From 0461a4149836c792d186027c8c859637a4cfb11a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 9 Dec 2014 21:38:05 +0000 Subject: spi: Pump transfers inside calling context for spi_sync() If we are using the standard SPI message pump (which all drivers should be transitioning over to) then special case the message enqueue and instead of starting the worker thread to push messages to the hardware do so in the context of the caller if the controller is idle. This avoids a context switch in the common case where the controller has a single user in a single thread, for short PIO transfers there may be no need to context switch away from the calling context to complete the transfer. The code is a bit more complex than is desirable in part due to the need to handle drivers not using the standard queue and in part due to handling the various combinations of bus locking and asynchronous submission in interrupt context. It is still suboptimal since it will still wake the message pump for each transfer in order to schedule idling of the hardware and if multiple contexts are using the controller simultaneously a caller may end up pumping a message for some random other thread rather than for itself, and if the thread ends up deferring due to another context idling the hardware then it will just busy wait. It can, however, have the benefit of aggregating power up and down of the hardware when a caller performs a series of transfers back to back without any need for the use of spi_async(). Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a6ef2a8e6de4..4e6db75e9469 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -260,6 +260,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @pump_messages: work struct for scheduling work to the message pump * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue + * @idling: the device is entering idle state * @cur_msg: the currently in-flight message * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message @@ -425,6 +426,7 @@ struct spi_master { spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; + bool idling; bool busy; bool running; bool rt; -- cgit v1.2.3 From e39f2d5956999c05c85814787a113ffadbcd4b26 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Fri, 12 Dec 2014 10:17:26 -0800 Subject: HID: rmi: Scan the report descriptor to determine if the device is suitable for the hid-rmi driver On composite HID devices there may be multiple HID devices on separate interfaces, but hid-rmi should only bind to the touchpad. The previous version simply checked that the interface protocol was set to mouse. Unfortuately, it is not always the case that the touchpad has the mouse interface protocol set. This patch takes a different approach and scans the report descriptor looking for the Generic Desktop Pointer usage and the Vendor Specific Top Level Collection needed by the hid-rmi driver to interface with the device. Signed-off-by: Andrew Duggan Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 22 +++++++++++++++++----- include/linux/hid.h | 4 +++- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index c3d0ac1a0988..81665b4f2258 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -698,6 +698,7 @@ static void hid_scan_feature_usage(struct hid_parser *parser, u32 usage) static void hid_scan_collection(struct hid_parser *parser, unsigned type) { struct hid_device *hid = parser->device; + int i; if (((parser->global.usage_page << 16) == HID_UP_SENSOR) && type == HID_COLLECTION_PHYSICAL) @@ -707,6 +708,14 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type) hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 && hid->group == HID_GROUP_MULTITOUCH) hid->group = HID_GROUP_GENERIC; + + if ((parser->global.usage_page << 16) == HID_UP_GENDESK) + for (i = 0; i < parser->local.usage_index; i++) + if (parser->local.usage[i] == HID_GD_POINTER) + parser->scan_flags |= HID_SCAN_FLAG_GD_POINTER; + + if ((parser->global.usage_page << 16) >= HID_UP_MSVENDOR) + parser->scan_flags |= HID_SCAN_FLAG_VENDOR_SPECIFIC; } static int hid_scan_main(struct hid_parser *parser, struct hid_item *item) @@ -792,11 +801,14 @@ static int hid_scan_report(struct hid_device *hid) hid->group = HID_GROUP_WACOM; break; case USB_VENDOR_ID_SYNAPTICS: - if ((hid->group == HID_GROUP_GENERIC) && - (hid->bus != BUS_USB || hid->type == HID_TYPE_USBMOUSE)) - /* hid-rmi should only bind to the mouse interface of - * composite USB devices */ - hid->group = HID_GROUP_RMI; + if (hid->group == HID_GROUP_GENERIC) + if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC) + && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER)) + /* + * hid-rmi should take care of them, + * not hid-generic + */ + hid->group = HID_GROUP_RMI; break; } diff --git a/include/linux/hid.h b/include/linux/hid.h index 06c4607744f6..efc7787a41a8 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -574,7 +574,9 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 -#define HID_SCAN_FLAG_MT_WIN_8 0x00000001 +#define HID_SCAN_FLAG_MT_WIN_8 BIT(0) +#define HID_SCAN_FLAG_VENDOR_SPECIFIC BIT(1) +#define HID_SCAN_FLAG_GD_POINTER BIT(2) struct hid_parser { struct hid_global global; -- cgit v1.2.3 From d64cb71bede87dbca60d586a7bb4cef87fbe2731 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Wed, 17 Dec 2014 10:31:08 -0800 Subject: Input: add regulator haptic driver This change adds support for haptic driver controlled by voltage of a regulator. Userspace can control the device via Force Feedback interface from input framework. Signed-off-by: Jaewon Kim Signed-off-by: Hyunhee Kim Acked-by: Kyungmin Park Tested-by: Chanwoo Choi Reviewed-by: Chanwoo Choi Reviewed-by: Pankaj Dubey Signed-off-by: Dmitry Torokhov --- .../devicetree/bindings/input/regulator-haptic.txt | 21 ++ drivers/input/misc/Kconfig | 12 + drivers/input/misc/Makefile | 1 + drivers/input/misc/regulator-haptic.c | 279 +++++++++++++++++++++ include/linux/platform_data/regulator-haptic.h | 29 +++ 5 files changed, 342 insertions(+) create mode 100644 Documentation/devicetree/bindings/input/regulator-haptic.txt create mode 100644 drivers/input/misc/regulator-haptic.c create mode 100644 include/linux/platform_data/regulator-haptic.h (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/input/regulator-haptic.txt b/Documentation/devicetree/bindings/input/regulator-haptic.txt new file mode 100644 index 000000000000..3ed1c7eb2f97 --- /dev/null +++ b/Documentation/devicetree/bindings/input/regulator-haptic.txt @@ -0,0 +1,21 @@ +* Regulator Haptic Device Tree Bindings + +Required Properties: + - compatible : Should be "regulator-haptic" + - haptic-supply : Power supply to the haptic motor. + [*] refer Documentation/devicetree/bindings/regulator/regulator.txt + + - max-microvolt : The maximum voltage value supplied to the haptic motor. + [The unit of the voltage is a micro] + + - min-microvolt : The minimum voltage value supplied to the haptic motor. + [The unit of the voltage is a micro] + +Example: + + haptics { + compatible = "regulator-haptic"; + haptic-supply = <&motor_regulator>; + max-microvolt = <2700000>; + min-microvolt = <1100000>; + }; diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 23297ab6163f..1da0a20c42ea 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -394,6 +394,18 @@ config INPUT_CM109 To compile this driver as a module, choose M here: the module will be called cm109. +config INPUT_REGULATOR_HAPTIC + tristate "Regulator haptics support" + depends on REGULATOR + select INPUT_FF_MEMLESS + help + This option enables device driver support for the haptic controlled + by a regulator. This driver supports ff-memless interface + from input framework. + + To compile this driver as a module, choose M here: the + module will be called regulator-haptic. + config INPUT_RETU_PWRBUTTON tristate "Retu Power button Driver" depends on MFD_RETU diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index 19c760361f80..1f135af4af01 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_INPUT_PMIC8XXX_PWRKEY) += pmic8xxx-pwrkey.o obj-$(CONFIG_INPUT_POWERMATE) += powermate.o obj-$(CONFIG_INPUT_PWM_BEEPER) += pwm-beeper.o obj-$(CONFIG_INPUT_RB532_BUTTON) += rb532_button.o +obj-$(CONFIG_INPUT_REGULATOR_HAPTIC) += regulator-haptic.o obj-$(CONFIG_INPUT_RETU_PWRBUTTON) += retu-pwrbutton.o obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER) += rotary_encoder.o obj-$(CONFIG_INPUT_SGI_BTNS) += sgi_btns.o diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c new file mode 100644 index 000000000000..942622189bee --- /dev/null +++ b/drivers/input/misc/regulator-haptic.c @@ -0,0 +1,279 @@ +/* + * Regulator haptic driver + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Jaewon Kim + * Author: Hyunhee Kim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define MAX_MAGNITUDE_SHIFT 16 + +struct regulator_haptic { + struct device *dev; + struct input_dev *input_dev; + struct regulator *regulator; + + struct work_struct work; + struct mutex mutex; + + bool active; + bool suspended; + + unsigned int max_volt; + unsigned int min_volt; + unsigned int magnitude; +}; + +static int regulator_haptic_toggle(struct regulator_haptic *haptic, bool on) +{ + int error; + + if (haptic->active != on) { + + error = on ? regulator_enable(haptic->regulator) : + regulator_disable(haptic->regulator); + if (error) { + dev_err(haptic->dev, + "failed to switch regulator %s: %d\n", + on ? "on" : "off", error); + return error; + } + + haptic->active = on; + } + + return 0; +} + +static int regulator_haptic_set_voltage(struct regulator_haptic *haptic, + unsigned int magnitude) +{ + u64 volt_mag_multi; + unsigned int intensity; + int error; + + volt_mag_multi = (u64)(haptic->max_volt - haptic->min_volt) * magnitude; + intensity = (unsigned int)(volt_mag_multi >> MAX_MAGNITUDE_SHIFT); + + error = regulator_set_voltage(haptic->regulator, + intensity + haptic->min_volt, + haptic->max_volt); + if (error) { + dev_err(haptic->dev, "cannot set regulator voltage to %d: %d\n", + intensity + haptic->min_volt, error); + return error; + } + + return 0; +} + +static void regulator_haptic_work(struct work_struct *work) +{ + struct regulator_haptic *haptic = container_of(work, + struct regulator_haptic, work); + unsigned int magnitude; + int error; + + mutex_lock(&haptic->mutex); + + if (haptic->suspended) + goto out; + + magnitude = ACCESS_ONCE(haptic->magnitude); + + error = regulator_haptic_set_voltage(haptic, magnitude); + if (error) + goto out; + + regulator_haptic_toggle(haptic, magnitude != 0); + +out: + mutex_unlock(&haptic->mutex); +} + +static int regulator_haptic_play_effect(struct input_dev *input, void *data, + struct ff_effect *effect) +{ + struct regulator_haptic *haptic = input_get_drvdata(input); + + haptic->magnitude = effect->u.rumble.strong_magnitude; + if (!haptic->magnitude) + haptic->magnitude = effect->u.rumble.weak_magnitude; + + schedule_work(&haptic->work); + + return 0; +} + +static void regulator_haptic_close(struct input_dev *input) +{ + struct regulator_haptic *haptic = input_get_drvdata(input); + + cancel_work_sync(&haptic->work); + regulator_haptic_set_voltage(haptic, 0); + regulator_haptic_toggle(haptic, false); +} + +static int __maybe_unused +regulator_haptic_parse_dt(struct device *dev, struct regulator_haptic *haptic) +{ + struct device_node *node; + int error; + + node = dev->of_node; + if(!node) { + dev_err(dev, "Missing dveice tree data\n"); + return -EINVAL; + } + + error = of_property_read_u32(node, "max-microvolt", &haptic->max_volt); + if (error) { + dev_err(dev, "cannot parse max-microvolt\n"); + return error; + } + + error = of_property_read_u32(node, "min-microvolt", &haptic->min_volt); + if (error) { + dev_err(dev, "cannot parse min-microvolt\n"); + return error; + } + + return 0; +} + +static int regulator_haptic_probe(struct platform_device *pdev) +{ + const struct regulator_haptic_data *pdata = dev_get_platdata(&pdev->dev); + struct regulator_haptic *haptic; + struct input_dev *input_dev; + int error; + + haptic = devm_kzalloc(&pdev->dev, sizeof(*haptic), GFP_KERNEL); + if (!haptic) + return -ENOMEM; + + platform_set_drvdata(pdev, haptic); + haptic->dev = &pdev->dev; + mutex_init(&haptic->mutex); + INIT_WORK(&haptic->work, regulator_haptic_work); + + if (pdata) { + haptic->max_volt = pdata->max_volt; + haptic->min_volt = pdata->min_volt; + } else if (IS_ENABLED(CONFIG_OF)) { + error = regulator_haptic_parse_dt(&pdev->dev, haptic); + if (error) + return error; + } else { + dev_err(&pdev->dev, "Missing platform data\n"); + return -EINVAL; + } + + haptic->regulator = devm_regulator_get_exclusive(&pdev->dev, "haptic"); + if (IS_ERR(haptic->regulator)) { + dev_err(&pdev->dev, "failed to get regulator\n"); + return PTR_ERR(haptic->regulator); + } + + input_dev = devm_input_allocate_device(&pdev->dev); + if (!input_dev) + return -ENOMEM; + + haptic->input_dev = input_dev; + haptic->input_dev->name = "regulator-haptic"; + haptic->input_dev->dev.parent = &pdev->dev; + haptic->input_dev->close = regulator_haptic_close; + input_set_drvdata(haptic->input_dev, haptic); + input_set_capability(haptic->input_dev, EV_FF, FF_RUMBLE); + + error = input_ff_create_memless(input_dev, NULL, + regulator_haptic_play_effect); + if (error) { + dev_err(&pdev->dev, "failed to create force-feedback\n"); + return error; + } + + error = input_register_device(haptic->input_dev); + if (error) { + dev_err(&pdev->dev, "failed to register input device\n"); + return error; + } + + return 0; +} + +static int __maybe_unused regulator_haptic_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct regulator_haptic *haptic = platform_get_drvdata(pdev); + int error; + + error = mutex_lock_interruptible(&haptic->mutex); + if (error) + return error; + + regulator_haptic_set_voltage(haptic, 0); + regulator_haptic_toggle(haptic, false); + + haptic->suspended = true; + + mutex_unlock(&haptic->mutex); + + return 0; +} + +static int __maybe_unused regulator_haptic_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct regulator_haptic *haptic = platform_get_drvdata(pdev); + unsigned int magnitude; + + mutex_lock(&haptic->mutex); + + haptic->suspended = false; + + magnitude = ACCESS_ONCE(haptic->magnitude); + if (magnitude) { + regulator_haptic_set_voltage(haptic, magnitude); + regulator_haptic_toggle(haptic, true); + } + + mutex_unlock(&haptic->mutex); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(regulator_haptic_pm_ops, + regulator_haptic_suspend, regulator_haptic_resume); + +static struct of_device_id regulator_haptic_dt_match[] = { + { .compatible = "regulator-haptic" }, + { /* sentinel */ }, +}; + +static struct platform_driver regulator_haptic_driver = { + .probe = regulator_haptic_probe, + .driver = { + .name = "regulator-haptic", + .of_match_table = regulator_haptic_dt_match, + .pm = ®ulator_haptic_pm_ops, + }, +}; +module_platform_driver(regulator_haptic_driver); + +MODULE_AUTHOR("Jaewon Kim "); +MODULE_AUTHOR("Hyunhee Kim "); +MODULE_DESCRIPTION("Regulator haptic driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/regulator-haptic.h b/include/linux/platform_data/regulator-haptic.h new file mode 100644 index 000000000000..5658e58e0738 --- /dev/null +++ b/include/linux/platform_data/regulator-haptic.h @@ -0,0 +1,29 @@ +/* + * Regulator Haptic Platform Data + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Jaewon Kim + * Author: Hyunhee Kim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _REGULATOR_HAPTIC_H +#define _REGULATOR_HAPTIC_H + +/* + * struct regulator_haptic_data - Platform device data + * + * @max_volt: maximum voltage value supplied to the haptic motor. + * + * @min_volt: minimum voltage value supplied to the haptic motor. + * + */ +struct regulator_haptic_data { + unsigned int max_volt; + unsigned int min_volt; +}; + +#endif /* _REGULATOR_HAPTIC_H */ -- cgit v1.2.3 From c5f4546593e9911800f0926c1090959b58bc5c93 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 16 Dec 2014 11:58:18 -0600 Subject: livepatch: kernel: add TAINT_LIVEPATCH This adds a new taint flag to indicate when the kernel or a kernel module has been live patched. This will provide a clean indication in bug reports that live patching was used. Additionally, if the crash occurs in a live patched function, the live patch module will appear beside the patched function in the backtrace. Signed-off-by: Seth Jennings Acked-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Reviewed-by: Petr Mladek Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Kosina --- Documentation/oops-tracing.txt | 2 ++ Documentation/sysctl/kernel.txt | 1 + include/linux/kernel.h | 1 + kernel/panic.c | 2 ++ 4 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt index beefb9f82902..f3ac05cc23e4 100644 --- a/Documentation/oops-tracing.txt +++ b/Documentation/oops-tracing.txt @@ -270,6 +270,8 @@ characters, each representing a particular tainted value. 15: 'L' if a soft lockup has previously occurred on the system. + 16: 'K' if the kernel has been live patched. + The primary reason for the 'Tainted: ' string is to tell kernel debuggers if this is a clean kernel or if anything unusual has occurred. Tainting is permanent: even if an offending module is diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 75511efefc64..83ab25660fc9 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -843,6 +843,7 @@ can be ORed together: 8192 - An unsigned module has been loaded in a kernel supporting module signature. 16384 - A soft lockup has previously occurred on the system. +32768 - The kernel has been live patched. ============================================================== diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5449d2f4a1ef..d03e3deee091 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -471,6 +471,7 @@ extern enum system_states { #define TAINT_OOT_MODULE 12 #define TAINT_UNSIGNED_MODULE 13 #define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] diff --git a/kernel/panic.c b/kernel/panic.c index 4d8d6f906dec..8136ad76e5fd 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -226,6 +226,7 @@ static const struct tnt tnts[] = { { TAINT_OOT_MODULE, 'O', ' ' }, { TAINT_UNSIGNED_MODULE, 'E', ' ' }, { TAINT_SOFTLOCKUP, 'L', ' ' }, + { TAINT_LIVEPATCH, 'K', ' ' }, }; /** @@ -246,6 +247,7 @@ static const struct tnt tnts[] = { * 'O' - Out-of-tree module has been loaded. * 'E' - Unsigned module has been loaded. * 'L' - A soft lockup has previously occurred. + * 'K' - Kernel has been live patched. * * The string is overwritten by the next call to print_tainted(). */ -- cgit v1.2.3 From b700e7f03df5d92f85fa5247fe1f557528d3363d Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 16 Dec 2014 11:58:19 -0600 Subject: livepatch: kernel: add support for live patching This commit introduces code for the live patching core. It implements an ftrace-based mechanism and kernel interface for doing live patching of kernel and kernel module functions. It represents the greatest common functionality set between kpatch and kgraft and can accept patches built using either method. This first version does not implement any consistency mechanism that ensures that old and new code do not run together. In practice, ~90% of CVEs are safe to apply in this way, since they simply add a conditional check. However, any function change that can not execute safely with the old version of the function can _not_ be safely applied in this version. [ jkosina@suse.cz: due to the number of contributions that got folded into this original patch from Seth Jennings, add SUSE's copyright as well, as discussed via e-mail ] Signed-off-by: Seth Jennings Signed-off-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Reviewed-by: Petr Mladek Reviewed-by: Masami Hiramatsu Signed-off-by: Miroslav Benes Signed-off-by: Petr Mladek Signed-off-by: Jiri Kosina --- Documentation/ABI/testing/sysfs-kernel-livepatch | 44 ++ MAINTAINERS | 13 + arch/x86/Kconfig | 3 + arch/x86/include/asm/livepatch.h | 37 + arch/x86/kernel/Makefile | 1 + arch/x86/kernel/livepatch.c | 90 +++ include/linux/livepatch.h | 133 ++++ kernel/Makefile | 1 + kernel/livepatch/Kconfig | 18 + kernel/livepatch/Makefile | 3 + kernel/livepatch/core.c | 930 +++++++++++++++++++++++ 11 files changed, 1273 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-kernel-livepatch create mode 100644 arch/x86/include/asm/livepatch.h create mode 100644 arch/x86/kernel/livepatch.c create mode 100644 include/linux/livepatch.h create mode 100644 kernel/livepatch/Kconfig create mode 100644 kernel/livepatch/Makefile create mode 100644 kernel/livepatch/core.c (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch new file mode 100644 index 000000000000..5bf42a840b22 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-livepatch @@ -0,0 +1,44 @@ +What: /sys/kernel/livepatch +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + Interface for kernel live patching + + The /sys/kernel/livepatch directory contains subdirectories for + each loaded live patch module. + +What: /sys/kernel/livepatch/ +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The patch directory contains subdirectories for each kernel + object (vmlinux or a module) in which it patched functions. + +What: /sys/kernel/livepatch//enabled +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + A writable attribute that indicates whether the patched + code is currently applied. Writing 0 will disable the patch + while writing 1 will re-enable the patch. + +What: /sys/kernel/livepatch// +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The object directory contains subdirectories for each function + that is patched within the object. + +What: /sys/kernel/livepatch/// +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The function directory contains attributes regarding the + properties and state of the patched function. + + There are currently no such attributes. diff --git a/MAINTAINERS b/MAINTAINERS index ddb9ac8d32b3..df6a0784b466 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5784,6 +5784,19 @@ F: Documentation/misc-devices/lis3lv02d F: drivers/misc/lis3lv02d/ F: drivers/platform/x86/hp_accel.c +LIVE PATCHING +M: Josh Poimboeuf +M: Seth Jennings +M: Jiri Kosina +M: Vojtech Pavlik +S: Maintained +F: kernel/livepatch/ +F: include/linux/livepatch.h +F: arch/x86/include/asm/livepatch.h +F: arch/x86/kernel/livepatch.c +F: Documentation/ABI/testing/sysfs-kernel-livepatch +L: live-patching@vger.kernel.org + LLC (802.2) M: Arnaldo Carvalho de Melo S: Maintained diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba397bde7948..460b31b79938 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -17,6 +17,7 @@ config X86_64 depends on 64BIT select X86_DEV_DMA_OPS select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_HAVE_LIVE_PATCHING ### Arch settings config X86 @@ -2008,6 +2009,8 @@ config CMDLINE_OVERRIDE This is used to work around broken boot loaders. This should be set to 'N' under normal conditions. +source "kernel/livepatch/Kconfig" + endmenu config ARCH_ENABLE_MEMORY_HOTPLUG diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h new file mode 100644 index 000000000000..d529db1b1edf --- /dev/null +++ b/arch/x86/include/asm/livepatch.h @@ -0,0 +1,37 @@ +/* + * livepatch.h - x86-specific Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef _ASM_X86_LIVEPATCH_H +#define _ASM_X86_LIVEPATCH_H + +#include + +#ifdef CONFIG_LIVE_PATCHING +#ifndef CC_USING_FENTRY +#error Your compiler must support -mfentry for live patching to work +#endif +extern int klp_write_module_reloc(struct module *mod, unsigned long type, + unsigned long loc, unsigned long value); + +#else +#error Live patching support is disabled; check CONFIG_LIVE_PATCHING +#endif + +#endif /* _ASM_X86_LIVEPATCH_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5d4502c8b983..316b34e74c15 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_LIVE_PATCHING) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c new file mode 100644 index 000000000000..ff3c3101d003 --- /dev/null +++ b/arch/x86/kernel/livepatch.c @@ -0,0 +1,90 @@ +/* + * livepatch.c - x86-specific Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include +#include +#include +#include +#include +#include + +/** + * klp_write_module_reloc() - write a relocation in a module + * @mod: module in which the section to be modified is found + * @type: ELF relocation type (see asm/elf.h) + * @loc: address that the relocation should be written to + * @value: relocation value (sym address + addend) + * + * This function writes a relocation to the specified location for + * a particular module. + */ +int klp_write_module_reloc(struct module *mod, unsigned long type, + unsigned long loc, unsigned long value) +{ + int ret, numpages, size = 4; + bool readonly; + unsigned long val; + unsigned long core = (unsigned long)mod->module_core; + unsigned long core_ro_size = mod->core_ro_size; + unsigned long core_size = mod->core_size; + + switch (type) { + case R_X86_64_NONE: + return 0; + case R_X86_64_64: + val = value; + size = 8; + break; + case R_X86_64_32: + val = (u32)value; + break; + case R_X86_64_32S: + val = (s32)value; + break; + case R_X86_64_PC32: + val = (u32)(value - loc); + break; + default: + /* unsupported relocation type */ + return -EINVAL; + } + + if (loc < core || loc >= core + core_size) + /* loc does not point to any symbol inside the module */ + return -EINVAL; + + if (loc < core + core_ro_size) + readonly = true; + else + readonly = false; + + /* determine if the relocation spans a page boundary */ + numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; + + if (readonly) + set_memory_rw(loc & PAGE_MASK, numpages); + + ret = probe_kernel_write((void *)loc, &val, size); + + if (readonly) + set_memory_ro(loc & PAGE_MASK, numpages); + + return ret; +} diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h new file mode 100644 index 000000000000..950bc615842f --- /dev/null +++ b/include/linux/livepatch.h @@ -0,0 +1,133 @@ +/* + * livepatch.h - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef _LINUX_LIVEPATCH_H_ +#define _LINUX_LIVEPATCH_H_ + +#include +#include + +#if IS_ENABLED(CONFIG_LIVE_PATCHING) + +#include + +enum klp_state { + KLP_DISABLED, + KLP_ENABLED +}; + +/** + * struct klp_func - function structure for live patching + * @old_name: name of the function to be patched + * @new_func: pointer to the patched function code + * @old_addr: a hint conveying at what address the old function + * can be found (optional, vmlinux patches only) + * @kobj: kobject for sysfs resources + * @fops: ftrace operations structure + * @state: tracks function-level patch application state + */ +struct klp_func { + /* external */ + const char *old_name; + void *new_func; + /* + * The old_addr field is optional and can be used to resolve + * duplicate symbol names in the vmlinux object. If this + * information is not present, the symbol is located by name + * with kallsyms. If the name is not unique and old_addr is + * not provided, the patch application fails as there is no + * way to resolve the ambiguity. + */ + unsigned long old_addr; + + /* internal */ + struct kobject kobj; + struct ftrace_ops *fops; + enum klp_state state; +}; + +/** + * struct klp_reloc - relocation structure for live patching + * @loc: address where the relocation will be written + * @val: address of the referenced symbol (optional, + * vmlinux patches only) + * @type: ELF relocation type + * @name: name of the referenced symbol (for lookup/verification) + * @addend: offset from the referenced symbol + * @external: symbol is either exported or within the live patch module itself + */ +struct klp_reloc { + unsigned long loc; + unsigned long val; + unsigned long type; + const char *name; + int addend; + int external; +}; + +/** + * struct klp_object - kernel object structure for live patching + * @name: module name (or NULL for vmlinux) + * @relocs: relocation entries to be applied at load time + * @funcs: function entries for functions to be patched in the object + * @kobj: kobject for sysfs resources + * @mod: kernel module associated with the patched object + * (NULL for vmlinux) + * @state: tracks object-level patch application state + */ +struct klp_object { + /* external */ + const char *name; + struct klp_reloc *relocs; + struct klp_func *funcs; + + /* internal */ + struct kobject *kobj; + struct module *mod; + enum klp_state state; +}; + +/** + * struct klp_patch - patch structure for live patching + * @mod: reference to the live patch module + * @objs: object entries for kernel objects to be patched + * @list: list node for global list of registered patches + * @kobj: kobject for sysfs resources + * @state: tracks patch-level application state + */ +struct klp_patch { + /* external */ + struct module *mod; + struct klp_object *objs; + + /* internal */ + struct list_head list; + struct kobject kobj; + enum klp_state state; +}; + +extern int klp_register_patch(struct klp_patch *); +extern int klp_unregister_patch(struct klp_patch *); +extern int klp_enable_patch(struct klp_patch *); +extern int klp_disable_patch(struct klp_patch *); + +#endif /* CONFIG_LIVE_PATCHING */ + +#endif /* _LINUX_LIVEPATCH_H_ */ diff --git a/kernel/Makefile b/kernel/Makefile index a59481a3fa6c..616994f0a76f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -26,6 +26,7 @@ obj-y += power/ obj-y += printk/ obj-y += irq/ obj-y += rcu/ +obj-y += livepatch/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig new file mode 100644 index 000000000000..96da00fbc120 --- /dev/null +++ b/kernel/livepatch/Kconfig @@ -0,0 +1,18 @@ +config ARCH_HAVE_LIVE_PATCHING + boolean + help + Arch supports kernel live patching + +config LIVE_PATCHING + boolean "Kernel Live Patching" + depends on DYNAMIC_FTRACE_WITH_REGS + depends on MODULES + depends on SYSFS + depends on KALLSYMS_ALL + depends on ARCH_HAVE_LIVE_PATCHING + help + Say Y here if you want to support kernel live patching. + This option has no runtime impact until a kernel "patch" + module uses the interface provided by this option to register + a patch, causing calls to patched functions to be redirected + to new function code contained in the patch module. diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile new file mode 100644 index 000000000000..7c1f00861428 --- /dev/null +++ b/kernel/livepatch/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_LIVE_PATCHING) += livepatch.o + +livepatch-objs := core.o diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c new file mode 100644 index 000000000000..f99fe189d596 --- /dev/null +++ b/kernel/livepatch/core.c @@ -0,0 +1,930 @@ +/* + * core.c - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * The klp_mutex protects the klp_patches list and state transitions of any + * structure reachable from the patches list. References to any structure must + * be obtained under mutex protection. + */ + +static DEFINE_MUTEX(klp_mutex); +static LIST_HEAD(klp_patches); + +static struct kobject *klp_root_kobj; + +static bool klp_is_module(struct klp_object *obj) +{ + return obj->name; +} + +static bool klp_is_object_loaded(struct klp_object *obj) +{ + return !obj->name || obj->mod; +} + +/* sets obj->mod if object is not vmlinux and module is found */ +static void klp_find_object_module(struct klp_object *obj) +{ + if (!klp_is_module(obj)) + return; + + mutex_lock(&module_mutex); + /* + * We don't need to take a reference on the module here because we have + * the klp_mutex, which is also taken by the module notifier. This + * prevents any module from unloading until we release the klp_mutex. + */ + obj->mod = find_module(obj->name); + mutex_unlock(&module_mutex); +} + +/* klp_mutex must be held by caller */ +static bool klp_is_patch_registered(struct klp_patch *patch) +{ + struct klp_patch *mypatch; + + list_for_each_entry(mypatch, &klp_patches, list) + if (mypatch == patch) + return true; + + return false; +} + +static bool klp_initialized(void) +{ + return klp_root_kobj; +} + +struct klp_find_arg { + const char *objname; + const char *name; + unsigned long addr; + /* + * If count == 0, the symbol was not found. If count == 1, a unique + * match was found and addr is set. If count > 1, there is + * unresolvable ambiguity among "count" number of symbols with the same + * name in the same object. + */ + unsigned long count; +}; + +static int klp_find_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_find_arg *args = data; + + if ((mod && !args->objname) || (!mod && args->objname)) + return 0; + + if (strcmp(args->name, name)) + return 0; + + if (args->objname && strcmp(args->objname, mod->name)) + return 0; + + /* + * args->addr might be overwritten if another match is found + * but klp_find_object_symbol() handles this and only returns the + * addr if count == 1. + */ + args->addr = addr; + args->count++; + + return 0; +} + +static int klp_find_object_symbol(const char *objname, const char *name, + unsigned long *addr) +{ + struct klp_find_arg args = { + .objname = objname, + .name = name, + .addr = 0, + .count = 0 + }; + + kallsyms_on_each_symbol(klp_find_callback, &args); + + if (args.count == 0) + pr_err("symbol '%s' not found in symbol table\n", name); + else if (args.count > 1) + pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", + args.count, name, objname); + else { + *addr = args.addr; + return 0; + } + + *addr = 0; + return -EINVAL; +} + +struct klp_verify_args { + const char *name; + const unsigned long addr; +}; + +static int klp_verify_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_verify_args *args = data; + + if (!mod && + !strcmp(args->name, name) && + args->addr == addr) + return 1; + + return 0; +} + +static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) +{ + struct klp_verify_args args = { + .name = name, + .addr = addr, + }; + + if (kallsyms_on_each_symbol(klp_verify_callback, &args)) + return 0; + + pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?", + name, addr); + return -EINVAL; +} + +static int klp_find_verify_func_addr(struct klp_object *obj, + struct klp_func *func) +{ + int ret; + +#if defined(CONFIG_RANDOMIZE_BASE) + /* KASLR is enabled, disregard old_addr from user */ + func->old_addr = 0; +#endif + + if (!func->old_addr || klp_is_module(obj)) + ret = klp_find_object_symbol(obj->name, func->old_name, + &func->old_addr); + else + ret = klp_verify_vmlinux_symbol(func->old_name, + func->old_addr); + + return ret; +} + +/* + * external symbols are located outside the parent object (where the parent + * object is either vmlinux or the kmod being patched). + */ +static int klp_find_external_symbol(struct module *pmod, const char *name, + unsigned long *addr) +{ + const struct kernel_symbol *sym; + + /* first, check if it's an exported symbol */ + preempt_disable(); + sym = find_symbol(name, NULL, NULL, true, true); + preempt_enable(); + if (sym) { + *addr = sym->value; + return 0; + } + + /* otherwise check if it's in another .o within the patch module */ + return klp_find_object_symbol(pmod->name, name, addr); +} + +static int klp_write_object_relocations(struct module *pmod, + struct klp_object *obj) +{ + int ret; + struct klp_reloc *reloc; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + if (WARN_ON(!obj->relocs)) + return -EINVAL; + + for (reloc = obj->relocs; reloc->name; reloc++) { + if (!klp_is_module(obj)) { + ret = klp_verify_vmlinux_symbol(reloc->name, + reloc->val); + if (ret) + return ret; + } else { + /* module, reloc->val needs to be discovered */ + if (reloc->external) + ret = klp_find_external_symbol(pmod, + reloc->name, + &reloc->val); + else + ret = klp_find_object_symbol(obj->mod->name, + reloc->name, + &reloc->val); + if (ret) + return ret; + } + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, + reloc->val + reloc->addend); + if (ret) { + pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", + reloc->name, reloc->val, ret); + return ret; + } + } + + return 0; +} + +static void notrace klp_ftrace_handler(unsigned long ip, + unsigned long parent_ip, + struct ftrace_ops *ops, + struct pt_regs *regs) +{ + struct klp_func *func = ops->private; + + regs->ip = (unsigned long)func->new_func; +} + +static int klp_disable_func(struct klp_func *func) +{ + int ret; + + if (WARN_ON(func->state != KLP_ENABLED)) + return -EINVAL; + + if (WARN_ON(!func->old_addr)) + return -EINVAL; + + ret = unregister_ftrace_function(func->fops); + if (ret) { + pr_err("failed to unregister ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + return ret; + } + + ret = ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0); + if (ret) + pr_warn("function unregister succeeded but failed to clear the filter\n"); + + func->state = KLP_DISABLED; + + return 0; +} + +static int klp_enable_func(struct klp_func *func) +{ + int ret; + + if (WARN_ON(!func->old_addr)) + return -EINVAL; + + if (WARN_ON(func->state != KLP_DISABLED)) + return -EINVAL; + + ret = ftrace_set_filter_ip(func->fops, func->old_addr, 0, 0); + if (ret) { + pr_err("failed to set ftrace filter for function '%s' (%d)\n", + func->old_name, ret); + return ret; + } + + ret = register_ftrace_function(func->fops); + if (ret) { + pr_err("failed to register ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0); + } else { + func->state = KLP_ENABLED; + } + + return ret; +} + +static int klp_disable_object(struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + for (func = obj->funcs; func->old_name; func++) { + if (func->state != KLP_ENABLED) + continue; + + ret = klp_disable_func(func); + if (ret) + return ret; + } + + obj->state = KLP_DISABLED; + + return 0; +} + +static int klp_enable_object(struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (WARN_ON(obj->state != KLP_DISABLED)) + return -EINVAL; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_enable_func(func); + if (ret) + goto unregister; + } + obj->state = KLP_ENABLED; + + return 0; + +unregister: + WARN_ON(klp_disable_object(obj)); + return ret; +} + +static int __klp_disable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + pr_notice("disabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + if (obj->state != KLP_ENABLED) + continue; + + ret = klp_disable_object(obj); + if (ret) + return ret; + } + + patch->state = KLP_DISABLED; + + return 0; +} + +/** + * klp_disable_patch() - disables a registered patch + * @patch: The registered, enabled patch to be disabled + * + * Unregisters the patched functions from ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_disable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + if (patch->state == KLP_DISABLED) { + ret = -EINVAL; + goto err; + } + + ret = __klp_disable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_disable_patch); + +static int __klp_enable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (WARN_ON(patch->state != KLP_DISABLED)) + return -EINVAL; + + pr_notice_once("tainting kernel with TAINT_LIVEPATCH\n"); + add_taint(TAINT_LIVEPATCH, LOCKDEP_STILL_OK); + + pr_notice("enabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + klp_find_object_module(obj); + + if (!klp_is_object_loaded(obj)) + continue; + + ret = klp_enable_object(obj); + if (ret) + goto unregister; + } + + patch->state = KLP_ENABLED; + + return 0; + +unregister: + WARN_ON(__klp_disable_patch(patch)); + return ret; +} + +/** + * klp_enable_patch() - enables a registered patch + * @patch: The registered, disabled patch to be enabled + * + * Performs the needed symbol lookups and code relocations, + * then registers the patched functions with ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_enable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + ret = __klp_enable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_enable_patch); + +/* + * Sysfs Interface + * + * /sys/kernel/livepatch + * /sys/kernel/livepatch/ + * /sys/kernel/livepatch//enabled + * /sys/kernel/livepatch// + * /sys/kernel/livepatch/// + */ + +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct klp_patch *patch; + int ret; + unsigned long val; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return -EINVAL; + + if (val != KLP_DISABLED && val != KLP_ENABLED) + return -EINVAL; + + patch = container_of(kobj, struct klp_patch, kobj); + + mutex_lock(&klp_mutex); + + if (val == patch->state) { + /* already in requested state */ + ret = -EINVAL; + goto err; + } + + if (val == KLP_ENABLED) { + ret = __klp_enable_patch(patch); + if (ret) + goto err; + } else { + ret = __klp_disable_patch(patch); + if (ret) + goto err; + } + + mutex_unlock(&klp_mutex); + + return count; + +err: + mutex_unlock(&klp_mutex); + return ret; +} + +static ssize_t enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch; + + patch = container_of(kobj, struct klp_patch, kobj); + return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->state); +} + +static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled); +static struct attribute *klp_patch_attrs[] = { + &enabled_kobj_attr.attr, + NULL +}; + +static void klp_kobj_release_patch(struct kobject *kobj) +{ + /* + * Once we have a consistency model we'll need to module_put() the + * patch module here. See klp_register_patch() for more details. + */ +} + +static struct kobj_type klp_ktype_patch = { + .release = klp_kobj_release_patch, + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = klp_patch_attrs, +}; + +static void klp_kobj_release_func(struct kobject *kobj) +{ + struct klp_func *func; + + func = container_of(kobj, struct klp_func, kobj); + kfree(func->fops); +} + +static struct kobj_type klp_ktype_func = { + .release = klp_kobj_release_func, + .sysfs_ops = &kobj_sysfs_ops, +}; + +/* + * Free all functions' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_funcs_limited(struct klp_object *obj, + struct klp_func *limit) +{ + struct klp_func *func; + + for (func = obj->funcs; func->old_name && func != limit; func++) + kobject_put(&func->kobj); +} + +/* Clean up when a patched object is unloaded */ +static void klp_free_object_loaded(struct klp_object *obj) +{ + struct klp_func *func; + + obj->mod = NULL; + + for (func = obj->funcs; func->old_name; func++) + func->old_addr = 0; +} + +/* + * Free all objects' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_objects_limited(struct klp_patch *patch, + struct klp_object *limit) +{ + struct klp_object *obj; + + for (obj = patch->objs; obj->funcs && obj != limit; obj++) { + klp_free_funcs_limited(obj, NULL); + kobject_put(obj->kobj); + } +} + +static void klp_free_patch(struct klp_patch *patch) +{ + klp_free_objects_limited(patch, NULL); + if (!list_empty(&patch->list)) + list_del(&patch->list); + kobject_put(&patch->kobj); +} + +static int klp_init_func(struct klp_object *obj, struct klp_func *func) +{ + struct ftrace_ops *ops; + int ret; + + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + ops->private = func; + ops->func = klp_ftrace_handler; + ops->flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_DYNAMIC; + func->fops = ops; + func->state = KLP_DISABLED; + + ret = kobject_init_and_add(&func->kobj, &klp_ktype_func, + obj->kobj, func->old_name); + if (ret) { + kfree(func->fops); + return ret; + } + + return 0; +} + +/* parts of the initialization that is done only when the object is loaded */ +static int klp_init_object_loaded(struct klp_patch *patch, + struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (obj->relocs) { + ret = klp_write_object_relocations(patch->mod, obj); + if (ret) + return ret; + } + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_find_verify_func_addr(obj, func); + if (ret) + return ret; + } + + return 0; +} + +static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) +{ + struct klp_func *func; + int ret; + const char *name; + + if (!obj->funcs) + return -EINVAL; + + obj->state = KLP_DISABLED; + + klp_find_object_module(obj); + + name = klp_is_module(obj) ? obj->name : "vmlinux"; + obj->kobj = kobject_create_and_add(name, &patch->kobj); + if (!obj->kobj) + return -ENOMEM; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_init_func(obj, func); + if (ret) + goto free; + } + + if (klp_is_object_loaded(obj)) { + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto free; + } + + return 0; + +free: + klp_free_funcs_limited(obj, func); + kobject_put(obj->kobj); + return ret; +} + +static int klp_init_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (!patch->objs) + return -EINVAL; + + mutex_lock(&klp_mutex); + + patch->state = KLP_DISABLED; + + ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, + klp_root_kobj, patch->mod->name); + if (ret) + goto unlock; + + for (obj = patch->objs; obj->funcs; obj++) { + ret = klp_init_object(patch, obj); + if (ret) + goto free; + } + + list_add(&patch->list, &klp_patches); + + mutex_unlock(&klp_mutex); + + return 0; + +free: + klp_free_objects_limited(patch, obj); + kobject_put(&patch->kobj); +unlock: + mutex_unlock(&klp_mutex); + return ret; +} + +/** + * klp_unregister_patch() - unregisters a patch + * @patch: Disabled patch to be unregistered + * + * Frees the data structures and removes the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_unregister_patch(struct klp_patch *patch) +{ + int ret = 0; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto out; + } + + if (patch->state == KLP_ENABLED) { + ret = -EBUSY; + goto out; + } + + klp_free_patch(patch); + +out: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_unregister_patch); + +/** + * klp_register_patch() - registers a patch + * @patch: Patch to be registered + * + * Initializes the data structure associated with the patch and + * creates the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_register_patch(struct klp_patch *patch) +{ + int ret; + + if (!klp_initialized()) + return -ENODEV; + + if (!patch || !patch->mod) + return -EINVAL; + + /* + * A reference is taken on the patch module to prevent it from being + * unloaded. Right now, we don't allow patch modules to unload since + * there is currently no method to determine if a thread is still + * running in the patched code contained in the patch module once + * the ftrace registration is successful. + */ + if (!try_module_get(patch->mod)) + return -ENODEV; + + ret = klp_init_patch(patch); + if (ret) + module_put(patch->mod); + + return ret; +} +EXPORT_SYMBOL_GPL(klp_register_patch); + +static void klp_module_notify_coming(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + int ret; + + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto err; + + if (patch->state == KLP_DISABLED) + return; + + pr_notice("applying patch '%s' to loading module '%s'\n", + pmod->name, mod->name); + + ret = klp_enable_object(obj); + if (!ret) + return; + +err: + pr_warn("failed to apply patch '%s' to module '%s' (%d)\n", + pmod->name, mod->name, ret); +} + +static void klp_module_notify_going(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + int ret; + + if (patch->state == KLP_DISABLED) + goto disabled; + + pr_notice("reverting patch '%s' on unloading module '%s'\n", + pmod->name, mod->name); + + ret = klp_disable_object(obj); + if (ret) + pr_warn("failed to revert patch '%s' on module '%s' (%d)\n", + pmod->name, mod->name, ret); + +disabled: + klp_free_object_loaded(obj); +} + +static int klp_module_notify(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct module *mod = data; + struct klp_patch *patch; + struct klp_object *obj; + + if (action != MODULE_STATE_COMING && action != MODULE_STATE_GOING) + return 0; + + mutex_lock(&klp_mutex); + + list_for_each_entry(patch, &klp_patches, list) { + for (obj = patch->objs; obj->funcs; obj++) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + if (action == MODULE_STATE_COMING) { + obj->mod = mod; + klp_module_notify_coming(patch, obj); + } else /* MODULE_STATE_GOING */ + klp_module_notify_going(patch, obj); + + break; + } + } + + mutex_unlock(&klp_mutex); + + return 0; +} + +static struct notifier_block klp_module_nb = { + .notifier_call = klp_module_notify, + .priority = INT_MIN+1, /* called late but before ftrace notifier */ +}; + +static int klp_init(void) +{ + int ret; + + ret = register_module_notifier(&klp_module_nb); + if (ret) + return ret; + + klp_root_kobj = kobject_create_and_add("livepatch", kernel_kobj); + if (!klp_root_kobj) { + ret = -ENOMEM; + goto unregister; + } + + return 0; + +unregister: + unregister_module_notifier(&klp_module_nb); + return ret; +} + +module_init(klp_init); -- cgit v1.2.3 From 2c658e212ce7e40ace56d9441c8c5634d4d420e3 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 18 Dec 2014 16:12:08 +0200 Subject: spi: Remove FSF mailing addresses Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown --- drivers/spi/spi-au1550.c | 4 ---- drivers/spi/spi-bcm2835.c | 4 ---- drivers/spi/spi-bcm63xx.c | 4 ---- drivers/spi/spi-bitbang.c | 4 ---- drivers/spi/spi-butterfly.c | 4 ---- drivers/spi/spi-coldfire-qspi.c | 5 ----- drivers/spi/spi-davinci.c | 4 ---- drivers/spi/spi-gpio.c | 4 ---- drivers/spi/spi-lm70llp.c | 4 ---- drivers/spi/spi-omap-100k.c | 5 ----- drivers/spi/spi-omap-uwire.c | 4 ---- drivers/spi/spi-omap2-mcspi.c | 5 ----- drivers/spi/spi-pxa2xx-pxadma.c | 4 ---- drivers/spi/spi-pxa2xx.c | 4 ---- drivers/spi/spi-rspi.c | 5 ----- drivers/spi/spi-s3c64xx.c | 4 ---- drivers/spi/spi-sc18is602.c | 4 ---- drivers/spi/spi-sh-hspi.c | 5 ----- drivers/spi/spi-sh.c | 5 ----- drivers/spi/spi-topcliff-pch.c | 4 ---- drivers/spi/spi.c | 4 ---- drivers/spi/spidev.c | 4 ---- include/linux/spi/at86rf230.h | 4 ---- include/linux/spi/l4f00242t03.h | 4 ---- include/linux/spi/lms283gf05.h | 4 ---- include/linux/spi/mxs-spi.h | 4 ---- include/linux/spi/pxa2xx_spi.h | 4 ---- include/linux/spi/rspi.h | 5 ----- include/linux/spi/sh_hspi.h | 4 ---- include/linux/spi/spi.h | 4 ---- include/linux/spi/tle62x0.h | 4 ---- include/linux/spi/tsc2005.h | 5 ----- 32 files changed, 136 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c index 326f47973684..f45e085c01a6 100644 --- a/drivers/spi/spi-au1550.c +++ b/drivers/spi/spi-au1550.c @@ -15,10 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 98aab457b24d..419a782ab6d5 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -17,10 +17,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ #include diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index c20530982e26..e73e2b052c9c 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, */ #include diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index dc7d2c2d643e..5ef6638d5e8a 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c index ee4f91ccd8fd..9a95862986c8 100644 --- a/drivers/spi/spi-butterfly.c +++ b/drivers/spi/spi-butterfly.