2932 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1982,27 +1982,27 @@ struct super_operations {
 /*
  * Inode flags - they have no relation to superblock flags now
  */
-#define S_SYNC		1	/* Writes are synced at once */
-#define S_NOATIME	2	/* Do not update access times */
-#define S_APPEND	4	/* Append-only file */
-#define S_IMMUTABLE	8	/* Immutable file */
-#define S_DEAD		16	/* removed, but still open directory */
-#define S_NOQUOTA	32	/* Inode is not counted to quota */
-#define S_DIRSYNC	64	/* Directory modifications are synchronous */
-#define S_NOCMTIME	128	/* Do not update file c/mtime */
-#define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
-#define S_PRIVATE	512	/* Inode is fs-internal */
-#define S_IMA		1024	/* Inode has an associated IMA struct */
-#define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
-#define S_NOSEC		4096	/* no suid or xattr security attributes */
+#define S_SYNC		(1 << 0)  /* Writes are synced at once */
+#define S_NOATIME	(1 << 1)  /* Do not update access times */
+#define S_APPEND	(1 << 2)  /* Append-only file */
+#define S_IMMUTABLE	(1 << 3)  /* Immutable file */
+#define S_DEAD		(1 << 4)  /* removed, but still open directory */
+#define S_NOQUOTA	(1 << 5)  /* Inode is not counted to quota */
+#define S_DIRSYNC	(1 << 6)  /* Directory modifications are synchronous */
+#define S_NOCMTIME	(1 << 7)  /* Do not update file c/mtime */
+#define S_SWAPFILE	(1 << 8)  /* Do not truncate: swapon got its bmaps */
+#define S_PRIVATE	(1 << 9)  /* Inode is fs-internal */
+#define S_IMA		(1 << 10) /* Inode has an associated IMA struct */
+#define S_AUTOMOUNT	(1 << 11) /* Automount/referral quasi-directory */
+#define S_NOSEC		(1 << 12) /* no suid or xattr security attributes */
 #ifdef CONFIG_FS_DAX
-#define S_DAX		8192	/* Direct Access, avoiding the page cache */
+#define S_DAX		(1 << 13) /* Direct Access, avoiding the page cache */
 #else
-#define S_DAX		0	/* Make all the DAX code disappear */
+#define S_DAX		0	  /* Make all the DAX code disappear */
 #endif
-#define S_ENCRYPTED	16384	/* Encrypted file (using fs/crypto/) */
-#define S_CASEFOLD	32768	/* Casefolded file */
-#define S_VERITY	65536	/* Verity file (using fs/verity/) */
+#define S_ENCRYPTED	(1 << 14) /* Encrypted file (using fs/crypto/) */
+#define S_CASEFOLD	(1 << 15) /* Casefolded file */
+#define S_VERITY	(1 << 16) /* Verity file (using fs/verity/) */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
-- 
cgit v1.2.3


From 08b95c338e0c5a96e47f4ca314ea1e7580ecb5d7 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 8 Jul 2020 14:11:52 +0300
Subject: fanotify: remove event FAN_DIR_MODIFY

It was never enabled in uapi and its functionality is about to be
superseded by events FAN_CREATE, FAN_DELETE, FAN_MOVE with group
flag FAN_REPORT_NAME.

Keep a place holder variable name_event instead of removing the
name recording code since it will be used by the new events.

Link: https://lore.kernel.org/r/20200708111156.24659-17-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c    | 9 ++-------
 fs/notify/fsnotify.c             | 2 +-
 include/linux/fsnotify.h         | 6 ------
 include/linux/fsnotify_backend.h | 4 +---
 include/uapi/linux/fanotify.h    | 1 -
 5 files changed, 4 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index e417c64c365b..e6ba605732d7 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -425,6 +425,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	gfp_t gfp = GFP_KERNEL_ACCOUNT;
 	struct inode *id = fanotify_fid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
+	bool name_event = false;
 
 	/*
 	 * For queues with unlimited length lost events are not expected and
@@ -442,12 +443,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 
 	if (fanotify_is_perm_event(mask)) {
 		event = fanotify_alloc_perm_event(path, gfp);
-	} else if (mask & FAN_DIR_MODIFY && !(WARN_ON_ONCE(!file_name))) {
-		/*
-		 * For FAN_DIR_MODIFY event, we report the fid of the directory
-		 * and the name of the modified entry.
-		 * Allocate an fanotify_name_event struct and copy the name.
-		 */
+	} else if (name_event && file_name) {
 		event = fanotify_alloc_name_event(id, fsid, file_name, gfp);
 	} else if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
 		event = fanotify_alloc_fid_event(id, fsid, gfp);
@@ -528,7 +524,6 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
 	BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
 	BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
-	BUILD_BUG_ON(FAN_DIR_MODIFY != FS_DIR_MODIFY);
 	BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
 	BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
 	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index c4ac4d13e10f..f12a554be3f0 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -393,7 +393,7 @@ static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 316c9b820517..9b2566d273a9 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -30,12 +30,6 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask,
 				 const struct qstr *name, u32 cookie)
 {
 	fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie);
-	/*
-	 * Send another flavor of the event without child inode data and
-	 * without the specific event type (e.g. FS_CREATE|FS_IS_DIR).
-	 * The name is relative to the dir inode the event is reported to.
-	 */
-	fsnotify(dir, FS_DIR_MODIFY, dir, FSNOTIFY_EVENT_INODE, name, 0);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 0de130cbf72d..94a4ff3d5bbe 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -47,7 +47,6 @@
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
-#define FS_DIR_MODIFY		0x00080000	/* Directory entry was modified */
 
 #define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
 /* This inode cares about things that happen to its children.  Always set for
@@ -67,8 +66,7 @@
  * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event
  * when a directory entry inside a child subdir changes.
  */
-#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE | \
-					 FS_DIR_MODIFY)
+#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE)
 
 #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
 				  FS_OPEN_EXEC_PERM)
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index a88c7c6d0692..7f2f17eacbf9 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -24,7 +24,6 @@
 #define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
 #define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
 #define FAN_OPEN_EXEC_PERM	0x00040000	/* File open/exec in perm check */
-#define FAN_DIR_MODIFY		0x00080000	/* Directory entry was modified */
 
 #define FAN_EVENT_ON_CHILD	0x08000000	/* Interested in child events */
 
-- 
cgit v1.2.3


From d809daf1b6add51eec001bf60b17885d697a299d Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:12 +0300
Subject: fanotify: generalize test for FAN_REPORT_FID

As preparation for new flags that report fids, define a bit set
of flags for a group reporting fids, currently containing the
only bit FAN_REPORT_FID.

Link: https://lore.kernel.org/r/20200716084230.30611-5-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c      | 10 ++++++----
 fs/notify/fanotify/fanotify_user.c | 12 ++++++------
 include/linux/fanotify.h           |  6 ++++--
 3 files changed, 16 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 3dc71a8e795a..b8c04a6f04c5 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -207,13 +207,14 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 	__u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
 				     FANOTIFY_EVENT_FLAGS;
 	const struct path *path = fsnotify_data_path(data, data_type);
+	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	struct fsnotify_mark *mark;
 	int type;
 
 	pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
 		 __func__, iter_info->report_mask, event_mask, data, data_type);
 
-	if (!FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	if (!fid_mode) {
 		/* Do we have path to open a file descriptor? */
 		if (!path)
 			return 0;
@@ -264,7 +265,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 	 * fanotify_alloc_event() when group is reporting fid as indication
 	 * that event happened on child.
 	 */
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	if (fid_mode) {
 		/* Do not report event flags without any event */
 		if (!(test_mask & ~FANOTIFY_EVENT_FLAGS))
 			return 0;
@@ -424,6 +425,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	gfp_t gfp = GFP_KERNEL_ACCOUNT;
 	struct inode *id = fanotify_fid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
+	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	bool name_event = false;
 
 	/*
@@ -444,7 +446,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		event = fanotify_alloc_perm_event(path, gfp);
 	} else if (name_event && file_name) {
 		event = fanotify_alloc_name_event(id, fsid, file_name, gfp);
-	} else if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	} else if (fid_mode) {
 		event = fanotify_alloc_fid_event(id, fsid, gfp);
 	} else {
 		event = fanotify_alloc_path_event(path, gfp);
@@ -551,7 +553,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
 		fsid = fanotify_get_fsid(iter_info);
 		/* Racing with mark destruction or creation? */
 		if (!fsid.val[0] && !fsid.val[1])
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c9a824e5c045..1e04caf8d6ba 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -100,7 +100,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 	if (fsnotify_notify_queue_is_empty(group))
 		goto out;
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
 		event_size += fanotify_event_info_len(
 			FANOTIFY_E(fsnotify_peek_first_event(group)));
 	}
@@ -882,7 +882,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		return -EINVAL;
 	}
 
-	if ((flags & FAN_REPORT_FID) &&
+	if ((flags & FANOTIFY_FID_BITS) &&
 	    (flags & FANOTIFY_CLASS_BITS) != FAN_CLASS_NOTIF)
 		return -EINVAL;
 
@@ -1040,7 +1040,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	__kernel_fsid_t __fsid, *fsid = NULL;
 	u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
 	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
-	unsigned int obj_type;
+	unsigned int obj_type, fid_mode;
 	int ret;
 
 	pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
@@ -1113,9 +1113,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	 * inode events are not supported on a mount mark, because they do not
 	 * carry enough information (i.e. path) to be filtered by mount point.
 	 */
+	fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	if (mask & FANOTIFY_INODE_EVENTS &&
-	    (!FAN_GROUP_FLAG(group, FAN_REPORT_FID) ||
-	     mark_type == FAN_MARK_MOUNT))
+	    (!fid_mode || mark_type == FAN_MARK_MOUNT))
 		goto fput_and_out;
 
 	if (flags & FAN_MARK_FLUSH) {
@@ -1140,7 +1140,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 			goto path_put_and_out;
 	}
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+	if (fid_mode) {
 		ret = fanotify_test_fid(&path, &__fsid);
 		if (ret)
 			goto path_put_and_out;
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index b79fa9bb7359..bbbee11d2521 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -18,8 +18,10 @@
 #define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
 				 FAN_CLASS_PRE_CONTENT)
 
-#define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | \
-				 FAN_REPORT_TID | FAN_REPORT_FID | \
+#define FANOTIFY_FID_BITS	(FAN_REPORT_FID)
+
+#define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \
+				 FAN_REPORT_TID | \
 				 FAN_CLOEXEC | FAN_NONBLOCK | \
 				 FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS)
 
-- 
cgit v1.2.3


From 6ba8d7107f27c1bde60a80bc5def027979af3e8e Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:16 +0300
Subject: fsnotify: add object type "child" to object type iterator

The object type iterator is used to collect all the marks of
a specific group that have interest in an event.

It is used by fanotify to get a single handle_event callback
when an event has a match to either of inode/sb/mount marks
of the group.

The nature of fsnotify events is that they are associated with
at most one sb at most one mount and at most one inode.

When a parent and child are both watching, two events are sent
to backend, one associated to parent inode and one associated
to the child inode.

This results in duplicate events in fanotify, which usually
get merged before user reads them, but this is sub-optimal.

It would be better if the same event is sent to backend with
an object type iterator that has both the child inode and its
parent, and let the backend decide if the event should be reported
once (fanotify) or twice (inotify).

Link: https://lore.kernel.org/r/20200716084230.30611-9-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/linux/fsnotify_backend.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 94a4ff3d5bbe..d22519001027 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -253,6 +253,7 @@ static inline const struct path *fsnotify_data_path(const void *data,
 
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
+	FSNOTIFY_OBJ_TYPE_CHILD,
 	FSNOTIFY_OBJ_TYPE_VFSMOUNT,
 	FSNOTIFY_OBJ_TYPE_SB,
 	FSNOTIFY_OBJ_TYPE_COUNT,
@@ -260,6 +261,7 @@ enum fsnotify_obj_type {
 };
 
 #define FSNOTIFY_OBJ_TYPE_INODE_FL	(1U << FSNOTIFY_OBJ_TYPE_INODE)
+#define FSNOTIFY_OBJ_TYPE_CHILD_FL	(1U << FSNOTIFY_OBJ_TYPE_CHILD)
 #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL	(1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT)
 #define FSNOTIFY_OBJ_TYPE_SB_FL		(1U << FSNOTIFY_OBJ_TYPE_SB)
 #define FSNOTIFY_OBJ_ALL_TYPES_MASK	((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1)
@@ -304,6 +306,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
 }
 
 FSNOTIFY_ITER_FUNCS(inode, INODE)
+FSNOTIFY_ITER_FUNCS(child, CHILD)
 FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT)
 FSNOTIFY_ITER_FUNCS(sb, SB)
 
-- 
cgit v1.2.3


From 8b7beaf9f185249f29912b5e2d7bc4147c5c2a6a Mon Sep 17 00:00:00 2001
From: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Date: Mon, 27 Jul 2020 13:43:39 -0600
Subject: PCI: Add Intel QuickAssist device IDs

Add device IDs for the following Intel QuickAssist devices: DH895XCC,
C3XXX and C62X.

The defines in this patch are going to be referenced in two independent
drivers, qat and vfio-pci.

Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/linux/pci_ids.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0ad57693f392..f3166b1425ca 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2659,6 +2659,8 @@
 #define PCI_DEVICE_ID_INTEL_80332_1	0x0332
 #define PCI_DEVICE_ID_INTEL_80333_0	0x0370
 #define PCI_DEVICE_ID_INTEL_80333_1	0x0372
+#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC	0x0435
+#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF	0x0443
 #define PCI_DEVICE_ID_INTEL_82375	0x0482
 #define PCI_DEVICE_ID_INTEL_82424	0x0483
 #define PCI_DEVICE_ID_INTEL_82378	0x0484
@@ -2708,6 +2710,8 @@
 #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_NHI     0x1577
 #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_BRIDGE  0x1578
 #define PCI_DEVICE_ID_INTEL_80960_RP	0x1960
+#define PCI_DEVICE_ID_INTEL_QAT_C3XXX	0x19e2
+#define PCI_DEVICE_ID_INTEL_QAT_C3XXX_VF	0x19e3
 #define PCI_DEVICE_ID_INTEL_82840_HB	0x1a21
 #define PCI_DEVICE_ID_INTEL_82845_HB	0x1a30
 #define PCI_DEVICE_ID_INTEL_IOAT	0x1a38
@@ -2924,6 +2928,8 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF7	0x3717
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF8	0x3718
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF9	0x3719
+#define PCI_DEVICE_ID_INTEL_QAT_C62X	0x37c8
+#define PCI_DEVICE_ID_INTEL_QAT_C62X_VF	0x37c9
 #define PCI_DEVICE_ID_INTEL_ICH10_0	0x3a14
 #define PCI_DEVICE_ID_INTEL_ICH10_1	0x3a16
 #define PCI_DEVICE_ID_INTEL_ICH10_2	0x3a18
-- 
cgit v1.2.3


From 82ace1efb3cb1d49a1681cc6e31156047d5ae1f2 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Jul 2020 15:58:44 +0300
Subject: fsnotify: create helper fsnotify_inode()

Simple helper to consolidate biolerplate code.

Link: https://lore.kernel.org/r/20200722125849.17418-5-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/kernfs/file.c         |  6 ++----
 fs/notify/fsnotify.c     |  2 +-
 include/linux/fsnotify.h | 26 +++++++++++---------------
 kernel/trace/trace.c     |  3 +--
 4 files changed, 15 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 5b1468bc509e..1d185bffc52f 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -910,10 +910,8 @@ repeat:
 			kernfs_put(parent);
 		}
 
-		if (!p_inode) {
-			fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
-				 NULL, 0);
-		}
+		if (!p_inode)
+			fsnotify_inode(inode, FS_MODIFY);
 
 		iput(inode);
 	}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 0b0e01e04349..ba172b742de5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -74,7 +74,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb)
 			iput(iput_inode);
 
 		/* for each watch, send FS_UNMOUNT and then remove it */
-		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+		fsnotify_inode(inode, FS_UNMOUNT);
 
 		fsnotify_inode_delete(inode);
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 9b2566d273a9..f9db7c9b3ef1 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -38,6 +38,14 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
 }
 
+static inline void fsnotify_inode(struct inode *inode, __u32 mask)
+{
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
 /* Notify this dentry's parent about a child's events. */
 static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 				  const void *data, int data_type)
@@ -105,12 +113,7 @@ static inline int fsnotify_perm(struct file *file, int mask)
  */
 static inline void fsnotify_link_count(struct inode *inode)
 {
-	__u32 mask = FS_ATTRIB;
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_inode(inode, FS_ATTRIB);
 }
 
 /*
@@ -125,7 +128,6 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 	u32 fs_cookie = fsnotify_get_cookie();
 	__u32 old_dir_mask = FS_MOVED_FROM;
 	__u32 new_dir_mask = FS_MOVED_TO;
-	__u32 mask = FS_MOVE_SELF;
 	const struct qstr *new_name = &moved->d_name;
 
 	if (old_dir == new_dir)
@@ -134,7 +136,6 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 	if (isdir) {
 		old_dir_mask |= FS_ISDIR;
 		new_dir_mask |= FS_ISDIR;
-		mask |= FS_ISDIR;
 	}
 
 	fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie);
@@ -144,7 +145,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		fsnotify_link_count(target);
 
 	if (source)
-		fsnotify(source, mask, source, FSNOTIFY_EVENT_INODE, NULL, 0);
+		fsnotify_inode(source, FS_MOVE_SELF);
 	audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE);
 }
 
@@ -169,12 +170,7 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt)
  */
 static inline void fsnotify_inoderemove(struct inode *inode)
 {
-	__u32 mask = FS_DELETE_SELF;
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_inode(inode, FS_DELETE_SELF);
 	__fsnotify_inode_delete(inode);
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bb62269724d5..0c655c039506 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1543,8 +1543,7 @@ static void latency_fsnotify_workfn(struct work_struct *work)
 {
 	struct trace_array *tr = container_of(work, struct trace_array,
 					      fsnotify_work);
-	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
-		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY);
 }
 
 static void latency_fsnotify_workfn_irq(struct irq_work *iwork)
-- 
cgit v1.2.3


From 40a100d3adc1ad7f0a34875468c499fcecd20ba4 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Jul 2020 15:58:46 +0300
Subject: fsnotify: pass dir and inode arguments to fsnotify()

The arguments of fsnotify() are overloaded and mean different things
for different event types.

Replace the to_tell argument with separate arguments @dir and @inode,
because we may be sending to both dir and child.  Using the @data
argument to pass the child is not enough, because dirent events pass
this argument (for audit), but we do not report to child.

Document the new fsnotify() function argumenets.

Link: https://lore.kernel.org/r/20200722125849.17418-7-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/kernfs/file.c                 |  5 ++--
 fs/notify/fsnotify.c             | 54 ++++++++++++++++++++++++++++------------
 include/linux/fsnotify.h         |  9 ++++---
 include/linux/fsnotify_backend.h | 10 +++++---
 4 files changed, 52 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 1d185bffc52f..f277d023ebcd 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -902,8 +902,9 @@ repeat:
 		if (parent) {
 			p_inode = ilookup(info->sb, kernfs_ino(parent));
 			if (p_inode) {
-				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
-					 inode, FSNOTIFY_EVENT_INODE, &name, 0);
+				fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD,
+					 inode, FSNOTIFY_EVENT_INODE,
+					 p_inode, &name, inode, 0);
 				iput(p_inode);
 			}
 
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index ba172b742de5..4a762c8c4a29 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -152,7 +152,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 {
 	struct inode *inode = d_inode(dentry);
 	struct dentry *parent;
-	struct inode *p_inode;
+	struct inode *p_inode = NULL;
 	struct name_snapshot name;
 	struct qstr *file_name = NULL;
 	int ret = 0;
@@ -171,14 +171,13 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 		WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
 
 		/* Notify both parent and child with child name info */
-		inode = p_inode;
 		take_dentry_name_snapshot(&name, dentry);
 		file_name = &name.name;
 		mask |= FS_EVENT_ON_CHILD;
 	}
 
 notify:
-	ret = fsnotify(inode, mask, data, data_type, file_name, 0);
+	ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0);
 
 	if (file_name)
 		release_dentry_name_snapshot(&name);
@@ -312,18 +311,31 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
 }
 
 /*
- * This is the main call to fsnotify.  The VFS calls into hook specific functions
- * in linux/fsnotify.h.  Those functions then in turn call here.  Here will call
- * out to all of the registered fsnotify_group.  Those groups can then use the
- * notification event in whatever means they feel necessary.
+ * fsnotify - This is the main call to fsnotify.
+ *
+ * The VFS calls into hook specific functions in linux/fsnotify.h.
+ * Those functions then in turn call here.  Here will call out to all of the
+ * registered fsnotify_group.  Those groups can then use the notification event
+ * in whatever means they feel necessary.
+ *
+ * @mask:	event type and flags
+ * @data:	object that event happened on
+ * @data_type:	type of object for fanotify_data_XXX() accessors
+ * @dir:	optional directory associated with event -
+ *		if @file_name is not NULL, this is the directory that
+ *		@file_name is relative to
+ * @file_name:	optional file name associated with event
+ * @inode:	optional inode associated with event -
+ *		either @dir or @inode must be non-NULL.
+ *		if both are non-NULL event may be reported to both.
+ * @cookie:	inotify rename cookie
  */
-int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type,
-	     const struct qstr *file_name, u32 cookie)
+int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
+	     const struct qstr *file_name, struct inode *inode, u32 cookie)
 {
 	const struct path *path = fsnotify_data_path(data, data_type);
 	struct fsnotify_iter_info iter_info = {};
-	struct super_block *sb = to_tell->i_sb;
-	struct inode *dir = file_name ? to_tell : NULL;
+	struct super_block *sb;
 	struct mount *mnt = NULL;
 	struct inode *child = NULL;
 	int ret = 0;
@@ -332,8 +344,18 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type,
 	if (path)
 		mnt = real_mount(path->mnt);
 
-	if (mask & FS_EVENT_ON_CHILD)
-		child = fsnotify_data_inode(data, data_type);
+	if (!inode) {
+		/* Dirent event - report on TYPE_INODE to dir */
+		inode = dir;
+	} else if (mask & FS_EVENT_ON_CHILD) {
+		/*
+		 * Event on child - report on TYPE_INODE to dir
+		 * and on TYPE_CHILD to child.
+		 */
+		child = inode;
+		inode = dir;
+	}
+	sb = inode->i_sb;
 
 	/*
 	 * Optimization: srcu_read_lock() has a memory barrier which can
@@ -342,12 +364,12 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type,
 	 * SRCU because we have no references to any objects and do not
 	 * need SRCU to keep them "alive".
 	 */
-	if (!to_tell->i_fsnotify_marks && !sb->s_fsnotify_marks &&
+	if (!inode->i_fsnotify_marks && !sb->s_fsnotify_marks &&
 	    (!mnt || !mnt->mnt_fsnotify_marks) &&
 	    (!child || !child->i_fsnotify_marks))
 		return 0;
 
-	marks_mask = to_tell->i_fsnotify_mask | sb->s_fsnotify_mask;
+	marks_mask = inode->i_fsnotify_mask | sb->s_fsnotify_mask;
 	if (mnt)
 		marks_mask |= mnt->mnt_fsnotify_mask;
 	if (child)
@@ -365,7 +387,7 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type,
 	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
 
 	iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
-		fsnotify_first_mark(&to_tell->i_fsnotify_marks);
+		fsnotify_first_mark(&inode->i_fsnotify_marks);
 	iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] =
 		fsnotify_first_mark(&sb->s_fsnotify_marks);
 	if (mnt) {
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index f9db7c9b3ef1..99922cac4fcd 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -23,13 +23,14 @@
  * have changed (i.e. renamed over).
  *
  * Unlike fsnotify_parent(), the event will be reported regardless of the
- * FS_EVENT_ON_CHILD mask on the parent inode.
+ * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only
+ * the child is interested and not the parent.
  */
 static inline void fsnotify_name(struct inode *dir, __u32 mask,
 				 struct inode *child,
 				 const struct qstr *name, u32 cookie)
 {
-	fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie);
+	fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
@@ -43,7 +44,7 @@ static inline void fsnotify_inode(struct inode *inode, __u32 mask)
 	if (S_ISDIR(inode->i_mode))
 		mask |= FS_ISDIR;
 
-	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0);
 }
 
 /* Notify this dentry's parent about a child's events. */
@@ -61,7 +62,7 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 	return __fsnotify_parent(dentry, mask, data, data_type);
 
 notify_child:
-	return fsnotify(inode, mask, data, data_type, NULL, 0);
+	return fsnotify(mask, data, data_type, NULL, NULL, inode, 0);
 }
 
 /*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index d22519001027..152520635bd3 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -387,8 +387,9 @@ struct fsnotify_mark {
 /* called from the vfs helpers */
 
 /* main fsnotify call to send events */
-extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
-		    int data_type, const struct qstr *name, u32 cookie);
+extern int fsnotify(__u32 mask, const void *data, int data_type,
+		    struct inode *dir, const struct qstr *name,
+		    struct inode *inode, u32 cookie);
 extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 			   int data_type);
 extern void __fsnotify_inode_delete(struct inode *inode);
@@ -545,8 +546,9 @@ static inline void fsnotify_init_event(struct fsnotify_event *event,
 
 #else
 
-static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
-			   int data_type, const struct qstr *name, u32 cookie)
+static inline int fsnotify(__u32 mask, const void *data, int data_type,
+			   struct inode *dir, const struct qstr *name,
+			   struct inode *inode, u32 cookie)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 9b93f33105f5f9bd3d016ff870eb6000c9d89eff Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:23 +0300
Subject: fsnotify: send event with parent/name info to sb/mount/non-dir marks

Similar to events "on child" to watching directory, send event
with parent/name info if sb/mount/non-dir marks are interested in
parent/name info.

The FS_EVENT_ON_CHILD flag can be set on sb/mount/non-dir marks to specify
interest in parent/name info for events on non-directory inodes.

Events on "orphan" children (disconnected dentries) are sent without
parent/name info.

Events on directories are sent with parent/name info only if the parent
directory is watching.

After this change, even groups that do not subscribe to events on
children could get an event with mark iterator type TYPE_CHILD and
without mark iterator type TYPE_INODE if fanotify has marks on the same
objects.

dnotify and inotify event handlers can already cope with that situation.
audit does not subscribe to events that are possible on child, so won't
get to this situation. nfsd does not access the marks iterator from its
event handler at the moment, so it is not affected.

This is a bit too fragile, so we should prepare all groups to cope with
mark type TYPE_CHILD preferably using a generic helper.

Link: https://lore.kernel.org/r/20200716084230.30611-16-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fsnotify.c             | 74 +++++++++++++++++++++++++++++++++-------
 include/linux/fsnotify.h         | 10 ++++--
 include/linux/fsnotify_backend.h | 32 ++++++++++++++---
 3 files changed, 97 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 4a762c8c4a29..494d5d70323f 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -142,38 +142,81 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 }
 
+/* Are inode/sb/mount interested in parent and name info with this event? */
+static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt,
+					__u32 mask)
+{
+	__u32 marks_mask = 0;
+
+	/* We only send parent/name to inode/sb/mount for events on non-dir */
+	if (mask & FS_ISDIR)
+		return false;
+
+	/* Did either inode/sb/mount subscribe for events with parent/name? */
+	marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
+	marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
+	if (mnt)
+		marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask);
+
+	/* Did they subscribe for this event with parent/name info? */
+	return mask & marks_mask;
+}
+
 /*
  * Notify this dentry's parent about a child's events with child name info
- * if parent is watching.
- * Notify only the child without name info if parent is not watching.
+ * if parent is watching or if inode/sb/mount are interested in events with
+ * parent and name info.
+ *
+ * Notify only the child without name info if parent is not watching and
+ * inode/sb/mount are not interested in events with parent and name info.
  */
 int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 		      int data_type)
 {
+	const struct path *path = fsnotify_data_path(data, data_type);
+	struct mount *mnt = path ? real_mount(path->mnt) : NULL;
 	struct inode *inode = d_inode(dentry);
 	struct dentry *parent;
+	bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
+	__u32 p_mask;
 	struct inode *p_inode = NULL;
 	struct name_snapshot name;
 	struct qstr *file_name = NULL;
 	int ret = 0;
 
+	/*
+	 * Do inode/sb/mount care about parent and name info on non-dir?
+	 * Do they care about any event at all?
+	 */
+	if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks &&
+	    (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched)
+		return 0;
+
 	parent = NULL;
-	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+	if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask))
 		goto notify;
 
+	/* Does parent inode care about events on children? */
 	parent = dget_parent(dentry);
 	p_inode = parent->d_inode;
-
-	if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
+	p_mask = fsnotify_inode_watches_children(p_inode);
+	if (unlikely(parent_watched && !p_mask))
 		__fsnotify_update_child_dentry_flags(p_inode);
-	} else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
+
+	/*
+	 * Include parent/name in notification either if some notification
+	 * groups require parent info (!parent_watched case) or the parent is
+	 * interested in this event.
+	 */
+	if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) {
 		/* When notifying parent, child should be passed as data */
 		WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
 
 		/* Notify both parent and child with child name info */
 		take_dentry_name_snapshot(&name, dentry);
 		file_name = &name.name;
-		mask |= FS_EVENT_ON_CHILD;
+		if (parent_watched)
+			mask |= FS_EVENT_ON_CHILD;
 	}
 
 notify:
@@ -349,8 +392,8 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		inode = dir;
 	} else if (mask & FS_EVENT_ON_CHILD) {
 		/*
-		 * Event on child - report on TYPE_INODE to dir
-		 * and on TYPE_CHILD to child.
+		 * Event on child - report on TYPE_INODE to dir if it is
+		 * watching children and on TYPE_CHILD to child.
 		 */
 		child = inode;
 		inode = dir;
@@ -364,14 +407,17 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	 * SRCU because we have no references to any objects and do not
 	 * need SRCU to keep them "alive".
 	 */
-	if (!inode->i_fsnotify_marks && !sb->s_fsnotify_marks &&
+	if (!sb->s_fsnotify_marks &&
 	    (!mnt || !mnt->mnt_fsnotify_marks) &&
+	    (!inode || !inode->i_fsnotify_marks) &&
 	    (!child || !child->i_fsnotify_marks))
 		return 0;
 
-	marks_mask = inode->i_fsnotify_mask | sb->s_fsnotify_mask;
+	marks_mask = sb->s_fsnotify_mask;
 	if (mnt)
 		marks_mask |= mnt->mnt_fsnotify_mask;
+	if (inode)
+		marks_mask |= inode->i_fsnotify_mask;
 	if (child)
 		marks_mask |= child->i_fsnotify_mask;
 
@@ -386,14 +432,16 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 
 	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
 
-	iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
-		fsnotify_first_mark(&inode->i_fsnotify_marks);
 	iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] =
 		fsnotify_first_mark(&sb->s_fsnotify_marks);
 	if (mnt) {
 		iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
 			fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
 	}
+	if (inode) {
+		iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
+			fsnotify_first_mark(&inode->i_fsnotify_marks);
+	}
 	if (child) {
 		iter_info.marks[FSNOTIFY_OBJ_TYPE_CHILD] =
 			fsnotify_first_mark(&child->i_fsnotify_marks);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 99922cac4fcd..6e63f7e10da0 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -53,10 +53,16 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
 		mask |= FS_ISDIR;
 
-	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+		/* sb/mount marks are not interested in name of directory */
+		if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+			goto notify_child;
+	}
+
+	/* disconnected dentry cannot notify parent */
+	if (IS_ROOT(dentry))
 		goto notify_child;
 
 	return __fsnotify_parent(dentry, mask, data, data_type);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 152520635bd3..32104cfc27a5 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -49,8 +49,11 @@
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
 
 #define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
-/* This inode cares about things that happen to its children.  Always set for
- * dnotify and inotify. */
+/*
+ * Set on inode mark that cares about things that happen to its children.
+ * Always set for dnotify and inotify.
+ * Set on inode/sb/mount marks that care about parent/name info.
+ */
 #define FS_EVENT_ON_CHILD	0x08000000
 
 #define FS_DN_RENAME		0x10000000	/* file renamed */
@@ -72,14 +75,22 @@
 				  FS_OPEN_EXEC_PERM)
 
 /*
- * This is a list of all events that may get sent to a parent based on fs event
- * happening to inodes inside that directory.
+ * This is a list of all events that may get sent to a parent that is watching
+ * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory.
  */
 #define FS_EVENTS_POSS_ON_CHILD   (ALL_FSNOTIFY_PERM_EVENTS | \
 				   FS_ACCESS | FS_MODIFY | FS_ATTRIB | \
 				   FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \
 				   FS_OPEN | FS_OPEN_EXEC)
 
+/*
+ * This is a list of all events that may get sent with the parent inode as the
+ * @to_tell argument of fsnotify().
+ * It may include events that can be sent to an inode/sb/mount mark, but cannot
+ * be sent to a parent watching children.
+ */
+#define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD)
+
 /* Events that can be reported to backends */
 #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
 			     FS_EVENTS_POSS_ON_CHILD | \
@@ -397,6 +408,19 @@ extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
 extern void fsnotify_sb_delete(struct super_block *sb);
 extern u32 fsnotify_get_cookie(void);
 
+static inline __u32 fsnotify_parent_needed_mask(__u32 mask)
+{
+	/* FS_EVENT_ON_CHILD is set on marks that want parent/name info */
+	if (!(mask & FS_EVENT_ON_CHILD))
+		return 0;
+	/*
+	 * This object might be watched by a mark that cares about parent/name
+	 * info, does it care about the specific set of events that can be
+	 * reported with parent/name info?
+	 */
+	return mask & FS_EVENTS_POSS_TO_PARENT;
+}
+
 static inline int fsnotify_inode_watches_children(struct inode *inode)
 {
 	/* FS_EVENT_ON_CHILD is set if the inode may care */
-- 
cgit v1.2.3


From 79cb299c7e181fad683bf6191edb8224b2412512 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:24 +0300
Subject: fsnotify: remove check that source dentry is positive

Remove the unneeded check for positive source dentry in
fsnotify_move().

fsnotify_move() hook is mostly called from vfs_rename() under
lock_rename() and vfs_rename() starts with may_delete() test that
verifies positive source dentry.  The only other caller of
fsnotify_move() - debugfs_rename() also verifies positive source.

Link: https://lore.kernel.org/r/20200716084230.30611-17-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/linux/fsnotify.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 6e63f7e10da0..f8acddcf54fb 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -150,9 +150,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 
 	if (target)
 		fsnotify_link_count(target);
-
-	if (source)
-		fsnotify_inode(source, FS_MOVE_SELF);
+	fsnotify_inode(source, FS_MOVE_SELF);
 	audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE);
 }
 
-- 
cgit v1.2.3


From 83b7a59896dd24015a34b7f00027f0ff3747972f Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:26 +0300
Subject: fanotify: add basic support for FAN_REPORT_DIR_FID

For now, the flag is mutually exclusive with FAN_REPORT_FID.
Events include a single info record of type FAN_EVENT_INFO_TYPE_DFID
with a directory file handle.

For now, events are only reported for:
- Directory modification events
- Events on children of a watching directory
- Events on directory objects

Soon, we will add support for reporting the parent directory fid
for events on non-directories with filesystem/mount mark and
support for reporting both parent directory fid and child fid.

Link: https://lore.kernel.org/r/20200716084230.30611-19-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c      | 34 ++++++++++++++++--
 fs/notify/fanotify/fanotify_user.c | 71 ++++++++++++++++++++++++++++++++------
 include/linux/fanotify.h           |  2 +-
 include/uapi/linux/fanotify.h      | 11 +++---
 4 files changed, 101 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 3baf93e998c1..fc2e1fab34af 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -223,7 +223,7 @@ out:
 static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 				     struct fsnotify_iter_info *iter_info,
 				     u32 event_mask, const void *data,
-				     int data_type)
+				     int data_type, struct inode *dir)
 {
 	__u32 marks_mask = 0, marks_ignored_mask = 0;
 	__u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
@@ -243,6 +243,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 		/* Path type events are only relevant for files and dirs */
 		if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
 			return 0;
+	} else if (!(fid_mode & FAN_REPORT_FID)) {
+		/* Do we have a directory inode to report? */
+		if (!dir && !(event_mask & FS_ISDIR))
+			return 0;
 	}
 
 	fsnotify_foreach_obj_type(type) {
@@ -396,6 +400,28 @@ static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
 	return fsnotify_data_inode(data, data_type);
 }
 
+/*
+ * The inode to use as identifier when reporting dir fid depends on the event.
+ * Report the modified directory inode on dirent modification events.
+ * Report the "victim" inode if "victim" is a directory.
+ * Report the parent inode if "victim" is not a directory and event is
+ * reported to parent.
+ * Otherwise, do not report dir fid.
+ */
+static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
+					 int data_type, struct inode *dir)
+{
+	struct inode *inode = fsnotify_data_inode(data, data_type);
+
+	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
+		return dir;
+
+	if (S_ISDIR(inode->i_mode))
+		return inode;
+
+	return dir;
+}
+
 static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
 							gfp_t gfp)
 {
@@ -491,10 +517,14 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	struct fanotify_event *event = NULL;
 	gfp_t gfp = GFP_KERNEL_ACCOUNT;
 	struct inode *id = fanotify_fid_inode(mask, data, data_type, dir);
+	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
 	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	bool name_event = false;
 
+	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid)
+		id = dirid;
+
 	/*
 	 * For queues with unlimited length lost events are not expected and
 	 * can possibly have security implications. Avoid losing events when
@@ -605,7 +635,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
 
 	mask = fanotify_group_event_mask(group, iter_info, mask, data,
-					 data_type);
+					 data_type, dir);
 	if (!mask)
 		return 0;
 
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 3842ef00b52e..e494400711c9 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -216,7 +216,7 @@ static int process_access_response(struct fsnotify_group *group,
 }
 
 static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
-			     const char *name, size_t name_len,
+			     int info_type, const char *name, size_t name_len,
 			     char __user *buf, size_t count)
 {
 	struct fanotify_event_info_fid info = { };
@@ -229,7 +229,7 @@ static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
 	pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
 		 __func__, fh_len, name_len, info_len, count);
 
-	if (!fh_len || (name && !name_len))
+	if (!fh_len)
 		return 0;
 
 	if (WARN_ON_ONCE(len < sizeof(info) || len > count))
@@ -239,8 +239,21 @@ static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
 	 * Copy event info fid header followed by variable sized file handle
 	 * and optionally followed by variable sized filename.
 	 */
-	info.hdr.info_type = name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
-					FAN_EVENT_INFO_TYPE_FID;
+	switch (info_type) {
+	case FAN_EVENT_INFO_TYPE_FID:
+	case FAN_EVENT_INFO_TYPE_DFID:
+		if (WARN_ON_ONCE(name_len))
+			return -EFAULT;
+		break;
+	case FAN_EVENT_INFO_TYPE_DFID_NAME:
+		if (WARN_ON_ONCE(!name || !name_len))
+			return -EFAULT;
+		break;
+	default:
+		return -EFAULT;
+	}
+
+	info.hdr.info_type = info_type;
 	info.hdr.len = len;
 	info.fsid = *fsid;
 	if (copy_to_user(buf, &info, sizeof(info)))
@@ -304,8 +317,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	struct fanotify_event_metadata metadata;
 	struct path *path = fanotify_event_path(event);
 	struct fanotify_info *info = fanotify_event_info(event);
+	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	struct file *f = NULL;
 	int ret, fd = FAN_NOFD;
+	int info_type = 0;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -346,9 +361,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
 	/* Event info records order is: dir fid + name, child fid */
 	if (fanotify_event_dir_fh_len(event)) {
+		info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
 		ret = copy_info_to_user(fanotify_event_fsid(event),
 					fanotify_info_dir_fh(info),
-					fanotify_info_name(info),
+					info_type, fanotify_info_name(info),
 					info->name_len, buf, count);
 		if (ret < 0)
 			return ret;
@@ -358,9 +374,33 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	}
 
 	if (fanotify_event_object_fh_len(event)) {
+		if (fid_mode == FAN_REPORT_FID || info_type) {
+			/*
+			 * With only group flag FAN_REPORT_FID only type FID is
+			 * reported. Second info record type is always FID.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_FID;
+		} else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
+			   (event->mask & FAN_ONDIR)) {
+			/*
+			 * With group flag FAN_REPORT_DIR_FID, a single info
+			 * record has type DFID for directory entry modification
+			 * event and for event on a directory.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_DFID;
+		} else {
+			/*
+			 * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
+			 * a single info record has type FID for event on a
+			 * non-directory, when there is no directory to report.
+			 * For example, on FAN_DELETE_SELF event.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_FID;
+		}
+
 		ret = copy_info_to_user(fanotify_event_fsid(event),
 					fanotify_event_object_fh(event),
-					NULL, 0, buf, count);
+					info_type, NULL, 0, buf, count);
 		if (ret < 0)
 			return ret;
 
@@ -861,6 +901,8 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	struct fsnotify_group *group;
 	int f_flags, fd;
 	struct user_struct *user;
+	unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
+	unsigned int class = flags & FANOTIFY_CLASS_BITS;
 
 	pr_debug("%s: flags=%x event_f_flags=%x\n",
 		 __func__, flags, event_f_flags);
@@ -887,10 +929,19 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		return -EINVAL;
 	}
 
-	if ((flags & FANOTIFY_FID_BITS) &&
-	    (flags & FANOTIFY_CLASS_BITS) != FAN_CLASS_NOTIF)
+	if (fid_mode && class != FAN_CLASS_NOTIF)
 		return -EINVAL;
 
+	/* Reporting either object fid or dir fid */
+	switch (fid_mode) {
+	case 0:
+	case FAN_REPORT_FID:
+	case FAN_REPORT_DIR_FID:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	user = get_current_user();
 	if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
 		free_uid(user);
@@ -926,7 +977,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->fanotify_data.f_flags = event_f_flags;
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	switch (flags & FANOTIFY_CLASS_BITS) {
+	switch (class) {
 	case FAN_CLASS_NOTIF:
 		group->priority = FS_PRIO_0;
 		break;
@@ -1236,7 +1287,7 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
  */
 static int __init fanotify_user_setup(void)
 {
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 8);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 9);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
 
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index bbbee11d2521..4ddac97b2bf7 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -18,7 +18,7 @@
 #define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
 				 FAN_CLASS_PRE_CONTENT)
 
-#define FANOTIFY_FID_BITS	(FAN_REPORT_FID)
+#define FANOTIFY_FID_BITS	(FAN_REPORT_FID | FAN_REPORT_DIR_FID)
 
 #define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \
 				 FAN_REPORT_TID | \
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index 7f2f17eacbf9..21afebf77fd7 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -53,6 +53,7 @@
 /* Flags to determine fanotify event format */
 #define FAN_REPORT_TID		0x00000100	/* event->pid is thread id */
 #define FAN_REPORT_FID		0x00000200	/* Report unique file id */
+#define FAN_REPORT_DIR_FID	0x00000400	/* Report unique directory id */
 
 /* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
@@ -117,6 +118,7 @@ struct fanotify_event_metadata {
 
 #define FAN_EVENT_INFO_TYPE_FID		1
 #define FAN_EVENT_INFO_TYPE_DFID_NAME	2
+#define FAN_EVENT_INFO_TYPE_DFID	3
 
 /* Variable length info record following event metadata */
 struct fanotify_event_info_header {
@@ -126,10 +128,11 @@ struct fanotify_event_info_header {
 };
 
 /*
- * Unique file identifier info record. This is used both for
- * FAN_EVENT_INFO_TYPE_FID records and for FAN_EVENT_INFO_TYPE_DFID_NAME
- * records. For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null
- * terminated name immediately after the file handle.
+ * Unique file identifier info record.
+ * This structure is used for records of types FAN_EVENT_INFO_TYPE_FID,
+ * FAN_EVENT_INFO_TYPE_DFID and FAN_EVENT_INFO_TYPE_DFID_NAME.
+ * For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null terminated
+ * name immediately after the file handle.
  */
 struct fanotify_event_info_fid {
 	struct fanotify_event_info_header hdr;
-- 
cgit v1.2.3


From 929943b38daf817f2e6d303ea04401651fc3bc05 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 16 Jul 2020 11:42:28 +0300
Subject: fanotify: add support for FAN_REPORT_NAME

Introduce a new fanotify_init() flag FAN_REPORT_NAME.  It requires the
flag FAN_REPORT_DIR_FID and there is a constant for setting both flags
named FAN_REPORT_DFID_NAME.

For a group with flag FAN_REPORT_NAME, the parent fid and name are
reported for directory entry modification events (create/detete/move)
and for events on non-directory objects.

Events on directories themselves are reported with their own fid and
"." as the name.

The parent fid and name are reported with an info record of type
FAN_EVENT_INFO_TYPE_DFID_NAME, similar to the way that parent fid is
reported with into type FAN_EVENT_INFO_TYPE_DFID, but with an appended
null terminated name string.

Link: https://lore.kernel.org/r/20200716084230.30611-21-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c      | 18 ++++++++++++++-
 fs/notify/fanotify/fanotify_user.c | 45 ++++++++++++++++++++++++++++++--------
 include/linux/fanotify.h           |  2 +-
 include/uapi/linux/fanotify.h      |  4 ++++
 4 files changed, 58 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index fc2e1fab34af..d793f3e56b26 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -522,9 +522,25 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 	bool name_event = false;
 
-	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid)
+	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
 		id = dirid;
 
+		/*
+		 * We record file name only in a group with FAN_REPORT_NAME
+		 * and when we have a directory inode to report.
+		 *
+		 * For directory entry modification event, we record the fid of
+		 * the directory and the name of the modified entry.
+		 *
+		 * For event on non-directory that is reported to parent, we
+		 * record the fid of the parent and the name of the child.
+		 */
+		if ((fid_mode & FAN_REPORT_NAME) &&
+		    ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
+		     !(mask & FAN_ONDIR)))
+			name_event = true;
+	}
+
 	/*
 	 * For queues with unlimited length lost events are not expected and
 	 * can possibly have security implications. Avoid losing events when
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 7caa64d028ba..6b839790cb42 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -64,18 +64,27 @@ static int fanotify_fid_info_len(int fh_len, int name_len)
 	return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
 }
 
-static int fanotify_event_info_len(struct fanotify_event *event)
+static int fanotify_event_info_len(unsigned int fid_mode,
+				   struct fanotify_event *event)
 {
 	struct fanotify_info *info = fanotify_event_info(event);
 	int dir_fh_len = fanotify_event_dir_fh_len(event);
 	int fh_len = fanotify_event_object_fh_len(event);
 	int info_len = 0;
+	int dot_len = 0;
 
-	if (dir_fh_len)
+	if (dir_fh_len) {
 		info_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
+	} else if ((fid_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) {
+		/*
+		 * With group flag FAN_REPORT_NAME, if name was not recorded in
+		 * event on a directory, we will report the name ".".
+		 */
+		dot_len = 1;
+	}
 
 	if (fh_len)
-		info_len += fanotify_fid_info_len(fh_len, 0);
+		info_len += fanotify_fid_info_len(fh_len, dot_len);
 
 	return info_len;
 }
@@ -91,6 +100,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 {
 	size_t event_size = FAN_EVENT_METADATA_LEN;
 	struct fanotify_event *event = NULL;
+	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 
 	pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
 
@@ -98,8 +108,8 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 	if (fsnotify_notify_queue_is_empty(group))
 		goto out;
 
-	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
-		event_size += fanotify_event_info_len(
+	if (fid_mode) {
+		event_size += fanotify_event_info_len(fid_mode,
 			FANOTIFY_E(fsnotify_peek_first_event(group)));
 	}
 
@@ -325,7 +335,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
 	metadata.event_len = FAN_EVENT_METADATA_LEN +
-					fanotify_event_info_len(event);
+				fanotify_event_info_len(fid_mode, event);
 	metadata.metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata.vers = FANOTIFY_METADATA_VERSION;
 	metadata.reserved = 0;
@@ -374,12 +384,25 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	}
 
 	if (fanotify_event_object_fh_len(event)) {
+		const char *dot = NULL;
+		int dot_len = 0;
+
 		if (fid_mode == FAN_REPORT_FID || info_type) {
 			/*
 			 * With only group flag FAN_REPORT_FID only type FID is
 			 * reported. Second info record type is always FID.
 			 */
 			info_type = FAN_EVENT_INFO_TYPE_FID;
+		} else if ((fid_mode & FAN_REPORT_NAME) &&
+			   (event->mask & FAN_ONDIR)) {
+			/*
+			 * With group flag FAN_REPORT_NAME, if name was not
+			 * recorded in an event on a directory, report the
+			 * name "." with info type DFID_NAME.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
+			dot = ".";
+			dot_len = 1;
 		} else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
 			   (event->mask & FAN_ONDIR)) {
 			/*
@@ -400,7 +423,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
 		ret = copy_info_to_user(fanotify_event_fsid(event),
 					fanotify_event_object_fh(event),
-					info_type, NULL, 0, buf, count);
+					info_type, dot, dot_len, buf, count);
 		if (ret < 0)
 			return ret;
 
@@ -932,11 +955,15 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	if (fid_mode && class != FAN_CLASS_NOTIF)
 		return -EINVAL;
 
-	/* Reporting either object fid or dir fid */
+	/*
+	 * Reporting either object fid or dir fid.
+	 * Child name is reported with parent fid so requires dir fid.
+	 */
 	switch (fid_mode) {
 	case 0:
 	case FAN_REPORT_FID:
 	case FAN_REPORT_DIR_FID:
+	case FAN_REPORT_DFID_NAME:
 		break;
 	default:
 		return -EINVAL;
@@ -1294,7 +1321,7 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
  */
 static int __init fanotify_user_setup(void)
 {
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 9);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
 
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 4ddac97b2bf7..3e9c56ee651f 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -18,7 +18,7 @@
 #define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
 				 FAN_CLASS_PRE_CONTENT)
 
-#define FANOTIFY_FID_BITS	(FAN_REPORT_FID | FAN_REPORT_DIR_FID)
+#define FANOTIFY_FID_BITS	(FAN_REPORT_FID | FAN_REPORT_DFID_NAME)
 
 #define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \
 				 FAN_REPORT_TID | \
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index 21afebf77fd7..fbf9c5c7dd59 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -54,6 +54,10 @@
 #define FAN_REPORT_TID		0x00000100	/* event->pid is thread id */
 #define FAN_REPORT_FID		0x00000200	/* Report unique file id */
 #define FAN_REPORT_DIR_FID	0x00000400	/* Report unique directory id */
+#define FAN_REPORT_NAME		0x00000800	/* Report events with name */
+
+/* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */
+#define FAN_REPORT_DFID_NAME	(FAN_REPORT_DIR_FID | FAN_REPORT_NAME)
 
 /* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
-- 
cgit v1.2.3


From b9a1b9772509cbc6f6aa8bcd0b019f6347a2b631 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Jul 2020 15:58:48 +0300
Subject: fsnotify: create method handle_inode_event() in fsnotify_operations

The method handle_event() grew a lot of complexity due to the design of
fanotify and merging of ignore masks.

Most backends do not care about this complex functionality, so we can hide
this complexity from them.

Introduce a method handle_inode_event() that serves those backends and
passes a single inode mark and less arguments.

This change converts all backends except fanotify and inotify to use the
simplified handle_inode_event() method.  In pricipal, inotify could have
also used the new method, but that would require passing more arguments
on the simple helper (data, data_type, cookie), so we leave it with the
handle_event() method.

Link: https://lore.kernel.org/r/20200722125849.17418-9-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/nfsd/filecache.c              | 12 ++++------
 fs/notify/dnotify/dnotify.c      | 38 +++++++----------------------
 fs/notify/fsnotify.c             | 52 ++++++++++++++++++++++++++++++++++++++--
 include/linux/fsnotify_backend.h | 19 ++++++++++++---
 kernel/audit_fsnotify.c          | 20 +++++++---------
 kernel/audit_tree.c              | 10 ++++----
 kernel/audit_watch.c             | 17 ++++++-------
 7 files changed, 97 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index bbc7892d2928..c8b9d2667ee6 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -598,14 +598,10 @@ static struct notifier_block nfsd_file_lease_notifier = {
 };
 
 static int
-nfsd_file_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
-				const void *data, int data_type,
-				struct inode *dir,
-				const struct qstr *file_name, u32 cookie,
-				struct fsnotify_iter_info *iter_info)
+nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
+				struct inode *inode, struct inode *dir,
+				const struct qstr *name)
 {
-	struct inode *inode = fsnotify_data_inode(data, data_type);
-
 	trace_nfsd_file_fsnotify_handle_event(inode, mask);
 
 	/* Should be no marks on non-regular files */
@@ -626,7 +622,7 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
 
 
 static const struct fsnotify_ops nfsd_file_fsnotify_ops = {
-	.handle_event = nfsd_file_fsnotify_handle_event,
+	.handle_inode_event = nfsd_file_fsnotify_handle_event,
 	.free_mark = nfsd_file_mark_free,
 };
 
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index ca78d3f78da8..5dcda8f20c04 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -70,8 +70,9 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
  * destroy the dnotify struct if it was not registered to receive multiple
  * events.
  */
-static void dnotify_one_event(struct fsnotify_group *group, u32 mask,
-			      struct fsnotify_mark *inode_mark)
+static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				struct inode *inode, struct inode *dir,
+				const struct qstr *name)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
@@ -79,6 +80,10 @@ static void dnotify_one_event(struct fsnotify_group *group, u32 mask,
 	struct fown_struct *fown;
 	__u32 test_mask = mask & ~FS_EVENT_ON_CHILD;
 
+	/* not a dir, dnotify doesn't care */
+	if (!dir && !(mask & FS_ISDIR))
+		return 0;
+
 	dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark);
 
 	spin_lock(&inode_mark->lock);
@@ -100,33 +105,6 @@ static void dnotify_one_event(struct fsnotify_group *group, u32 mask,
 	}
 
 	spin_unlock(&inode_mark->lock);
-}
-
-static int dnotify_handle_event(struct fsnotify_group *group, u32 mask,
-				const void *data, int data_type,
-				struct inode *dir,
-				const struct qstr *file_name, u32 cookie,
-				struct fsnotify_iter_info *iter_info)
-{
-	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
-	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
-
-	/* not a dir, dnotify doesn't care */
-	if (!dir && !(mask & FS_ISDIR))
-		return 0;
-
-	if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
-		return 0;
-
-	/*
-	 * Some events can be sent on both parent dir and subdir marks
-	 * (e.g. DN_ATTRIB).  If both parent dir and subdir are watching,
-	 * report the event once to parent dir and once to subdir.
-	 */
-	if (inode_mark)
-		dnotify_one_event(group, mask, inode_mark);
-	if (child_mark)
-		dnotify_one_event(group, mask, child_mark);
 
 	return 0;
 }
@@ -143,7 +121,7 @@ static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
 }
 
 static const struct fsnotify_ops dnotify_fsnotify_ops = {
-	.handle_event = dnotify_handle_event,
+	.handle_inode_event = dnotify_handle_event,
 	.free_mark = dnotify_free_mark,
 };
 
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 494d5d70323f..a960ec3a569a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -230,6 +230,49 @@ notify:
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
+static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
+				 const void *data, int data_type,
+				 struct inode *dir, const struct qstr *name,
+				 u32 cookie, struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
+	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
+	struct inode *inode = fsnotify_data_inode(data, data_type);
+	const struct fsnotify_ops *ops = group->ops;
+	int ret;
+
+	if (WARN_ON_ONCE(!ops->handle_inode_event))
+		return 0;
+
+	if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
+	    WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
+		return 0;
+
+	/*
+	 * An event can be sent on child mark iterator instead of inode mark
+	 * iterator because of other groups that have interest of this inode
+	 * and have marks on both parent and child.  We can simplify this case.
+	 */
+	if (!inode_mark) {
+		inode_mark = child_mark;
+		child_mark = NULL;
+		dir = NULL;
+		name = NULL;
+	}
+
+	ret = ops->handle_inode_event(inode_mark, mask, inode, dir, name);
+	if (ret || !child_mark)
+		return ret;
+
+	/*
+	 * Some events can be sent on both parent dir and child marks
+	 * (e.g. FS_ATTRIB).  If both parent dir and child are watching,
+	 * report the event once to parent dir with name and once to child
+	 * without name.
+	 */
+	return ops->handle_inode_event(child_mark, mask, inode, NULL, NULL);
+}
+
 static int send_to_group(__u32 mask, const void *data, int data_type,
 			 struct inode *dir, const struct qstr *file_name,
 			 u32 cookie, struct fsnotify_iter_info *iter_info)
@@ -275,8 +318,13 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
 	if (!(test_mask & marks_mask & ~marks_ignored_mask))
 		return 0;
 
-	return group->ops->handle_event(group, mask, data, data_type, dir,
-					file_name, cookie, iter_info);
+	if (group->ops->handle_event) {
+		return group->ops->handle_event(group, mask, data, data_type, dir,
+						file_name, cookie, iter_info);
+	}
+
+	return fsnotify_handle_event(group, mask, data, data_type, dir,
+				     file_name, cookie, iter_info);
 }
 
 static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 32104cfc27a5..f8529a3a2923 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -128,17 +128,30 @@ struct mem_cgroup;
  * @cookie:	inotify rename cookie
  * @iter_info:	array of marks from this group that are interested in the event
  *
+ * handle_inode_event - simple variant of handle_event() for groups that only
+ *		have inode marks and don't have ignore mask
+ * @mark:	mark to notify
+ * @mask:	event type and flags
+ * @inode:	inode that event happened on
+ * @dir:	optional directory associated with event -
+ *		if @file_name is not NULL, this is the directory that
+ *		@file_name is relative to.
+ * @file_name:	optional file name associated with event
+ *
  * free_group_priv - called when a group refcnt hits 0 to clean up the private union
  * freeing_mark - called when a mark is being destroyed for some reason.  The group
- * 		MUST be holding a reference on each mark and that reference must be
- * 		dropped in this function.  inotify uses this function to send
- * 		userspace messages that marks have been removed.
+ *		MUST be holding a reference on each mark and that reference must be
+ *		dropped in this function.  inotify uses this function to send
+ *		userspace messages that marks have been removed.
  */
 struct fsnotify_ops {
 	int (*handle_event)(struct fsnotify_group *group, u32 mask,
 			    const void *data, int data_type, struct inode *dir,
 			    const struct qstr *file_name, u32 cookie,
 			    struct fsnotify_iter_info *iter_info);
+	int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask,
+			    struct inode *inode, struct inode *dir,
+			    const struct qstr *file_name);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
 	void (*free_event)(struct fsnotify_event *event);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index bd3a6b79316a..bfcfcd61adb6 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -152,35 +152,31 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark)
 }
 
 /* Update mark data in audit rules based on fsnotify events. */
-static int audit_mark_handle_event(struct fsnotify_group *group, u32 mask,
-				   const void *data, int data_type,
-				   struct inode *dir,
-				   const struct qstr *dname, u32 cookie,
-				   struct fsnotify_iter_info *iter_info)
+static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				   struct inode *inode, struct inode *dir,
+				   const struct qstr *dname)
 {
-	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct audit_fsnotify_mark *audit_mark;
-	const struct inode *inode = fsnotify_data_inode(data, data_type);
 
 	audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
 
-	BUG_ON(group != audit_fsnotify_group);
-
-	if (WARN_ON(!inode))
+	if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) ||
+	    WARN_ON_ONCE(!inode))
 		return 0;
 
 	if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {
 		if (audit_compare_dname_path(dname, audit_mark->path, AUDIT_NAME_FULL))
 			return 0;
 		audit_update_mark(audit_mark, inode);
-	} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF))
+	} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF)) {
 		audit_autoremove_mark_rule(audit_mark);
+	}
 
 	return 0;
 }
 
 static const struct fsnotify_ops audit_mark_fsnotify_ops = {
-	.handle_event =	audit_mark_handle_event,
+	.handle_inode_event = audit_mark_handle_event,
 	.free_mark = audit_fsnotify_free_mark,
 };
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 2ce2ac1ce100..025d24abf15d 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -1037,11 +1037,9 @@ static void evict_chunk(struct audit_chunk *chunk)
 		audit_schedule_prune();
 }
 
-static int audit_tree_handle_event(struct fsnotify_group *group, u32 mask,
-				   const void *data, int data_type,
-				   struct inode *dir,
-				   const struct qstr *file_name, u32 cookie,
-				   struct fsnotify_iter_info *iter_info)
+static int audit_tree_handle_event(struct fsnotify_mark *mark, u32 mask,
+				   struct inode *inode, struct inode *dir,
+				   const struct qstr *file_name)
 {
 	return 0;
 }
@@ -1070,7 +1068,7 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *mark,
 }
 
 static const struct fsnotify_ops audit_tree_ops = {
-	.handle_event = audit_tree_handle_event,
+	.handle_inode_event = audit_tree_handle_event,
 	.freeing_mark = audit_tree_freeing_mark,
 	.free_mark = audit_tree_destroy_watch,
 };
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index e23d54bcc587..246e5ba704c0 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -464,20 +464,17 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 }
 
 /* Update watch data in audit rules based on fsnotify events. */
-static int audit_watch_handle_event(struct fsnotify_group *group, u32 mask,
-				    const void *data, int data_type,
-				    struct inode *dir,
-				    const struct qstr *dname, u32 cookie,
-				    struct fsnotify_iter_info *iter_info)
+static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				    struct inode *inode, struct inode *dir,
+				    const struct qstr *dname)
 {
-	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
-	const struct inode *inode = fsnotify_data_inode(data, data_type);
 	struct audit_parent *parent;
 
 	parent = container_of(inode_mark, struct audit_parent, mark);
 
-	BUG_ON(group != audit_watch_group);
-	WARN_ON(!inode);
+	if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) ||
+	    WARN_ON_ONCE(!inode))
+		return 0;
 
 	if (mask & (FS_CREATE|FS_MOVED_TO) && inode)
 		audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0);
@@ -490,7 +487,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group, u32 mask,
 }
 
 static const struct fsnotify_ops audit_watch_fsnotify_ops = {
-	.handle_event = 	audit_watch_handle_event,
+	.handle_inode_event =	audit_watch_handle_event,
 	.free_mark =		audit_watch_free_mark,
 };
 
-- 
cgit v1.2.3


From c1b7b8d42b5422627b0a8268416a60748f8d000f Mon Sep 17 00:00:00 2001
From: 王文虎 <wenhu.wang@vivo.com>
Date: Mon, 27 Jul 2020 21:39:51 +0800
Subject: sched: Fix a typo in a comment

Change the comment typo: "direcly" -> "directly".

Signed-off-by: Wang Wenhu <wenhu.wang@vivo.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/AAcAXwBTDSpsKN-5iyIOtaqk.1.1595857191899.Hmail.wenhu.wang@vivo.com
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5033813fecd5..adf0125190d4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -374,7 +374,7 @@ struct util_est {
  * For cfs_rq, they are the aggregated values of all runnable and blocked
  * sched_entities.
  *
- * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU
  * capacity scaling. The scaling is done through the rq_clock_pelt that is used
  * for computing those signals (see update_rq_clock_pelt())
  *
-- 
cgit v1.2.3


From af60459a543483c5ad155a92daa8c3a6c00a0829 Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <chunyan.zhang@unisoc.com>
Date: Fri, 24 Jul 2020 20:21:47 +0800
Subject: math64: New DIV_S64_ROUND_CLOSEST helper

Provide DIV_S64_ROUND_CLOSEST helper which uses div_s64 to perform
division rounded to the closest integer using signed 64bit
dividend and signed 32bit divisor.

Signed-off-by: Chunyan Zhang <chunyan.zhang@unisoc.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 include/linux/math64.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/math64.h b/include/linux/math64.h
index 11a267413e8e..cd0693989436 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -279,4 +279,23 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 #define DIV64_U64_ROUND_CLOSEST(dividend, divisor)	\
 	({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); })
 
+/*
+ * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer
+ * @dividend: signed 64bit dividend
+ * @divisor: signed 32bit divisor
+ *
+ * Divide signed 64bit dividend by signed 32bit divisor
+ * and round to closest integer.
+ *
+ * Return: dividend / divisor rounded to nearest integer
+ */
+#define DIV_S64_ROUND_CLOSEST(dividend, divisor)(	\
+{							\
+	s64 __x = (dividend);				\
+	s32 __d = (divisor);				\
+	((__x > 0) == (__d > 0)) ?			\
+		div_s64((__x + (__d / 2)), __d) :	\
+		div_s64((__x - (__d / 2)), __d);	\
+}							\
+)
 #endif /* _LINUX_MATH64_H */
-- 
cgit v1.2.3


From 62b9825827518843f0f93dec6730ddcde14eb5b2 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@nxp.com>
Date: Mon, 17 Feb 2020 09:26:43 +0800
Subject: usb: chipidea: add query_available_role interface

The glue layer may need to know current available role to do some
setting, eg, the wakeup setting. So we add ci_hdrc_query_available_role
for that.

Signed-off-by: Peter Chen <peter.chen@nxp.com>
---
 drivers/usb/chipidea/core.c  | 27 +++++++++++++++++++++++++++
 include/linux/usb/chipidea.h |  2 ++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 9a7c53d09ab4..87ae3c8686a7 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -877,6 +877,33 @@ void ci_hdrc_remove_device(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(ci_hdrc_remove_device);
 
+/**
+ * ci_hdrc_query_available_role: get runtime available operation mode
+ *
+ * The glue layer can get current operation mode (host/peripheral/otg)
+ * This function should be called after ci core device has created.
+ *
+ * @pdev: the platform device of ci core.
+ *
+ * Return runtime usb_dr_mode.
+ */
+enum usb_dr_mode ci_hdrc_query_available_role(struct platform_device *pdev)
+{
+	struct ci_hdrc *ci = platform_get_drvdata(pdev);
+
+	if (!ci)
+		return USB_DR_MODE_UNKNOWN;
+	if (ci->roles[CI_ROLE_HOST] && ci->roles[CI_ROLE_GADGET])
+		return USB_DR_MODE_OTG;
+	else if (ci->roles[CI_ROLE_HOST])
+		return USB_DR_MODE_HOST;
+	else if (ci->roles[CI_ROLE_GADGET])
+		return USB_DR_MODE_PERIPHERAL;
+	else
+		return USB_DR_MODE_UNKNOWN;
+}
+EXPORT_SYMBOL_GPL(ci_hdrc_query_available_role);
+
 static inline void ci_role_destroy(struct ci_hdrc *ci)
 {
 	ci_hdrc_gadget_destroy(ci);
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index 54167a2d28ea..025b41687ce9 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -99,5 +99,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev,
 			struct ci_hdrc_platform_data *platdata);
 /* Remove ci hdrc device */
 void ci_hdrc_remove_device(struct platform_device *pdev);
+/* Get current available role */
+enum usb_dr_mode ci_hdrc_query_available_role(struct platform_device *pdev);
 
 #endif
-- 
cgit v1.2.3


From e885d5d94793ef342e49d55672baabbc16e32bb1 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 16 Jul 2020 16:36:50 +1000
Subject: lockdep: Move list.h inclusion into lockdep.h

Currently lockdep_types.h includes list.h without actually using any
of its macros or functions.  All it needs are the type definitions
which were moved into types.h long ago.  This potentially causes
inclusion loops because both are included by many core header
files.

This patch moves the list.h inclusion into lockdep.h.  Note that
we could probably remove it completely but that could potentially
result in compile failures should any end users not include list.h
directly and also be unlucky enough to not get list.h via some other
header file.

Reported-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Petr Mladek <pmladek@suse.com>
Link: https://lkml.kernel.org/r/20200716063649.GA23065@gondor.apana.org.au
---
 include/linux/lockdep.h       | 1 +
 include/linux/lockdep_types.h | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 3b73cf84f77d..b1ad5c045353 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -21,6 +21,7 @@ extern int lock_stat;
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
+#include <linux/list.h>
 #include <linux/debug_locks.h>
 #include <linux/stacktrace.h>
 
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 7b9350624577..bb35b449f533 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -32,8 +32,6 @@ enum lockdep_wait_type {
 
 #ifdef CONFIG_LOCKDEP
 
-#include <linux/list.h>
-
 /*
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
-- 
cgit v1.2.3


From d6945242f45d4745a8169fdab7afeb40f4e36f06 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 18 May 2020 11:13:52 +0300
Subject: net/mlx5: Hold pages RB tree per VF

Per page request event, FW request to allocated or release pages for a
single function. Driver maintains FW pages object per function, so there
is no need to hold one global page data-base. Instead, have a page
data-base per function, which will improve performance release flow in all
cases, especially for "release all pages".

As the range of function IDs is large and not sequential, use xarray to
store a per function ID page data-base, where the function ID is the key.

Upon first allocation of a page to a function ID, create the page
data-base per function. This data-base will be released only at pagealloc
mechanism cleanup.

NIC: ConnectX-4 Lx
CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
Test case: 32 VFs, measure release pages on one VF as part of FLR
Before: 0.021 Sec
After:  0.014 Sec

The improvement depends on amount of VFs and memory utilization
by them. Time measurements above were taken from idle system.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 142 +++++++++++++++------
 include/linux/mlx5/driver.h                        |   2 +-
 2 files changed, 105 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 5ddd18639a1e..1b20e3397dde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -35,6 +35,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mlx5/driver.h>
+#include <linux/xarray.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
@@ -73,15 +74,45 @@ enum {
 	MLX5_NUM_4K_IN_PAGE		= PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
 };
 
+static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func_id)
+{
+	struct rb_root *root;
+	int err;
+
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (root)
+		return root;
+
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		return ERR_PTR(-ENOMEM);
+
+	err = xa_insert(&dev->priv.page_root_xa, func_id, root, GFP_KERNEL);
+	if (err) {
+		kfree(root);
+		return ERR_PTR(err);
+	}
+
+	*root = RB_ROOT;
+
+	return root;
+}
+
 static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id)
 {
-	struct rb_root *root = &dev->priv.page_root;
-	struct rb_node **new = &root->rb_node;
 	struct rb_node *parent = NULL;
+	struct rb_root *root;
+	struct rb_node **new;
 	struct fw_page *nfp;
 	struct fw_page *tfp;
 	int i;
 
+	root = page_root_per_func_id(dev, func_id);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	new = &root->rb_node;
+
 	while (*new) {
 		parent = *new;
 		tfp = rb_entry(parent, struct fw_page, rb_node);
@@ -111,13 +142,20 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u
 	return 0;
 }
 
-static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr)
+static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr,
+				    u32 func_id)
 {
-	struct rb_root *root = &dev->priv.page_root;
-	struct rb_node *tmp = root->rb_node;
 	struct fw_page *result = NULL;
+	struct rb_root *root;
+	struct rb_node *tmp;
 	struct fw_page *tfp;
 
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return NULL;
+
+	tmp = root->rb_node;
+
 	while (tmp) {
 		tfp = rb_entry(tmp, struct fw_page, rb_node);
 		if (tfp->addr < addr) {
@@ -191,7 +229,13 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id)
 static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
 		     bool in_free_list)
 {
-	rb_erase(&fwp->rb_node, &dev->priv.page_root);
+	struct rb_root *root;
+
+	root = xa_load(&dev->priv.page_root_xa, fwp->func_id);
+	if (WARN_ON_ONCE(!root))
+		return;
+
+	rb_erase(&fwp->rb_node, root);
 	if (in_free_list)
 		list_del(&fwp->list);
 	dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
@@ -200,12 +244,12 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
 	kfree(fwp);
 }
 
-static void free_4k(struct mlx5_core_dev *dev, u64 addr)
+static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id)
 {
 	struct fw_page *fwp;
 	int n;
 
-	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, func_id);
 	if (!fwp) {
 		mlx5_core_warn_rl(dev, "page not found\n");
 		return;
@@ -340,7 +384,7 @@ retry:
 
 out_4k:
 	for (i--; i >= 0; i--)
-		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), func_id);
 out_free:
 	kvfree(in);
 	if (notify_fail)
@@ -351,16 +395,19 @@ out_free:
 static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 			      bool ec_function)
 {
+	struct rb_root *root;
 	struct rb_node *p;
 	int npages = 0;
 
-	p = rb_first(&dev->priv.page_root);
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return;
+
+	p = rb_first(root);
 	while (p) {
 		struct fw_page *fwp = rb_entry(p, struct fw_page, rb_node);
 
 		p = rb_next(p);
-		if (fwp->func_id != func_id)
-			continue;
 		npages += (MLX5_NUM_4K_IN_PAGE - fwp->free_count);
 		free_fwp(dev, fwp, fwp->free_count);
 	}
@@ -378,6 +425,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 			     u32 *in, int in_size, u32 *out, int out_size)
 {
+	struct rb_root *root;
 	struct fw_page *fwp;
 	struct rb_node *p;
 	u32 func_id;
@@ -391,12 +439,14 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 	npages = MLX5_GET(manage_pages_in, in, input_num_entries);
 	func_id = MLX5_GET(manage_pages_in, in, function_id);
 
-	p = rb_first(&dev->priv.page_root);
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return -EEXIST;
+
+	p = rb_first(root);
 	while (p && i < npages) {
 		fwp = rb_entry(p, struct fw_page, rb_node);
 		p = rb_next(p);
-		if (fwp->func_id != func_id)
-			continue;
 
 		MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr);
 		i++;
@@ -446,7 +496,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	}
 
 	for (i = 0; i < num_claimed; i++)
-		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), func_id);
 
 	if (nclaimed)
 		*nclaimed = num_claimed;
@@ -560,35 +610,49 @@ static int optimal_reclaimed_pages(void)
 	return ret;
 }
 
-int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
+static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev,
+				   struct rb_root *root, u16 func_id)
 {
 	unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
-	struct fw_page *fwp;
-	struct rb_node *p;
-	int nclaimed = 0;
-	int err = 0;
 
-	do {
-		p = rb_first(&dev->priv.page_root);
-		if (p) {
-			fwp = rb_entry(p, struct fw_page, rb_node);
-			err = reclaim_pages(dev, fwp->func_id,
-					    optimal_reclaimed_pages(),
-					    &nclaimed, mlx5_core_is_ecpf(dev));
-
-			if (err) {
-				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
-					       err);
-				return err;
-			}
-			if (nclaimed)
-				end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
+	while (!RB_EMPTY_ROOT(root)) {
+		int nclaimed;
+		int err;
+
+		err = reclaim_pages(dev, func_id, optimal_reclaimed_pages(),
+				    &nclaimed, mlx5_core_is_ecpf(dev));
+		if (err) {
+			mlx5_core_warn(dev, "failed reclaiming pages (%d) for func id 0x%x\n",
+				       err, func_id);
+			return err;
 		}
+
+		if (nclaimed)
+			end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
+
 		if (time_after(jiffies, end)) {
 			mlx5_core_warn(dev, "FW did not return all pages. giving up...\n");
 			break;
 		}
-	} while (p);
+	}
+
+	return 0;
+}
+
+int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
+{
+	struct rb_root *root;
+	unsigned long id;
+	void *entry;
+
+	xa_for_each(&dev->priv.page_root_xa, id, entry) {
+		root = entry;
+		mlx5_reclaim_root_pages(dev, root, id);
+		xa_erase(&dev->priv.page_root_xa, id);
+		kfree(root);
+	}
+
+	WARN_ON(!xa_empty(&dev->priv.page_root_xa));
 
 	WARN(dev->priv.fw_pages,
 	     "FW pages counter is %d after reclaiming all pages\n",
@@ -605,17 +669,19 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 
 int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 {
-	dev->priv.page_root = RB_ROOT;
 	INIT_LIST_HEAD(&dev->priv.free_list);
 	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
 	if (!dev->priv.pg_wq)
 		return -ENOMEM;
 
+	xa_init(&dev->priv.page_root_xa);
+
 	return 0;
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
 {
+	xa_destroy(&dev->priv.page_root_xa);
 	destroy_workqueue(dev->priv.pg_wq);
 }
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6a97ad601991..a0fcc4d13e93 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -541,7 +541,7 @@ struct mlx5_priv {
 	/* pages stuff */
 	struct mlx5_nb          pg_nb;
 	struct workqueue_struct *pg_wq;
-	struct rb_root		page_root;
+	struct xarray           page_root_xa;
 	int			fw_pages;
 	atomic_t		reg_pages;
 	struct list_head	free_list;
-- 
cgit v1.2.3


From d1718a1b7a86743b9c517bf9521695ba909c734f Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:03 +0100
Subject: ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic

iort_get_device_domain() is PCI specific but it need not be,
since it can be used to retrieve IRQ domain nexus of any kind
by adding an irq_domain_bus_token input to it.

Make it PCI agnostic by also renaming the requestor ID input
to a more generic ID name.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>   # pci/msi.c
Cc: Will Deacon <will@kernel.org>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Link: https://lore.kernel.org/r/20200619082013.13661-3-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/acpi/arm64/iort.c | 14 +++++++-------
 drivers/pci/msi.c         |  3 ++-
 include/linux/acpi_iort.h |  7 ++++---
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 5eee81758184..902e2aaca946 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -550,7 +550,6 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 		node = iort_get_iort_node(dev->fwnode);
 		if (node)
 			return node;
-
 		/*
 		 * if not, then it should be a platform device defined in
 		 * DSDT/SSDT (with Named Component node in IORT)
@@ -641,13 +640,13 @@ static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base)
 /**
  * iort_dev_find_its_id() - Find the ITS identifier for a device
  * @dev: The device.
- * @req_id: Device's requester ID
+ * @id: Device's ID
  * @idx: Index of the ITS identifier list.
  * @its_id: ITS identifier.
  *
  * Returns: 0 on success, appropriate error value otherwise
  */
-static int iort_dev_find_its_id(struct device *dev, u32 req_id,
+static int iort_dev_find_its_id(struct device *dev, u32 id,
 				unsigned int idx, int *its_id)
 {
 	struct acpi_iort_its_group *its;
@@ -657,7 +656,7 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
 	if (!node)
 		return -ENXIO;
 
-	node = iort_node_map_id(node, req_id, NULL, IORT_MSI_TYPE);
+	node = iort_node_map_id(node, id, NULL, IORT_MSI_TYPE);
 	if (!node)
 		return -ENXIO;
 
@@ -680,19 +679,20 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
  *
  * Returns: the MSI domain for this device, NULL otherwise
  */
-struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id)
+struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
+					  enum irq_domain_bus_token bus_token)
 {
 	struct fwnode_handle *handle;
 	int its_id;
 
-	if (iort_dev_find_its_id(dev, req_id, 0, &its_id))
+	if (iort_dev_find_its_id(dev, id, 0, &its_id))
 		return NULL;
 
 	handle = iort_find_domain_token(its_id);
 	if (!handle)
 		return NULL;
 
-	return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
+	return irq_find_matching_fwnode(handle, bus_token);
 }
 
 static void iort_set_device_domain(struct device *dev,
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 6b43a5455c7a..74a91f52ecc0 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1558,7 +1558,8 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
 	dom = of_msi_map_get_device_domain(&pdev->dev, rid);
 	if (!dom)
-		dom = iort_get_device_domain(&pdev->dev, rid);
+		dom = iort_get_device_domain(&pdev->dev, rid,
+					     DOMAIN_BUS_PCI_MSI);
 	return dom;
 }
 #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 8e7e2ec37f1b..08ec6bd2297f 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -29,7 +29,8 @@ struct fwnode_handle *iort_find_domain_token(int trans_id);
 #ifdef CONFIG_ACPI_IORT
 void acpi_iort_init(void);
 u32 iort_msi_map_rid(struct device *dev, u32 req_id);
-struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id);
+struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
+					  enum irq_domain_bus_token bus_token);
 void acpi_configure_pmsi_domain(struct device *dev);
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 /* IOMMU interface */
@@ -40,8 +41,8 @@ int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 static inline void acpi_iort_init(void) { }
 static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
 { return req_id; }
-static inline struct irq_domain *iort_get_device_domain(struct device *dev,
-							u32 req_id)
+static inline struct irq_domain *iort_get_device_domain(
+	struct device *dev, u32 id, enum irq_domain_bus_token bus_token)
 { return NULL; }
 static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
-- 
cgit v1.2.3


From 39c3cf566ceafa7c1ae331a5f26fbb685d670001 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:04 +0100
Subject: ACPI/IORT: Make iort_msi_map_rid() PCI agnostic

There is nothing PCI specific in iort_msi_map_rid().

Rename the function using a bus protocol agnostic name,
iort_msi_map_id(), and convert current callers to it.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Link: https://lore.kernel.org/r/20200619082013.13661-4-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/acpi/arm64/iort.c | 12 ++++++------
 drivers/pci/msi.c         |  2 +-
 include/linux/acpi_iort.h |  6 +++---
 3 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 902e2aaca946..53f9ef515089 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -568,22 +568,22 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 }
 
 /**
- * iort_msi_map_rid() - Map a MSI requester ID for a device
+ * iort_msi_map_id() - Map a MSI input ID for a device
  * @dev: The device for which the mapping is to be done.
- * @req_id: The device requester ID.
+ * @input_id: The device input ID.
  *
- * Returns: mapped MSI RID on success, input requester ID otherwise
+ * Returns: mapped MSI ID on success, input ID otherwise
  */
-u32 iort_msi_map_rid(struct device *dev, u32 req_id)
+u32 iort_msi_map_id(struct device *dev, u32 input_id)
 {
 	struct acpi_iort_node *node;
 	u32 dev_id;
 
 	node = iort_find_dev_node(dev);
 	if (!node)
-		return req_id;
+		return input_id;
 
-	iort_node_map_id(node, req_id, &dev_id, IORT_MSI_TYPE);
+	iort_node_map_id(node, input_id, &dev_id, IORT_MSI_TYPE);
 	return dev_id;
 }
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 74a91f52ecc0..77f48b95e277 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1536,7 +1536,7 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
 
 	of_node = irq_domain_get_of_node(domain);
 	rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) :
-			iort_msi_map_rid(&pdev->dev, rid);
+			iort_msi_map_id(&pdev->dev, rid);
 
 	return rid;
 }
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 08ec6bd2297f..e51425e083da 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -28,7 +28,7 @@ void iort_deregister_domain_token(int trans_id);
 struct fwnode_handle *iort_find_domain_token(int trans_id);
 #ifdef CONFIG_ACPI_IORT
 void acpi_iort_init(void);
-u32 iort_msi_map_rid(struct device *dev, u32 req_id);
+u32 iort_msi_map_id(struct device *dev, u32 id);
 struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
 					  enum irq_domain_bus_token bus_token);
 void acpi_configure_pmsi_domain(struct device *dev);
@@ -39,8 +39,8 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 #else
 static inline void acpi_iort_init(void) { }
-static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
-{ return req_id; }
+static inline u32 iort_msi_map_id(struct device *dev, u32 id)
+{ return id; }
 static inline struct irq_domain *iort_get_device_domain(
 	struct device *dev, u32 id, enum irq_domain_bus_token bus_token)
 { return NULL; }
-- 
cgit v1.2.3


From b8e069a2a8da02137605ba585837a3a0c45df01a Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:06 +0100
Subject: ACPI/IORT: Add an input ID to acpi_dma_configure()

Some HW devices are created as child devices of proprietary busses,
that have a bus specific policy defining how the child devices
wires representing the devices ID are translated into IOMMU and
IRQ controllers device IDs.

Current IORT code provides translations for:

- PCI devices, where the device ID is well identified at bus level
  as the requester ID (RID)
- Platform devices that are endpoint devices where the device ID is
  retrieved from the ACPI object IORT mappings (Named components single
  mappings). A platform device is represented in IORT as a named
  component node

For devices that are child devices of proprietary busses the IORT
firmware represents the bus node as a named component node in IORT
and it is up to that named component node to define in/out bus
specific ID translations for the bus child devices that are
allocated and created in a bus specific manner.

In order to make IORT ID translations available for proprietary
bus child devices, the current ACPI (and IORT) code must be
augmented to provide an additional ID parameter to acpi_dma_configure()
representing the child devices input ID. This ID is bus specific
and it is retrieved in bus specific code.

By adding an ID parameter to acpi_dma_configure(), the IORT
code can map the child device ID to an IOMMU stream ID through
the IORT named component representing the bus in/out ID mappings.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Link: https://lore.kernel.org/r/20200619082013.13661-6-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/acpi/arm64/iort.c | 59 +++++++++++++++++++++++++++++++++++------------
 drivers/acpi/scan.c       |  8 ++++---
 include/acpi/acpi_bus.h   |  9 ++++++--
 include/linux/acpi.h      |  7 ++++++
 include/linux/acpi_iort.h |  7 +++---
 5 files changed, 67 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 421c6976ab81..ec782e4a0fe4 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -978,19 +978,54 @@ static void iort_named_component_init(struct device *dev,
 					   nc->node_flags);
 }
 
+static int iort_nc_iommu_map(struct device *dev, struct acpi_iort_node *node)
+{
+	struct acpi_iort_node *parent;
+	int err = -ENODEV, i = 0;
+	u32 streamid = 0;
+
+	do {
+
+		parent = iort_node_map_platform_id(node, &streamid,
+						   IORT_IOMMU_TYPE,
+						   i++);
+
+		if (parent)
+			err = iort_iommu_xlate(dev, parent, streamid);
+	} while (parent && !err);
+
+	return err;
+}
+
+static int iort_nc_iommu_map_id(struct device *dev,
+				struct acpi_iort_node *node,
+				const u32 *in_id)
+{
+	struct acpi_iort_node *parent;
+	u32 streamid;
+
+	parent = iort_node_map_id(node, *in_id, &streamid, IORT_IOMMU_TYPE);
+	if (parent)
+		return iort_iommu_xlate(dev, parent, streamid);
+
+	return -ENODEV;
+}
+
+
 /**
- * iort_iommu_configure - Set-up IOMMU configuration for a device.
+ * iort_iommu_configure_id - Set-up IOMMU configuration for a device.
  *
  * @dev: device to configure
+ * @id_in: optional input id const value pointer
  *
  * Returns: iommu_ops pointer on configuration success
  *          NULL on configuration failure
  */
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *id_in)
 {
-	struct acpi_iort_node *node, *parent;
+	struct acpi_iort_node *node;
 	const struct iommu_ops *ops;
-	u32 streamid = 0;
 	int err = -ENODEV;
 
 	/*
@@ -1019,21 +1054,13 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 		if (fwspec && iort_pci_rc_supports_ats(node))
 			fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS;
 	} else {
-		int i = 0;
-
 		node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
 				      iort_match_node_callback, dev);
 		if (!node)
 			return NULL;
 
-		do {
-			parent = iort_node_map_platform_id(node, &streamid,
-							   IORT_IOMMU_TYPE,
-							   i++);
-
-			if (parent)
-				err = iort_iommu_xlate(dev, parent, streamid);
-		} while (parent && !err);
+		err = id_in ? iort_nc_iommu_map_id(dev, node, id_in) :
+			      iort_nc_iommu_map(dev, node);
 
 		if (!err)
 			iort_named_component_init(dev, node);
@@ -1058,6 +1085,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 
 	return ops;
 }
+
 #else
 static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev)
 { return NULL; }
@@ -1066,7 +1094,8 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
 { return 0; }
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 { return 0; }
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *input_id)
 { return NULL; }
 #endif
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 8777faced51a..2142f1554761 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1457,8 +1457,10 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
  * acpi_dma_configure - Set-up DMA configuration for the device.
  * @dev: The pointer to the device
  * @attr: device dma attributes
+ * @input_id: input device id const value pointer
  */
-int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
+int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
+			  const u32 *input_id)
 {
 	const struct iommu_ops *iommu;
 	u64 dma_addr = 0, size = 0;
@@ -1470,7 +1472,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 
 	iort_dma_setup(dev, &dma_addr, &size);
 
-	iommu = iort_iommu_configure(dev);
+	iommu = iort_iommu_configure_id(dev, input_id);
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
@@ -1479,7 +1481,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(acpi_dma_configure);
+EXPORT_SYMBOL_GPL(acpi_dma_configure_id);
 
 static void acpi_init_coherency(struct acpi_device *adev)
 {
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 5afb6ceb284f..a3abcc4b7d9f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -588,8 +588,13 @@ bool acpi_dma_supported(struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
 		       u64 *size);
-int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
-
+int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
+			   const u32 *input_id);
+static inline int acpi_dma_configure(struct device *dev,
+				     enum dev_dma_attr attr)
+{
+	return acpi_dma_configure_id(dev, attr, NULL);
+}
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
 					   u64 address, bool check_children);
 int acpi_is_root_bridge(acpi_handle);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d661cd0ee64d..6d2c47489d90 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -905,6 +905,13 @@ static inline int acpi_dma_configure(struct device *dev,
 	return 0;
 }
 
+static inline int acpi_dma_configure_id(struct device *dev,
+					enum dev_dma_attr attr,
+					const u32 *input_id)
+{
+	return 0;
+}
+
 #define ACPI_PTR(_ptr)	(NULL)
 
 static inline void acpi_device_set_enumerated(struct acpi_device *adev)
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index e51425e083da..20a32120bb88 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -35,7 +35,8 @@ void acpi_configure_pmsi_domain(struct device *dev);
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 /* IOMMU interface */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
-const struct iommu_ops *iort_iommu_configure(struct device *dev);
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 #else
 static inline void acpi_iort_init(void) { }
@@ -48,8 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
 static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 				  u64 *size) { }
-static inline const struct iommu_ops *iort_iommu_configure(
-				      struct device *dev)
+static inline const struct iommu_ops *iort_iommu_configure_id(
+				      struct device *dev, const u32 *id_in)
 { return NULL; }
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
-- 
cgit v1.2.3


From 746a71d02b5d15817fcb13c956ba999a87773952 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:07 +0100
Subject: of/iommu: Make of_map_rid() PCI agnostic

There is nothing PCI specific (other than the RID - requester ID)
in the of_map_rid() implementation, so the same function can be
reused for input/output IDs mapping for other busses just as well.

Rename the RID instances/names to a generic "id" tag.

No functionality change intended.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Joerg Roedel <jroedel@suse.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200619082013.13661-7-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/iommu/of_iommu.c |  4 ++--
 drivers/of/base.c        | 42 +++++++++++++++++++++---------------------
 drivers/of/irq.c         |  2 +-
 include/linux/of.h       |  4 ++--
 4 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 20738aacac89..016316244737 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -129,7 +129,7 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
 	struct of_phandle_args iommu_spec = { .args_count = 1 };
 	int err;
 
-	err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask",
+	err = of_map_id(info->np, alias, "iommu-map", "iommu-map-mask",
 			 &iommu_spec.np, iommu_spec.args);
 	if (err)
 		return err == -ENODEV ? NO_IOMMU : err;
@@ -145,7 +145,7 @@ static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev,
 	struct of_phandle_args iommu_spec = { .args_count = 1 };
 	int err;
 
-	err = of_map_rid(master_np, mc_dev->icid, "iommu-map",
+	err = of_map_id(master_np, mc_dev->icid, "iommu-map",
 			 "iommu-map-mask", &iommu_spec.np,
 			 iommu_spec.args);
 	if (err)
diff --git a/drivers/of/base.c b/drivers/of/base.c
index ae03b1218b06..ea44fea99813 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -2201,15 +2201,15 @@ int of_find_last_cache_level(unsigned int cpu)
 }
 
 /**
- * of_map_rid - Translate a requester ID through a downstream mapping.
+ * of_map_id - Translate an ID through a downstream mapping.
  * @np: root complex device node.
- * @rid: device requester ID to map.
+ * @id: device ID to map.
  * @map_name: property name of the map to use.
  * @map_mask_name: optional property name of the mask to use.
  * @target: optional pointer to a target device node.
  * @id_out: optional pointer to receive the translated ID.
  *
- * Given a device requester ID, look up the appropriate implementation-defined
+ * Given a device ID, look up the appropriate implementation-defined
  * platform ID and/or the target device which receives transactions on that
  * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
  * @id_out may be NULL if only the other is required. If @target points to
@@ -2219,11 +2219,11 @@ int of_find_last_cache_level(unsigned int cpu)
  *
  * Return: 0 on success or a standard error code on failure.
  */
-int of_map_rid(struct device_node *np, u32 rid,
+int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out)
 {
-	u32 map_mask, masked_rid;
+	u32 map_mask, masked_id;
 	int map_len;
 	const __be32 *map = NULL;
 
@@ -2235,7 +2235,7 @@ int of_map_rid(struct device_node *np, u32 rid,
 		if (target)
 			return -ENODEV;
 		/* Otherwise, no map implies no translation */
-		*id_out = rid;
+		*id_out = id;
 		return 0;
 	}
 
@@ -2255,22 +2255,22 @@ int of_map_rid(struct device_node *np, u32 rid,
 	if (map_mask_name)
 		of_property_read_u32(np, map_mask_name, &map_mask);
 
-	masked_rid = map_mask & rid;
+	masked_id = map_mask & id;
 	for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
 		struct device_node *phandle_node;
-		u32 rid_base = be32_to_cpup(map + 0);
+		u32 id_base = be32_to_cpup(map + 0);
 		u32 phandle = be32_to_cpup(map + 1);
 		u32 out_base = be32_to_cpup(map + 2);
-		u32 rid_len = be32_to_cpup(map + 3);
+		u32 id_len = be32_to_cpup(map + 3);
 
-		if (rid_base & ~map_mask) {
-			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
+		if (id_base & ~map_mask) {
+			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores id-base (0x%x)\n",
 				np, map_name, map_name,
-				map_mask, rid_base);
+				map_mask, id_base);
 			return -EFAULT;
 		}
 
-		if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
+		if (masked_id < id_base || masked_id >= id_base + id_len)
 			continue;
 
 		phandle_node = of_find_node_by_phandle(phandle);
@@ -2288,20 +2288,20 @@ int of_map_rid(struct device_node *np, u32 rid,
 		}
 
 		if (id_out)
-			*id_out = masked_rid - rid_base + out_base;
+			*id_out = masked_id - id_base + out_base;
 
-		pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
-			np, map_name, map_mask, rid_base, out_base,
-			rid_len, rid, masked_rid - rid_base + out_base);
+		pr_debug("%pOF: %s, using mask %08x, id-base: %08x, out-base: %08x, length: %08x, id: %08x -> %08x\n",
+			np, map_name, map_mask, id_base, out_base,
+			id_len, id, masked_id - id_base + out_base);
 		return 0;
 	}
 
-	pr_info("%pOF: no %s translation for rid 0x%x on %pOF\n", np, map_name,
-		rid, target && *target ? *target : NULL);
+	pr_info("%pOF: no %s translation for id 0x%x on %pOF\n", np, map_name,
+		id, target && *target ? *target : NULL);
 
 	/* Bypasses translation */
 	if (id_out)
-		*id_out = rid;
+		*id_out = id;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_map_rid);
+EXPORT_SYMBOL_GPL(of_map_id);
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index a296eaf52a5b..d632bc5b3a2d 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -587,7 +587,7 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 	 * "msi-map" property.
 	 */
 	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
-		if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map",
+		if (!of_map_id(parent_dev->of_node, rid_in, "msi-map",
 				"msi-map-mask", np, &rid_out))
 			break;
 	return rid_out;
diff --git a/include/linux/of.h b/include/linux/of.h
index c669c0a4732f..60abe3f636ad 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -554,7 +554,7 @@ bool of_console_check(struct device_node *dn, char *name, int index);
 
 extern int of_cpu_node_to_id(struct device_node *np);
 
-int of_map_rid(struct device_node *np, u32 rid,
+int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
@@ -978,7 +978,7 @@ static inline int of_cpu_node_to_id(struct device_node *np)
 	return -ENODEV;
 }
 
-static inline int of_map_rid(struct device_node *np, u32 rid,
+static inline int of_map_id(struct device_node *np, u32 id,
 			     const char *map_name, const char *map_mask_name,
 			     struct device_node **target, u32 *id_out)
 {
-- 
cgit v1.2.3


From a081bd4af4ce80d845a0bab355ab5d0822db8058 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:08 +0100
Subject: of/device: Add input id to of_dma_configure()

Devices sitting on proprietary busses have a device ID space that
is owned by the respective bus and related firmware bindings. In order
to let the generic OF layer handle the input translations to
an IOMMU id, for such busses the current of_dma_configure() interface
should be extended in order to allow the bus layer to provide the
device input id parameter - that is retrieved/assigned in bus
specific code and firmware.

Augment of_dma_configure() to add an optional input_id parameter,
leaving current functionality unchanged.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Link: https://lore.kernel.org/r/20200619082013.13661-8-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c |  4 +-
 drivers/iommu/of_iommu.c        | 81 ++++++++++++++++++++++-------------------
 drivers/of/device.c             |  8 ++--
 include/linux/of_device.h       | 16 +++++++-
 include/linux/of_iommu.h        |  6 ++-
 5 files changed, 70 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 40526da5c6a6..8ead3f0238f2 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -118,11 +118,13 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 static int fsl_mc_dma_configure(struct device *dev)
 {
 	struct device *dma_dev = dev;
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	u32 input_id = mc_dev->icid;
 
 	while (dev_is_fsl_mc(dma_dev))
 		dma_dev = dma_dev->parent;
 
-	return of_dma_configure(dev, dma_dev->of_node, 0);
+	return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
 }
 
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 016316244737..e505b9130a1c 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -118,46 +118,66 @@ static int of_iommu_xlate(struct device *dev,
 	return ret;
 }
 
-struct of_pci_iommu_alias_info {
-	struct device *dev;
-	struct device_node *np;
-};
-
-static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+static int of_iommu_configure_dev_id(struct device_node *master_np,
+				     struct device *dev,
+				     const u32 *id)
 {
-	struct of_pci_iommu_alias_info *info = data;
 	struct of_phandle_args iommu_spec = { .args_count = 1 };
 	int err;
 
-	err = of_map_id(info->np, alias, "iommu-map", "iommu-map-mask",
-			 &iommu_spec.np, iommu_spec.args);
+	err = of_map_id(master_np, *id, "iommu-map",
+			 "iommu-map-mask", &iommu_spec.np,
+			 iommu_spec.args);
 	if (err)
 		return err == -ENODEV ? NO_IOMMU : err;
 
-	err = of_iommu_xlate(info->dev, &iommu_spec);
+	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
 	return err;
 }
 
-static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev,
-				struct device_node *master_np)
+static int of_iommu_configure_dev(struct device_node *master_np,
+				  struct device *dev)
 {
-	struct of_phandle_args iommu_spec = { .args_count = 1 };
-	int err;
-
-	err = of_map_id(master_np, mc_dev->icid, "iommu-map",
-			 "iommu-map-mask", &iommu_spec.np,
-			 iommu_spec.args);
-	if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+	struct of_phandle_args iommu_spec;
+	int err = NO_IOMMU, idx = 0;
+
+	while (!of_parse_phandle_with_args(master_np, "iommus",
+					   "#iommu-cells",
+					   idx, &iommu_spec)) {
+		err = of_iommu_xlate(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+		idx++;
+		if (err)
+			break;
+	}
 
-	err = of_iommu_xlate(&mc_dev->dev, &iommu_spec);
-	of_node_put(iommu_spec.np);
 	return err;
 }
 
+struct of_pci_iommu_alias_info {
+	struct device *dev;
+	struct device_node *np;
+};
+
+static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct of_pci_iommu_alias_info *info = data;
+	u32 input_id = alias;
+
+	return of_iommu_configure_dev_id(info->np, info->dev, &input_id);
+}
+
+static int of_iommu_configure_device(struct device_node *master_np,
+				     struct device *dev, const u32 *id)
+{
+	return (id) ? of_iommu_configure_dev_id(master_np, dev, id) :
+		      of_iommu_configure_dev(master_np, dev);
+}
+
 const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np)
+					   struct device_node *master_np,
+					   const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
@@ -188,21 +208,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		pci_request_acs();
 		err = pci_for_each_dma_alias(to_pci_dev(dev),
 					     of_pci_iommu_init, &info);
-	} else if (dev_is_fsl_mc(dev)) {
-		err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np);
 	} else {
-		struct of_phandle_args iommu_spec;
-		int idx = 0;
-
-		while (!of_parse_phandle_with_args(master_np, "iommus",
-						   "#iommu-cells",
-						   idx, &iommu_spec)) {
-			err = of_iommu_xlate(dev, &iommu_spec);
-			of_node_put(iommu_spec.np);
-			idx++;
-			if (err)
-				break;
-		}
+		err = of_iommu_configure_device(master_np, dev, id);
 
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (!err && fwspec)
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 27203bfd0b22..b439c1e05434 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -78,6 +78,7 @@ int of_device_add(struct platform_device *ofdev)
  * @np:		Pointer to OF node having DMA configuration
  * @force_dma:  Whether device is to be set up by of_dma_configure() even if
  *		DMA capability is not explicitly described by firmware.
+ * @id:		Optional const pointer value input id
  *
  * Try to get devices's DMA configuration from DT and update it
  * accordingly.
@@ -86,7 +87,8 @@ int of_device_add(struct platform_device *ofdev)
  * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
  * to fix up DMA configuration.
  */
-int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
+int of_dma_configure_id(struct device *dev, struct device_node *np,
+			bool force_dma, const u32 *id)
 {
 	u64 dma_addr, paddr, size = 0;
 	int ret;
@@ -160,7 +162,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np);
+	iommu = of_iommu_configure(dev, np, id);
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
@@ -171,7 +173,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_dma_configure);
+EXPORT_SYMBOL_GPL(of_dma_configure_id);
 
 int of_device_register(struct platform_device *pdev)
 {
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8d31e39dd564..07ca187fc5e4 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -55,9 +55,15 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-int of_dma_configure(struct device *dev,
+int of_dma_configure_id(struct device *dev,
 		     struct device_node *np,
-		     bool force_dma);
+		     bool force_dma, const u32 *id);
+static inline int of_dma_configure(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return of_dma_configure_id(dev, np, force_dma, NULL);
+}
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -106,6 +112,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return NULL;
 }
 
+static inline int of_dma_configure_id(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return 0;
+}
 static inline int of_dma_configure(struct device *dev,
 				   struct device_node *np,
 				   bool force_dma)
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index f3d40dd7bb66..16f4b3e87f20 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -13,7 +13,8 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     size_t *size);
 
 extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np);
+					struct device_node *master_np,
+					const u32 *id);
 
 #else
 
@@ -25,7 +26,8 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 }
 
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np)
+					 struct device_node *master_np,
+					 const u32 *id)
 {
 	return NULL;
 }
-- 
cgit v1.2.3


From 6f881aba01109a01a43e4f135673c19190f61133 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Fri, 19 Jun 2020 09:20:10 +0100
Subject: of/irq: make of_msi_map_get_device_domain() bus agnostic

of_msi_map_get_device_domain() is PCI specific but it need not be and
can be easily changed to be bus agnostic in order to be used by other
busses by adding an IRQ domain bus token as an input parameter.

Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>   # pci/msi.c
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200619082013.13661-10-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/irq.c       | 8 +++++---
 drivers/pci/msi.c      | 2 +-
 include/linux/of_irq.h | 5 +++--
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index d632bc5b3a2d..1005e4f349ef 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -613,18 +613,20 @@ u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in)
  * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain
  * @dev: device for which the mapping is to be done.
  * @rid: Requester ID for the device.
+ * @bus_token: Bus token
  *
  * Walk up the device hierarchy looking for devices with a "msi-map"
  * property.
  *
  * Returns: the MSI domain for this device (or NULL on failure)
  */
-struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid)
+struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id,
+						u32 bus_token)
 {
 	struct device_node *np = NULL;
 
-	__of_msi_map_rid(dev, &np, rid);
-	return irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI);
+	__of_msi_map_rid(dev, &np, id);
+	return irq_find_matching_host(np, bus_token);
 }
 
 /**
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 77f48b95e277..b4bfe0b03b2d 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1556,7 +1556,7 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 	u32 rid = pci_dev_id(pdev);
 
 	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
-	dom = of_msi_map_get_device_domain(&pdev->dev, rid);
+	dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI);
 	if (!dom)
 		dom = iort_get_device_domain(&pdev->dev, rid,
 					     DOMAIN_BUS_PCI_MSI);
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 1214cabb2247..7142a3722758 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -52,7 +52,8 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev,
 					    struct device_node *np,
 					    enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-						       u32 rid);
+							u32 id,
+							u32 bus_token);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
 u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 #else
@@ -85,7 +86,7 @@ static inline struct irq_domain *of_msi_get_domain(struct device *dev,
 	return NULL;
 }
 static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-							      u32 rid)
+						u32 id, u32 bus_token)
 {
 	return NULL;
 }
-- 
cgit v1.2.3


From 2bcdd8f2c07f1aa1bfd34fa0dab8e06949e34846 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 19 Jun 2020 09:20:11 +0100
Subject: of/irq: Make of_msi_map_rid() PCI bus agnostic

There is nothing PCI bus specific in the of_msi_map_rid()
implementation other than the requester ID tag for the input
ID space. Rename requester ID to a more generic ID so that
the translation code can be used by all busses that require
input/output ID translations.

No functional change intended.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200619082013.13661-11-lorenzo.pieralisi@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/irq.c       | 28 ++++++++++++++--------------
 drivers/pci/msi.c      |  2 +-
 include/linux/of_irq.h |  8 ++++----
 3 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 1005e4f349ef..25d17b8a1a1a 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -576,43 +576,43 @@ err:
 	}
 }
 
-static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
-			    u32 rid_in)
+static u32 __of_msi_map_id(struct device *dev, struct device_node **np,
+			    u32 id_in)
 {
 	struct device *parent_dev;
-	u32 rid_out = rid_in;
+	u32 id_out = id_in;
 
 	/*
 	 * Walk up the device parent links looking for one with a
 	 * "msi-map" property.
 	 */
 	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
-		if (!of_map_id(parent_dev->of_node, rid_in, "msi-map",
-				"msi-map-mask", np, &rid_out))
+		if (!of_map_id(parent_dev->of_node, id_in, "msi-map",
+				"msi-map-mask", np, &id_out))
 			break;
-	return rid_out;
+	return id_out;
 }
 
 /**
- * of_msi_map_rid - Map a MSI requester ID for a device.
+ * of_msi_map_id - Map a MSI ID for a device.
  * @dev: device for which the mapping is to be done.
  * @msi_np: device node of the expected msi controller.
- * @rid_in: unmapped MSI requester ID for the device.
+ * @id_in: unmapped MSI ID for the device.
  *
  * Walk up the device hierarchy looking for devices with a "msi-map"
- * property.  If found, apply the mapping to @rid_in.
+ * property.  If found, apply the mapping to @id_in.
  *
- * Returns the mapped MSI requester ID.
+ * Returns the mapped MSI ID.
  */
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in)
+u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in)
 {
-	return __of_msi_map_rid(dev, &msi_np, rid_in);
+	return __of_msi_map_id(dev, &msi_np, id_in);
 }
 
 /**
  * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain
  * @dev: device for which the mapping is to be done.
- * @rid: Requester ID for the device.
+ * @id: Device ID.
  * @bus_token: Bus token
  *
  * Walk up the device hierarchy looking for devices with a "msi-map"
@@ -625,7 +625,7 @@ struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id,
 {
 	struct device_node *np = NULL;
 
-	__of_msi_map_rid(dev, &np, id);
+	__of_msi_map_id(dev, &np, id);
 	return irq_find_matching_host(np, bus_token);
 }
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index b4bfe0b03b2d..19aeadb22f11 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1535,7 +1535,7 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
 	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
 
 	of_node = irq_domain_get_of_node(domain);
-	rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) :
+	rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) :
 			iort_msi_map_id(&pdev->dev, rid);
 
 	return rid;
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 7142a3722758..e8b78139f78c 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -55,7 +55,7 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
 							u32 id,
 							u32 bus_token);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
+u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -93,10 +93,10 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
-static inline u32 of_msi_map_rid(struct device *dev,
-				 struct device_node *msi_np, u32 rid_in)
+static inline u32 of_msi_map_id(struct device *dev,
+				 struct device_node *msi_np, u32 id_in)
 {
-	return rid_in;
+	return id_in;
 }
 #endif
 
-- 
cgit v1.2.3


From 0516c2f6ae6570a0c4a081189d71a48cfadc34a7 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Tue, 28 Jul 2020 18:20:36 +0200
Subject: block: Remove callback typedefs for blk_mq_ops

No need to define typedefs for the callbacks, because there is not a
single user except blk_mq_ops.

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 50 ++++++++++++++++++--------------------------------
 1 file changed, 18 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 23230c1d031e..9d2d5ad367a4 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -267,27 +267,9 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *,
-		const struct blk_mq_queue_data *);
-typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *);
-typedef bool (get_budget_fn)(struct request_queue *);
-typedef void (put_budget_fn)(struct request_queue *);
-typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
-typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
-typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
-typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *,
-		unsigned int, unsigned int);
-typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *,
-		unsigned int);
-
 typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
 typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
-typedef int (poll_fn)(struct blk_mq_hw_ctx *);
-typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
-typedef bool (busy_fn)(struct request_queue *);
-typedef void (complete_fn)(struct request *);
-typedef void (cleanup_rq_fn)(struct request *);
 
 /**
  * struct blk_mq_ops - Callback functions that implements block driver
@@ -297,7 +279,8 @@ struct blk_mq_ops {
 	/**
 	 * @queue_rq: Queue a new request from block IO.
 	 */
-	queue_rq_fn		*queue_rq;
+	blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *,
+				 const struct blk_mq_queue_data *);
 
 	/**
 	 * @commit_rqs: If a driver uses bd->last to judge when to submit
@@ -306,7 +289,7 @@ struct blk_mq_ops {
 	 * purpose of kicking the hardware (which the last request otherwise
 	 * would have done).
 	 */
-	commit_rqs_fn		*commit_rqs;
+	void (*commit_rqs)(struct blk_mq_hw_ctx *);
 
 	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
@@ -314,37 +297,38 @@ struct blk_mq_ops {
 	 * reserved budget. Also we have to handle failure case
 	 * of .get_budget for avoiding I/O deadlock.
 	 */
-	get_budget_fn		*get_budget;
+	bool (*get_budget)(struct request_queue *);
+
 	/**
 	 * @put_budget: Release the reserved budget.
 	 */
-	put_budget_fn		*put_budget;
+	void (*put_budget)(struct request_queue *);
 
 	/**
 	 * @timeout: Called on request timeout.
 	 */
-	timeout_fn		*timeout;
+	enum blk_eh_timer_return (*timeout)(struct request *, bool);
 
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
 	 */
-	poll_fn			*poll;
+	int (*poll)(struct blk_mq_hw_ctx *);
 
 	/**
 	 * @complete: Mark the request as complete.
 	 */
-	complete_fn		*complete;
+	void (*complete)(struct request *);
 
 	/**
 	 * @init_hctx: Called when the block layer side of a hardware queue has
 	 * been set up, allowing the driver to allocate/init matching
 	 * structures.
 	 */
-	init_hctx_fn		*init_hctx;
+	int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int);
 	/**
 	 * @exit_hctx: Ditto for exit/teardown.
 	 */
-	exit_hctx_fn		*exit_hctx;
+	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 
 	/**
 	 * @init_request: Called for every command allocated by the block layer
@@ -353,11 +337,13 @@ struct blk_mq_ops {
 	 * Tag greater than or equal to queue_depth is for setting up
 	 * flush request.
 	 */
-	init_request_fn		*init_request;
+	int (*init_request)(struct blk_mq_tag_set *set, struct request *,
+			    unsigned int, unsigned int);
 	/**
 	 * @exit_request: Ditto for exit/teardown.
 	 */
-	exit_request_fn		*exit_request;
+	void (*exit_request)(struct blk_mq_tag_set *set, struct request *,
+			     unsigned int);
 
 	/**
 	 * @initialize_rq_fn: Called from inside blk_get_request().
@@ -368,18 +354,18 @@ struct blk_mq_ops {
 	 * @cleanup_rq: Called before freeing one request which isn't completed
 	 * yet, and usually for freeing the driver private data.
 	 */
-	cleanup_rq_fn		*cleanup_rq;
+	void (*cleanup_rq)(struct request *);
 
 	/**
 	 * @busy: If set, returns whether or not this queue currently is busy.
 	 */
-	busy_fn			*busy;
+	bool (*busy)(struct request_queue *);
 
 	/**
 	 * @map_queues: This allows drivers specify their own queue mapping by
 	 * overriding the setup-time function that builds the mq_map.
 	 */
-	map_queues_fn		*map_queues;
+	int (*map_queues)(struct blk_mq_tag_set *set);
 
 #ifdef CONFIG_BLK_DEBUG_FS
 	/**
-- 
cgit v1.2.3


From 5143192cd410c4fc83be09a2e73423765aee072b Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Thu, 23 Jul 2020 15:30:00 -0700
Subject: mm/migrate: add a flags parameter to migrate_vma

The src_owner field in struct migrate_vma is being used for two purposes,
it acts as a selection filter for which types of pages are to be migrated
and it identifies device private pages owned by the caller.

Split this into separate parameters so the src_owner field can be used
just to identify device private pages owned by the caller of
migrate_vma_setup().

Rename the src_owner field to pgmap_owner to reflect it is now used only
to identify which device private pages to migrate.

Link: https://lore.kernel.org/r/20200723223004.9586-3-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     |  4 +++-
 drivers/gpu/drm/nouveau/nouveau_dmem.c |  4 +++-
 include/linux/migrate.h                | 13 +++++++++----
 lib/test_hmm.c                         | 15 ++++-----------
 mm/migrate.c                           |  6 ++++--
 5 files changed, 23 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 09d8119024db..6850bd04bcb9 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -400,6 +400,7 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 	mig.end = end;
 	mig.src = &src_pfn;
 	mig.dst = &dst_pfn;
+	mig.flags = MIGRATE_VMA_SELECT_SYSTEM;
 
 	/*
 	 * We come here with mmap_lock write lock held just for
@@ -577,7 +578,8 @@ kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
 	mig.end = end;
 	mig.src = &src_pfn;
 	mig.dst = &dst_pfn;
-	mig.src_owner = &kvmppc_uvmem_pgmap;
+	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
+	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
 	/* The requested page is already paged-out, nothing to do */
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index e5c230d9ae24..78b9e3c2a5b3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -182,7 +182,8 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 		.end		= vmf->address + PAGE_SIZE,
 		.src		= &src,
 		.dst		= &dst,
-		.src_owner	= drm->dev,
+		.pgmap_owner	= drm->dev,
+		.flags		= MIGRATE_VMA_SELECT_DEVICE_PRIVATE,
 	};
 
 	/*
@@ -615,6 +616,7 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 	struct migrate_vma args = {
 		.vma		= vma,
 		.start		= start,
+		.flags		= MIGRATE_VMA_SELECT_SYSTEM,
 	};
 	unsigned long i;
 	u64 *pfns;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 3e546cbf03dd..16e03a51e5cf 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -180,6 +180,11 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
 	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
 }
 
+enum migrate_vma_direction {
+	MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
+	MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
+};
+
 struct migrate_vma {
 	struct vm_area_struct	*vma;
 	/*
@@ -199,11 +204,11 @@ struct migrate_vma {
 
 	/*
 	 * Set to the owner value also stored in page->pgmap->owner for
-	 * migrating out of device private memory.  If set only device
-	 * private pages with this owner are migrated.  If not set
-	 * device private pages are not migrated at all.
+	 * migrating out of device private memory. The flags also need to
+	 * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
 	 */
-	void			*src_owner;
+	void			*pgmap_owner;
+	unsigned long		flags;
 };
 
 int migrate_vma_setup(struct migrate_vma *args);
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 9aa577afc269..e78a1414f58e 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -585,15 +585,6 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 */
 		spage = migrate_pfn_to_page(*src);
 
-		/*
-		 * Don't migrate device private pages from our own driver or
-		 * others. For our own we would do a device private memory copy
-		 * not a migration and for others, we would need to fault the
-		 * other device's page into system memory first.
-		 */
-		if (spage && is_zone_device_page(spage))
-			continue;
-
 		dpage = dmirror_devmem_alloc_page(mdevice);
 		if (!dpage)
 			continue;
@@ -702,7 +693,8 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		args.dst = dst_pfns;
 		args.start = addr;
 		args.end = next;
-		args.src_owner = NULL;
+		args.pgmap_owner = NULL;
+		args.flags = MIGRATE_VMA_SELECT_SYSTEM;
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out;
@@ -1053,7 +1045,8 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	args.end = args.start + PAGE_SIZE;
 	args.src = &src_pfns;
 	args.dst = &dst_pfns;
-	args.src_owner = dmirror->mdevice;
+	args.pgmap_owner = dmirror->mdevice;
+	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
diff --git a/mm/migrate.c b/mm/migrate.c
index f37729673558..e3ea68e3a08b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2287,7 +2287,9 @@ again:
 				goto next;
 
 			page = device_private_entry_to_page(entry);
-			if (page->pgmap->owner != migrate->src_owner)
+			if (!(migrate->flags &
+				MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
+			    page->pgmap->owner != migrate->pgmap_owner)
 				goto next;
 
 			mpfn = migrate_pfn(page_to_pfn(page)) |
@@ -2295,7 +2297,7 @@ again:
 			if (is_write_device_private_entry(entry))
 				mpfn |= MIGRATE_PFN_WRITE;
 		} else {
-			if (migrate->src_owner)
+			if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))
 				goto next;
 			pfn = pte_pfn(pte);
 			if (is_zero_pfn(pfn)) {
-- 
cgit v1.2.3


From 998427b3ad2c769082853880cf353557ec0ec77d Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Thu, 23 Jul 2020 15:30:01 -0700
Subject: mm/notifier: add migration invalidation type

Currently migrate_vma_setup() calls mmu_notifier_invalidate_range_start()
which flushes all device private page mappings whether or not a page is
being migrated to/from device private memory.

In order to not disrupt device mappings that are not being migrated, shift
the responsibility for clearing device private mappings to the device
driver and leave CPU page table unmapping handled by
migrate_vma_setup().

To support this, the caller of migrate_vma_setup() should always set
struct migrate_vma::pgmap_owner to a non NULL value that matches the
device private page->pgmap->owner. This value is then passed to the struct
mmu_notifier_range with a new event type which the driver's invalidation
function can use to avoid device MMU invalidations.

Link: https://lore.kernel.org/r/20200723223004.9586-4-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/migrate.h      | 3 +++
 include/linux/mmu_notifier.h | 6 ++++++
 mm/migrate.c                 | 8 +++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 16e03a51e5cf..540998d9810b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -206,6 +206,9 @@ struct migrate_vma {
 	 * Set to the owner value also stored in page->pgmap->owner for
 	 * migrating out of device private memory. The flags also need to
 	 * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
+	 * The caller should always set this field when using mmu notifier
+	 * callbacks to avoid device MMU invalidations for device private
+	 * pages that are not being migrated.
 	 */
 	void			*pgmap_owner;
 	unsigned long		flags;
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index fc68f3570e19..c6f0708195cd 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -38,6 +38,10 @@ struct mmu_interval_notifier;
  *
  * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
  * that the mm refcount is zero and the range is no longer accessible.
+ *
+ * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal
+ * a device driver to possibly ignore the invalidation if the
+ * migrate_pgmap_owner field matches the driver's device private pgmap owner.
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,
@@ -46,6 +50,7 @@ enum mmu_notifier_event {
 	MMU_NOTIFY_PROTECTION_PAGE,
 	MMU_NOTIFY_SOFT_DIRTY,
 	MMU_NOTIFY_RELEASE,
+	MMU_NOTIFY_MIGRATE,
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
@@ -264,6 +269,7 @@ struct mmu_notifier_range {
 	unsigned long end;
 	unsigned flags;
 	enum mmu_notifier_event event;
+	void *migrate_pgmap_owner;
 };
 
 static inline int mm_has_notifiers(struct mm_struct *mm)
diff --git a/mm/migrate.c b/mm/migrate.c
index e3ea68e3a08b..96e1f41a991e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2392,8 +2392,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
 {
 	struct mmu_notifier_range range;
 
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL,
+	/*
+	 * Note that the pgmap_owner is passed to the mmu notifier callback so
+	 * that the registered device driver can skip invalidating device
+	 * private page mappings that won't be migrated.
+	 */
+	mmu_notifier_range_init(&range, MMU_NOTIFY_MIGRATE, 0, migrate->vma,
 			migrate->vma->vm_mm, migrate->start, migrate->end);
+	range.migrate_pgmap_owner = migrate->pgmap_owner;
 	mmu_notifier_invalidate_range_start(&range);
 
 	walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
-- 
cgit v1.2.3


From 7d0314b11cdd92bca8b89684c06953bf114605fc Mon Sep 17 00:00:00 2001
From: Ron Diskin <rondi@mellanox.com>
Date: Sun, 5 Apr 2020 13:58:40 +0300
Subject: net/mlx5e: Modify uplink state on interface up/down

When setting the PF interface up/down, notify the firmware to update
uplink state via MODIFY_VPORT_STATE, when E-Switch is enabled.

This behavior will prevent sending traffic out on uplink port when PF is
down, such as sending traffic from a VF interface which is still up.
Currently when calling mlx5e_open/close(), the driver only sends PAOS
command to notify the firmware to set the physical port state to
up/down, however, it is not sufficient. When VF is in "auto" state, it
follows the uplink state, which was not updated on mlx5e_open/close()
before this patch.

When switchdev mode is enabled and uplink representor is first enabled,
set the uplink port state value back to its FW default "AUTO".

Fixes: 63bfd399de55 ("net/mlx5e: Send PAOS command on interface up/down")
Signed-off-by: Ron Diskin <rondi@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 25 ++++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 16 +++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h |  2 ++
 include/linux/mlx5/mlx5_ifc.h                     |  1 +
 5 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 31f9ecae98df..07fdbea7ea13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3069,6 +3069,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
 }
 
+static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
+				     enum mlx5_port_status state)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int vport_admin_state;
+
+	mlx5_set_port_admin_status(mdev, state);
+
+	if (!MLX5_ESWITCH_MANAGER(mdev) ||  mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS)
+		return;
+
+	if (state == MLX5_PORT_UP)
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	else
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
+	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
+}
+
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3101,7 +3120,7 @@ int mlx5e_open(struct net_device *netdev)
 	mutex_lock(&priv->state_lock);
 	err = mlx5e_open_locked(netdev);
 	if (!err)
-		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
+		mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
 	return err;
@@ -3135,7 +3154,7 @@ int mlx5e_close(struct net_device *netdev)
 		return -ENODEV;
 
 	mutex_lock(&priv->state_lock);
-	mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN);
+	mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN);
 	err = mlx5e_close_locked(netdev);
 	mutex_unlock(&priv->state_lock);
 
@@ -5182,7 +5201,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	/* Marking the link as currently not needed by the Driver */
 	if (!netif_running(netdev))
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
+		mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN);
 
 	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 8c294ab43f90..9519a61bd8ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1081,6 +1081,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 
 	mlx5e_rep_tc_enable(priv);
 
+	mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
+				      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d9376627584e..71d01143c455 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1826,6 +1826,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 				 u16 vport, int link_state)
 {
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT;
+	int other_vport = 1;
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
@@ -1833,15 +1835,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 	if (IS_ERR(evport))
 		return PTR_ERR(evport);
 
+	if (vport == MLX5_VPORT_UPLINK) {
+		opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK;
+		other_vport = 0;
+		vport = 0;
+	}
 	mutex_lock(&esw->state_lock);
 
-	err = mlx5_modify_vport_admin_state(esw->dev,
-					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					    vport, 1, link_state);
+	err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state);
 	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "Failed to set vport %d link state, err = %d",
-			       vport, err);
+		mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d",
+			       vport, opmod, err);
 		goto unlock;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a5175e98c0b3..5785596f13f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -680,6 +680,8 @@ static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { r
 static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {}
 static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
+static inline
+int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; }
 static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 {
 	return ERR_PTR(-EOPNOTSUPP);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 073b79eacc99..1340e02b14ef 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -4381,6 +4381,7 @@ struct mlx5_ifc_query_vport_state_out_bits {
 enum {
 	MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT  = 0x0,
 	MLX5_VPORT_STATE_OP_MOD_ESW_VPORT   = 0x1,
+	MLX5_VPORT_STATE_OP_MOD_UPLINK      = 0x2,
 };
 
 struct mlx5_ifc_arm_monitor_counter_in_bits {
-- 
cgit v1.2.3


From 035bfd051eae5b365368be915dfaf916aa501a52 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 28 Jul 2020 18:38:34 +0200
Subject: net: make sockptr_is_null strict aliasing safe

While the kernel in general is not strict aliasing safe we can trivially
do that in sockptr_is_null without affecting code generation, so always
check the actually assigned union member.

Reported-by: Jan Engelhardt <jengelh@inai.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockptr.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 7d5cdb2b30b5..b13ea1422f93 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -64,7 +64,9 @@ static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p)
 
 static inline bool sockptr_is_null(sockptr_t sockptr)
 {
-	return !sockptr.user && !sockptr.kernel;
+	if (sockptr_is_kernel(sockptr))
+		return !sockptr.kernel;
+	return !sockptr.user;
 }
 
 static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
-- 
cgit v1.2.3


From d3c48151512922dd35f1f393b30b9138e4441d14 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 28 Jul 2020 18:38:35 +0200
Subject: net: remove sockptr_advance

sockptr_advance never properly worked.  Replace it with _offset variants
of copy_from_sockptr and copy_to_sockptr.

Fixes: ba423fdaa589 ("net: add a new sockptr_t type")
Reported-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/chelsio/chtls/chtls_main.c | 12 ++++++------
 include/linux/sockptr.h                   | 27 +++++++++++++--------------
 net/dccp/proto.c                          |  5 ++---
 net/ipv4/netfilter/arp_tables.c           |  8 ++++----
 net/ipv4/netfilter/ip_tables.c            |  8 ++++----
 net/ipv4/tcp.c                            |  5 +++--
 net/ipv6/ip6_flowlabel.c                  | 11 ++++++-----
 net/ipv6/netfilter/ip6_tables.c           |  8 ++++----
 net/netfilter/x_tables.c                  |  7 ++++---
 net/tls/tls_main.c                        |  6 +++---
 10 files changed, 49 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index c3058dcdb33c..66d247efd561 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -525,9 +525,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 		/* Obtain version and type from previous copy */
 		crypto_info[0] = tmp_crypto_info;
 		/* Now copy the following data */
-		sockptr_advance(optval, sizeof(*crypto_info));
-		rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info),
-				optval,
+		rc = copy_from_sockptr_offset((char *)crypto_info +
+				sizeof(*crypto_info),
+				optval, sizeof(*crypto_info),
 				sizeof(struct tls12_crypto_info_aes_gcm_128)
 				- sizeof(*crypto_info));
 
@@ -542,9 +542,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 	}
 	case TLS_CIPHER_AES_GCM_256: {
 		crypto_info[0] = tmp_crypto_info;
-		sockptr_advance(optval, sizeof(*crypto_info));
-		rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info),
-				    optval,
+		rc = copy_from_sockptr_offset((char *)crypto_info +
+				sizeof(*crypto_info),
+				optval, sizeof(*crypto_info),
 				sizeof(struct tls12_crypto_info_aes_gcm_256)
 				- sizeof(*crypto_info));
 
diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index b13ea1422f93..9e6c81d474cb 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -69,19 +69,26 @@ static inline bool sockptr_is_null(sockptr_t sockptr)
 	return !sockptr.user;
 }
 
-static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
+static inline int copy_from_sockptr_offset(void *dst, sockptr_t src,
+		size_t offset, size_t size)
 {
 	if (!sockptr_is_kernel(src))
-		return copy_from_user(dst, src.user, size);
-	memcpy(dst, src.kernel, size);
+		return copy_from_user(dst, src.user + offset, size);
+	memcpy(dst, src.kernel + offset, size);
 	return 0;
 }
 
-static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size)
+static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
+{
+	return copy_from_sockptr_offset(dst, src, 0, size);
+}
+
+static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset,
+		const void *src, size_t size)
 {
 	if (!sockptr_is_kernel(dst))
-		return copy_to_user(dst.user, src, size);
-	memcpy(dst.kernel, src, size);
+		return copy_to_user(dst.user + offset, src, size);
+	memcpy(dst.kernel + offset, src, size);
 	return 0;
 }
 
@@ -112,14 +119,6 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len)
 	return p;
 }
 
-static inline void sockptr_advance(sockptr_t sockptr, size_t len)
-{
-	if (sockptr_is_kernel(sockptr))
-		sockptr.kernel += len;
-	else
-		sockptr.user += len;
-}
-
 static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count)
 {
 	if (sockptr_is_kernel(src)) {
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 2e9e8449698f..d148ab1530e5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -426,9 +426,8 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
 			return -ENOMEM;
 
 		sl->dccpsl_nr = optlen / sizeof(u32) - 1;
-		sockptr_advance(optval, sizeof(service));
-		if (copy_from_sockptr(sl->dccpsl_list, optval,
-				      optlen - sizeof(service)) ||
+		if (copy_from_sockptr_offset(sl->dccpsl_list, optval,
+				sizeof(service), optlen - sizeof(service)) ||
 		    dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
 			kfree(sl);
 			return -EFAULT;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 9a1567dbc022..d1e04d2b5170 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -971,8 +971,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1267,8 +1267,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f2a9680303d8..f15bc21d7301 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1126,8 +1126,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1508,8 +1508,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27de9380ed14..4afec552f211 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2801,12 +2801,13 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_repair_opt opt;
+	size_t offset = 0;
 
 	while (len >= sizeof(opt)) {
-		if (copy_from_sockptr(&opt, optbuf, sizeof(opt)))
+		if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt)))
 			return -EFAULT;
 
-		sockptr_advance(optbuf, sizeof(opt));
+		offset += sizeof(opt);
 		len -= sizeof(opt);
 
 		switch (opt.opt_code) {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 215b6f5e733e..2d655260dedc 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -401,8 +401,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		memset(fl->opt, 0, sizeof(*fl->opt));
 		fl->opt->tot_len = sizeof(*fl->opt) + olen;
 		err = -EFAULT;
-		sockptr_advance(optval, CMSG_ALIGN(sizeof(*freq)));
-		if (copy_from_sockptr(fl->opt + 1, optval, olen))
+		if (copy_from_sockptr_offset(fl->opt + 1, optval,
+				CMSG_ALIGN(sizeof(*freq)), olen))
 			goto done;
 
 		msg.msg_controllen = olen;
@@ -703,9 +703,10 @@ release:
 		goto recheck;
 
 	if (!freq->flr_label) {
-		sockptr_advance(optval,
-				offsetof(struct in6_flowlabel_req, flr_label));
-		if (copy_to_sockptr(optval, &fl->label, sizeof(fl->label))) {
+		size_t offset = offsetof(struct in6_flowlabel_req, flr_label);
+
+		if (copy_to_sockptr_offset(optval, offset, &fl->label,
+				sizeof(fl->label))) {
 			/* Intentionally ignore fault. */
 		}
 	}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 1d52957a413f..2e2119bfcf13 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1143,8 +1143,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
@@ -1517,8 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
-	sockptr_advance(arg, sizeof(tmp));
-	if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) {
+	if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp),
+			tmp.size) != 0) {
 		ret = -EFAULT;
 		goto free_newinfo;
 	}
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index b97eb4b538fd..91bf6635ea9e 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1050,6 +1050,7 @@ EXPORT_SYMBOL_GPL(xt_check_target);
 void *xt_copy_counters(sockptr_t arg, unsigned int len,
 		       struct xt_counters_info *info)
 {
+	size_t offset;
 	void *mem;
 	u64 size;
 
@@ -1067,7 +1068,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len,
 
 		memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1);
 		info->num_counters = compat_tmp.num_counters;
-		sockptr_advance(arg, sizeof(compat_tmp));
+		offset = sizeof(compat_tmp);
 	} else
 #endif
 	{
@@ -1078,7 +1079,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len,
 		if (copy_from_sockptr(info, arg, sizeof(*info)) != 0)
 			return ERR_PTR(-EFAULT);
 
-		sockptr_advance(arg, sizeof(*info));
+		offset = sizeof(*info);
 	}
 	info->name[sizeof(info->name) - 1] = '\0';
 
@@ -1092,7 +1093,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len,
 	if (!mem)
 		return ERR_PTR(-ENOMEM);
 
-	if (copy_from_sockptr(mem, arg, len) == 0)
+	if (copy_from_sockptr_offset(mem, arg, offset, len) == 0)
 		return mem;
 
 	vfree(mem);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index d77f7d821130..bbc52b088d29 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -522,9 +522,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 		goto err_crypto_info;
 	}
 
-	sockptr_advance(optval, sizeof(*crypto_info));
-	rc = copy_from_sockptr(crypto_info + 1, optval,
-			       optlen - sizeof(*crypto_info));
+	rc = copy_from_sockptr_offset(crypto_info + 1, optval,
+				      sizeof(*crypto_info),
+				      optlen - sizeof(*crypto_info));
 	if (rc) {
 		rc = -EFAULT;
 		goto err_crypto_info;
-- 
cgit v1.2.3


From a31edb2059ed4e498f9aa8230c734b59d0ad797a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 28 Jul 2020 18:38:36 +0200
Subject: net: improve the user pointer check in init_user_sockptr

Make sure not just the pointer itself but the whole range lies in
the user address space.  For that pass the length and then use
the access_ok helper to do the check.

Fixes: 6d04fe15f78a ("net: optimize the sockptr_t for unified kernel/user address spaces")
Reported-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockptr.h     | 18 ++++++------------
 net/ipv4/bpfilter/sockopt.c |  2 +-
 net/socket.c                |  2 +-
 3 files changed, 8 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 9e6c81d474cb..96840def9d69 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -27,14 +27,6 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p)
 {
 	return (sockptr_t) { .kernel = p };
 }
-
-static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p)
-{
-	if ((unsigned long)p >= TASK_SIZE)
-		return -EFAULT;
-	sp->user = p;
-	return 0;
-}
 #else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 typedef struct {
 	union {
@@ -53,14 +45,16 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p)
 {
 	return (sockptr_t) { .kernel = p, .is_kernel = true };
 }
+#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
-static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p)
+static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p,
+		size_t size)
 {
-	sp->user = p;
-	sp->is_kernel = false;
+	if (!access_ok(p, size))
+		return -EFAULT;
+	*sp = (sockptr_t) { .user = p };
 	return 0;
 }
-#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
 static inline bool sockptr_is_null(sockptr_t sockptr)
 {
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 94f18d2352d0..545b2640f019 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -65,7 +65,7 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname,
 
 	if (get_user(len, optlen))
 		return -EFAULT;
-	err = init_user_sockptr(&optval, user_optval);
+	err = init_user_sockptr(&optval, user_optval, len);
 	if (err)
 		return err;
 	return bpfilter_mbox_request(sk, optname, optval, len, false);
diff --git a/net/socket.c b/net/socket.c
index 94ca4547cd7c..aff52e81653c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2105,7 +2105,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 	if (optlen < 0)
 		return -EINVAL;
 
-	err = init_user_sockptr(&optval, user_optval);
+	err = init_user_sockptr(&optval, user_optval, optlen);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 2f96593ecc37e98bf99525f0629128080533867f Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Tue, 28 Jul 2020 23:36:55 +0800
Subject: of_address: Add bus type match for pci ranges parser

So the parser can be used to parse range property of ISA bus.

As they're all using PCI-like method of range property, there is no need
start a new parser.

Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 drivers/of/address.c       | 29 +++++++++++++++++------------
 include/linux/of_address.h |  4 ++++
 2 files changed, 21 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/address.c b/drivers/of/address.c
index 8eea3f6e29a4..813936d419ad 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -49,6 +49,7 @@ struct of_bus {
 	u64		(*map)(__be32 *addr, const __be32 *range,
 				int na, int ns, int pna);
 	int		(*translate)(__be32 *addr, u64 offset, int na);
+	bool	has_flags;
 	unsigned int	(*get_flags)(const __be32 *addr);
 };
 
@@ -364,6 +365,7 @@ static struct of_bus of_busses[] = {
 		.count_cells = of_bus_pci_count_cells,
 		.map = of_bus_pci_map,
 		.translate = of_bus_pci_translate,
+		.has_flags = true,
 		.get_flags = of_bus_pci_get_flags,
 	},
 #endif /* CONFIG_PCI */
@@ -375,6 +377,7 @@ static struct of_bus of_busses[] = {
 		.count_cells = of_bus_isa_count_cells,
 		.map = of_bus_isa_map,
 		.translate = of_bus_isa_translate,
+		.has_flags = true,
 		.get_flags = of_bus_isa_get_flags,
 	},
 	/* Default */
@@ -698,9 +701,10 @@ static int parser_init(struct of_pci_range_parser *parser,
 
 	parser->node = node;
 	parser->pna = of_n_addr_cells(node);
-	parser->na = of_bus_n_addr_cells(node);
-	parser->ns = of_bus_n_size_cells(node);
 	parser->dma = !strcmp(name, "dma-ranges");
+	parser->bus = of_match_bus(node);
+
+	parser->bus->count_cells(parser->node, &parser->na, &parser->ns);
 
 	parser->range = of_get_property(node, name, &rlen);
 	if (parser->range == NULL)
@@ -732,6 +736,7 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 	int na = parser->na;
 	int ns = parser->ns;
 	int np = parser->pna + na + ns;
+	int busflag_na = 0;
 
 	if (!range)
 		return NULL;
@@ -739,12 +744,13 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 	if (!parser->range || parser->range + np > parser->end)
 		return NULL;
 
-	if (parser->na == 3)
-		range->flags = of_bus_pci_get_flags(parser->range);
-	else
-		range->flags = 0;
+	range->flags = parser->bus->get_flags(parser->range);
+
+	/* A extra cell for resource flags */
+	if (parser->bus->has_flags)
+		busflag_na = 1;
 
-	range->pci_addr = of_read_number(parser->range, na);
+	range->bus_addr = of_read_number(parser->range + busflag_na, na - busflag_na);
 
 	if (parser->dma)
 		range->cpu_addr = of_translate_dma_address(parser->node,
@@ -759,11 +765,10 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 	/* Now consume following elements while they are contiguous */
 	while (parser->range + np <= parser->end) {
 		u32 flags = 0;
-		u64 pci_addr, cpu_addr, size;
+		u64 bus_addr, cpu_addr, size;
 
-		if (parser->na == 3)
-			flags = of_bus_pci_get_flags(parser->range);
-		pci_addr = of_read_number(parser->range, na);
+		flags = parser->bus->get_flags(parser->range);
+		bus_addr = of_read_number(parser->range + busflag_na, na - busflag_na);
 		if (parser->dma)
 			cpu_addr = of_translate_dma_address(parser->node,
 					parser->range + na);
@@ -774,7 +779,7 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 
 		if (flags != range->flags)
 			break;
-		if (pci_addr != range->pci_addr + range->size ||
+		if (bus_addr != range->bus_addr + range->size ||
 		    cpu_addr != range->cpu_addr + range->size)
 			break;
 
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 763022ed3456..88bc943405cd 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -6,8 +6,11 @@
 #include <linux/of.h>
 #include <linux/io.h>
 
+struct of_bus;
+
 struct of_pci_range_parser {
 	struct device_node *node;
+	struct of_bus *bus;
 	const __be32 *range;
 	const __be32 *end;
 	int na;
@@ -119,6 +122,7 @@ static inline void __iomem *of_iomap(struct device_node *device, int index)
 	return NULL;
 }
 #endif
+#define of_range_parser_init of_pci_range_parser_init
 
 #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI)
 extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no,
-- 
cgit v1.2.3


From b8265621f4888af9494e1d685620871ec81bc33d Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Thu, 23 Jul 2020 17:21:59 -0700
Subject: Add pldmfw library for PLDM firmware update

The pldmfw library is used to implement common logic needed to flash
devices based on firmware files using the format described by the PLDM
for Firmware Update standard.

This library consists of logic to parse the PLDM file format from
a firmware file object, as well as common logic for sending the relevant
PLDM header data to the device firmware.

A simple ops table is provided so that device drivers can implement
device specific hardware interactions while keeping the common logic to
the pldmfw library.

This library will be used by the Intel ice networking driver as part of
implementing device flash update via devlink. The library aims to be
vendor and device agnostic. For this reason, it has been placed in
lib/pldmfw, in the hopes that other devices which use the PLDM firmware
file format may benefit from it in the future. However, do note that not
all features defined in the PLDM standard have been implemented.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/driver-api/index.rst              |   1 +
 Documentation/driver-api/pldmfw/driver-ops.rst  |  56 ++
 Documentation/driver-api/pldmfw/file-format.rst | 203 ++++++
 Documentation/driver-api/pldmfw/index.rst       |  72 ++
 MAINTAINERS                                     |   7 +
 include/linux/pldmfw.h                          | 165 +++++
 lib/Kconfig                                     |   4 +
 lib/Makefile                                    |   3 +
 lib/pldmfw/Makefile                             |   2 +
 lib/pldmfw/pldmfw.c                             | 879 ++++++++++++++++++++++++
 lib/pldmfw/pldmfw_private.h                     | 238 +++++++
 11 files changed, 1630 insertions(+)
 create mode 100644 Documentation/driver-api/pldmfw/driver-ops.rst
 create mode 100644 Documentation/driver-api/pldmfw/file-format.rst
 create mode 100644 Documentation/driver-api/pldmfw/index.rst
 create mode 100644 include/linux/pldmfw.h
 create mode 100644 lib/pldmfw/Makefile
 create mode 100644 lib/pldmfw/pldmfw.c
 create mode 100644 lib/pldmfw/pldmfw_private.h

(limited to 'include/linux')

diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 6567187e7687..7fc1e0cccae7 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -95,6 +95,7 @@ available subsections can be seen below.
    phy/index
    pti_intel_mid
    pwm
+   pldmfw/index
    rfkill
    serial/index
    sm501
diff --git a/Documentation/driver-api/pldmfw/driver-ops.rst b/Documentation/driver-api/pldmfw/driver-ops.rst
new file mode 100644
index 000000000000..f0654783d3b3
--- /dev/null
+++ b/Documentation/driver-api/pldmfw/driver-ops.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+=========================
+Driver-specific callbacks
+=========================
+
+The ``pldmfw`` module relies on the device driver for implementing device
+specific behavior using the following operations.
+
+``.match_record``
+-----------------
+
+The ``.match_record`` operation is used to determine whether a given PLDM
+record matches the device being updated. This requires comparing the record
+descriptors in the record with information from the device. Many record
+descriptors are defined by the PLDM standard, but it is also allowed for
+devices to implement their own descriptors.
+
+The ``.match_record`` operation should return true if a given record matches
+the device.
+
+``.send_package_data``
+----------------------
+
+The ``.send_package_data`` operation is used to send the device-specific
+package data in a record to the device firmware. If the matching record
+provides package data, ``pldmfw`` will call the ``.send_package_data``
+function with a pointer to the package data and with the package data
+length. The device driver should send this data to firmware.
+
+``.send_component_table``
+-------------------------
+
+The ``.send_component_table`` operation is used to forward component
+information to the device. It is called once for each applicable component,
+that is, for each component indicated by the matching record. The
+device driver should send the component information to the device firmware,
+and wait for a response. The provided transfer flag indicates whether this
+is the first, last, or a middle component, and is expected to be forwarded
+to firmware as part of the component table information. The driver should an
+error in the case when the firmware indicates that the component cannot be
+updated, or return zero if the component can be updated.
+
+``.flash_component``
+--------------------
+
+The ``.flash_component`` operation is used to inform the device driver to
+flash a given component. The driver must perform any steps necessary to send
+the component data to the device.
+
+``.finalize_update``
+--------------------
+
+The ``.finalize_update`` operation is used by the ``pldmfw`` library in
+order to allow the device driver to perform any remaining device specific
+logic needed to finish the update.
diff --git a/Documentation/driver-api/pldmfw/file-format.rst b/Documentation/driver-api/pldmfw/file-format.rst
new file mode 100644
index 000000000000..b7a9cebe09c6
--- /dev/null
+++ b/Documentation/driver-api/pldmfw/file-format.rst
@@ -0,0 +1,203 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+==================================
+PLDM Firmware file format overview
+==================================
+
+A PLDM firmware package is a binary file which contains a header that
+describes the contents of the firmware package. This includes an initial
+package header, one or more firmware records, and one or more components
+describing the actual flash contents to program.
+
+This diagram provides an overview of the file format::
+
+        overall file layout
+      +----------------------+
+      |                      |
+      |  Package Header      |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Device Records      |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Component Info      |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Package Header CRC  |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Component Image 1   |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Component Image 2   |
+      |                      |
+      +----------------------+
+      |                      |
+      |         ...          |
+      |                      |
+      +----------------------+
+      |                      |
+      |  Component Image N   |
+      |                      |
+      +----------------------+
+
+Package Header
+==============
+
+The package header begins with the UUID of the PLDM file format, and
+contains information about the version of the format that the file uses. It
+also includes the total header size, a release date, the size of the
+component bitmap, and an overall package version.
+
+The following diagram provides an overview of the package header::
+
+             header layout
+      +-------------------------+
+      | PLDM UUID               |
+      +-------------------------+
+      | Format Revision         |
+      +-------------------------+
+      | Header Size             |
+      +-------------------------+
+      | Release Date            |
+      +-------------------------+
+      | Component Bitmap Length |
+      +-------------------------+
+      | Package Version Info    |
+      +-------------------------+
+
+Device Records
+==============
+
+The device firmware records area starts with a count indicating the total
+number of records in the file, followed by each record. A single device
+record describes what device matches this record. All valid PLDM firmware
+files must contain at least one record, but optionally may contain more than
+one record if they support multiple devices.
+
+Each record will identify the device it supports via TLVs that describe the
+device, such as the PCI device and vendor information. It will also indicate
+which set of components that are used by this device. It is possible that
+only subset of provided components will be used by a given record. A record
+may also optionally contain device-specific package data that will be used
+by the device firmware during the update process.
+
+The following diagram provides an overview of the device record area::
+
+         area layout
+      +---------------+
+      |               |
+      |  Record Count |
+      |               |
+      +---------------+
+      |               |
+      |  Record 1     |
+      |               |
+      +---------------+
+      |               |
+      |  Record 2     |
+      |               |
+      +---------------+
+      |               |
+      |      ...      |
+      |               |
+      +---------------+
+      |               |
+      |  Record N     |
+      |               |
+      +---------------+
+
+           record layout
+      +-----------------------+
+      | Record Length         |
+      +-----------------------+
+      | Descriptor Count      |
+      +-----------------------+
+      | Option Flags          |
+      +-----------------------+
+      | Version Settings      |
+      +-----------------------+
+      | Package Data Length   |
+      +-----------------------+
+      | Applicable Components |
+      +-----------------------+
+      | Version String        |
+      +-----------------------+
+      | Descriptor TLVs       |
+      +-----------------------+
+      | Package Data          |
+      +-----------------------+
+
+Component Info
+==============
+
+The component information area begins with a count of the number of
+components. Following this count is a description for each component. The
+component information points to the location in the file where the component
+data is stored, and includes version data used to identify the version of
+the component.
+
+The following diagram provides an overview of the component area::
+
+         area layout
+      +-----------------+
+      |                 |
+      | Component Count |
+      |                 |
+      +-----------------+
+      |                 |
+      | Component 1     |
+      |                 |
+      +-----------------+
+      |                 |
+      | Component 2     |
+      |                 |
+      +-----------------+
+      |                 |
+      |     ...         |
+      |                 |
+      +-----------------+
+      |                 |
+      | Component N     |
+      |                 |
+      +-----------------+
+
+           component layout
+      +------------------------+
+      | Classification         |
+      +------------------------+
+      | Component Identifier   |
+      +------------------------+
+      | Comparison Stamp       |
+      +------------------------+
+      | Component Options      |
+      +------------------------+
+      | Activation Method      |
+      +------------------------+
+      | Location Offset        |
+      +------------------------+
+      | Component Size         |
+      +------------------------+
+      | Component Version Info |
+      +------------------------+
+      | Package Data           |
+      +------------------------+
+
+
+Package Header CRC
+==================
+
+Following the component information is a short 4-byte CRC calculated over
+the contents of all of the header information.
+
+Component Images
+================
+
+The component images follow the package header information in the PLDM
+firmware file. Each of these is simply a binary chunk with its start and
+size defined by the matching component structure in the component info area.
diff --git a/Documentation/driver-api/pldmfw/index.rst b/Documentation/driver-api/pldmfw/index.rst
new file mode 100644
index 000000000000..ad2c33ece30f
--- /dev/null
+++ b/Documentation/driver-api/pldmfw/index.rst
@@ -0,0 +1,72 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+==================================
+PLDM Firmware Flash Update Library
+==================================
+
+``pldmfw`` implements functionality for updating the flash on a device using
+the PLDM for Firmware Update standard
+<https://www.dmtf.org/documents/pmci/pldm-firmware-update-specification-100>.
+
+.. toctree::
+   :maxdepth: 1
+
+   file-format
+   driver-ops
+
+==================================
+Overview of the ``pldmfw`` library
+==================================
+
+The ``pldmfw`` library is intended to be used by device drivers for
+implementing device flash update based on firmware files following the PLDM
+firwmare file format.
+
+It is implemented using an ops table that allows device drivers to provide
+the underlying device specific functionality.
+
+``pldmfw`` implements logic to parse the packed binary format of the PLDM
+firmware file into data structures, and then uses the provided function
+operations to determine if the firmware file is a match for the device. If
+so, it sends the record and component data to the firmware using the device
+specific implementations provided by device drivers. Once the device
+firmware indicates that the update may be performed, the firmware data is
+sent to the device for programming.
+
+Parsing the PLDM file
+=====================
+
+The PLDM file format uses packed binary data, with most multi-byte fields
+stored in the Little Endian format. Several pieces of data are variable
+length, including version strings and the number of records and components.
+Due to this, it is not straight forward to index the record, record
+descriptors, or components.
+
+To avoid proliferating access to the packed binary data, the ``pldmfw``
+library parses and extracts this data into simpler structures for ease of
+access.
+
+In order to safely process the firmware file, care is taken to avoid
+unaligned access of multi-byte fields, and to properly convert from Little
+Endian to CPU host format. Additionally the records, descriptors, and
+components are stored in linked lists.
+
+Performing a flash update
+=========================
+
+To perform a flash update, the ``pldmfw`` module performs the following
+steps
+
+1. Parse the firmware file for record and component information
+2. Scan through the records and determine if the device matches any record
+   in the file. The first matched record will be used.
+3. If the matching record provides package data, send this package data to
+   the device.
+4. For each component that the record indicates, send the component data to
+   the device. For each component, the firmware may respond with an
+   indication of whether the update is suitable or not. If any component is
+   not suitable, the update is canceled.
+5. For each component, send the binary data to the device firmware for
+   updating.
+6. After all components are programmed, perform any final device-specific
+   actions to finalize the update.
diff --git a/MAINTAINERS b/MAINTAINERS
index b61f9063faf2..7bc4360b592f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13604,6 +13604,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml
 F:	drivers/iio/chemical/pms7003.c
 
+PLDMFW LIBRARY
+M:	Jacob Keller <jacob.e.keller@intel.com>
+S:	Maintained
+F:	Documentation/driver-api/pldmfw/
+F:	include/linux/pldmfw.h
+F:	lib/pldmfw/
+
 PLX DMA DRIVER
 M:	Logan Gunthorpe <logang@deltatee.com>
 S:	Maintained
diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h
new file mode 100644
index 000000000000..0fc831338226
--- /dev/null
+++ b/include/linux/pldmfw.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2019, Intel Corporation. */
+
+#ifndef _PLDMFW_H_
+#define _PLDMFW_H_
+
+#include <linux/list.h>
+#include <linux/firmware.h>
+
+#define PLDM_DEVICE_UPDATE_CONTINUE_AFTER_FAIL BIT(0)
+
+#define PLDM_STRING_TYPE_UNKNOWN	0
+#define PLDM_STRING_TYPE_ASCII		1
+#define PLDM_STRING_TYPE_UTF8		2
+#define PLDM_STRING_TYPE_UTF16		3
+#define PLDM_STRING_TYPE_UTF16LE	4
+#define PLDM_STRING_TYPE_UTF16BE	5
+
+struct pldmfw_record {
+	struct list_head entry;
+
+	/* List of descriptor TLVs */
+	struct list_head descs;
+
+	/* Component Set version string*/
+	const u8 *version_string;
+	u8 version_type;
+	u8 version_len;
+
+	/* Package Data length */
+	u16 package_data_len;
+
+	/* Bitfield of Device Update Flags */
+	u32 device_update_flags;
+
+	/* Package Data block */
+	const u8 *package_data;
+
+	/* Bitmap of components applicable to this record */
+	unsigned long *component_bitmap;
+	u16 component_bitmap_len;
+};
+
+/* Standard descriptor TLV identifiers */
+#define PLDM_DESC_ID_PCI_VENDOR_ID	0x0000
+#define PLDM_DESC_ID_IANA_ENTERPRISE_ID	0x0001
+#define PLDM_DESC_ID_UUID		0x0002
+#define PLDM_DESC_ID_PNP_VENDOR_ID	0x0003
+#define PLDM_DESC_ID_ACPI_VENDOR_ID	0x0004
+#define PLDM_DESC_ID_PCI_DEVICE_ID	0x0100
+#define PLDM_DESC_ID_PCI_SUBVENDOR_ID	0x0101
+#define PLDM_DESC_ID_PCI_SUBDEV_ID	0x0102
+#define PLDM_DESC_ID_PCI_REVISION_ID	0x0103
+#define PLDM_DESC_ID_PNP_PRODUCT_ID	0x0104
+#define PLDM_DESC_ID_ACPI_PRODUCT_ID	0x0105
+#define PLDM_DESC_ID_VENDOR_DEFINED	0xFFFF
+
+struct pldmfw_desc_tlv {
+	struct list_head entry;
+
+	const u8 *data;
+	u16 type;
+	u16 size;
+};
+
+#define PLDM_CLASSIFICATION_UNKNOWN		0x0000
+#define PLDM_CLASSIFICATION_OTHER		0x0001
+#define PLDM_CLASSIFICATION_DRIVER		0x0002
+#define PLDM_CLASSIFICATION_CONFIG_SW		0x0003
+#define PLDM_CLASSIFICATION_APP_SW		0x0004
+#define PLDM_CLASSIFICATION_INSTRUMENTATION	0x0005
+#define PLDM_CLASSIFICATION_BIOS		0x0006
+#define PLDM_CLASSIFICATION_DIAGNOSTIC_SW	0x0007
+#define PLDM_CLASSIFICATION_OS			0x0008
+#define PLDM_CLASSIFICATION_MIDDLEWARE		0x0009
+#define PLDM_CLASSIFICATION_FIRMWARE		0x000A
+#define PLDM_CLASSIFICATION_CODE		0x000B
+#define PLDM_CLASSIFICATION_SERVICE_PACK	0x000C
+#define PLDM_CLASSIFICATION_SOFTWARE_BUNDLE	0x000D
+
+#define PLDM_ACTIVATION_METHOD_AUTO		BIT(0)
+#define PLDM_ACTIVATION_METHOD_SELF_CONTAINED	BIT(1)
+#define PLDM_ACTIVATION_METHOD_MEDIUM_SPECIFIC	BIT(2)
+#define PLDM_ACTIVATION_METHOD_REBOOT		BIT(3)
+#define PLDM_ACTIVATION_METHOD_DC_CYCLE		BIT(4)
+#define PLDM_ACTIVATION_METHOD_AC_CYCLE		BIT(5)
+
+#define PLDMFW_COMPONENT_OPTION_FORCE_UPDATE		BIT(0)
+#define PLDMFW_COMPONENT_OPTION_USE_COMPARISON_STAMP	BIT(1)
+
+struct pldmfw_component {
+	struct list_head entry;
+
+	/* component identifier */
+	u16 classification;
+	u16 identifier;
+
+	u16 options;
+	u16 activation_method;
+
+	u32 comparison_stamp;
+
+	u32 component_size;
+	const u8 *component_data;
+
+	/* Component version string */
+	const u8 *version_string;
+	u8 version_type;
+	u8 version_len;
+
+	/* component index */
+	u8 index;
+
+};
+
+/* Transfer flag used for sending components to the firmware */
+#define PLDM_TRANSFER_FLAG_START		BIT(0)
+#define PLDM_TRANSFER_FLAG_MIDDLE		BIT(1)
+#define PLDM_TRANSFER_FLAG_END			BIT(2)
+
+struct pldmfw_ops;
+
+/* Main entry point to the PLDM firmware update engine. Device drivers
+ * should embed this in a private structure and use container_of to obtain
+ * a pointer to their own data, used to implement the device specific
+ * operations.
+ */
+struct pldmfw {
+	const struct pldmfw_ops *ops;
+	struct device *dev;
+};
+
+bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record);
+
+/* Operations invoked by the generic PLDM firmware update engine. Used to
+ * implement device specific logic.
+ *
+ * @match_record: check if the device matches the given record. For
+ * convenience, a standard implementation is provided for PCI devices.
+ *
+ * @send_package_data: send the package data associated with the matching
+ * record to firmware.
+ *
+ * @send_component_table: send the component data associated with a given
+ * component to firmware. Called once for each applicable component.
+ *
+ * @flash_component: Flash the data for a given component to the device.
+ * Called once for each applicable component, after all component tables have
+ * been sent.
+ *
+ * @finalize_update: (optional) Finish the update. Called after all components
+ * have been flashed.
+ */
+struct pldmfw_ops {
+	bool (*match_record)(struct pldmfw *context, struct pldmfw_record *record);
+	int (*send_package_data)(struct pldmfw *context, const u8 *data, u16 length);
+	int (*send_component_table)(struct pldmfw *context, struct pldmfw_component *component,
+				    u8 transfer_flag);
+	int (*flash_component)(struct pldmfw *context, struct pldmfw_component *component);
+	int (*finalize_update)(struct pldmfw *context);
+};
+
+int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw);
+
+#endif
diff --git a/lib/Kconfig b/lib/Kconfig
index df3f3da95990..3ffbca6998e5 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -676,3 +676,7 @@ config GENERIC_LIB_CMPDI2
 
 config GENERIC_LIB_UCMPDI2
 	bool
+
+config PLDMFW
+	bool
+	default n
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..281888ff713b 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -315,6 +315,9 @@ obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
 obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
 obj-$(CONFIG_OBJAGG) += objagg.o
 
+# pldmfw library
+obj-$(CONFIG_PLDMFW) += pldmfw/
+
 # KUnit tests
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
 obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
diff --git a/lib/pldmfw/Makefile b/lib/pldmfw/Makefile
new file mode 100644
index 000000000000..99ad10711abe
--- /dev/null
+++ b/lib/pldmfw/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_PLDMFW)	+= pldmfw.o
diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c
new file mode 100644
index 000000000000..e5d4b3b2af81
--- /dev/null
+++ b/lib/pldmfw/pldmfw.c
@@ -0,0 +1,879 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2019, Intel Corporation. */
+
+#include <asm/unaligned.h>
+#include <linux/crc32.h>
+#include <linux/device.h>
+#include <linux/firmware.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pldmfw.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+
+#include "pldmfw_private.h"
+
+/* Internal structure used to store details about the PLDM image file as it is
+ * being validated and processed.
+ */
+struct pldmfw_priv {
+	struct pldmfw *context;
+	const struct firmware *fw;
+
+	/* current offset of firmware image */
+	size_t offset;
+
+	struct list_head records;
+	struct list_head components;
+
+	/* PLDM Firmware Package Header */
+	const struct __pldm_header *header;
+	u16 total_header_size;
+
+	/* length of the component bitmap */
+	u16 component_bitmap_len;
+	u16 bitmap_size;
+
+	/* Start of the component image information */
+	u16 component_count;
+	const u8 *component_start;
+
+	/* Start pf the firmware device id records */
+	const u8 *record_start;
+	u8 record_count;
+
+	/* The CRC at the end of the package header */
+	u32 header_crc;
+
+	struct pldmfw_record *matching_record;
+};
+
+/**
+ * pldm_check_fw_space - Verify that the firmware image has space left
+ * @data: pointer to private data
+ * @offset: offset to start from
+ * @length: length to check for
+ *
+ * Verify that the firmware data can hold a chunk of bytes with the specified
+ * offset and length.
+ *
+ * Returns: zero on success, or -EFAULT if the image does not have enough
+ * space left to fit the expected length.
+ */
+static int
+pldm_check_fw_space(struct pldmfw_priv *data, size_t offset, size_t length)
+{
+	size_t expected_size = offset + length;
+	struct device *dev = data->context->dev;
+
+	if (data->fw->size < expected_size) {
+		dev_dbg(dev, "Firmware file size smaller than expected. Got %zu bytes, needed %zu bytes\n",
+			data->fw->size, expected_size);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_move_fw_offset - Move the current firmware offset forward
+ * @data: pointer to private data
+ * @bytes_to_move: number of bytes to move the offset forward by
+ *
+ * Check that there is enough space past the current offset, and then move the
+ * offset forward by this ammount.
+ *
+ * Returns: zero on success, or -EFAULT if the image is too small to fit the
+ * expected length.
+ */
+static int
+pldm_move_fw_offset(struct pldmfw_priv *data, size_t bytes_to_move)
+{
+	int err;
+
+	err = pldm_check_fw_space(data, data->offset, bytes_to_move);
+	if (err)
+		return err;
+
+	data->offset += bytes_to_move;
+
+	return 0;
+}
+
+/**
+ * pldm_parse_header - Validate and extract details about the PLDM header
+ * @data: pointer to private data
+ *
+ * Performs initial basic verification of the PLDM image, up to the first
+ * firmware record.
+ *
+ * This includes the following checks and extractions
+ *
+ *   * Verify that the UUID at the start of the header matches the expected
+ *     value as defined in the DSP0267 PLDM specification
+ *   * Check that the revision is 0x01
+ *   * Extract the total header_size and verify that the image is large enough
+ *     to contain at least the length of this header
+ *   * Extract the size of the component bitmap length
+ *   * Extract a pointer to the start of the record area
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_header(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_record_area *record_area;
+	struct device *dev = data->context->dev;
+	const struct __pldm_header *header;
+	size_t header_size;
+	int err;
+
+	err = pldm_move_fw_offset(data, sizeof(*header));
+	if (err)
+		return err;
+
+	header = (const struct __pldm_header *)data->fw->data;
+	data->header = header;
+
+	if (!uuid_equal(&header->id, &pldm_firmware_header_id)) {
+		dev_dbg(dev, "Invalid package header identifier. Expected UUID %pUB, but got %pUB\n",
+			&pldm_firmware_header_id, &header->id);
+		return -EINVAL;
+	}
+
+	if (header->revision != PACKAGE_HEADER_FORMAT_REVISION) {
+		dev_dbg(dev, "Invalid package header revision. Expected revision %u but got %u\n",
+			PACKAGE_HEADER_FORMAT_REVISION, header->revision);
+		return -EOPNOTSUPP;
+	}
+
+	data->total_header_size = get_unaligned_le16(&header->size);
+	header_size = data->total_header_size - sizeof(*header);
+
+	err = pldm_check_fw_space(data, data->offset, header_size);
+	if (err)
+		return err;
+
+	data->component_bitmap_len =
+		get_unaligned_le16(&header->component_bitmap_len);
+
+	if (data->component_bitmap_len % 8 != 0) {
+		dev_dbg(dev, "Invalid component bitmap length. The length is %u, which is not a multiple of 8\n",
+			data->component_bitmap_len);
+		return -EINVAL;
+	}
+
+	data->bitmap_size = data->component_bitmap_len / 8;
+
+	err = pldm_move_fw_offset(data, header->version_len);
+	if (err)
+		return err;
+
+	/* extract a pointer to the record area, which just follows the main
+	 * PLDM header data.
+	 */
+	record_area = (const struct __pldmfw_record_area *)(data->fw->data +
+							 data->offset);
+
+	err = pldm_move_fw_offset(data, sizeof(*record_area));
+	if (err)
+		return err;
+
+	data->record_count = record_area->record_count;
+	data->record_start = record_area->records;
+
+	return 0;
+}
+
+/**
+ * pldm_check_desc_tlv_len - Check that the length matches expectation
+ * @data: pointer to image details
+ * @type: the descriptor type
+ * @size: the length from the descriptor header
+ *
+ * If the descriptor type is one of the documented descriptor types according
+ * to the standard, verify that the provided length matches.
+ *
+ * If the type is not recognized or is VENDOR_DEFINED, return zero.
+ *
+ * Returns: zero on success, or -EINVAL if the specified size of a standard
+ * TLV does not match the expected value defined for that TLV.
+ */
+static int
+pldm_check_desc_tlv_len(struct pldmfw_priv *data, u16 type, u16 size)
+{
+	struct device *dev = data->context->dev;
+	u16 expected_size;
+
+	switch (type) {
+	case PLDM_DESC_ID_PCI_VENDOR_ID:
+	case PLDM_DESC_ID_PCI_DEVICE_ID:
+	case PLDM_DESC_ID_PCI_SUBVENDOR_ID:
+	case PLDM_DESC_ID_PCI_SUBDEV_ID:
+		expected_size = 2;
+		break;
+	case PLDM_DESC_ID_PCI_REVISION_ID:
+		expected_size = 1;
+		break;
+	case PLDM_DESC_ID_PNP_VENDOR_ID:
+		expected_size = 3;
+		break;
+	case PLDM_DESC_ID_IANA_ENTERPRISE_ID:
+	case PLDM_DESC_ID_ACPI_VENDOR_ID:
+	case PLDM_DESC_ID_PNP_PRODUCT_ID:
+	case PLDM_DESC_ID_ACPI_PRODUCT_ID:
+		expected_size = 4;
+		break;
+	case PLDM_DESC_ID_UUID:
+		expected_size = 16;
+		break;
+	case PLDM_DESC_ID_VENDOR_DEFINED:
+		return 0;
+	default:
+		/* Do not report an error on an unexpected TLV */
+		dev_dbg(dev, "Found unrecognized TLV type 0x%04x\n", type);
+		return 0;
+	}
+
+	if (size != expected_size) {
+		dev_dbg(dev, "Found TLV type 0x%04x with unexpected length. Got %u bytes, but expected %u bytes\n",
+			type, size, expected_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_desc_tlvs - Check and skip past a number of TLVs
+ * @data: pointer to private data
+ * @record: pointer to the record this TLV belongs too
+ * @desc_count: descriptor count
+ *
+ * From the current offset, read and extract the descriptor TLVs, updating the
+ * current offset each time.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_parse_desc_tlvs(struct pldmfw_priv *data, struct pldmfw_record *record, u8 desc_count)
+{
+	const struct __pldmfw_desc_tlv *__desc;
+	const u8 *desc_start;
+	u8 i;
+
+	desc_start = data->fw->data + data->offset;
+
+	pldm_for_each_desc_tlv(i, __desc, desc_start, desc_count) {
+		struct pldmfw_desc_tlv *desc;
+		int err;
+		u16 type, size;
+
+		err = pldm_move_fw_offset(data, sizeof(*__desc));
+		if (err)
+			return err;
+
+		type = get_unaligned_le16(&__desc->type);
+
+		/* According to DSP0267, this only includes the data field */
+		size = get_unaligned_le16(&__desc->size);
+
+		err = pldm_check_desc_tlv_len(data, type, size);
+		if (err)
+			return err;
+
+		/* check that we have space and move the offset forward */
+		err = pldm_move_fw_offset(data, size);
+		if (err)
+			return err;
+
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+		if (!desc)
+			return -ENOMEM;
+
+		desc->type = type;
+		desc->size = size;
+		desc->data = __desc->data;
+
+		list_add_tail(&desc->entry, &record->descs);
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_one_record - Verify size of one PLDM record
+ * @data: pointer to image details
+ * @__record: pointer to the record to check
+ *
+ * This function checks that the record size does not exceed either the size
+ * of the firmware file or the total length specified in the header section.
+ *
+ * It also verifies that the recorded length of the start of the record
+ * matches the size calculated by adding the static structure length, the
+ * component bitmap length, the version string length, the length of all
+ * descriptor TLVs, and the length of the package data.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_parse_one_record(struct pldmfw_priv *data,
+		      const struct __pldmfw_record_info *__record)
+{
+	struct pldmfw_record *record;
+	size_t measured_length;
+	int err;
+	const u8 *bitmap_ptr;
+	u16 record_len;
+	int i;
+
+	/* Make a copy and insert it into the record list */
+	record = kzalloc(sizeof(*record), GFP_KERNEL);
+	if (!record)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&record->descs);
+	list_add_tail(&record->entry, &data->records);
+
+	/* Then check that we have space and move the offset */
+	err = pldm_move_fw_offset(data, sizeof(*__record));
+	if (err)
+		return err;
+
+	record_len = get_unaligned_le16(&__record->record_len);
+	record->package_data_len = get_unaligned_le16(&__record->package_data_len);
+	record->version_len = __record->version_len;
+	record->version_type = __record->version_type;
+
+	bitmap_ptr = data->fw->data + data->offset;
+
+	/* check that we have space for the component bitmap length */
+	err = pldm_move_fw_offset(data, data->bitmap_size);
+	if (err)
+		return err;
+
+	record->component_bitmap_len = data->component_bitmap_len;
+	record->component_bitmap = bitmap_zalloc(record->component_bitmap_len,
+						 GFP_KERNEL);
+	if (!record->component_bitmap)
+		return -ENOMEM;
+
+	for (i = 0; i < data->bitmap_size; i++)
+		bitmap_set_value8(record->component_bitmap, bitmap_ptr[i], i * 8);
+
+	record->version_string = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, record->version_len);
+	if (err)
+		return err;
+
+	/* Scan through the descriptor TLVs and find the end */
+	err = pldm_parse_desc_tlvs(data, record, __record->descriptor_count);
+	if (err)
+		return err;
+
+	record->package_data = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, record->package_data_len);
+	if (err)
+		return err;
+
+	measured_length = data->offset - ((const u8 *)__record - data->fw->data);
+	if (measured_length != record_len) {
+		dev_dbg(data->context->dev, "Unexpected record length. Measured record length is %zu bytes, expected length is %u bytes\n",
+			measured_length, record_len);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_records - Locate the start of the component area
+ * @data: pointer to private data
+ *
+ * Extract the record count, and loop through each record, searching for the
+ * component area.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_records(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_component_area *component_area;
+	const struct __pldmfw_record_info *record;
+	int err;
+	u8 i;
+
+	pldm_for_each_record(i, record, data->record_start, data->record_count) {
+		err = pldm_parse_one_record(data, record);
+		if (err)
+			return err;
+	}
+
+	/* Extract a pointer to the component area, which just follows the
+	 * PLDM device record data.
+	 */
+	component_area = (const struct __pldmfw_component_area *)(data->fw->data + data->offset);
+
+	err = pldm_move_fw_offset(data, sizeof(*component_area));
+	if (err)
+		return err;
+
+	data->component_count =
+		get_unaligned_le16(&component_area->component_image_count);
+	data->component_start = component_area->components;
+
+	return 0;
+}
+
+/**
+ * pldm_parse_components - Locate the CRC header checksum
+ * @data: pointer to private data
+ *
+ * Extract the component count, and find the pointer to the component area.
+ * Scan through each component searching for the end, which should point to
+ * the package header checksum.
+ *
+ * Extract the package header CRC and save it for verification.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_components(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_component_info *__component;
+	struct device *dev = data->context->dev;
+	const u8 *header_crc_ptr;
+	int err;
+	u8 i;
+
+	pldm_for_each_component(i, __component, data->component_start, data->component_count) {
+		struct pldmfw_component *component;
+		u32 offset, size;
+
+		err = pldm_move_fw_offset(data, sizeof(*__component));
+		if (err)
+			return err;
+
+		err = pldm_move_fw_offset(data, __component->version_len);
+		if (err)
+			return err;
+
+		offset = get_unaligned_le32(&__component->location_offset);
+		size = get_unaligned_le32(&__component->size);
+
+		err = pldm_check_fw_space(data, offset, size);
+		if (err)
+			return err;
+
+		component = kzalloc(sizeof(*component), GFP_KERNEL);
+		if (!component)
+			return -ENOMEM;
+
+		component->index = i;
+		component->classification = get_unaligned_le16(&__component->classification);
+		component->identifier = get_unaligned_le16(&__component->identifier);
+		component->comparison_stamp = get_unaligned_le32(&__component->comparison_stamp);
+		component->options = get_unaligned_le16(&__component->options);
+		component->activation_method = get_unaligned_le16(&__component->activation_method);
+		component->version_type = __component->version_type;
+		component->version_len = __component->version_len;
+		component->version_string = __component->version_string;
+		component->component_data = data->fw->data + offset;
+		component->component_size = size;
+
+		list_add_tail(&component->entry, &data->components);
+	}
+
+	header_crc_ptr = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, sizeof(data->header_crc));
+	if (err)
+		return err;
+
+	/* Make sure that we reached the expected offset */
+	if (data->offset != data->total_header_size) {
+		dev_dbg(dev, "Invalid firmware header size. Expected %u but got %zu\n",
+			data->total_header_size, data->offset);
+		return -EFAULT;
+	}
+
+	data->header_crc = get_unaligned_le32(header_crc_ptr);
+
+	return 0;
+}
+
+/**
+ * pldm_verify_header_crc - Verify that the CRC in the header matches
+ * @data: pointer to private data
+ *
+ * Calculates the 32-bit CRC using the standard IEEE 802.3 CRC polynomial and
+ * compares it to the value stored in the header.
+ *
+ * Returns: zero on success if the CRC matches, or -EBADMSG on an invalid CRC.
+ */
+static int pldm_verify_header_crc(struct pldmfw_priv *data)
+{
+	struct device *dev = data->context->dev;
+	u32 calculated_crc;
+	size_t length;
+
+	/* Calculate the 32-bit CRC of the header header contents up to but
+	 * not including the checksum. Note that the Linux crc32_le function
+	 * does not perform an expected final XOR.
+	 */
+	length = data->offset - sizeof(data->header_crc);
+	calculated_crc = crc32_le(~0, data->fw->data, length) ^ ~0;
+
+	if (calculated_crc != data->header_crc) {
+		dev_dbg(dev, "Invalid CRC in firmware header. Got 0x%08x but expected 0x%08x\n",
+			calculated_crc, data->header_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+/**
+ * pldmfw_free_priv - Free memory allocated while parsing the PLDM image
+ * @data: pointer to the PLDM data structure
+ *
+ * Loops through and clears all allocated memory associated with each
+ * allocated descriptor, record, and component.
+ */
+static void pldmfw_free_priv(struct pldmfw_priv *data)
+{
+	struct pldmfw_component *component, *c_safe;
+	struct pldmfw_record *record, *r_safe;
+	struct pldmfw_desc_tlv *desc, *d_safe;
+
+	list_for_each_entry_safe(component, c_safe, &data->components, entry) {
+		list_del(&component->entry);
+		kfree(component);
+	}
+
+	list_for_each_entry_safe(record, r_safe, &data->records, entry) {
+		list_for_each_entry_safe(desc, d_safe, &record->descs, entry) {
+			list_del(&desc->entry);
+			kfree(desc);
+		}
+
+		if (record->component_bitmap) {
+			bitmap_free(record->component_bitmap);
+			record->component_bitmap = NULL;
+		}
+
+		list_del(&record->entry);
+		kfree(record);
+	}
+}
+
+/**
+ * pldm_parse_image - parse and extract details from PLDM image
+ * @data: pointer to private data
+ *
+ * Verify that the firmware file contains valid data for a PLDM firmware
+ * file. Extract useful pointers and data from the firmware file and store
+ * them in the data structure.
+ *
+ * The PLDM firmware file format is defined in DMTF DSP0267 1.0.0. Care
+ * should be taken to use get_unaligned_le* when accessing data from the
+ * pointers in data.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_image(struct pldmfw_priv *data)
+{
+	int err;
+
+	if (WARN_ON(!(data->context->dev && data->fw->data && data->fw->size)))
+		return -EINVAL;
+
+	err = pldm_parse_header(data);
+	if (err)
+		return err;
+
+	err = pldm_parse_records(data);
+	if (err)
+		return err;
+
+	err = pldm_parse_components(data);
+	if (err)
+		return err;
+
+	return pldm_verify_header_crc(data);
+}
+
+/* these are u32 so that we can store PCI_ANY_ID */
+struct pldm_pci_record_id {
+	int vendor;
+	int device;
+	int subsystem_vendor;
+	int subsystem_device;
+};
+
+/**
+ * pldmfw_op_pci_match_record - Check if a PCI device matches the record
+ * @context: PLDM fw update structure
+ * @record: list of records extracted from the PLDM image
+ *
+ * Determine of the PCI device associated with this device matches the record
+ * data provided.
+ *
+ * Searches the descriptor TLVs and extracts the relevant descriptor data into
+ * a pldm_pci_record_id. This is then compared against the PCI device ID
+ * information.
+ *
+ * Returns: true if the device matches the record, false otherwise.
+ */
+bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pci_dev *pdev = to_pci_dev(context->dev);
+	struct pldm_pci_record_id id = {
+		.vendor = PCI_ANY_ID,
+		.device = PCI_ANY_ID,
+		.subsystem_vendor = PCI_ANY_ID,
+		.subsystem_device = PCI_ANY_ID,
+	};
+	struct pldmfw_desc_tlv *desc;
+
+	list_for_each_entry(desc, &record->descs, entry) {
+		u16 value;
+		int *ptr;
+
+		switch (desc->type) {
+		case PLDM_DESC_ID_PCI_VENDOR_ID:
+			ptr = &id.vendor;
+			break;
+		case PLDM_DESC_ID_PCI_DEVICE_ID:
+			ptr = &id.device;
+			break;
+		case PLDM_DESC_ID_PCI_SUBVENDOR_ID:
+			ptr = &id.subsystem_vendor;
+			break;
+		case PLDM_DESC_ID_PCI_SUBDEV_ID:
+			ptr = &id.subsystem_device;
+			break;
+		default:
+			/* Skip unrelated TLVs */
+			continue;
+		}
+
+		value = get_unaligned_le16(desc->data);
+		/* A value of zero for one of the descriptors is sometimes
+		 * used when the record should ignore this field when matching
+		 * device. For example if the record applies to any subsystem
+		 * device or vendor.
+		 */
+		if (value)
+			*ptr = (int)value;
+		else
+			*ptr = PCI_ANY_ID;
+	}
+
+	if ((id.vendor == PCI_ANY_ID || id.vendor == pdev->vendor) &&
+	    (id.device == PCI_ANY_ID || id.device == pdev->device) &&
+	    (id.subsystem_vendor == PCI_ANY_ID || id.subsystem_vendor == pdev->subsystem_vendor) &&
+	    (id.subsystem_device == PCI_ANY_ID || id.subsystem_device == pdev->subsystem_device))
+		return true;
+	else
+		return false;
+}
+EXPORT_SYMBOL(pldmfw_op_pci_match_record);
+
+/**
+ * pldm_find_matching_record - Find the first matching PLDM record
+ * @data: pointer to private data
+ *
+ * Search through PLDM records and find the first matching entry. It is
+ * expected that only one entry matches.
+ *
+ * Store a pointer to the matching record, if found.
+ *
+ * Returns: zero on success, or -ENOENT if no matching record is found.
+ */
+static int pldm_find_matching_record(struct pldmfw_priv *data)
+{
+	struct pldmfw_record *record;
+
+	list_for_each_entry(record, &data->records, entry) {
+		if (data->context->ops->match_record(data->context, record)) {
+			data->matching_record = record;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+/**
+ * pldm_send_package_data - Send firmware the package data for the record
+ * @data: pointer to private data
+ *
+ * Send the package data associated with the matching record to the firmware,
+ * using the send_pkg_data operation.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_send_package_data(struct pldmfw_priv *data)
+{
+	struct pldmfw_record *record = data->matching_record;
+	const struct pldmfw_ops *ops = data->context->ops;
+
+	return ops->send_package_data(data->context, record->package_data,
+				      record->package_data_len);
+}
+
+/**
+ * pldm_send_component_tables - Send component table information to firmware
+ * @data: pointer to private data
+ *
+ * Loop over each component, sending the applicable components to the firmware
+ * via the send_component_table operation.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_send_component_tables(struct pldmfw_priv *data)
+{
+	unsigned long *bitmap = data->matching_record->component_bitmap;
+	struct pldmfw_component *component;
+	int err;
+
+	list_for_each_entry(component, &data->components, entry) {
+		u8 index = component->index, transfer_flag = 0;
+
+		/* Skip components which are not intended for this device */
+		if (!test_bit(index, bitmap))
+			continue;
+
+		/* determine whether this is the start, middle, end, or both
+		 * the start and end of the component tables
+		 */
+		if (index == find_first_bit(bitmap, data->component_bitmap_len))
+			transfer_flag |= PLDM_TRANSFER_FLAG_START;
+		if (index == find_last_bit(bitmap, data->component_bitmap_len))
+			transfer_flag |= PLDM_TRANSFER_FLAG_END;
+		if (!transfer_flag)
+			transfer_flag = PLDM_TRANSFER_FLAG_MIDDLE;
+
+		err = data->context->ops->send_component_table(data->context,
+							       component,
+							       transfer_flag);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_flash_components - Program each component to device flash
+ * @data: pointer to private data
+ *
+ * Loop through each component that is active for the matching device record,
+ * and send it to the device driver for flashing.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_flash_components(struct pldmfw_priv *data)
+{
+	unsigned long *bitmap = data->matching_record->component_bitmap;
+	struct pldmfw_component *component;
+	int err;
+
+	list_for_each_entry(component, &data->components, entry) {
+		u8 index = component->index;
+
+		/* Skip components which are not intended for this device */
+		if (!test_bit(index, bitmap))
+			continue;
+
+		err = data->context->ops->flash_component(data->context, component);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_finalize_update - Finalize the device flash update
+ * @data: pointer to private data
+ *
+ * Tell the device driver to perform any remaining logic to complete the
+ * device update.
+ *
+ * Returns: zero on success, or a PLFM_FWU error indicating the reason for
+ * failure.
+ */
+static int pldm_finalize_update(struct pldmfw_priv *data)
+{
+	if (data->context->ops->finalize_update)
+		return data->context->ops->finalize_update(data->context);
+
+	return 0;
+}
+
+/**
+ * pldmfw_flash_image - Write a PLDM-formatted firmware image to the device
+ * @context: ops and data for firmware update
+ * @fw: firmware object pointing to the relevant firmware file to program
+ *
+ * Parse the data for a given firmware file, verifying that it is a valid PLDM
+ * formatted image that matches this device.
+ *
+ * Extract the device record Package Data and Component Tables and send them
+ * to the device firmware. Extract and write the flash data for each of the
+ * components indicated in the firmware file.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw)
+{
+	struct pldmfw_priv *data;
+	int err;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&data->records);
+	INIT_LIST_HEAD(&data->components);
+
+	data->fw = fw;
+	data->context = context;
+
+	err = pldm_parse_image(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_find_matching_record(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_send_package_data(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_send_component_tables(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_flash_components(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_finalize_update(data);
+
+out_release_data:
+	pldmfw_free_priv(data);
+	kfree(data);
+
+	return err;
+}
+EXPORT_SYMBOL(pldmfw_flash_image);
+
+MODULE_AUTHOR("Jacob Keller <jacob.e.keller@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("PLDM firmware flash update library");
diff --git a/lib/pldmfw/pldmfw_private.h b/lib/pldmfw/pldmfw_private.h
new file mode 100644
index 000000000000..687ef2200692
--- /dev/null
+++ b/lib/pldmfw/pldmfw_private.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2019, Intel Corporation. */
+
+#ifndef _PLDMFW_PRIVATE_H_
+#define _PLDMFW_PRIVATE_H_
+
+/* The following data structures define the layout of a firmware binary
+ * following the "PLDM For Firmware Update Specification", DMTF standard
+ * #DSP0267.
+ *
+ * pldmfw.c uses these structures to implement a simple engine that will parse
+ * a fw binary file in this format and perform a firmware update for a given
+ * device.
+ *
+ * Due to the variable sized data layout, alignment of fields within these
+ * structures is not guaranteed when reading. For this reason, all multi-byte
+ * field accesses should be done using the unaligned access macros.
+ * Additionally, the standard specifies that multi-byte fields are in
+ * LittleEndian format.
+ *
+ * The structure definitions are not made public, in order to keep direct
+ * accesses within code that is prepared to deal with the limitation of
+ * unaligned access.
+ */
+
+/* UUID for PLDM firmware packages: f018878c-cb7d-4943-9800-a02f059aca02 */
+static const uuid_t pldm_firmware_header_id =
+	UUID_INIT(0xf018878c, 0xcb7d, 0x4943,
+		  0x98, 0x00, 0xa0, 0x2f, 0x05, 0x9a, 0xca, 0x02);
+
+/* Revision number of the PLDM header format this code supports */
+#define PACKAGE_HEADER_FORMAT_REVISION 0x01
+
+/* timestamp104 structure defined in PLDM Base specification */
+#define PLDM_TIMESTAMP_SIZE 13
+struct __pldm_timestamp {
+	u8 b[PLDM_TIMESTAMP_SIZE];
+} __packed __aligned(1);
+
+/* Package Header Information */
+struct __pldm_header {
+	uuid_t id;			    /* PackageHeaderIdentifier */
+	u8 revision;			    /* PackageHeaderFormatRevision */
+	__le16 size;			    /* PackageHeaderSize */
+	struct __pldm_timestamp release_date; /* PackageReleaseDateTime */
+	__le16 component_bitmap_len;	    /* ComponentBitmapBitLength */
+	u8 version_type;		    /* PackageVersionStringType */
+	u8 version_len;			    /* PackageVersionStringLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * PackageVersionString, length is version_len.
+	 *
+	 * The total size of this section is
+	 *   sizeof(pldm_header) + version_len;
+	 */
+	u8 version_string[];		/* PackageVersionString */
+} __packed __aligned(1);
+
+/* Firmware Device ID Record */
+struct __pldmfw_record_info {
+	__le16 record_len;		/* RecordLength */
+	u8 descriptor_count;		/* DescriptorCount */
+	__le32 device_update_flags;	/* DeviceUpdateOptionFlags */
+	u8 version_type;		/* ComponentImageSetVersionType */
+	u8 version_len;			/* ComponentImageSetVersionLength */
+	__le16 package_data_len;	/* FirmwareDevicePackageDataLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * ApplicableComponents, length is component_bitmap_len from header
+	 * ComponentImageSetVersionString, length is version_len
+	 * RecordDescriptors, a series of TLVs with 16bit type and length
+	 * FirmwareDevicePackageData, length is package_data_len
+	 *
+	 * The total size of each record is
+	 *   sizeof(pldmfw_record_info) +
+	 *   component_bitmap_len (converted to bytes!) +
+	 *   version_len +
+	 *   <length of RecordDescriptors> +
+	 *   package_data_len
+	 */
+	u8 variable_record_data[];
+} __packed __aligned(1);
+
+/* Firmware Descriptor Definition */
+struct __pldmfw_desc_tlv {
+	__le16 type;			/* DescriptorType */
+	__le16 size;			/* DescriptorSize */
+	u8 data[];			/* DescriptorData */
+} __aligned(1);
+
+/* Firmware Device Identification Area */
+struct __pldmfw_record_area {
+	u8 record_count;		/* DeviceIDRecordCount */
+	/* This is not a struct type because the size of each record varies */
+	u8 records[];
+} __aligned(1);
+
+/* Individual Component Image Information */
+struct __pldmfw_component_info {
+	__le16 classification;		/* ComponentClassfication */
+	__le16 identifier;		/* ComponentIdentifier */
+	__le32 comparison_stamp;	/* ComponentComparisonStamp */
+	__le16 options;			/* componentOptions */
+	__le16 activation_method;	/* RequestedComponentActivationMethod */
+	__le32 location_offset;		/* ComponentLocationOffset */
+	__le32 size;			/* ComponentSize */
+	u8 version_type;		/* ComponentVersionStringType */
+	u8 version_len;		/* ComponentVersionStringLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * ComponentVersionString, length is version_len
+	 *
+	 * The total size of this section is
+	 *   sizeof(pldmfw_component_info) + version_len;
+	 */
+	u8 version_string[];		/* ComponentVersionString */
+} __packed __aligned(1);
+
+/* Component Image Information Area */
+struct __pldmfw_component_area {
+	__le16 component_image_count;
+	/* This is not a struct type because the component size varies */
+	u8 components[];
+} __aligned(1);
+
+/**
+ * pldm_first_desc_tlv
+ * @start: byte offset of the start of the descriptor TLVs
+ *
+ * Converts the starting offset of the descriptor TLVs into a pointer to the
+ * first descriptor.
+ */
+#define pldm_first_desc_tlv(start)					\
+	((const struct __pldmfw_desc_tlv *)(start))
+
+/**
+ * pldm_next_desc_tlv
+ * @desc: pointer to a descriptor TLV
+ *
+ * Finds the pointer to the next descriptor following a given descriptor
+ */
+#define pldm_next_desc_tlv(desc)						\
+	((const struct __pldmfw_desc_tlv *)((desc)->data +			\
+					     get_unaligned_le16(&(desc)->size)))
+
+/**
+ * pldm_for_each_desc_tlv
+ * @i: variable to store descriptor index
+ * @desc: variable to store descriptor pointer
+ * @start: byte offset of the start of the descriptors
+ * @count: the number of descriptors
+ *
+ * for loop macro to iterate over all of the descriptors of a given PLDM
+ * record.
+ */
+#define pldm_for_each_desc_tlv(i, desc, start, count)			\
+	for ((i) = 0, (desc) = pldm_first_desc_tlv(start);		\
+	     (i) < (count);						\
+	     (i)++, (desc) = pldm_next_desc_tlv(desc))
+
+/**
+ * pldm_first_record
+ * @start: byte offset of the start of the PLDM records
+ *
+ * Converts a starting offset of the PLDM records into a pointer to the first
+ * record.
+ */
+#define pldm_first_record(start)					\
+	((const struct __pldmfw_record_info *)(start))
+
+/**
+ * pldm_next_record
+ * @record: pointer to a PLDM record
+ *
+ * Finds a pointer to the next record following a given record
+ */
+#define pldm_next_record(record)					\
+	((const struct __pldmfw_record_info *)				\
+	 ((const u8 *)(record) + get_unaligned_le16(&(record)->record_len)))
+
+/**
+ * pldm_for_each_record
+ * @i: variable to store record index
+ * @record: variable to store record pointer
+ * @start: byte offset of the start of the records
+ * @count: the number of records
+ *
+ * for loop macro to iterate over all of the records of a PLDM file.
+ */
+#define pldm_for_each_record(i, record, start, count)			\
+	for ((i) = 0, (record) = pldm_first_record(start);		\
+	     (i) < (count);						\
+	     (i)++, (record) = pldm_next_record(record))
+
+/**
+ * pldm_first_component
+ * @start: byte offset of the start of the PLDM components
+ *
+ * Convert a starting offset of the PLDM components into a pointer to the
+ * first component
+ */
+#define pldm_first_component(start)					\
+	((const struct __pldmfw_component_info *)(start))
+
+/**
+ * pldm_next_component
+ * @component: pointer to a PLDM component
+ *
+ * Finds a pointer to the next component following a given component
+ */
+#define pldm_next_component(component)						\
+	((const struct __pldmfw_component_info *)((component)->version_string +	\
+						  (component)->version_len))
+
+/**
+ * pldm_for_each_component
+ * @i: variable to store component index
+ * @component: variable to store component pointer
+ * @start: byte offset to the start of the first component
+ * @count: the number of components
+ *
+ * for loop macro to iterate over all of the components of a PLDM file.
+ */
+#define pldm_for_each_component(i, component, start, count)		\
+	for ((i) = 0, (component) = pldm_first_component(start);	\
+	     (i) < (count);						\
+	     (i)++, (component) = pldm_next_component(component))
+
+#endif
-- 
cgit v1.2.3


From 1748f6a2cbc4694523f16da1c892b59861045b9d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 24 Jul 2020 20:12:53 +1000
Subject: rhashtable: Fix unprotected RCU dereference in __rht_ptr

The rcu_dereference call in rht_ptr_rcu is completely bogus because
we've already dereferenced the value in __rht_ptr and operated on it.
This causes potential double readings which could be fatal.  The RCU
dereference must occur prior to the comparison in __rht_ptr.

This patch changes the order of RCU dereference so that it is done
first and the result is then fed to __rht_ptr.  The RCU marking
changes have been minimised using casts which will be removed in
a follow-up patch.

Fixes: ba6306e3f648 ("rhashtable: Remove RCU marking from...")
Reported-by: "Gong, Sishuai" <sishuai@purdue.edu>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index d3432ee65de7..b8feb5da7c5a 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -349,11 +349,11 @@ static inline void rht_unlock(struct bucket_table *tbl,
 	local_bh_enable();
 }
 
-static inline struct rhash_head __rcu *__rht_ptr(
-	struct rhash_lock_head *const *bkt)
+static inline struct rhash_head *__rht_ptr(
+	struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt)
 {
-	return (struct rhash_head __rcu *)
-		((unsigned long)*bkt & ~BIT(0) ?:
+	return (struct rhash_head *)
+		((unsigned long)p & ~BIT(0) ?:
 		 (unsigned long)RHT_NULLS_MARKER(bkt));
 }
 
@@ -365,25 +365,26 @@ static inline struct rhash_head __rcu *__rht_ptr(
  *            access is guaranteed, such as when destroying the table.
  */
 static inline struct rhash_head *rht_ptr_rcu(
-	struct rhash_lock_head *const *bkt)
+	struct rhash_lock_head *const *p)
 {
-	struct rhash_head __rcu *p = __rht_ptr(bkt);
-
-	return rcu_dereference(p);
+	struct rhash_lock_head __rcu *const *bkt = (void *)p;
+	return __rht_ptr(rcu_dereference(*bkt), bkt);
 }
 
 static inline struct rhash_head *rht_ptr(
-	struct rhash_lock_head *const *bkt,
+	struct rhash_lock_head *const *p,
 	struct bucket_table *tbl,
 	unsigned int hash)
 {
-	return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash);
+	struct rhash_lock_head __rcu *const *bkt = (void *)p;
+	return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt);
 }
 
 static inline struct rhash_head *rht_ptr_exclusive(
-	struct rhash_lock_head *const *bkt)
+	struct rhash_lock_head *const *p)
 {
-	return rcu_dereference_protected(__rht_ptr(bkt), 1);
+	struct rhash_lock_head __rcu *const *bkt = (void *)p;
+	return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt);
 }
 
 static inline void rht_assign_locked(struct rhash_lock_head **bkt,
-- 
cgit v1.2.3


From ce9b362bf6db51a083c4221ef0f93c16cfb1facf Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 24 Jul 2020 20:14:34 +1000
Subject: rhashtable: Restore RCU marking on rhash_lock_head

This patch restores the RCU marking on bucket_table->buckets as
it really does need RCU protection.  Its removal had led to a fatal
bug.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 56 ++++++++++++++++++++--------------------------
 lib/rhashtable.c           | 35 +++++++++++++----------------
 2 files changed, 40 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index b8feb5da7c5a..68dab3e08aad 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -84,7 +84,7 @@ struct bucket_table {
 
 	struct lockdep_map	dep_map;
 
-	struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp;
+	struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
 /*
@@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void *arg);
 void rhashtable_destroy(struct rhashtable *ht);
 
-struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
-					   unsigned int hash);
-struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
-					     unsigned int hash);
-struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
-						  struct bucket_table *tbl,
-						  unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash);
+struct rhash_lock_head __rcu **__rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(
+	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash);
 
 #define rht_dereference(p, ht) \
 	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
@@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
 #define rht_entry(tpos, pos, member) \
 	({ tpos = container_of(pos, typeof(*tpos), member); 1; })
 
-static inline struct rhash_lock_head *const *rht_bucket(
+static inline struct rhash_lock_head __rcu *const *rht_bucket(
 	const struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_lock_head **rht_bucket_var(
+static inline struct rhash_lock_head __rcu **rht_bucket_var(
 	struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_lock_head **rht_bucket_insert(
+static inline struct rhash_lock_head __rcu **rht_bucket_insert(
 	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) :
@@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert(
  */
 
 static inline void rht_lock(struct bucket_table *tbl,
-			    struct rhash_lock_head **bkt)
+			    struct rhash_lock_head __rcu **bkt)
 {
 	local_bh_disable();
 	bit_spin_lock(0, (unsigned long *)bkt);
@@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl,
 }
 
 static inline void rht_lock_nested(struct bucket_table *tbl,
-				   struct rhash_lock_head **bucket,
+				   struct rhash_lock_head __rcu **bucket,
 				   unsigned int subclass)
 {
 	local_bh_disable();
@@ -342,7 +341,7 @@ static inline void rht_lock_nested(struct bucket_table *tbl,
 }
 
 static inline void rht_unlock(struct bucket_table *tbl,
-			      struct rhash_lock_head **bkt)
+			      struct rhash_lock_head __rcu **bkt)
 {
 	lock_map_release(&tbl->dep_map);
 	bit_spin_unlock(0, (unsigned long *)bkt);
@@ -365,48 +364,41 @@ static inline struct rhash_head *__rht_ptr(
  *            access is guaranteed, such as when destroying the table.
  */
 static inline struct rhash_head *rht_ptr_rcu(
-	struct rhash_lock_head *const *p)
+	struct rhash_lock_head __rcu *const *bkt)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rcu_dereference(*bkt), bkt);
 }
 
 static inline struct rhash_head *rht_ptr(
-	struct rhash_lock_head *const *p,
+	struct rhash_lock_head __rcu *const *bkt,
 	struct bucket_table *tbl,
 	unsigned int hash)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt);
 }
 
 static inline struct rhash_head *rht_ptr_exclusive(
-	struct rhash_lock_head *const *p)
+	struct rhash_lock_head __rcu *const *bkt)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt);
 }
 
-static inline void rht_assign_locked(struct rhash_lock_head **bkt,
+static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
 				     struct rhash_head *obj)
 {
-	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
-
 	if (rht_is_a_nulls(obj))
 		obj = NULL;
-	rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0)));
+	rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0)));
 }
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
-				     struct rhash_lock_head **bkt,
+				     struct rhash_lock_head __rcu **bkt,
 				     struct rhash_head *obj)
 {
-	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
-
 	if (rht_is_a_nulls(obj))
 		obj = NULL;
 	lock_map_release(&tbl->dep_map);
-	rcu_assign_pointer(*p, obj);
+	rcu_assign_pointer(*bkt, (void *)obj);
 	preempt_enable();
 	__release(bitlock);
 	local_bh_enable();
@@ -594,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_lock_head *const *bkt;
+	struct rhash_lock_head __rcu *const *bkt;
 	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -710,7 +702,7 @@ static inline void *__rhashtable_insert_fast(
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct bucket_table *tbl;
 	struct rhash_head *head;
@@ -996,7 +988,7 @@ static inline int __rhashtable_remove_fast_one(
 	struct rhash_head *obj, const struct rhashtable_params params,
 	bool rhlist)
 {
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -1148,7 +1140,7 @@ static inline int __rhashtable_replace_fast(
 	struct rhash_head *obj_old, struct rhash_head *obj_new,
 	const struct rhashtable_params params)
 {
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
 	unsigned int hash;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9f6890aedd1a..c949c1e3b87c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,7 +31,7 @@
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_lock_head *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -222,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 }
 
 static int rhashtable_rehash_one(struct rhashtable *ht,
-				 struct rhash_lock_head **bkt,
+				 struct rhash_lock_head __rcu **bkt,
 				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
@@ -275,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash);
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
 	if (!bkt)
@@ -485,7 +485,7 @@ fail:
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
-				   struct rhash_lock_head **bkt,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -535,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	return ERR_PTR(-ENOENT);
 }
 
-static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
-						  struct rhash_lock_head **bkt,
-						  struct bucket_table *tbl,
-						  unsigned int hash,
-						  struct rhash_head *obj,
-						  void *data)
+static struct bucket_table *rhashtable_insert_one(
+	struct rhashtable *ht, struct rhash_lock_head __rcu **bkt,
+	struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj,
+	void *data)
 {
 	struct bucket_table *new_tbl;
 	struct rhash_head *head;
@@ -591,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
 	void *data;
 
@@ -1173,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
-					     unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
@@ -1202,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(__rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
-					   unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
-	static struct rhash_lock_head *rhnull;
+	static struct rhash_lock_head __rcu *rhnull;
 
 	if (!rhnull)
 		INIT_RHT_NULLS_HEAD(rhnull);
@@ -1213,9 +1211,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
-						  struct bucket_table *tbl,
-						  unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(
+	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
-- 
cgit v1.2.3


From 2f3ee5e481ce850b5b51a306b01a5e9187b206ae Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Fri, 24 Jul 2020 13:11:42 -0500
Subject: remoteproc: kill IPA notify code

The IPA code now uses the generic remoteproc SSR notification
mechanism.  This makes the original IPA notification code unused
and unnecessary, so get rid of it.