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include #include diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c index 41b5dc4445f6..688956ff5095 100644 --- a/drivers/spi/spi-coldfire-qspi.c +++ b/drivers/spi/spi-coldfire-qspi.c @@ -12,11 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA - * */ #include diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c index b3707badb1e5..5e991065f5b0 100644 --- a/drivers/spi/spi-davinci.c +++ b/drivers/spi/spi-davinci.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index aee4e7589568..2b76492fe5c1 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include #include diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c index 41c5765be746..ba72347cb99d 100644 --- a/drivers/spi/spi-lm70llp.c +++ b/drivers/spi/spi-lm70llp.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c index 79399ae9c84c..d890d309dff9 100644 --- a/drivers/spi/spi-omap-100k.c +++ b/drivers/spi/spi-omap-100k.c @@ -16,11 +16,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #include #include diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c index daf1ada5cd11..3c0844457c07 100644 --- a/drivers/spi/spi-omap-uwire.c +++ b/drivers/spi/spi-omap-uwire.c @@ -28,10 +28,6 @@ * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. */ #include #include diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 3bc3cbabbbc0..4df8942058de 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -14,11 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #include diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c index e8a26f25d5c0..e51fcf9fd39b 100644 --- a/drivers/spi/spi-pxa2xx-pxadma.c +++ b/drivers/spi/spi-pxa2xx-pxadma.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 05c623cfb078..7a9a605d9bd2 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 2071f788c6fb..46ce47076e63 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -15,11 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 37b19836f5cb..9231c34b5a5c 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c index 237f2e7a7179..5a56acf8a43e 100644 --- a/drivers/spi/spi-sc18is602.c +++ b/drivers/spi/spi-sc18is602.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c index fc29233d0650..20e800e70442 100644 --- a/drivers/spi/spi-sh-hspi.c +++ b/drivers/spi/spi-sh-hspi.c @@ -16,11 +16,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include diff --git a/drivers/spi/spi-sh.c b/drivers/spi/spi-sh.c index 1cfc906dd174..502501187c9e 100644 --- a/drivers/spi/spi-sh.c +++ b/drivers/spi/spi-sh.c @@ -14,11 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c index be692ad50442..93dfcee0f987 100644 --- a/drivers/spi/spi-topcliff-pch.c +++ b/drivers/spi/spi-topcliff-pch.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. */ #include diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 66a70e9bc743..c76cc7568639 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 6941e04afb8c..6f97e5af282b 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -14,10 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index b2b1afbb3202..cd519a11c2c6 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -12,10 +12,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - * * Written by: * Dmitry Eremin-Solenikov */ diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h index bc8677c8eba9..e69e9b51b21a 100644 --- a/include/linux/spi/l4f00242t03.h +++ b/include/linux/spi/l4f00242t03.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h index 555d254e6606..fdd1d1d51da5 100644 --- a/include/linux/spi/lms283gf05.h +++ b/include/linux/spi/lms283gf05.h @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h index 4835486f58e5..381d368b91b4 100644 --- a/include/linux/spi/mxs-spi.h +++ b/include/linux/spi/mxs-spi.h @@ -15,10 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ #ifndef __LINUX_SPI_MXS_SPI_H__ diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index d5a316550177..5eb56e35cf0d 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __linux_pxa2xx_spi_h #define __linux_pxa2xx_spi_h diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h index e546b2ceb623..a693188cc08b 100644 --- a/include/linux/spi/rspi.h +++ b/include/linux/spi/rspi.h @@ -11,11 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #ifndef __LINUX_SPI_RENESAS_SPI_H__ diff --git a/include/linux/spi/sh_hspi.h b/include/linux/spi/sh_hspi.h index a1121f872ac1..aa0d440ab4f0 100644 --- a/include/linux/spi/sh_hspi.h +++ b/include/linux/spi/sh_hspi.h @@ -9,10 +9,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef SH_HSPI_H #define SH_HSPI_H diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a6ef2a8e6de4..6e2664a17114 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __LINUX_SPI_H diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h index 60b59187e590..414c6fddfcf0 100644 --- a/include/linux/spi/tle62x0.h +++ b/include/linux/spi/tle62x0.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ struct tle62x0_pdata { diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h index 8f721e465e05..563b3b1799a8 100644 --- a/include/linux/spi/tsc2005.h +++ b/include/linux/spi/tsc2005.h @@ -12,11 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _LINUX_SPI_TSC2005_H -- cgit v1.2.3 From c4827bb859cbe8afad9287c9dd4e7162119d3d59 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 18 Dec 2014 15:04:21 +0200 Subject: spi: pxa2xx: Add definition for Intel Quark DDS_RATE register Intel Quark DDS_RATE register is defined only in register access macro. Add a definition for it to common SSP register definitions for preparing to cleanup those macros. Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 77aed9ea1d26..dab545bb66b3 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -37,6 +37,7 @@ #define SSDR (0x10) /* SSP Data Write/Data Read Register */ #define SSTO (0x28) /* SSP Time Out Register */ +#define DDS_RATE (0x28) /* SSP DDS Clock Rate Register (Intel Quark) */ #define SSPSP (0x2C) /* SSP Programmable Serial Protocol */ #define SSTSA (0x30) /* SSP Tx Timeslot Active */ #define SSRSA (0x34) /* SSP Rx Timeslot Active */ -- cgit v1.2.3 From 32d17597d3e299ffe8b07e3afc12f8074e7ae483 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 9 Apr 2014 08:13:18 -0300 Subject: [media] v4l: vsp1: Remove support for platform data Now that all platforms instantiate the VSP1 through DT, platform data support isn't needed anymore. Signed-off-by: Laurent Pinchart Acked-by: Simon Horman Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/Kconfig | 2 +- drivers/media/platform/vsp1/vsp1.h | 14 +++++- drivers/media/platform/vsp1/vsp1_drv.c | 81 ++++++++++++---------------------- drivers/media/platform/vsp1/vsp1_wpf.c | 2 +- include/linux/platform_data/vsp1.h | 27 ------------ 5 files changed, 43 insertions(+), 83 deletions(-) delete mode 100644 include/linux/platform_data/vsp1.h (limited to 'include/linux') diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 765bffb49a72..480a174832a6 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -223,7 +223,7 @@ config VIDEO_SH_VEU config VIDEO_RENESAS_VSP1 tristate "Renesas VSP1 Video Processing Engine" depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA - depends on ARCH_SHMOBILE || COMPILE_TEST + depends on (ARCH_SHMOBILE && OF) || COMPILE_TEST select VIDEOBUF2_DMA_CONTIG ---help--- This is a V4L2 driver for the Renesas VSP1 video processing engine. diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h index 12467191dff4..989e96f7e360 100644 --- a/drivers/media/platform/vsp1/vsp1.h +++ b/drivers/media/platform/vsp1/vsp1.h @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -40,9 +39,20 @@ struct vsp1_uds; #define VSP1_MAX_UDS 3 #define VSP1_MAX_WPF 4 +#define VSP1_HAS_LIF (1 << 0) +#define VSP1_HAS_LUT (1 << 1) +#define VSP1_HAS_SRU (1 << 2) + +struct vsp1_platform_data { + unsigned int features; + unsigned int rpf_count; + unsigned int uds_count; + unsigned int wpf_count; +}; + struct vsp1_device { struct device *dev; - struct vsp1_platform_data *pdata; + struct vsp1_platform_data pdata; void __iomem *mmio; struct clk *clock; diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c index 5eb16e87d53f..913485a90e97 100644 --- a/drivers/media/platform/vsp1/vsp1_drv.c +++ b/drivers/media/platform/vsp1/vsp1_drv.c @@ -40,7 +40,7 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data) irqreturn_t ret = IRQ_NONE; unsigned int i; - for (i = 0; i < vsp1->pdata->wpf_count; ++i) { + for (i = 0; i < vsp1->pdata.wpf_count; ++i) { struct vsp1_rwpf *wpf = vsp1->wpf[i]; struct vsp1_pipeline *pipe; u32 status; @@ -181,7 +181,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities); - if (vsp1->pdata->features & VSP1_HAS_LIF) { + if (vsp1->pdata.features & VSP1_HAS_LIF) { vsp1->lif = vsp1_lif_create(vsp1); if (IS_ERR(vsp1->lif)) { ret = PTR_ERR(vsp1->lif); @@ -191,7 +191,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&vsp1->lif->entity.list_dev, &vsp1->entities); } - if (vsp1->pdata->features & VSP1_HAS_LUT) { + if (vsp1->pdata.features & VSP1_HAS_LUT) { vsp1->lut = vsp1_lut_create(vsp1); if (IS_ERR(vsp1->lut)) { ret = PTR_ERR(vsp1->lut); @@ -201,7 +201,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&vsp1->lut->entity.list_dev, &vsp1->entities); } - for (i = 0; i < vsp1->pdata->rpf_count; ++i) { + for (i = 0; i < vsp1->pdata.rpf_count; ++i) { struct vsp1_rwpf *rpf; rpf = vsp1_rpf_create(vsp1, i); @@ -214,7 +214,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&rpf->entity.list_dev, &vsp1->entities); } - if (vsp1->pdata->features & VSP1_HAS_SRU) { + if (vsp1->pdata.features & VSP1_HAS_SRU) { vsp1->sru = vsp1_sru_create(vsp1); if (IS_ERR(vsp1->sru)) { ret = PTR_ERR(vsp1->sru); @@ -224,7 +224,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&vsp1->sru->entity.list_dev, &vsp1->entities); } - for (i = 0; i < vsp1->pdata->uds_count; ++i) { + for (i = 0; i < vsp1->pdata.uds_count; ++i) { struct vsp1_uds *uds; uds = vsp1_uds_create(vsp1, i); @@ -237,7 +237,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) list_add_tail(&uds->entity.list_dev, &vsp1->entities); } - for (i = 0; i < vsp1->pdata->wpf_count; ++i) { + for (i = 0; i < vsp1->pdata.wpf_count; ++i) { struct vsp1_rwpf *wpf; wpf = vsp1_wpf_create(vsp1, i); @@ -261,7 +261,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) goto done; } - if (vsp1->pdata->features & VSP1_HAS_LIF) { + if (vsp1->pdata.features & VSP1_HAS_LIF) { ret = media_entity_create_link( &vsp1->wpf[0]->entity.subdev.entity, RWPF_PAD_SOURCE, &vsp1->lif->entity.subdev.entity, LIF_PAD_SINK, 0); @@ -294,7 +294,7 @@ static int vsp1_device_init(struct vsp1_device *vsp1) /* Reset any channel that might be running. */ status = vsp1_read(vsp1, VI6_STATUS); - for (i = 0; i < vsp1->pdata->wpf_count; ++i) { + for (i = 0; i < vsp1->pdata.wpf_count; ++i) { unsigned int timeout; if (!(status & VI6_STATUS_SYS_ACT(i))) @@ -318,10 +318,10 @@ static int vsp1_device_init(struct vsp1_device *vsp1) vsp1_write(vsp1, VI6_CLK_DCSWT, (8 << VI6_CLK_DCSWT_CSTPW_SHIFT) | (8 << VI6_CLK_DCSWT_CSTRW_SHIFT)); - for (i = 0; i < vsp1->pdata->rpf_count; ++i) + for (i = 0; i < vsp1->pdata.rpf_count; ++i) vsp1_write(vsp1, VI6_DPR_RPF_ROUTE(i), VI6_DPR_NODE_UNUSED); - for (i = 0; i < vsp1->pdata->uds_count; ++i) + for (i = 0; i < vsp1->pdata.uds_count; ++i) vsp1_write(vsp1, VI6_DPR_UDS_ROUTE(i), VI6_DPR_NODE_UNUSED); vsp1_write(vsp1, VI6_DPR_SRU_ROUTE, VI6_DPR_NODE_UNUSED); @@ -428,28 +428,36 @@ static const struct dev_pm_ops vsp1_pm_ops = { * Platform Driver */ -static int vsp1_validate_platform_data(struct platform_device *pdev, - struct vsp1_platform_data *pdata) +static int vsp1_parse_dt(struct vsp1_device *vsp1) { - if (pdata == NULL) { - dev_err(&pdev->dev, "missing platform data\n"); - return -EINVAL; - } + struct device_node *np = vsp1->dev->of_node; + struct vsp1_platform_data *pdata = &vsp1->pdata; + + if (of_property_read_bool(np, "renesas,has-lif")) + pdata->features |= VSP1_HAS_LIF; + if (of_property_read_bool(np, "renesas,has-lut")) + pdata->features |= VSP1_HAS_LUT; + if (of_property_read_bool(np, "renesas,has-sru")) + pdata->features |= VSP1_HAS_SRU; + + of_property_read_u32(np, "renesas,#rpf", &pdata->rpf_count); + of_property_read_u32(np, "renesas,#uds", &pdata->uds_count); + of_property_read_u32(np, "renesas,#wpf", &pdata->wpf_count); if (pdata->rpf_count <= 0 || pdata->rpf_count > VSP1_MAX_RPF) { - dev_err(&pdev->dev, "invalid number of RPF (%u)\n", + dev_err(vsp1->dev, "invalid number of RPF (%u)\n", pdata->rpf_count); return -EINVAL; } if (pdata->uds_count <= 0 || pdata->uds_count > VSP1_MAX_UDS) { - dev_err(&pdev->dev, "invalid number of UDS (%u)\n", + dev_err(vsp1->dev, "invalid number of UDS (%u)\n", pdata->uds_count); return -EINVAL; } if (pdata->wpf_count <= 0 || pdata->wpf_count > VSP1_MAX_WPF) { - dev_err(&pdev->dev, "invalid number of WPF (%u)\n", + dev_err(vsp1->dev, "invalid number of WPF (%u)\n", pdata->wpf_count); return -EINVAL; } @@ -457,33 +465,6 @@ static int vsp1_validate_platform_data(struct platform_device *pdev, return 0; } -static struct vsp1_platform_data * -vsp1_get_platform_data(struct platform_device *pdev) -{ - struct device_node *np = pdev->dev.of_node; - struct vsp1_platform_data *pdata; - - if (!IS_ENABLED(CONFIG_OF) || np == NULL) - return pdev->dev.platform_data; - - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (pdata == NULL) - return NULL; - - if (of_property_read_bool(np, "renesas,has-lif")) - pdata->features |= VSP1_HAS_LIF; - if (of_property_read_bool(np, "renesas,has-lut")) - pdata->features |= VSP1_HAS_LUT; - if (of_property_read_bool(np, "renesas,has-sru")) - pdata->features |= VSP1_HAS_SRU; - - of_property_read_u32(np, "renesas,#rpf", &pdata->rpf_count); - of_property_read_u32(np, "renesas,#uds", &pdata->uds_count); - of_property_read_u32(np, "renesas,#wpf", &pdata->wpf_count); - - return pdata; -} - static int vsp1_probe(struct platform_device *pdev) { struct vsp1_device *vsp1; @@ -499,11 +480,7 @@ static int vsp1_probe(struct platform_device *pdev) mutex_init(&vsp1->lock); INIT_LIST_HEAD(&vsp1->entities); - vsp1->pdata = vsp1_get_platform_data(pdev); - if (vsp1->pdata == NULL) - return -ENODEV; - - ret = vsp1_validate_platform_data(pdev, vsp1->pdata); + ret = vsp1_parse_dt(vsp1); if (ret < 0) return ret; diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c index 6e057762c933..b1089d05583a 100644 --- a/drivers/media/platform/vsp1/vsp1_wpf.c +++ b/drivers/media/platform/vsp1/vsp1_wpf.c @@ -280,7 +280,7 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index) * except for the WPF0 source link if a LIF is present. */ flags = MEDIA_LNK_FL_ENABLED; - if (!(vsp1->pdata->features & VSP1_HAS_LIF) || index != 0) + if (!(vsp1->pdata.features & VSP1_HAS_LIF) || index != 0) flags |= MEDIA_LNK_FL_IMMUTABLE; ret = media_entity_create_link(&wpf->entity.subdev.entity, diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h deleted file mode 100644 index 63170e2614b3..000000000000 --- a/include/linux/platform_data/vsp1.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * vsp1.h -- R-Car VSP1 Platform Data - * - * Copyright (C) 2013 Renesas Corporation - * - * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ -#ifndef __PLATFORM_VSP1_H__ -#define __PLATFORM_VSP1_H__ - -#define VSP1_HAS_LIF (1 << 0) -#define VSP1_HAS_LUT (1 << 1) -#define VSP1_HAS_SRU (1 << 2) - -struct vsp1_platform_data { - unsigned int features; - unsigned int rpf_count; - unsigned int uds_count; - unsigned int wpf_count; -}; - -#endif /* __PLATFORM_VSP1_H__ */ -- cgit v1.2.3 From 3110628d89f80fbafa085fd62e75afcb39fb764c Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Fri, 19 Dec 2014 17:15:53 +0900 Subject: spi: sh-msiof: Configure MSIOF sync signal timing in device tree The MSIOF controller has DTDL and SYNCDL in SITMDR1 register. So, this patch adds new properties like the following commit: d0fb47a5237d8b9576113568bacfd27892308b62 (spi: fsl-espi: Configure FSL eSPI CSBEF and CSAFT) Signed-off-by: Yoshihiro Shimoda Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/spi/sh-msiof.txt | 16 ++++++++ drivers/spi/spi-sh-msiof.c | 47 ++++++++++++++++++++++ include/linux/spi/sh_msiof.h | 2 + 3 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt index d11c3721e7cd..4c388bb2f0a2 100644 --- a/Documentation/devicetree/bindings/spi/sh-msiof.txt +++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt @@ -30,6 +30,22 @@ Optional properties: specifiers, one for transmission, and one for reception. - dma-names : Must contain a list of two DMA names, "tx" and "rx". +- renesas,dtdl : delay sync signal (setup) in transmit mode. + Must contain one of the following values: + 0 (no bit delay) + 50 (0.5-clock-cycle delay) + 100 (1-clock-cycle delay) + 150 (1.5-clock-cycle delay) + 200 (2-clock-cycle delay) + +- renesas,syncdl : delay sync signal (hold) in transmit mode. + Must contain one of the following values: + 0 (no bit delay) + 50 (0.5-clock-cycle delay) + 100 (1-clock-cycle delay) + 150 (1.5-clock-cycle delay) + 200 (2-clock-cycle delay) + 300 (3-clock-cycle delay) Optional properties, deprecated for soctype-specific bindings: - renesas,tx-fifo-size : Overrides the default tx fifo size given in words diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 239be7cbe5a8..2a87cb939f56 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -82,6 +82,8 @@ struct sh_msiof_spi_priv { #define MDR1_SYNCMD_LR 0x30000000 /* L/R mode */ #define MDR1_SYNCAC_SHIFT 25 /* Sync Polarity (1 = Active-low) */ #define MDR1_BITLSB_SHIFT 24 /* MSB/LSB First (1 = LSB first) */ +#define MDR1_DTDL_SHIFT 20 /* Data Pin Bit Delay for MSIOF_SYNC */ +#define MDR1_SYNCDL_SHIFT 16 /* Frame Sync Signal Timing Delay */ #define MDR1_FLD_MASK 0x000000c0 /* Frame Sync Signal Interval (0-3) */ #define MDR1_FLD_SHIFT 2 #define MDR1_XXSTP 0x00000001 /* Transmission/Reception Stop on FIFO */ @@ -279,6 +281,48 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p, sh_msiof_write(p, RSCR, sh_msiof_spi_clk_table[k].scr); } +static u32 sh_msiof_get_delay_bit(u32 dtdl_or_syncdl) +{ + /* + * DTDL/SYNCDL bit : p->info->dtdl or p->info->syncdl + * b'000 : 0 + * b'001 : 100 + * b'010 : 200 + * b'011 (SYNCDL only) : 300 + * b'101 : 50 + * b'110 : 150 + */ + if (dtdl_or_syncdl % 100) + return dtdl_or_syncdl / 100 + 5; + else + return dtdl_or_syncdl / 100; +} + +static u32 sh_msiof_spi_get_dtdl_and_syncdl(struct sh_msiof_spi_priv *p) +{ + u32 val; + + if (!p->info) + return 0; + + /* check if DTDL and SYNCDL is allowed value */ + if (p->info->dtdl > 200 || p->info->syncdl > 300) { + dev_warn(&p->pdev->dev, "DTDL or SYNCDL is too large\n"); + return 0; + } + + /* check if the sum of DTDL and SYNCDL becomes an integer value */ + if ((p->info->dtdl + p->info->syncdl) % 100) { + dev_warn(&p->pdev->dev, "the sum of DTDL/SYNCDL is not good\n"); + return 0; + } + + val = sh_msiof_get_delay_bit(p->info->dtdl) << MDR1_DTDL_SHIFT; + val |= sh_msiof_get_delay_bit(p->info->syncdl) << MDR1_SYNCDL_SHIFT; + + return val; +} + static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p, u32 cpol, u32 cpha, u32 tx_hi_z, u32 lsb_first, u32 cs_high) @@ -296,6 +340,7 @@ static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p, tmp = MDR1_SYNCMD_SPI | 1 << MDR1_FLD_SHIFT | MDR1_XXSTP; tmp |= !cs_high << MDR1_SYNCAC_SHIFT; tmp |= lsb_first << MDR1_BITLSB_SHIFT; + tmp |= sh_msiof_spi_get_dtdl_and_syncdl(p); sh_msiof_write(p, TMDR1, tmp | MDR1_TRMD | TMDR1_PCON); if (p->chipdata->master_flags & SPI_MASTER_MUST_TX) { /* These bits are reserved if RX needs TX */ @@ -952,6 +997,8 @@ static struct sh_msiof_spi_info *sh_msiof_spi_parse_dt(struct device *dev) &info->tx_fifo_override); of_property_read_u32(np, "renesas,rx-fifo-size", &info->rx_fifo_override); + of_property_read_u32(np, "renesas,dtdl", &info->dtdl); + of_property_read_u32(np, "renesas,syncdl", &info->syncdl); info->num_chipselect = num_cs; diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h index 88a14d81c49e..b087a85f5f72 100644 --- a/include/linux/spi/sh_msiof.h +++ b/include/linux/spi/sh_msiof.h @@ -7,6 +7,8 @@ struct sh_msiof_spi_info { u16 num_chipselect; unsigned int dma_tx_id; unsigned int dma_rx_id; + u32 dtdl; + u32 syncdl; }; #endif /* __SPI_SH_MSIOF_H__ */ -- cgit v1.2.3 From 0425e2420c0ab1b5da24f6d9fce39241ad85fc46 Mon Sep 17 00:00:00 2001 From: Flora Fu Date: Fri, 5 Dec 2014 12:07:54 +0800 Subject: regulator: mt6397: Add support for MT6397 regulator Add MT6397 regulator driver. Signed-off-by: Flora Fu Signed-off-by: Mark Brown --- drivers/regulator/Kconfig | 9 + drivers/regulator/Makefile | 1 + drivers/regulator/mt6397-regulator.c | 332 +++++++++++++++++++++++++++++ include/linux/regulator/mt6397-regulator.h | 49 +++++ 4 files changed, 391 insertions(+) create mode 100644 drivers/regulator/mt6397-regulator.c create mode 100644 include/linux/regulator/mt6397-regulator.h (limited to 'include/linux') diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index c3a60b57a865..f622d0613d27 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -433,6 +433,15 @@ config REGULATOR_MC13892 Say y here to support the regulators found on the Freescale MC13892 PMIC. +config REGULATOR_MT6397 + tristate "MediaTek MT6397 PMIC" + depends on MFD_MT6397 + help + Say y here to select this option to enable the power regulator of + MediaTek MT6397 PMIC. + This driver supports the control of different power rails of device + through regulator interface. + config REGULATOR_PALMAS tristate "TI Palmas PMIC Regulators" depends on MFD_PALMAS diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 1f28ebfc6f3a..1a0fbc397de1 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_REGULATOR_MAX77802) += max77802.o obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o obj-$(CONFIG_REGULATOR_MC13XXX_CORE) += mc13xxx-regulator-core.o +obj-$(CONFIG_REGULATOR_MT6397) += mt6397-regulator.o obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c new file mode 100644 index 000000000000..a5b2f4762677 --- /dev/null +++ b/drivers/regulator/mt6397-regulator.c @@ -0,0 +1,332 @@ +/* + * Copyright (c) 2014 MediaTek Inc. + * Author: Flora Fu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * MT6397 regulators' information + * + * @desc: standard fields of regulator description. + * @qi: Mask for query enable signal status of regulators + * @vselon_reg: Register sections for hardware control mode of bucks + * @vselctrl_reg: Register for controlling the buck control mode. + * @vselctrl_mask: Mask for query buck's voltage control mode. + */ +struct mt6397_regulator_info { + struct regulator_desc desc; + u32 qi; + u32 vselon_reg; + u32 vselctrl_reg; + u32 vselctrl_mask; +}; + +#define MT6397_BUCK(match, vreg, min, max, step, volt_ranges, enreg, \ + vosel, vosel_mask, voselon, vosel_ctrl) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_range_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = (max - min)/step + 1, \ + .linear_ranges = volt_ranges, \ + .