This is effectively a revert of commit d7f5f3c89c1a ("remoteproc:
add IPA notification to q6v5 driver").

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Alex Elder <elder@linaro.org>
Link: https://lore.kernel.org/r/20200724181142.13581-3-elder@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/Kconfig                      |  4 --
 drivers/remoteproc/Makefile                     |  1 -
 drivers/remoteproc/qcom_q6v5_ipa_notify.c       | 85 -------------------------
 drivers/remoteproc/qcom_q6v5_mss.c              | 38 -----------
 include/linux/remoteproc/qcom_q6v5_ipa_notify.h | 82 ------------------------
 5 files changed, 210 deletions(-)
 delete mode 100644 drivers/remoteproc/qcom_q6v5_ipa_notify.c
 delete mode 100644 include/linux/remoteproc/qcom_q6v5_ipa_notify.h

(limited to 'include/linux')

diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 3e70d972a186..48315dc4a30c 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -154,7 +154,6 @@ config QCOM_Q6V5_MSS
 	select QCOM_MDT_LOADER
 	select QCOM_PIL_INFO
 	select QCOM_Q6V5_COMMON
-	select QCOM_Q6V5_IPA_NOTIFY
 	select QCOM_RPROC_COMMON
 	select QCOM_SCM
 	help
@@ -196,9 +195,6 @@ config QCOM_Q6V5_WCSS
 	  Say y here to support the Qualcomm Peripheral Image Loader for the
 	  Hexagon V5 based WCSS remote processors.
 
-config QCOM_Q6V5_IPA_NOTIFY
-	tristate
-
 config QCOM_SYSMON
 	tristate "Qualcomm sysmon driver"
 	depends on RPMSG
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 7ce1b8ef7677..4d4307dc8fa9 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -24,7 +24,6 @@ obj-$(CONFIG_QCOM_Q6V5_ADSP)		+= qcom_q6v5_adsp.o
 obj-$(CONFIG_QCOM_Q6V5_MSS)		+= qcom_q6v5_mss.o
 obj-$(CONFIG_QCOM_Q6V5_PAS)		+= qcom_q6v5_pas.o
 obj-$(CONFIG_QCOM_Q6V5_WCSS)		+= qcom_q6v5_wcss.o
-obj-$(CONFIG_QCOM_Q6V5_IPA_NOTIFY)	+= qcom_q6v5_ipa_notify.o
 obj-$(CONFIG_QCOM_SYSMON)		+= qcom_sysmon.o
 obj-$(CONFIG_QCOM_WCNSS_PIL)		+= qcom_wcnss_pil.o
 qcom_wcnss_pil-y			+= qcom_wcnss.o
diff --git a/drivers/remoteproc/qcom_q6v5_ipa_notify.c b/drivers/remoteproc/qcom_q6v5_ipa_notify.c
deleted file mode 100644
index e1c10a128bfd..000000000000
--- a/drivers/remoteproc/qcom_q6v5_ipa_notify.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/*
- * Qualcomm IPA notification subdev support
- *
- * Copyright (C) 2019 Linaro Ltd.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/remoteproc.h>
-#include <linux/remoteproc/qcom_q6v5_ipa_notify.h>
-
-static void
-ipa_notify_common(struct rproc_subdev *subdev, enum qcom_rproc_event event)
-{
-	struct qcom_rproc_ipa_notify *ipa_notify;
-	qcom_ipa_notify_t notify;
-
-	ipa_notify = container_of(subdev, struct qcom_rproc_ipa_notify, subdev);
-	notify = ipa_notify->notify;
-	if (notify)
-		notify(ipa_notify->data, event);
-}
-
-static int ipa_notify_prepare(struct rproc_subdev *subdev)
-{
-	ipa_notify_common(subdev, MODEM_STARTING);
-
-	return 0;
-}
-
-static int ipa_notify_start(struct rproc_subdev *subdev)
-{
-	ipa_notify_common(subdev, MODEM_RUNNING);
-
-	return 0;
-}
-
-static void ipa_notify_stop(struct rproc_subdev *subdev, bool crashed)
-
-{
-	ipa_notify_common(subdev, crashed ? MODEM_CRASHED : MODEM_STOPPING);
-}
-
-static void ipa_notify_unprepare(struct rproc_subdev *subdev)
-{
-	ipa_notify_common(subdev, MODEM_OFFLINE);
-}
-
-static void ipa_notify_removing(struct rproc_subdev *subdev)
-{
-	ipa_notify_common(subdev, MODEM_REMOVING);
-}
-
-/* Register the IPA notification subdevice with the Q6V5 MSS remoteproc */
-void qcom_add_ipa_notify_subdev(struct rproc *rproc,
-		struct qcom_rproc_ipa_notify *ipa_notify)
-{
-	ipa_notify->notify = NULL;
-	ipa_notify->data = NULL;
-	ipa_notify->subdev.prepare = ipa_notify_prepare;
-	ipa_notify->subdev.start = ipa_notify_start;
-	ipa_notify->subdev.stop = ipa_notify_stop;
-	ipa_notify->subdev.unprepare = ipa_notify_unprepare;
-
-	rproc_add_subdev(rproc, &ipa_notify->subdev);
-}
-EXPORT_SYMBOL_GPL(qcom_add_ipa_notify_subdev);
-
-/* Remove the IPA notification subdevice */
-void qcom_remove_ipa_notify_subdev(struct rproc *rproc,
-		struct qcom_rproc_ipa_notify *ipa_notify)
-{
-	struct rproc_subdev *subdev = &ipa_notify->subdev;
-
-	ipa_notify_removing(subdev);
-
-	rproc_remove_subdev(rproc, subdev);
-	ipa_notify->notify = NULL;	/* Make it obvious */
-}
-EXPORT_SYMBOL_GPL(qcom_remove_ipa_notify_subdev);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Qualcomm IPA notification remoteproc subdev");
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index ae3739082fdd..68f158931010 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -23,7 +23,6 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/remoteproc.h>
-#include "linux/remoteproc/qcom_q6v5_ipa_notify.h"
 #include <linux/reset.h>
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/iopoll.h>
@@ -197,7 +196,6 @@ struct q6v5 {
 	struct qcom_rproc_glink glink_subdev;
 	struct qcom_rproc_subdev smd_subdev;
 	struct qcom_rproc_ssr ssr_subdev;
-	struct qcom_rproc_ipa_notify ipa_notify_subdev;
 	struct qcom_sysmon *sysmon;
 	bool need_mem_protection;
 	bool has_alt_reset;
@@ -1607,39 +1605,6 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY)
-
-/* Register IPA notification function */
-int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify,
-			     void *data)
-{
-	struct qcom_rproc_ipa_notify *ipa_notify;
-	struct q6v5 *qproc = rproc->priv;
-
-	if (!notify)
-		return -EINVAL;
-
-	ipa_notify = &qproc->ipa_notify_subdev;
-	if (ipa_notify->notify)
-		return -EBUSY;
-
-	ipa_notify->notify = notify;
-	ipa_notify->data = data;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(qcom_register_ipa_notify);
-
-/* Deregister IPA notification function */
-void qcom_deregister_ipa_notify(struct rproc *rproc)
-{
-	struct q6v5 *qproc = rproc->priv;
-
-	qproc->ipa_notify_subdev.notify = NULL;
-}
-EXPORT_SYMBOL_GPL(qcom_deregister_ipa_notify);
-#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */
-
 static int q6v5_probe(struct platform_device *pdev)
 {
 	const struct rproc_hexagon_res *desc;
@@ -1766,7 +1731,6 @@ static int q6v5_probe(struct platform_device *pdev)
 	qcom_add_glink_subdev(rproc, &qproc->glink_subdev, "mpss");
 	qcom_add_smd_subdev(rproc, &qproc->smd_subdev);
 	qcom_add_ssr_subdev(rproc, &qproc->ssr_subdev, "mpss");
-	qcom_add_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev);
 	qproc->sysmon = qcom_add_sysmon_subdev(rproc, "modem", 0x12);
 	if (IS_ERR(qproc->sysmon)) {
 		ret = PTR_ERR(qproc->sysmon);
@@ -1782,7 +1746,6 @@ static int q6v5_probe(struct platform_device *pdev)
 remove_sysmon_subdev:
 	qcom_remove_sysmon_subdev(qproc->sysmon);
 remove_subdevs:
-	qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev);
 	qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev);
 	qcom_remove_smd_subdev(rproc, &qproc->smd_subdev);
 	qcom_remove_glink_subdev(rproc, &qproc->glink_subdev);
@@ -1804,7 +1767,6 @@ static int q6v5_remove(struct platform_device *pdev)
 	rproc_del(rproc);
 
 	qcom_remove_sysmon_subdev(qproc->sysmon);
-	qcom_remove_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev);
 	qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev);
 	qcom_remove_smd_subdev(rproc, &qproc->smd_subdev);
 	qcom_remove_glink_subdev(rproc, &qproc->glink_subdev);
diff --git a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h b/include/linux/remoteproc/qcom_q6v5_ipa_notify.h
deleted file mode 100644
index 0820edc0ab7d..000000000000
--- a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/* Copyright (C) 2019 Linaro Ltd. */
-
-#ifndef __QCOM_Q6V5_IPA_NOTIFY_H__
-#define __QCOM_Q6V5_IPA_NOTIFY_H__
-
-#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY)
-
-#include <linux/remoteproc.h>
-
-enum qcom_rproc_event {
-	MODEM_STARTING	= 0,	/* Modem is about to be started */
-	MODEM_RUNNING	= 1,	/* Startup complete; modem is operational */
-	MODEM_STOPPING	= 2,	/* Modem is about to shut down */
-	MODEM_CRASHED	= 3,	/* Modem has crashed (implies stopping) */
-	MODEM_OFFLINE	= 4,	/* Modem is now offline */
-	MODEM_REMOVING	= 5,	/* Modem is about to be removed */
-};
-
-typedef void (*qcom_ipa_notify_t)(void *data, enum qcom_rproc_event event);
-
-struct qcom_rproc_ipa_notify {
-	struct rproc_subdev subdev;
-
-	qcom_ipa_notify_t notify;
-	void *data;
-};
-
-/**
- * qcom_add_ipa_notify_subdev() - Register IPA notification subdevice
- * @rproc:	rproc handle
- * @ipa_notify:	IPA notification subdevice handle
- *
- * Register the @ipa_notify subdevice with the @rproc so modem events
- * can be sent to IPA when they occur.
- *
- * This is defined in "qcom_q6v5_ipa_notify.c".
- */
-void qcom_add_ipa_notify_subdev(struct rproc *rproc,
-		struct qcom_rproc_ipa_notify *ipa_notify);
-
-/**
- * qcom_remove_ipa_notify_subdev() - Remove IPA SSR subdevice
- * @rproc:	rproc handle
- * @ipa_notify:	IPA notification subdevice handle
- *
- * This is defined in "qcom_q6v5_ipa_notify.c".
- */
-void qcom_remove_ipa_notify_subdev(struct rproc *rproc,
-		struct qcom_rproc_ipa_notify *ipa_notify);
-
-/**
- * qcom_register_ipa_notify() - Register IPA notification function
- * @rproc:	Remote processor handle
- * @notify:	Non-null IPA notification callback function pointer
- * @data:	Data supplied to IPA notification callback function
- *
- * @Return: 0 if successful, or a negative error code otherwise
- *
- * This is defined in "qcom_q6v5_mss.c".
- */
-int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify,
-			     void *data);
-/**
- * qcom_deregister_ipa_notify() - Deregister IPA notification function
- * @rproc:	Remote processor handle
- *
- * This is defined in "qcom_q6v5_mss.c".
- */
-void qcom_deregister_ipa_notify(struct rproc *rproc);
-
-#else /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */
-
-struct qcom_rproc_ipa_notify { /* empty */ };
-
-#define qcom_add_ipa_notify_subdev(rproc, ipa_notify)		/* no-op */
-#define qcom_remove_ipa_notify_subdev(rproc, ipa_notify)	/* no-op */
-
-#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */
-
-#endif /* !__QCOM_Q6V5_IPA_NOTIFY_H__ */
-- 
cgit v1.2.3


From 48001ea50d17f3eb06a552e9ecf21f7fc01b25da Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 20 Jul 2020 15:08:18 -0700
Subject: PM, libnvdimm: Add runtime firmware activation support

Abstract platform specific mechanics for nvdimm firmware activation
behind a handful of generic ops. At the bus level ->activate_state()
indicates the unified state (idle, busy, armed) of all DIMMs on the bus,
and ->capability() indicates the system state expectations for activate.
At the DIMM level ->activate_state() indicates the per-DIMM state,
->activate_result() indicates the outcome of the last activation
attempt, and ->arm() attempts to transition the DIMM from 'idle' to
'armed'.

A new hibernate_quiet_exec() facility is added to support firmware
activation in an OS defined system quiesce state. It leverages the fact
that the hibernate-freeze state wants to assert that a memory
hibernation snapshot can be taken. This is in contrast to a platform
firmware defined quiesce state that may forcefully quiet the memory
controller independent of whether an individual device-driver properly
supports hibernate-freeze.

The libnvdimm sysfs interface is extended to support detection of a
firmware activate capability. The mechanism supports enumeration and
triggering of firmware activate, optionally in the
hibernate_quiet_exec() context.

[rafael: hibernate_quiet_exec() proposal]
[vishal: fix up sparse warning, grammar in Documentation/]

Cc: Pavel Machek <pavel@ucw.cz>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Co-developed-by: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Signed-off-by: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 Documentation/ABI/testing/sysfs-bus-nvdimm         |   2 +
 .../driver-api/nvdimm/firmware-activate.rst        |  86 ++++++++++++
 drivers/nvdimm/core.c                              | 149 +++++++++++++++++++++
 drivers/nvdimm/dimm_devs.c                         | 115 ++++++++++++++++
 drivers/nvdimm/nd-core.h                           |   1 +
 include/linux/libnvdimm.h                          |  44 ++++++
 include/linux/suspend.h                            |   6 +
 kernel/power/hibernate.c                           |  97 ++++++++++++++
 8 files changed, 500 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-nvdimm
 create mode 100644 Documentation/driver-api/nvdimm/firmware-activate.rst

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-nvdimm b/Documentation/ABI/testing/sysfs-bus-nvdimm
new file mode 100644
index 000000000000..d64380262be8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-nvdimm
@@ -0,0 +1,2 @@
+The libnvdimm sub-system implements a common sysfs interface for
+platform nvdimm resources. See Documentation/driver-api/nvdimm/.
diff --git a/Documentation/driver-api/nvdimm/firmware-activate.rst b/Documentation/driver-api/nvdimm/firmware-activate.rst
new file mode 100644
index 000000000000..7ee7decbbdc3
--- /dev/null
+++ b/Documentation/driver-api/nvdimm/firmware-activate.rst
@@ -0,0 +1,86 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+NVDIMM Runtime Firmware Activation
+==================================
+
+Some persistent memory devices run a firmware locally on the device /
+"DIMM" to perform tasks like media management, capacity provisioning,
+and health monitoring. The process of updating that firmware typically
+involves a reboot because it has implications for in-flight memory
+transactions. However, reboots are disruptive and at least the Intel
+persistent memory platform implementation, described by the Intel ACPI
+DSM specification [1], has added support for activating firmware at
+runtime.
+
+A native sysfs interface is implemented in libnvdimm to allow platform
+to advertise and control their local runtime firmware activation
+capability.
+
+The libnvdimm bus object, ndbusX, implements an ndbusX/firmware/activate
+attribute that shows the state of the firmware activation as one of 'idle',
+'armed', 'overflow', and 'busy'.
+
+- idle:
+  No devices are set / armed to activate firmware
+
+- armed:
+  At least one device is armed
+
+- busy:
+  In the busy state armed devices are in the process of transitioning
+  back to idle and completing an activation cycle.
+
+- overflow:
+  If the platform has a concept of incremental work needed to perform
+  the activation it could be the case that too many DIMMs are armed for
+  activation. In that scenario the potential for firmware activation to
+  timeout is indicated by the 'overflow' state.
+
+The 'ndbusX/firmware/activate' property can be written with a value of
+either 'live', or 'quiesce'. A value of 'quiesce' triggers the kernel to
+run firmware activation from within the equivalent of the hibernation
+'freeze' state where drivers and applications are notified to stop their
+modifications of system memory. A value of 'live' attempts
+firmware activation without this hibernation cycle. The
+'ndbusX/firmware/activate' property will be elided completely if no
+firmware activation capability is detected.
+
+Another property 'ndbusX/firmware/capability' indicates a value of
+'live' or 'quiesce', where 'live' indicates that the firmware
+does not require or inflict any quiesce period on the system to update
+firmware. A capability value of 'quiesce' indicates that firmware does
+expect and injects a quiet period for the memory controller, but 'live'
+may still be written to 'ndbusX/firmware/activate' as an override to
+assume the risk of racing firmware update with in-flight device and
+application activity. The 'ndbusX/firmware/capability' property will be
+elided completely if no firmware activation capability is detected.
+
+The libnvdimm memory-device / DIMM object, nmemX, implements
+'nmemX/firmware/activate' and 'nmemX/firmware/result' attributes to
+communicate the per-device firmware activation state. Similar to the
+'ndbusX/firmware/activate' attribute, the 'nmemX/firmware/activate'
+attribute indicates 'idle', 'armed', or 'busy'. The state transitions
+from 'armed' to 'idle' when the system is prepared to activate firmware,
+firmware staged + state set to armed, and 'ndbusX/firmware/activate' is
+triggered. After that activation event the nmemX/firmware/result
+attribute reflects the state of the last activation as one of:
+
+- none:
+  No runtime activation triggered since the last time the device was reset
+
+- success:
+  The last runtime activation completed successfully.
+
+- fail:
+  The last runtime activation failed for device-specific reasons.
+
+- not_staged:
+  The last runtime activation failed due to a sequencing error of the
+  firmware image not being staged.
+
+- need_reset:
+  Runtime firmware activation failed, but the firmware can still be
+  activated via the legacy method of power-cycling the system.
+
+[1]: https://docs.pmem.io/persistent-memory/
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index fe9bd6febdd2..c21ba0602029 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -4,6 +4,7 @@
  */
 #include <linux/libnvdimm.h>
 #include <linux/badblocks.h>
+#include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/blkdev.h>
@@ -389,8 +390,156 @@ static const struct attribute_group nvdimm_bus_attribute_group = {
 	.attrs = nvdimm_bus_attributes,
 };
 
+static ssize_t capability_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	enum nvdimm_fwa_capability cap;
+
+	if (!nd_desc->fw_ops)
+		return -EOPNOTSUPP;
+
+	nvdimm_bus_lock(dev);
+	cap = nd_desc->fw_ops->capability(nd_desc);
+	nvdimm_bus_unlock(dev);
+
+	switch (cap) {
+	case NVDIMM_FWA_CAP_QUIESCE:
+		return sprintf(buf, "quiesce\n");
+	case NVDIMM_FWA_CAP_LIVE:
+		return sprintf(buf, "live\n");
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static DEVICE_ATTR_RO(capability);
+
+static ssize_t activate_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	enum nvdimm_fwa_capability cap;
+	enum nvdimm_fwa_state state;
+
+	if (!nd_desc->fw_ops)
+		return -EOPNOTSUPP;
+
+	nvdimm_bus_lock(dev);
+	cap = nd_desc->fw_ops->capability(nd_desc);
+	state = nd_desc->fw_ops->activate_state(nd_desc);
+	nvdimm_bus_unlock(dev);
+
+	if (cap < NVDIMM_FWA_CAP_QUIESCE)
+		return -EOPNOTSUPP;
+
+	switch (state) {
+	case NVDIMM_FWA_IDLE:
+		return sprintf(buf, "idle\n");
+	case NVDIMM_FWA_BUSY:
+		return sprintf(buf, "busy\n");
+	case NVDIMM_FWA_ARMED:
+		return sprintf(buf, "armed\n");
+	case NVDIMM_FWA_ARM_OVERFLOW:
+		return sprintf(buf, "overflow\n");
+	default:
+		return -ENXIO;
+	}
+}
+
+static int exec_firmware_activate(void *data)
+{
+	struct nvdimm_bus_descriptor *nd_desc = data;
+
+	return nd_desc->fw_ops->activate(nd_desc);
+}
+
+static ssize_t activate_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	enum nvdimm_fwa_state state;
+	bool quiesce;
+	ssize_t rc;
+
+	if (!nd_desc->fw_ops)
+		return -EOPNOTSUPP;
+
+	if (sysfs_streq(buf, "live"))
+		quiesce = false;
+	else if (sysfs_streq(buf, "quiesce"))
+		quiesce = true;
+	else
+		return -EINVAL;
+
+	nvdimm_bus_lock(dev);
+	state = nd_desc->fw_ops->activate_state(nd_desc);
+
+	switch (state) {
+	case NVDIMM_FWA_BUSY:
+		rc = -EBUSY;
+		break;
+	case NVDIMM_FWA_ARMED:
+	case NVDIMM_FWA_ARM_OVERFLOW:
+		if (quiesce)
+			rc = hibernate_quiet_exec(exec_firmware_activate, nd_desc);
+		else
+			rc = nd_desc->fw_ops->activate(nd_desc);
+		break;
+	case NVDIMM_FWA_IDLE:
+	default:
+		rc = -ENXIO;
+	}
+	nvdimm_bus_unlock(dev);
+
+	if (rc == 0)
+		rc = len;
+	return rc;
+}
+
+static DEVICE_ATTR_ADMIN_RW(activate);
+
+static umode_t nvdimm_bus_firmware_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	enum nvdimm_fwa_capability cap;
+
+	/*
+	 * Both 'activate' and 'capability' disappear when no ops
+	 * detected, or a negative capability is indicated.
+	 */
+	if (!nd_desc->fw_ops)
+		return 0;
+
+	nvdimm_bus_lock(dev);
+	cap = nd_desc->fw_ops->capability(nd_desc);
+	nvdimm_bus_unlock(dev);
+
+	if (cap < NVDIMM_FWA_CAP_QUIESCE)
+		return 0;
+
+	return a->mode;
+}
+static struct attribute *nvdimm_bus_firmware_attributes[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_capability.attr,
+	NULL,
+};
+
+static const struct attribute_group nvdimm_bus_firmware_attribute_group = {
+	.name = "firmware",
+	.attrs = nvdimm_bus_firmware_attributes,
+	.is_visible = nvdimm_bus_firmware_visible,
+};
+
 const struct attribute_group *nvdimm_bus_attribute_groups[] = {
 	&nvdimm_bus_attribute_group,
+	&nvdimm_bus_firmware_attribute_group,
 	NULL,
 };
 
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index b7b77e8d9027..85b53a7f44f2 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -446,9 +446,124 @@ static const struct attribute_group nvdimm_attribute_group = {
 	.is_visible = nvdimm_visible,
 };
 
+static ssize_t result_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	enum nvdimm_fwa_result result;
+
+	if (!nvdimm->fw_ops)
+		return -EOPNOTSUPP;
+
+	nvdimm_bus_lock(dev);
+	result = nvdimm->fw_ops->activate_result(nvdimm);
+	nvdimm_bus_unlock(dev);
+
+	switch (result) {
+	case NVDIMM_FWA_RESULT_NONE:
+		return sprintf(buf, "none\n");
+	case NVDIMM_FWA_RESULT_SUCCESS:
+		return sprintf(buf, "success\n");
+	case NVDIMM_FWA_RESULT_FAIL:
+		return sprintf(buf, "fail\n");
+	case NVDIMM_FWA_RESULT_NOTSTAGED:
+		return sprintf(buf, "not_staged\n");
+	case NVDIMM_FWA_RESULT_NEEDRESET:
+		return sprintf(buf, "need_reset\n");
+	default:
+		return -ENXIO;
+	}
+}
+static DEVICE_ATTR_ADMIN_RO(result);
+
+static ssize_t activate_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	enum nvdimm_fwa_state state;
+
+	if (!nvdimm->fw_ops)
+		return -EOPNOTSUPP;
+
+	nvdimm_bus_lock(dev);
+	state = nvdimm->fw_ops->activate_state(nvdimm);
+	nvdimm_bus_unlock(dev);
+
+	switch (state) {
+	case NVDIMM_FWA_IDLE:
+		return sprintf(buf, "idle\n");
+	case NVDIMM_FWA_BUSY:
+		return sprintf(buf, "busy\n");
+	case NVDIMM_FWA_ARMED:
+		return sprintf(buf, "armed\n");
+	default:
+		return -ENXIO;
+	}
+}
+
+static ssize_t activate_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t len)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	enum nvdimm_fwa_trigger arg;
+	int rc;
+
+	if (!nvdimm->fw_ops)
+		return -EOPNOTSUPP;
+
+	if (sysfs_streq(buf, "arm"))
+		arg = NVDIMM_FWA_ARM;
+	else if (sysfs_streq(buf, "disarm"))
+		arg = NVDIMM_FWA_DISARM;
+	else
+		return -EINVAL;
+
+	nvdimm_bus_lock(dev);
+	rc = nvdimm->fw_ops->arm(nvdimm, arg);
+	nvdimm_bus_unlock(dev);
+
+	if (rc < 0)
+		return rc;
+	return len;
+}
+static DEVICE_ATTR_ADMIN_RW(activate);
+
+static struct attribute *nvdimm_firmware_attributes[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_result.attr,
+};
+
+static umode_t nvdimm_firmware_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	enum nvdimm_fwa_capability cap;
+
+	if (!nd_desc->fw_ops)
+		return 0;
+	if (!nvdimm->fw_ops)
+		return 0;
+
+	nvdimm_bus_lock(dev);
+	cap = nd_desc->fw_ops->capability(nd_desc);
+	nvdimm_bus_unlock(dev);
+
+	if (cap < NVDIMM_FWA_CAP_QUIESCE)
+		return 0;
+
+	return a->mode;
+}
+
+static const struct attribute_group nvdimm_firmware_attribute_group = {
+	.name = "firmware",
+	.attrs = nvdimm_firmware_attributes,
+	.is_visible = nvdimm_firmware_visible,
+};
+
 static const struct attribute_group *nvdimm_attribute_groups[] = {
 	&nd_device_attribute_group,
 	&nvdimm_attribute_group,
+	&nvdimm_firmware_attribute_group,
 	NULL,
 };
 
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index ddb9d97d9129..564faa36a3ca 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -45,6 +45,7 @@ struct nvdimm {
 		struct kernfs_node *overwrite_state;
 	} sec;
 	struct delayed_work dwork;
+	const struct nvdimm_fw_ops *fw_ops;
 };
 
 static inline unsigned long nvdimm_security_flags(
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index ad9898ece7d3..15dbcb718316 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -86,6 +86,7 @@ struct nvdimm_bus_descriptor {
 	int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc);
 	int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc,
 			struct nvdimm *nvdimm, unsigned int cmd, void *data);
+	const struct nvdimm_bus_fw_ops *fw_ops;
 };
 
 struct nd_cmd_desc {
@@ -200,6 +201,49 @@ struct nvdimm_security_ops {
 	int (*query_overwrite)(struct nvdimm *nvdimm);
 };
 
+enum nvdimm_fwa_state {
+	NVDIMM_FWA_INVALID,
+	NVDIMM_FWA_IDLE,
+	NVDIMM_FWA_ARMED,
+	NVDIMM_FWA_BUSY,
+	NVDIMM_FWA_ARM_OVERFLOW,
+};
+
+enum nvdimm_fwa_trigger {
+	NVDIMM_FWA_ARM,
+	NVDIMM_FWA_DISARM,
+};
+
+enum nvdimm_fwa_capability {
+	NVDIMM_FWA_CAP_INVALID,
+	NVDIMM_FWA_CAP_NONE,
+	NVDIMM_FWA_CAP_QUIESCE,
+	NVDIMM_FWA_CAP_LIVE,
+};
+
+enum nvdimm_fwa_result {
+	NVDIMM_FWA_RESULT_INVALID,
+	NVDIMM_FWA_RESULT_NONE,
+	NVDIMM_FWA_RESULT_SUCCESS,
+	NVDIMM_FWA_RESULT_NOTSTAGED,
+	NVDIMM_FWA_RESULT_NEEDRESET,
+	NVDIMM_FWA_RESULT_FAIL,
+};
+
+struct nvdimm_bus_fw_ops {
+	enum nvdimm_fwa_state (*activate_state)
+		(struct nvdimm_bus_descriptor *nd_desc);
+	enum nvdimm_fwa_capability (*capability)
+		(struct nvdimm_bus_descriptor *nd_desc);
+	int (*activate)(struct nvdimm_bus_descriptor *nd_desc);
+};
+
+struct nvdimm_fw_ops {
+	enum nvdimm_fwa_state (*activate_state)(struct nvdimm *nvdimm);
+	enum nvdimm_fwa_result (*activate_result)(struct nvdimm *nvdimm);
+	int (*arm)(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arg);
+};
+
 void badrange_init(struct badrange *badrange);
 int badrange_add(struct badrange *badrange, u64 addr, u64 length);
 void badrange_forget(struct badrange *badrange, phys_addr_t start,
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index b960098acfb0..cb9afad82a90 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -453,6 +453,8 @@ extern bool hibernation_available(void);
 asmlinkage int swsusp_save(void);
 extern struct pbe *restore_pblist;
 int pfn_is_nosave(unsigned long pfn);
+
+int hibernate_quiet_exec(int (*func)(void *data), void *data);
 #else /* CONFIG_HIBERNATION */
 static inline void register_nosave_region(unsigned long b, unsigned long e) {}
 static inline void register_nosave_region_late(unsigned long b, unsigned long e) {}
@@ -464,6 +466,10 @@ static inline void hibernation_set_ops(const struct platform_hibernation_ops *op
 static inline int hibernate(void) { return -ENOSYS; }
 static inline bool system_entering_hibernation(void) { return false; }
 static inline bool hibernation_available(void) { return false; }
+
+static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) {
+	return -ENOTSUPP;
+}
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 02ec716a4927..e6fab3f09c98 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -795,6 +795,103 @@ int hibernate(void)
 	return error;
 }
 
+/**
+ * hibernate_quiet_exec - Execute a function with all devices frozen.
+ * @func: Function to execute.
+ * @data: Data pointer to pass to @func.
+ *
+ * Return the @func return value or an error code if it cannot be executed.
+ */
+int hibernate_quiet_exec(int (*func)(void *data), void *data)
+{
+	int error, nr_calls = 0;
+
+	lock_system_sleep();
+
+	if (!hibernate_acquire()) {
+		error = -EBUSY;
+		goto unlock;
+	}
+
+	pm_prepare_console();
+
+	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
+		goto exit;
+	}
+
+	error = freeze_processes();
+	if (error)
+		goto exit;
+
+	lock_device_hotplug();
+
+	pm_suspend_clear_flags();
+
+	error = platform_begin(true);
+	if (error)
+		goto thaw;
+
+	error = freeze_kernel_threads();
+	if (error)
+		goto thaw;
+
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
+		goto dpm_complete;
+
+	suspend_console();
+
+	error = dpm_suspend(PMSG_FREEZE);
+	if (error)
+		goto dpm_resume;
+
+	error = dpm_suspend_end(PMSG_FREEZE);
+	if (error)
+		goto dpm_resume;
+
+	error = platform_pre_snapshot(true);
+	if (error)
+		goto skip;
+
+	error = func(data);
+
+skip:
+	platform_finish(true);
+
+	dpm_resume_start(PMSG_THAW);
+
+dpm_resume:
+	dpm_resume(PMSG_THAW);
+
+	resume_console();
+
+dpm_complete:
+	dpm_complete(PMSG_THAW);
+
+	thaw_kernel_threads();
+
+thaw:
+	platform_end(true);
+
+	unlock_device_hotplug();
+
+	thaw_processes();
+
+exit:
+	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+
+	pm_restore_console();
+
+	hibernate_release();
+
+unlock:
+	unlock_system_sleep();
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(hibernate_quiet_exec);
 
 /**
  * software_resume - Resume from a saved hibernation image.
-- 
cgit v1.2.3


From a1facc1fffc17a65e2c12a8de7434b9325ec0324 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 20 Jul 2020 15:08:24 -0700
Subject: ACPI: NFIT: Add runtime firmware activate support

Plumb the platform specific backend for the generic libnvdimm firmware
activate interface. Register dimm level operations to arm/disarm
activation, and register bus level operations to report the dynamic
platform-quiesce time relative to the number of dimms armed for firmware
activation.

A new nfit-specific bus attribute "firmware_activate_noidle" is added to
allow the activation to switch between platform enforced, and OS
opportunistic device quiesce. In other words, let the hibernate cycle
handle in-flight device-dma rather than the platform attempting to
increase PCI-E timeouts and the like.

Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 Documentation/ABI/testing/sysfs-bus-nfit |  19 ++
 drivers/acpi/nfit/core.c                 |  41 +++-
 drivers/acpi/nfit/intel.c                | 386 +++++++++++++++++++++++++++++++
 drivers/acpi/nfit/intel.h                |   3 +
 drivers/acpi/nfit/nfit.h                 |  10 +
 drivers/nvdimm/dimm_devs.c               |   4 +-
 include/linux/libnvdimm.h                |   5 +-
 7 files changed, 461 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-nfit b/Documentation/ABI/testing/sysfs-bus-nfit
index a1cb44dcb908..e4f76e7eab93 100644
--- a/Documentation/ABI/testing/sysfs-bus-nfit
+++ b/Documentation/ABI/testing/sysfs-bus-nfit
@@ -202,6 +202,25 @@ Description:
 		functions. See the section named 'NVDIMM Root Device _DSMs' in
 		the ACPI specification.
 
+What:		/sys/bus/nd/devices/ndbusX/nfit/firmware_activate_noidle
+Date:		Apr, 2020
+KernelVersion:	v5.8
+Contact:	linux-nvdimm@lists.01.org
+Description:
+		(RW) The Intel platform implementation of firmware activate
+		support exposes an option let the platform force idle devices in
+		the system over the activation event, or trust that the OS will
+		do it. The safe default is to let the platform force idle
+		devices since the kernel is already in a suspend state, and on
+		the chance that a driver does not properly quiesce bus-mastering
+		after a suspend callback the platform will handle it.  However,
+		the activation might abort if, for example, platform firmware
+		determines that the activation time exceeds the max PCI-E
+		completion timeout. Since the platform does not know whether the
+		OS is running the activation from a suspend context it aborts,
+		but if the system owner trusts driver suspend callback to be
+		sufficient then 'firmware_activation_noidle' can be
+		enabled to bypass the activation abort.
 
 What:		/sys/bus/nd/devices/regionX/nfit/range_index
 Date:		Jun, 2015
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 78cc9e2d2aa3..fb775b967c52 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1392,8 +1392,12 @@ static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
 
-	if (a == &dev_attr_scrub.attr && !ars_supported(nvdimm_bus))
-		return 0;
+	if (a == &dev_attr_scrub.attr)
+		return ars_supported(nvdimm_bus) ? a->mode : 0;
+
+	if (a == &dev_attr_firmware_activate_noidle.attr)
+		return intel_fwa_supported(nvdimm_bus) ? a->mode : 0;
+
 	return a->mode;
 }
 
@@ -1402,6 +1406,7 @@ static struct attribute *acpi_nfit_attributes[] = {
 	&dev_attr_scrub.attr,
 	&dev_attr_hw_error_scrub.attr,
 	&dev_attr_bus_dsm_mask.attr,
+	&dev_attr_firmware_activate_noidle.attr,
 	NULL,
 };
 
@@ -2019,6 +2024,26 @@ static const struct nvdimm_security_ops *acpi_nfit_get_security_ops(int family)
 	}
 }
 
+static const struct nvdimm_fw_ops *acpi_nfit_get_fw_ops(
+		struct nfit_mem *nfit_mem)
+{
+	unsigned long mask;
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+
+	if (!nd_desc->fw_ops)
+		return NULL;
+
+	if (nfit_mem->family != NVDIMM_FAMILY_INTEL)
+		return NULL;
+
+	mask = nfit_mem->dsm_mask & NVDIMM_INTEL_FW_ACTIVATE_CMDMASK;
+	if (mask != NVDIMM_INTEL_FW_ACTIVATE_CMDMASK)
+		return NULL;
+
+	return intel_fw_ops;
+}
+
 static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nfit_mem *nfit_mem;
@@ -2095,7 +2120,8 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 				acpi_nfit_dimm_attribute_groups,
 				flags, cmd_mask, flush ? flush->hint_count : 0,
 				nfit_mem->flush_wpq, &nfit_mem->id[0],
-				acpi_nfit_get_security_ops(nfit_mem->family));
+				acpi_nfit_get_security_ops(nfit_mem->family),
+				acpi_nfit_get_fw_ops(nfit_mem));
 		if (!nvdimm)
 			return -ENOMEM;
 
@@ -2170,8 +2196,10 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	if (acpi_desc->bus_cmd_force_en) {
 		nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
 		mask = &nd_desc->bus_family_mask;
-		if (acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL])
+		if (acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]) {
 			set_bit(NVDIMM_BUS_FAMILY_INTEL, mask);
+			nd_desc->fw_ops = intel_bus_fw_ops;
+		}
 	}
 
 	adev = to_acpi_dev(acpi_desc);
@@ -2202,6 +2230,11 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
 		if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
 			set_bit(i, mask);
+
+	if (*mask == dsm_mask) {
+		set_bit(NVDIMM_BUS_FAMILY_INTEL, &nd_desc->bus_family_mask);
+		nd_desc->fw_ops = intel_bus_fw_ops;
+	}
 }
 
 static ssize_t range_index_show(struct device *dev,
diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c
index 1113b679cd7b..8dd792a55730 100644
--- a/drivers/acpi/nfit/intel.c
+++ b/drivers/acpi/nfit/intel.c
@@ -7,6 +7,48 @@
 #include "intel.h"
 #include "nfit.h"
 
+static ssize_t firmware_activate_noidle_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	return sprintf(buf, "%s\n", acpi_desc->fwa_noidle ? "Y" : "N");
+}
+
+static ssize_t firmware_activate_noidle_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	ssize_t rc;
+	bool val;
+
+	rc = kstrtobool(buf, &val);
+	if (rc)
+		return rc;
+	if (val != acpi_desc->fwa_noidle)
+		acpi_desc->fwa_cap = NVDIMM_FWA_CAP_INVALID;
+	acpi_desc->fwa_noidle = val;
+	return size;
+}
+DEVICE_ATTR_RW(firmware_activate_noidle);
+
+bool intel_fwa_supported(struct nvdimm_bus *nvdimm_bus)
+{
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	unsigned long *mask;
+
+	if (!test_bit(NVDIMM_BUS_FAMILY_INTEL, &nd_desc->bus_family_mask))
+		return false;
+
+	mask = &acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL];
+	return *mask == NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK;
+}
+
 static unsigned long intel_security_flags(struct nvdimm *nvdimm,
 		enum nvdimm_passphrase_type ptype)
 {
@@ -389,3 +431,347 @@ static const struct nvdimm_security_ops __intel_security_ops = {
 };
 
 const struct nvdimm_security_ops *intel_security_ops = &__intel_security_ops;
+
+static int intel_bus_fwa_businfo(struct nvdimm_bus_descriptor *nd_desc,
+		struct nd_intel_bus_fw_activate_businfo *info)
+{
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_bus_fw_activate_businfo cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO,
+			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
+			.nd_size_out =
+				sizeof(struct nd_intel_bus_fw_activate_businfo),
+			.nd_fw_size =
+				sizeof(struct nd_intel_bus_fw_activate_businfo),
+		},
+	};
+	int rc;
+
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd),
+			NULL);
+	*info = nd_cmd.cmd;
+	return rc;
+}
+
+/* The fw_ops expect to be called with the nvdimm_bus_lock() held */
+static enum nvdimm_fwa_state intel_bus_fwa_state(
+		struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	struct nd_intel_bus_fw_activate_businfo info;
+	struct device *dev = acpi_desc->dev;
+	enum nvdimm_fwa_state state;
+	int rc;
+
+	/*
+	 * It should not be possible for platform firmware to return
+	 * busy because activate is a synchronous operation. Treat it
+	 * similar to invalid, i.e. always refresh / poll the status.
+	 */
+	switch (acpi_desc->fwa_state) {
+	case NVDIMM_FWA_INVALID:
+	case NVDIMM_FWA_BUSY:
+		break;
+	default:
+		/* check if capability needs to be refreshed */
+		if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID)
+			break;
+		return acpi_desc->fwa_state;
+	}
+
+	/* Refresh with platform firmware */
+	rc = intel_bus_fwa_businfo(nd_desc, &info);
+	if (rc)
+		return NVDIMM_FWA_INVALID;
+
+	switch (info.state) {
+	case ND_INTEL_FWA_IDLE:
+		state = NVDIMM_FWA_IDLE;
+		break;
+	case ND_INTEL_FWA_BUSY:
+		state = NVDIMM_FWA_BUSY;
+		break;
+	case ND_INTEL_FWA_ARMED:
+		if (info.activate_tmo > info.max_quiesce_tmo)
+			state = NVDIMM_FWA_ARM_OVERFLOW;
+		else
+			state = NVDIMM_FWA_ARMED;
+		break;
+	default:
+		dev_err_once(dev, "invalid firmware activate state %d\n",
+				info.state);
+		return NVDIMM_FWA_INVALID;
+	}
+
+	/*
+	 * Capability data is available in the same payload as state. It
+	 * is expected to be static.
+	 */
+	if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID) {
+		if (info.capability & ND_INTEL_BUS_FWA_CAP_FWQUIESCE)
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_QUIESCE;
+		else if (info.capability & ND_INTEL_BUS_FWA_CAP_OSQUIESCE) {
+			/*
+			 * Skip hibernate cycle by default if platform
+			 * indicates that it does not need devices to be
+			 * quiesced.
+			 */
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_LIVE;
+		} else
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_NONE;
+	}
+
+	acpi_desc->fwa_state = state;
+
+	return state;
+}
+
+static enum nvdimm_fwa_capability intel_bus_fwa_capability(
+		struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	if (acpi_desc->fwa_cap > NVDIMM_FWA_CAP_INVALID)
+		return acpi_desc->fwa_cap;
+
+	if (intel_bus_fwa_state(nd_desc) > NVDIMM_FWA_INVALID)
+		return acpi_desc->fwa_cap;
+
+	return NVDIMM_FWA_CAP_INVALID;
+}
+
+static int intel_bus_fwa_activate(struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_bus_fw_activate cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE,
+			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
+			.nd_size_in = sizeof(nd_cmd.cmd.iodev_state),
+			.nd_size_out =
+				sizeof(struct nd_intel_bus_fw_activate),
+			.nd_fw_size =
+				sizeof(struct nd_intel_bus_fw_activate),
+		},
+		/*
+		 * Even though activate is run from a suspended context,
+		 * for safety, still ask platform firmware to force
+		 * quiesce devices by default. Let a module
+		 * parameter override that policy.
+		 */
+		.cmd = {
+			.iodev_state = acpi_desc->fwa_noidle
+				? ND_INTEL_BUS_FWA_IODEV_OS_IDLE
+				: ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE,
+		},
+	};
+	int rc;
+
+	switch (intel_bus_fwa_state(nd_desc)) {
+	case NVDIMM_FWA_ARMED:
+	case NVDIMM_FWA_ARM_OVERFLOW:
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd),
+			NULL);
+
+	/*
+	 * Whether the command succeeded, or failed, the agent checking
+	 * for the result needs to query the DIMMs individually.
+	 * Increment the activation count to invalidate all the DIMM
+	 * states at once (it's otherwise not possible to take
+	 * acpi_desc->init_mutex in this context)
+	 */
+	acpi_desc->fwa_state = NVDIMM_FWA_INVALID;
+	acpi_desc->fwa_count++;
+
+	dev_dbg(acpi_desc->dev, "result: %d\n", rc);
+
+	return rc;
+}
+
+static const struct nvdimm_bus_fw_ops __intel_bus_fw_ops = {
+	.activate_state = intel_bus_fwa_state,
+	.capability = intel_bus_fwa_capability,
+	.activate = intel_bus_fwa_activate,
+};
+
+const struct nvdimm_bus_fw_ops *intel_bus_fw_ops = &__intel_bus_fw_ops;
+
+static int intel_fwa_dimminfo(struct nvdimm *nvdimm,
+		struct nd_intel_fw_activate_dimminfo *info)
+{
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_fw_activate_dimminfo cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_out =
+				sizeof(struct nd_intel_fw_activate_dimminfo),
+			.nd_fw_size =
+				sizeof(struct nd_intel_fw_activate_dimminfo),
+		},
+	};
+	int rc;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	*info = nd_cmd.cmd;
+	return rc;
+}
+
+static enum nvdimm_fwa_state intel_fwa_state(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+	struct nd_intel_fw_activate_dimminfo info;
+	int rc;
+
+	/*
+	 * Similar to the bus state, since activate is synchronous the
+	 * busy state should resolve within the context of 'activate'.
+	 */
+	switch (nfit_mem->fwa_state) {
+	case NVDIMM_FWA_INVALID:
+	case NVDIMM_FWA_BUSY:
+		break;
+	default:
+		/* If no activations occurred the old state is still valid */
+		if (nfit_mem->fwa_count == acpi_desc->fwa_count)
+			return nfit_mem->fwa_state;
+	}
+
+	rc = intel_fwa_dimminfo(nvdimm, &info);
+	if (rc)
+		return NVDIMM_FWA_INVALID;
+
+	switch (info.state) {
+	case ND_INTEL_FWA_IDLE:
+		nfit_mem->fwa_state = NVDIMM_FWA_IDLE;
+		break;
+	case ND_INTEL_FWA_BUSY:
+		nfit_mem->fwa_state = NVDIMM_FWA_BUSY;
+		break;
+	case ND_INTEL_FWA_ARMED:
+		nfit_mem->fwa_state = NVDIMM_FWA_ARMED;
+		break;
+	default:
+		nfit_mem->fwa_state = NVDIMM_FWA_INVALID;
+		break;
+	}
+
+	switch (info.result) {
+	case ND_INTEL_DIMM_FWA_NONE:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NONE;
+		break;
+	case ND_INTEL_DIMM_FWA_SUCCESS:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_SUCCESS;
+		break;
+	case ND_INTEL_DIMM_FWA_NOTSTAGED:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NOTSTAGED;
+		break;
+	case ND_INTEL_DIMM_FWA_NEEDRESET:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NEEDRESET;
+		break;
+	case ND_INTEL_DIMM_FWA_MEDIAFAILED:
+	case ND_INTEL_DIMM_FWA_ABORT:
+	case ND_INTEL_DIMM_FWA_NOTSUPP:
+	case ND_INTEL_DIMM_FWA_ERROR:
+	default:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_FAIL;
+		break;
+	}
+
+	nfit_mem->fwa_count = acpi_desc->fwa_count;
+
+	return nfit_mem->fwa_state;
+}
+
+static enum nvdimm_fwa_result intel_fwa_result(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+
+	if (nfit_mem->fwa_count == acpi_desc->fwa_count
+			&& nfit_mem->fwa_result > NVDIMM_FWA_RESULT_INVALID)
+		return nfit_mem->fwa_result;
+
+	if (intel_fwa_state(nvdimm) > NVDIMM_FWA_INVALID)
+		return nfit_mem->fwa_result;
+
+	return NVDIMM_FWA_RESULT_INVALID;
+}
+
+static int intel_fwa_arm(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_fw_activate_arm cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_ARM,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = sizeof(nd_cmd.cmd.activate_arm),
+			.nd_size_out =
+				sizeof(struct nd_intel_fw_activate_arm),
+			.nd_fw_size =
+				sizeof(struct nd_intel_fw_activate_arm),
+		},
+		.cmd = {
+			.activate_arm = arm == NVDIMM_FWA_ARM
+				? ND_INTEL_DIMM_FWA_ARM
+				: ND_INTEL_DIMM_FWA_DISARM,
+		},
+	};
+	int rc;
+
+	switch (intel_fwa_state(nvdimm)) {
+	case NVDIMM_FWA_INVALID:
+		return -ENXIO;
+	case NVDIMM_FWA_BUSY:
+		return -EBUSY;
+	case NVDIMM_FWA_IDLE:
+		if (arm == NVDIMM_FWA_DISARM)
+			return 0;
+		break;
+	case NVDIMM_FWA_ARMED:
+		if (arm == NVDIMM_FWA_ARM)
+			return 0;
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	/*
+	 * Invalidate the bus-level state, now that we're committed to
+	 * changing the 'arm' state.
+	 */
+	acpi_desc->fwa_state = NVDIMM_FWA_INVALID;
+	nfit_mem->fwa_state = NVDIMM_FWA_INVALID;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+
+	dev_dbg(acpi_desc->dev, "%s result: %d\n", arm == NVDIMM_FWA_ARM
+			? "arm" : "disarm", rc);
+	return rc;
+}
+
+static const struct nvdimm_fw_ops __intel_fw_ops = {
+	.activate_state = intel_fwa_state,
+	.activate_result = intel_fwa_result,
+	.arm = intel_fwa_arm,
+};
+
+const struct nvdimm_fw_ops *intel_fw_ops = &__intel_fw_ops;
diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h
index 49a598623024..b768234ccebc 100644
--- a/drivers/acpi/nfit/intel.h
+++ b/drivers/acpi/nfit/intel.h
@@ -169,4 +169,7 @@ struct nd_intel_bus_fw_activate {
 	u8 iodev_state;
 	u32 status;
 } __packed;
+
+extern const struct nvdimm_fw_ops *intel_fw_ops;
+extern const struct nvdimm_bus_fw_ops *intel_bus_fw_ops;
 #endif
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 97c122628975..67b7807ed200 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -220,6 +220,9 @@ struct nfit_mem {
 	struct list_head list;
 	struct acpi_device *adev;
 	struct acpi_nfit_desc *acpi_desc;
+	enum nvdimm_fwa_state fwa_state;
+	enum nvdimm_fwa_result fwa_result;
+	int fwa_count;
 	char id[NFIT_DIMM_ID_LEN+1];
 	struct resource *flush_wpq;
 	unsigned long dsm_mask;
@@ -265,6 +268,11 @@ struct acpi_nfit_desc {
 	unsigned int scrub_tmo;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
 			void *iobuf, u64 len, int rw);
+	enum nvdimm_fwa_state fwa_state;
+	enum nvdimm_fwa_capability fwa_cap;
+	int fwa_count;
+	bool fwa_noidle;
+	bool fwa_nosuspend;
 };
 
 enum scrub_mode {
@@ -367,4 +375,6 @@ void __acpi_nvdimm_notify(struct device *dev, u32 event);
 int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc);
 void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev);
+bool intel_fwa_supported(struct nvdimm_bus *nvdimm_bus);
+extern struct device_attribute dev_attr_firmware_activate_noidle;
 #endif /* __NFIT_H__ */
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 85b53a7f44f2..2f0815e15986 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -582,7 +582,8 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 		void *provider_data, const struct attribute_group **groups,
 		unsigned long flags, unsigned long cmd_mask, int num_flush,
 		struct resource *flush_wpq, const char *dimm_id,
-		const struct nvdimm_security_ops *sec_ops)
+		const struct nvdimm_security_ops *sec_ops,
+		const struct nvdimm_fw_ops *fw_ops)
 {
 	struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL);
 	struct device *dev;
@@ -612,6 +613,7 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 	dev->devt = MKDEV(nvdimm_major, nvdimm->id);
 	dev->groups = groups;
 	nvdimm->sec.ops = sec_ops;
+	nvdimm->fw_ops = fw_ops;
 	nvdimm->sec.overwrite_tmo = 0;
 	INIT_DELAYED_WORK(&nvdimm->dwork, nvdimm_security_overwrite_query);
 	/*
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 15dbcb718316..01f251b6e36c 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -269,14 +269,15 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 		void *provider_data, const struct attribute_group **groups,
 		unsigned long flags, unsigned long cmd_mask, int num_flush,
 		struct resource *flush_wpq, const char *dimm_id,
-		const struct nvdimm_security_ops *sec_ops);
+		const struct nvdimm_security_ops *sec_ops,
+		const struct nvdimm_fw_ops *fw_ops);
 static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 		void *provider_data, const struct attribute_group **groups,
 		unsigned long flags, unsigned long cmd_mask, int num_flush,
 		struct resource *flush_wpq)
 {
 	return __nvdimm_create(nvdimm_bus, provider_data, groups, flags,
-			cmd_mask, num_flush, flush_wpq, NULL, NULL);
+			cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL);
 }
 
 const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd);
-- 
cgit v1.2.3


From fe5e26a70cc544004b9aa9c3b96cb1d1cc132e09 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:30:15 -0700
Subject: nvme-fc: drop a duplicated word in a comment

Drop the repeated word "a" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/nvme-fc-driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 41e7795a3ee4..2a38f2b477a5 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -672,7 +672,7 @@ enum {
  * Values set by the LLDD indicating completion status of the FCP operation.
  * Must be set prior to calling the done() callback.
  * @transferred_length: amount of DATA_OUT payload data received by a
- *            a WRITEDATA operation. If not a WRITEDATA operation, value must
+ *            WRITEDATA operation. If not a WRITEDATA operation, value must
  *            be set to 0. Should equal transfer_length on success.
  * @fcp_error: status of the FCP operation. Must be 0 on success; on failure
  *            must be a NVME_SC_FC_xxxx value.
-- 
cgit v1.2.3


From c1fef73f793b7fd9d2ffcb5ef85807ea55bf7adb Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Fri, 24 Jul 2020 11:25:17 -0600
Subject: nvmet: add passthru code to process commands

Add passthru command handling capability for the NVMeOF target and
export passthru APIs which are used to integrate passthru
code with nvmet-core.

The new file passthru.c handles passthru cmd parsing and execution.
In the passthru mode, we create a block layer request from the nvmet
request and map the data on to the block layer request.

Admin commands and features are on an allow list as there are a number
of each that don't make too much sense with passthrough. We use an
allow list such that new commands can be considered before being blindly
passed through. In both cases, vendor specific commands are always
allowed.

We also reject reservation IO commands as the underlying device cannot
differentiate between multiple hosts behind a fabric.

Based-on-a-patch-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/Makefile    |   1 +
 drivers/nvme/target/admin-cmd.c |   7 +-
 drivers/nvme/target/core.c      |   3 +
 drivers/nvme/target/nvmet.h     |  39 ++++
 drivers/nvme/target/passthru.c  | 458 ++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme.h            |   4 +
 6 files changed, 510 insertions(+), 2 deletions(-)
 create mode 100644 drivers/nvme/target/passthru.c

(limited to 'include/linux')

diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
index 2b33836f3d3e..ebf91fc4c72e 100644
--- a/drivers/nvme/target/Makefile
+++ b/drivers/nvme/target/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_NVME_TARGET_TCP)		+= nvmet-tcp.o
 
 nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
 			discovery.o io-cmd-file.o io-cmd-bdev.o
+nvmet-$(CONFIG_NVME_TARGET_PASSTHRU)	+= passthru.o
 nvme-loop-y	+= loop.o
 nvmet-rdma-y	+= rdma.o
 nvmet-fc-y	+= fc.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 55918fcef80b..e9fe91786bbb 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -749,7 +749,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
 	return 0;
 }
 
-static void nvmet_execute_set_features(struct nvmet_req *req)
+void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
@@ -824,7 +824,7 @@ void nvmet_get_feat_async_event(struct nvmet_req *req)
 	nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
 }
 
-static void nvmet_execute_get_features(struct nvmet_req *req)
+void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
@@ -940,6 +940,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 	if (unlikely(ret))
 		return ret;
 
+	if (nvmet_req_passthru_ctrl(req))
+		return nvmet_parse_passthru_admin_cmd(req);
+
 	switch (cmd->common.opcode) {
 	case nvme_admin_get_log_page:
 		req->execute = nvmet_execute_get_log_page;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 59621b816f6e..c5a1c82e699b 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -849,6 +849,9 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	if (unlikely(ret))
 		return ret;
 
+	if (nvmet_req_passthru_ctrl(req))
+		return nvmet_parse_passthru_io_cmd(req);
+
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns)) {
 		req->error_loc = offsetof(struct nvme_common_command, nsid);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 49e14111446c..51719dc62083 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -242,6 +242,10 @@ struct nvmet_subsys {
 	struct config_group	allowed_hosts_group;
 
 	struct nvmet_subsys_model	__rcu *model;
+
+#ifdef CONFIG_NVME_TARGET_PASSTHRU
+	struct nvme_ctrl	*passthru_ctrl;
+#endif /* CONFIG_NVME_TARGET_PASSTHRU */
 };
 
 static inline struct nvmet_subsys *to_subsys(struct config_item *item)
@@ -321,6 +325,11 @@ struct nvmet_req {
 			struct bio_vec          *bvec;
 			struct work_struct      work;
 		} f;
+		struct {
+			struct request		*rq;
+			struct work_struct      work;
+			bool			use_workqueue;
+		} p;
 	};
 	int			sg_cnt;
 	int			metadata_sg_cnt;
@@ -400,6 +409,8 @@ void nvmet_req_complete(struct nvmet_req *req, u16 status);
 int nvmet_req_alloc_sgls(struct nvmet_req *req);
 void nvmet_req_free_sgls(struct nvmet_req *req);
 
+void nvmet_execute_set_features(struct nvmet_req *req);
+void nvmet_execute_get_features(struct nvmet_req *req);
 void nvmet_execute_keep_alive(struct nvmet_req *req);
 
 void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
@@ -532,6 +543,34 @@ static inline u32 nvmet_dsm_len(struct nvmet_req *req)
 		sizeof(struct nvme_dsm_range);
 }
 
+#ifdef CONFIG_NVME_TARGET_PASSTHRU
+u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req);
+u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req);
+static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
+{
+	return subsys->passthru_ctrl;
+}
+#else /* CONFIG_NVME_TARGET_PASSTHRU */
+static inline u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
+{
+	return 0;
+}
+static inline u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
+{
+	return 0;
+}
+static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
+{
+	return NULL;
+}
+#endif /* CONFIG_NVME_TARGET_PASSTHRU */
+
+static inline struct nvme_ctrl *
+nvmet_req_passthru_ctrl(struct nvmet_req *req)
+{
+	return nvmet_passthru_ctrl(req->sq->ctrl->subsys);
+}
+
 u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
 
 /* Convert a 32-bit number to a 16-bit 0's based number */
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
new file mode 100644
index 000000000000..b9727553ab30
--- /dev/null
+++ b/drivers/nvme/target/passthru.c
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe Over Fabrics Target Passthrough command implementation.
+ *
+ * Copyright (c) 2017-2018 Western Digital Corporation or its
+ * affiliates.
+ * Copyright (c) 2019-2020, Eideticom Inc.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+
+#include "../host/nvme.h"
+#include "nvmet.h"
+
+MODULE_IMPORT_NS(NVME_TARGET_PASSTHRU);
+
+static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_ctrl *pctrl = ctrl->subsys->passthru_ctrl;
+	u16 status = NVME_SC_SUCCESS;
+	struct nvme_id_ctrl *id;
+	u32 max_hw_sectors;
+	int page_shift;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return NVME_SC_INTERNAL;
+
+	status = nvmet_copy_from_sgl(req, 0, id, sizeof(*id));
+	if (status)
+		goto out_free;
+
+	id->cntlid = cpu_to_le16(ctrl->cntlid);
+	id->ver = cpu_to_le32(ctrl->subsys->ver);
+
+	/*
+	 * The passthru NVMe driver may have a limit on the number of segments
+	 * which depends on the host's memory fragementation. To solve this,
+	 * ensure mdts is limited to the pages equal to the number of segments.
+	 */
+	max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
+				      pctrl->max_hw_sectors);
+
+	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+
+	id->mdts = ilog2(max_hw_sectors) + 9 - page_shift;
+
+	id->acl = 3;
+	/*
+	 * We export aerl limit for the fabrics controller, update this when
+	 * passthru based aerl support is added.
+	 */
+	id->aerl = NVMET_ASYNC_EVENTS - 1;
+
+	/* emulate kas as most of the PCIe ctrl don't have a support for kas */
+	id->kas = cpu_to_le16(NVMET_KAS);
+
+	/* don't support host memory buffer */
+	id->hmpre = 0;
+	id->hmmin = 0;
+
+	id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
+	id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+
+	/* don't support fuse commands */
+	id->fuses = 0;
+
+	id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
+	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
+		id->sgls |= cpu_to_le32(1 << 2);
+	if (req->port->inline_data_size)
+		id->sgls |= cpu_to_le32(1 << 20);
+
+	/*
+	 * When passsthru controller is setup using nvme-loop transport it will
+	 * export the passthru ctrl subsysnqn (PCIe NVMe ctrl) and will fail in
+	 * the nvme/host/core.c in the nvme_init_subsystem()->nvme_active_ctrl()
+	 * code path with duplicate ctr subsynqn. In order to prevent that we
+	 * mask the passthru-ctrl subsysnqn with the target ctrl subsysnqn.
+	 */
+	memcpy(id->subnqn, ctrl->subsysnqn, sizeof(id->subnqn));
+
+	/* use fabric id-ctrl values */
+	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
+				req->port->inline_data_size) / 16);
+	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
+
+	id->msdbd = ctrl->ops->msdbd;
+
+	/* Support multipath connections with fabrics */
+	id->cmic |= 1 << 1;
+
+	/* Disable reservations, see nvmet_parse_passthru_io_cmd() */
+	id->oncs &= cpu_to_le16(~NVME_CTRL_ONCS_RESERVATIONS);
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(struct nvme_id_ctrl));
+
+out_free:
+	kfree(id);
+	return status;
+}
+
+static u16 nvmet_passthru_override_id_ns(struct nvmet_req *req)
+{
+	u16 status = NVME_SC_SUCCESS;
+	struct nvme_id_ns *id;
+	int i;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return NVME_SC_INTERNAL;
+
+	status = nvmet_copy_from_sgl(req, 0, id, sizeof(struct nvme_id_ns));
+	if (status)
+		goto out_free;
+
+	for (i = 0; i < (id->nlbaf + 1); i++)
+		if (id->lbaf[i].ms)
+			memset(&id->lbaf[i], 0, sizeof(id->lbaf[i]));
+
+	id->flbas = id->flbas & ~(1 << 4);
+
+	/*
+	 * Presently the NVMEof target code does not support sending
+	 * metadata, so we must disable it here. This should be updated
+	 * once target starts supporting metadata.
+	 */
+	id->mc = 0;
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
+out_free:
+	kfree(id);
+	return status;
+}
+
+static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, p.work);
+	struct request *rq = req->p.rq;
+	u16 status;
+
+	nvme_execute_passthru_rq(rq);
+
+	status = nvme_req(rq)->status;
+	if (status == NVME_SC_SUCCESS &&
+	    req->cmd->common.opcode == nvme_admin_identify) {
+		switch (req->cmd->identify.cns) {
+		case NVME_ID_CNS_CTRL:
+			nvmet_passthru_override_id_ctrl(req);
+			break;
+		case NVME_ID_CNS_NS:
+			nvmet_passthru_override_id_ns(req);
+			break;
+		}
+	}
+
+	req->cqe->result = nvme_req(rq)->result;
+	nvmet_req_complete(req, status);
+	blk_put_request(rq);
+}
+
+static void nvmet_passthru_req_done(struct request *rq,
+				    blk_status_t blk_status)
+{
+	struct nvmet_req *req = rq->end_io_data;
+
+	req->cqe->result = nvme_req(rq)->result;
+	nvmet_req_complete(req, nvme_req(rq)->status);
+	blk_put_request(rq);
+}
+
+static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
+{
+	int sg_cnt = req->sg_cnt;
+	struct scatterlist *sg;
+	int op_flags = 0;
+	struct bio *bio;
+	int i, ret;
+
+	if (req->cmd->common.opcode == nvme_cmd_flush)
+		op_flags = REQ_FUA;
+	else if (nvme_is_write(req->cmd))
+		op_flags = REQ_SYNC | REQ_IDLE;
+
+	bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
+	bio->bi_end_io = bio_put;
+	bio->bi_opf = req_op(rq) | op_flags;
+
+	for_each_sg(req->sg, sg, req->sg_cnt, i) {
+		if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
+				    sg->offset) < sg->length) {
+			bio_put(bio);
+			return -EINVAL;
+		}
+		sg_cnt--;
+	}
+
+	ret = blk_rq_append_bio(rq, &bio);
+	if (unlikely(ret)) {
+		bio_put(bio);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
+{
+	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
+	struct request_queue *q = ctrl->admin_q;
+	struct nvme_ns *ns = NULL;
+	struct request *rq = NULL;
+	u32 effects;
+	u16 status;
+	int ret;
+
+	if (likely(req->sq->qid != 0)) {
+		u32 nsid = le32_to_cpu(req->cmd->common.nsid);
+
+		ns = nvme_find_get_ns(ctrl, nsid);
+		if (unlikely(!ns)) {
+			pr_err("failed to get passthru ns nsid:%u\n", nsid);
+			status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+			goto fail_out;
+		}
+
+		q = ns->queue;
+	}
+
+	rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
+	if (IS_ERR(rq)) {
+		rq = NULL;
+		status = NVME_SC_INTERNAL;
+		goto fail_out;
+	}
+
+	if (req->sg_cnt) {
+		ret = nvmet_passthru_map_sg(req, rq);
+		if (unlikely(ret)) {
+			status = NVME_SC_INTERNAL;
+			goto fail_out;
+		}
+	}
+
+	/*
+	 * If there are effects for the command we are about to execute, or
+	 * an end_req function we need to use nvme_execute_passthru_rq()
+	 * synchronously in a work item seeing the end_req function and
+	 * nvme_passthru_end() can't be called in the request done callback
+	 * which is typically in interrupt context.
+	 */
+	effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
+	if (req->p.use_workqueue || effects) {
+		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
+		req->p.rq = rq;
+		schedule_work(&req->p.work);
+	} else {
+		rq->end_io_data = req;
+		blk_execute_rq_nowait(rq->q, ns ? ns->disk : NULL, rq, 0,
+				      nvmet_passthru_req_done);
+	}
+
+	if (ns)
+		nvme_put_ns(ns);
+
+	return;
+
+fail_out:
+	if (ns)
+		nvme_put_ns(ns);
+	nvmet_req_complete(req, status);
+	blk_put_request(rq);
+}
+
+/*
+ * We need to emulate set host behaviour to ensure that any requested
+ * behaviour of the target's host matches the requested behaviour
+ * of the device's host and fail otherwise.
+ */
+static void nvmet_passthru_set_host_behaviour(struct nvmet_req *req)
+{
+	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
+	struct nvme_feat_host_behavior *host;
+	u16 status = NVME_SC_INTERNAL;
+	int ret;
+
+	host = kzalloc(sizeof(*host) * 2, GFP_KERNEL);
+	if (!host)
+		goto out_complete_req;
+
+	ret = nvme_get_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0,
+				host, sizeof(*host), NULL);
+	if (ret)
+		goto out_free_host;
+
+	status = nvmet_copy_from_sgl(req, 0, &host[1], sizeof(*host));
+	if (status)
+		goto out_free_host;
+
+	if (memcmp(&host[0], &host[1], sizeof(host[0]))) {
+		pr_warn("target host has requested different behaviour from the local host\n");
+		status = NVME_SC_INTERNAL;
+	}
+
+out_free_host:
+	kfree(host);
+out_complete_req:
+	nvmet_req_complete(req, status);
+}
+
+static u16 nvmet_setup_passthru_command(struct nvmet_req *req)
+{
+	req->p.use_workqueue = false;
+	req->execute = nvmet_passthru_execute_cmd;
+	return NVME_SC_SUCCESS;
+}
+
+u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
+{
+	switch (req->cmd->common.opcode) {
+	case nvme_cmd_resv_register:
+	case nvme_cmd_resv_report:
+	case nvme_cmd_resv_acquire:
+	case nvme_cmd_resv_release:
+		/*
+		 * Reservations cannot be supported properly because the
+		 * underlying device has no way of differentiating different
+		 * hosts that connect via fabrics. This could potentially be
+		 * emulated in the future if regular targets grow support for
+		 * this feature.
+		 */
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+
+	return nvmet_setup_passthru_command(req);
+}
+
+/*
+ * Only features that are emulated or specifically allowed in the list  are
+ * passed down to the controller. This function implements the allow list for
+ * both get and set features.
+ */
+static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
+{
+	switch (le32_to_cpu(req->cmd->features.fid)) {
+	case NVME_FEAT_ARBITRATION:
+	case NVME_FEAT_POWER_MGMT:
+	case NVME_FEAT_LBA_RANGE:
+	case NVME_FEAT_TEMP_THRESH:
+	case NVME_FEAT_ERR_RECOVERY:
+	case NVME_FEAT_VOLATILE_WC:
+	case NVME_FEAT_WRITE_ATOMIC:
+	case NVME_FEAT_AUTO_PST:
+	case NVME_FEAT_TIMESTAMP:
+	case NVME_FEAT_HCTM:
+	case NVME_FEAT_NOPSC:
+	case NVME_FEAT_RRL:
+	case NVME_FEAT_PLM_CONFIG:
+	case NVME_FEAT_PLM_WINDOW:
+	case NVME_FEAT_HOST_BEHAVIOR:
+	case NVME_FEAT_SANITIZE:
+	case NVME_FEAT_VENDOR_START ... NVME_FEAT_VENDOR_END:
+		return nvmet_setup_passthru_command(req);
+
+	case NVME_FEAT_ASYNC_EVENT:
+		/* There is no support for forwarding ASYNC events */
+	case NVME_FEAT_IRQ_COALESCE:
+	case NVME_FEAT_IRQ_CONFIG:
+		/* The IRQ settings will not apply to the target controller */
+	case NVME_FEAT_HOST_MEM_BUF:
+		/*
+		 * Any HMB that's set will not be passed through and will
+		 * not work as expected
+		 */
+	case NVME_FEAT_SW_PROGRESS:
+		/*
+		 * The Pre-Boot Software Load Count doesn't make much
+		 * sense for a target to export
+		 */
+	case NVME_FEAT_RESV_MASK:
+	case NVME_FEAT_RESV_PERSIST:
+		/* No reservations, see nvmet_parse_passthru_io_cmd() */
+	default:
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+}
+
+u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
+{
+	/*
+	 * Passthru all vendor specific commands
+	 */
+	if (req->cmd->common.opcode >= nvme_admin_vendor_start)
+		return nvmet_setup_passthru_command(req);
+
+	switch (req->cmd->common.opcode) {
+	case nvme_admin_async_event:
+		req->execute = nvmet_execute_async_event;
+		return NVME_SC_SUCCESS;
+	case nvme_admin_keep_alive:
+		/*
+		 * Most PCIe ctrls don't support keep alive cmd, we route keep
+		 * alive to the non-passthru mode. In future please change this
+		 * code when PCIe ctrls with keep alive support available.
+		 */
+		req->execute = nvmet_execute_keep_alive;
+		return NVME_SC_SUCCESS;
+	case nvme_admin_set_features:
+		switch (le32_to_cpu(req->cmd->features.fid)) {
+		case NVME_FEAT_ASYNC_EVENT:
+		case NVME_FEAT_KATO:
+		case NVME_FEAT_NUM_QUEUES:
+		case NVME_FEAT_HOST_ID:
+			req->execute = nvmet_execute_set_features;
+			return NVME_SC_SUCCESS;
+		case NVME_FEAT_HOST_BEHAVIOR:
+			req->execute = nvmet_passthru_set_host_behaviour;
+			return NVME_SC_SUCCESS;
+		default:
+			return nvmet_passthru_get_set_features(req);
+		}
+		break;
+	case nvme_admin_get_features:
+		switch (le32_to_cpu(req->cmd->features.fid)) {
+		case NVME_FEAT_ASYNC_EVENT:
+		case NVME_FEAT_KATO:
+		case NVME_FEAT_NUM_QUEUES:
+		case NVME_FEAT_HOST_ID:
+			req->execute = nvmet_execute_get_features;
+			return NVME_SC_SUCCESS;
+		default:
+			return nvmet_passthru_get_set_features(req);
+		}
+		break;
+	case nvme_admin_identify:
+		switch (req->cmd->identify.cns) {
+		case NVME_ID_CNS_CTRL:
+			req->execute = nvmet_passthru_execute_cmd;
+			req->p.use_workqueue = true;
+			return NVME_SC_SUCCESS;
+		case NVME_ID_CNS_NS:
+			req->execute = nvmet_passthru_execute_cmd;
+			req->p.use_workqueue = true;
+			return NVME_SC_SUCCESS;
+		default:
+			return nvmet_setup_passthru_command(req);
+		}
+	case nvme_admin_get_log_page:
+		return nvmet_setup_passthru_command(req);
+	default:
+		/* Reject commands not in the allowlist above */
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+}
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 1643005d21e3..d92535997687 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -312,6 +312,7 @@ enum {
 	NVME_CTRL_ONCS_WRITE_UNCORRECTABLE	= 1 << 1,
 	NVME_CTRL_ONCS_DSM			= 1 << 2,
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
+	NVME_CTRL_ONCS_RESERVATIONS		= 1 << 5,
 	NVME_CTRL_ONCS_TIMESTAMP		= 1 << 6,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
@@ -982,6 +983,7 @@ enum nvme_admin_opcode {
 	nvme_admin_security_recv	= 0x82,
 	nvme_admin_sanitize_nvm		= 0x84,
 	nvme_admin_get_lba_status	= 0x86,
+	nvme_admin_vendor_start		= 0xC0,
 };
 
 #define nvme_admin_opcode_name(opcode)	{ opcode, #opcode }
@@ -1045,6 +1047,8 @@ enum {
 	NVME_FEAT_RESV_MASK	= 0x82,
 	NVME_FEAT_RESV_PERSIST	= 0x83,
 	NVME_FEAT_WRITE_PROTECT	= 0x84,
+	NVME_FEAT_VENDOR_START	= 0xC0,
+	NVME_FEAT_VENDOR_END	= 0xFF,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
-- 
cgit v1.2.3


From 13685c4a08fca9dd76bf53bfcbadc044ab2a08cb Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@arm.com>
Date: Thu, 16 Jul 2020 12:03:45 +0100
Subject: sched/uclamp: Add a new sysctl to control RT default boost value

RT tasks by default run at the highest capacity/performance level. When
uclamp is selected this default behavior is retained by enforcing the
requested uclamp.min (p->uclamp_req[UCLAMP_MIN]) of the RT tasks to be
uclamp_none(UCLAMP_MAX), which is SCHED_CAPACITY_SCALE; the maximum
value.

This is also referred to as 'the default boost value of RT tasks'.

See commit 1a00d999971c ("sched/uclamp: Set default clamps for RT tasks").

On battery powered devices, it is desired to control this default
(currently hardcoded) behavior at runtime to reduce energy consumed by
RT tasks.

For example, a mobile device manufacturer where big.LITTLE architecture
is dominant, the performance of the little cores varies across SoCs, and
on high end ones the big cores could be too power hungry.

Given the diversity of SoCs, the new knob allows manufactures to tune
the best performance/power for RT tasks for the particular hardware they
run on.

They could opt to further tune the value when the user selects
a different power saving mode or when the device is actively charging.

The runtime aspect of it further helps in creating a single kernel image
that can be run on multiple devices that require different tuning.

Keep in mind that a lot of RT tasks in the system are created by the
kernel. On Android for instance I can see over 50 RT tasks, only
a handful of which created by the Android framework.

To control the default behavior globally by system admins and device
integrator, introduce the new sysctl_sched_uclamp_util_min_rt_default
to change the default boost value of the RT tasks.

I anticipate this to be mostly in the form of modifying the init script
of a particular device.

To avoid polluting the fast path with unnecessary code, the approach
taken is to synchronously do the update by traversing all the existing
tasks in the system. This could race with a concurrent fork(), which is
dealt with by introducing sched_post_fork() function which will ensure
the racy fork will get the right update applied.

Tested on Juno-r2 in combination with the RT capacity awareness [1].
By default an RT task will go to the highest capacity CPU and run at the
maximum frequency, which is particularly energy inefficient on high end
mobile devices because the biggest core[s] are 'huge' and power hungry.

With this patch the RT task can be controlled to run anywhere by
default, and doesn't cause the frequency to be maximum all the time.
Yet any task that really needs to be boosted can easily escape this
default behavior by modifying its requested uclamp.min value
(p->uclamp_req[UCLAMP_MIN]) via sched_setattr() syscall.

[1] 804d402fb6f6: ("sched/rt: Make RT capacity-aware")

Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200716110347.19553-2-qais.yousef@arm.com
---
 include/linux/sched.h        |  10 +++-
 include/linux/sched/sysctl.h |   1 +
 include/linux/sched/task.h   |   1 +
 kernel/fork.c                |   1 +
 kernel/sched/core.c          | 119 ++++++++++++++++++++++++++++++++++++++++---
 kernel/sysctl.c              |   7 +++
 6 files changed, 131 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index adf0125190d4..a6bf77c34687 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -686,9 +686,15 @@ struct task_struct {
 	struct sched_dl_entity		dl;
 
 #ifdef CONFIG_UCLAMP_TASK
-	/* Clamp values requested for a scheduling entity */
+	/*
+	 * Clamp values requested for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp_req[UCLAMP_CNT];
-	/* Effective clamp values used for a scheduling entity */
+	/*
+	 * Effective clamp values used for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp[UCLAMP_CNT];
 #endif
 
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 24be30a40814..3c31ba88aca5 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -67,6 +67,7 @@ extern unsigned int sysctl_sched_dl_period_min;
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
+extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 #endif
 
 #ifdef CONFIG_CFS_BANDWIDTH
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 38359071236a..e7ddab095baf 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -55,6 +55,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 void __noreturn do_task_dead(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index efc5493203ae..e75c2e41f3d1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2304,6 +2304,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
+	sched_post_fork(p);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e44d83f3e0e6..12e1f3a2cabc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -889,6 +889,23 @@ unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 /* Max allowed maximum utilization */
 unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
+/*
+ * By default RT tasks run at the maximum performance point/capacity of the
+ * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
+ * SCHED_CAPACITY_SCALE.
+ *
+ * This knob allows admins to change the default behavior when uclamp is being
+ * used. In battery powered devices, particularly, running at the maximum
+ * capacity and frequency will increase energy consumption and shorten the
+ * battery life.
+ *
+ * This knob only affects RT tasks that their uclamp_se->user_defined == false.
+ *
+ * This knob will not override the system default sched_util_clamp_min defined
+ * above.
+ */
+unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
@@ -991,6 +1008,64 @@ unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static void __uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	unsigned int default_util_min;
+	struct uclamp_se *uc_se;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	uc_se = &p->uclamp_req[UCLAMP_MIN];
+
+	/* Only sync if user didn't override the default */
+	if (uc_se->user_defined)
+		return;
+
+	default_util_min = sysctl_sched_uclamp_util_min_rt_default;
+	uclamp_se_set(uc_se, default_util_min, false);
+}
+
+static void uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	if (!rt_task(p))
+		return;
+
+	/* Protect updates to p->uclamp_* */
+	rq = task_rq_lock(p, &rf);
+	__uclamp_update_util_min_rt_default(p);
+	task_rq_unlock(rq, p, &rf);
+}
+
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	for_each_process_thread(g, p)
+		uclamp_update_util_min_rt_default(p);
+	rcu_read_unlock();
+}
+
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -1278,12 +1353,13 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
-	int old_min, old_max;
+	int old_min, old_max, old_min_rt;
 	int result;
 
 	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
+	old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
 
 	result = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (result)
@@ -1292,7 +1368,9 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		goto done;
 
 	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
-	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
+	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
+
 		result = -EINVAL;
 		goto undo;
 	}
@@ -1313,6 +1391,11 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		uclamp_update_root_tg();
 	}
 
+	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
+		static_branch_enable(&sched_uclamp_used);
+		uclamp_sync_util_min_rt_default();
+	}
+
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
 	 * Otherwise, keep it simple and do just a lazy update at each next
@@ -1324,6 +1407,7 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
+	sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
 done:
 	mutex_unlock(&uclamp_mutex);
 
@@ -1369,17 +1453,20 @@ static void __setscheduler_uclamp(struct task_struct *p,
 	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
-		unsigned int clamp_value = uclamp_none(clamp_id);
 
 		/* Keep using defined clamps across class changes */
 		if (uc_se->user_defined)
 			continue;
 
-		/* By default, RT tasks always get 100% boost */
+		/*
+		 * RT by default have a 100% boost value that could be modified
+		 * at runtime.
+		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+			__uclamp_update_util_min_rt_default(p);
+		else
+			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 
-		uclamp_se_set(uc_se, clamp_value, false);
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
@@ -1400,6 +1487,10 @@ static void uclamp_fork(struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * We don't need to hold task_rq_lock() when updating p->uclamp_* here
+	 * as the task is still at its early fork stages.
+	 */
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
 
@@ -1412,6 +1503,11 @@ static void uclamp_fork(struct task_struct *p)
 	}
 }
 
+static void uclamp_post_fork(struct task_struct *p)
+{
+	uclamp_update_util_min_rt_default(p);
+}
+
 static void __init init_uclamp_rq(struct rq *rq)
 {
 	enum uclamp_id clamp_id;
@@ -1462,6 +1558,7 @@ static inline int uclamp_validate(struct task_struct *p,
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
+static inline void uclamp_post_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -3205,6 +3302,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
+void sched_post_fork(struct task_struct *p)
+{
+	uclamp_post_fork(p);
+}
+
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -5724,6 +5826,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
+	/*
+	 * This could race with another potential updater, but this is fine
+	 * because it'll correctly read the old or the new value. We don't need
+	 * to guarantee who wins the race as long as it doesn't return garbage.
+	 */
 	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
 	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aea67d3d552..1b4d2dc270a5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1815,6 +1815,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_sched_uclamp_handler,
 	},
+	{
+		.procname	= "sched_util_clamp_min_rt_default",
+		.data		= &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sched_uclamp_handler,
+	},
 #endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
-- 
cgit v1.2.3


From f891f19736bdf404845f97d8038054be37160ea8 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Wed, 29 Jul 2020 17:09:19 +0530
Subject: kexec_file: Allow archs to handle special regions while locating
 memory hole

Some architectures may have special memory regions, within the given
memory range, which can't be used for the buffer in a kexec segment.
Implement weak arch_kexec_locate_mem_hole() definition which arch code
may override, to take care of special regions, while trying to locate
a memory hole.

Also, add the missing declarations for arch overridable functions and
and drop the __weak descriptors in the declarations to avoid non-weak
definitions from becoming weak.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Pingfan Liu <piliu@redhat.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Acked-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/159602273603.575379.17665852963340380839.stgit@hbathini
---
 include/linux/kexec.h | 29 ++++++++++++++++++-----------
 kernel/kexec_file.c   | 16 ++++++++++++++--
 2 files changed, 32 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index ea67910ae6b7..9e93bef52968 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -183,17 +183,24 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
 				   bool get_value);
 void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name);
 
-int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
-					 unsigned long buf_len);
-void * __weak arch_kexec_kernel_image_load(struct kimage *image);
-int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi,
-					    Elf_Shdr *section,
-					    const Elf_Shdr *relsec,
-					    const Elf_Shdr *symtab);
-int __weak arch_kexec_apply_relocations(struct purgatory_info *pi,
-					Elf_Shdr *section,
-					const Elf_Shdr *relsec,
-					const Elf_Shdr *symtab);
+/* Architectures may override the below functions */
+int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+				  unsigned long buf_len);
+void *arch_kexec_kernel_image_load(struct kimage *image);
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab);
+int arch_kexec_apply_relocations(struct purgatory_info *pi,
+				 Elf_Shdr *section,
+				 const Elf_Shdr *relsec,
+				 const Elf_Shdr *symtab);
+int arch_kimage_file_post_load_cleanup(struct kimage *image);
+#ifdef CONFIG_KEXEC_SIG
+int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
+				 unsigned long buf_len);
+#endif
+int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf);
 
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index bb05fd52de85..eb42d2efa16a 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -657,6 +657,19 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 	return ret == 1 ? 0 : -EADDRNOTAVAIL;
 }
 
+/**
+ * arch_kexec_locate_mem_hole - Find free memory to place the segments.
+ * @kbuf:                       Parameters for the memory search.
+ *
+ * On success, kbuf->mem will have the start address of the memory region found.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int __weak arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
+{
+	return kexec_locate_mem_hole(kbuf);
+}
+
 /**
  * kexec_add_buffer - place a buffer in a kexec segment
  * @kbuf:	Buffer contents and memory parameters.
@@ -669,7 +682,6 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
  */
 int kexec_add_buffer(struct kexec_buf *kbuf)
 {
-
 	struct kexec_segment *ksegment;
 	int ret;
 
@@ -697,7 +709,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	ret = kexec_locate_mem_hole(kbuf);
+	ret = arch_kexec_locate_mem_hole(kbuf);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 7ca8cf5347f720b07a0b32a924b768f5710547e7 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 29 Jul 2020 22:31:05 +1000
Subject: locking/atomic: Move ATOMIC_INIT into linux/types.h

This patch moves ATOMIC_INIT from asm/atomic.h into linux/types.h.
This allows users of atomic_t to use ATOMIC_INIT without having to
include atomic.h as that way may lead to header loops.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lkml.kernel.org/r/20200729123105.GB7047@gondor.apana.org.au
---
 arch/alpha/include/asm/atomic.h    | 1 -
 arch/arc/include/asm/atomic.h      | 2 --
 arch/arm/include/asm/atomic.h      | 2 --
 arch/arm64/include/asm/atomic.h    | 2 --
 arch/h8300/include/asm/atomic.h    | 2 --
 arch/hexagon/include/asm/atomic.h  | 2 --
 arch/ia64/include/asm/atomic.h     | 1 -
 arch/m68k/include/asm/atomic.h     | 2 --
 arch/mips/include/asm/atomic.h     | 1 -
 arch/parisc/include/asm/atomic.h   | 2 --
 arch/powerpc/include/asm/atomic.h  | 2 --
 arch/riscv/include/asm/atomic.h    | 2 --
 arch/s390/include/asm/atomic.h     | 2 --
 arch/sh/include/asm/atomic.h       | 2 --
 arch/sparc/include/asm/atomic_32.h | 2 --
 arch/sparc/include/asm/atomic_64.h | 1 -
 arch/x86/include/asm/atomic.h      | 2 --
 arch/xtensa/include/asm/atomic.h   | 2 --
 include/asm-generic/atomic.h       | 2 --
 include/linux/types.h              | 2 ++
 20 files changed, 2 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2144530d1428..e2093994fd0d 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -24,7 +24,6 @@
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 7298ce84762e..c614857eb209 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -14,8 +14,6 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 75bb2c543e59..455eb19a5ac1 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef __KERNEL__
 
 /*
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index a08890da696c..015ddffaf6ca 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -99,8 +99,6 @@ static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define arch_atomic_read(v)			__READ_ONCE((v)->counter)
 #define arch_atomic_set(v, i)			__WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index c6b6a06231b2..a990d151f163 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -12,8 +12,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 0231d69c8bf2..4ab895d7111f 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -12,8 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*  Normal writes in our arch don't clear lock reservations  */
 
 static inline void atomic_set(atomic_t *v, int new)
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 50440f3ddc43..f267d956458f 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -19,7 +19,6 @@
 #include <asm/barrier.h>
 
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 47228b0d4163..756c5cc58f94 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -16,8 +16,6 @@
  * We do not have SMP m68k systems, so we don't have to deal with that.
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index e5ac88392d1f..f904084fcb1f 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -45,7 +45,6 @@ static __always_inline type pfx##_xchg(pfx##_t *v, type n)		\
 	return xchg(&v->counter, n);					\
 }
 
-#define ATOMIC_INIT(i)		{ (i) }
 ATOMIC_OPS(atomic, int)
 
 #ifdef CONFIG_64BIT
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 118953d41763..f960e2f32b1b 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -136,8 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i) { (i) }
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 498785ffc25f..0311c3c42960 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -11,8 +11,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*
  * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 96f95c9ebd97..400a8c8b6de7 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define __atomic_acquire_fence()					\
 	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
 
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 491ad53a0d4e..cae473a7b6f7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 static inline int atomic_read(const atomic_t *v)
 {
 	int c;
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index f37b95a80232..7c2a8a703b9a 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v,i)		WRITE_ONCE((v)->counter, (i))
 
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 94c930f0bc62..efad5532f169 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -18,8 +18,6 @@
 #include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 int atomic_add_return(int, atomic_t *);
 int atomic_fetch_add(int, atomic_t *);
 int atomic_fetch_and(int, atomic_t *);
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index b60448397d4f..6b235d3d1d9d 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -12,7 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index bf35e476a776..b6cac6e9bb70 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -14,8 +14,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /**
  * arch_atomic_read - read atomic variable
  * @v: pointer of type atomic_t
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 3e7c6134ed32..744c2f463845 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /*
  * This Xtensa implementation assumes that the right mechanism
  * for exclusion is for locking interrupts to level EXCM_LEVEL.
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 286867f593d2..11f96f40f4a7 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -159,8 +159,6 @@ ATOMIC_OP(xor, ^)
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /**
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
diff --git a/include/linux/types.h b/include/linux/types.h
index d3021c879179..a147977602b5 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -167,6 +167,8 @@ typedef struct {
 	int counter;
 } atomic_t;
 
+#define ATOMIC_INIT(i) { (i) }
+
 #ifdef CONFIG_64BIT
 typedef struct {
 	s64 counter;
-- 
cgit v1.2.3


From 0d24f65e933ca89d55d17f6dbdb2a72ca88f0992 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:07 +0200
Subject: Documentation: locking: Describe seqlock design and usage

Proper documentation for the design and usage of sequence counters and
sequential locks does not exist. Complete the seqlock.h documentation as
follows:

  - Divide all documentation on a seqcount_t vs. seqlock_t basis. The
    description for both mechanisms was intermingled, which is incorrect
    since the usage constrains for each type are vastly different.

  - Add an introductory paragraph describing the internal design of, and
    rationale for, sequence counters.

  - Document seqcount_t writer non-preemptibility requirement, which was
    not previously documented anywhere, and provide a clear rationale.

  - Provide template code for seqcount_t and seqlock_t initialization
    and reader/writer critical sections.

  - Recommend using seqlock_t by default. It implicitly handles the
    serialization and non-preemptibility requirements of writers.

At seqlock.h:

  - Remove references to brlocks as they've long been removed from the
    kernel.

  - Remove references to gcc-3.x since the kernel's minimum supported
    gcc version is 4.9.

References: 0f6ed63b1707 ("no need to keep brlock macros anymore...")
References: 6ec4476ac825 ("Raise gcc version requirement to 4.9")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-2-a.darwish@linutronix.de
---
 Documentation/locking/index.rst   |   1 +
 Documentation/locking/seqlock.rst | 170 ++++++++++++++++++++++++++++++++++++++
 include/linux/seqlock.h           |  85 +++++++++----------
 3 files changed, 211 insertions(+), 45 deletions(-)
 create mode 100644 Documentation/locking/seqlock.rst

(limited to 'include/linux')

diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst
index d785878cad65..7003bd5aeff4 100644
--- a/Documentation/locking/index.rst
+++ b/Documentation/locking/index.rst
@@ -14,6 +14,7 @@ locking
     mutex-design
     rt-mutex-design
     rt-mutex
+    seqlock
     spinlocks
     ww-mutex-design
     preempt-locking
diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
new file mode 100644
index 000000000000..366dd368d90a
--- /dev/null
+++ b/Documentation/locking/seqlock.rst
@@ -0,0 +1,170 @@
+======================================
+Sequence counters and sequential locks
+======================================
+
+Introduction
+============
+
+Sequence counters are a reader-writer consistency mechanism with
+lockless readers (read-only retry loops), and no writer starvation. They
+are used for data that's rarely written to (e.g. system time), where the
+reader wants a consistent set of information and is willing to retry if
+that information changes.
+
+A data set is consistent when the sequence count at the beginning of the
+read side critical section is even and the same sequence count value is
+read again at the end of the critical section. The data in the set must
+be copied out inside the read side critical section. If the sequence
+count has changed between the start and the end of the critical section,
+the reader must retry.
+
+Writers increment the sequence count at the start and the end of their
+critical section. After starting the critical section the sequence count
+is odd and indicates to the readers that an update is in progress. At
+the end of the write side critical section the sequence count becomes
+even again which lets readers make progress.
+
+A sequence counter write side critical section must never be preempted
+or interrupted by read side sections. Otherwise the reader will spin for
+the entire scheduler tick due to the odd sequence count value and the
+interrupted writer. If that reader belongs to a real-time scheduling
+class, it can spin forever and the kernel will livelock.
+
+This mechanism cannot be used if the protected data contains pointers,
+as the writer can invalidate a pointer that the reader is following.
+
+
+.. _seqcount_t:
+
+Sequence counters (``seqcount_t``)
+==================================
+
+This is the the raw counting mechanism, which does not protect against
+multiple writers.  Write side critical sections must thus be serialized
+by an external lock.
+
+If the write serialization primitive is not implicitly disabling
+preemption, preemption must be explicitly disabled before entering the
+write side section. If the read section can be invoked from hardirq or
+softirq contexts, interrupts or bottom halves must also be respectively
+disabled before entering the write section.
+
+If it's desired to automatically handle the sequence counter
+requirements of writer serialization and non-preemptibility, use
+:ref:`seqlock_t` instead.
+
+Initialization::
+
+	/* dynamic */
+	seqcount_t foo_seqcount;
+	seqcount_init(&foo_seqcount);
+
+	/* static */
+	static seqcount_t foo_seqcount = SEQCNT_ZERO(foo_seqcount);
+
+	/* C99 struct init */
+	struct {
+		.seq   = SEQCNT_ZERO(foo.seq),
+	} foo;
+
+Write path::
+
+	/* Serialized context with disabled preemption */
+
+	write_seqcount_begin(&foo_seqcount);
+
+	/* ... [[write-side critical section]] ... */
+
+	write_seqcount_end(&foo_seqcount);
+
+Read path::
+
+	do {
+		seq = read_seqcount_begin(&foo_seqcount);
+
+		/* ... [[read-side critical section]] ... */
+
+	} while (read_seqcount_retry(&foo_seqcount, seq));
+
+
+.. _seqlock_t:
+
+Sequential locks (``seqlock_t``)
+================================
+
+This contains the :ref:`seqcount_t` mechanism earlier discussed, plus an
+embedded spinlock for writer serialization and non-preemptibility.
+
+If the read side section can be invoked from hardirq or softirq context,
+use the write side function variants which disable interrupts or bottom
+halves respectively.
+
+Initialization::
+
+	/* dynamic */
+	seqlock_t foo_seqlock;
+	seqlock_init(&foo_seqlock);
+
+	/* static */
+	static DEFINE_SEQLOCK(foo_seqlock);
+
+	/* C99 struct init */
+	struct {
+		.seql   = __SEQLOCK_UNLOCKED(foo.seql)
+	} foo;
+
+Write path::
+
+	write_seqlock(&foo_seqlock);
+
+	/* ... [[write-side critical section]] ... */
+
+	write_sequnlock(&foo_seqlock);
+
+Read path, three categories:
+
+1. Normal Sequence readers which never block a writer but they must
+   retry if a writer is in progress by detecting change in the sequence
+   number.  Writers do not wait for a sequence reader::
+
+	do {
+		seq = read_seqbegin(&foo_seqlock);
+
+		/* ... [[read-side critical section]] ... */
+
+	} while (read_seqretry(&foo_seqlock, seq));
+
+2. Locking readers which will wait if a writer or another locking reader
+   is in progress. A locking reader in progress will also block a writer
+   from entering its critical section. This read lock is
+   exclusive. Unlike rwlock_t, only one locking reader can acquire it::
+
+	read_seqlock_excl(&foo_seqlock);
+
+	/* ... [[read-side critical section]] ... */
+
+	read_sequnlock_excl(&foo_seqlock);
+
+3. Conditional lockless reader (as in 1), or locking reader (as in 2),
+   according to a passed marker. This is used to avoid lockless readers
+   starvation (too much retry loops) in case of a sharp spike in write
+   activity. First, a lockless read is tried (even marker passed). If
+   that trial fails (odd sequence counter is returned, which is used as
+   the next iteration marker), the lockless read is transformed to a
+   full locking read and no retry loop is necessary::
+
+	/* marker; even initialization */
+	int seq = 0;
+	do {
+		read_seqbegin_or_lock(&foo_seqlock, &seq);
+
+		/* ... [[read-side critical section]] ... */
+
+	} while (need_seqretry(&foo_seqlock, seq));
+	done_seqretry(&foo_seqlock, seq);
+
+
+API documentation
+=================
+
+.. kernel-doc:: include/linux/seqlock.h
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 8b97204f35a7..299d68f10325 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -1,36 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_SEQLOCK_H
 #define __LINUX_SEQLOCK_H
+
 /*
- * Reader/writer consistent mechanism without starving writers. This type of
- * lock for data where the reader wants a consistent set of information
- * and is willing to retry if the information changes. There are two types
- * of readers:
- * 1. Sequence readers which never block a writer but they may have to retry
- *    if a writer is in progress by detecting change in sequence number.
- *    Writers do not wait for a sequence reader.
- * 2. Locking readers which will wait if a writer or another locking reader
- *    is in progress. A locking reader in progress will also block a writer
- *    from going forward. Unlike the regular rwlock, the read lock here is
- *    exclusive so that only one locking reader can get it.
- *
- * This is not as cache friendly as brlock. Also, this may not work well
- * for data that contains pointers, because any writer could
- * invalidate a pointer that a reader was following.
- *
- * Expected non-blocking reader usage:
- * 	do {
- *	    seq = read_seqbegin(&foo);
- * 	...
- *      } while (read_seqretry(&foo, seq));
- *
- *
- * On non-SMP the spin locks disappear but the writer still needs
- * to increment the sequence variables because an interrupt routine could
- * change the state of the data.
- *
- * Based on x86_64 vsyscall gettimeofday 
- * by Keith Owens and Andrea Arcangeli
+ * seqcount_t / seqlock_t - a reader-writer consistency mechanism with
+ * lockless readers (read-only retry loops), and no writer starvation.
+ *
+ * See Documentation/locking/seqlock.rst
+ *
+ * Copyrights:
+ * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli
  */
 
 #include <linux/spinlock.h>
@@ -41,8 +20,8 @@
 #include <asm/processor.h>
 
 /*
- * The seqlock interface does not prescribe a precise sequence of read
- * begin/retry/end. For readers, typically there is a call to
+ * The seqlock seqcount_t interface does not prescribe a precise sequence of
+ * read begin/retry/end. For readers, typically there is a call to
  * read_seqcount_begin() and read_seqcount_retry(), however, there are more
  * esoteric cases which do not follow this pattern.
  *
@@ -50,16 +29,30 @@
  * via seqcount_t under KCSAN: upon beginning a seq-reader critical section,
  * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as
  * atomics; if there is a matching read_seqcount_retry() call, no following
- * memory operations are considered atomic. Usage of seqlocks via seqlock_t
- * interface is not affected.
+ * memory operations are considered atomic. Usage of the seqlock_t interface
+ * is not affected.
  */
 #define KCSAN_SEQLOCK_REGION_MAX 1000
 
 /*
- * Version using sequence counter only.
- * This can be used when code has its own mutex protecting the
- * updating starting before the write_seqcountbeqin() and ending
- * after the write_seqcount_end().
+ * Sequence counters (seqcount_t)
+ *
+ * This is the raw counting mechanism, without any writer protection.
+ *
+ * Write side critical sections must be serialized and non-preemptible.
+ *
+ * If readers can be invoked from hardirq or softirq contexts,
+ * interrupts or bottom halves must also be respectively disabled before
+ * entering the write section.
+ *
+ * This mechanism can't be used if the protected data contains pointers,
+ * as the writer can invalidate a pointer that a reader is following.
+ *
+ * If it's desired to automatically handle the sequence counter writer
+ * serialization and non-preemptibility requirements, use a sequential
+ * lock (seqlock_t) instead.
+ *
+ * See Documentation/locking/seqlock.rst
  */
 typedef struct seqcount {
 	unsigned sequence;
@@ -398,10 +391,6 @@ static inline void raw_write_seqcount_latch(seqcount_t *s)
        smp_wmb();      /* increment "sequence" before following stores */
 }
 
-/*
- * Sequence counter only version assumes that callers are using their
- * own mutexing.
- */
 static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
 	raw_write_seqcount_begin(s);
@@ -434,15 +423,21 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+/*
+ * Sequential locks (seqlock_t)
+ *
+ * Sequence counters with an embedded spinlock for writer serialization
+ * and non-preemptibility.
+ *
+ * For more info, see:
+ *    - Comments on top of seqcount_t
+ *    - Documentation/locking/seqlock.rst
+ */
 typedef struct {
 	struct seqcount seqcount;
 	spinlock_t lock;
 } seqlock_t;
 
-/*
- * These macros triggered gcc-3.x compile-time problems.  We think these are
- * OK now.  Be cautious.
- */
 #define __SEQLOCK_UNLOCKED(lockname)			\
 	{						\
 		.seqcount = SEQCNT_ZERO(lockname),	\
-- 
cgit v1.2.3


From 15cbe67bbd3adeb4854c42713dbeaf2ff876beee Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:08 +0200
Subject: seqlock: Properly format kernel-doc code samples

Align the code samples and note sections inside kernel-doc comments with
tabs. This way they can be properly parsed and rendered by Sphinx. It
also makes the code samples easier to read from text editors.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-3-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 108 +++++++++++++++++++++++++-----------------------
 1 file changed, 56 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 299d68f10325..6c4f68ef1393 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -263,32 +263,32 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  * atomically, avoiding compiler optimizations; b) to document which writes are
  * meant to propagate to the reader critical section. This is necessary because
  * neither writes before and after the barrier are enclosed in a seq-writer
- * critical section that would ensure readers are aware of ongoing writes.
+ * critical section that would ensure readers are aware of ongoing writes::
  *
- *      seqcount_t seq;
- *      bool X = true, Y = false;
+ *	seqcount_t seq;
+ *	bool X = true, Y = false;
  *
- *      void read(void)
- *      {
- *              bool x, y;
+ *	void read(void)
+ *	{
+ *		bool x, y;
  *
- *              do {
- *                      int s = read_seqcount_begin(&seq);
+ *		do {
+ *			int s = read_seqcount_begin(&seq);
  *
- *                      x = X; y = Y;
+ *			x = X; y = Y;
  *
- *              } while (read_seqcount_retry(&seq, s));
+ *		} while (read_seqcount_retry(&seq, s));
  *
- *              BUG_ON(!x && !y);
+ *		BUG_ON(!x && !y);
  *      }
  *
  *      void write(void)
  *      {
- *              WRITE_ONCE(Y, true);
+ *		WRITE_ONCE(Y, true);
  *
- *              raw_write_seqcount_barrier(seq);
+ *		raw_write_seqcount_barrier(seq);
  *
- *              WRITE_ONCE(X, false);
+ *		WRITE_ONCE(X, false);
  *      }
  */
 static inline void raw_write_seqcount_barrier(seqcount_t *s)
@@ -325,64 +325,68 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
  * Very simply put: we first modify one copy and then the other. This ensures
  * there is always one copy in a stable state, ready to give us an answer.
  *
- * The basic form is a data structure like:
+ * The basic form is a data structure like::
  *
- * struct latch_struct {
- *	seqcount_t		seq;
- *	struct data_struct	data[2];
- * };
+ *	struct latch_struct {
+ *		seqcount_t		seq;
+ *		struct data_struct	data[2];
+ *	};
  *
  * Where a modification, which is assumed to be externally serialized, does the
- * following:
+ * following::
  *
- * void latch_modify(struct latch_struct *latch, ...)
- * {
- *	smp_wmb();	<- Ensure that the last data[1] update is visible
- *	latch->seq++;
- *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *	void latch_modify(struct latch_struct *latch, ...)
+ *	{
+ *		smp_wmb();	// Ensure that the last data[1] update is visible
+ *		latch->seq++;
+ *		smp_wmb();	// Ensure that the seqcount update is visible
  *
- *	modify(latch->data[0], ...);
+ *		modify(latch->data[0], ...);
  *
- *	smp_wmb();	<- Ensure that the data[0] update is visible
- *	latch->seq++;
- *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *		smp_wmb();	// Ensure that the data[0] update is visible
+ *		latch->seq++;
+ *		smp_wmb();	// Ensure that the seqcount update is visible
  *
- *	modify(latch->data[1], ...);
- * }
+ *		modify(latch->data[1], ...);
+ *	}
  *
- * The query will have a form like:
+ * The query will have a form like::
  *
- * struct entry *latch_query(struct latch_struct *latch, ...)
- * {
- *	struct entry *entry;
- *	unsigned seq, idx;
+ *	struct entry *latch_query(struct latch_struct *latch, ...)
+ *	{
+ *		struct entry *entry;
+ *		unsigned seq, idx;
  *
- *	do {
- *		seq = raw_read_seqcount_latch(&latch->seq);
+ *		do {
+ *			seq = raw_read_seqcount_latch(&latch->seq);
  *
- *		idx = seq & 0x01;
- *		entry = data_query(latch->data[idx], ...);
+ *			idx = seq & 0x01;
+ *			entry = data_query(latch->data[idx], ...);
  *
- *		smp_rmb();
- *	} while (seq != latch->seq);
+ *			smp_rmb();
+ *		} while (seq != latch->seq);
  *
- *	return entry;
- * }
+ *		return entry;
+ *	}
  *
  * So during the modification, queries are first redirected to data[1]. Then we
  * modify data[0]. When that is complete, we redirect queries back to data[0]
  * and we can modify data[1].
  *
- * NOTE: The non-requirement for atomic modifications does _NOT_ include
- *       the publishing of new entries in the case where data is a dynamic
- *       data structure.
+ * NOTE:
+ *
+ *	The non-requirement for atomic modifications does _NOT_ include
+ *	the publishing of new entries in the case where data is a dynamic
+ *	data structure.
+ *
+ *	An iteration might start in data[0] and get suspended long enough
+ *	to miss an entire modification sequence, once it resumes it might
+ *	observe the new entry.
  *
- *       An iteration might start in data[0] and get suspended long enough
- *       to miss an entire modification sequence, once it resumes it might
- *       observe the new entry.
+ * NOTE:
  *
- * NOTE: When data is a dynamic data structure; one should use regular RCU
- *       patterns to manage the lifetimes of the objects within.
+ *	When data is a dynamic data structure; one should use regular RCU
+ *	patterns to manage the lifetimes of the objects within.
  */
 static inline void raw_write_seqcount_latch(seqcount_t *s)
 {
-- 
cgit v1.2.3


From d3b35b87f436c1b226a8061bee9c8875ba6658bd Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:09 +0200
Subject: seqlock: seqcount_t latch: End read sections with
 read_seqcount_retry()

The seqcount_t latch reader example at the raw_write_seqcount_latch()
kernel-doc comment ends the latch read section with a manual smp memory
barrier and sequence counter comparison.

This is technically correct, but it is suboptimal: read_seqcount_retry()
already contains the same logic of an smp memory barrier and sequence
counter comparison.

End the latch read critical section example with read_seqcount_retry().

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-4-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 6c4f68ef1393..d724b5e5408d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -363,8 +363,8 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
  *			idx = seq & 0x01;
  *			entry = data_query(latch->data[idx], ...);
  *
- *			smp_rmb();
- *		} while (seq != latch->seq);
+ *		// read_seqcount_retry() includes needed smp_rmb()
+ *		} while (read_seqcount_retry(&latch->seq, seq));
  *
  *		return entry;
  *	}
-- 
cgit v1.2.3


From f4a27cbcec90ac04ee60e04b222e1449dcdba0bd Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:10 +0200
Subject: seqlock: Reorder seqcount_t and seqlock_t API definitions

The seqlock.h seqcount_t and seqlock_t API definitions are presented in
the chronological order of their development rather than the order that
makes most sense to readers. This makes it hard to follow and understand
the header file code.

Group and reorder all of the exported seqlock.h functions according to
their function.

First, group together the seqcount_t standard read path functions:

    - __read_seqcount_begin()
    - raw_read_seqcount_begin()
    - read_seqcount_begin()

since each function is implemented exactly in terms of the one above
it. Then, group the special-case seqcount_t readers on their own as:

    - raw_read_seqcount()
    - raw_seqcount_begin()

since the only difference between the two functions is that the second
one masks the sequence counter LSB while the first one does not. Note
that raw_seqcount_begin() can actually be implemented in terms of
raw_read_seqcount(), which will be done in a follow-up commit.

Then, group the seqcount_t write path functions, instead of injecting
unrelated seqcount_t latch functions between them, and order them as:

    - raw_write_seqcount_begin()
    - raw_write_seqcount_end()
    - write_seqcount_begin_nested()
    - write_seqcount_begin()
    - write_seqcount_end()
    - raw_write_seqcount_barrier()
    - write_seqcount_invalidate()

which is the expected natural order. This also isolates the seqcount_t
latch functions into their own area, at the end of the sequence counters
section, and before jumping to the next one: sequential locks
(seqlock_t).

Do a similar grouping and reordering for seqlock_t "locking" readers vs.
the "conditionally locking or lockless" ones.

No implementation code was changed in any of the reordering above.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-5-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 158 ++++++++++++++++++++++++------------------------
 1 file changed, 78 insertions(+), 80 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index d724b5e5408d..4c1456008d89 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -128,23 +128,6 @@ repeat:
 	return ret;
 }
 
-/**
- * raw_read_seqcount - Read the raw seqcount
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
- *
- * raw_read_seqcount opens a read critical section of the given
- * seqcount without any lockdep checking and without checking or
- * masking the LSB. Calling code is responsible for handling that.
- */
-static inline unsigned raw_read_seqcount(const seqcount_t *s)
-{
-	unsigned ret = READ_ONCE(s->sequence);
-	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret;
-}
-
 /**
  * raw_read_seqcount_begin - start seq-read critical section w/o lockdep
  * @s: pointer to seqcount_t
@@ -176,6 +159,23 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 	return raw_read_seqcount_begin(s);
 }
 
+/**
+ * raw_read_seqcount - Read the raw seqcount
+ * @s: pointer to seqcount_t
+ * Returns: count to be passed to read_seqcount_retry
+ *
+ * raw_read_seqcount opens a read critical section of the given
+ * seqcount without any lockdep checking and without checking or
+ * masking the LSB. Calling code is responsible for handling that.
+ */
+static inline unsigned raw_read_seqcount(const seqcount_t *s)
+{
+	unsigned ret = READ_ONCE(s->sequence);
+	smp_rmb();
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
+	return ret;
+}
+
 /**
  * raw_seqcount_begin - begin a seq-read critical section
  * @s: pointer to seqcount_t
@@ -234,8 +234,6 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 	return __read_seqcount_retry(s, start);
 }
 
-
-
 static inline void raw_write_seqcount_begin(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
@@ -250,6 +248,23 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
+{
+	raw_write_seqcount_begin(s);
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+}
+
+static inline void write_seqcount_begin(seqcount_t *s)
+{
+	write_seqcount_begin_nested(s, 0);
+}
+
+static inline void write_seqcount_end(seqcount_t *s)
+{
+	seqcount_release(&s->dep_map, _RET_IP_);
+	raw_write_seqcount_end(s);
+}
+
 /**
  * raw_write_seqcount_barrier - do a seq write barrier
  * @s: pointer to seqcount_t
@@ -300,6 +315,21 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+/**
+ * write_seqcount_invalidate - invalidate in-progress read-side seq operations
+ * @s: pointer to seqcount_t
+ *
+ * After write_seqcount_invalidate, no read-side seq operations will complete
+ * successfully and see data older than this.
+ */
+static inline void write_seqcount_invalidate(seqcount_t *s)
+{
+	smp_wmb();
+	kcsan_nestable_atomic_begin();
+	s->sequence+=2;
+	kcsan_nestable_atomic_end();
+}
+
 static inline int raw_read_seqcount_latch(seqcount_t *s)
 {
 	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
@@ -395,38 +425,6 @@ static inline void raw_write_seqcount_latch(seqcount_t *s)
        smp_wmb();      /* increment "sequence" before following stores */
 }
 
-static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
-{
-	raw_write_seqcount_begin(s);
-	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
-}
-
-static inline void write_seqcount_begin(seqcount_t *s)
-{
-	write_seqcount_begin_nested(s, 0);
-}
-
-static inline void write_seqcount_end(seqcount_t *s)
-{
-	seqcount_release(&s->dep_map, _RET_IP_);
-	raw_write_seqcount_end(s);
-}
-
-/**
- * write_seqcount_invalidate - invalidate in-progress read-side seq operations
- * @s: pointer to seqcount_t
- *
- * After write_seqcount_invalidate, no read-side seq operations will complete
- * successfully and see data older than this.
- */
-static inline void write_seqcount_invalidate(seqcount_t *s)
-{
-	smp_wmb();
-	kcsan_nestable_atomic_begin();
-	s->sequence+=2;
-	kcsan_nestable_atomic_end();
-}
-
 /*
  * Sequential locks (seqlock_t)
  *
@@ -555,35 +553,6 @@ static inline void read_sequnlock_excl(seqlock_t *sl)
 	spin_unlock(&sl->lock);
 }
 
-/**
- * read_seqbegin_or_lock - begin a sequence number check or locking block
- * @lock: sequence lock
- * @seq : sequence number to be checked
- *
- * First try it once optimistically without taking the lock. If that fails,
- * take the lock. The sequence number is also used as a marker for deciding
- * whether to be a reader (even) or writer (odd).
- * N.B. seq must be initialized to an even number to begin with.
- */
-static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
-{
-	if (!(*seq & 1))	/* Even */
-		*seq = read_seqbegin(lock);
-	else			/* Odd */
-		read_seqlock_excl(lock);
-}
-
-static inline int need_seqretry(seqlock_t *lock, int seq)
-{
-	return !(seq & 1) && read_seqretry(lock, seq);
-}
-
-static inline void done_seqretry(seqlock_t *lock, int seq)
-{
-	if (seq & 1)
-		read_sequnlock_excl(lock);
-}
-
 static inline void read_seqlock_excl_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
@@ -621,6 +590,35 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
+/**
+ * read_seqbegin_or_lock - begin a sequence number check or locking block
+ * @lock: sequence lock
+ * @seq : sequence number to be checked
+ *
+ * First try it once optimistically without taking the lock. If that fails,
+ * take the lock. The sequence number is also used as a marker for deciding
+ * whether to be a reader (even) or writer (odd).
+ * N.B. seq must be initialized to an even number to begin with.
+ */
+static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
+{
+	if (!(*seq & 1))	/* Even */
+		*seq = read_seqbegin(lock);
+	else			/* Odd */
+		read_seqlock_excl(lock);
+}
+
+static inline int need_seqretry(seqlock_t *lock, int seq)
+{
+	return !(seq & 1) && read_seqretry(lock, seq);
+}
+
+static inline void done_seqretry(seqlock_t *lock, int seq)
+{
+	if (seq & 1)
+		read_sequnlock_excl(lock);
+}
+
 static inline unsigned long
 read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
 {
-- 
cgit v1.2.3


From 89b88845e05752b3d684eaf147f457c8dfa99c5f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:11 +0200
Subject: seqlock: Add kernel-doc for seqcount_t and seqlock_t APIs

seqlock.h is now included by kernel's RST documentation, but a small
number of the the exported seqlock.h functions are kernel-doc annotated.

Add kernel-doc for all seqlock.h exported APIs.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-6-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 425 +++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 348 insertions(+), 77 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 4c1456008d89..85fb3ac93ffb 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -75,6 +75,10 @@ static inline void __seqcount_init(seqcount_t *s, const char *name,
 # define SEQCOUNT_DEP_MAP_INIT(lockname) \
 		.dep_map = { .name = #lockname } \
 
+/**
+ * seqcount_init() - runtime initializer for seqcount_t
+ * @s: Pointer to the seqcount_t instance
+ */
 # define seqcount_init(s)				\
 	do {						\
 		static struct lock_class_key __key;	\
@@ -98,13 +102,15 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 # define seqcount_lockdep_reader_access(x)
 #endif
 
-#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)}
-
+/**
+ * SEQCNT_ZERO() - static initializer for seqcount_t
+ * @name: Name of the seqcount_t instance
+ */
+#define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
 
 /**
- * __read_seqcount_begin - begin a seq-read critical section (without barrier)
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
+ * @s: Pointer to seqcount_t
  *
  * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -113,6 +119,8 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  *
  * Use carefully, only in critical code, and comment how the barrier is
  * provided.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
 static inline unsigned __read_seqcount_begin(const seqcount_t *s)
 {
@@ -129,13 +137,10 @@ repeat:
 }
 
 /**
- * raw_read_seqcount_begin - start seq-read critical section w/o lockdep
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
+ * @s: Pointer to seqcount_t
  *
- * raw_read_seqcount_begin opens a read critical section of the given
- * seqcount, but without any lockdep checking. Validity of the critical
- * section is tested by checking read_seqcount_retry function.
+ * Return: count to be passed to read_seqcount_retry()
  */
 static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
 {
@@ -145,13 +150,10 @@ static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
 }
 
 /**
- * read_seqcount_begin - begin a seq-read critical section
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * read_seqcount_begin() - begin a seqcount_t read critical section
+ * @s: Pointer to seqcount_t
  *
- * read_seqcount_begin opens a read critical section of the given seqcount.
- * Validity of the critical section is tested by checking read_seqcount_retry
- * function.
+ * Return: count to be passed to read_seqcount_retry()
  */
 static inline unsigned read_seqcount_begin(const seqcount_t *s)
 {
@@ -160,13 +162,15 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 }
 
 /**
- * raw_read_seqcount - Read the raw seqcount
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_read_seqcount() - read the raw seqcount_t counter value
+ * @s: Pointer to seqcount_t
  *
  * raw_read_seqcount opens a read critical section of the given
- * seqcount without any lockdep checking and without checking or
- * masking the LSB. Calling code is responsible for handling that.
+ * seqcount_t, without any lockdep checking, and without checking or
+ * masking the sequence counter LSB. Calling code is responsible for
+ * handling that.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
 static inline unsigned raw_read_seqcount(const seqcount_t *s)
 {
@@ -177,18 +181,21 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
 }
 
 /**
- * raw_seqcount_begin - begin a seq-read critical section
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
+ *                        lockdep and w/o counter stabilization
+ * @s: Pointer to seqcount_t
  *
- * raw_seqcount_begin opens a read critical section of the given seqcount.
- * Validity of the critical section is tested by checking read_seqcount_retry
- * function.
+ * raw_seqcount_begin opens a read critical section of the given
+ * seqcount_t. Unlike read_seqcount_begin(), this function will not wait
+ * for the count to stabilize. If a writer is active when it begins, it
+ * will fail the read_seqcount_retry() at the end of the read critical
+ * section instead of stabilizing at the beginning of it.
  *
- * Unlike read_seqcount_begin(), this function will not wait for the count
- * to stabilize. If a writer is active when we begin, we will fail the
- * read_seqcount_retry() instead of stabilizing at the beginning of the
- * critical section.
+ * Use this only in special kernel hot paths where the read section is
+ * small and has a high probability of success through other external
+ * means. It will save a single branching instruction.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
@@ -199,10 +206,9 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 }
 
 /**
- * __read_seqcount_retry - end a seq-read critical section (without barrier)
- * @s: pointer to seqcount_t
- * @start: count, from read_seqcount_begin
- * Returns: 1 if retry is required, else 0
+ * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
+ * @s: Pointer to seqcount_t
+ * @start: count, from read_seqcount_begin()
  *
  * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -211,6 +217,8 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
  *
  * Use carefully, only in critical code, and comment how the barrier is
  * provided.
+ *
+ * Return: true if a read section retry is required, else false
  */
 static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
@@ -219,14 +227,15 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
 }
 
 /**
- * read_seqcount_retry - end a seq-read critical section
- * @s: pointer to seqcount_t
- * @start: count, from read_seqcount_begin
- * Returns: 1 if retry is required, else 0
+ * read_seqcount_retry() - end a seqcount_t read critical section
+ * @s: Pointer to seqcount_t
+ * @start: count, from read_seqcount_begin()
  *
- * read_seqcount_retry closes a read critical section of the given seqcount.
- * If the critical section was invalid, it must be ignored (and typically
- * retried).
+ * read_seqcount_retry closes the read critical section of given
+ * seqcount_t.  If the critical section was invalid, it must be ignored
+ * (and typically retried).
+ *
+ * Return: true if a read section retry is required, else false
  */
 static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
@@ -234,6 +243,10 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 	return __read_seqcount_retry(s, start);
 }
 
+/**
+ * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
+ * @s: Pointer to seqcount_t
+ */
 static inline void raw_write_seqcount_begin(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
@@ -241,6 +254,10 @@ static inline void raw_write_seqcount_begin(seqcount_t *s)
 	smp_wmb();
 }
 
+/**
+ * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
+ * @s: Pointer to seqcount_t
+ */
 static inline void raw_write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
@@ -248,17 +265,42 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+/**
+ * write_seqcount_begin_nested() - start a seqcount_t write section with
+ *                                 custom lockdep nesting level
+ * @s: Pointer to seqcount_t
+ * @subclass: lockdep nesting level
+ *
+ * See Documentation/locking/lockdep-design.rst
+ */
 static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
 	raw_write_seqcount_begin(s);
 	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
 }
 
+/**
+ * write_seqcount_begin() - start a seqcount_t write side critical section
+ * @s: Pointer to seqcount_t
+ *
+ * write_seqcount_begin opens a write side critical section of the given
+ * seqcount_t.
+ *
+ * Context: seqcount_t write side critical sections must be serialized and
+ * non-preemptible. If readers can be invoked from hardirq or softirq
+ * context, interrupts or bottom halves must be respectively disabled.
+ */
 static inline void write_seqcount_begin(seqcount_t *s)
 {
 	write_seqcount_begin_nested(s, 0);
 }
 
+/**
+ * write_seqcount_end() - end a seqcount_t write side critical section
+ * @s: Pointer to seqcount_t
+ *
+ * The write section must've been opened with write_seqcount_begin().
+ */
 static inline void write_seqcount_end(seqcount_t *s)
 {
 	seqcount_release(&s->dep_map, _RET_IP_);
@@ -266,12 +308,12 @@ static inline void write_seqcount_end(seqcount_t *s)
 }
 
 /**
- * raw_write_seqcount_barrier - do a seq write barrier
- * @s: pointer to seqcount_t
+ * raw_write_seqcount_barrier() - do a seqcount_t write barrier
+ * @s: Pointer to seqcount_t
  *
- * This can be used to provide an ordering guarantee instead of the
- * usual consistency guarantee. It is one wmb cheaper, because we can
- * collapse the two back-to-back wmb()s.
+ * This can be used to provide an ordering guarantee instead of the usual
+ * consistency guarantee. It is one wmb cheaper, because it can collapse
+ * the two back-to-back wmb()s.
  *
  * Note that writes surrounding the barrier should be declared atomic (e.g.
  * via WRITE_ONCE): a) to ensure the writes become visible to other threads
@@ -316,11 +358,12 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
 }
 
 /**
- * write_seqcount_invalidate - invalidate in-progress read-side seq operations
- * @s: pointer to seqcount_t
+ * write_seqcount_invalidate() - invalidate in-progress seqcount_t read
+ *                               side operations
+ * @s: Pointer to seqcount_t
  *
- * After write_seqcount_invalidate, no read-side seq operations will complete
- * successfully and see data older than this.
+ * After write_seqcount_invalidate, no seqcount_t read side operations
+ * will complete successfully and see data older than this.
  */
 static inline void write_seqcount_invalidate(seqcount_t *s)
 {
@@ -330,6 +373,21 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+/**
+ * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
+ * @s: Pointer to seqcount_t
+ *
+ * Use seqcount_t latching to switch between two storage places protected
+ * by a sequence counter. Doing so allows having interruptible, preemptible,
+ * seqcount_t write side critical sections.
+ *
+ * Check raw_write_seqcount_latch() for more details and a full reader and
+ * writer usage example.
+ *
+ * Return: sequence counter raw value. Use the lowest bit as an index for
+ * picking which data copy to read. The full counter value must then be
+ * checked with read_seqcount_retry().
+ */
 static inline int raw_read_seqcount_latch(seqcount_t *s)
 {
 	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
@@ -338,8 +396,8 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
 }
 
 /**
- * raw_write_seqcount_latch - redirect readers to even/odd copy
- * @s: pointer to seqcount_t
+ * raw_write_seqcount_latch() - redirect readers to even/odd copy
+ * @s: Pointer to seqcount_t
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -446,17 +504,28 @@ typedef struct {
 		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
 	}
 
-#define seqlock_init(x)					\
+/**
+ * seqlock_init() - dynamic initializer for seqlock_t
+ * @sl: Pointer to the seqlock_t instance
+ */
+#define seqlock_init(sl)				\
 	do {						\
-		seqcount_init(&(x)->seqcount);		\
-		spin_lock_init(&(x)->lock);		\
+		seqcount_init(&(sl)->seqcount);		\
+		spin_lock_init(&(sl)->lock);		\
 	} while (0)
 
-#define DEFINE_SEQLOCK(x) \
-		seqlock_t x = __SEQLOCK_UNLOCKED(x)
+/**
+ * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t
+ * @sl: Name of the seqlock_t instance
+ */
+#define DEFINE_SEQLOCK(sl) \
+		seqlock_t sl = __SEQLOCK_UNLOCKED(sl)
 
-/*
- * Read side functions for starting and finalizing a read side section.
+/**
+ * read_seqbegin() - start a seqlock_t read side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * Return: count, to be passed to read_seqretry()
  */
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
@@ -467,6 +536,17 @@ static inline unsigned read_seqbegin(const seqlock_t *sl)
 	return ret;
 }
 
+/**
+ * read_seqretry() - end a seqlock_t read side section
+ * @sl: Pointer to seqlock_t
+ * @start: count, from read_seqbegin()
+ *
+ * read_seqretry closes the read side critical section of given seqlock_t.
+ * If the critical section was invalid, it must be ignored (and typically
+ * retried).
+ *
+ * Return: true if a read section retry is required, else false
+ */
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
 	/*
@@ -478,10 +558,18 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 	return read_seqcount_retry(&sl->seqcount, start);
 }
 
-/*
- * Lock out other writers and update the count.
- * Acts like a normal spin_lock/unlock.
- * Don't need preempt_disable() because that is in the spin_lock already.
+/**
+ * write_seqlock() - start a seqlock_t write side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_seqlock opens a write side critical section for the given
+ * seqlock_t.  It also implicitly acquires the spinlock_t embedded inside
+ * that sequential lock. All seqlock_t write side sections are thus
+ * automatically serialized and non-preemptible.
+ *
+ * Context: if the seqlock_t read section, or other write side critical
+ * sections, can be invoked from hardirq or softirq contexts, use the
+ * _irqsave or _bh variants of this function instead.
  */
 static inline void write_seqlock(seqlock_t *sl)
 {
@@ -489,30 +577,66 @@ static inline void write_seqlock(seqlock_t *sl)
 	write_seqcount_begin(&sl->seqcount);
 }
 
+/**
+ * write_sequnlock() - end a seqlock_t write side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_sequnlock closes the (serialized and non-preemptible) write side
+ * critical section of given seqlock_t.
+ */
 static inline void write_sequnlock(seqlock_t *sl)
 {
 	write_seqcount_end(&sl->seqcount);
 	spin_unlock(&sl->lock);
 }
 
+/**
+ * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section
+ * @sl: Pointer to seqlock_t
+ *
+ * _bh variant of write_seqlock(). Use only if the read side section, or
+ * other write side sections, can be invoked from softirq contexts.
+ */
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
 	write_seqcount_begin(&sl->seqcount);
 }
 
+/**
+ * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_sequnlock_bh closes the serialized, non-preemptible, and
+ * softirqs-disabled, seqlock_t write side critical section opened with
+ * write_seqlock_bh().
+ */
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
 	write_seqcount_end(&sl->seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
+/**
+ * write_seqlock_irq() - start a non-interruptible seqlock_t write section
+ * @sl: Pointer to seqlock_t
+ *
+ * _irq variant of write_seqlock(). Use only if the read side section, or
+ * other write sections, can be invoked from hardirq contexts.
+ */
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
 	write_seqcount_begin(&sl->seqcount);
 }
 
+/**
+ * write_sequnlock_irq() - end a non-interruptible seqlock_t write section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_sequnlock_irq closes the serialized and non-interruptible
+ * seqlock_t write side section opened with write_seqlock_irq().
+ */
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
 	write_seqcount_end(&sl->seqcount);
@@ -528,9 +652,28 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	return flags;
 }
 
+/**
+ * write_seqlock_irqsave() - start a non-interruptible seqlock_t write
+ *                           section
+ * @lock:  Pointer to seqlock_t
+ * @flags: Stack-allocated storage for saving caller's local interrupt
+ *         state, to be passed to write_sequnlock_irqrestore().
+ *
+ * _irqsave variant of write_seqlock(). Use it only if the read side
+ * section, or other write sections, can be invoked from hardirq context.
+ */
 #define write_seqlock_irqsave(lock, flags)				\
 	do { flags = __write_seqlock_irqsave(lock); } while (0)
 
+/**
+ * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write
+ *                                section
+ * @sl:    Pointer to seqlock_t
+ * @flags: Caller's saved interrupt state, from write_seqlock_irqsave()
+ *
+ * write_sequnlock_irqrestore closes the serialized and non-interruptible
+ * seqlock_t write section previously opened with write_seqlock_irqsave().
+ */
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
@@ -538,36 +681,79 @@ write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
-/*
- * A locking reader exclusively locks out other writers and locking readers,
- * but doesn't update the sequence number. Acts like a normal spin_lock/unlock.
- * Don't need preempt_disable() because that is in the spin_lock already.
+/**
+ * read_seqlock_excl() - begin a seqlock_t locking reader section
+ * @sl: Pointer to seqlock_t
+ *
+ * read_seqlock_excl opens a seqlock_t locking reader critical section.  A
+ * locking reader exclusively locks out *both* other writers *and* other
+ * locking readers, but it does not update the embedded sequence number.
+ *
+ * Locking readers act like a normal spin_lock()/spin_unlock().
+ *
+ * Context: if the seqlock_t write section, *or other read sections*, can
+ * be invoked from hardirq or softirq contexts, use the _irqsave or _bh
+ * variant of this function instead.
+ *
+ * The opened read section must be closed with read_sequnlock_excl().
  */
 static inline void read_seqlock_excl(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
 }
 
+/**
+ * read_sequnlock_excl() - end a seqlock_t locking reader critical section
+ * @sl: Pointer to seqlock_t
+ */
 static inline void read_sequnlock_excl(seqlock_t *sl)
 {
 	spin_unlock(&sl->lock);
 }
 
+/**
+ * read_seqlock_excl_bh() - start a seqlock_t locking reader section with
+ *			    softirqs disabled
+ * @sl: Pointer to seqlock_t
+ *
+ * _bh variant of read_seqlock_excl(). Use this variant only if the
+ * seqlock_t write side section, *or other read sections*, can be invoked
+ * from softirq contexts.
+ */
 static inline void read_seqlock_excl_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
 }
 
+/**
+ * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking
+ *			      reader section
+ * @sl: Pointer to seqlock_t
+ */
 static inline void read_sequnlock_excl_bh(seqlock_t *sl)
 {
 	spin_unlock_bh(&sl->lock);
 }
 
+/**
+ * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking
+ *			     reader section
+ * @sl: Pointer to seqlock_t
+ *
+ * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t
+ * write side section, *or other read sections*, can be invoked from a
+ * hardirq context.
+ */
 static inline void read_seqlock_excl_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
 }
 
+/**
+ * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t
+ *                             locking reader section
+ * @sl: Pointer to seqlock_t
+ */
 static inline void read_sequnlock_excl_irq(seqlock_t *sl)
 {
 	spin_unlock_irq(&sl->lock);
@@ -581,9 +767,26 @@ static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl)
 	return flags;
 }
 
+/**
+ * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t
+ *				 locking reader section
+ * @lock:  Pointer to seqlock_t
+ * @flags: Stack-allocated storage for saving caller's local interrupt
+ *         state, to be passed to read_sequnlock_excl_irqrestore().
+ *
+ * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t
+ * write side section, *or other read sections*, can be invoked from a
+ * hardirq context.
+ */
 #define read_seqlock_excl_irqsave(lock, flags)				\
 	do { flags = __read_seqlock_excl_irqsave(lock); } while (0)
 
+/**
+ * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t
+ *				      locking reader section
+ * @sl:    Pointer to seqlock_t
+ * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave()
+ */
 static inline void
 read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 {
@@ -591,14 +794,35 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 }
 
 /**
- * read_seqbegin_or_lock - begin a sequence number check or locking block
- * @lock: sequence lock
- * @seq : sequence number to be checked
- *
- * First try it once optimistically without taking the lock. If that fails,
- * take the lock. The sequence number is also used as a marker for deciding
- * whether to be a reader (even) or writer (odd).
- * N.B. seq must be initialized to an even number to begin with.
+ * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader
+ * @lock: Pointer to seqlock_t
+ * @seq : Marker and return parameter. If the passed value is even, the
+ * reader will become a *lockless* seqlock_t reader as in read_seqbegin().
+ * If the passed value is odd, the reader will become a *locking* reader
+ * as in read_seqlock_excl().  In the first call to this function, the
+ * caller *must* initialize and pass an even value to @seq; this way, a
+ * lockless read can be optimistically tried first.
+ *
+ * read_seqbegin_or_lock is an API designed to optimistically try a normal
+ * lockless seqlock_t read section first.  If an odd counter is found, the
+ * lockless read trial has failed, and the next read iteration transforms
+ * itself into a full seqlock_t locking reader.
+ *
+ * This is typically used to avoid seqlock_t lockless readers starvation
+ * (too much retry loops) in the case of a sharp spike in write side
+ * activity.
+ *
+ * Context: if the seqlock_t write section, *or other read sections*, can
+ * be invoked from hardirq or softirq contexts, use the _irqsave or _bh
+ * variant of this function instead.
+ *
+ * Check Documentation/locking/seqlock.rst for template example code.
+ *
+ * Return: the encountered sequence counter value, through the @seq
+ * parameter, which is overloaded as a return parameter. This returned
+ * value must be checked with need_seqretry(). If the read section need to
+ * be retried, this returned value must also be passed as the @seq
+ * parameter of the next read_seqbegin_or_lock() iteration.
  */
 static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
 {
@@ -608,17 +832,52 @@ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
 		read_seqlock_excl(lock);
 }
 
+/**
+ * need_seqretry() - validate seqlock_t "locking or lockless" read section
+ * @lock: Pointer to seqlock_t
+ * @seq: sequence count, from read_seqbegin_or_lock()
+ *
+ * Return: true if a read section retry is required, false otherwise
+ */
 static inline int need_seqretry(seqlock_t *lock, int seq)
 {
 	return !(seq & 1) && read_seqretry(lock, seq);
 }
 
+/**
+ * done_seqretry() - end seqlock_t "locking or lockless" reader section
+ * @lock: Pointer to seqlock_t
+ * @seq: count, from read_seqbegin_or_lock()
+ *
+ * done_seqretry finishes the seqlock_t read side critical section started
+ * with read_seqbegin_or_lock() and validated by need_seqretry().
+ */
 static inline void done_seqretry(seqlock_t *lock, int seq)
 {
 	if (seq & 1)
 		read_sequnlock_excl(lock);
 }
 
+/**
+ * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or
+ *                                   a non-interruptible locking reader
+ * @lock: Pointer to seqlock_t
+ * @seq:  Marker and return parameter. Check read_seqbegin_or_lock().
+ *
+ * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if
+ * the seqlock_t write section, *or other read sections*, can be invoked
+ * from hardirq context.
+ *
+ * Note: Interrupts will be disabled only for "locking reader" mode.
+ *
+ * Return:
+ *
+ *   1. The saved local interrupts state in case of a locking reader, to
+ *      be passed to done_seqretry_irqrestore().
+ *
+ *   2. The encountered sequence counter value, returned through @seq
+ *      overloaded as a return parameter. Check read_seqbegin_or_lock().
+ */
 static inline unsigned long
 read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
 {
@@ -632,6 +891,18 @@ read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
 	return flags;
 }
 
+/**
+ * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a
+ *				non-interruptible locking reader section
+ * @lock:  Pointer to seqlock_t
+ * @seq:   Count, from read_seqbegin_or_lock_irqsave()
+ * @flags: Caller's saved local interrupt state in case of a locking
+ *	   reader, also from read_seqbegin_or_lock_irqsave()
+ *
+ * This is the _irqrestore variant of done_seqretry(). The read section
+ * must've been opened with read_seqbegin_or_lock_irqsave(), and validated
+ * by need_seqretry().
+ */
 static inline void
 done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
 {
-- 
cgit v1.2.3


From 932e46365226324d2cf26d8bdec8b51ceb296948 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:12 +0200
Subject: seqlock: Implement raw_seqcount_begin() in terms of
 raw_read_seqcount()

raw_seqcount_begin() has the same code as raw_read_seqcount(), with the
exception of masking the sequence counter's LSB before returning it to
the caller.

Note, raw_seqcount_begin() masks the counter's LSB before returning it
to the caller so that read_seqcount_retry() can fail if the counter is
odd -- without the overhead of an extra branching instruction.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-7-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 85fb3ac93ffb..e885702d8b82 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -199,10 +199,11 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
  */
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
-	unsigned ret = READ_ONCE(s->sequence);
-	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret & ~1;
+	/*
+	 * If the counter is odd, let read_seqcount_retry() fail
+	 * by decrementing the counter.
+	 */
+	return raw_read_seqcount(s) & ~1;
 }
 
 /**
-- 
cgit v1.2.3


From 8fd8ad5c5dfcb09cf62abadd4043eaf1afbbd0ce Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:13 +0200
Subject: lockdep: Add preemption enabled/disabled assertion APIs

Asserting that preemption is enabled or disabled is a critical sanity
check.  Developers are usually reluctant to add such a check in a
fastpath as reading the preemption count can be costly.

Extend the lockdep API with macros asserting that preemption is disabled
or enabled. If lockdep is disabled, or if the underlying architecture
does not support kernel preemption, this assert has no runtime overhead.

References: f54bb2ec02c8 ("locking/lockdep: Add IRQs disabled/enabled assertion APIs: ...")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-8-a.darwish@linutronix.de
---
 include/linux/lockdep.h | 19 +++++++++++++++++++
 lib/Kconfig.debug       |  1 +
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 7aafba0ddcf9..39a35699d0d6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -549,6 +549,22 @@ do {									\
 	WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context));	\
 } while (0)
 
+#define lockdep_assert_preemption_enabled()				\
+do {									\
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
+		     debug_locks			&&		\
+		     (preempt_count() != 0		||		\
+		      !this_cpu_read(hardirqs_enabled)));		\
+} while (0)
+
+#define lockdep_assert_preemption_disabled()				\
+do {									\
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
+		     debug_locks			&&		\
+		     (preempt_count() == 0		&&		\
+		      this_cpu_read(hardirqs_enabled)));		\
+} while (0)
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
@@ -557,6 +573,9 @@ do {									\
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
 # define lockdep_assert_in_irq() do { } while (0)
+
+# define lockdep_assert_preemption_enabled() do { } while (0)
+# define lockdep_assert_preemption_disabled() do { } while (0)
 #endif
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9ad9210d70a1..5379931ba3b5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1117,6 +1117,7 @@ config PROVE_LOCKING
 	select DEBUG_RWSEMS
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
+	select PREEMPT_COUNT if !ARCH_NO_PREEMPT
 	select TRACE_IRQFLAGS
 	default n
 	help
-- 
cgit v1.2.3


From 859247d39fb008ea812e8f0c398a58a20c12899e Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:14 +0200
Subject: seqlock: lockdep assert non-preemptibility on seqcount_t write

Preemption must be disabled before entering a sequence count write side
critical section.  Failing to do so, the seqcount read side can preempt
the write side section and spin for the entire scheduler tick.  If that
reader belongs to a real-time scheduling class, it can spin forever and
the kernel will livelock.

Assert through lockdep that preemption is disabled for seqcount writers.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-9-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e885702d8b82..54bc20496392 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -266,6 +266,12 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
+static inline void __write_seqcount_begin_nested(seqcount_t *s, int subclass)
+{
+	raw_write_seqcount_begin(s);
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+}
+
 /**
  * write_seqcount_begin_nested() - start a seqcount_t write section with
  *                                 custom lockdep nesting level
@@ -276,8 +282,19 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  */
 static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
-	raw_write_seqcount_begin(s);
-	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+	lockdep_assert_preemption_disabled();
+	__write_seqcount_begin_nested(s, subclass);
+}
+
+/*
+ * A write_seqcount_begin() variant w/o lockdep non-preemptibility checks.
+ *
+ * Use for internal seqlock.h code where it's known that preemption is
+ * already disabled. For example, seqlock_t write side functions.
+ */
+static inline void __write_seqcount_begin(seqcount_t *s)
+{
+	__write_seqcount_begin_nested(s, 0);
 }
 
 /**
@@ -575,7 +592,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 /**
@@ -601,7 +618,7 @@ static inline void write_sequnlock(seqlock_t *sl)
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 /**
@@ -628,7 +645,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 /**
@@ -649,7 +666,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 	return flags;
 }
 
-- 
cgit v1.2.3


From 55f3560df975f557c48aa6afc636808f31ecb87a Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:15 +0200
Subject: seqlock: Extend seqcount API with associated locks

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. If the serialization primitive is
not disabling preemption implicitly, preemption has to be explicitly
disabled before entering the write side critical section.

There is no built-in debugging mechanism to verify that the lock used
for writer serialization is held and preemption is disabled. Some usage
sites like dma-buf have explicit lockdep checks for the writer-side
lock, but this covers only a small portion of the sequence counter usage
in the kernel.

Add new sequence counter types which allows to associate a lock to the
sequence counter at initialization time. The seqcount API functions are
extended to provide appropriate lockdep assertions depending on the
seqcount/lock type.

For sequence counters with associated locks that do not implicitly
disable preemption, preemption protection is enforced in the sequence
counter write side functions. This removes the need to explicitly add
preempt_disable/enable() around the write side critical sections: the
write_begin/end() functions for these new sequence counter types
automatically do this.

Introduce the following seqcount types with associated locks:

     seqcount_spinlock_t
     seqcount_raw_spinlock_t
     seqcount_rwlock_t
     seqcount_mutex_t
     seqcount_ww_mutex_t

Extend the seqcount read and write functions to branch out to the
specific seqcount_LOCKTYPE_t implementation at compile-time. This avoids
kernel API explosion per each new seqcount_LOCKTYPE_t added. Add such
compile-time type detection logic into a new, internal, seqlock header.

Document the proper seqcount_LOCKTYPE_t usage, and rationale, at
Documentation/locking/seqlock.rst.

If lockdep is disabled, this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-10-a.darwish@linutronix.de
---
 Documentation/locking/seqlock.rst |  52 +++++
 include/linux/seqlock.h           | 464 ++++++++++++++++++++++++++++++++------
 2 files changed, 447 insertions(+), 69 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 366dd368d90a..62c5ad98c11c 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -87,6 +87,58 @@ Read path::
 	} while (read_seqcount_retry(&foo_seqcount, seq));
 
 
+.. _seqcount_locktype_t:
+
+Sequence counters with associated locks (``seqcount_LOCKTYPE_t``)
+-----------------------------------------------------------------
+
+As discussed at :ref:`seqcount_t`, sequence count write side critical
+sections must be serialized and non-preemptible. This variant of
+sequence counters associate the lock used for writer serialization at
+initialization time, which enables lockdep to validate that the write
+side critical sections are properly serialized.
+
+This lock association is a NOOP if lockdep is disabled and has neither
+storage nor runtime overhead. If lockdep is enabled, the lock pointer is
+stored in struct seqcount and lockdep's "lock is held" assertions are
+injected at the beginning of the write side critical section to validate
+that it is properly protected.
+
+For lock types which do not implicitly disable preemption, preemption
+protection is enforced in the write side function.
+
+The following sequence counters with associated locks are defined:
+
+  - ``seqcount_spinlock_t``
+  - ``seqcount_raw_spinlock_t``
+  - ``seqcount_rwlock_t``
+  - ``seqcount_mutex_t``
+  - ``seqcount_ww_mutex_t``
+
+The plain seqcount read and write APIs branch out to the specific
+seqcount_LOCKTYPE_t implementation at compile-time. This avoids kernel
+API explosion per each new seqcount LOCKTYPE.
+
+Initialization (replace "LOCKTYPE" with one of the supported locks)::
+
+	/* dynamic */
+	seqcount_LOCKTYPE_t foo_seqcount;
+	seqcount_LOCKTYPE_init(&foo_seqcount, &lock);
+
+	/* static */
+	static seqcount_LOCKTYPE_t foo_seqcount =
+		SEQCNT_LOCKTYPE_ZERO(foo_seqcount, &lock);
+
+	/* C99 struct init */
+	struct {
+		.seq   = SEQCNT_LOCKTYPE_ZERO(foo.seq, &lock),
+	} foo;
+
+Write path: same as in :ref:`seqcount_t`, while running from a context
+with the associated LOCKTYPE lock acquired.
+
+Read path: same as in :ref:`seqcount_t`.
+
 .. _seqlock_t:
 
 Sequential locks (``seqlock_t``)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 54bc20496392..8c16a494c968 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -10,13 +10,17 @@
  *
  * Copyrights:
  * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli
+ * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH
  */
 
-#include <linux/spinlock.h>
-#include <linux/preempt.h>
-#include <linux/lockdep.h>
 #include <linux/compiler.h>
 #include <linux/kcsan-checks.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/ww_mutex.h>
+
 #include <asm/processor.h>
 
 /*
@@ -48,6 +52,10 @@
  * This mechanism can't be used if the protected data contains pointers,
  * as the writer can invalidate a pointer that a reader is following.
  *
+ * If the write serialization mechanism is one of the common kernel
+ * locking primitives, use a sequence counter with associated lock
+ * (seqcount_LOCKTYPE_t) instead.
+ *
  * If it's desired to automatically handle the sequence counter writer
  * serialization and non-preemptibility requirements, use a sequential
  * lock (seqlock_t) instead.
@@ -108,9 +116,267 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  */
 #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
 
+/*
+ * Sequence counters with associated locks (seqcount_LOCKTYPE_t)
+ *
+ * A sequence counter which associates the lock used for writer
+ * serialization at initialization time. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ *
+ * For associated locks which do not implicitly disable preemption,
+ * preemption protection is enforced in the write side function.
+ *
+ * Lockdep is never used in any for the raw write variants.
+ *
+ * See Documentation/locking/seqlock.rst
+ */
+
+#ifdef CONFIG_LOCKDEP
+#define __SEQ_LOCKDEP(expr)	expr
+#else
+#define __SEQ_LOCKDEP(expr)
+#endif
+
+#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
+	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
+	__SEQ_LOCKDEP(.lock	= (assoc_lock))				\
+}
+
+#define seqcount_locktype_init(s, assoc_lock)				\
+do {									\
+	seqcount_init(&(s)->seqcount);					\
+	__SEQ_LOCKDEP((s)->lock = (assoc_lock));			\
+} while (0)
+
+/**
+ * typedef seqcount_spinlock_t - sequence counter with spinlock associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated spinlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * spinlock. The spinlock is associated to the sequence count in the
+ * static initializer or init function. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ */
+typedef struct seqcount_spinlock {
+	seqcount_t	seqcount;
+	__SEQ_LOCKDEP(spinlock_t	*lock);
+} seqcount_spinlock_t;
+
+/**
+ * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t
+ * @name:	Name of the seqcount_spinlock_t instance
+ * @lock:	Pointer to the associated spinlock
+ */
+#define SEQCNT_SPINLOCK_ZERO(name, lock)				\
+	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+/**
+ * seqcount_spinlock_init - runtime initializer for seqcount_spinlock_t
+ * @s:		Pointer to the seqcount_spinlock_t instance
+ * @lock:	Pointer to the associated spinlock
+ */
+#define seqcount_spinlock_init(s, lock)					\
+	seqcount_locktype_init(s, lock)
+
+/**
+ * typedef seqcount_raw_spinlock_t - sequence count with raw spinlock associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated raw spinlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * raw spinlock. The raw spinlock is associated to the sequence count in
+ * the static initializer or init function. This enables lockdep to
+ * validate that the write side critical section is properly serialized.
+ */
+typedef struct seqcount_raw_spinlock {
+	seqcount_t      seqcount;
+	__SEQ_LOCKDEP(raw_spinlock_t	*lock);
+} seqcount_raw_spinlock_t;
+
+/**
+ * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t
+ * @name:	Name of the seqcount_raw_spinlock_t instance
+ * @lock:	Pointer to the associated raw_spinlock
+ */
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)				\
+	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+/**
+ * seqcount_raw_spinlock_init - runtime initializer for seqcount_raw_spinlock_t
+ * @s:		Pointer to the seqcount_raw_spinlock_t instance
+ * @lock:	Pointer to the associated raw_spinlock
+ */
+#define seqcount_raw_spinlock_init(s, lock)				\
+	seqcount_locktype_init(s, lock)
+
+/**
+ * typedef seqcount_rwlock_t - sequence count with rwlock associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated rwlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * rwlock. The rwlock is associated to the sequence count in the static
+ * initializer or init function. This enables lockdep to validate that
+ * the write side critical section is properly serialized.
+ */
+typedef struct seqcount_rwlock {
+	seqcount_t      seqcount;
+	__SEQ_LOCKDEP(rwlock_t		*lock);
+} seqcount_rwlock_t;
+
+/**
+ * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t
+ * @name:	Name of the seqcount_rwlock_t instance
+ * @lock:	Pointer to the associated rwlock
+ */
+#define SEQCNT_RWLOCK_ZERO(name, lock)					\
+	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+/**
+ * seqcount_rwlock_init - runtime initializer for seqcount_rwlock_t
+ * @s:		Pointer to the seqcount_rwlock_t instance
+ * @lock:	Pointer to the associated rwlock
+ */
+#define seqcount_rwlock_init(s, lock)					\
+	seqcount_locktype_init(s, lock)
+
+/**
+ * typedef seqcount_mutex_t - sequence count with mutex associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated mutex
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * mutex. The mutex is associated to the sequence counter in the static
+ * initializer or init function. This enables lockdep to validate that
+ * the write side critical section is properly serialized.
+ *
+ * The write side API functions write_seqcount_begin()/end() automatically
+ * disable and enable preemption when used with seqcount_mutex_t.
+ */
+typedef struct seqcount_mutex {
+	seqcount_t      seqcount;
+	__SEQ_LOCKDEP(struct mutex	*lock);
+} seqcount_mutex_t;
+
+/**
+ * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t
+ * @name:	Name of the seqcount_mutex_t instance
+ * @lock:	Pointer to the associated mutex
+ */
+#define SEQCNT_MUTEX_ZERO(name, lock)					\
+	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+/**
+ * seqcount_mutex_init - runtime initializer for seqcount_mutex_t
+ * @s:		Pointer to the seqcount_mutex_t instance
+ * @lock:	Pointer to the associated mutex
+ */
+#define seqcount_mutex_init(s, lock)					\
+	seqcount_locktype_init(s, lock)
+
+/**
+ * typedef seqcount_ww_mutex_t - sequence count with ww_mutex associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated ww_mutex
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * ww_mutex. The ww_mutex is associated to the sequence counter in the static
+ * initializer or init function. This enables lockdep to validate that
+ * the write side critical section is properly serialized.
+ *
+ * The write side API functions write_seqcount_begin()/end() automatically
+ * disable and enable preemption when used with seqcount_ww_mutex_t.
+ */
+typedef struct seqcount_ww_mutex {
+	seqcount_t      seqcount;
+	__SEQ_LOCKDEP(struct ww_mutex	*lock);
+} seqcount_ww_mutex_t;
+
+/**
+ * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t
+ * @name:	Name of the seqcount_ww_mutex_t instance
+ * @lock:	Pointer to the associated ww_mutex
+ */
+#define SEQCNT_WW_MUTEX_ZERO(name, lock)				\
+	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+/**
+ * seqcount_ww_mutex_init - runtime initializer for seqcount_ww_mutex_t
+ * @s:		Pointer to the seqcount_ww_mutex_t instance
+ * @lock:	Pointer to the associated ww_mutex
+ */
+#define seqcount_ww_mutex_init(s, lock)					\
+	seqcount_locktype_init(s, lock)
+
+/*
+ * @preempt: Is the associated write serialization lock preemtpible?
+ */
+#define SEQCOUNT_LOCKTYPE(locktype, preempt, lockmember)		\
+static inline seqcount_t *						\
+__seqcount_##locktype##_ptr(seqcount_##locktype##_t *s)			\
+{									\
+	return &s->seqcount;						\
+}									\
+									\
+static inline bool							\
+__seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s)		\
+{									\
+	return preempt;							\
+}									\
+									\
+static inline void							\
+__seqcount_##locktype##_assert(seqcount_##locktype##_t *s)		\
+{									\
+	__SEQ_LOCKDEP(lockdep_assert_held(lockmember));			\
+}
+
+/*
+ * Similar hooks, but for plain seqcount_t
+ */
+
+static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
+{
+	return s;
+}
+
+static inline bool __seqcount_preemptible(seqcount_t *s)
+{
+	return false;
+}
+
+static inline void __seqcount_assert(seqcount_t *s)
+{
+	lockdep_assert_preemption_disabled();
+}
+
+/*
+ * @s: Pointer to seqcount_locktype_t, generated hooks first parameter.
+ */
+SEQCOUNT_LOCKTYPE(raw_spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(rwlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(mutex,	true,	s->lock)
+SEQCOUNT_LOCKTYPE(ww_mutex,	true,	&s->lock->base)
+
+#define __seqprop_case(s, locktype, prop)				\
+	seqcount_##locktype##_t: __seqcount_##locktype##_##prop((void *)(s))
+
+#define __seqprop(s, prop) _Generic(*(s),				\
+	seqcount_t:		__seqcount_##prop((void *)(s)),		\
+	__seqprop_case((s),	raw_spinlock,	prop),			\
+	__seqprop_case((s),	spinlock,	prop),			\
+	__seqprop_case((s),	rwlock,		prop),			\
+	__seqprop_case((s),	mutex,		prop),			\
+	__seqprop_case((s),	ww_mutex,	prop))
+
+#define __to_seqcount_t(s)				__seqprop(s, ptr)
+#define __associated_lock_exists_and_is_preemptible(s)	__seqprop(s, preemptible)
+#define __assert_write_section_is_protected(s)		__seqprop(s, assert)
+
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -122,7 +388,10 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  *
  * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned __read_seqcount_begin(const seqcount_t *s)
+#define __read_seqcount_begin(s)					\
+	__read_seqcount_t_begin(__to_seqcount_t(s))
+
+static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
 {
 	unsigned ret;
 
@@ -138,32 +407,38 @@ repeat:
 
 /**
  * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
+#define raw_read_seqcount_begin(s)					\
+	raw_read_seqcount_t_begin(__to_seqcount_t(s))
+
+static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
 {
-	unsigned ret = __read_seqcount_begin(s);
+	unsigned ret = __read_seqcount_t_begin(s);
 	smp_rmb();
 	return ret;
 }
 
 /**
  * read_seqcount_begin() - begin a seqcount_t read critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned read_seqcount_begin(const seqcount_t *s)
+#define read_seqcount_begin(s)						\
+	read_seqcount_t_begin(__to_seqcount_t(s))
+
+static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
 {
 	seqcount_lockdep_reader_access(s);
-	return raw_read_seqcount_begin(s);
+	return raw_read_seqcount_t_begin(s);
 }
 
 /**
  * raw_read_seqcount() - read the raw seqcount_t counter value
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * raw_read_seqcount opens a read critical section of the given
  * seqcount_t, without any lockdep checking, and without checking or
@@ -172,7 +447,10 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
  *
  * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_read_seqcount(const seqcount_t *s)
+#define raw_read_seqcount(s)						\
+	raw_read_seqcount_t(__to_seqcount_t(s))
+
+static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
 {
 	unsigned ret = READ_ONCE(s->sequence);
 	smp_rmb();
@@ -183,7 +461,7 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
  *                        lockdep and w/o counter stabilization
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * raw_seqcount_begin opens a read critical section of the given
  * seqcount_t. Unlike read_seqcount_begin(), this function will not wait
@@ -197,18 +475,21 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
  *
  * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_seqcount_begin(const seqcount_t *s)
+#define raw_seqcount_begin(s)						\
+	raw_seqcount_t_begin(__to_seqcount_t(s))
+
+static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
 {
 	/*
 	 * If the counter is odd, let read_seqcount_retry() fail
 	 * by decrementing the counter.
 	 */
-	return raw_read_seqcount(s) & ~1;
+	return raw_read_seqcount_t(s) & ~1;
 }
 
 /**
  * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  * @start: count, from read_seqcount_begin()
  *
  * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
@@ -221,7 +502,10 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
  *
  * Return: true if a read section retry is required, else false
  */
-static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define __read_seqcount_retry(s, start)					\
+	__read_seqcount_t_retry(__to_seqcount_t(s), start)
+
+static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
 	kcsan_atomic_next(0);
 	return unlikely(READ_ONCE(s->sequence) != start);
@@ -229,7 +513,7 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
 
 /**
  * read_seqcount_retry() - end a seqcount_t read critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  * @start: count, from read_seqcount_begin()
  *
  * read_seqcount_retry closes the read critical section of given
@@ -238,17 +522,28 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
  *
  * Return: true if a read section retry is required, else false
  */
-static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define read_seqcount_retry(s, start)					\
+	read_seqcount_t_retry(__to_seqcount_t(s), start)
+
+static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
 	smp_rmb();
-	return __read_seqcount_retry(s, start);
+	return __read_seqcount_t_retry(s, start);
 }
 
 /**
  * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  */
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+#define raw_write_seqcount_begin(s)					\
+do {									\
+	if (__associated_lock_exists_and_is_preemptible(s))		\
+		preempt_disable();					\
+									\
+	raw_write_seqcount_t_begin(__to_seqcount_t(s));			\
+} while (0)
+
+static inline void raw_write_seqcount_t_begin(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
@@ -257,49 +552,50 @@ static inline void raw_write_seqcount_begin(seqcount_t *s)
 
 /**
  * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  */
-static inline void raw_write_seqcount_end(seqcount_t *s)
+#define raw_write_seqcount_end(s)					\
+do {									\
+	raw_write_seqcount_t_end(__to_seqcount_t(s));			\
+									\
+	if (__associated_lock_exists_and_is_preemptible(s))		\
+		preempt_enable();					\
+} while (0)
+
+static inline void raw_write_seqcount_t_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
 	kcsan_nestable_atomic_end();
 }
 
-static inline void __write_seqcount_begin_nested(seqcount_t *s, int subclass)
-{
-	raw_write_seqcount_begin(s);
-	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
-}
-
 /**
  * write_seqcount_begin_nested() - start a seqcount_t write section with
  *                                 custom lockdep nesting level
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  * @subclass: lockdep nesting level
  *
  * See Documentation/locking/lockdep-design.rst
  */
-static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
-{
-	lockdep_assert_preemption_disabled();
-	__write_seqcount_begin_nested(s, subclass);
-}
-
-/*
- * A write_seqcount_begin() variant w/o lockdep non-preemptibility checks.
- *
- * Use for internal seqlock.h code where it's known that preemption is
- * already disabled. For example, seqlock_t write side functions.
- */
-static inline void __write_seqcount_begin(seqcount_t *s)
+#define write_seqcount_begin_nested(s, subclass)			\
+do {									\
+	__assert_write_section_is_protected(s);				\
+									\
+	if (__associated_lock_exists_and_is_preemptible(s))		\
+		preempt_disable();					\
+									\
+	write_seqcount_t_begin_nested(__to_seqcount_t(s), subclass);	\
+} while (0)
+
+static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
 {
-	__write_seqcount_begin_nested(s, 0);
+	raw_write_seqcount_t_begin(s);
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
 }
 
 /**
  * write_seqcount_begin() - start a seqcount_t write side critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * write_seqcount_begin opens a write side critical section of the given
  * seqcount_t.
@@ -308,26 +604,44 @@ static inline void __write_seqcount_begin(seqcount_t *s)
  * non-preemptible. If readers can be invoked from hardirq or softirq
  * context, interrupts or bottom halves must be respectively disabled.
  */
-static inline void write_seqcount_begin(seqcount_t *s)
+#define write_seqcount_begin(s)						\
+do {									\
+	__assert_write_section_is_protected(s);				\
+									\
+	if (__associated_lock_exists_and_is_preemptible(s))		\
+		preempt_disable();					\
+									\
+	write_seqcount_t_begin(__to_seqcount_t(s));			\
+} while (0)
+
+static inline void write_seqcount_t_begin(seqcount_t *s)
 {
-	write_seqcount_begin_nested(s, 0);
+	write_seqcount_t_begin_nested(s, 0);
 }
 
 /**
  * write_seqcount_end() - end a seqcount_t write side critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * The write section must've been opened with write_seqcount_begin().
  */
-static inline void write_seqcount_end(seqcount_t *s)
+#define write_seqcount_end(s)						\
+do {									\
+	write_seqcount_t_end(__to_seqcount_t(s));			\
+									\
+	if (__associated_lock_exists_and_is_preemptible(s))		\
+		preempt_enable();					\
+} while (0)
+
+static inline void write_seqcount_t_end(seqcount_t *s)
 {
 	seqcount_release(&s->dep_map, _RET_IP_);
-	raw_write_seqcount_end(s);
+	raw_write_seqcount_t_end(s);
 }
 
 /**
  * raw_write_seqcount_barrier() - do a seqcount_t write barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * This can be used to provide an ordering guarantee instead of the usual
  * consistency guarantee. It is one wmb cheaper, because it can collapse
@@ -366,7 +680,10 @@ static inline void write_seqcount_end(seqcount_t *s)
  *		WRITE_ONCE(X, false);
  *      }
  */
-static inline void raw_write_seqcount_barrier(seqcount_t *s)
+#define raw_write_seqcount_barrier(s)					\
+	raw_write_seqcount_t_barrier(__to_seqcount_t(s))
+
+static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
@@ -378,12 +695,15 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
 /**
  * write_seqcount_invalidate() - invalidate in-progress seqcount_t read
  *                               side operations
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * After write_seqcount_invalidate, no seqcount_t read side operations
  * will complete successfully and see data older than this.
  */
-static inline void write_seqcount_invalidate(seqcount_t *s)
+#define write_seqcount_invalidate(s)					\
+	write_seqcount_t_invalidate(__to_seqcount_t(s))
+
+static inline void write_seqcount_t_invalidate(seqcount_t *s)
 {
 	smp_wmb();
 	kcsan_nestable_atomic_begin();
@@ -393,7 +713,7 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
 
 /**
  * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * Use seqcount_t latching to switch between two storage places protected
  * by a sequence counter. Doing so allows having interruptible, preemptible,
@@ -406,7 +726,10 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
  * picking which data copy to read. The full counter value must then be
  * checked with read_seqcount_retry().
  */
-static inline int raw_read_seqcount_latch(seqcount_t *s)
+#define raw_read_seqcount_latch(s)					\
+	raw_read_seqcount_t_latch(__to_seqcount_t(s))
+
+static inline int raw_read_seqcount_t_latch(seqcount_t *s)
 {
 	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
 	int seq = READ_ONCE(s->sequence); /* ^^^ */
@@ -415,7 +738,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
 
 /**
  * raw_write_seqcount_latch() - redirect readers to even/odd copy
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -494,7 +817,10 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
  */
-static inline void raw_write_seqcount_latch(seqcount_t *s)
+#define raw_write_seqcount_latch(s)					\
+	raw_write_seqcount_t_latch(__to_seqcount_t(s))
+
+static inline void raw_write_seqcount_t_latch(seqcount_t *s)
 {
        smp_wmb();      /* prior stores before incrementing "sequence" */
        s->sequence++;
@@ -592,7 +918,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	__write_seqcount_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount);
 }
 
 /**
@@ -604,7 +930,7 @@ static inline void write_seqlock(seqlock_t *sl)
  */
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount);
 	spin_unlock(&sl->lock);
 }
 
@@ -618,7 +944,7 @@ static inline void write_sequnlock(seqlock_t *sl)
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	__write_seqcount_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount);
 }
 
 /**
@@ -631,7 +957,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
  */
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
@@ -645,7 +971,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	__write_seqcount_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount);
 }
 
 /**
@@ -657,7 +983,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
  */
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -666,7 +992,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	__write_seqcount_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount);
 	return flags;
 }
 
@@ -695,13 +1021,13 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
 /**
  * read_seqlock_excl() - begin a seqlock_t locking reader section
- * @sl: Pointer to seqlock_t
+ * @sl:	Pointer to seqlock_t
  *
  * read_seqlock_excl opens a seqlock_t locking reader critical section.  A
  * locking reader exclusively locks out *both* other writers *and* other
-- 
cgit v1.2.3


From ec8702da570ebb59f38471007bf71359c51b027b Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:16 +0200
Subject: seqlock: Align multi-line macros newline escapes at 72 columns

Parent commit, "seqlock: Extend seqcount API with associated locks",
introduced a big number of multi-line macros that are newline-escaped
at 72 columns.

For overall cohesion, align the earlier-existing macros similarly.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-11-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 8c16a494c968..b48729988325 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -80,17 +80,18 @@ static inline void __seqcount_init(seqcount_t *s, const char *name,
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SEQCOUNT_DEP_MAP_INIT(lockname) \
-		.dep_map = { .name = #lockname } \
+
+# define SEQCOUNT_DEP_MAP_INIT(lockname)				\
+		.dep_map = { .name = #lockname }
 
 /**
  * seqcount_init() - runtime initializer for seqcount_t
  * @s: Pointer to the seqcount_t instance
  */
-# define seqcount_init(s)				\
-	do {						\
-		static struct lock_class_key __key;	\
-		__seqcount_init((s), #s, &__key);	\
+# define seqcount_init(s)						\
+	do {								\
+		static struct lock_class_key __key;			\
+		__seqcount_init((s), #s, &__key);			\
 	} while (0)
 
 static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
@@ -842,20 +843,20 @@ typedef struct {
 	spinlock_t lock;
 } seqlock_t;
 
-#define __SEQLOCK_UNLOCKED(lockname)			\
-	{						\
-		.seqcount = SEQCNT_ZERO(lockname),	\
-		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
+#define __SEQLOCK_UNLOCKED(lockname)					\
+	{								\
+		.seqcount = SEQCNT_ZERO(lockname),			\
+		.lock =	__SPIN_LOCK_UNLOCKED(lockname)			\
 	}
 
 /**
  * seqlock_init() - dynamic initializer for seqlock_t
  * @sl: Pointer to the seqlock_t instance
  */
-#define seqlock_init(sl)				\
-	do {						\
-		seqcount_init(&(sl)->seqcount);		\
-		spin_lock_init(&(sl)->lock);		\
+#define seqlock_init(sl)						\
+	do {								\
+		seqcount_init(&(sl)->seqcount);				\
+		spin_lock_init(&(sl)->lock);				\
 	} while (0)
 
 /**
-- 
cgit v1.2.3


From 318ce71f3e3ae4108c1665f3860afa8a2a4c9f02 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:17 +0200
Subject: dma-buf: Remove custom seqcount lockdep class key

Commit 3c3b177a9369 ("reservation: add support for read-only access
using rcu") introduced a sequence counter to manage updates to
reservations. Back then, the reservation object initializer
reservation_object_init() was always inlined.

Having the sequence counter initialization inlined meant that each of
the call sites would have a different lockdep class key, which would've
broken lockdep's deadlock detection. The aforementioned commit thus
introduced, and exported, a custom seqcount lockdep class key and name.

The commit 8735f16803f00 ("dma-buf: cleanup reservation_object_init...")
transformed the reservation object initializer to a normal non-inlined C
function. seqcount_init(), which automatically defines the seqcount
lockdep class key and must be called non-inlined, can now be safely used.

Remove the seqcount custom lockdep class key, name, and export. Use
seqcount_init() inside the dma reservation object initializer.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://lkml.kernel.org/r/20200720155530.1173732-12-a.darwish@linutronix.de
---
 drivers/dma-buf/dma-resv.c | 9 +--------
 include/linux/dma-resv.h   | 2 --
 2 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index b45f8514dc82..15efa0c2dacb 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -51,12 +51,6 @@
 DEFINE_WD_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
-struct lock_class_key reservation_seqcount_class;
-EXPORT_SYMBOL(reservation_seqcount_class);
-
-const char reservation_seqcount_string[] = "reservation_seqcount";
-EXPORT_SYMBOL(reservation_seqcount_string);
-
 /**
  * dma_resv_list_alloc - allocate fence list
  * @shared_max: number of fences we need space for
@@ -135,9 +129,8 @@ subsys_initcall(dma_resv_lockdep);
 void dma_resv_init(struct dma_resv *obj)
 {
 	ww_mutex_init(&obj->lock, &reservation_ww_class);
+	seqcount_init(&obj->seq);
 
-	__seqcount_init(&obj->seq, reservation_seqcount_string,
-			&reservation_seqcount_class);
 	RCU_INIT_POINTER(obj->fence, NULL);
 	RCU_INIT_POINTER(obj->fence_excl, NULL);
 }
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index ee50d10f052b..a6538ae7d93f 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -46,8 +46,6 @@
 #include <linux/rcupdate.h>
 
 extern struct ww_class reservation_ww_class;
-extern struct lock_class_key reservation_seqcount_class;
-extern const char reservation_seqcount_string[];
 
 /**
  * struct dma_resv_list - a list of shared fences
-- 
cgit v1.2.3


From cd29f22019ec4ab998d2e1e8c831c7c42db4aa7d Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:18 +0200
Subject: dma-buf: Use sequence counter with associated wound/wait mutex

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. If the serialization primitive is
not disabling preemption implicitly, preemption has to be explicitly
disabled before entering the sequence counter write side critical
section.

The dma-buf reservation subsystem uses plain sequence counters to manage
updates to reservations. Writer serialization is accomplished through a
wound/wait mutex.

Acquiring a wound/wait mutex does not disable preemption, so this needs
to be done manually before and after the write side critical section.

Use the newly-added seqcount_ww_mutex_t instead:

  - It associates the ww_mutex with the sequence count, which enables
    lockdep to validate that the write side critical section is properly
    serialized.

  - It removes the need to explicitly add preempt_disable/enable()
    around the write side critical section because the write_begin/end()
    functions for this new data type automatically do this.

If lockdep is disabled this ww_mutex lock association is compiled out
and has neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://lkml.kernel.org/r/20200720155530.1173732-13-a.darwish@linutronix.de
---
 drivers/dma-buf/dma-resv.c                       | 8 +-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 --
 include/linux/dma-resv.h                         | 2 +-
 3 files changed, 2 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 15efa0c2dacb..a7631352a486 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -129,7 +129,7 @@ subsys_initcall(dma_resv_lockdep);
 void dma_resv_init(struct dma_resv *obj)
 {
 	ww_mutex_init(&obj->lock, &reservation_ww_class);
-	seqcount_init(&obj->seq);
+	seqcount_ww_mutex_init(&obj->seq, &obj->lock);
 
 	RCU_INIT_POINTER(obj->fence, NULL);
 	RCU_INIT_POINTER(obj->fence_excl, NULL);
@@ -260,7 +260,6 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
 	fobj = dma_resv_get_list(obj);
 	count = fobj->shared_count;
 
-	preempt_disable();
 	write_seqcount_begin(&obj->seq);
 
 	for (i = 0; i < count; ++i) {
@@ -282,7 +281,6 @@ replace:
 	smp_store_mb(fobj->shared_count, count);
 
 	write_seqcount_end(&obj->seq);
-	preempt_enable();
 	dma_fence_put(old);
 }
 EXPORT_SYMBOL(dma_resv_add_shared_fence);
@@ -309,14 +307,12 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
 	if (fence)
 		dma_fence_get(fence);
 
-	preempt_disable();
 	write_seqcount_begin(&obj->seq);
 	/* write_seqcount_begin provides the necessary memory barrier */
 	RCU_INIT_POINTER(obj->fence_excl, fence);
 	if (old)
 		old->shared_count = 0;
 	write_seqcount_end(&obj->seq);
-	preempt_enable();
 
 	/* inplace update, no shared fences */
 	while (i--)
@@ -394,13 +390,11 @@ retry:
 	src_list = dma_resv_get_list(dst);
 	old = dma_resv_get_excl(dst);
 
-	preempt_disable();
 	write_seqcount_begin(&dst->seq);
 	/* write_seqcount_begin provides the necessary memory barrier */
 	RCU_INIT_POINTER(dst->fence_excl, new);
 	RCU_INIT_POINTER(dst->fence, dst_list);
 	write_seqcount_end(&dst->seq);
-	preempt_enable();
 
 	dma_resv_list_free(src_list);
 	dma_fence_put(old);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index b91b5171270f..ff4b583cb96a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -258,11 +258,9 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
 	new->shared_count = k;
 
 	/* Install the new fence list, seqcount provides the barriers */
-	preempt_disable();
 	write_seqcount_begin(&resv->seq);
 	RCU_INIT_POINTER(resv->fence, new);
 	write_seqcount_end(&resv->seq);
-	preempt_enable();
 
 	/* Drop the references to the removed fences or move them to ef_list */
 	for (i = j, k = 0; i < old->shared_count; ++i) {
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index a6538ae7d93f..d44a77e8a7e3 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -69,7 +69,7 @@ struct dma_resv_list {
  */
 struct dma_resv {
 	struct ww_mutex lock;
-	seqcount_t seq;
+	seqcount_ww_mutex_t seq;
 
 	struct dma_fence __rcu *fence_excl;
 	struct dma_resv_list __rcu *fence;
-- 
cgit v1.2.3


From b75058614fdd3140074a640b514f6a0b4d485a2d Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:19 +0200
Subject: sched: tasks: Use sequence counter with associated spinlock

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. A plain seqcount_t does not
contain the information of which lock must be held when entering a write
side critical section.

Use the new seqcount_spinlock_t data type, which allows to associate a
spinlock with the sequence counter. This enables lockdep to verify that
the spinlock used for writer serialization is held when the write side
critical section is entered.

If lockdep is disabled this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-14-a.darwish@linutronix.de
---
 include/linux/sched.h | 2 +-
 init/init_task.c      | 3 ++-
 kernel/fork.c         | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8d1de021b315..9a9d8263962d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1050,7 +1050,7 @@ struct task_struct {
 	/* Protected by ->alloc_lock: */
 	nodemask_t			mems_allowed;
 	/* Seqence number to catch updates: */
-	seqcount_t			mems_allowed_seq;
+	seqcount_spinlock_t		mems_allowed_seq;
 	int				cpuset_mem_spread_rotor;
 	int				cpuset_slab_spread_rotor;
 #endif
diff --git a/init/init_task.c b/init/init_task.c
index 15089d15010a..94fe3ba1bb60 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -154,7 +154,8 @@ struct task_struct init_task
 	.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
 #endif
 #ifdef CONFIG_CPUSETS
-	.mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq),
+	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
+						 &init_task.alloc_lock),
 #endif
 #ifdef CONFIG_RT_MUTEXES
 	.pi_waiters	= RB_ROOT_CACHED,
diff --git a/kernel/fork.c b/kernel/fork.c
index 70d9d0a4de2a..fc72f09a61b2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2032,7 +2032,7 @@ static __latent_entropy struct task_struct *copy_process(
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
 	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
-	seqcount_init(&p->mems_allowed_seq);
+	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
-- 
cgit v1.2.3


From 26475371976c69489d3a8e6c8bbf35afbbc25055 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:24 +0200
Subject: vfs: Use sequence counter with associated spinlock

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. A plain seqcount_t does not
contain the information of which lock must be held when entering a write
side critical section.

Use the new seqcount_spinlock_t data type, which allows to associate a
spinlock with the sequence counter. This enables lockdep to verify that
the spinlock used for writer serialization is held when the write side
critical section is entered.

If lockdep is disabled this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-19-a.darwish@linutronix.de
---
 fs/dcache.c               | 2 +-
 fs/fs_struct.c            | 4 ++--
 include/linux/dcache.h    | 2 +-
 include/linux/fs_struct.h | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dcache.c b/fs/dcache.c
index 361ea7ab30ea..ea0485861d93 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1746,7 +1746,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	dentry->d_lockref.count = 1;
 	dentry->d_flags = 0;
 	spin_lock_init(&dentry->d_lock);
-	seqcount_init(&dentry->d_seq);
+	seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
 	dentry->d_inode = NULL;
 	dentry->d_parent = dentry;
 	dentry->d_sb = sb;
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index ca639ed967b7..04b3f5b9c629 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -117,7 +117,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 		fs->users = 1;
 		fs->in_exec = 0;
 		spin_lock_init(&fs->lock);
-		seqcount_init(&fs->seq);
+		seqcount_spinlock_init(&fs->seq, &fs->lock);
 		fs->umask = old->umask;
 
 		spin_lock(&old->lock);
@@ -163,6 +163,6 @@ EXPORT_SYMBOL(current_umask);
 struct fs_struct init_fs = {
 	.users		= 1,
 	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
-	.seq		= SEQCNT_ZERO(init_fs.seq),
+	.seq		= SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock),
 	.umask		= 0022,
 };
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index a81f0c3cf352..65d975bf9390 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -89,7 +89,7 @@ extern struct dentry_stat_t dentry_stat;
 struct dentry {
 	/* RCU lookup touched fields */
 	unsigned int d_flags;		/* protected by d_lock */
-	seqcount_t d_seq;		/* per dentry seqlock */
+	seqcount_spinlock_t d_seq;	/* per dentry seqlock */
 	struct hlist_bl_node d_hash;	/* lookup hash list */
 	struct dentry *d_parent;	/* parent directory */
 	struct qstr d_name;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index cf1015abfbf2..783b48dedb72 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -9,7 +9,7 @@
 struct fs_struct {
 	int users;
 	spinlock_t lock;
-	seqcount_t seq;
+	seqcount_spinlock_t seq;
 	int umask;
 	int in_exec;
 	struct path root, pwd;
-- 
cgit v1.2.3


From 5c73b9a2b1b4ecc809a914aa64970157b3d8c936 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:29 +0200
Subject: kvm/eventfd: Use sequence counter with associated spinlock

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. A plain seqcount_t does not
contain the information of which lock must be held when entering a write
side critical section.

Use the new seqcount_spinlock_t data type, which allows to associate a
spinlock with the sequence counter. This enables lockdep to verify that
the spinlock used for writer serialization is held when the write side
critical section is entered.

If lockdep is disabled this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lkml.kernel.org/r/20200720155530.1173732-24-a.darwish@linutronix.de
---
 include/linux/kvm_irqfd.h | 2 +-
 virt/kvm/eventfd.c        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index dc1da020305b..dac047abdba7 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -42,7 +42,7 @@ struct kvm_kernel_irqfd {
 	wait_queue_entry_t wait;
 	/* Update side is protected by irqfds.lock */
 	struct kvm_kernel_irq_routing_entry irq_entry;
-	seqcount_t irq_entry_sc;
+	seqcount_spinlock_t irq_entry_sc;
 	/* Used for level IRQ fast-path */
 	int gsi;
 	struct work_struct inject;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index ef7ed916ad4a..d6408bb497dc 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -303,7 +303,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	INIT_LIST_HEAD(&irqfd->list);
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
-	seqcount_init(&irqfd->irq_entry_sc);
+	seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock);
 
 	f = fdget(args->fd);
 	if (!f.file) {
-- 
cgit v1.2.3


From af5a06b582ec3d7b0160b4faaa65f73d8dcf989f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Mon, 20 Jul 2020 17:55:30 +0200
Subject: hrtimer: Use sequence counter with associated raw spinlock

A sequence counter write side critical section must be protected by some
form of locking to serialize writers. A plain seqcount_t does not
contain the information of which lock must be held when entering a write
side critical section.

Use the new seqcount_raw_spinlock_t data type, which allows to associate
a raw spinlock with the sequence counter. This enables lockdep to verify
that the raw spinlock used for writer serialization is held when the
write side critical section is entered.

If lockdep is disabled this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-25-a.darwish@linutronix.de
---
 include/linux/hrtimer.h |  2 +-
 kernel/time/hrtimer.c   | 13 ++++++++++---
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 15c8ac313678..25993b86ac5c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -159,7 +159,7 @@ struct hrtimer_clock_base {
 	struct hrtimer_cpu_base	*cpu_base;
 	unsigned int		index;
 	clockid_t		clockid;
-	seqcount_t		seq;
+	seqcount_raw_spinlock_t	seq;
 	struct hrtimer		*running;
 	struct timerqueue_head	active;
 	ktime_t			(*get_time)(void);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index d89da1c7e005..c4038511d5c9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -135,7 +135,11 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
  * timer->base->cpu_base
  */
 static struct hrtimer_cpu_base migration_cpu_base = {
-	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
+	.clock_base = { {
+		.cpu_base = &migration_cpu_base,
+		.seq      = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq,
+						     &migration_cpu_base.lock),
+	}, },
 };
 
 #define migration_base	migration_cpu_base.clock_base[0]
@@ -1998,8 +2002,11 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	int i;
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		cpu_base->clock_base[i].cpu_base = cpu_base;
-		timerqueue_init_head(&cpu_base->clock_base[i].active);
+		struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i];
+
+		clock_b->cpu_base = cpu_base;
+		seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock);
+		timerqueue_init_head(&clock_b->active);
 	}
 
 	cpu_base->cpu = cpu;
-- 
cgit v1.2.3


From e55687fe5c1e4849e5559a0a49199c9ca3fff36e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Jul 2020 11:56:22 +0200
Subject: seqlock: s/__SEQ_LOCKDEP/__SEQ_LOCK/g

__SEQ_LOCKDEP() is an expression gate for the
seqcount_LOCKNAME_t::lock member. Rename it to be about the member,
not the gate condition.

Later (PREEMPT_RT) patches will make the member available for !LOCKDEP
configs.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/seqlock.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index b48729988325..c689abab06c8 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -133,20 +133,20 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  */
 
 #ifdef CONFIG_LOCKDEP
-#define __SEQ_LOCKDEP(expr)	expr
+#define __SEQ_LOCK(expr)	expr
 #else
-#define __SEQ_LOCKDEP(expr)
+#define __SEQ_LOCK(expr)
 #endif
 
 #define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
 	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
-	__SEQ_LOCKDEP(.lock	= (assoc_lock))				\
+	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
 #define seqcount_locktype_init(s, assoc_lock)				\
 do {									\
 	seqcount_init(&(s)->seqcount);					\
-	__SEQ_LOCKDEP((s)->lock = (assoc_lock));			\
+	__SEQ_LOCK((s)->lock = (assoc_lock));				\
 } while (0)
 
 /**
@@ -161,7 +161,7 @@ do {									\
  */
 typedef struct seqcount_spinlock {
 	seqcount_t	seqcount;
-	__SEQ_LOCKDEP(spinlock_t	*lock);
+	__SEQ_LOCK(spinlock_t	*lock);
 } seqcount_spinlock_t;
 
 /**
@@ -192,7 +192,7 @@ typedef struct seqcount_spinlock {
  */
 typedef struct seqcount_raw_spinlock {
 	seqcount_t      seqcount;
-	__SEQ_LOCKDEP(raw_spinlock_t	*lock);
+	__SEQ_LOCK(raw_spinlock_t	*lock);
 } seqcount_raw_spinlock_t;
 
 /**
@@ -223,7 +223,7 @@ typedef struct seqcount_raw_spinlock {
  */
 typedef struct seqcount_rwlock {
 	seqcount_t      seqcount;
-	__SEQ_LOCKDEP(rwlock_t		*lock);
+	__SEQ_LOCK(rwlock_t		*lock);
 } seqcount_rwlock_t;
 
 /**
@@ -257,7 +257,7 @@ typedef struct seqcount_rwlock {
  */
 typedef struct seqcount_mutex {
 	seqcount_t      seqcount;
-	__SEQ_LOCKDEP(struct mutex	*lock);
+	__SEQ_LOCK(struct mutex	*lock);
 } seqcount_mutex_t;
 
 /**
@@ -291,7 +291,7 @@ typedef struct seqcount_mutex {
  */
 typedef struct seqcount_ww_mutex {
 	seqcount_t      seqcount;
-	__SEQ_LOCKDEP(struct ww_mutex	*lock);
+	__SEQ_LOCK(struct ww_mutex	*lock);
 } seqcount_ww_mutex_t;
 
 /**
@@ -329,7 +329,7 @@ __seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s)		\
 static inline void							\
 __seqcount_##locktype##_assert(seqcount_##locktype##_t *s)		\
 {									\
-	__SEQ_LOCKDEP(lockdep_assert_held(lockmember));			\
+	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
 }
 
 /*
-- 
cgit v1.2.3


From a8772dccb2ec7b139db1b3ba782ecb12ed92d7c3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Jul 2020 11:56:49 +0200
Subject: seqlock: Fold seqcount_LOCKNAME_t definition

Manual repetition is boring and error prone.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/seqlock.h | 142 +++++++++++++-----------------------------------
 1 file changed, 39 insertions(+), 103 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index c689abab06c8..4b259bb4d4b9 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -149,21 +149,6 @@ do {									\
 	__SEQ_LOCK((s)->lock = (assoc_lock));				\
 } while (0)
 
-/**
- * typedef seqcount_spinlock_t - sequence counter with spinlock associated
- * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated spinlock
- *
- * A plain sequence counter with external writer synchronization by a
- * spinlock. The spinlock is associated to the sequence count in the
- * static initializer or init function. This enables lockdep to validate
- * that the write side critical section is properly serialized.
- */
-typedef struct seqcount_spinlock {
-	seqcount_t	seqcount;
-	__SEQ_LOCK(spinlock_t	*lock);
-} seqcount_spinlock_t;
-
 /**
  * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t
  * @name:	Name of the seqcount_spinlock_t instance
@@ -180,21 +165,6 @@ typedef struct seqcount_spinlock {
 #define seqcount_spinlock_init(s, lock)					\
 	seqcount_locktype_init(s, lock)
 
-/**
- * typedef seqcount_raw_spinlock_t - sequence count with raw spinlock associated
- * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated raw spinlock
- *
- * A plain sequence counter with external writer synchronization by a
- * raw spinlock. The raw spinlock is associated to the sequence count in
- * the static initializer or init function. This enables lockdep to
- * validate that the write side critical section is properly serialized.
- */
-typedef struct seqcount_raw_spinlock {
-	seqcount_t      seqcount;
-	__SEQ_LOCK(raw_spinlock_t	*lock);
-} seqcount_raw_spinlock_t;
-
 /**
  * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t
  * @name:	Name of the seqcount_raw_spinlock_t instance
@@ -211,21 +181,6 @@ typedef struct seqcount_raw_spinlock {
 #define seqcount_raw_spinlock_init(s, lock)				\
 	seqcount_locktype_init(s, lock)
 
-/**
- * typedef seqcount_rwlock_t - sequence count with rwlock associated
- * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated rwlock
- *
- * A plain sequence counter with external writer synchronization by a
- * rwlock. The rwlock is associated to the sequence count in the static
- * initializer or init function. This enables lockdep to validate that
- * the write side critical section is properly serialized.
- */
-typedef struct seqcount_rwlock {
-	seqcount_t      seqcount;
-	__SEQ_LOCK(rwlock_t		*lock);
-} seqcount_rwlock_t;
-
 /**
  * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t
  * @name:	Name of the seqcount_rwlock_t instance
@@ -242,24 +197,6 @@ typedef struct seqcount_rwlock {
 #define seqcount_rwlock_init(s, lock)					\
 	seqcount_locktype_init(s, lock)
 
-/**
- * typedef seqcount_mutex_t - sequence count with mutex associated
- * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated mutex
- *
- * A plain sequence counter with external writer synchronization by a
- * mutex. The mutex is associated to the sequence counter in the static
- * initializer or init function. This enables lockdep to validate that
- * the write side critical section is properly serialized.
- *
- * The write side API functions write_seqcount_begin()/end() automatically
- * disable and enable preemption when used with seqcount_mutex_t.
- */
-typedef struct seqcount_mutex {
-	seqcount_t      seqcount;
-	__SEQ_LOCK(struct mutex	*lock);
-} seqcount_mutex_t;
-
 /**
  * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t
  * @name:	Name of the seqcount_mutex_t instance
@@ -276,24 +213,6 @@ typedef struct seqcount_mutex {
 #define seqcount_mutex_init(s, lock)					\
 	seqcount_locktype_init(s, lock)
 
-/**
- * typedef seqcount_ww_mutex_t - sequence count with ww_mutex associated
- * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated ww_mutex
- *
- * A plain sequence counter with external writer synchronization by a
- * ww_mutex. The ww_mutex is associated to the sequence counter in the static
- * initializer or init function. This enables lockdep to validate that
- * the write side critical section is properly serialized.
- *
- * The write side API functions write_seqcount_begin()/end() automatically
- * disable and enable preemption when used with seqcount_ww_mutex_t.
- */
-typedef struct seqcount_ww_mutex {
-	seqcount_t      seqcount;
-	__SEQ_LOCK(struct ww_mutex	*lock);
-} seqcount_ww_mutex_t;
-
 /**
  * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t
  * @name:	Name of the seqcount_ww_mutex_t instance
@@ -310,30 +229,50 @@ typedef struct seqcount_ww_mutex {
 #define seqcount_ww_mutex_init(s, lock)					\
 	seqcount_locktype_init(s, lock)
 
-/*
- * @preempt: Is the associated write serialization lock preemtpible?
+/**
+ * typedef seqcount_LOCKNAME_t - sequence counter with spinlock associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated spinlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * spinlock. The spinlock is associated to the sequence count in the
+ * static initializer or init function. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
  */
-#define SEQCOUNT_LOCKTYPE(locktype, preempt, lockmember)		\
-static inline seqcount_t *						\
-__seqcount_##locktype##_ptr(seqcount_##locktype##_t *s)			\
+
+/*
+ * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
+ * @locktype:		actual typename
+ * @lockname:		name
+ * @preemptible:	preemptibility of above locktype
+ * @lockmember:		argument for lockdep_assert_held()
+ */
+#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember)	\
+typedef struct seqcount_##lockname {					\
+	seqcount_t		seqcount;				\
+	__SEQ_LOCK(locktype	*lock);					\
+} seqcount_##lockname##_t;						\
+									\
+static __always_inline seqcount_t *					\
+__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
 	return &s->seqcount;						\
 }									\
 									\
-static inline bool							\
-__seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s)		\
+static __always_inline bool						\
+__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s)		\
 {									\
-	return preempt;							\
+	return preemptible;						\
 }									\
 									\
-static inline void							\
-__seqcount_##locktype##_assert(seqcount_##locktype##_t *s)		\
+static __always_inline void						\
+__seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
 {									\
 	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
 }
 
 /*
- * Similar hooks, but for plain seqcount_t
+ * __seqprop() for seqcount_t
  */
 
 static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
@@ -351,17 +290,14 @@ static inline void __seqcount_assert(seqcount_t *s)
 	lockdep_assert_preemption_disabled();
 }
 
-/*
- * @s: Pointer to seqcount_locktype_t, generated hooks first parameter.
- */
-SEQCOUNT_LOCKTYPE(raw_spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(rwlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(mutex,	true,	s->lock)
-SEQCOUNT_LOCKTYPE(ww_mutex,	true,	&s->lock->base)
-
-#define __seqprop_case(s, locktype, prop)				\
-	seqcount_##locktype##_t: __seqcount_##locktype##_##prop((void *)(s))
+SEQCOUNT_LOCKTYPE(raw_spinlock_t,	raw_spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(spinlock_t,		spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
+SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
+SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
+
+#define __seqprop_case(s, lockname, prop)				\
+	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
 
 #define __seqprop(s, prop) _Generic(*(s),				\
 	seqcount_t:		__seqcount_##prop((void *)(s)),		\
-- 
cgit v1.2.3


From e4e9ab3f9f91ad3b88d12363f890e8ad9b59b645 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Jul 2020 12:00:53 +0200
Subject: seqlock: Fold seqcount_LOCKNAME_init() definition

Manual repetition is boring and error prone.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/seqlock.h | 61 ++++++++++++-------------------------------------
 1 file changed, 14 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 4b259bb4d4b9..501ff47d1e8e 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -143,12 +143,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
-#define seqcount_locktype_init(s, assoc_lock)				\
-do {									\
-	seqcount_init(&(s)->seqcount);					\
-	__SEQ_LOCK((s)->lock = (assoc_lock));				\
-} while (0)
-
 /**
  * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t
  * @name:	Name of the seqcount_spinlock_t instance
@@ -157,14 +151,6 @@ do {									\
 #define SEQCNT_SPINLOCK_ZERO(name, lock)				\
 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
-/**
- * seqcount_spinlock_init - runtime initializer for seqcount_spinlock_t
- * @s:		Pointer to the seqcount_spinlock_t instance
- * @lock:	Pointer to the associated spinlock
- */
-#define seqcount_spinlock_init(s, lock)					\
-	seqcount_locktype_init(s, lock)
-
 /**
  * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t
  * @name:	Name of the seqcount_raw_spinlock_t instance
@@ -173,14 +159,6 @@ do {									\
 #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)				\
 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
-/**
- * seqcount_raw_spinlock_init - runtime initializer for seqcount_raw_spinlock_t
- * @s:		Pointer to the seqcount_raw_spinlock_t instance
- * @lock:	Pointer to the associated raw_spinlock
- */
-#define seqcount_raw_spinlock_init(s, lock)				\
-	seqcount_locktype_init(s, lock)
-
 /**
  * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t
  * @name:	Name of the seqcount_rwlock_t instance
@@ -189,14 +167,6 @@ do {									\
 #define SEQCNT_RWLOCK_ZERO(name, lock)					\
 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
-/**
- * seqcount_rwlock_init - runtime initializer for seqcount_rwlock_t
- * @s:		Pointer to the seqcount_rwlock_t instance
- * @lock:	Pointer to the associated rwlock
- */
-#define seqcount_rwlock_init(s, lock)					\
-	seqcount_locktype_init(s, lock)
-
 /**
  * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t
  * @name:	Name of the seqcount_mutex_t instance
@@ -205,14 +175,6 @@ do {									\
 #define SEQCNT_MUTEX_ZERO(name, lock)					\
 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
-/**
- * seqcount_mutex_init - runtime initializer for seqcount_mutex_t
- * @s:		Pointer to the seqcount_mutex_t instance
- * @lock:	Pointer to the associated mutex
- */
-#define seqcount_mutex_init(s, lock)					\
-	seqcount_locktype_init(s, lock)
-
 /**
  * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t
  * @name:	Name of the seqcount_ww_mutex_t instance
@@ -222,15 +184,7 @@ do {									\
 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
 /**
- * seqcount_ww_mutex_init - runtime initializer for seqcount_ww_mutex_t
- * @s:		Pointer to the seqcount_ww_mutex_t instance
- * @lock:	Pointer to the associated ww_mutex
- */
-#define seqcount_ww_mutex_init(s, lock)					\
-	seqcount_locktype_init(s, lock)
-
-/**
- * typedef seqcount_LOCKNAME_t - sequence counter with spinlock associated
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated
  * @seqcount:	The real sequence counter
  * @lock:	Pointer to the associated spinlock
  *
@@ -240,6 +194,12 @@ do {									\
  * that the write side critical section is properly serialized.
  */
 
+/**
+ * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
+ * @s:		Pointer to the seqcount_LOCKNAME_t instance
+ * @lock:	Pointer to the associated LOCKTYPE
+ */
+
 /*
  * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
  * @locktype:		actual typename
@@ -253,6 +213,13 @@ typedef struct seqcount_##lockname {					\
 	__SEQ_LOCK(locktype	*lock);					\
 } seqcount_##lockname##_t;						\
 									\
+static __always_inline void						\
+seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
+{									\
+	seqcount_init(&s->seqcount);					\
+	__SEQ_LOCK(s->lock = lock);					\
+}									\
+									\
 static __always_inline seqcount_t *					\
 __seqcount_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
-- 
cgit v1.2.3


From 0efc94c5d15c3da0a69543d86ad2180f39256ed6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Jul 2020 12:03:13 +0200
Subject: seqcount: Compress SEQCNT_LOCKNAME_ZERO()

Less is more.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/seqlock.h | 63 ++++++++++++++-----------------------------------
 1 file changed, 18 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 501ff47d1e8e..251dcd6f5cd8 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -138,51 +138,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #define __SEQ_LOCK(expr)
 #endif
 
-#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
-	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
-	__SEQ_LOCK(.lock	= (assoc_lock))				\
-}
-
-/**
- * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t
- * @name:	Name of the seqcount_spinlock_t instance
- * @lock:	Pointer to the associated spinlock
- */
-#define SEQCNT_SPINLOCK_ZERO(name, lock)				\
-	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
-/**
- * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t
- * @name:	Name of the seqcount_raw_spinlock_t instance
- * @lock:	Pointer to the associated raw_spinlock
- */
-#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)				\
-	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
-/**
- * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t
- * @name:	Name of the seqcount_rwlock_t instance
- * @lock:	Pointer to the associated rwlock
- */
-#define SEQCNT_RWLOCK_ZERO(name, lock)					\
-	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
-/**
- * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t
- * @name:	Name of the seqcount_mutex_t instance
- * @lock:	Pointer to the associated mutex
- */
-#define SEQCNT_MUTEX_ZERO(name, lock)					\
-	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
-/**
- * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t
- * @name:	Name of the seqcount_ww_mutex_t instance
- * @lock:	Pointer to the associated ww_mutex
- */
-#define SEQCNT_WW_MUTEX_ZERO(name, lock)				\
-	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
 /**
  * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated
  * @seqcount:	The real sequence counter
@@ -263,6 +218,24 @@ SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
 SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
 SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
 
+/**
+ * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
+ * @name:	Name of the seqcount_LOCKNAME_t instance
+ * @lock:	Pointer to the associated LOCKTYPE
+ */
+
+#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
+	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
+	__SEQ_LOCK(.lock	= (assoc_lock))				\
+}
+
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+
 #define __seqprop_case(s, lockname, prop)				\
 	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
 
-- 
cgit v1.2.3


From b5e6a027bd327daa679ca55182a920659e2cbb90 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Jul 2020 12:11:49 +0200
Subject: seqcount: More consistent seqprop names

Attempt uniformity and brevity.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/seqlock.h | 52 ++++++++++++++++++++++++-------------------------
 1 file changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 251dcd6f5cd8..a076f783aa36 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -247,9 +247,9 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
 	__seqprop_case((s),	mutex,		prop),			\
 	__seqprop_case((s),	ww_mutex,	prop))
 
-#define __to_seqcount_t(s)				__seqprop(s, ptr)
-#define __associated_lock_exists_and_is_preemptible(s)	__seqprop(s, preemptible)
-#define __assert_write_section_is_protected(s)		__seqprop(s, assert)
+#define __seqcount_ptr(s)		__seqprop(s, ptr)
+#define __seqcount_lock_preemptible(s)	__seqprop(s, preemptible)
+#define __seqcount_assert_lock_held(s)	__seqprop(s, assert)
 
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
@@ -266,7 +266,7 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define __read_seqcount_begin(s)					\
-	__read_seqcount_t_begin(__to_seqcount_t(s))
+	__read_seqcount_t_begin(__seqcount_ptr(s))
 
 static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
 {
@@ -289,7 +289,7 @@ repeat:
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount_begin(s)					\
-	raw_read_seqcount_t_begin(__to_seqcount_t(s))
+	raw_read_seqcount_t_begin(__seqcount_ptr(s))
 
 static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
 {
@@ -305,7 +305,7 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define read_seqcount_begin(s)						\
-	read_seqcount_t_begin(__to_seqcount_t(s))
+	read_seqcount_t_begin(__seqcount_ptr(s))
 
 static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
 {
@@ -325,7 +325,7 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount(s)						\
-	raw_read_seqcount_t(__to_seqcount_t(s))
+	raw_read_seqcount_t(__seqcount_ptr(s))
 
 static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
 {
@@ -353,7 +353,7 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_seqcount_begin(s)						\
-	raw_seqcount_t_begin(__to_seqcount_t(s))
+	raw_seqcount_t_begin(__seqcount_ptr(s))
 
 static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
 {
@@ -380,7 +380,7 @@ static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
  * Return: true if a read section retry is required, else false
  */
 #define __read_seqcount_retry(s, start)					\
-	__read_seqcount_t_retry(__to_seqcount_t(s), start)
+	__read_seqcount_t_retry(__seqcount_ptr(s), start)
 
 static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
@@ -400,7 +400,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
  * Return: true if a read section retry is required, else false
  */
 #define read_seqcount_retry(s, start)					\
-	read_seqcount_t_retry(__to_seqcount_t(s), start)
+	read_seqcount_t_retry(__seqcount_ptr(s), start)
 
 static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
@@ -414,10 +414,10 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
  */
 #define raw_write_seqcount_begin(s)					\
 do {									\
-	if (__associated_lock_exists_and_is_preemptible(s))		\
+	if (__seqcount_lock_preemptible(s))				\
 		preempt_disable();					\
 									\
-	raw_write_seqcount_t_begin(__to_seqcount_t(s));			\
+	raw_write_seqcount_t_begin(__seqcount_ptr(s));			\
 } while (0)
 
 static inline void raw_write_seqcount_t_begin(seqcount_t *s)
@@ -433,9 +433,9 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s)
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
-	raw_write_seqcount_t_end(__to_seqcount_t(s));			\
+	raw_write_seqcount_t_end(__seqcount_ptr(s));			\
 									\
-	if (__associated_lock_exists_and_is_preemptible(s))		\
+	if (__seqcount_lock_preemptible(s))				\
 		preempt_enable();					\
 } while (0)
 
@@ -456,12 +456,12 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s)
  */
 #define write_seqcount_begin_nested(s, subclass)			\
 do {									\
-	__assert_write_section_is_protected(s);				\
+	__seqcount_assert_lock_held(s);					\
 									\
-	if (__associated_lock_exists_and_is_preemptible(s))		\
+	if (__seqcount_lock_preemptible(s))				\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin_nested(__to_seqcount_t(s), subclass);	\
+	write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass);	\
 } while (0)
 
 static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
@@ -483,12 +483,12 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
  */
 #define write_seqcount_begin(s)						\
 do {									\
-	__assert_write_section_is_protected(s);				\
+	__seqcount_assert_lock_held(s);					\
 									\
-	if (__associated_lock_exists_and_is_preemptible(s))		\
+	if (__seqcount_lock_preemptible(s))				\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin(__to_seqcount_t(s));			\
+	write_seqcount_t_begin(__seqcount_ptr(s));			\
 } while (0)
 
 static inline void write_seqcount_t_begin(seqcount_t *s)
@@ -504,9 +504,9 @@ static inline void write_seqcount_t_begin(seqcount_t *s)
  */
 #define write_seqcount_end(s)						\
 do {									\
-	write_seqcount_t_end(__to_seqcount_t(s));			\
+	write_seqcount_t_end(__seqcount_ptr(s));			\
 									\
-	if (__associated_lock_exists_and_is_preemptible(s))		\
+	if (__seqcount_lock_preemptible(s))				\
 		preempt_enable();					\
 } while (0)
 
@@ -558,7 +558,7 @@ static inline void write_seqcount_t_end(seqcount_t *s)
  *      }
  */
 #define raw_write_seqcount_barrier(s)					\
-	raw_write_seqcount_t_barrier(__to_seqcount_t(s))
+	raw_write_seqcount_t_barrier(__seqcount_ptr(s))
 
 static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 {
@@ -578,7 +578,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
  * will complete successfully and see data older than this.
  */
 #define write_seqcount_invalidate(s)					\
-	write_seqcount_t_invalidate(__to_seqcount_t(s))
+	write_seqcount_t_invalidate(__seqcount_ptr(s))
 
 static inline void write_seqcount_t_invalidate(seqcount_t *s)
 {
@@ -604,7 +604,7 @@ static inline void write_seqcount_t_invalidate(seqcount_t *s)
  * checked with read_seqcount_retry().
  */
 #define raw_read_seqcount_latch(s)					\
-	raw_read_seqcount_t_latch(__to_seqcount_t(s))
+	raw_read_seqcount_t_latch(__seqcount_ptr(s))
 
 static inline int raw_read_seqcount_t_latch(seqcount_t *s)
 {
@@ -695,7 +695,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	patterns to manage the lifetimes of the objects within.
  */
 #define raw_write_seqcount_latch(s)					\
-	raw_write_seqcount_t_latch(__to_seqcount_t(s))
+	raw_write_seqcount_t_latch(__seqcount_ptr(s))
 
 static inline void raw_write_seqcount_t_latch(seqcount_t *s)
 {
-- 
cgit v1.2.3


From 5037d368b2c2c90e9432d477e5562dce1c33d5c9 Mon Sep 17 00:00:00 2001
From: Andreas Färber <afaerber@suse.de>
Date: Wed, 22 Jul 2020 11:06:57 +0100
Subject: nvmem: core: Add nvmem_cell_read_u8()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Complement the u16, u32 and u64 helpers with a u8 variant to ease
accessing byte-sized values.

This helper will be useful for Realtek Digital Home Center platforms,
which store some byte and sub-byte sized values in non-volatile memory.

Signed-off-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20200722100705.7772-7-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 15 +++++++++++++++
 include/linux/nvmem-consumer.h |  1 +
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 95bed31391cd..d6bacc878500 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -1374,6 +1374,21 @@ static int nvmem_cell_read_common(struct device *dev, const char *cell_id,
 	return 0;
 }
 
+/**
+ * nvmem_cell_read_u8() - Read a cell value as a u8
+ *
+ * @dev: Device that requests the nvmem cell.
+ * @cell_id: Name of nvmem cell to read.
+ * @val: pointer to output value.
+ *
+ * Return: 0 on success or negative errno.
+ */
+int nvmem_cell_read_u8(struct device *dev, const char *cell_id, u8 *val)
+{
+	return nvmem_cell_read_common(dev, cell_id, val, sizeof(*val));
+}
+EXPORT_SYMBOL_GPL(nvmem_cell_read_u8);
+
 /**
  * nvmem_cell_read_u16() - Read a cell value as a u16
  *
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 1b311d27c9b8..052293f4cbdb 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -61,6 +61,7 @@ void nvmem_cell_put(struct nvmem_cell *cell);
 void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell);
 void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len);
 int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len);
+int nvmem_cell_read_u8(struct device *dev, const char *cell_id, u8 *val);
 int nvmem_cell_read_u16(struct device *dev, const char *cell_id, u16 *val);
 int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val);
 int nvmem_cell_read_u64(struct device *dev, const char *cell_id, u64 *val);
-- 
cgit v1.2.3


From 731aa3fae8137ebca83a01d20fbf3effb4798fc8 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 22 Jul 2020 11:06:58 +0100
Subject: nvmem: core: add support to auto devid

For nvmem providers which have multiple instances, it is required
to suffix the provider name with proper id, so that they do not
confict for the same name. Currently the core does not handle
this case properly eventhough core already has logic to generate the id.

This patch add new devid type NVMEM_DEVID_AUTO for providers to be
able to allow core to assign id and append it to provier name.

Reported-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Tested-by: Shawn Guo <shawn.guo@linaro.org>
Link: https://lore.kernel.org/r/20200722100705.7772-8-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 10 ++++++++--
 include/linux/nvmem-provider.h |  3 +++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index d6bacc878500..6cd3edb2eaf6 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -635,12 +635,18 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (!config->no_of_node)
 		nvmem->dev.of_node = config->dev->of_node;
 
-	if (config->id == -1 && config->name) {
+	switch (config->id) {
+	case NVMEM_DEVID_NONE:
 		dev_set_name(&nvmem->dev, "%s", config->name);
-	} else {
+		break;
+	case NVMEM_DEVID_AUTO:
+		dev_set_name(&nvmem->dev, "%s%d", config->name, nvmem->id);
+		break;
+	default:
 		dev_set_name(&nvmem->dev, "%s%d",
 			     config->name ? : "nvmem",
 			     config->name ? config->id : nvmem->id);
+		break;
 	}
 
 	nvmem->read_only = device_property_present(config->dev, "read-only") ||
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 6d6f8e5d24c9..06409a6c40bc 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -27,6 +27,9 @@ enum nvmem_type {
 	NVMEM_TYPE_BATTERY_BACKED,
 };
 
+#define NVMEM_DEVID_NONE	(-1)
+#define NVMEM_DEVID_AUTO	(-2)
+
 /**
  * struct nvmem_config - NVMEM device configuration
  *
-- 
cgit v1.2.3


From 868f3ee6e452bc2b89e68183a1700fcbbe0807b1 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 23 Jul 2020 03:33:54 +0300
Subject: serial: 8250: Add 8250 port clock update method

Some platforms can be designed in a way so the UART port reference clock
might be asynchronously changed at some point. In Baikal-T1 SoC this may
happen due to the reference clock being shared between two UART ports, on
the Allwinner SoC the reference clock is derived from the CPU clock, so
any CPU frequency change should get to be known/reflected by/in the UART
controller as well. But it's not enough to just update the
uart_port->uartclk field of the corresponding UART port, the 8250
controller reference clock divisor should be altered so to preserve
current baud rate setting. All of these things is done in a coherent
way by calling the serial8250_update_uartclk() method provided in this
patch. Though note that it isn't supposed to be called from within the
UART port callbacks because the locks using to the protect the UART port
data are already taken in there.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>

Link: https://lore.kernel.org/r/20200723003357.26897-2-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 40 +++++++++++++++++++++++++++++++++++++
 include/linux/serial_8250.h         |  2 ++
 2 files changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index d64ca77d9cfa..09475695effd 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2632,6 +2632,46 @@ static unsigned int serial8250_get_baud_rate(struct uart_port *port,
 				  (port->uartclk + tolerance) / 16);
 }
 
+/*
+ * Note in order to avoid the tty port mutex deadlock don't use the next method
+ * within the uart port callbacks. Primarily it's supposed to be utilized to
+ * handle a sudden reference clock rate change.
+ */
+void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned int baud, quot, frac = 0;
+	struct ktermios *termios;
+	unsigned long flags;
+
+	mutex_lock(&port->state->port.mutex);
+
+	if (port->uartclk == uartclk)
+		goto out_lock;
+
+	port->uartclk = uartclk;
+	termios = &port->state->port.tty->termios;
+
+	baud = serial8250_get_baud_rate(port, termios, NULL);
+	quot = serial8250_get_divisor(port, baud, &frac);
+
+	serial8250_rpm_get(up);
+	spin_lock_irqsave(&port->lock, flags);
+
+	uart_update_timeout(port, termios->c_cflag, baud);
+
+	serial8250_set_divisor(port, baud, quot, frac);
+	serial_port_out(port, UART_LCR, up->lcr);
+	serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+	serial8250_rpm_put(up);
+
+out_lock:
+	mutex_unlock(&port->state->port.mutex);
+}
+EXPORT_SYMBOL_GPL(serial8250_update_uartclk);
+
 void
 serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 			  struct ktermios *old)
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 6545f8cfc8fa..2b70f736b091 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -155,6 +155,8 @@ extern int early_serial_setup(struct uart_port *port);
 
 extern int early_serial8250_setup(struct earlycon_device *device,
 					 const char *options);
+extern void serial8250_update_uartclk(struct uart_port *port,
+				      unsigned int uartclk);
 extern void serial8250_do_set_termios(struct uart_port *port,
 		struct ktermios *termios, struct ktermios *old);
 extern void serial8250_do_set_ldisc(struct uart_port *port,
-- 
cgit v1.2.3


From efe9711214e6138a5a2a46ca4068bfce50c03444 Mon Sep 17 00:00:00 2001
From: Neal Liu <neal.liu@mediatek.com>
Date: Mon, 27 Jul 2020 11:25:46 +0800
Subject: cpuidle: change enter_s2idle() prototype

Control Flow Integrity(CFI) is a security mechanism that disallows
changes to the original control flow graph of a compiled binary,
making it significantly harder to perform such attacks.

init_state_node() assign same function callback to different
function pointer declarations.

static int init_state_node(struct cpuidle_state *idle_state,
                           const struct of_device_id *matches,
                           struct device_node *state_node) { ...
        idle_state->enter = match_id->data; ...
        idle_state->enter_s2idle = match_id->data; }

Function declarations:

struct cpuidle_state { ...
        int (*enter) (struct cpuidle_device *dev,
                      struct cpuidle_driver *drv,
                      int index);

        void (*enter_s2idle) (struct cpuidle_device *dev,
                              struct cpuidle_driver *drv,
                              int index); };

In this case, either enter() or enter_s2idle() would cause CFI check
failed since they use same callee.

Align function prototype of enter() since it needs return value for
some use cases. The return value of enter_s2idle() is no
need currently.

Signed-off-by: Neal Liu <neal.liu@mediatek.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/processor_idle.c   | 6 ++++--
 drivers/cpuidle/cpuidle-tegra.c | 8 +++++---
 drivers/idle/intel_idle.c       | 6 ++++--
 include/linux/cpuidle.h         | 9 ++++++---
 4 files changed, 19 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 75534c5b5433..6ffb6c99c2de 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -655,8 +655,8 @@ static int acpi_idle_enter(struct cpuidle_device *dev,
 	return index;
 }
 
-static void acpi_idle_enter_s2idle(struct cpuidle_device *dev,
-				   struct cpuidle_driver *drv, int index)
+static int acpi_idle_enter_s2idle(struct cpuidle_device *dev,
+				  struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
 
@@ -674,6 +674,8 @@ static void acpi_idle_enter_s2idle(struct cpuidle_device *dev,
 		}
 	}
 	acpi_idle_do_entry(cx);
+
+	return 0;
 }
 
 static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index 150045849d78..a12fb141875a 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -253,11 +253,13 @@ static int tegra_cpuidle_enter(struct cpuidle_device *dev,
 	return err ? -1 : index;
 }
 
-static void tegra114_enter_s2idle(struct cpuidle_device *dev,
-				  struct cpuidle_driver *drv,
-				  int index)
+static int tegra114_enter_s2idle(struct cpuidle_device *dev,
+				 struct cpuidle_driver *drv,
+				 int index)
 {
 	tegra_cpuidle_enter(dev, drv, index);
+
+	return 0;
 }
 
 /*
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index fa23a7ea01ac..3f86f36dab2b 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -173,13 +173,15 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
  * Invoked as a suspend-to-idle callback routine with frozen user space, frozen
  * scheduler tick and suspended scheduler clock on the target CPU.
  */
-static __cpuidle void intel_idle_s2idle(struct cpuidle_device *dev,
-					struct cpuidle_driver *drv, int index)
+static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
 {
 	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
+
+	return 0;
 }
 
 /*
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index ec2ef63771f0..b65909ae4e20 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -65,10 +65,13 @@ struct cpuidle_state {
 	 * CPUs execute ->enter_s2idle with the local tick or entire timekeeping
 	 * suspended, so it must not re-enable interrupts at any point (even
 	 * temporarily) or attempt to change states of clock event devices.
+	 *
+	 * This callback may point to the same function as ->enter if all of
+	 * the above requirements are met by it.
 	 */
-	void (*enter_s2idle) (struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv,
-			      int index);
+	int (*enter_s2idle)(struct cpuidle_device *dev,
+			    struct cpuidle_driver *drv,
+			    int index);
 };
 
 /* Idle State Flags */
-- 
cgit v1.2.3


From f227e3ec3b5cad859ad15666874405e8c1bbc1d4 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Fri, 10 Jul 2020 15:23:19 +0200
Subject: random32: update the net random state on interrupt and activity

This modifies the first 32 bits out of the 128 bits of a random CPU's
net_rand_state on interrupt or CPU activity to complicate remote
observations that could lead to guessing the network RNG's internal
state.

Note that depending on some network devices' interrupt rate moderation
or binding, this re-seeding might happen on every packet or even almost
never.

In addition, with NOHZ some CPUs might not even get timer interrupts,
leaving their local state rarely updated, while they are running
networked processes making use of the random state.  For this reason, we
also perform this update in update_process_times() in order to at least
update the state when there is user or system activity, since it's the
only case we care about.

Reported-by: Amit Klein <aksecurity@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/random.c  | 1 +
 include/linux/random.h | 3 +++
 kernel/time/timer.c    | 8 ++++++++
 lib/random32.c         | 2 +-
 4 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2a41b21623ae..d20ba1b104ca 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1277,6 +1277,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/include/linux/random.h b/include/linux/random.h
index 45e1f8fa742b..39aaa1f78f9d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/once.h>
+#include <linux/percpu.h>
 
 #include <uapi/linux/random.h>
 
@@ -119,6 +120,8 @@ struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
+DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index df1ff803acc4..026ac01af9da 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,6 +43,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/random.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -1742,6 +1743,13 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
+
+	/* The current CPU might make use of net randoms without receiving IRQs
+	 * to renew them often enough. Let's update the net_rand_state from a
+	 * non-constant value that's not affine to the number of calls to make
+	 * sure it's updated when there's some activity (we don't care in idle).
+	 */
+	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/lib/random32.c b/lib/random32.c
index 763b920a6206..c4d317be2997 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
-- 
cgit v1.2.3


From 2167c40657981f8a3d1ff1f04d4bda6b4a64f8e2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 28 Jul 2020 23:03:41 +0200
Subject: PCI: Remove unused pci_lost_interrupt()

388c8c16abaf ("PCI: add routines for debugging and handling lost
interrupts") added pci_lost_interrupt() that apparently never has had a
single user.  Remove it.

Link: https://lore.kernel.org/r/e328d059-3068-6a40-28df-f81f616d15a0@gmail.com
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/irq.c   | 50 --------------------------------------------------
 include/linux/pci.h |  7 -------
 2 files changed, 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index a1de501a2729..12ecd0aaa28d 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -6,61 +6,11 @@
  * Copyright (C) 2017 Christoph Hellwig.
  */
 
-#include <linux/acpi.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/pci.h>
 
-static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
-{
-	struct pci_dev *parent = to_pci_dev(pdev->dev.parent);
-
-	pci_err(pdev, "Potentially misrouted IRQ (Bridge %s %04x:%04x)\n",
-		dev_name(&parent->dev), parent->vendor, parent->device);
-	pci_err(pdev, "%s\n", reason);
-	pci_err(pdev, "Please report to linux-kernel@vger.kernel.org\n");
-	WARN_ON(1);
-}
-
-/**
- * pci_lost_interrupt - reports a lost PCI interrupt
- * @pdev:	device whose interrupt is lost
- *
- * The primary function of this routine is to report a lost interrupt
- * in a standard way which users can recognise (instead of blaming the
- * driver).
- *
- * Returns:
- * a suggestion for fixing it (although the driver is not required to
- * act on this).
- */
-enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *pdev)
-{
-	if (pdev->msi_enabled || pdev->msix_enabled) {
-		enum pci_lost_interrupt_reason ret;
-
-		if (pdev->msix_enabled) {
-			pci_note_irq_problem(pdev, "MSIX routing failure");
-			ret = PCI_LOST_IRQ_DISABLE_MSIX;
-		} else {
-			pci_note_irq_problem(pdev, "MSI routing failure");
-			ret = PCI_LOST_IRQ_DISABLE_MSI;
-		}
-		return ret;
-	}
-#ifdef CONFIG_ACPI
-	if (!(acpi_disabled || acpi_noirq)) {
-		pci_note_irq_problem(pdev, "Potential ACPI misrouting please reboot with acpi=noirq");
-		/* currently no way to fix acpi on the fly */
-		return PCI_LOST_IRQ_DISABLE_ACPI;
-	}
-#endif
-	pci_note_irq_problem(pdev, "unknown cause (not MSI or ACPI)");
-	return PCI_LOST_IRQ_NO_INFORMATION;
-}
-EXPORT_SYMBOL(pci_lost_interrupt);
-
 /**
  * pci_request_irq - allocate an interrupt line for a PCI device
  * @dev:	PCI device to operate on
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c79d83304e52..2dcd67f509a8 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1053,13 +1053,6 @@ void pci_sort_breadthfirst(void);
 
 /* Generic PCI functions exported to card drivers */
 
-enum pci_lost_interrupt_reason {
-	PCI_LOST_IRQ_NO_INFORMATION = 0,
-	PCI_LOST_IRQ_DISABLE_MSI,
-	PCI_LOST_IRQ_DISABLE_MSIX,
-	PCI_LOST_IRQ_DISABLE_ACPI,
-};
-enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *dev);
 int pci_find_capability(struct pci_dev *dev, int cap);
 int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
 int pci_find_ext_capability(struct pci_dev *dev, int cap);
-- 
cgit v1.2.3


From 6f24ff97e3231a5303841c5196a6f460f8485eb4 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Wed, 29 Jul 2020 13:31:43 -0500
Subject: power: supply: bq27xxx_battery: Add the BQ27Z561 Battery monitor

Add the Texas Instruments BQ27Z561 battery monitor.  The register address
map is laid out the same as compared to other devices within the file.
The battery status register has differing bits to determine if the
battery is full, discharging or dead.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 68 +++++++++++++++++++++++++++++-
 drivers/power/supply/bq27xxx_battery_i2c.c |  2 +
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 70 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index acaafed037be..a05b9a2d112d 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -43,6 +43,7 @@
  * https://www.ti.com/product/bq27411-g1
  * https://www.ti.com/product/bq27441-g1
  * https://www.ti.com/product/bq27621-g1
+ * https://www.ti.com/product/bq27z561
  */
 
 #include <linux/device.h>
@@ -79,6 +80,11 @@
 #define BQ27000_FLAG_FC		BIT(5)
 #define BQ27000_FLAG_CHGS	BIT(7) /* Charge state flag */
 
+/* BQ27Z561 has different layout for Flags register */
+#define BQ27Z561_FLAG_FDC	BIT(4) /* Battery fully discharged */
+#define BQ27Z561_FLAG_FC		BIT(5) /* Battery fully charged */
+#define BQ27Z561_FLAG_DIS_CH	BIT(6) /* Battery is discharging */
+
 /* control register params */
 #define BQ27XXX_SEALED			0x20
 #define BQ27XXX_SET_CFGUPDATE		0x13
@@ -431,12 +437,32 @@ static u8
 		[BQ27XXX_REG_DCAP] = 0x3c,
 		[BQ27XXX_REG_AP] = 0x18,
 		BQ27XXX_DM_REG_ROWS,
-	};
+	},
 #define bq27411_regs bq27421_regs
 #define bq27425_regs bq27421_regs
 #define bq27426_regs bq27421_regs
 #define bq27441_regs bq27421_regs
 #define bq27621_regs bq27421_regs
+	bq27z561_regs[BQ27XXX_REG_MAX] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x22,
+		BQ27XXX_DM_REG_ROWS,
+	};
 
 static enum power_supply_property bq27000_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
@@ -672,6 +698,25 @@ static enum power_supply_property bq27421_props[] = {
 #define bq27441_props bq27421_props
 #define bq27621_props bq27421_props
 
+static enum power_supply_property bq27z561_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 struct bq27xxx_dm_reg {
 	u8 subclass_id;
 	u8 offset;
@@ -767,11 +812,14 @@ static struct bq27xxx_dm_reg bq27621_dm_regs[] = {
 #define bq27621_dm_regs 0
 #endif
 
+#define bq27z561_dm_regs 0
+
 #define BQ27XXX_O_ZERO	0x00000001
 #define BQ27XXX_O_OTDC	0x00000002 /* has OTC/OTD overtemperature flags */
 #define BQ27XXX_O_UTOT  0x00000004 /* has OT overtemperature flag */
 #define BQ27XXX_O_CFGUP	0x00000008
 #define BQ27XXX_O_RAM	0x00000010
+#define BQ27Z561_O_BITS	0x00000020
 
 #define BQ27XXX_DATA(ref, key, opt) {		\
 	.opts = (opt),				\
@@ -816,6 +864,7 @@ static struct {
 	[BQ27426]   = BQ27XXX_DATA(bq27426,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27441]   = BQ27XXX_DATA(bq27441,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27621]   = BQ27XXX_DATA(bq27621,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
+	[BQ27Z561]  = BQ27XXX_DATA(bq27z561,  0         , BQ27Z561_O_BITS),
 };
 
 static DEFINE_MUTEX(bq27xxx_list_lock);
@@ -1551,6 +1600,8 @@ static bool bq27xxx_battery_dead(struct bq27xxx_device_info *di, u16 flags)
 {
 	if (di->opts & BQ27XXX_O_ZERO)
 		return flags & (BQ27000_FLAG_EDV1 | BQ27000_FLAG_EDVF);
+	else if (di->opts & BQ27Z561_O_BITS)
+		return flags & BQ27Z561_FLAG_FDC;
 	else
 		return flags & (BQ27XXX_FLAG_SOC1 | BQ27XXX_FLAG_SOCF);
 }
@@ -1595,6 +1646,7 @@ void bq27xxx_battery_update(struct bq27xxx_device_info *di)
 				cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP);
 			if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR)
 				cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF);
+
 			cache.charge_full = bq27xxx_battery_read_fcc(di);
 			cache.capacity = bq27xxx_battery_read_soc(di);
 			if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR)
@@ -1682,6 +1734,13 @@ static int bq27xxx_battery_status(struct bq27xxx_device_info *di,
 			status = POWER_SUPPLY_STATUS_NOT_CHARGING;
 		else
 			status = POWER_SUPPLY_STATUS_DISCHARGING;
+	} else if (di->opts & BQ27Z561_O_BITS) {
+		if (di->cache.flags & BQ27Z561_FLAG_FC)
+			status = POWER_SUPPLY_STATUS_FULL;
+		else if (di->cache.flags & BQ27Z561_FLAG_DIS_CH)
+			status = POWER_SUPPLY_STATUS_DISCHARGING;
+		else
+			status = POWER_SUPPLY_STATUS_CHARGING;
 	} else {
 		if (di->cache.flags & BQ27XXX_FLAG_FC)
 			status = POWER_SUPPLY_STATUS_FULL;
@@ -1710,6 +1769,13 @@ static int bq27xxx_battery_capacity_level(struct bq27xxx_device_info *di,
 			level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
 		else
 			level = POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
+	} else if (di->opts & BQ27Z561_O_BITS) {
+		if (di->cache.flags & BQ27Z561_FLAG_FC)
+			level = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
+		else if (di->cache.flags & BQ27Z561_FLAG_FDC)
+			level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
+		else
+			level = POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
 	} else {
 		if (di->cache.flags & BQ27XXX_FLAG_FC)
 			level = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 8e114a7abfc9..15f4e75786ab 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -253,6 +253,7 @@ static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
 	{ "bq27426", BQ27426 },
 	{ "bq27441", BQ27441 },
 	{ "bq27621", BQ27621 },
+	{ "bq27z561", BQ27Z561 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table);
@@ -286,6 +287,7 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = {
 	{ .compatible = "ti,bq27426" },
 	{ .compatible = "ti,bq27441" },
 	{ .compatible = "ti,bq27621" },
+	{ .compatible = "ti,bq27z561" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, bq27xxx_battery_i2c_of_match_table);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 507c5e214c42..1f6ea5d5063d 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -30,6 +30,7 @@ enum bq27xxx_chip {
 	BQ27426,
 	BQ27441,
 	BQ27621,
+	BQ27Z561,
 };
 
 struct bq27xxx_device_info;
-- 
cgit v1.2.3


From 707d678a5c7c5e80d1caac6c6b021171f5ecde58 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Wed, 29 Jul 2020 13:31:45 -0500
Subject: power: supply: bq27xxx_battery: Add the BQ28z610 Battery monitor

Add the Texas Instruments BQ28z610 battery monitor.
The register address map is laid out the same as compared to other
devices within the file.

The battery status register bits are similar to the bq27z561 but they
are different compared to other fuel gauge devices within this file.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 42 ++++++++++++++++++++++++++++++
 drivers/power/supply/bq27xxx_battery_i2c.c |  2 ++
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index a05b9a2d112d..a123f6e21f08 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -44,6 +44,7 @@
  * https://www.ti.com/product/bq27441-g1
  * https://www.ti.com/product/bq27621-g1
  * https://www.ti.com/product/bq27z561
+ * https://www.ti.com/product/bq28z610
  */
 
 #include <linux/device.h>
@@ -462,6 +463,26 @@ static u8
 		[BQ27XXX_REG_DCAP] = 0x3c,
 		[BQ27XXX_REG_AP] = 0x22,
 		BQ27XXX_DM_REG_ROWS,
+	},
+	bq28z610_regs[BQ27XXX_REG_MAX] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x22,
+		BQ27XXX_DM_REG_ROWS,
 	};
 
 static enum power_supply_property bq27000_props[] = {
@@ -717,6 +738,25 @@ static enum power_supply_property bq27z561_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
+static enum power_supply_property bq28z610_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 struct bq27xxx_dm_reg {
 	u8 subclass_id;
 	u8 offset;
@@ -813,6 +853,7 @@ static struct bq27xxx_dm_reg bq27621_dm_regs[] = {
 #endif
 
 #define bq27z561_dm_regs 0
+#define bq28z610_dm_regs 0
 
 #define BQ27XXX_O_ZERO	0x00000001
 #define BQ27XXX_O_OTDC	0x00000002 /* has OTC/OTD overtemperature flags */
@@ -865,6 +906,7 @@ static struct {
 	[BQ27441]   = BQ27XXX_DATA(bq27441,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27621]   = BQ27XXX_DATA(bq27621,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27Z561]  = BQ27XXX_DATA(bq27z561,  0         , BQ27Z561_O_BITS),
+	[BQ28Z610]  = BQ27XXX_DATA(bq28z610,  0         , BQ27Z561_O_BITS),
 };
 
 static DEFINE_MUTEX(bq27xxx_list_lock);
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 15f4e75786ab..ab02456d69e5 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -254,6 +254,7 @@ static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
 	{ "bq27441", BQ27441 },
 	{ "bq27621", BQ27621 },
 	{ "bq27z561", BQ27Z561 },
+	{ "bq28z610", BQ28Z610 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table);
@@ -288,6 +289,7 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = {
 	{ .compatible = "ti,bq27441" },
 	{ .compatible = "ti,bq27621" },
 	{ .compatible = "ti,bq27z561" },
+	{ .compatible = "ti,bq28z610" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, bq27xxx_battery_i2c_of_match_table);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 1f6ea5d5063d..987d9652aa4e 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -31,6 +31,7 @@ enum bq27xxx_chip {
 	BQ27441,
 	BQ27621,
 	BQ27Z561,
+	BQ28Z610,
 };
 
 struct bq27xxx_device_info;
-- 
cgit v1.2.3


From 83bdc7275e6206f560d247be856bceba3e1ed8f2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 29 Jul 2020 19:11:00 -0700
Subject: random32: remove net_rand_state from the latent entropy gcc plugin

It turns out that the plugin right now ends up being really unhappy
about the change from 'static' to 'extern' storage that happened in
commit f227e3ec3b5c ("random32: update the net random state on interrupt
and activity").

This is probably a trivial fix for the latent_entropy plugin, but for
now, just remove net_rand_state from the list of things the plugin
worries about.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/random.h | 2 +-
 lib/random32.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/random.h b/include/linux/random.h
index 39aaa1f78f9d..f310897f051d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -120,7 +120,7 @@ struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
-DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DECLARE_PER_CPU(struct rnd_state, net_rand_state);
 
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
diff --git a/lib/random32.c b/lib/random32.c
index c4d317be2997..3d749abb9e80 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
-- 
cgit v1.2.3


From 3ae1f39aef08c5c584b0d0ce2186273be3f14d16 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <sibis@codeaurora.org>
Date: Sat, 6 Jun 2020 03:03:30 +0530
Subject: OPP: Add and export helper to set bandwidth

Add and export 'dev_pm_opp_set_bw' to set the bandwidth
levels associated with an OPP.

Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 31 +++++++++++++++++++++++++++++++
 include/linux/pm_opp.h |  6 ++++++
 2 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index dfbd3d10410c..6937bf45f497 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -831,6 +831,37 @@ static int _set_required_opps(struct device *dev,
 	return ret;
 }
 
+/**
+ * dev_pm_opp_set_bw() - sets bandwidth levels corresponding to an opp
+ * @dev:	device for which we do this operation
+ * @opp:	opp based on which the bandwidth levels are to be configured
+ *
+ * This configures the bandwidth to the levels specified by the OPP. However
+ * if the OPP specified is NULL the bandwidth levels are cleared out.
+ *
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp)
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp table doesn't exist\n", __func__);
+		return PTR_ERR(opp_table);
+	}
+
+	if (opp)
+		ret = _set_opp_bw(opp_table, opp, dev, false);
+	else
+		ret = _set_opp_bw(opp_table, NULL, dev, true);
+
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_bw);
+
 /**
  * dev_pm_opp_set_rate() - Configure new OPP based on frequency
  * @dev:	 device for which we do this operation
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index d5c4a329321d..ae68417c0ae0 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -151,6 +151,7 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names
 void dev_pm_opp_detach_genpd(struct opp_table *opp_table);
 int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
+int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
 void dev_pm_opp_remove_table(struct device *dev);
@@ -342,6 +343,11 @@ static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_f
 	return -ENOTSUPP;
 }
 
+static inline int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask)
 {
 	return -ENOTSUPP;
-- 
cgit v1.2.3


From 292072c38768bb2321cf643b27cdf8fd8282d028 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 30 Jul 2020 08:59:40 +0530
Subject: cpufreq: cached_resolved_idx can not be negative

It is not possible for cached_resolved_idx to be invalid here as the
cpufreq core always sets index to a positive value.

Change its type to unsigned int and fix qcom usage a bit.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c         | 2 +-
 drivers/cpufreq/qcom-cpufreq-hw.c | 5 +----
 include/linux/cpufreq.h           | 2 +-
 3 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0128de3603df..053d72e52a31 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -538,7 +538,7 @@ unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
 	policy->cached_target_freq = target_freq;
 
 	if (cpufreq_driver->target_index) {
-		int idx;
+		unsigned int idx;
 
 		idx = cpufreq_frequency_table_target(policy, target_freq,
 						     CPUFREQ_RELATION_L);
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index fa68fa8ebd95..599818d38717 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -112,13 +112,10 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 						unsigned int target_freq)
 {
 	void __iomem *perf_state_reg = policy->driver_data;
-	int index;
+	unsigned int index;
 	unsigned long freq;
 
 	index = policy->cached_resolved_idx;
-	if (index < 0)
-		return 0;
-
 	writel_relaxed(index, perf_state_reg);
 
 	freq = policy->freq_table[index].frequency;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 3494f6763597..540c3ea4eb3c 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -127,7 +127,7 @@ struct cpufreq_policy {
 
 	 /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
 	unsigned int cached_target_freq;
-	int cached_resolved_idx;
+	unsigned int cached_resolved_idx;
 
 	/* Synchronization for frequency transitions */
 	bool			transition_ongoing; /* Tracks transition status */
-- 
cgit v1.2.3


From c8376994c86c4eb02b9a1032cd3a8d44c911d671 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 4 Jun 2020 10:23:14 +0200
Subject: initrd: remove support for multiple floppies

Remove the special handling for multiple floppies in the initrd code.
No one should be using floppies for booting these days. (famous last
words..)

Includes a spelling fix from Colin Ian King <colin.king@canonical.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/atags_parse.c |  2 --
 arch/sh/kernel/setup.c        |  2 --
 arch/sparc/kernel/setup_32.c  |  2 --
 arch/sparc/kernel/setup_64.c  |  2 --
 arch/x86/kernel/setup.c       |  2 --
 include/linux/initrd.h        |  6 ----
 init/do_mounts.c              | 69 +++++--------------------------------------
 init/do_mounts.h              |  1 -
 init/do_mounts_rd.c           | 20 ++++---------
 9 files changed, 12 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index ce02f92f4ab2..6c12d9fe694e 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -91,8 +91,6 @@ __tagtable(ATAG_VIDEOTEXT, parse_tag_videotext);
 static int __init parse_tag_ramdisk(const struct tag *tag)
 {
 	rd_image_start = tag->u.ramdisk.start;
-	rd_doload = (tag->u.ramdisk.flags & 1) == 0;
-	rd_prompt = (tag->u.ramdisk.flags & 2) == 0;
 
 	if (tag->u.ramdisk.size)
 		rd_size = tag->u.ramdisk.size;
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 67f5a3b44c2e..4144be650d41 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -290,8 +290,6 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
-	rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
-	rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
 #endif
 
 	if (!MOUNT_ROOT_RDONLY)
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 6d07b85b9e24..eea43a1aef1b 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -353,8 +353,6 @@ void __init setup_arch(char **cmdline_p)
 	ROOT_DEV = old_decode_dev(root_dev);
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
-	rd_prompt = ((ram_flags & RAMDISK_PROMPT_FLAG) != 0);
-	rd_doload = ((ram_flags & RAMDISK_LOAD_FLAG) != 0);	
 #endif
 
 	prom_setsync(prom_sync_me);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index f765fda871eb..d87244197d5c 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -659,8 +659,6 @@ void __init setup_arch(char **cmdline_p)
 	ROOT_DEV = old_decode_dev(root_dev);
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
-	rd_prompt = ((ram_flags & RAMDISK_PROMPT_FLAG) != 0);
-	rd_doload = ((ram_flags & RAMDISK_LOAD_FLAG) != 0);
 #endif
 
 	task_thread_info(&init_task)->kregs = &fake_swapper_regs;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a3767e74c758..b9a68d8e06d8 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -870,8 +870,6 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
-	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
-	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
 #endif
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
diff --git a/include/linux/initrd.h b/include/linux/initrd.h
index aa5914355728..8db6f8c8030b 100644
--- a/include/linux/initrd.h
+++ b/include/linux/initrd.h
@@ -2,12 +2,6 @@
 
 #define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
 
-/* 1 = load ramdisk, 0 = don't load */
-extern int rd_doload;
-
-/* 1 = prompt for ramdisk, 0 = don't prompt */
-extern int rd_prompt;
-
 /* starting block # of image */
 extern int rd_image_start;
 
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 1a4dfa17fb28..a7f22cf58c7e 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -28,8 +28,6 @@
 
 #include "do_mounts.h"
 
-int __initdata rd_doload;	/* 1 = load RAM disk, 0 = don't load */
-
 int root_mountflags = MS_RDONLY | MS_SILENT;
 static char * __initdata root_device_name;
 static char __initdata saved_root_name[64];
@@ -39,7 +37,7 @@ dev_t ROOT_DEV;
 
 static int __init load_ramdisk(char *str)
 {
-	rd_doload = simple_strtol(str,NULL,0) & 3;
+	pr_warn("ignoring the deprecated load_ramdisk= option\n");
 	return 1;
 }
 __setup("load_ramdisk=", load_ramdisk);
@@ -553,66 +551,20 @@ static int __init mount_cifs_root(void)
 }
 #endif
 
-#if defined(CONFIG_BLK_DEV_RAM) || defined(CONFIG_BLK_DEV_FD)
-void __init change_floppy(char *fmt, ...)
-{
-	struct termios termios;
-	char buf[80];
-	char c;
-	int fd;
-	va_list args;
-	va_start(args, fmt);
-	vsprintf(buf, fmt, args);
-	va_end(args);
-	fd = ksys_open("/dev/root", O_RDWR | O_NDELAY, 0);
-	if (fd >= 0) {
-		ksys_ioctl(fd, FDEJECT, 0);
-		ksys_close(fd);
-	}
-	printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf);
-	fd = ksys_open("/dev/console", O_RDWR, 0);
-	if (fd >= 0) {
-		ksys_ioctl(fd, TCGETS, (long)&termios);
-		termios.c_lflag &= ~ICANON;
-		ksys_ioctl(fd, TCSETSF, (long)&termios);
-		ksys_read(fd, &c, 1);
-		termios.c_lflag |= ICANON;
-		ksys_ioctl(fd, TCSETSF, (long)&termios);
-		ksys_close(fd);
-	}
-}
-#endif
-
 void __init mount_root(void)
 {
 #ifdef CONFIG_ROOT_NFS
 	if (ROOT_DEV == Root_NFS) {
-		if (mount_nfs_root())
-			return;
-
-		printk(KERN_ERR "VFS: Unable to mount root fs via NFS, trying floppy.\n");
-		ROOT_DEV = Root_FD0;
+		if (!mount_nfs_root())
+			printk(KERN_ERR "VFS: Unable to mount root fs via NFS.\n");
+		return;
 	}
 #endif
 #ifdef CONFIG_CIFS_ROOT
 	if (ROOT_DEV == Root_CIFS) {
-		if (mount_cifs_root())
-			return;
-
-		printk(KERN_ERR "VFS: Unable to mount root fs via SMB, trying floppy.\n");
-		ROOT_DEV = Root_FD0;
-	}
-#endif
-#ifdef CONFIG_BLK_DEV_FD
-	if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
-		/* rd_doload is 2 for a dual initrd/ramload setup */
-		if (rd_doload==2) {
-			if (rd_load_disk(1)) {
-				ROOT_DEV = Root_RAM1;
-				root_device_name = NULL;
-			}
-		} else
-			change_floppy("root floppy");
+		if (!mount_cifs_root())
+			printk(KERN_ERR "VFS: Unable to mount root fs via SMB.\n");
+		return;
 	}
 #endif
 #ifdef CONFIG_BLOCK
@@ -631,8 +583,6 @@ void __init mount_root(void)
  */
 void __init prepare_namespace(void)
 {
-	int is_floppy;
-
 	if (root_delay) {
 		printk(KERN_INFO "Waiting %d sec before mounting root device...\n",
 		       root_delay);
@@ -675,11 +625,6 @@ void __init prepare_namespace(void)
 		async_synchronize_full();
 	}
 
-	is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
-
-	if (is_floppy && rd_doload && rd_load_disk(0))
-		ROOT_DEV = Root_RAM0;
-
 	mount_root();
 out:
 	devtmpfs_mount();
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 50d6c8941e15..c855b3f0e06d 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -9,7 +9,6 @@
 #include <linux/major.h>
 #include <linux/root_dev.h>
 
-void  change_floppy(char *fmt, ...);
 void  mount_block_root(char *name, int flags);
 void  mount_root(void);
 extern int root_mountflags;
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 32fb049d18f9..0a5c3ebee61d 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -15,11 +15,9 @@
 #include <linux/decompress/generic.h>
 
 
-int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */
-
 static int __init prompt_ramdisk(char *str)
 {
-	rd_prompt = simple_strtol(str,NULL,0) & 1;
+	pr_warn("ignoring the deprecated prompt_ramdisk= option\n");
 	return 1;
 }
 __setup("prompt_ramdisk=", prompt_ramdisk);
@@ -178,7 +176,7 @@ int __init rd_load_image(char *from)
 	int res = 0;
 	int in_fd, out_fd;
 	unsigned long rd_blocks, devblocks;
-	int nblocks, i, disk;
+	int nblocks, i;
 	char *buf = NULL;
 	unsigned short rotate = 0;
 	decompress_fn decompressor = NULL;
@@ -243,21 +241,15 @@ int __init rd_load_image(char *from)
 
 	printk(KERN_NOTICE "RAMDISK: Loading %dKiB [%ld disk%s] into ram disk... ",
 		nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
-	for (i = 0, disk = 1; i < nblocks; i++) {
+	for (i = 0; i < nblocks; i++) {
 		if (i && (i % devblocks == 0)) {
-			pr_cont("done disk #%d.\n", disk++);
+			pr_cont("done disk #1.\n");
 			rotate = 0;
 			if (ksys_close(in_fd)) {
 				printk("Error closing the disk.\n");
 				goto noclose_input;
 			}
-			change_floppy("disk #%d", disk);
-			in_fd = ksys_open(from, O_RDONLY, 0);
-			if (in_fd < 0)  {
-				printk("Error opening disk.\n");
-				goto noclose_input;
-			}
-			printk("Loading disk #%d... ", disk);
+			break;
 		}
 		ksys_read(in_fd, buf, BLOCK_SIZE);
 		ksys_write(out_fd, buf, BLOCK_SIZE);
@@ -284,8 +276,6 @@ out:
 
 int __init rd_load_disk(int n)
 {
-	if (rd_prompt)
-		change_floppy("root floppy disk to be loaded into RAM disk");
 	create_dev("/dev/root", ROOT_DEV);
 	create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, n));
 	return rd_load_image("/dev/root");
-- 
cgit v1.2.3


From bef173299613404f55b11180d9a865861637f31d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 6 Jun 2020 14:49:58 +0200
Subject: initrd: switch initrd loading to struct file based APIs

There is no good reason to mess with file descriptors from in-kernel
code, switch the initrd loading to struct file based read and writes
instead.

Also Pass an explicit offset instead of ->f_pos, and to make that easier,
use file scope file structs and offsets everywhere except for
identify_ramdisk_image instead of the current strange mix.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/read_write.c          |  2 +-
 include/linux/syscalls.h |  1 -
 init/do_mounts_rd.c      | 79 ++++++++++++++++++++++++------------------------
 3 files changed, 40 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index 4fb797822567..5db58b8c78d0 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -301,7 +301,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
 }
 EXPORT_SYMBOL(vfs_llseek);
 
-off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence)
+static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence)
 {
 	off_t retval;
 	struct fd f = fdget_pos(fd);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b951a87da987..10843a6adb77 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1246,7 +1246,6 @@ int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
 		    unsigned int count);
 int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
-off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
 void ksys_sync(void);
 int ksys_unshare(unsigned long unshare_flags);
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 0a5c3ebee61d..d4255c10432a 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -14,6 +14,8 @@
 
 #include <linux/decompress/generic.h>
 
+static struct file *in_file, *out_file;
+static loff_t in_pos, out_pos;
 
 static int __init prompt_ramdisk(char *str)
 {
@@ -31,7 +33,7 @@ static int __init ramdisk_start_setup(char *str)
 }
 __setup("ramdisk_start=", ramdisk_start_setup);
 
-static int __init crd_load(int in_fd, int out_fd, decompress_fn deco);
+static int __init crd_load(decompress_fn deco);
 
 /*
  * This routine tries to find a RAM disk image to load, and returns the
@@ -53,7 +55,8 @@ static int __init crd_load(int in_fd, int out_fd, decompress_fn deco);
  *	lz4
  */
 static int __init
-identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
+identify_ramdisk_image(struct file *file, loff_t pos,
+		decompress_fn *decompressor)
 {
 	const int size = 512;
 	struct minix_super_block *minixsb;
@@ -64,6 +67,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	unsigned char *buf;
 	const char *compress_name;
 	unsigned long n;
+	int start_block = rd_image_start;
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
@@ -78,8 +82,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	/*
 	 * Read block 0 to test for compressed kernel
 	 */
-	ksys_lseek(fd, start_block * BLOCK_SIZE, 0);
-	ksys_read(fd, buf, size);
+	pos = start_block * BLOCK_SIZE;
+	kernel_read(file, buf, size, &pos);
 
 	*decompressor = decompress_method(buf, size, &compress_name);
 	if (compress_name) {
@@ -124,8 +128,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	/*
 	 * Read 512 bytes further to check if cramfs is padded
 	 */
-	ksys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0);
-	ksys_read(fd, buf, size);
+	pos = start_block * BLOCK_SIZE + 0x200;
+	kernel_read(file, buf, size, &pos);
 
 	if (cramfsb->magic == CRAMFS_MAGIC) {
 		printk(KERN_NOTICE
@@ -138,8 +142,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	/*
 	 * Read block 1 to test for minix and ext2 superblock
 	 */
-	ksys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0);
-	ksys_read(fd, buf, size);
+	pos = (start_block + 1) * BLOCK_SIZE;
+	kernel_read(file, buf, size, &pos);
 
 	/* Try minix */
 	if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
@@ -166,15 +170,22 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	       start_block);
 
 done:
-	ksys_lseek(fd, start_block * BLOCK_SIZE, 0);
 	kfree(buf);
 	return nblocks;
 }
 
+static unsigned long nr_blocks(struct file *file)
+{
+	struct inode *inode = file->f_mapping->host;
+
+	if (!S_ISBLK(inode->i_mode))
+		return 0;
+	return i_size_read(inode) >> 10;
+}
+
 int __init rd_load_image(char *from)
 {
 	int res = 0;
-	int in_fd, out_fd;
 	unsigned long rd_blocks, devblocks;
 	int nblocks, i;
 	char *buf = NULL;
@@ -184,20 +195,21 @@ int __init rd_load_image(char *from)
 	char rotator[4] = { '|' , '/' , '-' , '\\' };
 #endif
 
-	out_fd = ksys_open("/dev/ram", O_RDWR, 0);
-	if (out_fd < 0)
+	out_file = filp_open("/dev/ram", O_RDWR, 0);
+	if (IS_ERR(out_file))
 		goto out;
 
-	in_fd = ksys_open(from, O_RDONLY, 0);
-	if (in_fd < 0)
+	in_file = filp_open(from, O_RDONLY, 0);
+	if (IS_ERR(in_file))
 		goto noclose_input;
 
-	nblocks = identify_ramdisk_image(in_fd, rd_image_start, &decompressor);
+	in_pos = rd_image_start * BLOCK_SIZE;
+	nblocks = identify_ramdisk_image(in_file, in_pos, &decompressor);
 	if (nblocks < 0)
 		goto done;
 
 	if (nblocks == 0) {
-		if (crd_load(in_fd, out_fd, decompressor) == 0)
+		if (crd_load(decompressor) == 0)
 			goto successful_load;
 		goto done;
 	}
@@ -206,11 +218,7 @@ int __init rd_load_image(char *from)
 	 * NOTE NOTE: nblocks is not actually blocks but
 	 * the number of kibibytes of data to load into a ramdisk.
 	 */
-	if (ksys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0)
-		rd_blocks = 0;
-	else
-		rd_blocks >>= 1;
-
+	rd_blocks = nr_blocks(out_file);
 	if (nblocks > rd_blocks) {
 		printk("RAMDISK: image too big! (%dKiB/%ldKiB)\n",
 		       nblocks, rd_blocks);
@@ -220,13 +228,10 @@ int __init rd_load_image(char *from)
 	/*
 	 * OK, time to copy in the data
 	 */
-	if (ksys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0)
-		devblocks = 0;
-	else
-		devblocks >>= 1;
-
 	if (strcmp(from, "/initrd.image") == 0)
 		devblocks = nblocks;
+	else
+		devblocks = nr_blocks(in_file);
 
 	if (devblocks == 0) {
 		printk(KERN_ERR "RAMDISK: could not determine device size\n");
@@ -245,14 +250,11 @@ int __init rd_load_image(char *from)
 		if (i && (i % devblocks == 0)) {
 			pr_cont("done disk #1.\n");
 			rotate = 0;
-			if (ksys_close(in_fd)) {
-				printk("Error closing the disk.\n");
-				goto noclose_input;
-			}
+			fput(in_file);
 			break;
 		}
-		ksys_read(in_fd, buf, BLOCK_SIZE);
-		ksys_write(out_fd, buf, BLOCK_SIZE);
+		kernel_read(in_file, buf, BLOCK_SIZE, &in_pos);
+		kernel_write(out_file, buf, BLOCK_SIZE, &out_pos);
 #if !defined(CONFIG_S390)
 		if (!(i % 16)) {
 			pr_cont("%c\b", rotator[rotate & 0x3]);
@@ -265,9 +267,9 @@ int __init rd_load_image(char *from)
 successful_load:
 	res = 1;
 done:
-	ksys_close(in_fd);
+	fput(in_file);
 noclose_input:
-	ksys_close(out_fd);
+	fput(out_file);
 out:
 	kfree(buf);
 	ksys_unlink("/dev/ram");
@@ -283,11 +285,10 @@ int __init rd_load_disk(int n)
 
 static int exit_code;
 static int decompress_error;
-static int crd_infd, crd_outfd;
 
 static long __init compr_fill(void *buf, unsigned long len)
 {
-	long r = ksys_read(crd_infd, buf, len);
+	long r = kernel_read(in_file, buf, len, &in_pos);
 	if (r < 0)
 		printk(KERN_ERR "RAMDISK: error while reading compressed data");
 	else if (r == 0)
@@ -297,7 +298,7 @@ static long __init compr_fill(void *buf, unsigned long len)
 
 static long __init compr_flush(void *window, unsigned long outcnt)
 {
-	long written = ksys_write(crd_outfd, window, outcnt);
+	long written = kernel_write(out_file, window, outcnt, &out_pos);
 	if (written != outcnt) {
 		if (decompress_error == 0)
 			printk(KERN_ERR
@@ -316,11 +317,9 @@ static void __init error(char *x)
 	decompress_error = 1;
 }
 
-static int __init crd_load(int in_fd, int out_fd, decompress_fn deco)
+static int __init crd_load(decompress_fn deco)
 {
 	int result;
-	crd_infd = in_fd;
-	crd_outfd = out_fd;
 
 	if (!deco) {
 		pr_emerg("Invalid ramdisk decompression routine.  "
-- 
cgit v1.2.3


From a787e5400a1ceeb0ef92d71ec43aeb35b1fa1334 Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <a.hajda@samsung.com>
Date: Mon, 13 Jul 2020 16:43:21 +0200
Subject: driver core: add device probe log helper

During probe every time driver gets resource it should usually check for
error printk some message if it is not -EPROBE_DEFER and return the error.
This pattern is simple but requires adding few lines after any resource
acquisition code, as a result it is often omitted or implemented only
partially.
dev_err_probe helps to replace such code sequences with simple call,
so code:
	if (err != -EPROBE_DEFER)
		dev_err(dev, ...);
	return err;
becomes:
	return dev_err_probe(dev, err, ...);

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200713144324.23654-2-a.hajda@samsung.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/device.h |  3 +++
 2 files changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 4d05868d9356..1606488ed741 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4203,6 +4203,48 @@ define_dev_printk_level(_dev_info, KERN_INFO);
 
 #endif
 
+/**
+ * dev_err_probe - probe error check and log helper
+ * @dev: the pointer to the struct device
+ * @err: error value to test
+ * @fmt: printf-style format string
+ * @...: arguments as specified in the format string
+ *
+ * This helper implements common pattern present in probe functions for error
+ * checking: print debug or error message depending if the error value is
+ * -EPROBE_DEFER and propagate error upwards.
+ * It replaces code sequence:
+ * 	if (err != -EPROBE_DEFER)
+ * 		dev_err(dev, ...);
+ * 	else
+ * 		dev_dbg(dev, ...);
+ * 	return err;
+ * with
+ * 	return dev_err_probe(dev, err, ...);
+ *
+ * Returns @err.
+ *
+ */
+int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (err != -EPROBE_DEFER)
+		dev_err(dev, "error %d: %pV", err, &vaf);
+	else
+		dev_dbg(dev, "error %d: %pV", err, &vaf);
+
+	va_end(args);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_err_probe);
+
 static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
 {
 	return fwnode && !IS_ERR(fwnode->secondary);
diff --git a/include/linux/device.h b/include/linux/device.h
index a120657d7587..065c24008f8b 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -962,6 +962,9 @@ void device_link_remove(void *consumer, struct device *supplier);
 void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 
+extern __printf(3, 4)
+int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
 	MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor))
-- 
cgit v1.2.3


From 4dc3bab8687f1ea11322611de6d4138b43eccdcd Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Thu, 2 Jul 2020 20:41:28 +0900
Subject: PM / devfreq: Add support delayed timer for polling mode

Until now, the devfreq driver using polling mode like simple_ondemand
governor have used only deferrable timer for reducing the redundant
power consumption. It reduces the CPU wake-up from idle due to polling mode
which check the status of Non-CPU device.

But, it has a problem for Non-CPU device like DMC device with DMA operation.
Some Non-CPU device need to do monitor continuously regardless of CPU state
in order to decide the proper next status of Non-CPU device.

So, add support the delayed timer for polling mode to support
the repetitive monitoring. The devfreq driver and user can select
the kind of timer on either deferrable and delayed timer.

For example, change the timer type of DMC device
based on Exynos5422-based Odroid-XU3 as following:

- If want to use deferrable timer as following:
echo deferrable > /sys/class/devfreq/10c20000.memory-controller/timer

- If want to use delayed timer as following:
echo delayed > /sys/class/devfreq/10c20000.memory-controller/timer

Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 Documentation/ABI/testing/sysfs-class-devfreq | 12 ++++
 drivers/devfreq/devfreq.c                     | 86 ++++++++++++++++++++++++++-
 include/linux/devfreq.h                       |  9 +++
 3 files changed, 106 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 9758eb85ade3..deefffb3bbe4 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -108,3 +108,15 @@ Description:
 		frequency requested by governors and min_freq.
 		The max_freq overrides min_freq because max_freq may be
 		used to throttle devices to avoid overheating.
+
+What:		/sys/class/devfreq/.../timer
+Date:		July 2020
+Contact:	Chanwoo Choi <cw00.choi@samsung.com>
+Description:
+		This ABI shows and stores the kind of work timer by users.
+		This work timer is used by devfreq workqueue in order to
+		monitor the device status such as utilization. The user
+		can change the work timer on runtime according to their demand
+		as following:
+			echo deferrable > /sys/class/devfreq/.../timer
+			echo delayed > /sys/class/devfreq/.../timer
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 52b9c3e141f3..5320c3b37f35 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -49,6 +49,11 @@ static LIST_HEAD(devfreq_governor_list);
 static LIST_HEAD(devfreq_list);
 static DEFINE_MUTEX(devfreq_list_lock);
 
+static const char timer_name[][DEVFREQ_NAME_LEN] = {
+	[DEVFREQ_TIMER_DEFERRABLE] = { "deferrable" },
+	[DEVFREQ_TIMER_DELAYED] = { "delayed" },
+};
+
 /**
  * find_device_devfreq() - find devfreq struct using device pointer
  * @dev:	device pointer used to lookup device devfreq.
@@ -454,7 +459,17 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 	if (devfreq->governor->interrupt_driven)
 		return;
 
-	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+	switch (devfreq->profile->timer) {
+	case DEVFREQ_TIMER_DEFERRABLE:
+		INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+		break;
+	case DEVFREQ_TIMER_DELAYED:
+		INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
+		break;
+	default:
+		return;
+	}
+
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
@@ -771,6 +786,11 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
+	if (devfreq->profile->timer < 0
+		|| devfreq->profile->timer >= DEVFREQ_TIMER_NUM) {
+		goto err_out;
+	}
+
 	if (!devfreq->profile->max_state && !devfreq->profile->freq_table) {
 		mutex_unlock(&devfreq->lock);
 		err = set_freq_table(devfreq);
@@ -1625,6 +1645,69 @@ static ssize_t trans_stat_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(trans_stat);
 
+static ssize_t timer_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct devfreq *df = to_devfreq(dev);
+
+	if (!df->profile)
+		return -EINVAL;
+
+	return sprintf(buf, "%s\n", timer_name[df->profile->timer]);
+}
+
+static ssize_t timer_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct devfreq *df = to_devfreq(dev);
+	char str_timer[DEVFREQ_NAME_LEN + 1];
+	int timer = -1;
+	int ret = 0, i;
+
+	if (!df->governor || !df->profile)
+		return -EINVAL;
+
+	ret = sscanf(buf, "%16s", str_timer);
+	if (ret != 1)
+		return -EINVAL;
+
+	for (i = 0; i < DEVFREQ_TIMER_NUM; i++) {
+		if (!strncmp(timer_name[i], str_timer, DEVFREQ_NAME_LEN)) {
+			timer = i;
+			break;
+		}
+	}
+
+	if (timer < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (df->profile->timer == timer) {
+		ret = 0;
+		goto out;
+	}
+
+	mutex_lock(&df->lock);
+	df->profile->timer = timer;
+	mutex_unlock(&df->lock);
+
+	ret = df->governor->event_handler(df, DEVFREQ_GOV_STOP, NULL);
+	if (ret) {
+		dev_warn(dev, "%s: Governor %s not stopped(%d)\n",
+			 __func__, df->governor->name, ret);
+		goto out;
+	}
+
+	ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
+	if (ret)
+		dev_warn(dev, "%s: Governor %s not started(%d)\n",
+			 __func__, df->governor->name, ret);
+out:
+	return ret ? ret : count;
+}
+static DEVICE_ATTR_RW(timer);
+
 static struct attribute *devfreq_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_governor.attr,
@@ -1636,6 +1719,7 @@ static struct attribute *devfreq_attrs[] = {
 	&dev_attr_min_freq.attr,
 	&dev_attr_max_freq.attr,
 	&dev_attr_trans_stat.attr,
+	&dev_attr_timer.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(devfreq);
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 57e871a559a9..12782fbb4c25 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -31,6 +31,13 @@
 #define	DEVFREQ_PRECHANGE		(0)
 #define DEVFREQ_POSTCHANGE		(1)
 
+/* DEVFREQ work timers */
+enum devfreq_timer {
+	DEVFREQ_TIMER_DEFERRABLE = 0,
+	DEVFREQ_TIMER_DELAYED,
+	DEVFREQ_TIMER_NUM,
+};
+
 struct devfreq;
 struct devfreq_governor;
 
@@ -70,6 +77,7 @@ struct devfreq_dev_status {
  * @initial_freq:	The operating frequency when devfreq_add_device() is
  *			called.
  * @polling_ms:		The polling interval in ms. 0 disables polling.
+ * @timer:		Timer type is either deferrable or delayed timer.
  * @target:		The device should set its operating frequency at
  *			freq or lowest-upper-than-freq value. If freq is
  *			higher than any operable frequency, set maximum.
@@ -96,6 +104,7 @@ struct devfreq_dev_status {
 struct devfreq_dev_profile {
 	unsigned long initial_freq;
 	unsigned int polling_ms;
+	enum devfreq_timer timer;
 
 	int (*target)(struct device *dev, unsigned long *freq, u32 flags);
 	int (*get_dev_status)(struct device *dev,
-- 
cgit v1.2.3


From 1c9df907da83812e4f33b59d3d142c864d9da57f Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Thu, 30 Jul 2020 07:59:24 +0200
Subject: random: fix circular include dependency on arm64 after addition of
 percpu.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Daniel Díaz and Kees Cook independently reported that commit
f227e3ec3b5c ("random32: update the net random state on interrupt and
activity") broke arm64 due to a circular dependency on include files
since the addition of percpu.h in random.h.

The correct fix would definitely be to move all the prandom32 stuff out
of random.h but for backporting, a smaller solution is preferred.

This one replaces linux/percpu.h with asm/percpu.h, and this fixes the
problem on x86_64, arm64, arm, and mips.  Note that moving percpu.h
around didn't change anything and that removing it entirely broke
differently.  When backporting, such options might still be considered
if this patch fails to help.

[ It turns out that an alternate fix seems to be to just remove the
  troublesome <asm/pointer_auth.h> remove from the arm64 <asm/smp.h>
  that causes the circular dependency.

  But we might as well do the whole belt-and-suspenders thing, and
  minimize inclusion in <linux/random.h> too. Either will fix the
  problem, and both are good changes.   - Linus ]

Reported-by: Daniel Díaz <daniel.diaz@linaro.org>
Reported-by: Kees Cook <keescook@chromium.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Fixes: f227e3ec3b5c
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/random.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/random.h b/include/linux/random.h
index f310897f051d..9ab7443bd91b 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -11,7 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/once.h>
-#include <linux/percpu.h>
+#include <asm/percpu.h>
 
 #include <uapi/linux/random.h>
 
-- 
cgit v1.2.3


From 0de967f24e6c26fca3845e5a5970866ae59ac766 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Thu, 30 Jul 2020 17:51:17 +0100
Subject: thermal: Update power allocator and devfreq cooling to SPDX licensing

Update the license to the SPDX licensing format.

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200730165117.13998-1-lukasz.luba@arm.com
---
 drivers/thermal/devfreq_cooling.c     | 10 +---------
 drivers/thermal/gov_power_allocator.c |  9 +--------
 include/linux/devfreq_cooling.h       |  9 +--------
 3 files changed, 3 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index f7f32e98331b..a12d29096229 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -1,18 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * devfreq_cooling: Thermal cooling device implementation for devices using
  *                  devfreq
  *
  * Copyright (C) 2014-2015 ARM Limited
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * TODO:
  *    - If OPPs are added or removed after devfreq cooling has
  *      registered, the devfreq cooling won't react to it.
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 44636475b2a3..5cb518d8f156 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -1,16 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * A power allocator to manage temperature
  *
  * Copyright (C) 2014 ARM Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
  */
 
 #define pr_fmt(fmt) "Power allocator: " fmt
diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h
index 79a6e37a1d6f..9df2dfca68dd 100644
--- a/include/linux/devfreq_cooling.h
+++ b/include/linux/devfreq_cooling.h
@@ -1,17 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * devfreq_cooling: Thermal cooling device implementation for devices using
  *                  devfreq
  *
  * Copyright (C) 2014-2015 ARM Limited
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __DEVFREQ_COOLING_H__
-- 
cgit v1.2.3


From b13fecb1c3a603c4b8e99b306fecf4f668c11b32 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 13 Jul 2020 15:01:26 -0700
Subject: treewide: Replace DECLARE_TASKLET() with DECLARE_TASKLET_OLD()

This converts all the existing DECLARE_TASKLET() (and ...DISABLED)
macros with DECLARE_TASKLET_OLD() in preparation for refactoring the
tasklet callback type. All existing DECLARE_TASKLET() users had a "0"
data argument, it has been removed here as well.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 drivers/input/keyboard/omap-keypad.c   |  2 +-
 drivers/input/serio/hil_mlc.c          |  2 +-
 drivers/net/wan/farsync.c              |  4 ++--
 drivers/s390/crypto/ap_bus.c           |  2 +-
 drivers/staging/most/dim2/dim2.c       |  2 +-
 drivers/staging/octeon/ethernet-tx.c   |  2 +-
 drivers/tty/vt/keyboard.c              |  2 +-
 drivers/usb/gadget/udc/snps_udc_core.c |  2 +-
 drivers/usb/host/fhci-sched.c          |  2 +-
 include/linux/interrupt.h              | 15 ++++++++++-----
 kernel/backtracetest.c                 |  2 +-
 kernel/debug/debug_core.c              |  2 +-
 kernel/irq/resend.c                    |  2 +-
 net/atm/pppoatm.c                      |  2 +-
 net/iucv/iucv.c                        |  2 +-
 sound/drivers/pcsp/pcsp_lib.c          |  2 +-
 16 files changed, 26 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 5fe7a5633e33..dbe836c7ff47 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -46,7 +46,7 @@ struct omap_kp {
 	unsigned short keymap[];
 };
 
-static DECLARE_TASKLET_DISABLED(kp_tasklet, omap_kp_tasklet, 0);
+static DECLARE_TASKLET_DISABLED_OLD(kp_tasklet, omap_kp_tasklet);
 
 static unsigned int *row_gpios;
 static unsigned int *col_gpios;
diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c
index e1423f7648d6..65f4e9d62a67 100644
--- a/drivers/input/serio/hil_mlc.c
+++ b/drivers/input/serio/hil_mlc.c
@@ -77,7 +77,7 @@ static struct timer_list	hil_mlcs_kicker;
 static int			hil_mlcs_probe;
 
 static void hil_mlcs_process(unsigned long unused);
-static DECLARE_TASKLET_DISABLED(hil_mlcs_tasklet, hil_mlcs_process, 0);
+static DECLARE_TASKLET_DISABLED_OLD(hil_mlcs_tasklet, hil_mlcs_process);
 
 
 /* #define HIL_MLC_DEBUG */
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 7916efce7188..f5198a391417 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -569,8 +569,8 @@ static void do_bottom_half_rx(struct fst_card_info *card);
 static void fst_process_tx_work_q(unsigned long work_q);
 static void fst_process_int_work_q(unsigned long work_q);
 
-static DECLARE_TASKLET(fst_tx_task, fst_process_tx_work_q, 0);
-static DECLARE_TASKLET(fst_int_task, fst_process_int_work_q, 0);
+static DECLARE_TASKLET_OLD(fst_tx_task, fst_process_tx_work_q);
+static DECLARE_TASKLET_OLD(fst_int_task, fst_process_int_work_q);
 
 static struct fst_card_info *fst_card_array[FST_MAX_CARDS];
 static spinlock_t fst_work_q_lock;
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index e71ca4a719a5..2589ccd257e3 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -93,7 +93,7 @@ static DECLARE_WORK(ap_scan_work, ap_scan_bus);
  * Tasklet & timer for AP request polling and interrupts
  */
 static void ap_tasklet_fn(unsigned long);
-static DECLARE_TASKLET(ap_tasklet, ap_tasklet_fn, 0);
+static DECLARE_TASKLET_OLD(ap_tasklet, ap_tasklet_fn);
 static DECLARE_WAIT_QUEUE_HEAD(ap_poll_wait);
 static struct task_struct *ap_poll_kthread;
 static DEFINE_MUTEX(ap_poll_thread_mutex);
diff --git a/drivers/staging/most/dim2/dim2.c b/drivers/staging/most/dim2/dim2.c
index 8e0f27e61652..509c8012d20b 100644
--- a/drivers/staging/most/dim2/dim2.c
+++ b/drivers/staging/most/dim2/dim2.c
@@ -46,7 +46,7 @@ MODULE_PARM_DESC(fcnt, "Num of frames per sub-buffer for sync channels as a powe
 static DEFINE_SPINLOCK(dim_lock);
 
 static void dim2_tasklet_fn(unsigned long data);
-static DECLARE_TASKLET(dim2_tasklet, dim2_tasklet_fn, 0);
+static DECLARE_TASKLET_OLD(dim2_tasklet, dim2_tasklet_fn);
 
 /**
  * struct hdm_channel - private structure to keep channel specific data
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index ab7dd8216006..9c71ad5af7b9 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -41,7 +41,7 @@
 #endif
 
 static void cvm_oct_tx_do_cleanup(unsigned long arg);
-static DECLARE_TASKLET(cvm_oct_tx_cleanup_tasklet, cvm_oct_tx_do_cleanup, 0);
+static DECLARE_TASKLET_OLD(cvm_oct_tx_cleanup_tasklet, cvm_oct_tx_do_cleanup);
 
 /* Maximum number of SKBs to try to free per xmit packet. */
 #define MAX_SKB_TO_FREE (MAX_OUT_QUEUE_DEPTH * 2)
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 568b2171f335..f80199984ee0 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -1236,7 +1236,7 @@ static void kbd_bh(unsigned long dummy)
 	}
 }
 
-DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh, 0);
+DECLARE_TASKLET_DISABLED_OLD(keyboard_tasklet, kbd_bh);
 
 #if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_ALPHA) ||\
     defined(CONFIG_MIPS) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) ||\
diff --git a/drivers/usb/gadget/udc/snps_udc_core.c b/drivers/usb/gadget/udc/snps_udc_core.c
index afdd28f332ce..e76f1a50b0fc 100644
--- a/drivers/usb/gadget/udc/snps_udc_core.c
+++ b/drivers/usb/gadget/udc/snps_udc_core.c
@@ -96,7 +96,7 @@ static int stop_pollstall_timer;
 static DECLARE_COMPLETION(on_pollstall_exit);
 
 /* tasklet for usb disconnect */
-static DECLARE_TASKLET(disconnect_tasklet, udc_tasklet_disconnect, 0);
+static DECLARE_TASKLET_OLD(disconnect_tasklet, udc_tasklet_disconnect);
 
 /* endpoint names used for print */
 static const char ep0_string[] = "ep0in";
diff --git a/drivers/usb/host/fhci-sched.c b/drivers/usb/host/fhci-sched.c
index 3235d5307403..5c423f240a1f 100644
--- a/drivers/usb/host/fhci-sched.c
+++ b/drivers/usb/host/fhci-sched.c
@@ -677,7 +677,7 @@ static void process_done_list(unsigned long data)
 	enable_irq(fhci_to_hcd(fhci)->irq);
 }
 
-DECLARE_TASKLET(fhci_tasklet, process_done_list, 0);
+DECLARE_TASKLET_OLD(fhci_tasklet, process_done_list);
 
 /* transfer complted callback */
 u32 fhci_transfer_confirm_callback(struct fhci_hcd *fhci)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5db970b6615a..b911196f03eb 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -612,12 +612,17 @@ struct tasklet_struct
 	unsigned long data;
 };
 
-#define DECLARE_TASKLET(name, func, data) \
-struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(0), func, data }
-
-#define DECLARE_TASKLET_DISABLED(name, func, data) \
-struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
+#define DECLARE_TASKLET_OLD(name, _func)		\
+struct tasklet_struct name = {				\
+	.count = ATOMIC_INIT(0),			\
+	.func = _func,					\
+}
 
+#define DECLARE_TASKLET_DISABLED_OLD(name, _func)	\
+struct tasklet_struct name = {				\
+	.count = ATOMIC_INIT(1),			\
+	.func = _func,					\
+}
 
 enum
 {
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index a2a97fa3071b..370217dd7e39 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -29,7 +29,7 @@ static void backtrace_test_irq_callback(unsigned long data)
 	complete(&backtrace_work);
 }
 
-static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0);
+static DECLARE_TASKLET_OLD(backtrace_tasklet, &backtrace_test_irq_callback);
 
 static void backtrace_test_irq(void)
 {
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 9e5934780f41..b16dbc1bf056 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -1068,7 +1068,7 @@ static void kgdb_tasklet_bpt(unsigned long ing)
 	atomic_set(&kgdb_break_tasklet_var, 0);
 }
 
-static DECLARE_TASKLET(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt, 0);
+static DECLARE_TASKLET_OLD(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt);
 
 void kgdb_schedule_breakpoint(void)
 {
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 27634f4022d0..c48ce19a257f 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -45,7 +45,7 @@ static void resend_irqs(unsigned long arg)
 }
 
 /* Tasklet to handle resend: */
-static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
+static DECLARE_TASKLET_OLD(resend_tasklet, resend_irqs);
 
 static int irq_sw_resend(struct irq_desc *desc)
 {
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index 45d8e1d5d033..579b66da1d95 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -393,7 +393,7 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg)
 	 * Each PPPoATM instance has its own tasklet - this is just a
 	 * prototypical one used to initialize them
 	 */
-	static const DECLARE_TASKLET(tasklet_proto, pppoatm_wakeup_sender, 0);
+	static const DECLARE_TASKLET_OLD(tasklet_proto, pppoatm_wakeup_sender);
 	if (copy_from_user(&be, arg, sizeof be))
 		return -EFAULT;
 	if (be.encaps != PPPOATM_ENCAPS_AUTODETECT &&
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 19250a0c85d3..cd2e468852e7 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -105,7 +105,7 @@ static LIST_HEAD(iucv_task_queue);
  * The tasklet for fast delivery of iucv interrupts.
  */
 static void iucv_tasklet_fn(unsigned long);
-static DECLARE_TASKLET(iucv_tasklet, iucv_tasklet_fn,0);
+static DECLARE_TASKLET_OLD(iucv_tasklet, iucv_tasklet_fn);
 
 /*
  * Queue of interrupt buffers for delivery via a work queue
diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index 05244b11ed5e..4e79293d7f11 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -36,7 +36,7 @@ static void pcsp_call_pcm_elapsed(unsigned long priv)
 	}
 }
 
-static DECLARE_TASKLET(pcsp_pcm_tasklet, pcsp_call_pcm_elapsed, 0);
+static DECLARE_TASKLET_OLD(pcsp_pcm_tasklet, pcsp_call_pcm_elapsed);
 
 /* write the port and returns the next expire time in ns;
  * called at the trigger-start and in hrtimer callback
-- 
cgit v1.2.3


From 12cc923f1ccc1df467e046b02a72c2b3b321b6a2 Mon Sep 17 00:00:00 2001
From: Romain Perier <romain.perier@gmail.com>
Date: Sun, 29 Sep 2019 18:30:13 +0200
Subject: tasklet: Introduce new initialization API

Nowadays, modern kernel subsystems that use callbacks pass the data
structure associated with a given callback as argument to the callback.
The tasklet subsystem remains one which passes an arbitrary unsigned
long to the callback function. This has several problems:

- This keeps an extra field for storing the argument in each tasklet
  data structure, it bloats the tasklet_struct structure with a redundant
  .data field

- No type checking can be performed on this argument. Instead of
  using container_of() like other callback subsystems, it forces callbacks
  to do explicit type cast of the unsigned long argument into the required
  object type.

- Buffer overflows can overwrite the .func and the .data field, so
  an attacker can easily overwrite the function and its first argument
  to whatever it wants.

Add a new tasklet initialization API, via DECLARE_TASKLET() and
tasklet_setup(), which will replace the existing ones.

This work is greatly inspired by the timer_struct conversion series,
see commit e99e88a9d2b0 ("treewide: setup_timer() -> timer_setup()")

To avoid problems with both -Wcast-function-type (which is enabled in
the kernel via -Wextra is several subsystems), and with mismatched
function prototypes when build with Control Flow Integrity enabled,
this adds the "use_callback" member to let the tasklet caller choose
which union member to call through. Once all old API uses are removed,
this and the .data member will be removed as well. (On 64-bit this does
not grow the struct size as the new member fills the hole after atomic_t,
which is also "int" sized.)

Signed-off-by: Romain Perier <romain.perier@gmail.com>
Co-developed-by: Allen Pais <allen.lkml@gmail.com>
Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Co-developed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/interrupt.h | 28 +++++++++++++++++++++++++++-
 kernel/softirq.c          | 18 +++++++++++++++++-
 2 files changed, 44 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index b911196f03eb..f9aee3538461 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -585,6 +585,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
 
 /* Tasklets --- multithreaded analogue of BHs.
 
+   This API is deprecated. Please consider using threaded IRQs instead:
+   https://lore.kernel.org/lkml/20200716081538.2sivhkj4hcyrusem@linutronix.de
+
    Main feature differing them of generic softirqs: tasklet
    is running only on one CPU simultaneously.
 
@@ -608,10 +611,31 @@ struct tasklet_struct
 	struct tasklet_struct *next;
 	unsigned long state;
 	atomic_t count;
-	void (*func)(unsigned long);
+	bool use_callback;
+	union {
+		void (*func)(unsigned long data);
+		void (*callback)(struct tasklet_struct *t);
+	};
 	unsigned long data;
 };
 
+#define DECLARE_TASKLET(name, _callback)		\
+struct tasklet_struct name = {				\
+	.count = ATOMIC_INIT(0),			\
+	.callback = _callback,				\
+	.use_callback = true,				\
+}
+
+#define DECLARE_TASKLET_DISABLED(name, _callback)	\
+struct tasklet_struct name = {				\
+	.count = ATOMIC_INIT(1),			\
+	.callback = _callback,				\
+	.use_callback = true,				\
+}
+
+#define from_tasklet(var, callback_tasklet, tasklet_fieldname)	\
+	container_of(callback_tasklet, typeof(*var), tasklet_fieldname)
+
 #define DECLARE_TASKLET_OLD(name, _func)		\
 struct tasklet_struct name = {				\
 	.count = ATOMIC_INIT(0),			\
@@ -691,6 +715,8 @@ extern void tasklet_kill(struct tasklet_struct *t);
 extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
 			 void (*func)(unsigned long), unsigned long data);
+extern void tasklet_setup(struct tasklet_struct *t,
+			  void (*callback)(struct tasklet_struct *));
 
 /*
  * Autoprobing for irqs:
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c4201b7f42b1..292e7c2d2333 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -547,7 +547,10 @@ static void tasklet_action_common(struct softirq_action *a,
 				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
 							&t->state))
 					BUG();
-				t->func(t->data);
+				if (t->use_callback)
+					t->callback(t);
+				else
+					t->func(t->data);
 				tasklet_unlock(t);
 				continue;
 			}
@@ -573,6 +576,18 @@ static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
 }
 
+void tasklet_setup(struct tasklet_struct *t,
+		   void (*callback)(struct tasklet_struct *))
+{
+	t->next = NULL;
+	t->state = 0;
+	atomic_set(&t->count, 0);
+	t->callback = callback;
+	t->use_callback = true;
+	t->data = 0;
+}
+EXPORT_SYMBOL(tasklet_setup);
+
 void tasklet_init(struct tasklet_struct *t,
 		  void (*func)(unsigned long), unsigned long data)
 {
@@ -580,6 +595,7 @@ void tasklet_init(struct tasklet_struct *t,
 	t->state = 0;
 	atomic_set(&t->count, 0);
 	t->func = func;
+	t->use_callback = false;
 	t->data = data;
 }
 EXPORT_SYMBOL(tasklet_init);
-- 
cgit v1.2.3


From 63bb76de4aeec833ae7ba05d85a7819ac4558126 Mon Sep 17 00:00:00 2001
From: Pekka Enberg <penberg@kernel.org>
Date: Wed, 15 Jul 2020 08:33:39 +0300
Subject: mm: pgtable: Make generic pgprot_* macros available for no-MMU

The <linux/pgtable.h> header defines some generic pgprot_*
implementations, but they are only available when CONFIG_MMU is enabled.
The RISC-V architecture, for example, therefore defines some of these
pgprot_* macros for !NOMMU.

Let's make the pgprot_* generic available even for !NOMMU so we can
remove the RISC-V specific definitions.

Compile-tested with x86 defconfig, and riscv defconfig and !MMU defconfig.

Suggested-by: Palmer Dabbelt <palmerdabbelt@google.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/linux/pgtable.h | 71 ++++++++++++++++++++++++++-----------------------
 1 file changed, 37 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 56c1e8eb7bb0..53e97da1e8e2 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -647,40 +647,6 @@ static inline int arch_unmap_one(struct mm_struct *mm,
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
 
-#ifndef pgprot_nx
-#define pgprot_nx(prot)	(prot)
-#endif
-
-#ifndef pgprot_noncached
-#define pgprot_noncached(prot)	(prot)
-#endif
-
-#ifndef pgprot_writecombine
-#define pgprot_writecombine pgprot_noncached
-#endif
-
-#ifndef pgprot_writethrough
-#define pgprot_writethrough pgprot_noncached
-#endif
-
-#ifndef pgprot_device
-#define pgprot_device pgprot_noncached
-#endif
-
-#ifndef pgprot_modify
-#define pgprot_modify pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
-		newprot = pgprot_noncached(newprot);
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
-		newprot = pgprot_writecombine(newprot);
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
-		newprot = pgprot_device(newprot);
-	return newprot;
-}
-#endif
-
 /*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
@@ -840,6 +806,43 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
  * No-op macros that just return the current protection value. Defined here
  * because these macros can be used used even if CONFIG_MMU is not defined.
  */
+
+#ifndef pgprot_nx
+#define pgprot_nx(prot)	(prot)
+#endif
+
+#ifndef pgprot_noncached
+#define pgprot_noncached(prot)	(prot)
+#endif
+
+#ifndef pgprot_writecombine
+#define pgprot_writecombine pgprot_noncached
+#endif
+
+#ifndef pgprot_writethrough
+#define pgprot_writethrough pgprot_noncached
+#endif
+
+#ifndef pgprot_device
+#define pgprot_device pgprot_noncached
+#endif
+
+#ifdef CONFIG_MMU
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+		newprot = pgprot_noncached(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+		newprot = pgprot_writecombine(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
+		newprot = pgprot_device(newprot);
+	return newprot;
+}
+#endif
+#endif /* CONFIG_MMU */
+
 #ifndef pgprot_encrypted
 #define pgprot_encrypted(prot)	(prot)
 #endif
-- 
cgit v1.2.3


From fb2da16cd70a5140acdd7a102e5cd3b697c3404f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 09:02:07 +0200
Subject: fs: remove ksys_getdents64

Just open code it in the only caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/readdir.c             | 11 ++---------
 include/linux/syscalls.h |  2 --
 2 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/readdir.c b/fs/readdir.c
index a49f07c11cfb..19434b3c982c 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -348,8 +348,8 @@ efault:
 	return -EFAULT;
 }
 
-int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
-		    unsigned int count)
+SYSCALL_DEFINE3(getdents64, unsigned int, fd,
+		struct linux_dirent64 __user *, dirent, unsigned int, count)
 {
 	struct fd f;
 	struct getdents_callback64 buf = {
@@ -380,13 +380,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
 	return error;
 }
 
-
-SYSCALL_DEFINE3(getdents64, unsigned int, fd,
-		struct linux_dirent64 __user *, dirent, unsigned int, count)
-{
-	return ksys_getdents64(fd, dirent, count);
-}
-
 #ifdef CONFIG_COMPAT
 struct compat_old_linux_dirent {
 	compat_ulong_t	d_ino;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 10843a6adb77..a998651629c7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1243,8 +1243,6 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
 int ksys_fchmod(unsigned int fd, umode_t mode);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
-int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
-		    unsigned int count);
 int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
 void ksys_sync(void);
-- 
cgit v1.2.3


From 166e07c37c6417c9713666268fc0eb89a9ce48b9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 6 Jun 2020 15:03:21 +0200
Subject: fs: remove ksys_open

Just open code it in the two callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/open.c                | 11 ++++++++---
 include/linux/syscalls.h | 11 -----------
 2 files changed, 8 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/open.c b/fs/open.c
index 75166f071d28..ab3671af8a97 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1208,7 +1208,9 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 
 SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
 {
-	return ksys_open(filename, flags, mode);
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+	return do_sys_open(AT_FDCWD, filename, flags, mode);
 }
 
 SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
@@ -1270,9 +1272,12 @@ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, fla
  */
 SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
 {
-	return ksys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
-}
+	int flags = O_CREAT | O_WRONLY | O_TRUNC;
 
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+	return do_sys_open(AT_FDCWD, pathname, flags, mode);
+}
 #endif
 
 /*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a998651629c7..363baaadf8e1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1374,17 +1374,6 @@ static inline int ksys_close(unsigned int fd)
 	return __close_fd(current->files, fd);
 }
 
-extern long do_sys_open(int dfd, const char __user *filename, int flags,
-			umode_t mode);
-
-static inline long ksys_open(const char __user *filename, int flags,
-			     umode_t mode)
-{
-	if (force_o_largefile())
-		flags |= O_LARGEFILE;
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
-}
-
 extern long do_sys_truncate(const char __user *pathname, loff_t length);
 
 static inline long ksys_truncate(const char __user *pathname, loff_t length)
-- 
cgit v1.2.3


From bc1cd99a9ad7e2c768e7ea92ae9c6ad4a4e0f7f7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 08:58:49 +0200
Subject: fs: remove ksys_dup

Fold it into the only remaining caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/file.c                | 7 +------
 include/linux/syscalls.h | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index abb8b7081d7a..85b7993165dd 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -985,7 +985,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 	return ksys_dup3(oldfd, newfd, 0);
 }
 
-int ksys_dup(unsigned int fildes)
+SYSCALL_DEFINE1(dup, unsigned int, fildes)
 {
 	int ret = -EBADF;
 	struct file *file = fget_raw(fildes);
@@ -1000,11 +1000,6 @@ int ksys_dup(unsigned int fildes)
 	return ret;
 }
 
-SYSCALL_DEFINE1(dup, unsigned int, fildes)
-{
-	return ksys_dup(fildes);
-}
-
 int f_dupfd(unsigned int from, struct file *file, unsigned flags)
 {
 	int err;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 363baaadf8e1..b6d900574762 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1237,7 +1237,6 @@ asmlinkage long sys_ni_syscall(void);
  */
 
 int ksys_umount(char __user *name, int flags);
-int ksys_dup(unsigned int fildes);
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
-- 
cgit v1.2.3


From b25ba7c3c9acdc4cf69f5bd69989819cabfc4e3b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 08:59:57 +0200
Subject: fs: remove ksys_fchmod

Fold it into the only remaining caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/open.c                | 7 +------
 include/linux/syscalls.h | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/open.c b/fs/open.c
index ab3671af8a97..b316dd6a86a8 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -608,7 +608,7 @@ int vfs_fchmod(struct file *file, umode_t mode)
 	return chmod_common(&file->f_path, mode);
 }
 
-int ksys_fchmod(unsigned int fd, umode_t mode)
+SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 {
 	struct fd f = fdget(fd);
 	int err = -EBADF;
@@ -620,11 +620,6 @@ int ksys_fchmod(unsigned int fd, umode_t mode)
 	return err;
 }
 
-SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
-{
-	return ksys_fchmod(fd, mode);
-}
-
 int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
 {
 	struct path path;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b6d900574762..39ff738997a1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1240,7 +1240,6 @@ int ksys_umount(char __user *name, int flags);
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
-int ksys_fchmod(unsigned int fd, umode_t mode);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
-- 
cgit v1.2.3


From 863b67e15177a7cd0c27b3e36e42fe7907dec9bd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Jul 2020 09:00:51 +0200
Subject: fs: remove ksys_ioctl

Fold it into the only remaining caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ioctl.c               | 7 +------
 include/linux/syscalls.h | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ioctl.c b/fs/ioctl.c
index d69786d1dd91..4e6cc0a7d69c 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -736,7 +736,7 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
 	return -ENOIOCTLCMD;
 }
 
-int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
+SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {
 	struct fd f = fdget(fd);
 	int error;
@@ -757,11 +757,6 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
-{
-	return ksys_ioctl(fd, cmd, arg);
-}
-
 #ifdef CONFIG_COMPAT
 /**
  * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 39ff738997a1..5b0f1fca4cfb 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1241,7 +1241,6 @@ int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
-int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
 void ksys_sync(void);
 int ksys_unshare(unsigned long unshare_flags);
-- 
cgit v1.2.3


From fd5ad30c782351ab4d4a15941fc61e743a1bd66c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 15 Jul 2020 08:19:55 +0200
Subject: fs: expose utimes_common

Rename utimes_common to vfs_utimes and make it available outside of
utimes.c.  This will be used by the initramfs unpacking code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/utimes.c        | 6 +++---
 include/linux/fs.h | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/utimes.c b/fs/utimes.c
index bfd86e81c590..fd3cc4226224 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -16,7 +16,7 @@ static bool nsec_valid(long nsec)
 	return nsec >= 0 && nsec <= 999999999;
 }
 
-static int utimes_common(const struct path *path, struct timespec64 *times)
+int vfs_utimes(const struct path *path, struct timespec64 *times)
 {
 	int error;
 	struct iattr newattrs;
@@ -94,7 +94,7 @@ retry:
 	if (error)
 		return error;
 
-	error = utimes_common(&path, times);
+	error = vfs_utimes(&path, times);
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -115,7 +115,7 @@ static int do_utimes_fd(int fd, struct timespec64 *times, int flags)
 	f = fdget(fd);
 	if (!f.file)
 		return -EBADF;
-	error = utimes_common(&f.file->f_path, times);
+	error = vfs_utimes(&f.file->f_path, times);
 	fdput(f);
 	return error;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 635086726f20..a1d2685a4878 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1746,6 +1746,7 @@ int vfs_mkobj(struct dentry *, umode_t,
 
 int vfs_fchown(struct file *file, uid_t user, gid_t group);
 int vfs_fchmod(struct file *file, umode_t mode);
+int vfs_utimes(const struct path *path, struct timespec64 *times);
 
 extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
-- 
cgit v1.2.3


From e24ab0ef689de43649327f54cd1088f3dad25bb3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 21 Jul 2020 10:48:15 +0200
Subject: fs: push the getname from do_rmdir into the callers

This mirrors do_unlinkat and will make life a little easier for
the init code to reuse the whole function with a kernel filename.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/internal.h            |  2 +-
 fs/namei.c               | 10 ++++------
 include/linux/syscalls.h |  4 ++--
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/internal.h b/fs/internal.h
index 9b863a7bd708..e903d5aae139 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -65,7 +65,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev);
 long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-long do_rmdir(int dfd, const char __user *pathname);
+long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname);
diff --git a/fs/namei.c b/fs/namei.c
index 72d4219c93ac..d75a6039ae39 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3720,17 +3720,16 @@ out:
 }
 EXPORT_SYMBOL(vfs_rmdir);
 
-long do_rmdir(int dfd, const char __user *pathname)
+long do_rmdir(int dfd, struct filename *name)
 {
 	int error = 0;
-	struct filename *name;
 	struct dentry *dentry;
 	struct path path;
 	struct qstr last;
 	int type;
 	unsigned int lookup_flags = 0;
 retry:
-	name = filename_parentat(dfd, getname(pathname), lookup_flags,
+	name = filename_parentat(dfd, name, lookup_flags,
 				&path, &last, &type);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
@@ -3781,7 +3780,7 @@ exit1:
 
 SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 {
-	return do_rmdir(AT_FDCWD, pathname);
+	return do_rmdir(AT_FDCWD, getname(pathname));
 }
 
 /**
@@ -3926,8 +3925,7 @@ SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
 		return -EINVAL;
 
 	if (flag & AT_REMOVEDIR)
-		return do_rmdir(dfd, pathname);
-
+		return do_rmdir(dfd, getname(pathname));
 	return do_unlinkat(dfd, getname(pathname));
 }
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5b0f1fca4cfb..e43816198e60 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1281,11 +1281,11 @@ static inline long ksys_unlink(const char __user *pathname)
 	return do_unlinkat(AT_FDCWD, getname(pathname));
 }
 
-extern long do_rmdir(int dfd, const char __user *pathname);
+long do_rmdir(int dfd, struct filename *name);
 
 static inline long ksys_rmdir(const char __user *pathname)
 {
-	return do_rmdir(AT_FDCWD, pathname);
+	return do_rmdir(AT_FDCWD, getname(pathname));
 }
 
 extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-- 
cgit v1.2.3


From c60166f04283ffba7b88b45d824bbfb2bfccee24 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 21 Jul 2020 11:12:08 +0200
Subject: init: add an init_mount helper

Like do_mount, but takes a kernel pointer for the destination path.
Switch over the mounts in the init code and devtmpfs to it, which
just happen to work due to the implicit set_fs(KERNEL_DS) during early
init right now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  5 +++--
 fs/Makefile                   |  2 +-
 fs/init.c                     | 25 +++++++++++++++++++++++++
 fs/internal.h                 |  4 ++++
 fs/namespace.c                |  2 +-
 include/linux/init_syscalls.h |  4 ++++
 init/do_mounts.c              |  8 ++++----
 init/do_mounts.h              |  1 +
 init/do_mounts_initrd.c       |  6 +++---
 9 files changed, 46 insertions(+), 11 deletions(-)
 create mode 100644 fs/init.c
 create mode 100644 include/linux/init_syscalls.h

(limited to 'include/linux')

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index d697634bc0d4..32af6cb987b4 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/init_syscalls.h>
 #include <uapi/linux/mount.h>
 #include "base.h"
 
@@ -359,7 +360,7 @@ int __init devtmpfs_mount(void)
 	if (!thread)
 		return 0;
 
-	err = do_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL);
+	err = init_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
 	else
@@ -408,7 +409,7 @@ static int __init devtmpfs_setup(void *p)
 	err = ksys_unshare(CLONE_NEWNS);
 	if (err)
 		goto out;
-	err = do_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
+	err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		goto out;
 	ksys_chdir("/.."); /* will traverse into overmounted root */
diff --git a/fs/Makefile b/fs/Makefile
index 2ce5112b02c8..1c7b0e3f6daa 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -13,7 +13,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o fsopen.o
+		fs_types.o fs_context.o fs_parser.o fsopen.o init.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/init.c b/fs/init.c
new file mode 100644
index 000000000000..c6eb724e1c7b
--- /dev/null
+++ b/fs/init.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Routines that mimic syscalls, but don't use the user address space or file
+ * descriptors.  Only for init/ and related early init code.
+ */
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include <linux/init_syscalls.h>
+#include "internal.h"
+
+int __init init_mount(const char *dev_name, const char *dir_name,
+		const char *type_page, unsigned long flags, void *data_page)
+{
+	struct path path;
+	int ret;
+
+	ret = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ret;
+	ret = path_mount(dev_name, &path, type_page, flags, data_page);
+	path_put(&path);
+	return ret;
+}
diff --git a/fs/internal.h b/fs/internal.h
index e903d5aae139..72ea0b6f7435 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -89,6 +89,10 @@ extern int __mnt_want_write_file(struct file *);
 extern void __mnt_drop_write_file(struct file *);
 
 extern void dissolve_on_fput(struct vfsmount *);
+
+int path_mount(const char *dev_name, struct path *path,
+		const char *type_page, unsigned long flags, void *data_page);
+
 /*
  * fs_struct.c
  */
diff --git a/fs/namespace.c b/fs/namespace.c
index 43834b59eff6..2c4d75920974 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3111,7 +3111,7 @@ char *copy_mount_string(const void __user *data)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-static int path_mount(const char *dev_name, struct path *path,
+int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	unsigned int mnt_flags = 0, sb_flags;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
new file mode 100644
index 000000000000..af9ea88a60e0
--- /dev/null
+++ b/include/linux/init_syscalls.h
@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+int __init init_mount(const char *dev_name, const char *dir_name,
+		const char *type_page, unsigned long flags, void *data_page);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index a7f22cf58c7e..83db87b6e5d1 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -395,16 +395,16 @@ static int __init do_mount_root(const char *name, const char *fs,
 	int ret;
 
 	if (data) {
-		/* do_mount() requires a full page as fifth argument */
+		/* init_mount() requires a full page as fifth argument */
 		p = alloc_page(GFP_KERNEL);
 		if (!p)
 			return -ENOMEM;
 		data_page = page_address(p);
-		/* zero-pad. do_mount() will make sure it's terminated */
+		/* zero-pad. init_mount() will make sure it's terminated */
 		strncpy(data_page, data, PAGE_SIZE);
 	}
 
-	ret = do_mount(name, "/root", fs, flags, data_page);
+	ret = init_mount(name, "/root", fs, flags, data_page);
 	if (ret)
 		goto out;
 
@@ -628,7 +628,7 @@ void __init prepare_namespace(void)
 	mount_root();
 out:
 	devtmpfs_mount();
-	do_mount(".", "/", NULL, MS_MOVE, NULL);
+	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 }
 
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 021e2f60223e..20e7fec8cb49 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -8,6 +8,7 @@
 #include <linux/mount.h>
 #include <linux/major.h>
 #include <linux/root_dev.h>
+#include <linux/init_syscalls.h>
 
 void  mount_block_root(char *name, int flags);
 void  mount_root(void);
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index e08669187d63..1f9336209ad9 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -62,7 +62,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	console_on_rootfs();
 	/* move initrd over / and chdir/chroot in initrd root */
 	ksys_chdir("/root");
-	do_mount(".", "/", NULL, MS_MOVE, NULL);
+	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 	ksys_setsid();
 	return 0;
@@ -99,7 +99,7 @@ static void __init handle_initrd(void)
 	current->flags &= ~PF_FREEZER_SKIP;
 
 	/* move initrd to rootfs' /old */
-	do_mount("..", ".", NULL, MS_MOVE, NULL);
+	init_mount("..", ".", NULL, MS_MOVE, NULL);
 	/* switch root and cwd back to / of rootfs */
 	ksys_chroot("..");
 
@@ -113,7 +113,7 @@ static void __init handle_initrd(void)
 	mount_root();
 
 	printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
-	error = do_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
+	error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
 	if (!error)
 		printk("okay\n");
 	else {
-- 
cgit v1.2.3


From 09267defa36aaff6ff829bd2fc8b043ec151cc3e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:23:08 +0200
Subject: init: add an init_umount helper

Like ksys_umount, but takes a kernel pointer for the destination path.
Switch over the umount in the init code, which just happen to work due to
the implicit set_fs(KERNEL_DS) during early init right now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 14 ++++++++++++++
 fs/internal.h                 |  1 +
 fs/namespace.c                |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  1 -
 init/do_mounts_initrd.c       |  2 +-
 6 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index c6eb724e1c7b..9c8e31fdb048 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -23,3 +23,17 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 	path_put(&path);
 	return ret;
 }
+
+int __init init_umount(const char *name, int flags)
+{
+	int lookup_flags = LOOKUP_MOUNTPOINT;
+	struct path path;
+	int ret;
+
+	if (!(flags & UMOUNT_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	ret = kern_path(name, lookup_flags, &path);
+	if (ret)
+		return ret;
+	return path_umount(&path, flags);
+}
diff --git a/fs/internal.h b/fs/internal.h
index 72ea0b6f7435..491d1e63809b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -92,6 +92,7 @@ extern void dissolve_on_fput(struct vfsmount *);
 
 int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page);
+int path_umount(struct path *path, int flags);
 
 /*
  * fs_struct.c
diff --git a/fs/namespace.c b/fs/namespace.c
index 2c4d75920974..a7301790abb2 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1706,7 +1706,7 @@ static inline bool may_mandlock(void)
 }
 #endif
 
-static int path_umount(struct path *path, int flags)
+int path_umount(struct path *path, int flags)
 {
 	struct mount *mnt;
 	int retval;
@@ -1736,7 +1736,7 @@ dput_and_out:
 	return retval;
 }
 
-int ksys_umount(char __user *name, int flags)
+static int ksys_umount(char __user *name, int flags)
 {
 	int lookup_flags = LOOKUP_MOUNTPOINT;
 	struct path path;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index af9ea88a60e0..a5a2e7f19916 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -2,3 +2,4 @@
 
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
+int __init init_umount(const char *name, int flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e43816198e60..1a4f5d8ee704 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1236,7 +1236,6 @@ asmlinkage long sys_ni_syscall(void);
  * the ksys_xyzyyz() functions prototyped below.
  */
 
-int ksys_umount(char __user *name, int flags);
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_chdir(const char __user *filename);
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 1f9336209ad9..6b020a069902 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -122,7 +122,7 @@ static void __init handle_initrd(void)
 		else
 			printk("failed\n");
 		printk(KERN_NOTICE "Unmounting old root\n");
-		ksys_umount("/old", MNT_DETACH);
+		init_umount("/old", MNT_DETACH);
 	}
 }
 
-- 
cgit v1.2.3


From 8fb9f73e5a539ab3aa4785f30fb52c65fa98600c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Jul 2020 08:23:40 +0200
Subject: init: add an init_unlink helper

Add a simple helper to unlink with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_unlink.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 5 +++++
 include/linux/init_syscalls.h | 1 +
 include/linux/syscalls.h      | 7 -------
 init/do_mounts.h              | 2 +-
 init/do_mounts_initrd.c       | 4 ++--
 init/do_mounts_rd.c           | 2 +-
 init/initramfs.c              | 3 ++-
 7 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 9c8e31fdb048..507ffbb5d146 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -37,3 +37,8 @@ int __init init_umount(const char *name, int flags)
 		return ret;
 	return path_umount(&path, flags);
 }
+
+int __init init_unlink(const char *pathname)
+{
+	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index a5a2e7f19916..00d597249549 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -3,3 +3,4 @@
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
+int __init init_unlink(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1a4f5d8ee704..26f9738e5ab8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_unlinkat(int dfd, struct filename *name);
-
-static inline long ksys_unlink(const char __user *pathname)
-{
-	return do_unlinkat(AT_FDCWD, getname(pathname));
-}
-
 long do_rmdir(int dfd, struct filename *name);
 
 static inline long ksys_rmdir(const char __user *pathname)
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 20e7fec8cb49..104d8431725a 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -16,7 +16,7 @@ extern int root_mountflags;
 
 static inline __init int create_dev(char *name, dev_t dev)
 {
-	ksys_unlink(name);
+	init_unlink(name);
 	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
 }
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 6b020a069902..8b44dd017842 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -137,11 +137,11 @@ bool __init initrd_load(void)
 		 * mounted in the normal path.
 		 */
 		if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) {
-			ksys_unlink("/initrd.image");
+			init_unlink("/initrd.image");
 			handle_initrd();
 			return true;
 		}
 	}
-	ksys_unlink("/initrd.image");
+	init_unlink("/initrd.image");
 	return false;
 }
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index d4255c10432a..ac021ae6e6fa 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -272,7 +272,7 @@ noclose_input:
 	fput(out_file);
 out:
 	kfree(buf);
-	ksys_unlink("/dev/ram");
+	init_unlink("/dev/ram");
 	return res;
 }
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 9820fca4d4e3..eb58cee6dadb 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -12,6 +12,7 @@
 #include <linux/file.h>
 #include <linux/memblock.h>
 #include <linux/namei.h>
+#include <linux/init_syscalls.h>
 
 static ssize_t __init xwrite(struct file *file, const char *p, size_t count,
 		loff_t *pos)
@@ -301,7 +302,7 @@ static void __init clean_path(char *path, umode_t fmode)
 		if (S_ISDIR(st.mode))
 			ksys_rmdir(path);
 		else
-			ksys_unlink(path);
+			init_unlink(path);
 	}
 }
 
-- 
cgit v1.2.3


From 20cce026c3e0972017b9cb4a7cccfb8cacf187d5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:11:45 +0200
Subject: init: add an init_rmdir helper

Add a simple helper to rmdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_rmdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 5 +++++
 include/linux/init_syscalls.h | 1 +
 include/linux/syscalls.h      | 7 -------
 init/initramfs.c              | 2 +-
 4 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 507ffbb5d146..eabd9ed2b510 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -42,3 +42,8 @@ int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
 }
+
+int __init init_rmdir(const char *pathname)
+{
+	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 00d597249549..abf3af563c0b 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -4,3 +4,4 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
 int __init init_unlink(const char *pathname);
+int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 26f9738e5ab8..a7b14258d245 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-long do_rmdir(int dfd, struct filename *name);
-
-static inline long ksys_rmdir(const char __user *pathname)
-{
-	return do_rmdir(AT_FDCWD, getname(pathname));
-}
-
 extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 
 static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
diff --git a/init/initramfs.c b/init/initramfs.c
index eb58cee6dadb..1a9159bf452f 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -300,7 +300,7 @@ static void __init clean_path(char *path, umode_t fmode)
 
 	if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
-			ksys_rmdir(path);
+			init_rmdir(path);
 		else
 			init_unlink(path);
 	}
-- 
cgit v1.2.3


From db63f1e315384590b979f8f74abd1b5363b69894 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:25:21 +0200
Subject: init: add an init_chdir helper

Add a simple helper to chdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_chdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  2 +-
 fs/init.c                     | 16 ++++++++++++++++
 fs/open.c                     |  7 +------
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  1 -
 init/do_mounts.c              |  2 +-
 init/do_mounts_initrd.c       |  8 ++++----
 7 files changed, 24 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 32af6cb987b4..e48aaba3166b 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -412,7 +412,7 @@ static int __init devtmpfs_setup(void *p)
 	err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL);
 	if (err)
 		goto out;
-	ksys_chdir("/.."); /* will traverse into overmounted root */
+	init_chdir("/.."); /* will traverse into overmounted root */
 	ksys_chroot(".");
 out:
 	*(int *)p = err;
diff --git a/fs/init.c b/fs/init.c
index eabd9ed2b510..64d4e12eba93 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -7,6 +7,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/init_syscalls.h>
 #include "internal.h"
 
@@ -38,6 +39,21 @@ int __init init_umount(const char *name, int flags)
 	return path_umount(&path, flags);
 }
 
+int __init init_chdir(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (error)
+		return error;
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+	if (!error)
+		set_fs_pwd(current->fs, &path);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index b316dd6a86a8..723e0ac89893 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -482,7 +482,7 @@ SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
 	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
-int ksys_chdir(const char __user *filename)
+SYSCALL_DEFINE1(chdir, const char __user *, filename)
 {
 	struct path path;
 	int error;
@@ -508,11 +508,6 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE1(chdir, const char __user *, filename)
-{
-	return ksys_chdir(filename);
-}
-
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
 	struct fd f = fdget_raw(fd);
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index abf3af563c0b..1e845910ae56 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -3,5 +3,6 @@
 int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
+int __init init_chdir(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a7b14258d245..31fa67fb9894 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1238,7 +1238,6 @@ asmlinkage long sys_ni_syscall(void);
 
 int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
-int ksys_chdir(const char __user *filename);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
 void ksys_sync(void);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 83db87b6e5d1..a7581c6e85f2 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -408,7 +408,7 @@ static int __init do_mount_root(const char *name, const char *fs,
 	if (ret)
 		goto out;
 
-	ksys_chdir("/root");
+	init_chdir("/root");
 	s = current->fs->pwd.dentry->d_sb;
 	ROOT_DEV = s->s_dev;
 	printk(KERN_INFO
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 8b44dd017842..04627fd22a92 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -61,7 +61,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	ksys_unshare(CLONE_FS | CLONE_FILES);
 	console_on_rootfs();
 	/* move initrd over / and chdir/chroot in initrd root */
-	ksys_chdir("/root");
+	init_chdir("/root");
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 	ksys_setsid();
@@ -82,7 +82,7 @@ static void __init handle_initrd(void)
 	/* mount initrd on rootfs' /root */
 	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
 	ksys_mkdir("/old", 0700);
-	ksys_chdir("/old");
+	init_chdir("/old");
 
 	/*
 	 * In case that a resume from disk is carried out by linuxrc or one of
@@ -104,11 +104,11 @@ static void __init handle_initrd(void)
 	ksys_chroot("..");
 
 	if (new_decode_dev(real_root_dev) == Root_RAM0) {
-		ksys_chdir("/old");
+		init_chdir("/old");
 		return;
 	}
 
-	ksys_chdir("/");
+	init_chdir("/");
 	ROOT_DEV = new_decode_dev(real_root_dev);
 	mount_root();
 
-- 
cgit v1.2.3


From 4b7ca5014cbef51cdb99fd644eae4f3773747a05 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:26:13 +0200
Subject: init: add an init_chroot helper

Add a simple helper to chroot with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_chroot.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/base/devtmpfs.c       |  2 +-
 fs/init.c                     | 24 ++++++++++++++++++++++++
 fs/open.c                     |  7 +------
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  2 --
 init/do_mounts.c              |  2 +-
 init/do_mounts_initrd.c       |  4 ++--
 7 files changed, 30 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index e48aaba3166b..eac184e6d657 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -413,7 +413,7 @@ static int __init devtmpfs_setup(void *p)
 	if (err)
 		goto out;
 	init_chdir("/.."); /* will traverse into overmounted root */
-	ksys_chroot(".");
+	init_chroot(".");
 out:
 	*(int *)p = err;
 	complete(&setup_done);
diff --git a/fs/init.c b/fs/init.c
index 64d4e12eba93..2c78f24814dd 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -9,6 +9,7 @@
 #include <linux/fs.h>
 #include <linux/fs_struct.h>
 #include <linux/init_syscalls.h>
+#include <linux/security.h>
 #include "internal.h"
 
 int __init init_mount(const char *dev_name, const char *dir_name,
@@ -54,6 +55,29 @@ int __init init_chdir(const char *filename)
 	return error;
 }
 
+int __init init_chroot(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (error)
+		return error;
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+	if (error)
+		goto dput_and_out;
+	error = -EPERM;
+	if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
+		goto dput_and_out;
+	error = security_path_chroot(&path);
+	if (error)
+		goto dput_and_out;
+	set_fs_root(current->fs, &path);
+dput_and_out:
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index 723e0ac89893..f62f4752bb43 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -530,7 +530,7 @@ out:
 	return error;
 }
 
-int ksys_chroot(const char __user *filename)
+SYSCALL_DEFINE1(chroot, const char __user *, filename)
 {
 	struct path path;
 	int error;
@@ -563,11 +563,6 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE1(chroot, const char __user *, filename)
-{
-	return ksys_chroot(filename);
-}
-
 static int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 1e845910ae56..e07099a14b91 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -4,5 +4,6 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 		const char *type_page, unsigned long flags, void *data_page);
 int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
+int __init init_chroot(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 31fa67fb9894..e89d62e944dc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1235,8 +1235,6 @@ asmlinkage long sys_ni_syscall(void);
  * Instead, use one of the functions which work equivalently, such as
  * the ksys_xyzyyz() functions prototyped below.
  */
-
-int ksys_chroot(const char __user *filename);
 ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
 int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
diff --git a/init/do_mounts.c b/init/do_mounts.c
index a7581c6e85f2..b5f9604d0c98 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -629,7 +629,7 @@ void __init prepare_namespace(void)
 out:
 	devtmpfs_mount();
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
-	ksys_chroot(".");
+	init_chroot(".");
 }
 
 static bool is_tmpfs;
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 04627fd22a92..a6b447b191db 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -63,7 +63,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	/* move initrd over / and chdir/chroot in initrd root */
 	init_chdir("/root");
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
-	ksys_chroot(".");
+	init_chroot(".");
 	ksys_setsid();
 	return 0;
 }
@@ -101,7 +101,7 @@ static void __init handle_initrd(void)
 	/* move initrd to rootfs' /old */
 	init_mount("..", ".", NULL, MS_MOVE, NULL);
 	/* switch root and cwd back to / of rootfs */
-	ksys_chroot("..");
+	init_chroot("..");
 
 	if (new_decode_dev(real_root_dev) == Root_RAM0) {
 		init_chdir("/old");
-- 
cgit v1.2.3


From b873498f99c77e7b5be3aa5ffe9ca67437232fe0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:13:26 +0200
Subject: init: add an init_chown helper

Add a simple helper to chown with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 18 ++++++++++++++++++
 fs/internal.h                 |  2 +-
 fs/open.c                     |  2 +-
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  6 +++---
 5 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 2c78f24814dd..edd024465595 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -78,6 +78,24 @@ dput_and_out:
 	return error;
 }
 
+int __init init_chown(const char *filename, uid_t user, gid_t group, int flags)
+{
+	int lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	error = kern_path(filename, lookup_flags, &path);
+	if (error)
+		return error;
+	error = mnt_want_write(path.mnt);
+	if (!error) {
+		error = chown_common(&path, user, group);
+		mnt_drop_write(path.mnt);
+	}
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 491d1e63809b..e81b9e23c3ea 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -134,7 +134,7 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
-
+int chown_common(const struct path *path, uid_t user, gid_t group);
 extern int vfs_open(const struct path *, struct file *);
 
 /*
diff --git a/fs/open.c b/fs/open.c
index f62f4752bb43..49960a1248f1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -639,7 +639,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 	return do_fchmodat(AT_FDCWD, filename, mode);
 }
 
-static int chown_common(const struct path *path, uid_t user, gid_t group)
+int chown_common(const struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct inode *delegated_inode = NULL;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index e07099a14b91..0da59d76133e 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -5,5 +5,6 @@ int __init init_mount(const char *dev_name, const char *dir_name,
 int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
+int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/init/initramfs.c b/init/initramfs.c
index 1a9159bf452f..358dcd93cb9d 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -349,14 +349,14 @@ static int __init do_name(void)
 		}
 	} else if (S_ISDIR(mode)) {
 		ksys_mkdir(collected, mode);
-		ksys_chown(collected, uid, gid);
+		init_chown(collected, uid, gid, 0);
 		ksys_chmod(collected, mode);
 		dir_add(collected, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
 			ksys_mknod(collected, mode, rdev);
-			ksys_chown(collected, uid, gid);
+			init_chown(collected, uid, gid, 0);
 			ksys_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
@@ -393,7 +393,7 @@ static int __init do_symlink(void)
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
 	ksys_symlink(collected + N_ALIGN(name_len), collected);
-	ksys_lchown(collected, uid, gid);
+	init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW);
 	do_utime(collected, mtime);
 	state = SkipIt;
 	next_state = Reset;
-- 
cgit v1.2.3


From 1097742efc643ffc667c5c6684635b2663145a7d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:41:02 +0200
Subject: init: add an init_chmod helper

Add a simple helper to chmod with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 13 +++++++++++++
 fs/internal.h                 |  2 +-
 fs/open.c                     |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/initramfs.c              |  4 ++--
 6 files changed, 19 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index edd024465595..a66032d128b6 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -96,6 +96,19 @@ int __init init_chown(const char *filename, uid_t user, gid_t group, int flags)
 	return error;
 }
 
+int __init init_chmod(const char *filename, umode_t mode)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW, &path);
+	if (error)
+		return error;
+	error = chmod_common(&path, mode);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index e81b9e23c3ea..6d82681c7d83 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -131,7 +131,7 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
-int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
+int chmod_common(const struct path *path, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 int chown_common(const struct path *path, uid_t user, gid_t group);
diff --git a/fs/open.c b/fs/open.c
index 49960a1248f1..7ba89eae46c5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -563,7 +563,7 @@ out:
 	return error;
 }
 
-static int chmod_common(const struct path *path, umode_t mode)
+int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct inode *delegated_inode = NULL;
@@ -610,7 +610,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 	return err;
 }
 
-int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
+static int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
 {
 	struct path path;
 	int error;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 0da59d76133e..2b1b4dc58682 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -6,5 +6,6 @@ int __init init_umount(const char *name, int flags);
 int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
+int __init init_chmod(const char *filename, umode_t mode);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e89d62e944dc..8b71fa321ca2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname,
 	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-extern int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
-
-static inline int ksys_chmod(const char __user *filename, umode_t mode)
-{
-	return do_fchmodat(AT_FDCWD, filename, mode);
-}
-
 long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
 
 static inline long ksys_access(const char __user *filename, int mode)
diff --git a/init/initramfs.c b/init/initramfs.c
index 358dcd93cb9d..efa9fb70038d 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -350,14 +350,14 @@ static int __init do_name(void)
 	} else if (S_ISDIR(mode)) {
 		ksys_mkdir(collected, mode);
 		init_chown(collected, uid, gid, 0);
-		ksys_chmod(collected, mode);
+		init_chmod(collected, mode);
 		dir_add(collected, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
 			ksys_mknod(collected, mode, rdev);
 			init_chown(collected, uid, gid, 0);
-			ksys_chmod(collected, mode);
+			init_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
 	}
-- 
cgit v1.2.3


From eb9d7d390e51108b4c6a9a7993ed9be92548c8f7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:14:02 +0200
Subject: init: add an init_eaccess helper

Add a simple helper to check if a file exists based on kernel space file
name and switch the early init code over to it.  Note that this
theoretically changes behavior as it always is based on the effective
permissions.  But during early init that doesn't make a difference.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 13 +++++++++++++
 fs/open.c                     |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/main.c                   |  4 ++--
 5 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index a66032d128b6..6d9af40d2897 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -109,6 +109,19 @@ int __init init_chmod(const char *filename, umode_t mode)
 	return error;
 }
 
+int __init init_eaccess(const char *filename)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, LOOKUP_FOLLOW, &path);
+	if (error)
+		return error;
+	error = inode_permission(d_inode(path.dentry), MAY_ACCESS);
+	path_put(&path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/open.c b/fs/open.c
index 7ba89eae46c5..aafecd1f7ba1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -394,7 +394,7 @@ static const struct cred *access_override_creds(void)
 	return old_cred;
 }
 
-long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
+static long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
 {
 	struct path path;
 	struct inode *inode;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 2b1b4dc58682..7031c0934bee 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -7,5 +7,6 @@ int __init init_chdir(const char *filename);
 int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
+int __init init_eaccess(const char *filename);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8b71fa321ca2..a2779638e414 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname,
 	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
-
-static inline long ksys_access(const char __user *filename, int mode)
-{
-	return do_faccessat(AT_FDCWD, filename, mode, 0);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/main.c b/init/main.c
index 47698427b15f..1c710d3e1d46 100644
--- a/init/main.c
+++ b/init/main.c
@@ -96,6 +96,7 @@
 #include <linux/jump_label.h>
 #include <linux/mem_encrypt.h>
 #include <linux/kcsan.h>
+#include <linux/init_syscalls.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -1514,8 +1515,7 @@ static noinline void __init kernel_init_freeable(void)
 	 * check if there is an early userspace init.  If yes, let it do all
 	 * the work
 	 */
-	if (ksys_access((const char __user *)
-			ramdisk_execute_command, 0) != 0) {
+	if (init_eaccess(ramdisk_execute_command) != 0) {
 		ramdisk_execute_command = NULL;
 		prepare_namespace();
 	}
-- 
cgit v1.2.3


From 812931d693da58cc24d2bb8dec01c2b4a7f4668f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:14:19 +0200
Subject: init: add an init_link helper

Add a simple helper to link with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_link.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 33 +++++++++++++++++++++++++++++++++
 fs/internal.h                 |  3 +--
 fs/namei.c                    |  4 ++--
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/initramfs.c              |  2 +-
 6 files changed, 38 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 6d9af40d2897..5db9d9f74868 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -122,6 +122,39 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_link(const char *oldname, const char *newname)
+{
+	struct dentry *new_dentry;
+	struct path old_path, new_path;
+	int error;
+
+	error = kern_path(oldname, 0, &old_path);
+	if (error)
+		return error;
+
+	new_dentry = kern_path_create(AT_FDCWD, newname, &new_path, 0);
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry))
+		goto out;
+
+	error = -EXDEV;
+	if (old_path.mnt != new_path.mnt)
+		goto out_dput;
+	error = may_linkat(&old_path);
+	if (unlikely(error))
+		goto out_dput;
+	error = security_path_link(old_path.dentry, &new_path, new_dentry);
+	if (error)
+		goto out_dput;
+	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry,
+			 NULL);
+out_dput:
+	done_path_create(&new_path, new_dentry);
+out:
+	path_put(&old_path);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 6d82681c7d83..58451b033d26 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -69,8 +69,7 @@ long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname);
-int do_linkat(int olddfd, const char __user *oldname, int newdfd,
-	      const char __user *newname, int flags);
+int may_linkat(struct path *link);
 
 /*
  * namespace.c
diff --git a/fs/namei.c b/fs/namei.c
index d75a6039ae39..13de64c6be76 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1024,7 +1024,7 @@ static bool safe_hardlink_source(struct inode *inode)
  *
  * Returns 0 if successful, -ve on error.
  */
-static int may_linkat(struct path *link)
+int may_linkat(struct path *link)
 {
 	struct inode *inode = link->dentry->d_inode;
 
@@ -4086,7 +4086,7 @@ EXPORT_SYMBOL(vfs_link);
  * with linux 2.0, and to avoid hard-linking to directories
  * and other special files.  --ADM
  */
-int do_linkat(int olddfd, const char __user *oldname, int newdfd,
+static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
 	      const char __user *newname, int flags)
 {
 	struct dentry *new_dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 7031c0934bee..5ca15a5b55b7 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,5 +8,6 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_link(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a2779638e414..4b18b91ce465 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1295,15 +1295,6 @@ static inline long ksys_mknod(const char __user *filename, umode_t mode,
 	return do_mknodat(AT_FDCWD, filename, mode, dev);
 }
 
-extern int do_linkat(int olddfd, const char __user *oldname, int newdfd,
-		     const char __user *newname, int flags);
-
-static inline long ksys_link(const char __user *oldname,
-			     const char __user *newname)
-{
-	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/initramfs.c b/init/initramfs.c
index efa9fb70038d..516a66900d7a 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -312,7 +312,7 @@ static int __init maybe_link(void)
 		char *old = find_link(major, minor, ino, mode, collected);
 		if (old) {
 			clean_path(collected, 0);
-			return (ksys_link(old, collected) < 0) ? -1 : 1;
+			return (init_link(old, collected) < 0) ? -1 : 1;
 		}
 	}
 	return 0;
-- 
cgit v1.2.3


From cd3acb6a79349f346714ab3d26d203a0c6ca5ab0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:14:36 +0200
Subject: init: add an init_symlink helper

Add a simple helper to symlink with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_symlink.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 16 ++++++++++++++++
 fs/internal.h                 |  2 --
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/initramfs.c              |  2 +-
 6 files changed, 19 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 5db9d9f74868..09ef2b58d48c 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -155,6 +155,22 @@ out:
 	return error;
 }
 
+int __init init_symlink(const char *oldname, const char *newname)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	dentry = kern_path_create(AT_FDCWD, newname, &path, 0);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	error = security_path_symlink(&path, dentry, oldname);
+	if (!error)
+		error = vfs_symlink(path.dentry->d_inode, dentry, oldname);
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_unlink(const char *pathname)
 {
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 58451b033d26..40b50a222d7a 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -67,8 +67,6 @@ long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
-long do_symlinkat(const char __user *oldname, int newdfd,
-		  const char __user *newname);
 int may_linkat(struct path *link);
 
 /*
diff --git a/fs/namei.c b/fs/namei.c
index 13de64c6be76..2f6fa53eb3da 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3955,7 +3955,7 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-long do_symlinkat(const char __user *oldname, int newdfd,
+static long do_symlinkat(const char __user *oldname, int newdfd,
 		  const char __user *newname)
 {
 	int error;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 5ca15a5b55b7..125f55ae3f80 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -9,5 +9,6 @@ int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
 int __init init_link(const char *oldname, const char *newname);
+int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 4b18b91ce465..7cdc0d749a04 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1277,15 +1277,6 @@ static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
 	return do_mkdirat(AT_FDCWD, pathname, mode);
 }
 
-extern long do_symlinkat(const char __user *oldname, int newdfd,
-			 const char __user *newname);
-
-static inline long ksys_symlink(const char __user *oldname,
-				const char __user *newname)
-{
-	return do_symlinkat(oldname, AT_FDCWD, newname);
-}
-
 extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		       unsigned int dev);
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 516a66900d7a..c91fc9a51d2a 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -392,7 +392,7 @@ static int __init do_symlink(void)
 {
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
-	ksys_symlink(collected + N_ALIGN(name_len), collected);
+	init_symlink(collected + N_ALIGN(name_len), collected);
 	init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW);
 	do_utime(collected, mtime);
 	state = SkipIt;
-- 
cgit v1.2.3


From 83ff98c3e9cd2b82b4289e185f2ce7d635a9cbd3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:14:59 +0200
Subject: init: add an init_mkdir helper

Add a simple helper to mkdir with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_mkdir.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 18 ++++++++++++++++++
 fs/internal.h                 |  1 -
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  7 -------
 init/do_mounts_initrd.c       |  2 +-
 init/initramfs.c              |  2 +-
 init/noinitramfs.c            |  5 +++--
 8 files changed, 25 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 09ef2b58d48c..127033d08426 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -176,6 +176,24 @@ int __init init_unlink(const char *pathname)
 	return do_unlinkat(AT_FDCWD, getname_kernel(pathname));
 }
 
+int __init init_mkdir(const char *pathname, umode_t mode)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	dentry = kern_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mkdir(&path, dentry, mode);
+	if (!error)
+		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_rmdir(const char *pathname)
 {
 	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
diff --git a/fs/internal.h b/fs/internal.h
index 40b50a222d7a..4741e591e923 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -64,7 +64,6 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
 long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev);
-long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct path *link);
diff --git a/fs/namei.c b/fs/namei.c
index 2f6fa53eb3da..d6b25dd32f4d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3645,7 +3645,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
-long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
+static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 125f55ae3f80..d808985231f8 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -11,4 +11,5 @@ int __init init_eaccess(const char *filename);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
+int __init init_mkdir(const char *pathname, umode_t mode);
 int __init init_rmdir(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7cdc0d749a04..5ef77a91382a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1270,13 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode);
-
-static inline long ksys_mkdir(const char __user *pathname, umode_t mode)
-{
-	return do_mkdirat(AT_FDCWD, pathname, mode);
-}
-
 extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		       unsigned int dev);
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index a6b447b191db..3f5ac81913dd 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -81,7 +81,7 @@ static void __init handle_initrd(void)
 	create_dev("/dev/root.old", Root_RAM0);
 	/* mount initrd on rootfs' /root */
 	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
-	ksys_mkdir("/old", 0700);
+	init_mkdir("/old", 0700);
 	init_chdir("/old");
 
 	/*
diff --git a/init/initramfs.c b/init/initramfs.c
index c91fc9a51d2a..0489eb65b3b8 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -348,7 +348,7 @@ static int __init do_name(void)
 			state = CopyFile;
 		}
 	} else if (S_ISDIR(mode)) {
-		ksys_mkdir(collected, mode);
+		init_mkdir(collected, mode);
 		init_chown(collected, uid, gid, 0);
 		init_chmod(collected, mode);
 		dir_add(collected, mtime);
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index fa9cdfa7101d..94cc4df74b11 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -9,6 +9,7 @@
 #include <linux/stat.h>
 #include <linux/kdev_t.h>
 #include <linux/syscalls.h>
+#include <linux/init_syscalls.h>
 
 /*
  * Create a simple rootfs that is similar to the default initramfs
@@ -17,7 +18,7 @@ static int __init default_rootfs(void)
 {
 	int err;
 
-	err = ksys_mkdir((const char __user __force *) "/dev", 0755);
+	err = init_mkdir("/dev", 0755);
 	if (err < 0)
 		goto out;
 
@@ -27,7 +28,7 @@ static int __init default_rootfs(void)
 	if (err < 0)
 		goto out;
 
-	err = ksys_mkdir((const char __user __force *) "/root", 0700);
+	err = init_mkdir("/root", 0700);
 	if (err < 0)
 		goto out;
 
-- 
cgit v1.2.3


From 5fee64fcde0770c41e926ff981022eaa512d8980 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:41:20 +0200
Subject: init: add an init_mknod helper

Add a simple helper to mknod with a kernel space file name and switch
the early init code over to it.  Remove the now unused ksys_mknod.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 25 +++++++++++++++++++++++++
 fs/internal.h                 |  2 --
 fs/namei.c                    |  2 +-
 include/linux/init_syscalls.h |  1 +
 include/linux/syscalls.h      |  9 ---------
 init/do_mounts.h              |  2 +-
 init/initramfs.c              |  2 +-
 init/noinitramfs.c            |  3 +--
 8 files changed, 30 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 127033d08426..145fb31b7a5f 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -122,6 +122,31 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+
+	if (S_ISFIFO(mode) || S_ISSOCK(mode))
+		dev = 0;
+	else if (!(S_ISBLK(mode) || S_ISCHR(mode)))
+		return -EINVAL;
+
+	dentry = kern_path_create(AT_FDCWD, filename, &path, 0);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mknod(&path, dentry, mode, dev);
+	if (!error)
+		error = vfs_mknod(path.dentry->d_inode, dentry, mode,
+				  new_decode_dev(dev));
+	done_path_create(&path, dentry);
+	return error;
+}
+
 int __init init_link(const char *oldname, const char *newname)
 {
 	struct dentry *new_dentry;
diff --git a/fs/internal.h b/fs/internal.h
index 4741e591e923..07e145b2f88c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -62,8 +62,6 @@ extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
 			   struct path *path, struct path *root);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
-long do_mknodat(int dfd, const char __user *filename, umode_t mode,
-		unsigned int dev);
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct path *link);
diff --git a/fs/namei.c b/fs/namei.c
index d6b25dd32f4d..fde8fe086c09 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3564,7 +3564,7 @@ static int may_mknod(umode_t mode)
 	}
 }
 
-long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		unsigned int dev)
 {
 	struct dentry *dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index d808985231f8..fa1fe7a87779 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,6 +8,7 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_mknod(const char *filename, umode_t mode, unsigned int dev);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5ef77a91382a..63046c5e9fc5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1270,15 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second,
  * The following kernel syscall equivalents are just wrappers to fs-internal
  * functions. Therefore, provide stubs to be inlined at the callsites.
  */
-extern long do_mknodat(int dfd, const char __user *filename, umode_t mode,
-		       unsigned int dev);
-
-static inline long ksys_mknod(const char __user *filename, umode_t mode,
-			      unsigned int dev)
-{
-	return do_mknodat(AT_FDCWD, filename, mode, dev);
-}
-
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,
 		       gid_t group, int flag);
 
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 104d8431725a..7a29ac3e427b 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -17,7 +17,7 @@ extern int root_mountflags;
 static inline __init int create_dev(char *name, dev_t dev)
 {
 	init_unlink(name);
-	return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
+	return init_mknod(name, S_IFBLK | 0600, new_encode_dev(dev));
 }
 
 #ifdef CONFIG_BLK_DEV_RAM
diff --git a/init/initramfs.c b/init/initramfs.c
index 0489eb65b3b8..425addaf7c69 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -355,7 +355,7 @@ static int __init do_name(void)
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
-			ksys_mknod(collected, mode, rdev);
+			init_mknod(collected, mode, rdev);
 			init_chown(collected, uid, gid, 0);
 			init_chmod(collected, mode);
 			do_utime(collected, mtime);
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 94cc4df74b11..3d62b07f3bb9 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -22,8 +22,7 @@ static int __init default_rootfs(void)
 	if (err < 0)
 		goto out;
 
-	err = ksys_mknod((const char __user __force *) "/dev/console",
-			S_IFCHR | S_IRUSR | S_IWUSR,
+	err = init_mknod("/dev/console", S_IFCHR | S_IRUSR | S_IWUSR,
 			new_encode_dev(MKDEV(5, 1)));
 	if (err < 0)
 		goto out;
-- 
cgit v1.2.3


From 716308a5331bf907b819f9db8dc942b19568f925 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 22 Jul 2020 11:15:40 +0200
Subject: init: add an init_stat helper

Add a simple helper to stat with a kernel space file name and switch
the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/md/md-autodetect.c    |  3 ++-
 fs/init.c                     | 15 +++++++++++++++
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  3 ++-
 4 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 14b6e86814c0..6bbec89976a7 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -5,6 +5,7 @@
 #include <linux/mount.h>
 #include <linux/major.h>
 #include <linux/delay.h>
+#include <linux/init_syscalls.h>
 #include <linux/raid/detect.h>
 #include <linux/raid/md_u.h>
 #include <linux/raid/md_p.h>
@@ -151,7 +152,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 		if (strncmp(devname, "/dev/", 5) == 0)
 			devname += 5;
 		snprintf(comp_name, 63, "/dev/%s", devname);
-		if (vfs_stat(comp_name, &stat) == 0 && S_ISBLK(stat.mode))
+		if (init_stat(comp_name, &stat, 0) == 0 && S_ISBLK(stat.mode))
 			dev = new_decode_dev(stat.rdev);
 		if (!dev) {
 			pr_warn("md: Unknown device name: %s\n", devname);
diff --git a/fs/init.c b/fs/init.c
index 145fb31b7a5f..51646ba38099 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -122,6 +122,21 @@ int __init init_eaccess(const char *filename)
 	return error;
 }
 
+int __init init_stat(const char *filename, struct kstat *stat, int flags)
+{
+	int lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	error = kern_path(filename, lookup_flags, &path);
+	if (error)
+		return error;
+	error = vfs_getattr(&path, stat, STATX_BASIC_STATS,
+			    flags | AT_NO_AUTOMOUNT);
+	path_put(&path);
+	return error;
+}
+
 int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
 {
 	struct dentry *dentry;
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index fa1fe7a87779..b2fda50daca6 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -8,6 +8,7 @@ int __init init_chroot(const char *filename);
 int __init init_chown(const char *filename, uid_t user, gid_t group, int flags);
 int __init init_chmod(const char *filename, umode_t mode);
 int __init init_eaccess(const char *filename);
+int __init init_stat(const char *filename, struct kstat *stat, int flags);
 int __init init_mknod(const char *filename, umode_t mode, unsigned int dev);
 int __init init_link(const char *oldname, const char *newname);
 int __init init_symlink(const char *oldname, const char *newname);
diff --git a/init/initramfs.c b/init/initramfs.c
index 425addaf7c69..744e111baba4 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -298,7 +298,8 @@ static void __init clean_path(char *path, umode_t fmode)
 {
 	struct kstat st;
 
-	if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) {
+	if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
+	    (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
 			init_rmdir(path);
 		else
-- 
cgit v1.2.3


From 235e57935bf328c4cce371ffc4dd1d8fab4885cd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 21 Jul 2020 16:05:31 +0200
Subject: init: add an init_utimes helper

Add a simple helper to set timestamps with a kernel space file name and
switch the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/init.c                     | 13 +++++++++++++
 include/linux/init_syscalls.h |  1 +
 init/initramfs.c              |  3 +--
 3 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index 51646ba38099..db5c48a85644 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -238,3 +238,16 @@ int __init init_rmdir(const char *pathname)
 {
 	return do_rmdir(AT_FDCWD, getname_kernel(pathname));
 }
+
+int __init init_utimes(char *filename, struct timespec64 *ts)
+{
+	struct path path;
+	int error;
+
+	error = kern_path(filename, 0, &path);
+	if (error)
+		return error;
+	error = vfs_utimes(&path, ts);
+	path_put(&path);
+	return error;
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index b2fda50daca6..3654b525ac0b 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -15,3 +15,4 @@ int __init init_symlink(const char *oldname, const char *newname);
 int __init init_unlink(const char *pathname);
 int __init init_mkdir(const char *pathname, umode_t mode);
 int __init init_rmdir(const char *pathname);
+int __init init_utimes(char *filename, struct timespec64 *ts);
diff --git a/init/initramfs.c b/init/initramfs.c
index 744e111baba4..e6dbfb767057 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -111,8 +111,7 @@ static long __init do_utime(char *filename, time64_t mtime)
 	t[0].tv_nsec = 0;
 	t[1].tv_sec = mtime;
 	t[1].tv_nsec = 0;
-
-	return do_utimes(AT_FDCWD, filename, t, AT_SYMLINK_NOFOLLOW);
+	return init_utimes(filename, t);
 }
 
 static __initdata LIST_HEAD(dir_list);
-- 
cgit v1.2.3


From 4278e9d99e38938a7611b927fa4d73e6c86cb4fc Mon Sep 17 00:00:00 2001
From: Marcelo Henrique Cerri <marcelo.cerri@canonical.com>
Date: Mon, 20 Jul 2020 19:08:09 +0200
Subject: lib/mpi: Add mpi_sub_ui()

Add mpi_sub_ui() based on Gnu MP mpz_sub_ui() function from file
mpz/aors_ui.h[1] from change id 510b83519d1c adapting the code to the
kernel's data structures, helper functions and coding style and also
removing the defines used to produce mpz_sub_ui() and mpz_add_ui()
from the same code.

[1] https://gmplib.org/repo/gmp-6.2/file/510b83519d1c/mpz/aors.h

Signed-off-by: Marcelo Henrique Cerri <marcelo.cerri@canonical.com>
Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/mpi.h  |  3 ++
 lib/mpi/Makefile     |  1 +
 lib/mpi/mpi-sub-ui.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 82 insertions(+)
 create mode 100644 lib/mpi/mpi-sub-ui.c

(limited to 'include/linux')

diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 7bd6d8af0004..5d906dfbf3ed 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -63,6 +63,9 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
 int mpi_cmp_ui(MPI u, ulong v);
 int mpi_cmp(MPI u, MPI v);
 
+/*-- mpi-sub-ui.c --*/
+int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
+
 /*-- mpi-bit.c --*/
 void mpi_normalize(MPI a);
 unsigned mpi_get_nbits(MPI a);
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index d5874a7f5ff9..43b8fce14079 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -16,6 +16,7 @@ mpi-y = \
 	mpicoder.o			\
 	mpi-bit.o			\
 	mpi-cmp.o			\
+	mpi-sub-ui.o			\
 	mpih-cmp.o			\
 	mpih-div.o			\
 	mpih-mul.o			\
diff --git a/lib/mpi/mpi-sub-ui.c b/lib/mpi/mpi-sub-ui.c
new file mode 100644
index 000000000000..b41b082b5f3e
--- /dev/null
+++ b/lib/mpi/mpi-sub-ui.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* mpi-sub-ui.c - Subtract an unsigned integer from an MPI.
+ *
+ * Copyright 1991, 1993, 1994, 1996, 1999-2002, 2004, 2012, 2013, 2015
+ * Free Software Foundation, Inc.
+ *
+ * This file was based on the GNU MP Library source file:
+ * https://gmplib.org/repo/gmp-6.2/file/510b83519d1c/mpz/aors_ui.h
+ *
+ * The GNU MP Library is free software; you can redistribute it and/or modify
+ * it under the terms of either:
+ *
+ *   * the GNU Lesser General Public License as published by the Free
+ *     Software Foundation; either version 3 of the License, or (at your
+ *     option) any later version.
+ *
+ * or
+ *
+ *   * the GNU General Public License as published by the Free Software
+ *     Foundation; either version 2 of the License, or (at your option) any
+ *     later version.
+ *
+ * or both in parallel, as here.
+ *
+ * The GNU MP Library is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received copies of the GNU General Public License and the
+ * GNU Lesser General Public License along with the GNU MP Library.  If not,
+ * see https://www.gnu.org/licenses/.
+ */
+
+#include "mpi-internal.h"
+
+int mpi_sub_ui(MPI w, MPI u, unsigned long vval)
+{
+	if (u->nlimbs == 0) {
+		if (mpi_resize(w, 1) < 0)
+			return -ENOMEM;
+		w->d[0] = vval;
+		w->nlimbs = (vval != 0);
+		w->sign = (vval != 0);
+		return 0;
+	}
+
+	/* If not space for W (and possible carry), increase space. */
+	if (mpi_resize(w, u->nlimbs + 1))
+		return -ENOMEM;
+
+	if (u->sign) {
+		mpi_limb_t cy;
+
+		cy = mpihelp_add_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+		w->d[u->nlimbs] = cy;
+		w->nlimbs = u->nlimbs + cy;
+		w->sign = 1;
+	} else {
+		/* The signs are different.  Need exact comparison to determine
+		 * which operand to subtract from which.
+		 */
+		if (u->nlimbs == 1 && u->d[0] < vval) {
+			w->d[0] = vval - u->d[0];
+			w->nlimbs = 1;
+			w->sign = 1;
+		} else {
+			mpihelp_sub_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+			/* Size can decrease with at most one limb. */
+			w->nlimbs = (u->nlimbs - (w->d[u->nlimbs - 1] == 0));
+			w->sign = 0;
+		}
+	}
+
+	mpi_normalize(w);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_sub_ui);
-- 
cgit v1.2.3


From 4963bb2b89884bbdb7e33e6a09c159551e9627aa Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Thu, 30 Jul 2020 12:08:35 -0700
Subject: lib: Add zstd support to decompress

- Add unzstd() and the zstd decompress interface.

- Add zstd support to decompress_method().

The decompress_method() and unzstd() functions are used to decompress
the initramfs and the initrd. The __decompress() function is used in
the preboot environment to decompress a zstd compressed kernel.

The zstd decompression function allows the input and output buffers to
overlap because that is used by x86 kernel decompression.

Signed-off-by: Nick Terrell <terrelln@fb.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200730190841.2071656-3-nickrterrell@gmail.com
---
 include/linux/decompress/unzstd.h |  11 ++
 lib/Kconfig                       |   4 +
 lib/Makefile                      |   1 +
 lib/decompress.c                  |   5 +
 lib/decompress_unzstd.c           | 345 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 366 insertions(+)
 create mode 100644 include/linux/decompress/unzstd.h
 create mode 100644 lib/decompress_unzstd.c

(limited to 'include/linux')

diff --git a/include/linux/decompress/unzstd.h b/include/linux/decompress/unzstd.h
new file mode 100644
index 000000000000..56d539ae880f
--- /dev/null
+++ b/include/linux/decompress/unzstd.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_DECOMPRESS_UNZSTD_H
+#define LINUX_DECOMPRESS_UNZSTD_H
+
+int unzstd(unsigned char *inbuf, long len,
+	   long (*fill)(void*, unsigned long),
+	   long (*flush)(void*, unsigned long),
+	   unsigned char *output,
+	   long *pos,
+	   void (*error_fn)(char *x));
+#endif
diff --git a/lib/Kconfig b/lib/Kconfig
index df3f3da95990..a5d6f23c4cab 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,6 +342,10 @@ config DECOMPRESS_LZ4
 	select LZ4_DECOMPRESS
 	tristate
 
+config DECOMPRESS_ZSTD
+	select ZSTD_DECOMPRESS
+	tristate
+
 #
 # Generic allocator support is selected if needed
 #
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..2ba9642a3a87 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -170,6 +170,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
 lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
 lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
 lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
+lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o
 obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
diff --git a/lib/decompress.c b/lib/decompress.c
index 857ab1af1ef3..ab3fc90ffc64 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/decompress/inflate.h>
 #include <linux/decompress/unlzo.h>
 #include <linux/decompress/unlz4.h>
+#include <linux/decompress/unzstd.h>
 
 #include <linux/types.h>
 #include <linux/string.h>
@@ -37,6 +38,9 @@
 #ifndef CONFIG_DECOMPRESS_LZ4
 # define unlz4 NULL
 #endif
+#ifndef CONFIG_DECOMPRESS_ZSTD
+# define unzstd NULL
+#endif
 
 struct compress_format {
 	unsigned char magic[2];
@@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = {
 	{ {0xfd, 0x37}, "xz", unxz },
 	{ {0x89, 0x4c}, "lzo", unlzo },
 	{ {0x02, 0x21}, "lz4", unlz4 },
+	{ {0x28, 0xb5}, "zstd", unzstd },
 	{ {0, 0}, NULL, NULL }
 };
 
diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c
new file mode 100644
index 000000000000..0ad2c15479ed
--- /dev/null
+++ b/lib/decompress_unzstd.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Important notes about in-place decompression
+ *
+ * At least on x86, the kernel is decompressed in place: the compressed data
+ * is placed to the end of the output buffer, and the decompressor overwrites
+ * most of the compressed data. There must be enough safety margin to
+ * guarantee that the write position is always behind the read position.
+ *
+ * The safety margin for ZSTD with a 128 KB block size is calculated below.
+ * Note that the margin with ZSTD is bigger than with GZIP or XZ!
+ *
+ * The worst case for in-place decompression is that the beginning of
+ * the file is compressed extremely well, and the rest of the file is
+ * uncompressible. Thus, we must look for worst-case expansion when the
+ * compressor is encoding uncompressible data.
+ *
+ * The structure of the .zst file in case of a compresed kernel is as follows.
+ * Maximum sizes (as bytes) of the fields are in parenthesis.
+ *
+ *    Frame Header: (18)
+ *    Blocks: (N)
+ *    Checksum: (4)
+ *
+ * The frame header and checksum overhead is at most 22 bytes.
+ *
+ * ZSTD stores the data in blocks. Each block has a header whose size is
+ * a 3 bytes. After the block header, there is up to 128 KB of payload.
+ * The maximum uncompressed size of the payload is 128 KB. The minimum
+ * uncompressed size of the payload is never less than the payload size
+ * (excluding the block header).
+ *
+ * The assumption, that the uncompressed size of the payload is never
+ * smaller than the payload itself, is valid only when talking about
+ * the payload as a whole. It is possible that the payload has parts where
+ * the decompressor consumes more input than it produces output. Calculating
+ * the worst case for this would be tricky. Instead of trying to do that,
+ * let's simply make sure that the decompressor never overwrites any bytes
+ * of the payload which it is currently reading.
+ *
+ * Now we have enough information to calculate the safety margin. We need
+ *   - 22 bytes for the .zst file format headers;
+ *   - 3 bytes per every 128 KiB of uncompressed size (one block header per
+ *     block); and
+ *   - 128 KiB (biggest possible zstd block size) to make sure that the
+ *     decompressor never overwrites anything from the block it is currently
+ *     reading.
+ *
+ * We get the following formula:
+ *
+ *    safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072
+ *                 <= 22 + (uncompressed_size >> 15) + 131072
+ */
+
+/*
+ * Preboot environments #include "path/to/decompress_unzstd.c".
+ * All of the source files we depend on must be #included.
+ * zstd's only source dependeny is xxhash, which has no source
+ * dependencies.
+ *
+ * When UNZSTD_PREBOOT is defined we declare __decompress(), which is
+ * used for kernel decompression, instead of unzstd().
+ *
+ * Define __DISABLE_EXPORTS in preboot environments to prevent symbols
+ * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro.
+ */
+#ifdef STATIC
+# define UNZSTD_PREBOOT
+# include "xxhash.c"
+# include "zstd/entropy_common.c"
+# include "zstd/fse_decompress.c"
+# include "zstd/huf_decompress.c"
+# include "zstd/zstd_common.c"
+# include "zstd/decompress.c"
+#endif
+
+#include <linux/decompress/mm.h>
+#include <linux/kernel.h>
+#include <linux/zstd.h>
+
+/* 128MB is the maximum window size supported by zstd. */
+#define ZSTD_WINDOWSIZE_MAX	(1 << ZSTD_WINDOWLOG_MAX)
+/*
+ * Size of the input and output buffers in multi-call mode.
+ * Pick a larger size because it isn't used during kernel decompression,
+ * since that is single pass, and we have to allocate a large buffer for
+ * zstd's window anyway. The larger size speeds up initramfs decompression.
+ */
+#define ZSTD_IOBUF_SIZE		(1 << 17)
+
+static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
+{
+	const int err = ZSTD_getErrorCode(ret);
+
+	if (!ZSTD_isError(ret))
+		return 0;
+
+	switch (err) {
+	case ZSTD_error_memory_allocation:
+		error("ZSTD decompressor ran out of memory");
+		break;
+	case ZSTD_error_prefix_unknown:
+		error("Input is not in the ZSTD format (wrong magic bytes)");
+		break;
+	case ZSTD_error_dstSize_tooSmall:
+	case ZSTD_error_corruption_detected:
+	case ZSTD_error_checksum_wrong:
+		error("ZSTD-compressed data is corrupt");
+		break;
+	default:
+		error("ZSTD-compressed data is probably corrupt");
+		break;
+	}
+	return -1;
+}
+
+/*
+ * Handle the case where we have the entire input and output in one segment.
+ * We can allocate less memory (no circular buffer for the sliding window),
+ * and avoid some memcpy() calls.
+ */
+static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf,
+				  long out_len, long *in_pos,
+				  void (*error)(char *x))
+{
+	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+	void *wksp = large_malloc(wksp_size);
+	ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size);
+	int err;
+	size_t ret;
+
+	if (dctx == NULL) {
+		error("Out of memory while allocating ZSTD_DCtx");
+		err = -1;
+		goto out;
+	}
+	/*
+	 * Find out how large the frame actually is, there may be junk at
+	 * the end of the frame that ZSTD_decompressDCtx() can't handle.
+	 */
+	ret = ZSTD_findFrameCompressedSize(in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	in_len = (long)ret;
+
+	ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+
+	if (in_pos != NULL)
+		*in_pos = in_len;
+
+	err = 0;
+out:
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+static int INIT __unzstd(unsigned char *in_buf, long in_len,
+			 long (*fill)(void*, unsigned long),
+			 long (*flush)(void*, unsigned long),
+			 unsigned char *out_buf, long out_len,
+			 long *in_pos,
+			 void (*error)(char *x))
+{
+	ZSTD_inBuffer in;
+	ZSTD_outBuffer out;
+	ZSTD_frameParams params;
+	void *in_allocated = NULL;
+	void *out_allocated = NULL;
+	void *wksp = NULL;
+	size_t wksp_size;
+	ZSTD_DStream *dstream;
+	int err;
+	size_t ret;
+
+	if (out_len == 0)
+		out_len = LONG_MAX; /* no limit */
+
+	if (fill == NULL && flush == NULL)
+		/*
+		 * We can decompress faster and with less memory when we have a
+		 * single chunk.
+		 */
+		return decompress_single(in_buf, in_len, out_buf, out_len,
+					 in_pos, error);
+
+	/*
+	 * If in_buf is not provided, we must be using fill(), so allocate
+	 * a large enough buffer. If it is provided, it must be at least
+	 * ZSTD_IOBUF_SIZE large.
+	 */
+	if (in_buf == NULL) {
+		in_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (in_allocated == NULL) {
+			error("Out of memory while allocating input buffer");
+			err = -1;
+			goto out;
+		}
+		in_buf = in_allocated;
+		in_len = 0;
+	}
+	/* Read the first chunk, since we need to decode the frame header. */
+	if (fill != NULL)
+		in_len = fill(in_buf, ZSTD_IOBUF_SIZE);
+	if (in_len < 0) {
+		error("ZSTD-compressed data is truncated");
+		err = -1;
+		goto out;
+	}
+	/* Set the first non-empty input buffer. */
+	in.src = in_buf;
+	in.pos = 0;
+	in.size = in_len;
+	/* Allocate the output buffer if we are using flush(). */
+	if (flush != NULL) {
+		out_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (out_allocated == NULL) {
+			error("Out of memory while allocating output buffer");
+			err = -1;
+			goto out;
+		}
+		out_buf = out_allocated;
+		out_len = ZSTD_IOBUF_SIZE;
+	}
+	/* Set the output buffer. */
+	out.dst = out_buf;
+	out.pos = 0;
+	out.size = out_len;
+
+	/*
+	 * We need to know the window size to allocate the ZSTD_DStream.
+	 * Since we are streaming, we need to allocate a buffer for the sliding
+	 * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX
+	 * (8 MB), so it is important to use the actual value so as not to
+	 * waste memory when it is smaller.
+	 */
+	ret = ZSTD_getFrameParams(&params, in.src, in.size);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	if (ret != 0) {
+		error("ZSTD-compressed data has an incomplete frame header");
+		err = -1;
+		goto out;
+	}
+	if (params.windowSize > ZSTD_WINDOWSIZE_MAX) {
+		error("ZSTD-compressed data has too large a window size");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Allocate the ZSTD_DStream now that we know how much memory is
+	 * required.
+	 */
+	wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize);
+	wksp = large_malloc(wksp_size);
+	dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size);
+	if (dstream == NULL) {
+		error("Out of memory while allocating ZSTD_DStream");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Decompression loop:
+	 * Read more data if necessary (error if no more data can be read).
+	 * Call the decompression function, which returns 0 when finished.
+	 * Flush any data produced if using flush().
+	 */
+	if (in_pos != NULL)
+		*in_pos = 0;
+	do {
+		/*
+		 * If we need to reload data, either we have fill() and can
+		 * try to get more data, or we don't and the input is truncated.
+		 */
+		if (in.pos == in.size) {
+			if (in_pos != NULL)
+				*in_pos += in.pos;
+			in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1;
+			if (in_len < 0) {
+				error("ZSTD-compressed data is truncated");
+				err = -1;
+				goto out;
+			}
+			in.pos = 0;
+			in.size = in_len;
+		}
+		/* Returns zero when the frame is complete. */
+		ret = ZSTD_decompressStream(dstream, &out, &in);
+		err = handle_zstd_error(ret, error);
+		if (err)
+			goto out;
+		/* Flush all of the data produced if using flush(). */
+		if (flush != NULL && out.pos > 0) {
+			if (out.pos != flush(out.dst, out.pos)) {
+				error("Failed to flush()");
+				err = -1;
+				goto out;
+			}
+			out.pos = 0;
+		}
+	} while (ret != 0);
+
+	if (in_pos != NULL)
+		*in_pos += in.pos;
+
+	err = 0;
+out:
+	if (in_allocated != NULL)
+		large_free(in_allocated);
+	if (out_allocated != NULL)
+		large_free(out_allocated);
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+#ifndef UNZSTD_PREBOOT
+STATIC int INIT unzstd(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf,
+		       long *pos,
+		       void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error);
+}
+#else
+STATIC int INIT __decompress(unsigned char *buf, long len,
+			     long (*fill)(void*, unsigned long),
+			     long (*flush)(void*, unsigned long),
+			     unsigned char *out_buf, long out_len,
+			     long *pos,
+			     void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error);
+}
+#endif
-- 
cgit v1.2.3


From 0584df9c12f449124d0bfef9899e5365604ee7a9 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Wed, 29 Jul 2020 13:09:15 +0200
Subject: lockdep: Refactor IRQ trace events fields into struct

Refactor the IRQ trace events fields, used for printing information
about the IRQ trace events, into a separate struct 'irqtrace_events'.

This improves readability by separating the information only used in
reporting, as well as enables (simplified) storing/restoring of
irqtrace_events snapshots.

No functional change intended.

Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200729110916.3920464-1-elver@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/irqflags.h | 13 +++++++++++
 include/linux/sched.h    | 11 ++-------
 kernel/fork.c            | 16 +++++--------
 kernel/locking/lockdep.c | 58 +++++++++++++++++++++++++-----------------------
 4 files changed, 50 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 5811ee8a5cd8..bd5c55755447 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -33,6 +33,19 @@
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 
+/* Per-task IRQ trace events information. */
+struct irqtrace_events {
+	unsigned int	irq_events;
+	unsigned long	hardirq_enable_ip;
+	unsigned long	hardirq_disable_ip;
+	unsigned int	hardirq_enable_event;
+	unsigned int	hardirq_disable_event;
+	unsigned long	softirq_disable_ip;
+	unsigned long	softirq_enable_ip;
+	unsigned int	softirq_disable_event;
+	unsigned int	softirq_enable_event;
+};
+
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8d1de021b315..52e0fdd6a555 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -18,6 +18,7 @@
 #include <linux/mutex.h>
 #include <linux/plist.h>
 #include <linux/hrtimer.h>
+#include <linux/irqflags.h>
 #include <linux/seccomp.h>
 #include <linux/nodemask.h>
 #include <linux/rcupdate.h>
@@ -980,17 +981,9 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-	unsigned int			irq_events;
+	struct irqtrace_events		irqtrace;
 	unsigned int			hardirq_threaded;
-	unsigned long			hardirq_enable_ip;
-	unsigned long			hardirq_disable_ip;
-	unsigned int			hardirq_enable_event;
-	unsigned int			hardirq_disable_event;
 	u64				hardirq_chain_key;
-	unsigned long			softirq_disable_ip;
-	unsigned long			softirq_enable_ip;
-	unsigned int			softirq_disable_event;
-	unsigned int			softirq_enable_event;
 	int				softirqs_enabled;
 	int				softirq_context;
 	int				irq_config;
diff --git a/kernel/fork.c b/kernel/fork.c
index 70d9d0a4de2a..56a640799680 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2035,17 +2035,11 @@ static __latent_entropy struct task_struct *copy_process(
 	seqcount_init(&p->mems_allowed_seq);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
-	p->irq_events = 0;
-	p->hardirq_enable_ip = 0;
-	p->hardirq_enable_event = 0;
-	p->hardirq_disable_ip = _THIS_IP_;
-	p->hardirq_disable_event = 0;
-	p->softirqs_enabled = 1;
-	p->softirq_enable_ip = _THIS_IP_;
-	p->softirq_enable_event = 0;
-	p->softirq_disable_ip = 0;
-	p->softirq_disable_event = 0;
-	p->softirq_context = 0;
+	memset(&p->irqtrace, 0, sizeof(p->irqtrace));
+	p->irqtrace.hardirq_disable_ip	= _THIS_IP_;
+	p->irqtrace.softirq_enable_ip	= _THIS_IP_;
+	p->softirqs_enabled		= 1;
+	p->softirq_context		= 0;
 #endif
 
 	p->pagefault_disabled = 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c9ea05edce25..7b5800374c40 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3484,19 +3484,21 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
 void print_irqtrace_events(struct task_struct *curr)
 {
-	printk("irq event stamp: %u\n", curr->irq_events);
+	const struct irqtrace_events *trace = &curr->irqtrace;
+
+	printk("irq event stamp: %u\n", trace->irq_events);
 	printk("hardirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip,
-		(void *)curr->hardirq_enable_ip);
+		trace->hardirq_enable_event, (void *)trace->hardirq_enable_ip,
+		(void *)trace->hardirq_enable_ip);
 	printk("hardirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip,
-		(void *)curr->hardirq_disable_ip);
+		trace->hardirq_disable_event, (void *)trace->hardirq_disable_ip,
+		(void *)trace->hardirq_disable_ip);
 	printk("softirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->softirq_enable_event, (void *)curr->softirq_enable_ip,
-		(void *)curr->softirq_enable_ip);
+		trace->softirq_enable_event, (void *)trace->softirq_enable_ip,
+		(void *)trace->softirq_enable_ip);
 	printk("softirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->softirq_disable_event, (void *)curr->softirq_disable_ip,
-		(void *)curr->softirq_disable_ip);
+		trace->softirq_disable_event, (void *)trace->softirq_disable_ip,
+		(void *)trace->softirq_disable_ip);
 }
 
 static int HARDIRQ_verbose(struct lock_class *class)
@@ -3699,7 +3701,7 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
 
 void noinstr lockdep_hardirqs_on(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	struct irqtrace_events *trace = &current->irqtrace;
 
 	if (unlikely(!debug_locks))
 		return;
@@ -3752,8 +3754,8 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 skip_checks:
 	/* we'll do an OFF -> ON transition: */
 	this_cpu_write(hardirqs_enabled, 1);
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
+	trace->hardirq_enable_ip = ip;
+	trace->hardirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(hardirqs_on_events);
 }
 EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
@@ -3763,8 +3765,6 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
  */
 void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
-
 	if (unlikely(!debug_locks))
 		return;
 
@@ -3784,12 +3784,14 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 		return;
 
 	if (lockdep_hardirqs_enabled()) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
 		this_cpu_write(hardirqs_enabled, 0);
-		curr->hardirq_disable_ip = ip;
-		curr->hardirq_disable_event = ++curr->irq_events;
+		trace->hardirq_disable_ip = ip;
+		trace->hardirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
 	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
@@ -3802,7 +3804,7 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
  */
 void lockdep_softirqs_on(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	struct irqtrace_events *trace = &current->irqtrace;
 
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3814,7 +3816,7 @@ void lockdep_softirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
 		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
@@ -3823,9 +3825,9 @@ void lockdep_softirqs_on(unsigned long ip)
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
-	curr->softirqs_enabled = 1;
-	curr->softirq_enable_ip = ip;
-	curr->softirq_enable_event = ++curr->irq_events;
+	current->softirqs_enabled = 1;
+	trace->softirq_enable_ip = ip;
+	trace->softirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
@@ -3833,7 +3835,7 @@ void lockdep_softirqs_on(unsigned long ip)
 	 * enabled too:
 	 */
 	if (lockdep_hardirqs_enabled())
-		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
+		mark_held_locks(current, LOCK_ENABLED_SOFTIRQ);
 	lockdep_recursion_finish();
 }
 
@@ -3842,8 +3844,6 @@ void lockdep_softirqs_on(unsigned long ip)
  */
 void lockdep_softirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
-
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
@@ -3853,13 +3853,15 @@ void lockdep_softirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->softirqs_enabled = 0;
-		curr->softirq_disable_ip = ip;
-		curr->softirq_disable_event = ++curr->irq_events;
+		current->softirqs_enabled = 0;
+		trace->softirq_disable_ip = ip;
+		trace->softirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(softirqs_off_events);
 		/*
 		 * Whoops, we wanted softirqs off, so why aren't they?
-- 
cgit v1.2.3


From 92c209ac6d3d35783c16c8a717547183e6e11162 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Wed, 29 Jul 2020 13:09:16 +0200
Subject: kcsan: Improve IRQ state trace reporting

To improve the general usefulness of the IRQ state trace events with
KCSAN enabled, save and restore the trace information when entering and
exiting the KCSAN runtime as well as when generating a KCSAN report.

Without this, reporting the IRQ trace events (whether via a KCSAN report
or outside of KCSAN via a lockdep report) is rather useless due to
continuously being touched by KCSAN. This is because if KCSAN is
enabled, every instrumented memory access causes changes to IRQ trace
events (either by KCSAN disabling/enabling interrupts or taking
report_lock when generating a report).

Before "lockdep: Prepare for NMI IRQ state tracking", KCSAN avoided
touching the IRQ trace events via raw_local_irq_save/restore() and
lockdep_off/on().

Fixes: 248591f5d257 ("kcsan: Make KCSAN compatible with new IRQ state tracking")
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200729110916.3920464-2-elver@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  4 ++++
 kernel/kcsan/core.c   | 23 +++++++++++++++++++++++
 kernel/kcsan/kcsan.h  |  7 +++++++
 kernel/kcsan/report.c |  3 +++
 4 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 52e0fdd6a555..060e9214c8b5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1184,8 +1184,12 @@ struct task_struct {
 #ifdef CONFIG_KASAN
 	unsigned int			kasan_depth;
 #endif
+
 #ifdef CONFIG_KCSAN
 	struct kcsan_ctx		kcsan_ctx;
+#ifdef CONFIG_TRACE_IRQFLAGS
+	struct irqtrace_events		kcsan_save_irqtrace;
+#endif
 #endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 732623c30359..0fe068192781 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -291,6 +291,20 @@ static inline unsigned int get_delay(void)
 				0);
 }
 
+void kcsan_save_irqtrace(struct task_struct *task)
+{
+#ifdef CONFIG_TRACE_IRQFLAGS
+	task->kcsan_save_irqtrace = task->irqtrace;
+#endif
+}
+
+void kcsan_restore_irqtrace(struct task_struct *task)
+{
+#ifdef CONFIG_TRACE_IRQFLAGS
+	task->irqtrace = task->kcsan_save_irqtrace;
+#endif
+}
+
 /*
  * Pull everything together: check_access() below contains the performance
  * critical operations; the fast-path (including check_access) functions should
@@ -336,9 +350,11 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr,
 	flags = user_access_save();
 
 	if (consumed) {
+		kcsan_save_irqtrace(current);
 		kcsan_report(ptr, size, type, KCSAN_VALUE_CHANGE_MAYBE,
 			     KCSAN_REPORT_CONSUMED_WATCHPOINT,
 			     watchpoint - watchpoints);
+		kcsan_restore_irqtrace(current);
 	} else {
 		/*
 		 * The other thread may not print any diagnostics, as it has
@@ -396,6 +412,12 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 		goto out;
 	}
 
+	/*
+	 * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's
+	 * runtime is entered for every memory access, and potentially useful
+	 * information is lost if dirtied by KCSAN.
+	 */
+	kcsan_save_irqtrace(current);
 	if (!kcsan_interrupt_watcher)
 		local_irq_save(irq_flags);
 
@@ -539,6 +561,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 out_unlock:
 	if (!kcsan_interrupt_watcher)
 		local_irq_restore(irq_flags);
+	kcsan_restore_irqtrace(current);
 out:
 	user_access_restore(ua_flags);
 }
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
index 763d6d08d94b..29480010dc30 100644
--- a/kernel/kcsan/kcsan.h
+++ b/kernel/kcsan/kcsan.h
@@ -9,6 +9,7 @@
 #define _KERNEL_KCSAN_KCSAN_H
 
 #include <linux/kcsan.h>
+#include <linux/sched.h>
 
 /* The number of adjacent watchpoints to check. */
 #define KCSAN_CHECK_ADJACENT 1
@@ -22,6 +23,12 @@ extern unsigned int kcsan_udelay_interrupt;
  */
 extern bool kcsan_enabled;
 
+/*
+ * Save/restore IRQ flags state trace dirtied by KCSAN.
+ */
+void kcsan_save_irqtrace(struct task_struct *task);
+void kcsan_restore_irqtrace(struct task_struct *task);
+
 /*
  * Initialize debugfs file.
  */
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index 6b2fb1a6d8cd..9d07e175de0f 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -308,6 +308,9 @@ static void print_verbose_info(struct task_struct *task)
 	if (!task)
 		return;
 
+	/* Restore IRQ state trace for printing. */
+	kcsan_restore_irqtrace(task);
+
 	pr_err("\n");
 	debug_show_held_locks(task);
 	print_irqtrace_events(task);
-- 
cgit v1.2.3


From 46cbd0b05799e8234b719d18f3a4b27679c4c92e Mon Sep 17 00:00:00 2001
From: Crag Wang <crag0715@gmail.com>
Date: Thu, 30 Jul 2020 11:26:09 +0800
Subject: power: supply: wilco_ec: Add long life charging mode

This is a long life mode set in the factory for extended warranty
battery, the power charging rate is customized so that battery at
work last longer.

Presently switching to a different battery charging mode is through
EC PID 0x0710 to configure the battery firmware, this operation will
be blocked by EC with failure code 0x01 when PLL mode is already
in use.

Signed-off-by: Crag Wang <crag.wang@dell.com>
Reviewed-by: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 Documentation/ABI/testing/sysfs-class-power-wilco | 4 ++++
 drivers/power/supply/power_supply_sysfs.c         | 1 +
 drivers/power/supply/wilco-charger.c              | 5 +++++
 include/linux/power_supply.h                      | 1 +
 4 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-power-wilco b/Documentation/ABI/testing/sysfs-class-power-wilco
index da1d6ffe5e3c..84fde1d0ada0 100644
--- a/Documentation/ABI/testing/sysfs-class-power-wilco
+++ b/Documentation/ABI/testing/sysfs-class-power-wilco
@@ -14,6 +14,10 @@ Description:
 			Charging begins when level drops below
 			charge_control_start_threshold, and ceases when
 			level is above charge_control_end_threshold.
+		Long Life: Customized charge rate for last longer battery life.
+			On Wilco device this mode is pre-configured in the factory
+			through EC's private PID. Swiching to a different mode will
+			be denied by Wilco EC when Long Life mode is enabled.
 
 What:		/sys/class/power_supply/wilco-charger/charge_control_start_threshold
 Date:		April 2019
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index b903cb4dca2b..3d383086018c 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -87,6 +87,7 @@ static const char * const POWER_SUPPLY_CHARGE_TYPE_TEXT[] = {
 	[POWER_SUPPLY_CHARGE_TYPE_STANDARD]	= "Standard",
 	[POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE]	= "Adaptive",
 	[POWER_SUPPLY_CHARGE_TYPE_CUSTOM]	= "Custom",
+	[POWER_SUPPLY_CHARGE_TYPE_LONGLIFE]	= "Long Life",
 };
 
 static const char * const POWER_SUPPLY_HEALTH_TEXT[] = {
diff --git a/drivers/power/supply/wilco-charger.c b/drivers/power/supply/wilco-charger.c
index b3c6d7cdd731..98ade073ef05 100644
--- a/drivers/power/supply/wilco-charger.c
+++ b/drivers/power/supply/wilco-charger.c
@@ -27,6 +27,7 @@ enum charge_mode {
 	CHARGE_MODE_AC = 3,	/* Mostly AC use, used for Trickle */
 	CHARGE_MODE_AUTO = 4,	/* Used for Adaptive */
 	CHARGE_MODE_CUSTOM = 5,	/* Used for Custom */
+	CHARGE_MODE_LONGLIFE = 6, /* Used for Long Life */
 };
 
 #define CHARGE_LOWER_LIMIT_MIN	50
@@ -48,6 +49,8 @@ static int psp_val_to_charge_mode(int psp_val)
 		return CHARGE_MODE_AUTO;
 	case POWER_SUPPLY_CHARGE_TYPE_CUSTOM:
 		return CHARGE_MODE_CUSTOM;
+	case POWER_SUPPLY_CHARGE_TYPE_LONGLIFE:
+		return CHARGE_MODE_LONGLIFE;
 	default:
 		return -EINVAL;
 	}
@@ -67,6 +70,8 @@ static int charge_mode_to_psp_val(enum charge_mode mode)
 		return POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE;
 	case CHARGE_MODE_CUSTOM:
 		return POWER_SUPPLY_CHARGE_TYPE_CUSTOM;
+	case CHARGE_MODE_LONGLIFE:
+		return POWER_SUPPLY_CHARGE_TYPE_LONGLIFE;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index b5ee35d3c304..97cc4b85bf61 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -48,6 +48,7 @@ enum {
 	POWER_SUPPLY_CHARGE_TYPE_STANDARD,	/* normal speed */
 	POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE,	/* dynamically adjusted speed */
 	POWER_SUPPLY_CHARGE_TYPE_CUSTOM,	/* use CHARGE_CONTROL_* props */
+	POWER_SUPPLY_CHARGE_TYPE_LONGLIFE,	/* slow speed, longer life */
 };
 
 enum {
-- 
cgit v1.2.3


From 48040793fa6003d211f021c6ad273477bcd90d91 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Thu, 30 Jul 2020 15:44:40 -0700
Subject: tcp: add earliest departure time to SCM_TIMESTAMPING_OPT_STATS

This change adds TCP_NLA_EDT to SCM_TIMESTAMPING_OPT_STATS that reports
the earliest departure time(EDT) of the timestamped skb. By tracking EDT
values of the skb from different timestamps, we can observe when and how
much the value changed. This allows to measure the precise delay
injected on the sender host e.g. by a bpf-base throttler.

Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 3 ++-
 include/uapi/linux/tcp.h | 1 +
 net/core/skbuff.c        | 2 +-
 net/ipv4/tcp.c           | 6 +++++-
 4 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 527d668a5275..14b62d7df942 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -484,7 +484,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
 	tp->saved_syn = NULL;
 }
 
-struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk);
+struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
+					       const struct sk_buff *orig_skb);
 
 static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
 {
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index f2acb2566333..cfcb10b75483 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -313,6 +313,7 @@ enum {
 	TCP_NLA_SRTT,		/* smoothed RTT in usecs */
 	TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */
 	TCP_NLA_BYTES_NOTSENT,	/* Bytes in write queue not yet sent */
+	TCP_NLA_EDT,		/* Earliest departure time (CLOCK_MONOTONIC) */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b8afefe6f6b6..4e2edfbe0e19 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4692,7 +4692,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk->sk_protocol == IPPROTO_TCP &&
 		    sk->sk_type == SOCK_STREAM) {
-			skb = tcp_get_timestamping_opt_stats(sk);
+			skb = tcp_get_timestamping_opt_stats(sk, orig_skb);
 			opt_stats = true;
 		} else
 #endif
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4afec552f211..c06d2bfd2ec4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3501,10 +3501,12 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */
 		nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */
 		0;
 }
 
-struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
+struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
+					       const struct sk_buff *orig_skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *stats;
@@ -3558,6 +3560,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash);
 	nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT,
 		    max_t(int, 0, tp->write_seq - tp->snd_nxt));
+	nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns,
+			  TCP_NLA_PAD);
 
 	return stats;
 }
-- 
cgit v1.2.3


From 829eb208e80d6db95c0201cb8fa00c2f9ad87faf Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 31 Jul 2020 17:34:01 -0700
Subject: rtnetlink: add support for protodown reason

netdev protodown is a mechanism that allows protocols to
hold an interface down. It was initially introduced in
the kernel to hold links down by a multihoming protocol.
There was also an attempt to introduce protodown
reason at the time but was rejected. protodown and protodown reason
is supported by almost every switching and routing platform.
It was ok for a while to live without a protodown reason.
But, its become more critical now given more than
one protocol may need to keep a link down on a system
at the same time. eg: vrrp peer node, port security,
multihoming protocol. Its common for Network operators and
protocol developers to look for such a reason on a networking
box (Its also known as errDisable by most networking operators)

This patch adds support for link protodown reason
attribute. There are two ways to maintain protodown
reasons.
(a) enumerate every possible reason code in kernel
    - A protocol developer has to make a request and
      have that appear in a certain kernel version
(b) provide the bits in the kernel, and allow user-space
(sysadmin or NOS distributions) to manage the bit-to-reasonname
map.
	- This makes extending reason codes easier (kind of like
      the iproute2 table to vrf-name map /etc/iproute2/rt_tables.d/)

This patch takes approach (b).

a few things about the patch:
- It treats the protodown reason bits as counter to indicate
active protodown users
- Since protodown attribute is already an exposed UAPI,
the reason is not enforced on a protodown set. Its a no-op
if not used.
the patch follows the below algorithm:
  - presence of reason bits set indicates protodown
    is in use
  - user can set protodown and protodown reason in a
    single or multiple setlink operations
  - setlink operation to clear protodown, will return -EBUSY
    if there are active protodown reason bits
  - reason is not included in link dumps if not used

example with patched iproute2:
$cat /etc/iproute2/protodown_reasons.d/r.conf
0 mlag
1 evpn
2 vrrp
3 psecurity

$ip link set dev vxlan0 protodown on protodown_reason vrrp on
$ip link set dev vxlan0 protodown_reason mlag on
$ip link show
14: vxlan0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode
DEFAULT group default qlen 1000
    link/ether f6:06:be:17:91:e7 brd ff:ff:ff:ff:ff:ff protodown on <mlag,vrrp>

$ip link set dev vxlan0 protodown_reason mlag off
$ip link set dev vxlan0 protodown off protodown_reason vrrp off

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h    |   4 ++
 include/uapi/linux/if_link.h |  10 ++++
 net/core/dev.c               |  25 ++++++++++
 net/core/rtnetlink.c         | 113 +++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 147 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ac2cd3f49aba..ba0fa6b22787 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2058,6 +2058,8 @@ struct net_device {
 	struct timer_list	watchdog_timer;
 	int			watchdog_timeo;
 
+	u32                     proto_down_reason;
+
 	struct list_head	todo_list;
 	int __percpu		*pcpu_refcnt;
 
@@ -3810,6 +3812,8 @@ int dev_get_port_parent_id(struct net_device *dev,
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
 int dev_change_proto_down(struct net_device *dev, bool proto_down);
 int dev_change_proto_down_generic(struct net_device *dev, bool proto_down);
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+				  u32 value);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 63af64646358..7fba4de511de 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -170,12 +170,22 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
diff --git a/net/core/dev.c b/net/core/dev.c
index 38a6371d9bc5..f7ef0f5c5569 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8715,6 +8715,31 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
+/**
+ *	dev_change_proto_down_reason - proto down reason
+ *
+ *	@dev: device
+ *	@mask: proto down mask
+ *	@value: proto down value
+ */
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+				  u32 value)
+{
+	int b;
+
+	if (!mask) {
+		dev->proto_down_reason = value;
+	} else {
+		for_each_set_bit(b, &mask, 32) {
+			if (value & (1 << b))
+				dev->proto_down_reason |= BIT(b);
+			else
+				dev->proto_down_reason &= ~BIT(b);
+		}
+	}
+}
+EXPORT_SYMBOL(dev_change_proto_down_reason);
+
 u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
 		    enum bpf_netdev_command cmd)
 {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 85a4b0101f76..a54c3e0f2ee1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1000,6 +1000,16 @@ static size_t rtnl_prop_list_size(const struct net_device *dev)
 	return size;
 }
 
+static size_t rtnl_proto_down_size(const struct net_device *dev)
+{
+	size_t size = nla_total_size(1);
+
+	if (dev->proto_down_reason)
+		size += nla_total_size(0) + nla_total_size(4);
+
+	return size;
+}
+
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
 				     u32 ext_filter_mask)
 {
@@ -1041,7 +1051,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4)  /* IFLA_EVENT */
 	       + nla_total_size(4)  /* IFLA_NEW_NETNSID */
 	       + nla_total_size(4)  /* IFLA_NEW_IFINDEX */
-	       + nla_total_size(1)  /* IFLA_PROTO_DOWN */
+	       + rtnl_proto_down_size(dev)  /* proto down */
 	       + nla_total_size(4)  /* IFLA_TARGET_NETNSID */
 	       + nla_total_size(4)  /* IFLA_CARRIER_UP_COUNT */
 	       + nla_total_size(4)  /* IFLA_CARRIER_DOWN_COUNT */
@@ -1658,6 +1668,35 @@ nest_cancel:
 	return ret;
 }
 
+static int rtnl_fill_proto_down(struct sk_buff *skb,
+				const struct net_device *dev)
+{
+	struct nlattr *pr;
+	u32 preason;
+
+	if (nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
+		goto nla_put_failure;
+
+	preason = dev->proto_down_reason;
+	if (!preason)
+		return 0;
+
+	pr = nla_nest_start(skb, IFLA_PROTO_DOWN_REASON);
+	if (!pr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, IFLA_PROTO_DOWN_REASON_VALUE, preason)) {
+		nla_nest_cancel(skb, pr);
+		goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, pr);
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			    struct net_device *dev, struct net *src_net,
 			    int type, u32 pid, u32 seq, u32 change,
@@ -1708,13 +1747,15 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
 			atomic_read(&dev->carrier_up_count) +
 			atomic_read(&dev->carrier_down_count)) ||
-	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down) ||
 	    nla_put_u32(skb, IFLA_CARRIER_UP_COUNT,
 			atomic_read(&dev->carrier_up_count)) ||
 	    nla_put_u32(skb, IFLA_CARRIER_DOWN_COUNT,
 			atomic_read(&dev->carrier_down_count)))
 		goto nla_put_failure;
 
+	if (rtnl_fill_proto_down(skb, dev))
+		goto nla_put_failure;
+
 	if (event != IFLA_EVENT_NONE) {
 		if (nla_put_u32(skb, IFLA_EVENT, event))
 			goto nla_put_failure;
@@ -1834,6 +1875,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_ALT_IFNAME]	= { .type = NLA_STRING,
 				    .len = ALTIFNAMSIZ - 1 },
 	[IFLA_PERM_ADDRESS]	= { .type = NLA_REJECT },
+	[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2483,6 +2525,67 @@ static int do_set_master(struct net_device *dev, int ifindex,
 	return 0;
 }
 
+static const struct nla_policy ifla_proto_down_reason_policy[IFLA_PROTO_DOWN_REASON_VALUE + 1] = {
+	[IFLA_PROTO_DOWN_REASON_MASK]	= { .type = NLA_U32 },
+	[IFLA_PROTO_DOWN_REASON_VALUE]	= { .type = NLA_U32 },
+};
+
+static int do_set_proto_down(struct net_device *dev,
+			     struct nlattr *nl_proto_down,
+			     struct nlattr *nl_proto_down_reason,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *pdreason[IFLA_PROTO_DOWN_REASON_MAX + 1];
+	const struct net_device_ops *ops = dev->netdev_ops;
+	unsigned long mask = 0;
+	u32 value;
+	bool proto_down;
+	int err;
+
+	if (!ops->ndo_change_proto_down) {
+		NL_SET_ERR_MSG(extack,  "Protodown not supported by device");
+		return -EOPNOTSUPP;
+	}
+
+	if (nl_proto_down_reason) {
+		err = nla_parse_nested_deprecated(pdreason,
+						  IFLA_PROTO_DOWN_REASON_MAX,
+						  nl_proto_down_reason,
+						  ifla_proto_down_reason_policy,
+						  NULL);
+		if (err < 0)
+			return err;
+
+		if (!pdreason[IFLA_PROTO_DOWN_REASON_VALUE]) {
+			NL_SET_ERR_MSG(extack, "Invalid protodown reason value");
+			return -EINVAL;
+		}
+
+		value = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_VALUE]);
+
+		if (pdreason[IFLA_PROTO_DOWN_REASON_MASK])
+			mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]);
+
+		dev_change_proto_down_reason(dev, mask, value);
+	}
+
+	if (nl_proto_down) {
+		proto_down = nla_get_u8(nl_proto_down);
+
+		/* Dont turn off protodown if there are active reasons */
+		if (!proto_down && dev->proto_down_reason) {
+			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
+			return -EBUSY;
+		}
+		err = dev_change_proto_down(dev,
+					    proto_down);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define DO_SETLINK_MODIFIED	0x01
 /* notify flag means notify + modified. */
 #define DO_SETLINK_NOTIFY	0x03
@@ -2771,9 +2874,9 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 	err = 0;
 
-	if (tb[IFLA_PROTO_DOWN]) {
-		err = dev_change_proto_down(dev,
-					    nla_get_u8(tb[IFLA_PROTO_DOWN]));
+	if (tb[IFLA_PROTO_DOWN] || tb[IFLA_PROTO_DOWN_REASON]) {
+		err = do_set_proto_down(dev, tb[IFLA_PROTO_DOWN],
+					tb[IFLA_PROTO_DOWN_REASON], extack);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_NOTIFY;
-- 
cgit v1.2.3


From f4470cdf108f00533e8079b19434e6cb48c17fa3 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Fri, 31 Jul 2020 20:20:14 +0100
Subject: sched: Document arch_scale_*_capacity()

Rather that hide their purpose in some dark, damp corner of Documentation/,
add some documentation to the default implementations.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200731192016.7484-2-valentin.schneider@arm.com
---
 include/linux/sched/topology.h | 10 ++++++++++
 kernel/sched/sched.h           | 10 ++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 764222d637b7..820511289857 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -217,6 +217,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 #endif	/* !CONFIG_SMP */
 
 #ifndef arch_scale_cpu_capacity
+/**
+ * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the CPU scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *             max_perf(cpu)
+ *      ----------------------------- * SCHED_CAPACITY_SCALE
+ *      max(max_perf(c) : c \in CPUs)
+ */
 static __always_inline
 unsigned long arch_scale_cpu_capacity(int cpu)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 296efd30d8c9..3fd283892761 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2049,6 +2049,16 @@ void arch_scale_freq_tick(void)
 #endif
 
 #ifndef arch_scale_freq_capacity
+/**
+ * arch_scale_freq_capacity - get the frequency scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the frequency scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *     f_curr
+ *     ------ * SCHED_CAPACITY_SCALE
+ *     f_max
+ */
 static __always_inline
 unsigned long arch_scale_freq_capacity(int cpu)
 {
-- 
cgit v1.2.3


From f369bc3f9096f5d355e8b80540bc30ac9a602912 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 1 Aug 2020 08:17:13 +0200
Subject: vgaarb: mark vga_tryget static

This symbols isn't used anywhere outside of vgaarb.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200801061713.307434-1-hch@lst.de
---
 drivers/gpu/vga/vgaarb.c | 3 +--
 include/linux/vgaarb.h   | 6 ------
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index f2f3ef8af271..5180c5687ee5 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -529,7 +529,7 @@ EXPORT_SYMBOL(vga_get);
  *
  * 0 on success, negative error code on failure.
  */
-int vga_tryget(struct pci_dev *pdev, unsigned int rsrc)
+static int vga_tryget(struct pci_dev *pdev, unsigned int rsrc)
 {
 	struct vga_device *vgadev;
 	unsigned long flags;
@@ -554,7 +554,6 @@ bail:
 	spin_unlock_irqrestore(&vga_lock, flags);
 	return rc;
 }
-EXPORT_SYMBOL(vga_tryget);
 
 /**
  * vga_put - release lock on legacy VGA resources
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 553b34c8b5f7..977caf96c8d2 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -109,12 +109,6 @@ static inline int vga_get_uninterruptible(struct pci_dev *pdev,
        return vga_get(pdev, rsrc, 0);
 }
 
-#if defined(CONFIG_VGA_ARB)
-extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc);
-#else
-static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; }
-#endif
-
 #if defined(CONFIG_VGA_ARB)
 extern void vga_put(struct pci_dev *pdev, unsigned int rsrc);
 #else
-- 
cgit v1.2.3


From 7ef5264de773279b9f23b6cc8afb5addb30e970b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Jul 2020 08:10:20 +0200
Subject: modules: mark ref_module static

ref_module isn't used anywhere outside of module.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 1 -
 kernel/module.c        | 6 ++----
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 2e6670860d27..f1fdbeef2153 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -657,7 +657,6 @@ static inline void __module_get(struct module *module)
 #define symbol_put_addr(p) do { } while (0)
 
 #endif /* CONFIG_MODULE_UNLOAD */
-int ref_module(struct module *a, struct module *b);
 
 /* This is a #define so the string doesn't get put in every .o file */
 #define module_name(mod)			\
diff --git a/kernel/module.c b/kernel/module.c
index e8a198588f26..baae0e83d630 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -869,7 +869,7 @@ static int add_module_usage(struct module *a, struct module *b)
 }
 
 /* Module a uses b: caller needs module_mutex() */
-int ref_module(struct module *a, struct module *b)
+static int ref_module(struct module *a, struct module *b)
 {
 	int err;
 
@@ -888,7 +888,6 @@ int ref_module(struct module *a, struct module *b)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ref_module);
 
 /* Clear the unload stuff of the module. */
 static void module_unload_free(struct module *mod)
@@ -1169,11 +1168,10 @@ static inline void module_unload_free(struct module *mod)
 {
 }
 
-int ref_module(struct module *a, struct module *b)
+static int ref_module(struct module *a, struct module *b)
 {
 	return strong_try_module_get(b);
 }
-EXPORT_SYMBOL_GPL(ref_module);
 
 static inline int module_unload_init(struct module *mod)
 {
-- 
cgit v1.2.3


From 773110470e2fa3839523384ae014f8a723c4d178 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Jul 2020 08:10:21 +0200
Subject: modules: mark find_symbol static

find_symbol is only used in module.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 11 -----------
 kernel/module.c        |  3 +--
 2 files changed, 1 insertion(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index f1fdbeef2153..90bdc362be36 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -590,17 +590,6 @@ struct symsearch {
 	bool unused;
 };
 
-/*
- * Search for an exported symbol by name.
- *
- * Must be called with module_mutex held or preemption disabled.
- */
-const struct kernel_symbol *find_symbol(const char *name,
-					struct module **owner,
-					const s32 **crc,
-					bool gplok,
-					bool warn);
-
 /*
  * Walk the exported symbol table
  *
diff --git a/kernel/module.c b/kernel/module.c
index baae0e83d630..0f95fb4b3e37 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -585,7 +585,7 @@ static bool find_exported_symbol_in_section(const struct symsearch *syms,
 
 /* Find an exported symbol and return it, along with, (optional) crc and
  * (optional) module which owns it.  Needs preempt disabled or module_mutex. */
-const struct kernel_symbol *find_symbol(const char *name,
+static const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
 					const s32 **crc,
 					bool gplok,
@@ -608,7 +608,6 @@ const struct kernel_symbol *find_symbol(const char *name,
 	pr_debug("Failed to find symbol %s\n", name);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(find_symbol);
 
 /*
  * Search for module by name: must hold module_mutex (or preempt disabled
-- 
cgit v1.2.3


From a54e04914c211b5678602a46b3ede5d82ec1327d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Jul 2020 08:10:22 +0200
Subject: modules: mark each_symbol_section static

each_symbol_section is only used inside of module.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 9 ---------
 kernel/module.c        | 3 +--
 2 files changed, 1 insertion(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 90bdc362be36..b79219eed83c 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -590,15 +590,6 @@ struct symsearch {
 	bool unused;
 };
 
-/*
- * Walk the exported symbol table
- *
- * Must be called with module_mutex held or preemption disabled.
- */
-bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
-				    struct module *owner,
-				    void *data), void *data);
-
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
diff --git a/kernel/module.c b/kernel/module.c
index 0f95fb4b3e37..c2a099a27b68 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -422,7 +422,7 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
+static bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 				    struct module *owner,
 				    void *data),
 			 void *data)
@@ -484,7 +484,6 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(each_symbol_section);
 
 struct find_symbol_arg {
 	/* Input */
-- 
cgit v1.2.3


From cd8732cdcc37d7077c4fa2c966b748c0662b607e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Jul 2020 08:10:25 +0200
Subject: modules: rename the licence field in struct symsearch to license

Use the same spelling variant as the rest of the file.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 2 +-
 kernel/module.c        | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index b79219eed83c..be04ba2f881d 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -586,7 +586,7 @@ struct symsearch {
 		NOT_GPL_ONLY,
 		GPL_ONLY,
 		WILL_BE_GPL_ONLY,
-	} licence;
+	} license;
 	bool unused;
 };
 
diff --git a/kernel/module.c b/kernel/module.c
index e85d06158fbc..62d817a0dca8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -504,9 +504,9 @@ static bool check_exported_symbol(const struct symsearch *syms,
 	struct find_symbol_arg *fsa = data;
 
 	if (!fsa->gplok) {
-		if (syms->licence == GPL_ONLY)
+		if (syms->license == GPL_ONLY)
 			return false;
-		if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
+		if (syms->license == WILL_BE_GPL_ONLY && fsa->warn) {
 			pr_warn("Symbol %s is being used by a non-GPL module, "
 				"which will not be allowed in the future\n",
 				fsa->name);
-- 
cgit v1.2.3


From ef1dac6021cc8ec5de02ce31722bf26ac4ed5523 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Jul 2020 08:10:26 +0200
Subject: modules: return licensing information from find_symbol

Report the GPLONLY status through a new argument.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h |  2 +-
 kernel/module.c        | 16 +++++++++++-----
 2 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index be04ba2f881d..30b0f5fcdb3c 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -582,7 +582,7 @@ struct module *find_module(const char *name);
 struct symsearch {
 	const struct kernel_symbol *start, *stop;
 	const s32 *crcs;
-	enum {
+	enum mod_license {
 		NOT_GPL_ONLY,
 		GPL_ONLY,
 		WILL_BE_GPL_ONLY,
diff --git a/kernel/module.c b/kernel/module.c
index 62d817a0dca8..656f5ff27088 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -495,6 +495,7 @@ struct find_symbol_arg {
 	struct module *owner;
 	const s32 *crc;
 	const struct kernel_symbol *sym;
+	enum mod_license license;
 };
 
 static bool check_exported_symbol(const struct symsearch *syms,
@@ -528,6 +529,7 @@ static bool check_exported_symbol(const struct symsearch *syms,
 	fsa->owner = owner;
 	fsa->crc = symversion(syms->crcs, symnum);
 	fsa->sym = &syms->start[symnum];
+	fsa->license = syms->license;
 	return true;
 }
 
@@ -587,6 +589,7 @@ static bool find_exported_symbol_in_section(const struct symsearch *syms,
 static const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
 					const s32 **crc,
+					enum mod_license *license,
 					bool gplok,
 					bool warn)
 {
@@ -601,6 +604,8 @@ static const struct kernel_symbol *find_symbol(const char *name,
 			*owner = fsa.owner;
 		if (crc)
 			*crc = fsa.crc;
+		if (license)
+			*license = fsa.license;
 		return fsa.sym;
 	}
 
@@ -1074,7 +1079,7 @@ void __symbol_put(const char *symbol)
 	struct module *owner;
 
 	preempt_disable();
-	if (!find_symbol(symbol, &owner, NULL, true, false))
+	if (!find_symbol(symbol, &owner, NULL, NULL, true, false))
 		BUG();
 	module_put(owner);
 	preempt_enable();
@@ -1352,7 +1357,7 @@ static inline int check_modstruct_version(const struct load_info *info,
 	 * locking is necessary -- use preempt_disable() to placate lockdep.
 	 */
 	preempt_disable();
-	if (!find_symbol("module_layout", NULL, &crc, true, false)) {
+	if (!find_symbol("module_layout", NULL, &crc, NULL, true, false)) {
 		preempt_enable();
 		BUG();
 	}
@@ -1436,6 +1441,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	struct module *owner;
 	const struct kernel_symbol *sym;
 	const s32 *crc;
+	enum mod_license license;
 	int err;
 
 	/*
@@ -1445,7 +1451,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	 */
 	sched_annotate_sleep();
 	mutex_lock(&module_mutex);
-	sym = find_symbol(name, &owner, &crc,
+	sym = find_symbol(name, &owner, &crc, &license,
 			  !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
 	if (!sym)
 		goto unlock;
@@ -2213,7 +2219,7 @@ void *__symbol_get(const char *symbol)
 	const struct kernel_symbol *sym;
 
 	preempt_disable();
-	sym = find_symbol(symbol, &owner, NULL, true, true);
+	sym = find_symbol(symbol, &owner, NULL, NULL, true, true);
 	if (sym && strong_try_module_get(owner))
 		sym = NULL;
 	preempt_enable();
@@ -2249,7 +2255,7 @@ static int verify_exported_symbols(struct module *mod)
 	for (i = 0; i < ARRAY_SIZE(arr); i++) {
 		for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
 			if (find_symbol(kernel_symbol_name(s), &owner, NULL,
-					true, false)) {
+					NULL, true, false)) {
 				pr_err("%s: exports duplicate symbol %s"
 				       " (owned by %s)\n",
 				       mod->name, kernel_symbol_name(s),
-- 
cgit v1.2.3


From 1752f0adea98ef859978c090e0726844348758f9 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 1 Aug 2020 13:36:33 +0300
Subject: fs: optimise kiocb_set_rw_flags()

Use a local var to collect flags in kiocb_set_rw_flags(). That spares
some memory writes and allows to replace most of the jumps with MOVEcc.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4090320360f4..e535543d31d9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3446,22 +3446,28 @@ static inline int iocb_flags(struct file *file)
 
 static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 {
+	int kiocb_flags = 0;
+
+	if (!flags)
+		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
 
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		ki->ki_flags |= IOCB_NOWAIT;
+		kiocb_flags |= IOCB_NOWAIT;
 	}
 	if (flags & RWF_HIPRI)
-		ki->ki_flags |= IOCB_HIPRI;
+		kiocb_flags |= IOCB_HIPRI;
 	if (flags & RWF_DSYNC)
-		ki->ki_flags |= IOCB_DSYNC;
+		kiocb_flags |= IOCB_DSYNC;
 	if (flags & RWF_SYNC)
-		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+		kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC);
 	if (flags & RWF_APPEND)
-		ki->ki_flags |= IOCB_APPEND;
+		kiocb_flags |= IOCB_APPEND;
+
+	ki->ki_flags |= kiocb_flags;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 73b11c2ab072d5b0599d1e12cc126f55ee306daf Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 31 Jul 2020 11:28:26 -0700
Subject: bpf: Add support for forced LINK_DETACH command

Add LINK_DETACH command to force-detach bpf_link without destroying it. It has
the same behavior as auto-detaching of bpf_link due to cgroup dying for
bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case,
bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF
program attached to corresponding BPF hook. This functionality allows users
with enough access rights to manually force-detach attached bpf_link without
killing respective owner process.