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = enreg, \ + .enable_mask = BIT(0), \ + }, \ + .qi = BIT(13), \ + .vselon_reg = voselon, \ + .vselctrl_reg = vosel_ctrl, \ + .vselctrl_mask = BIT(1), \ +} + +#define MT6397_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel, \ + vosel_mask) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_table_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = ARRAY_SIZE(ldo_volt_table), \ + .volt_table = ldo_volt_table, \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + }, \ + .qi = BIT(15), \ +} + +#define MT6397_REG_FIXED(match, vreg, enreg, enbit, volt) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_fixed_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = 1, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + .min_uV = volt, \ + }, \ + .qi = BIT(15), \ +} + +static const struct regulator_linear_range buck_volt_range1[] = { + REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250), +}; + +static const struct regulator_linear_range buck_volt_range2[] = { + REGULATOR_LINEAR_RANGE(800000, 0, 0x7f, 6250), +}; + +static const struct regulator_linear_range buck_volt_range3[] = { + REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000), +}; + +static const u32 ldo_volt_table1[] = { + 1500000, 1800000, 2500000, 2800000, +}; + +static const u32 ldo_volt_table2[] = { + 1800000, 3300000, +}; + +static const u32 ldo_volt_table3[] = { + 3000000, 3300000, +}; + +static const u32 ldo_volt_table4[] = { + 1220000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table5[] = { + 1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table5_v2[] = { + 1200000, 1000000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table6[] = { + 1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000, +}; + +static const u32 ldo_volt_table7[] = { + 1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000, +}; + +static int mt6397_get_status(struct regulator_dev *rdev) +{ + int ret; + u32 regval; + struct mt6397_regulator_info *info = rdev_get_drvdata(rdev); + + ret = regmap_read(rdev->regmap, info->desc.enable_reg, ®val); + if (ret != 0) { + dev_err(&rdev->dev, "Failed to get enable reg: %d\n", ret); + return ret; + } + + return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF; +} + +static struct regulator_ops mt6397_volt_range_ops = { + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +static struct regulator_ops mt6397_volt_table_ops = { + .list_voltage = regulator_list_voltage_table, + .map_voltage = regulator_map_voltage_iterate, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +static struct regulator_ops mt6397_volt_fixed_ops = { + .list_voltage = regulator_list_voltage_linear, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +/* The array is indexed by id(MT6397_ID_XXX) */ +static struct mt6397_regulator_info mt6397_regulators[] = { + MT6397_BUCK("buck_vpca15", VPCA15, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VCA15_CON7, MT6397_VCA15_CON9, 0x7f, + MT6397_VCA15_CON10, MT6397_VCA15_CON5), + MT6397_BUCK("buck_vpca7", VPCA7, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VPCA7_CON7, MT6397_VPCA7_CON9, 0x7f, + MT6397_VPCA7_CON10, MT6397_VPCA7_CON5), + MT6397_BUCK("buck_vsramca15", VSRAMCA15, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VSRMCA15_CON7, MT6397_VSRMCA15_CON9, + 0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5), + MT6397_BUCK("buck_vsramca7", VSRAMCA7, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VSRMCA7_CON7, MT6397_VSRMCA7_CON9, + 0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5), + MT6397_BUCK("buck_vcore", VCORE, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VCORE_CON7, MT6397_VCORE_CON9, 0x7f, + MT6397_VCORE_CON10, MT6397_VCORE_CON5), + MT6397_BUCK("buck_vgpu", VGPU, 700000, 1493750, 6250, buck_volt_range1, + MT6397_VGPU_CON7, MT6397_VGPU_CON9, 0x7f, + MT6397_VGPU_CON10, MT6397_VGPU_CON5), + MT6397_BUCK("buck_vdrm", VDRM, 800000, 1593750, 6250, buck_volt_range2, + MT6397_VDRM_CON7, MT6397_VDRM_CON9, 0x7f, + MT6397_VDRM_CON10, MT6397_VDRM_CON5), + MT6397_BUCK("buck_vio18", VIO18, 1500000, 2120000, 20000, + buck_volt_range3, MT6397_VIO18_CON7, MT6397_VIO18_CON9, 0x1f, + MT6397_VIO18_CON10, MT6397_VIO18_CON5), + MT6397_REG_FIXED("ldo_vtcxo", VTCXO, MT6397_ANALDO_CON0, 10, 2800000), + MT6397_REG_FIXED("ldo_va28", VA28, MT6397_ANALDO_CON1, 14, 2800000), + MT6397_LDO("ldo_vcama", VCAMA, ldo_volt_table1, + MT6397_ANALDO_CON2, 15, MT6397_ANALDO_CON6, 0xC0), + MT6397_REG_FIXED("ldo_vio28", VIO28, MT6397_DIGLDO_CON0, 14, 2800000), + MT6397_REG_FIXED("ldo_vusb", VUSB, MT6397_DIGLDO_CON1, 14, 3300000), + MT6397_LDO("ldo_vmc", VMC, ldo_volt_table2, + MT6397_DIGLDO_CON2, 12, MT6397_DIGLDO_CON29, 0x10), + MT6397_LDO("ldo_vmch", VMCH, ldo_volt_table3, + MT6397_DIGLDO_CON3, 14, MT6397_DIGLDO_CON17, 0x80), + MT6397_LDO("ldo_vemc3v3", VEMC3V3, ldo_volt_table3, + MT6397_DIGLDO_CON4, 14, MT6397_DIGLDO_CON18, 0x10), + MT6397_LDO("ldo_vgp1", VGP1, ldo_volt_table4, + MT6397_DIGLDO_CON5, 15, MT6397_DIGLDO_CON19, 0xE0), + MT6397_LDO("ldo_vgp2", VGP2, ldo_volt_table5, + MT6397_DIGLDO_CON6, 15, MT6397_DIGLDO_CON20, 0xE0), + MT6397_LDO("ldo_vgp3", VGP3, ldo_volt_table5, + MT6397_DIGLDO_CON7, 15, MT6397_DIGLDO_CON21, 0xE0), + MT6397_LDO("ldo_vgp4", VGP4, ldo_volt_table5, + MT6397_DIGLDO_CON8, 15, MT6397_DIGLDO_CON22, 0xE0), + MT6397_LDO("ldo_vgp5", VGP5, ldo_volt_table6, + MT6397_DIGLDO_CON9, 15, MT6397_DIGLDO_CON23, 0xE0), + MT6397_LDO("ldo_vgp6", VGP6, ldo_volt_table5, + MT6397_DIGLDO_CON10, 15, MT6397_DIGLDO_CON33, 0xE0), + MT6397_LDO("ldo_vibr", VIBR, ldo_volt_table7, + MT6397_DIGLDO_CON24, 15, MT6397_DIGLDO_CON25, 0xE00), +}; + +static int mt6397_set_buck_vosel_reg(struct platform_device *pdev) +{ + struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent); + int i; + u32 regval; + + for (i = 0; i < MT6397_MAX_REGULATOR; i++) { + if (mt6397_regulators[i].vselctrl_reg) { + if (regmap_read(mt6397->regmap, + mt6397_regulators[i].vselctrl_reg, + ®val) < 0) { + dev_err(&pdev->dev, + "Failed to read buck ctrl\n"); + return -EIO; + } + + if (regval & mt6397_regulators[i].vselctrl_mask) { + mt6397_regulators[i].desc.vsel_reg = + mt6397_regulators[i].vselon_reg; + } + } + } + + return 0; +} + +static int mt6397_regulator_probe(struct platform_device *pdev) +{ + struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = {}; + struct regulator_dev *rdev; + int i; + u32 reg_value, version; + + /* Query buck controller to select activated voltage register part */ + if (mt6397_set_buck_vosel_reg(pdev)) + return -EIO; + + /* Read PMIC chip revision to update constraints and voltage table */ + if (regmap_read(mt6397->regmap, MT6397_CID, ®_value) < 0) { + dev_err(&pdev->dev, "Failed to read Chip ID\n"); + return -EIO; + } + dev_info(&pdev->dev, "Chip ID = 0x%x\n", reg_value); + + version = (reg_value & 0xFF); + switch (version) { + case MT6397_REGULATOR_ID91: + mt6397_regulators[MT6397_ID_VGP2].desc.volt_table = + ldo_volt_table5_v2; + break; + default: + break; + } + + for (i = 0; i < MT6397_MAX_REGULATOR; i++) { + config.dev = &pdev->dev; + config.driver_data = &mt6397_regulators[i]; + config.regmap = mt6397->regmap; + rdev = devm_regulator_register(&pdev->dev, + &mt6397_regulators[i].desc, &config); + if (IS_ERR(rdev)) { + dev_err(&pdev->dev, "failed to register %s\n", + mt6397_regulators[i].desc.name); + return PTR_ERR(rdev); + } + } + + return 0; +} + +static struct platform_driver mt6397_regulator_driver = { + .driver = { + .name = "mt6397-regulator", + }, + .probe = mt6397_regulator_probe, +}; + +module_platform_driver(mt6397_regulator_driver); + +MODULE_AUTHOR("Flora Fu "); +MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6397 PMIC"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:mt6397-regulator"); diff --git a/include/linux/regulator/mt6397-regulator.h b/include/linux/regulator/mt6397-regulator.h new file mode 100644 index 000000000000..30cc5963e265 --- /dev/null +++ b/include/linux/regulator/mt6397-regulator.h @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2014 MediaTek Inc. + * Author: Flora Fu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_MT6397_H +#define __LINUX_REGULATOR_MT6397_H + +enum { + MT6397_ID_VPCA15 = 0, + MT6397_ID_VPCA7, + MT6397_ID_VSRAMCA15, + MT6397_ID_VSRAMCA7, + MT6397_ID_VCORE, + MT6397_ID_VGPU, + MT6397_ID_VDRM, + MT6397_ID_VIO18 = 7, + MT6397_ID_VTCXO, + MT6397_ID_VA28, + MT6397_ID_VCAMA, + MT6397_ID_VIO28, + MT6397_ID_VUSB, + MT6397_ID_VMC, + MT6397_ID_VMCH, + MT6397_ID_VEMC3V3, + MT6397_ID_VGP1, + MT6397_ID_VGP2, + MT6397_ID_VGP3, + MT6397_ID_VGP4, + MT6397_ID_VGP5, + MT6397_ID_VGP6, + MT6397_ID_VIBR, + MT6397_ID_RG_MAX, +}; + +#define MT6397_MAX_REGULATOR MT6397_ID_RG_MAX +#define MT6397_REGULATOR_ID97 0x97 +#define MT6397_REGULATOR_ID91 0x91 + +#endif /* __LINUX_REGULATOR_MT6397_H */ -- cgit v1.2.3 From 0628ee7c81a8ced9b10f9ee300707f7f79fdecf1 Mon Sep 17 00:00:00 2001 From: Nicholas Krause Date: Sun, 21 Dec 2014 22:36:37 -0500 Subject: libata: s/ata_id_removeable()/ata_id_removable()/ Changes the spelling typos of removeable to removable where ata_id_removeable is defined in ata.h and called in libata-scsi.c respectively. Signed-off-by: Nicholas Krause Signed-off-by: Tejun Heo --- drivers/ata/libata-scsi.c | 4 ++-- include/linux/ata.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e364e86e84d7..7659d6468303 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1995,8 +1995,8 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) VPRINTK("ENTER\n"); - /* set scsi removeable (RMB) bit per ata bit */ - if (ata_id_removeable(args->id)) + /* set scsi removable (RMB) bit per ata bit */ + if (ata_id_removable(args->id)) hdr[1] |= (1 << 7); if (args->dev->class == ATA_DEV_ZAC) { diff --git a/include/linux/ata.h b/include/linux/ata.h index f2f4d8da97c0..1648026e06b4 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -503,7 +503,7 @@ struct ata_bmdma_prd { #define ata_id_has_dma(id) ((id)[ATA_ID_CAPABILITY] & (1 << 8)) #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) -#define ata_id_removeable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) +#define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ -- cgit v1.2.3 From 6810e4a394f9d781050107529b8d1465c00b7b13 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 10:26:10 -0500 Subject: percpu_ref: remove unnecessary ACCESS_ONCE() in percpu_ref_tryget_live() __ref_is_percpu() needs the implied ACCESS_ONCE() in lockless_dereference() on @ref->percpu_count_ptr because the value is tested for !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then used as a pointer. If the compiler generates a separate fetch when using it as a pointer, __PERCPU_REF_ATOMIC may be set in between contaminating the pointer value. percpu_ref_tryget_live() also uses ACCESS_ONCE() to test __PERCPU_REF_DEAD; however, there's no reason for this. I just copied ACCESS_ONCE() usage blindly from __ref_is_percpu(). All it does is confusing people trying to understand what's going on. This patch removes the unnecessary ACCESS_ONCE() usage from percpu_ref_tryget_live() and adds a comment explaining why __ref_is_percpu() needs it. Signed-off-by: Tejun Heo Cc: Kent Overstreet --- include/linux/percpu-refcount.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b4337646388b..6a7a670366ab 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -128,8 +128,22 @@ static inline void percpu_ref_kill(struct percpu_ref *ref) static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { - /* paired with smp_store_release() in percpu_ref_reinit() */ - unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr); + unsigned long percpu_ptr; + + /* + * The value of @ref->percpu_count_ptr is tested for + * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then + * used as a pointer. If the compiler generates a separate fetch + * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in + * between contaminating the pointer value, meaning that + * ACCESS_ONCE() is required when fetching it. + * + * Also, we need a data dependency barrier to be paired with + * smp_store_release() in __percpu_ref_switch_to_percpu(). + * + * Use lockless deref which contains both. + */ + percpu_ptr = lockless_dereference(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, @@ -233,7 +247,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; - } else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) { + } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->count); } -- cgit v1.2.3 From 4c907baf36d8339f393bb576d0bab29194d0e6ad Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 10:26:10 -0500 Subject: percpu_ref: implement percpu_ref_is_dying() Implement percpu_ref_is_dying() which tests whether the ref is dying or dead. This is useful to determine the current state when a percpu_ref is used as a cyclic on/off switch via kill and reinit. Signed-off-by: Tejun Heo Cc: Kent Overstreet --- include/linux/percpu-refcount.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 6a7a670366ab..12c9b485beb7 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -294,6 +294,20 @@ static inline void percpu_ref_put(struct percpu_ref *ref) percpu_ref_put_many(ref, 1); } +/** + * percpu_ref_is_dying - test whether a percpu refcount is dying or dead + * @ref: percpu_ref to test + * + * Returns %true if @ref is dying or dead. + * + * This function is safe to call as long as @ref is between init and exit + * and the caller is responsible for synchronizing against state changes. + */ +static inline bool percpu_ref_is_dying(struct percpu_ref *ref) +{ + return ref->percpu_count_ptr & __PERCPU_REF_DEAD; +} + /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test -- cgit v1.2.3 From 24dab7a7b3534ef40ecec20cfd7fb3ad99d9ff33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 12:02:46 -0500 Subject: cgroup: reorder SUBSYS(blkio) in cgroup_subsys.h The scheduled cgroup writeback support requires blkio to be initialized before memcg as memcg needs to provide certain blkcg related functionalities. Relocate blkio so that it's right above memory. Signed-off-by: Tejun Heo --- include/linux/cgroup_subsys.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 98c4f9b12b03..e4a96fb14403 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -15,6 +15,10 @@ SUBSYS(cpu) SUBSYS(cpuacct) #endif +#if IS_ENABLED(CONFIG_BLK_CGROUP) +SUBSYS(blkio) +#endif + #if IS_ENABLED(CONFIG_MEMCG) SUBSYS(memory) #endif @@ -31,10 +35,6 @@ SUBSYS(freezer) SUBSYS(net_cls) #endif -#if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) -#endif - #if IS_ENABLED(CONFIG_CGROUP_PERF) SUBSYS(perf_event) #endif -- cgit v1.2.3 From f3ba53802eff25e3eedb60d7afe5262710e20bd5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 12:02:46 -0500 Subject: cgroup: add dummy css_put() for !CONFIG_CGROUPS This will later be depended upon by the scheduled cgroup writeback support. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index da0dae0600e6..b9cb94c3102a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -943,6 +943,8 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, #else /* !CONFIG_CGROUPS */ +struct cgroup_subsys_state; + static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_fork(struct task_struct *p) {} @@ -955,6 +957,8 @@ static inline int cgroupstats_build(struct cgroupstats *stats, return -EINVAL; } +static inline void css_put(struct cgroup_subsys_state *css) {} + /* No cgroups - nothing to do */ static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) -- cgit v1.2.3 From 536fa402221f09633e7c5801b327055ab716a363 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 5 Sep 2014 11:14:48 -0700 Subject: compiler: Allow 1- and 2-byte smp_load_acquire() and smp_store_release() CPUs without single-byte and double-byte loads and stores place some "interesting" requirements on concurrent code. For example (adapted from Peter Hurley's test code), suppose we have the following structure: struct foo { spinlock_t lock1; spinlock_t lock2; char a; /* Protected by lock1. */ char b; /* Protected by lock2. */ }; struct foo *foop; Of course, it is common (and good) practice to place data protected by different locks in separate cache lines. However, if the locks are rarely acquired (for example, only in rare error cases), and there are a great many instances of the data structure, then memory footprint can trump false-sharing concerns, so that it can be better to place them in the same cache cache line as above. But if the CPU does not support single-byte loads and stores, a store to foop->a will do a non-atomic read-modify-write operation on foop->b, which will come as a nasty surprise to someone holding foop->lock2. So we now require CPUs to support single-byte and double-byte loads and stores. Therefore, this commit adjusts the definition of __native_word() to allow these sizes to be used by smp_load_acquire() and smp_store_release(). Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a1c81f80978e..49811cdddaa5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -385,7 +385,7 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int /* Is this type a native word size -- useful for atomic operations */ #ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) #endif /* Compile time object size, -1 for unknown */ -- cgit v1.2.3 From ac59853c06993a442e8060bc19040b2ca3025aec Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Thu, 13 Nov 2014 14:24:14 -0500 Subject: rcupdate: Replace smp_read_barrier_depends() with lockless_dereference() Recently lockless_dereference() was added which can be used in place of hard-coding smp_read_barrier_depends(). The following PATCH makes the change. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ed4f5939a452..386ba288084a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -582,11 +582,11 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_check(p, c, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ @@ -603,10 +603,10 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_index_check(p, c) \ ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(p) _________p1 = lockless_dereference(p); \ rcu_lockdep_assert(c, \ "suspicious rcu_dereference_index_check() usage"); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3 From f520c98e3e5212d8c282a86d9b7697dd70326192 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 12 Dec 2014 09:36:14 +0800 Subject: rculist: Fix sparse warning This fixes the following sparse warnings: make C=1 CF=-D__CHECK_ENDIAN__ net/ipv6/addrconf.o net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) To silence these spare complaints, an RCU annotation should be added to "next" pointer of hlist_node structure through hlist_next_rcu() macro when iterating over a hlist with hlist_for_each_entry_continue_rcu_bh(). By the way, this commit also resolves the same error appearing in hlist_for_each_entry_continue_rcu(). Signed-off-by: Ying Xue Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 529bc946f450..a18b16f1dc0e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point @@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point -- cgit v1.2.3 From a5c198f4f7da6cc48116ca239c59c9f44b753364 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 23 Nov 2014 20:30:06 -0800 Subject: rcu: Expand SRCU ->completed to 64 bits When rcutorture used only the low-order 32 bits of the grace-period number, it was not a problem for SRCU to use a 32-bit completed field. However, rcutorture now uses the full 64 bits on 64-bit systems, so this commit converts SRCU's ->completed field to unsigned long so as to provide 64 bits on 64-bit systems. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 4 ++-- kernel/rcu/srcu.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index a2783cb5d275..ef923dd96249 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -45,7 +45,7 @@ struct rcu_batch { #define RCU_BATCH_INIT(name) { NULL, &(name.head) } struct srcu_struct { - unsigned completed; + unsigned long completed; struct srcu_struct_array __percpu *per_cpu_ref; spinlock_t queue_lock; /* protect ->batch_queue, ->running */ bool running; @@ -135,7 +135,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); -long srcu_batches_completed(struct srcu_struct *sp); +unsigned long srcu_batches_completed(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index e037f3eb2f7b..445bf8ffe3fb 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier); * Report the number of batches, correlated with, but not necessarily * precisely the same as, the number of grace periods that have elapsed. */ -long srcu_batches_completed(struct srcu_struct *sp) +unsigned long srcu_batches_completed(struct srcu_struct *sp) { return sp->completed; } -- cgit v1.2.3 From 9735af5c78599703be633c057af3faee26482028 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 26 Nov 2014 10:42:50 -0800 Subject: rcu: Combine DEFINE_SRCU() and DEFINE_STATIC_SRCU() The DEFINE_SRCU() and DEFINE_STATIC_SRCU() definitions are quite similar, so this commit combines them, saving a bit of code and removing redundancy. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index ef923dd96249..9cfd9623fb03 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work); * define and init a srcu struct at build time. * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it. */ -#define DEFINE_SRCU(name) \ +#define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - struct srcu_struct name = __SRCU_STRUCT_INIT(name); - -#define DEFINE_STATIC_SRCU(name) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name); + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) +#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) +#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) /** * call_srcu() - Queue a callback for invocation after an SRCU grace period -- cgit v1.2.3 From 9da7dae94fb8adab5cc5f395640e30736a66e910 Mon Sep 17 00:00:00 2001 From: Valentin Rothberg Date: Tue, 6 Jan 2015 17:29:29 +0100 Subject: workqueue.h: remove loops of single statement macros checkpatch.pl complained about two single statement macros in do while (0) loops. The loops and the trailing semicolons are now removed, which makes checkpatch happy and the two macros consistent with the rest of the file. Signed-off-by: Valentin Rothberg Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b996e6cde6bb..74db135f9957 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -220,14 +220,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif #define INIT_WORK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 0); \ - } while (0) + __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 1); \ - } while (0) + __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ -- cgit v1.2.3 From 26e022727f5e88c6e5054e14d954425deacbe56a Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 18 Dec 2014 16:02:17 +0100 Subject: efi: Rename efi_guid_unparse to efi_guid_to_str Call it what it does - "unparse" is plain-misleading. Signed-off-by: Borislav Petkov Signed-off-by: Ricardo Neri --- block/partitions/efi.c | 2 +- drivers/firmware/efi/efi.c | 4 ++-- drivers/firmware/efi/efivars.c | 6 +++--- fs/efivarfs/super.c | 2 +- include/linux/efi.h | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/partitions/efi.c b/block/partitions/efi.c index 56d08fd75b1a..26cb624ace05 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -715,7 +715,7 @@ int efi_partition(struct parsed_partitions *state) state->parts[i + 1].flags = ADDPART_FLAG_RAID; info = &state->parts[i + 1].info; - efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid); + efi_guid_to_str(&ptes[i].unique_partition_guid, info->uuid); /* Naively convert UTF16-LE to 7 bits. */ label_max = min(ARRAY_SIZE(info->volname) - 1, diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 8590099ac148..ff0bbe383b31 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -272,10 +272,10 @@ static __init int match_config_table(efi_guid_t *guid, int i; if (table_types) { - efi_guid_unparse(guid, str); + efi_guid_to_str(guid, str); for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) { - efi_guid_unparse(&table_types[i].guid, str); + efi_guid_to_str(&table_types[i].guid, str); if (!efi_guidcmp(*guid, table_types[i].guid)) { *(table_types[i].ptr) = table; diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index f256ecd8a176..7b2e0496e0c0 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -39,7 +39,7 @@ * fix locking per Peter Chubb's findings * * 25 Mar 2002 - Matt Domsch - * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_unparse() + * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_to_str() * * 12 Feb 2002 - Matt Domsch * use list_for_each_safe when deleting vars. @@ -128,7 +128,7 @@ efivar_guid_read(struct efivar_entry *entry, char *buf) if (!entry || !buf) return 0; - efi_guid_unparse(&var->VendorGuid, str); + efi_guid_to_str(&var->VendorGuid, str); str += strlen(str); str += sprintf(str, "\n"); @@ -569,7 +569,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var) private variables from another's. */ *(short_name + strlen(short_name)) = '-'; - efi_guid_unparse(&new_var->var.VendorGuid, + efi_guid_to_str(&new_var->var.VendorGuid, short_name + strlen(short_name)); new_var->kobj.kset = efivars_kset; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6dad1176ec52..ddbce42548c9 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -140,7 +140,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len] = '-'; - efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; diff --git a/include/linux/efi.h b/include/linux/efi.h index 0949f9c7e872..d762c81e62a8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -844,7 +844,7 @@ efi_guidcmp (efi_guid_t left, efi_guid_t right) } static inline char * -efi_guid_unparse(efi_guid_t *guid, char *out) +efi_guid_to_str(efi_guid_t *guid, char *out) { sprintf(out, "%pUl", guid->b); return out; -- cgit v1.2.3 From bfa21a0dfe6915dc85953b5d40ea9dae5fdf205f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 5 Jan 2015 12:48:42 +0100 Subject: regulator: Allow parsing custom properties when using simplified DT parsing When drivers use simplified DT parsing method (they provide 'regulator_desc.of_match') they still may want to parse custom properties for some of the regulators. For example some of the regulators support GPIO enable control. Add a driver-supplied callback for such case. This way the regulator core parses common bindings offloading a lot of code from drivers and still custom properties may be used. The callback, called for each parsed regulator, may modify the 'regulator_config' initially passed to regulator_register(). Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mark Brown --- drivers/regulator/core.c | 2 +- drivers/regulator/internal.h | 2 ++ drivers/regulator/of_regulator.c | 11 +++++++++++ include/linux/regulator/driver.h | 13 +++++++++++++ 4 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c13b557a560e..5fae8cabd254 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3635,7 +3635,7 @@ regulator_register(const struct regulator_desc *regulator_desc, return ERR_PTR(-ENOMEM); } - init_data = regulator_of_get_init_data(dev, regulator_desc, + init_data = regulator_of_get_init_data(dev, regulator_desc, config, &rdev->dev.of_node); if (!init_data) { init_data = config->init_data; diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h index 80ba2a35a04b..c74ac8734023 100644 --- a/drivers/regulator/internal.h +++ b/drivers/regulator/internal.h @@ -38,11 +38,13 @@ struct regulator { #ifdef CONFIG_OF struct regulator_init_data *regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node); #else static inline struct regulator_init_data * regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node) { return NULL; diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 91eaaf010524..24e812c48d93 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -270,6 +270,7 @@ EXPORT_SYMBOL_GPL(of_regulator_match); struct regulator_init_data *regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node) { struct device_node *search, *child; @@ -307,6 +308,16 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev, break; } + if (desc->of_parse_cb) { + if (desc->of_parse_cb(child, desc, config)) { + dev_err(dev, + "driver callback failed to parse DT for regulator %s\n", + child->name); + init_data = NULL; + break; + } + } + of_node_get(child); *node = child; break; diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 5f1e9ca47417..d4ad5b5a02bb 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -21,6 +21,7 @@ struct regmap; struct regulator_dev; +struct regulator_config; struct regulator_init_data; struct regulator_enable_gpio; @@ -205,6 +206,15 @@ enum regulator_type { * @supply_name: Identifying the regulator supply * @of_match: Name used to identify regulator in DT. * @regulators_node: Name of node containing regulator definitions in DT. + * @of_parse_cb: Optional callback called only if of_match is present. + * Will be called for each regulator parsed from DT, during + * init_data parsing. + * The regulator_config passed as argument to the callback will + * be a copy of config passed to regulator_register, valid only + * for this particular call. Callback may freely change the + * config but it cannot store it for later usage. + * Callback should return 0 on success or negative ERRNO + * indicating failure. * @id: Numerical identifier for the regulator. * @ops: Regulator operations table. * @irq: Interrupt number for the regulator. @@ -251,6 +261,9 @@ struct regulator_desc { const char *supply_name; const char *of_match; const char *regulators_node; + int (*of_parse_cb)(struct device_node *, + const struct regulator_desc *, + struct regulator_config *); int id; bool continuous_voltage_range; unsigned n_voltages; -- cgit v1.2.3 From e5a7a72cd51a585b8f1a1e299bf88fff44b94440 Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Fri, 9 Jan 2015 09:57:33 +0800 Subject: regulator: pfuze100-regulator: add pfuze3000 support Add pfuze3000 chip support. Signed-off-by: Robin Gong Signed-off-by: Mark Brown --- .../devicetree/bindings/regulator/pfuze100.txt | 94 ++++++++++++++- drivers/regulator/pfuze100-regulator.c | 134 +++++++++++++++++++-- include/linux/regulator/pfuze100.h | 14 +++ 3 files changed, 232 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt index 34ef5d16d0f1..9b40db88f637 100644 --- a/Documentation/devicetree/bindings/regulator/pfuze100.txt +++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt @@ -1,7 +1,7 @@ PFUZE100 family of regulators Required properties: -- compatible: "fsl,pfuze100" or "fsl,pfuze200" +- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000" - reg: I2C slave address Required child node: @@ -14,6 +14,8 @@ Required child node: sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6 --PFUZE200 sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6 + --PFUZE3000 + sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4 Each regulator is defined using the standard binding for regulators. @@ -205,3 +207,93 @@ Example 2: PFUZE200 }; }; }; + +Example 3: PFUZE3000 + + pmic: pfuze3000@08 { + compatible = "fsl,pfuze3000"; + reg = <0x08>; + + regulators { + sw1a_reg: sw1a { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1475000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + /* use sw1c_reg to align with pfuze100/pfuze200 */ + sw1c_reg: sw1b { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1475000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + + sw2_reg: sw2 { + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + sw3a_reg: sw3 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <1650000>; + regulator-boot-on; + regulator-always-on; + }; + + swbst_reg: swbst { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5150000>; + }; + + snvs_reg: vsnvs { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3000000>; + regulator-boot-on; + regulator-always-on; + }; + + vref_reg: vrefddr { + regulator-boot-on; + regulator-always-on; + }; + + vgen1_reg: vldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen2_reg: vldo2 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1550000>; + }; + + vgen3_reg: vccsd { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen4_reg: v33 { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + }; + + vgen5_reg: vldo3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen6_reg: vldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + }; + }; diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index c879dff597ee..8cc8d1877c44 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -56,7 +56,7 @@ #define PFUZE100_VGEN5VOL 0x70 #define PFUZE100_VGEN6VOL 0x71 -enum chips { PFUZE100, PFUZE200 }; +enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 }; struct pfuze_regulator { struct regulator_desc desc; @@ -80,9 +80,18 @@ static const int pfuze100_vsnvs[] = { 1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000, }; +static const int pfuze3000_sw2lo[] = { + 1500000, 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, +}; + +static const int pfuze3000_sw2hi[] = { + 2500000, 2800000, 2850000, 3000000, 3100000, 3150000, 3200000, 3300000, +}; + static const struct i2c_device_id pfuze_device_id[] = { {.name = "pfuze100", .driver_data = PFUZE100}, {.name = "pfuze200", .driver_data = PFUZE200}, + {.name = "pfuze3000", .driver_data = PFUZE3000}, { } }; MODULE_DEVICE_TABLE(i2c, pfuze_device_id); @@ -90,6 +99,7 @@ MODULE_DEVICE_TABLE(i2c, pfuze_device_id); static const struct of_device_id pfuze_dt_ids[] = { { .compatible = "fsl,pfuze100", .data = (void *)PFUZE100}, { .compatible = "fsl,pfuze200", .data = (void *)PFUZE200}, + { .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000}, { } }; MODULE_DEVICE_TABLE(of, pfuze_dt_ids); @@ -219,6 +229,60 @@ static struct regulator_ops pfuze100_swb_regulator_ops = { .stby_mask = 0x20, \ } +#define PFUZE3000_VCC_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name, \ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_ldo_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base), \ + .vsel_mask = 0x3, \ + .enable_reg = (base), \ + .enable_mask = 0x10, \ + }, \ + .stby_reg = (base), \ + .stby_mask = 0x20, \ +} + + +#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name,\ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = 0x7, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = 0x7, \ +} + +#define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name,\ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = 0xf, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = 0xf, \ +} + /* PFUZE100 */ static struct pfuze_regulator pfuze100_regulators[] = { PFUZE100_SW_REG(PFUZE100, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000), @@ -254,6 +318,22 @@ static struct pfuze_regulator pfuze200_regulators[] = { PFUZE100_VGEN_REG(PFUZE200, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), }; +static struct pfuze_regulator pfuze3000_regulators[] = { + PFUZE100_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 700000, 1475000, 25000), + PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000), + PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), + PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000), + PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst), + PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), + PFUZE100_FIXED_REG(PFUZE3000, VREFDDR, PFUZE100_VREFDDRCON, 750000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000), + PFUZE3000_VCC_REG(PFUZE3000, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000), + PFUZE3000_VCC_REG(PFUZE3000, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), +}; + static struct pfuze_regulator *pfuze_regulators; #ifdef CONFIG_OF @@ -294,6 +374,24 @@ static struct of_regulator_match pfuze200_matches[] = { { .name = "vgen6", }, }; +/* PFUZE3000 */ +static struct of_regulator_match pfuze3000_matches[] = { + + { .name = "sw1a", }, + { .name = "sw1b", }, + { .name = "sw2", }, + { .name = "sw3", }, + { .name = "swbst", }, + { .name = "vsnvs", }, + { .name = "vrefddr", }, + { .name = "vldo1", }, + { .name = "vldo2", }, + { .name = "vccsd", }, + { .name = "v33", }, + { .name = "vldo3", }, + { .name = "vldo4", }, +}; + static struct of_regulator_match *pfuze_matches; static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) @@ -313,6 +411,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) } switch (chip->chip_id) { + case PFUZE3000: + pfuze_matches = pfuze3000_matches; + ret = of_regulator_match(dev, parent, pfuze3000_matches, + ARRAY_SIZE(pfuze3000_matches)); + break; case PFUZE200: pfuze_matches = pfuze200_matches; ret = of_regulator_match(dev, parent, pfuze200_matches, @@ -378,7 +481,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip) * as ID=8 in PFUZE100 */ dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8"); - } else if ((value & 0x0f) != pfuze_chip->chip_id) { + } else if ((value & 0x0f) != pfuze_chip->chip_id && + (value & 0xf0) >> 4 != pfuze_chip->chip_id) { /* device id NOT match with your setting */ dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value); return -ENODEV; @@ -417,7 +521,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client, int i, ret; const struct of_device_id *match; u32 regulator_num; - u32 sw_check_start, sw_check_end; + u32 sw_check_start, sw_check_end, sw_hi = 0x40; pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip), GFP_KERNEL); @@ -458,13 +562,19 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* use the right regulators after identify the right device */ switch (pfuze_chip->chip_id) { + case PFUZE3000: + pfuze_regulators = pfuze3000_regulators; + regulator_num = ARRAY_SIZE(pfuze3000_regulators); + sw_check_start = PFUZE3000_SW2; + sw_check_end = PFUZE3000_SW2; + sw_hi = 1 << 3; + break; case PFUZE200: pfuze_regulators = pfuze200_regulators; regulator_num = ARRAY_SIZE(pfuze200_regulators); sw_check_start = PFUZE200_SW2; sw_check_end = PFUZE200_SW3B; break; - case PFUZE100: default: pfuze_regulators = pfuze100_regulators; @@ -474,7 +584,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client, break; } dev_info(&client->dev, "pfuze%s found.\n", - (pfuze_chip->chip_id == PFUZE100) ? "100" : "200"); + (pfuze_chip->chip_id == PFUZE100) ? "100" : + ((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000")); memcpy(pfuze_chip->regulator_descs, pfuze_regulators, sizeof(pfuze_chip->regulator_descs)); @@ -498,10 +609,15 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* SW2~SW4 high bit check and modify the voltage value table */ if (i >= sw_check_start && i <= sw_check_end) { regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val); - if (val & 0x40) { - desc->min_uV = 800000; - desc->uV_step = 50000; - desc->n_voltages = 51; + if (val & sw_hi) { + if (pfuze_chip->chip_id == PFUZE3000) { + desc->volt_table = pfuze3000_sw2hi; + desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi); + } else { + desc->min_uV = 800000; + desc->uV_step = 50000; + desc->n_voltages = 51; + } } } diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index 364f7a7c43db..70c6c66c5bcf 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -49,6 +49,20 @@ #define PFUZE200_VGEN5 11 #define PFUZE200_VGEN6 12 +#define PFUZE3000_SW1A 0 +#define PFUZE3000_SW1B 1 +#define PFUZE3000_SW2 2 +#define PFUZE3000_SW3 3 +#define PFUZE3000_SWBST 4 +#define PFUZE3000_VSNVS 5 +#define PFUZE3000_VREFDDR 6 +#define PFUZE3000_VLDO1 7 +#define PFUZE3000_VLDO2 8 +#define PFUZE3000_VCCSD 9 +#define PFUZE3000_V33 10 +#define PFUZE3000_VLDO3 11 +#define PFUZE3000_VLDO4 12 + struct regulator_init_data; struct pfuze_regulator_platform_data { -- cgit v1.2.3 From ed09dcc8bd7fe0991af7737e675996cbd022f38f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:14 -0800 Subject: ses: close potential registration race The slot and address fields have a small window of instability when userspace can read them before initialization. Separate enclosure_component allocation from registration. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/misc/enclosure.c | 37 ++++++++++++++++++++++++++----------- drivers/scsi/ses.c | 21 ++++++++++++++------- include/linux/enclosure.h | 5 +++-- 3 files changed, 43 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 180a5442fd4b..e18278aa6bbb 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -273,27 +273,26 @@ enclosure_component_find_by_name(struct enclosure_device *edev, static const struct attribute_group *enclosure_component_groups[]; /** - * enclosure_component_register - add a particular component to an enclosure + * enclosure_component_alloc - prepare a new enclosure component * @edev: the enclosure to add the component * @num: the device number * @type: the type of component being added * @name: an optional name to appear in sysfs (leave NULL if none) * - * Registers the component. The name is optional for enclosures that - * give their components a unique name. If not, leave the field NULL - * and a name will be assigned. + * The name is optional for enclosures that give their components a unique + * name. If not, leave the field NULL and a name will be assigned. * * Returns a pointer to the enclosure component or an error. */ struct enclosure_component * -enclosure_component_register(struct enclosure_device *edev, - unsigned int number, - enum enclosure_component_type type, - const char *name) +enclosure_component_alloc(struct enclosure_device *edev, + unsigned int number, + enum enclosure_component_type type, + const char *name) { struct enclosure_component *ecomp; struct device *cdev; - int err, i; + int i; char newname[COMPONENT_NAME_SIZE]; if (number >= edev->components) @@ -327,14 +326,30 @@ enclosure_component_register(struct enclosure_device *edev, cdev->release = enclosure_component_release; cdev->groups = enclosure_component_groups; + return ecomp; +} +EXPORT_SYMBOL_GPL(enclosure_component_alloc); + +/** + * enclosure_component_register - publishes an initialized enclosure component + * @ecomp: component to add + * + * Returns 0 on successful registration, releases the component otherwise + */ +int enclosure_component_register(struct enclosure_component *ecomp) +{ + struct device *cdev; + int err; + + cdev = &ecomp->cdev; err = device_register(cdev); if (err) { ecomp->number = -1; put_device(cdev); - return ERR_PTR(err); + return err; } - return ecomp; + return 0; } EXPORT_SYMBOL_GPL(enclosure_component_register); diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index b7e79e7646ad..7dd9cf558380 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -423,16 +423,23 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE) { if (create) - ecomp = enclosure_component_register(edev, - components++, - type_ptr[0], - name); + ecomp = enclosure_component_alloc( + edev, + components++, + type_ptr[0], + name); else ecomp = &edev->component[components++]; - if (!IS_ERR(ecomp) && addl_desc_ptr) - ses_process_descriptor(ecomp, - addl_desc_ptr); + if (!IS_ERR(ecomp)) { + if (addl_desc_ptr) + ses_process_descriptor( + ecomp, + addl_desc_ptr); + if (create) + enclosure_component_register( + ecomp); + } } if (desc_ptr) desc_ptr += len; diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 9a33c5f7e126..a835d335b924 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -120,8 +120,9 @@ enclosure_register(struct device *, const char *, int, struct enclosure_component_callbacks *); void enclosure_unregister(struct enclosure_device *); struct enclosure_component * -enclosure_component_register(struct enclosure_device *, unsigned int, - enum enclosure_component_type, const char *); +enclosure_component_alloc(struct enclosure_device *, unsigned int, + enum enclosure_component_type, const char *); +int enclosure_component_register(struct enclosure_component *); int enclosure_add_device(struct enclosure_device *enclosure, int component, struct device *dev); int enclosure_remove_device(struct enclosure_device *, struct device *); -- cgit v1.2.3 From 967f7bab0eaaa74d7d01a56d45aa309f78fb87dd Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:16 -0800 Subject: ses: add enclosure logical id Export the NAA logical id for the enclosure. This is optionally available from the sas_transport_class, but it is really a property of the enclosure. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/misc/enclosure.c | 13 +++++++++++++ drivers/scsi/ses.c | 9 +++++++++ include/linux/enclosure.h | 1 + 3 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index e18278aa6bbb..958ee988a1e1 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -432,8 +432,21 @@ static ssize_t components_show(struct device *cdev, } static DEVICE_ATTR_RO(components); +static ssize_t id_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + struct enclosure_device *edev = to_enclosure_device(cdev); + + if (edev->cb->show_id) + return edev->cb->show_id(edev, buf); + return -EINVAL; +} +static DEVICE_ATTR_RO(id); + static struct attribute *enclosure_class_attrs[] = { &dev_attr_components.attr, + &dev_attr_id.attr, NULL, }; ATTRIBUTE_GROUPS(enclosure_class); diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 6662b0ca6cfd..1041556cdbf3 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -258,6 +258,14 @@ static int ses_set_active(struct enclosure_device *edev, return ses_set_page2_descriptor(edev, ecomp, desc); } +static int ses_show_id(struct enclosure_device *edev, char *buf) +{ + struct ses_device *ses_dev = edev->scratch; + unsigned long long id = get_unaligned_be64(ses_dev->page1+8+4); + + return sprintf(buf, "%#llx\n", id); +} + static struct enclosure_component_callbacks ses_enclosure_callbacks = { .get_fault = ses_get_fault, .set_fault = ses_set_fault, @@ -265,6 +273,7 @@ static struct enclosure_component_callbacks ses_enclosure_callbacks = { .get_locate = ses_get_locate, .set_locate = ses_set_locate, .set_active = ses_set_active, + .show_id = ses_show_id, }; struct ses_host_edev { diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index a835d335b924..807622b252a4 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -79,6 +79,7 @@ struct enclosure_component_callbacks { int (*set_locate)(struct enclosure_device *, struct enclosure_component *, enum enclosure_component_setting); + int (*show_id)(struct enclosure_device *, char *buf); }; -- cgit v1.2.3 From 921ce7f5786052749a22a75780f5ce1a456bcdc6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:17 -0800 Subject: ses: add reliable slot attribute The name provided by firmware is in a vendor specific format, publish the slot number to have a reliable mechanism for identifying slots across firmware implementations. If the enclosure does not provide a slot number fallback to the component number which is guaranteed unique, and usually mirrors the slot number. Cleaned up the unused ses_component.desc in the process. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/misc/enclosure.c | 20 +++++++++++++++++++- drivers/scsi/ses.c | 17 ++++++++++++----- include/linux/enclosure.h | 1 + 3 files changed, 32 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 958ee988a1e1..b62314d627ae 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -145,8 +145,10 @@ enclosure_register(struct device *dev, const char *name, int components, if (err) goto err; - for (i = 0; i < components; i++) + for (i = 0; i < components; i++) { edev->component[i].number = -1; + edev->component[i].slot = -1; + } mutex_lock(&container_list_lock); list_add_tail(&edev->node, &container_list); @@ -589,6 +591,20 @@ static ssize_t get_component_type(struct device *cdev, return snprintf(buf, 40, "%s\n", enclosure_type[ecomp->type]); } +static ssize_t get_component_slot(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct enclosure_component *ecomp = to_enclosure_component(cdev); + int slot; + + /* if the enclosure does not override then use 'number' as a stand-in */ + if (ecomp->slot >= 0) + slot = ecomp->slot; + else + slot = ecomp->number; + + return snprintf(buf, 40, "%d\n", slot); +} static DEVICE_ATTR(fault, S_IRUGO | S_IWUSR, get_component_fault, set_component_fault); @@ -599,6 +615,7 @@ static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, get_component_active, static DEVICE_ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate, set_component_locate); static DEVICE_ATTR(type, S_IRUGO, get_component_type, NULL); +static DEVICE_ATTR(slot, S_IRUGO, get_component_slot, NULL); static struct attribute *enclosure_component_attrs[] = { &dev_attr_fault.attr, @@ -606,6 +623,7 @@ static struct attribute *enclosure_component_attrs[] = { &dev_attr_active.attr, &dev_attr_locate.attr, &dev_attr_type.attr, + &dev_attr_slot.attr, NULL }; ATTRIBUTE_GROUPS(enclosure_component); diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 1041556cdbf3..433de8e6f538 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -47,7 +47,6 @@ struct ses_device { struct ses_component { u64 addr; - unsigned char *desc; }; static int ses_probe(struct device *dev) @@ -307,19 +306,26 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, int invalid = desc[0] & 0x80; enum scsi_protocol proto = desc[0] & 0x0f; u64 addr = 0; + int slot = -1; struct ses_component *scomp = ecomp->scratch; unsigned char *d; - scomp->desc = desc; - if (invalid) return; switch (proto) { + case SCSI_PROTOCOL_FCP: + if (eip) { + d = desc + 4; + slot = d[3]; + } + break; case SCSI_PROTOCOL_SAS: - if (eip) + if (eip) { + d = desc + 4; + slot = d[3]; d = desc + 8; - else + } else d = desc + 4; /* only take the phy0 addr */ addr = (u64)d[12] << 56 | @@ -335,6 +341,7 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, /* FIXME: Need to add more protocols than just SAS */ break; } + ecomp->slot = slot; scomp->addr = addr; } diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 807622b252a4..0f826c14a337 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -92,6 +92,7 @@ struct enclosure_component { int fault; int active; int locate; + int slot; enum enclosure_status status; }; -- cgit v1.2.3 From 08024885a2a3ed432716e9d50046a620a5b2df05 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 30 Dec 2014 14:46:18 -0800 Subject: ses: Add power_status to SES device slot Add power_status to SES device slot, so we can power on/off the HDDs behind the enclosure. Check firmware status in ses_set_* before sending control pages to firmware. Signed-off-by: Song Liu Acked-by: Dan Williams Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/misc/enclosure.c | 38 ++++++++++++++++++ drivers/scsi/ses.c | 98 ++++++++++++++++++++++++++++++++++++++++++----- include/linux/enclosure.h | 6 +++ 3 files changed, 133 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index b62314d627ae..38552a31304a 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -148,6 +148,7 @@ enclosure_register(struct device *dev, const char *name, int components, for (i = 0; i < components; i++) { edev->component[i].number = -1; edev->component[i].slot = -1; + edev->component[i].power_status = 1; } mutex_lock(&container_list_lock); @@ -583,6 +584,40 @@ static ssize_t set_component_locate(struct device *cdev, return count; } +static ssize_t get_component_power_status(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + struct enclosure_device *edev = to_enclosure_device(cdev->parent); + struct enclosure_component *ecomp = to_enclosure_component(cdev); + + if (edev->cb->get_power_status) + edev->cb->get_power_status(edev, ecomp); + return snprintf(buf, 40, "%s\n", ecomp->power_status ? "on" : "off"); +} + +static ssize_t set_component_power_status(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct enclosure_device *edev = to_enclosure_device(cdev->parent); + struct enclosure_component *ecomp = to_enclosure_component(cdev); + int val; + + if (strncmp(buf, "on", 2) == 0 && + (buf[2] == '\n' || buf[2] == '\0')) + val = 1; + else if (strncmp(buf, "off", 3) == 0 && + (buf[3] == '\n' || buf[3] == '\0')) + val = 0; + else + return -EINVAL; + + if (edev->cb->set_power_status) + edev->cb->set_power_status(edev, ecomp, val); + return count; +} + static ssize_t get_component_type(struct device *cdev, struct device_attribute *attr, char *buf) { @@ -614,6 +649,8 @@ static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, get_component_active, set_component_active); static DEVICE_ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate, set_component_locate); +static DEVICE_ATTR(power_status, S_IRUGO | S_IWUSR, get_component_power_status, + set_component_power_status); static DEVICE_ATTR(type, S_IRUGO, get_component_type, NULL); static DEVICE_ATTR(slot, S_IRUGO, get_component_slot, NULL); @@ -622,6 +659,7 @@ static struct attribute *enclosure_component_attrs[] = { &dev_attr_status.attr, &dev_attr_active.attr, &dev_attr_locate.attr, + &dev_attr_power_status.attr, &dev_attr_type.attr, &dev_attr_slot.attr, NULL diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 433de8e6f538..dcb0d76d7312 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -67,6 +67,20 @@ static int ses_probe(struct device *dev) #define SES_TIMEOUT (30 * HZ) #define SES_RETRIES 3 +static void init_device_slot_control(unsigned char *dest_desc, + struct enclosure_component *ecomp, + unsigned char *status) +{ + memcpy(dest_desc, status, 4); + dest_desc[0] = 0; + /* only clear byte 1 for ENCLOSURE_COMPONENT_DEVICE */ + if (ecomp->type == ENCLOSURE_COMPONENT_DEVICE) + dest_desc[1] = 0; + dest_desc[2] &= 0xde; + dest_desc[3] &= 0x3c; +} + + static int ses_recv_diag(struct scsi_device *sdev, int page_code, void *buf, int bufflen) { @@ -178,14 +192,22 @@ static int ses_set_fault(struct enclosure_device *edev, struct enclosure_component *ecomp, enum enclosure_component_setting val) { - unsigned char desc[4] = {0 }; + unsigned char desc[4]; + unsigned char *desc_ptr; + + desc_ptr = ses_get_page2_descriptor(edev, ecomp); + + if (!desc_ptr) + return -EIO; + + init_device_slot_control(desc, ecomp, desc_ptr); switch (val) { case ENCLOSURE_SETTING_DISABLED: - /* zero is disabled */ + desc[3] &= 0xdf; break; case ENCLOSURE_SETTING_ENABLED: - desc[3] = 0x20; + desc[3] |= 0x20; break; default: /* SES doesn't do the SGPIO blink settings */ @@ -219,14 +241,22 @@ static int ses_set_locate(struct enclosure_device *edev, struct enclosure_component *ecomp, enum enclosure_component_setting val) { - unsigned char desc[4] = {0 }; + unsigned char desc[4]; + unsigned char *desc_ptr; + + desc_ptr = ses_get_page2_descriptor(edev, ecomp); + + if (!desc_ptr) + return -EIO; + + init_device_slot_control(desc, ecomp, desc_ptr); switch (val) { case ENCLOSURE_SETTING_DISABLED: - /* zero is disabled */ + desc[2] &= 0xfd; break; case ENCLOSURE_SETTING_ENABLED: - desc[2] = 0x02; + desc[2] |= 0x02; break; default: /* SES doesn't do the SGPIO blink settings */ @@ -239,15 +269,23 @@ static int ses_set_active(struct enclosure_device *edev, struct enclosure_component *ecomp, enum enclosure_component_setting val) { - unsigned char desc[4] = {0 }; + unsigned char desc[4]; + unsigned char *desc_ptr; + + desc_ptr = ses_get_page2_descriptor(edev, ecomp); + + if (!desc_ptr) + return -EIO; + + init_device_slot_control(desc, ecomp, desc_ptr); switch (val) { case ENCLOSURE_SETTING_DISABLED: - /* zero is disabled */ + desc[2] &= 0x7f; ecomp->active = 0; break; case ENCLOSURE_SETTING_ENABLED: - desc[2] = 0x80; + desc[2] |= 0x80; ecomp->active = 1; break; default: @@ -265,12 +303,53 @@ static int ses_show_id(struct enclosure_device *edev, char *buf) return sprintf(buf, "%#llx\n", id); } +static void ses_get_power_status(struct enclosure_device *edev, + struct enclosure_component *ecomp) +{ + unsigned char *desc; + + desc = ses_get_page2_descriptor(edev, ecomp); + if (desc) + ecomp->power_status = (desc[3] & 0x10) ? 