This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly
re-using existing link release handling code.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com
---
 include/linux/bpf.h        |  1 +
 include/uapi/linux/bpf.h   |  5 +++++
 kernel/bpf/cgroup.c        | 15 ++++++++++++++-
 kernel/bpf/net_namespace.c |  8 ++++++++
 kernel/bpf/syscall.c       | 26 ++++++++++++++++++++++++++
 net/core/dev.c             | 11 ++++++++++-
 6 files changed, 64 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 40c5e206ecf2..cef4ef0d2b4e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -793,6 +793,7 @@ struct bpf_link {
 struct bpf_link_ops {
 	void (*release)(struct bpf_link *link);
 	void (*dealloc)(struct bpf_link *link);
+	int (*detach)(struct bpf_link *link);
 	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
 			   struct bpf_prog *old_prog);
 	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index eb5e0c38eb2c..b134e679e9db 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -117,6 +117,7 @@ enum bpf_cmd {
 	BPF_LINK_GET_NEXT_ID,
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
+	BPF_LINK_DETACH,
 };
 
 enum bpf_map_type {
@@ -634,6 +635,10 @@ union bpf_attr {
 		__u32		old_prog_fd;
 	} link_update;
 
+	struct {
+		__u32		link_fd;
+	} link_detach;
+
 	struct { /* struct used by BPF_ENABLE_STATS command */
 		__u32		type;
 	} enable_stats;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 957cce1d5168..83ff127ef7ae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -814,6 +814,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 {
 	struct bpf_cgroup_link *cg_link =
 		container_of(link, struct bpf_cgroup_link, link);
+	struct cgroup *cg;
 
 	/* link might have been auto-detached by dying cgroup already,
 	 * in that case our work is done here
@@ -832,8 +833,12 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
 				    cg_link->type));
 
+	cg = cg_link->cgroup;
+	cg_link->cgroup = NULL;
+
 	mutex_unlock(&cgroup_mutex);
-	cgroup_put(cg_link->cgroup);
+
+	cgroup_put(cg);
 }
 
 static void bpf_cgroup_link_dealloc(struct bpf_link *link)
@@ -844,6 +849,13 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link)
 	kfree(cg_link);
 }
 
+static int bpf_cgroup_link_detach(struct bpf_link *link)
+{
+	bpf_cgroup_link_release(link);
+
+	return 0;
+}
+
 static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
 					struct seq_file *seq)
 {
@@ -883,6 +895,7 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_cgroup_link_lops = {
 	.release = bpf_cgroup_link_release,
 	.dealloc = bpf_cgroup_link_dealloc,
+	.detach = bpf_cgroup_link_detach,
 	.update_prog = cgroup_bpf_replace,
 	.show_fdinfo = bpf_cgroup_link_show_fdinfo,
 	.fill_link_info = bpf_cgroup_link_fill_link_info,
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 71405edd667c..542f275bf252 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -142,9 +142,16 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	bpf_prog_array_free(old_array);
 
 out_unlock:
+	net_link->net = NULL;
 	mutex_unlock(&netns_bpf_mutex);
 }
 
+static int bpf_netns_link_detach(struct bpf_link *link)
+{
+	bpf_netns_link_release(link);
+	return 0;
+}
+
 static void bpf_netns_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_netns_link *net_link =
@@ -228,6 +235,7 @@ static void bpf_netns_link_show_fdinfo(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_netns_link_ops = {
 	.release = bpf_netns_link_release,
 	.dealloc = bpf_netns_link_dealloc,
+	.detach = bpf_netns_link_detach,
 	.update_prog = bpf_netns_link_update_prog,
 	.fill_link_info = bpf_netns_link_fill_info,
 	.show_fdinfo = bpf_netns_link_show_fdinfo,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cd3d599e9e90..2f343ce15747 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3991,6 +3991,29 @@ out_put_link:
 	return ret;
 }
 
+#define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd
+
+static int link_detach(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_DETACH))
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->link_detach.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	if (link->ops->detach)
+		ret = link->ops->detach(link);
+	else
+		ret = -EOPNOTSUPP;
+
+	bpf_link_put(link);
+	return ret;
+}
+
 static int bpf_link_inc_not_zero(struct bpf_link *link)
 {
 	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
@@ -4240,6 +4263,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_ITER_CREATE:
 		err = bpf_iter_create(&attr);
 		break;
+	case BPF_LINK_DETACH:
+		err = link_detach(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/net/core/dev.c b/net/core/dev.c
index a2a57988880a..c8b911b10187 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8979,12 +8979,20 @@ static void bpf_xdp_link_release(struct bpf_link *link)
 	/* if racing with net_device's tear down, xdp_link->dev might be
 	 * already NULL, in which case link was already auto-detached
 	 */
-	if (xdp_link->dev)
+	if (xdp_link->dev) {
 		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+		xdp_link->dev = NULL;
+	}
 
 	rtnl_unlock();
 }
 
+static int bpf_xdp_link_detach(struct bpf_link *link)
+{
+	bpf_xdp_link_release(link);
+	return 0;
+}
+
 static void bpf_xdp_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
@@ -9066,6 +9074,7 @@ out_unlock:
 static const struct bpf_link_ops bpf_xdp_link_lops = {
 	.release = bpf_xdp_link_release,
 	.dealloc = bpf_xdp_link_dealloc,
+	.detach = bpf_xdp_link_detach,
 	.show_fdinfo = bpf_xdp_link_show_fdinfo,
 	.fill_link_info = bpf_xdp_link_fill_link_info,
 	.update_prog = bpf_xdp_link_update,
-- 
cgit v1.2.3


From c83e2a6e2fbbb7d47ea46fd7cb1f01292f2d0b6e Mon Sep 17 00:00:00 2001
From: Ajay Singh <ajay.kathat@microchip.com>
Date: Fri, 17 Jul 2020 05:11:38 +0000
Subject: wilc1000: Move wilc1000 SDIO ID's from driver source to common header
 file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Moved macros used for Vendor/Device ID from wilc1000 driver to common
header file and changed macro name for consistency with other macros.

Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20200717051134.19160-1-ajay.kathat@microchip.com
---
 drivers/net/wireless/microchip/wilc1000/sdio.c | 6 ++----
 include/linux/mmc/sdio_ids.h                   | 3 +++
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 36eb589263bf..3ece7b0b0392 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -6,6 +6,7 @@
 
 #include <linux/clk.h>
 #include <linux/mmc/sdio_func.h>
+#include <linux/mmc/sdio_ids.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio.h>
 #include <linux/of_irq.h>
@@ -15,11 +16,8 @@
 
 #define SDIO_MODALIAS "wilc1000_sdio"
 
-#define SDIO_VENDOR_ID_WILC 0x0296
-#define SDIO_DEVICE_ID_WILC 0x5347
-
 static const struct sdio_device_id wilc_sdio_ids[] = {
-	{ SDIO_DEVICE(SDIO_VENDOR_ID_WILC, SDIO_DEVICE_ID_WILC) },
+	{ SDIO_DEVICE(SDIO_VENDOR_ID_MICROCHIP_WILC, SDIO_DEVICE_ID_MICROCHIP_WILC1000) },
 	{ },
 };
 
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 15ed8ce9d394..519820d18e62 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -105,6 +105,9 @@
 #define SDIO_DEVICE_ID_MEDIATEK_MT7663		0x7663
 #define SDIO_DEVICE_ID_MEDIATEK_MT7668		0x7668
 
+#define SDIO_VENDOR_ID_MICROCHIP_WILC		0x0296
+#define SDIO_DEVICE_ID_MICROCHIP_WILC1000	0x5347
+
 #define SDIO_VENDOR_ID_SIANO			0x039a
 #define SDIO_DEVICE_ID_SIANO_NOVA_B0		0x0201
 #define SDIO_DEVICE_ID_SIANO_NICE		0x0202
-- 
cgit v1.2.3


From 614a895fc69497d99cc02c076fa712c75194eab3 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Thu, 9 Jul 2020 20:07:33 +0200
Subject: mtd: hyperbus: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/hyperbus/hbmc-am654.c    | 2 +-
 drivers/mtd/hyperbus/hyperbus-core.c | 2 +-
 include/linux/mtd/hyperbus.h         | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/hyperbus/hbmc-am654.c b/drivers/mtd/hyperbus/hbmc-am654.c
index f350a0809f88..e0e33f6bf513 100644
--- a/drivers/mtd/hyperbus/hbmc-am654.c
+++ b/drivers/mtd/hyperbus/hbmc-am654.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+// Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com/
 // Author: Vignesh Raghavendra <vigneshr@ti.com>
 
 #include <linux/err.h>
diff --git a/drivers/mtd/hyperbus/hyperbus-core.c b/drivers/mtd/hyperbus/hyperbus-core.c
index 32685e8dd278..2f9fc4e17d53 100644
--- a/drivers/mtd/hyperbus/hyperbus-core.c
+++ b/drivers/mtd/hyperbus/hyperbus-core.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+// Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com/
 // Author: Vignesh Raghavendra <vigneshr@ti.com>
 
 #include <linux/err.h>
diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h
index 2dfe65964f6e..2129f7d3b6eb 100644
--- a/include/linux/mtd/hyperbus.h
+++ b/include/linux/mtd/hyperbus.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef __LINUX_MTD_HYPERBUS_H__
-- 
cgit v1.2.3


From 0c84b7fc973f9220ef8732c430ccc7c92d083184 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:29:54 -0700
Subject: MTD: pfow.h: drop a duplicated word

Drop the repeated word "can" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Miquel Raynal <miquel.raynal@bootlin.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Cc: linux-mtd@lists.infradead.org
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 include/linux/mtd/pfow.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h
index 122f3439e1af..6166e7c60869 100644
--- a/include/linux/mtd/pfow.h
+++ b/include/linux/mtd/pfow.h
@@ -19,7 +19,7 @@
 /* Identification info for LPDDR chip */
 #define PFOW_MANUFACTURER_ID			0x0020
 #define PFOW_DEVICE_ID				0x0022
-/* Address in PFOW where prog buffer can can be found */
+/* Address in PFOW where prog buffer can be found */
 #define PFOW_PROGRAM_BUFFER_OFFSET		0x0040
 /* Size of program buffer in words */
 #define PFOW_PROGRAM_BUFFER_SIZE		0x0042
-- 
cgit v1.2.3


From c6fe44d96fc1536af5b11cd859686453d1b7bfd1 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 23 Jul 2020 12:33:41 -0700
Subject: list: add "list_del_init_careful()" to go with "list_empty_careful()"

That gives us ordering guarantees around the pair.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 20 +++++++++++++++++++-
 kernel/sched/wait.c  |  2 +-
 mm/filemap.c         |  7 +------
 3 files changed, 21 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/list.h b/include/linux/list.h
index aff44d34f4e4..0d0d17a10d25 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -282,6 +282,24 @@ static inline int list_empty(const struct list_head *head)
 	return READ_ONCE(head->next) == head;
 }
 
+/**
+ * list_del_init_careful - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ *
+ * This is the same as list_del_init(), except designed to be used
+ * together with list_empty_careful() in a way to guarantee ordering
+ * of other memory operations.
+ *
+ * Any memory operations done before a list_del_init_careful() are
+ * guaranteed to be visible after a list_empty_careful() test.
+ */
+static inline void list_del_init_careful(struct list_head *entry)
+{
+	__list_del_entry(entry);
+	entry->prev = entry;
+	smp_store_release(&entry->next, entry);
+}
+
 /**
  * list_empty_careful - tests whether a list is empty and not being modified
  * @head: the list to test
@@ -297,7 +315,7 @@ static inline int list_empty(const struct list_head *head)
  */
 static inline int list_empty_careful(const struct list_head *head)
 {
-	struct list_head *next = head->next;
+	struct list_head *next = smp_load_acquire(&head->next);
 	return (next == head) && (next == head->prev);
 }
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index ba059fbfc53a..01f5d3020589 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -389,7 +389,7 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wq_entry->entry);
+		list_del_init_careful(&wq_entry->entry);
 
 	return ret;
 }
diff --git a/mm/filemap.c b/mm/filemap.c
index 8c3d3e233d37..991503bbf922 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1041,13 +1041,8 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
 	 * since after list_del_init(&wait->entry) the wait entry
 	 * might be de-allocated and the process might even have
 	 * exited.
-	 *
-	 * We _really_ should have a "list_del_init_careful()" to
-	 * properly pair with the unlocked "list_empty_careful()"
-	 * in finish_wait().
 	 */
-	smp_mb();
-	list_del_init(&wait->entry);
+	list_del_init_careful(&wait->entry);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 4e56cde15f7d68cf86ff8efff8504497de152475 Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@codeaurora.org>
Date: Fri, 31 Jul 2020 21:38:30 +0300
Subject: mac80211: Handle special status codes in SAE commit

SAE authentication has been extended with H2E (IEEE 802.11 REVmd) and PK
(WFA) options. Those extensions use special status code values in the
SAE commit messages (Authentication frame with transaction sequence
number 1) to identify which extension is in use. mac80211 was
interpreting those new values as the AP denying authentication and that
resulted in failure to complete SAE authentication in some cases.

Fix this by adding exceptions for the new status code values 126 and
127.

Signed-off-by: Jouni Malinen <jouni@codeaurora.org>
Link: https://lore.kernel.org/r/20200731183830.18735-1-jouni@codeaurora.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 2 ++
 net/mac80211/mlme.c       | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 9f732499ea88..c47f43e65a2f 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2561,6 +2561,8 @@ enum ieee80211_statuscode {
 	/* 802.11ai */
 	WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108,
 	WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109,
+	WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126,
+	WLAN_STATUS_SAE_PK = 127,
 };
 
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 839d0367446c..8b7ca8ddfe20 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2988,7 +2988,10 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 		cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
 
 		if (auth_alg == WLAN_AUTH_SAE &&
-		    status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED)
+		    (status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED ||
+		     (auth_transaction == 1 &&
+		      (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT ||
+		       status_code == WLAN_STATUS_SAE_PK))))
 			return;
 
 		sdata_info(sdata, "%pM denied authentication (status %d)\n",
-- 
cgit v1.2.3


From 042f649810f61c4a834f3d6d866c567f7f6b3f8c Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 1 Jul 2020 11:54:43 -0400
Subject: libceph: just have osd_req_op_init() return a pointer

The caller can just ignore the return. No need for this wrapper that
just casts the other function to void.

[ idryomov: argument alignment ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  2 +-
 net/ceph/osd_client.c           | 39 ++++++++++++++++-----------------------
 2 files changed, 17 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index c60b59e9291b..83fa08a06507 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -404,7 +404,7 @@ void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc);
 	&__oreq->r_ops[__whch].typ.fld;					\
 })
 
-extern void osd_req_op_init(struct ceph_osd_request *osd_req,
+struct ceph_osd_req_op *osd_req_op_init(struct ceph_osd_request *osd_req,
 			    unsigned int which, u16 opcode, u32 flags);
 
 extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index db6abb5a5511..e4fbcad6e7d8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -525,7 +525,7 @@ EXPORT_SYMBOL(ceph_osdc_put_request);
 
 static void request_init(struct ceph_osd_request *req)
 {
-	/* req only, each op is zeroed in _osd_req_op_init() */
+	/* req only, each op is zeroed in osd_req_op_init() */
 	memset(req, 0, sizeof(*req));
 
 	kref_init(&req->r_kref);
@@ -746,8 +746,8 @@ EXPORT_SYMBOL(ceph_osdc_alloc_messages);
  * other information associated with them.  It also serves as a
  * common init routine for all the other init functions, below.
  */
-static struct ceph_osd_req_op *
-_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
+struct ceph_osd_req_op *
+osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
 		 u16 opcode, u32 flags)
 {
 	struct ceph_osd_req_op *op;
@@ -762,12 +762,6 @@ _osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
 
 	return op;
 }
-
-void osd_req_op_init(struct ceph_osd_request *osd_req,
-		     unsigned int which, u16 opcode, u32 flags)
-{
-	(void)_osd_req_op_init(osd_req, which, opcode, flags);
-}
 EXPORT_SYMBOL(osd_req_op_init);
 
 void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
@@ -775,8 +769,8 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
 				u64 offset, u64 length,
 				u64 truncate_size, u32 truncate_seq)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      opcode, 0);
+	struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+						     opcode, 0);
 	size_t payload_len = 0;
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
@@ -822,7 +816,7 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
 	BUG_ON(which + 1 >= osd_req->r_num_ops);
 
 	prev_op = &osd_req->r_ops[which];
-	op = _osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
+	op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
 	/* dup previous one */
 	op->indata_len = prev_op->indata_len;
 	op->outdata_len = prev_op->outdata_len;
@@ -845,7 +839,7 @@ int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 	size_t size;
 	int ret;
 
-	op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
+	op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
 
 	pagelist = ceph_pagelist_alloc(GFP_NOFS);
 	if (!pagelist)
@@ -883,8 +877,8 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
 			  u16 opcode, const char *name, const void *value,
 			  size_t size, u8 cmp_op, u8 cmp_mode)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      opcode, 0);
+	struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+						     opcode, 0);
 	struct ceph_pagelist *pagelist;
 	size_t payload_len;
 	int ret;
@@ -928,7 +922,7 @@ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
 {
 	struct ceph_osd_req_op *op;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
 	op->watch.cookie = cookie;
 	op->watch.op = watch_opcode;
 	op->watch.gen = 0;
@@ -943,10 +937,9 @@ void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
 				u64 expected_write_size,
 				u32 flags)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      CEPH_OSD_OP_SETALLOCHINT,
-						      0);
+	struct ceph_osd_req_op *op;
 
+	op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0);
 	op->alloc_hint.expected_object_size = expected_object_size;
 	op->alloc_hint.expected_write_size = expected_write_size;
 	op->alloc_hint.flags = flags;
@@ -4799,7 +4792,7 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
 	struct ceph_pagelist *pl;
 	int ret;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
 
 	pl = ceph_pagelist_alloc(GFP_NOIO);
 	if (!pl)
@@ -4868,7 +4861,7 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
 	struct ceph_pagelist *pl;
 	int ret;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
 	op->notify.cookie = cookie;
 
 	pl = ceph_pagelist_alloc(GFP_NOIO);
@@ -5332,8 +5325,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
-	op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
-			      dst_fadvise_flags);
+	op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
+			     dst_fadvise_flags);
 	op->copy_from.snapid = src_snapid;
 	op->copy_from.src_version = src_version;
 	op->copy_from.flags = copy_from_flags;
-- 
cgit v1.2.3


From 94f17c00d6687993101372f996cf6690ec9adf83 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Wed, 8 Jul 2020 08:53:28 +0200
Subject: libceph: replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

[ idryomov: Do the same for the CRUSH paper and replace
  ceph.newdream.net with ceph.io. ]

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/Kconfig             | 2 +-
 include/linux/crush/crush.h | 2 +-
 net/ceph/Kconfig            | 2 +-
 net/ceph/ceph_hash.c        | 2 +-
 net/ceph/crush/hash.c       | 2 +-
 net/ceph/crush/mapper.c     | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index cf235f6eacf9..471e40156065 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -13,7 +13,7 @@ config CEPH_FS
 	  scalable file system designed to provide high performance,
 	  reliable access to petabytes of storage.
 
-	  More information at http://ceph.newdream.net/.
+	  More information at https://ceph.io/.
 
 	  If unsure, say N.
 
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 33c16f2de7f6..2f811baf78d2 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -17,7 +17,7 @@
  * The algorithm was originally described in detail in this paper
  * (although the algorithm has evolved somewhat since then):
  *
- *     http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
+ *     https://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
  *
  * LGPL2
  */
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index d7bec7adc267..f36f9a3a4e20 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -13,7 +13,7 @@ config CEPH_LIB
 	  common functionality to both the Ceph filesystem and
 	  to the rados block device (rbd).
 
-	  More information at http://ceph.newdream.net/.
+	  More information at https://ceph.io/.
 
 	  If unsure, say N.
 
diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
index 9a5850f264ed..81e1e006c540 100644
--- a/net/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -4,7 +4,7 @@
 
 /*
  * Robert Jenkin's hash function.
- * http://burtleburtle.net/bob/hash/evahash.html
+ * https://burtleburtle.net/bob/hash/evahash.html
  * This is in the public domain.
  */
 #define mix(a, b, c)						\
diff --git a/net/ceph/crush/hash.c b/net/ceph/crush/hash.c
index e5cc603cdb17..fe79f6d2d0db 100644
--- a/net/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -7,7 +7,7 @@
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
- * http://burtleburtle.net/bob/hash/evahash.html
+ * https://burtleburtle.net/bob/hash/evahash.html
  * a, b = random bits, c = input and output
  */
 #define crush_hashmix(a, b, c) do {			\
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 3f323ed9df52..07e5614eb3f1 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -298,7 +298,7 @@ static __u64 crush_ln(unsigned int xin)
  *
  * for reference, see:
  *
- * http://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables
+ * https://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables
  *
  */
 
-- 
cgit v1.2.3


From 18f473b384a64cef69f166a3e2b73d3d2eca82c6 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 16 Jul 2020 10:05:57 -0400
Subject: ceph: periodically send perf metrics to MDSes

This will send the caps/read/write/metadata metrics to any available MDS
once per second, which will be the same as the userland client.  It will
skip the MDS sessions which don't support the metric collection, as the
MDSs will close socket connections when they get an unknown type
message.

We can disable the metric sending via the disable_send_metrics module
parameter.

[ jlayton: fix up endianness bug in ceph_mdsc_send_metrics() ]

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c         |   3 +
 fs/ceph/mds_client.h         |   4 +-
 fs/ceph/metric.c             | 148 +++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/metric.h             |  77 ++++++++++++++++++++++
 fs/ceph/super.c              |  42 ++++++++++++
 fs/ceph/super.h              |   2 +
 include/linux/ceph/ceph_fs.h |   1 +
 7 files changed, 276 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index ef8a1179171b..d6cd2e4f0bc8 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3334,6 +3334,8 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_state = CEPH_MDS_SESSION_OPEN;
 		session->s_features = features;
 		renewed_caps(mdsc, session, 0);
+		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features))
+			metric_schedule_delayed(&mdsc->metric);
 		wake = 1;
 		if (mdsc->stopping)
 			__close_session(mdsc, session);
@@ -4725,6 +4727,7 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	ceph_metric_destroy(&mdsc->metric);
 
+	flush_delayed_work(&mdsc->metric.delayed_work);
 	fsc->mdsc = NULL;
 	kfree(mdsc);
 	dout("mdsc_destroy %p done\n", mdsc);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 6147ff0a1cdf..bc9e95937d7c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -28,8 +28,9 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,
 	CEPHFS_FEATURE_MULTI_RECONNECT,
 	CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_METRIC_COLLECT,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
 };
 
 /*
@@ -43,6 +44,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
+	CEPHFS_FEATURE_METRIC_COLLECT,		\
 						\
 	CEPHFS_FEATURE_MAX,			\
 }
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 269eacbd2a15..2466b261fba2 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -1,10 +1,150 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/types.h>
 #include <linux/percpu_counter.h>
 #include <linux/math64.h>
 
 #include "metric.h"
+#include "mds_client.h"
+
+static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *s)
+{
+	struct ceph_metric_head *head;
+	struct ceph_metric_cap *cap;
+	struct ceph_metric_read_latency *read;
+	struct ceph_metric_write_latency *write;
+	struct ceph_metric_metadata_latency *meta;
+	struct ceph_client_metric *m = &mdsc->metric;
+	u64 nr_caps = atomic64_read(&m->total_caps);
+	struct ceph_msg *msg;
+	struct timespec64 ts;
+	s64 sum;
+	s32 items = 0;
+	s32 len;
+
+	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
+	      + sizeof(*meta);
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
+	if (!msg) {
+		pr_err("send metrics to mds%d, failed to allocate message\n",
+		       s->s_mds);
+		return false;
+	}
+
+	head = msg->front.iov_base;
+
+	/* encode the cap metric */
+	cap = (struct ceph_metric_cap *)(head + 1);
+	cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
+	cap->ver = 1;
+	cap->compat = 1;
+	cap->data_len = cpu_to_le32(sizeof(*cap) - 10);
+	cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit));
+	cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis));
+	cap->total = cpu_to_le64(nr_caps);
+	items++;
+
+	/* encode the read latency metric */
+	read = (struct ceph_metric_read_latency *)(cap + 1);
+	read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
+	read->ver = 1;
+	read->compat = 1;
+	read->data_len = cpu_to_le32(sizeof(*read) - 10);
+	sum = m->read_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	read->sec = cpu_to_le32(ts.tv_sec);
+	read->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the write latency metric */
+	write = (struct ceph_metric_write_latency *)(read + 1);
+	write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
+	write->ver = 1;
+	write->compat = 1;
+	write->data_len = cpu_to_le32(sizeof(*write) - 10);
+	sum = m->write_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	write->sec = cpu_to_le32(ts.tv_sec);
+	write->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the metadata latency metric */
+	meta = (struct ceph_metric_metadata_latency *)(write + 1);
+	meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
+	meta->ver = 1;
+	meta->compat = 1;
+	meta->data_len = cpu_to_le32(sizeof(*meta) - 10);
+	sum = m->metadata_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	meta->sec = cpu_to_le32(ts.tv_sec);
+	meta->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	put_unaligned_le32(items, &head->num);
+	msg->front.iov_len = len;
+	msg->hdr.version = cpu_to_le16(1);
+	msg->hdr.compat_version = cpu_to_le16(1);
+	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+	dout("client%llu send metrics to mds%d\n",
+	     ceph_client_gid(mdsc->fsc->client), s->s_mds);
+	ceph_con_send(&s->s_con, msg);
+
+	return true;
+}
+
+
+static void metric_get_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+
+		/*
+		 * Skip it if MDS doesn't support the metric collection,
+		 * or the MDS will close the session's socket connection
+		 * directly when it get this message.
+		 */
+		if (check_session_state(s) &&
+		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			mdsc->metric.session = s;
+			break;
+		}
+
+		ceph_put_mds_session(s);
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
+static void metric_delayed_work(struct work_struct *work)
+{
+	struct ceph_client_metric *m =
+		container_of(work, struct ceph_client_metric, delayed_work.work);
+	struct ceph_mds_client *mdsc =
+		container_of(m, struct ceph_mds_client, metric);
+
+	if (mdsc->stopping)
+		return;
+
+	if (!m->session || !check_session_state(m->session)) {
+		if (m->session) {
+			ceph_put_mds_session(m->session);
+			m->session = NULL;
+		}
+		metric_get_session(mdsc);
+	}
+	if (m->session) {
+		ceph_mdsc_send_metrics(mdsc, m->session);
+		metric_schedule_delayed(m);
+	}
+}
 
 int ceph_metric_init(struct ceph_client_metric *m)
 {
@@ -52,6 +192,9 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	m->total_metadatas = 0;
 	m->metadata_latency_sum = 0;
 
+	m->session = NULL;
+	INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work);
+
 	return 0;
 
 err_i_caps_mis:
@@ -73,6 +216,11 @@ void ceph_metric_destroy(struct ceph_client_metric *m)
 	percpu_counter_destroy(&m->i_caps_hit);
 	percpu_counter_destroy(&m->d_lease_mis);
 	percpu_counter_destroy(&m->d_lease_hit);
+
+	cancel_delayed_work_sync(&m->delayed_work);
+
+	if (m->session)
+		ceph_put_mds_session(m->session);
 }
 
 static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index 23a3373d5a3d..fe5d07d2e63a 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -6,6 +6,71 @@
 #include <linux/percpu_counter.h>
 #include <linux/ktime.h>
 
+extern bool disable_send_metrics;
+
+enum ceph_metric_type {
+	CLIENT_METRIC_TYPE_CAP_INFO,
+	CLIENT_METRIC_TYPE_READ_LATENCY,
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_DENTRY_LEASE,
+
+	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
+};
+
+/* metric caps header */
+struct ceph_metric_cap {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(hit + mis + total) */
+	__le64 hit;
+	__le64 mis;
+	__le64 total;
+} __packed;
+
+/* metric read latency header */
+struct ceph_metric_read_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric write latency header */
+struct ceph_metric_write_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric metadata latency header */
+struct ceph_metric_metadata_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+struct ceph_metric_head {
+	__le32 num;	/* the number of metrics that will be sent */
+} __packed;
+
 /* This is the global metrics */
 struct ceph_client_metric {
 	atomic64_t            total_dentries;
@@ -36,8 +101,20 @@ struct ceph_client_metric {
 	ktime_t metadata_latency_sq_sum;
 	ktime_t metadata_latency_min;
 	ktime_t metadata_latency_max;
+
+	struct ceph_mds_session *session;
+	struct delayed_work delayed_work;  /* delayed work */
 };
 
+static inline void metric_schedule_delayed(struct ceph_client_metric *m)
+{
+	if (disable_send_metrics)
+		return;
+
+	/* per second */
+	schedule_delayed_work(&m->delayed_work, round_jiffies_relative(HZ));
+}
+
 extern int ceph_metric_init(struct ceph_client_metric *m);
 extern void ceph_metric_destroy(struct ceph_client_metric *m);
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c9784eb1159a..933f5df5da7d 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,9 @@
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
 
+static DEFINE_SPINLOCK(ceph_fsc_lock);
+static LIST_HEAD(ceph_fsc_list);
+
 /*
  * Ceph superblock operations
  *
@@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->wb_pagevec_pool)
 		goto fail_cap_wq;
 
+	spin_lock(&ceph_fsc_lock);
+	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
+	spin_unlock(&ceph_fsc_lock);
+
 	return fsc;
 
 fail_cap_wq:
@@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
 	dout("destroy_fs_client %p\n", fsc);
 
+	spin_lock(&ceph_fsc_lock);
+	list_del(&fsc->metric_wakeup);
+	spin_unlock(&ceph_fsc_lock);
+
 	ceph_mdsc_destroy(fsc);
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
@@ -1282,6 +1293,37 @@ static void __exit exit_ceph(void)
 	destroy_caches();
 }
 
+static int param_set_metrics(const char *val, const struct kernel_param *kp)
+{
+	struct ceph_fs_client *fsc;
+	int ret;
+
+	ret = param_set_bool(val, kp);
+	if (ret) {
+		pr_err("Failed to parse sending metrics switch value '%s'\n",
+		       val);
+		return ret;
+	} else if (!disable_send_metrics) {
+		// wake up all the mds clients
+		spin_lock(&ceph_fsc_lock);
+		list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) {
+			metric_schedule_delayed(&fsc->mdsc->metric);
+		}
+		spin_unlock(&ceph_fsc_lock);
+	}
+
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_metrics = {
+	.set = param_set_metrics,
+	.get = param_get_bool,
+};
+
+bool disable_send_metrics = false;
+module_param_cb(disable_send_metrics, &param_ops_metrics, &disable_send_metrics, 0644);
+MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
+
 module_init(init_ceph);
 module_exit(exit_ceph);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 5a6cdd39bc10..2dcb6a90c636 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -101,6 +101,8 @@ struct ceph_mount_options {
 struct ceph_fs_client {
 	struct super_block *sb;
 
+	struct list_head metric_wakeup;
+
 	struct ceph_mount_options *mount_options;
 	struct ceph_client *client;
 
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ebf5ba62b772..455e9b9e2adf 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -130,6 +130,7 @@ struct ceph_dir_layout {
 #define CEPH_MSG_CLIENT_REQUEST         24
 #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
 #define CEPH_MSG_CLIENT_REPLY           26
+#define CEPH_MSG_CLIENT_METRICS         29
 #define CEPH_MSG_CLIENT_CAPS            0x310
 #define CEPH_MSG_CLIENT_LEASE           0x311
 #define CEPH_MSG_CLIENT_SNAP            0x312
-- 
cgit v1.2.3


From f1f565a26976612121f97464f9245307422d0ce8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:36:04 -0700
Subject: ceph: delete repeated words in fs/ceph/

Drop duplicated words "down" and "the" in fs/ceph/.

[ idryomov: merge into a single patch ]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/super.c                    | 2 +-
 fs/ceph/super.h                    | 2 +-
 include/linux/ceph/ceph_features.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 933f5df5da7d..585aecea5cad 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -839,7 +839,7 @@ static void destroy_caches(void)
 }
 
 /*
- * ceph_umount_begin - initiate forced umount.  Tear down down the
+ * ceph_umount_begin - initiate forced umount.  Tear down the
  * mount, skipping steps that may hang while waiting for server(s).
  */
 static void ceph_umount_begin(struct super_block *sb)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2dcb6a90c636..9001a896ae8c 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -355,7 +355,7 @@ struct ceph_inode_info {
 	unsigned i_dirty_caps, i_flushing_caps;     /* mask of dirtied fields */
 
 	/*
-	 * Link to the the auth cap's session's s_cap_dirty list. s_cap_dirty
+	 * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty
 	 * is protected by the mdsc->cap_dirty_lock, but each individual item
 	 * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty
 	 * requires the mdsc->cap_dirty_lock. List presence for an item can
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 39e6f4c57580..fcd84e8d88f4 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -58,7 +58,7 @@
  *    because 10.2.z (jewel) did not care if its peers advertised this
  *    feature bit.
  *
- *  - In the second phase we stop advertising the the bit and call it
+ *  - In the second phase we stop advertising the bit and call it
  *    RETIRED.  This can normally be done in the *next* major release
  *    following the one in which we marked the feature DEPRECATED.  In
  *    the above example, for 12.0.z (luminous) we can say:
-- 
cgit v1.2.3


From c9dff08485a6c11449307abde1d7bb404fcee481 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 9 Jul 2020 14:49:30 +0200
Subject: fs: Fix typo in comment

The comment for function filemap_check_wb_err accidentally refers to
it as filemap_check_wb_error.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5abba86107d..f9ae45795c1a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2798,7 +2798,7 @@ static inline void filemap_set_wb_err(struct address_space *mapping, int err)
 }
 
 /**
- * filemap_check_wb_error - has an error occurred since the mark was sampled?
+ * filemap_check_wb_err - has an error occurred since the mark was sampled?
  * @mapping: mapping to check for writeback errors
  * @since: previously-sampled errseq_t
  *
-- 
cgit v1.2.3


From f3751ad0116fb6881f2c3c957d66a9327f69cefb Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Thu, 30 Jul 2020 15:45:54 -0700
Subject: tracepoint: Mark __tracepoint_string's __used

__tracepoint_string's have their string data stored in .rodata, and an
address to that data stored in the "__tracepoint_str" section. Functions
that refer to those strings refer to the symbol of the address. Compiler
optimization can replace those address references with references
directly to the string data. If the address doesn't appear to have other
uses, then it appears dead to the compiler and is removed. This can
break the /tracing/printk_formats sysfs node which iterates the
addresses stored in the "__tracepoint_str" section.

Like other strings stored in custom sections in this header, mark these
__used to inform the compiler that there are other non-obvious users of
the address, so they should still be emitted.

Link: https://lkml.kernel.org/r/20200730224555.2142154-2-ndesaulniers@google.com

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: stable@vger.kernel.org
Fixes: 102c9323c35a8 ("tracing: Add __tracepoint_string() to export string pointers")
Reported-by: Tim Murray <timmurray@google.com>
Reported-by: Simon MacMullen <simonmacm@google.com>
Suggested-by: Greg Hackmann <ghackmann@google.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index a1fecf311621..3a5b717d92e8 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -361,7 +361,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__attribute__((section("__tracepoint_str")))
+#define __tracepoint_string	__attribute__((section("__tracepoint_str"), used))
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
-- 
cgit v1.2.3


From 1c39d761ff5c90227fc582c45018d5922efaa253 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Thu, 30 Jul 2020 15:45:55 -0700
Subject: tracepoint: Use __used attribute definitions from
 compiler_attributes.h

Just a small cleanup while I was touching this header.
compiler_attributes.h does feature detection of these __attributes__(())
and provides more concise ways to invoke them.

Link: https://lkml.kernel.org/r/20200730224555.2142154-3-ndesaulniers@google.com

Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 3a5b717d92e8..598fec9f9dbf 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -116,8 +116,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __TRACEPOINT_ENTRY(name)					 \
 	static tracepoint_ptr_t __tracepoint_ptr_##name __used		 \
-	__attribute__((section("__tracepoints_ptrs"))) =		 \
-		&__tracepoint_##name
+	__section(__tracepoints_ptrs) = &__tracepoint_##name
 #endif
 
 #endif /* _LINUX_TRACEPOINT_H */
@@ -280,9 +279,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  */
 #define DEFINE_TRACE_FN(name, reg, unreg)				 \
 	static const char __tpstrtab_##name[]				 \
-	__attribute__((section("__tracepoints_strings"))) = #name;	 \
-	struct tracepoint __tracepoint_##name				 \
-	__attribute__((section("__tracepoints"), used)) =		 \
+	__section(__tracepoints_strings) = #name;			 \
+	struct tracepoint __tracepoint_##name __used			 \
+	__section(__tracepoints) =					 \
 		{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
 	__TRACEPOINT_ENTRY(name);
 
@@ -361,7 +360,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__attribute__((section("__tracepoint_str"), used))
+#define __tracepoint_string	__used __section(__tracepoint_str)
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
-- 
cgit v1.2.3


From 321bd212619a7269308696e4ddc446930ea73fad Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 24 Jun 2020 18:24:33 -0400
Subject: virtio: VIRTIO_F_IOMMU_PLATFORM -> VIRTIO_F_ACCESS_PLATFORM

Rename the bit to match latest virtio spec.
Add a compat macro to avoid breaking existing userspace.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/um/drivers/virtio_uml.c       |  2 +-
 drivers/vdpa/ifcvf/ifcvf_base.h    |  2 +-
 drivers/vdpa/vdpa_sim/vdpa_sim.c   |  4 ++--
 drivers/vhost/net.c                |  4 ++--
 drivers/vhost/vdpa.c               |  2 +-
 drivers/virtio/virtio_balloon.c    |  2 +-
 drivers/virtio/virtio_ring.c       |  2 +-
 include/linux/virtio_config.h      |  2 +-
 include/uapi/linux/virtio_config.h | 10 +++++++---
 tools/virtio/linux/virtio_config.h |  2 +-
 10 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 351aee52aca6..a6c4bb6c2c01 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data)
 		}
 		break;
 	case VHOST_USER_SLAVE_IOTLB_MSG:
-		/* not supported - VIRTIO_F_IOMMU_PLATFORM */
+		/* not supported - VIRTIO_F_ACCESS_PLATFORM */
 	case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
 		/* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */
 	default:
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index f4554412e607..24af422b5a3e 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -29,7 +29,7 @@
 		 (1ULL << VIRTIO_F_VERSION_1)			| \
 		 (1ULL << VIRTIO_NET_F_STATUS)			| \
 		 (1ULL << VIRTIO_F_ORDER_PLATFORM)		| \
-		 (1ULL << VIRTIO_F_IOMMU_PLATFORM)		| \
+		 (1ULL << VIRTIO_F_ACCESS_PLATFORM)		| \
 		 (1ULL << VIRTIO_NET_F_MRG_RXBUF))
 
 /* Only one queue pair for now. */
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index c7334cc65bb2..a9bc5e0fb353 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -55,7 +55,7 @@ struct vdpasim_virtqueue {
 
 static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
 			      (1ULL << VIRTIO_F_VERSION_1)  |
-			      (1ULL << VIRTIO_F_IOMMU_PLATFORM);
+			      (1ULL << VIRTIO_F_ACCESS_PLATFORM);
 
 /* State of each vdpasim device */
 struct vdpasim {
@@ -450,7 +450,7 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	/* DMA mapping must be done by driver */
-	if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
+	if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
 		return -EINVAL;
 
 	vdpasim->features = features & vdpasim_features;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e992decfec53..8e0921d3805d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -73,7 +73,7 @@ enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
+			 (1ULL << VIRTIO_F_ACCESS_PLATFORM)
 };
 
 enum {
@@ -1653,7 +1653,7 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	    !vhost_log_access_ok(&n->dev))
 		goto out_unlock;
 
-	if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
+	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
 		if (vhost_init_device_iotlb(&n->dev, true))
 			goto out_unlock;
 	}
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index a54b60d6623f..18869a35d408 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -31,7 +31,7 @@ enum {
 		(1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
 		(1ULL << VIRTIO_F_ANY_LAYOUT) |
 		(1ULL << VIRTIO_F_VERSION_1) |
-		(1ULL << VIRTIO_F_IOMMU_PLATFORM) |
+		(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
 		(1ULL << VIRTIO_F_RING_PACKED) |
 		(1ULL << VIRTIO_F_ORDER_PLATFORM) |
 		(1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 8be02f333b7a..54fd989f9353 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1129,7 +1129,7 @@ static int virtballoon_validate(struct virtio_device *vdev)
 	else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
 		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
 
-	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
+	__virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
 	return 0;
 }
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 58b96baa8d48..a1a5c2a91426 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2225,7 +2225,7 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_F_VERSION_1:
 			break;
-		case VIRTIO_F_IOMMU_PLATFORM:
+		case VIRTIO_F_ACCESS_PLATFORM:
 			break;
 		case VIRTIO_F_RING_PACKED:
 			break;
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index bb4cc4910750..f2cc2a0df174 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -171,7 +171,7 @@ static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
 	 * Note the reverse polarity of the quirk feature (compared to most
 	 * other features), this is for compatibility with legacy systems.
 	 */
-	return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+	return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM);
 }
 
 static inline
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index ff8e7dc9d4dd..b5eda06f0d57 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -67,13 +67,17 @@
 #define VIRTIO_F_VERSION_1		32
 
 /*
- * If clear - device has the IOMMU bypass quirk feature.
- * If set - use platform tools to detect the IOMMU.
+ * If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature.
+ * If set - use platform DMA tools to access the memory.
  *
  * Note the reverse polarity (compared to most other features),
  * this is for compatibility with legacy systems.
  */
-#define VIRTIO_F_IOMMU_PLATFORM		33
+#define VIRTIO_F_ACCESS_PLATFORM	33
+#ifndef __KERNEL__
+/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */
+#define VIRTIO_F_IOMMU_PLATFORM		VIRTIO_F_ACCESS_PLATFORM
+#endif /* __KERNEL__ */
 
 /* This feature indicates support for the packed virtqueue layout. */
 #define VIRTIO_F_RING_PACKED		34
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index dbf14c1e2188..f99ae42668e0 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -51,7 +51,7 @@ static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
 	 * Note the reverse polarity of the quirk feature (compared to most
 	 * other features), this is for compatibility with legacy systems.
 	 */
-	return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+	return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM);
 }
 
 static inline bool virtio_is_little_endian(struct virtio_device *vdev)
-- 
cgit v1.2.3


From 24b6842ade6925199e182988259761504aacfbc0 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 24 Jun 2020 19:17:04 -0400
Subject: virtio: virtio_has_iommu_quirk -> virtio_has_dma_quirk

Now that the corresponding feature bit has been renamed,
rename the quirk too - it's about special ways to
do DMA, not necessarily about the IOMMU.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/gpu/drm/virtio/virtgpu_object.c | 2 +-
 drivers/gpu/drm/virtio/virtgpu_vq.c     | 4 ++--
 drivers/virtio/virtio_ring.c            | 2 +-
 include/linux/virtio_config.h           | 4 ++--
 tools/virtio/linux/virtio_config.h      | 4 ++--
 5 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 6ccbd01cd888..e8799ab0c753 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -141,7 +141,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 					struct virtio_gpu_mem_entry **ents,
 					unsigned int *nents)
 {
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 	struct scatterlist *sg;
 	int si, ret;
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 9e663a5d9952..53af60d484a4 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -599,7 +599,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
 	struct virtio_gpu_transfer_to_host_2d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)
@@ -1015,7 +1015,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
 	struct virtio_gpu_transfer_host_3d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index a1a5c2a91426..34253cb69cb8 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -240,7 +240,7 @@ static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
 
 static bool vring_use_dma_api(struct virtio_device *vdev)
 {
-	if (!virtio_has_iommu_quirk(vdev))
+	if (!virtio_has_dma_quirk(vdev))
 		return true;
 
 	/* Otherwise, we are left to guess. */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index f2cc2a0df174..3b4eae5ac5e3 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -162,10 +162,10 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 }
 
 /**
- * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * virtio_has_dma_quirk - determine whether this device has the DMA quirk
  * @vdev: the device
  */
-static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev)
 {
 	/*
 	 * Note the reverse polarity of the quirk feature (compared to most
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index f99ae42668e0..f2640e505c4e 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -42,10 +42,10 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 	(__virtio_test_bit((dev), feature))
 
 /**
- * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * virtio_has_dma_quirk - determine whether this device has the DMA quirk
  * @vdev: the device
  */
-static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev)
 {
 	/*
 	 * Note the reverse polarity of the quirk feature (compared to most
-- 
cgit v1.2.3


From 80a6e707dd9742390776a9306b400b1fbe405b4a Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Fri, 17 Jul 2020 17:42:55 +0900
Subject: kprobes: Remove show_registers() function prototype

Remove show_registers() function prototype because this function
has been renamed by commit 57da8b960b9a ("x86: Avoid double stack
traces with show_regs()"), and commit 80006dbee674 ("kprobes/x86:
Remove jprobe implementation") has removed the caller in kprobes.
So this doesn't exist anymore.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/kprobes.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 6adf90f248d7..81cb7e00ccdc 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
-extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
-- 
cgit v1.2.3


From 6cfde88418fe95240e32d2955b51988360ee0942 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Sat, 1 Aug 2020 10:53:42 +0200
Subject: clk: drop unused function __clk_get_flags

The function __clk_get_flags has not been used since the April 2019
commit a348f05361c9 ("ARM: omap2+: hwmod: drop CLK_IS_BASIC
flag usage").  Other uses were removed in June 2015, eg by
commit 98d8a60eccee ("clk: Convert __clk_get_flags() to
clk_hw_get_flags()"), which shows how clk_hw_get_flags can easily
be used instead.

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Link: https://lore.kernel.org/r/1596272022-14173-1-git-send-email-Julia.Lawall@inria.fr
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c            | 6 ------
 include/linux/clk-provider.h | 1 -
 2 files changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 3f588ed06ce3..d71456aad11d 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -500,12 +500,6 @@ static unsigned long clk_core_get_accuracy_no_lock(struct clk_core *core)
 	return core->accuracy;
 }
 
-unsigned long __clk_get_flags(struct clk *clk)
-{
-	return !clk ? 0 : clk->core->flags;
-}
-EXPORT_SYMBOL_GPL(__clk_get_flags);
-
 unsigned long clk_hw_get_flags(const struct clk_hw *hw)
 {
 	return hw->core->flags;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index bd1ee9039558..93a78a5256d1 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1096,7 +1096,6 @@ int clk_hw_get_parent_index(struct clk_hw *hw);
 int clk_hw_set_parent(struct clk_hw *hw, struct clk_hw *new_parent);
 unsigned int __clk_get_enable_count(struct clk *clk);
 unsigned long clk_hw_get_rate(const struct clk_hw *hw);
-unsigned long __clk_get_flags(struct clk *clk);
 unsigned long clk_hw_get_flags(const struct clk_hw *hw);
 #define clk_hw_can_set_rate_parent(hw) \
 	(clk_hw_get_flags((hw)) & CLK_SET_RATE_PARENT)
-- 
cgit v1.2.3


From bb3831294cd50750806f2ce8d73317dc8feeda09 Mon Sep 17 00:00:00 2001
From: Bruno Thomsen <bruno.thomsen@gmail.com>
Date: Thu, 30 Jul 2020 21:57:48 +0200
Subject: net: mdiobus: add reset-post-delay-us handling

Load new "reset-post-delay-us" value from MDIO properties,
and if configured to a greater then zero delay do a
flexible sleeping delay after MDIO bus reset deassert.
This allows devices to exit reset state before start
bus communication.

Signed-off-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 2 ++
 drivers/of/of_mdio.c       | 2 ++
 include/linux/phy.h        | 2 ++
 3 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 5df3782b05b4..0af20faad69d 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -556,6 +556,8 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 		gpiod_set_value_cansleep(gpiod, 1);
 		fsleep(bus->reset_delay_us);
 		gpiod_set_value_cansleep(gpiod, 0);
+		if (bus->reset_post_delay_us > 0)
+			fsleep(bus->reset_post_delay_us);
 	}
 
 	if (bus->reset) {
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index eb84507de28a..cb32d7ef4938 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -268,6 +268,8 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 	/* Get bus level PHY reset GPIO details */
 	mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY;
 	of_property_read_u32(np, "reset-delay-us", &mdio->reset_delay_us);
+	mdio->reset_post_delay_us = 0;
+	of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us);
 
 	/* Register the MDIO bus */
 	rc = mdiobus_register(mdio);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 0403eb799913..3a09d2bf69ea 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -293,6 +293,8 @@ struct mii_bus {
 
 	/* GPIO reset pulse width in microseconds */
 	int reset_delay_us;
+	/* GPIO reset deassert delay in microseconds */
+	int reset_post_delay_us;
 	/* RESET GPIO descriptor pointer */
 	struct gpio_desc *reset_gpiod;
 
-- 
cgit v1.2.3


From 038ebb1a713d114d54dbf14868a73181c0c92758 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Fri, 31 Jul 2020 10:45:01 +0800
Subject: net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct

When openvswitch conntrack offload with act_ct action. Fragment packets
defrag in the ingress tc act_ct action and miss the next chain. Then the
packet pass to the openvswitch datapath without the mru. The over
mtu packet will be dropped in output action in openvswitch for over mtu.

"kernel: net2: dropped over-mtu packet: 1528 > 1500"

This patch add mru in the tc_skb_ext for adefrag and miss next chain
situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru
to the qdisc_skb_cb when the packet defrag. And When the chain miss,
The mru is set to tc_skb_ext which can be got by ovs datapath.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 1 +
 include/net/sch_generic.h | 3 ++-
 net/openvswitch/flow.c    | 1 +
 net/sched/act_ct.c        | 8 ++++++--
 net/sched/cls_api.c       | 1 +
 5 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fa817a105517..3ad65d4ce085 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -283,6 +283,7 @@ struct nf_bridge_info {
  */
 struct tc_skb_ext {
 	__u32 chain;
+	__u16 mru;
 };
 #endif
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c510b03b9751..d60e7c39d60c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -384,6 +384,7 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
+	u16			mru;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
@@ -463,7 +464,7 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;
 
-	BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz);
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb));
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d375e74b607..03942c30d83e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -890,6 +890,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	if (static_branch_unlikely(&tc_recirc_sharing_support)) {
 		tc_ext = skb_ext_find(skb, TC_SKB_EXT);
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
+		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 	} else {
 		key->recirc_id = 0;
 	}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 97e27946897f..e6ad42b11835 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -706,8 +706,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IPCB(skb)->frag_max_size;
+		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
@@ -717,8 +719,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IP6CB(skb)->frag_max_size;
+		}
 #else
 		err = -EOPNOTSUPP;
 		goto out_free;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b8623b3b24f..41a55c6cbeb8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
+		ext->mru = qdisc_skb_cb(skb)->mru;
 	}
 
 	return ret;
-- 
cgit v1.2.3


From 5f402bb17533113c21d61c2d4bc4ef4a6fa1c9a5 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Fri, 31 Jul 2020 14:38:36 +0200
Subject: gpio: don't use same lockdep class for all devm_gpiochip_add_data
 users

Commit 959bc7b22bd2 ("gpio: Automatically add lockdep keys") documents
in its commits message its intention to "create a unique class key for
each driver".

It does so by having gpiochip_add_data add in-place the definition of
two static lockdep classes for LOCKDEP use. That way, every caller of
the macro adds their gpiochip with unique lockdep classes.

There are many indirect callers of gpiochip_add_data, however, via
use of devm_gpiochip_add_data. devm_gpiochip_add_data has external
linkage and all its users will share the same lockdep classes, which
probably is not intended.

Fix this by replicating the gpio_chip_add_data statics-in-macro for
the devm_ version as well.

Fixes: 959bc7b22bd2 ("gpio: Automatically add lockdep keys")
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Link: https://lore.kernel.org/r/20200731123835.8003-1-a.fatoum@pengutronix.de
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-devres.c | 13 ++++++++-----
 include/linux/gpio/driver.h   | 13 +++++++++++--
 2 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c
index 5c91c4365da1..7dbce4c4ebdf 100644
--- a/drivers/gpio/gpiolib-devres.c
+++ b/drivers/gpio/gpiolib-devres.c
@@ -487,10 +487,12 @@ static void devm_gpio_chip_release(struct device *dev, void *res)
 }
 
 /**
- * devm_gpiochip_add_data() - Resource managed gpiochip_add_data()
+ * devm_gpiochip_add_data_with_key() - Resource managed gpiochip_add_data_with_key()
  * @dev: pointer to the device that gpio_chip belongs to.
  * @gc: the GPIO chip to register
  * @data: driver-private data associated with this chip
+ * @lock_key: lockdep class for IRQ lock
+ * @request_key: lockdep class for IRQ request
  *
  * Context: potentially before irqs will work
  *
@@ -501,8 +503,9 @@ static void devm_gpio_chip_release(struct device *dev, void *res)
  * gc->base is invalid or already associated with a different chip.
  * Otherwise it returns zero as a success code.
  */
-int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *gc,
-			   void *data)
+int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data,
+				    struct lock_class_key *lock_key,
+				    struct lock_class_key *request_key)
 {
 	struct gpio_chip **ptr;
 	int ret;
@@ -512,7 +515,7 @@ int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *gc,
 	if (!ptr)
 		return -ENOMEM;
 
-	ret = gpiochip_add_data(gc, data);
+	ret = gpiochip_add_data_with_key(gc, data, lock_key, request_key);
 	if (ret < 0) {
 		devres_free(ptr);
 		return ret;
@@ -523,4 +526,4 @@ int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *gc,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(devm_gpiochip_add_data);
+EXPORT_SYMBOL_GPL(devm_gpiochip_add_data_with_key);
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 6e9f1826ecd7..d1cef5c2715c 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -525,8 +525,16 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		gpiochip_add_data_with_key(gc, data, &lock_key, \
 					   &request_key);	  \
 	})
+#define devm_gpiochip_add_data(dev, gc, data) ({ \
+		static struct lock_class_key lock_key;	\
+		static struct lock_class_key request_key;	  \
+		devm_gpiochip_add_data_with_key(dev, gc, data, &lock_key, \
+					   &request_key);	  \
+	})
 #else
 #define gpiochip_add_data(gc, data) gpiochip_add_data_with_key(gc, data, NULL, NULL)
+#define devm_gpiochip_add_data(dev, gc, data) \
+	devm_gpiochip_add_data_with_key(dev, gc, data, NULL, NULL)
 #endif /* CONFIG_LOCKDEP */
 
 static inline int gpiochip_add(struct gpio_chip *gc)
@@ -534,8 +542,9 @@ static inline int gpiochip_add(struct gpio_chip *gc)
 	return gpiochip_add_data(gc, NULL);
 }
 extern void gpiochip_remove(struct gpio_chip *gc);
-extern int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *gc,
-				  void *data);
+extern int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data,
+					   struct lock_class_key *lock_key,
+					   struct lock_class_key *request_key);
 
 extern struct gpio_chip *gpiochip_find(void *data,
 			      int (*match)(struct gpio_chip *gc, void *data));
-- 
cgit v1.2.3


From 6c84a589972f6458da3168a68e7d65f6ca8687f8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 3 Aug 2020 13:03:52 -0700
Subject: net: dsa: loop: Move data structures to header

In preparation for adding support for a mockup data path, move the
driver data structures to include/linux/dsa/loop.h such that we can
share them between net/dsa/ and drivers/net/dsa/ later on.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/dsa_loop.c | 32 +-------------------------------
 include/linux/dsa/loop.h   | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 31 deletions(-)
 create mode 100644 include/linux/dsa/loop.h

(limited to 'include/linux')

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index 6e97b44c6f3f..ed0b580c9944 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -14,28 +14,11 @@
 #include <linux/workqueue.h>
 #include <linux/module.h>
 #include <linux/if_bridge.h>
+#include <linux/dsa/loop.h>
 #include <net/dsa.h>
 
 #include "dsa_loop.h"
 
-struct dsa_loop_vlan {
-	u16 members;
-	u16 untagged;
-};
-
-struct dsa_loop_mib_entry {
-	char name[ETH_GSTRING_LEN];
-	unsigned long val;
-};
-
-enum dsa_loop_mib_counters {
-	DSA_LOOP_PHY_READ_OK,
-	DSA_LOOP_PHY_READ_ERR,
-	DSA_LOOP_PHY_WRITE_OK,
-	DSA_LOOP_PHY_WRITE_ERR,
-	__DSA_LOOP_CNT_MAX,
-};
-
 static struct dsa_loop_mib_entry dsa_loop_mibs[] = {
 	[DSA_LOOP_PHY_READ_OK]	= { "phy_read_ok", },
 	[DSA_LOOP_PHY_READ_ERR]	= { "phy_read_err", },
@@ -43,19 +26,6 @@ static struct dsa_loop_mib_entry dsa_loop_mibs[] = {
 	[DSA_LOOP_PHY_WRITE_ERR] = { "phy_write_err", },
 };
 
-struct dsa_loop_port {
-	struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX];
-	u16 pvid;
-};
-
-struct dsa_loop_priv {
-	struct mii_bus	*bus;
-	unsigned int	port_base;
-	struct dsa_loop_vlan vlans[VLAN_N_VID];
-	struct net_device *netdev;
-	struct dsa_loop_port ports[DSA_MAX_PORTS];
-};
-
 static struct phy_device *phydevs[PHY_MAX_ADDR];
 
 static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds,
diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h
new file mode 100644
index 000000000000..bb39401a8056
--- /dev/null
+++ b/include/linux/dsa/loop.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef DSA_LOOP_H
+#define DSA_LOOP_H
+
+#include <linux/types.h>
+#include <linux/ethtool.h>
+#include <net/dsa.h>
+
+struct dsa_loop_vlan {
+	u16 members;
+	u16 untagged;
+};
+
+struct dsa_loop_mib_entry {
+	char name[ETH_GSTRING_LEN];
+	unsigned long val;
+};
+
+enum dsa_loop_mib_counters {
+	DSA_LOOP_PHY_READ_OK,
+	DSA_LOOP_PHY_READ_ERR,
+	DSA_LOOP_PHY_WRITE_OK,
+	DSA_LOOP_PHY_WRITE_ERR,
+	__DSA_LOOP_CNT_MAX,
+};
+
+struct dsa_loop_port {
+	struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX];
+	u16 pvid;
+};
+
+struct dsa_loop_priv {
+	struct mii_bus	*bus;
+	unsigned int	port_base;
+	struct dsa_loop_vlan vlans[VLAN_N_VID];
+	struct net_device *netdev;
+	struct dsa_loop_port ports[DSA_MAX_PORTS];
+};
+
+#endif /* DSA_LOOP_H */
-- 
cgit v1.2.3


From c99194eded25deb58f606e59b3101ba05e786021 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 3 Aug 2020 13:03:53 -0700
Subject: net: dsa: loop: Wire-up MTU callbacks

For now we simply store the port MTU into a per-port member.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/dsa_loop.c | 17 +++++++++++++++++
 include/linux/dsa/loop.h   |  1 +
 2 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index ed0b580c9944..6a7d661b5a59 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -225,6 +225,21 @@ static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+static int dsa_loop_port_change_mtu(struct dsa_switch *ds, int port,
+				    int new_mtu)
+{
+	struct dsa_loop_priv *priv = ds->priv;
+
+	priv->ports[port].mtu = new_mtu;
+
+	return 0;
+}
+
+static int dsa_loop_port_max_mtu(struct dsa_switch *ds, int port)
+{
+	return ETH_MAX_MTU;
+}
+
 static const struct dsa_switch_ops dsa_loop_driver = {
 	.get_tag_protocol	= dsa_loop_get_protocol,
 	.setup			= dsa_loop_setup,
@@ -241,6 +256,8 @@ static const struct dsa_switch_ops dsa_loop_driver = {
 	.port_vlan_prepare	= dsa_loop_port_vlan_prepare,
 	.port_vlan_add		= dsa_loop_port_vlan_add,
 	.port_vlan_del		= dsa_loop_port_vlan_del,
+	.port_change_mtu	= dsa_loop_port_change_mtu,
+	.port_max_mtu		= dsa_loop_port_max_mtu,
 };
 
 static int dsa_loop_drv_probe(struct mdio_device *mdiodev)
diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h
index bb39401a8056..5a3470bcc8a7 100644
--- a/include/linux/dsa/loop.h
+++ b/include/linux/dsa/loop.h
@@ -27,6 +27,7 @@ enum dsa_loop_mib_counters {
 struct dsa_loop_port {
 	struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX];
 	u16 pvid;
+	int mtu;
 };
 
 struct dsa_loop_priv {
-- 
cgit v1.2.3


From 0858fde496f84fff2fdae53d9e33c7b308195f74 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Sun, 5 Jul 2020 14:37:14 +0800
Subject: mailbox: cmdq: variablize address shift in platform

Some gce hardware shift pc and end address in register to support
large dram addressing.
Implement gce address shift when write or read pc and end register.
And add shift bit in platform definition.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c       | 57 ++++++++++++++++++++++++--------
 include/linux/mailbox/mtk-cmdq-mailbox.h |  2 ++
 2 files changed, 46 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index b24822ad8409..49d9264145aa 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -75,8 +75,22 @@ struct cmdq {
 	struct cmdq_thread	*thread;
 	struct clk		*clock;
 	bool			suspended;
+	u8			shift_pa;
 };
 
+struct gce_plat {
+	u32 thread_nr;
+	u8 shift;
+};
+
+u8 cmdq_get_shift_pa(struct mbox_chan *chan)
+{
+	struct cmdq *cmdq = container_of(chan->mbox, struct cmdq, mbox);
+
+	return cmdq->shift_pa;
+}
+EXPORT_SYMBOL(cmdq_get_shift_pa);
+
 static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
 {
 	u32 status;
@@ -183,13 +197,15 @@ static void cmdq_task_handle_error(struct cmdq_task *task)
 {
 	struct cmdq_thread *thread = task->thread;
 	struct cmdq_task *next_task;
+	struct cmdq *cmdq = task->cmdq;
 
-	dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task);
-	WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0);
+	dev_err(cmdq->mbox.dev, "task 0x%p error\n", task);
+	WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
 	next_task = list_first_entry_or_null(&thread->task_busy_list,
 			struct cmdq_task, list_entry);
 	if (next_task)
-		writel(next_task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
+		writel(next_task->pa_base >> cmdq->shift_pa,
+		       thread->base + CMDQ_THR_CURR_ADDR);
 	cmdq_thread_resume(thread);
 }
 
@@ -219,7 +235,7 @@ static void cmdq_thread_irq_handler(struct cmdq *cmdq,
 	else
 		return;
 
-	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR) << cmdq->shift_pa;
 
 	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
 				 list_entry) {
@@ -335,27 +351,31 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
 		WARN_ON(clk_enable(cmdq->clock) < 0);
 		WARN_ON(cmdq_thread_reset(cmdq, thread) < 0);
 
-		writel(task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
-		writel(task->pa_base + pkt->cmd_buf_size,
+		writel(task->pa_base >> cmdq->shift_pa,
+		       thread->base + CMDQ_THR_CURR_ADDR);
+		writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->shift_pa,
 		       thread->base + CMDQ_THR_END_ADDR);
+
 		writel(thread->priority, thread->base + CMDQ_THR_PRIORITY);
 		writel(CMDQ_THR_IRQ_EN, thread->base + CMDQ_THR_IRQ_ENABLE);
 		writel(CMDQ_THR_ENABLED, thread->base + CMDQ_THR_ENABLE_TASK);
 	} else {
 		WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
-		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
-		end_pa = readl(thread->base + CMDQ_THR_END_ADDR);
+		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR) <<
+			cmdq->shift_pa;
+		end_pa = readl(thread->base + CMDQ_THR_END_ADDR) <<
+			cmdq->shift_pa;
 		/* check boundary */
 		if (curr_pa == end_pa - CMDQ_INST_SIZE ||
 		    curr_pa == end_pa) {
 			/* set to this task directly */
-			writel(task->pa_base,
+			writel(task->pa_base >> cmdq->shift_pa,
 			       thread->base + CMDQ_THR_CURR_ADDR);
 		} else {
 			cmdq_task_insert_into_thread(task);
 			smp_mb(); /* modify jump before enable thread */
 		}
-		writel(task->pa_base + pkt->cmd_buf_size,
+		writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->shift_pa,
 		       thread->base + CMDQ_THR_END_ADDR);
 		cmdq_thread_resume(thread);
 	}
@@ -453,6 +473,7 @@ static int cmdq_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct cmdq *cmdq;
 	int err, i;
+	struct gce_plat *plat_data;
 
 	cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL);
 	if (!cmdq)
@@ -471,7 +492,14 @@ static int cmdq_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev);
+	plat_data = (struct gce_plat *)of_device_get_match_data(dev);
+	if (!plat_data) {
+		dev_err(dev, "failed to get match data\n");
+		return -EINVAL;
+	}
+
+	cmdq->thread_nr = plat_data->thread_nr;
+	cmdq->shift_pa = plat_data->shift;
 	cmdq->irq_mask = GENMASK(cmdq->thread_nr - 1, 0);
 	err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED,
 			       "mtk_cmdq", cmdq);
@@ -534,9 +562,12 @@ static const struct dev_pm_ops cmdq_pm_ops = {
 	.resume = cmdq_resume,
 };
 
+static const struct gce_plat gce_plat_v2 = {.thread_nr = 16};
+static const struct gce_plat gce_plat_v3 = {.thread_nr = 24};
+
 static const struct of_device_id cmdq_of_ids[] = {
-	{.compatible = "mediatek,mt8173-gce", .data = (void *)16},
-	{.compatible = "mediatek,mt8183-gce", .data = (void *)24},
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_v2},
+	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_v3},
 	{}
 };
 
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index a4dc45fbec0a..c342b8799be8 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -88,4 +88,6 @@ struct cmdq_pkt {
 	void			*cl;
 };
 
+u8 cmdq_get_shift_pa(struct mbox_chan *chan);
+
 #endif /* __MTK_CMDQ_MAILBOX_H__ */
-- 
cgit v1.2.3


From d88ca7e1a27eb2df056bbf37ddef62e1c73d37ea Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Date: Thu, 30 Jul 2020 19:47:14 +0900
Subject: fbmem: pull fbcon_update_vcs() out of fb_set_var()

syzbot is reporting OOB read bug in vc_do_resize() [1] caused by memcpy()
based on outdated old_{rows,row_size} values, for resize_screen() can
recurse into vc_do_resize() which changes vc->vc_{cols,rows} that outdates
old_{rows,row_size} values which were saved before calling resize_screen().

Daniel Vetter explained that resize_screen() should not recurse into
fbcon_update_vcs() path due to FBINFO_MISC_USEREVENT being still set
when calling resize_screen().

Instead of masking FBINFO_MISC_USEREVENT before calling fbcon_update_vcs(),
we can remove FBINFO_MISC_USEREVENT by calling fbcon_update_vcs() only if
fb_set_var() returned 0. This change assumes that it is harmless to call
fbcon_update_vcs() when fb_set_var() returned 0 without reaching
fb_notifier_call_chain().

[1] https://syzkaller.appspot.com/bug?id=c70c88cfd16dcf6e1d3c7f0ab8648b3144b5b25e

Reported-and-tested-by: syzbot <syzbot+c37a14770d51a085a520@syzkaller.appspotmail.com>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: kernel test robot <lkp@intel.com> for missing #include
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/075b7e37-3278-cd7d-31ab-c5073cfa8e92@i-love.sakura.ne.jp
---
 drivers/video/fbdev/core/fbmem.c   | 8 ++------
 drivers/video/fbdev/core/fbsysfs.c | 4 ++--
 drivers/video/fbdev/ps3fb.c        | 5 +++--
 include/linux/fb.h                 | 2 --
 4 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 30e73ec4ad5c..da7c88ffaa6a 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -957,7 +957,6 @@ static int fb_check_caps(struct fb_info *info, struct fb_var_screeninfo *var,
 int
 fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 {
-	int flags = info->flags;
 	int ret = 0;
 	u32 activate;
 	struct fb_var_screeninfo old_var;
@@ -1052,9 +1051,6 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 	event.data = &mode;
 	fb_notifier_call_chain(FB_EVENT_MODE_CHANGE, &event);
 
-	if (flags & FBINFO_MISC_USEREVENT)
-		fbcon_update_vcs(info, activate & FB_ACTIVATE_ALL);
-
 	return 0;
 }
 EXPORT_SYMBOL(fb_set_var);
@@ -1105,9 +1101,9 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
 			return -EFAULT;
 		console_lock();
 		lock_fb_info(info);
-		info->flags |= FBINFO_MISC_USEREVENT;
 		ret = fb_set_var(info, &var);
-		info->flags &= ~FBINFO_MISC_USEREVENT;
+		if (!ret)
+			fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL);
 		unlock_fb_info(info);
 		console_unlock();
 		if (!ret && copy_to_user(argp, &var, sizeof(var)))
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index d54c88f88991..65dae05fff8e 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -91,9 +91,9 @@ static int activate(struct fb_info *fb_info, struct fb_var_screeninfo *var)
 
 	var->activate |= FB_ACTIVATE_FORCE;
 	console_lock();
-	fb_info->flags |= FBINFO_MISC_USEREVENT;
 	err = fb_set_var(fb_info, var);
-	fb_info->flags &= ~FBINFO_MISC_USEREVENT;
+	if (!err)
+		fbcon_update_vcs(fb_info, var->activate & FB_ACTIVATE_ALL);
 	console_unlock();
 	if (err)
 		return err;
diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
index 9df78fb77267..203c254f8f6c 100644
--- a/drivers/video/fbdev/ps3fb.c
+++ b/drivers/video/fbdev/ps3fb.c
@@ -29,6 +29,7 @@
 #include <linux/freezer.h>
 #include <linux/uaccess.h>
 #include <linux/fb.h>
+#include <linux/fbcon.h>
 #include <linux/init.h>
 
 #include <asm/cell-regs.h>
@@ -824,12 +825,12 @@ static int ps3fb_ioctl(struct fb_info *info, unsigned int cmd,
 				var = info->var;
 				fb_videomode_to_var(&var, vmode);
 				console_lock();
-				info->flags |= FBINFO_MISC_USEREVENT;
 				/* Force, in case only special bits changed */
 				var.activate |= FB_ACTIVATE_FORCE;
 				par->new_mode_id = val;
 				retval = fb_set_var(info, &var);
-				info->flags &= ~FBINFO_MISC_USEREVENT;
+				if (!retval)
+					fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL);
 				console_unlock();
 			}
 			break;
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 2b530e6d86e4..850f79e9a7cb 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -400,8 +400,6 @@ struct fb_tile_ops {
 #define FBINFO_HWACCEL_YPAN		0x2000 /* optional */
 #define FBINFO_HWACCEL_YWRAP		0x4000 /* optional */
 
-#define FBINFO_MISC_USEREVENT          0x10000 /* event request
-						  from userspace */
 #define FBINFO_MISC_TILEBLITTING       0x20000 /* use tile blitting */
 
 /* A driver may set this flag to indicate that it does want a set_par to be
-- 
cgit v1.2.3


From c0842fbc1b18c7a044e6ff3e8fa78bfa822c7d1a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 31 Jul 2020 07:51:14 +0200
Subject: random32: move the pseudo-random 32-bit definitions to prandom.h

The addition of percpu.h to the list of includes in random.h revealed
some circular dependencies on arm64 and possibly other platforms.  This
include was added solely for the pseudo-random definitions, which have
nothing to do with the rest of the definitions in this file but are
still there for legacy reasons.

This patch moves the pseudo-random parts to linux/prandom.h and the
percpu.h include with it, which is now guarded by _LINUX_PRANDOM_H and
protected against recursive inclusion.

A further cleanup step would be to remove this from <linux/random.h>
entirely, and make people who use the prandom infrastructure include
just the new header file.  That's a bit of a churn patch, but grepping
for "prandom_" and "next_pseudo_random32" "struct rnd_state" should
catch most users.

But it turns out that that nice cleanup step is fairly painful, because
a _lot_ of code currently seems to depend on the implicit include of
<linux/random.h>, which can currently come in a lot of ways, including
such fairly core headfers as <linux/net.h>.

So the "nice cleanup" part may or may never happen.

Fixes: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h")
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/prandom.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/random.h  | 66 +++--------------------------------------
 2 files changed, 82 insertions(+), 62 deletions(-)
 create mode 100644 include/linux/prandom.h

(limited to 'include/linux')

diff --git a/include/linux/prandom.h b/include/linux/prandom.h
new file mode 100644
index 000000000000..aa16e6468f91
--- /dev/null
+++ b/include/linux/prandom.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/prandom.h
+ *
+ * Include file for the fast pseudo-random 32-bit
+ * generation.
+ */
+#ifndef _LINUX_PRANDOM_H
+#define _LINUX_PRANDOM_H
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+
+u32 prandom_u32(void);
+void prandom_bytes(void *buf, size_t nbytes);
+void prandom_seed(u32 seed);
+void prandom_reseed_late(void);
+
+struct rnd_state {
+	__u32 s1, s2, s3, s4;
+};
+
+DECLARE_PER_CPU(struct rnd_state, net_rand_state);
+
+u32 prandom_u32_state(struct rnd_state *state);
+void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
+void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
+
+#define prandom_init_once(pcpu_state)			\
+	DO_ONCE(prandom_seed_full_state, (pcpu_state))
+
+/**
+ * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
+ * @ep_ro: right open interval endpoint
+ *
+ * Returns a pseudo-random number that is in interval [0, ep_ro). Note
+ * that the result depends on PRNG being well distributed in [0, ~0U]
+ * u32 space. Here we use maximally equidistributed combined Tausworthe
+ * generator, that is, prandom_u32(). This is useful when requesting a
+ * random index of an array containing ep_ro elements, for example.
+ *
+ * Returns: pseudo-random number in interval [0, ep_ro)
+ */
+static inline u32 prandom_u32_max(u32 ep_ro)
+{
+	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
+}
+
+/*
+ * Handle minimum values for seeds
+ */
+static inline u32 __seed(u32 x, u32 m)
+{
+	return (x < m) ? x + m : x;
+}
+
+/**
+ * prandom_seed_state - set seed for prandom_u32_state().
+ * @state: pointer to state structure to receive the seed.
+ * @seed: arbitrary 64-bit value to use as a seed.
+ */
+static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
+{
+	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
+
+	state->s1 = __seed(i,   2U);
+	state->s2 = __seed(i,   8U);
+	state->s3 = __seed(i,  16U);
+	state->s4 = __seed(i, 128U);
+}
+
+/* Pseudo random number generator from numerical recipes. */
+static inline u32 next_pseudo_random32(u32 seed)
+{
+	return seed * 1664525 + 1013904223;
+}
+
+#endif
diff --git a/include/linux/random.h b/include/linux/random.h
index 9ab7443bd91b..f45b8be3e3c4 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/once.h>
-#include <asm/percpu.h>
 
 #include <uapi/linux/random.h>
 
@@ -111,63 +110,12 @@ declare_get_random_var_wait(long)
 
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
-u32 prandom_u32(void);
-void prandom_bytes(void *buf, size_t nbytes);
-void prandom_seed(u32 seed);
-void prandom_reseed_late(void);
-
-struct rnd_state {
-	__u32 s1, s2, s3, s4;
-};
-
-DECLARE_PER_CPU(struct rnd_state, net_rand_state);
-
-u32 prandom_u32_state(struct rnd_state *state);
-void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
-void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
-
-#define prandom_init_once(pcpu_state)			\
-	DO_ONCE(prandom_seed_full_state, (pcpu_state))
-
-/**
- * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
- * @ep_ro: right open interval endpoint
- *
- * Returns a pseudo-random number that is in interval [0, ep_ro). Note
- * that the result depends on PRNG being well distributed in [0, ~0U]
- * u32 space. Here we use maximally equidistributed combined Tausworthe
- * generator, that is, prandom_u32(). This is useful when requesting a
- * random index of an array containing ep_ro elements, for example.
- *
- * Returns: pseudo-random number in interval [0, ep_ro)
- */
-static inline u32 prandom_u32_max(u32 ep_ro)
-{
-	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
-}
-
 /*
- * Handle minimum values for seeds
- */
-static inline u32 __seed(u32 x, u32 m)
-{
-	return (x < m) ? x + m : x;
-}
-
-/**
- * prandom_seed_state - set seed for prandom_u32_state().
- * @state: pointer to state structure to receive the seed.
- * @seed: arbitrary 64-bit value to use as a seed.
+ * This is designed to be standalone for just prandom
+ * users, but for now we include it from <linux/random.h>
+ * for legacy reasons.
  */
-static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
-{
-	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
-
-	state->s1 = __seed(i,   2U);
-	state->s2 = __seed(i,   8U);
-	state->s3 = __seed(i,  16U);
-	state->s4 = __seed(i, 128U);
-}
+#include <linux/prandom.h>
 
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
@@ -210,10 +158,4 @@ static inline bool __init arch_get_random_long_early(unsigned long *v)
 }
 #endif
 
-/* Pseudo random number generator from numerical recipes. */
-static inline u32 next_pseudo_random32(u32 seed)
-{
-	return seed * 1664525 + 1013904223;
-}
-
 #endif /* _LINUX_RANDOM_H */
-- 
cgit v1.2.3


From 403d2d116ec011942a8505068b943c5c6cd91176 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 31 Jul 2020 19:03:26 +0200
Subject: PM: runtime: Add kerneldoc comments to multiple helpers

Add kerneldoc comments to multiple PM-runtime helper functions
defined as static inline wrappers around lower-level routines to
provide quick reference decumentation of their behavior.

Some of them are similar to each other with subtle differences only
and the behavior of some of them may appear as counter-intuitive, so
clarify all that to avoid confusion.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 include/linux/pm_runtime.h | 246 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 246 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 3dbc207bff53..6245caa18034 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -60,58 +60,151 @@ extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
 extern void pm_runtime_drop_link(struct device *dev);
 
+/**
+ * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
+ * @dev: Target device.
+ *
+ * Increment the runtime PM usage counter of @dev if its runtime PM status is
+ * %RPM_ACTIVE and its runtime PM usage counter is greater than 0.
+ */
 static inline int pm_runtime_get_if_in_use(struct device *dev)
 {
 	return pm_runtime_get_if_active(dev, false);
 }
 
+/**
+ * pm_suspend_ignore_children - Set runtime PM behavior regarding children.
+ * @dev: Target device.
+ * @enable: Whether or not to ignore possible dependencies on children.
+ *
+ * The dependencies of @dev on its children will not be taken into account by
+ * the runtime PM framework going forward if @enable is %true, or they will
+ * be taken into account otherwise.
+ */
 static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
 {
 	dev->power.ignore_children = enable;
 }
 
+/**
+ * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device.
+ * @dev: Target device.
+ */
 static inline void pm_runtime_get_noresume(struct device *dev)
 {
 	atomic_inc(&dev->power.usage_count);
 }
 
+/**
+ * pm_runtime_put_noidle - Drop runtime PM usage counter of a device.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev unless it is 0 already.
+ */
 static inline void pm_runtime_put_noidle(struct device *dev)
 {
 	atomic_add_unless(&dev->power.usage_count, -1, 0);
 }
 
+/**
+ * pm_runtime_suspended - Check whether or not a device is runtime-suspended.
+ * @dev: Target device.
+ *
+ * Return %true if runtime PM is enabled for @dev and its runtime PM status is
+ * %RPM_SUSPENDED, or %false otherwise.
+ *
+ * Note that the return value of this function can only be trusted if it is
+ * called under the runtime PM lock of @dev or under conditions in which
+ * runtime PM cannot be either disabled or enabled for @dev and its runtime PM
+ * status cannot change.
+ */
 static inline bool pm_runtime_suspended(struct device *dev)
 {
 	return dev->power.runtime_status == RPM_SUSPENDED
 		&& !dev->power.disable_depth;
 }
 
+/**
+ * pm_runtime_active - Check whether or not a device is runtime-active.
+ * @dev: Target device.
+ *
+ * Return %true if runtime PM is enabled for @dev and its runtime PM status is
+ * %RPM_ACTIVE, or %false otherwise.
+ *
+ * Note that the return value of this function can only be trusted if it is
+ * called under the runtime PM lock of @dev or under conditions in which
+ * runtime PM cannot be either disabled or enabled for @dev and its runtime PM
+ * status cannot change.
+ */
 static inline bool pm_runtime_active(struct device *dev)
 {
 	return dev->power.runtime_status == RPM_ACTIVE
 		|| dev->power.disable_depth;
 }
 
+/**
+ * pm_runtime_status_suspended - Check if runtime PM status is "suspended".
+ * @dev: Target device.
+ *
+ * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false
+ * otherwise, regardless of whether or not runtime PM has been enabled for @dev.
+ *
+ * Note that the return value of this function can only be trusted if it is
+ * called under the runtime PM lock of @dev or under conditions in which the
+ * runtime PM status of @dev cannot change.
+ */
 static inline bool pm_runtime_status_suspended(struct device *dev)
 {
 	return dev->power.runtime_status == RPM_SUSPENDED;
 }
 
+/**
+ * pm_runtime_enabled - Check if runtime PM is enabled.
+ * @dev: Target device.
+ *
+ * Return %true if runtime PM is enabled for @dev or %false otherwise.
+ *
+ * Note that the return value of this function can only be trusted if it is
+ * called under the runtime PM lock of @dev or under conditions in which
+ * runtime PM cannot be either disabled or enabled for @dev.
+ */
 static inline bool pm_runtime_enabled(struct device *dev)
 {
 	return !dev->power.disable_depth;
 }
 
+/**
+ * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present.
+ * @dev: Target device.
+ *
+ * Return %true if @dev is a special device without runtime PM callbacks or
+ * %false otherwise.
+ */
 static inline bool pm_runtime_has_no_callbacks(struct device *dev)
 {
 	return dev->power.no_callbacks;
 }
 
+/**
+ * pm_runtime_mark_last_busy - Update the last access time of a device.
+ * @dev: Target device.
+ *
+ * Update the last access time of @dev used by the runtime PM autosuspend
+ * mechanism to the current time as returned by ktime_get_mono_fast_ns().
+ */
 static inline void pm_runtime_mark_last_busy(struct device *dev)
 {
 	WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns());
 }
 
+/**
+ * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context.
+ * @dev: Target device.
+ *
+ * Return %true if @dev has been marked as an "IRQ-safe" device (with respect
+ * to runtime PM), in which case its runtime PM callabcks can be expected to
+ * work correctly when invoked from interrupt handlers.
+ */
 static inline bool pm_runtime_is_irq_safe(struct device *dev)
 {
 	return dev->power.irq_safe;
@@ -191,97 +284,250 @@ static inline void pm_runtime_drop_link(struct device *dev) {}
 
 #endif /* !CONFIG_PM */
 
+/**
+ * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it.
+ * @dev: Target device.
+ *
+ * Invoke the "idle check" callback of @dev and, depending on its return value,
+ * set up autosuspend of @dev or suspend it (depending on whether or not
+ * autosuspend has been enabled for it).
+ */
 static inline int pm_runtime_idle(struct device *dev)
 {
 	return __pm_runtime_idle(dev, 0);
 }
 
+/**
+ * pm_runtime_suspend - Suspend a device synchronously.
+ * @dev: Target device.
+ */
 static inline int pm_runtime_suspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev, 0);
 }
 
+/**
+ * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it.
+ * @dev: Target device.
+ *
+ * Set up autosuspend of @dev or suspend it (depending on whether or not
+ * autosuspend is enabled for it) without engaging its "idle check" callback.
+ */
 static inline int pm_runtime_autosuspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev, RPM_AUTO);
 }
 
+/**
+ * pm_runtime_resume - Resume a device synchronously.
+ * @dev: Target device.
+ */
 static inline int pm_runtime_resume(struct device *dev)
 {
 	return __pm_runtime_resume(dev, 0);
 }
 
+/**
+ * pm_request_idle - Queue up "idle check" execution for a device.
+ * @dev: Target device.
+ *
+ * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev
+ * asynchronously.
+ */
 static inline int pm_request_idle(struct device *dev)
 {
 	return __pm_runtime_idle(dev, RPM_ASYNC);
 }
 
+/**
+ * pm_request_resume - Queue up runtime-resume of a device.
+ * @dev: Target device.
+ */
 static inline int pm_request_resume(struct device *dev)
 {
 	return __pm_runtime_resume(dev, RPM_ASYNC);
 }
 
+/**
+ * pm_request_autosuspend - Queue up autosuspend of a device.
+ * @dev: Target device.
+ *
+ * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev
+ * asynchronously.
+ */
 static inline int pm_request_autosuspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO);
 }
 
+/**
+ * pm_runtime_get - Bump up usage counter and queue up resume of a device.
+ * @dev: Target device.
+ *
+ * Bump up the runtime PM usage counter of @dev and queue up a work item to
+ * carry out runtime-resume of it.
+ */
 static inline int pm_runtime_get(struct device *dev)
 {
 	return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
+/**
+ * pm_runtime_get_sync - Bump up usage counter of a device and resume it.
+ * @dev: Target device.
+ *
+ * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of
+ * it synchronously.
+ *
+ * The possible return values of this function are the same as for
+ * pm_runtime_resume() and the runtime PM usage counter of @dev remains
+ * incremented in all cases, even if it returns an error code.
+ */
 static inline int pm_runtime_get_sync(struct device *dev)
 {
 	return __pm_runtime_resume(dev, RPM_GET_PUT);
 }
 
+/**
+ * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev and if it turns out to be
+ * equal to 0, queue up a work item for @dev like in pm_request_idle().
+ */
 static inline int pm_runtime_put(struct device *dev)
 {
 	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
+/**
+ * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev and if it turns out to be
+ * equal to 0, queue up a work item for @dev like in pm_request_autosuspend().
+ */
 static inline int pm_runtime_put_autosuspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev,
 	    RPM_GET_PUT | RPM_ASYNC | RPM_AUTO);
 }
 
+/**
+ * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev and if it turns out to be
+ * equal to 0, invoke the "idle check" callback of @dev and, depending on its
+ * return value, set up autosuspend of @dev or suspend it (depending on whether
+ * or not autosuspend has been enabled for it).
+ *
+ * The possible return values of this function are the same as for
+ * pm_runtime_idle() and the runtime PM usage counter of @dev remains
+ * decremented in all cases, even if it returns an error code.
+ */
 static inline int pm_runtime_put_sync(struct device *dev)
 {
 	return __pm_runtime_idle(dev, RPM_GET_PUT);
 }
 
+/**
+ * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev and if it turns out to be
+ * equal to 0, carry out runtime-suspend of @dev synchronously.
+ *
+ * The possible return values of this function are the same as for
+ * pm_runtime_suspend() and the runtime PM usage counter of @dev remains
+ * decremented in all cases, even if it returns an error code.
+ */
 static inline int pm_runtime_put_sync_suspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev, RPM_GET_PUT);
 }
 
+/**
+ * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0.
+ * @dev: Target device.
+ *
+ * Decrement the runtime PM usage counter of @dev and if it turns out to be
+ * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending
+ * on whether or not autosuspend has been enabled for it).
+ *
+ * The possible return values of this function are the same as for
+ * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains
+ * decremented in all cases, even if it returns an error code.
+ */
 static inline int pm_runtime_put_sync_autosuspend(struct device *dev)
 {
 	return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO);
 }
 
+/**
+ * pm_runtime_set_active - Set runtime PM status to "active".
+ * @dev: Target device.
+ *
+ * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies
+ * of it will be taken into account.
+ *
+ * It is not valid to call this function for devices with runtime PM enabled.
+ */
 static inline int pm_runtime_set_active(struct device *dev)
 {
 	return __pm_runtime_set_status(dev, RPM_ACTIVE);
 }
 
+/**
+ * pm_runtime_set_suspended - Set runtime PM status to "active".
+ * @dev: Target device.
+ *
+ * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that
+ * dependencies of it will be taken into account.
+ *
+ * It is not valid to call this function for devices with runtime PM enabled.
+ */
 static inline int pm_runtime_set_suspended(struct device *dev)
 {
 	return __pm_runtime_set_status(dev, RPM_SUSPENDED);
 }
 
+/**
+ * pm_runtime_disable - Disable runtime PM for a device.
+ * @dev: Target device.
+ *
+ * Prevent the runtime PM framework from working with @dev (by incrementing its
+ * "blocking" counter).
+ *
+ * For each invocation of this function for @dev there must be a matching
+ * pm_runtime_enable() call in order for runtime PM to be enabled for it.
+ */
 static inline void pm_runtime_disable(struct device *dev)
 {
 	__pm_runtime_disable(dev, true);
 }
 
+/**
+ * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device.
+ * @dev: Target device.
+ *
+ * Allow the runtime PM autosuspend mechanism to be used for @dev whenever
+ * requested (or "autosuspend" will be handled as direct runtime-suspend for
+ * it).
+ */
 static inline void pm_runtime_use_autosuspend(struct device *dev)
 {
 	__pm_runtime_use_autosuspend(dev, true);
 }
 
+/**
+ * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used.
+ * @dev: Target device.
+ *
+ * Prevent the runtime PM autosuspend mechanism from being used for @dev which
+ * means that "autosuspend" will be handled as direct runtime-suspend for it
+ * going forward.
+ */
 static inline void pm_runtime_dont_use_autosuspend(struct device *dev)
 {
 	__pm_runtime_use_autosuspend(dev, false);
-- 
cgit v1.2.3


From 669cbc708122fc7a02282058a09f096200cee090 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 21 Jul 2020 20:25:13 -0600
Subject: PCI: Move DT resource setup into devm_pci_alloc_host_bridge()

Now that pci_parse_request_of_pci_ranges() callers just setup
pci_host_bridge.windows and dma_ranges directly and don't need the bus
range returned, we can just initialize them when allocating the
pci_host_bridge struct.

With this, pci_parse_request_of_pci_ranges() becomes a static function.

Link: https://lore.kernel.org/r/20200722022514.1283916-19-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/cadence/pcie-cadence-host.c |  6 ----
 drivers/pci/controller/dwc/pcie-designware-host.c  |  5 ---
 .../pci/controller/mobiveil/pcie-mobiveil-host.c   |  8 -----
 drivers/pci/controller/pci-aardvark.c              |  7 ----
 drivers/pci/controller/pci-ftpci100.c              |  5 ---
 drivers/pci/controller/pci-host-common.c           | 13 ++++----
 drivers/pci/controller/pci-loongson.c              |  7 ----
 drivers/pci/controller/pci-rcar-gen2.c             |  6 ----
 drivers/pci/controller/pci-tegra.c                 |  6 ----
 drivers/pci/controller/pci-v3-semi.c               |  5 ---
 drivers/pci/controller/pci-versatile.c             |  7 +---
 drivers/pci/controller/pci-xgene.c                 |  5 ---
 drivers/pci/controller/pcie-altera.c               |  7 ----
 drivers/pci/controller/pcie-brcmstb.c              |  5 ---
 drivers/pci/controller/pcie-iproc-platform.c       |  7 ----
 drivers/pci/controller/pcie-mediatek.c             |  7 ----
 drivers/pci/controller/pcie-rcar-host.c            |  5 ---
 drivers/pci/controller/pcie-rockchip-host.c        |  5 ---
 drivers/pci/controller/pcie-xilinx-nwl.c           |  7 ----
 drivers/pci/controller/pcie-xilinx.c               |  7 ----
 drivers/pci/of.c                                   | 37 ++++++++++------------
 drivers/pci/pci.h                                  |  8 +++++
 drivers/pci/probe.c                                |  4 +++
 include/linux/pci.h                                | 12 -------
 24 files changed, 36 insertions(+), 155 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c
index 39a8a7a3051e..436eb9f3d68e 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-host.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-host.c
@@ -171,14 +171,8 @@ static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc)
 static int cdns_pcie_host_init(struct device *dev,
 			       struct cdns_pcie_rc *rc)
 {
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc);
 	int err;
 
-	/* Parse our PCI ranges and request their resources */
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL, NULL);
-	if (err)
-		return err;
-
 	err = cdns_pcie_host_init_root_port(rc);
 	if (err)
 		return err;
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 9775558acdc8..f9fa7b1f429d 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -346,11 +346,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (!bridge)
 		return -ENOMEM;
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	/* Get the I/O and memory ranges from DT */
 	resource_list_for_each_entry(win, &bridge->windows) {
 		switch (resource_type(win->res)) {
diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
index 7250b84a7efe..2954d6ad8333 100644
--- a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
+++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
@@ -577,14 +577,6 @@ int mobiveil_pcie_host_probe(struct mobiveil_pcie *pcie)
 	if (!mobiveil_pcie_is_bridge(pcie))
 		return -ENODEV;
 
-	/* parse the host bridge base addresses from the device tree file */
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret) {
-		dev_err(dev, "Getting bridge resources failed\n");
-		return ret;
-	}
-
 	/*
 	 * configure all inbound and outbound windows and prepare the RC for
 	 * config access
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 36dc2412c66f..7ee14cfb7f5a 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -1130,13 +1130,6 @@ static int advk_pcie_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret) {
-		dev_err(dev, "Failed to parse resources\n");
-		return ret;
-	}
-
 	pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node,
 						       "reset-gpios", 0,
 						       GPIOD_OUT_LOW,
diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c
index 5441a5f92739..94f6ab5fff70 100644
--- a/drivers/pci/controller/pci-ftpci100.c
+++ b/drivers/pci/controller/pci-ftpci100.c
@@ -465,11 +465,6 @@ static int faraday_pci_probe(struct platform_device *pdev)
 	if (IS_ERR(p->base))
 		return PTR_ERR(p->base);
 
-	ret = pci_parse_request_of_pci_ranges(dev, &host->windows,
-					      &host->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	win = resource_list_first_type(&host->windows, IORESOURCE_IO);
 	if (win) {
 		io = win->res;
diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index e662910fe032..509624175260 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -25,21 +25,20 @@ static struct pci_config_window *gen_pci_init(struct device *dev,
 {
 	int err;
 	struct resource cfgres;
-	struct resource *bus_range = NULL;
+	struct resource_entry *bus;
 	struct pci_config_window *cfg;
 
-	/* Parse our PCI ranges and request their resources */
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL, &bus_range);
-	if (err)
-		return ERR_PTR(err);
-
 	err = of_address_to_resource(dev->of_node, 0, &cfgres);
 	if (err) {
 		dev_err(dev, "missing \"reg\" property\n");
 		return ERR_PTR(err);
 	}
 
-	cfg = pci_ecam_create(dev, &cfgres, bus_range, ops);
+	bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS);
+	if (!bus)
+		return ERR_PTR(-ENODEV);
+
+	cfg = pci_ecam_create(dev, &cfgres, bus->res, ops);
 	if (IS_ERR(cfg))
 		return cfg;
 
diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
index 0198c15ed97c..a7a7fbe2b7a5 100644
--- a/drivers/pci/controller/pci-loongson.c
+++ b/drivers/pci/controller/pci-loongson.c
@@ -218,13 +218,6 @@ static int loongson_pci_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-						&bridge->dma_ranges, NULL);
-	if (err) {
-		dev_err(dev, "failed to get bridge resources\n");
-		return err;
-	}
-
 	bridge->sysdata = priv;
 	bridge->ops = &loongson_pci_ops;
 	bridge->map_irq = loongson_map_irq;
diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c
index 7bc6c1750ebe..c9530038ca9a 100644
--- a/drivers/pci/controller/pci-rcar-gen2.c
+++ b/drivers/pci/controller/pci-rcar-gen2.c
@@ -282,7 +282,6 @@ static int rcar_pci_probe(struct platform_device *pdev)
 	struct rcar_pci_priv *priv;
 	struct pci_host_bridge *bridge;
 	void __iomem *reg;
-	int ret;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*priv));
 	if (!bridge)
@@ -315,11 +314,6 @@ static int rcar_pci_probe(struct platform_device *pdev)
 		return priv->irq;
 	}
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	bridge->ops = &rcar_pci_ops;
 
 	pci_add_flags(PCI_REASSIGN_ALL_BUS);
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 8f37cbe7657e..c75ee4bb914e 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -2682,12 +2682,6 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&pcie->ports);
 	pcie->dev = dev;
 
-	err = pci_parse_request_of_pci_ranges(dev, &host->windows, NULL, NULL);
-	if (err) {
-		dev_err(dev, "Getting bridge resources failed\n");
-		return err;
-	}
-
 	err = tegra_pcie_parse_dt(pcie);
 	if (err < 0)
 		return err;
diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c
index d2619f583bfb..1a2cbc56b34b 100644
--- a/drivers/pci/controller/pci-v3-semi.c
+++ b/drivers/pci/controller/pci-v3-semi.c
@@ -764,11 +764,6 @@ static int v3_pci_probe(struct platform_device *pdev)
 	if (IS_ERR(v3->config_base))
 		return PTR_ERR(v3->config_base);
 
-	ret = pci_parse_request_of_pci_ranges(dev, &host->windows,
-					      &host->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	/* Get and request error IRQ resource */
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c
index 66f5c61b8eb8..fb45f8d158fe 100644
--- a/drivers/pci/controller/pci-versatile.c
+++ b/drivers/pci/controller/pci-versatile.c
@@ -67,7 +67,7 @@ static int versatile_pci_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct resource_entry *entry;
-	int ret, i, myslot = -1, mem = 1;
+	int i, myslot = -1, mem = 1;
 	u32 val;
 	void __iomem *local_pci_cfg_base;
 	struct pci_host_bridge *bridge;
@@ -89,11 +89,6 @@ static int versatile_pci_probe(struct platform_device *pdev)
 	if (IS_ERR(versatile_cfg_base[1]))
 		return PTR_ERR(versatile_cfg_base[1]);
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      NULL, NULL);
-	if (ret)
-		return ret;
-
 	resource_list_for_each_entry(entry, &bridge->windows) {
 		if (resource_type(entry->res) == IORESOURCE_MEM) {
 			writel(entry->res->start >> 28, PCI_IMAP(mem));
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index d3aa28e1a482..190234b7a3a9 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -614,11 +614,6 @@ static int xgene_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	ret = xgene_pcie_setup(port);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c
index 4424430dacb0..d93489e8978e 100644
--- a/drivers/pci/controller/pcie-altera.c
+++ b/drivers/pci/controller/pcie-altera.c
@@ -794,13 +794,6 @@ static int altera_pcie_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret) {
-		dev_err(dev, "Failed add resources\n");
-		return ret;
-	}
-
 	ret = altera_pcie_init_irq_domain(pcie);
 	if (ret) {
 		dev_err(dev, "Failed creating IRQ Domain\n");
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index 20e1aa23edc5..f0f283ec17a0 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -970,11 +970,6 @@ static int brcm_pcie_probe(struct platform_device *pdev)
 
 	pcie->ssc = of_property_read_bool(np, "brcm,enable-ssc");
 
-	ret = pci_parse_request_of_pci_ranges(pcie->dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret)
-		return ret;
-
 	ret = clk_prepare_enable(pcie->clk);
 	if (ret) {
 		dev_err(&pdev->dev, "could not enable clock\n");
diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index ff0a81a632a1..7c10c1cb6f65 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -95,13 +95,6 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 	if (IS_ERR(pcie->phy))
 		return PTR_ERR(pcie->phy);
 
-	ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (ret) {
-		dev_err(dev, "unable to get PCI host bridge resources\n");
-		return ret;
-	}
-
 	/* PAXC doesn't support legacy IRQs, skip mapping */
 	switch (pcie->type) {
 	case IPROC_PCIE_PAXC:
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index ac6dfa087247..a745f35a8396 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1027,15 +1027,8 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie)
 	struct device *dev = pcie->dev;
 	struct device_node *node = dev->of_node, *child;
 	struct mtk_pcie_port *port, *tmp;
-	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
-	struct list_head *windows = &host->windows;
 	int err;
 
-	err = pci_parse_request_of_pci_ranges(dev, windows,
-					      &host->dma_ranges, NULL);
-	if (err)
-		return err;
-
 	for_each_available_child_of_node(node, child) {
 		int slot;
 
diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index fa7b89378904..67f2a9d3bc29 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -913,11 +913,6 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	pcie->dev = dev;
 	platform_set_drvdata(pdev, host);
 
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (err)
-		return err;
-
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err < 0) {
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index 9a30d08976d8..fed4f6cd1b7b 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -989,11 +989,6 @@ static int rockchip_pcie_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto err_deinit_port;
 
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (err)
-		goto err_remove_irq_domain;
-
 	err = rockchip_pcie_cfg_atu(rockchip);
 	if (err)
 		goto err_remove_irq_domain;
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 566165c18fad..7e7c23c555c7 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -838,13 +838,6 @@ static int nwl_pcie_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (err) {
-		dev_err(dev, "Getting bridge resources failed\n");
-		return err;
-	}
-
 	err = nwl_pcie_init_irq_domain(pcie);
 	if (err) {
 		dev_err(dev, "Failed creating IRQ Domain\n");
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index 7bf80f68efa9..f8b8ccea5cbc 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -641,13 +641,6 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = pci_parse_request_of_pci_ranges(dev, &bridge->windows,
-					      &bridge->dma_ranges, NULL);
-	if (err) {
-		dev_err(dev, "Getting bridge resources failed\n");
-		return err;
-	}
-
 	bridge->sysdata = port;
 	bridge->ops = &xilinx_pcie_ops;
 	bridge->map_irq = of_irq_parse_and_map_pci;
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index cfb940c8b399..5e06aae1b4cd 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -521,28 +521,26 @@ int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin)
 EXPORT_SYMBOL_GPL(of_irq_parse_and_map_pci);
 #endif	/* CONFIG_OF_IRQ */
 
-int pci_parse_request_of_pci_ranges(struct device *dev,
-				    struct list_head *resources,
-				    struct list_head *ib_resources,
-				    struct resource **bus_range)
+static int pci_parse_request_of_pci_ranges(struct device *dev,
+					   struct pci_host_bridge *bridge)
 {
 	int err, res_valid = 0;
 	resource_size_t iobase;
 	struct resource_entry *win, *tmp;
 
-	INIT_LIST_HEAD(resources);
-	if (ib_resources)
-		INIT_LIST_HEAD(ib_resources);
-	err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, resources,
-						    ib_resources, &iobase);
+	INIT_LIST_HEAD(&bridge->windows);
+	INIT_LIST_HEAD(&bridge->dma_ranges);
+
+	err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &bridge->windows,
+						    &bridge->dma_ranges, &iobase);
 	if (err)
 		return err;
 
-	err = devm_request_pci_bus_resources(dev, resources);
+	err = devm_request_pci_bus_resources(dev, &bridge->windows);
 	if (err)
-		goto out_release_res;
+		return err;
 
-	resource_list_for_each_entry_safe(win, tmp, resources) {
+	resource_list_for_each_entry_safe(win, tmp, &bridge->windows) {
 		struct resource *res = win->res;
 
 		switch (resource_type(res)) {
@@ -557,10 +555,6 @@ int pci_parse_request_of_pci_ranges(struct device *dev,
 		case IORESOURCE_MEM:
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
-		case IORESOURCE_BUS:
-			if (bus_range)
-				*bus_range = res;
-			break;
 		}
 	}
 
@@ -568,12 +562,15 @@ int pci_parse_request_of_pci_ranges(struct device *dev,
 		dev_warn(dev, "non-prefetchable memory resource required\n");
 
 	return 0;
+}
 
- out_release_res:
-	pci_free_resource_list(resources);
-	return err;
+int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge)
+{
+	if (!dev->of_node)
+		return 0;
+
+	return pci_parse_request_of_pci_ranges(dev, bridge);
 }
-EXPORT_SYMBOL_GPL(pci_parse_request_of_pci_ranges);
 
 #endif /* CONFIG_PCI */
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6d3f75867106..56d67071e116 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -627,6 +627,8 @@ void pci_release_of_node(struct pci_dev *dev);
 void pci_set_bus_of_node(struct pci_bus *bus);
 void pci_release_bus_of_node(struct pci_bus *bus);
 
+int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge);
+
 #else
 static inline int
 of_pci_parse_bus_range(struct device_node *node, struct resource *res)
@@ -650,6 +652,12 @@ static inline void pci_set_of_node(struct pci_dev *dev) { }
 static inline void pci_release_of_node(struct pci_dev *dev) { }
 static inline void pci_set_bus_of_node(struct pci_bus *bus) { }
 static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
+
+static inline int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge)
+{
+	return 0;
+}
+
 #endif /* CONFIG_OF */
 
 #ifdef CONFIG_PCIEAER
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index f850782efc35..998f615cdb6d 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -635,6 +635,10 @@ struct pci_host_bridge *devm_pci_alloc_host_bridge(struct device *dev,
 	if (ret)
 		return NULL;
 
+	ret = devm_of_pci_bridge_init(dev, bridge);
+	if (ret)
+		return NULL;
+
 	return bridge;
 }
 EXPORT_SYMBOL(devm_pci_alloc_host_bridge);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c79d83304e52..2830799208fd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2303,10 +2303,6 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
 struct device_node;
 struct irq_domain;
 struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus);
-int pci_parse_request_of_pci_ranges(struct device *dev,
-				    struct list_head *resources,
-				    struct list_head *ib_resources,
-				    struct resource **bus_range);
 
 /* Arch may override this (weak) */
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus);
@@ -2314,14 +2310,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus);
 #else	/* CONFIG_OF */
 static inline struct irq_domain *
 pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; }
-static inline int
-pci_parse_request_of_pci_ranges(struct device *dev,
-				struct list_head *resources,
-				struct list_head *ib_resources,
-				struct resource **bus_range)
-{
-	return -EINVAL;
-}
 #endif  /* CONFIG_OF */
 
 static inline struct device_node *
-- 
cgit v1.2.3


From a0102bda5bc0991c5c8c7c07770b236894a810fd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 30 Jul 2020 11:03:55 -0400
Subject: ceph: move sb->wb_pagevec_pool to be a global mempool

When doing some testing recently, I hit some page allocation failures
on mount, when creating the wb_pagevec_pool for the mount. That
requires 128k (32 contiguous pages), and after thrashing the memory
during an xfstests run, sometimes that would fail.

128k for each mount seems like a lot to hold in reserve for a rainy
day, so let's change this to a global mempool that gets allocated
when the module is plugged in.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c               | 23 +++++++++++------------
 fs/ceph/super.c              | 22 ++++++++--------------
 fs/ceph/super.h              |  2 --
 include/linux/ceph/libceph.h |  1 +
 4 files changed, 20 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 01ad09733ac7..6ea761c84494 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -862,8 +862,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 
 	osd_data = osd_req_op_extent_osd_data(req, 0);
 	if (osd_data->pages_from_pool)
-		mempool_free(osd_data->pages,
-			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
+		mempool_free(osd_data->pages, ceph_wb_pagevec_pool);
 	else
 		kfree(osd_data->pages);
 	ceph_osdc_put_request(req);
@@ -955,10 +954,10 @@ retry:
 		int num_ops = 0, op_idx;
 		unsigned i, pvec_pages, max_pages, locked_pages = 0;
 		struct page **pages = NULL, **data_pages;
-		mempool_t *pool = NULL;	/* Becomes non-null if mempool used */
 		struct page *page;
 		pgoff_t strip_unit_end = 0;
 		u64 offset = 0, len = 0;
+		bool from_pool = false;
 
 		max_pages = wsize >> PAGE_SHIFT;
 
@@ -1057,16 +1056,16 @@ get_more_pages:
 						      sizeof(*pages),
 						      GFP_NOFS);
 				if (!pages) {
-					pool = fsc->wb_pagevec_pool;
-					pages = mempool_alloc(pool, GFP_NOFS);
+					from_pool = true;
+					pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
 					BUG_ON(!pages);
 				}
 
 				len = 0;
 			} else if (page->index !=
 				   (offset + len) >> PAGE_SHIFT) {
-				if (num_ops >= (pool ?  CEPH_OSD_SLAB_OPS :
-							CEPH_OSD_MAX_OPS)) {
+				if (num_ops >= (from_pool ?  CEPH_OSD_SLAB_OPS :
+							     CEPH_OSD_MAX_OPS)) {
 					redirty_page_for_writepage(wbc, page);
 					unlock_page(page);
 					break;
@@ -1161,7 +1160,7 @@ new_request:
 				     offset, len);
 				osd_req_op_extent_osd_data_pages(req, op_idx,
 							data_pages, len, 0,
-							!!pool, false);
+							from_pool, false);
 				osd_req_op_extent_update(req, op_idx, len);
 
 				len = 0;
@@ -1188,12 +1187,12 @@ new_request:
 		dout("writepages got pages at %llu~%llu\n", offset, len);
 
 		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
-						 0, !!pool, false);
+						 0, from_pool, false);
 		osd_req_op_extent_update(req, op_idx, len);
 
 		BUG_ON(op_idx + 1 != req->r_num_ops);
 
-		pool = NULL;
+		from_pool = false;
 		if (i < locked_pages) {
 			BUG_ON(num_ops <= req->r_num_ops);
 			num_ops -= req->r_num_ops;
@@ -1204,8 +1203,8 @@ new_request:
 			pages = kmalloc_array(locked_pages, sizeof(*pages),
 					      GFP_NOFS);
 			if (!pages) {
-				pool = fsc->wb_pagevec_pool;
-				pages = mempool_alloc(pool, GFP_NOFS);
+				from_pool = true;
+				pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
 				BUG_ON(!pages);
 			}
 			memcpy(pages, data_pages + i,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 585aecea5cad..7ec0e6d03d10 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -637,8 +637,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 					struct ceph_options *opt)
 {
 	struct ceph_fs_client *fsc;
-	int page_count;
-	size_t size;
 	int err;
 
 	fsc = kzalloc(sizeof(*fsc), GFP_KERNEL);
@@ -686,22 +684,12 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->cap_wq)
 		goto fail_inode_wq;
 
-	/* set up mempools */
-	err = -ENOMEM;
-	page_count = fsc->mount_options->wsize >> PAGE_SHIFT;
-	size = sizeof (struct page *) * (page_count ? page_count : 1);
-	fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, size);
-	if (!fsc->wb_pagevec_pool)
-		goto fail_cap_wq;
-
 	spin_lock(&ceph_fsc_lock);
 	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
 	spin_unlock(&ceph_fsc_lock);
 
 	return fsc;
 
-fail_cap_wq:
-	destroy_workqueue(fsc->cap_wq);
 fail_inode_wq:
 	destroy_workqueue(fsc->inode_wq);
 fail_client:
@@ -732,8 +720,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
 
-	mempool_destroy(fsc->wb_pagevec_pool);
-
 	destroy_mount_options(fsc->mount_options);
 
 	ceph_destroy_client(fsc->client);
@@ -752,6 +738,7 @@ struct kmem_cache *ceph_dentry_cachep;
 struct kmem_cache *ceph_file_cachep;
 struct kmem_cache *ceph_dir_file_cachep;
 struct kmem_cache *ceph_mds_request_cachep;
+mempool_t *ceph_wb_pagevec_pool;
 
 static void ceph_inode_init_once(void *foo)
 {
@@ -796,6 +783,10 @@ static int __init init_caches(void)
 	if (!ceph_mds_request_cachep)
 		goto bad_mds_req;
 
+	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
+	if (!ceph_wb_pagevec_pool)
+		goto bad_pagevec_pool;
+
 	error = ceph_fscache_register();
 	if (error)
 		goto bad_fscache;
@@ -804,6 +795,8 @@ static int __init init_caches(void)
 
 bad_fscache:
 	kmem_cache_destroy(ceph_mds_request_cachep);
+bad_pagevec_pool:
+	mempool_destroy(ceph_wb_pagevec_pool);
 bad_mds_req:
 	kmem_cache_destroy(ceph_dir_file_cachep);
 bad_dir_file:
@@ -834,6 +827,7 @@ static void destroy_caches(void)
 	kmem_cache_destroy(ceph_file_cachep);
 	kmem_cache_destroy(ceph_dir_file_cachep);
 	kmem_cache_destroy(ceph_mds_request_cachep);
+	mempool_destroy(ceph_wb_pagevec_pool);
 
 	ceph_fscache_unregister();
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 9001a896ae8c..4c3c964b1c54 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -118,8 +118,6 @@ struct ceph_fs_client {
 
 	struct ceph_mds_client *mdsc;
 
-	/* writeback */
-	mempool_t *wb_pagevec_pool;
 	atomic_long_t writeback_count;
 
 	struct workqueue_struct *inode_wq;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index e5ed1c541e7f..c8645f0b797d 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -282,6 +282,7 @@ extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 extern struct kmem_cache *ceph_dir_file_cachep;
 extern struct kmem_cache *ceph_mds_request_cachep;
+extern mempool_t *ceph_wb_pagevec_pool;
 
 /* ceph_common.c */
 extern bool libceph_compatible(void *data);
-- 
cgit v1.2.3


From df23bb18b44b9a1f2b54358201730e710a9df57f Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 4 Aug 2020 07:53:42 +0200
Subject: ipv4: route: Ignore output interface in FIB lookup for PMTU route

Currently, processes sending traffic to a local bridge with an
encapsulation device as a port don't get ICMP errors if they exceed
the PMTU of the encapsulated link.

David Ahern suggested this as a hack, but it actually looks like
the correct solution: when we update the PMTU for a given destination
by means of updating or creating a route exception, the encapsulation
might trigger this because of PMTU discovery happening either on the
encapsulation device itself, or its lower layer. This happens on
bridged encapsulations only.

The output interface shouldn't matter, because we already have a
valid destination. Drop the output interface restriction from the
associated route lookup.

For UDP tunnels, we will now have a route exception created for the
encapsulation itself, with a MTU value reflecting its headroom, which
allows a bridge forwarding IP packets originated locally to deliver
errors back to the sending socket.

The behaviour is now consistent with IPv6 and verified with selftests
pmtu_ipv{4,6}_br_{geneve,vxlan}{4,6}_exception introduced later in
this series.

v2:
- reset output interface only for bridge ports (David Ahern)
- add and use netif_is_any_bridge_port() helper (David Ahern)

Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 +++++
 net/ipv4/route.c          | 5 +++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88d40b9abaa1..90444622b703 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4840,6 +4840,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev)
 	return dev->priv_flags & IFF_OVS_DATAPATH;
 }
 
+static inline bool netif_is_any_bridge_port(const struct net_device *dev)
+{
+	return netif_is_bridge_port(dev) || netif_is_ovs_port(dev);
+}
+
 static inline bool netif_is_team_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_TEAM;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a01efa062f6b..8ca6bcab7b03 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1050,6 +1050,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
+
+	/* Don't make lookup fail for bridged encapsulations */
+	if (skb && netif_is_any_bridge_port(skb->dev))
+		fl4.flowi4_oif = 0;
+
 	__ip_rt_update_pmtu(rt, &fl4, mtu);
 }
 
-- 
cgit v1.2.3


From f073531070d24bbb82cb2658952d949f4851024b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 28 Jul 2020 17:49:47 +0200
Subject: init: add an init_dup helper

Add a simple helper to grab a reference to a file and install it at
the next available fd, and switch the early init code over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/init.c                     | 12 ++++++++++++
 include/linux/init_syscalls.h |  1 +
 init/main.c                   |  8 ++++----
 3 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/init.c b/fs/init.c
index db5c48a85644..e9c320a48cf1 100644
--- a/fs/init.c
+++ b/fs/init.c
@@ -8,6 +8,7 @@
 #include <linux/namei.h>
 #include <linux/fs.h>
 #include <linux/fs_struct.h>
+#include <linux/file.h>
 #include <linux/init_syscalls.h>
 #include <linux/security.h>
 #include "internal.h"
@@ -251,3 +252,14 @@ int __init init_utimes(char *filename, struct timespec64 *ts)
 	path_put(&path);
 	return error;
 }
+
+int __init init_dup(struct file *file)
+{
+	int fd;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+	fd_install(fd, get_file(file));
+	return 0;
+}
diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h
index 3654b525ac0b..92045d18cbfc 100644
--- a/include/linux/init_syscalls.h
+++ b/include/linux/init_syscalls.h
@@ -16,3 +16,4 @@ int __init init_unlink(const char *pathname);
 int __init init_mkdir(const char *pathname, umode_t mode);
 int __init init_rmdir(const char *pathname);
 int __init init_utimes(char *filename, struct timespec64 *ts);
+int __init init_dup(struct file *file);
diff --git a/init/main.c b/init/main.c
index 1c710d3e1d46..9dae9c4f806b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1467,10 +1467,10 @@ void __init console_on_rootfs(void)
 		pr_err("Warning: unable to open an initial console.\n");
 		return;
 	}
-	get_file_rcu_many(file, 2);
-	fd_install(get_unused_fd_flags(0), file);
-	fd_install(get_unused_fd_flags(0), file);
-	fd_install(get_unused_fd_flags(0), file);
+	init_dup(file);
+	init_dup(file);
+	init_dup(file);
+	fput(file);
 }
 
 static noinline void __init kernel_init_freeable(void)
-- 
cgit v1.2.3


From 4476770881d7ac647e3bcae0943f37e00b9c3f3c Mon Sep 17 00:00:00 2001
From: Siddharth Gupta <sidgup@codeaurora.org>
Date: Wed, 29 Jul 2020 10:40:00 -0700
Subject: remoteproc: Add remoteproc character device interface

Add the character device interface into remoteproc framework.
This interface can be used in order to boot/shutdown remote
subsystems and provides a basic ioctl based interface to implement
supplementary functionality. An ioctl call is implemented to enable
the shutdown on release feature which will allow remote processors to
be shutdown when the controlling userspace application crashes or hangs.

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Signed-off-by: Siddharth Gupta <sidgup@codeaurora.org>
Link: https://lore.kernel.org/r/1596044401-22083-2-git-send-email-sidgup@codeaurora.org
[bjorn: s/int32_t/s32/ per checkpatch]
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 Documentation/userspace-api/ioctl/ioctl-number.rst |   1 +
 drivers/remoteproc/Kconfig                         |   9 ++
 drivers/remoteproc/Makefile                        |   1 +
 drivers/remoteproc/remoteproc_cdev.c               | 124 +++++++++++++++++++++
 drivers/remoteproc/remoteproc_internal.h           |  28 +++++
 include/linux/remoteproc.h                         |   5 +
 include/uapi/linux/remoteproc_cdev.h               |  37 ++++++
 7 files changed, 205 insertions(+)
 create mode 100644 drivers/remoteproc/remoteproc_cdev.c
 create mode 100644 include/uapi/linux/remoteproc_cdev.h

(limited to 'include/linux')

diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 59472cd6a11d..2a198838fca9 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -339,6 +339,7 @@ Code  Seq#    Include File                                           Comments
 0xB4  00-0F  linux/gpio.h                                            <mailto:linux-gpio@vger.kernel.org>
 0xB5  00-0F  uapi/linux/rpmsg.h                                      <mailto:linux-remoteproc@vger.kernel.org>
 0xB6  all    linux/fpga-dfl.h
+0xB7  all    uapi/linux/remoteproc_cdev.h                            <mailto:linux-remoteproc@vger.kernel.org>
 0xC0  00-0F  linux/usb/iowarrior.h
 0xCA  00-0F  uapi/misc/cxl.h
 0xCA  10-2F  uapi/misc/ocxl.h
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 48315dc4a30c..c6659dfea7c7 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -14,6 +14,15 @@ config REMOTEPROC
 
 if REMOTEPROC
 
+config REMOTEPROC_CDEV
+	bool "Remoteproc character device interface"
+	help
+	  Say y here to have a character device interface for the remoteproc
+	  framework. Userspace can boot/shutdown remote processors through
+	  this interface.
+
+	  It's safe to say N if you don't want to use this interface.
+
 config IMX_REMOTEPROC
 	tristate "IMX6/7 remoteproc support"
 	depends on ARCH_MXC
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 4d4307dc8fa9..3dfa28e6c701 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -10,6 +10,7 @@ remoteproc-y				+= remoteproc_debugfs.o
 remoteproc-y				+= remoteproc_sysfs.o
 remoteproc-y				+= remoteproc_virtio.o
 remoteproc-y				+= remoteproc_elf_loader.o
+obj-$(CONFIG_REMOTEPROC_CDEV)		+= remoteproc_cdev.o
 obj-$(CONFIG_IMX_REMOTEPROC)		+= imx_rproc.o
 obj-$(CONFIG_INGENIC_VPU_RPROC)		+= ingenic_rproc.o
 obj-$(CONFIG_MTK_SCP)			+= mtk_scp.o mtk_scp_ipi.o
diff --git a/drivers/remoteproc/remoteproc_cdev.c b/drivers/remoteproc/remoteproc_cdev.c
new file mode 100644
index 000000000000..b19ea3057bde
--- /dev/null
+++ b/drivers/remoteproc/remoteproc_cdev.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Character device interface driver for Remoteproc framework.
+ *
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/cdev.h>
+#include <linux/compat.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/remoteproc.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/remoteproc_cdev.h>
+
+#include "remoteproc_internal.h"
+
+#define NUM_RPROC_DEVICES	64
+static dev_t rproc_major;
+
+static ssize_t rproc_cdev_write(struct file *filp, const char __user *buf, size_t len, loff_t *pos)
+{
+	struct rproc *rproc = container_of(filp->f_inode->i_cdev, struct rproc, cdev);
+	int ret = 0;
+	char cmd[10];
+
+	if (!len || len > sizeof(cmd))
+		return -EINVAL;
+
+	ret = copy_from_user(cmd, buf, len);
+	if (ret)
+		return -EFAULT;
+
+	if (!strncmp(cmd, "start", len)) {
+		if (rproc->state == RPROC_RUNNING)
+			return -EBUSY;
+
+		ret = rproc_boot(rproc);
+	} else if (!strncmp(cmd, "stop", len)) {
+		if (rproc->state != RPROC_RUNNING)
+			return -EINVAL;
+
+		rproc_shutdown(rproc);
+	} else {
+		dev_err(&rproc->dev, "Unrecognized option\n");
+		ret = -EINVAL;
+	}
+
+	return ret ? ret : len;
+}
+
+static long rproc_device_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	struct rproc *rproc = container_of(filp->f_inode->i_cdev, struct rproc, cdev);
+	void __user *argp = (void __user *)arg;
+	s32 param;
+
+	switch (ioctl) {
+	case RPROC_SET_SHUTDOWN_ON_RELEASE:
+		if (copy_from_user(&param, argp, sizeof(s32)))
+			return -EFAULT;
+
+		rproc->cdev_put_on_release = !!param;
+		break;
+	case RPROC_GET_SHUTDOWN_ON_RELEASE:
+		param = (s32)rproc->cdev_put_on_release;
+		if (copy_to_user(argp, &param, sizeof(s32)))
+			return -EFAULT;
+
+		break;
+	default:
+		dev_err(&rproc->dev, "Unsupported ioctl\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rproc_cdev_release(struct inode *inode, struct file *filp)
+{
+	struct rproc *rproc = container_of(inode->i_cdev, struct rproc, cdev);
+
+	if (rproc->cdev_put_on_release && rproc->state == RPROC_RUNNING)
+		rproc_shutdown(rproc);
+
+	return 0;
+}
+
+static const struct file_operations rproc_fops = {
+	.write = rproc_cdev_write,
+	.unlocked_ioctl = rproc_device_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+	.release = rproc_cdev_release,
+};
+
+int rproc_char_device_add(struct rproc *rproc)
+{
+	int ret;
+
+	cdev_init(&rproc->cdev, &rproc_fops);
+	rproc->cdev.owner = THIS_MODULE;
+
+	rproc->dev.devt = MKDEV(MAJOR(rproc_major), rproc->index);
+	cdev_set_parent(&rproc->cdev, &rproc->dev.kobj);
+	ret = cdev_add(&rproc->cdev, rproc->dev.devt, 1);
+	if (ret < 0)
+		dev_err(&rproc->dev, "Failed to add char dev for %s\n", rproc->name);
+
+	return ret;
+}
+
+void rproc_char_device_remove(struct rproc *rproc)
+{
+	__unregister_chrdev(MAJOR(rproc->dev.devt), rproc->index, 1, "remoteproc");
+}
+
+void __init rproc_init_cdev(void)
+{
+	int ret;
+
+	ret = alloc_chrdev_region(&rproc_major, 0, NUM_RPROC_DEVICES, "remoteproc");
+	if (ret < 0)
+		pr_err("Failed to alloc rproc_cdev region, err %d\n", ret);
+}
diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h
index cd4176b033a3..c34002888d2c 100644
--- a/drivers/remoteproc/remoteproc_internal.h
+++ b/drivers/remoteproc/remoteproc_internal.h
@@ -53,6 +53,34 @@ void rproc_exit_sysfs(void);
 void rproc_coredump_cleanup(struct rproc *rproc);
 void rproc_coredump(struct rproc *rproc);
 
+#ifdef CONFIG_REMOTEPROC_CDEV
+void rproc_init_cdev(void);
+void rproc_exit_cdev(void);
+int rproc_char_device_add(struct rproc *rproc);
+void rproc_char_device_remove(struct rproc *rproc);
+#else
+static inline void rproc_init_cdev(void)
+{
+}
+
+static inline void rproc_exit_cdev(void)
+{
+}
+
+/*
+ * The character device interface is an optional feature, if it is not enabled
+ * the function should not return an error.
+ */
+static inline int rproc_char_device_add(struct rproc *rproc)
+{
+	return 0;
+}
+
+static inline void  rproc_char_device_remove(struct rproc *rproc)
+{
+}
+#endif
+
 void rproc_free_vring(struct rproc_vring *rvring);
 int rproc_alloc_vring(struct rproc_vdev *rvdev, int i);
 
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 0e8d2ff575b4..2fa68bf5aa4f 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -38,6 +38,7 @@
 #include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/virtio.h>
+#include <linux/cdev.h>
 #include <linux/completion.h>
 #include <linux/idr.h>
 #include <linux/of.h>
@@ -509,6 +510,8 @@ struct rproc_dump_segment {
  * @autonomous: true if an external entity has booted the remote processor
  * @dump_segments: list of segments in the firmware
  * @nb_vdev: number of vdev currently handled by rproc
+ * @char_dev: character device of the rproc
+ * @cdev_put_on_release: flag to indicate if remoteproc should be shutdown on @char_dev release
  */
 struct rproc {
 	struct list_head node;
@@ -546,6 +549,8 @@ struct rproc {
 	int nb_vdev;
 	u8 elf_class;
 	u16 elf_machine;
+	struct cdev cdev;
+	bool cdev_put_on_release;
 };
 
 /**
diff --git a/include/uapi/linux/remoteproc_cdev.h b/include/uapi/linux/remoteproc_cdev.h
new file mode 100644
index 000000000000..c43768e4b0dc
--- /dev/null
+++ b/include/uapi/linux/remoteproc_cdev.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * IOCTLs for Remoteproc's character device interface.
+ *
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _UAPI_REMOTEPROC_CDEV_H_
+#define _UAPI_REMOTEPROC_CDEV_H_
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define RPROC_MAGIC	0xB7
+
+/*
+ * The RPROC_SET_SHUTDOWN_ON_RELEASE ioctl allows to enable/disable the shutdown of a remote
+ * processor automatically when the controlling userpsace closes the char device interface.
+ *
+ * input parameter: integer
+ *   0		: disable automatic shutdown
+ *   other	: enable automatic shutdown
+ */
+#define RPROC_SET_SHUTDOWN_ON_RELEASE _IOW(RPROC_MAGIC, 1, __s32)
+
+/*
+ * The RPROC_GET_SHUTDOWN_ON_RELEASE ioctl gets information about whether the automatic shutdown of
+ * a remote processor is enabled or disabled when the controlling userspace closes the char device
+ * interface.
+ *
+ * output parameter: integer
+ *   0		: automatic shutdown disable
+ *   other	: automatic shutdown enable
+ */
+#define RPROC_GET_SHUTDOWN_ON_RELEASE _IOR(RPROC_MAGIC, 2, __s32)
+
+#endif
-- 
cgit v1.2.3


From 7de62bc09fe6d100ebd6c931c3f9a6fa7e6ed10f Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <olga.kornievskaia@gmail.com>
Date: Wed, 15 Jul 2020 13:17:52 -0400
Subject: SUNRPC dont update timeout value on connection reset

Current behaviour: every time a v3 operation is re-sent to the server
we update (double) the timeout. There is no distinction between whether
or not the previous timer had expired before the re-sent happened.

Here's the scenario:
1. Client sends a v3 operation
2. Server RST-s the connection (prior to the timeout) (eg., connection
is immediately reset)
3. Client re-sends a v3 operation but the timeout is now 120sec.

As a result, an application sees 2mins pause before a retry in case
server again does not reply.

Instead, this patch proposes to keep track off when the minor timeout
should happen and if it didn't, then don't update the new timeout.
Value is updated based on the previous value to make timeouts
predictable.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xprt.h | 1 +
 net/sunrpc/xprt.c           | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index e64bd8222f55..a603d48d2b2c 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -101,6 +101,7 @@ struct rpc_rqst {
 							 * used in the softirq.
 							 */
 	unsigned long		rq_majortimeo;	/* major timeout alarm */
+	unsigned long		rq_minortimeo;	/* minor timeout alarm */
 	unsigned long		rq_timeout;	/* Current timeout value */
 	ktime_t			rq_rtt;		/* round-trip time */
 	unsigned int		rq_retries;	/* # of retries */
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d5cc5db9dbf3..6ba9d5842629 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req)
 	req->rq_majortimeo += xprt_calc_majortimeo(req);
 }
 
+static void xprt_reset_minortimeo(struct rpc_rqst *req)
+{
+	req->rq_minortimeo += req->rq_timeout;
+}
+
 static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 {
 	unsigned long time_init;
@@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 		time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
 	req->rq_timeout = task->tk_client->cl_timeout->to_initval;
 	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+	req->rq_minortimeo = time_init + req->rq_timeout;
 }
 
 /**
@@ -631,6 +637,8 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
 	int status = 0;
 
+	if (time_before(jiffies, req->rq_minortimeo))
+		return status;
 	if (time_before(jiffies, req->rq_majortimeo)) {
 		if (to->to_exponential)
 			req->rq_timeout <<= 1;
@@ -649,6 +657,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 		spin_unlock(&xprt->transport_lock);
 		status = -ETIMEDOUT;
 	}
+	xprt_reset_minortimeo(req);
 
 	if (req->rq_timeout == 0) {
 		printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
-- 
cgit v1.2.3


From 262e6ae7081df304fc625cf368d5c2cbba2bb991 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 28 Jul 2020 23:33:33 +0200
Subject: modules: inherit TAINT_PROPRIETARY_MODULE

If a TAINT_PROPRIETARY_MODULE exports symbol, inherit the taint flag
for all modules importing these symbols, and don't allow loading
symbols from TAINT_PROPRIETARY_MODULE modules if the module previously
imported gplonly symbols.  Add a anti-circumvention devices so people
don't accidentally get themselves into trouble this way.

Comment from Greg:
  "Ah, the proven-to-be-illegal "GPL Condom" defense :)"

[jeyu: pr_info -> pr_err and pr_warn as per discussion]
Link: http://lore.kernel.org/r/20200730162957.GA22469@lst.de
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h |  1 +
 kernel/module.c        | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 30b0f5fcdb3c..e30ed5fa33a7 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -389,6 +389,7 @@ struct module {
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
 	const s32 *gpl_crcs;
+	bool using_gplonly_symbols;
 
 #ifdef CONFIG_UNUSED_SYMBOLS
 	/* unused exported symbols. */
diff --git a/kernel/module.c b/kernel/module.c
index 656f5ff27088..09bf5a652a47 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1431,6 +1431,24 @@ static int verify_namespace_is_imported(const struct load_info *info,
 	return 0;
 }
 
+static bool inherit_taint(struct module *mod, struct module *owner)
+{
+	if (!owner || !test_bit(TAINT_PROPRIETARY_MODULE, &owner->taints))
+		return true;
+
+	if (mod->using_gplonly_symbols) {
+		pr_err("%s: module using GPL-only symbols uses symbols from proprietary module %s.\n",
+			mod->name, owner->name);
+		return false;
+	}
+
+	if (!test_bit(TAINT_PROPRIETARY_MODULE, &mod->taints)) {
+		pr_warn("%s: module uses symbols from proprietary module %s, inheriting taint.\n",
+			mod->name, owner->name);
+		set_bit(TAINT_PROPRIETARY_MODULE, &mod->taints);
+	}
+	return true;
+}
 
 /* Resolve a symbol for this module.  I.e. if we find one, record usage. */
 static const struct kernel_symbol *resolve_symbol(struct module *mod,
@@ -1456,6 +1474,14 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	if (!sym)
 		goto unlock;
 
+	if (license == GPL_ONLY)
+		mod->using_gplonly_symbols = true;
+
+	if (!inherit_taint(mod, owner)) {
+		sym = NULL;
+		goto getname;
+	}
+
 	if (!check_version(info, name, mod, crc)) {
 		sym = ERR_PTR(-EINVAL);
 		goto getname;
-- 
cgit v1.2.3


From 75820314de26b00aaea0d0e79269c0d17914c5c4 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 4 Aug 2020 12:59:24 +0300
Subject: i2c: core: add generic I2C GPIO recovery

Multiple I2C bus drivers use similar bindings to obtain information needed
for I2C recovery. For example, for platforms using device-tree, the
properties look something like this:

&i2c {
	...
	pinctrl-names = "default", "gpio";
	pinctrl-0 = <&pinctrl_i2c_default>;
	pinctrl-1 = <&pinctrl_i2c_gpio>;
	sda-gpios = <&pio 0 GPIO_ACTIVE_HIGH>;
	scl-gpios = <&pio 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
	...
}

For this reason, we can add this common initialization in the core. This
way, other I2C bus drivers will be able to support GPIO recovery just by
providing a pointer to platform's pinctrl and calling i2c_recover_bus()
when SDA is stuck low.

Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
[wsa: inverted one logic for better readability, minor update to kdoc]
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c | 126 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c.h         |  11 ++++
 2 files changed, 137 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 69217d2193da..ece25560eae4 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -32,6 +32,7 @@
 #include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_wakeirq.h>
@@ -181,6 +182,8 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 
 	if (bri->prepare_recovery)
 		bri->prepare_recovery(adap);
+	if (bri->pinctrl)
+		pinctrl_select_state(bri->pinctrl, bri->pins_gpio);
 
 	/*
 	 * If we can set SDA, we will always create a STOP to ensure additional
@@ -236,6 +239,8 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 
 	if (bri->unprepare_recovery)
 		bri->unprepare_recovery(adap);
+	if (bri->pinctrl)
+		pinctrl_select_state(bri->pinctrl, bri->pins_default);
 
 	return ret;
 }
@@ -251,6 +256,125 @@ int i2c_recover_bus(struct i2c_adapter *adap)
 }
 EXPORT_SYMBOL_GPL(i2c_recover_bus);
 
+static void i2c_gpio_init_pinctrl_recovery(struct i2c_adapter *adap)
+{
+	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
+	struct device *dev = &adap->dev;
+	struct pinctrl *p = bri->pinctrl;
+
+	/*
+	 * we can't change states without pinctrl, so remove the states if
+	 * populated
+	 */
+	if (!p) {
+		bri->pins_default = NULL;
+		bri->pins_gpio = NULL;
+		return;
+	}
+
+	if (!bri->pins_default) {
+		bri->pins_default = pinctrl_lookup_state(p,
+							 PINCTRL_STATE_DEFAULT);
+		if (IS_ERR(bri->pins_default)) {
+			dev_dbg(dev, PINCTRL_STATE_DEFAULT " state not found for GPIO recovery\n");
+			bri->pins_default = NULL;
+		}
+	}
+	if (!bri->pins_gpio) {
+		bri->pins_gpio = pinctrl_lookup_state(p, "gpio");
+		if (IS_ERR(bri->pins_gpio))
+			bri->pins_gpio = pinctrl_lookup_state(p, "recovery");
+
+		if (IS_ERR(bri->pins_gpio)) {
+			dev_dbg(dev, "no gpio or recovery state found for GPIO recovery\n");
+			bri->pins_gpio = NULL;
+		}
+	}
+
+	/* for pinctrl state changes, we need all the information */
+	if (bri->pins_default && bri->pins_gpio) {
+		dev_info(dev, "using pinctrl states for GPIO recovery");
+	} else {
+		bri->pinctrl = NULL;
+		bri->pins_default = NULL;
+		bri->pins_gpio = NULL;
+	}
+}
+
+static int i2c_gpio_init_generic_recovery(struct i2c_adapter *adap)
+{
+	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
+	struct device *dev = &adap->dev;
+	struct gpio_desc *gpiod;
+	int ret = 0;
+
+	/*
+	 * don't touch the recovery information if the driver is not using
+	 * generic SCL recovery
+	 */
+	if (bri->recover_bus && bri->recover_bus != i2c_generic_scl_recovery)
+		return 0;
+
+	/*
+	 * pins might be taken as GPIO, so we should inform pinctrl about
+	 * this and move the state to GPIO
+	 */
+	if (bri->pinctrl)
+		pinctrl_select_state(bri->pinctrl, bri->pins_gpio);
+
+	/*
+	 * if there is incomplete or no recovery information, see if generic
+	 * GPIO recovery is available
+	 */
+	if (!bri->scl_gpiod) {
+		gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
+		if (PTR_ERR(gpiod) == -EPROBE_DEFER) {
+			ret  = -EPROBE_DEFER;
+			goto cleanup_pinctrl_state;
+		}
+		if (!IS_ERR(gpiod)) {
+			bri->scl_gpiod = gpiod;
+			bri->recover_bus = i2c_generic_scl_recovery;
+			dev_info(dev, "using generic GPIOs for recovery\n");
+		}
+	}
+
+	/* SDA GPIOD line is optional, so we care about DEFER only */
+	if (!bri->sda_gpiod) {
+		/*
+		 * We have SCL. Pull SCL low and wait a bit so that SDA glitches
+		 * have no effect.
+		 */
+		gpiod_direction_output(bri->scl_gpiod, 0);
+		udelay(10);
+		gpiod = devm_gpiod_get(dev, "sda", GPIOD_IN);
+
+		/* Wait a bit in case of a SDA glitch, and then release SCL. */
+		udelay(10);
+		gpiod_direction_output(bri->scl_gpiod, 1);
+
+		if (PTR_ERR(gpiod) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto cleanup_pinctrl_state;
+		}
+		if (!IS_ERR(gpiod))
+			bri->sda_gpiod = gpiod;
+	}
+
+cleanup_pinctrl_state:
+	/* change the state of the pins back to their default state */
+	if (bri->pinctrl)
+		pinctrl_select_state(bri->pinctrl, bri->pins_default);
+
+	return ret;
+}
+
+static int i2c_gpio_init_recovery(struct i2c_adapter *adap)
+{
+	i2c_gpio_init_pinctrl_recovery(adap);
+	return i2c_gpio_init_generic_recovery(adap);
+}
+
 static void i2c_init_recovery(struct i2c_adapter *adap)
 {
 	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
@@ -259,6 +383,8 @@ static void i2c_init_recovery(struct i2c_adapter *adap)
 	if (!bri)
 		return;
 
+	i2c_gpio_init_recovery(adap);
+
 	if (!bri->recover_bus) {
 		err_str = "no recover_bus() found";
 		goto err;
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 8ea9c3f86dba..d387d3786429 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -606,6 +606,14 @@ struct i2c_timings {
  *	may configure padmux here for SDA/SCL line or something else they want.
  * @scl_gpiod: gpiod of the SCL line. Only required for GPIO recovery.
  * @sda_gpiod: gpiod of the SDA line. Only required for GPIO recovery.
+ * @pinctrl: pinctrl used by GPIO recovery to change the state of the I2C pins.
+ *      Optional.
+ * @pins_default: default pinctrl state of SCL/SDA lines, when they are assigned
+ *      to the I2C bus. Optional. Populated internally for GPIO recovery, if
+ *      state with the name PINCTRL_STATE_DEFAULT is found and pinctrl is valid.
+ * @pins_gpio: recovery pinctrl state of SCL/SDA lines, when they are used as
+ *      GPIOs. Optional. Populated internally for GPIO recovery, if this state
+ *      is called "gpio" or "recovery" and pinctrl is valid.
  */
 struct i2c_bus_recovery_info {
 	int (*recover_bus)(struct i2c_adapter *adap);
@@ -622,6 +630,9 @@ struct i2c_bus_recovery_info {
 	/* gpio recovery */
 	struct gpio_desc *scl_gpiod;
 	struct gpio_desc *sda_gpiod;
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_default;
+	struct pinctrl_state *pins_gpio;
 };
 
 int i2c_recover_bus(struct i2c_adapter *adap);
-- 
cgit v1.2.3


From 5487196878bc926a1ee15069c13aa48b9a894fab Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 10 Jul 2020 06:46:04 -0400
Subject: virtio_ring: sparse warning fixup

virtio_store_mb was built with split ring in mind so it accepts
__virtio16 arguments. Packed ring uses __le16 values, so sparse
complains.  It's just a store with some barriers so let's convert it to
a macro, we don't loose too much type safety by doing that.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
---
 include/linux/virtio_ring.h | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 3dc70adfe5f5..b485b13fa50b 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -46,16 +46,15 @@ static inline void virtio_wmb(bool weak_barriers)
 		dma_wmb();
 }
 
-static inline void virtio_store_mb(bool weak_barriers,
-				   __virtio16 *p, __virtio16 v)
-{
-	if (weak_barriers) {
-		virt_store_mb(*p, v);
-	} else {
-		WRITE_ONCE(*p, v);
-		mb();
-	}
-}
+#define virtio_store_mb(weak_barriers, p, v) \
+do { \
+	if (weak_barriers) { \
+		virt_store_mb(*p, v); \
+	} else { \
+		WRITE_ONCE(*p, v); \
+		mb(); \
+	} \
+} while (0) \
 
 struct virtio_device;
 struct virtqueue;
-- 
cgit v1.2.3


From a4235ec06acf05c58081700cda02dcd480d9e9cb Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 10 Jul 2020 03:20:21 -0400
Subject: virtio: allow __virtioXX, __leXX in config space

Currently all config space fields are of the type __uXX.
This confuses people and some drivers (notably vdpa)
access them using CPU endian-ness - which only
works well for legacy or LE platforms.

Update virtio_cread/virtio_cwrite macros to allow __virtioXX
and __leXX field types. Follow-up patches will convert
config space to use these types.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
---
 include/linux/virtio_config.h | 50 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 48 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 3b4eae5ac5e3..64da491936f7 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -6,6 +6,7 @@
 #include <linux/bug.h>
 #include <linux/virtio.h>
 #include <linux/virtio_byteorder.h>
+#include <linux/compiler_types.h>
 #include <uapi/linux/virtio_config.h>
 
 struct irq_affinity;
@@ -287,12 +288,57 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
 
+/*
+ * Only the checker differentiates between __virtioXX and __uXX types. But we
+ * try to share as much code as we can with the regular GCC build.
+ */
+#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__)
+
+/* Not a checker - we can keep things simple */
+#define __virtio_native_typeof(x) typeof(x)
+
+#else
+
+/*
+ * We build this out of a couple of helper macros in a vain attempt to
+ * help you keep your lunch down while reading it.
+ */
+#define __virtio_pick_value(x, type, then, otherwise)			\
+	__builtin_choose_expr(__same_type(x, type), then, otherwise)
+
+#define __virtio_pick_type(x, type, then, otherwise)			\
+	__virtio_pick_value(x, type, (then)0, otherwise)
+
+#define __virtio_pick_endian(x, x16, x32, x64, otherwise)			\
+	__virtio_pick_type(x, x16, __u16,					\
+		__virtio_pick_type(x, x32, __u32,				\
+			__virtio_pick_type(x, x64, __u64,			\
+				otherwise)))
+
+#define __virtio_native_typeof(x) typeof(					\
+	__virtio_pick_type(x, __u8, __u8,					\
+		__virtio_pick_endian(x, __virtio16, __virtio32, __virtio64,	\
+			__virtio_pick_endian(x, __le16, __le32, __le64,		\
+				__virtio_pick_endian(x, __u16, __u32, __u64,	\
+					/* No other type allowed */		\
+					(void)0)))))
+
+#endif
+
+#define __virtio_native_type(structname, member) \
+	__virtio_native_typeof(((structname*)0)->member)
+
+#define __virtio_typecheck(structname, member, val) \
+		/* Must match the member's type, and be integer */ \
+		typecheck(__virtio_native_type(structname, member), (val))
+
+
 /* Config space accessors. */
 #define virtio_cread(vdev, structname, member, ptr)			\
 	do {								\
 		might_sleep();						\
 		/* Must match the member's type, and be integer */	\
-		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
+		if (!__virtio_typecheck(structname, member, *(ptr)))	\
 			(*ptr) = 1;					\
 									\
 		switch (sizeof(*ptr)) {					\
@@ -322,7 +368,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 	do {								\
 		might_sleep();						\
 		/* Must match the member's type, and be integer */	\
-		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
+		if (!__virtio_typecheck(structname, member, *(ptr)))	\
 			BUG_ON((*ptr) == 1);				\
 									\
 		switch (sizeof(*ptr)) {					\
-- 
cgit v1.2.3


From 4a04cfb0eb5e00432f9ff978f2b81bd1736e85db Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 10 Jul 2020 07:55:52 -0400
Subject: virtio_config: disallow native type fields

Transitional devices should all use __virtioXX types (and __leXX for
fields not present in legacy devices).
Modern ones should use __leXX.
_uXX type would be a bug.
Let's prevent that.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 64da491936f7..c68f58f3bf34 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -319,9 +319,8 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 	__virtio_pick_type(x, __u8, __u8,					\
 		__virtio_pick_endian(x, __virtio16, __virtio32, __virtio64,	\
 			__virtio_pick_endian(x, __le16, __le32, __le64,		\
-				__virtio_pick_endian(x, __u16, __u32, __u64,	\
-					/* No other type allowed */		\
-					(void)0)))))
+				/* No other type allowed */			\
+				(void)0))))
 
 #endif
 
-- 
cgit v1.2.3


From 452639a64ad880792652b6d20cc5c8dd4ecf27d9 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 27 Jul 2020 10:51:55 -0400
Subject: vdpa: make sure set_features is invoked for legacy

Some legacy guests just assume features are 0 after reset.
We detect that config space is accessed before features are
set and set features to 0 automatically.
Note: some legacy guests might not even access config space, if this is
reported in the field we might need to catch a kick to handle these.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/vdpa.c  |  1 +
 include/linux/vdpa.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index de211ef3738c..7105265e4793 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -96,6 +96,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->dev.release = vdpa_release_dev;
 	vdev->index = err;
 	vdev->config = config;
+	vdev->features_valid = false;
 
 	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
 	if (err)
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 239db794357c..29b8296f1414 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -33,12 +33,14 @@ struct vdpa_notification_area {
  * @dma_dev: the actual device that is performing DMA
  * @config: the configuration ops for this device.
  * @index: device index
+ * @features_valid: were features initialized? for legacy guests
  */
 struct vdpa_device {
 	struct device dev;
 	struct device *dma_dev;
 	const struct vdpa_config_ops *config;
 	unsigned int index;
+	bool features_valid;
 };
 
 /**
@@ -266,4 +268,36 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 {
 	return vdev->dma_dev;
 }
+
+static inline void vdpa_reset(struct vdpa_device *vdev)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	vdev->features_valid = false;
+        ops->set_status(vdev, 0);
+}
+
+static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	vdev->features_valid = true;
+        return ops->set_features(vdev, features);
+}
+
+
+static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
+				   void *buf, unsigned int len)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	/*
+	 * Config accesses aren't supposed to trigger before features are set.
+	 * If it does happen we assume a legacy guest.
+	 */
+	if (!vdev->features_valid)
+		vdpa_set_features(vdev, 0);
+	ops->get_config(vdev, offset, buf, len);
+}
+
 #endif /* _LINUX_VDPA_H */
-- 
cgit v1.2.3


From cacaf775c699e9e8473491197587535f1c10ac8f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 30 Jul 2020 16:12:40 -0400
Subject: virtio_config: cread/write cleanup

Use vars of the correct type instead of casting.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index c68f58f3bf34..5c3b02245ecd 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -444,53 +444,60 @@ static inline void virtio_cwrite8(struct virtio_device *vdev,
 static inline u16 virtio_cread16(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u16 ret;
+	__virtio16 ret;
 
 	might_sleep();
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return virtio16_to_cpu(vdev, (__force __virtio16)ret);
+	return virtio16_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite16(struct virtio_device *vdev,
 				   unsigned int offset, u16 val)
 {
+	__virtio16 v;
+
 	might_sleep();
-	val = (__force u16)cpu_to_virtio16(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio16(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 static inline u32 virtio_cread32(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u32 ret;
+	__virtio32 ret;
 
 	might_sleep();
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return virtio32_to_cpu(vdev, (__force __virtio32)ret);
+	return virtio32_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite32(struct virtio_device *vdev,
 				   unsigned int offset, u32 val)
 {
+	__virtio32 v;
+
 	might_sleep();
-	val = (__force u32)cpu_to_virtio32(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio32(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 static inline u64 virtio_cread64(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u64 ret;
+	__virtio64 ret;
+
 	__virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret));
-	return virtio64_to_cpu(vdev, (__force __virtio64)ret);
+	return virtio64_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite64(struct virtio_device *vdev,
 				   unsigned int offset, u64 val)
 {
+	__virtio64 v;
+
 	might_sleep();
-	val = (__force u64)cpu_to_virtio64(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio64(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 /* Conditional config space accessors. */
-- 
cgit v1.2.3


From a5b90f2db8e0ef6504695cbd36a65fd8296338ee Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 3 Aug 2020 16:08:11 -0400
Subject: virtio_config: rewrite using _Generic

Min compiler version has been raised, so that's ok now.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 161 ++++++++++++++++++++----------------------
 1 file changed, 76 insertions(+), 85 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 5c3b02245ecd..7fa000f02721 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -288,112 +288,103 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
 
-/*
- * Only the checker differentiates between __virtioXX and __uXX types. But we
- * try to share as much code as we can with the regular GCC build.
- */
-#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__)
-
-/* Not a checker - we can keep things simple */
-#define __virtio_native_typeof(x) typeof(x)
-
-#else
-
-/*
- * We build this out of a couple of helper macros in a vain attempt to
- * help you keep your lunch down while reading it.
- */
-#define __virtio_pick_value(x, type, then, otherwise)			\
-	__builtin_choose_expr(__same_type(x, type), then, otherwise)
-
-#define __virtio_pick_type(x, type, then, otherwise)			\
-	__virtio_pick_value(x, type, (then)0, otherwise)
-
-#define __virtio_pick_endian(x, x16, x32, x64, otherwise)			\
-	__virtio_pick_type(x, x16, __u16,					\
-		__virtio_pick_type(x, x32, __u32,				\
-			__virtio_pick_type(x, x64, __u64,			\
-				otherwise)))
-
-#define __virtio_native_typeof(x) typeof(					\
-	__virtio_pick_type(x, __u8, __u8,					\
-		__virtio_pick_endian(x, __virtio16, __virtio32, __virtio64,	\
-			__virtio_pick_endian(x, __le16, __le32, __le64,		\
-				/* No other type allowed */			\
-				(void)0))))
-
-#endif
+#define virtio_to_cpu(vdev, x) \
+	_Generic((x), \
+		__u8: (x), \
+		__virtio16: virtio16_to_cpu((vdev), (x)), \
+		__virtio32: virtio32_to_cpu((vdev), (x)), \
+		__virtio64: virtio64_to_cpu((vdev), (x)), \
+		/*
+		 * Why define a default? checker can distinguish between
+		 * e.g. __u16, __le16 and __virtio16, but GCC can't so
+		 * attempts to define variants for both look like a duplicate
+		 * variant to it.
+		 */ \
+		default: _Generic((x), \
+				 __u8: (x), \
+				 __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \
+				 __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \
+				 __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \
+				 default: _Generic((x), \
+						  __u8: (x), \
+						  __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \
+						  __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \
+						  __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \
+						  ) \
+				 ) \
+		)
+
+#define cpu_to_virtio(vdev, x, m) \
+	_Generic((m), \
+		__u8: (x), \
+		__virtio16: cpu_to_virtio16((vdev), (x)), \
+		__virtio32: cpu_to_virtio32((vdev), (x)), \
+		__virtio64: cpu_to_virtio64((vdev), (x)), \
+		/*
+		 * Why define a default? checker can distinguish between
+		 * e.g. __u16, __le16 and __virtio16, but GCC can't so
+		 * attempts to define variants for both look like a duplicate
+		 * variant to it.
+		 */ \
+		default: _Generic((m), \
+				 __u8: (x), \
+				 __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \
+				 __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \
+				 __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \
+				 default: _Generic((m), \
+						  __u8: (x), \
+						  __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \
+						  __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \
+						  __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \
+						  ) \
+				 ) \
+		)
 
 #define __virtio_native_type(structname, member) \
-	__virtio_native_typeof(((structname*)0)->member)
-
-#define __virtio_typecheck(structname, member, val) \
-		/* Must match the member's type, and be integer */ \
-		typecheck(__virtio_native_type(structname, member), (val))
-
+	typeof(virtio_to_cpu(NULL, ((structname*)0)->member))
 
 /* Config space accessors. */
 #define virtio_cread(vdev, structname, member, ptr)			\
 	do {								\
+		typeof(((structname*)0)->member) virtio_cread_v;	\
+									\
 		might_sleep();						\
-		/* Must match the member's type, and be integer */	\
-		if (!__virtio_typecheck(structname, member, *(ptr)))	\
-			(*ptr) = 1;					\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_to_cpu((vdev), virtio_cread_v)), *(ptr)); \
 									\
-		switch (sizeof(*ptr)) {					\
+		switch (sizeof(virtio_cread_v)) {			\
 		case 1:							\
-			*(ptr) = virtio_cread8(vdev,			\
-					       offsetof(structname, member)); \
-			break;						\
 		case 2:							\
-			*(ptr) = virtio_cread16(vdev,			\
-						offsetof(structname, member)); \
-			break;						\
 		case 4:							\
-			*(ptr) = virtio_cread32(vdev,			\
-						offsetof(structname, member)); \
-			break;						\
-		case 8:							\
-			*(ptr) = virtio_cread64(vdev,			\
-						offsetof(structname, member)); \
+			vdev->config->get((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  sizeof(virtio_cread_v));	\
 			break;						\
 		default:						\
-			BUG();						\
+			__virtio_cread_many((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  1,				\
+					  sizeof(virtio_cread_v));	\
+			break;						\
 		}							\
+		*(ptr) = virtio_to_cpu(vdev, virtio_cread_v);		\
 	} while(0)
 
 /* Config space accessors. */
 #define virtio_cwrite(vdev, structname, member, ptr)			\
 	do {								\
+		typeof(((structname*)0)->member) virtio_cwrite_v =	\
+			cpu_to_virtio(vdev, *(ptr), ((structname*)0)->member); \
+									\
 		might_sleep();						\
-		/* Must match the member's type, and be integer */	\
-		if (!__virtio_typecheck(structname, member, *(ptr)))	\
-			BUG_ON((*ptr) == 1);				\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_to_cpu((vdev), virtio_cwrite_v)), *(ptr)); \
 									\
-		switch (sizeof(*ptr)) {					\
-		case 1:							\
-			virtio_cwrite8(vdev,				\
-				       offsetof(structname, member),	\
-				       *(ptr));				\
-			break;						\
-		case 2:							\
-			virtio_cwrite16(vdev,				\
-					offsetof(structname, member),	\
-					*(ptr));			\
-			break;						\
-		case 4:							\
-			virtio_cwrite32(vdev,				\
-					offsetof(structname, member),	\
-					*(ptr));			\
-			break;						\
-		case 8:							\
-			virtio_cwrite64(vdev,				\
-					offsetof(structname, member),	\
-					*(ptr));			\
-			break;						\
-		default:						\
-			BUG();						\
-		}							\
+		vdev->config->set((vdev), offsetof(structname, member),	\
+				  &virtio_cwrite_v,			\
+				  sizeof(virtio_cwrite_v));		\
 	} while(0)
 
 /* Read @count fields, @bytes each. */
-- 
cgit v1.2.3


From 14191c15ab9d87e60d2ebbfbf6df83d546152af1 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 10 Jul 2020 07:55:52 -0400
Subject: virtio_config: disallow native type fields (again)

_Generic version allowed __uXX types but that is no longer necessary:

Transitional devices should all use __virtioXX types (and __leXX for
fields not present in the legacy devices).
Modern ones should use __leXX.
_uXX type would be a bug.
Let's prevent that.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 7fa000f02721..441fd6dd42ab 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -304,13 +304,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 				 __u8: (x), \
 				 __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \
 				 __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \
-				 __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \
-				 default: _Generic((x), \
-						  __u8: (x), \
-						  __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \
-						  __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \
-						  __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \
-						  ) \
+				 __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \
 				 ) \
 		)
 
@@ -330,13 +324,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 				 __u8: (x), \
 				 __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \
 				 __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \
-				 __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \
-				 default: _Generic((m), \
-						  __u8: (x), \
-						  __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \
-						  __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \
-						  __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \
-						  ) \
+				 __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \
 				 ) \
 		)
 
-- 
cgit v1.2.3


From e598960ff5e511b76a0eb8dff25207d35c2442c8 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 4 Aug 2020 17:33:08 -0400
Subject: virtio_config: LE config space accessors

To be used by modern code, as well as to handle LE only fields such as
balloon.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 65 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 441fd6dd42ab..5b5196fec899 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -375,6 +375,71 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 				  sizeof(virtio_cwrite_v));		\
 	} while(0)
 
+/*
+ * Nothing virtio-specific about these, but let's worry about generalizing
+ * these later.
+ */
+#define virtio_le_to_cpu(x) \
+	_Generic((x), \
+		__u8: (x), \
+		 __le16: le16_to_cpu(x), \
+		 __le32: le32_to_cpu(x), \
+		 __le64: le64_to_cpu(x) \
+		)
+
+#define virtio_cpu_to_le(x, m) \
+	_Generic((m), \
+		 __u8: (x), \
+		 __le16: cpu_to_le16(x), \
+		 __le32: cpu_to_le32(x), \
+		 __le64: cpu_to_le64(x) \
+		)
+
+/* LE (e.g. modern) Config space accessors. */
+#define virtio_cread_le(vdev, structname, member, ptr)			\
+	do {								\
+		typeof(((structname*)0)->member) virtio_cread_v;	\
+									\
+		might_sleep();						\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_le_to_cpu(virtio_cread_v)), *(ptr)); \
+									\
+		switch (sizeof(virtio_cread_v)) {			\
+		case 1:							\
+		case 2:							\
+		case 4:							\
+			vdev->config->get((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  sizeof(virtio_cread_v));	\
+			break;						\
+		default:						\
+			__virtio_cread_many((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  1,				\
+					  sizeof(virtio_cread_v));	\
+			break;						\
+		}							\
+		*(ptr) = virtio_le_to_cpu(virtio_cread_v);		\
+	} while(0)
+
+/* Config space accessors. */
+#define virtio_cwrite_le(vdev, structname, member, ptr)			\
+	do {								\
+		typeof(((structname*)0)->member) virtio_cwrite_v =	\
+			virtio_cpu_to_le(*(ptr), ((structname*)0)->member); \
+									\
+		might_sleep();						\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_le_to_cpu(virtio_cwrite_v)), *(ptr)); \
+									\
+		vdev->config->set((vdev), offsetof(structname, member),	\
+				  &virtio_cwrite_v,			\
+				  sizeof(virtio_cwrite_v));		\
+	} while(0)
+
+
 /* Read @count fields, @bytes each. */
 static inline void __virtio_cread_many(struct virtio_device *vdev,
 				       unsigned int offset,
-- 
cgit v1.2.3


From e3e7994d53082e48d2a6a248376683d3be3dff9d Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 4 Aug 2020 18:02:39 -0400
Subject: virtio_caif: correct tags for config space fields

Tag config space fields as having virtio endian-ness.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_caif.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h
index 5d2d3124ca3d..ea722479510c 100644
--- a/include/linux/virtio_caif.h
+++ b/include/linux/virtio_caif.h
@@ -11,9 +11,9 @@
 
 #include <linux/types.h>
 struct virtio_caif_transf_config {
-	u16 headroom;
-	u16 tailroom;
-	u32 mtu;
+	__virtio16 headroom;
+	__virtio16 tailroom;
+	__virtio32 mtu;
 	u8 reserved[4];
 };
 
-- 
cgit v1.2.3


From 035ce4210be1257dd417785ff7818b5c0f2205fb Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 5 Aug 2020 09:17:38 -0400
Subject: virtio_config: add virtio_cread_le_feature

Mirrors virtio_cread_feature but for LE fields.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 5b5196fec899..cc7a2b1fd7b2 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -555,4 +555,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
 		_r;							\
 	})
 
+/* Conditional config space accessors. */
+#define virtio_cread_le_feature(vdev, fbit, structname, member, ptr)	\
+	({								\
+		int _r = 0;						\
+		if (!virtio_has_feature(vdev, fbit))			\
+			_r = -ENOENT;					\
+		else							\
+			virtio_cread_le((vdev), structname, member, ptr); \
+		_r;							\
+	})
 #endif /* _LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3


From 83eb9db95eb453f1db651909ad4598c3d44ef1e1 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 5 Aug 2020 07:29:12 -0400
Subject: virtio_config: drop LE option from config space

All drivers now use virtio_cread/write_le for LE config
space fields. Drop LE option from virtio_cread/write, only leaving
the option to access transitional fields.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index cc7a2b1fd7b2..ecb166c824bb 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -293,19 +293,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 		__u8: (x), \
 		__virtio16: virtio16_to_cpu((vdev), (x)), \
 		__virtio32: virtio32_to_cpu((vdev), (x)), \
-		__virtio64: virtio64_to_cpu((vdev), (x)), \
-		/*
-		 * Why define a default? checker can distinguish between
-		 * e.g. __u16, __le16 and __virtio16, but GCC can't so
-		 * attempts to define variants for both look like a duplicate
-		 * variant to it.
-		 */ \
-		default: _Generic((x), \
-				 __u8: (x), \
-				 __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \
-				 __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \
-				 __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \
-				 ) \
+		__virtio64: virtio64_to_cpu((vdev), (x)) \
 		)
 
 #define cpu_to_virtio(vdev, x, m) \
@@ -313,19 +301,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 		__u8: (x), \
 		__virtio16: cpu_to_virtio16((vdev), (x)), \
 		__virtio32: cpu_to_virtio32((vdev), (x)), \
-		__virtio64: cpu_to_virtio64((vdev), (x)), \
-		/*
-		 * Why define a default? checker can distinguish between
-		 * e.g. __u16, __le16 and __virtio16, but GCC can't so
-		 * attempts to define variants for both look like a duplicate
-		 * variant to it.
-		 */ \
-		default: _Generic((m), \
-				 __u8: (x), \
-				 __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \
-				 __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \
-				 __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \
-				 ) \
+		__virtio64: cpu_to_virtio64((vdev), (x)) \
 		)
 
 #define __virtio_native_type(structname, member) \
-- 
cgit v1.2.3


From 7164675ab5caf46867d6a5448f4ff3af92d80a30 Mon Sep 17 00:00:00 2001
From: Zhu Lingshan <lingshan.zhu@intel.com>
Date: Fri, 31 Jul 2020 14:55:30 +0800
Subject: vDPA: add get_vq_irq() in vdpa_config_ops

This commit adds a new function get_vq_irq() in struct
vdpa_config_ops, which will return the irq number of a
virtqueue.

Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20200731065533.4144-4-lingshan.zhu@intel.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/vdpa.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 29b8296f1414..5c530a64aa06 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -89,6 +89,12 @@ struct vdpa_device {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
+ * @get_vq_irq:			Get the irq number of a virtqueue (optional,
+ *				but must implemented if require vq irq offloading)
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns int: irq number of a virtqueue,
+ *				negative number if no irq assigned.
  * @get_vq_align:		Get the virtqueue align requirement
  *				for the device
  *				@vdev: vdpa device
@@ -180,6 +186,7 @@ struct vdpa_config_ops {
 	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
+	int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx);
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
-- 
cgit v1.2.3


From 4c05433bc6fb4ae172270f0279be8ba89a3da64f Mon Sep 17 00:00:00 2001
From: Zhu Lingshan <lingshan.zhu@intel.com>
Date: Tue, 4 Aug 2020 18:21:23 +0800
Subject: vDPA: dont change vq irq after DRIVER_OK

IRQ of a vq is not expected to be changed in a DRIVER_OK ~ !DRIVER_OK
period for irq offloading purposes. Place this comment at the side of
bus ops get_vq_irq than in set_status in vhost_vdpa.

Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Link: https://lore.kernel.org/r/20200804102123.69978-1-lingshan.zhu@intel.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vdpa.c | 1 -
 include/linux/vdpa.h | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 7441b9803eae..f8f8c9cf05b0 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -172,7 +172,6 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 
 	ops->set_status(vdpa, status);
 
-	/* vq irq is not expected to be changed once DRIVER_OK is set */
 	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
 		for (i = 0; i < nvqs; i++)
 			vhost_vdpa_setup_vq_irq(v, i);
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 5c530a64aa06..565298cb45d2 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -186,6 +186,7 @@ struct vdpa_config_ops {
 	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
+	/* vq irq is not expected to be changed once DRIVER_OK is set */
 	int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx);
 
 	/* Device ops */
-- 
cgit v1.2.3


From 923a3a863ae0c26876d704fb3453069e11ebdcb6 Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@mellanox.com>
Date: Mon, 4 May 2020 17:14:24 +0300
Subject: platform_data/mlxreg: support new watchdog type with longer timeout
 period

Add new watchdog type 3 with longer timeout period.
Extend size of health_cntr field that that can be used to init watchdog
timeout period.

Signed-off-by: Michael Shych <michaelsh@mellanox.com>
Reviewed-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200504141427.17685-2-michaelsh@mellanox.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 include/linux/platform_data/mlxreg.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index b8da8aef2446..2c5e58d1d77b 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -43,10 +43,13 @@
  *
  * TYPE1 HW watchdog implementation exist in old systems.
  * All new systems have TYPE2 HW watchdog.
+ * TYPE3 HW watchdog can exist on all systems with new CPLD.
+ * TYPE3 is selected by WD capability bit.
  */
 enum mlxreg_wdt_type {
 	MLX_WDT_TYPE1,
 	MLX_WDT_TYPE2,
+	MLX_WDT_TYPE3,
 };
 
 /**
@@ -90,7 +93,7 @@ struct mlxreg_core_data {
 	umode_t	mode;
 	struct device_node *np;
 	struct mlxreg_hotplug_device hpdev;
-	u8 health_cntr;
+	u32 health_cntr;
 	bool attached;
 };
 
-- 
cgit v1.2.3


From cef9572e9af373cefd1adc9e771e89670da5da3c Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 17 Jul 2020 16:29:56 +0300
Subject: watchdog: add support for adjusting last known HW keepalive time

Certain watchdogs require the watchdog only to be pinged within a
specific time window, pinging too early or too late cause the watchdog
to fire. In cases where this sort of watchdog has been started before
kernel comes up, we must adjust the watchdog keepalive window to match
the actually running timer, so add a new driver API for this purpose.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717132958.14304-3-t-kristo@ti.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/watchdog/watchdog-kernel-api.rst | 12 +++++++++++
 drivers/watchdog/watchdog_dev.c                | 30 ++++++++++++++++++++++++++
 include/linux/watchdog.h                       |  2 ++
 3 files changed, 44 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/watchdog/watchdog-kernel-api.rst b/Documentation/watchdog/watchdog-kernel-api.rst
index 068a55ee0d4a..baf44e986b07 100644
--- a/Documentation/watchdog/watchdog-kernel-api.rst
+++ b/Documentation/watchdog/watchdog-kernel-api.rst
@@ -336,3 +336,15 @@ an action is taken by a preconfigured pretimeout governor preassigned to
 the watchdog device. If watchdog pretimeout governor framework is not
 enabled, watchdog_notify_pretimeout() prints a notification message to
 the kernel log buffer.
+
+To set the last known HW keepalive time for a watchdog, the following function
+should be used::
+
+  int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd,
+                                     unsigned int last_ping_ms)
+
+This function must be called immediately after watchdog registration. It
+sets the last known hardware heartbeat to have happened last_ping_ms before
+current time. Calling this is only needed if the watchdog is already running
+when probe is called, and the watchdog can only be pinged after the
+min_hw_heartbeat_ms time has passed from the last ping.
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 0ad1c393c00e..531e74994b61 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -1138,6 +1138,36 @@ void watchdog_dev_unregister(struct watchdog_device *wdd)
 	watchdog_cdev_unregister(wdd);
 }
 
+/*
+ *	watchdog_set_last_hw_keepalive: set last HW keepalive time for watchdog
+ *	@wdd: watchdog device
+ *	@last_ping_ms: time since last HW heartbeat
+ *
+ *	Adjusts the last known HW keepalive time for a watchdog timer.
+ *	This is needed if the watchdog is already running when the probe
+ *	function is called, and it can't be pinged immediately. This
+ *	function must be called immediately after watchdog registration,
+ *	and min_hw_heartbeat_ms must be set for this to be useful.
+ */
+int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd,
+				   unsigned int last_ping_ms)
+{
+	struct watchdog_core_data *wd_data;
+	ktime_t now;
+
+	if (!wdd)
+		return -EINVAL;
+
+	wd_data = wdd->wd_data;
+
+	now = ktime_get();
+
+	wd_data->last_hw_keepalive = ktime_sub(now, ms_to_ktime(last_ping_ms));
+
+	return __watchdog_ping(wdd);
+}
+EXPORT_SYMBOL_GPL(watchdog_set_last_hw_keepalive);
+
 /*
  *	watchdog_dev_init: init dev part of watchdog core
  *
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 1464ce6ffa31..9b19e6bb68b5 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -210,6 +210,8 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd,
 extern int watchdog_register_device(struct watchdog_device *);
 extern void watchdog_unregister_device(struct watchdog_device *);
 
+int watchdog_set_last_hw_keepalive(struct watchdog_device *, unsigned int);
+
 /* devres register variant */
 int devm_watchdog_register_device(struct device *dev, struct watchdog_device *);
 
-- 
cgit v1.2.3


From a9974489b61c09c702c85c6cba3d1a3fd1be7a15 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Tue, 4 Aug 2020 19:20:42 +0300
Subject: vdpa: remove hard coded virtq num

This will enable vdpa providers to add support for multi queue feature
and publish it to upper layers (vhost and virtio).

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20200804162048.22587-7-eli@mellanox.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/ifcvf/ifcvf_main.c  | 3 ++-
 drivers/vdpa/vdpa.c              | 3 +++
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 4 ++--
 drivers/vhost/vdpa.c             | 9 +++------
 include/linux/vdpa.h             | 6 ++++--
 5 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index a902b29b0d29..7c93225367db 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -431,7 +431,8 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops);
+				    dev, &ifc_vdpa_ops,
+				    IFCVF_MAX_QUEUE_PAIRS * 2);
 	if (adapter == NULL) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return -ENOMEM;
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 7105265e4793..a69ffc991e13 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -61,6 +61,7 @@ static void vdpa_release_dev(struct device *d)
  * initialized but before registered.
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
+ * @nvqs: number of virtqueues supported by this device
  * @size: size of the parent structure that contains private data
  *
  * Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -71,6 +72,7 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					int nvqs,
 					size_t size)
 {
 	struct vdpa_device *vdev;
@@ -97,6 +99,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->index = err;
 	vdev->config = config;
 	vdev->features_valid = false;
+	vdev->nvqs = nvqs;
 
 	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
 	if (err)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 7b34d663778f..58baff89cc29 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -65,7 +65,7 @@ static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
 /* State of each vdpasim device */
 struct vdpasim {
 	struct vdpa_device vdpa;
-	struct vdpasim_virtqueue vqs[2];
+	struct vdpasim_virtqueue vqs[VDPASIM_VQ_NUM];
 	struct work_struct work;
 	/* spinlock to synchronize virtqueue state */
 	spinlock_t lock;
@@ -352,7 +352,7 @@ static struct vdpasim *vdpasim_create(void)
 	else
 		ops = &vdpasim_net_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops);
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
 	if (!vdpasim)
 		goto err_alloc;
 
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index e80db051845d..2d8c950ad3a8 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -32,9 +32,6 @@ enum {
 	(1ULL << VHOST_BACKEND_F_IOTLB_BATCH),
 };
 
-/* Currently, only network backend w/o multiqueue is supported. */
-#define VHOST_VDPA_VQ_MAX	2
-
 #define VHOST_VDPA_DEV_MAX (1U << MINORBITS)
 
 struct vhost_vdpa {
@@ -930,7 +927,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 {
 	const struct vdpa_config_ops *ops = vdpa->config;
 	struct vhost_vdpa *v;
-	int minor, nvqs = VHOST_VDPA_VQ_MAX;
+	int minor;
 	int r;
 
 	/* Currently, we only accept the network devices. */
@@ -951,14 +948,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 	atomic_set(&v->opened, 0);
 	v->minor = minor;
 	v->vdpa = vdpa;
-	v->nvqs = nvqs;
+	v->nvqs = vdpa->nvqs;
 	v->virtio_id = ops->get_device_id(vdpa);
 
 	device_initialize(&v->dev);
 	v->dev.release = vhost_vdpa_release_dev;
 	v->dev.parent = &vdpa->dev;
 	v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor);
-	v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue),
+	v->vqs = kmalloc_array(v->nvqs, sizeof(struct vhost_virtqueue),
 			       GFP_KERNEL);
 	if (!v->vqs) {
 		r = -ENOMEM;
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 565298cb45d2..b5901cde73e0 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -41,6 +41,7 @@ struct vdpa_device {
 	const struct vdpa_config_ops *config;
 	unsigned int index;
 	bool features_valid;
+	int nvqs;
 };
 
 /**
@@ -218,11 +219,12 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					int nvqs,
 					size_t size);
 
-#define vdpa_alloc_device(dev_struct, member, parent, config)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs)   \
 			  container_of(__vdpa_alloc_device( \
-				       parent, config, \
+				       parent, config, nvqs, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
 				       dev_struct, member))), \
-- 
cgit v1.2.3


From aac50c0bd434794b9950181349099e709ca4edad Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Tue, 4 Aug 2020 19:20:43 +0300
Subject: net/vdpa: Use struct for set/get vq state

For now VQ state involves 16 bit available index value encoded in u64
variable. In the future it will be extended to contain more fields. Use
struct to contain the state, now containing only a single u16 for the
available index. In the future we can add fields to this struct.

Reviewed-by: Parav Pandit <parav@mellanox.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Link: https://lore.kernel.org/r/20200804162048.22587-8-eli@mellanox.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/ifcvf/ifcvf_base.c  |  4 ++--
 drivers/vdpa/ifcvf/ifcvf_base.h  |  4 ++--
 drivers/vdpa/ifcvf/ifcvf_main.c  |  9 +++++----
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++----
 drivers/vhost/vdpa.c             |  7 +++++--
 include/linux/vdpa.h             | 18 ++++++++++++++----
 6 files changed, 34 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index 94bf0328b68d..f2a128e56de5 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -272,7 +272,7 @@ static int ifcvf_config_features(struct ifcvf_hw *hw)
 	return 0;
 }
 
-u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 {
 	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
 	void __iomem *avail_idx_addr;
@@ -287,7 +287,7 @@ u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 	return last_avail_idx;
 }
 
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num)
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num)
 {
 	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
 	void __iomem *avail_idx_addr;
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index 24af422b5a3e..08f267a2aafe 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -116,7 +116,7 @@ void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
 void io_write64_twopart(u64 val, u32 *lo, u32 *hi);
 void ifcvf_reset(struct ifcvf_hw *hw);
 u64 ifcvf_get_features(struct ifcvf_hw *hw);
-u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num);
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num);
 struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
 #endif /* _IFCVF_H_ */
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 7c93225367db..dc311e972b9e 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -237,19 +237,20 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
 	return IFCVF_QUEUE_MAX;
 }
 
-static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid)
+static void ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				    struct vdpa_vq_state *state)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return ifcvf_get_vq_state(vf, qid);
+	state->avail_index = ifcvf_get_vq_state(vf, qid);
 }
 
 static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
-				   u64 num)
+				   const struct vdpa_vq_state *state)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return ifcvf_set_vq_state(vf, qid, num);
+	return ifcvf_set_vq_state(vf, qid, state->avail_index);
 }
 
 static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 58baff89cc29..c93126ad09d1 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -450,26 +450,28 @@ static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
 	return vq->ready;
 }
 
-static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, u64 state)
+static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx,
+				const struct vdpa_vq_state *state)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 	struct vringh *vrh = &vq->vring;
 
 	spin_lock(&vdpasim->lock);
-	vrh->last_avail_idx = state;
+	vrh->last_avail_idx = state->avail_index;
 	spin_unlock(&vdpasim->lock);
 
 	return 0;
 }
 
-static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx)
+static void vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx,
+				 struct vdpa_vq_state *state)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 	struct vringh *vrh = &vq->vring;
 
-	return vrh->last_avail_idx;
+	state->avail_index = vrh->last_avail_idx;
 }
 
 static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 2d8c950ad3a8..066b165c17b1 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -349,6 +349,7 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vdpa_vq_state vq_state;
 	struct vdpa_callback cb;
 	struct vhost_virtqueue *vq;
 	struct vhost_vring_state s;
@@ -374,7 +375,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		ops->set_vq_ready(vdpa, idx, s.num);
 		return 0;
 	case VHOST_GET_VRING_BASE:
-		vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx);
+		ops->get_vq_state(v->vdpa, idx, &vq_state);
+		vq->last_avail_idx = vq_state.avail_index;
 		break;
 	case VHOST_GET_BACKEND_FEATURES:
 		features = VHOST_VDPA_BACKEND_FEATURES;
@@ -404,7 +406,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		break;
 
 	case VHOST_SET_VRING_BASE:
-		if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx))
+		vq_state.avail_index = vq->last_avail_idx;
+		if (ops->set_vq_state(vdpa, idx, &vq_state))
 			r = -EINVAL;
 		break;
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index b5901cde73e0..d7399c983734 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -27,6 +27,14 @@ struct vdpa_notification_area {
 	resource_size_t size;
 };
 
+/**
+ * vDPA vq_state definition
+ * @avail_index: available index
+ */
+struct vdpa_vq_state {
+	u16	avail_index;
+};
+
 /**
  * vDPA device - representation of a vDPA device
  * @dev: underlying device
@@ -80,12 +88,12 @@ struct vdpa_device {
  * @set_vq_state:		Set the state for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
- *				@state: virtqueue state (last_avail_idx)
+ *				@state: pointer to set virtqueue state (last_avail_idx)
  *				Returns integer: success (0) or error (< 0)
  * @get_vq_state:		Get the state for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
- *				Returns virtqueue state (last_avail_idx)
+ *				@state: pointer to returned state (last_avail_idx)
  * @get_vq_notification: 	Get the notification area for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
@@ -183,8 +191,10 @@ struct vdpa_config_ops {
 			  struct vdpa_callback *cb);
 	void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready);
 	bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
-	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state);
-	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
+	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx,
+			    const struct vdpa_vq_state *state);
+	void (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
+			     struct vdpa_vq_state *state);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
 	/* vq irq is not expected to be changed once DRIVER_OK is set */
-- 
cgit v1.2.3


From 23750e39d57433d0e3d89658f0bc448f9c42ff49 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Tue, 4 Aug 2020 19:20:44 +0300
Subject: vdpa: Modify get_vq_state() to return error code

Modify get_vq_state() so it returns an error code. In case of hardware
acceleration, the available index may be retrieved from the device, an
operation that can possibly fail.

Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Link: https://lore.kernel.org/r/20200804162048.22587-9-eli@mellanox.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/ifcvf/ifcvf_main.c  | 5 +++--
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 5 +++--
 drivers/vhost/vdpa.c             | 5 ++++-
 include/linux/vdpa.h             | 4 ++--
 4 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index dc311e972b9e..076d7ac5e723 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -237,12 +237,13 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
 	return IFCVF_QUEUE_MAX;
 }
 
-static void ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
-				    struct vdpa_vq_state *state)
+static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				   struct vdpa_vq_state *state)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
 	state->avail_index = ifcvf_get_vq_state(vf, qid);
+	return 0;
 }
 
 static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index c93126ad09d1..df3224b138ee 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -464,14 +464,15 @@ static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx,
 	return 0;
 }
 
-static void vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx,
-				 struct vdpa_vq_state *state)
+static int vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx,
+				struct vdpa_vq_state *state)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 	struct vringh *vrh = &vq->vring;
 
 	state->avail_index = vrh->last_avail_idx;
+	return 0;
 }
 
 static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 066b165c17b1..3fab94f88894 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -375,7 +375,10 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		ops->set_vq_ready(vdpa, idx, s.num);
 		return 0;
 	case VHOST_GET_VRING_BASE:
-		ops->get_vq_state(v->vdpa, idx, &vq_state);
+		r = ops->get_vq_state(v->vdpa, idx, &vq_state);
+		if (r)
+			return r;
+
 		vq->last_avail_idx = vq_state.avail_index;
 		break;
 	case VHOST_GET_BACKEND_FEATURES:
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index d7399c983734..eae0bfd87d91 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -193,8 +193,8 @@ struct vdpa_config_ops {
 	bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
 	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx,
 			    const struct vdpa_vq_state *state);
-	void (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
-			     struct vdpa_vq_state *state);
+	int (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
+			    struct vdpa_vq_state *state);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
 	/* vq irq is not expected to be changed once DRIVER_OK is set */
-- 
cgit v1.2.3


From c84f91e2622235bb742f9f20b8675cf095157026 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 5 Aug 2020 19:55:50 -0400
Subject: virtio_config: fix up warnings on parisc

Apparently, on parisc le16_to_cpu returns an int. virtio_cread_le
is very strict about type sizes so it causes a warning.
Fix it up by casting to the correct type.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20200805235550.1451637-1-mst@redhat.com
---
 include/linux/virtio_config.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index ecb166c824bb..8fe857e27ef3 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -357,10 +357,10 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
  */
 #define virtio_le_to_cpu(x) \
 	_Generic((x), \
-		__u8: (x), \
-		 __le16: le16_to_cpu(x), \
-		 __le32: le32_to_cpu(x), \
-		 __le64: le64_to_cpu(x) \
+		__u8: (u8)(x), \
+		 __le16: (u16)le16_to_cpu(x), \
+		 __le32: (u32)le32_to_cpu(x), \
+		 __le64: (u64)le64_to_cpu(x) \
 		)
 
 #define virtio_cpu_to_le(x, m) \
@@ -400,7 +400,6 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 		*(ptr) = virtio_le_to_cpu(virtio_cread_v);		\
 	} while(0)
 
-/* Config space accessors. */
 #define virtio_cwrite_le(vdev, structname, member, ptr)			\
 	do {								\
 		typeof(((structname*)0)->member) virtio_cwrite_v =	\
-- 
cgit v1.2.3


From 0cd39f4600ed4de859383018eb10f0f724900e1b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 6 Aug 2020 14:35:11 +0200
Subject: locking/seqlock, headers: Untangle the spaghetti monster

By using lockdep_assert_*() from seqlock.h, the spaghetti monster
attacked.

Attack back by reducing seqlock.h dependencies from two key high level headers:

 - <linux/seqlock.h>:               -Remove <linux/ww_mutex.h>
 - <linux/time.h>:                  -Remove <linux/seqlock.h>
 - <linux/sched.h>:                 +Add    <linux/seqlock.h>

The price was to add it to sched.h ...

Core header fallout, we add direct header dependencies instead of gaining them
parasitically from higher level headers:

 - <linux/dynamic_queue_limits.h>:  +Add <asm/bug.h>
 - <linux/hrtimer.h>:               +Add <linux/seqlock.h>
 - <linux/ktime.h>:                 +Add <asm/bug.h>
 - <linux/lockdep.h>:               +Add <linux/smp.h>
 - <linux/sched.h>:                 +Add <linux/seqlock.h>
 - <linux/videodev2.h>:             +Add <linux/kernel.h>

Arch headers fallout:

 - PARISC: <asm/timex.h>:           +Add <asm/special_insns.h>
 - SH:     <asm/io.h>:              +Add <asm/page.h>
 - SPARC:  <asm/timer_64.h>:        +Add <uapi/asm/asi.h>
 - SPARC:  <asm/vvar.h>:            +Add <asm/processor.h>, <asm/barrier.h>
                                    -Remove <linux/seqlock.h>
 - X86:    <asm/fixmap.h>:          +Add <asm/pgtable_types.h>
                                    -Remove <asm/acpi.h>

There's also a bunch of parasitic header dependency fallout in .c files, not listed
separately.

[ mingo: Extended the changelog, split up & fixed the original patch. ]

Co-developed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200804133438.GK2674@hirez.programming.kicks-ass.net
---
 arch/sh/include/asm/io.h             |  1 +
 arch/sh/kernel/machvec.c             |  1 +
 arch/sparc/include/asm/timer_64.h    |  1 +
 arch/sparc/include/asm/vvar.h        |  3 ++-
 arch/sparc/kernel/vdso.c             |  1 -
 arch/x86/include/asm/fixmap.h        |  2 +-
 arch/x86/kernel/apic/apic_noop.c     |  1 +
 arch/x86/kernel/apic/hw_nmi.c        |  1 +
 arch/x86/kernel/apic/probe_64.c      |  1 +
 arch/x86/kernel/cpu/amd.c            |  1 +
 arch/x86/kernel/cpu/common.c         |  1 +
 arch/x86/kernel/cpu/hygon.c          |  1 +
 arch/x86/kernel/cpu/intel.c          |  1 +
 arch/x86/kernel/jailhouse.c          |  1 +
 arch/x86/kernel/tsc_msr.c            |  1 +
 arch/x86/mm/init_32.c                |  1 +
 arch/x86/xen/apic.c                  |  1 +
 arch/x86/xen/smp_hvm.c               |  1 +
 arch/x86/xen/suspend_pv.c            |  4 ++--
 include/linux/dynamic_queue_limits.h |  2 ++
 include/linux/hrtimer.h              |  1 +
 include/linux/ktime.h                |  1 +
 include/linux/lockdep.h              |  1 +
 include/linux/mutex.h                | 11 +++++++++++
 include/linux/sched.h                |  1 +
 include/linux/seqlock.h              |  1 -
 include/linux/time.h                 |  1 -
 include/linux/videodev2.h            |  1 +
 include/linux/ww_mutex.h             |  8 --------
 29 files changed, 38 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 26f0f9b4658b..ec587b583822 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -17,6 +17,7 @@
 #include <asm/cache.h>
 #include <asm/addrspace.h>
 #include <asm/machvec.h>
+#include <asm/page.h>
 #include <linux/pgtable.h>
 #include <asm-generic/iomap.h>
 
diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c
index beadbbdb4486..76bd8955d4fe 100644
--- a/arch/sh/kernel/machvec.c
+++ b/arch/sh/kernel/machvec.c
@@ -15,6 +15,7 @@
 #include <asm/setup.h>
 #include <asm/io.h>
 #include <asm/irq.h>
+#include <asm/processor.h>
 
 #define MV_NAME_SIZE 32
 
diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h
index c7e4fb601a57..dcfad4613e18 100644
--- a/arch/sparc/include/asm/timer_64.h
+++ b/arch/sparc/include/asm/timer_64.h
@@ -7,6 +7,7 @@
 #ifndef _SPARC64_TIMER_H
 #define _SPARC64_TIMER_H
 
+#include <uapi/asm/asi.h>
 #include <linux/types.h>
 #include <linux/init.h>
 
diff --git a/arch/sparc/include/asm/vvar.h b/arch/sparc/include/asm/vvar.h
index 0289503d1cb0..6eaf5cfcaae1 100644
--- a/arch/sparc/include/asm/vvar.h
+++ b/arch/sparc/include/asm/vvar.h
@@ -6,7 +6,8 @@
 #define _ASM_SPARC_VVAR_DATA_H
 
 #include <asm/clocksource.h>
-#include <linux/seqlock.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
 #include <linux/time.h>
 #include <linux/types.h>
 
diff --git a/arch/sparc/kernel/vdso.c b/arch/sparc/kernel/vdso.c
index 58880662b271..0e27437eb97b 100644
--- a/arch/sparc/kernel/vdso.c
+++ b/arch/sparc/kernel/vdso.c
@@ -7,7 +7,6 @@
  *  a different vsyscall implementation for Linux/IA32 and for the name.
  */
 
-#include <linux/seqlock.h>
 #include <linux/time.h>
 #include <linux/timekeeper_internal.h>
 
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b9527a54db99..0f0dd645b594 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -26,9 +26,9 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
-#include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
+#include <asm/pgtable_types.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 98c9bb75d185..780c702969b7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -10,6 +10,7 @@
  * like self-ipi, etc...
  */
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 
 #include <asm/apic.h>
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d1fc62a67320..34a992e275ef 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *  Bits copied from original nmi.c file
  *
  */
+#include <linux/thread_info.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 29f0e0984557..bd3835d6b535 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -8,6 +8,7 @@
  * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
  * James Cleverdon.
  */
+#include <linux/thread_info.h>
 #include <asm/apic.h>
 
 #include "local.h"
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d4806eac9325..dcc3d943c68f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -15,6 +15,7 @@
 #include <asm/cpu.h>
 #include <asm/spec-ctrl.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 95c090a45b4b..52b565016eb1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -45,6 +45,7 @@
 #include <asm/mtrr.h>
 #include <asm/hwcap2.h>
 #include <linux/numa.h>
+#include <asm/numa.h>
 #include <asm/asm.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 4e28c1fc8749..ac6c30e5801d 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -10,6 +10,7 @@
 
 #include <asm/cpu.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 #include <asm/cacheinfo.h>
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 0ab48f1cdf84..6eb42d7a3dfd 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -23,6 +23,7 @@
 #include <asm/cmdline.h>
 #include <asm/traps.h>
 #include <asm/resctrl.h>
+#include <asm/numa.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 2caf5b990bf6..4eb8f2d19a87 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -14,6 +14,7 @@
 #include <linux/serial_8250.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/acpi.h>
 #include <asm/cpu.h>
 #include <asm/hypervisor.h>
 #include <asm/i8259.h>
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 4fec6f3a1858..46c72f2ec32f 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/thread_info.h>
 
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8b4afad84f4a..d46a5cf6ccb0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -52,6 +52,7 @@
 #include <asm/cpu_entry_area.h>
 #include <asm/init.h>
 #include <asm/pgtable_areas.h>
+#include <asm/numa.h>
 
 #include "mm_internal.h"
 
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 2df7d089ad54..1aff4ae65655 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
+#include <linux/thread_info.h>
 
 #include <asm/x86_init.h>
 #include <asm/apic.h>
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f8d39440b292..f5e7db4f82ab 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/thread_info.h>
 #include <asm/smp.h>
 
 #include <xen/events.h>
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index 8303b58c79a9..cae9660f4c67 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 
-#include <asm/fixmap.h>
-
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 
+#include <asm/fixmap.h>
+
 #include "xen-ops.h"
 
 void xen_pv_pre_suspend(void)
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 99fc06f0afc1..407c2f281b64 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -38,6 +38,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm/bug.h>
+
 struct dql {
 	/* Fields accessed in enqueue path (dql_queued) */
 	unsigned int	num_queued;		/* Total ever queued */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 25993b86ac5c..107cedd7019a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/seqlock.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
 
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 42d2e6ac35f2..a12b5523cc18 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -23,6 +23,7 @@
 
 #include <linux/time.h>
 #include <linux/jiffies.h>
+#include <asm/bug.h>
 
 /* Nanosecond scalar representation for kernel time values */
 typedef s64	ktime_t;
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 39a35699d0d6..62a382d1845b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -11,6 +11,7 @@
 #define __LINUX_LOCKDEP_H
 
 #include <linux/lockdep_types.h>
+#include <linux/smp.h>
 #include <asm/percpu.h>
 
 struct task_struct;
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index ae197cc00cc8..dcd185cbfe79 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -65,6 +65,17 @@ struct mutex {
 #endif
 };
 
+struct ww_class;
+struct ww_acquire_ctx;
+
+struct ww_mutex {
+	struct mutex base;
+	struct ww_acquire_ctx *ctx;
+#ifdef CONFIG_DEBUG_MUTEXES
+	struct ww_class *ww_class;
+#endif
+};
+
 /*
  * This is the control structure for tasks blocked on mutex,
  * which resides on the blocked task's kernel stack:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9a9d8263962d..7c7a9499d7bc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,6 +31,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
 #include <linux/rseq.h>
+#include <linux/seqlock.h>
 #include <linux/kcsan.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index a076f783aa36..962d9768945f 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -19,7 +19,6 @@
 #include <linux/mutex.h>
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
-#include <linux/ww_mutex.h>
 
 #include <asm/processor.h>
 
diff --git a/include/linux/time.h b/include/linux/time.h
index 4c325bf44ce0..b142cb5f5a53 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -3,7 +3,6 @@
 #define _LINUX_TIME_H
 
 # include <linux/cache.h>
-# include <linux/seqlock.h>
 # include <linux/math64.h>
 # include <linux/time64.h>
 
diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index 16c0ed6c50a7..219037f4c08d 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -57,6 +57,7 @@
 #define __LINUX_VIDEODEV2_H
 
 #include <linux/time.h>     /* need struct timeval */
+#include <linux/kernel.h>
 #include <uapi/linux/videodev2.h>
 
 #endif /* __LINUX_VIDEODEV2_H */
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index d7554252404c..850424e5d030 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -48,14 +48,6 @@ struct ww_acquire_ctx {
 #endif
 };
 
-struct ww_mutex {
-	struct mutex base;
-	struct ww_acquire_ctx *ctx;
-#ifdef CONFIG_DEBUG_MUTEXES
-	struct ww_class *ww_class;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \
 		, .ww_class = class
-- 
cgit v1.2.3


From 1fb497dd003009be95ce67689ac800c446b7acc5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 30 Jul 2020 12:14:06 +0200
Subject: posix-cpu-timers: Provide mechanisms to defer timer handling to
 task_work

Running posix CPU timers in hard interrupt context has a few downsides:

 - For PREEMPT_RT it cannot work as the expiry code needs to take
   sighand lock, which is a 'sleeping spinlock' in RT. The original RT
   approach of offloading the posix CPU timer handling into a high
   priority thread was clumsy and provided no real benefit in general.

 - For fine grained accounting it's just wrong to run this in context of
   the timer interrupt because that way a process specific CPU time is
   accounted to the timer interrupt.

 - Long running timer interrupts caused by a large amount of expiring
   timers which can be created and armed by unpriviledged user space.

There is no hard requirement to expire them in interrupt context.

If the signal is targeted at the task itself then it won't be delivered
before the task returns to user space anyway. If the signal is targeted at
a supervisor process then it might be slightly delayed, but posix CPU
timers are inaccurate anyway due to the fact that they are tied to the
tick.

Provide infrastructure to schedule task work which allows splitting the
posix CPU timer code into a quick check in interrupt context and a thread
context expiry and signal delivery function. This has to be enabled by
architectures as it requires that the architecture specific KVM
implementation handles pending task work before exiting to guest mode.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20200730102337.783470146@linutronix.de
---
 include/linux/posix-timers.h   |  17 ++++
 include/linux/sched.h          |   4 +
 kernel/time/Kconfig            |   9 ++
 kernel/time/posix-cpu-timers.c | 185 ++++++++++++++++++++++++++++++++++++++---
 kernel/time/timer.c            |   1 +
 5 files changed, 204 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index e3f0f8585da4..896c16d2c5fb 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -6,6 +6,7 @@
 #include <linux/list.h>
 #include <linux/alarmtimer.h>
 #include <linux/timerqueue.h>
+#include <linux/task_work.h>
 
 struct kernel_siginfo;
 struct task_struct;
@@ -125,6 +126,16 @@ struct posix_cputimers {
 	unsigned int			expiry_active;
 };
 
+/**
+ * posix_cputimers_work - Container for task work based posix CPU timer expiry
+ * @work:	The task work to be scheduled
+ * @scheduled:  @work has been scheduled already, no further processing
+ */
+struct posix_cputimers_work {
+	struct callback_head	work;
+	unsigned int		scheduled;
+};
+
 static inline void posix_cputimers_init(struct posix_cputimers *pct)
 {
 	memset(pct, 0, sizeof(*pct));
@@ -165,6 +176,12 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct,
 					      u64 cpu_limit) { }
 #endif
 
+#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
+void posix_cputimers_init_work(void);
+#else
+static inline void posix_cputimers_init_work(void) { }
+#endif
+
 #define REQUEUE_PENDING 1
 
 /**
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 06ec60462af0..e9942ce07ef1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -889,6 +889,10 @@ struct task_struct {
 	/* Empty if CONFIG_POSIX_CPUTIMERS=n */
 	struct posix_cputimers		posix_cputimers;
 
+#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
+	struct posix_cputimers_work	posix_cputimers_work;
+#endif
+
 	/* Process credentials: */
 
 	/* Tracer's credentials at attach: */
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index fcc42353f125..a09b1d61df6a 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -52,6 +52,15 @@ config GENERIC_CLOCKEVENTS_MIN_ADJUST
 config GENERIC_CMOS_UPDATE
 	bool
 
+# Select to handle posix CPU timers from task_work
+# and not from the timer interrupt context
+config HAVE_POSIX_CPU_TIMERS_TASK_WORK
+	bool
+
+config POSIX_CPU_TIMERS_TASK_WORK
+	bool
+	default y if POSIX_TIMERS && HAVE_POSIX_CPU_TIMERS_TASK_WORK
+
 if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e5ad87320468..a71758e34e45 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -377,6 +377,7 @@ static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp)
  */
 static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
+	static struct lock_class_key posix_cpu_timers_key;
 	struct pid *pid;
 
 	rcu_read_lock();
@@ -386,6 +387,17 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 		return -EINVAL;
 	}
 
+	/*
+	 * If posix timer expiry is handled in task work context then
+	 * timer::it_lock can be taken without disabling interrupts as all
+	 * other locking happens in task context. This requires a seperate
+	 * lock class key otherwise regular posix timer expiry would record
+	 * the lock class being taken in interrupt context and generate a
+	 * false positive warning.
+	 */
+	if (IS_ENABLED(CONFIG_POSIX_CPU_TIMERS_TASK_WORK))
+		lockdep_set_class(&new_timer->it_lock, &posix_cpu_timers_key);
+
 	new_timer->kclock = &clock_posix_cpu;
 	timerqueue_init(&new_timer->it.cpu.node);
 	new_timer->it.cpu.pid = get_pid(pid);
@@ -1080,26 +1092,163 @@ static inline bool fastpath_timer_check(struct task_struct *tsk)
 	return false;
 }
 
-static void __run_posix_cpu_timers(struct task_struct *tsk)
+static void handle_posix_cpu_timers(struct task_struct *tsk);
+
+#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
+static void posix_cpu_timers_work(struct callback_head *work)
+{
+	handle_posix_cpu_timers(current);
+}
+
+/*
+ * Initialize posix CPU timers task work in init task. Out of line to
+ * keep the callback static and to avoid header recursion hell.
+ */
+void __init posix_cputimers_init_work(void)
+{
+	init_task_work(&current->posix_cputimers_work.work,
+		       posix_cpu_timers_work);
+}
+
+/*
+ * Note: All operations on tsk->posix_cputimer_work.scheduled happen either
+ * in hard interrupt context or in task context with interrupts
+ * disabled. Aside of that the writer/reader interaction is always in the
+ * context of the current task, which means they are strict per CPU.
+ */
+static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk)
+{
+	return tsk->posix_cputimers_work.scheduled;
+}
+
+static inline void __run_posix_cpu_timers(struct task_struct *tsk)
+{
+	if (WARN_ON_ONCE(tsk->posix_cputimers_work.scheduled))
+		return;
+
+	/* Schedule task work to actually expire the timers */
+	tsk->posix_cputimers_work.scheduled = true;
+	task_work_add(tsk, &tsk->posix_cputimers_work.work, TWA_RESUME);
+}
+
+static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk,
+						unsigned long start)
+{
+	bool ret = true;
+
+	/*
+	 * On !RT kernels interrupts are disabled while collecting expired
+	 * timers, so no tick can happen and the fast path check can be
+	 * reenabled without further checks.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		tsk->posix_cputimers_work.scheduled = false;
+		return true;
+	}
+
+	/*
+	 * On RT enabled kernels ticks can happen while the expired timers
+	 * are collected under sighand lock. But any tick which observes
+	 * the CPUTIMERS_WORK_SCHEDULED bit set, does not run the fastpath
+	 * checks. So reenabling the tick work has do be done carefully:
+	 *
+	 * Disable interrupts and run the fast path check if jiffies have
+	 * advanced since the collecting of expired timers started. If
+	 * jiffies have not advanced or the fast path check did not find
+	 * newly expired timers, reenable the fast path check in the timer
+	 * interrupt. If there are newly expired timers, return false and
+	 * let the collection loop repeat.
+	 */
+	local_irq_disable();
+	if (start != jiffies && fastpath_timer_check(tsk))
+		ret = false;
+	else
+		tsk->posix_cputimers_work.scheduled = false;
+	local_irq_enable();
+
+	return ret;
+}
+#else /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */
+static inline void __run_posix_cpu_timers(struct task_struct *tsk)
+{
+	lockdep_posixtimer_enter();
+	handle_posix_cpu_timers(tsk);
+	lockdep_posixtimer_exit();
+}
+
+static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk)
+{
+	return false;
+}
+
+static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk,
+						unsigned long start)
+{
+	return true;
+}
+#endif /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */
+
+static void handle_posix_cpu_timers(struct task_struct *tsk)
 {
 	struct k_itimer *timer, *next;
-	unsigned long flags;
+	unsigned long flags, start;
 	LIST_HEAD(firing);
 
 	if (!lock_task_sighand(tsk, &flags))
 		return;
 
-	/*
-	 * Here we take off tsk->signal->cpu_timers[N] and
-	 * tsk->cpu_timers[N] all the timers that are firing, and
-	 * put them on the firing list.
-	 */
-	check_thread_timers(tsk, &firing);
+	do {
+		/*
+		 * On RT locking sighand lock does not disable interrupts,
+		 * so this needs to be careful vs. ticks. Store the current
+		 * jiffies value.
+		 */
+		start = READ_ONCE(jiffies);
+		barrier();
 
-	check_process_timers(tsk, &firing);
+		/*
+		 * Here we take off tsk->signal->cpu_timers[N] and
+		 * tsk->cpu_timers[N] all the timers that are firing, and
+		 * put them on the firing list.
+		 */
+		check_thread_timers(tsk, &firing);
+
+		check_process_timers(tsk, &firing);
+
+		/*
+		 * The above timer checks have updated the exipry cache and
+		 * because nothing can have queued or modified timers after
+		 * sighand lock was taken above it is guaranteed to be
+		 * consistent. So the next timer interrupt fastpath check
+		 * will find valid data.
+		 *
+		 * If timer expiry runs in the timer interrupt context then
+		 * the loop is not relevant as timers will be directly
+		 * expired in interrupt context. The stub function below
+		 * returns always true which allows the compiler to
+		 * optimize the loop out.
+		 *
+		 * If timer expiry is deferred to task work context then
+		 * the following rules apply:
+		 *
+		 * - On !RT kernels no tick can have happened on this CPU
+		 *   after sighand lock was acquired because interrupts are
+		 *   disabled. So reenabling task work before dropping
+		 *   sighand lock and reenabling interrupts is race free.
+		 *
+		 * - On RT kernels ticks might have happened but the tick
+		 *   work ignored posix CPU timer handling because the
+		 *   CPUTIMERS_WORK_SCHEDULED bit is set. Reenabling work
+		 *   must be done very carefully including a check whether
+		 *   ticks have happened since the start of the timer
+		 *   expiry checks. posix_cpu_timers_enable_work() takes
+		 *   care of that and eventually lets the expiry checks
+		 *   run again.
+		 */
+	} while (!posix_cpu_timers_enable_work(tsk, start));
 
 	/*
-	 * We must release these locks before taking any timer's lock.
+	 * We must release sighand lock before taking any timer's lock.
 	 * There is a potential race with timer deletion here, as the
 	 * siglock now protects our private firing list.  We have set
 	 * the firing flag in each timer, so that a deletion attempt
@@ -1117,6 +1266,13 @@ static void __run_posix_cpu_timers(struct task_struct *tsk)
 	list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) {
 		int cpu_firing;
 
+		/*
+		 * spin_lock() is sufficient here even independent of the
+		 * expiry context. If expiry happens in hard interrupt
+		 * context it's obvious. For task work context it's safe
+		 * because all other operations on timer::it_lock happen in
+		 * task context (syscall or exit).
+		 */
 		spin_lock(&timer->it_lock);
 		list_del_init(&timer->it.cpu.elist);
 		cpu_firing = timer->it.cpu.firing;
@@ -1143,6 +1299,13 @@ void run_posix_cpu_timers(void)
 
 	lockdep_assert_irqs_disabled();
 
+	/*
+	 * If the actual expiry is deferred to task work context and the
+	 * work is already scheduled there is no point to do anything here.
+	 */
+	if (posix_cpu_timers_work_scheduled(tsk))
+		return;
+
 	/*
 	 * The fast path checks that there are no expired thread or thread
 	 * group timers.  If that's so, just return.
@@ -1150,9 +1313,7 @@ void run_posix_cpu_timers(void)
 	if (!fastpath_timer_check(tsk))
 		return;
 
-	lockdep_posixtimer_enter();
 	__run_posix_cpu_timers(tsk);
-	lockdep_posixtimer_exit();
 }
 
 /*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ae5029f984a8..a16764b0116e 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2017,6 +2017,7 @@ static void __init init_timer_cpus(void)
 void __init init_timers(void)
 {
 	init_timer_cpus();
+	posix_cputimers_init_work();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 
-- 
cgit v1.2.3


From 09fc67b500c7f0bb1b5ed774197ac7f2c5285655 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Fri, 17 Jul 2020 17:42:55 +0900
Subject: kprobes: Remove show_registers() function prototype

Remove show_registers() function prototype because this function
has been renamed by commit:

  57da8b960b9a ("x86: Avoid double stack traces with show_regs()")

and this commit has removed the caller in kprobes altogether:

  80006dbee674 ("kprobes/x86: Remove jprobe implementation")

So this doesn't exist anymore - remove the orphan prototype.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kprobes.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 45b8cdc9fad7..9be1bff4f586 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
-extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
-- 
cgit v1.2.3


From b55b3fdce3e554a6bbe8f8ca6a01a892d720e64e Mon Sep 17 00:00:00 2001
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Fri, 17 Jul 2020 13:01:00 +0530
Subject: hw_breakpoint: Remove unused __register_perf_hw_breakpoint()
 declaration

Commit:

  b326e9560a28 ("hw-breakpoints: Use overflow handler instead of the event callback")

removed __register_perf_hw_breakpoint() function usage and replaced it
with register_perf_hw_breakpoint() function.

Remove the left-over unused __register_perf_hw_breakpoint() declaration
from <linux/hw_breakpoint.h> as well.

Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/1594971060-14180-1-git-send-email-bhsharma@redhat.com
---
 include/linux/hw_breakpoint.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index d7d4250cd1e4..78dd7035d1e5 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -72,7 +72,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
-extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
 extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
 
@@ -119,8 +118,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context)		{ return NULL; }
 static inline int
 register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
-static inline int
-__register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
 static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
 static inline void
 unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
-- 
cgit v1.2.3


From bb22d80b47d5dd641d09d31946c4be0f610f3f45 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:36:40 -0700
Subject: LSM: drop duplicated words in header file comments

Drop the doubled words "the" and "and" in comments.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Serge Hallyn <serge@hallyn.com>
Cc: linux-security-module@vger.kernel.org
Signed-off-by: James Morris <jmorris@namei.org>
---
 include/linux/lsm_hook_defs.h | 2 +-
 include/linux/lsm_hooks.h     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 5616b2567aa7..dec0e5186834 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -15,7 +15,7 @@
  */
 
 /*
- * The macro LSM_HOOK is used to define the data structures required by the
+ * The macro LSM_HOOK is used to define the data structures required by
  * the LSM framework using the pattern:
  *
  *	LSM_HOOK(<return_type>, <default_value>, <hook_name>, args...)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 988ca0df7824..afd2c5becec5 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -798,7 +798,7 @@
  *	structure. Note that the security field was not added directly to the
  *	socket structure, but rather, the socket security information is stored
  *	in the associated inode.  Typically, the inode alloc_security hook will
- *	allocate and and attach security information to
+ *	allocate and attach security information to
  *	SOCK_INODE(sock)->i_security.  This hook may be used to update the
  *	SOCK_INODE(sock)->i_security field with additional information that
  *	wasn't available when the inode was allocated.
-- 
cgit v1.2.3


From 5e7b30205cef80f6bb922e61834437ca7bff5837 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 4 Aug 2020 22:50:56 -0700
Subject: bpf: Change uapi for bpf iterator map elements

Commit a5cbe05a6673 ("bpf: Implement bpf iterator for
map elements") added bpf iterator support for
map elements. The map element bpf iterator requires
info to identify a particular map. In the above
commit, the attr->link_create.target_fd is used
to carry map_fd and an enum bpf_iter_link_info
is added to uapi to specify the target_fd actually
representing a map_fd:
    enum bpf_iter_link_info {
	BPF_ITER_LINK_UNSPEC = 0,
	BPF_ITER_LINK_MAP_FD = 1,

	MAX_BPF_ITER_LINK_INFO,
    };

This is an extensible approach as we can grow
enumerator for pid, cgroup_id, etc. and we can
unionize target_fd for pid, cgroup_id, etc.
But in the future, there are chances that
more complex customization may happen, e.g.,
for tasks, it could be filtered based on
both cgroup_id and user_id.

This patch changed the uapi to have fields
	__aligned_u64	iter_info;
	__u32		iter_info_len;
for additional iter_info for link_create.
The iter_info is defined as
	union bpf_iter_link_info {
		struct {
			__u32   map_fd;
		} map;
	};

So future extension for additional customization
will be easier. The bpf_iter_link_info will be
passed to target callback to validate and generic
bpf_iter framework does not need to deal it any
more.

Note that map_fd = 0 will be considered invalid
and -EBADF will be returned to user space.

Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com
---
 include/linux/bpf.h       | 10 ++++----
 include/uapi/linux/bpf.h  | 15 ++++++------
 kernel/bpf/bpf_iter.c     | 58 +++++++++++++++++++++++------------------------
 kernel/bpf/map_iter.c     | 37 +++++++++++++++++++++++-------
 kernel/bpf/syscall.c      |  2 +-
 net/core/bpf_sk_storage.c | 37 +++++++++++++++++++++++-------
 6 files changed, 102 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cef4ef0d2b4e..55f694b63164 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1214,15 +1214,17 @@ struct bpf_iter_aux_info {
 	struct bpf_map *map;
 };
 
-typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog,
-				       struct bpf_iter_aux_info *aux);
+typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
+					union bpf_iter_link_info *linfo,
+					struct bpf_iter_aux_info *aux);
+typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
 
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
-	bpf_iter_check_target_t check_target;
+	bpf_iter_attach_target_t attach_target;
+	bpf_iter_detach_target_t detach_target;
 	u32 ctx_arg_info_size;
-	enum bpf_iter_link_info req_linfo;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
 };
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b134e679e9db..0480f893facd 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -81,6 +81,12 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type */
 };
 
+union bpf_iter_link_info {
+	struct {
+		__u32	map_fd;
+	} map;
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
 	BPF_MAP_CREATE,
@@ -249,13 +255,6 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
-enum bpf_iter_link_info {
-	BPF_ITER_LINK_UNSPEC = 0,
-	BPF_ITER_LINK_MAP_FD = 1,
-
-	MAX_BPF_ITER_LINK_INFO,
-};
-
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -623,6 +622,8 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
+		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+		__u32		iter_info_len;	/* iter_info length */
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 363b9cafc2d8..b6715964b685 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -338,8 +338,8 @@ static void bpf_iter_link_release(struct bpf_link *link)
 	struct bpf_iter_link *iter_link =
 		container_of(link, struct bpf_iter_link, link);
 
-	if (iter_link->aux.map)
-		bpf_map_put_with_uref(iter_link->aux.map);
+	if (iter_link->tinfo->reg_info->detach_target)
+		iter_link->tinfo->reg_info->detach_target(&iter_link->aux);
 }
 
 static void bpf_iter_link_dealloc(struct bpf_link *link)
@@ -390,15 +390,35 @@ bool bpf_link_is_iter(struct bpf_link *link)
 
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
+	union bpf_iter_link_info __user *ulinfo;
 	struct bpf_link_primer link_primer;
 	struct bpf_iter_target_info *tinfo;
-	struct bpf_iter_aux_info aux = {};
+	union bpf_iter_link_info linfo;
 	struct bpf_iter_link *link;
-	u32 prog_btf_id, target_fd;
+	u32 prog_btf_id, linfo_len;
 	bool existed = false;
-	struct bpf_map *map;
 	int err;
 
+	if (attr->link_create.target_fd || attr->link_create.flags)
+		return -EINVAL;
+
+	memset(&linfo, 0, sizeof(union bpf_iter_link_info));
+
+	ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
+	linfo_len = attr->link_create.iter_info_len;
+	if (!ulinfo ^ !linfo_len)
+		return -EINVAL;
+
+	if (ulinfo) {
+		err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
+					       linfo_len);
+		if (err)
+			return err;
+		linfo_len = min_t(u32, linfo_len, sizeof(linfo));
+		if (copy_from_user(&linfo, ulinfo, linfo_len))
+			return -EFAULT;
+	}
+
 	prog_btf_id = prog->aux->attach_btf_id;
 	mutex_lock(&targets_mutex);
 	list_for_each_entry(tinfo, &targets, list) {
@@ -411,13 +431,6 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (!existed)
 		return -ENOENT;
 
-	/* Make sure user supplied flags are target expected. */
-	target_fd = attr->link_create.target_fd;
-	if (attr->link_create.flags != tinfo->reg_info->req_linfo)
-		return -EINVAL;
-	if (!attr->link_create.flags && target_fd)
-		return -EINVAL;
-
 	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
 	if (!link)
 		return -ENOMEM;
@@ -431,28 +444,15 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		return err;
 	}
 
-	if (tinfo->reg_info->req_linfo == BPF_ITER_LINK_MAP_FD) {
-		map = bpf_map_get_with_uref(target_fd);
-		if (IS_ERR(map)) {
-			err = PTR_ERR(map);
-			goto cleanup_link;
-		}
-
-		aux.map = map;
-		err = tinfo->reg_info->check_target(prog, &aux);
+	if (tinfo->reg_info->attach_target) {
+		err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux);
 		if (err) {
-			bpf_map_put_with_uref(map);
-			goto cleanup_link;
+			bpf_link_cleanup(&link_primer);
+			return err;
 		}
-
-		link->aux.map = map;
 	}
 
 	return bpf_link_settle(&link_primer);
-
-cleanup_link:
-	bpf_link_cleanup(&link_primer);
-	return err;
 }
 
 static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index fbe1f557cb88..af86048e5afd 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -98,12 +98,21 @@ static struct bpf_iter_reg bpf_map_reg_info = {
 	.seq_info		= &bpf_map_seq_info,
 };
 
-static int bpf_iter_check_map(struct bpf_prog *prog,
-			      struct bpf_iter_aux_info *aux)
+static int bpf_iter_attach_map(struct bpf_prog *prog,
+			       union bpf_iter_link_info *linfo,
+			       struct bpf_iter_aux_info *aux)
 {
 	u32 key_acc_size, value_acc_size, key_size, value_size;
-	struct bpf_map *map = aux->map;
+	struct bpf_map *map;
 	bool is_percpu = false;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -112,7 +121,7 @@ static int bpf_iter_check_map(struct bpf_prog *prog,
 	else if (map->map_type != BPF_MAP_TYPE_HASH &&
 		 map->map_type != BPF_MAP_TYPE_LRU_HASH &&
 		 map->map_type != BPF_MAP_TYPE_ARRAY)
-		return -EINVAL;
+		goto put_map;
 
 	key_acc_size = prog->aux->max_rdonly_access;
 	value_acc_size = prog->aux->max_rdwr_access;
@@ -122,10 +131,22 @@ static int bpf_iter_check_map(struct bpf_prog *prog,
 	else
 		value_size = round_up(map->value_size, 8) * num_possible_cpus();
 
-	if (key_acc_size > key_size || value_acc_size > value_size)
-		return -EACCES;
+	if (key_acc_size > key_size || value_acc_size > value_size) {
+		err = -EACCES;
+		goto put_map;
+	}
 
+	aux->map = map;
 	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
 }
 
 DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
@@ -133,8 +154,8 @@ DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
 
 static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.target			= "bpf_map_elem",
-	.check_target		= bpf_iter_check_map,
-	.req_linfo		= BPF_ITER_LINK_MAP_FD,
+	.attach_target		= bpf_iter_attach_map,
+	.detach_target		= bpf_iter_detach_map,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2f343ce15747..86299a292214 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3883,7 +3883,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *
 	return -EINVAL;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.flags
+#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
 static int link_create(union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d3377c90a291..b988f48153a4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -1384,18 +1384,39 @@ static int bpf_iter_init_sk_storage_map(void *priv_data,
 	return 0;
 }
 
-static int bpf_iter_check_map(struct bpf_prog *prog,
-			      struct bpf_iter_aux_info *aux)
+static int bpf_iter_attach_map(struct bpf_prog *prog,
+			       union bpf_iter_link_info *linfo,
+			       struct bpf_iter_aux_info *aux)
 {
-	struct bpf_map *map = aux->map;
+	struct bpf_map *map;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
-		return -EINVAL;
+		goto put_map;
 
-	if (prog->aux->max_rdonly_access > map->value_size)
-		return -EACCES;
+	if (prog->aux->max_rdonly_access > map->value_size) {
+		err = -EACCES;
+		goto put_map;
+	}
 
+	aux->map = map;
 	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
 }
 
 static const struct seq_operations bpf_sk_storage_map_seq_ops = {
@@ -1414,8 +1435,8 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 
 static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
 	.target			= "bpf_sk_storage_map",
-	.check_target		= bpf_iter_check_map,
-	.req_linfo		= BPF_ITER_LINK_MAP_FD,
+	.attach_target		= bpf_iter_attach_map,
+	.detach_target		= bpf_iter_detach_map,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
-- 
cgit v1.2.3


From d58669b093997e4e5f98c38a54f99761657c19d2 Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Fri, 31 Jul 2020 19:06:01 +0530
Subject: ACPI: APD: Change name from ST to FCH

AMD SoC general pupose clk is present in new platforms with
same MMIO mappings. We can reuse the same clk handler support
for other platforms. Hence, changing name from ST(SoC) to FCH(IP)

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_apd.c               | 14 +++++++-------
 drivers/clk/x86/clk-st.c              |  4 ++--
 include/linux/platform_data/clk-fch.h | 17 +++++++++++++++++
 include/linux/platform_data/clk-st.h  | 17 -----------------
 4 files changed, 26 insertions(+), 26 deletions(-)
 create mode 100644 include/linux/platform_data/clk-fch.h
 delete mode 100644 include/linux/platform_data/clk-st.h

(limited to 'include/linux')

diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index f24f6d3f1fa5..36319deb24d9 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/platform_data/clk-st.h>
+#include <linux/platform_data/clk-fch.h>
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
 #include <linux/clkdev.h>
@@ -79,11 +79,11 @@ static int misc_check_res(struct acpi_resource *ares, void *data)
 	return !acpi_dev_resource_memory(ares, &res);
 }
 
-static int st_misc_setup(struct apd_private_data *pdata)
+static int fch_misc_setup(struct apd_private_data *pdata)
 {
 	struct acpi_device *adev = pdata->adev;
 	struct platform_device *clkdev;
-	struct st_clk_data *clk_data;
+	struct fch_clk_data *clk_data;
 	struct resource_entry *rentry;
 	struct list_head resource_list;
 	int ret;
@@ -106,7 +106,7 @@ static int st_misc_setup(struct apd_private_data *pdata)
 
 	acpi_dev_free_resource_list(&resource_list);
 
-	clkdev = platform_device_register_data(&adev->dev, "clk-st",
+	clkdev = platform_device_register_data(&adev->dev, "clk-fch",
 					       PLATFORM_DEVID_NONE, clk_data,
 					       sizeof(*clk_data));
 	return PTR_ERR_OR_ZERO(clkdev);
@@ -135,8 +135,8 @@ static const struct apd_device_desc cz_uart_desc = {
 	.properties = uart_properties,
 };
 
-static const struct apd_device_desc st_misc_desc = {
-	.setup = st_misc_setup,
+static const struct apd_device_desc fch_misc_desc = {
+	.setup = fch_misc_setup,
 };
 #endif
 
@@ -239,7 +239,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
 	{ "AMD0020", APD_ADDR(cz_uart_desc) },
 	{ "AMDI0020", APD_ADDR(cz_uart_desc) },
 	{ "AMD0030", },
-	{ "AMD0040", APD_ADDR(st_misc_desc)},
+	{ "AMD0040", APD_ADDR(fch_misc_desc)},
 	{ "HYGO0010", APD_ADDR(wt_i2c_desc) },
 #endif
 #ifdef CONFIG_ARM64
diff --git a/drivers/clk/x86/clk-st.c b/drivers/clk/x86/clk-st.c
index 25d4b97aff9b..c2438874d9f2 100644
--- a/drivers/clk/x86/clk-st.c
+++ b/drivers/clk/x86/clk-st.c
@@ -8,7 +8,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
-#include <linux/platform_data/clk-st.h>
+#include <linux/platform_data/clk-fch.h>
 #include <linux/platform_device.h>
 
 /* Clock Driving Strength 2 register */
@@ -31,7 +31,7 @@ static struct clk_hw *hws[ST_MAX_CLKS];
 
 static int st_clk_probe(struct platform_device *pdev)
 {
-	struct st_clk_data *st_data;
+	struct fch_clk_data *st_data;
 
 	st_data = dev_get_platdata(&pdev->dev);
 	if (!st_data || !st_data->base)
diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h
new file mode 100644
index 000000000000..850ca776156d
--- /dev/null
+++ b/include/linux/platform_data/clk-fch.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * clock framework for AMD misc clocks
+ *
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __CLK_FCH_H
+#define __CLK_FCH_H
+
+#include <linux/compiler.h>
+
+struct fch_clk_data {
+	void __iomem *base;
+};
+
+#endif /* __CLK_FCH_H */
diff --git a/include/linux/platform_data/clk-st.h b/include/linux/platform_data/clk-st.h
deleted file mode 100644
index 7cdb6a402b35..000000000000
--- a/include/linux/platform_data/clk-st.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * clock framework for AMD Stoney based clock
- *
- * Copyright 2018 Advanced Micro Devices, Inc.
- */
-
-#ifndef __CLK_ST_H
-#define __CLK_ST_H
-
-#include <linux/compiler.h>
-
-struct st_clk_data {
-	void __iomem *base;
-};
-
-#endif /* __CLK_ST_H */
-- 
cgit v1.2.3


From 7f8802f2d2ed67ffbac9264f946a52507f749e19 Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Fri, 31 Jul 2020 19:06:03 +0530
Subject: ACPI: APD: Add a fmw property is_raven

Since there is slight difference in AMD RV based soc in misc
clk architecture. The fmw property will help in differentiating
the SoCs.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_apd.c               | 4 ++++
 include/linux/platform_data/clk-fch.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index 36319deb24d9..4c348377a39d 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -82,6 +82,7 @@ static int misc_check_res(struct acpi_resource *ares, void *data)
 static int fch_misc_setup(struct apd_private_data *pdata)
 {
 	struct acpi_device *adev = pdata->adev;
+	const union acpi_object *obj;
 	struct platform_device *clkdev;
 	struct fch_clk_data *clk_data;
 	struct resource_entry *rentry;
@@ -98,6 +99,9 @@ static int fch_misc_setup(struct apd_private_data *pdata)
 	if (ret < 0)
 		return -ENOENT;
 
+	acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj);
+	clk_data->is_rv = obj->integer.value;
+
 	list_for_each_entry(rentry, &resource_list, node) {
 		clk_data->base = devm_ioremap(&adev->dev, rentry->res->start,
 					      resource_size(rentry->res));
diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h
index 850ca776156d..b9f682459f08 100644
--- a/include/linux/platform_data/clk-fch.h
+++ b/include/linux/platform_data/clk-fch.h
@@ -12,6 +12,7 @@
 
 struct fch_clk_data {
 	void __iomem *base;
+	u32 is_rv;
 };
 
 #endif /* __CLK_FCH_H */
-- 
cgit v1.2.3


From 529a781ee07aaa58be8164d75ba5998eb7dd216c Mon Sep 17 00:00:00 2001
From: "zhangyi (F)" <yi.zhang@huawei.com>
Date: Sat, 20 Jun 2020 10:54:27 +0800
Subject: jbd2: remove unused parameter in jbd2_journal_try_to_free_buffers()

Parameter gfp_mask in jbd2_journal_try_to_free_buffers() is no longer
used after commit <536fc240e7147> ("jbd2: clean up
jbd2_journal_try_to_free_buffers()"), so just remove it.

Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Link: https://lore.kernel.org/r/20200620025427.1756360-6-yi.zhang@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c       | 2 +-
 fs/ext4/super.c       | 4 ++--
 fs/jbd2/transaction.c | 7 +------
 include/linux/jbd2.h  | 2 +-
 4 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6187c8880c02..551a1056870d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3288,7 +3288,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 	if (PageChecked(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page, wait);
+		return jbd2_journal_try_to_free_buffers(journal, page);
 	else
 		return try_to_free_buffers(page);
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c77b10257b36..8c00f0a09f4d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1288,8 +1288,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 	if (!page_has_buffers(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page,
-						wait & ~__GFP_DIRECT_RECLAIM);
+		return jbd2_journal_try_to_free_buffers(journal, page);
+
 	return try_to_free_buffers(page);
 }
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6250c9faa4cb..43985738aa86 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2081,10 +2081,6 @@ out:
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
- * code to release the buffers.
- *
  *
  * For all the buffers on this page,
  * if they are fully written out ordered data, move them onto BUF_CLEAN
@@ -2115,8 +2111,7 @@ out:
  *
  * Return 0 on failure, 1 on success
  */
-int jbd2_journal_try_to_free_buffers(journal_t *journal,
-				struct page *page, gfp_t gfp_mask)
+int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d56128df2aff..a756a4cdf939 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1380,7 +1380,7 @@ extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned int, unsigned int);
-extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
+extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
 extern int	 jbd2_journal_stop(handle_t *);
 extern int	 jbd2_journal_flush (journal_t *);
 extern void	 jbd2_journal_lock_updates (journal_t *);
-- 
cgit v1.2.3


From c1a06df6ebf6ca98fb7a672fe447c7469d6c1968 Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Thu, 6 Aug 2020 23:17:09 -0700
Subject: mm/migrate: fix migrate_pgmap_owner w/o CONFIG_MMU_NOTIFIER

On x86_64, when CONFIG_MMU_NOTIFIER is not set/enabled, there is a
compiler error:

   mm/migrate.c: In function 'migrate_vma_collect':
   mm/migrate.c:2481:7: error: 'struct mmu_notifier_range' has no member named 'migrate_pgmap_owner'
     range.migrate_pgmap_owner = migrate->pgmap_owner;
          ^

Fixes: 998427b3ad2c ("mm/notifier: add migration invalidation type")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "Jason Gunthorpe" <jgg@mellanox.com>
Link: http://lkml.kernel.org/r/20200806193353.7124-1-rcampbell@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmu_notifier.h | 13 +++++++++++++
 mm/migrate.c                 |  6 +++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index c6f0708195cd..b8200782dede 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -521,6 +521,16 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range,
 	range->flags = flags;
 }
 
+static inline void mmu_notifier_range_init_migrate(
+			struct mmu_notifier_range *range, unsigned int flags,
+			struct vm_area_struct *vma, struct mm_struct *mm,
+			unsigned long start, unsigned long end, void *pgmap)
+{
+	mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm,
+				start, end);
+	range->migrate_pgmap_owner = pgmap;
+}
+
 #define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
 ({									\
 	int __young;							\
@@ -645,6 +655,9 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range,
 
 #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end)  \
 	_mmu_notifier_range_init(range, start, end)
+#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \
+					pgmap) \
+	_mmu_notifier_range_init(range, start, end)
 
 static inline bool
 mmu_notifier_range_blockable(const struct mmu_notifier_range *range)
diff --git a/mm/migrate.c b/mm/migrate.c
index 4fcc465736ff..d179657f8685 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2386,9 +2386,9 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
 	 * that the registered device driver can skip invalidating device
 	 * private page mappings that won't be migrated.
 	 */
-	mmu_notifier_range_init(&range, MMU_NOTIFY_MIGRATE, 0, migrate->vma,
-			migrate->vma->vm_mm, migrate->start, migrate->end);
-	range.migrate_pgmap_owner = migrate->pgmap_owner;
+	mmu_notifier_range_init_migrate(&range, 0, migrate->vma,
+		migrate->vma->vm_mm, migrate->start, migrate->end,
+		migrate->pgmap_owner);
 	mmu_notifier_invalidate_range_start(&range);
 
 	walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
-- 
cgit v1.2.3


From 453431a54934d917153c65211b2dabf45562ca88 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 6 Aug 2020 23:18:13 -0700
Subject: mm, treewide: rename kzfree() to kfree_sensitive()

As said by Linus:

  A symmetric naming is only helpful if it implies symmetries in use.
  Otherwise it's actively misleading.

  In "kzalloc()", the z is meaningful and an important part of what the
  caller wants.

  In "kzfree()", the z is actively detrimental, because maybe in the
  future we really _might_ want to use that "memfill(0xdeadbeef)" or
  something. The "zero" part of the interface isn't even _relevant_.

The main reason that kzfree() exists is to clear sensitive information
that should not be leaked to other future users of the same memory
objects.

Rename kzfree() to kfree_sensitive() to follow the example of the recently
added kvfree_sensitive() and make the intention of the API more explicit.
In addition, memzero_explicit() is used to clear the memory to make sure
that it won't get optimized away by the compiler.

The renaming is done by using the command sequence:

  git grep -w --name-only kzfree |\
  xargs sed -i 's/kzfree/kfree_sensitive/'

followed by some editing of the kfree_sensitive() kerneldoc and adding
a kzfree backward compatibility macro in slab.h.

[akpm@linux-foundation.org: fs/crypto/inline_crypt.c needs linux/slab.h]
[akpm@linux-foundation.org: fix fs/crypto/inline_crypt.c some more]

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Howells <dhowells@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Joe Perches <joe@perches.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: "Jason A . Donenfeld" <Jason@zx2c4.com>
Link: http://lkml.kernel.org/r/20200616154311.12314-3-longman@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/crypto/prng.c                            |  4 +--
 arch/x86/power/hibernate.c                         |  2 +-
 crypto/adiantum.c                                  |  2 +-
 crypto/ahash.c                                     |  4 +--
 crypto/api.c                                       |  2 +-
 crypto/asymmetric_keys/verify_pefile.c             |  4 +--
 crypto/deflate.c                                   |  2 +-
 crypto/drbg.c                                      | 10 +++----
 crypto/ecc.c                                       |  8 ++---
 crypto/ecdh.c                                      |  2 +-
 crypto/gcm.c                                       |  2 +-
 crypto/gf128mul.c                                  |  4 +--
 crypto/jitterentropy-kcapi.c                       |  2 +-
 crypto/rng.c                                       |  2 +-
 crypto/rsa-pkcs1pad.c                              |  6 ++--
 crypto/seqiv.c                                     |  2 +-
 crypto/shash.c                                     |  2 +-
 crypto/skcipher.c                                  |  2 +-
 crypto/testmgr.c                                   |  6 ++--
 crypto/zstd.c                                      |  2 +-
 .../crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c    |  2 +-
 .../crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c    |  2 +-
 drivers/crypto/amlogic/amlogic-gxl-cipher.c        |  4 +--
 drivers/crypto/atmel-ecc.c                         |  2 +-
 drivers/crypto/caam/caampkc.c                      | 28 +++++++++---------
 drivers/crypto/cavium/cpt/cptvf_main.c             |  6 ++--
 drivers/crypto/cavium/cpt/cptvf_reqmanager.c       | 12 ++++----
 drivers/crypto/cavium/nitrox/nitrox_lib.c          |  4 +--
 drivers/crypto/cavium/zip/zip_crypto.c             |  6 ++--
 drivers/crypto/ccp/ccp-crypto-rsa.c                |  6 ++--
 drivers/crypto/ccree/cc_aead.c                     |  4 +--
 drivers/crypto/ccree/cc_buffer_mgr.c               |  4 +--
 drivers/crypto/ccree/cc_cipher.c                   |  6 ++--
 drivers/crypto/ccree/cc_hash.c                     |  8 ++---
 drivers/crypto/ccree/cc_request_mgr.c              |  2 +-
 drivers/crypto/marvell/cesa/hash.c                 |  2 +-
 drivers/crypto/marvell/octeontx/otx_cptvf_main.c   |  6 ++--
 drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.h |  2 +-
 drivers/crypto/nx/nx.c                             |  4 +--
 drivers/crypto/virtio/virtio_crypto_algs.c         | 12 ++++----
 drivers/crypto/virtio/virtio_crypto_core.c         |  2 +-
 drivers/md/dm-crypt.c                              | 32 ++++++++++----------
 drivers/md/dm-integrity.c                          |  6 ++--
 drivers/misc/ibmvmc.c                              |  6 ++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c     |  6 ++--
 drivers/net/ppp/ppp_mppe.c                         |  6 ++--
 drivers/net/wireguard/noise.c                      |  4 +--
 drivers/net/wireguard/peer.c                       |  2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       |  2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  |  6 ++--
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       |  6 ++--
 drivers/net/wireless/intersil/orinoco/wext.c       |  4 +--
 drivers/s390/crypto/ap_bus.h                       |  4 +--
 drivers/staging/ks7010/ks_hostif.c                 |  2 +-
 drivers/staging/rtl8723bs/core/rtw_security.c      |  2 +-
 drivers/staging/wlan-ng/p80211netdev.c             |  2 +-
 drivers/target/iscsi/iscsi_target_auth.c           |  2 +-
 fs/cifs/cifsencrypt.c                              |  2 +-
 fs/cifs/connect.c                                  | 10 +++----
 fs/cifs/dfs_cache.c                                |  2 +-
 fs/cifs/misc.c                                     |  8 ++---
 fs/crypto/inline_crypt.c                           |  5 ++--
 fs/crypto/keyring.c                                |  6 ++--
 fs/crypto/keysetup_v1.c                            |  4 +--
 fs/ecryptfs/keystore.c                             |  4 +--
 fs/ecryptfs/messaging.c                            |  2 +-
 include/crypto/aead.h                              |  2 +-
 include/crypto/akcipher.h                          |  2 +-
 include/crypto/gf128mul.h                          |  2 +-
 include/crypto/hash.h                              |  2 +-
 include/crypto/internal/acompress.h                |  2 +-
 include/crypto/kpp.h                               |  2 +-
 include/crypto/skcipher.h                          |  2 +-
 include/linux/slab.h                               |  4 ++-
 lib/mpi/mpiutil.c                                  |  6 ++--
 lib/test_kasan.c                                   |  6 ++--
 mm/slab_common.c                                   |  8 ++---
 net/atm/mpoa_caches.c                              |  4 +--
 net/bluetooth/ecdh_helper.c                        |  6 ++--
 net/bluetooth/smp.c                                | 24 +++++++--------
 net/core/sock.c                                    |  2 +-
 net/ipv4/tcp_fastopen.c                            |  2 +-
 net/mac80211/aead_api.c                            |  4 +--
 net/mac80211/aes_gmac.c                            |  2 +-
 net/mac80211/key.c                                 |  2 +-
 net/mac802154/llsec.c                              | 20 ++++++-------
 net/sctp/auth.c                                    |  2 +-
 net/sunrpc/auth_gss/gss_krb5_crypto.c              |  4 +--
 net/sunrpc/auth_gss/gss_krb5_keys.c                |  6 ++--
 net/sunrpc/auth_gss/gss_krb5_mech.c                |  2 +-
 net/tipc/crypto.c                                  | 10 +++----
 net/wireless/core.c                                |  2 +-
 net/wireless/ibss.c                                |  4 +--
 net/wireless/lib80211_crypt_tkip.c                 |  2 +-
 net/wireless/lib80211_crypt_wep.c                  |  2 +-
 net/wireless/nl80211.c                             | 24 +++++++--------
 net/wireless/sme.c                                 |  6 ++--
 net/wireless/util.c                                |  2 +-
 net/wireless/wext-sme.c                            |  2 +-
 scripts/coccinelle/free/devm_free.cocci            |  4 +--
 scripts/coccinelle/free/ifnullfree.cocci           |  4 +--
 scripts/coccinelle/free/kfree.cocci                |  6 ++--
 scripts/coccinelle/free/kfreeaddr.cocci            |  2 +-
 security/apparmor/domain.c                         |  4 +--
 security/apparmor/include/file.h                   |  2 +-
 security/apparmor/policy.c                         | 24 +++++++--------
 security/apparmor/policy_ns.c                      |  6 ++--
 security/apparmor/policy_unpack.c                  | 14 ++++-----
 security/keys/big_key.c                            |  6 ++--
 security/keys/dh.c                                 | 14 ++++-----
 security/keys/encrypted-keys/encrypted.c           | 14 ++++-----
 security/keys/trusted-keys/trusted_tpm1.c          | 34 +++++++++++-----------
 security/keys/user_defined.c                       |  6 ++--
 114 files changed, 323 insertions(+), 320 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index e1ae23911ccd..5057773f82e9 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -249,7 +249,7 @@ static void prng_tdes_deinstantiate(void)
 {
 	pr_debug("The prng module stopped "
 		 "after running in triple DES mode\n");
-	kzfree(prng_data);
+	kfree_sensitive(prng_data);
 }
 
 
@@ -442,7 +442,7 @@ outfree:
 static void prng_sha512_deinstantiate(void)
 {
 	pr_debug("The prng module stopped after running in SHA-512 mode\n");
-	kzfree(prng_data);
+	kfree_sensitive(prng_data);
 }
 
 
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index d147f1b2c925..cd3914fc9f3d 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -98,7 +98,7 @@ static int get_e820_md5(struct e820_table *table, void *buf)
 	if (crypto_shash_digest(desc, (u8 *)table, size, buf))
 		ret = -EINVAL;
 
-	kzfree(desc);
+	kfree_sensitive(desc);
 
 free_tfm:
 	crypto_free_shash(tfm);
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 7fbdc3270984..ce4d5725342c 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -177,7 +177,7 @@ static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	keyp += NHPOLY1305_KEY_SIZE;
 	WARN_ON(keyp != &data->derived_keys[ARRAY_SIZE(data->derived_keys)]);
 out:
-	kzfree(data);
+	kfree_sensitive(data);
 	return err;
 }
 
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 68a0f0cb75c4..d9d65d1cc669 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -183,7 +183,7 @@ static int ahash_setkey_unaligned(struct crypto_ahash *tfm, const u8 *key,
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
 	ret = tfm->setkey(tfm, alignbuffer, keylen);
-	kzfree(buffer);
+	kfree_sensitive(buffer);
 	return ret;
 }
 
@@ -302,7 +302,7 @@ static void ahash_restore_req(struct ahash_request *req, int err)
 	req->priv = NULL;
 
 	/* Free the req->priv.priv from the ADJUSTED request. */
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 static void ahash_notify_einprogress(struct ahash_request *req)
diff --git a/crypto/api.c b/crypto/api.c
index 5d8fe60b36c1..ed08cbd5b9d3 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -571,7 +571,7 @@ void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm)
 		alg->cra_exit(tfm);
 	crypto_exit_ops(tfm);
 	crypto_mod_put(alg);
-	kzfree(mem);
+	kfree_sensitive(mem);
 }
 EXPORT_SYMBOL_GPL(crypto_destroy_tfm);
 
diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c
index cc9dbcecaaca..7553ab18db89 100644
--- a/crypto/asymmetric_keys/verify_pefile.c
+++ b/crypto/asymmetric_keys/verify_pefile.c
@@ -376,7 +376,7 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen,
 	}
 
 error:
-	kzfree(desc);
+	kfree_sensitive(desc);
 error_no_desc:
 	crypto_free_shash(tfm);
 	kleave(" = %d", ret);
@@ -447,6 +447,6 @@ int verify_pefile_signature(const void *pebuf, unsigned pelen,
 	ret = pefile_digest_pe(pebuf, pelen, &ctx);
 
 error:
-	kzfree(ctx.digest);
+	kfree_sensitive(ctx.digest);
 	return ret;
 }
diff --git a/crypto/deflate.c b/crypto/deflate.c
index 4c0e6c9d942a..b2a46f6dc961 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -163,7 +163,7 @@ static void __deflate_exit(void *ctx)
 static void deflate_free_ctx(struct crypto_scomp *tfm, void *ctx)
 {
 	__deflate_exit(ctx);
-	kzfree(ctx);
+	kfree_sensitive(ctx);
 }
 
 static void deflate_exit(struct crypto_tfm *tfm)
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 8d80d93cab97..e99fe34cfa00 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1218,19 +1218,19 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 {
 	if (!drbg)
 		return;
-	kzfree(drbg->Vbuf);
+	kfree_sensitive(drbg->Vbuf);
 	drbg->Vbuf = NULL;
 	drbg->V = NULL;
-	kzfree(drbg->Cbuf);
+	kfree_sensitive(drbg->Cbuf);
 	drbg->Cbuf = NULL;
 	drbg->C = NULL;
-	kzfree(drbg->scratchpadbuf);
+	kfree_sensitive(drbg->scratchpadbuf);
 	drbg->scratchpadbuf = NULL;
 	drbg->reseed_ctr = 0;
 	drbg->d_ops = NULL;
 	drbg->core = NULL;
 	if (IS_ENABLED(CONFIG_CRYPTO_FIPS)) {
-		kzfree(drbg->prev);
+		kfree_sensitive(drbg->prev);
 		drbg->prev = NULL;
 		drbg->fips_primed = false;
 	}
@@ -1701,7 +1701,7 @@ static int drbg_fini_hash_kernel(struct drbg_state *drbg)
 	struct sdesc *sdesc = (struct sdesc *)drbg->priv_data;
 	if (sdesc) {
 		crypto_free_shash(sdesc->shash.tfm);
-		kzfree(sdesc);
+		kfree_sensitive(sdesc);
 	}
 	drbg->priv_data = NULL;
 	return 0;
diff --git a/crypto/ecc.c b/crypto/ecc.c
index 8acf8433ca29..c80aa25994a0 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -67,7 +67,7 @@ static u64 *ecc_alloc_digits_space(unsigned int ndigits)
 
 static void ecc_free_digits_space(u64 *space)
 {
-	kzfree(space);
+	kfree_sensitive(space);
 }
 
 static struct ecc_point *ecc_alloc_point(unsigned int ndigits)
@@ -101,9 +101,9 @@ static void ecc_free_point(struct ecc_point *p)
 	if (!p)
 		return;
 
-	kzfree(p->x);
-	kzfree(p->y);
-	kzfree(p);
+	kfree_sensitive(p->x);
+	kfree_sensitive(p->y);
+	kfree_sensitive(p);
 }
 
 static void vli_clear(u64 *vli, unsigned int ndigits)
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index bd599053a8c4..b0232d6ab4ce 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -124,7 +124,7 @@ static int ecdh_compute_value(struct kpp_request *req)
 
 	/* fall through */
 free_all:
-	kzfree(shared_secret);
+	kfree_sensitive(shared_secret);
 free_pubkey:
 	kfree(public_key);
 	return ret;
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 3a36a9533c96..338ee0769747 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -139,7 +139,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 			       CRYPTO_TFM_REQ_MASK);
 	err = crypto_ahash_setkey(ghash, (u8 *)&data->hash, sizeof(be128));
 out:
-	kzfree(data);
+	kfree_sensitive(data);
 	return err;
 }
 
diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c
index a4b1c026aaee..a69ae3e6c16c 100644
--- a/crypto/gf128mul.c
+++ b/crypto/gf128mul.c
@@ -304,8 +304,8 @@ void gf128mul_free_64k(struct gf128mul_64k *t)
 	int i;
 
 	for (i = 0; i < 16; i++)
-		kzfree(t->t[i]);
-	kzfree(t);
+		kfree_sensitive(t->t[i]);
+	kfree_sensitive(t);
 }
 EXPORT_SYMBOL(gf128mul_free_64k);
 
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index b43684c0dade..eb7d1dd506bf 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -57,7 +57,7 @@ void *jent_zalloc(unsigned int len)
 
 void jent_zfree(void *ptr)
 {
-	kzfree(ptr);
+	kfree_sensitive(ptr);
 }
 
 int jent_fips_enabled(void)
diff --git a/crypto/rng.c b/crypto/rng.c
index 1490d210f1a1..a888d84b524a 100644
--- a/crypto/rng.c
+++ b/crypto/rng.c
@@ -53,7 +53,7 @@ int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen)
 	err = crypto_rng_alg(tfm)->seed(tfm, seed, slen);
 	crypto_stats_rng_seed(alg, err);
 out:
-	kzfree(buf);
+	kfree_sensitive(buf);
 	return err;
 }
 EXPORT_SYMBOL_GPL(crypto_rng_reset);
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 4983b2b4a223..ddd3d10ffc15 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -199,7 +199,7 @@ static int pkcs1pad_encrypt_sign_complete(struct akcipher_request *req, int err)
 	sg_copy_from_buffer(req->dst,
 			    sg_nents_for_len(req->dst, ctx->key_size),
 			    out_buf, ctx->key_size);
-	kzfree(out_buf);
+	kfree_sensitive(out_buf);
 
 out:
 	req->dst_len = ctx->key_size;
@@ -322,7 +322,7 @@ static int pkcs1pad_decrypt_complete(struct akcipher_request *req, int err)
 				out_buf + pos, req->dst_len);
 
 done:
-	kzfree(req_ctx->out_buf);
+	kfree_sensitive(req_ctx->out_buf);
 
 	return err;
 }
@@ -500,7 +500,7 @@ static int pkcs1pad_verify_complete(struct akcipher_request *req, int err)
 		   req->dst_len) != 0)
 		err = -EKEYREJECTED;
 done:
-	kzfree(req_ctx->out_buf);
+	kfree_sensitive(req_ctx->out_buf);
 
 	return err;
 }
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index 23e22d8b63e6..0899d527c284 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -33,7 +33,7 @@ static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
 	memcpy(req->iv, subreq->iv, crypto_aead_ivsize(geniv));
 
 out:
-	kzfree(subreq->iv);
+	kfree_sensitive(subreq->iv);
 }
 
 static void seqiv_aead_encrypt_complete(struct crypto_async_request *base,
diff --git a/crypto/shash.c b/crypto/shash.c
index e6a4b5f39b8c..2e3433ad9762 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -44,7 +44,7 @@ static int shash_setkey_unaligned(struct crypto_shash *tfm, const u8 *key,
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
 	err = shash->setkey(tfm, alignbuffer, keylen);
-	kzfree(buffer);
+	kfree_sensitive(buffer);
 	return err;
 }
 
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 467af525848a..b4dae640de9f 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -592,7 +592,7 @@ static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm,
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
 	ret = cipher->setkey(tfm, alignbuffer, keylen);
-	kzfree(buffer);
+	kfree_sensitive(buffer);
 	return ret;
 }
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 6863f911fcee..23c27fc96394 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1744,7 +1744,7 @@ out:
 	kfree(vec.plaintext);
 	kfree(vec.digest);
 	crypto_free_shash(generic_tfm);
-	kzfree(generic_desc);
+	kfree_sensitive(generic_desc);
 	return err;
 }
 #else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
@@ -3665,7 +3665,7 @@ static int drbg_cavs_test(const struct drbg_testvec *test, int pr,
 	if (IS_ERR(drng)) {
 		printk(KERN_ERR "alg: drbg: could not allocate DRNG handle for "
 		       "%s\n", driver);
-		kzfree(buf);
+		kfree_sensitive(buf);
 		return -ENOMEM;
 	}
 
@@ -3712,7 +3712,7 @@ static int drbg_cavs_test(const struct drbg_testvec *test, int pr,
 
 outbuf:
 	crypto_free_rng(drng);
-	kzfree(buf);
+	kfree_sensitive(buf);
 	return ret;
 }
 
diff --git a/crypto/zstd.c b/crypto/zstd.c
index 5a3ff258d8f7..1a3309f066f7 100644
--- a/crypto/zstd.c
+++ b/crypto/zstd.c
@@ -137,7 +137,7 @@ static void __zstd_exit(void *ctx)
 static void zstd_free_ctx(struct crypto_scomp *tfm, void *ctx)
 {
 	__zstd_exit(ctx);
-	kzfree(ctx);
+	kfree_sensitive(ctx);
 }
 
 static void zstd_exit(struct crypto_tfm *tfm)
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
index 1e4f9a58bb24..b4d5fea27d20 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -254,7 +254,7 @@ theend_iv:
 		offset = areq->cryptlen - ivsize;
 		if (rctx->op_dir & CE_DECRYPTION) {
 			memcpy(areq->iv, backup_iv, ivsize);
-			kzfree(backup_iv);
+			kfree_sensitive(backup_iv);
 		} else {
 			scatterwalk_map_and_copy(areq->iv, areq->dst, offset,
 						 ivsize, 0);
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
index 7a131675a41c..7b39b4495571 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -249,7 +249,7 @@ theend_iv:
 			if (rctx->op_dir & SS_DECRYPTION) {
 				memcpy(areq->iv, backup_iv, ivsize);
 				memzero_explicit(backup_iv, ivsize);
-				kzfree(backup_iv);
+				kfree_sensitive(backup_iv);
 			} else {
 				scatterwalk_map_and_copy(areq->iv, areq->dst, offset,
 							 ivsize, 0);
diff --git a/drivers/crypto/amlogic/amlogic-gxl-cipher.c b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
index 5880b94dcb32..d93210726697 100644
--- a/drivers/crypto/amlogic/amlogic-gxl-cipher.c
+++ b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
@@ -252,8 +252,8 @@ static int meson_cipher(struct skcipher_request *areq)
 		}
 	}
 theend:
-	kzfree(bkeyiv);
-	kzfree(backup_iv);
+	kfree_sensitive(bkeyiv);
+	kfree_sensitive(backup_iv);
 
 	return err;
 }
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index ff02cc05affb..9bd8e5167be3 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -69,7 +69,7 @@ static void atmel_ecdh_done(struct atmel_i2c_work_data *work_data, void *areq,
 
 	/* fall through */
 free_work_data:
-	kzfree(work_data);
+	kfree_sensitive(work_data);
 	kpp_request_complete(req, status);
 }
 
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 2e44d685618f..dd5f101e43f8 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -854,14 +854,14 @@ static int caam_rsa_dec(struct akcipher_request *req)
 
 static void caam_rsa_free_key(struct caam_rsa_key *key)
 {
-	kzfree(key->d);
-	kzfree(key->p);
-	kzfree(key->q);
-	kzfree(key->dp);
-	kzfree(key->dq);
-	kzfree(key->qinv);
-	kzfree(key->tmp1);
-	kzfree(key->tmp2);
+	kfree_sensitive(key->d);
+	kfree_sensitive(key->p);
+	kfree_sensitive(key->q);
+	kfree_sensitive(key->dp);
+	kfree_sensitive(key->dq);
+	kfree_sensitive(key->qinv);
+	kfree_sensitive(key->tmp1);
+	kfree_sensitive(key->tmp2);
 	kfree(key->e);
 	kfree(key->n);
 	memset(key, 0, sizeof(*key));
@@ -1018,17 +1018,17 @@ static void caam_rsa_set_priv_key_form(struct caam_rsa_ctx *ctx,
 	return;
 
 free_dq:
-	kzfree(rsa_key->dq);
+	kfree_sensitive(rsa_key->dq);
 free_dp:
-	kzfree(rsa_key->dp);
+	kfree_sensitive(rsa_key->dp);
 free_tmp2:
-	kzfree(rsa_key->tmp2);
+	kfree_sensitive(rsa_key->tmp2);
 free_tmp1:
-	kzfree(rsa_key->tmp1);
+	kfree_sensitive(rsa_key->tmp1);
 free_q:
-	kzfree(rsa_key->q);
+	kfree_sensitive(rsa_key->q);
 free_p:
-	kzfree(rsa_key->p);
+	kfree_sensitive(rsa_key->p);
 }
 
 static int caam_rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
index 0f72e9abdefe..a15245992cf9 100644
--- a/drivers/crypto/cavium/cpt/cptvf_main.c
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -74,7 +74,7 @@ static void cleanup_worker_threads(struct cpt_vf *cptvf)
 	for (i = 0; i < cptvf->nr_queues; i++)
 		tasklet_kill(&cwqe_info->vq_wqe[i].twork);
 
-	kzfree(cwqe_info);
+	kfree_sensitive(cwqe_info);
 	cptvf->wqe_info = NULL;
 }
 
@@ -88,7 +88,7 @@ static void free_pending_queues(struct pending_qinfo *pqinfo)
 			continue;
 
 		/* free single queue */
-		kzfree((queue->head));
+		kfree_sensitive((queue->head));
 
 		queue->front = 0;
 		queue->rear = 0;
@@ -189,7 +189,7 @@ static void free_command_queues(struct cpt_vf *cptvf,
 			chunk->head = NULL;
 			chunk->dma_addr = 0;
 			hlist_del(&chunk->nextchunk);
-			kzfree(chunk);
+			kfree_sensitive(chunk);
 		}
 
 		queue->nchunks = 0;
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index 3878b01e19e1..dc5fda522719 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -305,12 +305,12 @@ static void do_request_cleanup(struct cpt_vf *cptvf,
 		}
 	}
 
-	kzfree(info->scatter_components);
-	kzfree(info->gather_components);
-	kzfree(info->out_buffer);
-	kzfree(info->in_buffer);
-	kzfree((void *)info->completion_addr);
-	kzfree(info);
+	kfree_sensitive(info->scatter_components);
+	kfree_sensitive(info->gather_components);
+	kfree_sensitive(info->out_buffer);
+	kfree_sensitive(info->in_buffer);
+	kfree_sensitive((void *)info->completion_addr);
+	kfree_sensitive(info);
 }
 
 static void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info)
diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c
index 5cbc64b851b9..a5cdc2b48bd6 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_lib.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_lib.c
@@ -90,7 +90,7 @@ static void nitrox_free_aqm_queues(struct nitrox_device *ndev)
 
 	for (i = 0; i < ndev->nr_queues; i++) {
 		nitrox_cmdq_cleanup(ndev->aqmq[i]);
-		kzfree(ndev->aqmq[i]);
+		kfree_sensitive(ndev->aqmq[i]);
 		ndev->aqmq[i] = NULL;
 	}
 }
@@ -122,7 +122,7 @@ static int nitrox_alloc_aqm_queues(struct nitrox_device *ndev)
 
 		err = nitrox_cmdq_init(cmdq, AQM_Q_ALIGN_BYTES);
 		if (err) {
-			kzfree(cmdq);
+			kfree_sensitive(cmdq);
 			goto aqmq_fail;
 		}
 		ndev->aqmq[i] = cmdq;
diff --git a/drivers/crypto/cavium/zip/zip_crypto.c b/drivers/crypto/cavium/zip/zip_crypto.c
index 4985bc812b0e..7df71fcebe8f 100644
--- a/drivers/crypto/cavium/zip/zip_crypto.c
+++ b/drivers/crypto/cavium/zip/zip_crypto.c
@@ -260,7 +260,7 @@ void *zip_alloc_scomp_ctx_deflate(struct crypto_scomp *tfm)
 	ret = zip_ctx_init(zip_ctx, 0);
 
 	if (ret) {
-		kzfree(zip_ctx);
+		kfree_sensitive(zip_ctx);
 		return ERR_PTR(ret);
 	}
 
@@ -279,7 +279,7 @@ void *zip_alloc_scomp_ctx_lzs(struct crypto_scomp *tfm)
 	ret = zip_ctx_init(zip_ctx, 1);
 
 	if (ret) {
-		kzfree(zip_ctx);
+		kfree_sensitive(zip_ctx);
 		return ERR_PTR(ret);
 	}
 
@@ -291,7 +291,7 @@ void zip_free_scomp_ctx(struct crypto_scomp *tfm, void *ctx)
 	struct zip_kernel_ctx *zip_ctx = ctx;
 
 	zip_ctx_exit(zip_ctx);
-	kzfree(zip_ctx);
+	kfree_sensitive(zip_ctx);
 }
 
 int zip_scomp_compress(struct crypto_scomp *tfm,
diff --git a/drivers/crypto/ccp/ccp-crypto-rsa.c b/drivers/crypto/ccp/ccp-crypto-rsa.c
index 649c91d60401..1223ac70aea2 100644
--- a/drivers/crypto/ccp/ccp-crypto-rsa.c
+++ b/drivers/crypto/ccp/ccp-crypto-rsa.c
@@ -112,13 +112,13 @@ static int ccp_check_key_length(unsigned int len)
 static void ccp_rsa_free_key_bufs(struct ccp_ctx *ctx)
 {
 	/* Clean up old key data */
-	kzfree(ctx->u.rsa.e_buf);
+	kfree_sensitive(ctx->u.rsa.e_buf);
 	ctx->u.rsa.e_buf = NULL;
 	ctx->u.rsa.e_len = 0;
-	kzfree(ctx->u.rsa.n_buf);
+	kfree_sensitive(ctx->u.rsa.n_buf);
 	ctx->u.rsa.n_buf = NULL;
 	ctx->u.rsa.n_len = 0;
-	kzfree(ctx->u.rsa.d_buf);
+	kfree_sensitive(ctx->u.rsa.d_buf);
 	ctx->u.rsa.d_buf = NULL;
 	ctx->u.rsa.d_len = 0;
 }
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 1cf51edbc4b9..35794c7271fb 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -448,7 +448,7 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *authkey,
 		if (dma_mapping_error(dev, key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 				key, keylen);
-			kzfree(key);
+			kfree_sensitive(key);
 			return -ENOMEM;
 		}
 		if (keylen > blocksize) {
@@ -533,7 +533,7 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *authkey,
 	if (key_dma_addr)
 		dma_unmap_single(dev, key_dma_addr, keylen, DMA_TO_DEVICE);
 
-	kzfree(key);
+	kfree_sensitive(key);
 
 	return rc;
 }
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index b2bd093e7013..a5e041d9d2cf 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -488,7 +488,7 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 	if (areq_ctx->gen_ctx.iv_dma_addr) {
 		dma_unmap_single(dev, areq_ctx->gen_ctx.iv_dma_addr,
 				 hw_iv_size, DMA_BIDIRECTIONAL);
-		kzfree(areq_ctx->gen_ctx.iv);
+		kfree_sensitive(areq_ctx->gen_ctx.iv);
 	}
 
 	/* Release pool */
@@ -559,7 +559,7 @@ static int cc_aead_chain_iv(struct cc_drvdata *drvdata,
 	if (dma_mapping_error(dev, areq_ctx->gen_ctx.iv_dma_addr)) {
 		dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 			hw_iv_size, req->iv);
-		kzfree(areq_ctx->gen_ctx.iv);
+		kfree_sensitive(areq_ctx->gen_ctx.iv);
 		areq_ctx->gen_ctx.iv = NULL;
 		rc = -ENOMEM;
 		goto chain_iv_exit;
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 076669dc1035..d77ae981b64b 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -257,7 +257,7 @@ static void cc_cipher_exit(struct crypto_tfm *tfm)
 		&ctx_p->user.key_dma_addr);
 
 	/* Free key buffer in context */
-	kzfree(ctx_p->user.key);
+	kfree_sensitive(ctx_p->user.key);
 	dev_dbg(dev, "Free key buffer in context. key=@%p\n", ctx_p->user.key);
 }
 
@@ -881,7 +881,7 @@ static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
 		/* Not a BACKLOG notification */
 		cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
 		memcpy(req->iv, req_ctx->iv, ivsize);
-		kzfree(req_ctx->iv);
+		kfree_sensitive(req_ctx->iv);
 	}
 
 	skcipher_request_complete(req, err);
@@ -994,7 +994,7 @@ static int cc_cipher_process(struct skcipher_request *req,
 
 exit_process:
 	if (rc != -EINPROGRESS && rc != -EBUSY) {
-		kzfree(req_ctx->iv);
+		kfree_sensitive(req_ctx->iv);
 	}
 
 	return rc;
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index d5310783af15..683c9a430e11 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -764,7 +764,7 @@ static int cc_hash_setkey(struct crypto_ahash *ahash, const u8 *key,
 		if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 				ctx->key_params.key, keylen);
-			kzfree(ctx->key_params.key);
+			kfree_sensitive(ctx->key_params.key);
 			return -ENOMEM;
 		}
 		dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -913,7 +913,7 @@ out:
 			&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 	}
 
-	kzfree(ctx->key_params.key);
+	kfree_sensitive(ctx->key_params.key);
 
 	return rc;
 }
@@ -950,7 +950,7 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 	if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 		dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 			key, keylen);
-		kzfree(ctx->key_params.key);
+		kfree_sensitive(ctx->key_params.key);
 		return -ENOMEM;
 	}
 	dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -999,7 +999,7 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 	dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
 		&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 
-	kzfree(ctx->key_params.key);
+	kfree_sensitive(ctx->key_params.key);
 
 	return rc;
 }
diff --git a/drivers/crypto/ccree/cc_request_mgr.c b/drivers/crypto/ccree/cc_request_mgr.c
index 1d7649ecf44e..33fb27745d52 100644
--- a/drivers/crypto/ccree/cc_request_mgr.c
+++ b/drivers/crypto/ccree/cc_request_mgr.c
@@ -107,7 +107,7 @@ void cc_req_mgr_fini(struct cc_drvdata *drvdata)
 	/* Kill tasklet */
 	tasklet_kill(&req_mgr_h->comptask);
 #endif
-	kzfree(req_mgr_h);
+	kfree_sensitive(req_mgr_h);
 	drvdata->request_mgr_handle = NULL;
 }
 
diff --git a/drivers/crypto/marvell/cesa/hash.c b/drivers/crypto/marvell/cesa/hash.c
index bd0bd9ffd6e9..f2a2fc111164 100644
--- a/drivers/crypto/marvell/cesa/hash.c
+++ b/drivers/crypto/marvell/cesa/hash.c
@@ -1157,7 +1157,7 @@ static int mv_cesa_ahmac_pad_init(struct ahash_request *req,
 		}
 
 		/* Set the memory region to 0 to avoid any leak. */
-		kzfree(keydup);
+		kfree_sensitive(keydup);
 
 		if (ret)
 			return ret;
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
index ce3168327a39..228fe8e47e0e 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
@@ -68,7 +68,7 @@ static void cleanup_worker_threads(struct otx_cptvf *cptvf)
 	for (i = 0; i < cptvf->num_queues; i++)
 		tasklet_kill(&cwqe_info->vq_wqe[i].twork);
 
-	kzfree(cwqe_info);
+	kfree_sensitive(cwqe_info);
 	cptvf->wqe_info = NULL;
 }
 
@@ -82,7 +82,7 @@ static void free_pending_queues(struct otx_cpt_pending_qinfo *pqinfo)
 			continue;
 
 		/* free single queue */
-		kzfree((queue->head));
+		kfree_sensitive((queue->head));
 		queue->front = 0;
 		queue->rear = 0;
 		queue->qlen = 0;
@@ -176,7 +176,7 @@ static void free_command_queues(struct otx_cptvf *cptvf,
 			chunk->head = NULL;
 			chunk->dma_addr = 0;
 			list_del(&chunk->nextchunk);
-			kzfree(chunk);
+			kfree_sensitive(chunk);
 		}
 		queue->num_chunks = 0;
 		queue->idx = 0;
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.h b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.h
index d912fe0c532d..a02d059fb652 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.h
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.h
@@ -215,7 +215,7 @@ static inline void do_request_cleanup(struct pci_dev *pdev,
 						 DMA_BIDIRECTIONAL);
 		}
 	}
-	kzfree(info);
+	kfree_sensitive(info);
 }
 
 struct otx_cptvf_wqe;
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index f03c238f5a31..40882d6d52c1 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -746,7 +746,7 @@ void nx_crypto_ctx_exit(struct crypto_tfm *tfm)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
 
-	kzfree(nx_ctx->kmem);
+	kfree_sensitive(nx_ctx->kmem);
 	nx_ctx->csbcpb = NULL;
 	nx_ctx->csbcpb_aead = NULL;
 	nx_ctx->in_sg = NULL;
@@ -762,7 +762,7 @@ void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
 
-	kzfree(nx_ctx->kmem);
+	kfree_sensitive(nx_ctx->kmem);
 }
 
 static int nx_probe(struct vio_dev *viodev, const struct vio_device_id *id)
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index b2601958282e..583c0b535d13 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -167,7 +167,7 @@ static int virtio_crypto_alg_skcipher_init_session(
 				num_in, vcrypto, GFP_ATOMIC);
 	if (err < 0) {
 		spin_unlock(&vcrypto->ctrl_lock);
-		kzfree(cipher_key);
+		kfree_sensitive(cipher_key);
 		return err;
 	}
 	virtqueue_kick(vcrypto->ctrl_vq);
@@ -184,7 +184,7 @@ static int virtio_crypto_alg_skcipher_init_session(
 		spin_unlock(&vcrypto->ctrl_lock);
 		pr_err("virtio_crypto: Create session failed status: %u\n",
 			le32_to_cpu(vcrypto->input.status));
-		kzfree(cipher_key);
+		kfree_sensitive(cipher_key);
 		return -EINVAL;
 	}
 
@@ -197,7 +197,7 @@ static int virtio_crypto_alg_skcipher_init_session(
 
 	spin_unlock(&vcrypto->ctrl_lock);
 
-	kzfree(cipher_key);
+	kfree_sensitive(cipher_key);
 	return 0;
 }
 
@@ -472,9 +472,9 @@ __virtio_crypto_skcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	return 0;
 
 free_iv:
-	kzfree(iv);
+	kfree_sensitive(iv);
 free:
-	kzfree(req_data);
+	kfree_sensitive(req_data);
 	kfree(sgs);
 	return err;
 }
@@ -583,7 +583,7 @@ static void virtio_crypto_skcipher_finalize_req(
 		scatterwalk_map_and_copy(req->iv, req->dst,
 					 req->cryptlen - AES_BLOCK_SIZE,
 					 AES_BLOCK_SIZE, 0);
-	kzfree(vc_sym_req->iv);
+	kfree_sensitive(vc_sym_req->iv);
 	virtcrypto_clear_request(&vc_sym_req->base);
 
 	crypto_finalize_skcipher_request(vc_sym_req->base.dataq->engine,
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 77e744eaedd0..0c66d6193ca2 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -17,7 +17,7 @@ void
 virtcrypto_clear_request(struct virtio_crypto_request *vc_req)
 {
 	if (vc_req) {
-		kzfree(vc_req->req_data);
+		kfree_sensitive(vc_req->req_data);
 		kfree(vc_req->sgs);
 	}
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index b437a14c4942..37dcc52cf21d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -407,7 +407,7 @@ static void crypt_iv_lmk_dtr(struct crypt_config *cc)
 		crypto_free_shash(lmk->hash_tfm);
 	lmk->hash_tfm = NULL;
 
-	kzfree(lmk->seed);
+	kfree_sensitive(lmk->seed);
 	lmk->seed = NULL;
 }
 
@@ -558,9 +558,9 @@ static void crypt_iv_tcw_dtr(struct crypt_config *cc)
 {
 	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
 
-	kzfree(tcw->iv_seed);
+	kfree_sensitive(tcw->iv_seed);
 	tcw->iv_seed = NULL;
-	kzfree(tcw->whitening);
+	kfree_sensitive(tcw->whitening);
 	tcw->whitening = NULL;
 
 	if (tcw->crc32_tfm && !IS_ERR(tcw->crc32_tfm))
@@ -994,8 +994,8 @@ static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *d
 
 	kunmap_atomic(data);
 out:
-	kzfree(ks);
-	kzfree(es);
+	kfree_sensitive(ks);
+	kfree_sensitive(es);
 	skcipher_request_free(req);
 	return r;
 }
@@ -2294,7 +2294,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	key = request_key(type, key_desc + 1, NULL);
 	if (IS_ERR(key)) {
-		kzfree(new_key_string);
+		kfree_sensitive(new_key_string);
 		return PTR_ERR(key);
 	}
 
@@ -2304,7 +2304,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 	if (ret < 0) {
 		up_read(&key->sem);
 		key_put(key);
-		kzfree(new_key_string);
+		kfree_sensitive(new_key_string);
 		return ret;
 	}
 
@@ -2318,10 +2318,10 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	if (!ret) {
 		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
-		kzfree(cc->key_string);
+		kfree_sensitive(cc->key_string);
 		cc->key_string = new_key_string;
 	} else
-		kzfree(new_key_string);
+		kfree_sensitive(new_key_string);
 
 	return ret;
 }
@@ -2382,7 +2382,7 @@ static int crypt_set_key(struct crypt_config *cc, char *key)
 	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
 	/* wipe references to any kernel keyring key */
-	kzfree(cc->key_string);
+	kfree_sensitive(cc->key_string);
 	cc->key_string = NULL;
 
 	/* Decode key from its hex representation. */
@@ -2414,7 +2414,7 @@ static int crypt_wipe_key(struct crypt_config *cc)
 			return r;
 	}
 
-	kzfree(cc->key_string);
+	kfree_sensitive(cc->key_string);
 	cc->key_string = NULL;
 	r = crypt_setkey(cc);
 	memset(&cc->key, 0, cc->key_size * sizeof(u8));
@@ -2493,15 +2493,15 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->dev)
 		dm_put_device(ti, cc->dev);
 
-	kzfree(cc->cipher_string);
-	kzfree(cc->key_string);
-	kzfree(cc->cipher_auth);
-	kzfree(cc->authenc_key);
+	kfree_sensitive(cc->cipher_string);
+	kfree_sensitive(cc->key_string);
+	kfree_sensitive(cc->cipher_auth);
+	kfree_sensitive(cc->authenc_key);
 
 	mutex_destroy(&cc->bio_alloc_lock);
 
 	/* Must zero key material before freeing */
-	kzfree(cc);
+	kfree_sensitive(cc);
 
 	spin_lock(&dm_crypt_clients_lock);
 	WARN_ON(!dm_crypt_clients_n);
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5da3eb661e50..8c8d940e532e 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3405,8 +3405,8 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int
 
 static void free_alg(struct alg_spec *a)
 {
-	kzfree(a->alg_string);
-	kzfree(a->key);
+	kfree_sensitive(a->alg_string);
+	kfree_sensitive(a->key);
 	memset(a, 0, sizeof *a);
 }
 
@@ -4337,7 +4337,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 		for (i = 0; i < ic->journal_sections; i++) {
 			struct skcipher_request *req = ic->sk_requests[i];
 			if (req) {
-				kzfree(req->iv);
+				kfree_sensitive(req->iv);
 				skcipher_request_free(req);
 			}
 		}
diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c
index c0d139c26505..2d778d0f011e 100644
--- a/drivers/misc/ibmvmc.c
+++ b/drivers/misc/ibmvmc.c
@@ -286,7 +286,7 @@ static void *alloc_dma_buffer(struct vio_dev *vdev, size_t size,
 
 	if (dma_mapping_error(&vdev->dev, *dma_handle)) {
 		*dma_handle = 0;
-		kzfree(buffer);
+		kfree_sensitive(buffer);
 		return NULL;
 	}
 
@@ -310,7 +310,7 @@ static void free_dma_buffer(struct vio_dev *vdev, size_t size, void *vaddr,
 	dma_unmap_single(&vdev->dev, dma_handle, size, DMA_BIDIRECTIONAL);
 
 	/* deallocate memory */
-	kzfree(vaddr);
+	kfree_sensitive(vaddr);
 }
 
 /**
@@ -883,7 +883,7 @@ static int ibmvmc_close(struct inode *inode, struct file *file)
 		spin_unlock_irqrestore(&hmc->lock, flags);
 	}
 
-	kzfree(session);
+	kfree_sensitive(session);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 0874ae47cb03..3ab6db2588d3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -137,7 +137,7 @@ static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
 
 	while (chain) {
 		chain_tmp = chain->next;
-		kzfree(chain);
+		kfree_sensitive(chain);
 		chain = chain_tmp;
 	}
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 6516980965a2..eca73526ac86 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -960,9 +960,9 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 	return 0;
 
 err_aead:
-	kzfree(xs->aead);
+	kfree_sensitive(xs->aead);
 err_xs:
-	kzfree(xs);
+	kfree_sensitive(xs);
 err_out:
 	msgbuf[1] = err;
 	return err;
@@ -1047,7 +1047,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 	ixgbe_ipsec_del_sa(xs);
 
 	/* remove the xs that was made-up in the add request */
-	kzfree(xs);
+	kfree_sensitive(xs);
 
 	return 0;
 }
diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index de3b57d09d0c..208f6e24f37c 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -222,7 +222,7 @@ out_free:
 	kfree(state->sha1_digest);
 	if (state->sha1) {
 		crypto_free_shash(state->sha1->tfm);
-		kzfree(state->sha1);
+		kfree_sensitive(state->sha1);
 	}
 	kfree(state);
 out:
@@ -238,8 +238,8 @@ static void mppe_free(void *arg)
 	if (state) {
 		kfree(state->sha1_digest);
 		crypto_free_shash(state->sha1->tfm);
-		kzfree(state->sha1);
-		kzfree(state);
+		kfree_sensitive(state->sha1);
+		kfree_sensitive(state);
 	}
 }
 
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 201a22681945..3dd3b76790d0 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -114,7 +114,7 @@ static struct noise_keypair *keypair_create(struct wg_peer *peer)
 
 static void keypair_free_rcu(struct rcu_head *rcu)
 {
-	kzfree(container_of(rcu, struct noise_keypair, rcu));
+	kfree_sensitive(container_of(rcu, struct noise_keypair, rcu));
 }
 
 static void keypair_free_kref(struct kref *kref)
@@ -821,7 +821,7 @@ bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
 			handshake->entry.peer->device->index_hashtable,
 			&handshake->entry, &new_keypair->entry);
 	} else {
-		kzfree(new_keypair);
+		kfree_sensitive(new_keypair);
 	}
 	rcu_read_unlock_bh();
 
diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c
index 1d634bd3038f..b3b6370e6b95 100644
--- a/drivers/net/wireguard/peer.c
+++ b/drivers/net/wireguard/peer.c
@@ -203,7 +203,7 @@ static void rcu_release(struct rcu_head *rcu)
 	/* The final zeroing takes care of clearing any remaining handshake key
 	 * material and other potentially sensitive information.
 	 */
-	kzfree(peer);
+	kfree_sensitive(peer);
 }
 
 static void kref_release(struct kref *refcount)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 24cb1b1f21f0..9463c108aa96 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1369,7 +1369,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 					   &rxcb, rxq->id);
 
 		if (reclaim) {
-			kzfree(txq->entries[cmd_index].free_buf);
+			kfree_sensitive(txq->entries[cmd_index].free_buf);
 			txq->entries[cmd_index].free_buf = NULL;
 		}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 7fc7542535d8..606bef2ecc7b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1026,7 +1026,7 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 	BUILD_BUG_ON(IWL_TFH_NUM_TBS > sizeof(out_meta->tbs) * BITS_PER_BYTE);
 	out_meta->flags = cmd->flags;
 	if (WARN_ON_ONCE(txq->entries[idx].free_buf))
-		kzfree(txq->entries[idx].free_buf);
+		kfree_sensitive(txq->entries[idx].free_buf);
 	txq->entries[idx].free_buf = dup_buf;
 
 	trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size, &out_cmd->hdr_wide);
@@ -1257,8 +1257,8 @@ static void iwl_pcie_gen2_txq_free(struct iwl_trans *trans, int txq_id)
 	/* De-alloc array of command/tx buffers */
 	if (txq_id == trans->txqs.cmd.q_id)
 		for (i = 0; i < txq->n_window; i++) {
-			kzfree(txq->entries[i].cmd);
-			kzfree(txq->entries[i].free_buf);
+			kfree_sensitive(txq->entries[i].cmd);
+			kfree_sensitive(txq->entries[i].free_buf);
 		}
 	del_timer_sync(&txq->stuck_timer);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 5c6c3fa0d29f..eb396c06b7fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -721,8 +721,8 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	/* De-alloc array of command/tx buffers */
 	if (txq_id == trans->txqs.cmd.q_id)
 		for (i = 0; i < txq->n_window; i++) {
-			kzfree(txq->entries[i].cmd);
-			kzfree(txq->entries[i].free_buf);
+			kfree_sensitive(txq->entries[i].cmd);
+			kfree_sensitive(txq->entries[i].free_buf);
 		}
 
 	/* De-alloc circular buffer of TFDs */
@@ -1765,7 +1765,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	BUILD_BUG_ON(IWL_TFH_NUM_TBS > sizeof(out_meta->tbs) * BITS_PER_BYTE);
 	out_meta->flags = cmd->flags;
 	if (WARN_ON_ONCE(txq->entries[idx].free_buf))
-		kzfree(txq->entries[idx].free_buf);
+		kfree_sensitive(txq->entries[idx].free_buf);
 	txq->entries[idx].free_buf = dup_buf;
 
 	trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size, &out_cmd->hdr_wide);
diff --git a/drivers/net/wireless/intersil/orinoco/wext.c b/drivers/net/wireless/intersil/orinoco/wext.c
index 1d4dae422106..7b6c4ae8ddb3 100644
--- a/drivers/net/wireless/intersil/orinoco/wext.c
+++ b/drivers/net/wireless/intersil/orinoco/wext.c
@@ -31,8 +31,8 @@ static int orinoco_set_key(struct orinoco_private *priv, int index,
 			   enum orinoco_alg alg, const u8 *key, int key_len,
 			   const u8 *seq, int seq_len)
 {
-	kzfree(priv->keys[index].key);
-	kzfree(priv->keys[index].seq);
+	kfree_sensitive(priv->keys[index].key);
+	kfree_sensitive(priv->keys[index].seq);
 
 	if (key_len) {
 		priv->keys[index].key = kzalloc(key_len, GFP_ATOMIC);
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 1a1d5e3c8d45..1ea046324e8f 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -219,8 +219,8 @@ static inline void ap_init_message(struct ap_message *ap_msg)
  */
 static inline void ap_release_message(struct ap_message *ap_msg)
 {
-	kzfree(ap_msg->msg);
-	kzfree(ap_msg->private);
+	kfree_sensitive(ap_msg->msg);
+	kfree_sensitive(ap_msg->private);
 }
 
 /*
diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c
index b10a92ae2067..eaaf6a5440a9 100644
--- a/drivers/staging/ks7010/ks_hostif.c
+++ b/drivers/staging/ks7010/ks_hostif.c
@@ -245,7 +245,7 @@ michael_mic(u8 *key, u8 *data, unsigned int len, u8 priority, u8 *result)
 	ret = crypto_shash_finup(desc, data + 12, len - 12, result);
 
 err_free_desc:
-	kzfree(desc);
+	kfree_sensitive(desc);
 
 err_free_tfm:
 	crypto_free_shash(tfm);
diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c
index 0f15c96183a0..7f74e1d05b3a 100644
--- a/drivers/staging/rtl8723bs/core/rtw_security.c
+++ b/drivers/staging/rtl8723bs/core/rtw_security.c
@@ -2251,7 +2251,7 @@ static void gf_mulx(u8 *pad)
 
 static void aes_encrypt_deinit(void *ctx)
 {
-	kzfree(ctx);
+	kfree_sensitive(ctx);
 }
 
 
diff --git a/drivers/staging/wlan-ng/p80211netdev.c b/drivers/staging/wlan-ng/p80211netdev.c
index b809c0015c0c..7b091c5a2984 100644
--- a/drivers/staging/wlan-ng/p80211netdev.c
+++ b/drivers/staging/wlan-ng/p80211netdev.c
@@ -429,7 +429,7 @@ static netdev_tx_t p80211knetdev_hard_start_xmit(struct sk_buff *skb,
 failed:
 	/* Free up the WEP buffer if it's not the same as the skb */
 	if ((p80211_wep.data) && (p80211_wep.data != skb->data))
-		kzfree(p80211_wep.data);
+		kfree_sensitive(p80211_wep.data);
 
 	/* we always free the skb here, never in a lower level. */
 	if (!result)
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index 0e54627d9aa8..62d912b79c61 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -484,7 +484,7 @@ static int chap_server_compute_hash(
 	pr_debug("[server] Sending CHAP_R=0x%s\n", response);
 	auth_ret = 0;
 out:
-	kzfree(desc);
+	kfree_sensitive(desc);
 	if (tfm)
 		crypto_free_shash(tfm);
 	kfree(initiatorchg);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 874a551f339c..9daa256f69d4 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -797,7 +797,7 @@ calc_seckey(struct cifs_ses *ses)
 	ses->auth_key.len = CIFS_SESS_KEY_SIZE;
 
 	memzero_explicit(sec_key, CIFS_SESS_KEY_SIZE);
-	kzfree(ctx_arc4);
+	kfree_sensitive(ctx_arc4);
 	return 0;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a61abde09ffe..889fee586d94 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2182,7 +2182,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			tmp_end++;
 			if (!(tmp_end < end && tmp_end[1] == delim)) {
 				/* No it is not. Set the password to NULL */
-				kzfree(vol->password);
+				kfree_sensitive(vol->password);
 				vol->password = NULL;
 				break;
 			}
@@ -2220,7 +2220,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 					options = end;
 			}
 
-			kzfree(vol->password);
+			kfree_sensitive(vol->password);
 			/* Now build new password string */
 			temp_len = strlen(value);
 			vol->password = kzalloc(temp_len+1, GFP_KERNEL);
@@ -3198,7 +3198,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
 			rc = -ENOMEM;
 			kfree(vol->username);
 			vol->username = NULL;
-			kzfree(vol->password);
+			kfree_sensitive(vol->password);
 			vol->password = NULL;
 			goto out_key_put;
 		}
@@ -4219,7 +4219,7 @@ void
 cifs_cleanup_volume_info_contents(struct smb_vol *volume_info)
 {
 	kfree(volume_info->username);
-	kzfree(volume_info->password);
+	kfree_sensitive(volume_info->password);
 	kfree(volume_info->UNC);
 	kfree(volume_info->domainname);
 	kfree(volume_info->iocharset);
@@ -5345,7 +5345,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 
 out:
 	kfree(vol_info->username);
-	kzfree(vol_info->password);
+	kfree_sensitive(vol_info->password);
 	kfree(vol_info);
 
 	return tcon;
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index df81c718d2fa..7a8d41493aad 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1131,7 +1131,7 @@ err_free_domainname:
 err_free_unc:
 	kfree(new->UNC);
 err_free_password:
-	kzfree(new->password);
+	kfree_sensitive(new->password);
 err_free_username:
 	kfree(new->username);
 	kfree(new);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index e44d049142d0..3e3772446c71 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -103,12 +103,12 @@ sesInfoFree(struct cifs_ses *buf_to_free)
 	kfree(buf_to_free->serverOS);
 	kfree(buf_to_free->serverDomain);
 	kfree(buf_to_free->serverNOS);
-	kzfree(buf_to_free->password);
+	kfree_sensitive(buf_to_free->password);
 	kfree(buf_to_free->user_name);
 	kfree(buf_to_free->domainName);
-	kzfree(buf_to_free->auth_key.response);
+	kfree_sensitive(buf_to_free->auth_key.response);
 	kfree(buf_to_free->iface_list);
-	kzfree(buf_to_free);
+	kfree_sensitive(buf_to_free);
 }
 
 struct cifs_tcon *
@@ -148,7 +148,7 @@ tconInfoFree(struct cifs_tcon *buf_to_free)
 	}
 	atomic_dec(&tconInfoAllocCount);
 	kfree(buf_to_free->nativeFileSystem);
-	kzfree(buf_to_free->password);
+	kfree_sensitive(buf_to_free->password);
 	kfree(buf_to_free->crfid.fid);
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	kfree(buf_to_free->dfs_path);
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index b6b8574caa13..faa25541ccb6 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -16,6 +16,7 @@
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/sched/mm.h>
+#include <linux/slab.h>
 
 #include "fscrypt_private.h"
 
@@ -187,7 +188,7 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
 fail:
 	for (i = 0; i < queue_refs; i++)
 		blk_put_queue(blk_key->devs[i]);
-	kzfree(blk_key);
+	kfree_sensitive(blk_key);
 	return err;
 }
 
@@ -201,7 +202,7 @@ void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key)
 			blk_crypto_evict_key(blk_key->devs[i], &blk_key->base);
 			blk_put_queue(blk_key->devs[i]);
 		}
-		kzfree(blk_key);
+		kfree_sensitive(blk_key);
 	}
 }
 
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 71d56f8e2870..e74f239c4428 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -51,7 +51,7 @@ static void free_master_key(struct fscrypt_master_key *mk)
 	}
 
 	key_put(mk->mk_users);
-	kzfree(mk);
+	kfree_sensitive(mk);
 }
 
 static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec)
@@ -531,7 +531,7 @@ static int fscrypt_provisioning_key_preparse(struct key_preparsed_payload *prep)
 static void fscrypt_provisioning_key_free_preparse(
 					struct key_preparsed_payload *prep)
 {
-	kzfree(prep->payload.data[0]);
+	kfree_sensitive(prep->payload.data[0]);
 }
 
 static void fscrypt_provisioning_key_describe(const struct key *key,
@@ -548,7 +548,7 @@ static void fscrypt_provisioning_key_describe(const struct key *key,
 
 static void fscrypt_provisioning_key_destroy(struct key *key)
 {
-	kzfree(key->payload.data[0]);
+	kfree_sensitive(key->payload.data[0]);
 }
 
 static struct key_type key_type_fscrypt_provisioning = {
diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c
index e4e707fb1100..a3cb52572b05 100644
--- a/fs/crypto/keysetup_v1.c
+++ b/fs/crypto/keysetup_v1.c
@@ -155,7 +155,7 @@ static void free_direct_key(struct fscrypt_direct_key *dk)
 {
 	if (dk) {
 		fscrypt_destroy_prepared_key(&dk->dk_key);
-		kzfree(dk);
+		kfree_sensitive(dk);
 	}
 }
 
@@ -283,7 +283,7 @@ static int setup_v1_file_key_derived(struct fscrypt_info *ci,
 
 	err = fscrypt_set_per_file_enc_key(ci, derived_key);
 out:
-	kzfree(derived_key);
+	kfree_sensitive(derived_key);
 	return err;
 }
 
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index af3eb02bbca1..f6a17d259db7 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -838,7 +838,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 out_release_free_unlock:
 	crypto_free_shash(s->hash_tfm);
 out_free_unlock:
-	kzfree(s->block_aligned_filename);
+	kfree_sensitive(s->block_aligned_filename);
 out_unlock:
 	mutex_unlock(s->tfm_mutex);
 out:
@@ -847,7 +847,7 @@ out:
 		key_put(auth_tok_key);
 	}
 	skcipher_request_free(s->skcipher_req);
-	kzfree(s->hash_desc);
+	kfree_sensitive(s->hash_desc);
 	kfree(s);
 	return rc;
 }
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 8646ba76def3..c0dfd9647627 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -175,7 +175,7 @@ int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon)
 	}
 	hlist_del(&daemon->euid_chain);
 	mutex_unlock(&daemon->mux);
-	kzfree(daemon);
+	kfree_sensitive(daemon);
 out:
 	return rc;
 }
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 62c68550aab6..c32a6f5664e9 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -425,7 +425,7 @@ static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm,
  */
 static inline void aead_request_free(struct aead_request *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 /**
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
index 6924b091adec..1d3aa252caba 100644
--- a/include/crypto/akcipher.h
+++ b/include/crypto/akcipher.h
@@ -207,7 +207,7 @@ static inline struct akcipher_request *akcipher_request_alloc(
  */
 static inline void akcipher_request_free(struct akcipher_request *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 /**
diff --git a/include/crypto/gf128mul.h b/include/crypto/gf128mul.h
index fa0a63d298dc..81330c6446f6 100644
--- a/include/crypto/gf128mul.h
+++ b/include/crypto/gf128mul.h
@@ -230,7 +230,7 @@ void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t);
 void gf128mul_x8_ble(le128 *r, const le128 *x);
 static inline void gf128mul_free_4k(struct gf128mul_4k *t)
 {
-	kzfree(t);
+	kfree_sensitive(t);
 }
 
 
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 19ce91f2359f..0d1b403888c9 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -606,7 +606,7 @@ static inline struct ahash_request *ahash_request_alloc(
  */
 static inline void ahash_request_free(struct ahash_request *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 static inline void ahash_request_zero(struct ahash_request *req)
diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h
index cf478681b53e..cfc47e18820f 100644
--- a/include/crypto/internal/acompress.h
+++ b/include/crypto/internal/acompress.h
@@ -46,7 +46,7 @@ static inline struct acomp_req *__acomp_request_alloc(struct crypto_acomp *tfm)
 
 static inline void __acomp_request_free(struct acomp_req *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 /**
diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h
index cd9a9b500624..88b591215d5c 100644
--- a/include/crypto/kpp.h
+++ b/include/crypto/kpp.h
@@ -187,7 +187,7 @@ static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm,
  */
 static inline void kpp_request_free(struct kpp_request *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 /**
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 5663f71198b3..6a733b171a5d 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -508,7 +508,7 @@ static inline struct skcipher_request *skcipher_request_alloc(
  */
 static inline void skcipher_request_free(struct skcipher_request *req)
 {
-	kzfree(req);
+	kfree_sensitive(req);
 }
 
 static inline void skcipher_request_zero(struct skcipher_request *req)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 6d454886bcaf..0884d82c55ee 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -186,10 +186,12 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *);
  */
 void * __must_check krealloc(const void *, size_t, gfp_t);
 void kfree(const void *);
-void kzfree(const void *);
+void kfree_sensitive(const void *);
 size_t __ksize(const void *);
 size_t ksize(const void *);
 
+#define kzfree(x)	kfree_sensitive(x)	/* For backward compatibility */
+
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
 void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 			bool to_user);
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index 20ed0f766787..4cd2b335cb7f 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -69,7 +69,7 @@ void mpi_free_limb_space(mpi_ptr_t a)
 	if (!a)
 		return;
 
-	kzfree(a);
+	kfree_sensitive(a);
 }
 
 void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs)
@@ -95,7 +95,7 @@ int mpi_resize(MPI a, unsigned nlimbs)
 		if (!p)
 			return -ENOMEM;
 		memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));
-		kzfree(a->d);
+		kfree_sensitive(a->d);
 		a->d = p;
 	} else {
 		a->d = kcalloc(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL);
@@ -112,7 +112,7 @@ void mpi_free(MPI a)
 		return;
 
 	if (a->flags & 4)
-		kzfree(a->d);
+		kfree_sensitive(a->d);
 	else
 		mpi_free_limb_space(a->d);
 
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index dc2c6a51d11a..e4d9a86b174b 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -766,15 +766,15 @@ static noinline void __init kmalloc_double_kzfree(void)
 	char *ptr;
 	size_t size = 16;
 
-	pr_info("double-free (kzfree)\n");
+	pr_info("double-free (kfree_sensitive)\n");
 	ptr = kmalloc(size, GFP_KERNEL);
 	if (!ptr) {
 		pr_err("Allocation failed\n");
 		return;
 	}
 
-	kzfree(ptr);
-	kzfree(ptr);
+	kfree_sensitive(ptr);
+	kfree_sensitive(ptr);
 }
 
 #ifdef CONFIG_KASAN_VMALLOC
diff --git a/mm/slab_common.c b/mm/slab_common.c
index fe8b68482670..f47a097bb4b8 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1729,17 +1729,17 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags)
 EXPORT_SYMBOL(krealloc);
 
 /**
- * kzfree - like kfree but zero memory
+ * kfree_sensitive - Clear sensitive information in memory before freeing
  * @p: object to free memory of
  *
  * The memory of the object @p points to is zeroed before freed.
- * If @p is %NULL, kzfree() does nothing.
+ * If @p is %NULL, kfree_sensitive() does nothing.
  *
  * Note: this function zeroes the whole allocated buffer which can be a good
  * deal bigger than the requested buffer size passed to kmalloc(). So be
  * careful when using this function in performance sensitive code.
  */
-void kzfree(const void *p)
+void kfree_sensitive(const void *p)
 {
 	size_t ks;
 	void *mem = (void *)p;
@@ -1750,7 +1750,7 @@ void kzfree(const void *p)
 	memzero_explicit(mem, ks);
 	kfree(mem);
 }
-EXPORT_SYMBOL(kzfree);
+EXPORT_SYMBOL(kfree_sensitive);
 
 /**
  * ksize - get the actual amount of memory allocated for a given object
diff --git a/net/atm/mpoa_caches.c b/net/atm/mpoa_caches.c
index 3286f9d527d3..f7a2f0e41105 100644
--- a/net/atm/mpoa_caches.c
+++ b/net/atm/mpoa_caches.c
@@ -180,7 +180,7 @@ static int cache_hit(in_cache_entry *entry, struct mpoa_client *mpc)
 static void in_cache_put(in_cache_entry *entry)
 {
 	if (refcount_dec_and_test(&entry->use)) {
-		kzfree(entry);
+		kfree_sensitive(entry);
 	}
 }
 
@@ -415,7 +415,7 @@ static eg_cache_entry *eg_cache_get_by_src_ip(__be32 ipaddr,
 static void eg_cache_put(eg_cache_entry *entry)
 {
 	if (refcount_dec_and_test(&entry->use)) {
-		kzfree(entry);
+		kfree_sensitive(entry);
 	}
 }
 
diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c
index 2155ce802877..3226fe02e875 100644
--- a/net/bluetooth/ecdh_helper.c
+++ b/net/bluetooth/ecdh_helper.c
@@ -104,7 +104,7 @@ int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 public_key[64],
 free_all:
 	kpp_request_free(req);
 free_tmp:
-	kzfree(tmp);
+	kfree_sensitive(tmp);
 	return err;
 }
 
@@ -151,9 +151,9 @@ int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32])
 	err = crypto_kpp_set_secret(tfm, buf, buf_len);
 	/* fall through */
 free_all:
-	kzfree(buf);
+	kfree_sensitive(buf);
 free_tmp:
-	kzfree(tmp);
+	kfree_sensitive(tmp);
 	return err;
 }
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 433227f96c73..bf4bef13d935 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -753,9 +753,9 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 	complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags);
 	mgmt_smp_complete(hcon, complete);
 
-	kzfree(smp->csrk);
-	kzfree(smp->slave_csrk);
-	kzfree(smp->link_key);
+	kfree_sensitive(smp->csrk);
+	kfree_sensitive(smp->slave_csrk);
+	kfree_sensitive(smp->link_key);
 
 	crypto_free_shash(smp->tfm_cmac);
 	crypto_free_kpp(smp->tfm_ecdh);
@@ -789,7 +789,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 	}
 
 	chan->data = NULL;
-	kzfree(smp);
+	kfree_sensitive(smp);
 	hci_conn_drop(hcon);
 }
 
@@ -1156,7 +1156,7 @@ static void sc_generate_link_key(struct smp_chan *smp)
 		const u8 salt[16] = { 0x31, 0x70, 0x6d, 0x74 };
 
 		if (smp_h7(smp->tfm_cmac, smp->tk, salt, smp->link_key)) {
-			kzfree(smp->link_key);
+			kfree_sensitive(smp->link_key);
 			smp->link_key = NULL;
 			return;
 		}
@@ -1165,14 +1165,14 @@ static void sc_generate_link_key(struct smp_chan *smp)
 		const u8 tmp1[4] = { 0x31, 0x70, 0x6d, 0x74 };
 
 		if (smp_h6(smp->tfm_cmac, smp->tk, tmp1, smp->link_key)) {
-			kzfree(smp->link_key);
+			kfree_sensitive(smp->link_key);
 			smp->link_key = NULL;
 			return;
 		}
 	}
 
 	if (smp_h6(smp->tfm_cmac, smp->link_key, lebr, smp->link_key)) {
-		kzfree(smp->link_key);
+		kfree_sensitive(smp->link_key);
 		smp->link_key = NULL;
 		return;
 	}
@@ -1407,7 +1407,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 free_shash:
 	crypto_free_shash(smp->tfm_cmac);
 zfree_smp:
-	kzfree(smp);
+	kfree_sensitive(smp);
 	return NULL;
 }
 
@@ -3278,7 +3278,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 	tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
 	if (IS_ERR(tfm_cmac)) {
 		BT_ERR("Unable to create CMAC crypto context");
-		kzfree(smp);
+		kfree_sensitive(smp);
 		return ERR_CAST(tfm_cmac);
 	}
 
@@ -3286,7 +3286,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 	if (IS_ERR(tfm_ecdh)) {
 		BT_ERR("Unable to create ECDH crypto context");
 		crypto_free_shash(tfm_cmac);
-		kzfree(smp);
+		kfree_sensitive(smp);
 		return ERR_CAST(tfm_ecdh);
 	}
 
@@ -3300,7 +3300,7 @@ create_chan:
 		if (smp) {
 			crypto_free_shash(smp->tfm_cmac);
 			crypto_free_kpp(smp->tfm_ecdh);
-			kzfree(smp);
+			kfree_sensitive(smp);
 		}
 		return ERR_PTR(-ENOMEM);
 	}
@@ -3347,7 +3347,7 @@ static void smp_del_chan(struct l2cap_chan *chan)
 		chan->data = NULL;
 		crypto_free_shash(smp->tfm_cmac);
 		crypto_free_kpp(smp->tfm_ecdh);
-		kzfree(smp);
+		kfree_sensitive(smp);
 	}
 
 	l2cap_chan_put(chan);
diff --git a/net/core/sock.c b/net/core/sock.c
index 49cd5ffe673e..9d8b15bfd192 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2257,7 +2257,7 @@ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
 	if (WARN_ON_ONCE(!mem))
 		return;
 	if (nullify)
-		kzfree(mem);
+		kfree_sensitive(mem);
 	else
 		kfree(mem);
 	atomic_sub(size, &sk->sk_omem_alloc);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 19ad9586c720..c1a54f3d58f5 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -38,7 +38,7 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
 	struct tcp_fastopen_context *ctx =
 	    container_of(head, struct tcp_fastopen_context, rcu);
 
-	kzfree(ctx);
+	kfree_sensitive(ctx);
 }
 
 void tcp_fastopen_destroy_cipher(struct sock *sk)
diff --git a/net/mac80211/aead_api.c b/net/mac80211/aead_api.c
index c5fe95e49c68..d7b3d905d535 100644
--- a/net/mac80211/aead_api.c
+++ b/net/mac80211/aead_api.c
@@ -41,7 +41,7 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
 	aead_request_set_ad(aead_req, sg[0].length);
 
 	crypto_aead_encrypt(aead_req);
-	kzfree(aead_req);
+	kfree_sensitive(aead_req);
 
 	return 0;
 }
@@ -76,7 +76,7 @@ int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
 	aead_request_set_ad(aead_req, sg[0].length);
 
 	err = crypto_aead_decrypt(aead_req);
-	kzfree(aead_req);
+	kfree_sensitive(aead_req);
 
 	return err;
 }
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
index 16ba09cb5def..6f3b3a0cc10a 100644
--- a/net/mac80211/aes_gmac.c
+++ b/net/mac80211/aes_gmac.c
@@ -60,7 +60,7 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 	aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len);
 
 	crypto_aead_encrypt(aead_req);
-	kzfree(aead_req);
+	kfree_sensitive(aead_req);
 
 	return 0;
 }
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 9c2888004878..2df636c32432 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -732,7 +732,7 @@ static void ieee80211_key_free_common(struct ieee80211_key *key)
 		ieee80211_aes_gcm_key_free(key->u.gcmp.tfm);
 		break;
 	}
-	kzfree(key);
+	kfree_sensitive(key);
 }
 
 static void __ieee80211_key_destroy(struct ieee80211_key *key,
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index c079ee69d3d0..585d33144c33 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -49,7 +49,7 @@ void mac802154_llsec_destroy(struct mac802154_llsec *sec)
 
 		msl = container_of(sl, struct mac802154_llsec_seclevel, level);
 		list_del(&sl->list);
-		kzfree(msl);
+		kfree_sensitive(msl);
 	}
 
 	list_for_each_entry_safe(dev, dn, &sec->table.devices, list) {
@@ -66,7 +66,7 @@ void mac802154_llsec_destroy(struct mac802154_llsec *sec)
 		mkey = container_of(key->key, struct mac802154_llsec_key, key);
 		list_del(&key->list);
 		llsec_key_put(mkey);
-		kzfree(key);
+		kfree_sensitive(key);
 	}
 }
 
@@ -155,7 +155,7 @@ err_tfm:
 		if (key->tfm[i])
 			crypto_free_aead(key->tfm[i]);
 
-	kzfree(key);
+	kfree_sensitive(key);
 	return NULL;
 }
 
@@ -170,7 +170,7 @@ static void llsec_key_release(struct kref *ref)
 		crypto_free_aead(key->tfm[i]);
 
 	crypto_free_sync_skcipher(key->tfm0);
-	kzfree(key);
+	kfree_sensitive(key);
 }
 
 static struct mac802154_llsec_key*
@@ -261,7 +261,7 @@ int mac802154_llsec_key_add(struct mac802154_llsec *sec,
 	return 0;
 
 fail:
-	kzfree(new);
+	kfree_sensitive(new);
 	return -ENOMEM;
 }
 
@@ -341,10 +341,10 @@ static void llsec_dev_free(struct mac802154_llsec_device *dev)
 				      devkey);
 
 		list_del(&pos->list);
-		kzfree(devkey);
+		kfree_sensitive(devkey);
 	}
 
-	kzfree(dev);
+	kfree_sensitive(dev);
 }
 
 int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
@@ -682,7 +682,7 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 
 	rc = crypto_aead_encrypt(req);
 
-	kzfree(req);
+	kfree_sensitive(req);
 
 	return rc;
 }
@@ -886,7 +886,7 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 
 	rc = crypto_aead_decrypt(req);
 
-	kzfree(req);
+	kfree_sensitive(req);
 	skb_trim(skb, skb->len - authlen);
 
 	return rc;
@@ -926,7 +926,7 @@ llsec_update_devkey_record(struct mac802154_llsec_device *dev,
 		if (!devkey)
 			list_add_rcu(&next->devkey.list, &dev->dev.keys);
 		else
-			kzfree(next);
+			kfree_sensitive(next);
 
 		spin_unlock_bh(&dev->lock);
 	}
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 83e97e8892e0..9e289c770574 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -49,7 +49,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key)
 		return;
 
 	if (refcount_dec_and_test(&key->refcnt)) {
-		kzfree(key);
+		kfree_sensitive(key);
 		SCTP_DBG_OBJCNT_DEC(keys);
 	}
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index e7180da1fc6a..794fb3001880 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -1003,7 +1003,7 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
 	err = 0;
 
 out_err:
-	kzfree(desc);
+	kfree_sensitive(desc);
 	crypto_free_shash(hmac);
 	dprintk("%s: returning %d\n", __func__, err);
 	return err;
@@ -1079,7 +1079,7 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
 	err = 0;
 
 out_err:
-	kzfree(desc);
+	kfree_sensitive(desc);
 	crypto_free_shash(hmac);
 	dprintk("%s: returning %d\n", __func__, err);
 	return err;
diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 3b7f721c023b..726c076950c0 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -228,11 +228,11 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e,
 	ret = 0;
 
 err_free_raw:
-	kzfree(rawkey);
+	kfree_sensitive(rawkey);
 err_free_out:
-	kzfree(outblockdata);
+	kfree_sensitive(outblockdata);
 err_free_in:
-	kzfree(inblockdata);
+	kfree_sensitive(inblockdata);
 err_free_cipher:
 	crypto_free_sync_skcipher(cipher);
 err_return:
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 75b3c2e9e8f8..a84a5b289484 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -443,7 +443,7 @@ context_derive_keys_rc4(struct krb5_ctx *ctx)
 	desc->tfm = hmac;
 
 	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
-	kzfree(desc);
+	kfree_sensitive(desc);
 	if (err)
 		goto out_err_free_hmac;
 	/*
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c8c47fc72653..001bcb0f2480 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -441,7 +441,7 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
 	/* Allocate per-cpu TFM entry pointer */
 	tmp->tfm_entry = alloc_percpu(struct tipc_tfm *);
 	if (!tmp->tfm_entry) {
-		kzfree(tmp);
+		kfree_sensitive(tmp);
 		return -ENOMEM;
 	}
 
@@ -491,7 +491,7 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
 	/* Not any TFM is allocated? */
 	if (!tfm_cnt) {
 		free_percpu(tmp->tfm_entry);
-		kzfree(tmp);
+		kfree_sensitive(tmp);
 		return err;
 	}
 
@@ -545,7 +545,7 @@ static int tipc_aead_clone(struct tipc_aead **dst, struct tipc_aead *src)
 
 	aead->tfm_entry = alloc_percpu_gfp(struct tipc_tfm *, GFP_ATOMIC);
 	if (unlikely(!aead->tfm_entry)) {
-		kzfree(aead);
+		kfree_sensitive(aead);
 		return -ENOMEM;
 	}
 
@@ -1352,7 +1352,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 	/* Allocate statistic structure */
 	c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC);
 	if (!c->stats) {
-		kzfree(c);
+		kfree_sensitive(c);
 		return -ENOMEM;
 	}
 
@@ -1408,7 +1408,7 @@ void tipc_crypto_stop(struct tipc_crypto **crypto)
 	free_percpu(c->stats);
 
 	*crypto = NULL;
-	kzfree(c);
+	kfree_sensitive(c);
 }
 
 void tipc_crypto_timeout(struct tipc_crypto *rx)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 1971d7e6eb55..354b0ccbdc24 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1125,7 +1125,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync)
 	}
 
 #ifdef CONFIG_CFG80211_WEXT
-	kzfree(wdev->wext.keys);
+	kfree_sensitive(wdev->wext.keys);
 	wdev->wext.keys = NULL;
 #endif
 	/* only initialized if we have a netdev */
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index ae8fe66a9bb8..a0621bb76d8e 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -127,7 +127,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 		return -EINVAL;
 
 	if (WARN_ON(wdev->connect_keys))
-		kzfree(wdev->connect_keys);
+		kfree_sensitive(wdev->connect_keys);
 	wdev->connect_keys = connkeys;
 
 	wdev->ibss_fixed = params->channel_fixed;
@@ -161,7 +161,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 
 	ASSERT_WDEV_LOCK(wdev);
 
-	kzfree(wdev->connect_keys);
+	kfree_sensitive(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 
 	rdev_set_qos_map(rdev, dev, NULL);
diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index f5e842ba7673..1b4d6c87a5c5 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -131,7 +131,7 @@ static void lib80211_tkip_deinit(void *priv)
 		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_shash(_priv->rx_tfm_michael);
 	}
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 static inline u16 RotR1(u16 val)
diff --git a/net/wireless/lib80211_crypt_wep.c b/net/wireless/lib80211_crypt_wep.c
index dafc6f3571db..6ab9957b8f96 100644
--- a/net/wireless/lib80211_crypt_wep.c
+++ b/net/wireless/lib80211_crypt_wep.c
@@ -56,7 +56,7 @@ static void *lib80211_wep_init(int keyidx)
 
 static void lib80211_wep_deinit(void *priv)
 {
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 /* Add WEP IV/key info to a frame that has at least 4 bytes of headroom */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 814e23d3ce7c..c04fc6cf6583 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9836,7 +9836,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 
 		if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) &&
 		    no_ht) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return -EINVAL;
 		}
 	}
@@ -9848,7 +9848,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		int r = validate_pae_over_nl80211(rdev, info);
 
 		if (r < 0) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return r;
 		}
 
@@ -9861,7 +9861,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	wdev_lock(dev->ieee80211_ptr);
 	err = __cfg80211_join_ibss(rdev, dev, &ibss, connkeys);
 	if (err)
-		kzfree(connkeys);
+		kfree_sensitive(connkeys);
 	else if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
 		dev->ieee80211_ptr->conn_owner_nlportid = info->snd_portid;
 	wdev_unlock(dev->ieee80211_ptr);
@@ -10289,7 +10289,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_HT_CAPABILITY]) {
 		if (!info->attrs[NL80211_ATTR_HT_CAPABILITY_MASK]) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return -EINVAL;
 		}
 		memcpy(&connect.ht_capa,
@@ -10307,7 +10307,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_VHT_CAPABILITY]) {
 		if (!info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return -EINVAL;
 		}
 		memcpy(&connect.vht_capa,
@@ -10321,7 +10321,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 		       (rdev->wiphy.features & NL80211_FEATURE_QUIET)) &&
 		    !wiphy_ext_feature_isset(&rdev->wiphy,
 					     NL80211_EXT_FEATURE_RRM)) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return -EINVAL;
 		}
 		connect.flags |= ASSOC_REQ_USE_RRM;
@@ -10329,21 +10329,21 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	connect.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]);
 	if (connect.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) {
-		kzfree(connkeys);
+		kfree_sensitive(connkeys);
 		return -EOPNOTSUPP;
 	}
 
 	if (info->attrs[NL80211_ATTR_BSS_SELECT]) {
 		/* bss selection makes no sense if bssid is set */
 		if (connect.bssid) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return -EINVAL;
 		}
 
 		err = parse_bss_select(info->attrs[NL80211_ATTR_BSS_SELECT],
 				       wiphy, &connect.bss_select);
 		if (err) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			return err;
 		}
 	}
@@ -10373,13 +10373,13 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 		   info->attrs[NL80211_ATTR_FILS_ERP_REALM] ||
 		   info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] ||
 		   info->attrs[NL80211_ATTR_FILS_ERP_RRK]) {
-		kzfree(connkeys);
+		kfree_sensitive(connkeys);
 		return -EINVAL;
 	}
 
 	if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) {
 		if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
-			kzfree(connkeys);
+			kfree_sensitive(connkeys);
 			GENL_SET_ERR_MSG(info,
 					 "external auth requires connection ownership");
 			return -EINVAL;
@@ -10392,7 +10392,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 	err = cfg80211_connect(rdev, dev, &connect, connkeys,
 			       connect.prev_bssid);
 	if (err)
-		kzfree(connkeys);
+		kfree_sensitive(connkeys);
 
 	if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
 		dev->ieee80211_ptr->conn_owner_nlportid = info->snd_portid;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 15595cf401de..985f3c23f054 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -742,7 +742,7 @@ void __cfg80211_connect_result(struct net_device *dev,
 	}
 
 	if (cr->status != WLAN_STATUS_SUCCESS) {
-		kzfree(wdev->connect_keys);
+		kfree_sensitive(wdev->connect_keys);
 		wdev->connect_keys = NULL;
 		wdev->ssid_len = 0;
 		wdev->conn_owner_nlportid = 0;
@@ -1098,7 +1098,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 	wdev->current_bss = NULL;
 	wdev->ssid_len = 0;
 	wdev->conn_owner_nlportid = 0;
-	kzfree(wdev->connect_keys);
+	kfree_sensitive(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 
 	nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap);
@@ -1281,7 +1281,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev,
 
 	ASSERT_WDEV_LOCK(wdev);
 
-	kzfree(wdev->connect_keys);
+	kfree_sensitive(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 
 	wdev->conn_owner_nlportid = 0;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 26a977343c3b..dfad1c0f57ad 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -871,7 +871,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev)
 		}
 	}
 
-	kzfree(wdev->connect_keys);
+	kfree_sensitive(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 }
 
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 73fd0eae08ca..73df23570d43 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -57,7 +57,7 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev,
 	err = cfg80211_connect(rdev, wdev->netdev,
 			       &wdev->wext.connect, ck, prev_bssid);
 	if (err)
-		kzfree(ck);
+		kfree_sensitive(ck);
 
 	return err;
 }
diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci
index 3357bf4dbd7c..da80050b91ff 100644
--- a/scripts/coccinelle/free/devm_free.cocci
+++ b/scripts/coccinelle/free/devm_free.cocci
@@ -89,7 +89,7 @@ position p;
 (
  kfree@p(x)
 |
- kzfree@p(x)
+ kfree_sensitive@p(x)
 |
  krealloc@p(x, ...)
 |
@@ -112,7 +112,7 @@ position p != safe.p;
 (
 * kfree@p(x)
 |
-* kzfree@p(x)
+* kfree_sensitive@p(x)
 |
 * krealloc@p(x, ...)
 |
diff --git a/scripts/coccinelle/free/ifnullfree.cocci b/scripts/coccinelle/free/ifnullfree.cocci
index b3290c4ee239..2045391e36a0 100644
--- a/scripts/coccinelle/free/ifnullfree.cocci
+++ b/scripts/coccinelle/free/ifnullfree.cocci
@@ -21,7 +21,7 @@ expression E;
 (
   kfree(E);
 |
-  kzfree(E);
+  kfree_sensitive(E);
 |
   debugfs_remove(E);
 |
@@ -42,7 +42,7 @@ position p;
 @@
 
 * if (E != NULL)
-*	\(kfree@p\|kzfree@p\|debugfs_remove@p\|debugfs_remove_recursive@p\|
+*	\(kfree@p\|kfree_sensitive@p\|debugfs_remove@p\|debugfs_remove_recursive@p\|
 *         usb_free_urb@p\|kmem_cache_destroy@p\|mempool_destroy@p\|
 *         dma_pool_destroy@p\)(E);
 
diff --git a/scripts/coccinelle/free/kfree.cocci b/scripts/coccinelle/free/kfree.cocci
index e9d50e718e46..168568386034 100644
--- a/scripts/coccinelle/free/kfree.cocci
+++ b/scripts/coccinelle/free/kfree.cocci
@@ -24,7 +24,7 @@ position p1;
 (
 * kfree@p1(E)
 |
-* kzfree@p1(E)
+* kfree_sensitive@p1(E)
 )
 
 @print expression@
@@ -68,7 +68,7 @@ while (1) { ...
 (
 * kfree@ok(E)
 |
-* kzfree@ok(E)
+* kfree_sensitive@ok(E)
 )
   ... when != break;
       when != goto l;
@@ -86,7 +86,7 @@ position free.p1!=loop.ok,p2!={print.p,sz.p};
 (
 * kfree@p1(E,...)
 |
-* kzfree@p1(E,...)
+* kfree_sensitive@p1(E,...)
 )
 ...
 (
diff --git a/scripts/coccinelle/free/kfreeaddr.cocci b/scripts/coccinelle/free/kfreeaddr.cocci
index cfaf308328d8..142af6337a04 100644
--- a/scripts/coccinelle/free/kfreeaddr.cocci
+++ b/scripts/coccinelle/free/kfreeaddr.cocci
@@ -20,7 +20,7 @@ position p;
 (
 * kfree@p(&e->f)
 |
-* kzfree@p(&e->f)
+* kfree_sensitive@p(&e->f)
 )
 
 @script:python depends on org@
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 1c898055a476..7b0e13ce7dc7 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -40,8 +40,8 @@ void aa_free_domain_entries(struct aa_domain *domain)
 			return;
 
 		for (i = 0; i < domain->size; i++)
-			kzfree(domain->table[i]);
-		kzfree(domain->table);
+			kfree_sensitive(domain->table[i]);
+		kfree_sensitive(domain->table);
 		domain->table = NULL;
 	}
 }
diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h
index aff26fc71407..d4f8948517d9 100644
--- a/security/apparmor/include/file.h
+++ b/security/apparmor/include/file.h
@@ -72,7 +72,7 @@ static inline void aa_free_file_ctx(struct aa_file_ctx *ctx)
 {
 	if (ctx) {
 		aa_put_label(rcu_access_pointer(ctx->label));
-		kzfree(ctx);
+		kfree_sensitive(ctx);
 	}
 }
 
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index af4f50fda9e3..4c010c9a6af1 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -187,9 +187,9 @@ static void aa_free_data(void *ptr, void *arg)
 {
 	struct aa_data *data = ptr;
 
-	kzfree(data->data);
-	kzfree(data->key);
-	kzfree(data);
+	kfree_sensitive(data->data);
+	kfree_sensitive(data->key);
+	kfree_sensitive(data);
 }
 
 /**
@@ -217,19 +217,19 @@ void aa_free_profile(struct aa_profile *profile)
 	aa_put_profile(rcu_access_pointer(profile->parent));
 
 	aa_put_ns(profile->ns);
-	kzfree(profile->rename);
+	kfree_sensitive(profile->rename);
 
 	aa_free_file_rules(&profile->file);
 	aa_free_cap_rules(&profile->caps);
 	aa_free_rlimit_rules(&profile->rlimits);
 
 	for (i = 0; i < profile->xattr_count; i++)
-		kzfree(profile->xattrs[i]);
-	kzfree(profile->xattrs);
+		kfree_sensitive(profile->xattrs[i]);
+	kfree_sensitive(profile->xattrs);
 	for (i = 0; i < profile->secmark_count; i++)
-		kzfree(profile->secmark[i].label);
-	kzfree(profile->secmark);
-	kzfree(profile->dirname);
+		kfree_sensitive(profile->secmark[i].label);
+	kfree_sensitive(profile->secmark);
+	kfree_sensitive(profile->dirname);
 	aa_put_dfa(profile->xmatch);
 	aa_put_dfa(profile->policy.dfa);
 
@@ -237,14 +237,14 @@ void aa_free_profile(struct aa_profile *profile)
 		rht = profile->data;
 		profile->data = NULL;
 		rhashtable_free_and_destroy(rht, aa_free_data, NULL);
-		kzfree(rht);
+		kfree_sensitive(rht);
 	}
 
-	kzfree(profile->hash);
+	kfree_sensitive(profile->hash);
 	aa_put_loaddata(profile->rawdata);
 	aa_label_destroy(&profile->label);
 
-	kzfree(profile);
+	kfree_sensitive(profile);
 }
 
 /**
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
index d7ef540027a5..70921d95fb40 100644
--- a/security/apparmor/policy_ns.c
+++ b/security/apparmor/policy_ns.c
@@ -121,9 +121,9 @@ static struct aa_ns *alloc_ns(const char *prefix, const char *name)
 	return ns;
 
 fail_unconfined:
-	kzfree(ns->base.hname);
+	kfree_sensitive(ns->base.hname);
 fail_ns:
-	kzfree(ns);
+	kfree_sensitive(ns);
 	return NULL;
 }
 
@@ -145,7 +145,7 @@ void aa_free_ns(struct aa_ns *ns)
 
 	ns->unconfined->ns = NULL;
 	aa_free_profile(ns->unconfined);
-	kzfree(ns);
+	kfree_sensitive(ns);
 }
 
 /**
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index b67322abcc33..dc345ac93205 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -163,10 +163,10 @@ static void do_loaddata_free(struct work_struct *work)
 		aa_put_ns(ns);
 	}
 
-	kzfree(d->hash);
-	kzfree(d->name);
+	kfree_sensitive(d->hash);
+	kfree_sensitive(d->name);
 	kvfree(d->data);
-	kzfree(d);
+	kfree_sensitive(d);
 }
 
 void aa_loaddata_kref(struct kref *kref)
@@ -894,7 +894,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 		while (unpack_strdup(e, &key, NULL)) {
 			data = kzalloc(sizeof(*data), GFP_KERNEL);
 			if (!data) {
-				kzfree(key);
+				kfree_sensitive(key);
 				goto fail;
 			}
 
@@ -902,8 +902,8 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 			data->size = unpack_blob(e, &data->data, NULL);
 			data->data = kvmemdup(data->data, data->size);
 			if (data->size && !data->data) {
-				kzfree(data->key);
-				kzfree(data);
+				kfree_sensitive(data->key);
+				kfree_sensitive(data);
 				goto fail;
 			}
 
@@ -1037,7 +1037,7 @@ void aa_load_ent_free(struct aa_load_ent *ent)
 		aa_put_profile(ent->old);
 		aa_put_profile(ent->new);
 		kfree(ent->ns_name);
-		kzfree(ent);
+		kfree_sensitive(ent);
 	}
 }
 
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index dd708e8f13c0..691347dea3c1 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -138,7 +138,7 @@ int big_key_preparse(struct key_preparsed_payload *prep)
 err_fput:
 	fput(file);
 err_enckey:
-	kzfree(enckey);
+	kfree_sensitive(enckey);
 error:
 	memzero_explicit(buf, enclen);
 	kvfree(buf);
@@ -155,7 +155,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep)
 
 		path_put(path);
 	}
-	kzfree(prep->payload.data[big_key_data]);
+	kfree_sensitive(prep->payload.data[big_key_data]);
 }
 
 /*
@@ -187,7 +187,7 @@ void big_key_destroy(struct key *key)
 		path->mnt = NULL;
 		path->dentry = NULL;
 	}
-	kzfree(key->payload.data[big_key_data]);
+	kfree_sensitive(key->payload.data[big_key_data]);
 	key->payload.data[big_key_data] = NULL;
 }
 
diff --git a/security/keys/dh.c b/security/keys/dh.c
index c4c629bb1c03..1abfa70ed6e1 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -58,9 +58,9 @@ error:
 
 static void dh_free_data(struct dh *dh)
 {
-	kzfree(dh->key);
-	kzfree(dh->p);
-	kzfree(dh->g);
+	kfree_sensitive(dh->key);
+	kfree_sensitive(dh->p);
+	kfree_sensitive(dh->g);
 }
 
 struct dh_completion {
@@ -126,7 +126,7 @@ static void kdf_dealloc(struct kdf_sdesc *sdesc)
 	if (sdesc->shash.tfm)
 		crypto_free_shash(sdesc->shash.tfm);
 
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 }
 
 /*
@@ -220,7 +220,7 @@ static int keyctl_dh_compute_kdf(struct kdf_sdesc *sdesc,
 		ret = -EFAULT;
 
 err:
-	kzfree(outbuf);
+	kfree_sensitive(outbuf);
 	return ret;
 }
 
@@ -395,11 +395,11 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params,
 out6:
 	kpp_request_free(req);
 out5:
-	kzfree(outbuf);
+	kfree_sensitive(outbuf);
 out4:
 	crypto_free_kpp(tfm);
 out3:
-	kzfree(secret);
+	kfree_sensitive(secret);
 out2:
 	dh_free_data(&dh_inputs);
 out1:
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 14cf81d1a30b..deebbf14eeca 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -370,7 +370,7 @@ static int get_derived_key(u8 *derived_key, enum derived_key_type key_type,
 	       master_keylen);
 	ret = crypto_shash_tfm_digest(hash_tfm, derived_buf, derived_buf_len,
 				      derived_key);
-	kzfree(derived_buf);
+	kfree_sensitive(derived_buf);
 	return ret;
 }
 
@@ -812,13 +812,13 @@ static int encrypted_instantiate(struct key *key,
 	ret = encrypted_init(epayload, key->description, format, master_desc,
 			     decrypted_datalen, hex_encoded_iv);
 	if (ret < 0) {
-		kzfree(epayload);
+		kfree_sensitive(epayload);
 		goto out;
 	}
 
 	rcu_assign_keypointer(key, epayload);
 out:
-	kzfree(datablob);
+	kfree_sensitive(datablob);
 	return ret;
 }
 
@@ -827,7 +827,7 @@ static void encrypted_rcu_free(struct rcu_head *rcu)
 	struct encrypted_key_payload *epayload;
 
 	epayload = container_of(rcu, struct encrypted_key_payload, rcu);
-	kzfree(epayload);
+	kfree_sensitive(epayload);
 }
 
 /*
@@ -885,7 +885,7 @@ static int encrypted_update(struct key *key, struct key_preparsed_payload *prep)
 	rcu_assign_keypointer(key, new_epayload);
 	call_rcu(&epayload->rcu, encrypted_rcu_free);
 out:
-	kzfree(buf);
+	kfree_sensitive(buf);
 	return ret;
 }
 
@@ -946,7 +946,7 @@ static long encrypted_read(const struct key *key, char *buffer,
 	memzero_explicit(derived_key, sizeof(derived_key));
 
 	memcpy(buffer, ascii_buf, asciiblob_len);
-	kzfree(ascii_buf);
+	kfree_sensitive(ascii_buf);
 
 	return asciiblob_len;
 out:
@@ -961,7 +961,7 @@ out:
  */
 static void encrypted_destroy(struct key *key)
 {
-	kzfree(key->payload.data[0]);
+	kfree_sensitive(key->payload.data[0]);
 }
 
 struct key_type key_type_encrypted = {
diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c
index 8001ab07e63b..b9fe02e5f84f 100644
--- a/security/keys/trusted-keys/trusted_tpm1.c
+++ b/security/keys/trusted-keys/trusted_tpm1.c
@@ -68,7 +68,7 @@ static int TSS_sha1(const unsigned char *data, unsigned int datalen,
 	}
 
 	ret = crypto_shash_digest(&sdesc->shash, data, datalen, digest);
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 	return ret;
 }
 
@@ -112,7 +112,7 @@ static int TSS_rawhmac(unsigned char *digest, const unsigned char *key,
 	if (!ret)
 		ret = crypto_shash_final(&sdesc->shash, digest);
 out:
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 	return ret;
 }
 
@@ -166,7 +166,7 @@ int TSS_authhmac(unsigned char *digest, const unsigned char *key,
 				  paramdigest, TPM_NONCE_SIZE, h1,
 				  TPM_NONCE_SIZE, h2, 1, &c, 0, 0);
 out:
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(TSS_authhmac);
@@ -251,7 +251,7 @@ int TSS_checkhmac1(unsigned char *buffer,
 	if (memcmp(testhmac, authdata, SHA1_DIGEST_SIZE))
 		ret = -EINVAL;
 out:
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(TSS_checkhmac1);
@@ -353,7 +353,7 @@ static int TSS_checkhmac2(unsigned char *buffer,
 	if (memcmp(testhmac2, authdata2, SHA1_DIGEST_SIZE))
 		ret = -EINVAL;
 out:
-	kzfree(sdesc);
+	kfree_sensitive(sdesc);
 	return ret;
 }
 
@@ -563,7 +563,7 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype,
 		*bloblen = storedsize;
 	}
 out:
-	kzfree(td);
+	kfree_sensitive(td);
 	return ret;
 }
 
@@ -1031,12 +1031,12 @@ static int trusted_instantiate(struct key *key,
 	if (!ret && options->pcrlock)
 		ret = pcrlock(options->pcrlock);
 out:
-	kzfree(datablob);
-	kzfree(options);
+	kfree_sensitive(datablob);
+	kfree_sensitive(options);
 	if (!ret)
 		rcu_assign_keypointer(key, payload);
 	else
-		kzfree(payload);
+		kfree_sensitive(payload);
 	return ret;
 }
 
@@ -1045,7 +1045,7 @@ static void trusted_rcu_free(struct rcu_head *rcu)
 	struct trusted_key_payload *p;
 
 	p = container_of(rcu, struct trusted_key_payload, rcu);
-	kzfree(p);
+	kfree_sensitive(p);
 }
 
 /*
@@ -1087,13 +1087,13 @@ static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 	ret = datablob_parse(datablob, new_p, new_o);
 	if (ret != Opt_update) {
 		ret = -EINVAL;
-		kzfree(new_p);
+		kfree_sensitive(new_p);
 		goto out;
 	}
 
 	if (!new_o->keyhandle) {
 		ret = -EINVAL;
-		kzfree(new_p);
+		kfree_sensitive(new_p);
 		goto out;
 	}
 
@@ -1107,22 +1107,22 @@ static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 	ret = key_seal(new_p, new_o);
 	if (ret < 0) {
 		pr_info("trusted_key: key_seal failed (%d)\n", ret);
-		kzfree(new_p);
+		kfree_sensitive(new_p);
 		goto out;
 	}
 	if (new_o->pcrlock) {
 		ret = pcrlock(new_o->pcrlock);
 		if (ret < 0) {
 			pr_info("trusted_key: pcrlock failed (%d)\n", ret);
-			kzfree(new_p);
+			kfree_sensitive(new_p);
 			goto out;
 		}
 	}
 	rcu_assign_keypointer(key, new_p);
 	call_rcu(&p->rcu, trusted_rcu_free);
 out:
-	kzfree(datablob);
-	kzfree(new_o);
+	kfree_sensitive(datablob);
+	kfree_sensitive(new_o);
 	return ret;
 }
 
@@ -1154,7 +1154,7 @@ static long trusted_read(const struct key *key, char *buffer,
  */
 static void trusted_destroy(struct key *key)
 {
-	kzfree(key->payload.data[0]);
+	kfree_sensitive(key->payload.data[0]);
 }
 
 struct key_type key_type_trusted = {
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 07d4287e9084..749e2a4dcb13 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -82,7 +82,7 @@ EXPORT_SYMBOL_GPL(user_preparse);
  */
 void user_free_preparse(struct key_preparsed_payload *prep)
 {
-	kzfree(prep->payload.data[0]);
+	kfree_sensitive(prep->payload.data[0]);
 }
 EXPORT_SYMBOL_GPL(user_free_preparse);
 
@@ -91,7 +91,7 @@ static void user_free_payload_rcu(struct rcu_head *head)
 	struct user_key_payload *payload;
 
 	payload = container_of(head, struct user_key_payload, rcu);
-	kzfree(payload);
+	kfree_sensitive(payload);
 }
 
 /*
@@ -147,7 +147,7 @@ void user_destroy(struct key *key)
 {
 	struct user_key_payload *upayload = key->payload.data[0];
 
-	kzfree(upayload);
+	kfree_sensitive(upayload);
 }
 
 EXPORT_SYMBOL_GPL(user_destroy);
-- 
cgit v1.2.3


From 6dc5ea16c86f753951f53085aa04df49cf17cb50 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Thu, 6 Aug 2020 23:19:51 -0700
Subject: mm, dump_page: do not crash with bad compound_mapcount()

If a compound page is being split while dump_page() is being run on that
page, we can end up calling compound_mapcount() on a page that is no
longer compound.  This leads to a crash (already seen at least once in the
field), due to the VM_BUG_ON_PAGE() assertion inside compound_mapcount().

(The above is from Matthew Wilcox's analysis of Qian Cai's bug report.)

A similar problem is possible, via compound_pincount() instead of
compound_mapcount().

In order to avoid this kind of crash, make dump_page() slightly more
robust, by providing a pair of simpler routines that don't contain
assertions: head_mapcount() and head_pincount().

For debug tools, we don't want to go *too* far in this direction, but this
is a simple small fix, and the crash has already been seen, so it's a good
trade-off.

Reported-by: Qian Cai <cai@lca.pw>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: http://lkml.kernel.org/r/20200804214807.169256-1-jhubbard@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 14 ++++++++++++--
 mm/debug.c         |  6 +++---
 2 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc7b87310c10..303a47a9769d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -779,6 +779,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 extern void kvfree(const void *addr);
 extern void kvfree_sensitive(const void *addr, size_t len);
 
+static inline int head_mapcount(struct page *head)
+{
+	return atomic_read(compound_mapcount_ptr(head)) + 1;
+}
+
 /*
  * Mapcount of compound page as a whole, does not include mapped sub-pages.
  *
@@ -788,7 +793,7 @@ static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	page = compound_head(page);
-	return atomic_read(compound_mapcount_ptr(page)) + 1;
+	return head_mapcount(page);
 }
 
 /*
@@ -901,11 +906,16 @@ static inline bool hpage_pincount_available(struct page *page)
 	return PageCompound(page) && compound_order(page) > 1;
 }
 
+static inline int head_pincount(struct page *head)
+{
+	return atomic_read(compound_pincount_ptr(head));
+}
+
 static inline int compound_pincount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
 	page = compound_head(page);
-	return atomic_read(compound_pincount_ptr(page));
+	return head_pincount(page);
 }
 
 static inline void set_compound_order(struct page *page, unsigned int order)
diff --git a/mm/debug.c b/mm/debug.c
index 8f569db9a514..ca8d1cacdecc 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -102,12 +102,12 @@ void __dump_page(struct page *page, const char *reason)
 		if (hpage_pincount_available(page)) {
 			pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n",
 					head, compound_order(head),
-					compound_mapcount(head),
-					compound_pincount(head));
+					head_mapcount(head),
+					head_pincount(head));
 		} else {
 			pr_warn("head:%p order:%u compound_mapcount:%d\n",
 					head, compound_order(head),
-					compound_mapcount(head));
+					head_mapcount(head));
 		}
 	}
 	if (PageKsm(page))
-- 
cgit v1.2.3


From e809d5f0b5c912fe981dce738f3283b2010665f0 Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Thu, 6 Aug 2020 23:20:20 -0700
Subject: tmpfs: per-superblock i_ino support

Patch series "tmpfs: inode: Reduce risk of inum overflow", v7.

In Facebook production we are seeing heavy i_ino wraparounds on tmpfs.  On
affected tiers, in excess of 10% of hosts show multiple files with
different content and the same inode number, with some servers even having
as many as 150 duplicated inode numbers with differing file content.

This causes actual, tangible problems in production.  For example, we have
complaints from those working on remote caches that their application is
reporting cache corruptions because it uses (device, inodenum) to
establish the identity of a particular cache object, but because it's not
unique any more, the application refuses to continue and reports cache
corruption.  Even worse, sometimes applications may not even detect the
corruption but may continue anyway, causing phantom and hard to debug
behaviour.

In general, userspace applications expect that (device, inodenum) should
be enough to be uniquely point to one inode, which seems fair enough.  One
might also need to check the generation, but in this case:

1. That's not currently exposed to userspace
   (ioctl(...FS_IOC_GETVERSION...) returns ENOTTY on tmpfs);
2. Even with generation, there shouldn't be two live inodes with the
   same inode number on one device.

In order to mitigate this, we take a two-pronged approach:

1. Moving inum generation from being global to per-sb for tmpfs. This
   itself allows some reduction in i_ino churn. This works on both 64-
   and 32- bit machines.
2. Adding inode{64,32} for tmpfs. This fix is supported on machines with
   64-bit ino_t only: we allow users to mount tmpfs with a new inode64
   option that uses the full width of ino_t, or CONFIG_TMPFS_INODE64.

You can see how this compares to previous related patches which didn't
implement this per-superblock:

- https://patchwork.kernel.org/patch/11254001/
- https://patchwork.kernel.org/patch/11023915/

This patch (of 2):

get_next_ino has a number of problems:

- It uses and returns a uint, which is susceptible to become overflowed
  if a lot of volatile inodes that use get_next_ino are created.
- It's global, with no specificity per-sb or even per-filesystem. This
  means it's not that difficult to cause inode number wraparounds on a
  single device, which can result in having multiple distinct inodes
  with the same inode number.

This patch adds a per-superblock counter that mitigates the second case.
This design also allows us to later have a specific i_ino size per-device,
for example, allowing users to choose whether to use 32- or 64-bit inodes
for each tmpfs mount.  This is implemented in the next commit.

For internal shmem mounts which may be less tolerant to spinlock delays,
we implement a percpu batching scheme which only takes the stat_lock at
each batch boundary.

Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/cover.1594661218.git.chris@chrisdown.name
Link: http://lkml.kernel.org/r/1986b9d63b986f08ec07a4aa4b2275e718e47d8a.1594661218.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h       | 15 +++++++++++
 include/linux/shmem_fs.h |  2 ++
 mm/shmem.c               | 66 ++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 78 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 488c3ef93601..b1c3a14f12e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2946,6 +2946,21 @@ extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
 
+/*
+ * Userspace may rely on the the inode number being non-zero. For example, glibc
+ * simply ignores files with zero i_ino in unlink() and other places.
+ *
+ * As an additional complication, if userspace was compiled with
+ * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the
+ * lower 32 bits, so we need to check that those aren't zero explicitly. With
+ * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but
+ * better safe than sorry.
+ */
+static inline bool is_zero_ino(ino_t ino)
+{
+	return (u32)ino == 0;
+}
+
 extern void __iget(struct inode * inode);
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 7a35a6901221..eb628696ec66 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -36,6 +36,8 @@ struct shmem_sb_info {
 	unsigned char huge;	    /* Whether to try for hugepages */
 	kuid_t uid;		    /* Mount uid for root directory */
 	kgid_t gid;		    /* Mount gid for root directory */
+	ino_t next_ino;		    /* The next per-sb inode number to use */
+	ino_t __percpu *ino_batch;  /* The next per-cpu inode number to use */
 	struct mempolicy *mpol;     /* default memory policy for mappings */
 	spinlock_t shrinklist_lock;   /* Protects shrinklist */
 	struct list_head shrinklist;  /* List of shinkable inodes */
diff --git a/mm/shmem.c b/mm/shmem.c
index b2abca3f7f33..585a82d87a92 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -260,18 +260,67 @@ bool vma_is_shmem(struct vm_area_struct *vma)
 static LIST_HEAD(shmem_swaplist);
 static DEFINE_MUTEX(shmem_swaplist_mutex);
 
-static int shmem_reserve_inode(struct super_block *sb)
+/*
+ * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and
+ * produces a novel ino for the newly allocated inode.
+ *
+ * It may also be called when making a hard link to permit the space needed by
+ * each dentry. However, in that case, no new inode number is needed since that
+ * internally draws from another pool of inode numbers (currently global
+ * get_next_ino()). This case is indicated by passing NULL as inop.
+ */
+#define SHMEM_INO_BATCH 1024
+static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 {
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
-	if (sbinfo->max_inodes) {
+	ino_t ino;
+
+	if (!(sb->s_flags & SB_KERNMOUNT)) {
 		spin_lock(&sbinfo->stat_lock);
 		if (!sbinfo->free_inodes) {
 			spin_unlock(&sbinfo->stat_lock);
 			return -ENOSPC;
 		}
 		sbinfo->free_inodes--;
+		if (inop) {
+			ino = sbinfo->next_ino++;
+			if (unlikely(is_zero_ino(ino)))
+				ino = sbinfo->next_ino++;
+			if (unlikely(ino > UINT_MAX)) {
+				/*
+				 * Emulate get_next_ino uint wraparound for
+				 * compatibility
+				 */
+				ino = 1;
+			}
+			*inop = ino;
+		}
 		spin_unlock(&sbinfo->stat_lock);
+	} else if (inop) {
+		/*
+		 * __shmem_file_setup, one of our callers, is lock-free: it
+		 * doesn't hold stat_lock in shmem_reserve_inode since
+		 * max_inodes is always 0, and is called from potentially
+		 * unknown contexts. As such, use a per-cpu batched allocator
+		 * which doesn't require the per-sb stat_lock unless we are at
+		 * the batch boundary.
+		 */
+		ino_t *next_ino;
+		next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
+		ino = *next_ino;
+		if (unlikely(ino % SHMEM_INO_BATCH == 0)) {
+			spin_lock(&sbinfo->stat_lock);
+			ino = sbinfo->next_ino;
+			sbinfo->next_ino += SHMEM_INO_BATCH;
+			spin_unlock(&sbinfo->stat_lock);
+			if (unlikely(is_zero_ino(ino)))
+				ino++;
+		}
+		*inop = ino;
+		*next_ino = ++ino;
+		put_cpu();
 	}
+
 	return 0;
 }
 
@@ -2222,13 +2271,14 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	struct inode *inode;
 	struct shmem_inode_info *info;
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+	ino_t ino;
 
-	if (shmem_reserve_inode(sb))
+	if (shmem_reserve_inode(sb, &ino))
 		return NULL;
 
 	inode = new_inode(sb);
 	if (inode) {
-		inode->i_ino = get_next_ino();
+		inode->i_ino = ino;
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -2932,7 +2982,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr
 	 * first link must skip that, to get the accounting right.
 	 */
 	if (inode->i_nlink) {
-		ret = shmem_reserve_inode(inode->i_sb);
+		ret = shmem_reserve_inode(inode->i_sb, NULL);
 		if (ret)
 			goto out;
 	}
@@ -3584,6 +3634,7 @@ static void shmem_put_super(struct super_block *sb)
 {
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
 
+	free_percpu(sbinfo->ino_batch);
 	percpu_counter_destroy(&sbinfo->used_blocks);
 	mpol_put(sbinfo->mpol);
 	kfree(sbinfo);
@@ -3626,6 +3677,11 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 #endif
 	sbinfo->max_blocks = ctx->blocks;
 	sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes;
+	if (sb->s_flags & SB_KERNMOUNT) {
+		sbinfo->ino_batch = alloc_percpu(ino_t);
+		if (!sbinfo->ino_batch)
+			goto failed;
+	}
 	sbinfo->uid = ctx->uid;
 	sbinfo->gid = ctx->gid;
 	sbinfo->mode = ctx->mode;
-- 
cgit v1.2.3


From ea3271f7196c65ae5d3e1c7b3f733892c017dbd6 Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Thu, 6 Aug 2020 23:20:25 -0700
Subject: tmpfs: support 64-bit inums per-sb

The default is still set to inode32 for backwards compatibility, but
system administrators can opt in to the new 64-bit inode numbers by
either:

1. Passing inode64 on the command line when mounting, or
2. Configuring the kernel with CONFIG_TMPFS_INODE64=y

The inode64 and inode32 names are used based on existing precedent from
XFS.

[hughd@google.com: Kconfig fixes]
  Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008011928010.13320@eggly.anvils

Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/8b23758d0c66b5e2263e08baf9c4b6a7565cbd8f.1594661218.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/tmpfs.rst | 18 ++++++++++
 fs/Kconfig                          | 21 ++++++++++++
 include/linux/shmem_fs.h            |  1 +
 mm/shmem.c                          | 65 +++++++++++++++++++++++++++++++++++--
 4 files changed, 103 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/tmpfs.rst b/Documentation/filesystems/tmpfs.rst
index 4e95929301a5..c44f8b1d3cab 100644
--- a/Documentation/filesystems/tmpfs.rst
+++ b/Documentation/filesystems/tmpfs.rst
@@ -150,6 +150,22 @@ These options do not have any effect on remount. You can change these
 parameters with chmod(1), chown(1) and chgrp(1) on a mounted filesystem.
 
 
+tmpfs has a mount option to select whether it will wrap at 32- or 64-bit inode
+numbers:
+
+=======   ========================
+inode64   Use 64-bit inode numbers
+inode32   Use 32-bit inode numbers
+=======   ========================
+
+On a 32-bit kernel, inode32 is implicit, and inode64 is refused at mount time.
+On a 64-bit kernel, CONFIG_TMPFS_INODE64 sets the default.  inode64 avoids the
+possibility of multiple files with the same inode number on a single device;
+but risks glibc failing with EOVERFLOW once 33-bit inode numbers are reached -
+if a long-lived tmpfs is accessed by 32-bit applications so ancient that
+opening a file larger than 2GiB fails with EINVAL.
+
+
 So 'mount -t tmpfs -o size=10G,nr_inodes=10k,mode=700 tmpfs /mytmpfs'
 will give you tmpfs instance on /mytmpfs which can allocate 10GB
 RAM/SWAP in 10240 inodes and it is only accessible by root.
@@ -161,3 +177,5 @@ RAM/SWAP in 10240 inodes and it is only accessible by root.
    Hugh Dickins, 4 June 2007
 :Updated:
    KOSAKI Motohiro, 16 Mar 2010
+:Updated:
+   Chris Down, 13 July 2020
diff --git a/fs/Kconfig b/fs/Kconfig
index a88aa3af73c1..aa4c12282301 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -201,6 +201,27 @@ config TMPFS_XATTR
 
 	  If unsure, say N.
 
+config TMPFS_INODE64
+	bool "Use 64-bit ino_t by default in tmpfs"
+	depends on TMPFS && 64BIT
+	default n
+	help
+	  tmpfs has historically used only inode numbers as wide as an unsigned
+	  int. In some cases this can cause wraparound, potentially resulting
+	  in multiple files with the same inode number on a single device. This
+	  option makes tmpfs use the full width of ino_t by default, without
+	  needing to specify the inode64 option when mounting.
+
+	  But if a long-lived tmpfs is to be accessed by 32-bit applications so
+	  ancient that opening a file larger than 2GiB fails with EINVAL, then
+	  the INODE64 config option and inode64 mount option risk operations
+	  failing with EOVERFLOW once 33-bit inode numbers are reached.
+
+	  To override this configured default, use the inode32 or inode64
+	  option when mounting.
+
+	  If unsure, say N.
+
 config HUGETLBFS
 	bool "HugeTLB file system support"
 	depends on X86 || IA64 || SPARC64 || (S390 && 64BIT) || \
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index eb628696ec66..a5a5d1d4d7b1 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -36,6 +36,7 @@ struct shmem_sb_info {
 	unsigned char huge;	    /* Whether to try for hugepages */
 	kuid_t uid;		    /* Mount uid for root directory */
 	kgid_t gid;		    /* Mount gid for root directory */
+	bool full_inums;	    /* If i_ino should be uint or ino_t */
 	ino_t next_ino;		    /* The next per-sb inode number to use */
 	ino_t __percpu *ino_batch;  /* The next per-cpu inode number to use */
 	struct mempolicy *mpol;     /* default memory policy for mappings */
diff --git a/mm/shmem.c b/mm/shmem.c
index 585a82d87a92..c5c281893bb8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -114,11 +114,13 @@ struct shmem_options {
 	kuid_t uid;
 	kgid_t gid;
 	umode_t mode;
+	bool full_inums;
 	int huge;
 	int seen;
 #define SHMEM_SEEN_BLOCKS 1
 #define SHMEM_SEEN_INODES 2
 #define SHMEM_SEEN_HUGE 4
+#define SHMEM_SEEN_INUMS 8
 };
 
 #ifdef CONFIG_TMPFS
@@ -286,12 +288,17 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 			ino = sbinfo->next_ino++;
 			if (unlikely(is_zero_ino(ino)))
 				ino = sbinfo->next_ino++;
-			if (unlikely(ino > UINT_MAX)) {
+			if (unlikely(!sbinfo->full_inums &&
+				     ino > UINT_MAX)) {
 				/*
 				 * Emulate get_next_ino uint wraparound for
 				 * compatibility
 				 */
-				ino = 1;
+				if (IS_ENABLED(CONFIG_64BIT))
+					pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n",
+						__func__, MINOR(sb->s_dev));
+				sbinfo->next_ino = 1;
+				ino = sbinfo->next_ino++;
 			}
 			*inop = ino;
 		}
@@ -304,6 +311,10 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 		 * unknown contexts. As such, use a per-cpu batched allocator
 		 * which doesn't require the per-sb stat_lock unless we are at
 		 * the batch boundary.
+		 *
+		 * We don't need to worry about inode{32,64} since SB_KERNMOUNT
+		 * shmem mounts are not exposed to userspace, so we don't need
+		 * to worry about things like glibc compatibility.
 		 */
 		ino_t *next_ino;
 		next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
@@ -3397,6 +3408,8 @@ enum shmem_param {
 	Opt_nr_inodes,
 	Opt_size,
 	Opt_uid,
+	Opt_inode32,
+	Opt_inode64,
 };
 
 static const struct constant_table shmem_param_enums_huge[] = {
@@ -3416,6 +3429,8 @@ const struct fs_parameter_spec shmem_fs_parameters[] = {
 	fsparam_string("nr_inodes",	Opt_nr_inodes),
 	fsparam_string("size",		Opt_size),
 	fsparam_u32   ("uid",		Opt_uid),
+	fsparam_flag  ("inode32",	Opt_inode32),
+	fsparam_flag  ("inode64",	Opt_inode64),
 	{}
 };
 
@@ -3487,6 +3502,18 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
 			break;
 		}
 		goto unsupported_parameter;
+	case Opt_inode32:
+		ctx->full_inums = false;
+		ctx->seen |= SHMEM_SEEN_INUMS;
+		break;
+	case Opt_inode64:
+		if (sizeof(ino_t) < 8) {
+			return invalfc(fc,
+				       "Cannot use inode64 with <64bit inums in kernel\n");
+		}
+		ctx->full_inums = true;
+		ctx->seen |= SHMEM_SEEN_INUMS;
+		break;
 	}
 	return 0;
 
@@ -3578,8 +3605,16 @@ static int shmem_reconfigure(struct fs_context *fc)
 		}
 	}
 
+	if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums &&
+	    sbinfo->next_ino > UINT_MAX) {
+		err = "Current inum too high to switch to 32-bit inums";
+		goto out;
+	}
+
 	if (ctx->seen & SHMEM_SEEN_HUGE)
 		sbinfo->huge = ctx->huge;
+	if (ctx->seen & SHMEM_SEEN_INUMS)
+		sbinfo->full_inums = ctx->full_inums;
 	if (ctx->seen & SHMEM_SEEN_BLOCKS)
 		sbinfo->max_blocks  = ctx->blocks;
 	if (ctx->seen & SHMEM_SEEN_INODES) {
@@ -3619,6 +3654,29 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 	if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
 		seq_printf(seq, ",gid=%u",
 				from_kgid_munged(&init_user_ns, sbinfo->gid));
+
+	/*
+	 * Showing inode{64,32} might be useful even if it's the system default,
+	 * since then people don't have to resort to checking both here and
+	 * /proc/config.gz to confirm 64-bit inums were successfully applied
+	 * (which may not even exist if IKCONFIG_PROC isn't enabled).
+	 *
+	 * We hide it when inode64 isn't the default and we are using 32-bit
+	 * inodes, since that probably just means the feature isn't even under
+	 * consideration.
+	 *
+	 * As such:
+	 *
+	 *                     +-----------------+-----------------+
+	 *                     | TMPFS_INODE64=y | TMPFS_INODE64=n |
+	 *  +------------------+-----------------+-----------------+
+	 *  | full_inums=true  | show            | show            |
+	 *  | full_inums=false | show            | hide            |
+	 *  +------------------+-----------------+-----------------+
+	 *
+	 */
+	if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums)
+		seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32));
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Rightly or wrongly, show huge mount option unmasked by shmem_huge */
 	if (sbinfo->huge)
@@ -3667,6 +3725,8 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 			ctx->blocks = shmem_default_max_blocks();
 		if (!(ctx->seen & SHMEM_SEEN_INODES))
 			ctx->inodes = shmem_default_max_inodes();
+		if (!(ctx->seen & SHMEM_SEEN_INUMS))
+			ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64);
 	} else {
 		sb->s_flags |= SB_NOUSER;
 	}
@@ -3684,6 +3744,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 	}
 	sbinfo->uid = ctx->uid;
 	sbinfo->gid = ctx->gid;
+	sbinfo->full_inums = ctx->full_inums;
 	sbinfo->mode = ctx->mode;
 	sbinfo->huge = ctx->huge;
 	sbinfo->mpol = ctx->mpol;
-- 
cgit v1.2.3


From eedc4e5a142cc33fbb54f8d72b929a0e123c48c4 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:32 -0700
Subject: mm: memcg: factor out memcg- and lruvec-level changes out of
 __mod_lruvec_state()

Patch series "The new cgroup slab memory controller", v7.

The patchset moves the accounting from the page level to the object level.
It allows to share slab pages between memory cgroups.  This leads to a
significant win in the slab utilization (up to 45%) and the corresponding
drop in the total kernel memory footprint.  The reduced number of
unmovable slab pages should also have a positive effect on the memory
fragmentation.

The patchset makes the slab accounting code simpler: there is no more need
in the complicated dynamic creation and destruction of per-cgroup slab
caches, all memory cgroups use a global set of shared slab caches.  The
lifetime of slab caches is not more connected to the lifetime of memory
cgroups.

The more precise accounting does require more CPU, however in practice the
difference seems to be negligible.  We've been using the new slab
controller in Facebook production for several months with different
workloads and haven't seen any noticeable regressions.  What we've seen
were memory savings in order of 1 GB per host (it varied heavily depending
on the actual workload, size of RAM, number of CPUs, memory pressure,
etc).

The third version of the patchset added yet another step towards the
simplification of the code: sharing of slab caches between accounted and
non-accounted allocations.  It comes with significant upsides (most
noticeable, a complete elimination of dynamic slab caches creation) but
not without some regression risks, so this change sits on top of the
patchset and is not completely merged in.  So in the unlikely event of a
noticeable performance regression it can be reverted separately.

The slab memory accounting works in exactly the same way for SLAB and
SLUB.  With both allocators the new controller shows significant memory
savings, with SLUB the difference is bigger.  On my 16-core desktop
machine running Fedora 32 the size of the slab memory measured after the
start of the system was lower by 58% and 38% with SLUB and SLAB
correspondingly.

As an estimation of a potential CPU overhead, below are results of
slab_bulk_test01 test, kindly provided by Jesper D.  Brouer.  He also
helped with the evaluation of results.

The test can be found here: https://github.com/netoptimizer/prototype-kernel/
The smallest number in each row should be picked for a comparison.

SLUB-patched - bulk-API
 - SLUB-patched : bulk_quick_reuse objects=1 : 187 -  90 - 224  cycles(tsc)
 - SLUB-patched : bulk_quick_reuse objects=2 : 110 -  53 - 133  cycles(tsc)
 - SLUB-patched : bulk_quick_reuse objects=3 :  88 -  95 -  42  cycles(tsc)
 - SLUB-patched : bulk_quick_reuse objects=4 :  91 -  85 -  36  cycles(tsc)
 - SLUB-patched : bulk_quick_reuse objects=8 :  32 -  66 -  32  cycles(tsc)

SLUB-original -  bulk-API
 - SLUB-original: bulk_quick_reuse objects=1 :  87 -  87 - 142  cycles(tsc)
 - SLUB-original: bulk_quick_reuse objects=2 :  52 -  53 -  53  cycles(tsc)
 - SLUB-original: bulk_quick_reuse objects=3 :  42 -  42 -  91  cycles(tsc)
 - SLUB-original: bulk_quick_reuse objects=4 :  91 -  37 -  37  cycles(tsc)
 - SLUB-original: bulk_quick_reuse objects=8 :  31 -  79 -  76  cycles(tsc)

SLAB-patched -  bulk-API
 - SLAB-patched : bulk_quick_reuse objects=1 :  67 -  67 - 140  cycles(tsc)
 - SLAB-patched : bulk_quick_reuse objects=2 :  55 -  46 -  46  cycles(tsc)
 - SLAB-patched : bulk_quick_reuse objects=3 :  93 -  94 -  39  cycles(tsc)
 - SLAB-patched : bulk_quick_reuse objects=4 :  35 -  88 -  85  cycles(tsc)
 - SLAB-patched : bulk_quick_reuse objects=8 :  30 -  30 -  30  cycles(tsc)

SLAB-original-  bulk-API
 - SLAB-original: bulk_quick_reuse objects=1 : 143 - 136 -  67  cycles(tsc)
 - SLAB-original: bulk_quick_reuse objects=2 :  45 -  46 -  46  cycles(tsc)
 - SLAB-original: bulk_quick_reuse objects=3 :  38 -  39 -  39  cycles(tsc)
 - SLAB-original: bulk_quick_reuse objects=4 :  35 -  87 -  87  cycles(tsc)
 - SLAB-original: bulk_quick_reuse objects=8 :  29 -  66 -  30  cycles(tsc)

This patch (of 19):

To convert memcg and lruvec slab counters to bytes there must be a way to
change these counters without touching node counters.  Factor out
__mod_memcg_lruvec_state() out of __mod_lruvec_state().

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200623174037.3951353-2-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 17 +++++++++++++++++
 mm/memcontrol.c            | 43 ++++++++++++++++++++++++-------------------
 2 files changed, 41 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e77197a62809..b250f8197710 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -679,11 +679,23 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
+void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			      int val);
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
 void mod_memcg_obj_state(void *p, int idx, int val);
 
+static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
+					  enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_memcg_lruvec_state(lruvec, idx, val);
+	local_irq_restore(flags);
+}
+
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
 {
@@ -1057,6 +1069,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
+static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
+					    enum node_stat_item idx, int val)
+{
+}
+
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
 				      enum node_stat_item idx, int val)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 24892a14cc75..5863ceb310fb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -713,30 +713,13 @@ parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
 	return mem_cgroup_nodeinfo(parent, nid);
 }
 
-/**
- * __mod_lruvec_state - update lruvec memory statistics
- * @lruvec: the lruvec
- * @idx: the stat item
- * @val: delta to add to the counter, can be negative
- *
- * The lruvec is the intersection of the NUMA node and a cgroup. This
- * function updates the all three counters that are affected by a
- * change of state at this level: per-node, per-cgroup, per-lruvec.
- */
-void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
-			int val)
+void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			      int val)
 {
-	pg_data_t *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
 	long x;
 
-	/* Update node */
-	__mod_node_page_state(pgdat, idx, val);
-
-	if (mem_cgroup_disabled())
-		return;
-
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
 
@@ -748,6 +731,7 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		pg_data_t *pgdat = lruvec_pgdat(lruvec);
 		struct mem_cgroup_per_node *pi;
 
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
@@ -757,6 +741,27 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
+/**
+ * __mod_lruvec_state - update lruvec memory statistics
+ * @lruvec: the lruvec
+ * @idx: the stat item
+ * @val: delta to add to the counter, can be negative
+ *
+ * The lruvec is the intersection of the NUMA node and a cgroup. This
+ * function updates the all three counters that are affected by a
+ * change of state at this level: per-node, per-cgroup, per-lruvec.
+ */
+void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			int val)
+{
+	/* Update node */
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
+	/* Update memcg and lruvec */
+	if (!mem_cgroup_disabled())
+		__mod_memcg_lruvec_state(lruvec, idx, val);
+}
+
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 {
 	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
-- 
cgit v1.2.3


From ea426c2a7de8e575108b7cecd3374e0c15a9f25e Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:35 -0700
Subject: mm: memcg: prepare for byte-sized vmstat items

To implement per-object slab memory accounting, we need to convert slab
vmstat counters to bytes.  Actually, out of 4 levels of counters: global,
per-node, per-memcg and per-lruvec only two last levels will require
byte-sized counters.  It's because global and per-node counters will be
counting the number of slab pages, and per-memcg and per-lruvec will be
counting the amount of memory taken by charged slab objects.

Converting all vmstat counters to bytes or even all slab counters to bytes
would introduce an additional overhead.  So instead let's store global and
per-node counters in pages, and memcg and lruvec counters in bytes.

To make the API clean all access helpers (both on the read and write
sides) are dealing with bytes.

To avoid back-and-forth conversions a new flavor of read-side helpers is
introduced, which always returns values in pages: node_page_state_pages()
and global_node_page_state_pages().

Actually new helpers are just reading raw values.  Old helpers are simple
wrappers, which will complain on an attempt to read byte value, because at
the moment no one actually needs bytes.

Thanks to Johannes Weiner for the idea of having the byte-sized API on top
of the page-sized internal storage.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-3-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c    |  2 +-
 include/linux/mmzone.h | 10 ++++++++++
 include/linux/vmstat.h | 14 +++++++++++++-
 mm/memcontrol.c        | 14 ++++++++++----
 mm/vmstat.c            | 30 ++++++++++++++++++++++++++----
 5 files changed, 60 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 5b02f69769e8..e21e31359297 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -513,7 +513,7 @@ static ssize_t node_read_vmstat(struct device *dev,
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 		n += sprintf(buf+n, "%s %lu\n", node_stat_name(i),
-			     node_page_state(pgdat, i));
+			     node_page_state_pages(pgdat, i));
 
 	return n;
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f6f884970511..f16306e15b98 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,6 +206,16 @@ enum node_stat_item {
 	NR_VM_NODE_STAT_ITEMS
 };
 
+/*
+ * Returns true if the value is measured in bytes (most vmstat values are
+ * measured in pages). This defines the API part, the internal representation
+ * might be different.
+ */
+static __always_inline bool vmstat_item_in_bytes(int idx)
+{
+	return false;
+}
+
 /*
  * We do arithmetic on the LRU lists in various places in the code,
  * so it is important to keep the active lists LRU_ACTIVE higher in
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index aa961088c551..91220ace31da 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -8,6 +8,7 @@
 #include <linux/vm_event_item.h>
 #include <linux/atomic.h>
 #include <linux/static_key.h>
+#include <linux/mmdebug.h>
 
 extern int sysctl_stat_interval;
 
@@ -192,7 +193,8 @@ static inline unsigned long global_zone_page_state(enum zone_stat_item item)
 	return x;
 }
 
-static inline unsigned long global_node_page_state(enum node_stat_item item)
+static inline
+unsigned long global_node_page_state_pages(enum node_stat_item item)
 {
 	long x = atomic_long_read(&vm_node_stat[item]);
 #ifdef CONFIG_SMP
@@ -202,6 +204,13 @@ static inline unsigned long global_node_page_state(enum node_stat_item item)
 	return x;
 }
 
+static inline unsigned long global_node_page_state(enum node_stat_item item)
+{
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
+	return global_node_page_state_pages(item);
+}
+
 static inline unsigned long zone_page_state(struct zone *zone,
 					enum zone_stat_item item)
 {
@@ -242,9 +251,12 @@ extern unsigned long sum_zone_node_page_state(int node,
 extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
 extern unsigned long node_page_state(struct pglist_data *pgdat,
 						enum node_stat_item item);
+extern unsigned long node_page_state_pages(struct pglist_data *pgdat,
+					   enum node_stat_item item);
 #else
 #define sum_zone_node_page_state(node, item) global_zone_page_state(item)
 #define node_page_state(node, item) global_node_page_state(item)
+#define node_page_state_pages(node, item) global_node_page_state_pages(item)
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5863ceb310fb..61ae6658d59f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -681,13 +681,16 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
  */
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 {
-	long x;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	if (mem_cgroup_disabled())
 		return;
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
 		struct mem_cgroup *mi;
 
 		/*
@@ -718,7 +721,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
-	long x;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
@@ -729,8 +732,11 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update lruvec */
 	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
 		pg_data_t *pgdat = lruvec_pgdat(lruvec);
 		struct mem_cgroup_per_node *pi;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 3fb23a21f6dd..b171a76bfe83 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -341,6 +341,11 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
 	long x;
 	long t;
 
+	if (vmstat_item_in_bytes(item)) {
+		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
+		delta >>= PAGE_SHIFT;
+	}
+
 	x = delta + __this_cpu_read(*p);
 
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -398,6 +403,8 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	s8 v, t;
 
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
 	v = __this_cpu_inc_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v > t)) {
@@ -442,6 +449,8 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	s8 v, t;
 
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
 	v = __this_cpu_dec_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v < - t)) {
@@ -541,6 +550,11 @@ static inline void mod_node_state(struct pglist_data *pgdat,
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	long o, n, t, z;
 
+	if (vmstat_item_in_bytes(item)) {
+		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
+		delta >>= PAGE_SHIFT;
+	}
+
 	do {
 		z = 0;  /* overflow to node counters */
 
@@ -989,8 +1003,8 @@ unsigned long sum_zone_numa_state(int node,
 /*
  * Determine the per node value of a stat item.
  */
-unsigned long node_page_state(struct pglist_data *pgdat,
-				enum node_stat_item item)
+unsigned long node_page_state_pages(struct pglist_data *pgdat,
+				    enum node_stat_item item)
 {
 	long x = atomic_long_read(&pgdat->vm_stat[item]);
 #ifdef CONFIG_SMP
@@ -999,6 +1013,14 @@ unsigned long node_page_state(struct pglist_data *pgdat,
 #endif
 	return x;
 }
+
+unsigned long node_page_state(struct pglist_data *pgdat,
+			      enum node_stat_item item)
+{
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
+	return node_page_state_pages(pgdat, item);
+}
 #endif
 
 #ifdef CONFIG_COMPACTION
@@ -1577,7 +1599,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		seq_printf(m, "\n  per-node stats");
 		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
 			seq_printf(m, "\n      %-12s %lu", node_stat_name(i),
-				   node_page_state(pgdat, i));
+				   node_page_state_pages(pgdat, i));
 		}
 	}
 	seq_printf(m,
@@ -1698,7 +1720,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 #endif
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-		v[i] = global_node_page_state(i);
+		v[i] = global_node_page_state_pages(i);
 	v += NR_VM_NODE_STAT_ITEMS;
 
 	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
-- 
cgit v1.2.3


From d42f3245c7e299e017213fa028c319316bcdb7f4 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:39 -0700
Subject: mm: memcg: convert vmstat slab counters to bytes

In order to prepare for per-object slab memory accounting, convert
NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE vmstat items to bytes.

To make it obvious, rename them to NR_SLAB_RECLAIMABLE_B and
NR_SLAB_UNRECLAIMABLE_B (similar to NR_KERNEL_STACK_KB).

Internally global and per-node counters are stored in pages, however memcg
and lruvec counters are stored in bytes.  This scheme may look weird, but
only for now.  As soon as slab pages will be shared between multiple
cgroups, global and node counters will reflect the total number of slab
pages.  However memcg and lruvec counters will be used for per-memcg slab
memory tracking, which will take separate kernel objects in the account.
Keeping global and node counters in pages helps to avoid additional
overhead.

The size of slab memory shouldn't exceed 4Gb on 32-bit machines, so it
will fit into atomic_long_t we use for vmstats.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c     |  4 ++--
 fs/proc/meminfo.c       |  4 ++--
 include/linux/mmzone.h  | 16 +++++++++++++---
 kernel/power/snapshot.c |  2 +-
 mm/memcontrol.c         | 11 ++++-------
 mm/oom_kill.c           |  2 +-
 mm/page_alloc.c         |  8 ++++----
 mm/slab.h               | 15 ++++++++-------
 mm/slab_common.c        |  4 ++--
 mm/slob.c               | 12 ++++++------
 mm/slub.c               |  8 ++++----
 mm/vmscan.c             |  3 ++-
 mm/workingset.c         |  6 ++++--
 13 files changed, 53 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index e21e31359297..0cf13e31603c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -368,8 +368,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 	unsigned long sreclaimable, sunreclaimable;
 
 	si_meminfo_node(&i, nid);
-	sreclaimable = node_page_state(pgdat, NR_SLAB_RECLAIMABLE);
-	sunreclaimable = node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE);
+	sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
+	sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B);
 	n = sprintf(buf,
 		       "Node %d MemTotal:       %8lu kB\n"
 		       "Node %d MemFree:        %8lu kB\n"
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index e9a6841fc25b..38ea95fd919a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -52,8 +52,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
 
 	available = si_mem_available();
-	sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
-	sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
+	sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B);
+	sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B);
 
 	show_val_kb(m, "MemTotal:       ", i.totalram);
 	show_val_kb(m, "MemFree:        ", i.freeram);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f16306e15b98..b79100edd228 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -174,8 +174,8 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
+	NR_SLAB_RECLAIMABLE_B,
+	NR_SLAB_UNRECLAIMABLE_B,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,
@@ -213,7 +213,17 @@ enum node_stat_item {
  */
 static __always_inline bool vmstat_item_in_bytes(int idx)
 {
-	return false;
+	/*
+	 * Global and per-node slab counters track slab pages.
+	 * It's expected that changes are multiples of PAGE_SIZE.
+	 * Internally values are stored in pages.
+	 *
+	 * Per-memcg and per-lruvec counters track memory, consumed
+	 * by individual slab objects. These counters are actually
+	 * byte-precise.
+	 */
+	return (idx == NR_SLAB_RECLAIMABLE_B ||
+		idx == NR_SLAB_UNRECLAIMABLE_B);
 }
 
 /*
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index cef154261fe2..d25749bce7cf 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1663,7 +1663,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
 {
 	unsigned long size;
 
-	size = global_node_page_state(NR_SLAB_RECLAIMABLE)
+	size = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B)
 		+ global_node_page_state(NR_ACTIVE_ANON)
 		+ global_node_page_state(NR_INACTIVE_ANON)
 		+ global_node_page_state(NR_ACTIVE_FILE)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 61ae6658d59f..328b7e7bf9ab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1391,9 +1391,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
 		       1024);
 	seq_buf_printf(&s, "slab %llu\n",
-		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
-			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
-		       PAGE_SIZE);
+		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
+			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
 	seq_buf_printf(&s, "sock %llu\n",
 		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
 		       PAGE_SIZE);
@@ -1423,11 +1422,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 			       PAGE_SIZE);
 
 	seq_buf_printf(&s, "slab_reclaimable %llu\n",
-		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
-		       PAGE_SIZE);
+		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B));
 	seq_buf_printf(&s, "slab_unreclaimable %llu\n",
-		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
-		       PAGE_SIZE);
+		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B));
 
 	/* Accumulated memory events */
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6e94962893ee..d30ce75f23fb 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -184,7 +184,7 @@ static bool is_dump_unreclaim_slabs(void)
 		 global_node_page_state(NR_ISOLATED_FILE) +
 		 global_node_page_state(NR_UNEVICTABLE);
 
-	return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
+	return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 901a21f61d68..f9ad093814d2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5220,8 +5220,8 @@ long si_mem_available(void)
 	 * items that are in use, and cannot be freed. Cap this estimate at the
 	 * low watermark.
 	 */
-	reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) +
-			global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+	reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) +
+		global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
 	available += reclaimable - min(reclaimable / 2, wmark_low);
 
 	if (available < 0)
@@ -5364,8 +5364,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state(NR_UNEVICTABLE),
 		global_node_page_state(NR_FILE_DIRTY),
 		global_node_page_state(NR_WRITEBACK),
-		global_node_page_state(NR_SLAB_RECLAIMABLE),
-		global_node_page_state(NR_SLAB_UNRECLAIMABLE),
+		global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B),
+		global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
 		global_node_page_state(NR_FILE_MAPPED),
 		global_node_page_state(NR_SHMEM),
 		global_zone_page_state(NR_PAGETABLE),
diff --git a/mm/slab.h b/mm/slab.h
index fceb4341ba91..09be3ca6fe87 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -273,7 +273,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 static inline int cache_vmstat_idx(struct kmem_cache *s)
 {
 	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE;
+		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
 }
 
 #ifdef CONFIG_SLUB_DEBUG
@@ -390,7 +390,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 
 	if (unlikely(!memcg || mem_cgroup_is_root(memcg))) {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    nr_pages);
+				    nr_pages << PAGE_SHIFT);
 		percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
 		return 0;
 	}
@@ -400,7 +400,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 		goto out;
 
 	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-	mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages);
+	mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages << PAGE_SHIFT);
 
 	/* transer try_charge() page references to kmem_cache */
 	percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
@@ -425,11 +425,12 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 	memcg = READ_ONCE(s->memcg_params.memcg);
 	if (likely(!mem_cgroup_is_root(memcg))) {
 		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-		mod_lruvec_state(lruvec, cache_vmstat_idx(s), -nr_pages);
+		mod_lruvec_state(lruvec, cache_vmstat_idx(s),
+				 -(nr_pages << PAGE_SHIFT));
 		memcg_kmem_uncharge(memcg, nr_pages);
 	} else {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -nr_pages);
+				    -(nr_pages << PAGE_SHIFT));
 	}
 	rcu_read_unlock();
 
@@ -513,7 +514,7 @@ static __always_inline int charge_slab_page(struct page *page,
 {
 	if (is_root_cache(s)) {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    1 << order);
+				    PAGE_SIZE << order);
 		return 0;
 	}
 
@@ -525,7 +526,7 @@ static __always_inline void uncharge_slab_page(struct page *page, int order,
 {
 	if (is_root_cache(s)) {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -(1 << order));
+				    -(PAGE_SIZE << order));
 		return;
 	}
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 616ec8a0d91a..a73f168b1035 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1363,8 +1363,8 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 	page = alloc_pages(flags, order);
 	if (likely(page)) {
 		ret = page_address(page);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
-				    1 << order);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+				    PAGE_SIZE << order);
 	}
 	ret = kasan_kmalloc_large(ret, size, flags);
 	/* As ret might get tagged, call kmemleak hook after KASAN. */
diff --git a/mm/slob.c b/mm/slob.c
index ac2aecfbc7a8..7cc9805c8091 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -202,8 +202,8 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 	if (!page)
 		return NULL;
 
-	mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
-			    1 << order);
+	mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+			    PAGE_SIZE << order);
 	return page_address(page);
 }
 
@@ -214,8 +214,8 @@ static void slob_free_pages(void *b, int order)
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += 1 << order;
 
-	mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
-			    -(1 << order));
+	mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+			    -(PAGE_SIZE << order));
 	__free_pages(sp, order);
 }
 
@@ -552,8 +552,8 @@ void kfree(const void *block)
 		slob_free(m, *m + align);
 	} else {
 		unsigned int order = compound_order(sp);
-		mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
-				    -(1 << order));
+		mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+				    -(PAGE_SIZE << order));
 		__free_pages(sp, order);
 
 	}
diff --git a/mm/slub.c b/mm/slub.c
index ae39eb392396..2d73d677f7ac 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3991,8 +3991,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	page = alloc_pages_node(node, flags, order);
 	if (page) {
 		ptr = page_address(page);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
-				    1 << order);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+				    PAGE_SIZE << order);
 	}
 
 	return kmalloc_large_node_hook(ptr, size, flags);
@@ -4123,8 +4123,8 @@ void kfree(const void *x)
 
 		BUG_ON(!PageCompound(page));
 		kfree_hook(object);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
-				    -(1 << order));
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+				    -(PAGE_SIZE << order));
 		__free_pages(page, order);
 		return;
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 749d239c62b2..2ac43664aba4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4222,7 +4222,8 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	 * unmapped file backed pages.
 	 */
 	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
-	    node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+	    node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
+	    pgdat->min_slab_pages)
 		return NODE_RECLAIM_FULL;
 
 	/*
diff --git a/mm/workingset.c b/mm/workingset.c
index 50b7937bab32..b199726924dd 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -486,8 +486,10 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
 							 NR_LRU_BASE + i);
-		pages += lruvec_page_state_local(lruvec, NR_SLAB_RECLAIMABLE);
-		pages += lruvec_page_state_local(lruvec, NR_SLAB_UNRECLAIMABLE);
+		pages += lruvec_page_state_local(
+			lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
+		pages += lruvec_page_state_local(
+			lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
 	} else
 #endif
 		pages = node_present_pages(sc->nid);
-- 
cgit v1.2.3


From 4138fdfc8b5db5a7a4b9b50c69d475fb2ac351b7 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:42 -0700
Subject: mm: slub: implement SLUB version of obj_to_index()

This commit implements SLUB version of the obj_to_index() function, which
will be required to calculate the offset of obj_cgroup in the obj_cgroups
vector to store/obtain the objcg ownership data.

To make it faster, let's repeat the SLAB's trick introduced by commit
6a2d7a955d8d ("SLAB: use a multiply instead of a divide in
obj_to_index()") and avoid an expensive division.

Vlastimil Babka noticed, that SLUB does have already a similar function
called slab_index(), which is defined only if SLUB_DEBUG is enabled.  The
function does a similar math, but with a division, and it also takes a
page address instead of a page pointer.

Let's remove slab_index() and replace it with the new helper
__obj_to_index(), which takes a page address.  obj_to_index() will be a
simple wrapper taking a page pointer and passing page_address(page) into
__obj_to_index().

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-5-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slub_def.h | 16 ++++++++++++++++
 mm/slub.c                | 15 +++++----------
 2 files changed, 21 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index d2153789bd9f..30e91c83d401 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -8,6 +8,7 @@
  * (C) 2007 SGI, Christoph Lameter
  */
 #include <linux/kobject.h>
+#include <linux/reciprocal_div.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
@@ -86,6 +87,7 @@ struct kmem_cache {
 	unsigned long min_partial;
 	unsigned int size;	/* The size of an object including metadata */
 	unsigned int object_size;/* The size of an object without metadata */
+	struct reciprocal_value reciprocal_size;
 	unsigned int offset;	/* Free pointer offset */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 	/* Number of per cpu partial objects to keep around */
@@ -182,4 +184,18 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
 	return result;
 }
 
+/* Determine object index from a given position */
+static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
+					  void *addr, void *obj)
+{
+	return reciprocal_divide(kasan_reset_tag(obj) - addr,
+				 cache->reciprocal_size);
+}
+
+static inline unsigned int obj_to_index(const struct kmem_cache *cache,
+					const struct page *page, void *obj)
+{
+	return __obj_to_index(cache, page_address(page), obj);
+}
+
 #endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/slub.c b/mm/slub.c
index 2d73d677f7ac..2a3075538f26 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -317,12 +317,6 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 		__p < (__addr) + (__objects) * (__s)->size; \
 		__p += (__s)->size)
 
-/* Determine object index from a given position */
-static inline unsigned int slab_index(void *p, struct kmem_cache *s, void *addr)
-{
-	return (kasan_reset_tag(p) - addr) / s->size;
-}
-
 static inline unsigned int order_objects(unsigned int order, unsigned int size)
 {
 	return ((unsigned int)PAGE_SIZE << order) / size;
@@ -465,7 +459,7 @@ static unsigned long *get_map(struct kmem_cache *s, struct page *page)
 	bitmap_zero(object_map, page->objects);
 
 	for (p = page->freelist; p; p = get_freepointer(s, p))
-		set_bit(slab_index(p, s, addr), object_map);
+		set_bit(__obj_to_index(s, addr, p), object_map);
 
 	return object_map;
 }
@@ -3754,6 +3748,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	 */
 	size = ALIGN(size, s->align);
 	s->size = size;
+	s->reciprocal_size = reciprocal_value(size);
 	if (forced_order >= 0)
 		order = forced_order;
 	else
@@ -3858,7 +3853,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
 
-		if (!test_bit(slab_index(p, s, addr), map)) {
+		if (!test_bit(__obj_to_index(s, addr, p), map)) {
 			pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr);
 			print_tracking(s, p);
 		}
@@ -4574,7 +4569,7 @@ static void validate_slab(struct kmem_cache *s, struct page *page)
 	/* Now we know that a valid freelist exists */
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
-		u8 val = test_bit(slab_index(p, s, addr), map) ?
+		u8 val = test_bit(__obj_to_index(s, addr, p), map) ?
 			 SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
 
 		if (!check_object(s, page, p, val))
@@ -4765,7 +4760,7 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects)
-		if (!test_bit(slab_index(p, s, addr), map))
+		if (!test_bit(__obj_to_index(s, addr, p), map))
 			add_location(t, s, get_track(s, p, alloc));
 	put_map(map);
 }
-- 
cgit v1.2.3


From bf4f059954dcb221384b2f784677e19a13cd4bdb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:49 -0700
Subject: mm: memcg/slab: obj_cgroup API

Obj_cgroup API provides an ability to account sub-page sized kernel
objects, which potentially outlive the original memory cgroup.

The top-level API consists of the following functions:
  bool obj_cgroup_tryget(struct obj_cgroup *objcg);
  void obj_cgroup_get(struct obj_cgroup *objcg);
  void obj_cgroup_put(struct obj_cgroup *objcg);

  int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
  void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);

  struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg);
  struct obj_cgroup *get_obj_cgroup_from_current(void);

Object cgroup is basically a pointer to a memory cgroup with a per-cpu
reference counter.  It substitutes a memory cgroup in places where it's
necessary to charge a custom amount of bytes instead of pages.

All charged memory rounded down to pages is charged to the corresponding
memory cgroup using __memcg_kmem_charge().

It implements reparenting: on memcg offlining it's getting reattached to
the parent memory cgroup.  Each online memory cgroup has an associated
active object cgroup to handle new allocations and the list of all
attached object cgroups.  On offlining of a cgroup this list is reparented
and for each object cgroup in the list the memcg pointer is swapped to the
parent memory cgroup.  It prevents long-living objects from pinning the
original memory cgroup in the memory.

The implementation is based on byte-sized per-cpu stocks.  A sub-page
sized leftover is stored in an atomic field, which is a part of obj_cgroup
object.  So on cgroup offlining the leftover is automatically reparented.

memcg->objcg is rcu protected.  objcg->memcg is a raw pointer, which is
always pointing at a memory cgroup, but can be atomically swapped to the
parent memory cgroup.  So a user must ensure the lifetime of the
cgroup, e.g.  grab rcu_read_lock or css_set_lock.

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/20200623174037.3951353-7-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  51 ++++++++
 mm/memcontrol.c            | 288 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 338 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b250f8197710..f2f9d5d6b7d1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,7 @@
 #include <linux/page-flags.h>
 
 struct mem_cgroup;
+struct obj_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
@@ -192,6 +193,22 @@ struct memcg_cgwb_frn {
 	struct wb_completion done;	/* tracks in-flight foreign writebacks */
 };
 
+/*
+ * Bucket for arbitrarily byte-sized objects charged to a memory
+ * cgroup. The bucket can be reparented in one piece when the cgroup
+ * is destroyed, without having to round up the individual references
+ * of all live memory objects in the wild.
+ */
+struct obj_cgroup {
+	struct percpu_ref refcnt;
+	struct mem_cgroup *memcg;
+	atomic_t nr_charged_bytes;
+	union {
+		struct list_head list;
+		struct rcu_head rcu;
+	};
+};
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -301,6 +318,8 @@ struct mem_cgroup {
 	int kmemcg_id;
 	enum memcg_kmem_state kmem_state;
 	struct list_head kmem_caches;
+	struct obj_cgroup __rcu *objcg;
+	struct list_head objcg_list; /* list of inherited objcgs */
 #endif
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -416,6 +435,33 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
+{
+	return percpu_ref_tryget(&objcg->refcnt);
+}
+
+static inline void obj_cgroup_get(struct obj_cgroup *objcg)
+{
+	percpu_ref_get(&objcg->refcnt);
+}
+
+static inline void obj_cgroup_put(struct obj_cgroup *objcg)
+{
+	percpu_ref_put(&objcg->refcnt);
+}
+
+/*
+ * After the initialization objcg->memcg is always pointing at
+ * a valid memcg, but can be atomically swapped to the parent memcg.
+ *
+ * The caller must ensure that the returned memcg won't be released:
+ * e.g. acquire the rcu_read_lock or css_set_lock.
+ */
+static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
+{
+	return READ_ONCE(objcg->memcg);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -1368,6 +1414,11 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
+struct obj_cgroup *get_obj_cgroup_from_current(void);
+
+int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
+void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
+
 extern struct static_key_false memcg_kmem_enabled_key;
 extern struct workqueue_struct *memcg_kmem_cache_wq;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4f9a3f55db71..1cc784556e05 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -257,6 +257,98 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+extern spinlock_t css_set_lock;
+
+static void obj_cgroup_release(struct percpu_ref *ref)
+{
+	struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
+	struct mem_cgroup *memcg;
+	unsigned int nr_bytes;
+	unsigned int nr_pages;
+	unsigned long flags;
+
+	/*
+	 * At this point all allocated objects are freed, and
+	 * objcg->nr_charged_bytes can't have an arbitrary byte value.
+	 * However, it can be PAGE_SIZE or (x * PAGE_SIZE).
+	 *
+	 * The following sequence can lead to it:
+	 * 1) CPU0: objcg == stock->cached_objcg
+	 * 2) CPU1: we do a small allocation (e.g. 92 bytes),
+	 *          PAGE_SIZE bytes are charged
+	 * 3) CPU1: a process from another memcg is allocating something,
+	 *          the stock if flushed,
+	 *          objcg->nr_charged_bytes = PAGE_SIZE - 92
+	 * 5) CPU0: we do release this object,
+	 *          92 bytes are added to stock->nr_bytes
+	 * 6) CPU0: stock is flushed,
+	 *          92 bytes are added to objcg->nr_charged_bytes
+	 *
+	 * In the result, nr_charged_bytes == PAGE_SIZE.
+	 * This page will be uncharged in obj_cgroup_release().
+	 */
+	nr_bytes = atomic_read(&objcg->nr_charged_bytes);
+	WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
+	nr_pages = nr_bytes >> PAGE_SHIFT;
+
+	spin_lock_irqsave(&css_set_lock, flags);
+	memcg = obj_cgroup_memcg(objcg);
+	if (nr_pages)
+		__memcg_kmem_uncharge(memcg, nr_pages);
+	list_del(&objcg->list);
+	mem_cgroup_put(memcg);
+	spin_unlock_irqrestore(&css_set_lock, flags);
+
+	percpu_ref_exit(ref);
+	kfree_rcu(objcg, rcu);
+}
+
+static struct obj_cgroup *obj_cgroup_alloc(void)
+{
+	struct obj_cgroup *objcg;
+	int ret;
+
+	objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
+	if (!objcg)
+		return NULL;
+
+	ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
+			      GFP_KERNEL);
+	if (ret) {
+		kfree(objcg);
+		return NULL;
+	}
+	INIT_LIST_HEAD(&objcg->list);
+	return objcg;
+}
+
+static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
+				  struct mem_cgroup *parent)
+{
+	struct obj_cgroup *objcg, *iter;
+
+	objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
+
+	spin_lock_irq(&css_set_lock);
+
+	/* Move active objcg to the parent's list */
+	xchg(&objcg->memcg, parent);
+	css_get(&parent->css);
+	list_add(&objcg->list, &parent->objcg_list);
+
+	/* Move already reparented objcgs to the parent's list */
+	list_for_each_entry(iter, &memcg->objcg_list, list) {
+		css_get(&parent->css);
+		xchg(&iter->memcg, parent);
+		css_put(&memcg->css);
+	}
+	list_splice(&memcg->objcg_list, &parent->objcg_list);
+
+	spin_unlock_irq(&css_set_lock);
+
+	percpu_ref_kill(&objcg->refcnt);
+}
+
 /*
  * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
  * The main reason for not using cgroup id for this:
@@ -2047,6 +2139,12 @@ EXPORT_SYMBOL(unlock_page_memcg);
 struct memcg_stock_pcp {
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
+
+#ifdef CONFIG_MEMCG_KMEM
+	struct obj_cgroup *cached_objcg;
+	unsigned int nr_bytes;
+#endif
+
 	struct work_struct work;
 	unsigned long flags;
 #define FLUSHING_CACHED_CHARGE	0
@@ -2054,6 +2152,22 @@ struct memcg_stock_pcp {
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
 static DEFINE_MUTEX(percpu_charge_mutex);
 
+#ifdef CONFIG_MEMCG_KMEM
+static void drain_obj_stock(struct memcg_stock_pcp *stock);
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg);
+
+#else
+static inline void drain_obj_stock(struct memcg_stock_pcp *stock)
+{
+}
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg)
+{
+	return false;
+}
+#endif
+
 /**
  * consume_stock: Try to consume stocked charge on this cpu.
  * @memcg: memcg to consume from.
@@ -2120,6 +2234,7 @@ static void drain_local_stock(struct work_struct *dummy)
 	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
+	drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
@@ -2179,6 +2294,8 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		if (memcg && stock->nr_pages &&
 		    mem_cgroup_is_descendant(memcg, root_memcg))
 			flush = true;
+		if (obj_stock_flush_required(stock, root_memcg))
+			flush = true;
 		rcu_read_unlock();
 
 		if (flush &&
@@ -2705,6 +2822,30 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	return page->mem_cgroup;
 }
 
+__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
+{
+	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg;
+
+	if (unlikely(!current->mm && !current->active_memcg))
+		return NULL;
+
+	rcu_read_lock();
+	if (unlikely(current->active_memcg))
+		memcg = rcu_dereference(current->active_memcg);
+	else
+		memcg = mem_cgroup_from_task(current);
+
+	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+		objcg = rcu_dereference(memcg->objcg);
+		if (objcg && obj_cgroup_tryget(objcg))
+			break;
+	}
+	rcu_read_unlock();
+
+	return objcg;
+}
+
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -2996,6 +3137,140 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 	if (PageKmemcg(page))
 		__ClearPageKmemcg(page);
 }
+
+static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
+{
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+	bool ret = false;
+
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
+	if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) {
+		stock->nr_bytes -= nr_bytes;
+		ret = true;
+	}
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static void drain_obj_stock(struct memcg_stock_pcp *stock)
+{
+	struct obj_cgroup *old = stock->cached_objcg;
+
+	if (!old)
+		return;
+
+	if (stock->nr_bytes) {
+		unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
+		unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
+
+		if (nr_pages) {
+			rcu_read_lock();
+			__memcg_kmem_uncharge(obj_cgroup_memcg(old), nr_pages);
+			rcu_read_unlock();
+		}
+
+		/*
+		 * The leftover is flushed to the centralized per-memcg value.
+		 * On the next attempt to refill obj stock it will be moved
+		 * to a per-cpu stock (probably, on an other CPU), see
+		 * refill_obj_stock().
+		 *
+		 * How often it's flushed is a trade-off between the memory
+		 * limit enforcement accuracy and potential CPU contention,
+		 * so it might be changed in the future.
+		 */
+		atomic_add(nr_bytes, &old->nr_charged_bytes);
+		stock->nr_bytes = 0;
+	}
+
+	obj_cgroup_put(old);
+	stock->cached_objcg = NULL;
+}
+
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg)
+{
+	struct mem_cgroup *memcg;
+
+	if (stock->cached_objcg) {
+		memcg = obj_cgroup_memcg(stock->cached_objcg);
+		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
+			return true;
+	}
+
+	return false;
+}
+
+static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
+{
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
+	if (stock->cached_objcg != objcg) { /* reset if necessary */
+		drain_obj_stock(stock);
+		obj_cgroup_get(objcg);
+		stock->cached_objcg = objcg;
+		stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0);
+	}
+	stock->nr_bytes += nr_bytes;
+
+	if (stock->nr_bytes > PAGE_SIZE)
+		drain_obj_stock(stock);
+
+	local_irq_restore(flags);
+}
+
+int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
+{
+	struct mem_cgroup *memcg;
+	unsigned int nr_pages, nr_bytes;
+	int ret;
+
+	if (consume_obj_stock(objcg, size))
+		return 0;
+
+	/*
+	 * In theory, memcg->nr_charged_bytes can have enough
+	 * pre-charged bytes to satisfy the allocation. However,
+	 * flushing memcg->nr_charged_bytes requires two atomic
+	 * operations, and memcg->nr_charged_bytes can't be big,
+	 * so it's better to ignore it and try grab some new pages.
+	 * memcg->nr_charged_bytes will be flushed in
+	 * refill_obj_stock(), called from this function or
+	 * independently later.
+	 */
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	css_get(&memcg->css);
+	rcu_read_unlock();
+
+	nr_pages = size >> PAGE_SHIFT;
+	nr_bytes = size & (PAGE_SIZE - 1);
+
+	if (nr_bytes)
+		nr_pages += 1;
+
+	ret = __memcg_kmem_charge(memcg, gfp, nr_pages);
+	if (!ret && nr_bytes)
+		refill_obj_stock(objcg, PAGE_SIZE - nr_bytes);
+
+	css_put(&memcg->css);
+	return ret;
+}
+
+void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
+{
+	refill_obj_stock(objcg, size);
+}
+
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -3416,6 +3691,7 @@ static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
+	struct obj_cgroup *objcg;
 	int memcg_id;
 
 	if (cgroup_memory_nokmem)
@@ -3428,6 +3704,14 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	if (memcg_id < 0)
 		return memcg_id;
 
+	objcg = obj_cgroup_alloc();
+	if (!objcg) {
+		memcg_free_cache_id(memcg_id);
+		return -ENOMEM;
+	}
+	objcg->memcg = memcg;
+	rcu_assign_pointer(memcg->objcg, objcg);
+
 	static_branch_enable(&memcg_kmem_enabled_key);
 
 	/*
@@ -3464,9 +3748,10 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		parent = root_mem_cgroup;
 
 	/*
-	 * Deactivate and reparent kmem_caches.
+	 * Deactivate and reparent kmem_caches and objcgs.
 	 */
 	memcg_deactivate_kmem_caches(memcg, parent);
+	memcg_reparent_objcgs(memcg, parent);
 
 	kmemcg_id = memcg->kmemcg_id;
 	BUG_ON(kmemcg_id < 0);
@@ -5030,6 +5315,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	memcg->socket_pressure = jiffies;
 #ifdef CONFIG_MEMCG_KMEM
 	memcg->kmemcg_id = -1;
+	INIT_LIST_HEAD(&memcg->objcg_list);
 #endif
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
-- 
cgit v1.2.3


From 286e04b8ed7a04279ae277f0f024430246ea5eec Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:52 -0700
Subject: mm: memcg/slab: allocate obj_cgroups for non-root slab pages

Allocate and release memory to store obj_cgroup pointers for each non-root
slab page. Reuse page->mem_cgroup pointer to store a pointer to the
allocated space.