0 : 1; +} + +static int ses_set_power_status(struct enclosure_device *edev, + struct enclosure_component *ecomp, + int val) +{ + unsigned char desc[4]; + unsigned char *desc_ptr; + + desc_ptr = ses_get_page2_descriptor(edev, ecomp); + + if (!desc_ptr) + return -EIO; + + init_device_slot_control(desc, ecomp, desc_ptr); + + switch (val) { + /* power = 1 is device_off = 0 and vice versa */ + case 0: + desc[3] |= 0x10; + break; + case 1: + desc[3] &= 0xef; + break; + default: + return -EINVAL; + } + ecomp->power_status = val; + return ses_set_page2_descriptor(edev, ecomp, desc); +} + static struct enclosure_component_callbacks ses_enclosure_callbacks = { .get_fault = ses_get_fault, .set_fault = ses_set_fault, .get_status = ses_get_status, .get_locate = ses_get_locate, .set_locate = ses_set_locate, + .get_power_status = ses_get_power_status, + .set_power_status = ses_set_power_status, .set_active = ses_set_active, .show_id = ses_show_id, }; @@ -449,6 +528,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, ecomp = &edev->component[components++]; if (!IS_ERR(ecomp)) { + ses_get_power_status(edev, ecomp); if (addl_desc_ptr) ses_process_descriptor( ecomp, diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 0f826c14a337..7be22da321f3 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -79,6 +79,11 @@ struct enclosure_component_callbacks { int (*set_locate)(struct enclosure_device *, struct enclosure_component *, enum enclosure_component_setting); + void (*get_power_status)(struct enclosure_device *, + struct enclosure_component *); + int (*set_power_status)(struct enclosure_device *, + struct enclosure_component *, + int); int (*show_id)(struct enclosure_device *, char *buf); }; @@ -94,6 +99,7 @@ struct enclosure_component { int locate; int slot; enum enclosure_status status; + int power_status; }; struct enclosure_device { -- cgit v1.2.3 From 9733e4f0a973a354034f5dd603b4142a3095c85f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 12:49:13 -0800 Subject: rcu: Make _batches_completed() functions return unsigned long Long ago, the various ->completed fields were of type long, but now are unsigned long due to signed-integer-overflow concerns. However, the various _batches_completed() functions remained of type long, even though their only purpose in life is to return the corresponding ->completed field. This patch cleans this up by changing these functions' return types to unsigned long. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 4 ++-- include/linux/rcutree.h | 6 +++--- kernel/rcu/tree.c | 4 ++-- kernel/rcu/tree.h | 2 +- kernel/rcu/tree_plugin.h | 6 +++--- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0e5366200154..91f7e4c37800 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -94,7 +94,7 @@ static inline void rcu_virt_note_context_switch(int cpu) /* * Return the number of grace periods. */ -static inline long rcu_batches_completed(void) +static inline unsigned long rcu_batches_completed(void) { return 0; } @@ -102,7 +102,7 @@ static inline long rcu_batches_completed(void) /* * Return the number of bottom-half grace periods. */ -static inline long rcu_batches_completed_bh(void) +static inline unsigned long rcu_batches_completed_bh(void) { return 0; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 52953790dcca..9885bfb6b123 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -81,9 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; -long rcu_batches_completed(void); -long rcu_batches_completed_bh(void); -long rcu_batches_completed_sched(void); +unsigned long rcu_batches_completed(void); +unsigned long rcu_batches_completed_bh(void); +unsigned long rcu_batches_completed_sched(void); void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4c106fcc0d54..e26d78712e16 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -317,7 +317,7 @@ static int rcu_pending(void); /* * Return the number of RCU-sched batches processed thus far for debug & stats. */ -long rcu_batches_completed_sched(void) +unsigned long rcu_batches_completed_sched(void) { return rcu_sched_state.completed; } @@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); /* * Return the number of RCU BH batches processed thus far for debug & stats. */ -long rcu_batches_completed_bh(void) +unsigned long rcu_batches_completed_bh(void) { return rcu_bh_state.completed; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 8e7b1843896e..1a07d7379ac6 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -546,7 +546,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); -long rcu_batches_completed(void); +unsigned long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(void); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3ec85cb5d544..f69300d4a51f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -117,7 +117,7 @@ static void __init rcu_bootup_announce(void) * Return the number of RCU-preempt batches processed thus far * for debug and statistics. */ -static long rcu_batches_completed_preempt(void) +static unsigned long rcu_batches_completed_preempt(void) { return rcu_preempt_state.completed; } @@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt); /* * Return the number of RCU batches processed thus far for debug & stats. */ -long rcu_batches_completed(void) +unsigned long rcu_batches_completed(void) { return rcu_batches_completed_preempt(); } @@ -935,7 +935,7 @@ static void __init rcu_bootup_announce(void) /* * Return the number of RCU batches processed thus far for debug & stats. */ -long rcu_batches_completed(void) +unsigned long rcu_batches_completed(void) { return rcu_batches_completed_sched(); } -- cgit v1.2.3 From c1fe9cde4ae904fffb5b4d975d0a37e99136ff50 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 15:45:27 -0800 Subject: rcu: Provide rcu_batches_completed_sched() for TINY_RCU A bug in rcutorture has caused it to ignore completed batches. In preparation for fixing that bug, this commit provides TINY_RCU with the required rcu_batches_completed_sched(). Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 91f7e4c37800..1ce2d6b8f0c3 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -107,6 +107,14 @@ static inline unsigned long rcu_batches_completed_bh(void) return 0; } +/* + * Return the number of sched grace periods. + */ +static inline unsigned long rcu_batches_completed_sched(void) +{ + return 0; +} + static inline void rcu_force_quiescent_state(void) { } -- cgit v1.2.3 From 917963d0b30f9c4153c372c165178501d97b6b55 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 17:10:16 -0800 Subject: rcutorture: Check from beginning to end of grace period Currently, rcutorture's Reader Batch checks measure from the end of the previous grace period to the end of the current one. This commit tightens up these checks by measuring from the start and end of the same grace period. This involves adding rcu_batches_started() and friends corresponding to the existing rcu_batches_completed() and friends. We leave SRCU alone for the moment, as it does not yet have a way of tracking both ends of its grace periods. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 30 +++++++++++++++++++++++++++--- include/linux/rcutree.h | 3 +++ kernel/rcu/rcutorture.c | 37 +++++++++++++++++++++++++++---------- kernel/rcu/tree.c | 40 ++++++++++++++++++++++++++++++++++++++-- kernel/rcu/tree_plugin.h | 28 ---------------------------- 5 files changed, 95 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 1ce2d6b8f0c3..984192160e9b 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -92,7 +92,31 @@ static inline void rcu_virt_note_context_switch(int cpu) } /* - * Return the number of grace periods. + * Return the number of grace periods started. + */ +static inline unsigned long rcu_batches_started(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods started. + */ +static inline unsigned long rcu_batches_started_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods started. + */ +static inline unsigned long rcu_batches_started_sched(void) +{ + return 0; +} + +/* + * Return the number of grace periods completed. */ static inline unsigned long rcu_batches_completed(void) { @@ -100,7 +124,7 @@ static inline unsigned long rcu_batches_completed(void) } /* - * Return the number of bottom-half grace periods. + * Return the number of bottom-half grace periods completed. */ static inline unsigned long rcu_batches_completed_bh(void) { @@ -108,7 +132,7 @@ static inline unsigned long rcu_batches_completed_bh(void) } /* - * Return the number of sched grace periods. + * Return the number of sched grace periods completed. */ static inline unsigned long rcu_batches_completed_sched(void) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9885bfb6b123..c0dd124e69ec 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -81,6 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; +unsigned long rcu_batches_started(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_started_sched(void); unsigned long rcu_batches_completed(void); unsigned long rcu_batches_completed_bh(void); unsigned long rcu_batches_completed_sched(void); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index aadbc072ccf4..24142c200901 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -244,6 +244,7 @@ struct rcu_torture_ops { int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); + unsigned long (*started)(void); unsigned long (*completed)(void); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); @@ -372,6 +373,7 @@ static struct rcu_torture_ops rcu_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, + .started = rcu_batches_started, .completed = rcu_batches_completed, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, @@ -413,6 +415,7 @@ static struct rcu_torture_ops rcu_bh_ops = { .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, + .started = rcu_batches_started_bh, .completed = rcu_batches_completed_bh, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, @@ -456,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_torture_read_unlock, + .started = rcu_no_completed, .completed = rcu_no_completed, .deferred_free = rcu_busted_torture_deferred_free, .sync = synchronize_rcu_busted, @@ -554,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, + .started = NULL, .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, @@ -590,6 +595,7 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, + .started = rcu_batches_started_sched, .completed = rcu_batches_completed_sched, .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, @@ -628,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = { .readlock = tasks_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = tasks_torture_read_unlock, + .started = rcu_no_completed, .completed = rcu_no_completed, .deferred_free = rcu_tasks_torture_deferred_free, .sync = synchronize_rcu_tasks, @@ -1005,8 +1012,8 @@ static void rcutorture_trace_dump(void) static void rcu_torture_timer(unsigned long unused) { int idx; + unsigned long started; unsigned long completed; - unsigned long completed_end; static DEFINE_TORTURE_RANDOM(rand); static DEFINE_SPINLOCK(rand_lock); struct rcu_torture *p; @@ -1014,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused) unsigned long long ts; idx = cur_ops->readlock(); - completed = cur_ops->completed(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1037,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed_end = cur_ops->completed(); + completed = cur_ops->completed(); if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, - completed, completed_end); + started, completed); rcutorture_trace_dump(); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed_end - completed; + completed = completed - started; + if (cur_ops->started) + completed++; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; @@ -1063,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused) static int rcu_torture_reader(void *arg) { + unsigned long started; unsigned long completed; - unsigned long completed_end; int idx; DEFINE_TORTURE_RANDOM(rand); struct rcu_torture *p; @@ -1083,7 +1095,10 @@ rcu_torture_reader(void *arg) mod_timer(&t, jiffies + 1); } idx = cur_ops->readlock(); - completed = cur_ops->completed(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1104,14 +1119,16 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed_end = cur_ops->completed(); + completed = cur_ops->completed(); if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, - ts, completed, completed_end); + ts, started, completed); rcutorture_trace_dump(); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed_end - completed; + completed = completed - started; + if (cur_ops->started) + completed++; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e26d78712e16..c0faad51ae87 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -315,7 +315,43 @@ static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); /* - * Return the number of RCU-sched batches processed thus far for debug & stats. + * Return the number of RCU batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started(void) +{ + return rcu_state_p->gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started); + +/* + * Return the number of RCU-sched batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started_sched(void) +{ + return rcu_sched_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_sched); + +/* + * Return the number of RCU BH batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started_bh(void) +{ + return rcu_bh_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_bh); + +/* + * Return the number of RCU batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed(void) +{ + return rcu_state_p->completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed); + +/* + * Return the number of RCU-sched batches completed thus far for debug & stats. */ unsigned long rcu_batches_completed_sched(void) { @@ -324,7 +360,7 @@ unsigned long rcu_batches_completed_sched(void) EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); /* - * Return the number of RCU BH batches processed thus far for debug & stats. + * Return the number of RCU BH batches completed thus far for debug & stats. */ unsigned long rcu_batches_completed_bh(void) { diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index f69300d4a51f..07e61a04de1d 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -113,25 +113,6 @@ static void __init rcu_bootup_announce(void) rcu_bootup_announce_oddness(); } -/* - * Return the number of RCU-preempt batches processed thus far - * for debug and statistics. - */ -static unsigned long rcu_batches_completed_preempt(void) -{ - return rcu_preempt_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt); - -/* - * Return the number of RCU batches processed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_batches_completed_preempt(); -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is @@ -932,15 +913,6 @@ static void __init rcu_bootup_announce(void) rcu_bootup_announce_oddness(); } -/* - * Return the number of RCU batches processed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_batches_completed_sched(); -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - /* * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. -- cgit v1.2.3 From 31c89c959667194350f496947b576c149503ce98 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Fri, 9 Jan 2015 07:43:45 -0800 Subject: pinctrl: pinconf-generic: Infer map type from DT property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the new 'groups' property, the DT parser can infer the map type from the fact whether 'pins' or 'groups' is used to specify the pin group to work on. To maintain backwards compatibitliy with current usage of the DT binding, this is only done when PIN_MAP_TYPE_INVALID is passed to the parsing function as type. Also, a new helper 'pinconf_generic_dt_node_to_map_all()' is introduced, which can be used by drivers as generic callback for dt_node_to_map() to leverage the new feature. Changes since v2: - rename dt_pin_specifier to subnode_target_type - add additional comment in header file explaining passing an invalid map type - mention map_all() helper in commit message Changes since RFC v2: - none Signed-off-by: Soren Brinkmann Tested-by: Andreas Färber Signed-off-by: Linus Walleij --- drivers/pinctrl/pinconf-generic.c | 17 ++++++++++++++--- include/linux/pinctrl/pinconf-generic.h | 11 +++++++++++ 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index f78b416d7984..21b3d90ebb2d 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -264,6 +264,7 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, unsigned reserve; struct property *prop; const char *group; + const char *subnode_target_type = "pins"; ret = of_property_read_string(np, "function", &function); if (ret < 0) { @@ -284,10 +285,20 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, reserve++; if (num_configs) reserve++; + ret = of_property_count_strings(np, "pins"); if (ret < 0) { - dev_err(dev, "could not parse property pins\n"); - goto exit; + ret = of_property_count_strings(np, "groups"); + if (ret < 0) { + dev_err(dev, "could not parse property pins/groups\n"); + goto exit; + } + if (type == PIN_MAP_TYPE_INVALID) + type = PIN_MAP_TYPE_CONFIGS_GROUP; + subnode_target_type = "groups"; + } else { + if (type == PIN_MAP_TYPE_INVALID) + type = PIN_MAP_TYPE_CONFIGS_PIN; } reserve *= ret; @@ -296,7 +307,7 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, if (ret < 0) goto exit; - of_property_for_each_string(np, "pins", prop, group) { + of_property_for_each_string(np, subnode_target_type, prop, group) { if (function) { ret = pinctrl_utils_add_map_mux(pctldev, map, reserved_maps, num_maps, group, diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index d578a60eff23..83c89f5ab705 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -174,6 +174,17 @@ static inline int pinconf_generic_dt_node_to_map_pin( PIN_MAP_TYPE_CONFIGS_PIN); } +static inline int pinconf_generic_dt_node_to_map_all( + struct pinctrl_dev *pctldev, struct device_node *np_config, + struct pinctrl_map **map, unsigned *num_maps) +{ + /* + * passing the type as PIN_MAP_TYPE_INVALID causes the underlying parser + * to infer the map type from the DT properties used. + */ + return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, + PIN_MAP_TYPE_INVALID); +} #endif #endif /* CONFIG_GENERIC_PINCONF */ -- cgit v1.2.3 From dd4d01f7bad886c22687224bc7070b87de8deb51 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Fri, 9 Jan 2015 07:43:46 -0800 Subject: pinctrl: pinconf-generic: Allow driver to specify DT params MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Additionally to the generic DT parameters, allow drivers to provide driver-specific DT parameters to be used with the generic parser infrastructure. To achieve this 'struct pinctrl_desc' is extended to pass custom pinconf option to the core. In order to pass this kind of information, the related data structures - 'struct pinconf_generic_dt_params', 'pin_config_item' - are moved from pinconf internals to the pinconf-generic header. Additionally pinconfg-generic is refactored to not only iterate over the generic pinconf parameters but also take the parameters into account that are provided through the driver's 'struct pinctrl_desc'. In particular 'pinconf_generic_parse_dt_config()' and 'pinconf_generic_dump' helpers are split into two parts each. In order to have a more generic helper that can be used to process the generic parameters as well as the driver-specific ones. v2: - fix typo - add missing documentation for @conf_items member in struct - rebase to pinctrl/devel: conflict in abx500 - rename _pinconf_generic_dump() to pinconf_generic_dump_one() - removed '_' from _parse_dt_cfg() - removed BUG_ONs, error condition is handled in if statements - removed pinconf_generic_dump_group() & pinconf_generic_dump_pin helpers - fixed up corresponding call sites - renamed pinconf_generic_dump() to pinconf_generic_dump_pins() - added kernel-doc to pinconf_generic_dump_pins() - add kernel-doc - more verbose commit message Signed-off-by: Soren Brinkmann Tested-by: Andreas Färber Signed-off-by: Linus Walleij --- drivers/pinctrl/nomadik/pinctrl-abx500.c | 2 +- drivers/pinctrl/pinconf-generic.c | 182 +++++++++++++++++-------------- drivers/pinctrl/pinconf.c | 4 +- drivers/pinctrl/pinconf.h | 22 ++-- drivers/pinctrl/pinctrl-rockchip.c | 2 +- drivers/pinctrl/pinctrl-tz1090-pdc.c | 2 +- drivers/pinctrl/pinctrl-tz1090.c | 2 +- drivers/pinctrl/sh-pfc/pinctrl.c | 2 +- include/linux/pinctrl/pinconf-generic.h | 18 +++ include/linux/pinctrl/pinctrl.h | 9 ++ 10 files changed, 141 insertions(+), 104 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index 3d6d97228523..1806b24faa14 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -914,7 +914,7 @@ static int abx500_dt_subnode_to_map(struct pinctrl_dev *pctldev, } } - ret = pinconf_generic_parse_dt_config(np, &configs, &nconfigs); + ret = pinconf_generic_parse_dt_config(np, pctldev, &configs, &nconfigs); if (nconfigs) { const char *gpio_name; const char *pin; diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 21b3d90ebb2d..e0886665b70a 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -27,17 +27,6 @@ #include "pinctrl-utils.h" #ifdef CONFIG_DEBUG_FS - -struct pin_config_item { - const enum pin_config_param param; - const char * const display; - const char * const format; - bool has_arg; -}; - -#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \ - .has_arg = d } - static const struct pin_config_item conf_items[] = { PCONFDUMP(PIN_CONFIG_BIAS_DISABLE, "input bias disabled", NULL, false), PCONFDUMP(PIN_CONFIG_BIAS_HIGH_IMPEDANCE, "input bias high impedance", NULL, false), @@ -60,22 +49,25 @@ static const struct pin_config_item conf_items[] = { PCONFDUMP(PIN_CONFIG_OUTPUT, "pin output", "level", true), }; -void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev, - struct seq_file *s, unsigned pin) +static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev, + struct seq_file *s, const char *gname, + unsigned pin, + const struct pin_config_item *items, + int nitems) { - const struct pinconf_ops *ops = pctldev->desc->confops; int i; - if (!ops->is_generic) - return; - - for (i = 0; i < ARRAY_SIZE(conf_items); i++) { + for (i = 0; i < nitems; i++) { unsigned long config; int ret; /* We want to check out this parameter */ - config = pinconf_to_config_packed(conf_items[i].param, 0); - ret = pin_config_get_for_pin(pctldev, pin, &config); + config = pinconf_to_config_packed(items[i].param, 0); + if (gname) + ret = pin_config_group_get(dev_name(pctldev->dev), + gname, &config); + else + ret = pin_config_get_for_pin(pctldev, pin, &config); /* These are legal errors */ if (ret == -EINVAL || ret == -ENOTSUPP) continue; @@ -85,56 +77,46 @@ void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev, } /* Space between multiple configs */ seq_puts(s, " "); - seq_puts(s, conf_items[i].display); + seq_puts(s, items[i].display); /* Print unit if available */ - if (conf_items[i].has_arg) { + if (items[i].has_arg) { seq_printf(s, " (%u", pinconf_to_config_argument(config)); - if (conf_items[i].format) - seq_printf(s, " %s)", conf_items[i].format); + if (items[i].format) + seq_printf(s, " %s)", items[i].format); else seq_puts(s, ")"); } } } -void pinconf_generic_dump_group(struct pinctrl_dev *pctldev, - struct seq_file *s, const char *gname) +/** + * pinconf_generic_dump_pins - Print information about pin or group of pins + * @pctldev: Pincontrol device + * @s: File to print to + * @gname: Group name specifying pins + * @pin: Pin number specyfying pin + * + * Print the pinconf configuration for the requested pin(s) to @s. Pins can be + * specified either by pin using @pin or by group using @gname. Only one needs + * to be specified the other can be NULL/0. + */ +void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s, + const char *gname, unsigned pin) { const struct pinconf_ops *ops = pctldev->desc->confops; - int i; if (!ops->is_generic) return; - for (i = 0; i < ARRAY_SIZE(conf_items); i++) { - unsigned long config; - int ret; - - /* We want to check out this parameter */ - config = pinconf_to_config_packed(conf_items[i].param, 0); - ret = pin_config_group_get(dev_name(pctldev->dev), gname, - &config); - /* These are legal errors */ - if (ret == -EINVAL || ret == -ENOTSUPP) - continue; - if (ret) { - seq_printf(s, "ERROR READING CONFIG SETTING %d ", i); - continue; - } - /* Space between multiple configs */ - seq_puts(s, " "); - seq_puts(s, conf_items[i].display); - /* Print unit if available */ - if (conf_items[i].has_arg) { - seq_printf(s, " (%u", - pinconf_to_config_argument(config)); - if (conf_items[i].format) - seq_printf(s, " %s)", conf_items[i].format); - else - seq_puts(s, ")"); - } - } + /* generic parameters */ + pinconf_generic_dump_one(pctldev, s, gname, pin, conf_items, + ARRAY_SIZE(conf_items)); + /* driver-specific parameters */ + if (pctldev->desc->num_dt_params && pctldev->desc->conf_items) + pinconf_generic_dump_one(pctldev, s, gname, pin, + pctldev->desc->conf_items, + pctldev->desc->num_dt_params); } void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, @@ -148,17 +130,21 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, seq_printf(s, "%s: 0x%x", conf_items[i].display, pinconf_to_config_argument(config)); } + + if (!pctldev->desc->num_dt_params || !pctldev->desc->conf_items) + return; + + for (i = 0; i < pctldev->desc->num_dt_params; i++) { + if (pinconf_to_config_param(config) != pctldev->desc->conf_items[i].param) + continue; + seq_printf(s, "%s: 0x%x", pctldev->desc->conf_items[i].display, + pinconf_to_config_argument(config)); + } } EXPORT_SYMBOL_GPL(pinconf_generic_dump_config); #endif #ifdef CONFIG_OF -struct pinconf_generic_dt_params { - const char * const property; - enum pin_config_param param; - u32 default_value; -}; - static const struct pinconf_generic_dt_params dt_params[] = { { "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 }, { "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 }, @@ -183,6 +169,47 @@ static const struct pinconf_generic_dt_params dt_params[] = { { "slew-rate", PIN_CONFIG_SLEW_RATE, 0}, }; +/** + * parse_dt_cfg - Parse DT pinconf parameters + * @np: DT node + * @params: Array of describing DT parameters + * @count: Number of entries in @params + * @cfg: Array of parsed config options + * @ncfg: Number of entries in @cfg + * + * Parse the config options described in @params from @np and puts the result + * in @cfg. @cfg does not need to be empty, entries are added beggining at + * @ncfg. @ncfg is updated to reflect the number of entries after parsing. @cfg + * needs to have enough memory allocated to hold all possible entries. + */ +static void parse_dt_cfg(struct device_node *np, + const struct pinconf_generic_dt_params *params, + unsigned int count, unsigned long *cfg, + unsigned int *ncfg) +{ + int i; + + for (i = 0; i < count; i++) { + u32 val; + int ret; + const struct pinconf_generic_dt_params *par = ¶ms[i]; + + ret = of_property_read_u32(np, par->property, &val); + + /* property not found */ + if (ret == -EINVAL) + continue; + + /* use default value, when no value is specified */ + if (ret) + val = par->default_value; + + pr_debug("found %s with value %u\n", par->property, val); + cfg[*ncfg] = pinconf_to_config_packed(par->param, val); + (*ncfg)++; + } +} + /** * pinconf_generic_parse_dt_config() * parse the config properties into generic pinconfig values. @@ -191,39 +218,29 @@ static const struct pinconf_generic_dt_params dt_params[] = { * @nconfigs: umber of configurations */ int pinconf_generic_parse_dt_config(struct device_node *np, + struct pinctrl_dev *pctldev, unsigned long **configs, unsigned int *nconfigs) { unsigned long *cfg; - unsigned int ncfg = 0; + unsigned int max_cfg, ncfg = 0; int ret; - int i; - u32 val; if (!np) return -EINVAL; /* allocate a temporary array big enough to hold one of each option */ - cfg = kzalloc(sizeof(*cfg) * ARRAY_SIZE(dt_params), GFP_KERNEL); + max_cfg = ARRAY_SIZE(dt_params); + if (pctldev) + max_cfg += pctldev->desc->num_dt_params; + cfg = kcalloc(max_cfg, sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(dt_params); i++) { - const struct pinconf_generic_dt_params *par = &dt_params[i]; - ret = of_property_read_u32(np, par->property, &val); - - /* property not found */ - if (ret == -EINVAL) - continue; - - /* use default value, when no value is specified */ - if (ret) - val = par->default_value; - - pr_debug("found %s with value %u\n", par->property, val); - cfg[ncfg] = pinconf_to_config_packed(par->param, val); - ncfg++; - } + parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg); + if (pctldev && pctldev->desc->num_dt_params && pctldev->desc->params) + parse_dt_cfg(np, pctldev->desc->params, + pctldev->desc->num_dt_params, cfg, &ncfg); ret = 0; @@ -274,7 +291,8 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, function = NULL; } - ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs); + ret = pinconf_generic_parse_dt_config(np, pctldev, &configs, + &num_configs); if (ret < 0) { dev_err(dev, "could not parse node property\n"); return ret; diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c index 8bfa0643e5dc..1fc09dc20199 100644 --- a/drivers/pinctrl/pinconf.c +++ b/drivers/pinctrl/pinconf.c @@ -288,7 +288,7 @@ static void pinconf_dump_pin(struct pinctrl_dev *pctldev, const struct pinconf_ops *ops = pctldev->desc->confops; /* no-op when not using generic pin config */ - pinconf_generic_dump_pin(pctldev, s, pin); + pinconf_generic_dump_pins(pctldev, s, NULL, pin); if (ops && ops->pin_config_dbg_show) ops->pin_config_dbg_show(pctldev, s, pin); } @@ -333,7 +333,7 @@ static void pinconf_dump_group(struct pinctrl_dev *pctldev, const struct pinconf_ops *ops = pctldev->desc->confops; /* no-op when not using generic pin config */ - pinconf_generic_dump_group(pctldev, s, gname); + pinconf_generic_dump_pins(pctldev, s, gname, 0); if (ops && ops->pin_config_group_dbg_show) ops->pin_config_group_dbg_show(pctldev, s, selector); } diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h index a4a5417e1413..55c75780b3b2 100644 --- a/drivers/pinctrl/pinconf.h +++ b/drivers/pinctrl/pinconf.h @@ -92,26 +92,17 @@ static inline void pinconf_init_device_debugfs(struct dentry *devroot, #if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_DEBUG_FS) -void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev, - struct seq_file *s, unsigned pin); - -void pinconf_generic_dump_group(struct pinctrl_dev *pctldev, - struct seq_file *s, const char *gname); +void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, + struct seq_file *s, const char *gname, + unsigned pin); void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, struct seq_file *s, unsigned long config); #else -static inline void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev, - struct seq_file *s, - unsigned pin) -{ - return; -} - -static inline void pinconf_generic_dump_group(struct pinctrl_dev *pctldev, - struct seq_file *s, - const char *gname) +static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, + struct seq_file *s, + const char *gname, unsigned pin) { return; } @@ -126,6 +117,7 @@ static inline void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, #if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF) int pinconf_generic_parse_dt_config(struct device_node *np, + struct pinctrl_dev *pctldev, unsigned long **configs, unsigned int *nconfigs); #endif diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index ba74f0aa60c7..7625f333ab07 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -1140,7 +1140,7 @@ static int rockchip_pinctrl_parse_groups(struct device_node *np, return -EINVAL; np_config = of_find_node_by_phandle(be32_to_cpup(phandle)); - ret = pinconf_generic_parse_dt_config(np_config, + ret = pinconf_generic_parse_dt_config(np_config, NULL, &grp->data[j].configs, &grp->data[j].nconfigs); if (ret) return ret; diff --git a/drivers/pinctrl/pinctrl-tz1090-pdc.c b/drivers/pinctrl/pinctrl-tz1090-pdc.c index 146e48a9b839..fab6aafa6a9f 100644 --- a/drivers/pinctrl/pinctrl-tz1090-pdc.c +++ b/drivers/pinctrl/pinctrl-tz1090-pdc.c @@ -415,7 +415,7 @@ static int tz1090_pdc_pinctrl_dt_subnode_to_map(struct device *dev, function = NULL; } - ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs); + ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs); if (ret) return ret; diff --git a/drivers/pinctrl/pinctrl-tz1090.c b/drivers/pinctrl/pinctrl-tz1090.c index df8cb1e5b7b4..8bd73075f9dd 100644 --- a/drivers/pinctrl/pinctrl-tz1090.c +++ b/drivers/pinctrl/pinctrl-tz1090.c @@ -1131,7 +1131,7 @@ static int tz1090_pinctrl_dt_subnode_to_map(struct device *dev, function = NULL; } - ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs); + ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs); if (ret) return ret; diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c index 910deaefa0ac..072e7c62cab7 100644 --- a/drivers/pinctrl/sh-pfc/pinctrl.c +++ b/drivers/pinctrl/sh-pfc/pinctrl.c @@ -122,7 +122,7 @@ static int sh_pfc_dt_subnode_to_map(struct device *dev, struct device_node *np, return ret; } - ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs); + ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs); if (ret < 0) return ret; diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 83c89f5ab705..342409f7f3ec 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -115,6 +115,18 @@ enum pin_config_param { PIN_CONFIG_END = 0x7FFF, }; +#ifdef CONFIG_DEBUG_FS +#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \ + .has_arg = d } + +struct pin_config_item { + const enum pin_config_param param; + const char * const display; + const char * const format; + bool has_arg; +}; +#endif /* CONFIG_DEBUG_FS */ + /* * Helpful configuration macro to be used in tables etc. */ @@ -150,6 +162,12 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param struct pinctrl_dev; struct pinctrl_map; +struct pinconf_generic_dt_params { + const char * const property; + enum pin_config_param param; + u32 default_value; +}; + int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, struct pinctrl_map **map, unsigned *reserved_maps, unsigned *num_maps, diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index cc8e1aff0e28..c58b3e11ba8e 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -24,6 +24,7 @@ struct pinctrl_dev; struct pinctrl_map; struct pinmux_ops; struct pinconf_ops; +struct pin_config_item; struct gpio_chip; struct device_node; @@ -117,6 +118,9 @@ struct pinctrl_ops { * @confops: pin config operations vtable, if you support pin configuration in * your driver * @owner: module providing the pin controller, used for refcounting + * @num_dt_params: Number of driver-specific DT parameters + * @params: List of DT parameters + * @conf_items: Information how to print @params in debugfs */ struct pinctrl_desc { const char *name; @@ -126,6 +130,11 @@ struct pinctrl_desc { const struct pinmux_ops *pmxops; const struct pinconf_ops *confops; struct module *owner; +#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF) + unsigned int num_dt_params; + const struct pinconf_generic_dt_params *params; + const struct pin_config_item *conf_items; +#endif }; /* External interface to pin controller */ -- cgit v1.2.3 From 7bb68410ef22067b08fd52887875b8f337f89dcc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 18 Oct 2014 15:04:15 +0200 Subject: efi: split off remapping code from efi_config_init() Split of the remapping code from efi_config_init() so that the caller can perform its own remapping. This is necessary to correctly handle virtually remapped UEFI memory regions under kexec, as efi.systab will have been updated to a virtual address. Acked-by: Matt Fleming Tested-by: Leif Lindholm Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 56 ++++++++++++++++++++++++++-------------------- include/linux/efi.h | 2 ++ 2 files changed, 34 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 9035c1b74d58..b7ba9d8ec4b0 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -293,29 +293,15 @@ static __init int match_config_table(efi_guid_t *guid, return 0; } -int __init efi_config_init(efi_config_table_type_t *arch_tables) +int __init efi_config_parse_tables(void *config_tables, int count, int sz, + efi_config_table_type_t *arch_tables) { - void *config_tables, *tablep; - int i, sz; - - if (efi_enabled(EFI_64BIT)) - sz = sizeof(efi_config_table_64_t); - else - sz = sizeof(efi_config_table_32_t); - - /* - * Let's see what config tables the firmware passed to us. - */ - config_tables = early_memremap(efi.systab->tables, - efi.systab->nr_tables * sz); - if (config_tables == NULL) { - pr_err("Could not map Configuration table!\n"); - return -ENOMEM; - } + void *tablep; + int i; tablep = config_tables; pr_info(""); - for (i = 0; i < efi.systab->nr_tables; i++) { + for (i = 0; i < count; i++) { efi_guid_t guid; unsigned long table; @@ -328,8 +314,6 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) if (table64 >> 32) { pr_cont("\n"); pr_err("Table located above 4GB, disabling EFI.\n"); - early_memunmap(config_tables, - efi.systab->nr_tables * sz); return -EINVAL; } #endif @@ -344,13 +328,37 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) tablep += sz; } pr_cont("\n"); - early_memunmap(config_tables, efi.systab->nr_tables * sz); - set_bit(EFI_CONFIG_TABLES, &efi.flags); - return 0; } +int __init efi_config_init(efi_config_table_type_t *arch_tables) +{ + void *config_tables; + int sz, ret; + + if (efi_enabled(EFI_64BIT)) + sz = sizeof(efi_config_table_64_t); + else + sz = sizeof(efi_config_table_32_t); + + /* + * Let's see what config tables the firmware passed to us. + */ + config_tables = early_memremap(efi.systab->tables, + efi.systab->nr_tables * sz); + if (config_tables == NULL) { + pr_err("Could not map Configuration table!\n"); + return -ENOMEM; + } + + ret = efi_config_parse_tables(config_tables, efi.systab->nr_tables, sz, + arch_tables); + + early_memunmap(config_tables, efi.systab->nr_tables * sz); + return ret; +} + #ifdef CONFIG_EFI_VARS_MODULE static int __init efi_load_efivars(void) { diff --git a/include/linux/efi.h b/include/linux/efi.h index 0238d612750e..5ffe5115951f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -875,6 +875,8 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern int efi_config_init(efi_config_table_type_t *arch_tables); +extern int efi_config_parse_tables(void *config_tables, int count, int sz, + efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); extern u32 efi_mem_type (unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); -- cgit v1.2.3 From f684e4ac9f4bae4e6ecff92eef9645a44764fc04 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 12 Jan 2015 00:45:55 +0100 Subject: pinctrl: pinconf-generic: loose DT dependence New pin controllers such as ACPI-based may also have custom properties to parse, and should be able to use generic pin config. Let's make the code compile on !OF systems and rename members a bit to underscore it is custom parameters and not necessarily DT parameters. This fixes a build regression for x86_64 on the zeroday kernel builds. Reported-by: kbuild test robot Reviewed-and-tested-by: Soren Brinkmann Signed-off-by: Linus Walleij --- drivers/pinctrl/pinconf-generic.c | 39 ++++++++++++++++++-------------- drivers/pinctrl/pinctrl-zynq.c | 8 +++---- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 8 +++---- include/linux/pinctrl/pinconf-generic.h | 2 +- include/linux/pinctrl/pinctrl.h | 17 ++++++++------ 5 files changed, 41 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index e0886665b70a..4db92f64b4de 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -113,10 +113,11 @@ void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s, pinconf_generic_dump_one(pctldev, s, gname, pin, conf_items, ARRAY_SIZE(conf_items)); /* driver-specific parameters */ - if (pctldev->desc->num_dt_params && pctldev->desc->conf_items) + if (pctldev->desc->num_custom_params && + pctldev->desc->custom_conf_items) pinconf_generic_dump_one(pctldev, s, gname, pin, - pctldev->desc->conf_items, - pctldev->desc->num_dt_params); + pctldev->desc->custom_conf_items, + pctldev->desc->num_custom_params); } void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, @@ -131,21 +132,24 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev, pinconf_to_config_argument(config)); } - if (!pctldev->desc->num_dt_params || !pctldev->desc->conf_items) + if (!pctldev->desc->num_custom_params || + !pctldev->desc->custom_conf_items) return; - for (i = 0; i < pctldev->desc->num_dt_params; i++) { - if (pinconf_to_config_param(config) != pctldev->desc->conf_items[i].param) + for (i = 0; i < pctldev->desc->num_custom_params; i++) { + if (pinconf_to_config_param(config) != + pctldev->desc->custom_conf_items[i].param) continue; - seq_printf(s, "%s: 0x%x", pctldev->desc->conf_items[i].display, - pinconf_to_config_argument(config)); + seq_printf(s, "%s: 0x%x", + pctldev->desc->custom_conf_items[i].display, + pinconf_to_config_argument(config)); } } EXPORT_SYMBOL_GPL(pinconf_generic_dump_config); #endif #ifdef CONFIG_OF -static const struct pinconf_generic_dt_params dt_params[] = { +static const struct pinconf_generic_params dt_params[] = { { "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 }, { "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 }, { "bias-bus-hold", PIN_CONFIG_BIAS_BUS_HOLD, 0 }, @@ -170,9 +174,9 @@ static const struct pinconf_generic_dt_params dt_params[] = { }; /** - * parse_dt_cfg - Parse DT pinconf parameters + * parse_dt_cfg() - Parse DT pinconf parameters * @np: DT node - * @params: Array of describing DT parameters + * @params: Array of describing generic parameters * @count: Number of entries in @params * @cfg: Array of parsed config options * @ncfg: Number of entries in @cfg @@ -183,7 +187,7 @@ static const struct pinconf_generic_dt_params dt_params[] = { * needs to have enough memory allocated to hold all possible entries. */ static void parse_dt_cfg(struct device_node *np, - const struct pinconf_generic_dt_params *params, + const struct pinconf_generic_params *params, unsigned int count, unsigned long *cfg, unsigned int *ncfg) { @@ -192,7 +196,7 @@ static void parse_dt_cfg(struct device_node *np, for (i = 0; i < count; i++) { u32 val; int ret; - const struct pinconf_generic_dt_params *par = ¶ms[i]; + const struct pinconf_generic_params *par = ¶ms[i]; ret = of_property_read_u32(np, par->property, &val); @@ -232,15 +236,16 @@ int pinconf_generic_parse_dt_config(struct device_node *np, /* allocate a temporary array big enough to hold one of each option */ max_cfg = ARRAY_SIZE(dt_params); if (pctldev) - max_cfg += pctldev->desc->num_dt_params; + max_cfg += pctldev->desc->num_custom_params; cfg = kcalloc(max_cfg, sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg); - if (pctldev && pctldev->desc->num_dt_params && pctldev->desc->params) - parse_dt_cfg(np, pctldev->desc->params, - pctldev->desc->num_dt_params, cfg, &ncfg); + if (pctldev && pctldev->desc->num_custom_params && + pctldev->desc->custom_params) + parse_dt_cfg(np, pctldev->desc->custom_params, + pctldev->desc->num_custom_params, cfg, &ncfg); ret = 0; diff --git a/drivers/pinctrl/pinctrl-zynq.c b/drivers/pinctrl/pinctrl-zynq.c index 62534234da78..8aa05e2eb705 100644 --- a/drivers/pinctrl/pinctrl-zynq.c +++ b/drivers/pinctrl/pinctrl-zynq.c @@ -920,7 +920,7 @@ enum zynq_pin_config_param { PIN_CONFIG_IOSTANDARD = PIN_CONFIG_END + 1, }; -static const struct pinconf_generic_dt_params zynq_dt_params[] = { +static const struct pinconf_generic_params zynq_dt_params[] = { {"io-standard", PIN_CONFIG_IOSTANDARD, zynq_iostd_lvcmos18}, }; @@ -1099,9 +1099,9 @@ static struct pinctrl_desc zynq_desc = { .pctlops = &zynq_pctrl_ops, .pmxops = &zynq_pinmux_ops, .confops = &zynq_pinconf_ops, - .num_dt_params = ARRAY_SIZE(zynq_dt_params), - .params = zynq_dt_params, - .conf_items = zynq_conf_items, + .num_custom_params = ARRAY_SIZE(zynq_dt_params), + .custom_params = zynq_dt_params, + .custom_conf_items = zynq_conf_items, .owner = THIS_MODULE, }; diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 17f811c9c2c0..bbf99a715b63 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -131,7 +131,7 @@ struct pmic_gpio_state { struct gpio_chip chip; }; -static const struct pinconf_generic_dt_params pmic_gpio_bindings[] = { +static const struct pinconf_generic_params pmic_gpio_bindings[] = { {"qcom,pull-up-strength", PMIC_GPIO_CONF_PULL_UP, 0}, {"qcom,drive-strength", PMIC_GPIO_CONF_STRENGTH, 0}, }; @@ -742,9 +742,9 @@ static int pmic_gpio_probe(struct platform_device *pdev) pctrldesc->name = dev_name(dev); pctrldesc->pins = pindesc; pctrldesc->npins = npins; - pctrldesc->num_dt_params = ARRAY_SIZE(pmic_gpio_bindings); - pctrldesc->params = pmic_gpio_bindings; - pctrldesc->conf_items = pmic_conf_items; + pctrldesc->num_custom_params = ARRAY_SIZE(pmic_gpio_bindings); + pctrldesc->custom_params = pmic_gpio_bindings; + pctrldesc->custom_conf_items = pmic_conf_items; for (i = 0; i < npins; i++, pindesc++) { pad = &pads[i]; diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 342409f7f3ec..fe65962b264f 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -162,7 +162,7 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param struct pinctrl_dev; struct pinctrl_map; -struct pinconf_generic_dt_params { +struct pinconf_generic_params { const char * const property; enum pin_config_param param; u32 default_value; diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index c58b3e11ba8e..66e4697516de 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -118,9 +118,12 @@ struct pinctrl_ops { * @confops: pin config operations vtable, if you support pin configuration in * your driver * @owner: module providing the pin controller, used for refcounting - * @num_dt_params: Number of driver-specific DT parameters - * @params: List of DT parameters - * @conf_items: Information how to print @params in debugfs + * @num_custom_params: Number of driver-specific custom parameters to be parsed + * from the hardware description + * @custom_params: List of driver_specific custom parameters to be parsed from + * the hardware description + * @custom_conf_items: Information how to print @params in debugfs, must be + * the same size as the @custom_params, i.e. @num_custom_params */ struct pinctrl_desc { const char *name; @@ -130,10 +133,10 @@ struct pinctrl_desc { const struct pinmux_ops *pmxops; const struct pinconf_ops *confops; struct module *owner; -#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF) - unsigned int num_dt_params; - const struct pinconf_generic_dt_params *params; - const struct pin_config_item *conf_items; +#ifdef CONFIG_GENERIC_PINCONF + unsigned int num_custom_params; + const struct pinconf_generic_params *custom_params; + const struct pin_config_item *custom_conf_items; #endif }; -- cgit v1.2.3 From 5a7d2efdd93f6c4bb6cd3d5df3d2f5611c9b87ac Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 16 Dec 2014 10:59:17 +0100 Subject: pinctrl: consumer: use correct retval for placeholder functions These functions are supposed to return an error pointer, not NULL. Signed-off-by: Wolfram Sang Signed-off-by: Linus Walleij --- include/linux/pinctrl/consumer.