This commit temporarily increases the memory footprint of the kernel memory
accounting. To store obj_cgroup pointers we'll need a place for an
objcg_pointer for each allocated object. However, the following patches
in the series will enable sharing of slab pages between memory cgroups,
which will dramatically increase the total slab utilization. And the final
memory footprint will be significantly smaller than before.

To distinguish between obj_cgroups and memcg pointers in case when it's
not obvious which one is used (as in page_cgroup_ino()), let's always set
the lowest bit in the obj_cgroup case. The original obj_cgroups
pointer is marked to be ignored by kmemleak, which otherwise would
report a memory leak for each allocated vector.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-8-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h |  5 ++++-
 include/linux/slab_def.h |  6 ++++++
 include/linux/slub_def.h |  5 +++++
 mm/memcontrol.c          | 17 +++++++++++++---
 mm/slab.h                | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 81 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 64ede5f150dc..0277fbab7c93 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -198,7 +198,10 @@ struct page {
 	atomic_t _refcount;
 
 #ifdef CONFIG_MEMCG
-	struct mem_cgroup *mem_cgroup;
+	union {
+		struct mem_cgroup *mem_cgroup;
+		struct obj_cgroup **obj_cgroups;
+	};
 #endif
 
 	/*
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index abc7de77b988..ccda7b9669a5 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -114,4 +114,10 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+				     const struct page *page)
+{
+	return cache->num;
+}
+
 #endif	/* _LINUX_SLAB_DEF_H */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 30e91c83d401..f87302dcfe8c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -198,4 +198,9 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return __obj_to_index(cache, page_address(page), obj);
 }
 
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+				     const struct page *page)
+{
+	return page->objects;
+}
 #endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1cc784556e05..e6cd4c0d44d1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -569,10 +569,21 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageSlab(page) && !PageTail(page))
+	if (PageSlab(page) && !PageTail(page)) {
 		memcg = memcg_from_slab_page(page);
-	else
-		memcg = READ_ONCE(page->mem_cgroup);
+	} else {
+		memcg = page->mem_cgroup;
+
+		/*
+		 * The lowest bit set means that memcg isn't a valid
+		 * memcg pointer, but a obj_cgroups pointer.
+		 * In this case the page is shared and doesn't belong
+		 * to any specific memory cgroup.
+		 */
+		if ((unsigned long) memcg & 0x1UL)
+			memcg = NULL;
+	}
+
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
 	if (memcg)
diff --git a/mm/slab.h b/mm/slab.h
index 161ca34acb01..9f78e3167f19 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -109,6 +109,7 @@ struct memcg_cache_params {
 #include <linux/kmemleak.h>
 #include <linux/random.h>
 #include <linux/sched/mm.h>
+#include <linux/kmemleak.h>
 
 /*
  * State of the slab allocator.
@@ -348,6 +349,18 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s->memcg_params.root_cache;
 }
 
+static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
+{
+	/*
+	 * page->mem_cgroup and page->obj_cgroups are sharing the same
+	 * space. To distinguish between them in case we don't know for sure
+	 * that the page is a slab page (e.g. page_cgroup_ino()), let's
+	 * always set the lowest bit of obj_cgroups.
+	 */
+	return (struct obj_cgroup **)
+		((unsigned long)page->obj_cgroups & ~0x1UL);
+}
+
 /*
  * Expects a pointer to a slab page. Please note, that PageSlab() check
  * isn't sufficient, as it returns true also for tail compound slab pages,
@@ -435,6 +448,28 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 	percpu_ref_put_many(&s->memcg_params.refcnt, nr_pages);
 }
 
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+					       struct kmem_cache *s, gfp_t gfp)
+{
+	unsigned int objects = objs_per_slab_page(s, page);
+	void *vec;
+
+	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
+			   page_to_nid(page));
+	if (!vec)
+		return -ENOMEM;
+
+	kmemleak_not_leak(vec);
+	page->obj_cgroups = (struct obj_cgroup **) ((unsigned long)vec | 0x1UL);
+	return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+	kfree(page_obj_cgroups(page));
+	page->obj_cgroups = NULL;
+}
+
 extern void slab_init_memcg_params(struct kmem_cache *);
 extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
 
@@ -484,6 +519,16 @@ static inline void memcg_uncharge_slab(struct page *page, int order,
 {
 }
 
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+					       struct kmem_cache *s, gfp_t gfp)
+{
+	return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+}
+
 static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
@@ -510,12 +555,18 @@ static __always_inline int charge_slab_page(struct page *page,
 					    gfp_t gfp, int order,
 					    struct kmem_cache *s)
 {
+	int ret;
+
 	if (is_root_cache(s)) {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 				    PAGE_SIZE << order);
 		return 0;
 	}
 
+	ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
+	if (ret)
+		return ret;
+
 	return memcg_charge_slab(page, gfp, order, s);
 }
 
@@ -528,6 +579,7 @@ static __always_inline void uncharge_slab_page(struct page *page, int order,
 		return;
 	}
 
+	memcg_free_page_obj_cgroups(page);
 	memcg_uncharge_slab(page, order, s);
 }
 
-- 
cgit v1.2.3


From 964d4bd370d559d9bd8e4abc139e85d2753956fb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:20:56 -0700
Subject: mm: memcg/slab: save obj_cgroup for non-root slab objects

Store the obj_cgroup pointer in the corresponding place of
page->obj_cgroups for each allocated non-root slab object.  Make sure that
each allocated object holds a reference to obj_cgroup.

Objcg pointer is obtained from the memcg->objcg dereferencing in
memcg_kmem_get_cache() and passed from pre_alloc_hook to post_alloc_hook.
Then in case of successful allocation(s) it's getting stored in the
page->obj_cgroups vector.

The objcg obtaining part look a bit bulky now, but it will be simplified
by next commits in the series.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-9-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  3 ++-
 mm/memcontrol.c            | 14 +++++++++--
 mm/slab.c                  | 18 ++++++++------
 mm/slab.h                  | 60 +++++++++++++++++++++++++++++++++++++++++-----
 mm/slub.c                  | 14 +++++++----
 5 files changed, 88 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f2f9d5d6b7d1..b845e908e76e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1404,7 +1404,8 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 }
 #endif
 
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
+					struct obj_cgroup **objcgp);
 void memcg_kmem_put_cache(struct kmem_cache *cachep);
 
 #ifdef CONFIG_MEMCG_KMEM
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6cd4c0d44d1..ab96a120e630 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2973,7 +2973,8 @@ static inline bool memcg_kmem_bypass(void)
  * done with it, memcg_kmem_put_cache() must be called to release the
  * reference.
  */
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
+					struct obj_cgroup **objcgp)
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
@@ -3029,8 +3030,17 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 	 */
 	if (unlikely(!memcg_cachep))
 		memcg_schedule_kmem_cache_create(memcg, cachep);
-	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
+	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) {
+		struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
+
+		if (!objcg || !obj_cgroup_tryget(objcg)) {
+			percpu_ref_put(&memcg_cachep->memcg_params.refcnt);
+			goto out_unlock;
+		}
+
+		*objcgp = objcg;
 		cachep = memcg_cachep;
+	}
 out_unlock:
 	rcu_read_unlock();
 	return cachep;
diff --git a/mm/slab.c b/mm/slab.c
index fa31cbb76124..1e90b67735aa 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3228,9 +3228,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 	int slab_node = numa_mem_id();
+	struct obj_cgroup *objcg = NULL;
 
 	flags &= gfp_allowed_mask;
-	cachep = slab_pre_alloc_hook(cachep, flags);
+	cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
 	if (unlikely(!cachep))
 		return NULL;
 
@@ -3266,7 +3267,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr)
 		memset(ptr, 0, cachep->object_size);
 
-	slab_post_alloc_hook(cachep, flags, 1, &ptr);
+	slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr);
 	return ptr;
 }
 
@@ -3307,9 +3308,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 {
 	unsigned long save_flags;
 	void *objp;
+	struct obj_cgroup *objcg = NULL;
 
 	flags &= gfp_allowed_mask;
-	cachep = slab_pre_alloc_hook(cachep, flags);
+	cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
 	if (unlikely(!cachep))
 		return NULL;
 
@@ -3323,7 +3325,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp)
 		memset(objp, 0, cachep->object_size);
 
-	slab_post_alloc_hook(cachep, flags, 1, &objp);
+	slab_post_alloc_hook(cachep, objcg, flags, 1, &objp);
 	return objp;
 }
 
@@ -3450,6 +3452,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp,
 		memset(objp, 0, cachep->object_size);
 	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, caller);
+	memcg_slab_free_hook(cachep, virt_to_head_page(objp), objp);
 
 	/*
 	 * Skip calling cache_free_alien() when the platform is not numa.
@@ -3515,8 +3518,9 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			  void **p)
 {
 	size_t i;
+	struct obj_cgroup *objcg = NULL;
 
-	s = slab_pre_alloc_hook(s, flags);
+	s = slab_pre_alloc_hook(s, &objcg, size, flags);
 	if (!s)
 		return 0;
 
@@ -3539,13 +3543,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 		for (i = 0; i < size; i++)
 			memset(p[i], 0, s->object_size);
 
-	slab_post_alloc_hook(s, flags, size, p);
+	slab_post_alloc_hook(s, objcg, flags, size, p);
 	/* FIXME: Trace call missing. Christoph would like a bulk variant */
 	return size;
 error:
 	local_irq_enable();
 	cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
-	slab_post_alloc_hook(s, flags, i, p);
+	slab_post_alloc_hook(s, objcg, flags, i, p);
 	__kmem_cache_free_bulk(s, i, p);
 	return 0;
 }
diff --git a/mm/slab.h b/mm/slab.h
index 9f78e3167f19..d4f9fc93546f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -470,6 +470,41 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 	page->obj_cgroups = NULL;
 }
 
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					      struct obj_cgroup *objcg,
+					      size_t size, void **p)
+{
+	struct page *page;
+	unsigned long off;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		if (likely(p[i])) {
+			page = virt_to_head_page(p[i]);
+			off = obj_to_index(s, page, p[i]);
+			obj_cgroup_get(objcg);
+			page_obj_cgroups(page)[off] = objcg;
+		}
+	}
+	obj_cgroup_put(objcg);
+	memcg_kmem_put_cache(s);
+}
+
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+					void *p)
+{
+	struct obj_cgroup *objcg;
+	unsigned int off;
+
+	if (!memcg_kmem_enabled() || is_root_cache(s))
+		return;
+
+	off = obj_to_index(s, page, p);
+	objcg = page_obj_cgroups(page)[off];
+	page_obj_cgroups(page)[off] = NULL;
+	obj_cgroup_put(objcg);
+}
+
 extern void slab_init_memcg_params(struct kmem_cache *);
 extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
 
@@ -529,6 +564,17 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 }
 
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					      struct obj_cgroup *objcg,
+					      size_t size, void **p)
+{
+}
+
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+					void *p)
+{
+}
+
 static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
@@ -631,7 +677,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
 }
 
 static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
-						     gfp_t flags)
+						     struct obj_cgroup **objcgp,
+						     size_t size, gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
 
@@ -645,13 +692,14 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 
 	if (memcg_kmem_enabled() &&
 	    ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
-		return memcg_kmem_get_cache(s);
+		return memcg_kmem_get_cache(s, objcgp);
 
 	return s;
 }
 
-static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-					size_t size, void **p)
+static inline void slab_post_alloc_hook(struct kmem_cache *s,
+					struct obj_cgroup *objcg,
+					gfp_t flags, size_t size, void **p)
 {
 	size_t i;
 
@@ -663,8 +711,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
 					 s->flags, flags);
 	}
 
-	if (memcg_kmem_enabled())
-		memcg_kmem_put_cache(s);
+	if (memcg_kmem_enabled() && !is_root_cache(s))
+		memcg_slab_post_alloc_hook(s, objcg, size, p);
 }
 
 #ifndef CONFIG_SLOB
diff --git a/mm/slub.c b/mm/slub.c
index 2a3075538f26..47e63b1100d4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2817,8 +2817,9 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	struct page *page;
 	unsigned long tid;
+	struct obj_cgroup *objcg = NULL;
 
-	s = slab_pre_alloc_hook(s, gfpflags);
+	s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
 	if (!s)
 		return NULL;
 redo:
@@ -2894,7 +2895,7 @@ redo:
 	if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
 		memset(object, 0, s->object_size);
 
-	slab_post_alloc_hook(s, gfpflags, 1, &object);
+	slab_post_alloc_hook(s, objcg, gfpflags, 1, &object);
 
 	return object;
 }
@@ -3099,6 +3100,8 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
 	void *tail_obj = tail ? : head;
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
+
+	memcg_slab_free_hook(s, page, head);
 redo:
 	/*
 	 * Determine the currently cpus per cpu slab.
@@ -3278,9 +3281,10 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 {
 	struct kmem_cache_cpu *c;
 	int i;
+	struct obj_cgroup *objcg = NULL;
 
 	/* memcg and kmem_cache debug support */
-	s = slab_pre_alloc_hook(s, flags);
+	s = slab_pre_alloc_hook(s, &objcg, size, flags);
 	if (unlikely(!s))
 		return false;
 	/*
@@ -3334,11 +3338,11 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	}
 
 	/* memcg and kmem_cache debug support */
-	slab_post_alloc_hook(s, flags, size, p);
+	slab_post_alloc_hook(s, objcg, flags, size, p);
 	return i;
 error:
 	local_irq_enable();
-	slab_post_alloc_hook(s, flags, i, p);
+	slab_post_alloc_hook(s, objcg, flags, i, p);
 	__kmem_cache_free_bulk(s, i, p);
 	return 0;
 }
-- 
cgit v1.2.3


From 0f876e4dc55db5fafef774917fd66e1373c0f390 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:06 -0700
Subject: mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h

To make the memcg_kmem_bypass() function available outside of the
memcontrol.c, let's move it to memcontrol.h.  The function is small and
nicely fits into static inline sort of functions.

It will be used from the slab code.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-12-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 12 ++++++++++++
 mm/memcontrol.c            | 12 ------------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b845e908e76e..83e2858aecf2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1440,6 +1440,18 @@ static inline bool memcg_kmem_enabled(void)
 	return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
+static inline bool memcg_kmem_bypass(void)
+{
+	if (in_interrupt())
+		return true;
+
+	/* Allow remote memcg charging in kthread contexts. */
+	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
+	     !current->active_memcg)
+		return true;
+	return false;
+}
+
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0356e05bc6e6..5cb2a588cc10 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2945,18 +2945,6 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	queue_work(memcg_kmem_cache_wq, &cw->work);
 }
 
-static inline bool memcg_kmem_bypass(void)
-{
-	if (in_interrupt())
-		return true;
-
-	/* Allow remote memcg charging in kthread contexts. */
-	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
-	     !current->active_memcg)
-		return true;
-	return false;
-}
-
 /**
  * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
  * @cachep: the original global kmem cache
-- 
cgit v1.2.3


From 9855609bde03e2472b99a95e869d29ee1e78a751 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:10 -0700
Subject: mm: memcg/slab: use a single set of kmem_caches for all accounted
 allocations

This is fairly big but mostly red patch, which makes all accounted slab
allocations use a single set of kmem_caches instead of creating a separate
set for each memory cgroup.

Because the number of non-root kmem_caches is now capped by the number of
root kmem_caches, there is no need to shrink or destroy them prematurely.
They can be perfectly destroyed together with their root counterparts.
This allows to dramatically simplify the management of non-root
kmem_caches and delete a ton of code.

This patch performs the following changes:
1) introduces memcg_params.memcg_cache pointer to represent the
   kmem_cache which will be used for all non-root allocations
2) reuses the existing memcg kmem_cache creation mechanism
   to create memcg kmem_cache on the first allocation attempt
3) memcg kmem_caches are named <kmemcache_name>-memcg,
   e.g. dentry-memcg
4) simplifies memcg_kmem_get_cache() to just return memcg kmem_cache
   or schedule it's creation and return the root cache
5) removes almost all non-root kmem_cache management code
   (separate refcounter, reparenting, shrinking, etc)
6) makes slab debugfs to display root_mem_cgroup css id and never
   show :dead and :deact flags in the memcg_slabinfo attribute.

Following patches in the series will simplify the kmem_cache creation.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-13-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |   5 +-
 include/linux/slab.h       |   5 +-
 mm/memcontrol.c            | 163 ++++------------
 mm/slab.c                  |  16 +-
 mm/slab.h                  | 146 +++++---------
 mm/slab_common.c           | 459 +++++----------------------------------------
 mm/slub.c                  |  38 +---
 7 files changed, 134 insertions(+), 698 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 83e2858aecf2..11fd18b3d6c6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -317,7 +317,6 @@ struct mem_cgroup {
         /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
 	enum memcg_kmem_state kmem_state;
-	struct list_head kmem_caches;
 	struct obj_cgroup __rcu *objcg;
 	struct list_head objcg_list; /* list of inherited objcgs */
 #endif
@@ -1404,9 +1403,7 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 }
 #endif
 
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
-					struct obj_cgroup **objcgp);
-void memcg_kmem_put_cache(struct kmem_cache *cachep);
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
 
 #ifdef CONFIG_MEMCG_KMEM
 int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 0884d82c55ee..8b1f91e320f9 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -155,8 +155,7 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name,
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 
-void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
-void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *);
+void memcg_create_kmem_cache(struct kmem_cache *cachep);
 
 /*
  * Please use this macro to create slab caches. Simply specify the
@@ -580,8 +579,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
-int memcg_update_all_caches(int num_memcgs);
-
 /**
  * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5cb2a588cc10..874704c4a48a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -350,7 +350,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
 }
 
 /*
- * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
+ * This will be used as a shrinker list's index.
  * The main reason for not using cgroup id for this:
  *  this works better in sparse environments, where we have a lot of memcgs,
  *  but only a few kmem-limited. Or also, if we have, for instance, 200
@@ -569,20 +569,16 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageSlab(page) && !PageTail(page)) {
-		memcg = memcg_from_slab_page(page);
-	} else {
-		memcg = page->mem_cgroup;
+	memcg = page->mem_cgroup;
 
-		/*
-		 * The lowest bit set means that memcg isn't a valid
-		 * memcg pointer, but a obj_cgroups pointer.
-		 * In this case the page is shared and doesn't belong
-		 * to any specific memory cgroup.
-		 */
-		if ((unsigned long) memcg & 0x1UL)
-			memcg = NULL;
-	}
+	/*
+	 * The lowest bit set means that memcg isn't a valid
+	 * memcg pointer, but a obj_cgroups pointer.
+	 * In this case the page is shared and doesn't belong
+	 * to any specific memory cgroup.
+	 */
+	if ((unsigned long) memcg & 0x1UL)
+		memcg = NULL;
 
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
@@ -2822,12 +2818,18 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	page = virt_to_head_page(p);
 
 	/*
-	 * Slab pages don't have page->mem_cgroup set because corresponding
-	 * kmem caches can be reparented during the lifetime. That's why
-	 * memcg_from_slab_page() should be used instead.
+	 * Slab objects are accounted individually, not per-page.
+	 * Memcg membership data for each individual object is saved in
+	 * the page->obj_cgroups.
 	 */
-	if (PageSlab(page))
-		return memcg_from_slab_page(page);
+	if (page_has_obj_cgroups(page)) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
+
+		off = obj_to_index(page->slab_cache, page, p);
+		objcg = page_obj_cgroups(page)[off];
+		return obj_cgroup_memcg(objcg);
+	}
 
 	/* All other pages use page->mem_cgroup */
 	return page->mem_cgroup;
@@ -2882,9 +2884,7 @@ static int memcg_alloc_cache_id(void)
 	else if (size > MEMCG_CACHES_MAX_SIZE)
 		size = MEMCG_CACHES_MAX_SIZE;
 
-	err = memcg_update_all_caches(size);
-	if (!err)
-		err = memcg_update_all_list_lrus(size);
+	err = memcg_update_all_list_lrus(size);
 	if (!err)
 		memcg_nr_cache_ids = size;
 
@@ -2903,7 +2903,6 @@ static void memcg_free_cache_id(int id)
 }
 
 struct memcg_kmem_cache_create_work {
-	struct mem_cgroup *memcg;
 	struct kmem_cache *cachep;
 	struct work_struct work;
 };
@@ -2912,33 +2911,24 @@ static void memcg_kmem_cache_create_func(struct work_struct *w)
 {
 	struct memcg_kmem_cache_create_work *cw =
 		container_of(w, struct memcg_kmem_cache_create_work, work);
-	struct mem_cgroup *memcg = cw->memcg;
 	struct kmem_cache *cachep = cw->cachep;
 
-	memcg_create_kmem_cache(memcg, cachep);
+	memcg_create_kmem_cache(cachep);
 
-	css_put(&memcg->css);
 	kfree(cw);
 }
 
 /*
  * Enqueue the creation of a per-memcg kmem_cache.
  */
-static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
-					       struct kmem_cache *cachep)
+static void memcg_schedule_kmem_cache_create(struct kmem_cache *cachep)
 {
 	struct memcg_kmem_cache_create_work *cw;
 
-	if (!css_tryget_online(&memcg->css))
-		return;
-
 	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
-	if (!cw) {
-		css_put(&memcg->css);
+	if (!cw)
 		return;
-	}
 
-	cw->memcg = memcg;
 	cw->cachep = cachep;
 	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
 
@@ -2946,102 +2936,26 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 }
 
 /**
- * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
+ * memcg_kmem_get_cache: select memcg or root cache for allocation
  * @cachep: the original global kmem cache
  *
  * Return the kmem_cache we're supposed to use for a slab allocation.
- * We try to use the current memcg's version of the cache.
  *
  * If the cache does not exist yet, if we are the first user of it, we
  * create it asynchronously in a workqueue and let the current allocation
  * go through with the original cache.
- *
- * This function takes a reference to the cache it returns to assure it
- * won't get destroyed while we are working with it. Once the caller is
- * done with it, memcg_kmem_put_cache() must be called to release the
- * reference.
  */
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
-					struct obj_cgroup **objcgp)
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
-	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
-	struct memcg_cache_array *arr;
-	int kmemcg_id;
 
-	VM_BUG_ON(!is_root_cache(cachep));
-
-	if (memcg_kmem_bypass())
+	memcg_cachep = READ_ONCE(cachep->memcg_params.memcg_cache);
+	if (unlikely(!memcg_cachep)) {
+		memcg_schedule_kmem_cache_create(cachep);
 		return cachep;
-
-	rcu_read_lock();
-
-	if (unlikely(current->active_memcg))
-		memcg = current->active_memcg;
-	else
-		memcg = mem_cgroup_from_task(current);
-
-	if (!memcg || memcg == root_mem_cgroup)
-		goto out_unlock;
-
-	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
-	if (kmemcg_id < 0)
-		goto out_unlock;
-
-	arr = rcu_dereference(cachep->memcg_params.memcg_caches);
-
-	/*
-	 * Make sure we will access the up-to-date value. The code updating
-	 * memcg_caches issues a write barrier to match the data dependency
-	 * barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
-	 */
-	memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);
-
-	/*
-	 * If we are in a safe context (can wait, and not in interrupt
-	 * context), we could be be predictable and return right away.
-	 * This would guarantee that the allocation being performed
-	 * already belongs in the new cache.
-	 *
-	 * However, there are some clashes that can arrive from locking.
-	 * For instance, because we acquire the slab_mutex while doing
-	 * memcg_create_kmem_cache, this means no further allocation
-	 * could happen with the slab_mutex held. So it's better to
-	 * defer everything.
-	 *
-	 * If the memcg is dying or memcg_cache is about to be released,
-	 * don't bother creating new kmem_caches. Because memcg_cachep
-	 * is ZEROed as the fist step of kmem offlining, we don't need
-	 * percpu_ref_tryget_live() here. css_tryget_online() check in
-	 * memcg_schedule_kmem_cache_create() will prevent us from
-	 * creation of a new kmem_cache.
-	 */
-	if (unlikely(!memcg_cachep))
-		memcg_schedule_kmem_cache_create(memcg, cachep);
-	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) {
-		struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
-
-		if (!objcg || !obj_cgroup_tryget(objcg)) {
-			percpu_ref_put(&memcg_cachep->memcg_params.refcnt);
-			goto out_unlock;
-		}
-
-		*objcgp = objcg;
-		cachep = memcg_cachep;
 	}
-out_unlock:
-	rcu_read_unlock();
-	return cachep;
-}
 
-/**
- * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
- * @cachep: the cache returned by memcg_kmem_get_cache
- */
-void memcg_kmem_put_cache(struct kmem_cache *cachep)
-{
-	if (!is_root_cache(cachep))
-		percpu_ref_put(&cachep->memcg_params.refcnt);
+	return memcg_cachep;
 }
 
 /**
@@ -3731,7 +3645,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
-	INIT_LIST_HEAD(&memcg->kmem_caches);
 
 	return 0;
 }
@@ -3744,22 +3657,13 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 
 	if (memcg->kmem_state != KMEM_ONLINE)
 		return;
-	/*
-	 * Clear the online state before clearing memcg_caches array
-	 * entries. The slab_mutex in memcg_deactivate_kmem_caches()
-	 * guarantees that no cache will be created for this cgroup
-	 * after we are done (see memcg_create_kmem_cache()).
-	 */
+
 	memcg->kmem_state = KMEM_ALLOCATED;
 
 	parent = parent_mem_cgroup(memcg);
 	if (!parent)
 		parent = root_mem_cgroup;
 
-	/*
-	 * Deactivate and reparent kmem_caches and objcgs.
-	 */
-	memcg_deactivate_kmem_caches(memcg, parent);
 	memcg_reparent_objcgs(memcg, parent);
 
 	kmemcg_id = memcg->kmemcg_id;
@@ -5384,9 +5288,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	/* The following stuff does not apply to the root */
 	if (!parent) {
-#ifdef CONFIG_MEMCG_KMEM
-		INIT_LIST_HEAD(&memcg->kmem_caches);
-#endif
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
diff --git a/mm/slab.c b/mm/slab.c
index 1e90b67735aa..0dd6956585dc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1249,7 +1249,7 @@ void __init kmem_cache_init(void)
 				  nr_node_ids * sizeof(struct kmem_cache_node *),
 				  SLAB_HWCACHE_ALIGN, 0, 0);
 	list_add(&kmem_cache->list, &slab_caches);
-	memcg_link_cache(kmem_cache, NULL);
+	memcg_link_cache(kmem_cache);
 	slab_state = PARTIAL;
 
 	/*
@@ -2253,17 +2253,6 @@ int __kmem_cache_shrink(struct kmem_cache *cachep)
 	return (ret ? 1 : 0);
 }
 
-#ifdef CONFIG_MEMCG
-void __kmemcg_cache_deactivate(struct kmem_cache *cachep)
-{
-	__kmem_cache_shrink(cachep);
-}
-
-void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
-{
-}
-#endif
-
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
 	return __kmem_cache_shrink(cachep);
@@ -3872,7 +3861,8 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 		return ret;
 
 	lockdep_assert_held(&slab_mutex);
-	for_each_memcg_cache(c, cachep) {
+	c = memcg_cache(cachep);
+	if (c) {
 		/* return value determined by the root cache only */
 		__do_tune_cpucache(c, limit, batchcount, shared, gfp);
 	}
diff --git a/mm/slab.h b/mm/slab.h
index 1f067e8bc377..e716b80befc2 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -32,66 +32,25 @@ struct kmem_cache {
 
 #else /* !CONFIG_SLOB */
 
-struct memcg_cache_array {
-	struct rcu_head rcu;
-	struct kmem_cache *entries[0];
-};
-
 /*
  * This is the main placeholder for memcg-related information in kmem caches.
- * Both the root cache and the child caches will have it. For the root cache,
- * this will hold a dynamically allocated array large enough to hold
- * information about the currently limited memcgs in the system. To allow the
- * array to be accessed without taking any locks, on relocation we free the old
- * version only after a grace period.
- *
- * Root and child caches hold different metadata.
+ * Both the root cache and the child cache will have it. Some fields are used
+ * in both cases, other are specific to root caches.
  *
  * @root_cache:	Common to root and child caches.  NULL for root, pointer to
  *		the root cache for children.
  *
  * The following fields are specific to root caches.
  *
- * @memcg_caches: kmemcg ID indexed table of child caches.  This table is
- *		used to index child cachces during allocation and cleared
- *		early during shutdown.
- *
- * @root_caches_node: List node for slab_root_caches list.
- *
- * @children:	List of all child caches.  While the child caches are also
- *		reachable through @memcg_caches, a child cache remains on
- *		this list until it is actually destroyed.
- *
- * The following fields are specific to child caches.
- *
- * @memcg:	Pointer to the memcg this cache belongs to.
- *
- * @children_node: List node for @root_cache->children list.
- *
- * @kmem_caches_node: List node for @memcg->kmem_caches list.
+ * @memcg_cache: pointer to memcg kmem cache, used by all non-root memory
+ *		cgroups.
+ * @root_caches_node: list node for slab_root_caches list.
  */
 struct memcg_cache_params {
 	struct kmem_cache *root_cache;
-	union {
-		struct {
-			struct memcg_cache_array __rcu *memcg_caches;
-			struct list_head __root_caches_node;
-			struct list_head children;
-			bool dying;
-		};
-		struct {
-			struct mem_cgroup *memcg;
-			struct list_head children_node;
-			struct list_head kmem_caches_node;
-			struct percpu_ref refcnt;
-
-			void (*work_fn)(struct kmem_cache *);
-			union {
-				struct rcu_head rcu_head;
-				struct work_struct work;
-			};
-		};
-	};
+
+	struct kmem_cache *memcg_cache;
+	struct list_head __root_caches_node;
 };
 #endif /* CONFIG_SLOB */
 
@@ -236,8 +195,6 @@ bool __kmem_cache_empty(struct kmem_cache *);
 int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
-void __kmemcg_cache_deactivate(struct kmem_cache *s);
-void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s);
 void slab_kmem_cache_release(struct kmem_cache *);
 void kmem_cache_shrink_all(struct kmem_cache *s);
 
@@ -311,14 +268,6 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 extern struct list_head		slab_root_caches;
 #define root_caches_node	memcg_params.__root_caches_node
 
-/*
- * Iterate over all memcg caches of the given root cache. The caller must hold
- * slab_mutex.
- */
-#define for_each_memcg_cache(iter, root) \
-	list_for_each_entry(iter, &(root)->memcg_params.children, \
-			    memcg_params.children_node)
-
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return !s->memcg_params.root_cache;
@@ -349,6 +298,13 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s->memcg_params.root_cache;
 }
 
+static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s))
+		return s->memcg_params.memcg_cache;
+	return NULL;
+}
+
 static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 {
 	/*
@@ -361,25 +317,9 @@ static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 		((unsigned long)page->obj_cgroups & ~0x1UL);
 }
 
-/*
- * Expects a pointer to a slab page. Please note, that PageSlab() check
- * isn't sufficient, as it returns true also for tail compound slab pages,
- * which do not have slab_cache pointer set.
- * So this function assumes that the page can pass PageSlab() && !PageTail()
- * check.
- *
- * The kmem_cache can be reparented asynchronously. The caller must ensure
- * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
- */
-static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+static inline bool page_has_obj_cgroups(struct page *page)
 {
-	struct kmem_cache *s;
-
-	s = READ_ONCE(page->slab_cache);
-	if (s && !is_root_cache(s))
-		return READ_ONCE(s->memcg_params.memcg);
-
-	return NULL;
+	return ((unsigned long)page->obj_cgroups & 0x1UL);
 }
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
@@ -418,17 +358,25 @@ static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 						size_t objects, gfp_t flags)
 {
 	struct kmem_cache *cachep;
+	struct obj_cgroup *objcg;
+
+	if (memcg_kmem_bypass())
+		return s;
 
-	cachep = memcg_kmem_get_cache(s, objcgp);
+	cachep = memcg_kmem_get_cache(s);
 	if (is_root_cache(cachep))
 		return s;
 
-	if (obj_cgroup_charge(*objcgp, flags, objects * obj_full_size(s))) {
-		obj_cgroup_put(*objcgp);
-		memcg_kmem_put_cache(cachep);
+	objcg = get_obj_cgroup_from_current();
+	if (!objcg)
+		return s;
+
+	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
+		obj_cgroup_put(objcg);
 		cachep = NULL;
 	}
 
+	*objcgp = objcg;
 	return cachep;
 }
 
@@ -467,7 +415,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 		}
 	}
 	obj_cgroup_put(objcg);
-	memcg_kmem_put_cache(s);
 }
 
 static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
@@ -491,7 +438,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 }
 
 extern void slab_init_memcg_params(struct kmem_cache *);
-extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
+extern void memcg_link_cache(struct kmem_cache *s);
 
 #else /* CONFIG_MEMCG_KMEM */
 
@@ -499,9 +446,6 @@ extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
 #define slab_root_caches	slab_caches
 #define root_caches_node	list
 
-#define for_each_memcg_cache(iter, root) \
-	for ((void)(iter), (void)(root); 0; )
-
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
@@ -523,7 +467,17 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s;
 }
 
-static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
+{
+	return NULL;
+}
+
+static inline bool page_has_obj_cgroups(struct page *page)
+{
+	return false;
+}
+
+static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 {
 	return NULL;
 }
@@ -560,8 +514,7 @@ static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
 
-static inline void memcg_link_cache(struct kmem_cache *s,
-				    struct mem_cgroup *memcg)
+static inline void memcg_link_cache(struct kmem_cache *s)
 {
 }
 
@@ -582,17 +535,14 @@ static __always_inline int charge_slab_page(struct page *page,
 					    gfp_t gfp, int order,
 					    struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG_KMEM
 	if (memcg_kmem_enabled() && !is_root_cache(s)) {
 		int ret;
 
 		ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
 		if (ret)
 			return ret;
-
-		percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
 	}
-#endif
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
 	return 0;
@@ -601,12 +551,9 @@ static __always_inline int charge_slab_page(struct page *page,
 static __always_inline void uncharge_slab_page(struct page *page, int order,
 					       struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG_KMEM
-	if (memcg_kmem_enabled() && !is_root_cache(s)) {
+	if (memcg_kmem_enabled() && !is_root_cache(s))
 		memcg_free_page_obj_cgroups(page);
-		percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
-	}
-#endif
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    -(PAGE_SIZE << order));
 }
@@ -749,9 +696,6 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
-void *memcg_slab_start(struct seq_file *m, loff_t *pos);
-void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
-void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
 #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f86431d0de73..e752132eb64d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -133,141 +133,36 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 #ifdef CONFIG_MEMCG_KMEM
 
 LIST_HEAD(slab_root_caches);
-static DEFINE_SPINLOCK(memcg_kmem_wq_lock);
-
-static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref);
 
 void slab_init_memcg_params(struct kmem_cache *s)
 {
 	s->memcg_params.root_cache = NULL;
-	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
-	INIT_LIST_HEAD(&s->memcg_params.children);
-	s->memcg_params.dying = false;
+	s->memcg_params.memcg_cache = NULL;
 }
 
-static int init_memcg_params(struct kmem_cache *s,
-			     struct kmem_cache *root_cache)
+static void init_memcg_params(struct kmem_cache *s,
+			      struct kmem_cache *root_cache)
 {
-	struct memcg_cache_array *arr;
-
-	if (root_cache) {
-		int ret = percpu_ref_init(&s->memcg_params.refcnt,
-					  kmemcg_cache_shutdown,
-					  0, GFP_KERNEL);
-		if (ret)
-			return ret;
-
+	if (root_cache)
 		s->memcg_params.root_cache = root_cache;
-		INIT_LIST_HEAD(&s->memcg_params.children_node);
-		INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
-		return 0;
-	}
-
-	slab_init_memcg_params(s);
-
-	if (!memcg_nr_cache_ids)
-		return 0;
-
-	arr = kvzalloc(sizeof(struct memcg_cache_array) +
-		       memcg_nr_cache_ids * sizeof(void *),
-		       GFP_KERNEL);
-	if (!arr)
-		return -ENOMEM;
-
-	RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
-	return 0;
-}
-
-static void destroy_memcg_params(struct kmem_cache *s)
-{
-	if (is_root_cache(s)) {
-		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
-	} else {
-		mem_cgroup_put(s->memcg_params.memcg);
-		WRITE_ONCE(s->memcg_params.memcg, NULL);
-		percpu_ref_exit(&s->memcg_params.refcnt);
-	}
-}
-
-static void free_memcg_params(struct rcu_head *rcu)
-{
-	struct memcg_cache_array *old;
-
-	old = container_of(rcu, struct memcg_cache_array, rcu);
-	kvfree(old);
-}
-
-static int update_memcg_params(struct kmem_cache *s, int new_array_size)
-{
-	struct memcg_cache_array *old, *new;
-
-	new = kvzalloc(sizeof(struct memcg_cache_array) +
-		       new_array_size * sizeof(void *), GFP_KERNEL);
-	if (!new)
-		return -ENOMEM;
-
-	old = rcu_dereference_protected(s->memcg_params.memcg_caches,
-					lockdep_is_held(&slab_mutex));
-	if (old)
-		memcpy(new->entries, old->entries,
-		       memcg_nr_cache_ids * sizeof(void *));
-
-	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
-	if (old)
-		call_rcu(&old->rcu, free_memcg_params);
-	return 0;
+	else
+		slab_init_memcg_params(s);
 }
 
-int memcg_update_all_caches(int num_memcgs)
+void memcg_link_cache(struct kmem_cache *s)
 {
-	struct kmem_cache *s;
-	int ret = 0;
-
-	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
-		ret = update_memcg_params(s, num_memcgs);
-		/*
-		 * Instead of freeing the memory, we'll just leave the caches
-		 * up to this point in an updated state.
-		 */
-		if (ret)
-			break;
-	}
-	mutex_unlock(&slab_mutex);
-	return ret;
-}
-
-void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg)
-{
-	if (is_root_cache(s)) {
+	if (is_root_cache(s))
 		list_add(&s->root_caches_node, &slab_root_caches);
-	} else {
-		css_get(&memcg->css);
-		s->memcg_params.memcg = memcg;
-		list_add(&s->memcg_params.children_node,
-			 &s->memcg_params.root_cache->memcg_params.children);
-		list_add(&s->memcg_params.kmem_caches_node,
-			 &s->memcg_params.memcg->kmem_caches);
-	}
 }
 
 static void memcg_unlink_cache(struct kmem_cache *s)
 {
-	if (is_root_cache(s)) {
+	if (is_root_cache(s))
 		list_del(&s->root_caches_node);
-	} else {
-		list_del(&s->memcg_params.children_node);
-		list_del(&s->memcg_params.kmem_caches_node);
-	}
 }
 #else
-static inline int init_memcg_params(struct kmem_cache *s,
-				    struct kmem_cache *root_cache)
-{
-	return 0;
-}
-
-static inline void destroy_memcg_params(struct kmem_cache *s)
+static inline void init_memcg_params(struct kmem_cache *s,
+				     struct kmem_cache *root_cache)
 {
 }
 
@@ -328,14 +223,6 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (s->refcount < 0)
 		return 1;
 
-#ifdef CONFIG_MEMCG_KMEM
-	/*
-	 * Skip the dying kmem_cache.
-	 */
-	if (s->memcg_params.dying)
-		return 1;
-#endif
-
 	return 0;
 }
 
@@ -390,7 +277,7 @@ static struct kmem_cache *create_cache(const char *name,
 		unsigned int object_size, unsigned int align,
 		slab_flags_t flags, unsigned int useroffset,
 		unsigned int usersize, void (*ctor)(void *),
-		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+		struct kmem_cache *root_cache)
 {
 	struct kmem_cache *s;
 	int err;
@@ -410,24 +297,20 @@ static struct kmem_cache *create_cache(const char *name,
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
-	err = init_memcg_params(s, root_cache);
-	if (err)
-		goto out_free_cache;
-
+	init_memcg_params(s, root_cache);
 	err = __kmem_cache_create(s, flags);
 	if (err)
 		goto out_free_cache;
 
 	s->refcount = 1;
 	list_add(&s->list, &slab_caches);
-	memcg_link_cache(s, memcg);
+	memcg_link_cache(s);
 out:
 	if (err)
 		return ERR_PTR(err);
 	return s;
 
 out_free_cache:
-	destroy_memcg_params(s);
 	kmem_cache_free(kmem_cache, s);
 	goto out;
 }
@@ -514,7 +397,7 @@ kmem_cache_create_usercopy(const char *name,
 
 	s = create_cache(cache_name, size,
 			 calculate_alignment(flags, align, size),
-			 flags, useroffset, usersize, ctor, NULL, NULL);
+			 flags, useroffset, usersize, ctor, NULL);
 	if (IS_ERR(s)) {
 		err = PTR_ERR(s);
 		kfree_const(cache_name);
@@ -639,51 +522,27 @@ static int shutdown_cache(struct kmem_cache *s)
 
 #ifdef CONFIG_MEMCG_KMEM
 /*
- * memcg_create_kmem_cache - Create a cache for a memory cgroup.
- * @memcg: The memory cgroup the new cache is for.
+ * memcg_create_kmem_cache - Create a cache for non-root memory cgroups.
  * @root_cache: The parent of the new cache.
  *
  * This function attempts to create a kmem cache that will serve allocation
- * requests going from @memcg to @root_cache. The new cache inherits properties
- * from its parent.
+ * requests going all non-root memory cgroups to @root_cache. The new cache
+ * inherits properties from its parent.
  */
-void memcg_create_kmem_cache(struct mem_cgroup *memcg,
-			     struct kmem_cache *root_cache)
+void memcg_create_kmem_cache(struct kmem_cache *root_cache)
 {
-	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
-	struct cgroup_subsys_state *css = &memcg->css;
-	struct memcg_cache_array *arr;
 	struct kmem_cache *s = NULL;
 	char *cache_name;
-	int idx;
 
 	get_online_cpus();
 	get_online_mems();
 
 	mutex_lock(&slab_mutex);
 
-	/*
-	 * The memory cgroup could have been offlined while the cache
-	 * creation work was pending.
-	 */
-	if (memcg->kmem_state != KMEM_ONLINE)
+	if (root_cache->memcg_params.memcg_cache)
 		goto out_unlock;
 
-	idx = memcg_cache_id(memcg);
-	arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
-					lockdep_is_held(&slab_mutex));
-
-	/*
-	 * Since per-memcg caches are created asynchronously on first
-	 * allocation (see memcg_kmem_get_cache()), several threads can try to
-	 * create the same cache, but only one of them may succeed.
-	 */
-	if (arr->entries[idx])
-		goto out_unlock;
-
-	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
-	cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
-			       css->serial_nr, memcg_name_buf);
+	cache_name = kasprintf(GFP_KERNEL, "%s-memcg", root_cache->name);
 	if (!cache_name)
 		goto out_unlock;
 
@@ -691,7 +550,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 			 root_cache->align,
 			 root_cache->flags & CACHE_CREATE_MASK,
 			 root_cache->useroffset, root_cache->usersize,
-			 root_cache->ctor, memcg, root_cache);
+			 root_cache->ctor, root_cache);
 	/*
 	 * If we could not create a memcg cache, do not complain, because
 	 * that's not critical at all as we can always proceed with the root
@@ -708,7 +567,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	 * initialized.
 	 */
 	smp_wmb();
-	arr->entries[idx] = s;
+	root_cache->memcg_params.memcg_cache = s;
 
 out_unlock:
 	mutex_unlock(&slab_mutex);
@@ -717,200 +576,18 @@ out_unlock:
 	put_online_cpus();
 }
 
-static void kmemcg_workfn(struct work_struct *work)
-{
-	struct kmem_cache *s = container_of(work, struct kmem_cache,
-					    memcg_params.work);
-
-	get_online_cpus();
-	get_online_mems();
-
-	mutex_lock(&slab_mutex);
-	s->memcg_params.work_fn(s);
-	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
-}
-
-static void kmemcg_rcufn(struct rcu_head *head)
-{
-	struct kmem_cache *s = container_of(head, struct kmem_cache,
-					    memcg_params.rcu_head);
-
-	/*
-	 * We need to grab blocking locks.  Bounce to ->work.  The
-	 * work item shares the space with the RCU head and can't be
-	 * initialized earlier.
-	 */
-	INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
-	queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
-}
-
-static void kmemcg_cache_shutdown_fn(struct kmem_cache *s)
-{
-	WARN_ON(shutdown_cache(s));
-}
-
-static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref)
-{
-	struct kmem_cache *s = container_of(percpu_ref, struct kmem_cache,
-					    memcg_params.refcnt);
-	unsigned long flags;
-
-	spin_lock_irqsave(&memcg_kmem_wq_lock, flags);
-	if (s->memcg_params.root_cache->memcg_params.dying)
-		goto unlock;
-
-	s->memcg_params.work_fn = kmemcg_cache_shutdown_fn;
-	INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
-	queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
-
-unlock:
-	spin_unlock_irqrestore(&memcg_kmem_wq_lock, flags);
-}
-
-static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
-{
-	__kmemcg_cache_deactivate_after_rcu(s);
-	percpu_ref_kill(&s->memcg_params.refcnt);
-}
-
-static void kmemcg_cache_deactivate(struct kmem_cache *s)
-{
-	if (WARN_ON_ONCE(is_root_cache(s)))
-		return;
-
-	__kmemcg_cache_deactivate(s);
-	s->flags |= SLAB_DEACTIVATED;
-
-	/*
-	 * memcg_kmem_wq_lock is used to synchronize memcg_params.dying
-	 * flag and make sure that no new kmem_cache deactivation tasks
-	 * are queued (see flush_memcg_workqueue() ).
-	 */
-	spin_lock_irq(&memcg_kmem_wq_lock);
-	if (s->memcg_params.root_cache->memcg_params.dying)
-		goto unlock;
-
-	s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu;
-	call_rcu(&s->memcg_params.rcu_head, kmemcg_rcufn);
-unlock:
-	spin_unlock_irq(&memcg_kmem_wq_lock);
-}
-
-void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg,
-				  struct mem_cgroup *parent)
-{
-	int idx;
-	struct memcg_cache_array *arr;
-	struct kmem_cache *s, *c;
-	unsigned int nr_reparented;
-
-	idx = memcg_cache_id(memcg);
-
-	get_online_cpus();
-	get_online_mems();
-
-	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
-		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
-						lockdep_is_held(&slab_mutex));
-		c = arr->entries[idx];
-		if (!c)
-			continue;
-
-		kmemcg_cache_deactivate(c);
-		arr->entries[idx] = NULL;
-	}
-	nr_reparented = 0;
-	list_for_each_entry(s, &memcg->kmem_caches,
-			    memcg_params.kmem_caches_node) {
-		WRITE_ONCE(s->memcg_params.memcg, parent);
-		css_put(&memcg->css);
-		nr_reparented++;
-	}
-	if (nr_reparented) {
-		list_splice_init(&memcg->kmem_caches,
-				 &parent->kmem_caches);
-		css_get_many(&parent->css, nr_reparented);
-	}
-	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
-}
-
 static int shutdown_memcg_caches(struct kmem_cache *s)
 {
-	struct memcg_cache_array *arr;
-	struct kmem_cache *c, *c2;
-	LIST_HEAD(busy);
-	int i;
-
 	BUG_ON(!is_root_cache(s));
 
-	/*
-	 * First, shutdown active caches, i.e. caches that belong to online
-	 * memory cgroups.
-	 */
-	arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
-					lockdep_is_held(&slab_mutex));
-	for_each_memcg_cache_index(i) {
-		c = arr->entries[i];
-		if (!c)
-			continue;
-		if (shutdown_cache(c))
-			/*
-			 * The cache still has objects. Move it to a temporary
-			 * list so as not to try to destroy it for a second
-			 * time while iterating over inactive caches below.
-			 */
-			list_move(&c->memcg_params.children_node, &busy);
-		else
-			/*
-			 * The cache is empty and will be destroyed soon. Clear
-			 * the pointer to it in the memcg_caches array so that
-			 * it will never be accessed even if the root cache
-			 * stays alive.
-			 */
-			arr->entries[i] = NULL;
-	}
-
-	/*
-	 * Second, shutdown all caches left from memory cgroups that are now
-	 * offline.
-	 */
-	list_for_each_entry_safe(c, c2, &s->memcg_params.children,
-				 memcg_params.children_node)
-		shutdown_cache(c);
-
-	list_splice(&busy, &s->memcg_params.children);
+	if (s->memcg_params.memcg_cache)
+		WARN_ON(shutdown_cache(s->memcg_params.memcg_cache));
 
-	/*
-	 * A cache being destroyed must be empty. In particular, this means
-	 * that all per memcg caches attached to it must be empty too.
-	 */
-	if (!list_empty(&s->memcg_params.children))
-		return -EBUSY;
 	return 0;
 }
 
-static void memcg_set_kmem_cache_dying(struct kmem_cache *s)
-{
-	spin_lock_irq(&memcg_kmem_wq_lock);
-	s->memcg_params.dying = true;
-	spin_unlock_irq(&memcg_kmem_wq_lock);
-}
-
 static void flush_memcg_workqueue(struct kmem_cache *s)
 {
-	/*
-	 * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
-	 * sure all registered rcu callbacks have been invoked.
-	 */
-	rcu_barrier();
-
 	/*
 	 * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
 	 * deactivates the memcg kmem_caches through workqueue. Make sure all
@@ -918,30 +595,21 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
 	 */
 	if (likely(memcg_kmem_cache_wq))
 		flush_workqueue(memcg_kmem_cache_wq);
-
-	/*
-	 * If we're racing with children kmem_cache deactivation, it might
-	 * take another rcu grace period to complete their destruction.
-	 * At this moment the corresponding percpu_ref_kill() call should be
-	 * done, but it might take another rcu grace period to complete
-	 * switching to the atomic mode.
-	 * Please, note that we check without grabbing the slab_mutex. It's safe
-	 * because at this moment the children list can't grow.
-	 */
-	if (!list_empty(&s->memcg_params.children))
-		rcu_barrier();
 }
 #else
 static inline int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	return 0;
 }
+
+static inline void flush_memcg_workqueue(struct kmem_cache *s)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
 	__kmem_cache_release(s);
-	destroy_memcg_params(s);
 	kfree_const(s->name);
 	kmem_cache_free(kmem_cache, s);
 }
@@ -953,6 +621,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
+	flush_memcg_workqueue(s);
+
 	get_online_cpus();
 	get_online_mems();
 
@@ -962,22 +632,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
-#ifdef CONFIG_MEMCG_KMEM
-	memcg_set_kmem_cache_dying(s);
-
-	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
-
-	flush_memcg_workqueue(s);
-
-	get_online_cpus();
-	get_online_mems();
-
-	mutex_lock(&slab_mutex);
-#endif
-
 	err = shutdown_memcg_caches(s);
 	if (!err)
 		err = shutdown_cache(s);
@@ -1019,7 +673,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 EXPORT_SYMBOL(kmem_cache_shrink);
 
 /**
- * kmem_cache_shrink_all - shrink a cache and all memcg caches for root cache
+ * kmem_cache_shrink_all - shrink root and memcg caches
  * @s: The cache pointer
  */
 void kmem_cache_shrink_all(struct kmem_cache *s)
@@ -1036,21 +690,11 @@ void kmem_cache_shrink_all(struct kmem_cache *s)
 	kasan_cache_shrink(s);
 	__kmem_cache_shrink(s);
 
-	/*
-	 * We have to take the slab_mutex to protect from the memcg list
-	 * modification.
-	 */
-	mutex_lock(&slab_mutex);
-	for_each_memcg_cache(c, s) {
-		/*
-		 * Don't need to shrink deactivated memcg caches.
-		 */
-		if (s->flags & SLAB_DEACTIVATED)
-			continue;
+	c = memcg_cache(s);
+	if (c) {
 		kasan_cache_shrink(c);
 		__kmem_cache_shrink(c);
 	}
-	mutex_unlock(&slab_mutex);
 	put_online_mems();
 	put_online_cpus();
 }
@@ -1105,7 +749,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name,
 
 	create_boot_cache(s, name, size, flags, useroffset, usersize);
 	list_add(&s->list, &slab_caches);
-	memcg_link_cache(s, NULL);
+	memcg_link_cache(s);
 	s->refcount = 1;
 	return s;
 }
@@ -1483,7 +1127,8 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 	if (!is_root_cache(s))
 		return;
 
-	for_each_memcg_cache(c, s) {
+	c = memcg_cache(s);
+	if (c) {
 		memset(&sinfo, 0, sizeof(sinfo));
 		get_slabinfo(c, &sinfo);
 
@@ -1614,7 +1259,7 @@ module_init(slab_proc_init);
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM)
 /*
- * Display information about kmem caches that have child memcg caches.
+ * Display information about kmem caches that have memcg cache.
  */
 static int memcg_slabinfo_show(struct seq_file *m, void *unused)
 {
@@ -1626,9 +1271,9 @@ static int memcg_slabinfo_show(struct seq_file *m, void *unused)
 	seq_puts(m, " <active_slabs> <num_slabs>\n");
 	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
 		/*
-		 * Skip kmem caches that don't have any memcg children.
+		 * Skip kmem caches that don't have the memcg cache.
 		 */
-		if (list_empty(&s->memcg_params.children))
+		if (!s->memcg_params.memcg_cache)
 			continue;
 
 		memset(&sinfo, 0, sizeof(sinfo));
@@ -1637,23 +1282,13 @@ static int memcg_slabinfo_show(struct seq_file *m, void *unused)
 			   cache_name(s), sinfo.active_objs, sinfo.num_objs,
 			   sinfo.active_slabs, sinfo.num_slabs);
 
-		for_each_memcg_cache(c, s) {
-			struct cgroup_subsys_state *css;
-			char *status = "";
-
-			css = &c->memcg_params.memcg->css;
-			if (!(css->flags & CSS_ONLINE))
-				status = ":dead";
-			else if (c->flags & SLAB_DEACTIVATED)
-				status = ":deact";
-
-			memset(&sinfo, 0, sizeof(sinfo));
-			get_slabinfo(c, &sinfo);
-			seq_printf(m, "%-17s %4d%-6s %6lu %6lu %6lu %6lu\n",
-				   cache_name(c), css->id, status,
-				   sinfo.active_objs, sinfo.num_objs,
-				   sinfo.active_slabs, sinfo.num_slabs);
-		}
+		c = s->memcg_params.memcg_cache;
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(c, &sinfo);
+		seq_printf(m, "%-17s %4d %6lu %6lu %6lu %6lu\n",
+			   cache_name(c), root_mem_cgroup->css.id,
+			   sinfo.active_objs, sinfo.num_objs,
+			   sinfo.active_slabs, sinfo.num_slabs);
 	}
 	mutex_unlock(&slab_mutex);
 	return 0;
diff --git a/mm/slub.c b/mm/slub.c
index 47e63b1100d4..44a48a08a691 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4204,36 +4204,6 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	return ret;
 }
 
-#ifdef CONFIG_MEMCG
-void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
-{
-	/*
-	 * Called with all the locks held after a sched RCU grace period.
-	 * Even if @s becomes empty after shrinking, we can't know that @s
-	 * doesn't have allocations already in-flight and thus can't
-	 * destroy @s until the associated memcg is released.
-	 *
-	 * However, let's remove the sysfs files for empty caches here.
-	 * Each cache has a lot of interface files which aren't
-	 * particularly useful for empty draining caches; otherwise, we can
-	 * easily end up with millions of unnecessary sysfs files on
-	 * systems which have a lot of memory and transient cgroups.
-	 */
-	if (!__kmem_cache_shrink(s))
-		sysfs_slab_remove(s);
-}
-
-void __kmemcg_cache_deactivate(struct kmem_cache *s)
-{
-	/*
-	 * Disable empty slabs caching. Used to avoid pinning offline
-	 * memory cgroups by kmem pages that can be freed.
-	 */
-	slub_set_cpu_partial(s, 0);
-	s->min_partial = 0;
-}
-#endif	/* CONFIG_MEMCG */
-
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
@@ -4390,7 +4360,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 	}
 	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
-	memcg_link_cache(s, NULL);
+	memcg_link_cache(s);
 	return s;
 }
 
@@ -4458,7 +4428,8 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		s->object_size = max(s->object_size, size);
 		s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
 
-		for_each_memcg_cache(c, s) {
+		c = memcg_cache(s);
+		if (c) {
 			c->object_size = s->object_size;
 			c->inuse = max(c->inuse, ALIGN(size, sizeof(void *)));
 		}
@@ -5591,7 +5562,8 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		 * directly either failed or succeeded, in which case we loop
 		 * through the descendants with best-effort propagation.
 		 */
-		for_each_memcg_cache(c, s)
+		c = memcg_cache(s);
+		if (c)
 			attribute->store(c, buf, len);
 		mutex_unlock(&slab_mutex);
 	}
-- 
cgit v1.2.3


From d797b7d05405c519f7b62ea69a75cea1883863b2 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:14 -0700
Subject: mm: memcg/slab: simplify memcg cache creation

Because the number of non-root kmem_caches doesn't depend on the number of
memory cgroups anymore and is generally not very big, there is no more
need for a dedicated workqueue.

Also, as there is no more need to pass any arguments to the
memcg_create_kmem_cache() except the root kmem_cache, it's possible to
just embed the work structure into the kmem_cache and avoid the dynamic
allocation of the work structure.

This will also simplify the synchronization: for each root kmem_cache
there is only one work.  So there will be no more concurrent attempts to
create a non-root kmem_cache for a root kmem_cache: the second and all
following attempts to queue the work will fail.

On the kmem_cache destruction path there is no more need to call the
expensive flush_workqueue() and wait for all pending works to be finished.
Instead, cancel_work_sync() can be used to cancel/wait for only one work.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-14-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  1 -
 mm/memcontrol.c            | 48 +---------------------------------------------
 mm/slab.h                  |  2 ++
 mm/slab_common.c           | 22 +++++++++++----------
 4 files changed, 15 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 11fd18b3d6c6..2ac84dcfc9e5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1418,7 +1418,6 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
 void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
 
 extern struct static_key_false memcg_kmem_enabled_key;
-extern struct workqueue_struct *memcg_kmem_cache_wq;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 874704c4a48a..c713867e496d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -399,8 +399,6 @@ void memcg_put_cache_ids(void)
  */
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
-
-struct workqueue_struct *memcg_kmem_cache_wq;
 #endif
 
 static int memcg_shrinker_map_size;
@@ -2902,39 +2900,6 @@ static void memcg_free_cache_id(int id)
 	ida_simple_remove(&memcg_cache_ida, id);
 }
 
-struct memcg_kmem_cache_create_work {
-	struct kmem_cache *cachep;
-	struct work_struct work;
-};
-
-static void memcg_kmem_cache_create_func(struct work_struct *w)
-{
-	struct memcg_kmem_cache_create_work *cw =
-		container_of(w, struct memcg_kmem_cache_create_work, work);
-	struct kmem_cache *cachep = cw->cachep;
-
-	memcg_create_kmem_cache(cachep);
-
-	kfree(cw);
-}
-
-/*
- * Enqueue the creation of a per-memcg kmem_cache.
- */
-static void memcg_schedule_kmem_cache_create(struct kmem_cache *cachep)
-{
-	struct memcg_kmem_cache_create_work *cw;
-
-	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
-	if (!cw)
-		return;
-
-	cw->cachep = cachep;
-	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
-
-	queue_work(memcg_kmem_cache_wq, &cw->work);
-}
-
 /**
  * memcg_kmem_get_cache: select memcg or root cache for allocation
  * @cachep: the original global kmem cache
@@ -2951,7 +2916,7 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 
 	memcg_cachep = READ_ONCE(cachep->memcg_params.memcg_cache);
 	if (unlikely(!memcg_cachep)) {
-		memcg_schedule_kmem_cache_create(cachep);
+		queue_work(system_wq, &cachep->memcg_params.work);
 		return cachep;
 	}
 
@@ -7022,17 +6987,6 @@ static int __init mem_cgroup_init(void)
 {
 	int cpu, node;
 
-#ifdef CONFIG_MEMCG_KMEM
-	/*
-	 * Kmem cache creation is mostly done with the slab_mutex held,
-	 * so use a workqueue with limited concurrency to avoid stalling
-	 * all worker threads in case lots of cgroups are created and
-	 * destroyed simultaneously.
-	 */
-	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
-	BUG_ON(!memcg_kmem_cache_wq);
-#endif
-
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);
 
diff --git a/mm/slab.h b/mm/slab.h
index e716b80befc2..fd9fcdfb3789 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -45,12 +45,14 @@ struct kmem_cache {
  * @memcg_cache: pointer to memcg kmem cache, used by all non-root memory
  *		cgroups.
  * @root_caches_node: list node for slab_root_caches list.
+ * @work: work struct used to create the non-root cache.
  */
 struct memcg_cache_params {
 	struct kmem_cache *root_cache;
 
 	struct kmem_cache *memcg_cache;
 	struct list_head __root_caches_node;
+	struct work_struct work;
 };
 #endif /* CONFIG_SLOB */
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index e752132eb64d..b898698f6c8a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -134,10 +134,18 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 
 LIST_HEAD(slab_root_caches);
 
+static void memcg_kmem_cache_create_func(struct work_struct *work)
+{
+	struct kmem_cache *cachep = container_of(work, struct kmem_cache,
+						 memcg_params.work);
+	memcg_create_kmem_cache(cachep);
+}
+
 void slab_init_memcg_params(struct kmem_cache *s)
 {
 	s->memcg_params.root_cache = NULL;
 	s->memcg_params.memcg_cache = NULL;
+	INIT_WORK(&s->memcg_params.work, memcg_kmem_cache_create_func);
 }
 
 static void init_memcg_params(struct kmem_cache *s,
@@ -586,15 +594,9 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 	return 0;
 }
 
-static void flush_memcg_workqueue(struct kmem_cache *s)
+static void cancel_memcg_cache_creation(struct kmem_cache *s)
 {
-	/*
-	 * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
-	 * deactivates the memcg kmem_caches through workqueue. Make sure all
-	 * previous workitems on workqueue are processed.
-	 */
-	if (likely(memcg_kmem_cache_wq))
-		flush_workqueue(memcg_kmem_cache_wq);
+	cancel_work_sync(&s->memcg_params.work);
 }
 #else
 static inline int shutdown_memcg_caches(struct kmem_cache *s)
@@ -602,7 +604,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s)
 	return 0;
 }
 
-static inline void flush_memcg_workqueue(struct kmem_cache *s)
+static inline void cancel_memcg_cache_creation(struct kmem_cache *s)
 {
 }
 #endif /* CONFIG_MEMCG_KMEM */
@@ -621,7 +623,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
-	flush_memcg_workqueue(s);
+	cancel_memcg_cache_creation(s);
 
 	get_online_cpus();
 	get_online_mems();
-- 
cgit v1.2.3


From 272911a4ad18c48f8bc449a5db945a54987dd687 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:17 -0700
Subject: mm: memcg/slab: remove memcg_kmem_get_cache()

The memcg_kmem_get_cache() function became really trivial, so let's just
inline it into the single call point: memcg_slab_pre_alloc_hook().

It will make the code less bulky and can also help the compiler to
generate a better code.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-15-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  2 --
 mm/memcontrol.c            | 25 +------------------------
 mm/slab.h                  | 11 +++++++++--
 mm/slab_common.c           |  2 +-
 4 files changed, 11 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2ac84dcfc9e5..5a8b62d075e6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1403,8 +1403,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 }
 #endif
 
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
-
 #ifdef CONFIG_MEMCG_KMEM
 int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
 			unsigned int nr_pages);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c713867e496d..a8113b77b23a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -393,7 +393,7 @@ void memcg_put_cache_ids(void)
 
 /*
  * A lot of the calls to the cache allocation functions are expected to be
- * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
+ * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are
  * conditional to this static branch, we'll have to allow modules that does
  * kmem_cache_alloc and the such to see this symbol as well
  */
@@ -2900,29 +2900,6 @@ static void memcg_free_cache_id(int id)
 	ida_simple_remove(&memcg_cache_ida, id);
 }
 
-/**
- * memcg_kmem_get_cache: select memcg or root cache for allocation
- * @cachep: the original global kmem cache
- *
- * Return the kmem_cache we're supposed to use for a slab allocation.
- *
- * If the cache does not exist yet, if we are the first user of it, we
- * create it asynchronously in a workqueue and let the current allocation
- * go through with the original cache.
- */
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
-{
-	struct kmem_cache *memcg_cachep;
-
-	memcg_cachep = READ_ONCE(cachep->memcg_params.memcg_cache);
-	if (unlikely(!memcg_cachep)) {
-		queue_work(system_wq, &cachep->memcg_params.work);
-		return cachep;
-	}
-
-	return memcg_cachep;
-}
-
 /**
  * __memcg_kmem_charge: charge a number of kernel pages to a memcg
  * @memcg: memory cgroup to charge
diff --git a/mm/slab.h b/mm/slab.h
index fd9fcdfb3789..342eac852967 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -365,9 +365,16 @@ static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 	if (memcg_kmem_bypass())
 		return s;
 
-	cachep = memcg_kmem_get_cache(s);
-	if (is_root_cache(cachep))
+	cachep = READ_ONCE(s->memcg_params.memcg_cache);
+	if (unlikely(!cachep)) {
+		/*
+		 * If memcg cache does not exist yet, we schedule it's
+		 * asynchronous creation and let the current allocation
+		 * go through with the root cache.
+		 */
+		queue_work(system_wq, &s->memcg_params.work);
 		return s;
+	}
 
 	objcg = get_obj_cgroup_from_current();
 	if (!objcg)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index b898698f6c8a..de0a46cf974a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -570,7 +570,7 @@ void memcg_create_kmem_cache(struct kmem_cache *root_cache)
 	}
 
 	/*
-	 * Since readers won't lock (see memcg_kmem_get_cache()), we need a
+	 * Since readers won't lock (see memcg_slab_pre_alloc_hook()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
 	 * initialized.
 	 */
-- 
cgit v1.2.3


From 10befea91b61c4e2c2d1df06a2e978d182fcf792 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:27 -0700
Subject: mm: memcg/slab: use a single set of kmem_caches for all allocations

Instead of having two sets of kmem_caches: one for system-wide and
non-accounted allocations and the second one shared by all accounted
allocations, we can use just one.

The idea is simple: space for obj_cgroup metadata can be allocated on
demand and filled only for accounted allocations.

It allows to remove a bunch of code which is required to handle kmem_cache
clones for accounted allocations.  There is no more need to create them,
accumulate statistics, propagate attributes, etc.  It's a quite
significant simplification.

Also, because the total number of slab_caches is reduced almost twice (not
all kmem_caches have a memcg clone), some additional memory savings are
expected.  On my devvm it additionally saves about 3.5% of slab memory.

[guro@fb.com: fix build on MIPS]
  Link: http://lkml.kernel.org/r/20200717214810.3733082-1-guro@fb.com

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-18-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h     |   2 -
 include/linux/slab_def.h |   3 -
 include/linux/slub_def.h |  10 ---
 mm/memcontrol.c          |  25 +++++-
 mm/slab.c                |  41 +--------
 mm/slab.h                | 194 +++++++++------------------------------
 mm/slab_common.c         | 230 ++---------------------------------------------
 mm/slub.c                | 163 +--------------------------------
 8 files changed, 78 insertions(+), 590 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 8b1f91e320f9..24df2393ec03 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -155,8 +155,6 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name,
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 
-void memcg_create_kmem_cache(struct kmem_cache *cachep);
-
 /*
  * Please use this macro to create slab caches. Simply specify the
  * name of the structure and maybe some flags that are listed above.
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index ccda7b9669a5..9eb430c163c2 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -72,9 +72,6 @@ struct kmem_cache {
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
 
-#ifdef CONFIG_MEMCG
-	struct memcg_cache_params memcg_params;
-#endif
 #ifdef CONFIG_KASAN
 	struct kasan_cache kasan_info;
 #endif
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index f87302dcfe8c..1be0ed5befa1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -108,17 +108,7 @@ struct kmem_cache {
 	struct list_head list;	/* List of slab caches */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
-	struct work_struct kobj_remove_work;
 #endif
-#ifdef CONFIG_MEMCG
-	struct memcg_cache_params memcg_params;
-	/* For propagation, maximum size of a stored attr */
-	unsigned int max_attr_size;
-#ifdef CONFIG_SYSFS
-	struct kset *memcg_kset;
-#endif
-#endif
-
 #ifdef CONFIG_SLAB_FREELIST_HARDENED
 	unsigned long random;
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a8113b77b23a..473f9b91d51f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2800,6 +2800,26 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
+				 gfp_t gfp)
+{
+	unsigned int objects = objs_per_slab_page(s, page);
+	void *vec;
+
+	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
+			   page_to_nid(page));
+	if (!vec)
+		return -ENOMEM;
+
+	if (cmpxchg(&page->obj_cgroups, NULL,
+		    (struct obj_cgroup **) ((unsigned long)vec | 0x1UL)))
+		kfree(vec);
+	else
+		kmemleak_not_leak(vec);
+
+	return 0;
+}
+
 /*
  * Returns a pointer to the memory cgroup to which the kernel object is charged.
  *
@@ -2826,7 +2846,10 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 
 		off = obj_to_index(page->slab_cache, page, p);
 		objcg = page_obj_cgroups(page)[off];
-		return obj_cgroup_memcg(objcg);
+		if (objcg)
+			return obj_cgroup_memcg(objcg);
+
+		return NULL;
 	}
 
 	/* All other pages use page->mem_cgroup */
diff --git a/mm/slab.c b/mm/slab.c
index f40e5c95e11a..684ebe5b0c7a 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1379,11 +1379,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	if (charge_slab_page(page, flags, cachep->gfporder, cachep)) {
-		__free_pages(page, cachep->gfporder);
-		return NULL;
-	}
-
+	charge_slab_page(page, flags, cachep->gfporder, cachep);
 	__SetPageSlab(page);
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
@@ -3799,8 +3795,8 @@ fail:
 }
 
 /* Always called with the slab_mutex held */
-static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
-				int batchcount, int shared, gfp_t gfp)
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+			    int batchcount, int shared, gfp_t gfp)
 {
 	struct array_cache __percpu *cpu_cache, *prev;
 	int cpu;
@@ -3845,30 +3841,6 @@ setup_node:
 	return setup_kmem_cache_nodes(cachep, gfp);
 }
 
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
-				int batchcount, int shared, gfp_t gfp)
-{
-	int ret;
-	struct kmem_cache *c;
-
-	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
-
-	if (slab_state < FULL)
-		return ret;
-
-	if ((ret < 0) || !is_root_cache(cachep))
-		return ret;
-
-	lockdep_assert_held(&slab_mutex);
-	c = memcg_cache(cachep);
-	if (c) {
-		/* return value determined by the root cache only */
-		__do_tune_cpucache(c, limit, batchcount, shared, gfp);
-	}
-
-	return ret;
-}
-
 /* Called with slab_mutex held always */
 static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 {
@@ -3881,13 +3853,6 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 	if (err)
 		goto end;
 
-	if (!is_root_cache(cachep)) {
-		struct kmem_cache *root = memcg_root_cache(cachep);
-		limit = root->limit;
-		shared = root->shared;
-		batchcount = root->batchcount;
-	}
-
 	if (limit && shared && batchcount)
 		goto skip_setup;
 	/*
diff --git a/mm/slab.h b/mm/slab.h
index 7500a707121b..ec8e22ee6544 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -30,28 +30,6 @@ struct kmem_cache {
 	struct list_head list;	/* List of all slab caches on the system */
 };
 
-#else /* !CONFIG_SLOB */
-
-/*
- * This is the main placeholder for memcg-related information in kmem caches.
- * Both the root cache and the child cache will have it. Some fields are used
- * in both cases, other are specific to root caches.
- *
- * @root_cache:	Common to root and child caches.  NULL for root, pointer to
- *		the root cache for children.
- *
- * The following fields are specific to root caches.
- *
- * @memcg_cache: pointer to memcg kmem cache, used by all non-root memory
- *		cgroups.
- * @work: work struct used to create the non-root cache.
- */
-struct memcg_cache_params {
-	struct kmem_cache *root_cache;
-
-	struct kmem_cache *memcg_cache;
-	struct work_struct work;
-};
 #endif /* CONFIG_SLOB */
 
 #ifdef CONFIG_SLAB
@@ -196,7 +174,6 @@ int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
 void slab_kmem_cache_release(struct kmem_cache *);
-void kmem_cache_shrink_all(struct kmem_cache *s);
 
 struct seq_file;
 struct file;
@@ -263,43 +240,6 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-static inline bool is_root_cache(struct kmem_cache *s)
-{
-	return !s->memcg_params.root_cache;
-}
-
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
-{
-	return p == s || p == s->memcg_params.root_cache;
-}
-
-/*
- * We use suffixes to the name in memcg because we can't have caches
- * created in the system with the same name. But when we print them
- * locally, better refer to them with the base name
- */
-static inline const char *cache_name(struct kmem_cache *s)
-{
-	if (!is_root_cache(s))
-		s = s->memcg_params.root_cache;
-	return s->name;
-}
-
-static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
-{
-	if (is_root_cache(s))
-		return s;
-	return s->memcg_params.root_cache;
-}
-
-static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
-{
-	if (is_root_cache(s))
-		return s->memcg_params.memcg_cache;
-	return NULL;
-}
-
 static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 {
 	/*
@@ -317,21 +257,8 @@ static inline bool page_has_obj_cgroups(struct page *page)
 	return ((unsigned long)page->obj_cgroups & 0x1UL);
 }
 
-static inline int memcg_alloc_page_obj_cgroups(struct page *page,
-					       struct kmem_cache *s, gfp_t gfp)
-{
-	unsigned int objects = objs_per_slab_page(s, page);
-	void *vec;
-
-	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
-			   page_to_nid(page));
-	if (!vec)
-		return -ENOMEM;
-
-	kmemleak_not_leak(vec);
-	page->obj_cgroups = (struct obj_cgroup **) ((unsigned long)vec | 0x1UL);
-	return 0;
-}
+int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
+				 gfp_t gfp);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -348,38 +275,25 @@ static inline size_t obj_full_size(struct kmem_cache *s)
 	return s->size + sizeof(struct obj_cgroup *);
 }
 
-static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-						struct obj_cgroup **objcgp,
-						size_t objects, gfp_t flags)
+static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+							   size_t objects,
+							   gfp_t flags)
 {
-	struct kmem_cache *cachep;
 	struct obj_cgroup *objcg;
 
 	if (memcg_kmem_bypass())
-		return s;
-
-	cachep = READ_ONCE(s->memcg_params.memcg_cache);
-	if (unlikely(!cachep)) {
-		/*
-		 * If memcg cache does not exist yet, we schedule it's
-		 * asynchronous creation and let the current allocation
-		 * go through with the root cache.
-		 */
-		queue_work(system_wq, &s->memcg_params.work);
-		return s;
-	}
+		return NULL;
 
 	objcg = get_obj_cgroup_from_current();
 	if (!objcg)
-		return s;
+		return NULL;
 
 	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
 		obj_cgroup_put(objcg);
-		cachep = NULL;
+		return NULL;
 	}
 
-	*objcgp = objcg;
-	return cachep;
+	return objcg;
 }
 
 static inline void mod_objcg_state(struct obj_cgroup *objcg,
@@ -398,15 +312,27 @@ static inline void mod_objcg_state(struct obj_cgroup *objcg,
 
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
-					      size_t size, void **p)
+					      gfp_t flags, size_t size,
+					      void **p)
 {
 	struct page *page;
 	unsigned long off;
 	size_t i;
 
+	if (!objcg)
+		return;
+
+	flags &= ~__GFP_ACCOUNT;
 	for (i = 0; i < size; i++) {
 		if (likely(p[i])) {
 			page = virt_to_head_page(p[i]);
+
+			if (!page_has_obj_cgroups(page) &&
+			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+				obj_cgroup_uncharge(objcg, obj_full_size(s));
+				continue;
+			}
+
 			off = obj_to_index(s, page, p[i]);
 			obj_cgroup_get(objcg);
 			page_obj_cgroups(page)[off] = objcg;
@@ -425,13 +351,19 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 	struct obj_cgroup *objcg;
 	unsigned int off;
 
-	if (!memcg_kmem_enabled() || is_root_cache(s))
+	if (!memcg_kmem_enabled())
+		return;
+
+	if (!page_has_obj_cgroups(page))
 		return;
 
 	off = obj_to_index(s, page, p);
 	objcg = page_obj_cgroups(page)[off];
 	page_obj_cgroups(page)[off] = NULL;
 
+	if (!objcg)
+		return;
+
 	obj_cgroup_uncharge(objcg, obj_full_size(s));
 	mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
 			-obj_full_size(s));
@@ -439,35 +371,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 	obj_cgroup_put(objcg);
 }
 
-extern void slab_init_memcg_params(struct kmem_cache *);
-
 #else /* CONFIG_MEMCG_KMEM */
-static inline bool is_root_cache(struct kmem_cache *s)
-{
-	return true;
-}
-
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
-{
-	return s == p;
-}
-
-static inline const char *cache_name(struct kmem_cache *s)
-{
-	return s->name;
-}
-
-static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
-{
-	return s;
-}
-
-static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
-{
-	return NULL;
-}
-
 static inline bool page_has_obj_cgroups(struct page *page)
 {
 	return false;
@@ -488,16 +392,17 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 }
 
-static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-						struct obj_cgroup **objcgp,
-						size_t objects, gfp_t flags)
+static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+							   size_t objects,
+							   gfp_t flags)
 {
 	return NULL;
 }
 
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
-					      size_t size, void **p)
+					      gfp_t flags, size_t size,
+					      void **p)
 {
 }
 
@@ -505,11 +410,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 					void *p)
 {
 }
-
-static inline void slab_init_memcg_params(struct kmem_cache *s)
-{
-}
-
 #endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *virt_to_cache(const void *obj)
@@ -523,27 +423,18 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 	return page->slab_cache;
 }
 
-static __always_inline int charge_slab_page(struct page *page,
-					    gfp_t gfp, int order,
-					    struct kmem_cache *s)
+static __always_inline void charge_slab_page(struct page *page,
+					     gfp_t gfp, int order,
+					     struct kmem_cache *s)
 {
-	if (memcg_kmem_enabled() && !is_root_cache(s)) {
-		int ret;
-
-		ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
-		if (ret)
-			return ret;
-	}
-
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
-	return 0;
 }
 
 static __always_inline void uncharge_slab_page(struct page *page, int order,
 					       struct kmem_cache *s)
 {
-	if (memcg_kmem_enabled() && !is_root_cache(s))
+	if (memcg_kmem_enabled())
 		memcg_free_page_obj_cgroups(page);
 
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
@@ -555,12 +446,11 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 	struct kmem_cache *cachep;
 
 	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    !memcg_kmem_enabled() &&
 	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
 		return s;
 
 	cachep = virt_to_cache(x);
-	if (WARN(cachep && !slab_equal_or_root(cachep, s),
+	if (WARN(cachep && cachep != s,
 		  "%s: Wrong slab cache. %s but object is from %s\n",
 		  __func__, s->name, cachep->name))
 		print_tracking(cachep, x);
@@ -613,7 +503,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 
 	if (memcg_kmem_enabled() &&
 	    ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
-		return memcg_slab_pre_alloc_hook(s, objcgp, size, flags);
+		*objcgp = memcg_slab_pre_alloc_hook(s, size, flags);
 
 	return s;
 }
@@ -632,8 +522,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
 					 s->flags, flags);
 	}
 
-	if (memcg_kmem_enabled() && !is_root_cache(s))
-		memcg_slab_post_alloc_hook(s, objcg, size, p);
+	if (memcg_kmem_enabled())
+		memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
 }
 
 #ifndef CONFIG_SLOB
diff --git a/mm/slab_common.c b/mm/slab_common.c
index ad67a03c592a..a513f3237155 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -130,36 +130,6 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 	return i;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-static void memcg_kmem_cache_create_func(struct work_struct *work)
-{
-	struct kmem_cache *cachep = container_of(work, struct kmem_cache,
-						 memcg_params.work);
-	memcg_create_kmem_cache(cachep);
-}
-
-void slab_init_memcg_params(struct kmem_cache *s)
-{
-	s->memcg_params.root_cache = NULL;
-	s->memcg_params.memcg_cache = NULL;
-	INIT_WORK(&s->memcg_params.work, memcg_kmem_cache_create_func);
-}
-
-static void init_memcg_params(struct kmem_cache *s,
-			      struct kmem_cache *root_cache)
-{
-	if (root_cache)
-		s->memcg_params.root_cache = root_cache;
-	else
-		slab_init_memcg_params(s);
-}
-#else
-static inline void init_memcg_params(struct kmem_cache *s,
-				     struct kmem_cache *root_cache)
-{
-}
-#endif /* CONFIG_MEMCG_KMEM */
-
 /*
  * Figure out what the alignment of the objects will be given a set of
  * flags, a user specified alignment and the size of the objects.
@@ -197,9 +167,6 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
 		return 1;
 
-	if (!is_root_cache(s))
-		return 1;
-
 	if (s->ctor)
 		return 1;
 
@@ -286,7 +253,6 @@ static struct kmem_cache *create_cache(const char *name,
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
-	init_memcg_params(s, root_cache);
 	err = __kmem_cache_create(s, flags);
 	if (err)
 		goto out_free_cache;
@@ -344,7 +310,6 @@ kmem_cache_create_usercopy(const char *name,
 
 	get_online_cpus();
 	get_online_mems();
-	memcg_get_cache_ids();
 
 	mutex_lock(&slab_mutex);
 
@@ -394,7 +359,6 @@ kmem_cache_create_usercopy(const char *name,
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
-	memcg_put_cache_ids();
 	put_online_mems();
 	put_online_cpus();
 
@@ -507,87 +471,6 @@ static int shutdown_cache(struct kmem_cache *s)
 	return 0;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-/*
- * memcg_create_kmem_cache - Create a cache for non-root memory cgroups.
- * @root_cache: The parent of the new cache.
- *
- * This function attempts to create a kmem cache that will serve allocation
- * requests going all non-root memory cgroups to @root_cache. The new cache
- * inherits properties from its parent.
- */
-void memcg_create_kmem_cache(struct kmem_cache *root_cache)
-{
-	struct kmem_cache *s = NULL;
-	char *cache_name;
-
-	get_online_cpus();
-	get_online_mems();
-
-	mutex_lock(&slab_mutex);
-
-	if (root_cache->memcg_params.memcg_cache)
-		goto out_unlock;
-
-	cache_name = kasprintf(GFP_KERNEL, "%s-memcg", root_cache->name);
-	if (!cache_name)
-		goto out_unlock;
-
-	s = create_cache(cache_name, root_cache->object_size,
-			 root_cache->align,
-			 root_cache->flags & CACHE_CREATE_MASK,
-			 root_cache->useroffset, root_cache->usersize,
-			 root_cache->ctor, root_cache);
-	/*
-	 * If we could not create a memcg cache, do not complain, because
-	 * that's not critical at all as we can always proceed with the root
-	 * cache.
-	 */
-	if (IS_ERR(s)) {
-		kfree(cache_name);
-		goto out_unlock;
-	}
-
-	/*
-	 * Since readers won't lock (see memcg_slab_pre_alloc_hook()), we need a
-	 * barrier here to ensure nobody will see the kmem_cache partially
-	 * initialized.
-	 */
-	smp_wmb();
-	root_cache->memcg_params.memcg_cache = s;
-
-out_unlock:
-	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
-}
-
-static int shutdown_memcg_caches(struct kmem_cache *s)
-{
-	BUG_ON(!is_root_cache(s));
-
-	if (s->memcg_params.memcg_cache)
-		WARN_ON(shutdown_cache(s->memcg_params.memcg_cache));
-
-	return 0;
-}
-
-static void cancel_memcg_cache_creation(struct kmem_cache *s)
-{
-	cancel_work_sync(&s->memcg_params.work);
-}
-#else
-static inline int shutdown_memcg_caches(struct kmem_cache *s)
-{
-	return 0;
-}
-
-static inline void cancel_memcg_cache_creation(struct kmem_cache *s)
-{
-}
-#endif /* CONFIG_MEMCG_KMEM */
-
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
 	__kmem_cache_release(s);
@@ -602,8 +485,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
-	cancel_memcg_cache_creation(s);
-
 	get_online_cpus();
 	get_online_mems();
 
@@ -613,10 +494,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
-	err = shutdown_memcg_caches(s);
-	if (!err)
-		err = shutdown_cache(s);
-
+	err = shutdown_cache(s);
 	if (err) {
 		pr_err("kmem_cache_destroy %s: Slab cache still has objects\n",
 		       s->name);
@@ -653,33 +531,6 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
-/**
- * kmem_cache_shrink_all - shrink root and memcg caches
- * @s: The cache pointer
- */
-void kmem_cache_shrink_all(struct kmem_cache *s)
-{
-	struct kmem_cache *c;
-
-	if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || !is_root_cache(s)) {
-		kmem_cache_shrink(s);
-		return;
-	}
-
-	get_online_cpus();
-	get_online_mems();
-	kasan_cache_shrink(s);
-	__kmem_cache_shrink(s);
-
-	c = memcg_cache(s);
-	if (c) {
-		kasan_cache_shrink(c);
-		__kmem_cache_shrink(c);
-	}
-	put_online_mems();
-	put_online_cpus();
-}
-
 bool slab_is_available(void)
 {
 	return slab_state >= UP;
@@ -708,8 +559,6 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
-	slab_init_memcg_params(s);
-
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
@@ -1098,25 +947,6 @@ void slab_stop(struct seq_file *m, void *p)
 	mutex_unlock(&slab_mutex);
 }
 
-static void
-memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
-{
-	struct kmem_cache *c;
-	struct slabinfo sinfo;
-
-	c = memcg_cache(s);
-	if (c) {
-		memset(&sinfo, 0, sizeof(sinfo));
-		get_slabinfo(c, &sinfo);
-
-		info->active_slabs += sinfo.active_slabs;
-		info->num_slabs += sinfo.num_slabs;
-		info->shared_avail += sinfo.shared_avail;
-		info->active_objs += sinfo.active_objs;
-		info->num_objs += sinfo.num_objs;
-	}
-}
-
 static void cache_show(struct kmem_cache *s, struct seq_file *m)
 {
 	struct slabinfo sinfo;
@@ -1124,10 +954,8 @@ static void cache_show(struct kmem_cache *s, struct seq_file *m)
 	memset(&sinfo, 0, sizeof(sinfo));
 	get_slabinfo(s, &sinfo);
 
-	memcg_accumulate_slabinfo(s, &sinfo);
-
 	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
-		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
+		   s->name, sinfo.active_objs, sinfo.num_objs, s->size,
 		   sinfo.objects_per_slab, (1 << sinfo.cache_order));
 
 	seq_printf(m, " : tunables %4u %4u %4u",
@@ -1144,8 +972,7 @@ static int slab_show(struct seq_file *m, void *p)
 
 	if (p == slab_caches.next)
 		print_slabinfo_header(m);
-	if (is_root_cache(s))
-		cache_show(s, m);
+	cache_show(s, m);
 	return 0;
 }
 
@@ -1170,13 +997,13 @@ void dump_unreclaimable_slab(void)
 	pr_info("Name                      Used          Total\n");
 
 	list_for_each_entry_safe(s, s2, &slab_caches, list) {
-		if (!is_root_cache(s) || (s->flags & SLAB_RECLAIM_ACCOUNT))
+		if (s->flags & SLAB_RECLAIM_ACCOUNT)
 			continue;
 
 		get_slabinfo(s, &sinfo);
 
 		if (sinfo.num_objs > 0)
-			pr_info("%-17s %10luKB %10luKB\n", cache_name(s),
+			pr_info("%-17s %10luKB %10luKB\n", s->name,
 				(sinfo.active_objs * s->size) / 1024,
 				(sinfo.num_objs * s->size) / 1024);
 	}
@@ -1235,53 +1062,6 @@ static int __init slab_proc_init(void)
 }
 module_init(slab_proc_init);
 
-#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM)
-/*
- * Display information about kmem caches that have memcg cache.
- */
-static int memcg_slabinfo_show(struct seq_file *m, void *unused)
-{
-	struct kmem_cache *s, *c;
-	struct slabinfo sinfo;
-
-	mutex_lock(&slab_mutex);
-	seq_puts(m, "# <name> <css_id[:dead|deact]> <active_objs> <num_objs>");
-	seq_puts(m, " <active_slabs> <num_slabs>\n");
-	list_for_each_entry(s, &slab_caches, list) {
-		/*
-		 * Skip kmem caches that don't have the memcg cache.
-		 */
-		if (!s->memcg_params.memcg_cache)
-			continue;
-
-		memset(&sinfo, 0, sizeof(sinfo));
-		get_slabinfo(s, &sinfo);
-		seq_printf(m, "%-17s root       %6lu %6lu %6lu %6lu\n",
-			   cache_name(s), sinfo.active_objs, sinfo.num_objs,
-			   sinfo.active_slabs, sinfo.num_slabs);
-
-		c = s->memcg_params.memcg_cache;
-		memset(&sinfo, 0, sizeof(sinfo));
-		get_slabinfo(c, &sinfo);
-		seq_printf(m, "%-17s %4d %6lu %6lu %6lu %6lu\n",
-			   cache_name(c), root_mem_cgroup->css.id,
-			   sinfo.active_objs, sinfo.num_objs,
-			   sinfo.active_slabs, sinfo.num_slabs);
-	}
-	mutex_unlock(&slab_mutex);
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(memcg_slabinfo);
-
-static int __init memcg_slabinfo_init(void)
-{
-	debugfs_create_file("memcg_slabinfo", S_IFREG | S_IRUGO,
-			    NULL, NULL, &memcg_slabinfo_fops);
-	return 0;
-}
-
-late_initcall(memcg_slabinfo_init);
-#endif /* CONFIG_DEBUG_FS && CONFIG_MEMCG_KMEM */
 #endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */
 
 static __always_inline void *__do_krealloc(const void *p, size_t new_size,
diff --git a/mm/slub.c b/mm/slub.c
index 9cd724fe37d8..eba8f57d5734 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -218,14 +218,10 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 #ifdef CONFIG_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
-static void memcg_propagate_slab_attrs(struct kmem_cache *s);
-static void sysfs_slab_remove(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
-static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -1624,10 +1620,8 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 	else
 		page = __alloc_pages_node(node, flags, order);
 
-	if (page && charge_slab_page(page, flags, order, s)) {
-		__free_pages(page, order);
-		page = NULL;
-	}
+	if (page)
+		charge_slab_page(page, flags, order, s);
 
 	return page;
 }
@@ -3920,7 +3914,6 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
-	sysfs_slab_remove(s);
 	return 0;
 }
 
@@ -4358,7 +4351,6 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 			p->slab_cache = s;
 #endif
 	}
-	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
 	return s;
 }
@@ -4414,7 +4406,7 @@ struct kmem_cache *
 __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s, *c;
+	struct kmem_cache *s;
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
@@ -4427,12 +4419,6 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		s->object_size = max(s->object_size, size);
 		s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
 
-		c = memcg_cache(s);
-		if (c) {
-			c->object_size = s->object_size;
-			c->inuse = max(c->inuse, ALIGN(size, sizeof(void *)));
-		}
-
 		if (sysfs_slab_alias(s, name)) {
 			s->refcount--;
 			s = NULL;
@@ -4454,7 +4440,6 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
 	if (slab_state <= UP)
 		return 0;
 
-	memcg_propagate_slab_attrs(s);
 	err = sysfs_slab_add(s);
 	if (err)
 		__kmem_cache_release(s);
@@ -5312,7 +5297,7 @@ static ssize_t shrink_store(struct kmem_cache *s,
 			const char *buf, size_t length)
 {
 	if (buf[0] == '1')
-		kmem_cache_shrink_all(s);
+		kmem_cache_shrink(s);
 	else
 		return -EINVAL;
 	return length;
@@ -5536,99 +5521,9 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		return -EIO;
 
 	err = attribute->store(s, buf, len);
-#ifdef CONFIG_MEMCG
-	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-		struct kmem_cache *c;
-
-		mutex_lock(&slab_mutex);
-		if (s->max_attr_size < len)
-			s->max_attr_size = len;
-
-		/*
-		 * This is a best effort propagation, so this function's return
-		 * value will be determined by the parent cache only. This is
-		 * basically because not all attributes will have a well
-		 * defined semantics for rollbacks - most of the actions will
-		 * have permanent effects.
-		 *
-		 * Returning the error value of any of the children that fail
-		 * is not 100 % defined, in the sense that users seeing the
-		 * error code won't be able to know anything about the state of
-		 * the cache.
-		 *
-		 * Only returning the error code for the parent cache at least
-		 * has well defined semantics. The cache being written to
-		 * directly either failed or succeeded, in which case we loop
-		 * through the descendants with best-effort propagation.
-		 */
-		c = memcg_cache(s);
-		if (c)
-			attribute->store(c, buf, len);
-		mutex_unlock(&slab_mutex);
-	}
-#endif
 	return err;
 }
 
-static void memcg_propagate_slab_attrs(struct kmem_cache *s)
-{
-#ifdef CONFIG_MEMCG
-	int i;
-	char *buffer = NULL;
-	struct kmem_cache *root_cache;
-
-	if (is_root_cache(s))
-		return;
-
-	root_cache = s->memcg_params.root_cache;
-
-	/*
-	 * This mean this cache had no attribute written. Therefore, no point
-	 * in copying default values around
-	 */
-	if (!root_cache->max_attr_size)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
-		char mbuf[64];
-		char *buf;
-		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
-		ssize_t len;
-
-		if (!attr || !attr->store || !attr->show)
-			continue;
-
-		/*
-		 * It is really bad that we have to allocate here, so we will
-		 * do it only as a fallback. If we actually allocate, though,
-		 * we can just use the allocated buffer until the end.
-		 *
-		 * Most of the slub attributes will tend to be very small in
-		 * size, but sysfs allows buffers up to a page, so they can
-		 * theoretically happen.
-		 */
-		if (buffer)
-			buf = buffer;
-		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf) &&
-			 !IS_ENABLED(CONFIG_SLUB_STATS))
-			buf = mbuf;
-		else {
-			buffer = (char *) get_zeroed_page(GFP_KERNEL);
-			if (WARN_ON(!buffer))
-				continue;
-			buf = buffer;
-		}
-
-		len = attr->show(root_cache, buf);
-		if (len > 0)
-			attr->store(s, buf, len);
-	}
-
-	if (buffer)
-		free_page((unsigned long)buffer);
-#endif	/* CONFIG_MEMCG */
-}
-
 static void kmem_cache_release(struct kobject *k)
 {
 	slab_kmem_cache_release(to_slab(k));
@@ -5648,10 +5543,6 @@ static struct kset *slab_kset;
 
 static inline struct kset *cache_kset(struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG
-	if (!is_root_cache(s))
-		return s->memcg_params.root_cache->memcg_kset;
-#endif
 	return slab_kset;
 }
 
@@ -5694,27 +5585,6 @@ static char *create_unique_id(struct kmem_cache *s)
 	return name;
 }
 
-static void sysfs_slab_remove_workfn(struct work_struct *work)
-{
-	struct kmem_cache *s =
-		container_of(work, struct kmem_cache, kobj_remove_work);
-
-	if (!s->kobj.state_in_sysfs)
-		/*
-		 * For a memcg cache, this may be called during
-		 * deactivation and again on shutdown.  Remove only once.
-		 * A cache is never shut down before deactivation is
-		 * complete, so no need to worry about synchronization.
-		 */
-		goto out;
-
-#ifdef CONFIG_MEMCG
-	kset_unregister(s->memcg_kset);
-#endif
-out:
-	kobject_put(&s->kobj);
-}
-
 static int sysfs_slab_add(struct kmem_cache *s)
 {
 	int err;
@@ -5722,8 +5592,6 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	struct kset *kset = cache_kset(s);
 	int unmergeable = slab_unmergeable(s);
 
-	INIT_WORK(&s->kobj_remove_work, sysfs_slab_remove_workfn);
-
 	if (!kset) {
 		kobject_init(&s->kobj, &slab_ktype);
 		return 0;
@@ -5760,16 +5628,6 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	if (err)
 		goto out_del_kobj;
 
-#ifdef CONFIG_MEMCG
-	if (is_root_cache(s) && memcg_sysfs_enabled) {
-		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
-		if (!s->memcg_kset) {
-			err = -ENOMEM;
-			goto out_del_kobj;
-		}
-	}
-#endif
-
 	if (!unmergeable) {
 		/* Setup first alias */
 		sysfs_slab_alias(s, s->name);
@@ -5783,19 +5641,6 @@ out_del_kobj:
 	goto out;
 }
 
-static void sysfs_slab_remove(struct kmem_cache *s)
-{
-	if (slab_state < FULL)
-		/*
-		 * Sysfs has not been setup yet so no need to remove the
-		 * cache from sysfs.
-		 */
-		return;
-
-	kobject_get(&s->kobj);
-	schedule_work(&s->kobj_remove_work);
-}
-
 void sysfs_slab_unlink(struct kmem_cache *s)
 {
 	if (slab_state >= FULL)
-- 
cgit v1.2.3


From 991e7673859ed41e7ba83c8c4e57afe8cfebe314 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Thu, 6 Aug 2020 23:21:37 -0700
Subject: mm: memcontrol: account kernel stack per node

Currently the kernel stack is being accounted per-zone.  There is no need
to do that.  In addition due to being per-zone, memcg has to keep a
separate MEMCG_KERNEL_STACK_KB.  Make the stat per-node and deprecate
MEMCG_KERNEL_STACK_KB as memcg_stat_item is an extension of
node_stat_item.  In addition localize the kernel stack stats updates to
account_kernel_stack().

Signed-off-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200630161539.1759185-1-shakeelb@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c        |  4 ++--
 fs/proc/meminfo.c          |  4 ++--
 include/linux/memcontrol.h | 21 +++++++++++++++++--
 include/linux/mmzone.h     |  8 ++++----
 kernel/fork.c              | 51 +++++++++++++---------------------------------
 kernel/scs.c               |  2 +-
 mm/memcontrol.c            |  2 +-
 mm/page_alloc.c            | 16 +++++++--------
 mm/vmstat.c                |  8 ++++----
 9 files changed, 55 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 0cf13e31603c..508b80f6329b 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -440,9 +440,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
 		       nid, K(i.sharedram),
-		       nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB),
+		       nid, node_page_state(pgdat, NR_KERNEL_STACK_KB),
 #ifdef CONFIG_SHADOW_CALL_STACK
-		       nid, sum_zone_node_page_state(nid, NR_KERNEL_SCS_KB),
+		       nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
 #endif
 		       nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
 		       nid, 0UL,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 38ea95fd919a..2a4c58f70fb9 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -101,10 +101,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "SReclaimable:   ", sreclaimable);
 	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
 	seq_printf(m, "KernelStack:    %8lu kB\n",
-		   global_zone_page_state(NR_KERNEL_STACK_KB));
+		   global_node_page_state(NR_KERNEL_STACK_KB));
 #ifdef CONFIG_SHADOW_CALL_STACK
 	seq_printf(m, "ShadowCallStack:%8lu kB\n",
-		   global_zone_page_state(NR_KERNEL_SCS_KB));
+		   global_node_page_state(NR_KERNEL_SCS_KB));
 #endif
 	show_val_kb(m, "PageTables:     ",
 		    global_zone_page_state(NR_PAGETABLE));
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5a8b62d075e6..624400c27eba 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -32,8 +32,6 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
-	/* XXX: why are these zone and not node counters? */
-	MEMCG_KERNEL_STACK_KB,
 	MEMCG_NR_STAT,
 };
 
@@ -729,8 +727,19 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
+
 void mod_memcg_obj_state(void *p, int idx, int val);
 
+static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+					 int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_slab_state(p, idx, val);
+	local_irq_restore(flags);
+}
+
 static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
 					  enum node_stat_item idx, int val)
 {
@@ -1151,6 +1160,14 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 	__mod_node_page_state(page_pgdat(page), idx, val);
 }
 
+static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+					 int val)
+{
+	struct page *page = virt_to_head_page(p);
+
+	mod_node_page_state(page_pgdat(page), idx, val);
+}
+
 static inline void mod_memcg_obj_state(void *p, int idx, int val)
 {
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b79100edd228..a3bd54139a30 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -155,10 +155,6 @@ enum zone_stat_item {
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK_KB,	/* measured in KiB */
-#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
-	NR_KERNEL_SCS_KB,	/* measured in KiB */
-#endif
 	/* Second 128 byte cacheline */
 	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -203,6 +199,10 @@ enum node_stat_item {
 	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
 	NR_FOLL_PIN_ACQUIRED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
 	NR_FOLL_PIN_RELEASED,	/* pages returned via unpin_user_page() */
+	NR_KERNEL_STACK_KB,	/* measured in KiB */
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	NR_KERNEL_SCS_KB,	/* measured in KiB */
+#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 76d3f3387554..c7b4ce9d2647 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -276,13 +276,8 @@ static inline void free_thread_stack(struct task_struct *tsk)
 	if (vm) {
 		int i;
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     -(int)(PAGE_SIZE / 1024));
-
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
 			memcg_kmem_uncharge_page(vm->pages[i], 0);
-		}
 
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
 			if (this_cpu_cmpxchg(cached_stacks[i],
@@ -382,31 +377,14 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
-
-	if (vm) {
-		int i;
-
-		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_zone_page_state(page_zone(vm->pages[i]),
-					    NR_KERNEL_STACK_KB,
-					    PAGE_SIZE / 1024 * account);
-		}
-	} else {
-		/*
-		 * All stack pages are in the same zone and belong to the
-		 * same memcg.
-		 */
-		struct page *first_page = virt_to_page(stack);
-
-		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
-				    THREAD_SIZE / 1024 * account);
-
-		mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
-				    account * (THREAD_SIZE / 1024));
-	}
+	/* All stack pages are in the same node. */
+	if (vm)
+		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
+	else
+		mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
@@ -415,24 +393,23 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 	int ret;
 
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
 	if (vm) {
 		int i;
 
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
 			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
-			 * pointer is NULL, and both memcg_kmem_uncharge_page()
-			 * and mod_memcg_page_state() in free_thread_stack()
-			 * will ignore this page. So it's safe.
+			 * pointer is NULL, and memcg_kmem_uncharge_page() in
+			 * free_thread_stack() will ignore this page.
 			 */
 			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
 						     0);
 			if (ret)
 				return ret;
-
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     PAGE_SIZE / 1024);
 		}
 	}
 #endif
diff --git a/kernel/scs.c b/kernel/scs.c
index 5d4d9bbdec36..4ff4a7ba0094 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -17,7 +17,7 @@ static void __scs_account(void *s, int account)
 {
 	struct page *scs_page = virt_to_page(s);
 
-	mod_zone_page_state(page_zone(scs_page), NR_KERNEL_SCS_KB,
+	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
 			    account * (SCS_SIZE / SZ_1K));
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 473f9b91d51f..a3e963366769 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1485,7 +1485,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 		       (u64)memcg_page_state(memcg, NR_FILE_PAGES) *
 		       PAGE_SIZE);
 	seq_buf_printf(&s, "kernel_stack %llu\n",
-		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
+		       (u64)memcg_page_state(memcg, NR_KERNEL_STACK_KB) *
 		       1024);
 	seq_buf_printf(&s, "slab %llu\n",
 		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f9ad093814d2..8d5d8526c2f3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5396,6 +5396,10 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" anon_thp: %lukB"
 #endif
 			" writeback_tmp:%lukB"
+			" kernel_stack:%lukB"
+#ifdef CONFIG_SHADOW_CALL_STACK
+			" shadow_call_stack:%lukB"
+#endif
 			" all_unreclaimable? %s"
 			"\n",
 			pgdat->node_id,
@@ -5417,6 +5421,10 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
 #endif
 			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+			node_page_state(pgdat, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+			node_page_state(pgdat, NR_KERNEL_SCS_KB),
+#endif
 			pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
 				"yes" : "no");
 	}
@@ -5448,10 +5456,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" kernel_stack:%lukB"
-#ifdef CONFIG_SHADOW_CALL_STACK
-			" shadow_call_stack:%lukB"
-#endif
 			" pagetables:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
@@ -5473,10 +5477,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone->present_pages),
 			K(zone_managed_pages(zone)),
 			K(zone_page_state(zone, NR_MLOCK)),
-			zone_page_state(zone, NR_KERNEL_STACK_KB),
-#ifdef CONFIG_SHADOW_CALL_STACK
-			zone_page_state(zone, NR_KERNEL_SCS_KB),
-#endif
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b171a76bfe83..2b866cbab11d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1140,10 +1140,6 @@ const char * const vmstat_text[] = {
 	"nr_zone_write_pending",
 	"nr_mlock",
 	"nr_page_table_pages",
-	"nr_kernel_stack",
-#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
-	"nr_shadow_call_stack",
-#endif
 	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
@@ -1194,6 +1190,10 @@ const char * const vmstat_text[] = {
 	"nr_kernel_misc_reclaimable",
 	"nr_foll_pin_acquired",
 	"nr_foll_pin_released",
+	"nr_kernel_stack",
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	"nr_shadow_call_stack",
+#endif
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
cgit v1.2.3


From eda330e57b26df8fabce184736ae3d11e7a104bd Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 6 Aug 2020 23:21:47 -0700
Subject: mm: kmem: switch to static_branch_likely() in memcg_kmem_enabled()

Currently memcg_kmem_enabled() is optimized for the kernel memory
accounting being off.  It was so for a long time, and arguably the reason
behind was that the kernel memory accounting was initially an opt-in
feature.  However, now it's on by default on both cgroup v1 and cgroup v2,
and it's on for all cgroups.  So let's switch over to
static_branch_likely() to reflect this fact.

Unlikely there is a significant performance difference, as the cost of a
memory allocation and its accounting significantly exceeds the cost of a
jump.  However, the conversion makes the code look more logically.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Link: http://lkml.kernel.org/r/20200707173612.124425-3-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 624400c27eba..3f8ff6519c9d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1448,7 +1448,7 @@ void memcg_put_cache_ids(void);
 
 static inline bool memcg_kmem_enabled(void)
 {
-	return static_branch_unlikely(&memcg_kmem_enabled_key);
+	return static_branch_likely(&memcg_kmem_enabled_key);
 }
 
 static inline bool memcg_kmem_bypass(void)
-- 
cgit v1.2.3


From 22f7496f0b901249f23c5251eb8a10aae126b909 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 6 Aug 2020 23:22:01 -0700
Subject: mm, memcg: avoid stale protection values when cgroup is above
 protection

Patch series "mm, memcg: memory.{low,min} reclaim fix & cleanup", v4.

This series contains a fix for a edge case in my earlier protection
calculation patches, and a patch to make the area overall a little more
robust to hopefully help avoid this in future.

This patch (of 2):

A cgroup can have both memory protection and a memory limit to isolate it
from its siblings in both directions - for example, to prevent it from
being shrunk below 2G under high pressure from outside, but also from
growing beyond 4G under low pressure.

Commit 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
implemented proportional scan pressure so that multiple siblings in excess
of their protection settings don't get reclaimed equally but instead in
accordance to their unprotected portion.

During limit reclaim, this proportionality shouldn't apply of course:
there is no competition, all pressure is from within the cgroup and should
be applied as such.  Reclaim should operate at full efficiency.

However, mem_cgroup_protected() never expected anybody to look at the
effective protection values when it indicated that the cgroup is above its
protection.  As a result, a query during limit reclaim may return stale
protection values that were calculated by a previous reclaim cycle in
which the cgroup did have siblings.

When this happens, reclaim is unnecessarily hesitant and potentially slow
to meet the desired limit.  In theory this could lead to premature OOM
kills, although it's not obvious this has occurred in practice.

Workaround the problem by special casing reclaim roots in
mem_cgroup_protection.  These memcgs are never participating in the
reclaim protection because the reclaim is internal.

We have to ignore effective protection values for reclaim roots because
mem_cgroup_protected might be called from racing reclaim contexts with
different roots.  Calculation is relying on root -> leaf tree traversal
therefore top-down reclaim protection invariants should hold.  The only
exception is the reclaim root which should have effective protection set
to 0 but that would be problematic for the following setup:

 Let's have global and A's reclaim in parallel:
  |
  A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
  |\
  | C (low = 1G, usage = 2.5G)
  B (low = 1G, usage = 0.5G)

 for A reclaim we have
 B.elow = B.low
 C.elow = C.low

 For the global reclaim
 A.elow = A.low
 B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
 C.elow = min(C.usage, C.low)

 With the effective values resetting we have A reclaim
 A.elow = 0
 B.elow = B.low
 C.elow = C.low

 and global reclaim could see the above and then
 B.elow = C.elow = 0 because children_low_usage > A.elow

Which means that protected memcgs would get reclaimed.

In future we would like to make mem_cgroup_protected more robust against
racing reclaim contexts but that is likely more complex solution than this
simple workaround.

[hannes@cmpxchg.org - large part of the changelog]
[mhocko@suse.com - workaround explanation]
[chris@chrisdown.name - retitle]

Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Chris Down <chris@chrisdown.name>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/cover.1594638158.git.chris@chrisdown.name
Link: http://lkml.kernel.org/r/044fb8ecffd001c7905d27c0c2ad998069fdc396.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 42 ++++++++++++++++++++++++++++++++++++++++--
 mm/memcontrol.c            |  8 ++++++++
 mm/vmscan.c                |  3 ++-
 3 files changed, 50 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3f8ff6519c9d..0301b231fd02 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -355,12 +355,49 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
+						  struct mem_cgroup *memcg,
 						  bool in_low_reclaim)
 {
 	if (mem_cgroup_disabled())
 		return 0;
 
+	/*
+	 * There is no reclaim protection applied to a targeted reclaim.
+	 * We are special casing this specific case here because
+	 * mem_cgroup_protected calculation is not robust enough to keep
+	 * the protection invariant for calculated effective values for
+	 * parallel reclaimers with different reclaim target. This is
+	 * especially a problem for tail memcgs (as they have pages on LRU)
+	 * which would want to have effective values 0 for targeted reclaim
+	 * but a different value for external reclaim.
+	 *
+	 * Example
+	 * Let's have global and A's reclaim in parallel:
+	 *  |
+	 *  A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
+	 *  |\
+	 *  | C (low = 1G, usage = 2.5G)
+	 *  B (low = 1G, usage = 0.5G)
+	 *
+	 * For the global reclaim
+	 * A.elow = A.low
+	 * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
+	 * C.elow = min(C.usage, C.low)
+	 *
+	 * With the effective values resetting we have A reclaim
+	 * A.elow = 0
+	 * B.elow = B.low
+	 * C.elow = C.low
+	 *
+	 * If the global reclaim races with A's reclaim then
+	 * B.elow = C.elow = 0 because children_low_usage > A.elow)
+	 * is possible and reclaiming B would be violating the protection.
+	 *
+	 */
+	if (root == memcg)
+		return 0;
+
 	if (in_low_reclaim)
 		return READ_ONCE(memcg->memory.emin);
 
@@ -891,7 +928,8 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
+						  struct mem_cgroup *memcg,
 						  bool in_low_reclaim)
 {
 	return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b4cb1bb61d46..c610617bb19a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6605,6 +6605,14 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 
 	if (!root)
 		root = root_mem_cgroup;
+
+	/*
+	 * Effective values of the reclaim targets are ignored so they
+	 * can be stale. Have a look at mem_cgroup_protection for more
+	 * details.
+	 * TODO: calculation should be more robust so that we do not need
+	 * that special casing.
+	 */
 	if (memcg == root)
 		return MEMCG_PROT_NONE;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2ac43664aba4..9f0811d24255 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2331,7 +2331,8 @@ out:
 		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(memcg,
+		protection = mem_cgroup_protection(sc->target_mem_cgroup,
+						   memcg,
 						   sc->memcg_low_reclaim);
 
 		if (protection) {
-- 
cgit v1.2.3


From 45c7f7e1ef17f09fe70bad4b705ce43772153fd7 Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Thu, 6 Aug 2020 23:22:05 -0700
Subject: mm, memcg: decouple e{low,min} state mutations from protection checks

mem_cgroup_protected currently is both used to set effective low and min
and return a mem_cgroup_protection based on the result.  As a user, this
can be a little unexpected: it appears to be a simple predicate function,
if not for the big warning in the comment above about the order in which
it must be executed.

This change makes it so that we separate the state mutations from the
actual protection checks, which makes it more obvious where we need to be
careful mutating internal state, and where we are simply checking and
don't need to worry about that.

[mhocko@suse.com - don't check protection on root memcgs]

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: http://lkml.kernel.org/r/ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 53 ++++++++++++++++++++++++++++++++++++----------
 mm/memcontrol.c            | 28 ++++++------------------
 mm/vmscan.c                | 17 ++++-----------
 3 files changed, 53 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0301b231fd02..1bb49b600310 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -47,12 +47,6 @@ enum memcg_memory_event {
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
-enum mem_cgroup_protection {
-	MEMCG_PROT_NONE,
-	MEMCG_PROT_LOW,
-	MEMCG_PROT_MIN,
-};
-
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
 	unsigned int generation;
@@ -405,8 +399,36 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 		   READ_ONCE(memcg->memory.elow));
 }
 
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg);
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg);
+
+static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
+{
+	/*
+	 * The root memcg doesn't account charges, and doesn't support
+	 * protection.
+	 */
+	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
+
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+	if (!mem_cgroup_supports_protection(memcg))
+		return false;
+
+	return READ_ONCE(memcg->memory.elow) >=
+		page_counter_read(&memcg->memory);
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+	if (!mem_cgroup_supports_protection(memcg))
+		return false;
+
+	return READ_ONCE(memcg->memory.emin) >=
+		page_counter_read(&memcg->memory);
+}
 
 int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
 
@@ -935,10 +957,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 	return 0;
 }
 
-static inline enum mem_cgroup_protection mem_cgroup_protected(
-	struct mem_cgroup *root, struct mem_cgroup *memcg)
+static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+						   struct mem_cgroup *memcg)
 {
-	return MEMCG_PROT_NONE;
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+	return false;
 }
 
 static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c610617bb19a..b30a52db6b2d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6587,21 +6587,15 @@ static unsigned long effective_protection(unsigned long usage,
  *
  * WARNING: This function is not stateless! It can only be used as part
  *          of a top-down tree iteration, not for isolated queries.
- *
- * Returns one of the following:
- *   MEMCG_PROT_NONE: cgroup memory is not protected
- *   MEMCG_PROT_LOW: cgroup memory is protected as long there is
- *     an unprotected supply of reclaimable memory from other cgroups.
- *   MEMCG_PROT_MIN: cgroup memory is protected
  */
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg)
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg)
 {
 	unsigned long usage, parent_usage;
 	struct mem_cgroup *parent;
 
 	if (mem_cgroup_disabled())
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -6614,21 +6608,21 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 	 * that special casing.
 	 */
 	if (memcg == root)
-		return MEMCG_PROT_NONE;
+		return;
 
 	usage = page_counter_read(&memcg->memory);
 	if (!usage)
-		return MEMCG_PROT_NONE;
+		return;
 
 	parent = parent_mem_cgroup(memcg);
 	/* No parent means a non-hierarchical mode on v1 memcg */
 	if (!parent)
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (parent == root) {
 		memcg->memory.emin = READ_ONCE(memcg->memory.min);
 		memcg->memory.elow = READ_ONCE(memcg->memory.low);
-		goto out;
+		return;
 	}
 
 	parent_usage = page_counter_read(&parent->memory);
@@ -6642,14 +6636,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 			READ_ONCE(memcg->memory.low),
 			READ_ONCE(parent->memory.elow),
 			atomic_long_read(&parent->memory.children_low_usage)));
-
-out:
-	if (usage <= memcg->memory.emin)
-		return MEMCG_PROT_MIN;
-	else if (usage <= memcg->memory.elow)
-		return MEMCG_PROT_LOW;
-	else
-		return MEMCG_PROT_NONE;
 }
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9f0811d24255..5747867f0082 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2620,14 +2620,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
-		switch (mem_cgroup_protected(target_memcg, memcg)) {
-		case MEMCG_PROT_MIN:
+		mem_cgroup_calculate_protection(target_memcg, memcg);
+
+		if (mem_cgroup_below_min(memcg)) {
 			/*
 			 * Hard protection.
 			 * If there is no reclaimable memory, OOM.
 			 */
 			continue;
-		case MEMCG_PROT_LOW:
+		} else if (mem_cgroup_below_low(memcg)) {
 			/*
 			 * Soft protection.
 			 * Respect the protection only as long as
@@ -2639,16 +2640,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 				continue;
 			}
 			memcg_memory_event(memcg, MEMCG_LOW);
-			break;
-		case MEMCG_PROT_NONE:
-			/*
-			 * All protection thresholds breached. We may
-			 * still choose to vary the scan pressure
-			 * applied based on by how much the cgroup in
-			 * question has exceeded its protection
-			 * thresholds (see get_scan_count).
-			 */
-			break;
 		}
 
 		reclaimed = sc->nr_reclaimed;
-- 
cgit v1.2.3


From 2a681cfa5bb41e78e7bfafbb748b581374ce9b1d Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Thu, 6 Aug 2020 23:22:55 -0700
Subject: mm: move p?d_alloc_track to separate header file

The functions are only used in two source files, so there is no need for
them to be in the global <linux/mm.h> header.  Move them to the new
<linux/pgalloc-track.h> header and include it only where needed.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Matthew Wilcox <willy@infradead.org>
Link: http://lkml.kernel.org/r/20200609120533.25867-1-joro@8bytes.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 45 ---------------------------------------------
 mm/ioremap.c       |  2 ++
 mm/pgalloc-track.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/vmalloc.c       |  1 +
 4 files changed, 54 insertions(+), 45 deletions(-)
 create mode 100644 mm/pgalloc-track.h

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 303a47a9769d..2830f1c0fdc3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2103,51 +2103,11 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 		NULL : pud_offset(p4d, address);
 }
 
-static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd,
-				     unsigned long address,
-				     pgtbl_mod_mask *mod_mask)
-
-{
-	if (unlikely(pgd_none(*pgd))) {
-		if (__p4d_alloc(mm, pgd, address))
-			return NULL;
-		*mod_mask |= PGTBL_PGD_MODIFIED;
-	}
-
-	return p4d_offset(pgd, address);
-}
-
-static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d,
-				     unsigned long address,
-				     pgtbl_mod_mask *mod_mask)
-{
-	if (unlikely(p4d_none(*p4d))) {
-		if (__pud_alloc(mm, p4d, address))
-			return NULL;
-		*mod_mask |= PGTBL_P4D_MODIFIED;
-	}
-
-	return pud_offset(p4d, address);
-}
-
 static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {
 	return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
 		NULL: pmd_offset(pud, address);
 }
-
-static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud,
-				     unsigned long address,
-				     pgtbl_mod_mask *mod_mask)
-{
-	if (unlikely(pud_none(*pud))) {
-		if (__pmd_alloc(mm, pud, address))
-			return NULL;
-		*mod_mask |= PGTBL_PUD_MODIFIED;
-	}
-
-	return pmd_offset(pud, address);
-}
 #endif /* CONFIG_MMU */
 
 #if USE_SPLIT_PTE_PTLOCKS
@@ -2263,11 +2223,6 @@ static inline void pgtable_pte_page_dtor(struct page *page)
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
 		NULL: pte_offset_kernel(pmd, address))
 
-#define pte_alloc_kernel_track(pmd, address, mask)			\
-	((unlikely(pmd_none(*(pmd))) &&					\
-	  (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\
-		NULL: pte_offset_kernel(pmd, address))
-
 #if USE_SPLIT_PMD_PTLOCKS
 
 static struct page *pmd_to_page(pmd_t *pmd)
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 5ee3526f71b8..5fa1ab41d152 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -13,6 +13,8 @@
 #include <linux/export.h>
 #include <asm/cacheflush.h>
 
+#include "pgalloc-track.h"
+
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 static int __read_mostly ioremap_p4d_capable;
 static int __read_mostly ioremap_pud_capable;
diff --git a/mm/pgalloc-track.h b/mm/pgalloc-track.h
new file mode 100644
index 000000000000..1dcc865029a2
--- /dev/null
+++ b/mm/pgalloc-track.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLLC_TRACK_H
+#define _LINUX_PGALLLC_TRACK_H
+
+#if defined(CONFIG_MMU)
+static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(pgd_none(*pgd))) {
+		if (__p4d_alloc(mm, pgd, address))
+			return NULL;
+		*mod_mask |= PGTBL_PGD_MODIFIED;
+	}
+
+	return p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(p4d_none(*p4d))) {
+		if (__pud_alloc(mm, p4d, address))
+			return NULL;
+		*mod_mask |= PGTBL_P4D_MODIFIED;
+	}
+
+	return pud_offset(p4d, address);
+}
+
+static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(pud_none(*pud))) {
+		if (__pmd_alloc(mm, pud, address))
+			return NULL;
+		*mod_mask |= PGTBL_PUD_MODIFIED;
+	}
+
+	return pmd_offset(pud, address);
+}
+#endif /* CONFIG_MMU */
+
+#define pte_alloc_kernel_track(pmd, address, mask)			\
+	((unlikely(pmd_none(*(pmd))) &&					\
+	  (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\
+		NULL: pte_offset_kernel(pmd, address))
+
+#endif /* _LINUX_PGALLLC_TRACK_H */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5a2b55c8dd9a..5be3cf3b59de 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -41,6 +41,7 @@
 #include <asm/shmparam.h>
 
 #include "internal.h"
+#include "pgalloc-track.h"
 
 bool is_vmalloc_addr(const void *x)
 {
-- 
cgit v1.2.3


From 0a4954a850b0c4d0a5d18b1a55d6e5a653e362b5 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Thu, 6 Aug 2020 23:23:11 -0700
Subject: percpu_counter: add percpu_counter_sync()

percpu_counter's accuracy is related to its batch size.  For a
percpu_counter with a big batch, its deviation could be big, so when the
counter's batch is runtime changed to a smaller value for better accuracy,
there could also be requirment to reduce the big deviation.

So add a percpu-counter sync function to be run on each CPU.

Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Tim Chen <tim.c.chen@intel.com>
Link: http://lkml.kernel.org/r/1594389708-60781-4-git-send-email-feng.tang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu_counter.h |  4 ++++
 lib/percpu_counter.c           | 19 +++++++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 0a4f54dd4737..01861eebed79 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -44,6 +44,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
 			      s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
 int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+void percpu_counter_sync(struct percpu_counter *fbc);
 
 static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
 {
@@ -172,6 +173,9 @@ static inline bool percpu_counter_initialized(struct percpu_counter *fbc)
 	return true;
 }
 
+static inline void percpu_counter_sync(struct percpu_counter *fbc)
+{
+}
 #endif	/* CONFIG_SMP */
 
 static inline void percpu_counter_inc(struct percpu_counter *fbc)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a66595ba5543..a2345de90e93 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -98,6 +98,25 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 }
 EXPORT_SYMBOL(percpu_counter_add_batch);
 
+/*
+ * For percpu_counter with a big batch, the devication of its count could
+ * be big, and there is requirement to reduce the deviation, like when the
+ * counter's batch could be runtime decreased to get a better accuracy,
+ * which can be achieved by running this sync function on each CPU.
+ */
+void percpu_counter_sync(struct percpu_counter *fbc)
+{
+	unsigned long flags;
+	s64 count;
+
+	raw_spin_lock_irqsave(&fbc->lock, flags);
+	count = __this_cpu_read(*fbc->counters);
+	fbc->count += count;
+	__this_cpu_sub(*fbc->counters, count);
+	raw_spin_unlock_irqrestore(&fbc->lock, flags);
+}
+EXPORT_SYMBOL(percpu_counter_sync);
+
 /*
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
-- 
cgit v1.2.3


From 56f3547bfa4d361148aa748ccb86073bc57f5e6c Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Thu, 6 Aug 2020 23:23:15 -0700
Subject: mm: adjust vm_committed_as_batch according to vm overcommit policy

When checking a performance change for will-it-scale scalability mmap test
[1], we found very high lock contention for spinlock of percpu counter
'vm_committed_as':

    94.14%     0.35%  [kernel.kallsyms]         [k] _raw_spin_lock_irqsave
    48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap;
    45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap;

Actually this heavy lock contention is not always necessary.  The
'vm_committed_as' needs to be very precise when the strict
OVERCOMMIT_NEVER policy is set, which requires a rather small batch number
for the percpu counter.

So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and
lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies.  Also
add a sysctl handler to adjust it when the policy is reconfigured.

Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T
desktop, and 2097%(20X) on a 4S/72C/144T server.  We tested with test
platforms in 0day (server, desktop and laptop), and 80%+ platforms shows
improvements with that test.  And whether it shows improvements depends on
if the test mmap size is bigger than the batch number computed.

And if the lift is 16X, 1/3 of the platforms will show improvements,
though it should help the mmap/unmap usage generally, as Michal Hocko
mentioned:

: I believe that there are non-synthetic worklaods which would benefit from
: a larger batch.  E.g.  large in memory databases which do large mmaps
: during startups from multiple threads.

[1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/

Signed-off-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Qian Cai <cai@lca.pw>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: kernel test robot <rong.a.chen@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com
Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com
Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h   |  2 ++
 include/linux/mman.h |  4 ++++
 kernel/sysctl.c      |  2 +-
 mm/mm_init.c         | 22 ++++++++++++++++------
 mm/util.c            | 41 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 64 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2830f1c0fdc3..1c3470550395 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -206,6 +206,8 @@ int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
+int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 4b08e9c9c538..6f34c33075f9 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -57,8 +57,12 @@ extern struct percpu_counter vm_committed_as;
 
 #ifdef CONFIG_SMP
 extern s32 vm_committed_as_batch;
+extern void mm_compute_batch(int overcommit_policy);
 #else
 #define vm_committed_as_batch 0
+static inline void mm_compute_batch(int overcommit_policy)
+{
+}
 #endif
 
 unsigned long vm_memory_committed(void);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1b4d2dc270a5..f785de3caac0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2671,7 +2671,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &sysctl_overcommit_memory,
 		.maxlen		= sizeof(sysctl_overcommit_memory),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= overcommit_policy_handler,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 435e5f794b3b..b06a30fbedff 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -13,6 +13,7 @@
 #include <linux/memory.h>
 #include <linux/notifier.h>
 #include <linux/sched.h>
+#include <linux/mman.h>
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
@@ -144,14 +145,23 @@ EXPORT_SYMBOL_GPL(mm_kobj);
 #ifdef CONFIG_SMP
 s32 vm_committed_as_batch = 32;
 
-static void __meminit mm_compute_batch(void)
+void mm_compute_batch(int overcommit_policy)
 {
 	u64 memsized_batch;
 	s32 nr = num_present_cpus();
 	s32 batch = max_t(s32, nr*2, 32);
-
-	/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
-	memsized_batch = min_t(u64, (totalram_pages()/nr)/256, 0x7fffffff);
+	unsigned long ram_pages = totalram_pages();
+
+	/*
+	 * For policy OVERCOMMIT_NEVER, set batch size to 0.4% of
+	 * (total memory/#cpus), and lift it to 25% for other policies
+	 * to easy the possible lock contention for percpu_counter
+	 * vm_committed_as, while the max limit is INT_MAX
+	 */
+	if (overcommit_policy == OVERCOMMIT_NEVER)
+		memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX);
+	else
+		memsized_batch = min_t(u64, ram_pages/nr/4, INT_MAX);
 
 	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
 }
@@ -162,7 +172,7 @@ static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
 	switch (action) {
 	case MEM_ONLINE:
 	case MEM_OFFLINE:
-		mm_compute_batch();
+		mm_compute_batch(sysctl_overcommit_memory);
 	default:
 		break;
 	}
@@ -176,7 +186,7 @@ static struct notifier_block compute_batch_nb __meminitdata = {
 
 static int __init mm_compute_batch_init(void)
 {
-	mm_compute_batch();
+	mm_compute_batch(sysctl_overcommit_memory);
 	register_hotmemory_notifier(&compute_batch_nb);
 
 	return 0;
diff --git a/mm/util.c b/mm/util.c
index 1c9d097d7e48..8d6280c05238 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -746,6 +746,47 @@ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
+static void sync_overcommit_as(struct work_struct *dummy)
+{
+	percpu_counter_sync(&vm_committed_as);
+}
+
+int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int new_policy;
+	int ret;
+
+	/*
+	 * The deviation of sync_overcommit_as could be big with loose policy
+	 * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
+	 * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
+	 * with the strict "NEVER", and to avoid possible race condtion (even
+	 * though user usually won't too frequently do the switching to policy
+	 * OVERCOMMIT_NEVER), the switch is done in the following order:
+	 *	1. changing the batch
+	 *	2. sync percpu count on each CPU
+	 *	3. switch the policy
+	 */
+	if (write) {
+		t = *table;
+		t.data = &new_policy;
+		ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+		if (ret)
+			return ret;
+
+		mm_compute_batch(new_policy);
+		if (new_policy == OVERCOMMIT_NEVER)
+			schedule_on_each_cpu(sync_overcommit_as);
+		sysctl_overcommit_memory = new_policy;
+	} else {
+		ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	}
+
+	return ret;
+}
+
 int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
-- 
cgit v1.2.3


From 1d9cfee7535c213038a615f112c900c2d0ba8f54 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 6 Aug 2020 23:23:19 -0700
Subject: mm/sparsemem: enable vmem_altmap support in
 vmemmap_populate_basepages()

Patch series "arm64: Enable vmemmap mapping from device memory", v4.

This series enables vmemmap backing memory allocation from device memory
ranges on arm64.  But before that, it enables vmemmap_populate_basepages()
and vmemmap_alloc_block_buf() to accommodate struct vmem_altmap based
alocation requests.

This patch (of 3):

vmemmap_populate_basepages() is used across platforms to allocate backing
memory for vmemmap mapping.  This is used as a standard default choice or
as a fallback when intended huge pages allocation fails.  This just
creates entire vmemmap mapping with base pages (PAGE_SIZE).

On arm64 platforms, vmemmap_populate_basepages() is called instead of the
platform specific vmemmap_populate() when ARM64_SWAPPER_USES_SECTION_MAPS
is not enabled as in case for ARM64_16K_PAGES and ARM64_64K_PAGES configs.

At present vmemmap_populate_basepages() does not support allocating from
driver defined struct vmem_altmap while trying to create vmemmap mapping
for a device memory range.  It prevents ARM64_16K_PAGES and
ARM64_64K_PAGES configs on arm64 from supporting device memory with
vmemap_altmap request.

This enables vmem_altmap support in vmemmap_populate_basepages() unlocking
device memory allocation for vmemap mapping on arm64 platforms with 16K or
64K base page configs.

Each architecture should evaluate and decide on subscribing device memory
based base page allocation through vmemmap_populate_basepages().  Hence
lets keep it disabled on all archs in order to preserve the existing
semantics.  A subsequent patch enables it on arm64.

Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Jia He <justin.he@arm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Yu Zhao <yuzhao@google.com>
Link: http://lkml.kernel.org/r/1594004178-8861-1-git-send-email-anshuman.khandual@arm.com
Link: http://lkml.kernel.org/r/1594004178-8861-2-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/mm/mmu.c      |  2 +-
 arch/ia64/mm/discontig.c |  2 +-
 arch/riscv/mm/init.c     |  2 +-
 arch/x86/mm/init_64.c    |  6 +++---
 include/linux/mm.h       |  5 +++--
 mm/sparse-vmemmap.c      | 16 +++++++++++-----
 6 files changed, 20 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index cafefb147a5e..a32ddd021fe9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1070,7 +1070,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node);
+	return vmemmap_populate_basepages(start, end, node, NULL);
 }
 #else	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 37f8b6875ac9..2ba2127335a7 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -655,7 +655,7 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node);
+	return vmemmap_populate_basepages(start, end, node, NULL);
 }
 
 void vmemmap_free(unsigned long start, unsigned long end,
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 79e9d55bdf1a..416e520d07d3 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -554,6 +554,6 @@ void __init paging_init(void)
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node);
+	return vmemmap_populate_basepages(start, end, node, NULL);
 }
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3f4e29a78f2b..1acc5627b21c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1545,7 +1545,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 			continue;
 		}
-		if (vmemmap_populate_basepages(addr, next, node))
+		if (vmemmap_populate_basepages(addr, next, node, NULL))
 			return -ENOMEM;
 	}
 	return 0;
@@ -1557,7 +1557,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	int err;
 
 	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
-		err = vmemmap_populate_basepages(start, end, node);
+		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
 	else if (altmap) {
@@ -1565,7 +1565,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 				__func__);
 		err = -ENOMEM;
 	} else
-		err = vmemmap_populate_basepages(start, end, node);
+		err = vmemmap_populate_basepages(start, end, node, NULL);
 	if (!err)
 		sync_global_pgds(start, end - 1);
 	return err;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1c3470550395..a7ff98738126 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2978,14 +2978,15 @@ pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
-pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
+pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+			    struct vmem_altmap *altmap);
 void *vmemmap_alloc_block(unsigned long size, int node);
 struct vmem_altmap;
 void *vmemmap_alloc_block_buf(unsigned long size, int node);
 void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
-			       int node);
+			       int node, struct vmem_altmap *altmap);
 int vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap);
 void vmemmap_populate_print_last(void);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 0db7738d76e9..ceed10dec31e 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -139,12 +139,18 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
 			start, end - 1);
 }
 
-pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
+pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+				       struct vmem_altmap *altmap)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
-		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
+		void *p;
+
+		if (altmap)
+			p = altmap_alloc_block_buf(PAGE_SIZE, altmap);
+		else
+			p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
@@ -212,8 +218,8 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 	return pgd;
 }
 
-int __meminit vmemmap_populate_basepages(unsigned long start,
-					 unsigned long end, int node)
+int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
+					 int node, struct vmem_altmap *altmap)
 {
 	unsigned long addr = start;
 	pgd_t *pgd;
@@ -235,7 +241,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 		pmd = vmemmap_pmd_populate(pud, addr, node);
 		if (!pmd)
 			return -ENOMEM;
-		pte = vmemmap_pte_populate(pmd, addr, node);
+		pte = vmemmap_pte_populate(pmd, addr, node, altmap);
 		if (!pte)
 			return -ENOMEM;
 		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
-- 
cgit v1.2.3


From 56993b4e147e9f2ba91ac15ef9ae5ee0626a6850 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 6 Aug 2020 23:23:24 -0700
Subject: mm/sparsemem: enable vmem_altmap support in vmemmap_alloc_block_buf()

There are many instances where vmemap allocation is often switched between
regular memory and device memory just based on whether altmap is available
or not.  vmemmap_alloc_block_buf() is used in various platforms to
allocate vmemmap mappings.  Lets also enable it to handle altmap based
device memory allocation along with existing regular memory allocations.
This will help in avoiding the altmap based allocation switch in many
places.  To summarize there are two different methods to call
vmemmap_alloc_block_buf().

vmemmap_alloc_block_buf(size, node, NULL)   /* Allocate from system RAM */
vmemmap_alloc_block_buf(size, node, altmap) /* Allocate from altmap */

This converts altmap_alloc_block_buf() into a static function, drops it's
entry from the header and updates Documentation/vm/memory-model.rst.

Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Jia He <justin.he@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Will Deacon <will@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Yu Zhao <yuzhao@google.com>
Link: http://lkml.kernel.org/r/1594004178-8861-3-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/memory-model.rst |  2 +-
 arch/arm64/mm/mmu.c               |  2 +-
 arch/powerpc/mm/init_64.c         |  4 ++--
 arch/x86/mm/init_64.c             |  5 +----
 include/linux/mm.h                |  4 ++--
 mm/sparse-vmemmap.c               | 28 +++++++++++++---------------
 6 files changed, 20 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst
index cc65bc85d260..2b898a27b346 100644
--- a/Documentation/vm/memory-model.rst
+++ b/Documentation/vm/memory-model.rst
@@ -178,7 +178,7 @@ for persistent memory devices in pre-allocated storage on those
 devices. This storage is represented with :c:type:`struct vmem_altmap`
 that is eventually passed to vmemmap_populate() through a long chain
 of function calls. The vmemmap_populate() implementation may use the
-`vmem_altmap` along with :c:func:`altmap_alloc_block_buf` helper to
+`vmem_altmap` along with :c:func:`vmemmap_alloc_block_buf` helper to
 allocate memory map on the persistent memory device.
 
 ZONE_DEVICE
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a32ddd021fe9..f3d9ff323c8f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1102,7 +1102,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		if (pmd_none(READ_ONCE(*pmdp))) {
 			void *p = NULL;
 
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node, NULL);
 			if (!p)
 				return -ENOMEM;
 
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index bc73abf0bc25..3fd504d72c5e 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -225,12 +225,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		 * fall back to system memory if the altmap allocation fail.
 		 */
 		if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
-			p = altmap_alloc_block_buf(page_size, altmap);
+			p = vmemmap_alloc_block_buf(page_size, node, altmap);
 			if (!p)
 				pr_debug("altmap block allocation failed, falling back to system memory");
 		}
 		if (!p)
-			p = vmemmap_alloc_block_buf(page_size, node);
+			p = vmemmap_alloc_block_buf(page_size, node, NULL);
 		if (!p)
 			return -ENOMEM;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1acc5627b21c..53e1d4f4ed9d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1515,10 +1515,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 		if (pmd_none(*pmd)) {
 			void *p;
 
-			if (altmap)
-				p = altmap_alloc_block_buf(PMD_SIZE, altmap);
-			else
-				p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
 			if (p) {
 				pte_t entry;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a7ff98738126..98e35df8d88e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2982,8 +2982,8 @@ pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
 			    struct vmem_altmap *altmap);
 void *vmemmap_alloc_block(unsigned long size, int node);
 struct vmem_altmap;
-void *vmemmap_alloc_block_buf(unsigned long size, int node);
-void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap);
+void *vmemmap_alloc_block_buf(unsigned long size, int node,
+			      struct vmem_altmap *altmap);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
 			       int node, struct vmem_altmap *altmap);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index ceed10dec31e..41eeac67723b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -69,11 +69,19 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 				__pa(MAX_DMA_ADDRESS));
 }
 
+static void * __meminit altmap_alloc_block_buf(unsigned long size,
+					       struct vmem_altmap *altmap);
+
 /* need to make sure size is all the same during early stage */
-void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node,
+					 struct vmem_altmap *altmap)
 {
-	void *ptr = sparse_buffer_alloc(size);
+	void *ptr;
+
+	if (altmap)
+		return altmap_alloc_block_buf(size, altmap);
 
+	ptr = sparse_buffer_alloc(size);
 	if (!ptr)
 		ptr = vmemmap_alloc_block(size, node);
 	return ptr;
@@ -94,15 +102,8 @@ static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
 	return 0;
 }
 
-/**
- * altmap_alloc_block_buf - allocate pages from the device page map
- * @altmap:	device page map
- * @size:	size (in bytes) of the allocation
- *
- * Allocations are aligned to the size of the request.
- */
-void * __meminit altmap_alloc_block_buf(unsigned long size,
-		struct vmem_altmap *altmap)
+static void * __meminit altmap_alloc_block_buf(unsigned long size,
+					       struct vmem_altmap *altmap)
 {
 	unsigned long pfn, nr_pfns, nr_align;
 
@@ -147,10 +148,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
 		pte_t entry;
 		void *p;
 
-		if (altmap)
-			p = altmap_alloc_block_buf(PAGE_SIZE, altmap);
-		else
-			p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
+		p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
-- 
cgit v1.2.3


From 45e55300f11495ed58c53427da7f0d958800a30f Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Thu, 6 Aug 2020 23:23:37 -0700
Subject: mm: remove unnecessary wrapper function do_mmap_pgoff()

The current split between do_mmap() and do_mmap_pgoff() was introduced in
commit 1fcfd8db7f82 ("mm, mpx: add "vm_flags_t vm_flags" arg to
do_mmap_pgoff()") to support MPX.

The wrapper function do_mmap_pgoff() always passed 0 as the value of the
vm_flags argument to do_mmap().  However, MPX support has subsequently
been removed from the kernel and there were no more direct callers of
do_mmap(); all calls were going via do_mmap_pgoff().

Simplify the code by removing do_mmap_pgoff() and changing all callers to
directly call do_mmap(), which now no longer takes a vm_flags argument.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Link: http://lkml.kernel.org/r/20200727194109.1371462-1-pcc@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/aio.c             |  6 +++---
 fs/hugetlbfs/inode.c |  2 +-
 include/linux/fs.h   |  2 +-
 include/linux/mm.h   | 12 +-----------
 ipc/shm.c            |  2 +-
 mm/mmap.c            | 16 ++++++++--------
 mm/nommu.c           |  6 +++---
 mm/shmem.c           |  2 +-
 mm/util.c            |  4 ++--
 9 files changed, 21 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/fs/aio.c b/fs/aio.c
index 91e7cc4a9f17..5736bff48e9e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -525,9 +525,9 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 		return -EINTR;
 	}
 
-	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
-				       PROT_READ | PROT_WRITE,
-				       MAP_SHARED, 0, &unused, NULL);
+	ctx->mmap_base = do_mmap(ctx->aio_ring_file, 0, ctx->mmap_size,
+				 PROT_READ | PROT_WRITE,
+				 MAP_SHARED, 0, &unused, NULL);
 	mmap_write_unlock(mm);
 	if (IS_ERR((void *)ctx->mmap_base)) {
 		ctx->mmap_size = 0;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ef5313f9c78f..523954d00dff 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -140,7 +140,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * already been checked by prepare_hugepage_range.  If you add
 	 * any error returns here, do so after setting VM_HUGETLB, so
 	 * is_vm_hugetlb_page tests below unmap_region go the right
-	 * way when do_mmap_pgoff unwinds (may be important on powerpc
+	 * way when do_mmap unwinds (may be important on powerpc
 	 * and ia64).
 	 */
 	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b1c3a14f12e8..f5da33bcaaae 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -528,7 +528,7 @@ static inline int mapping_mapped(struct address_space *mapping)
 
 /*
  * Might pages of this file have been modified in userspace?
- * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
+ * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap
  * marks vma as VM_SHARED if it is shared, and the file was opened for
  * writing i.e. vma may be mprotected writable even if now readonly.
  *
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 98e35df8d88e..cf7e4605ff3f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2546,23 +2546,13 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	struct list_head *uf);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
-	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
-	struct list_head *uf);
+	unsigned long pgoff, unsigned long *populate, struct list_head *uf);
 extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
 extern int do_madvise(unsigned long start, size_t len_in, int behavior);
 
-static inline unsigned long
-do_mmap_pgoff(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot, unsigned long flags,
-	unsigned long pgoff, unsigned long *populate,
-	struct list_head *uf)
-{
-	return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf);
-}
-
 #ifdef CONFIG_MMU
 extern int __mm_populate(unsigned long addr, unsigned long len,
 			 int ignore_errors);
diff --git a/ipc/shm.c b/ipc/shm.c
index 0a6dd94afa21..bf38d7e2fbe9 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1558,7 +1558,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 			goto invalid;
 	}
 
-	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate, NULL);
+	addr = do_mmap(file, addr, size, prot, flags, 0, &populate, NULL);
 	*raddr = addr;
 	err = 0;
 	if (IS_ERR_VALUE(addr))
diff --git a/mm/mmap.c b/mm/mmap.c
index ba39409cdb17..40248d84ad5f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1030,7 +1030,7 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
  * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
  *
  * We don't check here for the merged mmap wrapping around the end of pagecache
- * indices (16TB on ia32) because do_mmap_pgoff() does not permit mmap's which
+ * indices (16TB on ia32) because do_mmap() does not permit mmap's which
  * wrap, nor mmaps which cover the final page at index -1UL.
  */
 static int
@@ -1365,11 +1365,11 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode,
  */
 unsigned long do_mmap(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
-			unsigned long flags, vm_flags_t vm_flags,
-			unsigned long pgoff, unsigned long *populate,
-			struct list_head *uf)
+			unsigned long flags, unsigned long pgoff,
+			unsigned long *populate, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
+	vm_flags_t vm_flags;
 	int pkey = 0;
 
 	*populate = 0;
@@ -1431,7 +1431,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	 * to. we assume access permissions have been handled by the open
 	 * of the memory object, so we don't do any here.
 	 */
-	vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) |
+	vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) |
 			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
 
 	if (flags & MAP_LOCKED)
@@ -2230,7 +2230,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		/*
 		 * mmap_region() will call shmem_zero_setup() to create a file,
 		 * so use shmem's get_unmapped_area in case it can be huge.
-		 * do_mmap_pgoff() will clear pgoff, so match alignment.
+		 * do_mmap() will clear pgoff, so match alignment.
 		 */
 		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
@@ -3003,7 +3003,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	}
 
 	file = get_file(vma->vm_file);
-	ret = do_mmap_pgoff(vma->vm_file, start, size,
+	ret = do_mmap(vma->vm_file, start, size,
 			prot, flags, pgoff, &populate, NULL);
 	fput(file);
 out:
@@ -3223,7 +3223,7 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 	 * By setting it to reflect the virtual start address of the
 	 * vma, merges and splits can happen in a seamless way, just
 	 * using the existing file pgoff checks and manipulations.
-	 * Similarly in do_mmap_pgoff and in do_brk.
+	 * Similarly in do_mmap and in do_brk.
 	 */
 	if (vma_is_anonymous(vma)) {
 		BUG_ON(vma->anon_vma);
diff --git a/mm/nommu.c b/mm/nommu.c
index 314174817b04..340ae7774c13 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1078,7 +1078,6 @@ unsigned long do_mmap(struct file *file,
 			unsigned long len,
 			unsigned long prot,
 			unsigned long flags,
-			vm_flags_t vm_flags,
 			unsigned long pgoff,
 			unsigned long *populate,
 			struct list_head *uf)
@@ -1086,6 +1085,7 @@ unsigned long do_mmap(struct file *file,
 	struct vm_area_struct *vma;
 	struct vm_region *region;
 	struct rb_node *rb;
+	vm_flags_t vm_flags;
 	unsigned long capabilities, result;
 	int ret;
 
@@ -1104,7 +1104,7 @@ unsigned long do_mmap(struct file *file,
 
 	/* we've determined that we can make the mapping, now translate what we
 	 * now know into VMA flags */
-	vm_flags |= determine_vm_flags(file, prot, flags, capabilities);
+	vm_flags = determine_vm_flags(file, prot, flags, capabilities);
 
 	/* we're going to need to record the mapping */
 	region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
@@ -1763,7 +1763,7 @@ EXPORT_SYMBOL_GPL(access_process_vm);
  *
  * Check the shared mappings on an inode on behalf of a shrinking truncate to
  * make sure that that any outstanding VMAs aren't broken and then shrink the
- * vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
+ * vm_regions that extend that beyond so that do_mmap() doesn't
  * automatically grant mappings that are too large.
  */
 int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
diff --git a/mm/shmem.c b/mm/shmem.c
index c5c281893bb8..eb6b36d89722 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4245,7 +4245,7 @@ EXPORT_SYMBOL_GPL(shmem_file_setup_with_mnt);
 
 /**
  * shmem_zero_setup - setup a shared anonymous mapping
- * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
+ * @vma: the vma to be mmapped is prepared by do_mmap
  */
 int shmem_zero_setup(struct vm_area_struct *vma)
 {
diff --git a/mm/util.c b/mm/util.c
index 8d6280c05238..5ef378a2a038 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -503,8 +503,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	if (!ret) {
 		if (mmap_write_lock_killable(mm))
 			return -EINTR;
-		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
-				    &populate, &uf);
+		ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
+			      &uf);
 		mmap_write_unlock(mm);
 		userfaultfd_unmap_complete(mm, &uf);
 		if (populate)
-- 
cgit v1.2.3


From b8aa9d9d95b3b4b60d42ac95f65d33a92527aef3 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 6 Aug 2020 23:23:40 -0700
Subject: mm/mremap: it is sure to have enough space when extent meets
 requirement

Patch series "mm/mremap: cleanup move_page_tables() a little", v5.

move_page_tables() tries to move page table by PMD or PTE.

The root reason is if it tries to move PMD, both old and new range should
be PMD aligned.  But current code calculate old range and new range
separately.  This leads to some redundant check and calculation.

This cleanup tries to consolidate the range check in one place to reduce
some extra range handling.

This patch (of 3):

old_end is passed to these two functions to check whether there is enough
space to do the move, while this check is done before invoking these
functions.

These two functions only would be invoked when extent meets the
requirement and there is one check before invoking these functions:

    if (extent > old_end - old_addr)
        extent = old_end - old_addr;

This implies (old_end - old_addr) won't fail the check in these two
functions.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Thomas Hellstrom (VMware) <thomas_os@shipmail.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Link: http://lkml.kernel.org/r/20200710092835.56368-1-richard.weiyang@linux.alibaba.com
Link: http://lkml.kernel.org/r/20200710092835.56368-2-richard.weiyang@linux.alibaba.com
Link: http://lkml.kernel.org/r/20200708095028.41706-1-richard.weiyang@linux.alibaba.com
Link: http://lkml.kernel.org/r/20200708095028.41706-2-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  2 +-
 mm/huge_memory.c        |  7 ++-----
 mm/mremap.c             | 10 ++++------
 3 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 71f20776b06c..17c4c4975145 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -42,7 +42,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);
 extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-			 unsigned long new_addr, unsigned long old_end,
+			 unsigned long new_addr,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 78c84bee7e29..1e580fdad4d0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1722,17 +1722,14 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
 }
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
 	struct mm_struct *mm = vma->vm_mm;
 	bool force_flush = false;
 
-	if ((old_addr & ~HPAGE_PMD_MASK) ||
-	    (new_addr & ~HPAGE_PMD_MASK) ||
-	    old_end - old_addr < HPAGE_PMD_SIZE)
+	if ((old_addr & ~HPAGE_PMD_MASK) || (new_addr & ~HPAGE_PMD_MASK))
 		return false;
 
 	/*
diff --git a/mm/mremap.c b/mm/mremap.c
index 6b153dc05fe4..4f434062d154 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -193,15 +193,13 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 
 #ifdef CONFIG_HAVE_MOVE_PMD
 static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t pmd;
 
-	if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
-	    || old_end - old_addr < PMD_SIZE)
+	if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK))
 		return false;
 
 	/*
@@ -292,7 +290,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				if (need_rmap_locks)
 					take_rmap_locks(vma);
 				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd);
+						      old_pmd, new_pmd);
 				if (need_rmap_locks)
 					drop_rmap_locks(vma);
 				if (moved)
@@ -312,7 +310,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			if (need_rmap_locks)
 				take_rmap_locks(vma);
 			moved = move_normal_pmd(vma, old_addr, new_addr,
-					old_end, old_pmd, new_pmd);
+						old_pmd, new_pmd);
 			if (need_rmap_locks)
 				drop_rmap_locks(vma);
 			if (moved)
-- 
cgit v1.2.3


From c89ab04febf97d2db8ca4ef8e2866fadc474351b Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Thu, 6 Aug 2020 23:24:02 -0700
Subject: mm/sparse: cleanup the code surrounding memory_present()

After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP we have two equivalent
functions that call memory_present() for each region in memblock.memory:
sparse_memory_present_with_active_regions() and membocks_present().

Moreover, all architectures have a call to either of these functions
preceding the call to sparse_init() and in the most cases they are called
one after the other.

Mark the regions from memblock.memory as present during sparce_init() by
making sparse_init() call memblocks_present(), make memblocks_present()
and memory_present() functions static and remove redundant
sparse_memory_present_with_active_regions() function.

Also remove no longer required HAVE_MEMORY_PRESENT configuration option.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200712083130.22919-1-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/memory-model.rst |  7 ++-----
 arch/arm/mm/init.c                |  9 ++-------
 arch/arm64/mm/init.c              |  6 ++----
 arch/ia64/mm/discontig.c          |  1 -
 arch/microblaze/mm/init.c         |  3 ---
 arch/mips/kernel/setup.c          |  8 --------
 arch/mips/loongson64/numa.c       |  1 -
 arch/mips/sgi-ip27/ip27-memory.c  |  2 --
 arch/parisc/mm/init.c             |  5 -----
 arch/powerpc/mm/mem.c             |  2 --
 arch/powerpc/mm/numa.c            |  1 -
 arch/riscv/mm/init.c              |  1 -
 arch/s390/mm/init.c               |  1 -
 arch/sh/mm/init.c                 |  6 ------
 arch/sh/mm/numa.c                 |  3 ---
 arch/sparc/mm/init_64.c           |  1 -
 arch/x86/mm/init_32.c             |  2 --
 arch/x86/mm/init_64.c             |  1 -
 include/linux/mm.h                |  4 ----
 include/linux/mmzone.h            | 14 --------------
 mm/Kconfig                        |  6 +-----
 mm/page_alloc.c                   | 16 ----------------
 mm/sparse.c                       | 20 ++++++++++++--------
 23 files changed, 19 insertions(+), 101 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst
index 2b898a27b346..769449734573 100644
--- a/Documentation/vm/memory-model.rst
+++ b/Documentation/vm/memory-model.rst
@@ -141,11 +141,8 @@ sections:
   `mem_section` objects and the number of rows is calculated to fit
   all the memory sections.
 
-The architecture setup code should call :c:func:`memory_present` for
-each active memory range or use :c:func:`memblocks_present` or
-:c:func:`sparse_memory_present_with_active_regions` wrappers to
-initialize the memory sections. Next, the actual memory maps should be
-set up using :c:func:`sparse_init`.
+The architecture setup code should call sparse_init() to
+initialize the memory sections and the memory maps.
 
 With SPARSEMEM there are two possible ways to convert a PFN to the
 corresponding `struct page` - a "classic sparse" and "sparse
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 01e18e43b174..000c1b48e973 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -243,13 +243,8 @@ void __init bootmem_init(void)
 		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
 
 	/*
-	 * Sparsemem tries to allocate bootmem in memory_present(),
-	 * so must be done after the fixed reservations
-	 */
-	memblocks_present();
-
-	/*
-	 * sparse_init() needs the bootmem allocator up and running.
+	 * sparse_init() tries to allocate memory from memblock, so must be
+	 * done after the fixed reservations
 	 */
 	sparse_init();
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f8c19c6c8e71..481d22c32a2e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -430,11 +430,9 @@ void __init bootmem_init(void)
 #endif
 
 	/*
-	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
-	 * done after the fixed reservations.
+	 * sparse_init() tries to allocate memory from memblock, so must be
+	 * done after the fixed reservations
 	 */
-	memblocks_present();
-
 	sparse_init();
 	zone_sizes_init(min, max);
 
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 2ba2127335a7..dbe829fc5298 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -600,7 +600,6 @@ void __init paging_init(void)
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 521b59ba716c..0880a003573d 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -172,9 +172,6 @@ void __init setup_memory(void)
 				  &memblock.memory, 0);
 	}
 
-	/* XXX need to clip this if using highmem? */
-	sparse_memory_present_with_active_regions(0);
-
 	paging_init();
 }
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 588b21245e00..bf5f5acab0a8 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -371,14 +371,6 @@ static void __init bootmem_init(void)
 #endif
 	}
 
-
-	/*
-	 * In any case the added to the memblock memory regions
-	 * (highmem/lowmem, available/reserved, etc) are considered
-	 * as present, so inform sparsemem about them.
-	 */
-	memblocks_present();
-
 	/*
 	 * Reserve initrd memory if needed.
 	 */
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 901f5be5ee76..ea8bb1bc667e 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -220,7 +220,6 @@ static __init void prom_meminit(void)
 			cpumask_clear(&__node_cpumask[node]);
 		}
 	}
-	memblocks_present();
 	max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
 
 	for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 1213215ea965..d411e0a90a5b 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -402,8 +402,6 @@ void __init prom_meminit(void)
 		}
 		__node_data[node] = &null_node;
 	}
-
-	memblocks_present();
 }
 
 void __init prom_free_prom_memory(void)
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 39ea464c8bd9..4381b65ae1e0 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -689,11 +689,6 @@ void __init paging_init(void)
 	flush_cache_all_local(); /* start with known state */
 	flush_tlb_all_local(NULL);
 
-	/*
-	 * Mark all memblocks as present for sparsemem using
-	 * memory_present() and then initialize sparsemem.
-	 */
-	memblocks_present();
 	sparse_init();
 	parisc_bootmem_free();
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index ab12916ec1a7..ec68c9eeac0e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -183,8 +183,6 @@ void __init mem_topology_setup(void)
 
 void __init initmem_init(void)
 {
-	/* XXX need to clip this if using highmem? */
-	sparse_memory_present_with_active_regions(0);
 	sparse_init();
 }
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9fcf2d195830..03a81d65095b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -949,7 +949,6 @@ void __init initmem_init(void)
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 		setup_node_data(nid, start_pfn, end_pfn);
-		sparse_memory_present_with_active_regions(nid);
 	}
 
 	sparse_init();
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 416e520d07d3..f6e6286b3d15 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -544,7 +544,6 @@ void mark_rodata_ro(void)
 void __init paging_init(void)
 {
 	setup_vm_final();
-	memblocks_present();
 	sparse_init();
 	setup_zero_page();
 	zone_sizes_init();
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 6dc7c3b60ef6..0d282081dc1f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -115,7 +115,6 @@ void __init paging_init(void)
 	__load_psw_mask(psw.mask);
 	kasan_free_early_identity();
 
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	zone_dma_bits = 31;
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index a86ce13f392c..613de8096335 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -241,12 +241,6 @@ static void __init do_init_bootmem(void)
 
 	plat_mem_setup();
 
-	for_each_memblock(memory, reg) {
-		int nid = memblock_get_region_node(reg);
-
-		memory_present(nid, memblock_region_memory_base_pfn(reg),
-			memblock_region_memory_end_pfn(reg));
-	}
 	sparse_init();
 }
 
diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c
index f7e4439deb17..50f0dc1744d0 100644
--- a/arch/sh/mm/numa.c
+++ b/arch/sh/mm/numa.c
@@ -53,7 +53,4 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 
 	/* It's up */
 	node_set_online(nid);
-
-	/* Kick sparsemem */
-	sparse_memory_present_with_active_regions(nid);
 }
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 02e6e5e0f106..fad6d3129904 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1610,7 +1610,6 @@ static unsigned long __init bootmem_init(unsigned long phys_base)
 
 	/* XXX cpu notifier XXX */
 
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 
 	return end_pfn;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8b4afad84f4a..4cb958419fb0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -678,7 +678,6 @@ void __init initmem_init(void)
 #endif
 
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
-	sparse_memory_present_with_active_regions(0);
 
 #ifdef CONFIG_FLATMEM
 	max_mapnr = IS_ENABLED(CONFIG_HIGHMEM) ? highend_pfn : max_low_pfn;
@@ -718,7 +717,6 @@ void __init paging_init(void)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 	olpc_dt_build_devicetree();
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	zone_sizes_init();
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 53e1d4f4ed9d..1c1209da55fe 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -817,7 +817,6 @@ void __init initmem_init(void)
 
 void __init paging_init(void)
 {
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 
 	/*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cf7e4605ff3f..392016ce5878 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2382,9 +2382,6 @@ static inline unsigned long get_num_physpages(void)
  * for_each_valid_physical_page_range()
  * 	memblock_add_node(base, size, nid)
  * free_area_init(max_zone_pfns);
- *
- * sparse_memory_present_with_active_regions() calls memory_present() for
- * each range when SPARSEMEM is enabled.
  */
 void free_area_init(unsigned long *max_zone_pfn);
 unsigned long node_map_pfn_alignment(void);
@@ -2395,7 +2392,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 extern void get_pfn_range_for_nid(unsigned int nid,
 			unsigned long *start_pfn, unsigned long *end_pfn);
 extern unsigned long find_min_pfn_with_active_regions(void);
-extern void sparse_memory_present_with_active_regions(int nid);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 static inline int early_pfn_to_nid(unsigned long pfn)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a3bd54139a30..2eef8afd3a0f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -839,18 +839,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 
 extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
 
-#ifdef CONFIG_HAVE_MEMORY_PRESENT
-void memory_present(int nid, unsigned long start, unsigned long end);
-#else
-static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
-#endif
-
-#if defined(CONFIG_SPARSEMEM)
-void memblocks_present(void);
-#else
-static inline void memblocks_present(void) {}
-#endif
-
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 int local_memory_node(int node_id);
 #else
@@ -1407,8 +1395,6 @@ struct mminit_pfnnid_cache {
 #define early_pfn_valid(pfn)	(1)
 #endif
 
-void memory_present(int nid, unsigned long start, unsigned long end);
-
 /*
  * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
  * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
diff --git a/mm/Kconfig b/mm/Kconfig
index d41f3fa7e923..6c974888f86f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -88,13 +88,9 @@ config NEED_MULTIPLE_NODES
 	def_bool y
 	depends on DISCONTIGMEM || NUMA
 
-config HAVE_MEMORY_PRESENT
-	def_bool y
-	depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
-
 #
 # SPARSEMEM_EXTREME (which is the default) does some bootmem
-# allocations when memory_present() is called.  If this cannot
+# allocations when sparse_init() is called.  If this cannot
 # be done on your architecture, select this option.  However,
 # statically allocating the mem_section[] array can potentially
 # consume vast quantities of .bss, so be careful.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8d5d8526c2f3..f49de9e97bf2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6324,22 +6324,6 @@ void __meminit init_currently_empty_zone(struct zone *zone,
 	zone->initialized = 1;
 }
 
-/**
- * sparse_memory_present_with_active_regions - Call memory_present for each active range
- * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
- *
- * If an architecture guarantees that all ranges registered contain no holes and may
- * be freed, this function may be used instead of calling memory_present() manually.
- */
-void __init sparse_memory_present_with_active_regions(int nid)
-{
-	unsigned long start_pfn, end_pfn;
-	int i, this_nid;
-
-	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
-		memory_present(this_nid, start_pfn, end_pfn);
-}
-
 /**
  * get_pfn_range_for_nid - Return the start and end page frames for a node
  * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
diff --git a/mm/sparse.c b/mm/sparse.c
index 1b5e0385f419..fcc3d176f1ea 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -249,7 +249,7 @@ void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
 #endif
 
 /* Record a memory area against a node. */
-void __init memory_present(int nid, unsigned long start, unsigned long end)
+static void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
 	unsigned long pfn;
 
@@ -285,11 +285,11 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 }
 
 /*
- * Mark all memblocks as present using memory_present(). This is a
- * convenience function that is useful for a number of arches
- * to mark all of the systems memory as present during initialization.
+ * Mark all memblocks as present using memory_present().
+ * This is a convenience function that is useful to mark all of the systems
+ * memory as present during initialization.
  */
-void __init memblocks_present(void)
+static void __init memblocks_present(void)
 {
 	struct memblock_region *reg;
 
@@ -574,9 +574,13 @@ failed:
  */
 void __init sparse_init(void)
 {
-	unsigned long pnum_begin = first_present_section_nr();
-	int nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
-	unsigned long pnum_end, map_count = 1;
+	unsigned long pnum_end, pnum_begin, map_count = 1;
+	int nid_begin;
+
+	memblocks_present();
+
+	pnum_begin = first_present_section_nr();
+	nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
 
 	/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
 	set_pageblock_order();
-- 
cgit v1.2.3


From 26e760c9a7c8ec31fa1a6bfbbce3f63f189ccef0 Mon Sep 17 00:00:00 2001
From: Walter Wu <walter-zh.wu@mediatek.com>
Date: Thu, 6 Aug 2020 23:24:35 -0700
Subject: rcu: kasan: record and print call_rcu() call stack

Patch series "kasan: memorize and print call_rcu stack", v8.

This patchset improves KASAN reports by making them to have call_rcu()
call stack information.  It is useful for programmers to solve
use-after-free or double-free memory issue.

The KASAN report was as follows(cleaned up slightly):

BUG: KASAN: use-after-free in kasan_rcu_reclaim+0x58/0x60

Freed by task 0:
 kasan_save_stack+0x24/0x50
 kasan_set_track+0x24/0x38
 kasan_set_free_info+0x18/0x20
 __kasan_slab_free+0x10c/0x170
 kasan_slab_free+0x10/0x18
 kfree+0x98/0x270
 kasan_rcu_reclaim+0x1c/0x60

Last call_rcu():
 kasan_save_stack+0x24/0x50
 kasan_record_aux_stack+0xbc/0xd0
 call_rcu+0x8c/0x580
 kasan_rcu_uaf+0xf4/0xf8

Generic KASAN will record the last two call_rcu() call stacks and print up
to 2 call_rcu() call stacks in KASAN report.  it is only suitable for
generic KASAN.

This feature considers the size of struct kasan_alloc_meta and
kasan_free_meta, we try to optimize the structure layout and size, lets it
get better memory consumption.

[1]https://bugzilla.kernel.org/show_bug.cgi?id=198437
[2]https://groups.google.com/forum/#!searchin/kasan-dev/better$20stack$20traces$20for$20rcu%7Csort:date/kasan-dev/KQsjT_88hDE/7rNUZprRBgAJ

This patch (of 4):

This feature will record the last two call_rcu() call stacks and prints up
to 2 call_rcu() call stacks in KASAN report.

When call_rcu() is called, we store the call_rcu() call stack into slub
alloc meta-data, so that the KASAN report can print rcu stack.

[1]https://bugzilla.kernel.org/show_bug.cgi?id=198437
[2]https://groups.google.com/forum/#!searchin/kasan-dev/better$20stack$20traces$20for$20rcu%7Csort:date/kasan-dev/KQsjT_88hDE/7rNUZprRBgAJ

[walter-zh.wu@mediatek.com: build fix]
  Link: http://lkml.kernel.org/r/20200710162401.23816-1-walter-zh.wu@mediatek.com

Suggested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Walter Wu <walter-zh.wu@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: http://lkml.kernel.org/r/20200710162123.23713-1-walter-zh.wu@mediatek.com
Link: http://lkml.kernel.org/r/20200601050847.1096-1-walter-zh.wu@mediatek.com
Link: http://lkml.kernel.org/r/20200601050927.1153-1-walter-zh.wu@mediatek.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h |  2 ++
 kernel/rcu/tree.c     |  2 ++
 mm/kasan/common.c     |  4 ++--
 mm/kasan/generic.c    | 21 +++++++++++++++++++++
 mm/kasan/kasan.h      |  9 +++++++++
 mm/kasan/report.c     | 28 +++++++++++++++++++++++-----
 6 files changed, 59 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 82522e996c76..18452e35e7b2 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -174,11 +174,13 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
+void kasan_record_aux_stack(void *ptr);
 
 #else /* CONFIG_KASAN_GENERIC */
 
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
+static inline void kasan_record_aux_stack(void *ptr) {}
 
 #endif /* CONFIG_KASAN_GENERIC */
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ac7198ed3197..8ce77d9ac716 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -59,6 +59,7 @@
 #include <linux/sched/clock.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
+#include <linux/kasan.h>
 #include "../time/tick-internal.h"
 
 #include "tree.h"
@@ -2890,6 +2891,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
+	kasan_record_aux_stack(head);
 	rdp = this_cpu_ptr(&rcu_data);
 
 	/* Add the callback to our list. */
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 757d4074fe28..ad24666f50e4 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -40,7 +40,7 @@
 #include "kasan.h"
 #include "../slab.h"
 
-static inline depot_stack_handle_t save_stack(gfp_t flags)
+depot_stack_handle_t kasan_save_stack(gfp_t flags)
 {
 	unsigned long entries[KASAN_STACK_DEPTH];
 	unsigned int nr_entries;
@@ -53,7 +53,7 @@ static inline depot_stack_handle_t save_stack(gfp_t flags)
 static inline void set_track(struct kasan_track *track, gfp_t flags)
 {
 	track->pid = current->pid;
-	track->stack = save_stack(flags);
+	track->stack = kasan_save_stack(flags);
 }
 
 void kasan_enable_current(void)
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 098a7dbaced6..d70586393b04 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -324,3 +324,24 @@ DEFINE_ASAN_SET_SHADOW(f2);
 DEFINE_ASAN_SET_SHADOW(f3);
 DEFINE_ASAN_SET_SHADOW(f5);
 DEFINE_ASAN_SET_SHADOW(f8);
+
+void kasan_record_aux_stack(void *addr)
+{
+	struct page *page = kasan_addr_to_page(addr);
+	struct kmem_cache *cache;
+	struct kasan_alloc_meta *alloc_info;
+	void *object;
+
+	if (!(page && PageSlab(page)))
+		return;
+
+	cache = page->slab_cache;
+	object = nearest_obj(cache, page, addr);
+	alloc_info = get_alloc_info(cache, object);
+
+	/*
+	 * record the last two call_rcu() call stacks.
+	 */
+	alloc_info->aux_stack[1] = alloc_info->aux_stack[0];
+	alloc_info->aux_stack[0] = kasan_save_stack(GFP_NOWAIT);
+}
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index cfade6413528..f89a195e336a 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -104,6 +104,13 @@ struct kasan_track {
 
 struct kasan_alloc_meta {
 	struct kasan_track alloc_track;
+#ifdef CONFIG_KASAN_GENERIC
+	/*
+	 * call_rcu() call stack is stored into struct kasan_alloc_meta.
+	 * The free stack is stored into struct kasan_free_meta.
+	 */
+	depot_stack_handle_t aux_stack[2];
+#endif
 	struct kasan_track free_track[KASAN_NR_FREE_STACKS];
 #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
 	u8 free_pointer_tag[KASAN_NR_FREE_STACKS];
@@ -159,6 +166,8 @@ void kasan_report_invalid_free(void *object, unsigned long ip);
 
 struct page *kasan_addr_to_page(const void *addr);
 
+depot_stack_handle_t kasan_save_stack(gfp_t flags);
+
 #if defined(CONFIG_KASAN_GENERIC) && \
 	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB))
 void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 51ec45407a0b..445a9d56eb13 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -106,15 +106,20 @@ static void end_report(unsigned long *flags)
 	kasan_enable_current();
 }
 
+static void print_stack(depot_stack_handle_t stack)
+{
+	unsigned long *entries;
+	unsigned int nr_entries;
+
+	nr_entries = stack_depot_fetch(stack, &entries);
+	stack_trace_print(entries, nr_entries, 0);
+}
+
 static void print_track(struct kasan_track *track, const char *prefix)
 {
 	pr_err("%s by task %u:\n", prefix, track->pid);
 	if (track->stack) {
-		unsigned long *entries;
-		unsigned int nr_entries;
-
-		nr_entries = stack_depot_fetch(track->stack, &entries);
-		stack_trace_print(entries, nr_entries, 0);
+		print_stack(track->stack);
 	} else {
 		pr_err("(stack is not available)\n");
 	}
@@ -193,6 +198,19 @@ static void describe_object(struct kmem_cache *cache, void *object,
 		free_track = kasan_get_free_track(cache, object, tag);
 		print_track(free_track, "Freed");
 		pr_err("\n");
+
+#ifdef CONFIG_KASAN_GENERIC
+		if (alloc_info->aux_stack[0]) {
+			pr_err("Last call_rcu():\n");
+			print_stack(alloc_info->aux_stack[0]);
+			pr_err("\n");
+		}
+		if (alloc_info->aux_stack[1]) {
+			pr_err("Second to last call_rcu():\n");
+			print_stack(alloc_info->aux_stack[1]);
+			pr_err("\n");
+		}
+#endif
 	}
 
 	describe_object_addr(cache, object, addr);
-- 
cgit v1.2.3


From c0e16ab3b5887e86cd45b95e28cf66498b161ee1 Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 6 Aug 2020 23:24:50 -0700
Subject: kasan: remove kasan_unpoison_stack_above_sp_to()

kasan_unpoison_stack_above_sp_to() is defined in kasan code but never
used.  The function was introduced as part of the commit:

   commit 9f7d416c36124667 ("kprobes: Unpoison stack in jprobe_return() for KASAN")

... where it was necessary because x86's jprobe_return() would leave
stale shadow on the stack, and was an oddity in that regard.

Since then, jprobes were removed entirely, and as of commit:

  commit 80006dbee674f9fa ("kprobes/x86: Remove jprobe implementation")

... there have been no callers of this function.

Remove the declaration and the implementation.

Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Link: http://lkml.kernel.org/r/20200706143505.23299-1-vincenzo.frascino@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h |  2 --
 mm/kasan/common.c     | 15 ---------------
 2 files changed, 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 18452e35e7b2..087fba34b209 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -38,7 +38,6 @@ extern void kasan_disable_current(void);
 void kasan_unpoison_shadow(const void *address, size_t size);
 
 void kasan_unpoison_task_stack(struct task_struct *task);
-void kasan_unpoison_stack_above_sp_to(const void *watermark);
 
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
@@ -101,7 +100,6 @@ void kasan_restore_multi_shot(bool enabled);
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
-static inline void kasan_unpoison_stack_above_sp_to(const void *watermark) {}
 
 static inline void kasan_enable_current(void) {}
 static inline void kasan_disable_current(void) {}
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index f18067736f7c..950fd372a07e 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -180,21 +180,6 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 	kasan_unpoison_shadow(base, watermark - base);
 }
 
-/*
- * Clear all poison for the region between the current SP and a provided
- * watermark value, as is sometimes required prior to hand-crafted asm function
- * returns in the middle of functions.
- */
-void kasan_unpoison_stack_above_sp_to(const void *watermark)
-{
-	const void *sp = __builtin_frame_address(0);
-	size_t size = watermark - sp;
-
-	if (WARN_ON(sp > watermark))
-		return;
-	kasan_unpoison_shadow(sp, size);
-}
-
 void kasan_alloc_pages(struct page *page, unsigned int order)
 {
 	u8 tag;
-- 
cgit v1.2.3


From 2c547f9da0539ad1f7ef7f08c8c82036d61b011a Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 6 Aug 2020 23:25:01 -0700
Subject: efi: provide empty efi_enter_virtual_mode implementation

When CONFIG_EFI is not enabled, we might get an undefined reference to
efi_enter_virtual_mode() error, if this efi_enabled() call isn't inlined
into start_kernel().  This happens in particular, if start_kernel() is
annodated with __no_sanitize_address.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Elena Petrova <lenaptr@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Walter Wu <walter-zh.wu@mediatek.com>
Link: http://lkml.kernel.org/r/6514652d3a32d3ed33d6eb5c91d0af63bf0d1a0c.1596544734.git.andreyknvl@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/efi.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/efi.h b/include/linux/efi.h
index 05c47f857383..73db1ae04cef 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -606,7 +606,11 @@ extern void *efi_get_pal_addr (void);
 extern void efi_map_pal_code (void);
 extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timespec64 *ts);
+#ifdef CONFIG_EFI
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
+#else
+static inline void efi_enter_virtual_mode (void) {}
+#endif
 #ifdef CONFIG_X86
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
-- 
cgit v1.2.3


From 0a18e60788d6a39436e8b5e91001b790043fc29c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 6 Aug 2020 23:25:27 -0700
Subject: mm: remove vm_total_pages

The global variable "vm_total_pages" is a relic from older days.  There is
only a single user that reads the variable - build_all_zonelists() - and
the first thing it does is update it.

Use a local variable in build_all_zonelists() instead and remove the
global variable.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/20200619132410.23859-2-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 1 -
 mm/memory_hotplug.c  | 3 ---
 mm/page-writeback.c  | 6 ++----
 mm/page_alloc.c      | 2 ++
 mm/vmscan.c          | 5 -----
 5 files changed, 4 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5b3216ba39a9..4ab236692e05 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -372,7 +372,6 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);
-extern unsigned long vm_total_pages;
 
 extern unsigned long reclaim_pages(struct list_head *page_list);
 #ifdef CONFIG_NUMA
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index da374cd3d45b..be3c62e3fb95 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -844,8 +844,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	kswapd_run(nid);
 	kcompactd_run(nid);
 
-	vm_total_pages = nr_free_pagecache_pages();
-
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_ONLINE, &arg);
@@ -1595,7 +1593,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		kcompactd_stop(node);
 	}
 
-	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 28b3e7a67565..4e4ddd67b71e 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2076,13 +2076,11 @@ static int page_writeback_cpu_online(unsigned int cpu)
  * Called early on to tune the page writeback dirty limits.
  *
  * We used to scale dirty pages according to how total memory
- * related to pages that could be allocated for buffers (by
- * comparing nr_free_buffer_pages() to vm_total_pages.
+ * related to pages that could be allocated for buffers.
  *
  * However, that was when we used "dirty_ratio" to scale with
  * all memory, and we don't do that any more. "dirty_ratio"
- * is now applied to total non-HIGHPAGE memory (by subtracting
- * totalhigh_pages from vm_total_pages), and as such we can't
+ * is now applied to total non-HIGHPAGE memory, and as such we can't
  * get into the old insane situation any more where we had
  * large amounts of dirty pages compared to a small amount of
  * non-HIGHMEM memory.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0fb5c97ac94c..20184e2a8cfe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5912,6 +5912,8 @@ build_all_zonelists_init(void)
  */
 void __ref build_all_zonelists(pg_data_t *pgdat)
 {
+	unsigned long vm_total_pages;
+
 	if (system_state == SYSTEM_BOOTING) {
 		build_all_zonelists_init();
 	} else {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23156c252e0a..d4d7cd1d24c1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -170,11 +170,6 @@ struct scan_control {
  * From 0 .. 200.  Higher means more swappy.
  */
 int vm_swappiness = 60;
-/*
- * The total number of pages which are beyond the high watermark within all
- * zones.
- */
-unsigned long vm_total_pages;
 
 static void set_task_reclaim_state(struct task_struct *task,
 				   struct reclaim_state *rs)
-- 
cgit v1.2.3


From 56b9413bcb369f1329a438c7b61d235b4123e794 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 6 Aug 2020 23:25:30 -0700
Subject: mm/page_alloc: remove nr_free_pagecache_pages()

nr_free_pagecache_pages() isn't used outside page_alloc.c anymore - and
the name does not really help to understand what's going on.  Let's
open-code it instead and add a comment.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Huang Ying <ying.huang@intel.com>
Link: http://lkml.kernel.org/r/20200619132410.23859-3-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  1 -
 mm/page_alloc.c      | 16 ++--------------
 2 files changed, 2 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4ab236692e05..7eb59bc552a5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -328,7 +328,6 @@ void workingset_update_node(struct xa_node *node);
 /* linux/mm/page_alloc.c */
 extern unsigned long totalreserve_pages;
 extern unsigned long nr_free_buffer_pages(void);
-extern unsigned long nr_free_pagecache_pages(void);
 
 /* Definition of global_zone_page_state not available yet */
 #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 20184e2a8cfe..ba09a3aeb76b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5186,19 +5186,6 @@ unsigned long nr_free_buffer_pages(void)
 }
 EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
 
-/**
- * nr_free_pagecache_pages - count number of pages beyond high watermark
- *
- * nr_free_pagecache_pages() counts the number of pages which are beyond the
- * high watermark within all zones.
- *
- * Return: number of pages beyond high watermark within all zones.
- */
-unsigned long nr_free_pagecache_pages(void)
-{
-	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
-}
-
 static inline void show_node(struct zone *zone)
 {
 	if (IS_ENABLED(CONFIG_NUMA))
@@ -5920,7 +5907,8 @@ void __ref build_all_zonelists(pg_data_t *pgdat)
 		__build_all_zonelists(pgdat);
 		/* cpuset refresh routine should be here */
 	}
-	vm_total_pages = nr_free_pagecache_pages();
+	/* Get the number of free pages beyond high watermark in all zones. */
+	vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
 	/*
 	 * Disable grouping by mobility if the number of pages in the
 	 * system is too low to allow the mechanism to work. It would be
-- 
cgit v1.2.3


From d38ac97f8a7c4519ba141bbd7c2f7a8da8c9ff8d Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 6 Aug 2020 23:25:41 -0700
Subject: mm/page_alloc.c: replace the definition of NR_MIGRATETYPE_BITS with
 PB_migratetype_bits

We already have the definition of PB_migratetype_bits and current
NR_MIGRATETYPE_BITS looks like a cyclic definition.

Just use PB_migratetype_bits is enough.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/20200623124201.8199-1-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2eef8afd3a0f..f509ede317b5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -88,8 +88,7 @@ static inline bool is_migrate_movable(int mt)
 
 extern int page_group_by_mobility_disabled;
 
-#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
-#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
+#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
 
 #define get_pageblock_migratetype(page)					\
 	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
-- 
cgit v1.2.3


From d93d5ab9ca01e24efc6add60371b0d5684b5c146 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 6 Aug 2020 23:25:48 -0700
Subject: mm/page_alloc.c: simplify pageblock bitmap access

Due to commit e58469bafd05 ("mm: page_alloc: use word-based accesses for
get/set pageblock bitmaps"), pageblock bitmap is accessed with word-based
access.  This operation could be simplified a little.

Intuitively, if we want to get a bit range [start_idx, end_idx] in a word,
we can do like this:

    mask = (1 << (end_bitidx - start_bitidx + 1)) - 1;
    ret = (word >> start_idx) & mask;

And also if we want to set a bit range [start_idx, end_idx] with flags, we
can do the same by just shift start_bitidx.

By doing so we reduce some instructions for these two helper functions:

                                Before   Patched
    set_pfnblock_flags_mask     209      198(-5%)
    get_pfnblock_flags_mask     101      87(-13%)

Since the syntax is changed a little, we need to check the whole 4-bit
migrate_type instead of part of it.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/20200623124201.8199-3-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pageblock-flags.h | 22 +++++++---------------
 mm/page_alloc.c                 | 13 ++++++-------
 2 files changed, 13 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index c066fec5b74b..6556e4474409 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -66,25 +66,17 @@ void set_pfnblock_flags_mask(struct page *page,
 				unsigned long mask);
 
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
-#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \
-	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
-			end_bitidx,					\
-			(1 << (end_bitidx - start_bitidx + 1)) - 1)
-#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \
-	set_pfnblock_flags_mask(page, flags, page_to_pfn(page),		\
-			end_bitidx,					\
-			(1 << (end_bitidx - start_bitidx + 1)) - 1)
-
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
-			get_pageblock_flags_group(page, PB_migrate_skip,     \
-							PB_migrate_skip)
+	get_pfnblock_flags_mask(page, page_to_pfn(page),	\
+			PB_migrate_skip, (1 << (PB_migrate_skip)))
 #define clear_pageblock_skip(page) \
-			set_pageblock_flags_group(page, 0, PB_migrate_skip,  \
-							PB_migrate_skip)
+	set_pfnblock_flags_mask(page, 0, page_to_pfn(page),	\
+			PB_migrate_skip, (1 << PB_migrate_skip))
 #define set_pageblock_skip(page) \
-			set_pageblock_flags_group(page, 1, PB_migrate_skip,  \
-							PB_migrate_skip)
+	set_pfnblock_flags_mask(page, (1 << PB_migrate_skip),	\
+			page_to_pfn(page),			\
+			PB_migrate_skip, (1 << PB_migrate_skip))
 #else
 static inline bool get_pageblock_skip(struct page *page)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6c524fb76b31..e1fdca9ef4e9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -489,8 +489,7 @@ static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page
 	bitidx &= (BITS_PER_LONG-1);
 
 	word = bitmap[word_bitidx];
-	bitidx += end_bitidx;
-	return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
+	return (word >> bitidx) & mask;
 }
 
 unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
@@ -532,9 +531,8 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
 
 	VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
 
-	bitidx += end_bitidx;
-	mask <<= (BITS_PER_LONG - bitidx - 1);
-	flags <<= (BITS_PER_LONG - bitidx - 1);
+	mask <<= bitidx;
+	flags <<= bitidx;
 
 	word = READ_ONCE(bitmap[word_bitidx]);
 	for (;;) {
@@ -551,8 +549,9 @@ void set_pageblock_migratetype(struct page *page, int migratetype)
 		     migratetype < MIGRATE_PCPTYPES))
 		migratetype = MIGRATE_UNMOVABLE;
 
-	set_pageblock_flags_group(page, (unsigned long)migratetype,
-					PB_migrate, PB_migrate_end);
+	set_pfnblock_flags_mask(page, (unsigned long)migratetype,
+				page_to_pfn(page), PB_migrate_end,
+				MIGRATETYPE_MASK);
 }
 
 #ifdef CONFIG_DEBUG_VM
-- 
cgit v1.2.3


From 535b81e209219e03f815379746bfd1eeb82d68e5 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 6 Aug 2020 23:25:51 -0700
Subject: mm/page_alloc.c: remove unnecessary end_bitidx for
 [set|get]_pfnblock_flags_mask()

After previous cleanup, the end_bitidx is not necessary any more.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/20200623124201.8199-4-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h          |  3 +--
 include/linux/pageblock-flags.h |  8 +++-----
 mm/page_alloc.c                 | 15 +++++----------
 3 files changed, 9 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f509ede317b5..635a96cd9b1f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -91,8 +91,7 @@ extern int page_group_by_mobility_disabled;
 #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
 
 #define get_pageblock_migratetype(page)					\
-	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
-			PB_migrate_end, MIGRATETYPE_MASK)
+	get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
 
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 6556e4474409..fff52ad370c1 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -56,27 +56,25 @@ struct page;
 
 unsigned long get_pfnblock_flags_mask(struct page *page,
 				unsigned long pfn,
-				unsigned long end_bitidx,
 				unsigned long mask);
 
 void set_pfnblock_flags_mask(struct page *page,
 				unsigned long flags,
 				unsigned long pfn,
-				unsigned long end_bitidx,
 				unsigned long mask);
 
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
 	get_pfnblock_flags_mask(page, page_to_pfn(page),	\
-			PB_migrate_skip, (1 << (PB_migrate_skip)))
+			(1 << (PB_migrate_skip)))
 #define clear_pageblock_skip(page) \
 	set_pfnblock_flags_mask(page, 0, page_to_pfn(page),	\
-			PB_migrate_skip, (1 << PB_migrate_skip))
+			(1 << PB_migrate_skip))
 #define set_pageblock_skip(page) \
 	set_pfnblock_flags_mask(page, (1 << PB_migrate_skip),	\
 			page_to_pfn(page),			\
-			PB_migrate_skip, (1 << PB_migrate_skip))
+			(1 << PB_migrate_skip))
 #else
 static inline bool get_pageblock_skip(struct page *page)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e1fdca9ef4e9..53c89de89e46 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -469,14 +469,13 @@ static inline int pfn_to_bitidx(struct page *page, unsigned long pfn)
  * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @pfn: The target page frame number
- * @end_bitidx: The last bit of interest to retrieve
  * @mask: mask of bits that the caller is interested in
  *
  * Return: pageblock_bits flags
  */
-static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page,
+static __always_inline
+unsigned long __get_pfnblock_flags_mask(struct page *page,
 					unsigned long pfn,
-					unsigned long end_bitidx,
 					unsigned long mask)
 {
 	unsigned long *bitmap;
@@ -493,15 +492,14 @@ static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page
 }
 
 unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
-					unsigned long end_bitidx,
 					unsigned long mask)
 {
-	return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask);
+	return __get_pfnblock_flags_mask(page, pfn, mask);
 }
 
 static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
 {
-	return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK);
+	return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
 }
 
 /**
@@ -509,12 +507,10 @@ static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned
  * @page: The page within the block of interest
  * @flags: The flags to set
  * @pfn: The target page frame number
- * @end_bitidx: The last bit of interest
  * @mask: mask of bits that the caller is interested in
  */
 void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
 					unsigned long pfn,
-					unsigned long end_bitidx,
 					unsigned long mask)
 {
 	unsigned long *bitmap;
@@ -550,8 +546,7 @@ void set_pageblock_migratetype(struct page *page, int migratetype)
 		migratetype = MIGRATE_UNMOVABLE;
 
 	set_pfnblock_flags_mask(page, (unsigned long)migratetype,
-				page_to_pfn(page), PB_migrate_end,
-				MIGRATETYPE_MASK);
+				page_to_pfn(page), MIGRATETYPE_MASK);
 }
 
 #ifdef CONFIG_DEBUG_VM
-- 
cgit v1.2.3


From 8510e69c8efef82f2b37ea3e8ea19a27122c533e Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 6 Aug 2020 23:26:04 -0700
Subject: mm/page_alloc: fix memalloc_nocma_{save/restore} APIs

Currently, memalloc_nocma_{save/restore} API that prevents CMA area
in page allocation is implemented by using current_gfp_context(). However,
there are two problems of this implementation.

First, this doesn't work for allocation fastpath. In the fastpath,
original gfp_mask is used since current_gfp_context() is introduced in
order to control reclaim and it is on slowpath. So, CMA area can be
allocated through the allocation fastpath even if
memalloc_nocma_{save/restore} APIs are used. Currently, there is just
one user for these APIs and it has a fallback method to prevent actual
problem.
Second, clearing __GFP_MOVABLE in current_gfp_context() has a side effect
to exclude the memory on the ZONE_MOVABLE for allocation target.

To fix these problems, this patch changes the implementation to exclude
CMA area in page allocation. Main point of this change is using the
alloc_flags. alloc_flags is mainly used to control allocation so it fits
for excluding CMA area in allocation.

Fixes: d7fefcc8de91 (mm/cma: add PF flag to force non cma alloc)
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Link: http://lkml.kernel.org/r/1595468942-29687-1-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h |  8 +-------
 mm/page_alloc.c          | 31 +++++++++++++++++++++----------
 2 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 6be66f52a2ad..85023ddc2dc2 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -175,12 +175,10 @@ static inline bool in_vfork(struct task_struct *tsk)
  * Applies per-task gfp context to the given allocation flags.
  * PF_MEMALLOC_NOIO implies GFP_NOIO
  * PF_MEMALLOC_NOFS implies GFP_NOFS
- * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
-	if (unlikely(current->flags &
-		     (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+	if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
 		/*
 		 * NOIO implies both NOIO and NOFS and it is a weaker context
 		 * so always make sure it makes precedence
@@ -189,10 +187,6 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (current->flags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
-#ifdef CONFIG_CMA
-		if (current->flags & PF_MEMALLOC_NOCMA)
-			flags &= ~__GFP_MOVABLE;
-#endif
 	}
 	return flags;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9f9e15a502ae..167732f4d124 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2785,7 +2785,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 	 * allocating from CMA when over half of the zone's free memory
 	 * is in the CMA area.
 	 */
-	if (migratetype == MIGRATE_MOVABLE &&
+	if (alloc_flags & ALLOC_CMA &&
 	    zone_page_state(zone, NR_FREE_CMA_PAGES) >
 	    zone_page_state(zone, NR_FREE_PAGES) / 2) {
 		page = __rmqueue_cma_fallback(zone, order);
@@ -2796,7 +2796,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 retry:
 	page = __rmqueue_smallest(zone, order, migratetype);
 	if (unlikely(!page)) {
-		if (migratetype == MIGRATE_MOVABLE)
+		if (alloc_flags & ALLOC_CMA)
 			page = __rmqueue_cma_fallback(zone, order);
 
 		if (!page && __rmqueue_fallback(zone, order, migratetype,
@@ -3687,6 +3687,20 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 	return alloc_flags;
 }
 
+static inline unsigned int current_alloc_flags(gfp_t gfp_mask,
+					unsigned int alloc_flags)
+{
+#ifdef CONFIG_CMA
+	unsigned int pflags = current->flags;
+
+	if (!(pflags & PF_MEMALLOC_NOCMA) &&
+			gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+
+#endif
+	return alloc_flags;
+}
+
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -4333,10 +4347,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-#ifdef CONFIG_CMA
-	if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
+	alloc_flags = current_alloc_flags(gfp_mask, alloc_flags);
+
 	return alloc_flags;
 }
 
@@ -4637,7 +4649,7 @@ retry:
 
 	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
 	if (reserve_flags)
-		alloc_flags = reserve_flags;
+		alloc_flags = current_alloc_flags(gfp_mask, reserve_flags);
 
 	/*
 	 * Reset the nodemask and zonelist iterators if memory policies can be
@@ -4714,7 +4726,7 @@ retry:
 
 	/* Avoid allocations with no watermarks from looping endlessly */
 	if (tsk_is_oom_victim(current) &&
-	    (alloc_flags == ALLOC_OOM ||
+	    (alloc_flags & ALLOC_OOM ||
 	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
@@ -4806,8 +4818,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
-	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
-		*alloc_flags |= ALLOC_CMA;
+	*alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags);
 
 	return true;
 }
-- 
cgit v1.2.3


From 38ce2a9e33db61a3041840310077072d6210ead4 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 6 Aug 2020 12:46:49 -0400
Subject: tracing: Add trace_array_init_printk() to initialize instance
 trace_printk() buffers

As trace_array_printk() used with not global instances will not add noise to
the main buffer, they are OK to have in the kernel (unlike trace_printk()).
This require the subsystem to create their own tracing instance, and the
trace_array_printk() only writes into those instances.

Add trace_array_init_printk() to initialize the trace_printk() buffers
without printing out the WARNING message.

Reported-by: Sean Paul <sean@poorly.run>
Reviewed-by: Sean Paul <sean@poorly.run>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace.h |  1 +
 kernel/trace/trace.c  | 44 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 7fd86d3c691f..36d255d66f88 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -29,6 +29,7 @@ struct trace_array;
 void trace_printk_init_buffers(void);
 int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		const char *fmt, ...);
+int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
 struct trace_array *trace_array_get_by_name(const char *name);
 int trace_array_destroy(struct trace_array *tr);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 06c0feae5ff9..c5f822736261 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3129,6 +3129,9 @@ static int alloc_percpu_trace_buffer(void)
 {
 	struct trace_buffer_struct *buffers;
 
+	if (trace_percpu_buffer)
+		return 0;
+
 	buffers = alloc_percpu(struct trace_buffer_struct);
 	if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer"))
 		return -ENOMEM;
@@ -3331,6 +3334,26 @@ int trace_array_vprintk(struct trace_array *tr,
 	return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
 }
 
+/**
+ * trace_array_printk - Print a message to a specific instance
+ * @tr: The instance trace_array descriptor
+ * @ip: The instruction pointer that this is called from.
+ * @fmt: The format to print (printf format)
+ *
+ * If a subsystem sets up its own instance, they have the right to
+ * printk strings into their tracing instance buffer using this
+ * function. Note, this function will not write into the top level
+ * buffer (use trace_printk() for that), as writing into the top level
+ * buffer should only have events that can be individually disabled.
+ * trace_printk() is only used for debugging a kernel, and should not
+ * be ever encorporated in normal use.
+ *
+ * trace_array_printk() can be used, as it will not add noise to the
+ * top level tracing buffer.
+ *
+ * Note, trace_array_init_printk() must be called on @tr before this
+ * can be used.
+ */
 __printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
@@ -3355,6 +3378,27 @@ int trace_array_printk(struct trace_array *tr,
 }
 EXPORT_SYMBOL_GPL(trace_array_printk);
 
+/**
+ * trace_array_init_printk - Initialize buffers for trace_array_printk()
+ * @tr: The trace array to initialize the buffers for
+ *
+ * As trace_array_printk() only writes into instances, they are OK to
+ * have in the kernel (unlike trace_printk()). This needs to be called
+ * before trace_array_printk() can be used on a trace_array.
+ */
+int trace_array_init_printk(struct trace_array *tr)
+{
+	if (!tr)
+		return -ENOENT;
+
+	/* This is only allowed for created instances */
+	if (tr == &global_trace)
+		return -EINVAL;
+
+	return alloc_percpu_trace_buffer();
+}
+EXPORT_SYMBOL_GPL(trace_array_init_printk);
+
 __printf(3, 4)
 int trace_array_printk_buf(struct trace_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
-- 
cgit v1.2.3


From 519a8a6cf91dda095be2d36216fc4ebc525270a1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 10 Aug 2020 18:42:14 +0200
Subject: net: Revert "net: optimize the sockptr_t for unified kernel/user
 address spaces"

This reverts commits 6d04fe15f78acdf8e32329e208552e226f7a8ae6 and
a31edb2059ed4e498f9aa8230c734b59d0ad797a.

It turns out the idea to share a single pointer for both kernel and user
space address causes various kinds of problems.  So use the slightly less
optimal version that uses an extra bit, but which is guaranteed to be safe
everywhere.

Fixes: 6d04fe15f78a ("net: optimize the sockptr_t for unified kernel/user address spaces")
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockptr.h     | 26 ++------------------------
 net/ipv4/bpfilter/sockopt.c | 14 ++++++--------
 net/socket.c                |  6 +-----
 3 files changed, 9 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 96840def9d69..ea193414298b 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -8,26 +8,9 @@
 #ifndef _LINUX_SOCKPTR_H
 #define _LINUX_SOCKPTR_H
 
-#include <linux/compiler.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
-typedef union {
-	void		*kernel;
-	void __user	*user;
-} sockptr_t;
-
-static inline bool sockptr_is_kernel(sockptr_t sockptr)
-{
-	return (unsigned long)sockptr.kernel >= TASK_SIZE;
-}
-
-static inline sockptr_t KERNEL_SOCKPTR(void *p)
-{
-	return (sockptr_t) { .kernel = p };
-}
-#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 typedef struct {
 	union {
 		void		*kernel;
@@ -45,15 +28,10 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p)
 {
 	return (sockptr_t) { .kernel = p, .is_kernel = true };
 }
-#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
-static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p,
-		size_t size)
+static inline sockptr_t USER_SOCKPTR(void __user *p)
 {
-	if (!access_ok(p, size))
-		return -EFAULT;
-	*sp = (sockptr_t) { .user = p };
-	return 0;
+	return (sockptr_t) { .user = p };
 }
 
 static inline bool sockptr_is_null(sockptr_t sockptr)
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 545b2640f019..1b34cb9a7708 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -57,18 +57,16 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
 	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
 }
 
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname,
-			    char __user *user_optval, int __user *optlen)
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
+			    int __user *optlen)
 {
-	sockptr_t optval;
-	int err, len;
+	int len;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
-	err = init_user_sockptr(&optval, user_optval, len);
-	if (err)
-		return err;
-	return bpfilter_mbox_request(sk, optname, optval, len, false);
+
+	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
+				     false);
 }
 
 static int __init bpfilter_sockopt_init(void)
diff --git a/net/socket.c b/net/socket.c
index f4d5998bdcba..dbbe8ea7d395 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2095,7 +2095,7 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
 int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 		int optlen)
 {
-	sockptr_t optval;
+	sockptr_t optval = USER_SOCKPTR(user_optval);
 	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
@@ -2103,10 +2103,6 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 	if (optlen < 0)
 		return -EINVAL;
 
-	err = init_user_sockptr(&optval, user_optval, optlen);
-	if (err)
-		return err;
-
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		return err;
-- 
cgit v1.2.3


From 444da3f52407d74c9aa12187ac6b01f76ee47d62 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 10 Aug 2020 11:21:11 -0700
Subject: bitfield.h: don't compile-time validate _val in FIELD_FIT

When ur_load_imm_any() is inlined into jeq_imm(), it's possible for the
compiler to deduce a case where _val can only have the value of -1 at
compile time. Specifically,

/* struct bpf_insn: _s32 imm */
u64 imm = insn->imm; /* sign extend */
if (imm >> 32) { /* non-zero only if insn->imm is negative */
  /* inlined from ur_load_imm_any */
  u32 __imm = imm >> 32; /* therefore, always 0xffffffff */
  if (__builtin_constant_p(__imm) && __imm > 255)
    compiletime_assert_XXX()

This can result in tripping a BUILD_BUG_ON() in __BF_FIELD_CHECK() that
checks that a given value is representable in one byte (interpreted as
unsigned).

FIELD_FIT() should return true or false at runtime for whether a value
can fit for not. Don't break the build over a value that's too large for
the mask. We'd prefer to keep the inlining and compiler optimizations
though we know this case will always return false.

Cc: stable@vger.kernel.org
Fixes: 1697599ee301a ("bitfield.h: add FIELD_FIT() helper")
Link: https://lore.kernel.org/kernel-hardening/CAK7LNASvb0UDJ0U5wkYYRzTAdnEs64HjXpEUL7d=V0CXiAXcNw@mail.gmail.com/
Reported-by: Masahiro Yamada <masahiroy@kernel.org>
Debugged-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bitfield.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 48ea093ff04c..4e035aca6f7e 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -77,7 +77,7 @@
  */
 #define FIELD_FIT(_mask, _val)						\
 	({								\
-		__BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: ");	\
+		__BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: ");	\
 		!((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \
 	})
 
-- 
cgit v1.2.3


From efa8480a831673bb52400df9dbe5da0aacda97bf Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 10 Aug 2020 18:44:24 -0600
Subject: fs: RWF_NOWAIT should imply IOCB_NOIO

With the change allowing read-ahead for IOCB_NOWAIT, we changed the
RWF_NOWAIT semantics of only doing cached reads. Since we know have
IOCB_NOIO to manage that specific side of it, just make RWF_NOWAIT
imply IOCB_NOIO as well to restore the previous behavior.

Fixes: 2e85abf053b9 ("mm: allow read-ahead with IOCB_NOWAIT set")
Reported-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bd7ec3eaeed0..f1cca4bfdd7b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3293,7 +3293,7 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		kiocb_flags |= IOCB_NOWAIT;
+		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
 	}
 	if (flags & RWF_HIPRI)
 		kiocb_flags |= IOCB_HIPRI;
-- 
cgit v1.2.3


From f6ebbcf08f37b01827c51309a188e85165e498e7 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 6 Aug 2020 14:03:55 +0200
Subject: cpufreq: intel_pstate: Implement passive mode with HWP enabled

Allow intel_pstate to work in the passive mode with HWP enabled and
make it set the HWP minimum performance limit (HWP floor) to the
P-state value given by the target frequency supplied by the cpufreq
governor, so as to prevent the HWP algorithm and the CPU scheduler
from working against each other, at least when the schedutil governor
is in use, and update the intel_pstate documentation accordingly.

Among other things, this allows utilization clamps to be taken
into account, at least to a certain extent, when intel_pstate is
in use and makes it more likely that sufficient capacity for
deadline tasks will be provided.

After this change, the resulting behavior of an HWP system with
intel_pstate in the passive mode should be close to the behavior
of the analogous non-HWP system with intel_pstate in the passive
mode, except that the HWP algorithm is generally allowed to make the
CPU run at a frequency above the floor P-state set by intel_pstate in
the entire available range of P-states, while without HWP a CPU can
run in a P-state above the requested one if the latter falls into the
range of turbo P-states (referred to as the turbo range) or if the
P-states of all CPUs in one package are coordinated with each other
at the hardware level.

[Note that in principle the HWP floor may not be taken into account
 by the processor if it falls into the turbo range, in which case the
 processor has a license to choose any P-state, either below or above
 the HWP floor, just like a non-HWP processor in the case when the
 target P-state falls into the turbo range.]

With this change applied, intel_pstate in the passive mode assumes
complete control over the HWP request MSR and concurrent changes of
that MSR (eg. via the direct MSR access interface) are overridden by
it.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
---
 Documentation/admin-guide/pm/intel_pstate.rst |  89 +++++-----
 drivers/cpufreq/cpufreq.c                     |   6 +-
 drivers/cpufreq/intel_pstate.c                | 245 +++++++++++++++++++-------
 include/linux/cpufreq.h                       |   2 +
 4 files changed, 229 insertions(+), 113 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index 40d481cca368..f85767e09911 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -54,10 +54,13 @@ registered (see `below <status_attr_>`_).
 Operation Modes
 ===============
 
-``intel_pstate`` can operate in three different modes: in the active mode with
-or without hardware-managed P-states support and in the passive mode.  Which of
-them will be in effect depends on what kernel command line options are used and
-on the capabilities of the processor.
+``intel_pstate`` can operate in two different modes, active or passive.  In the
+active mode, it uses its own internal performance scaling governor algorithm or
+allows the hardware to do preformance scaling by itself, while in the passive
+mode it responds to requests made by a generic ``CPUFreq`` governor implementing
+a certain performance scaling algorithm.  Which of them will be in effect
+depends on what kernel command line options are used and on the capabilities of
+the processor.
 
 Active Mode
 -----------
@@ -194,10 +197,11 @@ This is the default operation mode of ``intel_pstate`` for processors without
 hardware-managed P-states (HWP) support.  It is always used if the
 ``intel_pstate=passive`` argument is passed to the kernel in the command line
 regardless of whether or not the given processor supports HWP.  [Note that the
-``intel_pstate=no_hwp`` setting implies ``intel_pstate=passive`` if it is used
-without ``intel_pstate=active``.]  Like in the active mode without HWP support,
-in this mode ``intel_pstate`` may refuse to work with processors that are not
-recognized by it.
+``intel_pstate=no_hwp`` setting causes the driver to start in the passive mode
+if it is not combined with ``intel_pstate=active``.]  Like in the active mode
+without HWP support, in this mode ``intel_pstate`` may refuse to work with
+processors that are not recognized by it if HWP is prevented from being enabled
+through the kernel command line.
 
 If the driver works in this mode, the ``scaling_driver`` policy attribute in
 ``sysfs`` for all ``CPUFreq`` policies contains the string "intel_cpufreq".
@@ -318,10 +322,9 @@ manuals need to be consulted to get to it too.
 
 For this reason, there is a list of supported processors in ``intel_pstate`` and
 the driver initialization will fail if the detected processor is not in that
-list, unless it supports the `HWP feature <Active Mode_>`_.  [The interface to
-obtain all of the information listed above is the same for all of the processors
-supporting the HWP feature, which is why they all are supported by
-``intel_pstate``.]
+list, unless it supports the HWP feature.  [The interface to obtain all of the
+information listed above is the same for all of the processors supporting the
+HWP feature, which is why ``intel_pstate`` works with all of them.]
 
 
 User Space Interface in ``sysfs``
@@ -425,22 +428,16 @@ argument is passed to the kernel in the command line.
 	as well as the per-policy ones) are then reset to their default
 	values, possibly depending on the target operation mode.]
 
-	That only is supported in some configurations, though (for example, if
-	the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
-	the operation mode of the driver cannot be changed), and if it is not
-	supported in the current configuration, writes to this attribute will
-	fail with an appropriate error.
-
 ``energy_efficiency``
-	This attribute is only present on platforms, which have CPUs matching
-	Kaby Lake or Coffee Lake desktop CPU model. By default
-	energy efficiency optimizations are disabled on these CPU models in HWP
-	mode by this driver. Enabling energy efficiency may limit maximum
-	operating frequency in both HWP and non HWP mode. In non HWP mode,
-	optimizations are done only in the turbo frequency range. In HWP mode,
-	optimizations are done in the entire frequency range. Setting this
-	attribute to "1" enables energy efficiency optimizations and setting
-	to "0" disables energy efficiency optimizations.
+	This attribute is only present on platforms with CPUs matching the Kaby
+	Lake or Coffee Lake desktop CPU model. By default, energy-efficiency
+	optimizations are disabled on these CPU models if HWP is enabled.
+	Enabling energy-efficiency optimizations may limit maximum operating
+	frequency with or without the HWP feature.  With HWP enabled, the
+	optimizations are done only in the turbo frequency range.  Without it,
+	they are done in the entire available frequency range.  Setting this
+	attribute to "1" enables the energy-efficiency optimizations and setting
+	to "0" disables them.
 
 Interpretation of Policy Attributes
 -----------------------------------
@@ -484,8 +481,8 @@ Next, the following policy attributes have special meaning if
 	policy for the time interval between the last two invocations of the
 	driver's utilization update callback by the CPU scheduler for that CPU.
 
-One more policy attribute is present if the `HWP feature is enabled in the
-processor <Active Mode With HWP_>`_:
+One more policy attribute is present if the HWP feature is enabled in the
+processor:
 
 ``base_frequency``
 	Shows the base frequency of the CPU. Any frequency above this will be
@@ -526,11 +523,11 @@ on the following rules, regardless of the current operation mode of the driver:
 
  3. The global and per-policy limits can be set independently.
 
-If the `HWP feature is enabled in the processor <Active Mode With HWP_>`_, the
-resulting effective values are written into its registers whenever the limits
-change in order to request its internal P-state selection logic to always set
-P-states within these limits.  Otherwise, the limits are taken into account by
-scaling governors (in the `passive mode <Passive Mode_>`_) and by the driver
+In the `active mode with the HWP feature enabled <Active Mode With HWP_>`_, the
+resulting effective values are written into hardware registers whenever the
+limits change in order to request its internal P-state selection logic to always
+set P-states within these limits.  Otherwise, the limits are taken into account
+by scaling governors (in the `passive mode <Passive Mode_>`_) and by the driver
 every time before setting a new P-state for a CPU.
 
 Additionally, if the ``intel_pstate=per_cpu_perf_limits`` command line argument
@@ -541,12 +538,11 @@ at all and the only way to set the limits is by using the policy attributes.
 Energy vs Performance Hints
 ---------------------------
 
-If ``intel_pstate`` works in the `active mode with the HWP feature enabled
-<Active Mode With HWP_>`_ in the processor, additional attributes are present
-in every ``CPUFreq`` policy directory in ``sysfs``.  They are intended to allow
-user space to help ``intel_pstate`` to adjust the processor's internal P-state
-selection logic by focusing it on performance or on energy-efficiency, or
-somewhere between the two extremes:
+If the hardware-managed P-states (HWP) is enabled in the processor, additional
+attributes, intended to allow user space to help ``intel_pstate`` to adjust the
+processor's internal P-state selection logic by focusing it on performance or on
+energy-efficiency, or somewhere between the two extremes, are present in every
+``CPUFreq`` policy directory in ``sysfs``.  They are :
 
 ``energy_performance_preference``
 	Current value of the energy vs performance hint for the given policy
@@ -650,12 +646,14 @@ of them have to be prepended with the ``intel_pstate=`` prefix.
 	Do not register ``intel_pstate`` as the scaling driver even if the
 	processor is supported by it.
 
+``active``
+	Register ``intel_pstate`` in the `active mode <Active Mode_>`_ to start
+	with.
+
 ``passive``
 	Register ``intel_pstate`` in the `passive mode <Passive Mode_>`_ to
 	start with.
 
-	This option implies the ``no_hwp`` one described below.
-
 ``force``
 	Register ``intel_pstate`` as the scaling driver instead of
 	``acpi-cpufreq`` even if the latter is preferred on the given system.
@@ -670,13 +668,12 @@ of them have to be prepended with the ``intel_pstate=`` prefix.
 	driver is used instead of ``acpi-cpufreq``.
 
 ``no_hwp``
-	Do not enable the `hardware-managed P-states (HWP) feature
-	<Active Mode With HWP_>`_ even if it is supported by the processor.
+	Do not enable the hardware-managed P-states (HWP) feature even if it is
+	supported by the processor.
 
 ``hwp_only``
 	Register ``intel_pstate`` as the scaling driver only if the
-	`hardware-managed P-states (HWP) feature <Active Mode With HWP_>`_ is
-	supported by the processor.
+	hardware-managed P-states (HWP) feature is supported by the processor.
 
 ``support_acpi_ppc``
 	Take ACPI ``_PPC`` performance limits into account.
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index afad06b91c77..02ab56b2a0d8 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -73,8 +73,6 @@ static inline bool has_target(void)
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
 static int cpufreq_init_governor(struct cpufreq_policy *policy);
 static void cpufreq_exit_governor(struct cpufreq_policy *policy);
-static int cpufreq_start_governor(struct cpufreq_policy *policy);
-static void cpufreq_stop_governor(struct cpufreq_policy *policy);
 static void cpufreq_governor_limits(struct cpufreq_policy *policy);
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			      struct cpufreq_governor *new_gov,
@@ -2266,7 +2264,7 @@ static void cpufreq_exit_governor(struct cpufreq_policy *policy)
 	module_put(policy->governor->owner);
 }
 
-static int cpufreq_start_governor(struct cpufreq_policy *policy)
+int cpufreq_start_governor(struct cpufreq_policy *policy)
 {
 	int ret;
 
@@ -2293,7 +2291,7 @@ static int cpufreq_start_governor(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void cpufreq_stop_governor(struct cpufreq_policy *policy)
+void cpufreq_stop_governor(struct cpufreq_policy *policy)
 {
 	if (cpufreq_suspended || !policy->governor)
 		return;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fc459c9c00ff..e0220a6fbc69 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -36,6 +36,7 @@
 #define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
 
 #define INTEL_CPUFREQ_TRANSITION_LATENCY	20000
+#define INTEL_CPUFREQ_TRANSITION_DELAY_HWP	5000
 #define INTEL_CPUFREQ_TRANSITION_DELAY		500
 
 #ifdef CONFIG_ACPI
@@ -220,6 +221,7 @@ struct global_params {
  *			preference/bias
  * @epp_saved:		Saved EPP/EPB during system suspend or CPU offline
  *			operation
+ * @epp_cached		Cached HWP energy-performance preference value
  * @hwp_req_cached:	Cached value of the last HWP Request MSR
  * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
  * @last_io_update:	Last time when IO wake flag was set
@@ -257,6 +259,7 @@ struct cpudata {
 	s16 epp_policy;
 	s16 epp_default;
 	s16 epp_saved;
+	s16 epp_cached;
 	u64 hwp_req_cached;
 	u64 hwp_cap_cached;
 	u64 last_io_update;
@@ -639,6 +642,26 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw
 	return index;
 }
 
+static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
+{
+	/*
+	 * Use the cached HWP Request MSR value, because in the active mode the
+	 * register itself may be updated by intel_pstate_hwp_boost_up() or
+	 * intel_pstate_hwp_boost_down() at any time.
+	 */
+	u64 value = READ_ONCE(cpu->hwp_req_cached);
+
+	value &= ~GENMASK_ULL(31, 24);
+	value |= (u64)epp << 24;
+	/*
+	 * The only other updater of hwp_req_cached in the active mode,
+	 * intel_pstate_hwp_set(), is called under the same lock as this
+	 * function, so it cannot run in parallel with the update below.
+	 */
+	WRITE_ONCE(cpu->hwp_req_cached, value);
+	return wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+}
+
 static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 					      int pref_index, bool use_raw,
 					      u32 raw_epp)
@@ -650,28 +673,12 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 		epp = cpu_data->epp_default;
 
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
-		/*
-		 * Use the cached HWP Request MSR value, because the register
-		 * itself may be updated by intel_pstate_hwp_boost_up() or
-		 * intel_pstate_hwp_boost_down() at any time.
-		 */
-		u64 value = READ_ONCE(cpu_data->hwp_req_cached);
-
-		value &= ~GENMASK_ULL(31, 24);
-
 		if (use_raw)
 			epp = raw_epp;
 		else if (epp == -EINVAL)
 			epp = epp_values[pref_index - 1];
 
-		value |= (u64)epp << 24;
-		/*
-		 * The only other updater of hwp_req_cached in the active mode,
-		 * intel_pstate_hwp_set(), is called under the same lock as this
-		 * function, so it cannot run in parallel with the update below.
-		 */
-		WRITE_ONCE(cpu_data->hwp_req_cached, value);
-		ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value);
+		ret = intel_pstate_set_epp(cpu_data, epp);
 	} else {
 		if (epp == -EINVAL)
 			epp = (pref_index - 1) << 2;
@@ -697,10 +704,12 @@ static ssize_t show_energy_performance_available_preferences(
 
 cpufreq_freq_attr_ro(energy_performance_available_preferences);
 
+static struct cpufreq_driver intel_pstate;
+
 static ssize_t store_energy_performance_preference(
 		struct cpufreq_policy *policy, const char *buf, size_t count)
 {
-	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	char str_preference[21];
 	bool raw = false;
 	ssize_t ret;
@@ -725,15 +734,44 @@ static ssize_t store_energy_performance_preference(
 		raw = true;
 	}
 
+	/*
+	 * This function runs with the policy R/W semaphore held, which
+	 * guarantees that the driver pointer will not change while it is
+	 * running.
+	 */
+	if (!intel_pstate_driver)
+		return -EAGAIN;
+
 	mutex_lock(&intel_pstate_limits_lock);
 
-	ret = intel_pstate_set_energy_pref_index(cpu_data, ret, raw, epp);
-	if (!ret)
-		ret = count;
+	if (intel_pstate_driver == &intel_pstate) {
+		ret = intel_pstate_set_energy_pref_index(cpu, ret, raw, epp);
+	} else {
+		/*
+		 * In the passive mode the governor needs to be stopped on the
+		 * target CPU before the EPP update and restarted after it,
+		 * which is super-heavy-weight, so make sure it is worth doing
+		 * upfront.
+		 */
+		if (!raw)
+			epp = ret ? epp_values[ret - 1] : cpu->epp_default;
+
+		if (cpu->epp_cached != epp) {
+			int err;
+
+			cpufreq_stop_governor(policy);
+			ret = intel_pstate_set_epp(cpu, epp);
+			err = cpufreq_start_governor(policy);
+			if (!ret) {
+				cpu->epp_cached = epp;
+				ret = err;
+			}
+		}
+	}
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
-	return ret;
+	return ret ?: count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -1145,8 +1183,6 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 	return count;
 }
 
-static struct cpufreq_driver intel_pstate;
-
 static void update_qos_request(enum freq_qos_req_type type)
 {
 	int max_state, turbo_max, freq, i, perf_pct;
@@ -1330,9 +1366,10 @@ static const struct attribute_group intel_pstate_attr_group = {
 
 static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[];
 
+static struct kobject *intel_pstate_kobject;
+
 static void __init intel_pstate_sysfs_expose_params(void)
 {
-	struct kobject *intel_pstate_kobject;
 	int rc;
 
 	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
@@ -1357,17 +1394,31 @@ static void __init intel_pstate_sysfs_expose_params(void)
 	rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr);
 	WARN_ON(rc);
 
-	if (hwp_active) {
-		rc = sysfs_create_file(intel_pstate_kobject,
-				       &hwp_dynamic_boost.attr);
-		WARN_ON(rc);
-	}
-
 	if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids)) {
 		rc = sysfs_create_file(intel_pstate_kobject, &energy_efficiency.attr);
 		WARN_ON(rc);
 	}
 }
+
+static void intel_pstate_sysfs_expose_hwp_dynamic_boost(void)
+{
+	int rc;
+
+	if (!hwp_active)
+		return;
+
+	rc = sysfs_create_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
+	WARN_ON_ONCE(rc);
+}
+
+static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
+{
+	if (!hwp_active)
+		return;
+
+	sysfs_remove_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
+}
+
 /************************** sysfs end ************************/
 
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
@@ -2247,7 +2298,10 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 
 static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
-	intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]);
+	if (hwp_active)
+		intel_pstate_hwp_force_min_perf(policy->cpu);
+	else
+		intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]);
 }
 
 static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
@@ -2255,12 +2309,10 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	pr_debug("CPU %d exiting\n", policy->cpu);
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
-	if (hwp_active) {
+	if (hwp_active)
 		intel_pstate_hwp_save_state(policy);
-		intel_pstate_hwp_force_min_perf(policy->cpu);
-	} else {
-		intel_cpufreq_stop_cpu(policy);
-	}
+
+	intel_cpufreq_stop_cpu(policy);
 }
 
 static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
@@ -2390,13 +2442,71 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in
 		fp_toint(cpu->iowait_boost * 100));
 }
 
+static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
+				     bool fast_switch)
+{
+	u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
+
+	value &= ~HWP_MIN_PERF(~0L);
+	value |= HWP_MIN_PERF(target_pstate);
+
+	/*
+	 * The entire MSR needs to be updated in order to update the HWP min
+	 * field in it, so opportunistically update the max too if needed.
+	 */
+	value &= ~HWP_MAX_PERF(~0L);
+	value |= HWP_MAX_PERF(cpu->max_perf_ratio);
+
+	if (value == prev)
+		return;
+
+	WRITE_ONCE(cpu->hwp_req_cached, value);
+	if (fast_switch)
+		wrmsrl(MSR_HWP_REQUEST, value);
+	else
+		wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+}
+
+static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu,
+					  u32 target_pstate, bool fast_switch)
+{
+	if (fast_switch)
+		wrmsrl(MSR_IA32_PERF_CTL,
+		       pstate_funcs.get_val(cpu, target_pstate));
+	else
+		wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
+			      pstate_funcs.get_val(cpu, target_pstate));
+}
+
+static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
+				       bool fast_switch)
+{
+	int old_pstate = cpu->pstate.current_pstate;
+
+	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	if (target_pstate != old_pstate) {
+		cpu->pstate.current_pstate = target_pstate;
+		if (hwp_active)
+			intel_cpufreq_adjust_hwp(cpu, target_pstate,
+						 fast_switch);
+		else
+			intel_cpufreq_adjust_perf_ctl(cpu, target_pstate,
+						      fast_switch);
+	}
+
+	intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
+			    INTEL_PSTATE_TRACE_TARGET, old_pstate);
+
+	return target_pstate;
+}
+
 static int intel_cpufreq_target(struct cpufreq_policy *policy,
 				unsigned int target_freq,
 				unsigned int relation)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	struct cpufreq_freqs freqs;
-	int target_pstate, old_pstate;
+	int target_pstate;
 
 	update_turbo_state();
 
@@ -2404,6 +2514,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 	freqs.new = target_freq;
 
 	cpufreq_freq_transition_begin(policy, &freqs);
+
 	switch (relation) {
 	case CPUFREQ_RELATION_L:
 		target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling);
@@ -2415,15 +2526,11 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 		target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling);
 		break;
 	}
-	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
-	old_pstate = cpu->pstate.current_pstate;
-	if (target_pstate != cpu->pstate.current_pstate) {
-		cpu->pstate.current_pstate = target_pstate;
-		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
-			      pstate_funcs.get_val(cpu, target_pstate));
-	}
+
+	target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false);
+
 	freqs.new = target_pstate * cpu->pstate.scaling;
-	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_TARGET, old_pstate);
+
 	cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
@@ -2433,15 +2540,14 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	int target_pstate, old_pstate;
+	int target_pstate;
 
 	update_turbo_state();
 
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
-	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
-	old_pstate = cpu->pstate.current_pstate;
-	intel_pstate_update_pstate(cpu, target_pstate);
-	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
+
+	target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true);
+
 	return target_pstate * cpu->pstate.scaling;
 }
 
@@ -2461,7 +2567,6 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 
 	policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
-	policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
 	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
 	policy->cur = policy->cpuinfo.min_freq;
 
@@ -2473,10 +2578,18 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	if (hwp_active)
+	if (hwp_active) {
+		u64 value;
+
 		intel_pstate_get_hwp_max(policy->cpu, &turbo_max, &max_state);
-	else
+		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;
+		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
+		WRITE_ONCE(cpu->hwp_req_cached, value);
+		cpu->epp_cached = (value & GENMASK_ULL(31, 24)) >> 24;
+	} else {
 		turbo_max = cpu->pstate.turbo_pstate;
+		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
+	}
 
 	min_freq = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
 	min_freq *= cpu->pstate.scaling;
@@ -2553,6 +2666,10 @@ static void intel_pstate_driver_cleanup(void)
 		}
 	}
 	put_online_cpus();
+
+	if (intel_pstate_driver == &intel_pstate)
+		intel_pstate_sysfs_hide_hwp_dynamic_boost();
+
 	intel_pstate_driver = NULL;
 }
 
@@ -2560,6 +2677,9 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver)
 {
 	int ret;
 
+	if (driver == &intel_pstate)
+		intel_pstate_sysfs_expose_hwp_dynamic_boost();
+
 	memset(&global, 0, sizeof(global));
 	global.max_perf_pct = 100;
 
@@ -2577,9 +2697,6 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver)
 
 static int intel_pstate_unregister_driver(void)
 {
-	if (hwp_active)
-		return -EBUSY;
-
 	cpufreq_unregister_driver(intel_pstate_driver);
 	intel_pstate_driver_cleanup();
 
@@ -2835,7 +2952,10 @@ static int __init intel_pstate_init(void)
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
-			default_driver = &intel_pstate;
+			intel_cpufreq.attr = hwp_cpufreq_attrs;
+			if (!default_driver)
+				default_driver = &intel_pstate;
+
 			goto hwp_cpu_matched;
 		}
 	} else {
@@ -2906,14 +3026,13 @@ static int __init intel_pstate_setup(char *str)
 	if (!str)
 		return -EINVAL;
 
-	if (!strcmp(str, "disable")) {
+	if (!strcmp(str, "disable"))
 		no_load = 1;
-	} else if (!strcmp(str, "active")) {
+	else if (!strcmp(str, "active"))
 		default_driver = &intel_pstate;
-	} else if (!strcmp(str, "passive")) {
+	else if (!strcmp(str, "passive"))
 		default_driver = &intel_cpufreq;
-		no_hwp = 1;
-	}
+
 	if (!strcmp(str, "no_hwp")) {
 		pr_info("HWP disabled\n");
 		no_hwp = 1;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 58687a5bf9c8..8f141d4c859c 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -576,6 +576,8 @@ unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
 unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy);
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
+int cpufreq_start_governor(struct cpufreq_policy *policy);
+void cpufreq_stop_governor(struct cpufreq_policy *policy);
 
 #define cpufreq_governor_init(__governor)			\
 static int __init __governor##_init(void)			\
-- 
cgit v1.2.3


From 772616b031f06e05846488b01dab46a7c832da13 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:21 -0700
Subject: mm: memcg/percpu: per-memcg percpu memory statistics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Percpu memory can represent a noticeable chunk of the total memory
consumption, especially on big machines with many CPUs.  Let's track
percpu memory usage for each memcg and display it in memory.stat.

A percpu allocation is usually scattered over multiple pages (and nodes),
and can be significantly smaller than a page.  So let's add a byte-sized
counter on the memcg level: MEMCG_PERCPU_B.  Byte-sized vmstat infra
created for slabs can be perfectly reused for percpu case.

[guro@fb.com: v3]
  Link: http://lkml.kernel.org/r/20200623184515.4132564-4-guro@fb.com

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200608230819.832349-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst |  4 ++++
 include/linux/memcontrol.h              |  8 ++++++++
 mm/memcontrol.c                         |  4 +++-
 mm/percpu.c                             | 10 ++++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index fa4018afa5a4..6be43781ec7f 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1274,6 +1274,10 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used for storing in-kernel data
 		structures.
 
+	  percpu
+		Amount of memory used for storing per-cpu kernel
+		data structures.
+
 	  sock
 		Amount of memory used in network transmission buffers
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1bb49b600310..2c2d301eac33 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -32,6 +32,7 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
+	MEMCG_PERCPU_B,
 	MEMCG_NR_STAT,
 };
 
@@ -339,6 +340,13 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+static __always_inline bool memcg_stat_item_in_bytes(int idx)
+{
+	if (idx == MEMCG_PERCPU_B)
+		return true;
+	return vmstat_item_in_bytes(idx);
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8d9ceea7fe4d..36d5300f9b69 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -781,7 +781,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 	if (mem_cgroup_disabled())
 		return;
 
-	if (vmstat_item_in_bytes(idx))
+	if (memcg_stat_item_in_bytes(idx))
 		threshold <<= PAGE_SHIFT;
 
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
@@ -1488,6 +1488,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "slab %llu\n",
 		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
 			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
+	seq_buf_printf(&s, "percpu %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_PERCPU_B));
 	seq_buf_printf(&s, "sock %llu\n",
 		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
 		       PAGE_SIZE);
diff --git a/mm/percpu.c b/mm/percpu.c
index dc1a213293aa..f4709629e6de 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1610,6 +1610,11 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 
 	if (chunk) {
 		chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg;
+
+		rcu_read_lock();
+		mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+				size * num_possible_cpus());
+		rcu_read_unlock();
 	} else {
 		obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 		obj_cgroup_put(objcg);
@@ -1628,6 +1633,11 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 
 	obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 
+	rcu_read_lock();
+	mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+			-(size * num_possible_cpus()));
+	rcu_read_unlock();
+
 	obj_cgroup_put(objcg);
 }
 
-- 
cgit v1.2.3


From 8ca39e6874f812a393bb66d9fdbb7598d5f0451c Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Tue, 11 Aug 2020 18:30:32 -0700
Subject: mm/hugetlb: add mempolicy check in the reservation routine

In the reservation routine, we only check whether the cpuset meets the
memory allocation requirements.  But we ignore the mempolicy of MPOL_BIND
case.  If someone mmap hugetlb succeeds, but the subsequent memory
allocation may fail due to mempolicy restrictions and receives the SIGBUS
signal.  This can be reproduced by the follow steps.

 1) Compile the test case.
    cd tools/testing/selftests/vm/
    gcc map_hugetlb.c -o map_hugetlb

 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
    system. Each node will pre-allocate one huge page.
    echo 2 > /proc/sys/vm/nr_hugepages

 3) Run test case(mmap 4MB). We receive the SIGBUS signal.
    numactl --membind=3D0 ./map_hugetlb 4

With this patch applied, the mmap will fail in the step 3) and throw
"mmap: Cannot allocate memory".

[akpm@linux-foundation.org: include sched.h for `current']

Reported-by: Jianchao Guo <guojianchao@bytedance.com>
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michel Lespinasse <walken@google.com>
Cc: Baoquan He <bhe@redhat.com>
Link: http://lkml.kernel.org/r/20200728034938.14993-1-songmuchun@bytedance.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h | 16 +++++++++++++++-
 mm/hugetlb.c              | 22 ++++++++++++++++++----
 mm/mempolicy.c            |  2 +-
 3 files changed, 34 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index ea9c15b60a96..5f1648c23e29 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -6,7 +6,7 @@
 #ifndef _LINUX_MEMPOLICY_H
 #define _LINUX_MEMPOLICY_H 1
 
-
+#include <linux/sched.h>
 #include <linux/mmzone.h>
 #include <linux/dax.h>
 #include <linux/slab.h>
@@ -152,6 +152,15 @@ extern int huge_node(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
+extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
+
+static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+{
+	struct mempolicy *mpol = get_task_policy(current);
+
+	return policy_nodemask(gfp, mpol);
+}
+
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -281,5 +290,10 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
 static inline void mpol_put_task_policy(struct task_struct *task)
 {
 }
+
+static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+{
+	return NULL;
+}
 #endif /* CONFIG_NUMA */
 #endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e52c878940bb..dffafb5bf2ed 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3458,13 +3458,21 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;
 	unsigned int nr = 0;
+	nodemask_t *mpol_allowed;
+	unsigned int *array = h->free_huge_pages_node;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
+
+	mpol_allowed = policy_nodemask_current(gfp_mask);
 
-	for_each_node_mask(node, cpuset_current_mems_allowed)
-		nr += array[node];
+	for_each_node_mask(node, cpuset_current_mems_allowed) {
+		if (!mpol_allowed ||
+		    (mpol_allowed && node_isset(node, *mpol_allowed)))
+			nr += array[node];
+	}
 
 	return nr;
 }
@@ -3643,12 +3651,18 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
 	 * we fall back to check against current free page availability as
 	 * a best attempt and hopefully to minimize the impact of changing
 	 * semantics that cpuset has.
+	 *
+	 * Apart from cpuset, we also have memory policy mechanism that
+	 * also determines from which node the kernel will allocate memory
+	 * in a NUMA system. So similar to cpuset, we also should consider
+	 * the memory policy of the current task. Similar to the description
+	 * above.
 	 */
 	if (delta > 0) {
 		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+		if (delta > allowed_mems_nr(h)) {
 			return_unused_surplus_pages(h, delta);
 			goto out;
 		}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b9e85d467352..7af44d7cdd11 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1890,7 +1890,7 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
  * Return a nodemask representing a mempolicy for filtering nodes for
  * page allocation
  */
-static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
+nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
 	/* Lower zones don't get a nodemask applied for MPOL_BIND */
 	if (unlikely(policy->mode == MPOL_BIND) &&
-- 
cgit v1.2.3


From b518154e59aab3ad0780a169c5cc84bd4ee4357e Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:40 -0700
Subject: mm/vmscan: protect the workingset on anonymous LRU

In current implementation, newly created or swap-in anonymous page is
started on active list.  Growing active list results in rebalancing
active/inactive list so old pages on active list are demoted to inactive
list.  Hence, the page on active list isn't protected at all.

Following is an example of this situation.

Assume that 50 hot pages on active list.  Numbers denote the number of
pages on active/inactive list (active | inactive).

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(uo) | 50(h)

3. workload: another 50 newly created (used-once) pages
50(uo) | 50(uo), swap-out 50(h)

This patch tries to fix this issue.  Like as file LRU, newly created or
swap-in anonymous pages will be inserted to the inactive list.  They are
promoted to active list if enough reference happens.  This simple
modification changes the above example as following.

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(h) | 50(uo)

3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(uo)

As you can see, hot pages on active list would be protected.

Note that, this implementation has a drawback that the page cannot be
promoted and will be swapped-out if re-access interval is greater than the
size of inactive list but less than the size of total(active+inactive).
To solve this potential issue, following patch will apply workingset
detection similar to the one that's already applied to file LRU.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h    |  2 +-
 kernel/events/uprobes.c |  2 +-
 mm/huge_memory.c        |  2 +-
 mm/khugepaged.c         |  2 +-
 mm/memory.c             |  9 ++++-----
 mm/migrate.c            |  2 +-
 mm/swap.c               | 13 +++++++------
 mm/swapfile.c           |  2 +-
 mm/userfaultfd.c        |  2 +-
 mm/vmscan.c             |  4 +---
 10 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7eb59bc552a5..51ec9cdb92c0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -352,7 +352,7 @@ extern void deactivate_page(struct page *page);
 extern void mark_page_lazyfree(struct page *page);
 extern void swap_setup(void);
 
-extern void lru_cache_add_active_or_unevictable(struct page *page,
+extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 						struct vm_area_struct *vma);
 
 /* linux/mm/vmscan.c */
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 25de10c904e6..49047d479c57 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -184,7 +184,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	if (new_page) {
 		get_page(new_page);
 		page_add_new_anon_rmap(new_page, vma, addr, false);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
 		dec_mm_counter(mm, MM_ANONPAGES);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 206f52b36ffb..863c495776d7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -640,7 +640,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr, true);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b52bd46ad146..15a9af791014 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1173,7 +1173,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address, true);
-	lru_cache_add_active_or_unevictable(new_page, vma);
+	lru_cache_add_inactive_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
diff --git a/mm/memory.c b/mm/memory.c
index c39a13b09602..6fe8b5b22c57 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2715,7 +2715,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
 		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
 		 * mmu page tables (such as kvm shadow page tables), we want the
@@ -3266,10 +3266,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	/* ksm created a completely new copy */
 	if (unlikely(page != swapcache && swapcache)) {
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
-		activate_page(page);
 	}
 
 	swap_free(entry);
@@ -3414,7 +3413,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, vmf->address, false);
-	lru_cache_add_active_or_unevictable(page, vma);
+	lru_cache_add_inactive_or_unevictable(page, vma);
 setpte:
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
@@ -3672,7 +3671,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
diff --git a/mm/migrate.c b/mm/migrate.c
index d179657f8685..819e55130134 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2830,7 +2830,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	inc_mm_counter(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, addr, false);
 	if (!is_zone_device_page(page))
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	get_page(page);
 
 	if (flush) {
diff --git a/mm/swap.c b/mm/swap.c
index de257c0a89b1..9285e60c7d6e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -476,23 +476,24 @@ void lru_cache_add(struct page *page)
 EXPORT_SYMBOL(lru_cache_add);
 
 /**
- * lru_cache_add_active_or_unevictable
+ * lru_cache_add_inactive_or_unevictable
  * @page:  the page to be added to LRU
  * @vma:   vma in which page is mapped for determining reclaimability
  *
- * Place @page on the active or unevictable LRU list, depending on its
+ * Place @page on the inactive or unevictable LRU list, depending on its
  * evictability.  Note that if the page is not evictable, it goes
  * directly back onto it's zone's unevictable list, it does NOT use a
  * per cpu pagevec.
  */
-void lru_cache_add_active_or_unevictable(struct page *page,
+void lru_cache_add_inactive_or_unevictable(struct page *page,
 					 struct vm_area_struct *vma)
 {
+	bool unevictable;
+
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
-		SetPageActive(page);
-	else if (!TestSetPageMlocked(page)) {
+	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
+	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c26916e95fd..82183432fdd0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1915,7 +1915,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		page_add_anon_rmap(page, vma, addr, false);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, addr, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	swap_free(entry);
 	/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index b80419320c7d..9a3d451402d7 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -123,7 +123,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	inc_mm_counter(dst_mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
-	lru_cache_add_active_or_unevictable(page, dst_vma);
+	lru_cache_add_inactive_or_unevictable(page, dst_vma);
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e34fc04b7045..783cd7fdc61a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -998,8 +998,6 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageSwapBacked(page))
-			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
 		 * references from the instantiating fault, so we need
@@ -1022,7 +1020,7 @@ static enum page_references page_check_references(struct page *page,
 		/*
 		 * Activate file-backed executable pages after first usage.
 		 */
-		if (vm_flags & VM_EXEC)
+		if ((vm_flags & VM_EXEC) && !PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 
 		return PAGEREF_KEEP;
-- 
cgit v1.2.3


From 170b04b7ae49634df103810dad67b22cf8a99aa6 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:43 -0700
Subject: mm/workingset: prepare the workingset detection infrastructure for
 anon LRU

To prepare the workingset detection for anon LRU, this patch splits
workingset event counters for refault, activate and restore into anon and
file variants, as well as the refaults counter in struct lruvec.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-4-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 16 +++++++++++-----
 mm/memcontrol.c        | 16 +++++++++++-----
 mm/vmscan.c            | 15 ++++++++++-----
 mm/vmstat.c            |  9 ++++++---
 mm/workingset.c        |  8 +++++---
 5 files changed, 43 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 635a96cd9b1f..efbd95dd3bbf 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -173,9 +173,15 @@ enum node_stat_item {
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,
-	WORKINGSET_REFAULT,
-	WORKINGSET_ACTIVATE,
-	WORKINGSET_RESTORE,
+	WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_FILE,
+	WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_FILE,
+	WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_FILE,
 	WORKINGSET_NODERECLAIM,
 	NR_ANON_MAPPED,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
@@ -277,8 +283,8 @@ struct lruvec {
 	unsigned long			file_cost;
 	/* Non-resident age, driven by LRU movement */
 	atomic_long_t			nonresident_age;
-	/* Refaults at the time of last reclaim cycle */
-	unsigned long			refaults;
+	/* Refaults at the time of last reclaim cycle, anon=0, file=1 */
+	unsigned long			refaults[2];
 	/* Various lruvec state flags (enum lruvec_flags) */
 	unsigned long			flags;
 #ifdef CONFIG_MEMCG
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f1fd265b9f9e..c6c579217855 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1530,12 +1530,18 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT),
 		       memcg_events(memcg, PGMAJFAULT));
 
-	seq_buf_printf(&s, "workingset_refault %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_REFAULT));
-	seq_buf_printf(&s, "workingset_activate %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
+	seq_buf_printf(&s, "workingset_refault_anon %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_REFAULT_ANON));
+	seq_buf_printf(&s, "workingset_refault_file %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_REFAULT_FILE));
+	seq_buf_printf(&s, "workingset_activate_anon %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON));
+	seq_buf_printf(&s, "workingset_activate_file %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE));
 	seq_buf_printf(&s, "workingset_restore %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_RESTORE));
+		       memcg_page_state(memcg, WORKINGSET_RESTORE_ANON));
+	seq_buf_printf(&s, "workingset_restore %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_RESTORE_FILE));
 	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 783cd7fdc61a..017f323318a3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2683,7 +2683,10 @@ again:
 	if (!sc->force_deactivate) {
 		unsigned long refaults;
 
-		if (inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
+		refaults = lruvec_page_state(target_lruvec,
+				WORKINGSET_ACTIVATE_ANON);
+		if (refaults != target_lruvec->refaults[0] ||
+			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
 			sc->may_deactivate |= DEACTIVATE_ANON;
 		else
 			sc->may_deactivate &= ~DEACTIVATE_ANON;
@@ -2694,8 +2697,8 @@ again:
 		 * rid of any stale active pages quickly.
 		 */
 		refaults = lruvec_page_state(target_lruvec,
-					     WORKINGSET_ACTIVATE);
-		if (refaults != target_lruvec->refaults ||
+				WORKINGSET_ACTIVATE_FILE);
+		if (refaults != target_lruvec->refaults[1] ||
 		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
 			sc->may_deactivate |= DEACTIVATE_FILE;
 		else
@@ -2972,8 +2975,10 @@ static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
 	unsigned long refaults;
 
 	target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
-	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE);
-	target_lruvec->refaults = refaults;
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
+	target_lruvec->refaults[0] = refaults;
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
+	target_lruvec->refaults[1] = refaults;
 }
 
 /*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 2b866cbab11d..fef03463a0cf 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1167,9 +1167,12 @@ const char * const vmstat_text[] = {
 	"nr_isolated_anon",
 	"nr_isolated_file",
 	"workingset_nodes",
-	"workingset_refault",
-	"workingset_activate",
-	"workingset_restore",
+	"workingset_refault_anon",
+	"workingset_refault_file",
+	"workingset_activate_anon",
+	"workingset_activate_file",
+	"workingset_restore_anon",
+	"workingset_restore_file",
 	"workingset_nodereclaim",
 	"nr_anon_pages",
 	"nr_mapped",
diff --git a/mm/workingset.c b/mm/workingset.c
index b199726924dd..941bbaa6c262 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
 #include <linux/writeback.h>
 #include <linux/shmem_fs.h>
 #include <linux/pagemap.h>
@@ -280,6 +281,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
  */
 void workingset_refault(struct page *page, void *shadow)
 {
+	bool file = page_is_file_lru(page);
 	struct mem_cgroup *eviction_memcg;
 	struct lruvec *eviction_lruvec;
 	unsigned long refault_distance;
@@ -346,7 +348,7 @@ void workingset_refault(struct page *page, void *shadow)
 	memcg = page_memcg(page);
 	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
-	inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
+	inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
 
 	/*
 	 * Compare the distance to the existing workingset size. We
@@ -366,7 +368,7 @@ void workingset_refault(struct page *page, void *shadow)
 
 	SetPageActive(page);
 	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
-	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
+	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
 
 	/* Page was active prior to eviction */
 	if (workingset) {
@@ -375,7 +377,7 @@ void workingset_refault(struct page *page, void *shadow)
 		spin_lock_irq(&page_pgdat(page)->lru_lock);
 		lru_note_cost_page(page);
 		spin_unlock_irq(&page_pgdat(page)->lru_lock);
-		inc_lruvec_state(lruvec, WORKINGSET_RESTORE);
+		inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
 	}
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 3852f6768ede542ed48b9077bedf482c7ecb6327 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:47 -0700
Subject: mm/swapcache: support to handle the shadow entries

Workingset detection for anonymous page will be implemented in the
following patch and it requires to store the shadow entries into the
swapcache.  This patch implements an infrastructure to store the shadow
entry in the swapcache.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/1595490560-15117-5-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 17 ++++++++++++----
 mm/shmem.c           |  3 ++-
 mm/swap_state.c      | 57 ++++++++++++++++++++++++++++++++++++++++++++++------
 mm/swapfile.c        |  2 ++
 mm/vmscan.c          |  2 +-
 5 files changed, 69 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 51ec9cdb92c0..8a4c592698a9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -414,9 +414,13 @@ extern struct address_space *swapper_spaces[];
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
-extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
-extern void __delete_from_swap_cache(struct page *, swp_entry_t entry);
+extern int add_to_swap_cache(struct page *page, swp_entry_t entry,
+			gfp_t gfp, void **shadowp);
+extern void __delete_from_swap_cache(struct page *page,
+			swp_entry_t entry, void *shadow);
 extern void delete_from_swap_cache(struct page *);
+extern void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
@@ -570,13 +574,13 @@ static inline int add_to_swap(struct page *page)
 }
 
 static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
-							gfp_t gfp_mask)
+					gfp_t gfp_mask, void **shadowp)
 {
 	return -1;
 }
 
 static inline void __delete_from_swap_cache(struct page *page,
-							swp_entry_t entry)
+					swp_entry_t entry, void *shadow)
 {
 }
 
@@ -584,6 +588,11 @@ static inline void delete_from_swap_cache(struct page *page)
 {
 }
 
+static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+}
+
 static inline int page_swapcount(struct page *page)
 {
 	return 0;
diff --git a/mm/shmem.c b/mm/shmem.c
index eb6b36d89722..49bde088a7ea 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1434,7 +1434,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		list_add(&info->swaplist, &shmem_swaplist);
 
 	if (add_to_swap_cache(page, swap,
-			__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN) == 0) {
+			__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN,
+			NULL) == 0) {
 		spin_lock_irq(&info->lock);
 		shmem_recalc_inode(inode);
 		info->swapped++;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e82f4f8b1f63..a29b33c7c236 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -110,12 +110,14 @@ void show_swap_cache_info(void)
  * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
-int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
+int add_to_swap_cache(struct page *page, swp_entry_t entry,
+			gfp_t gfp, void **shadowp)
 {
 	struct address_space *address_space = swap_address_space(entry);
 	pgoff_t idx = swp_offset(entry);
 	XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page));
 	unsigned long i, nr = hpage_nr_pages(page);
+	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapCache(page), page);
@@ -125,16 +127,25 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
 	SetPageSwapCache(page);
 
 	do {
+		unsigned long nr_shadows = 0;
+
 		xas_lock_irq(&xas);
 		xas_create_range(&xas);
 		if (xas_error(&xas))
 			goto unlock;
 		for (i = 0; i < nr; i++) {
 			VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
+			old = xas_load(&xas);
+			if (xa_is_value(old)) {
+				nr_shadows++;
+				if (shadowp)
+					*shadowp = old;
+			}
 			set_page_private(page + i, entry.val + i);
 			xas_store(&xas, page);
 			xas_next(&xas);
 		}
+		address_space->nrexceptional -= nr_shadows;
 		address_space->nrpages += nr;
 		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
 		ADD_CACHE_INFO(add_total, nr);
@@ -154,7 +165,8 @@ unlock:
  * This must be called only on pages that have
  * been verified to be in the swap cache.
  */
-void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
+void __delete_from_swap_cache(struct page *page,
+			swp_entry_t entry, void *shadow)
 {
 	struct address_space *address_space = swap_address_space(entry);
 	int i, nr = hpage_nr_pages(page);
@@ -166,12 +178,14 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
 	VM_BUG_ON_PAGE(PageWriteback(page), page);
 
 	for (i = 0; i < nr; i++) {
-		void *entry = xas_store(&xas, NULL);
+		void *entry = xas_store(&xas, shadow);
 		VM_BUG_ON_PAGE(entry != page, entry);
 		set_page_private(page + i, 0);
 		xas_next(&xas);
 	}
 	ClearPageSwapCache(page);
+	if (shadow)
+		address_space->nrexceptional += nr;
 	address_space->nrpages -= nr;
 	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
 	ADD_CACHE_INFO(del_total, nr);
@@ -208,7 +222,7 @@ int add_to_swap(struct page *page)
 	 * Add it to the swap cache.
 	 */
 	err = add_to_swap_cache(page, entry,
-			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
+			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
 	if (err)
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
@@ -246,13 +260,44 @@ void delete_from_swap_cache(struct page *page)
 	struct address_space *address_space = swap_address_space(entry);
 
 	xa_lock_irq(&address_space->i_pages);
-	__delete_from_swap_cache(page, entry);
+	__delete_from_swap_cache(page, entry, NULL);
 	xa_unlock_irq(&address_space->i_pages);
 
 	put_swap_page(page, entry);
 	page_ref_sub(page, hpage_nr_pages(page));
 }
 
+void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+	unsigned long curr = begin;
+	void *old;
+
+	for (;;) {
+		unsigned long nr_shadows = 0;
+		swp_entry_t entry = swp_entry(type, curr);
+		struct address_space *address_space = swap_address_space(entry);
+		XA_STATE(xas, &address_space->i_pages, curr);
+
+		xa_lock_irq(&address_space->i_pages);
+		xas_for_each(&xas, old, end) {
+			if (!xa_is_value(old))
+				continue;
+			xas_store(&xas, NULL);
+			nr_shadows++;
+		}
+		address_space->nrexceptional -= nr_shadows;
+		xa_unlock_irq(&address_space->i_pages);
+
+		/* search the next swapcache until we meet end */
+		curr >>= SWAP_ADDRESS_SPACE_SHIFT;
+		curr++;
+		curr <<= SWAP_ADDRESS_SPACE_SHIFT;
+		if (curr > end)
+			break;
+	}
+}
+
 /* 
  * If we are the only user, then try to free up the swap cache. 
  * 
@@ -429,7 +474,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	__SetPageSwapBacked(page);
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK)) {
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, NULL)) {
 		put_swap_page(page, entry);
 		goto fail_unlock;
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 82183432fdd0..e653eea1eb88 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -696,6 +696,7 @@ static void add_to_avail_list(struct swap_info_struct *p)
 static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 			    unsigned int nr_entries)
 {
+	unsigned long begin = offset;
 	unsigned long end = offset + nr_entries - 1;
 	void (*swap_slot_free_notify)(struct block_device *, unsigned long);
 
@@ -721,6 +722,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 			swap_slot_free_notify(si->bdev, offset);
 		offset++;
 	}
+	clear_shadow_from_swap_cache(si->type, begin, end);
 }
 
 static void set_cluster_next(struct swap_info_struct *si, unsigned long next)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 017f323318a3..e84c4dd08c4e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -896,7 +896,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
-		__delete_from_swap_cache(page, swap);
+		__delete_from_swap_cache(page, swap, NULL);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
 		workingset_eviction(page, target_memcg);
-- 
cgit v1.2.3


From aae466b0052e1888edd1d7f473d4310d64936196 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:50 -0700
Subject: mm/swap: implement workingset detection for anonymous LRU

This patch implements workingset detection for anonymous LRU.  All the
infrastructure is implemented by the previous patches so this patch just
activates the workingset detection by installing/retrieving the shadow
entry and adding refault calculation.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-6-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  6 ++++++
 mm/memory.c          | 11 ++++-------
 mm/swap_state.c      | 23 ++++++++++++++++++-----
 mm/vmscan.c          |  7 ++++---
 mm/workingset.c      | 15 +++++++++++----
 5 files changed, 43 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8a4c592698a9..661046994db4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -414,6 +414,7 @@ extern struct address_space *swapper_spaces[];
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
+extern void *get_shadow_from_swap_cache(swp_entry_t entry);
 extern int add_to_swap_cache(struct page *page, swp_entry_t entry,
 			gfp_t gfp, void **shadowp);
 extern void __delete_from_swap_cache(struct page *page,
@@ -573,6 +574,11 @@ static inline int add_to_swap(struct page *page)
 	return 0;
 }
 
+static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
+{
+	return NULL;
+}
+
 static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
 					gfp_t gfp_mask, void **shadowp)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 6fe8b5b22c57..de311fc7639e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3098,6 +3098,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	int locked;
 	int exclusive = 0;
 	vm_fault_t ret = 0;
+	void *shadow = NULL;
 
 	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
 		goto out;
@@ -3149,13 +3150,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 					goto out_page;
 				}
 
-				/*
-				 * XXX: Move to lru_cache_add() when it
-				 * supports new vs putback
-				 */
-				spin_lock_irq(&page_pgdat(page)->lru_lock);
-				lru_note_cost_page(page);
-				spin_unlock_irq(&page_pgdat(page)->lru_lock);
+				shadow = get_shadow_from_swap_cache(entry);
+				if (shadow)
+					workingset_refault(page, shadow);
 
 				lru_cache_add(page);
 				swap_readpage(page, true);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index a29b33c7c236..b73aabdfd35a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -106,6 +106,20 @@ void show_swap_cache_info(void)
 	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
 }
 
+void *get_shadow_from_swap_cache(swp_entry_t entry)
+{
+	struct address_space *address_space = swap_address_space(entry);
+	pgoff_t idx = swp_offset(entry);
+	struct page *page;
+
+	page = find_get_entry(address_space, idx);
+	if (xa_is_value(page))
+		return page;
+	if (page)
+		put_page(page);
+	return NULL;
+}
+
 /*
  * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
@@ -406,6 +420,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 {
 	struct swap_info_struct *si;
 	struct page *page;
+	void *shadow = NULL;
 
 	*new_page_allocated = false;
 
@@ -474,7 +489,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	__SetPageSwapBacked(page);
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, NULL)) {
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) {
 		put_swap_page(page, entry);
 		goto fail_unlock;
 	}
@@ -484,10 +499,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		goto fail_unlock;
 	}
 
-	/* XXX: Move to lru_cache_add() when it supports new vs putback */
-	spin_lock_irq(&page_pgdat(page)->lru_lock);
-	lru_note_cost_page(page);
-	spin_unlock_irq(&page_pgdat(page)->lru_lock);
+	if (shadow)
+		workingset_refault(page, shadow);
 
 	/* Caller will initiate read into locked page */
 	SetPageWorkingset(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e84c4dd08c4e..66d73fea80e4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -854,6 +854,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 {
 	unsigned long flags;
 	int refcount;
+	void *shadow = NULL;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
@@ -896,13 +897,13 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
-		__delete_from_swap_cache(page, swap, NULL);
+		if (reclaimed && !mapping_exiting(mapping))
+			shadow = workingset_eviction(page, target_memcg);
+		__delete_from_swap_cache(page, swap, shadow);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
-		workingset_eviction(page, target_memcg);
 	} else {
 		void (*freepage)(struct page *);
-		void *shadow = NULL;
 
 		freepage = mapping->a_ops->freepage;
 		/*
diff --git a/mm/workingset.c b/mm/workingset.c
index 941bbaa6c262..8cbe4e3cbe5c 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -353,15 +353,22 @@ void workingset_refault(struct page *page, void *shadow)
 	/*
 	 * Compare the distance to the existing workingset size. We
 	 * don't activate pages that couldn't stay resident even if
-	 * all the memory was available to the page cache. Whether
-	 * cache can compete with anon or not depends on having swap.
+	 * all the memory was available to the workingset. Whether
+	 * workingset competition needs to consider anon or not depends
+	 * on having swap.
 	 */
 	workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
-	if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
+	if (!file) {
 		workingset_size += lruvec_page_state(eviction_lruvec,
-						     NR_INACTIVE_ANON);
+						     NR_INACTIVE_FILE);
+	}
+	if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
 		workingset_size += lruvec_page_state(eviction_lruvec,
 						     NR_ACTIVE_ANON);
+		if (file) {
+			workingset_size += lruvec_page_state(eviction_lruvec,
+						     NR_INACTIVE_ANON);
+		}
 	}
 	if (refault_distance > workingset_size)
 		goto out;
-- 
cgit v1.2.3


From facdaa917c4d5a376d09d25865f5a863f906234a Mon Sep 17 00:00:00 2001
From: Nitin Gupta <nigupta@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:00 -0700
Subject: mm: proactive compaction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some applications, we need to allocate almost all memory as hugepages.
However, on a running system, higher-order allocations can fail if the
memory is fragmented.  Linux kernel currently does on-demand compaction as
we request more hugepages, but this style of compaction incurs very high
latency.  Experiments with one-time full memory compaction (followed by
hugepage allocations) show that kernel is able to restore a highly
fragmented memory state to a fairly compacted memory state within <1 sec
for a 32G system.  Such data suggests that a more proactive compaction can
help us allocate a large fraction of memory as hugepages keeping
allocation latencies low.

For a more proactive compaction, the approach taken here is to define a
new sysctl called 'vm.compaction_proactiveness' which dictates bounds for
external fragmentation which kcompactd tries to maintain.

The tunable takes a value in range [0, 100], with a default of 20.

Note that a previous version of this patch [1] was found to introduce too
many tunables (per-order extfrag{low, high}), but this one reduces them to
just one sysctl.  Also, the new tunable is an opaque value instead of
asking for specific bounds of "external fragmentation", which would have
been difficult to estimate.  The internal interpretation of this opaque
value allows for future fine-tuning.

Currently, we use a simple translation from this tunable to [low, high]
"fragmentation score" thresholds (low=100-proactiveness, high=low+10%).
The score for a node is defined as weighted mean of per-zone external
fragmentation.  A zone's present_pages determines its weight.

To periodically check per-node score, we reuse per-node kcompactd threads,
which are woken up every 500 milliseconds to check the same.  If a node's
score exceeds its high threshold (as derived from user-provided
proactiveness value), proactive compaction is started until its score
reaches its low threshold value.  By default, proactiveness is set to 20,
which implies threshold values of low=80 and high=90.

This patch is largely based on ideas from Michal Hocko [2].  See also the
LWN article [3].

Performance data
================

System: x64_64, 1T RAM, 80 CPU threads.
Kernel: 5.6.0-rc3 + this patch

echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/defrag

Before starting the driver, the system was fragmented from a userspace
program that allocates all memory and then for each 2M aligned section,
frees 3/4 of base pages using munmap.  The workload is mainly anonymous
userspace pages, which are easy to move around.  I intentionally avoided
unmovable pages in this test to see how much latency we incur when
hugepage allocations hit direct compaction.

1. Kernel hugepage allocation latencies

With the system in such a fragmented state, a kernel driver then allocates
as many hugepages as possible and measures allocation latency:

(all latency values are in microseconds)

- With vanilla 5.6.0-rc3

  percentile latency
  –––––––––– –––––––
	   5    7894
	  10    9496
	  25   12561
	  30   15295
	  40   18244
	  50   21229
	  60   27556
	  75   30147
	  80   31047
	  90   32859
	  95   33799

Total 2M hugepages allocated = 383859 (749G worth of hugepages out of 762G
total free => 98% of free memory could be allocated as hugepages)

- With 5.6.0-rc3 + this patch, with proactiveness=20

sysctl -w vm.compaction_proactiveness=20

  percentile latency
  –––––––––– –––––––
	   5       2
	  10       2
	  25       3
	  30       3
	  40       3
	  50       4
	  60       4
	  75       4
	  80       4
	  90       5
	  95     429

Total 2M hugepages allocated = 384105 (750G worth of hugepages out of 762G
total free => 98% of free memory could be allocated as hugepages)

2. JAVA heap allocation

In this test, we first fragment memory using the same method as for (1).

Then, we start a Java process with a heap size set to 700G and request the
heap to be allocated with THP hugepages.  We also set THP to madvise to
allow hugepage backing of this heap.

/usr/bin/time
 java -Xms700G -Xmx700G -XX:+UseTransparentHugePages -XX:+AlwaysPreTouch

The above command allocates 700G of Java heap using hugepages.

- With vanilla 5.6.0-rc3

17.39user 1666.48system 27:37.89elapsed

- With 5.6.0-rc3 + this patch, with proactiveness=20

8.35user 194.58system 3:19.62elapsed

Elapsed time remains around 3:15, as proactiveness is further increased.

Note that proactive compaction happens throughout the runtime of these
workloads.  The situation of one-time compaction, sufficient to supply
hugepages for following allocation stream, can probably happen for more
extreme proactiveness values, like 80 or 90.

In the above Java workload, proactiveness is set to 20.  The test starts
with a node's score of 80 or higher, depending on the delay between the
fragmentation step and starting the benchmark, which gives more-or-less
time for the initial round of compaction.  As t he benchmark consumes
hugepages, node's score quickly rises above the high threshold (90) and
proactive compaction starts again, which brings down the score to the low
threshold level (80).  Repeat.

bpftrace also confirms proactive compaction running 20+ times during the
runtime of this Java benchmark.  kcompactd threads consume 100% of one of
the CPUs while it tries to bring a node's score within thresholds.

Backoff behavior
================

Above workloads produce a memory state which is easy to compact.  However,
if memory is filled with unmovable pages, proactive compaction should
essentially back off.  To test this aspect:

- Created a kernel driver that allocates almost all memory as hugepages
  followed by freeing first 3/4 of each hugepage.
- Set proactiveness=40
- Note that proactive_compact_node() is deferred maximum number of times
  with HPAGE_FRAG_CHECK_INTERVAL_MSEC of wait between each check
  (=> ~30 seconds between retries).

[1] https://patchwork.kernel.org/patch/11098289/
[2] https://lore.kernel.org/linux-mm/20161230131412.GI13301@dhcp22.suse.cz/
[3] https://lwn.net/Articles/817905/

Signed-off-by: Nitin Gupta <nigupta@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Oleksandr Natalenko <oleksandr@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Reviewed-by: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nitin Gupta <ngupta@nitingupta.dev>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Link: http://lkml.kernel.org/r/20200616204527.19185-1-nigupta@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/vm.rst |  15 +++
 include/linux/compaction.h              |   2 +
 kernel/sysctl.c                         |   9 ++
 mm/compaction.c                         | 183 +++++++++++++++++++++++++++++++-
 mm/internal.h                           |   1 +
 mm/vmstat.c                             |  18 ++++
 6 files changed, 223 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index d997cc3c26d0..4b9d2e8e9142 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -119,6 +119,21 @@ all zones are compacted such that free memory is available in contiguous
 blocks where possible. This can be important for example in the allocation of
 huge pages although processes will also directly compact memory as required.
 
+compaction_proactiveness
+========================
+
+This tunable takes a value in the range [0, 100] with a default value of
+20. This tunable determines how aggressively compaction is done in the
+background. Setting it to 0 disables proactive compaction.
+
+Note that compaction has a non-trivial system-wide impact as pages
+belonging to different processes are moved around, which could also lead
+to latency spikes in unsuspecting applications. The kernel employs
+various heuristics to avoid wasting CPU cycles if it detects that
+proactive compaction is not being effective.
+
+Be careful when setting it to extreme values like 100, as that may
+cause excessive background compaction activity.
 
 compact_unevictable_allowed
 ===========================
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 6fa0eea3f530..7a242d46454e 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -85,11 +85,13 @@ static inline unsigned long compact_gap(unsigned int order)
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
+extern int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
+extern int extfrag_for_order(struct zone *zone, unsigned int order);
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		unsigned int order, unsigned int alloc_flags,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f785de3caac0..ab72e52f8a7b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2851,6 +2851,15 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0200,
 		.proc_handler	= sysctl_compaction_handler,
 	},
+	{
+		.procname	= "compaction_proactiveness",
+		.data		= &sysctl_compaction_proactiveness,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &one_hundred,
+	},
 	{
 		.procname	= "extfrag_threshold",
 		.data		= &sysctl_extfrag_threshold,
diff --git a/mm/compaction.c b/mm/compaction.c
index 86375605faa9..544a98811c82 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -50,6 +50,24 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #define pageblock_start_pfn(pfn)	block_start_pfn(pfn, pageblock_order)
 #define pageblock_end_pfn(pfn)		block_end_pfn(pfn, pageblock_order)
 
+/*
+ * Fragmentation score check interval for proactive compaction purposes.
+ */
+static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+
+/*
+ * Page order with-respect-to which proactive compaction
+ * calculates external fragmentation, which is used as
+ * the "fragmentation score" of a node/zone.
+ */
+#if defined CONFIG_TRANSPARENT_HUGEPAGE
+#define COMPACTION_HPAGE_ORDER	HPAGE_PMD_ORDER
+#elif defined HUGETLB_PAGE_ORDER
+#define COMPACTION_HPAGE_ORDER	HUGETLB_PAGE_ORDER
+#else
+#define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
+#endif
+
 static unsigned long release_freepages(struct list_head *freelist)
 {
 	struct page *page, *next;
@@ -1857,6 +1875,76 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
+static bool kswapd_is_running(pg_data_t *pgdat)
+{
+	return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING);
+}
+
+/*
+ * A zone's fragmentation score is the external fragmentation wrt to the
+ * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
+ * in the range [0, 100].
+ *
+ * The scaling factor ensures that proactive compaction focuses on larger
+ * zones like ZONE_NORMAL, rather than smaller, specialized zones like
+ * ZONE_DMA32. For smaller zones, the score value remains close to zero,
+ * and thus never exceeds the high threshold for proactive compaction.
+ */
+static int fragmentation_score_zone(struct zone *zone)
+{
+	unsigned long score;
+
+	score = zone->present_pages *
+			extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
+}
+
+/*
+ * The per-node proactive (background) compaction process is started by its
+ * corresponding kcompactd thread when the node's fragmentation score
+ * exceeds the high threshold. The compaction process remains active till
+ * the node's score falls below the low threshold, or one of the back-off
+ * conditions is met.
+ */
+static int fragmentation_score_node(pg_data_t *pgdat)
+{
+	unsigned long score = 0;
+	int zoneid;
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		struct zone *zone;
+
+		zone = &pgdat->node_zones[zoneid];
+		score += fragmentation_score_zone(zone);
+	}
+
+	return score;
+}
+
+static int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+{
+	int wmark_low;
+
+	/*
+	 * Cap the low watermak to avoid excessive compaction
+	 * activity in case a user sets the proactivess tunable
+	 * close to 100 (maximum).
+	 */
+	wmark_low = max(100 - sysctl_compaction_proactiveness, 5);
+	return low ? wmark_low : min(wmark_low + 10, 100);
+}
+
+static bool should_proactive_compact_node(pg_data_t *pgdat)
+{
+	int wmark_high;
+
+	if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
+		return false;
+
+	wmark_high = fragmentation_score_wmark(pgdat, false);
+	return fragmentation_score_node(pgdat) > wmark_high;
+}
+
 static enum compact_result __compact_finished(struct compact_control *cc)
 {
 	unsigned int order;
@@ -1883,6 +1971,25 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 			return COMPACT_PARTIAL_SKIPPED;
 	}
 
+	if (cc->proactive_compaction) {
+		int score, wmark_low;
+		pg_data_t *pgdat;
+
+		pgdat = cc->zone->zone_pgdat;
+		if (kswapd_is_running(pgdat))
+			return COMPACT_PARTIAL_SKIPPED;
+
+		score = fragmentation_score_zone(cc->zone);
+		wmark_low = fragmentation_score_wmark(pgdat, true);
+
+		if (score > wmark_low)
+			ret = COMPACT_CONTINUE;
+		else
+			ret = COMPACT_SUCCESS;
+
+		goto out;
+	}
+
 	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
@@ -1941,6 +2048,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 		}
 	}
 
+out:
 	if (cc->contended || fatal_signal_pending(current))
 		ret = COMPACT_CONTENDED;
 
@@ -2421,6 +2529,41 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 	return rc;
 }
 
+/*
+ * Compact all zones within a node till each zone's fragmentation score
+ * reaches within proactive compaction thresholds (as determined by the
+ * proactiveness tunable).
+ *
+ * It is possible that the function returns before reaching score targets
+ * due to various back-off conditions, such as, contention on per-node or
+ * per-zone locks.
+ */
+static void proactive_compact_node(pg_data_t *pgdat)
+{
+	int zoneid;
+	struct zone *zone;
+	struct compact_control cc = {
+		.order = -1,
+		.mode = MIGRATE_SYNC_LIGHT,
+		.ignore_skip_hint = true,
+		.whole_zone = true,
+		.gfp_mask = GFP_KERNEL,
+		.proactive_compaction = true,
+	};
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		zone = &pgdat->node_zones[zoneid];
+		if (!populated_zone(zone))
+			continue;
+
+		cc.zone = zone;
+
+		compact_zone(&cc, NULL);
+
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
+	}
+}
 
 /* Compact all zones within a node */
 static void compact_node(int nid)
@@ -2467,6 +2610,13 @@ static void compact_nodes(void)
 /* The written value is actually unused, all memory is compacted */
 int sysctl_compact_memory;
 
+/*
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
+ */
+int __read_mostly sysctl_compaction_proactiveness = 20;
+
 /*
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
@@ -2646,6 +2796,7 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
+	unsigned int proactive_defer = 0;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2661,12 +2812,34 @@ static int kcompactd(void *p)
 		unsigned long pflags;
 
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
-		wait_event_freezable(pgdat->kcompactd_wait,
-				kcompactd_work_requested(pgdat));
+		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
+			kcompactd_work_requested(pgdat),
+			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+
+			psi_memstall_enter(&pflags);
+			kcompactd_do_work(pgdat);
+			psi_memstall_leave(&pflags);
+			continue;
+		}
 
-		psi_memstall_enter(&pflags);
-		kcompactd_do_work(pgdat);
-		psi_memstall_leave(&pflags);
+		/* kcompactd wait timeout */
+		if (should_proactive_compact_node(pgdat)) {
+			unsigned int prev_score, score;
+
+			if (proactive_defer) {
+				proactive_defer--;
+				continue;
+			}
+			prev_score = fragmentation_score_node(pgdat);
+			proactive_compact_node(pgdat);
+			score = fragmentation_score_node(pgdat);
+			/*
+			 * Defer proactive compaction if the fragmentation
+			 * score did not go down i.e. no progress made.
+			 */
+			proactive_defer = score < prev_score ?
+					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+		}
 	}
 
 	return 0;
diff --git a/mm/internal.h b/mm/internal.h
index 9886db20d94f..42cf0b610847 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -239,6 +239,7 @@ struct compact_control {
 	bool no_set_skip_hint;		/* Don't mark blocks for skipping */
 	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
 	bool direct_compaction;		/* False from kcompactd or /proc/... */
+	bool proactive_compaction;	/* kcompactd proactive compaction */
 	bool whole_zone;		/* Whole zone should/has been scanned */
 	bool contended;			/* Signal lock or sched contention */
 	bool rescan;			/* Rescanning the same pageblock */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index fef03463a0cf..f183aa37994e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1096,6 +1096,24 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
 	return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
 }
 
+/*
+ * Calculates external fragmentation within a zone wrt the given order.
+ * It is defined as the percentage of pages found in blocks of size
+ * less than 1 << order. It returns values in range [0, 100].
+ */
+int extfrag_for_order(struct zone *zone, unsigned int order)
+{
+	struct contig_page_info info;
+
+	fill_contig_page_info(zone, order, &info);
+	if (info.free_pages == 0)
+		return 0;
+
+	return div_u64((info.free_pages -
+			(info.free_blocks_suitable << order)) * 100,
+			info.free_pages);
+}
+
 /* Same as __fragmentation index but allocs contig_page_info on stack */
 int fragmentation_index(struct zone *zone, unsigned int order)
 {
-- 
cgit v1.2.3


From d34c0a7599ea8c301bc471dfa1eb2bf2db6752d1 Mon Sep 17 00:00:00 2001
From: Nitin Gupta <nigupta@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:07 -0700
Subject: mm: use unsigned types for fragmentation score

Proactive compaction uses per-node/zone "fragmentation score" which is
always in range [0, 100], so use unsigned type of these scores as well as
for related constants.

Signed-off-by: Nitin Gupta <nigupta@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/20200618010319.13159-1-nigupta@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  4 ++--
 kernel/sysctl.c            |  2 +-
 mm/compaction.c            | 18 +++++++++---------
 mm/vmstat.c                |  2 +-
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 7a242d46454e..25a521d299c1 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -85,13 +85,13 @@ static inline unsigned long compact_gap(unsigned int order)
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
-extern int sysctl_compaction_proactiveness;
+extern unsigned int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
-extern int extfrag_for_order(struct zone *zone, unsigned int order);
+extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		unsigned int order, unsigned int alloc_flags,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ab72e52f8a7b..287862f91717 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2854,7 +2854,7 @@ static struct ctl_table vm_table[] = {
 	{
 		.procname	= "compaction_proactiveness",
 		.data		= &sysctl_compaction_proactiveness,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(sysctl_compaction_proactiveness),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
diff --git a/mm/compaction.c b/mm/compaction.c
index ed8ea1511634..b7d433f1706a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -53,7 +53,7 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 /*
  * Fragmentation score check interval for proactive compaction purposes.
  */
-static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
 
 /*
  * Page order with-respect-to which proactive compaction
@@ -1890,7 +1890,7 @@ static bool kswapd_is_running(pg_data_t *pgdat)
  * ZONE_DMA32. For smaller zones, the score value remains close to zero,
  * and thus never exceeds the high threshold for proactive compaction.
  */
-static int fragmentation_score_zone(struct zone *zone)
+static unsigned int fragmentation_score_zone(struct zone *zone)
 {
 	unsigned long score;
 
@@ -1906,9 +1906,9 @@ static int fragmentation_score_zone(struct zone *zone)
  * the node's score falls below the low threshold, or one of the back-off
  * conditions is met.
  */
-static int fragmentation_score_node(pg_data_t *pgdat)
+static unsigned int fragmentation_score_node(pg_data_t *pgdat)
 {
-	unsigned long score = 0;
+	unsigned int score = 0;
 	int zoneid;
 
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
@@ -1921,17 +1921,17 @@ static int fragmentation_score_node(pg_data_t *pgdat)
 	return score;
 }
 
-static int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
 {
-	int wmark_low;
+	unsigned int wmark_low;
 
 	/*
 	 * Cap the low watermak to avoid excessive compaction
 	 * activity in case a user sets the proactivess tunable
 	 * close to 100 (maximum).
 	 */
-	wmark_low = max(100 - sysctl_compaction_proactiveness, 5);
-	return low ? wmark_low : min(wmark_low + 10, 100);
+	wmark_low = max(100U - sysctl_compaction_proactiveness, 5U);
+	return low ? wmark_low : min(wmark_low + 10, 100U);
 }
 
 static bool should_proactive_compact_node(pg_data_t *pgdat)
@@ -2615,7 +2615,7 @@ int sysctl_compact_memory;
  * aggressively the kernel should compact memory in the
  * background. It takes values in the range [0, 100].
  */
-int __read_mostly sysctl_compaction_proactiveness = 20;
+unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
 
 /*
  * This is the entry point for compacting all nodes via
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f183aa37994e..3bb034c99887 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1101,7 +1101,7 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
  * It is defined as the percentage of pages found in blocks of size
  * less than 1 << order. It returns values in range [0, 100].
  */
-int extfrag_for_order(struct zone *zone, unsigned int order)
+unsigned int extfrag_for_order(struct zone *zone, unsigned int order)
 {
 	struct contig_page_info info;
 
-- 
cgit v1.2.3


From 860b32729a21e0565585a9e2ecea2e5244d65acd Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 11 Aug 2020 18:31:10 -0700
Subject: mm/compaction: correct the comments of compact_defer_shift

There is no compact_defer_limit. It should be compact_defer_shift in
use. and add compact_order_failed explanation.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Link: http://lkml.kernel.org/r/3bd60e1b-a74e-050d-ade4-6e8f54e00b92@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 1 +
 mm/compaction.c        | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index efbd95dd3bbf..8379432f4f2f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -536,6 +536,7 @@ struct zone {
 	 * On compaction failure, 1<<compact_defer_shift compactions
 	 * are skipped before trying again. The number attempted since
 	 * last failure is tracked with compact_considered.
+	 * compact_order_failed is the minimum compaction failed order.
 	 */
 	unsigned int		compact_considered;
 	unsigned int		compact_defer_shift;
diff --git a/mm/compaction.c b/mm/compaction.c
index b7d433f1706a..5e8f2e22b73e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -154,7 +154,7 @@ EXPORT_SYMBOL(__ClearPageMovable);
 
 /*
  * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * allocation success. 1 << compact_defer_shift, compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
 void defer_compaction(struct zone *zone, int order)
-- 
cgit v1.2.3


From f3f3416c2234c0a9372316bec5c48cbd58b565c5 Mon Sep 17 00:00:00 2001
From: Yanfei Xu <yanfei.xu@windriver.com>
Date: Tue, 11 Aug 2020 18:31:19 -0700
Subject: include/linux/mempolicy.h: fix typo

Change "interlave" to "interleave".

Signed-off-by: Yanfei Xu <yanfei.xu@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200810063454.9357-1-yanfei.xu@windriver.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1648c23e29..5f1c74df264d 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -28,7 +28,7 @@ struct mm_struct;
  * the process policy is used. Interrupts ignore the memory policy
  * of the current process.
  *
- * Locking policy for interlave:
+ * Locking policy for interleave:
  * In process context there is no locking because only the process accesses
  * its own state. All vma manipulation is somewhat protected by a down_read on
  * mmap_lock.
-- 
cgit v1.2.3


From 9066e5cfb73cdbcdbb49e87999482ab615e9fc76 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 11 Aug 2020 18:31:22 -0700
Subject: mm, oom: make the calculation of oom badness more accurate

Recently we found an issue on our production environment that when memcg
oom is triggered the oom killer doesn't chose the process with largest
resident memory but chose the first scanned process.  Note that all
processes in this memcg have the same oom_score_adj, so the oom killer
should chose the process with largest resident memory.

Bellow is part of the oom info, which is enough to analyze this issue.
[7516987.983223] memory: usage 16777216kB, limit 16777216kB, failcnt 52843037
[7516987.983224] memory+swap: usage 16777216kB, limit 9007199254740988kB, failcnt 0
[7516987.983225] kmem: usage 301464kB, limit 9007199254740988kB, failcnt 0
[...]
[7516987.983293] [ pid ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name
[7516987.983510] [ 5740]     0  5740      257        1    32768        0          -998 pause
[7516987.983574] [58804]     0 58804     4594      771    81920        0          -998 entry_point.bas
[7516987.983577] [58908]     0 58908     7089      689    98304        0          -998 cron
[7516987.983580] [58910]     0 58910    16235     5576   163840        0          -998 supervisord
[7516987.983590] [59620]     0 59620    18074     1395   188416        0          -998 sshd
[7516987.983594] [59622]     0 59622    18680     6679   188416        0          -998 python
[7516987.983598] [59624]     0 59624  1859266     5161   548864        0          -998 odin-agent
[7516987.983600] [59625]     0 59625   707223     9248   983040        0          -998 filebeat
[7516987.983604] [59627]     0 59627   416433    64239   774144        0          -998 odin-log-agent
[7516987.983607] [59631]     0 59631   180671    15012   385024        0          -998 python3
[7516987.983612] [61396]     0 61396   791287     3189   352256        0          -998 client
[7516987.983615] [61641]     0 61641  1844642    29089   946176        0          -998 client
[7516987.983765] [ 9236]     0  9236     2642      467    53248        0          -998 php_scanner
[7516987.983911] [42898]     0 42898    15543      838   167936        0          -998 su
[7516987.983915] [42900]  1000 42900     3673      867    77824        0          -998 exec_script_vr2
[7516987.983918] [42925]  1000 42925    36475    19033   335872        0          -998 python
[7516987.983921] [57146]  1000 57146     3673      848    73728        0          -998 exec_script_J2p
[7516987.983925] [57195]  1000 57195   186359    22958   491520        0          -998 python2
[7516987.983928] [58376]  1000 58376   275764    14402   290816        0          -998 rosmaster
[7516987.983931] [58395]  1000 58395   155166     4449   245760        0          -998 rosout
[7516987.983935] [58406]  1000 58406 18285584  3967322 37101568        0          -998 data_sim
[7516987.984221] oom-kill:constraint=CONSTRAINT_MEMCG,nodemask=(null),cpuset=3aa16c9482ae3a6f6b78bda68a55d32c87c99b985e0f11331cddf05af6c4d753,mems_allowed=0-1,oom_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184,task_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184/1f246a3eeea8f70bf91141eeaf1805346a666e225f823906485ea0b6c37dfc3d,task=pause,pid=5740,uid=0
[7516987.984254] Memory cgroup out of memory: Killed process 5740 (pause) total-vm:1028kB, anon-rss:4kB, file-rss:0kB, shmem-rss:0kB
[7516988.092344] oom_reaper: reaped process 5740 (pause), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB

We can find that the first scanned process 5740 (pause) was killed, but
its rss is only one page.  That is because, when we calculate the oom
badness in oom_badness(), we always ignore the negtive point and convert
all of these negtive points to 1.  Now as oom_score_adj of all the
processes in this targeted memcg have the same value -998, the points of
these processes are all negtive value.  As a result, the first scanned
process will be killed.

The oom_socre_adj (-998) in this memcg is set by kubelet, because it is a
a Guaranteed pod, which has higher priority to prevent from being killed
by system oom.

To fix this issue, we should make the calculation of oom point more
accurate.  We can achieve it by convert the chosen_point from 'unsigned
long' to 'long'.

[cai@lca.pw: reported a issue in the previous version]
[mhocko@suse.com: fixed the issue reported by Cai]
[mhocko@suse.com: add the comment in proc_oom_score()]
[laoar.shao@gmail.com: v3]
  Link: http://lkml.kernel.org/r/1594396651-9931-1-git-send-email-laoar.shao@gmail.com

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/1594309987-9919-1-git-send-email-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c      | 11 ++++++++++-
 include/linux/oom.h |  4 ++--
 mm/oom_kill.c       | 22 ++++++++++------------
 3 files changed, 22 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index a333caeca291..617db4e0faa0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -551,8 +551,17 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 {
 	unsigned long totalpages = totalram_pages() + total_swap_pages;
 	unsigned long points = 0;
+	long badness;
+
+	badness = oom_badness(task, totalpages);
+	/*
+	 * Special case OOM_SCORE_ADJ_MIN for all others scale the
+	 * badness value into [0, 2000] range which we have been
+	 * exporting for a long time so userspace might depend on it.
+	 */
+	if (badness != LONG_MIN)
+		points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3;
 
-	points = oom_badness(task, totalpages) * 1000 / totalpages;
 	seq_printf(m, "%lu\n", points);
 
 	return 0;
diff --git a/include/linux/oom.h b/include/linux/oom.h
index c696c265f019..f022f581ac29 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -48,7 +48,7 @@ struct oom_control {
 	/* Used by oom implementation, do not set */
 	unsigned long totalpages;
 	struct task_struct *chosen;
-	unsigned long chosen_points;
+	long chosen_points;
 
 	/* Used to print the constraint info. */
 	enum oom_constraint constraint;
@@ -107,7 +107,7 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm)
 
 bool __oom_reap_task_mm(struct mm_struct *mm);
 
-extern unsigned long oom_badness(struct task_struct *p,
+long oom_badness(struct task_struct *p,
 		unsigned long totalpages);
 
 extern bool out_of_memory(struct oom_control *oc);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d30ce75f23fb..48e0db54d838 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -196,17 +196,17 @@ static bool is_dump_unreclaim_slabs(void)
  * predictable as possible.  The goal is to return the highest value for the
  * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
+long oom_badness(struct task_struct *p, unsigned long totalpages)
 {
 	long points;
 	long adj;
 
 	if (oom_unkillable_task(p))
-		return 0;
+		return LONG_MIN;
 
 	p = find_lock_task_mm(p);
 	if (!p)
-		return 0;
+		return LONG_MIN;
 
 	/*
 	 * Do not even consider tasks which are explicitly marked oom
@@ -218,7 +218,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 			test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
 			in_vfork(p)) {
 		task_unlock(p);
-		return 0;
+		return LONG_MIN;
 	}
 
 	/*
@@ -233,11 +233,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 	adj *= totalpages / 1000;
 	points += adj;
 
-	/*
-	 * Never return 0 for an eligible task regardless of the root bonus and
-	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
-	 */
-	return points > 0 ? points : 1;
+	return points;
 }
 
 static const char * const oom_constraint_text[] = {
@@ -310,7 +306,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 static int oom_evaluate_task(struct task_struct *task, void *arg)
 {
 	struct oom_control *oc = arg;
-	unsigned long points;
+	long points;
 
 	if (oom_unkillable_task(task))
 		goto next;
@@ -336,12 +332,12 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 	 * killed first if it triggers an oom, then select it.
 	 */
 	if (oom_task_origin(task)) {
-		points = ULONG_MAX;
+		points = LONG_MAX;
 		goto select;
 	}
 
 	points = oom_badness(task, oc->totalpages);
-	if (!points || points < oc->chosen_points)
+	if (points == LONG_MIN || points < oc->chosen_points)
 		goto next;
 
 select:
@@ -365,6 +361,8 @@ abort:
  */
 static void select_bad_process(struct oom_control *oc)
 {
+	oc->chosen_points = LONG_MIN;
+
 	if (is_memcg_oom(oc))
 		mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
 	else {
-- 
cgit v1.2.3


From 34ae204f18519f0920bd50a644abd6fefc8dbfcf Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 11 Aug 2020 18:31:38 -0700
Subject: hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem

Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem
in at least read mode.  This is because the explicit locking in
huge_pmd_share (called by huge_pte_alloc) was removed.  When restructuring
the code, the call to huge_pte_alloc in the else block at the beginning of
hugetlb_fault was missed.

Unfortunately, that else clause is exercised when there is no page table
entry.  This will likely lead to a call to huge_pmd_share.  If
huge_pmd_share thinks pmd sharing is possible, it will traverse the
mapping tree (i_mmap) without holding i_mmap_rwsem.  If someone else is
modifying the tree, bad things such as addressing exceptions or worse
could happen.

Simply remove the else clause.  It should have been removed previously.
The code following the else will call huge_pte_alloc with the appropriate
locking.

To prevent this type of issue in the future, add routines to assert that
i_mmap_rwsem is held, and call these routines in huge pmd sharing
routines.

Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization")
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A.Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Prakash Sangappa <prakash.sangappa@oracle.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/e670f327-5cf9-1959-96e4-6dc7cc30d3d5@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h      | 10 ++++++++++
 include/linux/hugetlb.h |  8 +++++---
 mm/hugetlb.c            | 15 +++++++--------
 mm/rmap.c               |  2 +-
 4 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 011af396aa17..7c69dd7c6160 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -518,6 +518,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
 	up_read(&mapping->i_mmap_rwsem);
 }
 
+static inline void i_mmap_assert_locked(struct address_space *mapping)
+{
+	lockdep_assert_held(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_assert_write_locked(struct address_space *mapping)
+{
+	lockdep_assert_held_write(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 50650d0d01b9..a520bf26e5d8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -164,7 +164,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long *addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -203,8 +204,9 @@ static inline struct address_space *hugetlb_page_mapping_lock_write(
 	return NULL;
 }
 
-static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
-					pte_t *ptep)
+static inline int huge_pmd_unshare(struct mm_struct *mm,
+					struct vm_area_struct *vma,
+					unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dffafb5bf2ed..8a18f1234e80 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3967,7 +3967,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			continue;
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			spin_unlock(ptl);
 			/*
 			 * We just unmapped a page of PMDs by clearing a PUD.
@@ -4554,10 +4554,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
-	} else {
-		ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
-		if (!ptep)
-			return VM_FAULT_OOM;
 	}
 
 	/*
@@ -5034,7 +5030,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
@@ -5415,12 +5411,14 @@ out:
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
  */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+					unsigned long *addr, pte_t *ptep)
 {
 	pgd_t *pgd = pgd_offset(mm, *addr);
 	p4d_t *p4d = p4d_offset(pgd, *addr);
 	pud_t *pud = pud_offset(p4d, *addr);
 
+	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
 		return 0;
@@ -5438,7 +5436,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	return NULL;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 5fe2dedce1fc..6cce9ef06753 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1469,7 +1469,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * do this outside rmap routines.
 			 */
 			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
-			if (huge_pmd_unshare(mm, &address, pvmw.pte)) {
+			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
 				/*
 				 * huge_pmd_unshare unmapped an entire PMD
 				 * page.  There is no way of knowing exactly
-- 
cgit v1.2.3


From 4958e4d86ecb011a81f5d80ce2023ef9f10692d8 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang.shi@linux.alibaba.com>
Date: Tue, 11 Aug 2020 18:31:48 -0700
Subject: mm: thp: remove debug_cow switch

Since commit 3917c80280c93a7123f ("thp: change CoW semantics for
anon-THP"), the CoW page fault of THP has been rewritten, debug_cow is not
used anymore.  So, just remove it.

Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/1592270980-116062-1-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  7 -------
 mm/huge_memory.c        | 21 ---------------------
 2 files changed, 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 17c4c4975145..467302056e17 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -181,13 +181,6 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
-#ifdef CONFIG_DEBUG_VM
-#define transparent_hugepage_debug_cow()				\
-	(transparent_hugepage_flags &					\
-	 (1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
-#else /* CONFIG_DEBUG_VM */
-#define transparent_hugepage_debug_cow() 0
-#endif /* CONFIG_DEBUG_VM */
 
 extern unsigned long thp_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len, unsigned long pgoff,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 863c495776d7..2ccff8472cd4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -303,24 +303,6 @@ static ssize_t hpage_pmd_size_show(struct kobject *kobj,
 static struct kobj_attribute hpage_pmd_size_attr =
 	__ATTR_RO(hpage_pmd_size);
 
-#ifdef CONFIG_DEBUG_VM
-static ssize_t debug_cow_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf)
-{
-	return single_hugepage_flag_show(kobj, attr, buf,
-				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static ssize_t debug_cow_store(struct kobject *kobj,
-			       struct kobj_attribute *attr,
-			       const char *buf, size_t count)
-{
-	return single_hugepage_flag_store(kobj, attr, buf, count,
-				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static struct kobj_attribute debug_cow_attr =
-	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
-#endif /* CONFIG_DEBUG_VM */
-
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
@@ -328,9 +310,6 @@ static struct attribute *hugepage_attr[] = {
 	&hpage_pmd_size_attr.attr,
 #ifdef CONFIG_SHMEM
 	&shmem_enabled_attr.attr,
-#endif
-#ifdef CONFIG_DEBUG_VM
-	&debug_cow_attr.attr,
 #endif
 	NULL,
 };
-- 
cgit v1.2.3


From 1a5bae25e3cf95c4e83a97f87a6b5280d9acbb22 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Tue, 11 Aug 2020 18:31:51 -0700
Subject: mm/vmstat: add events for THP migration without split

Add following new vmstat events which will help in validating THP
migration without split.  Statistics reported through these new VM events
will help in performance debugging.

1. THP_MIGRATION_SUCCESS
2. THP_MIGRATION_FAILURE
3. THP_MIGRATION_SPLIT

In addition, these new events also update normal page migration statistics
appropriately via PGMIGRATE_SUCCESS and PGMIGRATE_FAILURE.  While here,
this updates current trace event 'mm_migrate_pages' to accommodate now
available THP statistics.

[akpm@linux-foundation.org: s/hpage_nr_pages/thp_nr_pages/]
[ziy@nvidia.com: v2]
  Link: http://lkml.kernel.org/r/C5E3C65C-8253-4638-9D3C-71A61858BB8B@nvidia.com
[anshuman.khandual@arm.com: s/thp_nr_pages/hpage_nr_pages/]
  Link: http://lkml.kernel.org/r/1594287583-16568-1-git-send-email-anshuman.khandual@arm.com

Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Link: http://lkml.kernel.org/r/1594080415-27924-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/page_migration.rst | 27 +++++++++++++++++++
 include/linux/vm_event_item.h       |  3 +++
 include/trace/events/migrate.h      | 17 +++++++++---
 mm/migrate.c                        | 52 +++++++++++++++++++++++++++++++------
 mm/vmstat.c                         |  3 +++
 5 files changed, 91 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/page_migration.rst b/Documentation/vm/page_migration.rst
index 1d6cd7db4e43..68883ac485fa 100644
--- a/Documentation/vm/page_migration.rst
+++ b/Documentation/vm/page_migration.rst
@@ -253,5 +253,32 @@ which are function pointers of struct address_space_operations.
      PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
      for own purpose.
 
+Monitoring Migration
+=====================
+
+The following events (counters) can be used to monitor page migration.
+
+1. PGMIGRATE_SUCCESS: Normal page migration success. Each count means that a
+   page was migrated. If the page was a non-THP page, then this counter is
+   increased by one. If the page was a THP, then this counter is increased by
+   the number of THP subpages. For example, migration of a single 2MB THP that
+   has 4KB-size base pages (subpages) will cause this counter to increase by
+   512.
+
+2. PGMIGRATE_FAIL: Normal page migration failure. Same counting rules as for
+   _SUCCESS, above: this will be increased by the number of subpages, if it was
+   a THP.
+
+3. THP_MIGRATION_SUCCESS: A THP was migrated without being split.
+
+4. THP_MIGRATION_FAIL: A THP could not be migrated nor it could be split.
+
+5. THP_MIGRATION_SPLIT: A THP was migrated, but not as such: first, the THP had
+   to be split. After splitting, a migration retry was used for it's sub-pages.
+
+THP_MIGRATION_* events also update the appropriate PGMIGRATE_SUCCESS or
+PGMIGRATE_FAIL events. For example, a THP migration failure will cause both
+THP_MIGRATION_FAIL and PGMIGRATE_FAIL to increase.
+
 Christoph Lameter, May 8, 2006.
 Minchan Kim, Mar 28, 2016.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 24fc7c3ae7d6..2e6ca53b9bbd 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -56,6 +56,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
+		THP_MIGRATION_SUCCESS,
+		THP_MIGRATION_FAIL,
+		THP_MIGRATION_SPLIT,
 #endif
 #ifdef CONFIG_COMPACTION
 		COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 705b33d1e395..4d434398d64d 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -46,13 +46,18 @@ MIGRATE_REASON
 TRACE_EVENT(mm_migrate_pages,
 
 	TP_PROTO(unsigned long succeeded, unsigned long failed,
-		 enum migrate_mode mode, int reason),
+		 unsigned long thp_succeeded, unsigned long thp_failed,
+		 unsigned long thp_split, enum migrate_mode mode, int reason),
 
-	TP_ARGS(succeeded, failed, mode, reason),
+	TP_ARGS(succeeded, failed, thp_succeeded, thp_failed,
+		thp_split, mode, reason),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,		succeeded)
 		__field(	unsigned long,		failed)
+		__field(	unsigned long,		thp_succeeded)
+		__field(	unsigned long,		thp_failed)
+		__field(	unsigned long,		thp_split)
 		__field(	enum migrate_mode,	mode)
 		__field(	int,			reason)
 	),
@@ -60,13 +65,19 @@ TRACE_EVENT(mm_migrate_pages,
 	TP_fast_assign(
 		__entry->succeeded	= succeeded;
 		__entry->failed		= failed;
+		__entry->thp_succeeded	= thp_succeeded;
+		__entry->thp_failed	= thp_failed;
+		__entry->thp_split	= thp_split;
 		__entry->mode		= mode;
 		__entry->reason		= reason;
 	),
 
-	TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s",
+	TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu mode=%s reason=%s",
 		__entry->succeeded,
 		__entry->failed,
+		__entry->thp_succeeded,
+		__entry->thp_failed,
+		__entry->thp_split,
 		__print_symbolic(__entry->mode, MIGRATE_MODE),
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );
diff --git a/mm/migrate.c b/mm/migrate.c
index b52f30113366..5ea275878383 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1418,22 +1418,35 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
+	int thp_retry = 1;
 	int nr_failed = 0;
 	int nr_succeeded = 0;
+	int nr_thp_succeeded = 0;
+	int nr_thp_failed = 0;
+	int nr_thp_split = 0;
 	int pass = 0;
+	bool is_thp = false;
 	struct page *page;
 	struct page *page2;
 	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
+	int rc, nr_subpages;
 
 	if (!swapwrite)
 		current->flags |= PF_SWAPWRITE;
 
-	for(pass = 0; pass < 10 && retry; pass++) {
+	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
+		thp_retry = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
 retry:
+			/*
+			 * THP statistics is based on the source huge page.
+			 * Capture required information that might get lost
+			 * during migration.
+			 */
+			is_thp = PageTransHuge(page);
+			nr_subpages = hpage_nr_pages(page);
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1464,15 +1477,30 @@ retry:
 					unlock_page(page);
 					if (!rc) {
 						list_safe_reset_next(page, page2, lru);
+						nr_thp_split++;
 						goto retry;
 					}
 				}
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					goto out;
+				}
 				nr_failed++;
 				goto out;
 			case -EAGAIN:
+				if (is_thp) {
+					thp_retry++;
+					break;
+				}
 				retry++;
 				break;
 			case MIGRATEPAGE_SUCCESS:
+				if (is_thp) {
+					nr_thp_succeeded++;
+					nr_succeeded += nr_subpages;
+					break;
+				}
 				nr_succeeded++;
 				break;
 			default:
@@ -1482,19 +1510,27 @@ retry:
 				 * removed from migration page list and not
 				 * retried in the next outer loop.
 				 */
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					break;
+				}
 				nr_failed++;
 				break;
 			}
 		}
 	}
-	nr_failed += retry;
+	nr_failed += retry + thp_retry;
+	nr_thp_failed += thp_retry;
 	rc = nr_failed;
 out:
-	if (nr_succeeded)
-		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
-	if (nr_failed)
-		count_vm_events(PGMIGRATE_FAIL, nr_failed);
-	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+	count_vm_events(PGMIGRATE_FAIL, nr_failed);
+	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
+	count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
+	count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
+	trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded,
+			       nr_thp_failed, nr_thp_split, mode, reason);
 
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 3bb034c99887..727a26d1ec1d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1277,6 +1277,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
 	"pgmigrate_fail",
+	"thp_migration_success",
+	"thp_migration_fail",
+	"thp_migration_split",
 #endif
 #ifdef CONFIG_COMPACTION
 	"compact_migrate_scanned",
-- 
cgit v1.2.3


From af161bee93332a1ff10ba029f41936d21850ae82 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 11 Aug 2020 18:32:06 -0700
Subject: include/linux/sched/mm.h: optimize current_gfp_context()

The current_gfp_context() converts a number of PF_MEMALLOC_* per-process
flags into the corresponding GFP_* flags for memory allocation.  In that
function, current->flags is accessed 3 times.  That may lead to duplicated
access of the same memory location.

This is not usually a problem with minimal debug config options on as the
compiler can optimize away the duplicated memory accesses.  With most of
the debug config options on, however, that may not be the case.  For
example, the x86-64 object size of the __need_fs_reclaim() in a debug
kernel that calls current_gfp_context() was 309 bytes.  With this patch
applied, the object size is reduced to 202 bytes.  This is a saving of 107
bytes and will probably be slightly faster too.

Use READ_ONCE() to access current->flags to prevent the compiler from
possibly accessing current->flags multiple times.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michel Lespinasse <walken@google.com>
Link: http://lkml.kernel.org/r/20200618212936.9776-1-longman@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 85023ddc2dc2..f889e332912f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -178,14 +178,16 @@ static inline bool in_vfork(struct task_struct *tsk)
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
-	if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
+	unsigned int pflags = READ_ONCE(current->flags);
+
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
 		/*
 		 * NOIO implies both NOIO and NOFS and it is a weaker context
 		 * so always make sure it makes precedence
 		 */
-		if (current->flags & PF_MEMALLOC_NOIO)
+		if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
-		else if (current->flags & PF_MEMALLOC_NOFS)
+		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
 	}
 	return flags;
-- 
cgit v1.2.3


From 1067b261cc973d68c29de54ef0587c56786e6bd5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:27 -0700
Subject: mm: drop duplicated words in <linux/pgtable.h>

Drop the doubled words "used" and "by".

Drop the repeated acronym "TLB" and make several other fixes around it.
(capital letters, spellos)

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Link: http://lkml.kernel.org/r/2bb6e13e-44df-4920-52d9-4d3539945f73@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pgtable.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 53e97da1e8e2..a124c21e3204 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -804,7 +804,7 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 
 /*
  * No-op macros that just return the current protection value. Defined here
- * because these macros can be used used even if CONFIG_MMU is not defined.
+ * because these macros can be used even if CONFIG_MMU is not defined.
  */
 
 #ifndef pgprot_nx
@@ -1234,7 +1234,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
  * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
  * the only case the kernel cares is for NUMA balancing and is only ever set
  * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
- * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * _PAGE_PROTNONE so by default, implement the helper as "always no". It
  * is the responsibility of the caller to distinguish between PROT_NONE
  * protections and NUMA hinting fault protections.
  */
@@ -1318,10 +1318,10 @@ static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 /*
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
- * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshold, which will
- * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * THP regime. Stock flush_tlb_range() typically has optimization to nuke the
+ * entire TLB if flush span is greater than a threshold, which will
+ * likely be true for a single huge page. Thus a single THP flush will
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
-- 
cgit v1.2.3


From 11192337206d2211bce3ba4ec1575439b6045654 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:30 -0700
Subject: mm: drop duplicated words in <linux/mm.h>

Drop the doubled words "to" and "the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Link: http://lkml.kernel.org/r/d9fae8d6-0d60-4d52-9385-3199ee98de49@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6a82f9bccd7..f97b10117d44 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -479,7 +479,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
 	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }
 
 /*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled by the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
@@ -2599,7 +2599,7 @@ extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
-/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */
+/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */
 extern int expand_downwards(struct vm_area_struct *vma,
 		unsigned long address);
 #if VM_GROWSUP
-- 
cgit v1.2.3


From 3ecabd31341fb4307f156a2bf4467c3f8fa9101b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:33 -0700
Subject: include/linux/highmem.h: fix duplicated words in a comment

Change the doubled word "is" in a comment to "it is".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/ad605959-0083-4794-8d31-6b073300dd6f@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/highmem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d6e82e3de027..14e6202ce47f 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -73,7 +73,7 @@ static inline void kunmap(struct page *page)
  * no global lock is needed and because the kmap code must perform a global TLB
  * invalidation when the kmap pool wraps.
  *
- * However when holding an atomic kmap is is not legal to sleep, so atomic
+ * However when holding an atomic kmap it is not legal to sleep, so atomic
  * kmaps are appropriate for short, tight code paths only.
  *
  * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
-- 
cgit v1.2.3


From c82f16b52cb3b50ac1b47e6c590e3dddefc5a97c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:36 -0700
Subject: include/linux/frontswap.h: drop duplicated word in a comment

Drop the doubled word "in" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/3af7ed91-ad62-8445-40a4-9e07a64b9523@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/frontswap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 6d775984905b..b07d88c92bb2 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -10,7 +10,7 @@
 /*
  * Return code to denote that requested number of
  * frontswap pages are unused(moved to page cache).
- * Used in in shmem_unuse and try_to_unuse.
+ * Used in shmem_unuse and try_to_unuse.
  */
 #define FRONTSWAP_PAGES_UNUSED	2
 
-- 
cgit v1.2.3


From 0845f83122d93ae3bafa7ea10209de2148a3b9bc Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:40 -0700
Subject: include/linux/memcontrol.h: drop duplicate word and fix spello

Drop the doubled word "for" in a comment.
Fix spello of "incremented".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Chris Down <chris@chrisdown.name>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Link: http://lkml.kernel.org/r/b04aa2e4-7c95-12f0-599d-43d07fb28134@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2c2d301eac33..385237e4cb44 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -65,8 +65,8 @@ struct mem_cgroup_id {
 
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremated by the number of pages. This counter is used for
- * for trigger some periodic events. This is straightforward and better
+ * it will be incremented by the number of pages. This counter is used
+ * to trigger some periodic events. This is straightforward and better
  * than using jiffies etc. to handle periodic memcg event.
  */
 enum mem_cgroup_events_target {
-- 
cgit v1.2.3


From bfe00c5bbd9ee37b99c281429556c335271d027b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:34 -0700
Subject: syscalls: use uaccess_kernel in addr_limit_user_check

Patch series "clean up address limit helpers", v2.

In preparation for eventually phasing out direct use of set_fs(), this
series removes the segment_eq() arch helper that is only used to implement
or duplicate the uaccess_kernel() API, and then adds descriptive helpers
to force the kernel address limit.

This patch (of 6):

Use the uaccess_kernel helper instead of duplicating it.

[hch@lst.de: arm: don't call addr_limit_user_check for nommu]
  Link: http://lkml.kernel.org/r/20200721045834.GA9613@lst.de

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200714105505.935079-1-hch@lst.de
Link: http://lkml.kernel.org/r/20200710135706.537715-1-hch@lst.de
Link: http://lkml.kernel.org/r/20200710135706.537715-2-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/signal.c | 2 ++
 include/linux/syscalls.h | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab2568996ddb..c9dc912b83f0 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -713,7 +713,9 @@ struct page *get_signal_page(void)
 /* Defer to generic check */
 asmlinkage void addr_limit_check_failed(void)
 {
+#ifdef CONFIG_MMU
 	addr_limit_user_check();
+#endif
 }
 
 #ifdef CONFIG_DEBUG_RSEQ
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a2429d336593..dc2b827c81e5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -263,7 +263,7 @@ static inline void addr_limit_user_check(void)
 		return;
 #endif
 
-	if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+	if (CHECK_DATA_CORRUPTION(uaccess_kernel(),
 				  "Invalid address limit on user-mode return"))
 		force_sig(SIGKILL);
 
-- 
cgit v1.2.3


From 428e2976a5bf7e7f5554286d7a5a33b8147b106a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:44 -0700
Subject: uaccess: remove segment_eq

segment_eq is only used to implement uaccess_kernel.  Just open code
uaccess_kernel in the arch uaccess headers and remove one layer of
indirection.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Link: http://lkml.kernel.org/r/20200710135706.537715-5-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/uaccess.h      | 2 +-
 arch/arc/include/asm/segment.h        | 3 +--
 arch/arm/include/asm/uaccess.h        | 4 ++--
 arch/arm64/include/asm/uaccess.h      | 2 +-
 arch/csky/include/asm/segment.h       | 2 +-
 arch/h8300/include/asm/segment.h      | 2 +-
 arch/ia64/include/asm/uaccess.h       | 2 +-
 arch/m68k/include/asm/segment.h       | 2 +-
 arch/microblaze/include/asm/uaccess.h | 2 +-
 arch/mips/include/asm/uaccess.h       | 2 +-
 arch/nds32/include/asm/uaccess.h      | 2 +-
 arch/nios2/include/asm/uaccess.h      | 2 +-
 arch/openrisc/include/asm/uaccess.h   | 2 +-
 arch/parisc/include/asm/uaccess.h     | 2 +-
 arch/powerpc/include/asm/uaccess.h    | 3 +--
 arch/riscv/include/asm/uaccess.h      | 4 +---
 arch/s390/include/asm/uaccess.h       | 2 +-
 arch/sh/include/asm/segment.h         | 3 +--
 arch/sparc/include/asm/uaccess_32.h   | 2 +-
 arch/sparc/include/asm/uaccess_64.h   | 2 +-
 arch/x86/include/asm/uaccess.h        | 2 +-
 arch/xtensa/include/asm/uaccess.h     | 2 +-
 include/asm-generic/uaccess.h         | 4 ++--
 include/linux/uaccess.h               | 2 --
 24 files changed, 25 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 1fe2b56cb861..1b6f25efa247 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -20,7 +20,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * Is a address valid? This does a straightforward calculation rather
diff --git a/arch/arc/include/asm/segment.h b/arch/arc/include/asm/segment.h
index 6a2a5be5026d..871f8ab11bfd 100644
--- a/arch/arc/include/asm/segment.h
+++ b/arch/arc/include/asm/segment.h
@@ -14,8 +14,7 @@ typedef unsigned long mm_segment_t;
 
 #define KERNEL_DS		MAKE_MM_SEG(0)
 #define USER_DS			MAKE_MM_SEG(TASK_SIZE)
-
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASMARC_SEGMENT_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index b5fdd30252f8..a13d90206472 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -76,7 +76,7 @@ static inline void set_fs(mm_segment_t fs)
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * We use 33-bit arithmetic here.  Success returns zero, failure returns
@@ -267,7 +267,7 @@ extern int __put_user_8(void *, unsigned long long);
  */
 #define USER_DS			KERNEL_DS
 
-#define segment_eq(a, b)		(1)
+#define uaccess_kernel()	(true)
 #define __addr_ok(addr)		((void)(addr), 1)
 #define __range_ok(addr, size)	((void)(addr), 0)
 #define get_fs()		(KERNEL_DS)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8d7c466f809b..991dd5f031e4 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -50,7 +50,7 @@ static inline void set_fs(mm_segment_t fs)
 				CONFIG_ARM64_UAO));
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * Test whether a block of memory is a valid user space address.
diff --git a/arch/csky/include/asm/segment.h b/arch/csky/include/asm/segment.h
index db2640d5f575..79ede9b1a646 100644
--- a/arch/csky/include/asm/segment.h
+++ b/arch/csky/include/asm/segment.h
@@ -13,6 +13,6 @@ typedef struct {
 #define USER_DS			((mm_segment_t) { 0x80000000UL })
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(x)		(current_thread_info()->addr_limit = (x))
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASM_CSKY_SEGMENT_H */
diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h
index a407978f9f9f..37950725d9b9 100644
--- a/arch/h8300/include/asm/segment.h
+++ b/arch/h8300/include/asm/segment.h
@@ -33,7 +33,7 @@ static inline mm_segment_t get_fs(void)
 	return USER_DS;
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 8aa473a4b0f4..179243c3dfc7 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -50,7 +50,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * When accessing user memory, we need to make sure the entire area really is in
diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h
index c6686559e9b7..2b5e68a71ef7 100644
--- a/arch/m68k/include/asm/segment.h
+++ b/arch/m68k/include/asm/segment.h
@@ -52,7 +52,7 @@ static inline void set_fs(mm_segment_t val)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 6723c56ec378..304b04ffea2f 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -41,7 +41,7 @@
 # define get_fs()	(current_thread_info()->addr_limit)
 # define set_fs(val)	(current_thread_info()->addr_limit = (val))
 
-# define segment_eq(a, b)	((a).seg == (b).seg)
+# define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #ifndef CONFIG_MMU
 
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 62b298c50905..61fc01f177a6 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -72,7 +72,7 @@ extern u64 __ua_limit;
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * eva_kernel_access() - determine whether kernel memory access on an EVA system
diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h
index 3a9219f53ee0..010ba5f1d7dd 100644
--- a/arch/nds32/include/asm/uaccess.h
+++ b/arch/nds32/include/asm/uaccess.h
@@ -44,7 +44,7 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size))
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index e83f831a76f9..a741abbed6fb 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -30,7 +30,7 @@
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(seg)		(current_thread_info()->addr_limit = (seg))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __access_ok(addr, len)			\
 	(((signed long)(((long)get_fs().seg) &	\
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 17c24f14615f..48b691530d3e 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /* Ensure that the range from addr to addr+size is all within the process'
  * address space
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index ebbb9ffe038c..ed2cd4fb479b 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -14,7 +14,7 @@
 #define KERNEL_DS	((mm_segment_t){0})
 #define USER_DS 	((mm_segment_t){1})
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 64c04ab09112..00699903f1ef 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -38,8 +38,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
 #ifdef __powerpc64__
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 22de922d6ecb..f56c66b3f5fe 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -64,11 +64,9 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
-
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 324438889fe1..f09444d6aeab 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define USER_DS_SACF	(3)
 
 #define get_fs()        (current->thread.mm_segment)
-#define segment_eq(a,b) (((a) & 2) == ((b) & 2))
+#define uaccess_kernel() ((get_fs() & 2) == KERNEL_DS)
 
 void set_fs(mm_segment_t fs);
 
diff --git a/arch/sh/include/asm/segment.h b/arch/sh/include/asm/segment.h
index 33d1d28057cb..02e54a3335d6 100644
--- a/arch/sh/include/asm/segment.h
+++ b/arch/sh/include/asm/segment.h
@@ -24,8 +24,7 @@ typedef struct {
 #define USER_DS		KERNEL_DS
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index d6d8413eca83..0a2d3ebc4bb8 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -28,7 +28,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	((current->thread.current_ds) = (val))
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 /* We have there a nice not-mapped page at PAGE_OFFSET - PAGE_SIZE, so that this test
  * can be fairly lightweight.
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index bf9d330073b2..698cf69f74e9 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -32,7 +32,7 @@
 
 #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)})
 
-#define segment_eq(a, b)  ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define set_fs(val)								\
 do {										\
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2f3e8f2a958f..ecefaffd15d4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,7 +33,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max() (current->thread.addr_limit.seg)
 
 /*
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index e57f0d0a88d8..b9758119feca 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -35,7 +35,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	(current->thread.current_ds = (val))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __kernel_ok (uaccess_kernel())
 #define __user_ok(addr, size) \
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index e935318804f8..ba68ee4dabfa 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -86,8 +86,8 @@ static inline void set_fs(mm_segment_t fs)
 }
 #endif
 
-#ifndef segment_eq
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#ifndef uaccess_kernel
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #endif
 
 #define access_ok(addr, size) __access_ok((unsigned long)(addr),(size))
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 0a76ddc07d59..5c62d0c6f15b 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -6,8 +6,6 @@
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
-#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
-
 #include <asm/uaccess.h>
 
 /*
-- 
cgit v1.2.3


From 3d13f313ce4c34c524ccc37986fe77172f601ff3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:47 -0700
Subject: uaccess: add force_uaccess_{begin,end} helpers

Add helpers to wrap the get_fs/set_fs magic for undoing any damange done
by set_fs(KERNEL_DS).  There is no real functional benefit, but this
documents the intent of these calls better, and will allow stubbing the
functions out easily for kernels builds that do not allow address space
overrides in the future.

[hch@lst.de: drop two incorrect hunks, fix a commit log typo]
  Link: http://lkml.kernel.org/r/20200714105505.935079-6-hch@lst.de

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Link: http://lkml.kernel.org/r/20200710135706.537715-6-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/kernel/sdei.c         |  2 +-
 arch/m68k/include/asm/tlbflush.h |  6 +++---
 arch/mips/kernel/unaligned.c     | 27 +++++++++++++--------------
 arch/nds32/mm/alignment.c        |  7 +++----
 arch/sh/kernel/traps_32.c        | 12 +++++-------
 drivers/firmware/arm_sdei.c      |  5 ++---
 include/linux/uaccess.h          | 18 ++++++++++++++++++
 kernel/events/callchain.c        |  5 ++---
 kernel/events/core.c             |  5 ++---
 kernel/kthread.c                 |  5 ++---
 kernel/stacktrace.c              |  5 ++---
 mm/maccess.c                     | 22 ++++++++++------------
 12 files changed, 63 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index dab88260b137..7689f2031c0c 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -180,7 +180,7 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
 
 	/*
 	 * We didn't take an exception to get here, set PAN. UAO will be cleared
-	 * by sdei_event_handler()s set_fs(USER_DS) call.
+	 * by sdei_event_handler()s force_uaccess_begin() call.
 	 */
 	__uaccess_enable_hw_pan();
 
diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h
index 191e75a6bb24..5337bc2c262f 100644
--- a/arch/m68k/include/asm/tlbflush.h
+++ b/arch/m68k/include/asm/tlbflush.h
@@ -85,10 +85,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (vma->vm_mm == current->active_mm) {
-		mm_segment_t old_fs = get_fs();
-		set_fs(USER_DS);
+		mm_segment_t old_fs = force_uaccess_begin();
+
 		__flush_tlb_one(addr);
-		set_fs(old_fs);
+		force_uaccess_end(old_fs);
 	}
 }
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 0adce604fa44..126a5f3f4e4c 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -191,17 +191,16 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			 * memory, so we need to "switch" the address limit to
 			 * user space, so that address check can work properly.
 			 */
-			seg = get_fs();
-			set_fs(USER_DS);
+			seg = force_uaccess_begin();
 			switch (insn.spec3_format.func) {
 			case lhe_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -209,12 +208,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lwe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -222,12 +221,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lhue_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWUE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -235,35 +234,35 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case she_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			case swe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			default:
-				set_fs(seg);
+				force_uaccess_end(seg);
 				goto sigill;
 			}
-			set_fs(seg);
+			force_uaccess_end(seg);
 		}
 #endif
 		break;
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index c8b9061a2ee3..1eb7ded6992b 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -512,7 +512,7 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 {
 	unsigned long inst;
 	int ret = -EFAULT;
-	mm_segment_t seg = get_fs();
+	mm_segment_t seg;
 
 	inst = get_inst(regs->ipc);
 
@@ -520,13 +520,12 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 	      "Faulting addr: 0x%08lx, pc: 0x%08lx [inst: 0x%08lx ]\n", addr,
 	      regs->ipc, inst);
 
-	set_fs(USER_DS);
-
+	seg = force_uaccess_begin();
 	if (inst & NDS32_16BIT_INSTRUCTION)
 		ret = do_16((inst >> 16) & 0xffff, regs);
 	else
 		ret = do_32(inst, regs);
-	set_fs(seg);
+	force_uaccess_end(seg);
 
 	return ret;
 }
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 058c6181bb30..b62ad0ba2395 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -482,8 +482,6 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 	error_code = lookup_exception_vector();
 #endif
 
-	oldfs = get_fs();
-
 	if (user_mode(regs)) {
 		int si_code = BUS_ADRERR;
 		unsigned int user_action;
@@ -491,13 +489,13 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 		local_irq_enable();
 		inc_unaligned_user_access();
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1),
 				   sizeof(instruction))) {
-			set_fs(oldfs);
+			force_uaccess_end(oldfs);
 			goto uspace_segv;
 		}
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		/* shout about userspace fixups */
 		unaligned_fixups_notify(current, instruction, regs);
@@ -520,11 +518,11 @@ fixup:
 			goto uspace_segv;
 		}
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		tmp = handle_unaligned_access(instruction, regs,
 					      &user_mem_access, 0,
 					      address);
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		if (tmp == 0)
 			return; /* sorted */
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e7e36aab2386..b4b9ce97f415 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -1136,15 +1136,14 @@ int sdei_event_handler(struct pt_regs *regs,
 	 * access kernel memory.
 	 * Do the same here because this doesn't come via the same entry code.
 	*/
-	orig_addr_limit = get_fs();
-	set_fs(USER_DS);
+	orig_addr_limit = force_uaccess_begin();
 
 	err = arg->callback(event_num, regs, arg->callback_arg);
 	if (err)
 		pr_err_ratelimited("event %u on CPU %u failed with error: %d\n",
 				   event_num, smp_processor_id(), err);
 
-	set_fs(orig_addr_limit);
+	force_uaccess_end(orig_addr_limit);
 
 	return err;
 }
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 5c62d0c6f15b..94b285411659 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -8,6 +8,24 @@
 
 #include <asm/uaccess.h>
 
+/*
+ * Force the uaccess routines to be wired up for actual userspace access,
+ * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
+ * using force_uaccess_end below.
+ */
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	mm_segment_t fs = get_fs();
+
+	set_fs(USER_DS);
+	return fs;
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+	set_fs(oldfs);
+}
+
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
  * and get rid of their private instances of copy_{to,from}_user() and
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index c6ce894e4ce9..58cbe357fb2b 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -217,10 +217,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
-			fs = get_fs();
-			set_fs(USER_DS);
+			fs = force_uaccess_begin();
 			perf_callchain_user(&ctx, regs);
-			set_fs(fs);
+			force_uaccess_end(fs);
 		}
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1f0a7e5b182..6961333ebad5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6453,10 +6453,9 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
-		fs = get_fs();
-		set_fs(USER_DS);
+		fs = force_uaccess_begin();
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
-		set_fs(fs);
+		force_uaccess_end(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b2807e7be772..3edaa380dc7b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1258,8 +1258,7 @@ void kthread_use_mm(struct mm_struct *mm)
 	if (active_mm != mm)
 		mmdrop(active_mm);
 
-	to_kthread(tsk)->oldfs = get_fs();
-	set_fs(USER_DS);
+	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
 EXPORT_SYMBOL_GPL(kthread_use_mm);
 
@@ -1274,7 +1273,7 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!tsk->mm);
 
-	set_fs(to_kthread(tsk)->oldfs);
+	force_uaccess_end(to_kthread(tsk)->oldfs);
 
 	task_lock(tsk);
 	sync_mm_rss(mm);
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 2af66e449aa6..946f44a9e86a 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -233,10 +233,9 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
 	if (current->flags & PF_KTHREAD)
 		return 0;
 
-	fs = get_fs();
-	set_fs(USER_DS);
+	fs = force_uaccess_begin();
 	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
-	set_fs(fs);
+	force_uaccess_end(fs);
 
 	return c.len;
 }
diff --git a/mm/maccess.c b/mm/maccess.c
index f98ff91e32c6..3bd70405f2d8 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -205,15 +205,14 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 long copy_from_user_nofault(void *dst, const void __user *src, size_t size)
 {
 	long ret = -EFAULT;
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs = force_uaccess_begin();
 
-	set_fs(USER_DS);
 	if (access_ok(src, size)) {
 		pagefault_disable();
 		ret = __copy_from_user_inatomic(dst, src, size);
 		pagefault_enable();
 	}
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret)
 		return -EFAULT;
@@ -233,15 +232,14 @@ EXPORT_SYMBOL_GPL(copy_from_user_nofault);
 long copy_to_user_nofault(void __user *dst, const void *src, size_t size)
 {
 	long ret = -EFAULT;
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs = force_uaccess_begin();
 
-	set_fs(USER_DS);
 	if (access_ok(dst, size)) {
 		pagefault_disable();
 		ret = __copy_to_user_inatomic(dst, src, size);
 		pagefault_enable();
 	}
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret)
 		return -EFAULT;
@@ -270,17 +268,17 @@ EXPORT_SYMBOL_GPL(copy_to_user_nofault);
 long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
 			      long count)
 {
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs;
 	long ret;
 
 	if (unlikely(count <= 0))
 		return 0;
 
-	set_fs(USER_DS);
+	old_fs = force_uaccess_begin();
 	pagefault_disable();
 	ret = strncpy_from_user(dst, unsafe_addr, count);
 	pagefault_enable();
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret >= count) {
 		ret = count;
@@ -310,14 +308,14 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
  */
 long strnlen_user_nofault(const void __user *unsafe_addr, long count)
 {
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs;
 	int ret;
 
-	set_fs(USER_DS);
+	old_fs = force_uaccess_begin();
 	pagefault_disable();
 	ret = strnlen_user(unsafe_addr, count);
 	pagefault_enable();
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	return ret;
 }
-- 
cgit v1.2.3


From c5f748e2f2ad970078de11bd6b12bcd81147c636 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:57 -0700
Subject: include/linux/compiler-clang.h: drop duplicated word in a comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Link: http://lkml.kernel.org/r/6a18c301-3505-742f-4dd7-0f38d0e537b9@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 8a072d00e688..cee0c728d39a 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -40,7 +40,7 @@
 #endif
 
 /*
- * Not all versions of clang implement the the type-generic versions
+ * Not all versions of clang implement the type-generic versions
  * of the builtin overflow checkers. Fortunately, clang implements
  * __has_builtin allowing us to avoid awkward version
  * checks. Unfortunately, we don't know which version of gcc clang
-- 
cgit v1.2.3


From cd1a406fa46f81b1a859ef874b8413a6fa6ac7e8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:00 -0700
Subject: include/linux/exportfs.h: drop duplicated word in a comment

Drop the doubled word "a" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Link: http://lkml.kernel.org/r/c61b707a-8fd8-5b1b-aab0-679122881543@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/exportfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index d896b8657085..3ceb72b67a7a 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -178,7 +178,7 @@ struct fid {
  * get_name:
  *    @get_name should find a name for the given @child in the given @parent
  *    directory.  The name should be stored in the @name (with the
- *    understanding that it is already pointing to a a %NAME_MAX+1 sized
+ *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
  *    or error.  @get_name will be called without @parent->i_mutex held.
  *
-- 
cgit v1.2.3


From 121ae8da9cd49f7139bf80f26352337458e63fe1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:04 -0700
Subject: include/linux/async_tx.h: drop duplicated word in a comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Link: http://lkml.kernel.org/r/e85802f7-8f48-8b4c-29b3-ea237a2c7ae9@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/async_tx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 75e582b8d2d9..4c328fef403c 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -36,7 +36,7 @@ struct dma_chan_ref {
 /**
  * async_tx_flags - modifiers for the async_* calls
  * @ASYNC_TX_XOR_ZERO_DST: this flag must be used for xor operations where the
- * the destination address is not a source.  The asynchronous case handles this
+ * destination address is not a source.  The asynchronous case handles this
  * implicitly, the synchronous case needs to zero the destination block.
  * @ASYNC_TX_XOR_DROP_DST: this flag must be used if the destination address is
  * also one of the source addresses.  In the synchronous case the destination
-- 
cgit v1.2.3


From f48ff83e9c1a8fc2e8bfedb4855933eb1ed159b2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:07 -0700
Subject: include/linux/xz.h: drop duplicated word

Drop the doubled word "than" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Lasse Collin <lasse.collin@tukaani.org>
Link: http://lkml.kernel.org/r/05ebba7a-c1e4-01ae-fc7b-15c081b33f3e@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xz.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/xz.h b/include/linux/xz.h
index 64cffa6ddfce..24ad7d875977 100644
--- a/include/linux/xz.h
+++ b/include/linux/xz.h
@@ -28,7 +28,7 @@
  * enum xz_mode - Operation mode
  *
  * @XZ_SINGLE:              Single-call mode. This uses less RAM than
- *                          than multi-call modes, because the LZMA2
+ *                          multi-call modes, because the LZMA2
  *                          dictionary doesn't need to be allocated as
  *                          part of the decoder state. All required data
  *                          structures are allocated at initialization,
-- 
cgit v1.2.3


From 8043fc147a97ec2eefc582487f344f2cbe86d12e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:34:10 -0700
Subject: kernel: add a kernel_wait helper

Add a helper that waits for a pid and stores the status in the passed in
kernel pointer.  Use it to fix the usage of kernel_wait4 in
call_usermodehelper_exec_sync that only happens to work due to the
implicit set_fs(KERNEL_DS) for kernel threads.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Link: http://lkml.kernel.org/r/20200721130449.5008-1-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/task.h |  1 +
 kernel/exit.c              | 16 ++++++++++++++++
 kernel/umh.c               | 29 ++++-------------------------
 3 files changed, 21 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ae3060f0b0c9..a98965007eef 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -88,6 +88,7 @@ struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
+int kernel_wait(pid_t pid, int *stat);
 
 extern void free_task(struct task_struct *tsk);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c2d2961576f2..733e80f334e7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1626,6 +1626,22 @@ long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
 	return ret;
 }
 
+int kernel_wait(pid_t pid, int *stat)
+{
+	struct wait_opts wo = {
+		.wo_type	= PIDTYPE_PID,
+		.wo_pid		= find_get_pid(pid),
+		.wo_flags	= WEXITED,
+	};
+	int ret;
+
+	ret = do_wait(&wo);
+	if (ret > 0 && wo.wo_stat)
+		*stat = wo.wo_stat;
+	put_pid(wo.wo_pid);
+	return ret;
+}
+
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {
diff --git a/kernel/umh.c b/kernel/umh.c
index a25433f9cd9a..fcf3ee803630 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -119,37 +119,16 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 {
 	pid_t pid;
 
-	/* If SIGCLD is ignored kernel_wait4 won't populate the status. */
+	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
 	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
-	if (pid < 0) {
+	if (pid < 0)
 		sub_info->retval = pid;
-	} else {
-		int ret = -ECHILD;
-		/*
-		 * Normally it is bogus to call wait4() from in-kernel because
-		 * wait4() wants to write the exit code to a userspace address.
-		 * But call_usermodehelper_exec_sync() always runs as kernel
-		 * thread (workqueue) and put_user() to a kernel address works
-		 * OK for kernel threads, due to their having an mm_segment_t
-		 * which spans the entire address space.
-		 *
-		 * Thus the __user pointer cast is valid here.
-		 */
-		kernel_wait4(pid, (int __user *)&ret, 0, NULL);
-
-		/*
-		 * If ret is 0, either call_usermodehelper_exec_async failed and
-		 * the real error code is already in sub_info->retval or
-		 * sub_info->retval is 0 anyway, so don't mess with it then.
-		 */
-		if (ret)
-			sub_info->retval = ret;
-	}
+	else
+		kernel_wait(pid, &sub_info->retval);
 
 	/* Restore default kernel sig handler */
 	kernel_sigaction(SIGCHLD, SIG_IGN);
-
 	umh_complete(sub_info);
 }
 
-- 
cgit v1.2.3


From 376653435dacf84a8aca87e66aff94079a817cf2 Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Tue, 11 Aug 2020 18:34:16 -0700
Subject: kernel.h: remove duplicate include of asm/div64.h

This seems to have been added inadvertently in commit
  72deb455b5ec ("block: remove CONFIG_LBDAF")

Fixes: 72deb455b5ec ("block: remove CONFIG_LBDAF")
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200727034852.2813453-1-nivedita@alum.mit.edu
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 7339a00c895e..e19c13616666 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -17,7 +17,6 @@
 #include <asm/byteorder.h>
 #include <asm/div64.h>
 #include <uapi/linux/kernel.h>
-#include <asm/div64.h>
 
 #define STACK_MAGIC	0xdeadbeef
 
-- 
cgit v1.2.3


From 7f317d34906c1033f0752fc137dda04e43979bb8 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 11 Aug 2020 18:34:19 -0700
Subject: include/: replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20200726110117.16346-1-grandmaster@al2klimov.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/clocksource/timer-ti-dm.h               | 2 +-
 include/linux/btree.h                           | 2 +-
 include/linux/delay.h                           | 2 +-
 include/linux/dma/k3-psil.h                     | 2 +-
 include/linux/dma/k3-udma-glue.h                | 2 +-
 include/linux/dma/ti-cppi5.h                    | 2 +-
 include/linux/irqchip/irq-omap-intc.h           | 2 +-
 include/linux/jhash.h                           | 2 +-
 include/linux/leds-ti-lmu-common.h              | 2 +-
 include/linux/platform_data/davinci-cpufreq.h   | 2 +-
 include/linux/platform_data/davinci_asp.h       | 2 +-
 include/linux/platform_data/elm.h               | 2 +-
 include/linux/platform_data/gpio-davinci.h      | 2 +-
 include/linux/platform_data/gpmc-omap.h         | 2 +-
 include/linux/platform_data/mtd-davinci-aemif.h | 2 +-
 include/linux/platform_data/omap-twl4030.h      | 2 +-
 include/linux/platform_data/uio_pruss.h         | 2 +-
 include/linux/platform_data/usb-omap.h          | 2 +-
 include/linux/soc/ti/k3-ringacc.h               | 2 +-
 include/linux/soc/ti/knav_qmss.h                | 2 +-
 include/linux/soc/ti/ti-msgmgr.h                | 2 +-
 include/linux/wkup_m3_ipc.h                     | 2 +-
 include/linux/xxhash.h                          | 2 +-
 include/linux/xz.h                              | 2 +-
 include/linux/zlib.h                            | 2 +-
 include/soc/arc/aux.h                           | 2 +-
 include/uapi/linux/elf.h                        | 2 +-
 include/uapi/linux/map_to_7segment.h            | 2 +-
 include/uapi/linux/types.h                      | 2 +-
 include/uapi/linux/usb/ch9.h                    | 2 +-
 30 files changed, 30 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/clocksource/timer-ti-dm.h b/include/clocksource/timer-ti-dm.h
index 531ca87fcd08..4c61dade8835 100644
--- a/include/clocksource/timer-ti-dm.h
+++ b/include/clocksource/timer-ti-dm.h
@@ -1,7 +1,7 @@
 /*
  * OMAP Dual-Mode Timers
  *
- * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2010 Texas Instruments Incorporated - https://www.ti.com/
  * Tarun Kanti DebBarma <tarun.kanti@ti.com>
  * Thara Gopinath <thara@ti.com>
  *
diff --git a/include/linux/btree.h b/include/linux/btree.h
index 68f858c831b1..243ee544397a 100644
--- a/include/linux/btree.h
+++ b/include/linux/btree.h
@@ -10,7 +10,7 @@
  *
  * A B+Tree is a data structure for looking up arbitrary (currently allowing
  * unsigned long, u32, u64 and 2 * u64) keys into pointers. The data structure
- * is described at http://en.wikipedia.org/wiki/B-tree, we currently do not
+ * is described at https://en.wikipedia.org/wiki/B-tree, we currently do not
  * use binary search to find the key on lookups.
  *
  * Each B+Tree consists of a head, that contains bookkeeping information and
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 5e016a4029d9..1d0e2ce6b6d9 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -16,7 +16,7 @@
  *  3. CPU clock rate changes.
  *
  * Please see this thread:
- *   http://lists.openwall.net/linux-kernel/2011/01/09/56
+ *   https://lists.openwall.net/linux-kernel/2011/01/09/56
  */
 
 #include <linux/kernel.h>
diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h
index 61d5cc0ad601..1962f75fa2d3 100644
--- a/include/linux/dma/k3-psil.h
+++ b/include/linux/dma/k3-psil.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef K3_PSIL_H_
diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h
index caadbab1632a..5eb34ad973a7 100644
--- a/include/linux/dma/k3-udma-glue.h
+++ b/include/linux/dma/k3-udma-glue.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef K3_UDMA_GLUE_H_
diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h
index 579356ae447e..5896441ee604 100644
--- a/include/linux/dma/ti-cppi5.h
+++ b/include/linux/dma/ti-cppi5.h
@@ -2,7 +2,7 @@
 /*
  * CPPI5 descriptors interface
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef __TI_CPPI5_H__
diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h
index 216e5adf80ce..dca379c0d7eb 100644
--- a/include/linux/irqchip/irq-omap-intc.h
+++ b/include/linux/irqchip/irq-omap-intc.h
@@ -2,7 +2,7 @@
 /**
  * irq-omap-intc.h - INTC Idle Functions
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com
  *
  * Author: Felipe Balbi <balbi@ti.com>
  */
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index ba2f6a9776b6..19ddd43aee68 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net)
  *
- * http://burtleburtle.net/bob/hash/
+ * https://burtleburtle.net/bob/hash/
  *
  * These are the credits from Bob's sources:
  *
diff --git a/include/linux/leds-ti-lmu-common.h b/include/linux/leds-ti-lmu-common.h
index 5eb111f38803..420b61e5a213 100644
--- a/include/linux/leds-ti-lmu-common.h
+++ b/include/linux/leds-ti-lmu-common.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // TI LMU Common Core
-// Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/
+// Copyright (C) 2018 Texas Instruments Incorporated - https://www.ti.com/
 
 #ifndef _TI_LMU_COMMON_H_
 #define _TI_LMU_COMMON_H_
diff --git a/include/linux/platform_data/davinci-cpufreq.h b/include/linux/platform_data/davinci-cpufreq.h
index 3fbf9f2793b5..bc208c64e3d7 100644
--- a/include/linux/platform_data/davinci-cpufreq.h
+++ b/include/linux/platform_data/davinci-cpufreq.h
@@ -2,7 +2,7 @@
 /*
  * TI DaVinci CPUFreq platform support.
  *
- * Copyright (C) 2009 Texas Instruments, Inc. http://www.ti.com/
+ * Copyright (C) 2009 Texas Instruments, Inc. https://www.ti.com/
  */
 
 #ifndef _MACH_DAVINCI_CPUFREQ_H
diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h
index 7fe80f1c7e08..5d1fb0d78a22 100644
--- a/include/linux/platform_data/davinci_asp.h
+++ b/include/linux/platform_data/davinci_asp.h
@@ -1,7 +1,7 @@
 /*
  * TI DaVinci Audio Serial Port support
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 0f491d8abfdd..3cc78f0447b1 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -2,7 +2,7 @@
 /*
  * BCH Error Location Module
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef __ELM_H
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
index a93841bfb9f7..e182a46e609f 100644
--- a/include/linux/platform_data/gpio-davinci.h
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -1,7 +1,7 @@
 /*
  * DaVinci GPIO Platform Related Defines
  *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/gpmc-omap.h b/include/linux/platform_data/gpmc-omap.h
index ef663e570552..c9cc4e32435d 100644
--- a/include/linux/platform_data/gpmc-omap.h
+++ b/include/linux/platform_data/gpmc-omap.h
@@ -2,7 +2,7 @@
 /*
  * OMAP GPMC Platform data
  *
- * Copyright (C) 2014 Texas Instruments, Inc. - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments, Inc. - https://www.ti.com
  *	Roger Quadros <rogerq@ti.com>
  */
 
diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h
index a403dd51dacc..a49826214a39 100644
--- a/include/linux/platform_data/mtd-davinci-aemif.h
+++ b/include/linux/platform_data/mtd-davinci-aemif.h
@@ -1,7 +1,7 @@
 /*
  * TI DaVinci AEMIF support
  *
- * Copyright 2010 (C) Texas Instruments, Inc. http://www.ti.com/
+ * Copyright 2010 (C) Texas Instruments, Inc. https://www.ti.com/
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2. This program is licensed "as is" without any warranty of any
diff --git a/include/linux/platform_data/omap-twl4030.h b/include/linux/platform_data/omap-twl4030.h
index 8419c8caf54e..0dd851ea1c72 100644
--- a/include/linux/platform_data/omap-twl4030.h
+++ b/include/linux/platform_data/omap-twl4030.h
@@ -3,7 +3,7 @@
  * omap-twl4030.h - ASoC machine driver for TI SoC based boards with twl4030
  *		    codec, header.
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com
  * All rights reserved.
  *
  * Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h
index 3d47d219827f..31f2e22661bc 100644
--- a/include/linux/platform_data/uio_pruss.h
+++ b/include/linux/platform_data/uio_pruss.h
@@ -3,7 +3,7 @@
  *
  * Platform data for uio_pruss driver
  *
- * Copyright (C) 2010-11 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h
index fa579b4c666b..5e70d667031c 100644
--- a/include/linux/platform_data/usb-omap.h
+++ b/include/linux/platform_data/usb-omap.h
@@ -1,7 +1,7 @@
 /*
  * usb-omap.h - Platform data for the various OMAP USB IPs
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com
  *
  * This software is distributed under the terms of the GNU General Public
  * License ("GPL") version 2, as published by the Free Software Foundation.
diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h
index 7ac115432fa1..5a472eca5ee4 100644
--- a/include/linux/soc/ti/k3-ringacc.h
+++ b/include/linux/soc/ti/k3-ringacc.h
@@ -2,7 +2,7 @@
 /*
  * K3 Ring Accelerator (RA) subsystem interface
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef __SOC_TI_K3_RINGACC_API_H_
diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h
index 9745df6ed9d3..c75ef99c99ca 100644
--- a/include/linux/soc/ti/knav_qmss.h
+++ b/include/linux/soc/ti/knav_qmss.h
@@ -1,7 +1,7 @@
 /*
  * Keystone Navigator Queue Management Sub-System header
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com
  * Author:	Sandeep Nair <sandeep_n@ti.com>
  *		Cyril Chemparathy <cyril@ti.com>
  *		Santosh Shilimkar <santosh.shilimkar@ti.com>
diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h
index eac8e0c6fe11..1f6e76d423cf 100644
--- a/include/linux/soc/ti/ti-msgmgr.h
+++ b/include/linux/soc/ti/ti-msgmgr.h
@@ -1,7 +1,7 @@
 /*
  * Texas Instruments' Message Manager
  *
- * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/
  *	Nishanth Menon
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index e497e621dbb7..3f496967b538 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -1,7 +1,7 @@
 /*
  * TI Wakeup M3 for AMx3 SoCs Power Management Routines
  *
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  * Dave Gerlach <d-gerlach@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h
index 52b073fea17f..df42511438d0 100644
--- a/include/linux/xxhash.h
+++ b/include/linux/xxhash.h
@@ -34,7 +34,7 @@
  * ("BSD").
  *
  * You can contact the author at:
- * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash homepage: https://cyan4973.github.io/xxHash/
  * - xxHash source repository: https://github.com/Cyan4973/xxHash
  */
 
diff --git a/include/linux/xz.h b/include/linux/xz.h
index 24ad7d875977..9884c8440188 100644
--- a/include/linux/xz.h
+++ b/include/linux/xz.h
@@ -2,7 +2,7 @@
  * XZ decompressor
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/include/linux/zlib.h b/include/linux/zlib.h
index c757d848a758..78ede944c082 100644
--- a/include/linux/zlib.h
+++ b/include/linux/zlib.h
@@ -23,7 +23,7 @@
 
 
   The data format used by the zlib library is described by RFCs (Request for
-  Comments) 1950 to 1952 in the files http://www.ietf.org/rfc/rfc1950.txt
+  Comments) 1950 to 1952 in the files https://www.ietf.org/rfc/rfc1950.txt
   (zlib format), rfc1951.txt (deflate format) and rfc1952.txt (gzip format).
 */
 
diff --git a/include/soc/arc/aux.h b/include/soc/arc/aux.h
index e223c4ffa153..9c2eff6140b6 100644
--- a/include/soc/arc/aux.h
+++ b/include/soc/arc/aux.h
@@ -22,7 +22,7 @@ static inline int read_aux_reg(u32 r)
 
 /*
  * function helps elide unused variable warning
- * see: http://lists.infradead.org/pipermail/linux-snps-arc/2016-November/001748.html
+ * see: https://lists.infradead.org/pipermail/linux-snps-arc/2016-November/001748.html
  */
 static inline void write_aux_reg(u32 r, u32 v)
 {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index c6dd0215482e..22220945a5fd 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -53,7 +53,7 @@ typedef __s64	Elf64_Sxword;
  *
  * - Oracle: Linker and Libraries.
  *   Part No: 817–1984–19, August 2011.
- *   http://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
+ *   https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
  *
  * - System V ABI AMD64 Architecture Processor Supplement
  *   Draft Version 0.99.4,
diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h
index f9ed18134b83..13a06e5e966e 100644
--- a/include/uapi/linux/map_to_7segment.h
+++ b/include/uapi/linux/map_to_7segment.h
@@ -24,7 +24,7 @@
  * of (ASCII) characters to a 7-segments notation.
  *
  * The 7 segment's wikipedia notation below is used as standard.
- * See: http://en.wikipedia.org/wiki/Seven_segment_display
+ * See: https://en.wikipedia.org/wiki/Seven_segment_display
  *
  * Notation:	+-a-+
  *		f   b
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
index 2fce8b6876e9..f6d2f83cbe29 100644
--- a/include/uapi/linux/types.h
+++ b/include/uapi/linux/types.h
@@ -7,7 +7,7 @@
 #ifndef __ASSEMBLY__
 #ifndef	__KERNEL__
 #ifndef __EXPORTED_HEADERS__
-#warning "Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders"
+#warning "Attempt to use kernel headers from user space, see https://kernelnewbies.org/KernelHeaders"
 #endif /* __EXPORTED_HEADERS__ */
 #endif
 
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 48766fdf6580..0f865ae4ba89 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -1229,7 +1229,7 @@ struct usb_set_sel_req {
  * As per USB compliance update, a device that is actively drawing
  * more than 100mA from USB must report itself as bus-powered in
  * the GetStatus(DEVICE) call.
- * http://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34
+ * https://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34
  */
 #define USB_SELF_POWER_VBUS_MAX_DRAW		100
 
-- 
cgit v1.2.3


From 9e58c5e2fcd8d8d8820ea277e0f577f563eed1f1 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 11 Aug 2020 18:34:23 -0700
Subject: include/linux/poison.h: remove obsolete comment

When the definition was changed, the comment became stale.  Just remove
it since there isn't anything useful to say here.

Fixes: b8a0255db958 ("include/linux/poison.h: use POISON_POINTER_DELTA for poison pointers")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vasily Kulikov <segoon@openwall.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20200730174108.GJ23808@casper.infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/poison.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/poison.h b/include/linux/poison.h
index df34330b4e34..dc8ae5d8db03 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -24,10 +24,6 @@
 #define LIST_POISON2  ((void *) 0x122 + POISON_POINTER_DELTA)
 
 /********** include/linux/timer.h **********/
-/*
- * Magic number "tsta" to indicate a static timer initializer
- * for the object debugging code.
- */
 #define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/page_poison.c **********/
-- 
cgit v1.2.3


From 25fd529c34d063d1bef23742f2e8f8341c639dc3 Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Tue, 11 Aug 2020 18:34:26 -0700
Subject: sparse: group the defines by functionality

By popular demand, reorder the defines for sparse annotations and group
them by functionality.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: lore.kernel.org/r/CAMuHMdWQsirja-h3wBcZezk+H2Q_HShhAks8Hc8ps5fTAp=ObQ@mail.gmail.com
Link: http://lkml.kernel.org/r/20200621143652.53798-1-luc.vanoostenryck@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler_types.h | 44 ++++++++++++++++++++++++------------------
 1 file changed, 25 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 2e231ba8fe3f..4b33cb385f96 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -5,48 +5,54 @@
 #ifndef __ASSEMBLY__
 
 #ifdef __CHECKER__
+/* address spaces */
 # define __kernel	__attribute__((address_space(0)))
 # define __user		__attribute__((noderef, address_space(__user)))
-# define __safe		__attribute__((safe))
-# define __force	__attribute__((force))
-# define __nocast	__attribute__((nocast))
 # define __iomem	__attribute__((noderef, address_space(__iomem)))
+# define __percpu	__attribute__((noderef, address_space(__percpu)))
+# define __rcu		__attribute__((noderef, address_space(__rcu)))
+extern void __chk_user_ptr(const volatile void __user *);
+extern void __chk_io_ptr(const volatile void __iomem *);
+/* context/locking */
 # define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
 # define __releases(x)	__attribute__((context(x,1,0)))
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu	__attribute__((noderef, address_space(__percpu)))
-# define __rcu		__attribute__((noderef, address_space(__rcu)))
+/* other */
+# define __force	__attribute__((force))
+# define __nocast	__attribute__((nocast))
+# define __safe		__attribute__((safe))
 # define __private	__attribute__((noderef))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
 # define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
 #else /* __CHECKER__ */
+/* address spaces */
+# define __kernel
 # ifdef STRUCTLEAK_PLUGIN
-#  define __user __attribute__((user))
+#  define __user	__attribute__((user))
 # else
 #  define __user
 # endif
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
 # define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
+# define __percpu
+# define __rcu
+# define __chk_user_ptr(x)	(void)0
+# define __chk_io_ptr(x)	(void)0
+/* context/locking */
 # define __must_hold(x)
 # define __acquires(x)
 # define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
+# define __acquire(x)	(void)0
+# define __release(x)	(void)0
 # define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
+/* other */
+# define __force
+# define __nocast
+# define __safe
 # define __private
 # define ACCESS_PRIVATE(p, member) ((p)->member)
+# define __builtin_warning(x, y...) (1)
 #endif /* __CHECKER__ */
 
 /* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-- 
cgit v1.2.3


From 0a650e472d2039a5f768acd82f2a7068bf338dfd Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Tue, 11 Aug 2020 18:34:35 -0700
Subject: lib/generic-radix-tree.c: remove unneeded __rcu

struct __genradix is defined as having its member 'root'
annotated as __rcu. But in the corresponding API RCU is not used.
Sparse reports this type mismatch as:
	lib/generic-radix-tree.c:56:35: warning: incorrect type in initializer (different address spaces)
	lib/generic-radix-tree.c:56:35:    expected struct genradix_root *r
	lib/generic-radix-tree.c:56:35:    got struct genradix_root [noderef] <asn:4> *__val
with 6 other ones.

So, correct root's type by removing this unneeded __rcu.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Link: http://lkml.kernel.org/r/20200621161745.55396-1-luc.vanoostenryck@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/generic-radix-tree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h
index 02393c0c98f9..bfd00320c7f3 100644
--- a/include/linux/generic-radix-tree.h
+++ b/include/linux/generic-radix-tree.h
@@ -44,7 +44,7 @@
 struct genradix_root;
 
 struct __genradix {
-	struct genradix_root __rcu	*root;
+	struct genradix_root		*root;
 };
 
 /*
-- 
cgit v1.2.3


From b642e44e8ab335868b549fe5753b783ca47bf3a3 Mon Sep 17 00:00:00 2001
From: Kars Mulder <kerneldev@karsmulder.nl>
Date: Tue, 11 Aug 2020 18:34:53 -0700
Subject: kstrto*: correct documentation references to simple_strto*()

The documentation of the kstrto*() functions reference the simple_strtoull
function by "used as a replacement for [the obsolete] simple_strtoull".
All these functions describes themselves as replacements for the function
simple_strtoull, even though a function like kstrtol() would be more aptly
described as a replacement of simple_strtol().

Fix these references by making the documentation of kstrto*() reference
the closest simple_strto*() equivalent available.  The functions
kstrto[u]int() do not have direct simple_strto[u]int() equivalences, so
these are made to refer to simple_strto[u]l() instead.

Furthermore, add parentheses after function names, as is standard in
kernel documentation.

Fixes: 4c925d6031f71 ("kstrto*: add documentation")
Signed-off-by: Kars Mulder <kerneldev@karsmulder.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Eldad Zack <eldad@fogrefinery.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Mans Rullgard <mans@mansr.com>
Cc: Petr Mladek <pmladek@suse.com>
Link: http://lkml.kernel.org/r/1ee1-5f234c00-f3-165a6440@234394593
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 4 ++--
 lib/kstrtox.c          | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e19c13616666..47b1dad63ffc 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoull. Return code must be checked.
+ * Used as a replacement for the simple_strtoul(). Return code must be checked.
 */
 static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
 {
@@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoull. Return code must be checked.
+ * Used as a replacement for the simple_strtol(). Return code must be checked.
  */
 static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
 {
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 1006bf70bf74..252ac414ba9a 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -115,7 +115,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoull(). Return code must
  * be checked.
  */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
@@ -139,7 +139,7 @@ EXPORT_SYMBOL(kstrtoull);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoll(). Return code must
  * be checked.
  */
 int kstrtoll(const char *s, unsigned int base, long long *res)
@@ -211,7 +211,7 @@ EXPORT_SYMBOL(_kstrtol);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoul(). Return code must
  * be checked.
  */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
@@ -242,7 +242,7 @@ EXPORT_SYMBOL(kstrtouint);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtol(). Return code must
  * be checked.
  */
 int kstrtoint(const char *s, unsigned int base, int *res)
-- 
cgit v1.2.3


From ef0f2685336bbc334e8b6997ce9b155e5f7edd31 Mon Sep 17 00:00:00 2001
From: Kars Mulder <kerneldev@karsmulder.nl>
Date: Tue, 11 Aug 2020 18:34:56 -0700
Subject: kstrto*: do not describe simple_strto*() as obsolete/replaced

The documentation of the kstrto*() functions describes kstrto*() as
"replacements" of the "obsolete" simple_strto*() functions.  Both of these
terms are inaccurate: they're not replacements because they have different
behaviour, and the simple_strto*() are not obsolete because there are
cases where they have benefits over kstrto*().

Remove usage of the terms "replacement" and "obsolete" in reference to
simple_strto*(), and instead use the term "preferred over".

Fixes: 4c925d6031f71 ("kstrto*: add documentation")
Fixes: 885e68e8b7b13 ("kernel.h: update comment about simple_strto<foo>() functions")
Signed-off-by: Kars Mulder <kerneldev@karsmulder.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Eldad Zack <eldad@fogrefinery.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Mans Rullgard <mans@mansr.com>
Cc: Petr Mladek <pmladek@suse.com>
Link: http://lkml.kernel.org/r/29b9-5f234c80-13-4e3aa200@244003027
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h |  4 ++--
 lib/kstrtox.c          | 12 ++++--------
 2 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 47b1dad63ffc..92517ae53e7c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoul(). Return code must be checked.
+ * Preferred over simple_strtoul(). Return code must be checked.
 */
 static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
 {
@@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtol(). Return code must be checked.
+ * Preferred over simple_strtol(). Return code must be checked.
  */
 static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
 {
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 252ac414ba9a..a14ccf905055 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -115,8 +115,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull(). Return code must
- * be checked.
+ * Preferred over simple_strtoull(). Return code must be checked.
  */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 {
@@ -139,8 +138,7 @@ EXPORT_SYMBOL(kstrtoull);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoll(). Return code must
- * be checked.
+ * Preferred over simple_strtoll(). Return code must be checked.
  */
 int kstrtoll(const char *s, unsigned int base, long long *res)
 {
@@ -211,8 +209,7 @@ EXPORT_SYMBOL(_kstrtol);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoul(). Return code must
- * be checked.
+ * Preferred over simple_strtoul(). Return code must be checked.
  */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
 {
@@ -242,8 +239,7 @@ EXPORT_SYMBOL(kstrtouint);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtol(). Return code must
- * be checked.
+ * Preferred over simple_strtol(). Return code must be checked.
  */
 int kstrtoint(const char *s, unsigned int base, int *res)
 {
-- 
cgit v1.2.3


From 0935288c6e008c0682ab6171fb5605dcc049e7bd Mon Sep 17 00:00:00 2001
From: Vijay Balakrishna <vijayb@linux.microsoft.com>
Date: Tue, 11 Aug 2020 18:36:33 -0700
Subject: kdump: append kernel build-id string to VMCOREINFO

Make kernel GNU build-id available in VMCOREINFO.  Having build-id in
VMCOREINFO facilitates presenting appropriate kernel namelist image with
debug information file to kernel crash dump analysis tools.  Currently
VMCOREINFO lacks uniquely identifiable key for crash analysis automation.

Regarding if this patch is necessary or matching of linux_banner and
OSRELEASE in VMCOREINFO employed by crash(8) meets the need -- IMO,
build-id approach more foolproof, in most instances it is a cryptographic
hash generated using internal code/ELF bits unlike kernel version string
upon which linux_banner is based that is external to the code.  I feel
each is intended for a different purpose.  Also OSRELEASE is not suitable
when two different kernel builds from same version with different features
enabled.

Currently for most linux (and non-linux) systems build-id can be extracted
using standard methods for file types such as user mode crash dumps,
shared libraries, loadable kernel modules etc., This is an exception for
linux kernel dump.  Having build-id in VMCOREINFO brings some uniformity
for automation tools.

Tyler said:

: I think this is a nice improvement over today's linux_banner approach for
: correlating vmlinux to a kernel dump.
:
: The elf notes parsing in this patch lines up with what is described in in
: the "Notes (Nhdr)" section of the elf(5) man page.
:
: BUILD_ID_MAX is sufficient to hold a sha1 build-id, which is the default
: build-id type today in GNU ld(2).  It is also sufficient to hold the
: "fast" build-id, which is the default build-id type today in LLVM lld(2).

Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1591849672-34104-1-git-send-email-vijayb@linux.microsoft.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/crash_core.h |  6 ++++++
 kernel/crash_core.c        | 50 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 525510a9f965..6594dbc34a37 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -38,6 +38,8 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 
 #define VMCOREINFO_OSRELEASE(value) \
 	vmcoreinfo_append_str("OSRELEASE=%s\n", value)
+#define VMCOREINFO_BUILD_ID(value) \
+	vmcoreinfo_append_str("BUILD-ID=%s\n", value)
 #define VMCOREINFO_PAGESIZE(value) \
 	vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
 #define VMCOREINFO_SYMBOL(name) \
@@ -64,6 +66,10 @@ extern unsigned char *vmcoreinfo_data;
 extern size_t vmcoreinfo_size;
 extern u32 *vmcoreinfo_note;
 
+/* raw contents of kernel .notes section */
+extern const void __start_notes __weak;
+extern const void __stop_notes __weak;
+
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
 void final_note(Elf_Word *buf);
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 18175687133a..106e4500fd53 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,6 +11,8 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 
+#include <crypto/sha.h>
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -376,6 +378,53 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void)
 }
 EXPORT_SYMBOL(paddr_vmcoreinfo_note);
 
+#define NOTES_SIZE (&__stop_notes - &__start_notes)
+#define BUILD_ID_MAX SHA1_DIGEST_SIZE
+#define NT_GNU_BUILD_ID 3
+
+struct elf_note_section {
+	struct elf_note	n_hdr;
+	u8 n_data[];
+};
+
+/*
+ * Add build ID from .notes section as generated by the GNU ld(1)
+ * or LLVM lld(1) --build-id option.
+ */
+static void add_build_id_vmcoreinfo(void)
+{
+	char build_id[BUILD_ID_MAX * 2 + 1];
+	int n_remain = NOTES_SIZE;
+
+	while (n_remain >= sizeof(struct elf_note)) {
+		const struct elf_note_section *note_sec =
+			&__start_notes + NOTES_SIZE - n_remain;
+		const u32 n_namesz = note_sec->n_hdr.n_namesz;
+
+		if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID &&
+		    n_namesz != 0 &&
+		    !strcmp((char *)&note_sec->n_data[0], "GNU")) {
+			if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) {
+				const u32 n_descsz = note_sec->n_hdr.n_descsz;
+				const u8 *s = &note_sec->n_data[n_namesz];
+
+				s = PTR_ALIGN(s, 4);
+				bin2hex(build_id, s, n_descsz);
+				build_id[2 * n_descsz] = '\0';
+				VMCOREINFO_BUILD_ID(build_id);
+				return;
+			}
+			pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n",
+				note_sec->n_hdr.n_descsz,
+				BUILD_ID_MAX);
+			return;
+		}
+		n_remain -= sizeof(struct elf_note) +
+			ALIGN(note_sec->n_hdr.n_namesz, 4) +
+			ALIGN(note_sec->n_hdr.n_descsz, 4);
+	}
+}
+
 static int __init crash_save_vmcoreinfo_init(void)
 {
 	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
@@ -394,6 +443,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	}
 
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	add_build_id_vmcoreinfo();
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
 	VMCOREINFO_SYMBOL(init_uts_ns);
-- 
cgit v1.2.3


From 79076e1241bb3bf02d0aac7d39120d8161fe07b1 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:46 -0700
Subject: kernel/panic.c: make oops_may_print() return bool

The return value of oops_may_print() is true or false, so change its type
to reflect that.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Xuefeng Li <lixuefeng@loongson.cn>
Link: http://lkml.kernel.org/r/1591103358-32087-1-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 2 +-
 kernel/panic.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 92517ae53e7c..211005163682 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -322,7 +322,7 @@ void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
-extern int oops_may_print(void);
+extern bool oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
 
diff --git a/kernel/panic.c b/kernel/panic.c
index e2157ca387c8..93ba061d1c79 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -505,7 +505,7 @@ static void do_oops_enter_exit(void)
  * Return true if the calling CPU is allowed to print oops-related info.
  * This is a bit racy..
  */
-int oops_may_print(void)
+bool oops_may_print(void)
 {
 	return pause_on_oops_flag == 0;
 }
-- 
cgit v1.2.3


From 63037f74725ddd8a767ed2ad0369e60a3bf1f2ce Mon Sep 17 00:00:00 2001
From: Yue Hu <huyue2@yulong.com>
Date: Tue, 11 Aug 2020 18:36:53 -0700
Subject: panic: make print_oops_end_marker() static

Since print_oops_end_marker() is not used externally, also remove it in
kernel.h at the same time.

Signed-off-by: Yue Hu <huyue2@yulong.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20200724011516.12756-1-zbestahu@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 1 -
 kernel/panic.c         | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 211005163682..500def620d8f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -321,7 +321,6 @@ void panic(const char *fmt, ...) __noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
-void print_oops_end_marker(void);
 extern bool oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
diff --git a/kernel/panic.c b/kernel/panic.c
index 93ba061d1c79..aef8872ba843 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -551,7 +551,7 @@ static int init_oops_id(void)
 }
 late_initcall(init_oops_id);
 
-void print_oops_end_marker(void)
+static void print_oops_end_marker(void)
 {
 	init_oops_id();
 	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
-- 
cgit v1.2.3


From b4b382238ed2f94f0d3860f9120b66404fa99463 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:14 -0700
Subject: mm/migrate: move migration helper from .h to .c

It's not performance sensitive function.  Move it to .c.  This is a
preparation step for future change.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 33 +++++----------------------------
 mm/migrate.c            | 29 +++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 540998d9810b..abeb4b15b297 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -31,34 +31,6 @@ enum migrate_reason {
 /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
 extern const char *migrate_reason_names[MR_TYPES];
 
-static inline struct page *new_page_nodemask(struct page *page,
-				int preferred_nid, nodemask_t *nodemask)
-{
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
-	unsigned int order = 0;
-	struct page *new_page = NULL;
-
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
-				preferred_nid, nodemask);
-
-	if (PageTransHuge(page)) {
-		gfp_mask |= GFP_TRANSHUGE;
-		order = HPAGE_PMD_ORDER;
-	}
-
-	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	new_page = __alloc_pages_nodemask(gfp_mask, order,
-				preferred_nid, nodemask);
-
-	if (new_page && PageTransHuge(new_page))
-		prep_transhuge_page(new_page);
-
-	return new_page;
-}
-
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
@@ -67,6 +39,8 @@ extern int migrate_page(struct address_space *mapping,
 			enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
+extern struct page *new_page_nodemask(struct page *page,
+		int preferred_nid, nodemask_t *nodemask);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 extern void putback_movable_page(struct page *page);
 
@@ -85,6 +59,9 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
 		int reason)
 	{ return -ENOSYS; }
+static inline struct page *new_page_nodemask(struct page *page,
+		int preferred_nid, nodemask_t *nodemask)
+	{ return NULL; }
 static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
 	{ return -EBUSY; }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 52896b4921a7..5269bc520aee 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1538,6 +1538,35 @@ out:
 	return rc;
 }
 
+struct page *new_page_nodemask(struct page *page,
+				int preferred_nid, nodemask_t *nodemask)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
+	unsigned int order = 0;
+	struct page *new_page = NULL;
+
+	if (PageHuge(page))
+		return alloc_huge_page_nodemask(
+				page_hstate(compound_head(page)),
+				preferred_nid, nodemask);
+
+	if (PageTransHuge(page)) {
+		gfp_mask |= GFP_TRANSHUGE;
+		order = HPAGE_PMD_ORDER;
+	}
+
+	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	new_page = __alloc_pages_nodemask(gfp_mask, order,
+				preferred_nid, nodemask);
+
+	if (new_page && PageTransHuge(new_page))
+		prep_transhuge_page(new_page);
+
+	return new_page;
+}
+
 #ifdef CONFIG_NUMA
 
 static int store_status(int __user *status, int start, int value, int nr)
-- 
cgit v1.2.3


From d92bbc2719bd2be237ee336113b63492a6baca3b Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:17 -0700
Subject: mm/hugetlb: unify migration callbacks

There is no difference between two migration callback functions,
alloc_huge_page_node() and alloc_huge_page_nodemask(), except
__GFP_THISNODE handling.  It's redundant to have two almost similar
functions in order to handle this flag.  So, this patch tries to remove
one by introducing a new argument, gfp_mask, to
alloc_huge_page_nodemask().

After introducing gfp_mask argument, it's caller's job to provide correct
gfp_mask.  So, every callsites for alloc_huge_page_nodemask() are changed
to provide gfp_mask.

Note that it's safe to remove a node id check in alloc_huge_page_node()
since there is no caller passing NUMA_NO_NODE as a node id.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-4-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 26 ++++++++++++++++++--------
 mm/hugetlb.c            | 35 ++---------------------------------
 mm/mempolicy.c          | 10 ++++++----
 mm/migrate.c            | 11 +++++++----
 4 files changed, 33 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index a520bf26e5d8..3517edde681e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/pgtable.h>
+#include <linux/gfp.h>
 
 struct ctl_table;
 struct user_struct;
@@ -506,9 +507,8 @@ struct huge_bootmem_page {
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
-struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask);
+				nodemask_t *nmask, gfp_t gfp_mask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
 struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
@@ -694,6 +694,15 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 	return true;
 }
 
+/* Movability of hugepages depends on migration support. */
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+	if (hugepage_movable_supported(h))
+		return GFP_HIGHUSER_MOVABLE;
+	else
+		return GFP_HIGHUSER;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -761,13 +770,9 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 	return NULL;
 }
 
-static inline struct page *alloc_huge_page_node(struct hstate *h, int nid)
-{
-	return NULL;
-}
-
 static inline struct page *
-alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask)
+alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+			nodemask_t *nmask, gfp_t gfp_mask)
 {
 	return NULL;
 }
@@ -880,6 +885,11 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 	return false;
 }
 
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+	return 0;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b66bf74e999e..eaab9ef88e9d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1093,15 +1093,6 @@ retry_cpuset:
 	return NULL;
 }
 
-/* Movability of hugepages depends on migration support. */
-static inline gfp_t htlb_alloc_mask(struct hstate *h)
-{
-	if (hugepage_movable_supported(h))
-		return GFP_HIGHUSER_MOVABLE;
-	else
-		return GFP_HIGHUSER;
-}
-
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve,
@@ -1985,32 +1976,10 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 	return page;
 }
 
-/* page migration callback function */
-struct page *alloc_huge_page_node(struct hstate *h, int nid)
-{
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-	struct page *page = NULL;
-
-	if (nid != NUMA_NO_NODE)
-		gfp_mask |= __GFP_THISNODE;
-
-	spin_lock(&hugetlb_lock);
-	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
-	spin_unlock(&hugetlb_lock);
-
-	if (!page)
-		page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
-
-	return page;
-}
-
 /* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask)
+		nodemask_t *nmask, gfp_t gfp_mask)
 {
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
 		struct page *page;
@@ -2038,7 +2007,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask);
+	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
 	mpol_cond_put(mpol);
 
 	return page;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 25b7e412c20b..9ae2b704bdf6 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1068,10 +1068,12 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist,
 /* page allocation callback for NUMA node migration */
 struct page *alloc_new_node_page(struct page *page, unsigned long node)
 {
-	if (PageHuge(page))
-		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					node);
-	else if (PageTransHuge(page)) {
+	if (PageHuge(page)) {
+		struct hstate *h = page_hstate(compound_head(page));
+		gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
+
+		return alloc_huge_page_nodemask(h, node, NULL, gfp_mask);
+	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
 		thp = alloc_pages_node(node,
diff --git a/mm/migrate.c b/mm/migrate.c
index 5269bc520aee..8d084e9bc13b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1545,10 +1545,13 @@ struct page *new_page_nodemask(struct page *page,
 	unsigned int order = 0;
 	struct page *new_page = NULL;
 
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(
-				page_hstate(compound_head(page)),
-				preferred_nid, nodemask);
+	if (PageHuge(page)) {
+		struct hstate *h = page_hstate(compound_head(page));
+
+		gfp_mask = htlb_alloc_mask(h);
+		return alloc_huge_page_nodemask(h, preferred_nid,
+						nodemask, gfp_mask);
+	}
 
 	if (PageTransHuge(page)) {
 		gfp_mask |= GFP_TRANSHUGE;
-- 
cgit v1.2.3


From 19fc7bed252c16ace29491e4cfa2bafb264eb505 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:25 -0700
Subject: mm/migrate: introduce a standard migration target allocation function

There are some similar functions for migration target allocation.  Since
there is no fundamental difference, it's better to keep just one rather
than keeping all variants.  This patch implements base migration target
allocation function.  In the following patches, variants will be converted
to use this function.

Changes should be mechanical, but, unfortunately, there are some
differences.  First, some callers' nodemask is assgined to NULL since NULL
nodemask will be considered as all available nodes, that is,
&node_states[N_MEMORY].  Second, for hugetlb page allocation, gfp_mask is
redefined as regular hugetlb allocation gfp_mask plus __GFP_THISNODE if
user provided gfp_mask has it.  This is because future caller of this
function requires to set this node constaint.  Lastly, if provided nodeid
is NUMA_NO_NODE, nodeid is set up to the node where migration source
lives.  It helps to remove simple wrappers for setting up the nodeid.

Note that PageHighmem() call in previous function is changed to open-code
"is_highmem_idx()" since it provides more readability.

[akpm@linux-foundation.org: tweak patch title, per Vlastimil]
[akpm@linux-foundation.org: fix typo in comment]

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-6-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 15 +++++++++++++++
 include/linux/migrate.h |  9 +++++----
 mm/internal.h           |  7 +++++++
 mm/memory-failure.c     |  7 +++++--
 mm/memory_hotplug.c     | 12 ++++++++----
 mm/migrate.c            | 26 ++++++++++++++++----------
 mm/page_isolation.c     |  7 +++++--
 7 files changed, 61 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3517edde681e..30e1f14119c8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -703,6 +703,16 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h)
 		return GFP_HIGHUSER;
 }
 
+static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
+{
+	gfp_t modified_mask = htlb_alloc_mask(h);
+
+	/* Some callers might want to enforce node */
+	modified_mask |= (gfp_mask & __GFP_THISNODE);
+
+	return modified_mask;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -890,6 +900,11 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h)
 	return 0;
 }
 
+static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
+{
+	return 0;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index abeb4b15b297..0f8d1583fa8e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -10,6 +10,8 @@
 typedef struct page *new_page_t(struct page *page, unsigned long private);
 typedef void free_page_t(struct page *page, unsigned long private);
 
+struct migration_target_control;
+
 /*
  * Return values from addresss_space_operations.migratepage():
  * - negative errno on page migration failure;
@@ -39,8 +41,7 @@ extern int migrate_page(struct address_space *mapping,
 			enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
-extern struct page *new_page_nodemask(struct page *page,
-		int preferred_nid, nodemask_t *nodemask);
+extern struct page *alloc_migration_target(struct page *page, unsigned long private);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 extern void putback_movable_page(struct page *page);
 
@@ -59,8 +60,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
 		int reason)
 	{ return -ENOSYS; }
-static inline struct page *new_page_nodemask(struct page *page,
-		int preferred_nid, nodemask_t *nodemask)
+static inline struct page *alloc_migration_target(struct page *page,
+		unsigned long private)
 	{ return NULL; }
 static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
 	{ return -EBUSY; }
diff --git a/mm/internal.h b/mm/internal.h
index 42cf0b610847..f725aa8a9698 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -614,4 +614,11 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 
 void setup_zone_pageset(struct zone *zone);
 extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
+
+struct migration_target_control {
+	int nid;		/* preferred node id */
+	nodemask_t *nmask;
+	gfp_t gfp_mask;
+};
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 47b8ccb1fb9b..f1aa6433f404 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1648,9 +1648,12 @@ EXPORT_SYMBOL(unpoison_memory);
 
 static struct page *new_page(struct page *p, unsigned long private)
 {
-	int nid = page_to_nid(p);
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(p),
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
-	return new_page_nodemask(p, nid, &node_states[N_MEMORY]);
+	return alloc_migration_target(p, (unsigned long)&mtc);
 }
 
 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0a9e1972fbe7..c32ead89c911 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1276,19 +1276,23 @@ found:
 
 static struct page *new_node_page(struct page *page, unsigned long private)
 {
-	int nid = page_to_nid(page);
 	nodemask_t nmask = node_states[N_MEMORY];
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(page),
+		.nmask = &nmask,
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
 	/*
 	 * try to allocate from a different node but reuse this node if there
 	 * are no other online nodes to be used (e.g. we are offlining a part
 	 * of the only existing node)
 	 */
-	node_clear(nid, nmask);
+	node_clear(mtc.nid, nmask);
 	if (nodes_empty(nmask))
-		node_set(nid, nmask);
+		node_set(mtc.nid, nmask);
 
-	return new_page_nodemask(page, nid, &nmask);
+	return alloc_migration_target(page, (unsigned long)&mtc);
 }
 
 static int
diff --git a/mm/migrate.c b/mm/migrate.c
index 46cca5c2ebff..48b1f149494b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1538,19 +1538,26 @@ out:
 	return rc;
 }
 
-struct page *new_page_nodemask(struct page *page,
-				int preferred_nid, nodemask_t *nodemask)
+struct page *alloc_migration_target(struct page *page, unsigned long private)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
+	struct migration_target_control *mtc;
+	gfp_t gfp_mask;
 	unsigned int order = 0;
 	struct page *new_page = NULL;
+	int nid;
+	int zidx;
+
+	mtc = (struct migration_target_control *)private;
+	gfp_mask = mtc->gfp_mask;
+	nid = mtc->nid;
+	if (nid == NUMA_NO_NODE)
+		nid = page_to_nid(page);
 
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(compound_head(page));
 
-		gfp_mask = htlb_alloc_mask(h);
-		return alloc_huge_page_nodemask(h, preferred_nid,
-						nodemask, gfp_mask);
+		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
+		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
 	}
 
 	if (PageTransHuge(page)) {
@@ -1562,12 +1569,11 @@ struct page *new_page_nodemask(struct page *page,
 		gfp_mask |= GFP_TRANSHUGE;
 		order = HPAGE_PMD_ORDER;
 	}
-
-	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+	zidx = zone_idx(page_zone(page));
+	if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
 		gfp_mask |= __GFP_HIGHMEM;
 
-	new_page = __alloc_pages_nodemask(gfp_mask, order,
-				preferred_nid, nodemask);
+	new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask);
 
 	if (new_page && PageTransHuge(new_page))
 		prep_transhuge_page(new_page);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index aec26d972b9f..f25c66ea37ac 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -309,7 +309,10 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 
 struct page *alloc_migrate_target(struct page *page, unsigned long private)
 {
-	int nid = page_to_nid(page);
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(page),
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
-	return new_page_nodemask(page, nid, &node_states[N_MEMORY]);
+	return alloc_migration_target(page, (unsigned long)&mtc);
 }
-- 
cgit v1.2.3


From 41b4dc14ee807cb1bd15e67cad287534046f92dc Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:34 -0700
Subject: mm/gup: restrict CMA region by using allocation scope API

We have well defined scope API to exclude CMA region.  Use it rather than
manipulating gfp_mask manually.  With this change, we can now restore
__GFP_MOVABLE for gfp_mask like as usual migration target allocation.  It
would result in that the ZONE_MOVABLE is also searched by page allocator.
For hugetlb, gfp_mask is redefined since it has a regular allocation mask
filter for migration target.  __GPF_NOWARN is added to hugetlb gfp_mask
filter since a new user for gfp_mask filter, gup, want to be silent when
allocation fails.

Note that this can be considered as a fix for the commit 9a4e9f3b2d73
("mm: update get_user_pages_longterm to migrate pages allocated from CMA
region").  However, "Fixes" tag isn't added here since it is just
suboptimal but it doesn't cause any problem.

Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Link: http://lkml.kernel.org/r/1596180906-8442-1-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 ++
 mm/gup.c                | 17 ++++++++---------
 2 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 30e1f14119c8..d86c82749836 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -710,6 +710,8 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	/* Some callers might want to enforce node */
 	modified_mask |= (gfp_mask & __GFP_THISNODE);
 
+	modified_mask |= (gfp_mask & __GFP_NOWARN);
+
 	return modified_mask;
 }
 
diff --git a/mm/gup.c b/mm/gup.c
index d8a33dd1430d..6c20c6e37635 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1620,10 +1620,12 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 	 * Trying to allocate a page for migration. Ignore allocation
 	 * failure warnings. We don't force __GFP_THISNODE here because
 	 * this node here is the node where we have CMA reservation and
-	 * in some case these nodes will have really less non movable
+	 * in some case these nodes will have really less non CMA
 	 * allocation memory.
+	 *
+	 * Note that CMA region is prohibited by allocation scope.
 	 */
-	gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN;
 
 	if (PageHighMem(page))
 		gfp_mask |= __GFP_HIGHMEM;
@@ -1631,6 +1633,8 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(page);
+
+		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
 		/*
 		 * We don't want to dequeue from the pool because pool pages will
 		 * mostly be from the CMA region.
@@ -1645,11 +1649,6 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 		 */
 		gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
 
-		/*
-		 * Remove the movable mask so that we don't allocate from
-		 * CMA area again.
-		 */
-		thp_gfpmask &= ~__GFP_MOVABLE;
 		thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
 		if (!thp)
 			return NULL;
@@ -1795,7 +1794,6 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 				     vmas_tmp, NULL, gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
-		memalloc_nocma_restore(flags);
 		if (rc < 0)
 			goto out;
 
@@ -1808,9 +1806,10 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 
 		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
 						 vmas_tmp, gup_flags);
+out:
+		memalloc_nocma_restore(flags);
 	}
 
-out:
 	if (vmas_tmp != vmas)
 		kfree(vmas_tmp);
 	return rc;
-- 
cgit v1.2.3


From bbe88753bd42b1faf1458dde8f58ff1239990436 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:38 -0700
Subject: mm/hugetlb: make hugetlb migration callback CMA aware

new_non_cma_page() in gup.c requires to allocate the new page that is not
on the CMA area.  new_non_cma_page() implements it by using allocation
scope APIs.

However, there is a work-around for hugetlb.  Normal hugetlb page
allocation API for migration is alloc_huge_page_nodemask().  It consists
of two steps.  First is dequeing from the pool.  Second is, if there is no
available page on the queue, allocating by using the page allocator.

new_non_cma_page() can't use this API since first step (deque) isn't aware
of scope API to exclude CMA area.  So, new_non_cma_page() exports hugetlb
internal function for the second step, alloc_migrate_huge_page(), to
global scope and uses it directly.  This is suboptimal since hugetlb pages
on the queue cannot be utilized.

This patch tries to fix this situation by making the deque function on
hugetlb CMA aware.  In the deque function, CMA memory is skipped if
PF_MEMALLOC_NOCMA flag is found.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1596180906-8442-2-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 --
 mm/gup.c                |  6 +-----
 mm/hugetlb.c            | 11 +++++++++--
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d86c82749836..d5cc5f802dd4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -511,8 +511,6 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
-				     int nid, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
diff --git a/mm/gup.c b/mm/gup.c
index 6c20c6e37635..c55427beeb26 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1635,11 +1635,7 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 		struct hstate *h = page_hstate(page);
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
-		/*
-		 * We don't want to dequeue from the pool because pool pages will
-		 * mostly be from the CMA region.
-		 */
-		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+		return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask);
 	}
 #endif
 	if (PageTransHuge(page)) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eaab9ef88e9d..a301c2d672bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -19,6 +19,7 @@
 #include <linux/memblock.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
@@ -1040,10 +1041,16 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
+	bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
+
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (nocma && is_migrate_cma_page(page))
+			continue;
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
 		if (!PageHWPoison(page))
 			break;
+	}
+
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
 	 * the allocation fails.
@@ -1935,7 +1942,7 @@ out_unlock:
 	return page;
 }
 
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 				     int nid, nodemask_t *nmask)
 {
 	struct page *page;
-- 
cgit v1.2.3


From bce617edecada007aee8610fbe2c14d10b8de2f6 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:44 -0700
Subject: mm: do page fault accounting in handle_mm_fault

Patch series "mm: Page fault accounting cleanups", v5.

This is v5 of the pf accounting cleanup series.  It originates from Gerald
Schaefer's report on an issue a week ago regarding to incorrect page fault
accountings for retried page fault after commit 4064b9827063 ("mm: allow
VM_FAULT_RETRY for multiple times"):

  https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/

What this series did:

  - Correct page fault accounting: we do accounting for a page fault
    (no matter whether it's from #PF handling, or gup, or anything else)
    only with the one that completed the fault.  For example, page fault
    retries should not be counted in page fault counters.  Same to the
    perf events.

  - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf
    event is used in an adhoc way across different archs.

    Case (1): for many archs it's done at the entry of a page fault
    handler, so that it will also cover e.g.  errornous faults.

    Case (2): for some other archs, it is only accounted when the page
    fault is resolved successfully.

    Case (3): there're still quite some archs that have not enabled
    this perf event.

    Since this series will touch merely all the archs, we unify this
    perf event to always follow case (1), which is the one that makes most
    sense.  And since we moved the accounting into handle_mm_fault, the
    other two MAJ/MIN perf events are well taken care of naturally.

  - Unify definition of "major faults": the definition of "major
    fault" is slightly changed when used in accounting (not
    VM_FAULT_MAJOR).  More information in patch 1.

  - Always account the page fault onto the one that triggered the page
    fault.  This does not matter much for #PF handlings, but mostly for
    gup.  More information on this in patch 25.

Patchset layout:

Patch 1:     Introduced the accounting in handle_mm_fault(), not enabled.
Patch 2-23:  Enable the new accounting for arch #PF handlers one by one.
Patch 24:    Enable the new accounting for the rest outliers (gup, iommu, etc.)
Patch 25:    Cleanup GUP task_struct pointer since it's not needed any more

This patch (of 25):

This is a preparation patch to move page fault accountings into the
general code in handle_mm_fault().  This includes both the per task
flt_maj/flt_min counters, and the major/minor page fault perf events.  To
do this, the pt_regs pointer is passed into handle_mm_fault().

PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault
handlers.

So far, all the pt_regs pointer that passed into handle_mm_fault() is
NULL, which means this patch should have no intented functional change.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com
Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/mm/fault.c         |  2 +-
 arch/arc/mm/fault.c           |  2 +-
 arch/arm/mm/fault.c           |  2 +-
 arch/arm64/mm/fault.c         |  2 +-
 arch/csky/mm/fault.c          |  3 +-
 arch/hexagon/mm/vm_fault.c    |  2 +-
 arch/ia64/mm/fault.c          |  2 +-
 arch/m68k/mm/fault.c          |  2 +-
 arch/microblaze/mm/fault.c    |  2 +-
 arch/mips/mm/fault.c          |  2 +-
 arch/nds32/mm/fault.c         |  2 +-
 arch/nios2/mm/fault.c         |  2 +-
 arch/openrisc/mm/fault.c      |  2 +-
 arch/parisc/mm/fault.c        |  2 +-
 arch/powerpc/mm/copro_fault.c |  2 +-
 arch/powerpc/mm/fault.c       |  2 +-
 arch/riscv/mm/fault.c         |  2 +-
 arch/s390/mm/fault.c          |  2 +-
 arch/sh/mm/fault.c            |  2 +-
 arch/sparc/mm/fault_32.c      |  4 +--
 arch/sparc/mm/fault_64.c      |  2 +-
 arch/um/kernel/trap.c         |  2 +-
 arch/x86/mm/fault.c           |  2 +-
 arch/xtensa/mm/fault.c        |  2 +-
 drivers/iommu/amd/iommu_v2.c  |  2 +-
 drivers/iommu/intel/svm.c     |  3 +-
 include/linux/mm.h            |  7 +++--
 mm/gup.c                      |  4 +--
 mm/hmm.c                      |  3 +-
 mm/ksm.c                      |  3 +-
 mm/memory.c                   | 64 ++++++++++++++++++++++++++++++++++++++++++-
 31 files changed, 103 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index c2303a8c2b9f..1983e43a5e2f 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -148,7 +148,7 @@ retry:
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 7287c793d1c9..587dea524e6b 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -130,7 +130,7 @@ retry:
 		goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c6550eddfce1..01a8e0f8fef7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -224,7 +224,7 @@ good_area:
 		goto out;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, NULL);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 8afb238ff335..be29f4076fe3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -428,7 +428,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, NULL);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index b1dce9f2f04d..b252e6e4d32f 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -150,7 +150,8 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0,
+				NULL);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index cd3808f96b93..f12f330e7946 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -88,7 +88,7 @@ good_area:
 		break;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 3a4dec334cc5..abf2808f9b4b 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -143,7 +143,7 @@ retry:
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 508abb63da67..08b35a318ebe 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -134,7 +134,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
 	if (fault_signal_pending(fault, regs))
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index a2bfe587b491..1a3d4c4ca28b 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -214,7 +214,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 01b168a90434..b1db39784db9 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -152,7 +152,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 8fb73f6401a0..d0ecc8fb5b23 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -206,7 +206,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, NULL);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 4112ef0e247e..86beb9a2698e 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -131,7 +131,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index d2224ccca294..3daa491d1edb 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -159,7 +159,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 66ac0719bd49..e32d06928c24 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -302,7 +302,7 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index b83abbead4a2..2d0276abe0a6 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	}
 
 	ret = 0;
-	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL);
 	if (unlikely(*flt & VM_FAULT_ERROR)) {
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 925a7231abb3..c6a5225a3521 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -511,7 +511,7 @@ retry:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	major |= fault & VM_FAULT_MAJOR;
 
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 5873835a3e6b..30c1124d0fb6 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -109,7 +109,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, NULL);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index aebf9183bedd..ad783aaaf649 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -476,7 +476,7 @@ retry:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	if (fault_signal_pending(fault, regs)) {
 		fault = VM_FAULT_SIGNAL;
 		if (flags & FAULT_FLAG_RETRY_NOWAIT)
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index fbe1f2fe9a8c..3c0a11827f7e 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -482,7 +482,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index cfef656eda0f..06af03db4417 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -234,7 +234,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -410,7 +410,7 @@ good_area:
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(vma, address, flags)) {
+	switch (handle_mm_fault(vma, address, flags, NULL)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index a3806614e4dc..9ebee14ee893 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -422,7 +422,7 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		goto exit_exception;
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 2b3afa354a90..8d9870d76da1 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -71,7 +71,7 @@ good_area:
 	do {
 		vm_fault_t fault;
 
-		fault = handle_mm_fault(vma, address, flags);
+		fault = handle_mm_fault(vma, address, flags, NULL);
 
 		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 			goto out_nosemaphore;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 0c7643d9f7cb..e1bf5555d80a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1291,7 +1291,7 @@ good_area:
 	 * userland). The return to userland is identified whenever
 	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	major |= fault & VM_FAULT_MAJOR;
 
 	/* Quick path to respond to signals */
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index c128dcc7c85b..e72c8c1359a6 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -107,7 +107,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index e4b025c5637c..c259108ab6dd 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -495,7 +495,7 @@ static void do_fault(struct work_struct *work)
 	if (access_error(vma, fault))
 		goto out;
 
-	ret = handle_mm_fault(vma, address, flags);
+	ret = handle_mm_fault(vma, address, flags, NULL);
 out:
 	mmap_read_unlock(mm);
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 6c87c807a0ab..5ae59a6ad681 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -872,7 +872,8 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			goto invalid;
 
 		ret = handle_mm_fault(vma, address,
-				      req->wr_req ? FAULT_FLAG_WRITE : 0);
+				      req->wr_req ? FAULT_FLAG_WRITE : 0,
+				      NULL);
 		if (ret & VM_FAULT_ERROR)
 			goto invalid;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f97b10117d44..ec0ffb423769 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -38,6 +38,7 @@ struct file_ra_state;
 struct user_struct;
 struct writeback_control;
 struct bdi_writeback;
+struct pt_regs;
 
 void init_mm_internals(void);
 
@@ -1658,7 +1659,8 @@ int invalidate_inode_page(struct page *page);
 
 #ifdef CONFIG_MMU
 extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
-			unsigned long address, unsigned int flags);
+				  unsigned long address, unsigned int flags,
+				  struct pt_regs *regs);
 extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
@@ -1668,7 +1670,8 @@ void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
 #else
 static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags)
+					 unsigned long address, unsigned int flags,
+					 struct pt_regs *regs)
 {
 	/* should never happen if there's no MMU */
 	BUG();
diff --git a/mm/gup.c b/mm/gup.c
index e9d1d0cc18f0..ae7121d729fa 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -884,7 +884,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, *flags);
 
@@ -1238,7 +1238,7 @@ retry:
 	    fatal_signal_pending(current))
 		return -EINTR;
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
diff --git a/mm/hmm.c b/mm/hmm.c
index bb279319bf40..943cb2ba4442 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -75,7 +75,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end,
 	}
 
 	for (; addr < end; addr += PAGE_SIZE)
-		if (handle_mm_fault(vma, addr, fault_flags) & VM_FAULT_ERROR)
+		if (handle_mm_fault(vma, addr, fault_flags, NULL) &
+		    VM_FAULT_ERROR)
 			return -EFAULT;
 	return -EBUSY;
 }
diff --git a/mm/ksm.c b/mm/ksm.c
index 217842a66912..0aa2247bddd7 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -480,7 +480,8 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 			break;
 		if (PageKsm(page))
 			ret = handle_mm_fault(vma, addr,
-					FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
+					      FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE,
+					      NULL);
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
diff --git a/mm/memory.c b/mm/memory.c
index 325bb575e7ec..9b7d35734caa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -71,6 +71,8 @@
 #include <linux/dax.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
 
 #include <trace/events/kmem.h>
 
@@ -4356,6 +4358,64 @@ retry_pud:
 	return handle_pte_fault(&vmf);
 }
 
+/**
+ * mm_account_fault - Do page fault accountings
+ *
+ * @regs: the pt_regs struct pointer.  When set to NULL, will skip accounting
+ *        of perf event counters, but we'll still do the per-task accounting to
+ *        the task who triggered this page fault.
+ * @address: the faulted address.
+ * @flags: the fault flags.
+ * @ret: the fault retcode.
+ *
+ * This will take care of most of the page fault accountings.  Meanwhile, it
+ * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
+ * updates.  However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
+ * still be in per-arch page fault handlers at the entry of page fault.
+ */
+static inline void mm_account_fault(struct pt_regs *regs,
+				    unsigned long address, unsigned int flags,
+				    vm_fault_t ret)
+{
+	bool major;
+
+	/*
+	 * We don't do accounting for some specific faults:
+	 *
+	 * - Unsuccessful faults (e.g. when the address wasn't valid).  That
+	 *   includes arch_vma_access_permitted() failing before reaching here.
+	 *   So this is not a "this many hardware page faults" counter.  We
+	 *   should use the hw profiling for that.
+	 *
+	 * - Incomplete faults (VM_FAULT_RETRY).  They will only be counted
+	 *   once they're completed.
+	 */
+	if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY))
+		return;
+
+	/*
+	 * We define the fault as a major fault when the final successful fault
+	 * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
+	 * handle it immediately previously).
+	 */
+	major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
+
+	/*
+	 * If the fault is done for GUP, regs will be NULL, and we will skip
+	 * the fault accounting.
+	 */
+	if (!regs)
+		return;
+
+	if (major) {
+		current->maj_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	} else {
+		current->min_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+	}
+}
+
 /*
  * By the time we get here, we already hold the mm semaphore
  *
@@ -4363,7 +4423,7 @@ retry_pud:
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
-		unsigned int flags)
+			   unsigned int flags, struct pt_regs *regs)
 {
 	vm_fault_t ret;
 
@@ -4404,6 +4464,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 			mem_cgroup_oom_synchronize(false);
 	}
 
+	mm_account_fault(regs, address, flags, ret);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
-- 
cgit v1.2.3


From 64019a2e467a288a16b65ab55ddcbf58c1b00187 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:39:01 -0700
Subject: mm/gup: remove task_struct pointer for all gup code

After the cleanup of page fault accounting, gup does not need to pass
task_struct around any more.  Remove that parameter in the whole gup
stack.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-26-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/kernel/process.c                   |   2 +-
 arch/s390/kvm/interrupt.c                   |   2 +-
 arch/s390/kvm/kvm-s390.c                    |   2 +-
 arch/s390/kvm/priv.c                        |   8 +--
 arch/s390/mm/gmap.c                         |   4 +-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c |   2 +-
 drivers/infiniband/core/umem_odp.c          |   2 +-
 drivers/vfio/vfio_iommu_type1.c             |   4 +-
 fs/exec.c                                   |   2 +-
 include/linux/mm.h                          |   9 ++-
 kernel/events/uprobes.c                     |   6 +-
 kernel/futex.c                              |   2 +-
 mm/gup.c                                    | 101 ++++++++++++----------------
 mm/memory.c                                 |   2 +-
 mm/process_vm_access.c                      |   2 +-
 security/tomoyo/domain.c                    |   2 +-
 virt/kvm/async_pf.c                         |   2 +-
 virt/kvm/kvm_main.c                         |   2 +-
 18 files changed, 69 insertions(+), 87 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index e12c80d71b78..efeba1fe7252 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -91,7 +91,7 @@ fault:
 		 goto fail;
 
 	mmap_read_lock(current->mm);
-	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+	ret = fixup_user_fault(current->mm, (unsigned long) uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(current->mm);
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1608fd99bbee..2f177298c663 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2768,7 +2768,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
 	struct page *page = NULL;
 
 	mmap_read_lock(kvm->mm);
-	get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE,
+	get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE,
 			      &page, NULL, NULL);
 	mmap_read_unlock(kvm->mm);
 	return page;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 66da278a67fb..6b74b92c1a58 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1892,7 +1892,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
 		if (r) {
-			r = fixup_user_fault(current, current->mm, hva,
+			r = fixup_user_fault(current->mm, hva,
 					     FAULT_FLAG_WRITE, &unlocked);
 			if (r)
 				break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 2f721a923b54..cd74989ce0b0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -273,7 +273,7 @@ retry:
 	rc = get_guest_storage_key(current->mm, vmaddr, &key);
 
 	if (rc) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -319,7 +319,7 @@ retry:
 	mmap_read_lock(current->mm);
 	rc = reset_guest_reference_bit(current->mm, vmaddr);
 	if (rc < 0) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -390,7 +390,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 						m3 & SSKE_MC);
 
 		if (rc < 0) {
-			rc = fixup_user_fault(current, current->mm, vmaddr,
+			rc = fixup_user_fault(current->mm, vmaddr,
 					      FAULT_FLAG_WRITE, &unlocked);
 			rc = !rc ? -EAGAIN : rc;
 		}
@@ -1094,7 +1094,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
 			if (rc < 0) {
-				rc = fixup_user_fault(current, current->mm, vmaddr,
+				rc = fixup_user_fault(current->mm, vmaddr,
 						      FAULT_FLAG_WRITE, &unlocked);
 				rc = !rc ? -EAGAIN : rc;
 			}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 190357ff86b3..8747487c50a8 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -649,7 +649,7 @@ retry:
 		rc = vmaddr;
 		goto out_up;
 	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
+	if (fixup_user_fault(gmap->mm, vmaddr, fault_flags,
 			     &unlocked)) {
 		rc = -EFAULT;
 		goto out_up;
@@ -879,7 +879,7 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
 
 	BUG_ON(gmap_is_shadow(gmap));
 	fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
-	if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked))
+	if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked))
 		return -EFAULT;
 	if (unlocked)
 		/* lost mmap_lock, caller has to retry __gmap_translate */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index e946032b13e4..2c2bf24140c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -469,7 +469,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 					locked = 1;
 				}
 				ret = pin_user_pages_remote
-					(work->task, mm,
+					(mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 flags,
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 5e32f61a2fe4..cc6b4befde7c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -439,7 +439,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 		 * complex (and doesn't gain us much performance in most use
 		 * cases).
 		 */
-		npages = get_user_pages_remote(owning_process, owning_mm,
+		npages = get_user_pages_remote(owning_mm,
 				user_virt, gup_num_pages,
 				flags, local_page_list, NULL, NULL);
 		mmap_read_unlock(owning_mm);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5e556ac9102a..9d41105bfd01 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -425,7 +425,7 @@ static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
 	if (ret) {
 		bool unlocked = false;
 
-		ret = fixup_user_fault(NULL, mm, vaddr,
+		ret = fixup_user_fault(mm, vaddr,
 				       FAULT_FLAG_REMOTE |
 				       (write_fault ?  FAULT_FLAG_WRITE : 0),
 				       &unlocked);
@@ -453,7 +453,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	mmap_read_lock(mm);
-	ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+	ret = pin_user_pages_remote(mm, vaddr, 1, flags | FOLL_LONGTERM,
 				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
diff --git a/fs/exec.c b/fs/exec.c
index a57d9785832b..a91003e28eaa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -217,7 +217,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 	 * We are doing an exec().  'current' is the process
 	 * doing the exec and bprm->mm is the new process's mm.
 	 */
-	ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags,
+	ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags,
 			&page, NULL, NULL);
 	if (ret <= 0)
 		return NULL;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ec0ffb423769..e7602a3bcef1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1661,7 +1661,7 @@ int invalidate_inode_page(struct page *page);
 extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 				  unsigned long address, unsigned int flags,
 				  struct pt_regs *regs);
-extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+extern int fixup_user_fault(struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
 void unmap_mapping_pages(struct address_space *mapping,
@@ -1677,8 +1677,7 @@ static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 	BUG();
 	return VM_FAULT_SIGBUS;
 }
-static inline int fixup_user_fault(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long address,
+static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
 		unsigned int fault_flags, bool *unlocked)
 {
 	/* should never happen if there's no MMU */
@@ -1704,11 +1703,11 @@ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, unsigned int gup_flags);
 
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas, int *locked);
-long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 49047d479c57..649fd53dc9ad 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -376,7 +376,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 	if (!vaddr || !d)
 		return -EINVAL;
 
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1,
+	ret = get_user_pages_remote(mm, vaddr, 1,
 			FOLL_WRITE, &page, &vma, NULL);
 	if (unlikely(ret <= 0)) {
 		/*
@@ -477,7 +477,7 @@ retry:
 	if (is_register)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags,
 				    &old_page, &vma, NULL);
 	if (ret <= 0)
 		return ret;
@@ -2029,7 +2029,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page,
 			NULL, NULL);
 	if (result < 0)
 		return result;
diff --git a/kernel/futex.c b/kernel/futex.c
index 83404124b77b..61e8153e6c76 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -678,7 +678,7 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 	int ret;
 
 	mmap_read_lock(mm);
-	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+	ret = fixup_user_fault(mm, (unsigned long)uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(mm);
 
diff --git a/mm/gup.c b/mm/gup.c
index d5d44c68fa19..39e58df6925d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -859,7 +859,7 @@ unmap:
  * does not include FOLL_NOWAIT, the mmap_lock may be released.  If it
  * is, *@locked will be set to 0 and -EBUSY returned.
  */
-static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
+static int faultin_page(struct vm_area_struct *vma,
 		unsigned long address, unsigned int *flags, int *locked)
 {
 	unsigned int fault_flags = 0;
@@ -962,7 +962,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 
 /**
  * __get_user_pages() - pin user pages in memory
- * @tsk:	task_struct of target task
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -1021,7 +1020,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas, int *locked)
@@ -1103,8 +1102,7 @@ retry:
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
 		if (!page) {
-			ret = faultin_page(tsk, vma, start, &foll_flags,
-					   locked);
+			ret = faultin_page(vma, start, &foll_flags, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
@@ -1178,8 +1176,6 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
 
 /**
  * fixup_user_fault() - manually resolve a user page fault
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @address:	user address
  * @fault_flags:flags to pass down to handle_mm_fault()
@@ -1207,7 +1203,7 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
  * This function will not return with an unlocked mmap_lock. So it has not the
  * same semantics wrt the @mm->mmap_lock as does filemap_fault().
  */
-int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+int fixup_user_fault(struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags,
 		     bool *unlocked)
 {
@@ -1256,8 +1252,7 @@ EXPORT_SYMBOL_GPL(fixup_user_fault);
  * Please note that this function, unlike __get_user_pages will not
  * return 0 for nr_pages > 0 without FOLL_NOWAIT
  */
-static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
-						struct mm_struct *mm,
+static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 						unsigned long start,
 						unsigned long nr_pages,
 						struct page **pages,
@@ -1290,7 +1285,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 	pages_done = 0;
 	lock_dropped = false;
 	for (;;) {
-		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+		ret = __get_user_pages(mm, start, nr_pages, flags, pages,
 				       vmas, locked);
 		if (!locked)
 			/* VM_FAULT_RETRY couldn't trigger, bypass */
@@ -1350,7 +1345,7 @@ retry:
 		}
 
 		*locked = 1;
-		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
+		ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
 				       pages, NULL, locked);
 		if (!*locked) {
 			/* Continue to retry until we succeeded */
@@ -1437,7 +1432,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	 * We made sure addr is within a VMA, so the following will
 	 * not result in a stack expansion that recurses back here.
 	 */
-	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
+	return __get_user_pages(mm, start, nr_pages, gup_flags,
 				NULL, NULL, locked);
 }
 
@@ -1521,7 +1516,7 @@ struct page *get_dump_page(unsigned long addr)
 	struct vm_area_struct *vma;
 	struct page *page;
 
-	if (__get_user_pages(current, current->mm, addr, 1,
+	if (__get_user_pages(current->mm, addr, 1,
 			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
 			     NULL) < 1)
 		return NULL;
@@ -1530,8 +1525,7 @@ struct page *get_dump_page(unsigned long addr)
 }
 #endif /* CONFIG_ELF_CORE */
 #else /* CONFIG_MMU */
-static long __get_user_pages_locked(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long start,
+static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 		unsigned long nr_pages, struct page **pages,
 		struct vm_area_struct **vmas, int *locked,
 		unsigned int foll_flags)
@@ -1596,8 +1590,7 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
 }
 
 #ifdef CONFIG_CMA
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
@@ -1675,7 +1668,7 @@ check_again:
 		 * again migrating any new CMA pages which we failed to isolate
 		 * earlier.
 		 */
-		ret = __get_user_pages_locked(tsk, mm, start, nr_pages,
+		ret = __get_user_pages_locked(mm, start, nr_pages,
 						   pages, vmas, NULL,
 						   gup_flags);
 
@@ -1689,8 +1682,7 @@ check_again:
 	return ret;
 }
 #else
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
@@ -1705,8 +1697,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
  * allows us to process the FOLL_LONGTERM flag.
  */
-static long __gup_longterm_locked(struct task_struct *tsk,
-				  struct mm_struct *mm,
+static long __gup_longterm_locked(struct mm_struct *mm,
 				  unsigned long start,
 				  unsigned long nr_pages,
 				  struct page **pages,
@@ -1731,7 +1722,7 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 		flags = memalloc_nocma_save();
 	}
 
-	rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
+	rc = __get_user_pages_locked(mm, start, nr_pages, pages,
 				     vmas_tmp, NULL, gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
@@ -1745,7 +1736,7 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 			goto out;
 		}
 
-		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
+		rc = check_and_migrate_cma_pages(mm, start, rc, pages,
 						 vmas_tmp, gup_flags);
 out:
 		memalloc_nocma_restore(flags);
@@ -1756,22 +1747,20 @@ out:
 	return rc;
 }
 #else /* !CONFIG_FS_DAX && !CONFIG_CMA */
-static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
-						  struct mm_struct *mm,
+static __always_inline long __gup_longterm_locked(struct mm_struct *mm,
 						  unsigned long start,
 						  unsigned long nr_pages,
 						  struct page **pages,
 						  struct vm_area_struct **vmas,
 						  unsigned int flags)
 {
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
 				       NULL, flags);
 }
 #endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
 #ifdef CONFIG_MMU
-static long __get_user_pages_remote(struct task_struct *tsk,
-				    struct mm_struct *mm,
+static long __get_user_pages_remote(struct mm_struct *mm,
 				    unsigned long start, unsigned long nr_pages,
 				    unsigned int gup_flags, struct page **pages,
 				    struct vm_area_struct **vmas, int *locked)
@@ -1790,20 +1779,18 @@ static long __get_user_pages_remote(struct task_struct *tsk,
 		 * This will check the vmas (even if our vmas arg is NULL)
 		 * and return -ENOTSUPP if DAX isn't allowed in this case:
 		 */
-		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+		return __gup_longterm_locked(mm, start, nr_pages, pages,
 					     vmas, gup_flags | FOLL_TOUCH |
 					     FOLL_REMOTE);
 	}
 
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
 				       locked,
 				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
 }
 
 /**
  * get_user_pages_remote() - pin user pages in memory
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -1862,7 +1849,7 @@ static long __get_user_pages_remote(struct task_struct *tsk,
  * should use get_user_pages_remote because it cannot pass
  * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
  */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas, int *locked)
@@ -1874,13 +1861,13 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags,
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
 				       pages, vmas, locked);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
 
 #else /* CONFIG_MMU */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked)
@@ -1888,8 +1875,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 	return 0;
 }
 
-static long __get_user_pages_remote(struct task_struct *tsk,
-				    struct mm_struct *mm,
+static long __get_user_pages_remote(struct mm_struct *mm,
 				    unsigned long start, unsigned long nr_pages,
 				    unsigned int gup_flags, struct page **pages,
 				    struct vm_area_struct **vmas, int *locked)
@@ -1909,11 +1895,10 @@ static long __get_user_pages_remote(struct task_struct *tsk,
  * @vmas:       array of pointers to vmas corresponding to each page.
  *              Or NULL if the caller does not require them.
  *
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's and don't allow
- * passing of a locked parameter.  We also obviously don't pass
- * FOLL_REMOTE in here.
+ * This is the same as get_user_pages_remote(), just with a less-flexible
+ * calling convention where we assume that the mm being operated on belongs to
+ * the current task, and doesn't allow passing of a locked parameter.  We also
+ * obviously don't pass FOLL_REMOTE in here.
  */
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
@@ -1926,7 +1911,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __gup_longterm_locked(current, current->mm, start, nr_pages,
+	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
@@ -1936,7 +1921,7 @@ EXPORT_SYMBOL(get_user_pages);
  *
  *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      get_user_pages(mm, ..., pages, NULL);
  *      mmap_read_unlock(mm);
  *
  *  to:
@@ -1944,7 +1929,7 @@ EXPORT_SYMBOL(get_user_pages);
  *      int locked = 1;
  *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ *      get_user_pages_locked(mm, ..., pages, &locked);
  *      if (locked)
  *          mmap_read_unlock(mm);
  *
@@ -1982,7 +1967,7 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+	return __get_user_pages_locked(current->mm, start, nr_pages,
 				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
@@ -1992,12 +1977,12 @@ EXPORT_SYMBOL(get_user_pages_locked);
  * get_user_pages_unlocked() is suitable to replace the form:
  *
  *      mmap_read_lock(mm);
- *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      get_user_pages(mm, ..., pages, NULL);
  *      mmap_read_unlock(mm);
  *
  *  with:
  *
- *      get_user_pages_unlocked(tsk, mm, ..., pages);
+ *      get_user_pages_unlocked(mm, ..., pages);
  *
  * It is functionally equivalent to get_user_pages_fast so
  * get_user_pages_fast should be used instead if specific gup_flags
@@ -2020,7 +2005,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	mmap_read_lock(mm);
-	ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+	ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
 				      &locked, gup_flags | FOLL_TOUCH);
 	if (locked)
 		mmap_read_unlock(mm);
@@ -2665,7 +2650,7 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
 	 */
 	if (gup_flags & FOLL_LONGTERM) {
 		mmap_read_lock(current->mm);
-		ret = __gup_longterm_locked(current, current->mm,
+		ret = __gup_longterm_locked(current->mm,
 					    start, nr_pages,
 					    pages, NULL, gup_flags);
 		mmap_read_unlock(current->mm);
@@ -2908,10 +2893,8 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages,
 EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
 
 /**
- * pin_user_pages_remote() - pin pages of a remote process (task != current)
+ * pin_user_pages_remote() - pin pages of a remote process
  *
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -2932,7 +2915,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
  */
-long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked)
@@ -2942,7 +2925,7 @@ long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags,
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
 				       pages, vmas, locked);
 }
 EXPORT_SYMBOL(pin_user_pages_remote);
@@ -2974,7 +2957,7 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __gup_longterm_locked(current, current->mm, start, nr_pages,
+	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages);
@@ -3019,7 +3002,7 @@ long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+	return __get_user_pages_locked(current->mm, start, nr_pages,
 				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 2b7f0e00f312..228efaca75d3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4742,7 +4742,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		void *maddr;
 		struct page *page = NULL;
 
-		ret = get_user_pages_remote(tsk, mm, addr, 1,
+		ret = get_user_pages_remote(mm, addr, 1,
 				gup_flags, &page, &vma, NULL);
 		if (ret <= 0) {
 #ifndef CONFIG_HAVE_IOREMAP_PROT
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index cc85ce81914a..29c052099aff 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -105,7 +105,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		 * current/current->mm
 		 */
 		mmap_read_lock(mm);
-		pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages,
+		pinned_pages = pin_user_pages_remote(mm, pa, pinned_pages,
 						     flags, process_pages,
 						     NULL, &locked);
 		if (locked)
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 53b3e1f5f227..dc4ecc0b2038 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -914,7 +914,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
 	 * (represented by bprm).  'current' is the process doing
 	 * the execve().
 	 */
-	if (get_user_pages_remote(current, bprm->mm, pos, 1,
+	if (get_user_pages_remote(bprm->mm, pos, 1,
 				FOLL_FORCE, &page, NULL, NULL) <= 0)
 		return false;
 #else
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 390f758d5a27..dd777688d14a 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -61,7 +61,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * access remotely.
 	 */
 	mmap_read_lock(mm);
-	get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
+	get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, NULL,
 			&locked);
 	if (locked)
 		mmap_read_unlock(mm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2c2c0254c2d8..737666db02de 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1893,7 +1893,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 		 * not call the fault handler, so do it here.
 		 */
 		bool unlocked = false;
-		r = fixup_user_fault(current, current->mm, addr,
+		r = fixup_user_fault(current->mm, addr,
 				     (write_fault ? FAULT_FLAG_WRITE : 0),
 				     &unlocked);
 		if (unlocked)
-- 
cgit v1.2.3


From 2404b73c3f1a5f15726c6ecd226b56f6f992767f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 10 Aug 2020 13:52:15 +0200
Subject: netfilter: avoid ipv6 -> nf_defrag_ipv6 module dependency

nf_ct_frag6_gather is part of nf_defrag_ipv6.ko, not ipv6 core.

The current use of the netfilter ipv6 stub indirections  causes a module
dependency between ipv6 and nf_defrag_ipv6.

This prevents nf_defrag_ipv6 module from being removed because ipv6 can't
be unloaded.

Remove the indirection and always use a direct call.  This creates a
depency from nf_conntrack_bridge to nf_defrag_ipv6 instead:

modinfo nf_conntrack
depends:        nf_conntrack,nf_defrag_ipv6,bridge

.. and nf_conntrack already depends on nf_defrag_ipv6 anyway.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv6.h             | 18 ------------------
 net/bridge/netfilter/nf_conntrack_bridge.c |  8 ++++++--
 net/ipv6/netfilter.c                       |  3 ---
 3 files changed, 6 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index aac42c28fe62..9b67394471e1 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -58,7 +58,6 @@ struct nf_ipv6_ops {
 			int (*output)(struct net *, struct sock *, struct sk_buff *));
 	int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry);
 #if IS_MODULE(CONFIG_IPV6)
-	int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user);
 	int (*br_fragment)(struct net *net, struct sock *sk,
 			   struct sk_buff *skb,
 			   struct nf_bridge_frag_data *data,
@@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst,
 
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 
-static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb,
-				    u32 user)
-{
-#if IS_MODULE(CONFIG_IPV6)
-	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
-	if (!v6_ops)
-		return 1;
-
-	return v6_ops->br_defrag(net, skb, user);
-#elif IS_BUILTIN(CONFIG_IPV6)
-	return nf_ct_frag6_gather(net, skb, user);
-#else
-	return 1;
-#endif
-}
-
 int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		    struct nf_bridge_frag_data *data,
 		    int (*output)(struct net *, struct sock *sk,
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 809673222382..8d033a75a766 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb,
 static unsigned int nf_ct_br_defrag6(struct sk_buff *skb,
 				     const struct nf_hook_state *state)
 {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 	enum ip_conntrack_info ctinfo;
 	struct br_input_skb_cb cb;
@@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb,
 
 	br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm));
 
-	err = nf_ipv6_br_defrag(state->net, skb,
-				IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
+	err = nf_ct_frag6_gather(state->net, skb,
+				 IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
 	/* queued */
 	if (err == -EINPROGRESS)
 		return NF_STOLEN;
 
 	br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size);
 	return err == 0 ? NF_ACCEPT : NF_DROP;
+#else
+	return NF_ACCEPT;
+#endif
 }
 
 static int nf_ct_br_ip_check(const struct sk_buff *skb)
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 409e79b84a83..6d0e942d082d 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = {
 	.route_input		= ip6_route_input,
 	.fragment		= ip6_fragment,
 	.reroute		= nf_ip6_reroute,
-#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-	.br_defrag		= nf_ct_frag6_gather,
-#endif
 #if IS_MODULE(CONFIG_IPV6)
 	.br_fragment		= br_ip6_fragment,
 #endif
-- 
cgit v1.2.3


From 466a62d7642f02f36d37d9b30c19a725538a01ca Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 11 Jun 2020 07:35:33 +0100
Subject: mfd: core: Make a best effort attempt to match devices with the
 correct of_nodes

Currently, when a child platform device (sometimes referred to as a
sub-device) is registered via the Multi-Functional Device (MFD) API,
the framework attempts to match the newly registered platform device
with its associated Device Tree (OF) node.  Until now, the device has
been allocated the first node found with an identical OF compatible
string.  Unfortunately, if there are, say for example '3' devices
which are to be handled by the same driver and therefore have the same
compatible string, each of them will be allocated a pointer to the
*first* node.

An example Device Tree entry might look like this:

  mfd_of_test {
          compatible = "mfd,of-test-parent";
          #address-cells = <0x02>;
          #size-cells = <0x02>;

          child@aaaaaaaaaaaaaaaa {
                  compatible = "mfd,of-test-child";
                  reg = <0xaaaaaaaa 0xaaaaaaaa 0 0x11>,
                        <0xbbbbbbbb 0xbbbbbbbb 0 0x22>;
          };

          child@cccccccc {
                  compatible = "mfd,of-test-child";
                  reg = <0x00000000 0xcccccccc 0 0x33>;
          };

          child@dddddddd00000000 {
                  compatible = "mfd,of-test-child";
                  reg = <0xdddddddd 0x00000000 0 0x44>;
          };
  };

When used with example sub-device registration like this:

  static const struct mfd_cell mfd_of_test_cell[] = {
        OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 0, "mfd,of-test-child"),
        OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child"),
        OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child")
  };

... the current implementation will result in all devices being allocated
the first OF node found containing a matching compatible string:

  [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0
  [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@aaaaaaaaaaaaaaaa
  [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1
  [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa
  [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2
  [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@aaaaaaaaaaaaaaaa

After this patch each device will be allocated a unique OF node:

  [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0
  [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@aaaaaaaaaaaaaaaa
  [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1
  [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@cccccccc
  [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2
  [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@dddddddd00000000

Which is fine if all OF nodes are identical.  However if we wish to
apply an attribute to particular device, we really need to ensure the
correct OF node will be associated with the device containing the
correct address.  We accomplish this by matching the device's address
expressed in DT with one provided during sub-device registration.
Like this:

  static const struct mfd_cell mfd_of_test_cell[] = {
        OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child", 0xdddddddd00000000),
        OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child", 0xaaaaaaaaaaaaaaaa),
        OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 3, "mfd,of-test-child", 0x00000000cccccccc)
  };

This will ensure a specific device (designated here using the
platform_ids; 1, 2 and 3) is matched with a particular OF node:

  [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0
  [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@dddddddd00000000
  [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1
  [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa
  [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2
  [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@cccccccc

This implementation is still not infallible, hence the mention of
"best effort" in the commit subject.  Since we have not *insisted* on
the existence of 'reg' properties (in some scenarios they just do not
make sense) and no device currently uses the new 'of_reg' attribute,
we have to make an on-the-fly judgement call whether to associate the
OF node anyway.  Which we do in cases where parent drivers haven't
specified a particular OF node to match to.  So there is a *slight*
possibility of the following result (note: the implementation here is
convoluted, but it shows you one means by which this process can
still break):

  /*
   * First entry will match to the first OF node with matching compatible
   * Second will fail, since the first took its OF node and is no longer available
   * Third will succeed
   */
  static const struct mfd_cell mfd_of_test_cell[] = {
        OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child"),
	OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child", 0xaaaaaaaaaaaaaaaa),
        OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 3, "mfd,of-test-child", 0x00000000cccccccc)
  };

The result:

  [0.753869] mfd-of-test-parent mfd_of_test: Registering 3 devices
  [0.756597] mfd-of-test-child: Failed to locate of_node [id: 2]
  [0.759999] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1
  [0.760314] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa
  [0.760908] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2
  [0.761183] mfd-of-test-child mfd-of-test-child.2: No OF node associated with this device
  [0.761621] mfd-of-test-child mfd-of-test-child.3: Probing platform device: 3
  [0.761899] mfd-of-test-child mfd-of-test-child.3: Using OF node: child@cccccccc

We could code around this with some pre-parsing semantics, but the
added complexity required to cover each and every corner-case is not
justified.  Merely patching the current failing (via this patch) is
already working with some pretty small corner-cases.  Other issues
should be patched in the parent drivers which can be achieved simply
by implementing OF_MFD_CELL_REG().

Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/mfd-core.c   | 95 ++++++++++++++++++++++++++++++++++++++++++------
 include/linux/mfd/core.h | 10 +++++
 2 files changed, 93 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 720e5c8b1588..b201842f82ad 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
+#include <linux/list.h>
 #include <linux/property.h>
 #include <linux/mfd/core.h>
 #include <linux/pm_runtime.h>
@@ -17,8 +18,17 @@
 #include <linux/module.h>
 #include <linux/irqdomain.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/regulator/consumer.h>
 
+static LIST_HEAD(mfd_of_node_list);
+
+struct mfd_of_node_entry {
+	struct list_head list;
+	struct device *dev;
+	struct device_node *np;
+};
+
 static struct device_type mfd_dev_type = {
 	.name	= "mfd_device",
 };
@@ -107,6 +117,55 @@ static inline void mfd_acpi_add_device(const struct mfd_cell *cell,
 }
 #endif
 
+static int mfd_match_of_node_to_dev(struct platform_device *pdev,
+				    struct device_node *np,
+				    const struct mfd_cell *cell)
+{
+#if IS_ENABLED(CONFIG_OF)
+	struct mfd_of_node_entry *of_entry;
+	const __be32 *reg;
+	u64 of_node_addr;
+
+	/* Skip devices 'disabled' by Device Tree */
+	if (!of_device_is_available(np))
+		return -ENODEV;
+
+	/* Skip if OF node has previously been allocated to a device */
+	list_for_each_entry(of_entry, &mfd_of_node_list, list)
+		if (of_entry->np == np)
+			return -EAGAIN;
+
+	if (!cell->use_of_reg)
+		/* No of_reg defined - allocate first free compatible match */
+		goto allocate_of_node;
+
+	/* We only care about each node's first defined address */
+	reg = of_get_address(np, 0, NULL, NULL);
+	if (!reg)
+		/* OF node does not contatin a 'reg' property to match to */
+		return -EAGAIN;
+
+	of_node_addr = of_read_number(reg, of_n_addr_cells(np));
+
+	if (cell->of_reg != of_node_addr)
+		/* No match */
+		return -EAGAIN;
+
+allocate_of_node:
+	of_entry = kzalloc(sizeof(*of_entry), GFP_KERNEL);
+	if (!of_entry)
+		return -ENOMEM;
+
+	of_entry->dev = &pdev->dev;
+	of_entry->np = np;
+	list_add_tail(&of_entry->list, &mfd_of_node_list);
+
+	pdev->dev.of_node = np;
+	pdev->dev.fwnode = &np->fwnode;
+#endif
+	return 0;
+}
+
 static int mfd_add_device(struct device *parent, int id,
 			  const struct mfd_cell *cell,
 			  struct resource *mem_base,
@@ -115,6 +174,7 @@ static int mfd_add_device(struct device *parent, int id,
 	struct resource *res;
 	struct platform_device *pdev;
 	struct device_node *np = NULL;
+	struct mfd_of_node_entry *of_entry, *tmp;
 	int ret = -ENOMEM;
 	int platform_id;
 	int r;
@@ -149,19 +209,22 @@ static int mfd_add_device(struct device *parent, int id,
 	if (ret < 0)
 		goto fail_res;
 
-	if (parent->of_node && cell->of_compatible) {
+	if (IS_ENABLED(CONFIG_OF) && parent->of_node && cell->of_compatible) {
 		for_each_child_of_node(parent->of_node, np) {
 			if (of_device_is_compatible(np, cell->of_compatible)) {
-				if (!of_device_is_available(np)) {
-					/* Ignore disabled devices error free */
-					ret = 0;
+				ret = mfd_match_of_node_to_dev(pdev, np, cell);
+				if (ret == -EAGAIN)
+					continue;
+				if (ret)
 					goto fail_alias;
-				}
-				pdev->dev.of_node = np;
-				pdev->dev.fwnode = &np->fwnode;
+
 				break;
 			}
 		}
+
+		if (!pdev->dev.of_node)
+			pr_warn("%s: Failed to locate of_node [id: %d]\n",
+				cell->name, platform_id);
 	}
 
 	mfd_acpi_add_device(cell, pdev);
@@ -170,13 +233,13 @@ static int mfd_add_device(struct device *parent, int id,
 		ret = platform_device_add_data(pdev,
 					cell->platform_data, cell->pdata_size);
 		if (ret)
-			goto fail_alias;
+			goto fail_of_entry;
 	}
 
 	if (cell->properties) {
 		ret = platform_device_add_properties(pdev, cell->properties);
 		if (ret)
-			goto fail_alias;
+			goto fail_of_entry;
 	}
 
 	for (r = 0; r < cell->num_resources; r++) {
@@ -213,18 +276,18 @@ static int mfd_add_device(struct device *parent, int id,
 			if (has_acpi_companion(&pdev->dev)) {
 				ret = acpi_check_resource_conflict(&res[r]);
 				if (ret)
-					goto fail_alias;
+					goto fail_of_entry;
 			}
 		}
 	}
 
 	ret = platform_device_add_resources(pdev, res, cell->num_resources);
 	if (ret)
-		goto fail_alias;
+		goto fail_of_entry;
 
 	ret = platform_device_add(pdev);
 	if (ret)
-		goto fail_alias;
+		goto fail_of_entry;
 
 	if (cell->pm_runtime_no_callbacks)
 		pm_runtime_no_callbacks(&pdev->dev);
@@ -233,6 +296,12 @@ static int mfd_add_device(struct device *parent, int id,
 
 	return 0;
 
+fail_of_entry:
+	list_for_each_entry_safe(of_entry, tmp, &mfd_of_node_list, list)
+		if (of_entry->dev == &pdev->dev) {
+			list_del(&of_entry->list);
+			kfree(of_entry);
+		}
 fail_alias:
 	regulator_bulk_unregister_supply_alias(&pdev->dev,
 					       cell->parent_supplies,
@@ -297,6 +366,8 @@ static int mfd_remove_devices_fn(struct device *dev, void *data)
 	regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies,
 					       cell->num_parent_supplies);
 
+	kfree(cell);
+
 	platform_device_unregister(pdev);
 	return 0;
 }
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index ab76cdd06199..c437a73b43a3 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -78,6 +78,16 @@ struct mfd_cell {
 	 */
 	const char		*of_compatible;
 
+	/*
+	 * Address as defined in Device Tree.  Used to compement 'of_compatible'
+	 * (above) when matching OF nodes with devices that have identical
+	 * compatible strings
+	 */
+	const u64 of_reg;
+
+	/* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */
+	bool use_of_reg;
+
 	/* Matches ACPI */
 	const struct mfd_cell_acpi_match	*acpi_match;
 
-- 
cgit v1.2.3


From d097965bb6682afe1f8481923b16c033f708923b Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 11 Jun 2020 10:18:43 +0100
Subject: mfd: core: Fix formatting of MFD helpers

Remove unnecessary '\'s and leading tabs.

This will help to clean-up future diffs when subsequent changes are
made.

Hint: The aforementioned changes follow this patch.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/core.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index c437a73b43a3..da9b066e1594 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -26,20 +26,20 @@
 		.id = (_id),						\
 	}
 
-#define OF_MFD_CELL(_name, _res, _pdata, _pdsize,_id, _compat)		\
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL)	\
+#define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL)
 
-#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match)	\
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match)	\
+#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match)
 
-#define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id)		\
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL)	\
+#define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL)
 
-#define MFD_CELL_RES(_name, _res)					\
-	MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL)		\
+#define MFD_CELL_RES(_name, _res) \
+	MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL)
 
-#define MFD_CELL_NAME(_name)						\
-	MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL)		\
+#define MFD_CELL_NAME(_name) \
+	MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL)
 
 struct irq_domain;
 struct property_entry;
-- 
cgit v1.2.3


From 44e6171ed04a0cd0378e2503f03a444ebdd4e8e3 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 11 Jun 2020 10:12:05 +0100
Subject: mfd: core: Add OF_MFD_CELL_REG() helper

Extend current list of helpers to provide support for parent drivers
wishing to match specific child devices to particular OF nodes.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/core.h | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index da9b066e1594..6d68f44a26a1 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -14,7 +14,7 @@
 
 #define MFD_RES_SIZE(arr) (sizeof(arr) / sizeof(struct resource))
 
-#define MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _match)\
+#define MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, _use_of_reg, _match) \
 	{								\
 		.name = (_name),					\
 		.resources = (_res),					\
@@ -22,24 +22,29 @@
 		.platform_data = (_pdata),				\
 		.pdata_size = (_pdsize),				\
 		.of_compatible = (_compat),				\
+		.of_reg = (_of_reg),					\
+		.use_of_reg = (_use_of_reg),				\
 		.acpi_match = (_match),					\
 		.id = (_id),						\
 	}
 
+#define OF_MFD_CELL_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, true, NULL)
+
 #define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL)
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, 0, false, NULL)
 
 #define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match)
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, _match)
 
 #define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \
-	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL)
+	MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, NULL)
 
 #define MFD_CELL_RES(_name, _res) \
-	MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL)
+	MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, 0, false, NULL)
 
 #define MFD_CELL_NAME(_name) \
-	MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL)
+	MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, 0, false, NULL)
 
 struct irq_domain;
 struct property_entry;
-- 
cgit v1.2.3


From 7d2594cd1fa0b03b2746ce811926ee150a3a14fa Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Wed, 1 Jul 2020 23:23:48 +0200
Subject: mfd: smsc-ece1099: Remove driver

This MFD driver has no user. The keypad driver of this device never made
it into the kernel. Therefore, this driver is useless. Remove it.

Signed-off-by: Michael Walle <michael@walle.cc>
Cc: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 Documentation/driver-api/index.rst        |   1 -
 Documentation/driver-api/smsc_ece1099.rst |  60 -----------------
 drivers/mfd/Kconfig                       |  12 ----
 drivers/mfd/Makefile                      |   1 -
 drivers/mfd/smsc-ece1099.c                |  87 -------------------------
 include/linux/mfd/smsc.h                  | 104 ------------------------------
 6 files changed, 265 deletions(-)
 delete mode 100644 Documentation/driver-api/smsc_ece1099.rst
 delete mode 100644 drivers/mfd/smsc-ece1099.c
 delete mode 100644 include/linux/mfd/smsc.h

(limited to 'include/linux')

diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 6567187e7687..1397a30188eb 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -98,7 +98,6 @@ available subsections can be seen below.
    rfkill
    serial/index
    sm501
-   smsc_ece1099
    switchtec
    sync_file
    vfio-mediated-device
diff --git a/Documentation/driver-api/smsc_ece1099.rst b/Documentation/driver-api/smsc_ece1099.rst
deleted file mode 100644
index 079277421eaf..000000000000
--- a/Documentation/driver-api/smsc_ece1099.rst
+++ /dev/null
@@ -1,60 +0,0 @@
-=================================================
-Msc Keyboard Scan Expansion/GPIO Expansion device
-=================================================
-
-What is smsc-ece1099?
-----------------------
-
-The ECE1099 is a 40-Pin 3.3V Keyboard Scan Expansion
-or GPIO Expansion device. The device supports a keyboard
-scan matrix of 23x8. The device is connected to a Master
-via the SMSC BC-Link interface or via the SMBus.
-Keypad scan Input(KSI) and Keypad Scan Output(KSO) signals
-are multiplexed with GPIOs.
-
-Interrupt generation
---------------------
-
-Interrupts can be generated by an edge detection on a GPIO
-pin or an edge detection on one of the bus interface pins.
-Interrupts can also be detected on the keyboard scan interface.
-The bus interrupt pin (BC_INT# or SMBUS_INT#) is asserted if
-any bit in one of the Interrupt Status registers is 1 and
-the corresponding Interrupt Mask bit is also 1.
-
-In order for software to determine which device is the source
-of an interrupt, it should first read the Group Interrupt Status Register
-to determine which Status register group is a source for the interrupt.
-Software should read both the Status register and the associated Mask register,
-then AND the two values together. Bits that are 1 in the result of the AND
-are active interrupts. Software clears an interrupt by writing a 1 to the
-corresponding bit in the Status register.
-
-Communication Protocol
-----------------------
-
-- SMbus slave Interface
-	The host processor communicates with the ECE1099 device
-	through a series of read/write registers via the SMBus
-	interface. SMBus is a serial communication protocol between
-	a computer host and its peripheral devices. The SMBus data
-	rate is 10KHz minimum to 400 KHz maximum
-
-- Slave Bus Interface
-	The ECE1099 device SMBus implementation is a subset of the
-	SMBus interface to the host. The device is a slave-only SMBus device.
-	The implementation in the device is a subset of SMBus since it
-	only supports four protocols.
-
-	The Write Byte, Read Byte, Send Byte, and Receive Byte protocols are the
-	only valid SMBus protocols for the device.
-
-- BC-LinkTM Interface
-	The BC-Link is a proprietary bus that allows communication
-	between a Master device and a Companion device. The Master
-	device uses this serial bus to read and write registers
-	located on the Companion device. The bus comprises three signals,
-	BC_CLK, BC_DAT and BC_INT#. The Master device always provides the
-	clock, BC_CLK, and the Companion device is the source for an
-	independent asynchronous interrupt signal, BC_INT#. The ECE1099
-	supports BC-Link speeds up to 24MHz.
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d13bb0abfd6f..33df0837ab41 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1193,18 +1193,6 @@ config MFD_SKY81452
 	  This driver can also be built as a module.  If so, the module
 	  will be called sky81452.
 
-config MFD_SMSC
-	bool "SMSC ECE1099 series chips"
-	depends on I2C=y
-	select MFD_CORE
-	select REGMAP_I2C
-	help
-	  If you say yes here you get support for the
-	  ece1099 chips from SMSC.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called smsc.
-
 config MFD_SC27XX_PMIC
 	tristate "Spreadtrum SC27xx PMICs"
 	depends on ARCH_SPRD || COMPILE_TEST
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 1c8d6be3347d..a60e5f835283 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -127,7 +127,6 @@ obj-$(CONFIG_MFD_CPCAP)		+= motorola-cpcap.o
 obj-$(CONFIG_MCP)		+= mcp-core.o
 obj-$(CONFIG_MCP_SA11X0)	+= mcp-sa11x0.o
 obj-$(CONFIG_MCP_UCB1200)	+= ucb1x00-core.o
-obj-$(CONFIG_MFD_SMSC)        += smsc-ece1099.o
 obj-$(CONFIG_MCP_UCB1200_TS)	+= ucb1x00-ts.o
 
 ifeq ($(CONFIG_SA1100_ASSABET),y)
diff --git a/drivers/mfd/smsc-ece1099.c b/drivers/mfd/smsc-ece1099.c
deleted file mode 100644
index 57b792eb58fd..000000000000
--- a/drivers/mfd/smsc-ece1099.c
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * TI SMSC MFD Driver
- *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
- *
- * Author: Sourav Poddar <sourav.poddar@ti.com>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  GPL v2.
- *
- */
-
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/i2c.h>
-#include <linux/gpio.h>
-#include <linux/workqueue.h>
-#include <linux/irq.h>
-#include <linux/regmap.h>
-#include <linux/err.h>
-#include <linux/mfd/core.h>
-#include <linux/mfd/smsc.h>
-#include <linux/of_platform.h>
-
-static const struct regmap_config smsc_regmap_config = {
-		.reg_bits = 8,
-		.val_bits = 8,
-		.max_register = SMSC_VEN_ID_H,
-		.cache_type = REGCACHE_RBTREE,
-};
-
-static int smsc_i2c_probe(struct i2c_client *i2c,
-			const struct i2c_device_id *id)
-{
-	struct smsc *smsc;
-	int devid, rev, venid_l, venid_h;
-	int ret;
-
-	smsc = devm_kzalloc(&i2c->dev, sizeof(*smsc), GFP_KERNEL);
-	if (!smsc)
-		return -ENOMEM;
-
-	smsc->regmap = devm_regmap_init_i2c(i2c, &smsc_regmap_config);
-	if (IS_ERR(smsc->regmap))
-		return PTR_ERR(smsc->regmap);
-
-	i2c_set_clientdata(i2c, smsc);
-	smsc->dev = &i2c->dev;
-
-#ifdef CONFIG_OF
-	of_property_read_u32(i2c->dev.of_node, "clock", &smsc->clk);
-#endif
-
-	regmap_read(smsc->regmap, SMSC_DEV_ID, &devid);
-	regmap_read(smsc->regmap, SMSC_DEV_REV, &rev);
-	regmap_read(smsc->regmap, SMSC_VEN_ID_L, &venid_l);
-	regmap_read(smsc->regmap, SMSC_VEN_ID_H, &venid_h);
-
-	dev_info(&i2c->dev, "SMSCxxx devid: %02x rev: %02x venid: %02x\n",
-		devid, rev, (venid_h << 8) | venid_l);
-
-	ret = regmap_write(smsc->regmap, SMSC_CLK_CTRL, smsc->clk);
-	if (ret)
-		return ret;
-
-#ifdef CONFIG_OF
-	if (i2c->dev.of_node)
-		ret = devm_of_platform_populate(&i2c->dev);
-#endif
-
-	return ret;
-}
-
-static const struct i2c_device_id smsc_i2c_id[] = {
-	{ "smscece1099", 0},
-	{},
-};
-
-static struct i2c_driver smsc_i2c_driver = {
-	.driver = {
-		   .name = "smsc",
-	},
-	.probe = smsc_i2c_probe,
-	.id_table = smsc_i2c_id,
-};
-builtin_i2c_driver(smsc_i2c_driver);
diff --git a/include/linux/mfd/smsc.h b/include/linux/mfd/smsc.h
deleted file mode 100644
index 83944124e886..000000000000
--- a/include/linux/mfd/smsc.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * SMSC ECE1099
- *
- * Copyright 2012 Texas Instruments Inc.
- *
- * Author: Sourav Poddar <sourav.poddar@ti.com>
- */
-
-#ifndef __LINUX_MFD_SMSC_H
-#define __LINUX_MFD_SMSC_H
-
-#include <linux/regmap.h>
-
-#define SMSC_ID_ECE1099			1
-#define SMSC_NUM_CLIENTS		2
-
-#define SMSC_BASE_ADDR			0x38
-#define OMAP_GPIO_SMSC_IRQ		151
-
-#define SMSC_MAXGPIO         32
-#define SMSC_BANK(offs)      ((offs) >> 3)
-#define SMSC_BIT(offs)       (1u << ((offs) & 0x7))
-
-struct smsc {
-	struct device *dev;
-	struct i2c_client *i2c_clients[SMSC_NUM_CLIENTS];
-	struct regmap *regmap;
-	int clk;
-	/* Stored chip id */
-	int id;
-};
-
-struct smsc_gpio;
-struct smsc_keypad;
-
-static inline int smsc_read(struct device *child, unsigned int reg,
-	unsigned int *dest)
-{
-	struct smsc     *smsc = dev_get_drvdata(child->parent);
-
-	return regmap_read(smsc->regmap, reg, dest);
-}
-
-static inline int smsc_write(struct device *child, unsigned int reg,
-	unsigned int value)
-{
-	struct smsc     *smsc = dev_get_drvdata(child->parent);
-
-	return regmap_write(smsc->regmap, reg, value);
-}
-
-/* Registers for SMSC */
-#define SMSC_RESET						0xF5
-#define SMSC_GRP_INT						0xF9
-#define SMSC_CLK_CTRL						0xFA
-#define SMSC_WKUP_CTRL						0xFB
-#define SMSC_DEV_ID						0xFC
-#define SMSC_DEV_REV						0xFD
-#define SMSC_VEN_ID_L						0xFE
-#define SMSC_VEN_ID_H						0xFF
-
-/* CLK VALUE */
-#define SMSC_CLK_VALUE						0x13
-
-/* Registers for function GPIO INPUT */
-#define SMSC_GPIO_DATA_IN_START					0x00
-
-/* Registers for function GPIO OUPUT */
-#define SMSC_GPIO_DATA_OUT_START                                       0x05
-
-/* Definitions for SMSC GPIO CONFIGURATION REGISTER*/
-#define SMSC_GPIO_INPUT_LOW					0x01
-#define SMSC_GPIO_INPUT_RISING					0x09
-#define SMSC_GPIO_INPUT_FALLING					0x11
-#define SMSC_GPIO_INPUT_BOTH_EDGE				0x19
-#define SMSC_GPIO_OUTPUT_PP					0x21
-#define SMSC_GPIO_OUTPUT_OP					0x31
-
-#define GRP_INT_STAT						0xf9
-#define	SMSC_GPI_INT						0x0f
-#define SMSC_CFG_START						0x0A
-
-/* Registers for SMSC GPIO INTERRUPT STATUS REGISTER*/
-#define SMSC_GPIO_INT_STAT_START                                  0x32
-
-/* Registers for SMSC GPIO INTERRUPT MASK REGISTER*/
-#define SMSC_GPIO_INT_MASK_START                               0x37
-
-/* Registers for SMSC function KEYPAD*/
-#define SMSC_KP_OUT						0x40
-#define SMSC_KP_IN						0x41
-#define SMSC_KP_INT_STAT					0x42
-#define SMSC_KP_INT_MASK					0x43
-
-/* Definitions for keypad */
-#define SMSC_KP_KSO           0x70
-#define SMSC_KP_KSI           0x51
-#define SMSC_KSO_ALL_LOW        0x20
-#define SMSC_KP_SET_LOW_PWR        0x0B
-#define SMSC_KP_SET_HIGH           0xFF
-#define SMSC_KSO_EVAL           0x00
-
-#endif /*  __LINUX_MFD_SMSC_H */
-- 
cgit v1.2.3


From 091c6110862bce4e2380e353cb062dcb6a56bcb6 Mon Sep 17 00:00:00 2001
From: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Date: Mon, 13 Jul 2020 10:38:57 +0100
Subject: mfd: da9063: Fix revision handling to correctly select reg tables

The current implementation performs checking in the i2c_probe()
function of the variant_code but does this immediately after the
containing struct has been initialised as all zero. This means the
check for variant code will always default to using the BB tables
and will never select AD. The variant code is subsequently set
by device_init() and later used by the RTC so really it's a little
fortunate this mismatch works.

This update adds raw I2C read access functionality to read the chip
and variant/revision information (common to all revisions) so that
it can subsequently correctly choose the proper regmap tables for
real initialisation.

Signed-off-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/da9063-core.c            |  31 ------
 drivers/mfd/da9063-i2c.c             | 184 +++++++++++++++++++++++++++++++----
 include/linux/mfd/da9063/registers.h |  15 ++-
 3 files changed, 177 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/da9063-core.c b/drivers/mfd/da9063-core.c
index b125f90dd375..a353d52210a9 100644
--- a/drivers/mfd/da9063-core.c
+++ b/drivers/mfd/da9063-core.c
@@ -160,7 +160,6 @@ static int da9063_clear_fault_log(struct da9063 *da9063)
 
 int da9063_device_init(struct da9063 *da9063, unsigned int irq)
 {
-	int model, variant_id, variant_code;
 	int ret;
 
 	ret = da9063_clear_fault_log(da9063);
@@ -171,36 +170,6 @@ int da9063_device_init(struct da9063 *da9063, unsigned int irq)
 	da9063->irq_base = -1;
 	da9063->chip_irq = irq;
 
-	ret = regmap_read(da9063->regmap, DA9063_REG_CHIP_ID, &model);
-	if (ret < 0) {
-		dev_err(da9063->dev, "Cannot read chip model id.\n");
-		return -EIO;
-	}
-	if (model != PMIC_CHIP_ID_DA9063) {
-		dev_err(da9063->dev, "Invalid chip model id: 0x%02x\n", model);
-		return -ENODEV;
-	}
-
-	ret = regmap_read(da9063->regmap, DA9063_REG_CHIP_VARIANT, &variant_id);
-	if (ret < 0) {
-		dev_err(da9063->dev, "Cannot read chip variant id.\n");
-		return -EIO;
-	}
-
-	variant_code = variant_id >> DA9063_CHIP_VARIANT_SHIFT;
-
-	dev_info(da9063->dev,
-		 "Device detected (chip-ID: 0x%02X, var-ID: 0x%02X)\n",
-		 model, variant_id);
-
-	if (variant_code < PMIC_DA9063_BB && variant_code != PMIC_DA9063_AD) {
-		dev_err(da9063->dev,
-			"Cannot support variant code: 0x%02X\n", variant_code);
-		return -ENODEV;
-	}
-
-	da9063->variant_code = variant_code;
-
 	ret = da9063_irq_init(da9063);
 	if (ret) {
 		dev_err(da9063->dev, "Cannot initialize interrupts.\n");
diff --git a/drivers/mfd/da9063-i2c.c b/drivers/mfd/da9063-i2c.c
index 455de74c0dd2..481548948bc0 100644
--- a/drivers/mfd/da9063-i2c.c
+++ b/drivers/mfd/da9063-i2c.c
@@ -22,12 +22,124 @@
 #include <linux/of.h>
 #include <linux/regulator/of_regulator.h>
 
+/*
+ * Raw I2C access required for just accessing chip and variant info before we
+ * know which device is present. The info read from the device using this
+ * approach is then used to select the correct regmap tables.
+ */
+
+#define DA9063_REG_PAGE_SIZE		0x100
+#define DA9063_REG_PAGED_ADDR_MASK	0xFF
+
+enum da9063_page_sel_buf_fmt {
+	DA9063_PAGE_SEL_BUF_PAGE_REG = 0,
+	DA9063_PAGE_SEL_BUF_PAGE_VAL,
+	DA9063_PAGE_SEL_BUF_SIZE,
+};
+
+enum da9063_paged_read_msgs {
+	DA9063_PAGED_READ_MSG_PAGE_SEL = 0,
+	DA9063_PAGED_READ_MSG_REG_SEL,
+	DA9063_PAGED_READ_MSG_DATA,
+	DA9063_PAGED_READ_MSG_CNT,
+};
+
+static int da9063_i2c_blockreg_read(struct i2c_client *client, u16 addr,
+				    u8 *buf, int count)
+{
+	struct i2c_msg xfer[DA9063_PAGED_READ_MSG_CNT];
+	u8 page_sel_buf[DA9063_PAGE_SEL_BUF_SIZE];
+	u8 page_num, paged_addr;
+	int ret;
+
+	/* Determine page info based on register address */
+	page_num = (addr / DA9063_REG_PAGE_SIZE);
+	if (page_num > 1) {
+		dev_err(&client->dev, "Invalid register address provided\n");
+		return -EINVAL;
+	}
+
+	paged_addr = (addr % DA9063_REG_PAGE_SIZE) & DA9063_REG_PAGED_ADDR_MASK;
+	page_sel_buf[DA9063_PAGE_SEL_BUF_PAGE_REG] = DA9063_REG_PAGE_CON;
+	page_sel_buf[DA9063_PAGE_SEL_BUF_PAGE_VAL] =
+		(page_num << DA9063_I2C_PAGE_SEL_SHIFT) & DA9063_REG_PAGE_MASK;
+
+	/* Write reg address, page selection */
+	xfer[DA9063_PAGED_READ_MSG_PAGE_SEL].addr = client->addr;
+	xfer[DA9063_PAGED_READ_MSG_PAGE_SEL].flags = 0;
+	xfer[DA9063_PAGED_READ_MSG_PAGE_SEL].len = DA9063_PAGE_SEL_BUF_SIZE;
+	xfer[DA9063_PAGED_READ_MSG_PAGE_SEL].buf = page_sel_buf;
+
+	/* Select register address */
+	xfer[DA9063_PAGED_READ_MSG_REG_SEL].addr = client->addr;
+	xfer[DA9063_PAGED_READ_MSG_REG_SEL].flags = 0;
+	xfer[DA9063_PAGED_READ_MSG_REG_SEL].len = sizeof(paged_addr);
+	xfer[DA9063_PAGED_READ_MSG_REG_SEL].buf = &paged_addr;
+
+	/* Read data */
+	xfer[DA9063_PAGED_READ_MSG_DATA].addr = client->addr;
+	xfer[DA9063_PAGED_READ_MSG_DATA].flags = I2C_M_RD;
+	xfer[DA9063_PAGED_READ_MSG_DATA].len = count;
+	xfer[DA9063_PAGED_READ_MSG_DATA].buf = buf;
+
+	ret = i2c_transfer(client->adapter, xfer, DA9063_PAGED_READ_MSG_CNT);
+	if (ret < 0) {
+		dev_err(&client->dev, "Paged block read failed: %d\n", ret);
+		return ret;
+	}
+
+	if (ret != DA9063_PAGED_READ_MSG_CNT) {
+		dev_err(&client->dev, "Paged block read failed to complete\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+enum {
+	DA9063_DEV_ID_REG = 0,
+	DA9063_VAR_ID_REG,
+	DA9063_CHIP_ID_REGS,
+};
+
+static int da9063_get_device_type(struct i2c_client *i2c, struct da9063 *da9063)
+{
+	u8 buf[DA9063_CHIP_ID_REGS];
+	int ret;
+
+	ret = da9063_i2c_blockreg_read(i2c, DA9063_REG_DEVICE_ID, buf,
+				       DA9063_CHIP_ID_REGS);
+	if (ret)
+		return ret;
+
+	if (buf[DA9063_DEV_ID_REG] != PMIC_CHIP_ID_DA9063) {
+		dev_err(da9063->dev,
+			"Invalid chip device ID: 0x%02x\n",
+			buf[DA9063_DEV_ID_REG]);
+		return -ENODEV;
+	}
+
+	dev_info(da9063->dev,
+		 "Device detected (chip-ID: 0x%02X, var-ID: 0x%02X)\n",
+		 buf[DA9063_DEV_ID_REG], buf[DA9063_VAR_ID_REG]);
+
+	da9063->variant_code =
+		(buf[DA9063_VAR_ID_REG] & DA9063_VARIANT_ID_MRC_MASK)
+		>> DA9063_VARIANT_ID_MRC_SHIFT;
+
+	return 0;
+}
+
+/*
+ * Variant specific regmap configs
+ */
+
 static const struct regmap_range da9063_ad_readable_ranges[] = {
 	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_AD_REG_SECOND_D),
 	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
 	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
 	regmap_reg_range(DA9063_REG_T_OFFSET, DA9063_AD_REG_GP_ID_19),
-	regmap_reg_range(DA9063_REG_CHIP_ID, DA9063_REG_CHIP_VARIANT),
+	regmap_reg_range(DA9063_REG_DEVICE_ID, DA9063_REG_VARIANT_ID),
 };
 
 static const struct regmap_range da9063_ad_writeable_ranges[] = {
@@ -72,7 +184,7 @@ static const struct regmap_range da9063_bb_readable_ranges[] = {
 	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
 	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
 	regmap_reg_range(DA9063_REG_T_OFFSET, DA9063_BB_REG_GP_ID_19),
-	regmap_reg_range(DA9063_REG_CHIP_ID, DA9063_REG_CHIP_VARIANT),
+	regmap_reg_range(DA9063_REG_DEVICE_ID, DA9063_REG_VARIANT_ID),
 };
 
 static const struct regmap_range da9063_bb_writeable_ranges[] = {
@@ -117,7 +229,7 @@ static const struct regmap_range da9063l_bb_readable_ranges[] = {
 	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
 	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
 	regmap_reg_range(DA9063_REG_T_OFFSET, DA9063_BB_REG_GP_ID_19),
-	regmap_reg_range(DA9063_REG_CHIP_ID, DA9063_REG_CHIP_VARIANT),
+	regmap_reg_range(DA9063_REG_DEVICE_ID, DA9063_REG_VARIANT_ID),
 };
 
 static const struct regmap_range da9063l_bb_writeable_ranges[] = {
@@ -159,7 +271,7 @@ static const struct regmap_access_table da9063l_bb_volatile_table = {
 static const struct regmap_range_cfg da9063_range_cfg[] = {
 	{
 		.range_min = DA9063_REG_PAGE_CON,
-		.range_max = DA9063_REG_CHIP_VARIANT,
+		.range_max = DA9063_REG_CONFIG_ID,
 		.selector_reg = DA9063_REG_PAGE_CON,
 		.selector_mask = 1 << DA9063_I2C_PAGE_SEL_SHIFT,
 		.selector_shift = DA9063_I2C_PAGE_SEL_SHIFT,
@@ -173,7 +285,7 @@ static struct regmap_config da9063_regmap_config = {
 	.val_bits = 8,
 	.ranges = da9063_range_cfg,
 	.num_ranges = ARRAY_SIZE(da9063_range_cfg),
-	.max_register = DA9063_REG_CHIP_VARIANT,
+	.max_register = DA9063_REG_CONFIG_ID,
 
 	.cache_type = REGCACHE_RBTREE,
 };
@@ -199,18 +311,56 @@ static int da9063_i2c_probe(struct i2c_client *i2c,
 	da9063->chip_irq = i2c->irq;
 	da9063->type = id->driver_data;
 
-	if (da9063->variant_code == PMIC_DA9063_AD) {
-		da9063_regmap_config.rd_table = &da9063_ad_readable_table;
-		da9063_regmap_config.wr_table = &da9063_ad_writeable_table;
-		da9063_regmap_config.volatile_table = &da9063_ad_volatile_table;
-	} else if (da9063->type == PMIC_TYPE_DA9063L) {
-		da9063_regmap_config.rd_table = &da9063l_bb_readable_table;
-		da9063_regmap_config.wr_table = &da9063l_bb_writeable_table;
-		da9063_regmap_config.volatile_table = &da9063l_bb_volatile_table;
-	} else {
-		da9063_regmap_config.rd_table = &da9063_bb_readable_table;
-		da9063_regmap_config.wr_table = &da9063_bb_writeable_table;
-		da9063_regmap_config.volatile_table = &da9063_bb_volatile_table;
+	ret = da9063_get_device_type(i2c, da9063);
+	if (ret)
+		return ret;
+
+	switch (da9063->type) {
+	case PMIC_TYPE_DA9063:
+		switch (da9063->variant_code) {
+		case PMIC_DA9063_AD:
+			da9063_regmap_config.rd_table =
+				&da9063_ad_readable_table;
+			da9063_regmap_config.wr_table =
+				&da9063_ad_writeable_table;
+			da9063_regmap_config.volatile_table =
+				&da9063_ad_volatile_table;
+			break;
+		case PMIC_DA9063_BB:
+		case PMIC_DA9063_CA:
+			da9063_regmap_config.rd_table =
+				&da9063_bb_readable_table;
+			da9063_regmap_config.wr_table =
+				&da9063_bb_writeable_table;
+			da9063_regmap_config.volatile_table =
+				&da9063_bb_volatile_table;
+			break;
+		default:
+			dev_err(da9063->dev,
+				"Chip variant not supported for DA9063\n");
+			return -ENODEV;
+		}
+		break;
+	case PMIC_TYPE_DA9063L:
+		switch (da9063->variant_code) {
+		case PMIC_DA9063_BB:
+		case PMIC_DA9063_CA:
+			da9063_regmap_config.rd_table =
+				&da9063l_bb_readable_table;
+			da9063_regmap_config.wr_table =
+				&da9063l_bb_writeable_table;
+			da9063_regmap_config.volatile_table =
+				&da9063l_bb_volatile_table;
+			break;
+		default:
+			dev_err(da9063->dev,
+				"Chip variant not supported for DA9063L\n");
+			return -ENODEV;
+		}
+		break;
+	default:
+		dev_err(da9063->dev, "Chip type not supported\n");
+		return -ENODEV;
 	}
 
 	da9063->regmap = devm_regmap_init_i2c(i2c, &da9063_regmap_config);
diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h
index ba706b0e28c2..1dbabf1b3cb8 100644
--- a/include/linux/mfd/da9063/registers.h
+++ b/include/linux/mfd/da9063/registers.h
@@ -292,8 +292,10 @@
 #define	DA9063_BB_REG_GP_ID_19		0x134
 
 /* Chip ID and variant */
-#define	DA9063_REG_CHIP_ID		0x181
-#define	DA9063_REG_CHIP_VARIANT		0x182
+#define	DA9063_REG_DEVICE_ID		0x181
+#define	DA9063_REG_VARIANT_ID		0x182
+#define	DA9063_REG_CUSTOMER_ID		0x183
+#define	DA9063_REG_CONFIG_ID		0x184
 
 /*
  * PMIC registers bits
@@ -929,9 +931,6 @@
 #define	DA9063_RTC_CLOCK			0x40
 #define	DA9063_OUT_32K_EN			0x80
 
-/* DA9063_REG_CHIP_VARIANT */
-#define	DA9063_CHIP_VARIANT_SHIFT		4
-
 /* DA9063_REG_BUCK_ILIM_A (addr=0x9A) */
 #define DA9063_BIO_ILIM_MASK			0x0F
 #define DA9063_BMEM_ILIM_MASK			0xF0
@@ -1065,4 +1064,10 @@
 #define		DA9063_MON_A10_IDX_LDO9		0x04
 #define		DA9063_MON_A10_IDX_LDO10	0x05
 
+/* DA9063_REG_VARIANT_ID (addr=0x182) */
+#define	DA9063_VARIANT_ID_VRC_SHIFT		0
+#define DA9063_VARIANT_ID_VRC_MASK		0x0F
+#define	DA9063_VARIANT_ID_MRC_SHIFT		4
+#define DA9063_VARIANT_ID_MRC_MASK		0xF0
+
 #endif /* _DA9063_REG_H */
-- 
cgit v1.2.3


From 9ece3601aed46f7b460b79cd7d60908b47b2b0d4 Mon Sep 17 00:00:00 2001
From: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Date: Mon, 13 Jul 2020 10:38:59 +0100
Subject: mfd: da9063: Add support for latest DA silicon revision

This update adds new regmap tables to support the latest DA silicon
which will automatically be selected based on the chip and variant
information read from the device.

Signed-off-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/da9063-i2c.c        | 91 ++++++++++++++++++++++++++++++++++++-----
 include/linux/mfd/da9063/core.h |  1 +
 2 files changed, 82 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/da9063-i2c.c b/drivers/mfd/da9063-i2c.c
index 481548948bc0..b8217ad303ce 100644
--- a/drivers/mfd/da9063-i2c.c
+++ b/drivers/mfd/da9063-i2c.c
@@ -197,7 +197,7 @@ static const struct regmap_range da9063_bb_writeable_ranges[] = {
 	regmap_reg_range(DA9063_BB_REG_GP_ID_0, DA9063_BB_REG_GP_ID_19),
 };
 
-static const struct regmap_range da9063_bb_volatile_ranges[] = {
+static const struct regmap_range da9063_bb_da_volatile_ranges[] = {
 	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_REG_EVENT_D),
 	regmap_reg_range(DA9063_REG_CONTROL_A, DA9063_REG_CONTROL_B),
 	regmap_reg_range(DA9063_REG_CONTROL_E, DA9063_REG_CONTROL_F),
@@ -219,9 +219,9 @@ static const struct regmap_access_table da9063_bb_writeable_table = {
 	.n_yes_ranges = ARRAY_SIZE(da9063_bb_writeable_ranges),
 };
 
-static const struct regmap_access_table da9063_bb_volatile_table = {
-	.yes_ranges = da9063_bb_volatile_ranges,
-	.n_yes_ranges = ARRAY_SIZE(da9063_bb_volatile_ranges),
+static const struct regmap_access_table da9063_bb_da_volatile_table = {
+	.yes_ranges = da9063_bb_da_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063_bb_da_volatile_ranges),
 };
 
 static const struct regmap_range da9063l_bb_readable_ranges[] = {
@@ -241,7 +241,7 @@ static const struct regmap_range da9063l_bb_writeable_ranges[] = {
 	regmap_reg_range(DA9063_BB_REG_GP_ID_0, DA9063_BB_REG_GP_ID_19),
 };
 
-static const struct regmap_range da9063l_bb_volatile_ranges[] = {
+static const struct regmap_range da9063l_bb_da_volatile_ranges[] = {
 	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_REG_EVENT_D),
 	regmap_reg_range(DA9063_REG_CONTROL_A, DA9063_REG_CONTROL_B),
 	regmap_reg_range(DA9063_REG_CONTROL_E, DA9063_REG_CONTROL_F),
@@ -263,9 +263,64 @@ static const struct regmap_access_table da9063l_bb_writeable_table = {
 	.n_yes_ranges = ARRAY_SIZE(da9063l_bb_writeable_ranges),
 };
 
-static const struct regmap_access_table da9063l_bb_volatile_table = {
-	.yes_ranges = da9063l_bb_volatile_ranges,
-	.n_yes_ranges = ARRAY_SIZE(da9063l_bb_volatile_ranges),
+static const struct regmap_access_table da9063l_bb_da_volatile_table = {
+	.yes_ranges = da9063l_bb_da_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063l_bb_da_volatile_ranges),
+};
+
+static const struct regmap_range da9063_da_readable_ranges[] = {
+	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_BB_REG_SECOND_D),
+	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
+	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
+	regmap_reg_range(DA9063_REG_T_OFFSET, DA9063_BB_REG_GP_ID_11),
+	regmap_reg_range(DA9063_REG_DEVICE_ID, DA9063_REG_VARIANT_ID),
+};
+
+static const struct regmap_range da9063_da_writeable_ranges[] = {
+	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_REG_PAGE_CON),
+	regmap_reg_range(DA9063_REG_FAULT_LOG, DA9063_REG_VSYS_MON),
+	regmap_reg_range(DA9063_REG_COUNT_S, DA9063_BB_REG_ALARM_Y),
+	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
+	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
+	regmap_reg_range(DA9063_REG_CONFIG_I, DA9063_BB_REG_MON_REG_4),
+	regmap_reg_range(DA9063_BB_REG_GP_ID_0, DA9063_BB_REG_GP_ID_11),
+};
+
+static const struct regmap_access_table da9063_da_readable_table = {
+	.yes_ranges = da9063_da_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063_da_readable_ranges),
+};
+
+static const struct regmap_access_table da9063_da_writeable_table = {
+	.yes_ranges = da9063_da_writeable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063_da_writeable_ranges),
+};
+
+static const struct regmap_range da9063l_da_readable_ranges[] = {
+	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_REG_MON_A10_RES),
+	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
+	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
+	regmap_reg_range(DA9063_REG_T_OFFSET, DA9063_BB_REG_GP_ID_11),
+	regmap_reg_range(DA9063_REG_DEVICE_ID, DA9063_REG_VARIANT_ID),
+};
+
+static const struct regmap_range da9063l_da_writeable_ranges[] = {
+	regmap_reg_range(DA9063_REG_PAGE_CON, DA9063_REG_PAGE_CON),
+	regmap_reg_range(DA9063_REG_FAULT_LOG, DA9063_REG_VSYS_MON),
+	regmap_reg_range(DA9063_REG_SEQ, DA9063_REG_ID_32_31),
+	regmap_reg_range(DA9063_REG_SEQ_A, DA9063_REG_AUTO3_LOW),
+	regmap_reg_range(DA9063_REG_CONFIG_I, DA9063_BB_REG_MON_REG_4),
+	regmap_reg_range(DA9063_BB_REG_GP_ID_0, DA9063_BB_REG_GP_ID_11),
+};
+
+static const struct regmap_access_table da9063l_da_readable_table = {
+	.yes_ranges = da9063l_da_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063l_da_readable_ranges),
+};
+
+static const struct regmap_access_table da9063l_da_writeable_table = {
+	.yes_ranges = da9063l_da_writeable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9063l_da_writeable_ranges),
 };
 
 static const struct regmap_range_cfg da9063_range_cfg[] = {
@@ -333,7 +388,15 @@ static int da9063_i2c_probe(struct i2c_client *i2c,
 			da9063_regmap_config.wr_table =
 				&da9063_bb_writeable_table;
 			da9063_regmap_config.volatile_table =
-				&da9063_bb_volatile_table;
+				&da9063_bb_da_volatile_table;
+			break;
+		case PMIC_DA9063_DA:
+			da9063_regmap_config.rd_table =
+				&da9063_da_readable_table;
+			da9063_regmap_config.wr_table =
+				&da9063_da_writeable_table;
+			da9063_regmap_config.volatile_table =
+				&da9063_bb_da_volatile_table;
 			break;
 		default:
 			dev_err(da9063->dev,
@@ -350,7 +413,15 @@ static int da9063_i2c_probe(struct i2c_client *i2c,
 			da9063_regmap_config.wr_table =
 				&da9063l_bb_writeable_table;
 			da9063_regmap_config.volatile_table =
-				&da9063l_bb_volatile_table;
+				&da9063l_bb_da_volatile_table;
+			break;
+		case PMIC_DA9063_DA:
+			da9063_regmap_config.rd_table =
+				&da9063l_da_readable_table;
+			da9063_regmap_config.wr_table =
+				&da9063l_da_writeable_table;
+			da9063_regmap_config.volatile_table =
+				&da9063l_bb_da_volatile_table;
 			break;
 		default:
 			dev_err(da9063->dev,
diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h
index 5cd06ab26352..fa7a43f02f27 100644
--- a/include/linux/mfd/da9063/core.h
+++ b/include/linux/mfd/da9063/core.h
@@ -35,6 +35,7 @@ enum da9063_variant_codes {
 	PMIC_DA9063_AD = 0x3,
 	PMIC_DA9063_BB = 0x5,
 	PMIC_DA9063_CA = 0x6,
+	PMIC_DA9063_DA = 0x7,
 };
 
 /* Interrupts */
-- 
cgit v1.2.3


From 23ef2b642b85f03a109fbf5958134a5e40193dbd Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:29:17 -0700
Subject: mfd: da9055: pdata.h: Drop a duplicated word

Drop the repeated word "that" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/da9055/pdata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h
index eac48e483190..d3f126990ad0 100644
--- a/include/linux/mfd/da9055/pdata.h
+++ b/include/linux/mfd/da9055/pdata.h
@@ -35,7 +35,7 @@ struct da9055_pdata {
 	int *gpio_rsel;
 	/*
 	 * Regulator mode control bits value (GPI offset) that
-	 * that controls the regulator state, 0 if not available.
+	 * controls the regulator state, 0 if not available.
 	 */
 	enum gpio_select *reg_ren;
 	/*
-- 
cgit v1.2.3


From e7b85500885f2a70129f5d3a72153e23b37d0fe5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:29:31 -0700
Subject: mfd: max77693-private: Drop a duplicated word

Drop the repeated word "in" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/max77693-private.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index e798c81aec31..311f7d3d2323 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -131,7 +131,7 @@ enum max77693_pmic_reg {
 #define FLASH_INT_FLED1_SHORT	BIT(3)
 #define FLASH_INT_OVER_CURRENT	BIT(4)
 
-/* Fast charge timer in in hours */
+/* Fast charge timer in hours */
 #define DEFAULT_FAST_CHARGE_TIMER		4
 /* microamps */
 #define DEFAULT_TOP_OFF_THRESHOLD_CURRENT	150000
-- 
cgit v1.2.3


From 114294d276279d6cda81f9c685452239ea89cdb8 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 23 Jul 2020 11:54:58 +0100
Subject: mfd: mfd-core: Add mechanism for removal of a subset of children

Currently, the only way to remove MFD children is with a call to
mfd_remove_devices, which will remove all the children. Under
some circumstances it is useful to remove only a subset of the
child devices. For example if some additional clean up is required
between removal of certain child devices.

To accomplish this a level field is added to mfd_cell, the normal
mfd_remove_devices is modified to not remove devices that are set
to a higher level and a corresponding mfd_remove_devices_late
function is added to remove those children.

See further discussion at:
https://lore.kernel.org/lkml/20200616075834.GF2608702@dell/

Suggested-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/mfd-core.c   | 16 +++++++++++++++-
 include/linux/mfd/core.h |  5 +++++
 2 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index b201842f82ad..c3651f06684f 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -356,6 +356,7 @@ static int mfd_remove_devices_fn(struct device *dev, void *data)
 {
 	struct platform_device *pdev;
 	const struct mfd_cell *cell;
+	int *level = data;
 
 	if (dev->type != &mfd_dev_type)
 		return 0;
@@ -363,6 +364,9 @@ static int mfd_remove_devices_fn(struct device *dev, void *data)
 	pdev = to_platform_device(dev);
 	cell = mfd_get_cell(pdev);
 
+	if (level && cell->level > *level)
+		return 0;
+
 	regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies,
 					       cell->num_parent_supplies);
 
@@ -372,9 +376,19 @@ static int mfd_remove_devices_fn(struct device *dev, void *data)
 	return 0;
 }
 
+void mfd_remove_devices_late(struct device *parent)
+{
+	int level = MFD_DEP_LEVEL_HIGH;
+
+	device_for_each_child_reverse(parent, &level, mfd_remove_devices_fn);
+}
+EXPORT_SYMBOL(mfd_remove_devices_late);
+
 void mfd_remove_devices(struct device *parent)
 {
-	device_for_each_child_reverse(parent, NULL, mfd_remove_devices_fn);
+	int level = MFD_DEP_LEVEL_NORMAL;
+
+	device_for_each_child_reverse(parent, &level, mfd_remove_devices_fn);
 }
 EXPORT_SYMBOL(mfd_remove_devices);
 
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index 6d68f44a26a1..4b35baa14d30 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -46,6 +46,9 @@
 #define MFD_CELL_NAME(_name) \
 	MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, 0, false, NULL)
 
+#define MFD_DEP_LEVEL_NORMAL 0
+#define MFD_DEP_LEVEL_HIGH 1
+
 struct irq_domain;
 struct property_entry;
 
@@ -63,6 +66,7 @@ struct mfd_cell_acpi_match {
 struct mfd_cell {
 	const char		*name;
 	int			id;
+	int			level;
 
 	int			(*enable)(struct platform_device *dev);
 	int			(*disable)(struct platform_device *dev);
@@ -150,6 +154,7 @@ static inline int mfd_add_hotplug_devices(struct device *parent,
 }
 
 extern void mfd_remove_devices(struct device *parent);
+extern void mfd_remove_devices_late(struct device *parent);
 
 extern int devm_mfd_add_devices(struct device *dev, int id,
 				const struct mfd_cell *cells, int n_devs,
-- 
cgit v1.2.3


From 4f4ed4543e2096dc0158ff79bd6d8bc09e27fa93 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Wed, 22 Jul 2020 21:24:54 +0200
Subject: mfd: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 Documentation/devicetree/bindings/mfd/twl-family.txt | 2 +-
 drivers/mfd/hi6421-pmic-core.c                       | 2 +-
 drivers/mfd/lp873x.c                                 | 2 +-
 drivers/mfd/lp87565.c                                | 2 +-
 drivers/mfd/omap-usb-host.c                          | 2 +-
 drivers/mfd/omap-usb-tll.c                           | 2 +-
 drivers/mfd/ti_am335x_tscadc.c                       | 2 +-
 drivers/mfd/tps65086.c                               | 2 +-
 drivers/mfd/tps65217.c                               | 2 +-
 drivers/mfd/tps65218.c                               | 2 +-
 drivers/mfd/tps65912-core.c                          | 2 +-
 drivers/mfd/tps65912-i2c.c                           | 2 +-
 drivers/mfd/tps65912-spi.c                           | 2 +-
 include/linux/mfd/hi6421-pmic.h                      | 2 +-
 include/linux/mfd/lp873x.h                           | 2 +-
 include/linux/mfd/lp87565.h                          | 2 +-
 include/linux/mfd/ti_am335x_tscadc.h                 | 2 +-
 include/linux/mfd/tps65086.h                         | 2 +-
 include/linux/mfd/tps65217.h                         | 2 +-
 include/linux/mfd/tps65218.h                         | 2 +-
 include/linux/mfd/tps65912.h                         | 2 +-
 21 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/mfd/twl-family.txt b/Documentation/devicetree/bindings/mfd/twl-family.txt
index 56f244b5d8a4..c2f9302965de 100644
--- a/Documentation/devicetree/bindings/mfd/twl-family.txt
+++ b/Documentation/devicetree/bindings/mfd/twl-family.txt
@@ -26,7 +26,7 @@ Optional node:
 Example:
 /*
  * Integrated Power Management Chip
- * http://www.ti.com/lit/ds/symlink/twl6030.pdf
+ * https://www.ti.com/lit/ds/symlink/twl6030.pdf
  */
 twl@48 {
     compatible = "ti,twl6030";
diff --git a/drivers/mfd/hi6421-pmic-core.c b/drivers/mfd/hi6421-pmic-core.c
index edfc172b8607..eba88b80d969 100644
--- a/drivers/mfd/hi6421-pmic-core.c
+++ b/drivers/mfd/hi6421-pmic-core.c
@@ -5,7 +5,7 @@
  * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
  *              http://www.hisilicon.com
  * Copyright (c) <2013-2017> Linaro Ltd.
- *              http://www.linaro.org
+ *              https://www.linaro.org
  *
  * Author: Guodong Xu <guodong.xu@linaro.org>
  */
diff --git a/drivers/mfd/lp873x.c b/drivers/mfd/lp873x.c
index 873c608e6a5d..858c9e0a49a4 100644
--- a/drivers/mfd/lp873x.c
+++ b/drivers/mfd/lp873x.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2016 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Author: Keerthy <j-keerthy@ti.com>
  *
diff --git a/drivers/mfd/lp87565.c b/drivers/mfd/lp87565.c
index 4a5c8ade4ae0..2268be9113f1 100644
--- a/drivers/mfd/lp87565.c
+++ b/drivers/mfd/lp87565.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2017 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Author: Keerthy <j-keerthy@ti.com>
  */
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index aca5a160c1b2..1e6431cb8536 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -2,7 +2,7 @@
 /**
  * omap-usb-host.c - The USBHS core driver for OMAP EHCI & OHCI
  *
- * Copyright (C) 2011-2013 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2011-2013 Texas Instruments Incorporated - https://www.ti.com
  * Author: Keshava Munegowda <keshava_mgowda@ti.com>
  * Author: Roger Quadros <rogerq@ti.com>
  */
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 04a444007cf4..16fad79c73f1 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -2,7 +2,7 @@
 /**
  * omap-usb-tll.c - The USB TLL driver for OMAP EHCI & OHCI
  *
- * Copyright (C) 2012-2013 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012-2013 Texas Instruments Incorporated - https://www.ti.com
  * Author: Keshava Munegowda <keshava_mgowda@ti.com>
  * Author: Roger Quadros <rogerq@ti.com>
  */
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index 926c289cb040..0e6e25308190 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -1,7 +1,7 @@
 /*
  * TI Touch Screen / ADC MFD driver
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/drivers/mfd/tps65086.c b/drivers/mfd/tps65086.c
index 43119a6867fe..341466ef20cc 100644
--- a/drivers/mfd/tps65086.c
+++ b/drivers/mfd/tps65086.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 923602599549..2d9c282ec917 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -3,7 +3,7 @@
  *
  * TPS65217 chip family multi-function driver
  *
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/drivers/mfd/tps65218.c b/drivers/mfd/tps65218.c
index d41dd864b472..167e9fc308ef 100644
--- a/drivers/mfd/tps65218.c
+++ b/drivers/mfd/tps65218.c
@@ -1,7 +1,7 @@
 /*
  * Driver for TPS65218 Integrated power management chipsets
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2 as
diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c
index f33567bc428d..b55b1d5d6955 100644
--- a/drivers/mfd/tps65912-core.c
+++ b/drivers/mfd/tps65912-core.c
@@ -1,7 +1,7 @@
 /*
  * Core functions for TI TPS65912x PMICs
  *
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/mfd/tps65912-i2c.c b/drivers/mfd/tps65912-i2c.c
index 785d19f6f7c9..f7c22ea7b36c 100644
--- a/drivers/mfd/tps65912-i2c.c
+++ b/drivers/mfd/tps65912-i2c.c
@@ -1,7 +1,7 @@
 /*
  * I2C access driver for TI TPS65912x PMICs
  *
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/mfd/tps65912-spi.c b/drivers/mfd/tps65912-spi.c
index f78be039e463..21a8d6ac5c4a 100644
--- a/drivers/mfd/tps65912-spi.c
+++ b/drivers/mfd/tps65912-spi.c
@@ -1,7 +1,7 @@
 /*
  * SPI access driver for TI TPS65912x PMICs
  *
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h
index bbc64484c021..2cadf8897c64 100644
--- a/include/linux/mfd/hi6421-pmic.h
+++ b/include/linux/mfd/hi6421-pmic.h
@@ -5,7 +5,7 @@
  * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
  *              http://www.hisilicon.com
  * Copyright (c) <2013-2014> Linaro Ltd.
- *              http://www.linaro.org
+ *              https://www.linaro.org
  *
  * Author: Guodong Xu <guodong.xu@linaro.org>
  */
diff --git a/include/linux/mfd/lp873x.h b/include/linux/mfd/lp873x.h
index edbec8350a49..5546688c7da7 100644
--- a/include/linux/mfd/lp873x.h
+++ b/include/linux/mfd/lp873x.h
@@ -1,7 +1,7 @@
 /*
  * Functions to access LP873X power management chip.
  *
- * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2016 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h
index ce965354bbad..43716aca46fa 100644
--- a/include/linux/mfd/lp87565.h
+++ b/include/linux/mfd/lp87565.h
@@ -2,7 +2,7 @@
 /*
  * Functions to access LP87565 power management chip.
  *
- * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef __LINUX_MFD_LP87565_H
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index 483168403ae5..ffc091b77633 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -4,7 +4,7 @@
 /*
  * TI Touch Screen / ADC MFD driver
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/mfd/tps65086.h b/include/linux/mfd/tps65086.h
index a228ae4c88d9..e0a417e53766 100644
--- a/include/linux/mfd/tps65086.h
+++ b/include/linux/mfd/tps65086.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index b5dd108421c8..db7091824ed0 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -3,7 +3,7 @@
  *
  * Functions to access TPS65217 power management chip.
  *
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h
index b0470c35162d..f4ca367e3473 100644
--- a/include/linux/mfd/tps65218.h
+++ b/include/linux/mfd/tps65218.h
@@ -3,7 +3,7 @@
  *
  * Functions to access TPS65219 power management chip.
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2 as
diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h
index b25d0297ba88..7943e413deae 100644
--- a/include/linux/mfd/tps65912.h
+++ b/include/linux/mfd/tps65912.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
  *
  * This program is free software; you can redistribute it and/or
-- 
cgit v1.2.3


From 9420139f516d7fbc248ce17f35275cb005ed98ea Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 14 Aug 2020 12:26:24 +0200
Subject: dma-pool: fix coherent pool allocations for IOMMU mappings

When allocating coherent pool memory for an IOMMU mapping we don't care
about the DMA mask.  Move the guess for the initial GFP mask into the
dma_direct_alloc_pages and pass dma_coherent_ok as a function pointer
argument so that it doesn't get applied to the IOMMU case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Amit Pundir <amit.pundir@linaro.org>
---
 drivers/iommu/dma-iommu.c   |   4 +-
 include/linux/dma-direct.h  |   3 --
 include/linux/dma-mapping.h |   5 +-
 kernel/dma/direct.c         |  13 +++--
 kernel/dma/pool.c           | 114 +++++++++++++++++++-------------------------
 5 files changed, 62 insertions(+), 77 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 4959f5df21bd..5141d49a046b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    !gfpflags_allow_blocking(gfp) && !coherent)
-		cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page,
-					       gfp);
+		page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr,
+					       gfp, NULL);
 	else
 		cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs);
 	if (!cpu_addr)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 5a3ce2a24794..6e87225600ae 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 }
 
 u64 dma_direct_get_required_mask(struct device *dev);
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-				  u64 *phys_mask);
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 016b96b384bd..52635e91143b 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 			pgprot_t prot, const void *caller);
 void dma_common_free_remap(void *cpu_addr, size_t size);
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags);
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
 bool dma_free_from_pool(struct device *dev, void *start, size_t size);
 
 int
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index bb0041e99659..db6ef07aec3b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
 
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 				  u64 *phys_limit)
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
@@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
@@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
-		ret = dma_alloc_from_pool(dev, size, &page, gfp);
-		if (!ret)
+		u64 phys_mask;
+
+		gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+				&phys_mask);
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
 			return NULL;
 		goto done;
 	}
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 6bc74a2d5127..5d071d4a3cba 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -196,93 +196,75 @@ static int __init dma_atomic_pool_init(void)
 }
 postcore_initcall(dma_atomic_pool_init);
 
-static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev)
+static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
 {
-	u64 phys_mask;
-	gfp_t gfp;
-
-	gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-					  &phys_mask);
-	if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA)
+	if (prev == NULL) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+			return atomic_pool_dma32;
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+			return atomic_pool_dma;
+		return atomic_pool_kernel;
+	}
+	if (prev == atomic_pool_kernel)
+		return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
+	if (prev == atomic_pool_dma32)
 		return atomic_pool_dma;
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32)
-		return atomic_pool_dma32;
-	return atomic_pool_kernel;
+	return NULL;
 }
 
-static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool)
+static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
+		struct gen_pool *pool, void **cpu_addr,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
-	if (bad_pool == atomic_pool_kernel)
-		return atomic_pool_dma32 ? : atomic_pool_dma;
+	unsigned long addr;
+	phys_addr_t phys;
 
-	if (bad_pool == atomic_pool_dma32)
-		return atomic_pool_dma;
+	addr = gen_pool_alloc(pool, size);
+	if (!addr)
+		return NULL;
 
-	return NULL;
-}
+	phys = gen_pool_virt_to_phys(pool, addr);
+	if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) {
+		gen_pool_free(pool, addr, size);
+		return NULL;
+	}
 
-static inline struct gen_pool *dma_guess_pool(struct device *dev,
-					      struct gen_pool *bad_pool)
-{
-	if (bad_pool)
-		return dma_get_safer_pool(bad_pool);
+	if (gen_pool_avail(pool) < atomic_pool_size)
+		schedule_work(&atomic_pool_work);
 
-	return dma_guess_pool_from_device(dev);
+	*cpu_addr = (void *)addr;
+	memset(*cpu_addr, 0, size);
+	return pfn_to_page(__phys_to_pfn(phys));
 }
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags)
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t gfp,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
 	struct gen_pool *pool = NULL;
-	unsigned long val = 0;
-	void *ptr = NULL;
-	phys_addr_t phys;
-
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool) {
-			WARN(1, "Failed to get suitable pool for %s\n",
-			     dev_name(dev));
-			break;
-		}
-
-		val = gen_pool_alloc(pool, size);
-		if (!val)
-			continue;
-
-		phys = gen_pool_virt_to_phys(pool, val);
-		if (dma_coherent_ok(dev, phys, size))
-			break;
-
-		gen_pool_free(pool, val, size);
-		val = 0;
-	}
-
-
-	if (val) {
-		*ret_page = pfn_to_page(__phys_to_pfn(phys));
-		ptr = (void *)val;
-		memset(ptr, 0, size);
+	struct page *page;
 
-		if (gen_pool_avail(pool) < atomic_pool_size)
-			schedule_work(&atomic_pool_work);
+	while ((pool = dma_guess_pool(pool, gfp))) {
+		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+					     phys_addr_ok);
+		if (page)
+			return page;
 	}
 
-	return ptr;
+	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	return NULL;
 }
 
 bool dma_free_from_pool(struct device *dev, void *start, size_t size)
 {
 	struct gen_pool *pool = NULL;
 
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool)
-			return false;
-
-		if (gen_pool_has_addr(pool, (unsigned long)start, size)) {
-			gen_pool_free(pool, (unsigned long)start, size);
-			return true;
-		}
+	while ((pool = dma_guess_pool(pool, 0))) {
+		if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+			continue;
+		gen_pool_free(pool, (unsigned long)start, size);
+		return true;
 	}
+
+	return false;
 }
-- 
cgit v1.2.3


From 5848dc5b1b76d83599dcec1b39f188a7cbdca7e2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 14 Aug 2020 15:22:43 -0700
Subject: dma-debug: remove debug_dma_assert_idle() function

This remoes the code from the COW path to call debug_dma_assert_idle(),
which was added many years ago.

Google shows that it hasn't caught anything in the 6+ years we've had it
apart from a false positive, and Hugh just noticed how it had a very
unfortunate spinlock serialization in the COW path.

He fixed that issue the previous commit (a85ffd59bd36: "dma-debug: fix
debug_dma_assert_idle(), use rcu_read_lock()"), but let's see if anybody
even notices when we remove this function entirely.

NOTE! We keep the dma tracking infrastructure that was added by the
commit that introduced it.  Partly to make it easier to resurrect this
debug code if we ever deside to, and partly because that tracking by pfn
and offset looks quite reasonable.

The problem with this debug code was simply that it was expensive and
didn't seem worth it, not that it was wrong per se.

Acked-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/dma-debug.h |  6 ------
 kernel/dma/Kconfig        |  5 -----
 kernel/dma/debug.c        | 46 +---------------------------------------------
 mm/memory.c               |  2 --
 4 files changed, 1 insertion(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 4208f94d93f7..7b3b04ba60f3 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -67,8 +67,6 @@ extern void debug_dma_sync_sg_for_device(struct device *dev,
 
 extern void debug_dma_dump_mappings(struct device *dev);
 
-extern void debug_dma_assert_idle(struct page *page);
-
 #else /* CONFIG_DMA_API_DEBUG */
 
 static inline void dma_debug_add_bus(struct bus_type *bus)
@@ -157,10 +155,6 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 {
 }
 
-static inline void debug_dma_assert_idle(struct page *page)
-{
-}
-
 #endif /* CONFIG_DMA_API_DEBUG */
 
 #endif /* __DMA_DEBUG_H */
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index f4770fcfa62b..5732b2b3ef17 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -186,11 +186,6 @@ config DMA_API_DEBUG
 	  drivers like double-freeing of DMA mappings or freeing mappings that
 	  were never allocated.
 
-	  This also attempts to catch cases where a page owned by DMA is
-	  accessed by the cpu in a way that could cause data corruption.  For
-	  example, this enables cow_user_page() to check that the source page is
-	  not undergoing DMA.
-
 	  This option causes a performance degradation.  Use only if you want to
 	  debug device drivers and dma interactions.
 
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 6f4f4b9d2d03..8e9f7b301c6d 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -448,9 +448,6 @@ void debug_dma_dump_mappings(struct device *dev)
  * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
  * other hand, consumes a single dma_debug_entry, but inserts 'nents'
  * entries into the tree.
- *
- * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if any cachelines in the given page are in the active set.
  */
 static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
 static DEFINE_SPINLOCK(radix_lock);
@@ -497,10 +494,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln)
 	overlap = active_cacheline_set_overlap(cln, ++overlap);
 
 	/* If we overflowed the overlap counter then we're potentially
-	 * leaking dma-mappings.  Otherwise, if maps and unmaps are
-	 * balanced then this overflow may cause false negatives in
-	 * debug_dma_assert_idle() as the cacheline may be marked idle
-	 * prematurely.
+	 * leaking dma-mappings.
 	 */
 	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
 		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
@@ -555,44 +549,6 @@ static void active_cacheline_remove(struct dma_debug_entry *entry)
 	spin_unlock_irqrestore(&radix_lock, flags);
 }
 
-/**
- * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_cacheline tree
- *
- * Place a call to this routine in cases where the cpu touching the page
- * before the dma completes (page is dma_unmapped) will lead to data
- * corruption.
- */
-void debug_dma_assert_idle(struct page *page)
-{
-	struct dma_debug_entry *entry;
-	unsigned long pfn;
-	phys_addr_t cln;
-
-	if (dma_debug_disabled())
-		return;
-
-	if (!page)
-		return;
-
-	pfn = page_to_pfn(page);
-	cln = (phys_addr_t) pfn << CACHELINE_PER_PAGE_SHIFT;
-
-	rcu_read_lock();
-	if (!radix_tree_gang_lookup(&dma_active_cacheline, (void **) &entry,
-				    cln, 1) || entry->pfn != pfn)
-		entry = NULL;
-	rcu_read_unlock();
-
-	if (!entry)
-		return;
-
-	cln = to_cacheline_number(entry);
-	err_printk(entry->dev, entry,
-		   "cpu touching an active dma mapped cacheline [cln=%pa]\n",
-		   &cln);
-}
-
 /*
  * Wrapper function for adding an entry to the hash.
  * This function takes care of locking itself.
diff --git a/mm/memory.c b/mm/memory.c
index 228efaca75d3..d3c3bbd65a7e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2411,8 +2411,6 @@ static inline bool cow_user_page(struct page *dst, struct page *src,
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long addr = vmf->address;
 
-	debug_dma_assert_idle(src);
-
 	if (likely(src)) {
 		copy_user_highpage(dst, src, addr, vma);
 		return true;
-- 
cgit v1.2.3


From 1378a5ee451a5e87d0d8dd6356a0b7844db231f6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:23 -0700
Subject: mm: store compound_nr as well as compound_order

Patch series "THP prep patches".

These are some generic cleanups and improvements, which I would like
merged into mmotm soon.  The first one should be a performance improvement
for all users of compound pages, and the others are aimed at getting code
to compile away when CONFIG_TRANSPARENT_HUGEPAGE is disabled (ie small
systems).  Also better documented / less confusing than the current prefix
mixture of compound, hpage and thp.

This patch (of 7):

This removes a few instructions from functions which need to know how many
pages are in a compound page.  The storage used is either page->mapping on
64-bit or page->index on 32-bit.  Both of these are fine to overlay on
tail pages.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-1-willy@infradead.org
Link: http://lkml.kernel.org/r/20200629151959.15779-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h       | 5 ++++-
 include/linux/mm_types.h | 1 +
 mm/page_alloc.c          | 5 +++--
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index e7602a3bcef1..10b1e6e5f885 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -922,12 +922,15 @@ static inline int compound_pincount(struct page *page)
 static inline void set_compound_order(struct page *page, unsigned int order)
 {
 	page[1].compound_order = order;
+	page[1].compound_nr = 1U << order;
 }
 
 /* Returns the number of pages in this potentially compound page. */
 static inline unsigned long compound_nr(struct page *page)
 {
-	return 1UL << compound_order(page);
+	if (!PageHead(page))
+		return 1;
+	return page[1].compound_nr;
 }
 
 /* Returns the number of bytes in this potentially compound page. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0277fbab7c93..496c3ff97cce 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -134,6 +134,7 @@ struct page {
 			unsigned char compound_dtor;
 			unsigned char compound_order;
 			atomic_t compound_mapcount;
+			unsigned int compound_nr; /* 1 << compound_order */
 		};
 		struct {	/* Second tail page of compound page */
 			unsigned long _compound_pad_1;	/* compound_head */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8b7d0ecf30b1..0e2bab486fea 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -666,8 +666,6 @@ void prep_compound_page(struct page *page, unsigned int order)
 	int i;
 	int nr_pages = 1 << order;
 
-	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
-	set_compound_order(page, order);
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
@@ -675,6 +673,9 @@ void prep_compound_page(struct page *page, unsigned int order)
 		p->mapping = TAIL_MAPPING;
 		set_compound_head(p, page);
 	}
+
+	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
+	set_compound_order(page, order);
 	atomic_set(compound_mapcount_ptr(page), -1);
 	if (hpage_pincount_available(page))
 		atomic_set(compound_pincount_ptr(page), 0);
-- 
cgit v1.2.3


From 419015675fef6c4b28689bd2ace559564c2e106c Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:26 -0700
Subject: mm: move page-flags include to top of file

Give up on the notion that we can remove page-flags.h from mm.h.  There
are currently 14 inline functions which use a PageFoo function.  Also, two
of the files directly included by mm.h include page-flags.h themselves,
and there are probably more indirect inclusions.  So just include it at
the top like any other header file.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 10b1e6e5f885..fd0cd4e93029 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -24,6 +24,7 @@
 #include <linux/resource.h>
 #include <linux/page_ext.h>
 #include <linux/err.h>
+#include <linux/page-flags.h>
 #include <linux/page_ref.h>
 #include <linux/memremap.h>
 #include <linux/overflow.h>
@@ -668,11 +669,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
-/*
- * FIXME: take this include out, include page-flags.h in
- * files which need it (119 of them)
- */
-#include <linux/page-flags.h>
 #include <linux/huge_mm.h>
 
 /*
-- 
cgit v1.2.3


From 6ffbb45826f5d9ae09aa60cd88594b7816c96190 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:30 -0700
Subject: mm: add thp_order

This function returns the order of a transparent huge page.  It compiles
to 0 if CONFIG_TRANSPARENT_HUGEPAGE is disabled.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-4-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 467302056e17..9521cfdf18ca 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -258,6 +258,19 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 	else
 		return NULL;
 }
+
+/**
+ * thp_order - Order of a transparent huge page.
+ * @page: Head page of a transparent huge page.
+ */
+static inline unsigned int thp_order(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	if (PageHead(page))
+		return HPAGE_PMD_ORDER;
+	return 0;
+}
+
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -317,6 +330,12 @@ static inline struct list_head *page_deferred_list(struct page *page)
 #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
 #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
 
+static inline unsigned int thp_order(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	return 0;
+}
+
 static inline int hpage_nr_pages(struct page *page)
 {
 	VM_BUG_ON_PAGE(PageTail(page), page);
-- 
cgit v1.2.3


From af3bbc12df80e8c279b94c752b6edca29841f4f5 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:33 -0700
Subject: mm: add thp_size

This function returns the number of bytes in a THP.  It is like
page_size(), but compiles to just PAGE_SIZE if CONFIG_TRANSPARENT_HUGEPAGE
is disabled.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-5-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/nvdimm/btt.c    |  4 +---
 drivers/nvdimm/pmem.c   |  6 ++----
 include/linux/huge_mm.h | 11 +++++++++++
 mm/internal.h           |  2 +-
 mm/page_io.c            |  2 +-
 mm/page_vma_mapped.c    |  4 ++--
 6 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 412d21d8f643..0ff610e728ff 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1490,10 +1490,8 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector,
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
-	unsigned int len;
 
-	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
+	rc = btt_do_bvec(btt, NULL, page, thp_size(page), 0, op, sector);
 	if (rc == 0)
 		page_endio(page, op_is_write(op), 0);
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 94790e6e0e4c..fab29b514372 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -238,11 +238,9 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	blk_status_t rc;
 
 	if (op_is_write(op))
-		rc = pmem_do_write(pmem, page, 0, sector,
-				   hpage_nr_pages(page) * PAGE_SIZE);
+		rc = pmem_do_write(pmem, page, 0, sector, thp_size(page));
 	else
-		rc = pmem_do_read(pmem, page, 0, sector,
-				   hpage_nr_pages(page) * PAGE_SIZE);
+		rc = pmem_do_read(pmem, page, 0, sector, thp_size(page));
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
 	 * retries on any error, so we can only invoke page_endio() in
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9521cfdf18ca..9b33ac774fdd 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -462,4 +462,15 @@ static inline bool thp_migration_supported(void)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+/**
+ * thp_size - Size of a transparent huge page.
+ * @page: Head page of a transparent huge page.
+ *
+ * Return: Number of bytes in this page.
+ */
+static inline unsigned long thp_size(struct page *page)
+{
+	return PAGE_SIZE << thp_order(page);
+}
+
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/mm/internal.h b/mm/internal.h
index d11a9a8d2135..912bb1a1c10e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -396,7 +396,7 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	unsigned long start, end;
 
 	start = __vma_address(page, vma);
-	end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
+	end = start + thp_size(page) - PAGE_SIZE;
 
 	/* page should be within @vma mapping range */
 	VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
diff --git a/mm/page_io.c b/mm/page_io.c
index 9e362567d454..f5e8bec8a8c7 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -40,7 +40,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
 		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
 		bio->bi_end_io = end_io;
 
-		bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0);
+		bio_add_page(bio, page, thp_size(page), 0);
 	}
 	return bio;
 }
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 719c35246cfa..e65629c056e8 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -227,7 +227,7 @@ next_pte:
 			if (pvmw->address >= pvmw->vma->vm_end ||
 			    pvmw->address >=
 					__vma_address(pvmw->page, pvmw->vma) +
-					hpage_nr_pages(pvmw->page) * PAGE_SIZE)
+					thp_size(pvmw->page))
 				return not_found(pvmw);
 			/* Did we cross page table boundary? */
 			if (pvmw->address % PMD_SIZE == 0) {
@@ -268,7 +268,7 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 	unsigned long start, end;
 
 	start = __vma_address(page, vma);
-	end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
+	end = start + thp_size(page) - PAGE_SIZE;
 
 	if (unlikely(end < vma->vm_start || start >= vma->vm_end))
 		return 0;
-- 
cgit v1.2.3


From 6c357848b44b4016ca422178aa368a7472245f6f Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:37 -0700
Subject: mm: replace hpage_nr_pages with thp_nr_pages

The thp prefix is more frequently used than hpage and we should be
consistent between the various functions.

[akpm@linux-foundation.org: fix mm/migrate.c]

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-6-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h   | 13 +++++++++----
 include/linux/mm_inline.h |  6 +++---
 include/linux/pagemap.h   |  6 +++---
 mm/compaction.c           |  2 +-
 mm/filemap.c              |  2 +-
 mm/gup.c                  |  2 +-
 mm/internal.h             |  2 +-
 mm/memcontrol.c           | 10 +++++-----
 mm/memory_hotplug.c       |  7 +++----
 mm/mempolicy.c            |  2 +-
 mm/migrate.c              | 18 +++++++++---------
 mm/mlock.c                |  9 ++++-----
 mm/page_io.c              |  2 +-
 mm/page_vma_mapped.c      |  2 +-
 mm/rmap.c                 |  8 ++++----
 mm/swap.c                 | 16 ++++++++--------
 mm/swap_state.c           |  6 +++---
 mm/swapfile.c             |  2 +-
 mm/vmscan.c               |  6 +++---
 mm/workingset.c           |  6 +++---
 20 files changed, 65 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9b33ac774fdd..229f986d535a 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -271,9 +271,14 @@ static inline unsigned int thp_order(struct page *page)
 	return 0;
 }
 
-static inline int hpage_nr_pages(struct page *page)
+/**
+ * thp_nr_pages - The number of regular pages in this huge page.
+ * @page: The head page of a huge page.
+ */
+static inline int thp_nr_pages(struct page *page)
 {
-	if (unlikely(PageTransHuge(page)))
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	if (PageHead(page))
 		return HPAGE_PMD_NR;
 	return 1;
 }
@@ -336,9 +341,9 @@ static inline unsigned int thp_order(struct page *page)
 	return 0;
 }
 
-static inline int hpage_nr_pages(struct page *page)
+static inline int thp_nr_pages(struct page *page)
 {
-	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
 	return 1;
 }
 
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 219bef41d87c..8fc71e9d7bb0 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -48,14 +48,14 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 static __always_inline void add_page_to_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
 	list_add(&page->lru, &lruvec->lists[lru]);
 }
 
 static __always_inline void add_page_to_lru_list_tail(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
 	list_add_tail(&page->lru, &lruvec->lists[lru]);
 }
 
@@ -63,7 +63,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
 	list_del(&page->lru);
-	update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page));
 }
 
 /**
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d1f4eff605ad..7de11dcd534d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -381,7 +381,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	if (PageHuge(head))
 		return head;
 
-	return head + (index & (hpage_nr_pages(head) - 1));
+	return head + (index & (thp_nr_pages(head) - 1));
 }
 
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
@@ -773,7 +773,7 @@ static inline struct page *readahead_page(struct readahead_control *rac)
 
 	page = xa_load(&rac->mapping->i_pages, rac->_index);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	rac->_batch_count = hpage_nr_pages(page);
+	rac->_batch_count = thp_nr_pages(page);
 
 	return page;
 }
@@ -796,7 +796,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(PageTail(page), page);
 		array[i++] = page;
-		rac->_batch_count += hpage_nr_pages(page);
+		rac->_batch_count += thp_nr_pages(page);
 
 		/*
 		 * The page cache isn't using multi-index entries yet,
diff --git a/mm/compaction.c b/mm/compaction.c
index b89581bf859c..176dcded298e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1009,7 +1009,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		mod_node_page_state(page_pgdat(page),
 				NR_ISOLATED_ANON + page_is_file_lru(page),
-				hpage_nr_pages(page));
+				thp_nr_pages(page));
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
diff --git a/mm/filemap.c b/mm/filemap.c
index 8e75bce0346d..653190943aa7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -198,7 +198,7 @@ static void unaccount_page_cache_page(struct address_space *mapping,
 	if (PageHuge(page))
 		return;
 
-	nr = hpage_nr_pages(page);
+	nr = thp_nr_pages(page);
 
 	__mod_lruvec_page_state(page, NR_FILE_PAGES, -nr);
 	if (PageSwapBacked(page)) {
diff --git a/mm/gup.c b/mm/gup.c
index 39e58df6925d..ae096ea7583f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1637,7 +1637,7 @@ check_again:
 					mod_node_page_state(page_pgdat(head),
 							    NR_ISOLATED_ANON +
 							    page_is_file_lru(head),
-							    hpage_nr_pages(head));
+							    thp_nr_pages(head));
 				}
 			}
 		}
diff --git a/mm/internal.h b/mm/internal.h
index 912bb1a1c10e..10c677655912 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -369,7 +369,7 @@ extern void clear_page_mlock(struct page *page);
 static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 {
 	if (TestClearPageMlocked(page)) {
-		int nr_pages = hpage_nr_pages(page);
+		int nr_pages = thp_nr_pages(page);
 
 		/* Holding pmd lock, no change in irq context: __mod is safe */
 		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9d87082e64aa..b807952b4d43 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5589,7 +5589,7 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	struct lruvec *from_vec, *to_vec;
 	struct pglist_data *pgdat;
-	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
+	unsigned int nr_pages = compound ? thp_nr_pages(page) : 1;
 	int ret;
 
 	VM_BUG_ON(from == to);
@@ -6682,7 +6682,7 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
  */
 int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 {
-	unsigned int nr_pages = hpage_nr_pages(page);
+	unsigned int nr_pages = thp_nr_pages(page);
 	struct mem_cgroup *memcg = NULL;
 	int ret = 0;
 
@@ -6912,7 +6912,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 		return;
 
 	/* Force-charge the new page. The old one will be freed soon */
-	nr_pages = hpage_nr_pages(newpage);
+	nr_pages = thp_nr_pages(newpage);
 
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
@@ -7114,7 +7114,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	 * ancestor for the swap instead and transfer the memory+swap charge.
 	 */
 	swap_memcg = mem_cgroup_id_get_online(memcg);
-	nr_entries = hpage_nr_pages(page);
+	nr_entries = thp_nr_pages(page);
 	/* Get references for the tail pages, too */
 	if (nr_entries > 1)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
@@ -7158,7 +7158,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
  */
 int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 {
-	unsigned int nr_pages = hpage_nr_pages(page);
+	unsigned int nr_pages = thp_nr_pages(page);
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
 	unsigned short oldid;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c32ead89c911..e9d5ab5d3ca0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1299,7 +1299,7 @@ static int
 do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
-	struct page *page;
+	struct page *page, *head;
 	int ret = 0;
 	LIST_HEAD(source);
 
@@ -1307,15 +1307,14 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (!pfn_valid(pfn))
 			continue;
 		page = pfn_to_page(pfn);
+		head = compound_head(page);
 
 		if (PageHuge(page)) {
-			struct page *head = compound_head(page);
 			pfn = page_to_pfn(head) + compound_nr(head) - 1;
 			isolate_huge_page(head, &source);
 			continue;
 		} else if (PageTransHuge(page))
-			pfn = page_to_pfn(compound_head(page))
-				+ hpage_nr_pages(page) - 1;
+			pfn = page_to_pfn(head) + thp_nr_pages(page) - 1;
 
 		/*
 		 * HWPoison pages have elevated reference counts so the migration would
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index afaa09ff9f6c..eddbe4e56c73 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1049,7 +1049,7 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist,
 			list_add_tail(&head->lru, pagelist);
 			mod_node_page_state(page_pgdat(head),
 				NR_ISOLATED_ANON + page_is_file_lru(head),
-				hpage_nr_pages(head));
+				thp_nr_pages(head));
 		} else if (flags & MPOL_MF_STRICT) {
 			/*
 			 * Non-movable page may reach here.  And, there may be
diff --git a/mm/migrate.c b/mm/migrate.c
index 5053439be6ab..34a842a8eb6a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -193,7 +193,7 @@ void putback_movable_pages(struct list_head *l)
 			put_page(page);
 		} else {
 			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
-					page_is_file_lru(page), -hpage_nr_pages(page));
+					page_is_file_lru(page), -thp_nr_pages(page));
 			putback_lru_page(page);
 		}
 	}
@@ -386,7 +386,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
 	 */
 	expected_count += is_device_private_page(page);
 	if (mapping)
-		expected_count += hpage_nr_pages(page) + page_has_private(page);
+		expected_count += thp_nr_pages(page) + page_has_private(page);
 
 	return expected_count;
 }
@@ -441,7 +441,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
-	page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
+	page_ref_add(newpage, thp_nr_pages(page)); /* add cache reference */
 	if (PageSwapBacked(page)) {
 		__SetPageSwapBacked(newpage);
 		if (PageSwapCache(page)) {
@@ -474,7 +474,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * to one less reference.
 	 * We know this isn't the last reference.
 	 */
-	page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
+	page_ref_unfreeze(page, expected_count - thp_nr_pages(page));
 
 	xas_unlock(&xas);
 	/* Leave irq disabled to prevent preemption while updating stats */
@@ -591,7 +591,7 @@ static void copy_huge_page(struct page *dst, struct page *src)
 	} else {
 		/* thp page */
 		BUG_ON(!PageTransHuge(src));
-		nr_pages = hpage_nr_pages(src);
+		nr_pages = thp_nr_pages(src);
 	}
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1213,7 +1213,7 @@ out:
 		 */
 		if (likely(!__PageMovable(page)))
 			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
-					page_is_file_lru(page), -hpage_nr_pages(page));
+					page_is_file_lru(page), -thp_nr_pages(page));
 	}
 
 	/*
@@ -1446,7 +1446,7 @@ retry:
 			 * during migration.
 			 */
 			is_thp = PageTransHuge(page);
-			nr_subpages = hpage_nr_pages(page);
+			nr_subpages = thp_nr_pages(page);
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1670,7 +1670,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		list_add_tail(&head->lru, pagelist);
 		mod_node_page_state(page_pgdat(head),
 			NR_ISOLATED_ANON + page_is_file_lru(head),
-			hpage_nr_pages(head));
+			thp_nr_pages(head));
 	}
 out_putpage:
 	/*
@@ -2034,7 +2034,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 
 	page_lru = page_is_file_lru(page);
 	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
-				hpage_nr_pages(page));
+				thp_nr_pages(page));
 
 	/*
 	 * Isolating the page has taken another reference, so the
diff --git a/mm/mlock.c b/mm/mlock.c
index f8736136fad7..93ca2bf30b4f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -61,8 +61,7 @@ void clear_page_mlock(struct page *page)
 	if (!TestClearPageMlocked(page))
 		return;
 
-	mod_zone_page_state(page_zone(page), NR_MLOCK,
-			    -hpage_nr_pages(page));
+	mod_zone_page_state(page_zone(page), NR_MLOCK, -thp_nr_pages(page));
 	count_vm_event(UNEVICTABLE_PGCLEARED);
 	/*
 	 * The previous TestClearPageMlocked() corresponds to the smp_mb()
@@ -95,7 +94,7 @@ void mlock_vma_page(struct page *page)
 
 	if (!TestSetPageMlocked(page)) {
 		mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    hpage_nr_pages(page));
+				    thp_nr_pages(page));
 		count_vm_event(UNEVICTABLE_PGMLOCKED);
 		if (!isolate_lru_page(page))
 			putback_lru_page(page);
@@ -192,7 +191,7 @@ unsigned int munlock_vma_page(struct page *page)
 	/*
 	 * Serialize with any parallel __split_huge_page_refcount() which
 	 * might otherwise copy PageMlocked to part of the tail pages before
-	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
+	 * we clear it in the head page. It also stabilizes thp_nr_pages().
 	 */
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -202,7 +201,7 @@ unsigned int munlock_vma_page(struct page *page)
 		goto unlock_out;
 	}
 
-	nr_pages = hpage_nr_pages(page);
+	nr_pages = thp_nr_pages(page);
 	__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
 
 	if (__munlock_isolate_lru_page(page, true)) {
diff --git a/mm/page_io.c b/mm/page_io.c
index f5e8bec8a8c7..454b70d8cda7 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -274,7 +274,7 @@ static inline void count_swpout_vm_event(struct page *page)
 	if (unlikely(PageTransHuge(page)))
 		count_vm_event(THP_SWPOUT);
 #endif
-	count_vm_events(PSWPOUT, hpage_nr_pages(page));
+	count_vm_events(PSWPOUT, thp_nr_pages(page));
 }
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index e65629c056e8..5e77b269c330 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -61,7 +61,7 @@ static inline bool pfn_is_match(struct page *page, unsigned long pfn)
 		return page_pfn == pfn;
 
 	/* THP can be referenced by any subpage */
-	return pfn >= page_pfn && pfn - page_pfn < hpage_nr_pages(page);
+	return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page);
 }
 
 /**
diff --git a/mm/rmap.c b/mm/rmap.c
index 6cce9ef06753..4ace1e32f705 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1130,7 +1130,7 @@ void do_page_add_anon_rmap(struct page *page,
 	}
 
 	if (first) {
-		int nr = compound ? hpage_nr_pages(page) : 1;
+		int nr = compound ? thp_nr_pages(page) : 1;
 		/*
 		 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 		 * these counters are not modified in interrupt context, and
@@ -1169,7 +1169,7 @@ void do_page_add_anon_rmap(struct page *page,
 void page_add_new_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, bool compound)
 {
-	int nr = compound ? hpage_nr_pages(page) : 1;
+	int nr = compound ? thp_nr_pages(page) : 1;
 
 	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 	__SetPageSwapBacked(page);
@@ -1860,7 +1860,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc,
 		return;
 
 	pgoff_start = page_to_pgoff(page);
-	pgoff_end = pgoff_start + hpage_nr_pages(page) - 1;
+	pgoff_end = pgoff_start + thp_nr_pages(page) - 1;
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
 			pgoff_start, pgoff_end) {
 		struct vm_area_struct *vma = avc->vma;
@@ -1913,7 +1913,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc,
 		return;
 
 	pgoff_start = page_to_pgoff(page);
-	pgoff_end = pgoff_start + hpage_nr_pages(page) - 1;
+	pgoff_end = pgoff_start + thp_nr_pages(page) - 1;
 	if (!locked)
 		i_mmap_lock_read(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap,
diff --git a/mm/swap.c b/mm/swap.c
index 9285e60c7d6e..d26c22baf7c5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -241,7 +241,7 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		ClearPageActive(page);
 		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
-		(*pgmoved) += hpage_nr_pages(page);
+		(*pgmoved) += thp_nr_pages(page);
 	}
 }
 
@@ -312,7 +312,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 void lru_note_cost_page(struct page *page)
 {
 	lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)),
-		      page_is_file_lru(page), hpage_nr_pages(page));
+		      page_is_file_lru(page), thp_nr_pages(page));
 }
 
 static void __activate_page(struct page *page, struct lruvec *lruvec,
@@ -320,7 +320,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
 {
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
-		int nr_pages = hpage_nr_pages(page);
+		int nr_pages = thp_nr_pages(page);
 
 		del_page_from_lru_list(page, lruvec, lru);
 		SetPageActive(page);
@@ -500,7 +500,7 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 		 * lock is held(spinlock), which implies preemption disabled.
 		 */
 		__mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    hpage_nr_pages(page));
+				    thp_nr_pages(page));
 		count_vm_event(UNEVICTABLE_PGMLOCKED);
 	}
 	lru_cache_add(page);
@@ -532,7 +532,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
 {
 	int lru;
 	bool active;
-	int nr_pages = hpage_nr_pages(page);
+	int nr_pages = thp_nr_pages(page);
 
 	if (!PageLRU(page))
 		return;
@@ -580,7 +580,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
 {
 	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
-		int nr_pages = hpage_nr_pages(page);
+		int nr_pages = thp_nr_pages(page);
 
 		del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
 		ClearPageActive(page);
@@ -599,7 +599,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
-		int nr_pages = hpage_nr_pages(page);
+		int nr_pages = thp_nr_pages(page);
 
 		del_page_from_lru_list(page, lruvec,
 				       LRU_INACTIVE_ANON + active);
@@ -972,7 +972,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 {
 	enum lru_list lru;
 	int was_unevictable = TestClearPageUnevictable(page);
-	int nr_pages = hpage_nr_pages(page);
+	int nr_pages = thp_nr_pages(page);
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index b73aabdfd35a..d9d4a49f3241 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -130,7 +130,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry,
 	struct address_space *address_space = swap_address_space(entry);
 	pgoff_t idx = swp_offset(entry);
 	XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page));
-	unsigned long i, nr = hpage_nr_pages(page);
+	unsigned long i, nr = thp_nr_pages(page);
 	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -183,7 +183,7 @@ void __delete_from_swap_cache(struct page *page,
 			swp_entry_t entry, void *shadow)
 {
 	struct address_space *address_space = swap_address_space(entry);
-	int i, nr = hpage_nr_pages(page);
+	int i, nr = thp_nr_pages(page);
 	pgoff_t idx = swp_offset(entry);
 	XA_STATE(xas, &address_space->i_pages, idx);
 
@@ -278,7 +278,7 @@ void delete_from_swap_cache(struct page *page)
 	xa_unlock_irq(&address_space->i_pages);
 
 	put_swap_page(page, entry);
-	page_ref_sub(page, hpage_nr_pages(page));
+	page_ref_sub(page, thp_nr_pages(page));
 }
 
 void clear_shadow_from_swap_cache(int type, unsigned long begin,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e653eea1eb88..eb410d3c8de8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1370,7 +1370,7 @@ void put_swap_page(struct page *page, swp_entry_t entry)
 	unsigned char *map;
 	unsigned int i, free_entries = 0;
 	unsigned char val;
-	int size = swap_entry_size(hpage_nr_pages(page));
+	int size = swap_entry_size(thp_nr_pages(page));
 
 	si = _swap_info_get(entry);
 	if (!si)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 738115ed75e2..99e1796eb833 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1354,7 +1354,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			case PAGE_ACTIVATE:
 				goto activate_locked;
 			case PAGE_SUCCESS:
-				stat->nr_pageout += hpage_nr_pages(page);
+				stat->nr_pageout += thp_nr_pages(page);
 
 				if (PageWriteback(page))
 					goto keep;
@@ -1862,7 +1862,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		SetPageLRU(page);
 		lru = page_lru(page);
 
-		nr_pages = hpage_nr_pages(page);
+		nr_pages = thp_nr_pages(page);
 		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
 		list_move(&page->lru, &lruvec->lists[lru]);
 
@@ -2065,7 +2065,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			 * so we ignore them here.
 			 */
 			if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) {
-				nr_rotated += hpage_nr_pages(page);
+				nr_rotated += thp_nr_pages(page);
 				list_add(&page->lru, &l_active);
 				continue;
 			}
diff --git a/mm/workingset.c b/mm/workingset.c
index 8cbe4e3cbe5c..92e66113a577 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -263,7 +263,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
-	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
+	workingset_age_nonresident(lruvec, thp_nr_pages(page));
 	/* XXX: target_memcg can be NULL, go through lruvec */
 	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
 	eviction = atomic_long_read(&lruvec->nonresident_age);
@@ -374,7 +374,7 @@ void workingset_refault(struct page *page, void *shadow)
 		goto out;
 
 	SetPageActive(page);
-	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
+	workingset_age_nonresident(lruvec, thp_nr_pages(page));
 	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
 
 	/* Page was active prior to eviction */
@@ -411,7 +411,7 @@ void workingset_activation(struct page *page)
 	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
 	lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
+	workingset_age_nonresident(lruvec, thp_nr_pages(page));
 out:
 	rcu_read_unlock();
 }
-- 
cgit v1.2.3


From 2be1d71841b7ecfb01ce4c59f6e1d082c3c18a8a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:40 -0700
Subject: mm: add thp_head

This is like compound_head() but compiles away when
CONFIG_TRANSPARENT_HUGEPAGE is not enabled.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-7-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 229f986d535a..8a8bc46a2432 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -259,6 +259,15 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 		return NULL;
 }
 
+/**
+ * thp_head - Head page of a transparent huge page.
+ * @page: Any page (tail, head or regular) found in the page cache.
+ */
+static inline struct page *thp_head(struct page *page)
+{
+	return compound_head(page);
+}
+
 /**
  * thp_order - Order of a transparent huge page.
  * @page: Head page of a transparent huge page.
@@ -335,6 +344,12 @@ static inline struct list_head *page_deferred_list(struct page *page)
 #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
 #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
 
+static inline struct page *thp_head(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	return page;
+}
+
 static inline unsigned int thp_order(struct page *page)
 {
 	VM_BUG_ON_PGFLAGS(PageTail(page), page);
-- 
cgit v1.2.3


From ee6c400f5c05459b8c5f2884a176a1287ce2f68f Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 14 Aug 2020 17:30:43 -0700
Subject: mm: introduce offset_in_thp

Mirroring offset_in_page(), this gives you the offset within this
particular page, no matter what size page it is.  It optimises down to
offset_in_page() if CONFIG_TRANSPARENT_HUGEPAGE is not set.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20200629151959.15779-8-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fd0cd4e93029..2e7ec3ee34cf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1594,6 +1594,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
 extern void pagefault_out_of_memory(void);
 
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
+#define offset_in_thp(page, p)	((unsigned long)(p) & (thp_size(page) - 1))
 
 /*
  * Flags passed to show_mem() and show_free_areas() to suppress output in
-- 
cgit v1.2.3


From 88db0aa2421666d2f73486d15b239a4521983d55 Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Fri, 14 Aug 2020 17:31:07 -0700
Subject: all arch: remove system call sys_sysctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 61a47c1ad3a4dc ("sysctl: Remove the sysctl system call"),
sys_sysctl is actually unavailable: any input can only return an error.

We have been warning about people using the sysctl system call for years
and believe there are no more users.  Even if there are users of this
interface if they have not complained or fixed their code by now they
probably are not going to, so there is no point in warning them any
longer.

So completely remove sys_sysctl on all architectures.

[nixiaoming@huawei.com: s390: fix build error for sys_call_table_emu]
 Link: http://lkml.kernel.org/r/20200618141426.16884-1-nixiaoming@huawei.com

Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Will Deacon <will@kernel.org>		[arm/arm64]
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bin Meng <bin.meng@windriver.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: chenzefeng <chenzefeng2@huawei.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Chris Zankel <chris@zankel.net>
Cc: David Howells <dhowells@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Diego Elio Pettenò <flameeyes@flameeyes.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kars de Jong <jongk@linux-m68k.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Paul Burton <paulburton@kernel.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Sven Schnelle <svens@stackframe.org>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Zhou Yanjie <zhouyanjie@wanyeetech.com>
Link: http://lkml.kernel.org/r/20200616030734.87257-1-nixiaoming@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl             |   2 +-
 arch/arm/configs/am200epdkit_defconfig             |   1 -
 arch/arm/tools/syscall.tbl                         |   2 +-
 arch/arm64/include/asm/unistd32.h                  |   4 +-
 arch/ia64/kernel/syscalls/syscall.tbl              |   2 +-
 arch/m68k/kernel/syscalls/syscall.tbl              |   2 +-
 arch/microblaze/kernel/syscalls/syscall.tbl        |   2 +-
 arch/mips/configs/cu1000-neo_defconfig             |   1 -
 arch/mips/kernel/syscalls/syscall_n32.tbl          |   2 +-
 arch/mips/kernel/syscalls/syscall_n64.tbl          |   2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |   2 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |   2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |   2 +-
 arch/s390/kernel/syscalls/syscall.tbl              |   2 +-
 arch/sh/configs/dreamcast_defconfig                |   1 -
 arch/sh/configs/espt_defconfig                     |   1 -
 arch/sh/configs/hp6xx_defconfig                    |   1 -
 arch/sh/configs/landisk_defconfig                  |   1 -
 arch/sh/configs/lboxre2_defconfig                  |   1 -
 arch/sh/configs/microdev_defconfig                 |   1 -
 arch/sh/configs/migor_defconfig                    |   1 -
 arch/sh/configs/r7780mp_defconfig                  |   1 -
 arch/sh/configs/r7785rp_defconfig                  |   1 -
 arch/sh/configs/rts7751r2d1_defconfig              |   1 -
 arch/sh/configs/rts7751r2dplus_defconfig           |   1 -
 arch/sh/configs/se7206_defconfig                   |   1 -
 arch/sh/configs/se7343_defconfig                   |   1 -
 arch/sh/configs/se7619_defconfig                   |   1 -
 arch/sh/configs/se7705_defconfig                   |   1 -
 arch/sh/configs/se7750_defconfig                   |   1 -
 arch/sh/configs/se7751_defconfig                   |   1 -
 arch/sh/configs/secureedge5410_defconfig           |   1 -
 arch/sh/configs/sh03_defconfig                     |   1 -
 arch/sh/configs/sh7710voipgw_defconfig             |   1 -
 arch/sh/configs/sh7757lcr_defconfig                |   1 -
 arch/sh/configs/sh7763rdp_defconfig                |   1 -
 arch/sh/configs/shmin_defconfig                    |   1 -
 arch/sh/configs/titan_defconfig                    |   1 -
 arch/sh/kernel/syscalls/syscall.tbl                |   2 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |   2 +-
 arch/x86/entry/syscalls/syscall_32.tbl             |   2 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |   2 +-
 arch/xtensa/kernel/syscalls/syscall.tbl            |   2 +-
 include/linux/compat.h                             |   1 -
 include/linux/syscalls.h                           |   2 -
 include/linux/sysctl.h                             |   6 +-
 kernel/Makefile                                    |   2 +-
 kernel/sys_ni.c                                    |   1 -
 kernel/sysctl_binary.c                             | 171 ---------------------
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |   2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |   2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |   2 +-
 52 files changed, 24 insertions(+), 227 deletions(-)
 delete mode 100644 kernel/sysctl_binary.c

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index a28fb211881d..ec8bed9e7b75 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -249,7 +249,7 @@
 316	common	mlockall			sys_mlockall
 317	common	munlockall			sys_munlockall
 318	common	sysinfo				sys_sysinfo
-319	common	_sysctl				sys_sysctl
+319	common	_sysctl				sys_ni_syscall
 # 320 was sys_idle
 321	common	oldumount			sys_oldumount
 322	common	swapon				sys_swapon
diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig
index f56ac394caf1..4e49d6cb2f62 100644
--- a/arch/arm/configs/am200epdkit_defconfig
+++ b/arch/arm/configs/am200epdkit_defconfig
@@ -3,7 +3,6 @@ CONFIG_LOCALVERSION="gum"
 CONFIG_SYSVIPC=y
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_EXPERT=y
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 7e8ee4adf269..171077cbf419 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -162,7 +162,7 @@
 146	common	writev			sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
-149	common	_sysctl			sys_sysctl
+149	common	_sysctl			sys_ni_syscall
 150	common	mlock			sys_mlock
 151	common	munlock			sys_munlock
 152	common	mlockall		sys_mlockall
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 17e81bd9a2d3..734860ac7cf9 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -308,8 +308,8 @@ __SYSCALL(__NR_writev, compat_sys_writev)
 __SYSCALL(__NR_getsid, sys_getsid)
 #define __NR_fdatasync 148
 __SYSCALL(__NR_fdatasync, sys_fdatasync)
-#define __NR__sysctl 149
-__SYSCALL(__NR__sysctl, compat_sys_sysctl)
+			/* 149 was sys_sysctl */
+__SYSCALL(149, sys_ni_syscall)
 #define __NR_mlock 150
 __SYSCALL(__NR_mlock, sys_mlock)
 #define __NR_munlock 151
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ced9c83e47c9..f52a41f4c340 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -135,7 +135,7 @@
 123	common	writev				sys_writev
 124	common	pread64				sys_pread64
 125	common	pwrite64			sys_pwrite64
-126	common	_sysctl				sys_sysctl
+126	common	_sysctl				sys_ni_syscall
 127	common	mmap				sys_mmap
 128	common	munmap				sys_munmap
 129	common	mlock				sys_mlock
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 1a4822de7292..81fc799d8392 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index a3f4be8e7238..b4e263916f41 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig
index 6b471cdb16cf..e924c817f73d 100644
--- a/arch/mips/configs/cu1000-neo_defconfig
+++ b/arch/mips/configs/cu1000-neo_defconfig
@@ -17,7 +17,6 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 6b4ee92e3aed..f9df9edb67a4 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -159,7 +159,7 @@
 149	n32	munlockall			sys_munlockall
 150	n32	vhangup				sys_vhangup
 151	n32	pivot_root			sys_pivot_root
-152	n32	_sysctl				compat_sys_sysctl
+152	n32	_sysctl				sys_ni_syscall
 153	n32	prctl				sys_prctl
 154	n32	adjtimex			sys_adjtimex_time32
 155	n32	setrlimit			compat_sys_setrlimit
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 391acbf425a0..557f9954a2b9 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -159,7 +159,7 @@
 149	n64	munlockall			sys_munlockall
 150	n64	vhangup				sys_vhangup
 151	n64	pivot_root			sys_pivot_root
-152	n64	_sysctl				sys_sysctl
+152	n64	_sysctl				sys_ni_syscall
 153	n64	prctl				sys_prctl
 154	n64	adjtimex			sys_adjtimex
 155	n64	setrlimit			sys_setrlimit
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 5727c5187508..195b43cf27c8 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -164,7 +164,7 @@
 150	o32	unused150			sys_ni_syscall
 151	o32	getsid				sys_getsid
 152	o32	fdatasync			sys_fdatasync
-153	o32	_sysctl				sys_sysctl			compat_sys_sysctl
+153	o32	_sysctl				sys_ni_syscall
 154	o32	mlock				sys_mlock
 155	o32	munlock				sys_munlock
 156	o32	mlockall			sys_mlockall
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 292baabefade..def64d221cd4 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -163,7 +163,7 @@
 146	common	writev			sys_writev			compat_sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
-149	common	_sysctl			sys_sysctl			compat_sys_sysctl
+149	common	_sysctl			sys_ni_syscall
 150	common	mlock			sys_mlock
 151	common	munlock			sys_munlock
 152	common	mlockall		sys_mlockall
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index be9f74546068..c2d737ff2e7b 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -197,7 +197,7 @@
 146	common	writev				sys_writev			compat_sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+149	nospu	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index f1fda4375526..10456bc936fb 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -138,7 +138,7 @@
 146  common	writev			sys_writev			compat_sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
-149  common	_sysctl			sys_sysctl			compat_sys_sysctl
+149  common	_sysctl			-				-
 150  common	mlock			sys_mlock			sys_mlock
 151  common	munlock			sys_munlock			sys_munlock
 152  common	mlockall		sys_mlockall			sys_mlockall
diff --git a/arch/sh/configs/dreamcast_defconfig b/arch/sh/configs/dreamcast_defconfig
index ae067e0b15e3..6a82c7b8ff32 100644
--- a/arch/sh/configs/dreamcast_defconfig
+++ b/arch/sh/configs/dreamcast_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index a5b865a75d22..9a988c347e9d 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
 CONFIG_IPC_NS=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index a92db6694ce2..70e6605d7f7e 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -3,7 +3,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH7709=y
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index 567af752b1bb..ba6ec042606f 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 10f6d371ce2c..05e4ac6fed5f 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig
index ed84d1303acf..c65667d00313 100644
--- a/arch/sh/configs/microdev_defconfig
+++ b/arch/sh/configs/microdev_defconfig
@@ -2,7 +2,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH4_202=y
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index 37e9521a99e5..a24cf8cd2cea 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -4,7 +4,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index c97ec60cff27..e922659fdadb 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 CONFIG_SLAB=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index 55fce65eb454..5978866358ec 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -7,7 +7,6 @@ CONFIG_RCU_TRACE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index 6a3cfe08295f..fc9c22152b08 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index 2b3d7d280672..ff3fd6787fd6 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 21a43f14ffac..ff5bb4489922 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -18,7 +18,6 @@ CONFIG_USER_NS=y
 CONFIG_PID_NS=y
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_ELF_CORE is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index 4e794e719a28..5d6c19338ebf 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -2,7 +2,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
diff --git a/arch/sh/configs/se7619_defconfig b/arch/sh/configs/se7619_defconfig
index 3264415a5931..71a672c30716 100644
--- a/arch/sh/configs/se7619_defconfig
+++ b/arch/sh/configs/se7619_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 # CONFIG_ELF_CORE is not set
diff --git a/arch/sh/configs/se7705_defconfig b/arch/sh/configs/se7705_defconfig
index 4496b94b7d88..ed00a6eeadf5 100644
--- a/arch/sh/configs/se7705_defconfig
+++ b/arch/sh/configs/se7705_defconfig
@@ -2,7 +2,6 @@
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig
index b23f67542728..3f1c13799d79 100644
--- a/arch/sh/configs/se7750_defconfig
+++ b/arch/sh/configs/se7750_defconfig
@@ -5,7 +5,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig
index 162343683937..4a024065bb75 100644
--- a/arch/sh/configs/se7751_defconfig
+++ b/arch/sh/configs/se7751_defconfig
@@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/secureedge5410_defconfig b/arch/sh/configs/secureedge5410_defconfig
index 360592d63a2f..8422599cfb04 100644
--- a/arch/sh/configs/secureedge5410_defconfig
+++ b/arch/sh/configs/secureedge5410_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 87db9a84b5ec..f0073ed39947 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -3,7 +3,6 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=m
diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig
index 08426913c0e3..0d814770b07f 100644
--- a/arch/sh/configs/sh7710voipgw_defconfig
+++ b/arch/sh/configs/sh7710voipgw_defconfig
@@ -2,7 +2,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig
index d0933a9b9799..a2700ab165af 100644
--- a/arch/sh/configs/sh7757lcr_defconfig
+++ b/arch/sh/configs/sh7757lcr_defconfig
@@ -8,7 +8,6 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_ALL=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index d0a0aa74cecf..26c5fd02c87a 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
 CONFIG_IPC_NS=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig
index a27b129b93c5..c0b6f40d01cc 100644
--- a/arch/sh/configs/shmin_defconfig
+++ b/arch/sh/configs/shmin_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 # CONFIG_BUG is not set
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 4ec961ace688..ba887f1351be 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -6,7 +6,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 96848db9659e..ae0a00beea5f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 46024e80ee86..4af114e84f20 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -300,7 +300,7 @@
 249	64	nanosleep		sys_nanosleep
 250	32	mremap			sys_mremap
 250	64	mremap			sys_64_mremap
-251	common	_sysctl			sys_sysctl			compat_sys_sysctl
+251	common	_sysctl			sys_ni_syscall
 252	common	getsid			sys_getsid
 253	common	fdatasync		sys_fdatasync
 254	32	nfsservctl		sys_ni_syscall			sys_nis_syscall
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index e31a75262c9c..9d1102873666 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -160,7 +160,7 @@
 146	i386	writev			sys_writev			compat_sys_writev
 147	i386	getsid			sys_getsid
 148	i386	fdatasync		sys_fdatasync
-149	i386	_sysctl			sys_sysctl			compat_sys_sysctl
+149	i386	_sysctl			sys_ni_syscall
 150	i386	mlock			sys_mlock
 151	i386	munlock			sys_munlock
 152	i386	mlockall		sys_mlockall
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9d82078c949a..f30d6ae9a688 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -164,7 +164,7 @@
 153	common	vhangup			sys_vhangup
 154	common	modify_ldt		sys_modify_ldt
 155	common	pivot_root		sys_pivot_root
-156	64	_sysctl			sys_sysctl
+156	64	_sysctl			sys_ni_syscall
 157	common	prctl			sys_prctl
 158	common	arch_prctl		sys_arch_prctl
 159	common	adjtimex		sys_adjtimex
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index d216ccba42f7..6276e3c2d3fc 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -222,7 +222,7 @@
 204	common	quotactl			sys_quotactl
 # 205 was old nfsservctl
 205	common	nfsservctl			sys_ni_syscall
-206	common	_sysctl				sys_sysctl
+206	common	_sysctl				sys_ni_syscall
 207	common	bdflush				sys_bdflush
 208	common	uname				sys_newuname
 209	common	sysinfo				sys_sysinfo
diff --git a/include/linux/compat.h b/include/linux/compat.h
index c4255d8a4a8a..d38c4d7e83bd 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -851,7 +851,6 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len,
 				unsigned flags);
-asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args);
 
 /* obsolete: fs/readdir.c */
 asmlinkage long compat_sys_old_readdir(unsigned int fd,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index dc2b827c81e5..75ac7f8ae93c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -47,7 +47,6 @@ struct stat64;
 struct statfs;
 struct statfs64;
 struct statx;
-struct __sysctl_args;
 struct sysinfo;
 struct timespec;
 struct __kernel_old_timeval;
@@ -1117,7 +1116,6 @@ asmlinkage long sys_send(int, void __user *, size_t, unsigned);
 asmlinkage long sys_bdflush(int func, long data);
 asmlinkage long sys_oldumount(char __user *name);
 asmlinkage long sys_uselib(const char __user *library);
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args);
 asmlinkage long sys_sysfs(int option,
 				unsigned long arg1, unsigned long arg2);
 asmlinkage long sys_fork(void);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 50bb7f383a1b..51298a4f4623 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -74,15 +74,13 @@ int proc_do_static_key(struct ctl_table *table, int write, void *buffer,
  * sysctl names can be mirrored automatically under /proc/sys.  The
  * procname supplied controls /proc naming.
  *
- * The table's mode will be honoured both for sys_sysctl(2) and
- * proc-fs access.
+ * The table's mode will be honoured for proc-fs access.
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
  * under /proc; non-leaf nodes will be represented by directories.  A
  * null procname disables /proc mirroring at this node.
  *
- * sysctl(2) can automatically manage read and write requests through
- * the sysctl table.  The data and maxlen fields of the ctl_table
+ * The data and maxlen fields of the ctl_table
  * struct enable minimal validation of the values being written to be
  * performed, and the mode field allows minimal authentication.
  * 
diff --git a/kernel/Makefile b/kernel/Makefile
index b3da548691c9..9a20016d4900 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -5,7 +5,7 @@
 
 obj-y     = fork.o exec_domain.o panic.o \
 	    cpu.o exit.o softirq.o resource.o \
-	    sysctl.o sysctl_binary.o capability.o ptrace.o user.o \
+	    sysctl.o capability.o ptrace.o user.o \
 	    signal.o sys.o umh.o workqueue.o pid.o task_work.o \
 	    extable.o params.o \
 	    kthread.o sys_ni.o nsproxy.o \
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 3b69a560a7ac..4d59775ea79c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -364,7 +364,6 @@ COND_SYSCALL(socketcall);
 COND_SYSCALL_COMPAT(socketcall);
 
 /* compat syscalls for arm64, x86, ... */
-COND_SYSCALL_COMPAT(sysctl);
 COND_SYSCALL_COMPAT(fanotify_mark);
 
 /* x86 */
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
deleted file mode 100644
index 7d550cc76a3b..000000000000
--- a/kernel/sysctl_binary.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stat.h>
-#include <linux/sysctl.h>
-#include "../fs/xfs/xfs_sysctl.h"
-#include <linux/sunrpc/debug.h>
-#include <linux/string.h>
-#include <linux/syscalls.h>
-#include <linux/namei.h>
-#include <linux/mount.h>
-#include <linux/fs.h>
-#include <linux/nsproxy.h>
-#include <linux/pid_namespace.h>
-#include <linux/file.h>
-#include <linux/ctype.h>
-#include <linux/netdevice.h>
-#include <linux/kernel.h>
-#include <linux/uuid.h>
-#include <linux/slab.h>
-#include <linux/compat.h>
-
-static ssize_t binary_sysctl(const int *name, int nlen,
-	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
-{
-	return -ENOSYS;
-}
-
-static void deprecated_sysctl_warning(const int *name, int nlen)
-{
-	int i;
-
-	/*
-	 * CTL_KERN/KERN_VERSION is used by older glibc and cannot
-	 * ever go away.
-	 */
-	if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION)
-		return;
-
-	if (printk_ratelimit()) {
-		printk(KERN_INFO
-			"warning: process `%s' used the deprecated sysctl "
-			"system call with ", current->comm);
-		for (i = 0; i < nlen; i++)
-			printk(KERN_CONT "%d.", name[i]);
-		printk(KERN_CONT "\n");
-	}
-	return;
-}
-
-#define WARN_ONCE_HASH_BITS 8
-#define WARN_ONCE_HASH_SIZE (1<<WARN_ONCE_HASH_BITS)
-
-static DECLARE_BITMAP(warn_once_bitmap, WARN_ONCE_HASH_SIZE);
-
-#define FNV32_OFFSET 2166136261U
-#define FNV32_PRIME 0x01000193
-
-/*
- * Print each legacy sysctl (approximately) only once.
- * To avoid making the tables non-const use a external
- * hash-table instead.
- * Worst case hash collision: 6, but very rarely.
- * NOTE! We don't use the SMP-safe bit tests. We simply
- * don't care enough.
- */
-static void warn_on_bintable(const int *name, int nlen)
-{
-	int i;
-	u32 hash = FNV32_OFFSET;
-
-	for (i = 0; i < nlen; i++)
-		hash = (hash ^ name[i]) * FNV32_PRIME;
-	hash %= WARN_ONCE_HASH_SIZE;
-	if (__test_and_set_bit(hash, warn_once_bitmap))
-		return;
-	deprecated_sysctl_warning(name, nlen);
-}
-
-static ssize_t do_sysctl(int __user *args_name, int nlen,
-	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
-{
-	int name[CTL_MAXNAME];
-	int i;
-
-	/* Check args->nlen. */
-	if (nlen < 0 || nlen > CTL_MAXNAME)
-		return -ENOTDIR;
-	/* Read in the sysctl name for simplicity */
-	for (i = 0; i < nlen; i++)
-		if (get_user(name[i], args_name + i))
-			return -EFAULT;
-
-	warn_on_bintable(name, nlen);
-
-	return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen);
-}
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
-	struct __sysctl_args tmp;
-	size_t oldlen = 0;
-	ssize_t result;
-
-	if (copy_from_user(&tmp, args, sizeof(tmp)))
-		return -EFAULT;
-
-	if (tmp.oldval && !tmp.oldlenp)
-		return -EFAULT;
-
-	if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp))
-		return -EFAULT;
-
-	result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen,
-			   tmp.newval, tmp.newlen);
-
-	if (result >= 0) {
-		oldlen = result;
-		result = 0;
-	}
-
-	if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp))
-		return -EFAULT;
-
-	return result;
-}
-
-
-#ifdef CONFIG_COMPAT
-
-struct compat_sysctl_args {
-	compat_uptr_t	name;
-	int		nlen;
-	compat_uptr_t	oldval;
-	compat_uptr_t	oldlenp;
-	compat_uptr_t	newval;
-	compat_size_t	newlen;
-	compat_ulong_t	__unused[4];
-};
-
-COMPAT_SYSCALL_DEFINE1(sysctl, struct compat_sysctl_args __user *, args)
-{
-	struct compat_sysctl_args tmp;
-	compat_size_t __user *compat_oldlenp;
-	size_t oldlen = 0;
-	ssize_t result;
-
-	if (copy_from_user(&tmp, args, sizeof(tmp)))
-		return -EFAULT;
-
-	if (tmp.oldval && !tmp.oldlenp)
-		return -EFAULT;
-
-	compat_oldlenp = compat_ptr(tmp.oldlenp);
-	if (compat_oldlenp && get_user(oldlen, compat_oldlenp))
-		return -EFAULT;
-
-	result = do_sysctl(compat_ptr(tmp.name), tmp.nlen,
-			   compat_ptr(tmp.oldval), oldlen,
-			   compat_ptr(tmp.newval), tmp.newlen);
-
-	if (result >= 0) {
-		oldlen = result;
-		result = 0;
-	}
-
-	if (compat_oldlenp && put_user(oldlen, compat_oldlenp))
-		return -EFAULT;
-
-	return result;
-}
-
-#endif /* CONFIG_COMPAT */
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index b190f2eb2611..3ca6fe057a0b 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -193,7 +193,7 @@
 146	common	writev				sys_writev			compat_sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+149	nospu	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 56ae24b6e4be..6a0bbea225db 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -138,7 +138,7 @@
 146  common	writev			sys_writev			compat_sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
-149  common	_sysctl			sys_sysctl			compat_sys_sysctl
+149  common	_sysctl			-				-
 150  common	mlock			sys_mlock			compat_sys_mlock
 151  common	munlock			sys_munlock			compat_sys_munlock
 152  common	mlockall		sys_mlockall			sys_mlockall
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 9d82078c949a..f30d6ae9a688 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -164,7 +164,7 @@
 153	common	vhangup			sys_vhangup
 154	common	modify_ldt		sys_modify_ldt
 155	common	pivot_root		sys_pivot_root
-156	64	_sysctl			sys_sysctl
+156	64	_sysctl			sys_ni_syscall
 157	common	prctl			sys_prctl
 158	common	arch_prctl		sys_arch_prctl
 159	common	adjtimex		sys_adjtimex
-- 
cgit v1.2.3


From e0e3f42fd96cf830c61aa720f0abb4eef41c5ce3 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Fri, 14 Aug 2020 17:31:37 -0700
Subject: mm/memcontrol: fix a data race in scan count

struct mem_cgroup_per_node mz.lru_zone_size[zone_idx][lru] could be
accessed concurrently as noticed by KCSAN,

 BUG: KCSAN: data-race in lruvec_lru_size / mem_cgroup_update_lru_size

 write to 0xffff9c804ca285f8 of 8 bytes by task 50951 on cpu 12:
  mem_cgroup_update_lru_size+0x11c/0x1d0
  mem_cgroup_update_lru_size at mm/memcontrol.c:1266
  isolate_lru_pages+0x6a9/0xf30
  shrink_active_list+0x123/0xcc0
  shrink_lruvec+0x8fd/0x1380
  shrink_node+0x317/0xd80
  do_try_to_free_pages+0x1f7/0xa10
  try_to_free_pages+0x26c/0x5e0
  __alloc_pages_slowpath+0x458/0x1290
  __alloc_pages_nodemask+0x3bb/0x450
  alloc_pages_vma+0x8a/0x2c0
  do_anonymous_page+0x170/0x700
  __handle_mm_fault+0xc9f/0xd00
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 read to 0xffff9c804ca285f8 of 8 bytes by task 50964 on cpu 95:
  lruvec_lru_size+0xbb/0x270
  mem_cgroup_get_zone_lru_size at include/linux/memcontrol.h:536
  (inlined by) lruvec_lru_size at mm/vmscan.c:326
  shrink_lruvec+0x1d0/0x1380
  shrink_node+0x317/0xd80
  do_try_to_free_pages+0x1f7/0xa10
  try_to_free_pages+0x26c/0x5e0
  __alloc_pages_slowpath+0x458/0x1290
  __alloc_pages_nodemask+0x3bb/0x450
  alloc_pages_current+0xa6/0x120
  alloc_slab_page+0x3b1/0x540
  allocate_slab+0x70/0x660
  new_slab+0x46/0x70
  ___slab_alloc+0x4ad/0x7d0
  __slab_alloc+0x43/0x70
  kmem_cache_alloc+0x2c3/0x420
  getname_flags+0x4c/0x230
  getname+0x22/0x30
  do_sys_openat2+0x205/0x3b0
  do_sys_open+0x9a/0xf0
  __x64_sys_openat+0x62/0x80
  do_syscall_64+0x91/0xb47
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

 Reported by Kernel Concurrency Sanitizer on:
 CPU: 95 PID: 50964 Comm: cc1 Tainted: G        W  O L    5.5.0-next-20200204+ #6
 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019

The write is under lru_lock, but the read is done as lockless.  The scan
count is used to determine how aggressively the anon and file LRU lists
should be scanned.  Load tearing could generate an inefficient heuristic,
so fix it by adding READ_ONCE() for the read.

Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Link: http://lkml.kernel.org/r/20200206034945.2481-1-cai@lca.pw
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 385237e4cb44..d0b036123c6a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -630,7 +630,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	struct mem_cgroup_per_node *mz;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return mz->lru_zone_size[zone_idx][lru];
+	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
 void mem_cgroup_handle_over_high(void);
-- 
cgit v1.2.3


From c403f6a3a792a6601185497c12b0bdf4be880439 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Fri, 14 Aug 2020 17:31:53 -0700
Subject: mm: annotate a data race in page_zonenum()

 BUG: KCSAN: data-race in page_cpupid_xchg_last / put_page

 write (marked) to 0xfffffc0d48ec1a00 of 8 bytes by task 91442 on cpu 3:
  page_cpupid_xchg_last+0x51/0x80
  page_cpupid_xchg_last at mm/mmzone.c:109 (discriminator 11)
  wp_page_reuse+0x3e/0xc0
  wp_page_reuse at mm/memory.c:2453
  do_wp_page+0x472/0x7b0
  do_wp_page at mm/memory.c:2798
  __handle_mm_fault+0xcb0/0xd00
  handle_pte_fault at mm/memory.c:4049
  (inlined by) __handle_mm_fault at mm/memory.c:4163
  handle_mm_fault+0xfc/0x2f0
  handle_mm_fault at mm/memory.c:4200
  do_page_fault+0x263/0x6f9
  do_user_addr_fault at arch/x86/mm/fault.c:1465
  (inlined by) do_page_fault at arch/x86/mm/fault.c:1539
  page_fault+0x34/0x40

 read to 0xfffffc0d48ec1a00 of 8 bytes by task 94817 on cpu 69:
  put_page+0x15a/0x1f0
  page_zonenum at include/linux/mm.h:923
  (inlined by) is_zone_device_page at include/linux/mm.h:929
  (inlined by) page_is_devmap_managed at include/linux/mm.h:948
  (inlined by) put_page at include/linux/mm.h:1023
  wp_page_copy+0x571/0x930
  wp_page_copy at mm/memory.c:2615
  do_wp_page+0x107/0x7b0
  __handle_mm_fault+0xcb0/0xd00
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 Reported by Kernel Concurrency Sanitizer on:
 CPU: 69 PID: 94817 Comm: systemd-udevd Tainted: G        W  O L 5.5.0-next-20200204+ #6
 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019

A page never changes its zone number. The zone number happens to be
stored in the same word as other bits which are modified, but the zone
number bits will never be modified by any other write, so it can accept
a reload of the zone bits after an intervening write and it don't need
to use READ_ONCE(). Thus, annotate this data race using
ASSERT_EXCLUSIVE_BITS() to also assert that there are no concurrent
writes to it.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Link: http://lkml.kernel.org/r/1581619089-14472-1-git-send-email-cai@lca.pw
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2e7ec3ee34cf..1983e08f5906 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1067,6 +1067,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 
 static inline enum zone_type page_zonenum(const struct page *page)
 {
+	ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
 
-- 
cgit v1.2.3


From 8f28ca6bd8211214faf717677bbffe375c2a6072 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Fri, 14 Aug 2020 17:32:07 -0700
Subject: iomap: constify ioreadX() iomem argument (as in generic
 implementation)

Patch series "iomap: Constify ioreadX() iomem argument", v3.

The ioread8/16/32() and others have inconsistent interface among the
architectures: some taking address as const, some not.

It seems there is nothing really stopping all of them to take pointer to
const.

This patch (of 4):

The ioreadX() and ioreadX_rep() helpers have inconsistent interface.  On
some architectures void *__iomem address argument is a pointer to const,
on some not.

Implementations of ioreadX() do not modify the memory under the address so
they can be converted to a "const" version for const-safety and
consistency among architectures.

[krzk@kernel.org: sh: clk: fix assignment from incompatible pointer type for ioreadX()]
  Link: http://lkml.kernel.org/r/20200723082017.24053-1-krzk@kernel.org
[akpm@linux-foundation.org: fix drivers/mailbox/bcm-pdc-mailbox.c]
  Link: http://lkml.kernel.org/r/202007132209.Rxmv4QyS%25lkp@intel.com

Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: Allen Hubbe <allenbh@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Link: http://lkml.kernel.org/r/20200709072837.5869-1-krzk@kernel.org
Link: http://lkml.kernel.org/r/20200709072837.5869-2-krzk@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/core_apecs.h   |  6 +--
 arch/alpha/include/asm/core_cia.h     |  6 +--
 arch/alpha/include/asm/core_lca.h     |  6 +--
 arch/alpha/include/asm/core_marvel.h  |  4 +-
 arch/alpha/include/asm/core_mcpcia.h  |  6 +--
 arch/alpha/include/asm/core_t2.h      |  2 +-
 arch/alpha/include/asm/io.h           | 12 +++---
 arch/alpha/include/asm/io_trivial.h   | 16 ++++----
 arch/alpha/include/asm/jensen.h       |  2 +-
 arch/alpha/include/asm/machvec.h      |  6 +--
 arch/alpha/kernel/core_marvel.c       |  2 +-
 arch/alpha/kernel/io.c                | 12 +++---
 arch/parisc/include/asm/io.h          |  4 +-
 arch/parisc/lib/iomap.c               | 72 +++++++++++++++++------------------
 arch/powerpc/kernel/iomap.c           | 28 +++++++-------
 arch/sh/kernel/iomap.c                | 22 +++++------
 drivers/mailbox/bcm-pdc-mailbox.c     |  2 +-
 drivers/sh/clk/cpg.c                  |  2 +-
 include/asm-generic/iomap.h           | 28 +++++++-------
 include/linux/io-64-nonatomic-hi-lo.h |  4 +-
 include/linux/io-64-nonatomic-lo-hi.h |  4 +-
 lib/iomap.c                           | 30 +++++++--------
 22 files changed, 138 insertions(+), 138 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/include/asm/core_apecs.h b/arch/alpha/include/asm/core_apecs.h
index 0a07055bc0fe..2d9726fc02ef 100644
--- a/arch/alpha/include/asm/core_apecs.h
+++ b/arch/alpha/include/asm/core_apecs.h
@@ -384,7 +384,7 @@ struct el_apecs_procdata
 		}						\
 	} while (0)
 
-__EXTERN_INLINE unsigned int apecs_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -420,7 +420,7 @@ __EXTERN_INLINE void apecs_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -456,7 +456,7 @@ __EXTERN_INLINE void apecs_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < APECS_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_cia.h b/arch/alpha/include/asm/core_cia.h
index c706a7f2b061..cb22991f6761 100644
--- a/arch/alpha/include/asm/core_cia.h
+++ b/arch/alpha/include/asm/core_cia.h
@@ -342,7 +342,7 @@ struct el_CIA_sysdata_mcheck {
 #define vuip	volatile unsigned int __force *
 #define vulp	volatile unsigned long __force *
 
-__EXTERN_INLINE unsigned int cia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -374,7 +374,7 @@ __EXTERN_INLINE void cia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -404,7 +404,7 @@ __EXTERN_INLINE void cia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < CIA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h
index 84d5e5b84f4f..ec86314418cb 100644
--- a/arch/alpha/include/asm/core_lca.h
+++ b/arch/alpha/include/asm/core_lca.h
@@ -230,7 +230,7 @@ union el_lca {
 	} while (0)
 
 
-__EXTERN_INLINE unsigned int lca_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -266,7 +266,7 @@ __EXTERN_INLINE void lca_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -302,7 +302,7 @@ __EXTERN_INLINE void lca_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < LCA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_marvel.h b/arch/alpha/include/asm/core_marvel.h
index cc6fd92d5fa9..b266e02e284b 100644
--- a/arch/alpha/include/asm/core_marvel.h
+++ b/arch/alpha/include/asm/core_marvel.h
@@ -332,10 +332,10 @@ struct io7 {
 #define vucp	volatile unsigned char __force *
 #define vusp	volatile unsigned short __force *
 
-extern unsigned int marvel_ioread8(void __iomem *);
+extern unsigned int marvel_ioread8(const void __iomem *);
 extern void marvel_iowrite8(u8 b, void __iomem *);
 
-__EXTERN_INLINE unsigned int marvel_ioread16(void __iomem *addr)
+__EXTERN_INLINE unsigned int marvel_ioread16(const void __iomem *addr)
 {
 	return __kernel_ldwu(*(vusp)addr);
 }
diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h
index b30dc128210d..cb24d1bd6141 100644
--- a/arch/alpha/include/asm/core_mcpcia.h
+++ b/arch/alpha/include/asm/core_mcpcia.h
@@ -267,7 +267,7 @@ extern inline int __mcpcia_is_mmio(unsigned long addr)
 	return (addr & 0x80000000UL) == 0;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -291,7 +291,7 @@ __EXTERN_INLINE void mcpcia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x00) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -315,7 +315,7 @@ __EXTERN_INLINE void mcpcia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x08) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr;
 
diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h
index e0b33d09e93a..12bb7addc789 100644
--- a/arch/alpha/include/asm/core_t2.h
+++ b/arch/alpha/include/asm/core_t2.h
@@ -572,7 +572,7 @@ __EXTERN_INLINE int t2_is_mmio(const volatile void __iomem *addr)
    it doesn't make sense to merge the pio and mmio routines.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int t2_ioread##NS(void __iomem *xaddr)		\
+__EXTERN_INLINE unsigned int t2_ioread##NS(const void __iomem *xaddr)		\
 {									\
 	if (t2_is_mmio(xaddr))						\
 		return t2_read##OS(xaddr);				\
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 640e1a2f57b4..1f6a909d1fa5 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -150,9 +150,9 @@ static inline void generic_##NAME(TYPE b, QUAL void __iomem *addr)	\
 	alpha_mv.mv_##NAME(b, addr);					\
 }
 
-REMAP1(unsigned int, ioread8, /**/)
-REMAP1(unsigned int, ioread16, /**/)
-REMAP1(unsigned int, ioread32, /**/)
+REMAP1(unsigned int, ioread8, const)
+REMAP1(unsigned int, ioread16, const)
+REMAP1(unsigned int, ioread32, const)
 REMAP1(u8, readb, const volatile)
 REMAP1(u16, readw, const volatile)
 REMAP1(u32, readl, const volatile)
@@ -307,7 +307,7 @@ static inline int __is_mmio(const volatile void __iomem *addr)
  */
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
-extern inline unsigned int ioread8(void __iomem *addr)
+extern inline unsigned int ioread8(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -316,7 +316,7 @@ extern inline unsigned int ioread8(void __iomem *addr)
 	return ret;
 }
 
-extern inline unsigned int ioread16(void __iomem *addr)
+extern inline unsigned int ioread16(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -359,7 +359,7 @@ extern inline void outw(u16 b, unsigned long port)
 #endif
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
-extern inline unsigned int ioread32(void __iomem *addr)
+extern inline unsigned int ioread32(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
diff --git a/arch/alpha/include/asm/io_trivial.h b/arch/alpha/include/asm/io_trivial.h
index ba3d8f0cfe0c..a1a29cbe02fa 100644
--- a/arch/alpha/include/asm/io_trivial.h
+++ b/arch/alpha/include/asm/io_trivial.h
@@ -7,15 +7,15 @@
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread8)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread8)(const void __iomem *a)
 {
-	return __kernel_ldbu(*(volatile u8 __force *)a);
+	return __kernel_ldbu(*(const volatile u8 __force *)a);
 }
 
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread16)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread16)(const void __iomem *a)
 {
-	return __kernel_ldwu(*(volatile u16 __force *)a);
+	return __kernel_ldwu(*(const volatile u16 __force *)a);
 }
 
 __EXTERN_INLINE void
@@ -33,9 +33,9 @@ IO_CONCAT(__IO_PREFIX,iowrite16)(u16 b, void __iomem *a)
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread32)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread32)(const void __iomem *a)
 {
-	return *(volatile u32 __force *)a;
+	return *(const volatile u32 __force *)a;
 }
 
 __EXTERN_INLINE void
@@ -73,14 +73,14 @@ IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a)
 __EXTERN_INLINE u8
 IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 }
 
 __EXTERN_INLINE u16
 IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 }
 
diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h
index 436dc905b6ad..916895155a88 100644
--- a/arch/alpha/include/asm/jensen.h
+++ b/arch/alpha/include/asm/jensen.h
@@ -305,7 +305,7 @@ __EXTERN_INLINE int jensen_is_mmio(const volatile void __iomem *addr)
    that it doesn't make sense to merge them.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int jensen_ioread##NS(void __iomem *xaddr)	\
+__EXTERN_INLINE unsigned int jensen_ioread##NS(const void __iomem *xaddr)	\
 {									\
 	if (jensen_is_mmio(xaddr))					\
 		return jensen_read##OS(xaddr - 0x100000000ul);		\
diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h
index a6b73c6d10ee..a4e96e2bec74 100644
--- a/arch/alpha/include/asm/machvec.h
+++ b/arch/alpha/include/asm/machvec.h
@@ -46,9 +46,9 @@ struct alpha_machine_vector
 	void (*mv_pci_tbi)(struct pci_controller *hose,
 			   dma_addr_t start, dma_addr_t end);
 
-	unsigned int (*mv_ioread8)(void __iomem *);
-	unsigned int (*mv_ioread16)(void __iomem *);
-	unsigned int (*mv_ioread32)(void __iomem *);
+	unsigned int (*mv_ioread8)(const void __iomem *);
+	unsigned int (*mv_ioread16)(const void __iomem *);
+	unsigned int (*mv_ioread32)(const void __iomem *);
 
 	void (*mv_iowrite8)(u8, void __iomem *);
 	void (*mv_iowrite16)(u16, void __iomem *);
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index 4c80d992a659..4485b77f8658 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -806,7 +806,7 @@ void __iomem *marvel_ioportmap (unsigned long addr)
 }
 
 unsigned int
-marvel_ioread8(void __iomem *xaddr)
+marvel_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (__marvel_is_port_kbd(addr))
diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c
index 938de13adfbf..838586abb1e0 100644
--- a/arch/alpha/kernel/io.c
+++ b/arch/alpha/kernel/io.c
@@ -14,7 +14,7 @@
    "generic", which bumps through the machine vector.  */
 
 unsigned int
-ioread8(void __iomem *addr)
+ioread8(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -23,7 +23,7 @@ ioread8(void __iomem *addr)
 	return ret;
 }
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -32,7 +32,7 @@ unsigned int ioread16(void __iomem *addr)
 	return ret;
 }
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -257,7 +257,7 @@ EXPORT_SYMBOL(readq_relaxed);
 /*
  * Read COUNT 8-bit bytes from port PORT into memory starting at SRC.
  */
-void ioread8_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	while ((unsigned long)dst & 0x3) {
 		if (!count)
@@ -300,7 +300,7 @@ EXPORT_SYMBOL(insb);
  * the interfaces seems to be slow: just using the inlined version
  * of the inw() breaks things.
  */
-void ioread16_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	if (unlikely((unsigned long)dst & 0x3)) {
 		if (!count)
@@ -340,7 +340,7 @@ EXPORT_SYMBOL(insw);
  * but the interfaces seems to be slow: just using the inlined version
  * of the inl() breaks things.
  */
-void ioread32_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	if (unlikely((unsigned long)dst & 0x3)) {
 		while (count--) {
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 116effe26143..45e20d38dc59 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -303,8 +303,8 @@ extern void outsl (unsigned long port, const void *src, unsigned long count);
 #define ioread64be ioread64be
 #define iowrite64 iowrite64
 #define iowrite64be iowrite64be
-extern u64 ioread64(void __iomem *addr);
-extern u64 ioread64be(void __iomem *addr);
+extern u64 ioread64(const void __iomem *addr);
+extern u64 ioread64be(const void __iomem *addr);
 extern void iowrite64(u64 val, void __iomem *addr);
 extern void iowrite64be(u64 val, void __iomem *addr);
 
diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c
index 0195aec657e2..ce400417d54e 100644
--- a/arch/parisc/lib/iomap.c
+++ b/arch/parisc/lib/iomap.c
@@ -43,13 +43,13 @@
 #endif
 
 struct iomap_ops {
-	unsigned int (*read8)(void __iomem *);
-	unsigned int (*read16)(void __iomem *);
-	unsigned int (*read16be)(void __iomem *);
-	unsigned int (*read32)(void __iomem *);
-	unsigned int (*read32be)(void __iomem *);
-	u64 (*read64)(void __iomem *);
-	u64 (*read64be)(void __iomem *);
+	unsigned int (*read8)(const void __iomem *);
+	unsigned int (*read16)(const void __iomem *);
+	unsigned int (*read16be)(const void __iomem *);
+	unsigned int (*read32)(const void __iomem *);
+	unsigned int (*read32be)(const void __iomem *);
+	u64 (*read64)(const void __iomem *);
+	u64 (*read64be)(const void __iomem *);
 	void (*write8)(u8, void __iomem *);
 	void (*write16)(u16, void __iomem *);
 	void (*write16be)(u16, void __iomem *);
@@ -57,9 +57,9 @@ struct iomap_ops {
 	void (*write32be)(u32, void __iomem *);
 	void (*write64)(u64, void __iomem *);
 	void (*write64be)(u64, void __iomem *);
-	void (*read8r)(void __iomem *, void *, unsigned long);
-	void (*read16r)(void __iomem *, void *, unsigned long);
-	void (*read32r)(void __iomem *, void *, unsigned long);
+	void (*read8r)(const void __iomem *, void *, unsigned long);
+	void (*read16r)(const void __iomem *, void *, unsigned long);
+	void (*read32r)(const void __iomem *, void *, unsigned long);
 	void (*write8r)(void __iomem *, const void *, unsigned long);
 	void (*write16r)(void __iomem *, const void *, unsigned long);
 	void (*write32r)(void __iomem *, const void *, unsigned long);
@@ -69,17 +69,17 @@ struct iomap_ops {
 
 #define ADDR2PORT(addr) ((unsigned long __force)(addr) & 0xffffff)
 
-static unsigned int ioport_read8(void __iomem *addr)
+static unsigned int ioport_read8(const void __iomem *addr)
 {
 	return inb(ADDR2PORT(addr));
 }
 
-static unsigned int ioport_read16(void __iomem *addr)
+static unsigned int ioport_read16(const void __iomem *addr)
 {
 	return inw(ADDR2PORT(addr));
 }
 
-static unsigned int ioport_read32(void __iomem *addr)
+static unsigned int ioport_read32(const void __iomem *addr)
 {
 	return inl(ADDR2PORT(addr));
 }
@@ -99,17 +99,17 @@ static void ioport_write32(u32 datum, void __iomem *addr)
 	outl(datum, ADDR2PORT(addr));
 }
 
-static void ioport_read8r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read8r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insb(ADDR2PORT(addr), dst, count);
 }
 
-static void ioport_read16r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read16r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insw(ADDR2PORT(addr), dst, count);
 }
 
-static void ioport_read32r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read32r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insl(ADDR2PORT(addr), dst, count);
 }
@@ -150,37 +150,37 @@ static const struct iomap_ops ioport_ops = {
 
 /* Legacy I/O memory ops */
 
-static unsigned int iomem_read8(void __iomem *addr)
+static unsigned int iomem_read8(const void __iomem *addr)
 {
 	return readb(addr);
 }
 
-static unsigned int iomem_read16(void __iomem *addr)
+static unsigned int iomem_read16(const void __iomem *addr)
 {
 	return readw(addr);
 }
 
-static unsigned int iomem_read16be(void __iomem *addr)
+static unsigned int iomem_read16be(const void __iomem *addr)
 {
 	return __raw_readw(addr);
 }
 
-static unsigned int iomem_read32(void __iomem *addr)
+static unsigned int iomem_read32(const void __iomem *addr)
 {
 	return readl(addr);
 }
 
-static unsigned int iomem_read32be(void __iomem *addr)
+static unsigned int iomem_read32be(const void __iomem *addr)
 {
 	return __raw_readl(addr);
 }
 
-static u64 iomem_read64(void __iomem *addr)
+static u64 iomem_read64(const void __iomem *addr)
 {
 	return readq(addr);
 }
 
-static u64 iomem_read64be(void __iomem *addr)
+static u64 iomem_read64be(const void __iomem *addr)
 {
 	return __raw_readq(addr);
 }
@@ -220,7 +220,7 @@ static void iomem_write64be(u64 datum, void __iomem *addr)
 	__raw_writel(datum, addr);
 }
 
-static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read8r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u8 *)dst = __raw_readb(addr);
@@ -228,7 +228,7 @@ static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read16r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u16 *)dst = __raw_readw(addr);
@@ -236,7 +236,7 @@ static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-static void iomem_read32r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read32r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u32 *)dst = __raw_readl(addr);
@@ -297,49 +297,49 @@ static const struct iomap_ops *iomap_ops[8] = {
 };
 
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read8(addr);
 	return *((u8 *)addr);
 }
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read16(addr);
 	return le16_to_cpup((u16 *)addr);
 }
 
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read16be(addr);
 	return *((u16 *)addr);
 }
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read32(addr);
 	return le32_to_cpup((u32 *)addr);
 }
 
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read32be(addr);
 	return *((u32 *)addr);
 }
 
-u64 ioread64(void __iomem *addr)
+u64 ioread64(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read64(addr);
 	return le64_to_cpup((u64 *)addr);
 }
 
-u64 ioread64be(void __iomem *addr)
+u64 ioread64be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read64be(addr);
@@ -411,7 +411,7 @@ void iowrite64be(u64 datum, void __iomem *addr)
 
 /* Repeating interfaces */
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read8r(addr, dst, count);
@@ -423,7 +423,7 @@ void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read16r(addr, dst, count);
@@ -435,7 +435,7 @@ void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read32r(addr, dst, count);
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 5ac84efc6ede..9fe4fb3b08aa 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -15,23 +15,23 @@
  * Here comes the ppc64 implementation of the IOMAP 
  * interfaces.
  */
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	return readb(addr);
 }
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	return readw(addr);
 }
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	return readw_be(addr);
 }
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	return readl(addr);
 }
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	return readl_be(addr);
 }
@@ -41,27 +41,27 @@ EXPORT_SYMBOL(ioread16be);
 EXPORT_SYMBOL(ioread32);
 EXPORT_SYMBOL(ioread32be);
 #ifdef __powerpc64__
-u64 ioread64(void __iomem *addr)
+u64 ioread64(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64be(void __iomem *addr)
+u64 ioread64be(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
@@ -139,15 +139,15 @@ EXPORT_SYMBOL(iowrite64be_hi_lo);
  * FIXME! We could make these do EEH handling if we really
  * wanted. Not clear if we do.
  */
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsb(addr, dst, count);
 }
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsw(addr, dst, count);
 }
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsl(addr, dst, count);
 }
diff --git a/arch/sh/kernel/iomap.c b/arch/sh/kernel/iomap.c
index ef9e2c97cbb7..0a0dff4e66de 100644
--- a/arch/sh/kernel/iomap.c
+++ b/arch/sh/kernel/iomap.c
@@ -8,31 +8,31 @@
 #include <linux/module.h>
 #include <linux/io.h>
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	return readb(addr);
 }
 EXPORT_SYMBOL(ioread8);
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	return readw(addr);
 }
 EXPORT_SYMBOL(ioread16);
 
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	return be16_to_cpu(__raw_readw(addr));
 }
 EXPORT_SYMBOL(ioread16be);
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	return readl(addr);
 }
 EXPORT_SYMBOL(ioread32);
 
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	return be32_to_cpu(__raw_readl(addr));
 }
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(iowrite32be);
  * convert to CPU byte order. We write in "IO byte
  * order" (we also don't have IO barriers).
  */
-static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
 		u8 data = __raw_readb(addr);
@@ -83,7 +83,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 	}
 }
 
-static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
 {
 	while (--count >= 0) {
 		u16 data = __raw_readw(addr);
@@ -92,7 +92,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
 	}
 }
 
-static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
 {
 	while (--count >= 0) {
 		u32 data = __raw_readl(addr);
@@ -125,19 +125,19 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 	}
 }
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insb(addr, dst, count);
 }
 EXPORT_SYMBOL(ioread8_rep);
 
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insw(addr, dst, count);
 }
 EXPORT_SYMBOL(ioread16_rep);
 
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insl(addr, dst, count);
 }
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index c10a9318a4b7..53945ca5d785 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -679,7 +679,7 @@ pdc_receive(struct pdc_state *pdcs)
 
 	/* read last_rx_curr from register once */
 	pdcs->last_rx_curr =
-	    (ioread32(&pdcs->rxregs_64->status0) &
+	    (ioread32((const void __iomem *)&pdcs->rxregs_64->status0) &
 	     CRYPTO_D64_RS0_CD_MASK) / RING_ENTRY_SIZE;
 
 	do {
diff --git a/drivers/sh/clk/cpg.c b/drivers/sh/clk/cpg.c
index a5cacfe24a42..fd72d9088bdc 100644
--- a/drivers/sh/clk/cpg.c
+++ b/drivers/sh/clk/cpg.c
@@ -40,7 +40,7 @@ static int sh_clk_mstp_enable(struct clk *clk)
 {
 	sh_clk_write(sh_clk_read(clk) & ~(1 << clk->enable_bit), clk);
 	if (clk->status_reg) {
-		unsigned int (*read)(void __iomem *addr);
+		unsigned int (*read)(const void __iomem *addr);
 		int i;
 		void __iomem *mapped_status = (phys_addr_t)clk->status_reg -
 			(phys_addr_t)clk->enable_reg + clk->mapped_reg;
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index 9d28a5e82f73..649224664969 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -26,14 +26,14 @@
  * in the low address range. Architectures for which this is not
  * true can't use this generic implementation.
  */
-extern unsigned int ioread8(void __iomem *);
-extern unsigned int ioread16(void __iomem *);
-extern unsigned int ioread16be(void __iomem *);
-extern unsigned int ioread32(void __iomem *);
-extern unsigned int ioread32be(void __iomem *);
+extern unsigned int ioread8(const void __iomem *);
+extern unsigned int ioread16(const void __iomem *);
+extern unsigned int ioread16be(const void __iomem *);
+extern unsigned int ioread32(const void __iomem *);
+extern unsigned int ioread32be(const void __iomem *);
 #ifdef CONFIG_64BIT
-extern u64 ioread64(void __iomem *);
-extern u64 ioread64be(void __iomem *);
+extern u64 ioread64(const void __iomem *);
+extern u64 ioread64be(const void __iomem *);
 #endif
 
 #ifdef readq
@@ -41,10 +41,10 @@ extern u64 ioread64be(void __iomem *);
 #define ioread64_hi_lo ioread64_hi_lo
 #define ioread64be_lo_hi ioread64be_lo_hi
 #define ioread64be_hi_lo ioread64be_hi_lo
-extern u64 ioread64_lo_hi(void __iomem *addr);
-extern u64 ioread64_hi_lo(void __iomem *addr);
-extern u64 ioread64be_lo_hi(void __iomem *addr);
-extern u64 ioread64be_hi_lo(void __iomem *addr);
+extern u64 ioread64_lo_hi(const void __iomem *addr);
+extern u64 ioread64_hi_lo(const void __iomem *addr);
+extern u64 ioread64be_lo_hi(const void __iomem *addr);
+extern u64 ioread64be_hi_lo(const void __iomem *addr);
 #endif
 
 extern void iowrite8(u8, void __iomem *);
@@ -79,9 +79,9 @@ extern void iowrite64be_hi_lo(u64 val, void __iomem *addr);
  * memory across multiple ports, use "memcpy_toio()"
  * and friends.
  */
-extern void ioread8_rep(void __iomem *port, void *buf, unsigned long count);
-extern void ioread16_rep(void __iomem *port, void *buf, unsigned long count);
-extern void ioread32_rep(void __iomem *port, void *buf, unsigned long count);
+extern void ioread8_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread16_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread32_rep(const void __iomem *port, void *buf, unsigned long count);
 
 extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count);
 extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h
index ae21b72cce85..f32522bb3aa5 100644
--- a/include/linux/io-64-nonatomic-hi-lo.h
+++ b/include/linux/io-64-nonatomic-hi-lo.h
@@ -57,7 +57,7 @@ static inline void hi_lo_writeq_relaxed(__u64 val, volatile void __iomem *addr)
 
 #ifndef ioread64_hi_lo
 #define ioread64_hi_lo ioread64_hi_lo
-static inline u64 ioread64_hi_lo(void __iomem *addr)
+static inline u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	u32 low, high;
 
@@ -79,7 +79,7 @@ static inline void iowrite64_hi_lo(u64 val, void __iomem *addr)
 
 #ifndef ioread64be_hi_lo
 #define ioread64be_hi_lo ioread64be_hi_lo
-static inline u64 ioread64be_hi_lo(void __iomem *addr)
+static inline u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	u32 low, high;
 
diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h
index faaa842dbdb9..448a21435dba 100644
--- a/include/linux/io-64-nonatomic-lo-hi.h
+++ b/include/linux/io-64-nonatomic-lo-hi.h
@@ -57,7 +57,7 @@ static inline void lo_hi_writeq_relaxed(__u64 val, volatile void __iomem *addr)
 
 #ifndef ioread64_lo_hi
 #define ioread64_lo_hi ioread64_lo_hi
-static inline u64 ioread64_lo_hi(void __iomem *addr)
+static inline u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	u32 low, high;
 
@@ -79,7 +79,7 @@ static inline void iowrite64_lo_hi(u64 val, void __iomem *addr)
 
 #ifndef ioread64be_lo_hi
 #define ioread64be_lo_hi ioread64be_lo_hi
-static inline u64 ioread64be_lo_hi(void __iomem *addr)
+static inline u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	u32 low, high;
 
diff --git a/lib/iomap.c b/lib/iomap.c
index e909ab71e995..fbaa3e8f19d6 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -70,27 +70,27 @@ static void bad_io_access(unsigned long port, const char *access)
 #define mmio_read64be(addr) swab64(readq(addr))
 #endif
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	IO_COND(addr, return inb(port), return readb(addr));
 	return 0xff;
 }
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	IO_COND(addr, return inw(port), return readw(addr));
 	return 0xffff;
 }
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr));
 	return 0xffff;
 }
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	IO_COND(addr, return inl(port), return readl(addr));
 	return 0xffffffff;
 }
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr));
 	return 0xffffffff;
@@ -142,26 +142,26 @@ static u64 pio_read64be_hi_lo(unsigned long port)
 	return lo | (hi << 32);
 }
 
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_lo_hi(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_hi_lo(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_lo_hi(port),
 		return mmio_read64be(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_hi_lo(port),
 		return mmio_read64be(addr));
@@ -275,7 +275,7 @@ EXPORT_SYMBOL(iowrite64be_hi_lo);
  * order" (we also don't have IO barriers).
  */
 #ifndef mmio_insb
-static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
 		u8 data = __raw_readb(addr);
@@ -283,7 +283,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
 {
 	while (--count >= 0) {
 		u16 data = __raw_readw(addr);
@@ -291,7 +291,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
 {
 	while (--count >= 0) {
 		u32 data = __raw_readl(addr);
@@ -325,15 +325,15 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 }
 #endif
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count));
 }
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count));
 }
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count));
 }
-- 
cgit v1.2.3


From 29e44f4535faa71a70827af3639b5e6762d8f02a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 17 Aug 2020 11:07:28 +0100
Subject: watch_queue: Limit the number of watches a user can hold

Impose a limit on the number of watches that a user can hold so that
they can't use this mechanism to fill up all the available memory.

This is done by putting a counter in user_struct that's incremented when
a watch is allocated and decreased when it is released.  If the number
exceeds the RLIMIT_NOFILE limit, the watch is rejected with EAGAIN.

This can be tested by the following means:

 (1) Create a watch queue and attach it to fd 5 in the program given - in
     this case, bash:

	keyctl watch_session /tmp/nlog /tmp/gclog 5 bash

 (2) In the shell, set the maximum number of files to, say, 99:

	ulimit -n 99

 (3) Add 200 keyrings:

	for ((i=0; i<200; i++)); do keyctl newring a$i @s || break; done

 (4) Try to watch all of the keyrings:

	for ((i=0; i<200; i++)); do echo $i; keyctl watch_add 5 %:a$i || break; done

     This should fail when the number of watches belonging to the user hits
     99.

 (5) Remove all the keyrings and all of those watches should go away:

	for ((i=0; i<200; i++)); do keyctl unlink %:a$i; done

 (6) Kill off the watch queue by exiting the shell spawned by
     watch_session.

Fixes: c73be61cede5 ("pipe: Add general notification queue support")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/user.h | 3 +++
 kernel/watch_queue.c       | 8 ++++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 917d88edb7b9..a8ec3b6093fc 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -36,6 +36,9 @@ struct user_struct {
     defined(CONFIG_NET) || defined(CONFIG_IO_URING)
 	atomic_long_t locked_vm;
 #endif
+#ifdef CONFIG_WATCH_QUEUE
+	atomic_t nr_watches;	/* The number of watches this user currently has */
+#endif
 
 	/* Miscellaneous per-user rate limit */
 	struct ratelimit_state ratelimit;
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index f74020f6bd9d..0ef8f65bd2d7 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu)
 	struct watch *watch = container_of(rcu, struct watch, rcu);
 
 	put_watch_queue(rcu_access_pointer(watch->queue));
+	atomic_dec(&watch->cred->user->nr_watches);
 	put_cred(watch->cred);
 }
 
@@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
 	watch->cred = get_current_cred();
 	rcu_assign_pointer(watch->watch_list, wlist);
 
+	if (atomic_inc_return(&watch->cred->user->nr_watches) >
+	    task_rlimit(current, RLIMIT_NOFILE)) {
+		atomic_dec(&watch->cred->user->nr_watches);
+		put_cred(watch->cred);
+		return -EAGAIN;
+	}
+
 	spin_lock_bh(&wqueue->lock);
 	kref_get(&wqueue->usage);
 	kref_get(&watch->usage);
-- 
cgit v1.2.3


From 0b76e642f9ad2471e899e2dd71b9543b7e85e9f6 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 16 Aug 2020 15:25:49 -0700
Subject: phylink: <linux/phylink.h>: fix function prototype kernel-doc warning

Fix a kernel-doc warning for the pcs_config() function prototype:

../include/linux/phylink.h:406: warning: Excess function parameter 'permit_pause_to_mac' description in 'pcs_config'

Fixes: 7137e18f6f88 ("net: phylink: add struct phylink_pcs")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phylink.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index a8e876317e25..c36fb41a7d90 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs,
  * For most 10GBASE-R, there is no advertisement.
  */
 int pcs_config(struct phylink_pcs *pcs, unsigned int mode,
-	       phy_interface_t interface, const unsigned long *advertising);
+	       phy_interface_t interface, const unsigned long *advertising,
+	       bool permit_pause_to_mac);
 
 /**
  * pcs_an_restart() - restart 802.3z BaseX autonegotiation
-- 
cgit v1.2.3


From bd05220c7be3356046861c317d9c287ca50445ba Mon Sep 17 00:00:00 2001
From: Jessica Clarke <jrtc27@jrtc27.com>
Date: Tue, 11 Aug 2020 19:24:57 +0100
Subject: arch/ia64: Restore arch-specific pgd_offset_k implementation

IA-64 is special and treats pgd_offset_k() differently to pgd_offset(),
using different formulae to calculate the indices into the kernel and user
PGDs.  The index into the user PGDs takes into account the region number,
but the index into the kernel (init_mm) PGD always assumes a predefined
kernel region number. Commit 974b9b2c68f3 ("mm: consolidate pte_index() and
pte_offset_*() definitions") made IA-64 use a generic pgd_offset_k() which
incorrectly used pgd_index() for kernel page tables.  As a result, the
index into the kernel PGD was going out of bounds and the kernel hung
during early boot.

Allow overrides of pgd_offset_k() and override it on IA-64 with the old
implementation that will correctly index the kernel PGD.

Fixes: 974b9b2c68f3 ("mm: consolidate pte_index() and pte_offset_*() definitions")
Reported-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: Jessica Clarke <jrtc27@jrtc27.com>
Tested-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 arch/ia64/include/asm/pgtable.h | 9 +++++++++
 include/linux/pgtable.h         | 2 ++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 10850897a91c..779b6972aa84 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -366,6 +366,15 @@ pgd_index (unsigned long address)
 }
 #define pgd_index pgd_index
 
+/*
+ * In the kernel's mapped region we know everything is in region number 5, so
+ * as an optimisation its PGD already points to the area for that region.
+ * However, this also means that we cannot use pgd_index() and we must
+ * never add the region here.
+ */
+#define pgd_offset_k(addr) \
+	(init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)))
+
 /* Look up a pgd entry in the gate area.  On IA-64, the gate-area
    resides in the kernel-mapped segment, hence we use pgd_offset_k()
    here.  */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index a124c21e3204..e8cbc2e795d5 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address)
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
  */
+#ifndef pgd_offset_k
 #define pgd_offset_k(address)		pgd_offset(&init_mm, (address))
+#endif
 
 /*
  * In many cases it is known that a virtual address is mapped at PMD or PTE
-- 
cgit v1.2.3


From 2ac6795fcc085e8d03649f1bbd0d70aaff612cad Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@wdc.com>
Date: Mon, 17 Aug 2020 18:12:49 +0530
Subject: clocksource/drivers: Add CLINT timer driver

We add a separate CLINT timer driver for Linux RISC-V M-mode (i.e.
RISC-V NoMMU kernel).

The CLINT MMIO device provides three things:
1. 64bit free running counter register
2. 64bit per-CPU time compare registers
3. 32bit per-CPU inter-processor interrupt registers

Unlike other timer devices, CLINT provides IPI registers along with
timer registers. To use CLINT IPI registers, the CLINT timer driver
provides IPI related callbacks to arch/riscv.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
Tested-by: Emil Renner Berhing <kernel@esmil.dk>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Atish Patra <atish.patra@wdc.com>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 drivers/clocksource/Kconfig       |   9 ++
 drivers/clocksource/Makefile      |   1 +
 drivers/clocksource/timer-clint.c | 226 ++++++++++++++++++++++++++++++++++++++
 include/linux/cpuhotplug.h        |   1 +
 4 files changed, 237 insertions(+)
 create mode 100644 drivers/clocksource/timer-clint.c

(limited to 'include/linux')

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 3576ad7bd380..d95cc7234a66 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -663,6 +663,15 @@ config RISCV_TIMER
 	  is accessed via both the SBI and the rdcycle instruction.  This is
 	  required for all RISC-V systems.
 
+config CLINT_TIMER
+	bool "CLINT Timer for the RISC-V platform" if COMPILE_TEST
+	depends on GENERIC_SCHED_CLOCK && RISCV
+	select TIMER_PROBE
+	select TIMER_OF
+	help
+	  This option enables the CLINT timer for RISC-V systems.  The CLINT
+	  driver is usually used for NoMMU RISC-V systems.
+
 config CSKY_MP_TIMER
 	bool "SMP Timer for the C-SKY platform" if COMPILE_TEST
 	depends on CSKY
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index eaedb7240ae7..1c444cc3bb44 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -89,6 +89,7 @@ obj-$(CONFIG_CLKSRC_ST_LPC)		+= clksrc_st_lpc.o
 obj-$(CONFIG_X86_NUMACHIP)		+= numachip.o
 obj-$(CONFIG_ATCPIT100_TIMER)		+= timer-atcpit100.o
 obj-$(CONFIG_RISCV_TIMER)		+= timer-riscv.o
+obj-$(CONFIG_CLINT_TIMER)		+= timer-clint.o
 obj-$(CONFIG_CSKY_MP_TIMER)		+= timer-mp-csky.o
 obj-$(CONFIG_GX6605S_TIMER)		+= timer-gx6605s.o
 obj-$(CONFIG_HYPERV_TIMER)		+= hyperv_timer.o
diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c
new file mode 100644
index 000000000000..8eeafa82c03d
--- /dev/null
+++ b/drivers/clocksource/timer-clint.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ *
+ * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a
+ * CLINT MMIO timer device.
+ */
+
+#define pr_fmt(fmt) "clint: " fmt
+#include <linux/bitops.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/sched_clock.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include <linux/smp.h>
+
+#define CLINT_IPI_OFF		0
+#define CLINT_TIMER_CMP_OFF	0x4000
+#define CLINT_TIMER_VAL_OFF	0xbff8
+
+/* CLINT manages IPI and Timer for RISC-V M-mode  */
+static u32 __iomem *clint_ipi_base;
+static u64 __iomem *clint_timer_cmp;
+static u64 __iomem *clint_timer_val;
+static unsigned long clint_timer_freq;
+static unsigned int clint_timer_irq;
+
+static void clint_send_ipi(const struct cpumask *target)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, target)
+		writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu));
+}
+
+static void clint_clear_ipi(void)
+{
+	writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id()));
+}
+
+static struct riscv_ipi_ops clint_ipi_ops = {
+	.ipi_inject = clint_send_ipi,
+	.ipi_clear = clint_clear_ipi,
+};
+
+#ifdef CONFIG_64BIT
+#define clint_get_cycles()	readq_relaxed(clint_timer_val)
+#else
+#define clint_get_cycles()	readl_relaxed(clint_timer_val)
+#define clint_get_cycles_hi()	readl_relaxed(((u32 *)clint_timer_val) + 1)
+#endif
+
+#ifdef CONFIG_64BIT
+static u64 notrace clint_get_cycles64(void)
+{
+	return clint_get_cycles();
+}
+#else /* CONFIG_64BIT */
+static u64 notrace clint_get_cycles64(void)
+{
+	u32 hi, lo;
+
+	do {
+		hi = clint_get_cycles_hi();
+		lo = clint_get_cycles();
+	} while (hi != clint_get_cycles_hi());
+
+	return ((u64)hi << 32) | lo;
+}
+#endif /* CONFIG_64BIT */
+
+static u64 clint_rdtime(struct clocksource *cs)
+{
+	return clint_get_cycles64();
+}
+
+static struct clocksource clint_clocksource = {
+	.name		= "clint_clocksource",
+	.rating		= 300,
+	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+	.read		= clint_rdtime,
+};
+
+static int clint_clock_next_event(unsigned long delta,
+				   struct clock_event_device *ce)
+{
+	void __iomem *r = clint_timer_cmp +
+			  cpuid_to_hartid_map(smp_processor_id());
+
+	csr_set(CSR_IE, IE_TIE);
+	writeq_relaxed(clint_get_cycles64() + delta, r);
+	return 0;
+}
+
+static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = {
+	.name		= "clint_clockevent",
+	.features	= CLOCK_EVT_FEAT_ONESHOT,
+	.rating		= 100,
+	.set_next_event	= clint_clock_next_event,
+};
+
+static int clint_timer_starting_cpu(unsigned int cpu)
+{
+	struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu);
+
+	ce->cpumask = cpumask_of(cpu);
+	clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff);
+
+	enable_percpu_irq(clint_timer_irq,
+			  irq_get_trigger_type(clint_timer_irq));
+	return 0;
+}
+
+static int clint_timer_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(clint_timer_irq);
+	return 0;
+}
+
+static irqreturn_t clint_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event);
+
+	csr_clear(CSR_IE, IE_TIE);
+	evdev->event_handler(evdev);
+
+	return IRQ_HANDLED;
+}
+
+static int __init clint_timer_init_dt(struct device_node *np)
+{
+	int rc;
+	u32 i, nr_irqs;
+	void __iomem *base;
+	struct of_phandle_args oirq;
+
+	/*
+	 * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or
+	 * RV_IRQ_SOFT. If it's anything else then we ignore the device.
+	 */
+	nr_irqs = of_irq_count(np);
+	for (i = 0; i < nr_irqs; i++) {
+		if (of_irq_parse_one(np, i, &oirq)) {
+			pr_err("%pOFP: failed to parse irq %d.\n", np, i);
+			continue;
+		}
+
+		if ((oirq.args_count != 1) ||
+		    (oirq.args[0] != RV_IRQ_TIMER &&
+		     oirq.args[0] != RV_IRQ_SOFT)) {
+			pr_err("%pOFP: invalid irq %d (hwirq %d)\n",
+			       np, i, oirq.args[0]);
+			return -ENODEV;
+		}
+
+		/* Find parent irq domain and map timer irq */
+		if (!clint_timer_irq &&
+		    oirq.args[0] == RV_IRQ_TIMER &&
+		    irq_find_host(oirq.np))
+			clint_timer_irq = irq_of_parse_and_map(np, i);
+	}
+
+	/* If CLINT timer irq not found then fail */
+	if (!clint_timer_irq) {
+		pr_err("%pOFP: timer irq not found\n", np);
+		return -ENODEV;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("%pOFP: could not map registers\n", np);
+		return -ENODEV;
+	}
+
+	clint_ipi_base = base + CLINT_IPI_OFF;
+	clint_timer_cmp = base + CLINT_TIMER_CMP_OFF;
+	clint_timer_val = base + CLINT_TIMER_VAL_OFF;
+	clint_timer_freq = riscv_timebase;
+
+	pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq);
+
+	rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq);
+	if (rc) {
+		pr_err("%pOFP: clocksource register failed [%d]\n", np, rc);
+		goto fail_iounmap;
+	}
+
+	sched_clock_register(clint_get_cycles64, 64, clint_timer_freq);
+
+	rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt,
+				 "clint-timer", &clint_clock_event);
+	if (rc) {
+		pr_err("registering percpu irq failed [%d]\n", rc);
+		goto fail_iounmap;
+	}
+
+	rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING,
+				"clockevents/clint/timer:starting",
+				clint_timer_starting_cpu,
+				clint_timer_dying_cpu);
+	if (rc) {
+		pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc);
+		goto fail_free_irq;
+	}
+
+	riscv_set_ipi_ops(&clint_ipi_ops);
+	clint_clear_ipi();
+
+	return 0;
+
+fail_free_irq:
+	free_irq(clint_timer_irq, &clint_clock_event);
+fail_iounmap:
+	iounmap(base);
+	return rc;
+}
+
+TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt);
+TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index a2710e654b64..3215023d4852 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -132,6 +132,7 @@ enum cpuhp_state {
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
+	CPUHP_AP_CLINT_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
 	CPUHP_AP_HYPERV_TIMER_STARTING,
 	CPUHP_AP_KVM_STARTING,
-- 
cgit v1.2.3