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 18eccefea06e..72c0415d6c21 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -82,7 +82,7 @@ static inline int pinctrl_gpio_direction_output(unsigned gpio) static inline struct pinctrl * __must_check pinctrl_get(struct device *dev) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline void pinctrl_put(struct pinctrl *p) @@ -93,7 +93,7 @@ static inline struct pinctrl_state * __must_check pinctrl_lookup_state( struct pinctrl *p, const char *name) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline int pinctrl_select_state(struct pinctrl *p, @@ -104,7 +104,7 @@ static inline int pinctrl_select_state(struct pinctrl *p, static inline struct pinctrl * __must_check devm_pinctrl_get(struct device *dev) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline void devm_pinctrl_put(struct pinctrl *p) -- cgit v1.2.3 From d84b6728c54dcf73bcef3e3f7cf6767e2d224e39 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 6 Jan 2015 11:45:07 -0800 Subject: locking/mcs: Better differentiate between MCS variants We have two flavors of the MCS spinlock: standard and cancelable (OSQ). While each one is independent of the other, we currently mix and match them. This patch: - Moves the OSQ code out of mcs_spinlock.h (which only deals with the traditional version) into include/linux/osq_lock.h. No unnecessary code is added to the more global header file, anything locks that make use of OSQ must include it anyway. - Renames mcs_spinlock.c to osq_lock.c. This file only contains osq code. - Introduces a CONFIG_LOCK_SPIN_ON_OWNER in order to only build osq_lock if there is support for it. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Thomas Gleixner Cc: "Paul E. McKenney" Cc: Jason Low Cc: Linus Torvalds Cc: Mikulas Patocka Cc: Waiman Long Link: http://lkml.kernel.org/r/1420573509-24774-5-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- include/linux/osq_lock.h | 12 ++- kernel/Kconfig.locks | 4 + kernel/locking/Makefile | 3 +- kernel/locking/mcs_spinlock.c | 208 ------------------------------------------ kernel/locking/mcs_spinlock.h | 16 ---- kernel/locking/osq_lock.c | 203 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 219 insertions(+), 227 deletions(-) delete mode 100644 kernel/locking/mcs_spinlock.c create mode 100644 kernel/locking/osq_lock.c (limited to 'include/linux') diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 90230d5811c5..3a6490e81b28 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -5,8 +5,11 @@ * An MCS like lock especially tailored for optimistic spinning for sleeping * lock implementations (mutex, rwsem, etc). */ - -#define OSQ_UNLOCKED_VAL (0) +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; + int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # + 1 value */ +}; struct optimistic_spin_queue { /* @@ -16,6 +19,8 @@ struct optimistic_spin_queue { atomic_t tail; }; +#define OSQ_UNLOCKED_VAL (0) + /* Init macro and function. */ #define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) } @@ -24,4 +29,7 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) atomic_set(&lock->tail, OSQ_UNLOCKED_VAL); } +extern bool osq_lock(struct optimistic_spin_queue *lock); +extern void osq_unlock(struct optimistic_spin_queue *lock); + #endif diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 76768ee812b2..08561f1acd13 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -231,6 +231,10 @@ config RWSEM_SPIN_ON_OWNER def_bool y depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW +config LOCK_SPIN_ON_OWNER + def_bool y + depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER + config ARCH_USE_QUEUE_RWLOCK bool diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 8541bfdfd232..4ca8eb151975 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o +obj-y += mutex.o semaphore.o rwsem.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c deleted file mode 100644 index 9887a905a762..000000000000 --- a/kernel/locking/mcs_spinlock.c +++ /dev/null @@ -1,208 +0,0 @@ -#include -#include -#include "mcs_spinlock.h" - -#ifdef CONFIG_SMP - -/* - * An MCS like lock especially tailored for optimistic spinning for sleeping - * lock implementations (mutex, rwsem, etc). - * - * Using a single mcs node per CPU is safe because sleeping locks should not be - * called from interrupt context and we have preemption disabled while - * spinning. - */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); - -/* - * We use the value 0 to represent "no CPU", thus the encoded value - * will be the CPU number incremented by 1. - */ -static inline int encode_cpu(int cpu_nr) -{ - return cpu_nr + 1; -} - -static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) -{ - int cpu_nr = encoded_cpu_val - 1; - - return per_cpu_ptr(&osq_node, cpu_nr); -} - -/* - * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. - * Can return NULL in case we were the last queued and we updated @lock instead. - */ -static inline struct optimistic_spin_node * -osq_wait_next(struct optimistic_spin_queue *lock, - struct optimistic_spin_node *node, - struct optimistic_spin_node *prev) -{ - struct optimistic_spin_node *next = NULL; - int curr = encode_cpu(smp_processor_id()); - int old; - - /* - * If there is a prev node in queue, then the 'old' value will be - * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if - * we're currently last in queue, then the queue will then become empty. - */ - old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; - - for (;;) { - if (atomic_read(&lock->tail) == curr && - atomic_cmpxchg(&lock->tail, curr, old) == curr) { - /* - * We were the last queued, we moved @lock back. @prev - * will now observe @lock and will complete its - * unlock()/unqueue(). - */ - break; - } - - /* - * We must xchg() the @node->next value, because if we were to - * leave it in, a concurrent unlock()/unqueue() from - * @node->next might complete Step-A and think its @prev is - * still valid. - * - * If the concurrent unlock()/unqueue() wins the race, we'll - * wait for either @lock to point to us, through its Step-B, or - * wait for a new @node->next from its Step-C. - */ - if (node->next) { - next = xchg(&node->next, NULL); - if (next) - break; - } - - cpu_relax_lowlatency(); - } - - return next; -} - -bool osq_lock(struct optimistic_spin_queue *lock) -{ - struct optimistic_spin_node *node = this_cpu_ptr(&osq_node); - struct optimistic_spin_node *prev, *next; - int curr = encode_cpu(smp_processor_id()); - int old; - - node->locked = 0; - node->next = NULL; - node->cpu = curr; - - old = atomic_xchg(&lock->tail, curr); - if (old == OSQ_UNLOCKED_VAL) - return true; - - prev = decode_cpu(old); - node->prev = prev; - ACCESS_ONCE(prev->next) = node; - - /* - * Normally @prev is untouchable after the above store; because at that - * moment unlock can proceed and wipe the node element from stack. - * - * However, since our nodes are static per-cpu storage, we're - * guaranteed their existence -- this allows us to apply - * cmpxchg in an attempt to undo our queueing. - */ - - while (!smp_load_acquire(&node->locked)) { - /* - * If we need to reschedule bail... so we can block. - */ - if (need_resched()) - goto unqueue; - - cpu_relax_lowlatency(); - } - return true; - -unqueue: - /* - * Step - A -- stabilize @prev - * - * Undo our @prev->next assignment; this will make @prev's - * unlock()/unqueue() wait for a next pointer since @lock points to us - * (or later). - */ - - for (;;) { - if (prev->next == node && - cmpxchg(&prev->next, node, NULL) == node) - break; - - /* - * We can only fail the cmpxchg() racing against an unlock(), - * in which case we should observe @node->locked becomming - * true. - */ - if (smp_load_acquire(&node->locked)) - return true; - - cpu_relax_lowlatency(); - - /* - * Or we race against a concurrent unqueue()'s step-B, in which - * case its step-C will write us a new @node->prev pointer. - */ - prev = ACCESS_ONCE(node->prev); - } - - /* - * Step - B -- stabilize @next - * - * Similar to unlock(), wait for @node->next or move @lock from @node - * back to @prev. - */ - - next = osq_wait_next(lock, node, prev); - if (!next) - return false; - - /* - * Step - C -- unlink - * - * @prev is stable because its still waiting for a new @prev->next - * pointer, @next is stable because our @node->next pointer is NULL and - * it will wait in Step-A. - */ - - ACCESS_ONCE(next->prev) = prev; - ACCESS_ONCE(prev->next) = next; - - return false; -} - -void osq_unlock(struct optimistic_spin_queue *lock) -{ - struct optimistic_spin_node *node, *next; - int curr = encode_cpu(smp_processor_id()); - - /* - * Fast path for the uncontended case. - */ - if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) - return; - - /* - * Second most likely case. - */ - node = this_cpu_ptr(&osq_node); - next = xchg(&node->next, NULL); - if (next) { - ACCESS_ONCE(next->locked) = 1; - return; - } - - next = osq_wait_next(lock, node, NULL); - if (next) - ACCESS_ONCE(next->locked) = 1; -} - -#endif - diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 4d60986fcbee..d1fe2ba5bac9 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -108,20 +108,4 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) arch_mcs_spin_unlock_contended(&next->locked); } -/* - * Cancellable version of the MCS lock above. - * - * Intended for adaptive spinning of sleeping locks: - * mutex_lock()/rwsem_down_{read,write}() etc. - */ - -struct optimistic_spin_node { - struct optimistic_spin_node *next, *prev; - int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # value */ -}; - -extern bool osq_lock(struct optimistic_spin_queue *lock); -extern void osq_unlock(struct optimistic_spin_queue *lock); - #endif /* __LINUX_MCS_SPINLOCK_H */ diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c new file mode 100644 index 000000000000..ec83d4db8ec6 --- /dev/null +++ b/kernel/locking/osq_lock.c @@ -0,0 +1,203 @@ +#include +#include +#include + +/* + * An MCS like lock especially tailored for optimistic spinning for sleeping + * lock implementations (mutex, rwsem, etc). + * + * Using a single mcs node per CPU is safe because sleeping locks should not be + * called from interrupt context and we have preemption disabled while + * spinning. + */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); + +/* + * We use the value 0 to represent "no CPU", thus the encoded value + * will be the CPU number incremented by 1. + */ +static inline int encode_cpu(int cpu_nr) +{ + return cpu_nr + 1; +} + +static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) +{ + int cpu_nr = encoded_cpu_val - 1; + + return per_cpu_ptr(&osq_node, cpu_nr); +} + +/* + * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. + * Can return NULL in case we were the last queued and we updated @lock instead. + */ +static inline struct optimistic_spin_node * +osq_wait_next(struct optimistic_spin_queue *lock, + struct optimistic_spin_node *node, + struct optimistic_spin_node *prev) +{ + struct optimistic_spin_node *next = NULL; + int curr = encode_cpu(smp_processor_id()); + int old; + + /* + * If there is a prev node in queue, then the 'old' value will be + * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if + * we're currently last in queue, then the queue will then become empty. + */ + old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; + + for (;;) { + if (atomic_read(&lock->tail) == curr && + atomic_cmpxchg(&lock->tail, curr, old) == curr) { + /* + * We were the last queued, we moved @lock back. @prev + * will now observe @lock and will complete its + * unlock()/unqueue(). + */ + break; + } + + /* + * We must xchg() the @node->next value, because if we were to + * leave it in, a concurrent unlock()/unqueue() from + * @node->next might complete Step-A and think its @prev is + * still valid. + * + * If the concurrent unlock()/unqueue() wins the race, we'll + * wait for either @lock to point to us, through its Step-B, or + * wait for a new @node->next from its Step-C. + */ + if (node->next) { + next = xchg(&node->next, NULL); + if (next) + break; + } + + cpu_relax_lowlatency(); + } + + return next; +} + +bool osq_lock(struct optimistic_spin_queue *lock) +{ + struct optimistic_spin_node *node = this_cpu_ptr(&osq_node); + struct optimistic_spin_node *prev, *next; + int curr = encode_cpu(smp_processor_id()); + int old; + + node->locked = 0; + node->next = NULL; + node->cpu = curr; + + old = atomic_xchg(&lock->tail, curr); + if (old == OSQ_UNLOCKED_VAL) + return true; + + prev = decode_cpu(old); + node->prev = prev; + ACCESS_ONCE(prev->next) = node; + + /* + * Normally @prev is untouchable after the above store; because at that + * moment unlock can proceed and wipe the node element from stack. + * + * However, since our nodes are static per-cpu storage, we're + * guaranteed their existence -- this allows us to apply + * cmpxchg in an attempt to undo our queueing. + */ + + while (!smp_load_acquire(&node->locked)) { + /* + * If we need to reschedule bail... so we can block. + */ + if (need_resched()) + goto unqueue; + + cpu_relax_lowlatency(); + } + return true; + +unqueue: + /* + * Step - A -- stabilize @prev + * + * Undo our @prev->next assignment; this will make @prev's + * unlock()/unqueue() wait for a next pointer since @lock points to us + * (or later). + */ + + for (;;) { + if (prev->next == node && + cmpxchg(&prev->next, node, NULL) == node) + break; + + /* + * We can only fail the cmpxchg() racing against an unlock(), + * in which case we should observe @node->locked becomming + * true. + */ + if (smp_load_acquire(&node->locked)) + return true; + + cpu_relax_lowlatency(); + + /* + * Or we race against a concurrent unqueue()'s step-B, in which + * case its step-C will write us a new @node->prev pointer. + */ + prev = ACCESS_ONCE(node->prev); + } + + /* + * Step - B -- stabilize @next + * + * Similar to unlock(), wait for @node->next or move @lock from @node + * back to @prev. + */ + + next = osq_wait_next(lock, node, prev); + if (!next) + return false; + + /* + * Step - C -- unlink + * + * @prev is stable because its still waiting for a new @prev->next + * pointer, @next is stable because our @node->next pointer is NULL and + * it will wait in Step-A. + */ + + ACCESS_ONCE(next->prev) = prev; + ACCESS_ONCE(prev->next) = next; + + return false; +} + +void osq_unlock(struct optimistic_spin_queue *lock) +{ + struct optimistic_spin_node *node, *next; + int curr = encode_cpu(smp_processor_id()); + + /* + * Fast path for the uncontended case. + */ + if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) + return; + + /* + * Second most likely case. + */ + node = this_cpu_ptr(&osq_node); + next = xchg(&node->next, NULL); + if (next) { + ACCESS_ONCE(next->locked) = 1; + return; + } + + next = osq_wait_next(lock, node, NULL); + if (next) + ACCESS_ONCE(next->locked) = 1; +} -- cgit v1.2.3 From 86038c5ea81b519a8a1fcfcd5e4599aab0cdd119 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 16 Dec 2014 12:47:34 +0100 Subject: perf: Avoid horrible stack usage Both Linus (most recent) and Steve (a while ago) reported that perf related callbacks have massive stack bloat. The problem is that software events need a pt_regs in order to properly report the event location and unwind stack. And because we could not assume one was present we allocated one on stack and filled it with minimal bits required for operation. Now, pt_regs is quite large, so this is undesirable. Furthermore it turns out that most sites actually have a pt_regs pointer available, making this even more onerous, as the stack space is pointless waste. This patch addresses the problem by observing that software events have well defined nesting semantics, therefore we can use static per-cpu storage instead of on-stack. Linus made the further observation that all but the scheduler callers of perf_sw_event() have a pt_regs available, so we change the regular perf_sw_event() to require a valid pt_regs (where it used to be optional) and add perf_sw_event_sched() for the scheduler. We have a scheduler specific call instead of a more generic _noregs() like construct because we can assume non-recursion from the scheduler and thereby simplify the code further (_noregs would have to put the recursion context call inline in order to assertain which __perf_regs element to use). One last note on the implementation of perf_trace_buf_prepare(); we allow .regs = NULL for those cases where we already have a pt_regs pointer available and do not need another. Reported-by: Linus Torvalds Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Javi Merino Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Oleg Nesterov Cc: Paul Mackerras Cc: Petr Mladek Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vaibhav Nagarnaik Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 2 +- include/linux/perf_event.h | 28 +++++++++++++++++++++------- include/trace/ftrace.h | 7 ++++--- kernel/events/core.c | 23 +++++++++++++++++------ kernel/sched/core.c | 2 +- kernel/trace/trace_event_perf.c | 4 +++- kernel/trace/trace_kprobe.c | 4 ++-- kernel/trace/trace_syscalls.c | 4 ++-- kernel/trace/trace_uprobe.c | 2 +- 9 files changed, 52 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0bebb5c348b8..d36f68b08acc 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -595,7 +595,7 @@ extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp); + struct pt_regs **regs, int *rctxp); static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4f7a61ca4b39..3a7bd80b4db8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -665,6 +665,7 @@ static inline int is_software_event(struct perf_event *event) extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; +extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs @@ -689,14 +690,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs) static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { - struct pt_regs hot_regs; + if (static_key_false(&perf_swevent_enabled[event_id])) + __perf_sw_event(event_id, nr, regs, addr); +} + +DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); +/* + * 'Special' version for the scheduler, it hard assumes no recursion, + * which is guaranteed by us not actually scheduling inside other swevents + * because those disable preemption. + */ +static __always_inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) +{ if (static_key_false(&perf_swevent_enabled[event_id])) { - if (!regs) { - perf_fetch_caller_regs(&hot_regs); - regs = &hot_regs; - } - __perf_sw_event(event_id, nr, regs, addr); + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); + + perf_fetch_caller_regs(regs); + ___perf_sw_event(event_id, nr, regs, addr); } } @@ -712,7 +724,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev, static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { - perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); + perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_out(prev, next); @@ -823,6 +835,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh) static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } +static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 139b5067345b..27609dfcce25 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto) \ struct ftrace_event_call *event_call = __data; \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ftrace_raw_##call *entry; \ - struct pt_regs __regs; \ + struct pt_regs *__regs; \ u64 __addr = 0, __count = 1; \ struct task_struct *__task = NULL; \ struct hlist_head *head; \ @@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto) \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - perf_fetch_caller_regs(&__regs); \ entry = perf_trace_buf_prepare(__entry_size, \ event_call->event.type, &__regs, &rctx); \ if (!entry) \ return; \ \ + perf_fetch_caller_regs(__regs); \ + \ tstruct \ \ { assign; } \ \ perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ - __count, &__regs, head, __task); \ + __count, __regs, head, __task); \ } /* diff --git a/kernel/events/core.c b/kernel/events/core.c index 882f835a0d85..c10124b772c4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5889,6 +5889,8 @@ end: rcu_read_unlock(); } +DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]); + int perf_swevent_get_recursion_context(void) { struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); @@ -5904,21 +5906,30 @@ inline void perf_swevent_put_recursion_context(int rctx) put_recursion_context(swhash->recursion, rctx); } -void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { struct perf_sample_data data; - int rctx; - preempt_disable_notrace(); - rctx = perf_swevent_get_recursion_context(); - if (rctx < 0) + if (WARN_ON_ONCE(!regs)) return; perf_sample_data_init(&data, addr, 0); - do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs); +} + +void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +{ + int rctx; + + preempt_disable_notrace(); + rctx = perf_swevent_get_recursion_context(); + if (unlikely(rctx < 0)) + goto fail; + + ___perf_sw_event(event_id, nr, regs, addr); perf_swevent_put_recursion_context(rctx); +fail: preempt_enable_notrace(); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c0accc00566e..d22fb16a7153 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1082,7 +1082,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; - perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0); + perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); } __set_task_cpu(p, new_cpu); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 4b9c114ee9de..6fa484de2ba1 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -261,7 +261,7 @@ void perf_trace_del(struct perf_event *p_event, int flags) } void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp) + struct pt_regs **regs, int *rctxp) { struct trace_entry *entry; unsigned long flags; @@ -280,6 +280,8 @@ void *perf_trace_buf_prepare(int size, unsigned short type, if (*rctxp < 0) return NULL; + if (regs) + *regs = this_cpu_ptr(&__perf_regs[*rctxp]); raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]); /* zero the dead bytes from align to not leak stack to user */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5edb518be345..296079ae6583 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1148,7 +1148,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) return; @@ -1179,7 +1179,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) return; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index c6ee36fcbf90..f97f6e3a676c 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -574,7 +574,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) size -= sizeof(u32); rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, - sys_data->enter_event->event.type, regs, &rctx); + sys_data->enter_event->event.type, NULL, &rctx); if (!rec) return; @@ -647,7 +647,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) size -= sizeof(u32); rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, - sys_data->exit_event->event.type, regs, &rctx); + sys_data->exit_event->event.type, NULL, &rctx); if (!rec) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8520acc34b18..b11441321e7a 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1111,7 +1111,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, if (hlist_empty(head)) goto out; - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) goto out; -- cgit v1.2.3 From c38fda3fe8163898f538a45d3c1419e6870625ed Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 14 Jan 2015 22:59:13 -0800 Subject: jbd: drop jbd_ENOSYS debug A quick search shows that there are no users, drop the macro for both jbd and jbd2. Signed-off-by: Davidlohr Bueso Cc: Jan Kara Signed-off-by: Jan Kara --- include/linux/jbd.h | 9 --------- include/linux/jbd2.h | 9 --------- 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 31229e0be90b..d32615280be9 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -956,15 +956,6 @@ void __log_wait_for_space(journal_t *journal); extern void __journal_drop_transaction(journal_t *, transaction_t *); extern int cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 704b9a599b26..20e7f78041c8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1251,15 +1251,6 @@ void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * -- cgit v1.2.3 From 37715f556a0776356300391f8ac41ace91bea447 Mon Sep 17 00:00:00 2001 From: David Ung Date: Tue, 13 Jan 2015 19:04:25 -0800 Subject: video: fbdev: Add additional vesa modes Add high resolution modes to vesa_modes struct. Signed-off-by: David Ung Signed-off-by: Tomi Valkeinen --- drivers/video/fbdev/core/modedb.c | 27 +++++++++++++++++++++++++++ include/linux/fb.h | 2 +- 2 files changed, 28 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 388f7971494b..0b57c1df73e3 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -468,6 +468,33 @@ const struct fb_videomode vesa_modes[] = { /* 33 1920x1440-75 VESA */ { NULL, 75, 1920, 1440, 3367, 352, 144, 56, 1, 224, 3, FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 34 1920x1200-60 RB VESA */ + { NULL, 60, 1920, 1200, 6493, 80, 48, 26, 3, 32, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 35 1920x1200-60 VESA */ + { NULL, 60, 1920, 1200, 5174, 336, 136, 36, 3, 200, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 36 1920x1200-75 VESA */ + { NULL, 75, 1920, 1200, 4077, 344, 136, 46, 3, 208, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 37 1920x1200-85 VESA */ + { NULL, 85, 1920, 1200, 3555, 352, 144, 53, 3, 208, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 38 2560x1600-60 RB VESA */ + { NULL, 60, 2560, 1600, 3724, 80, 48, 37, 3, 32, 6, + FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 39 2560x1600-60 VESA */ + { NULL, 60, 2560, 1600, 2869, 472, 192, 49, 3, 280, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 40 2560x1600-75 VESA */ + { NULL, 75, 2560, 1600, 2256, 488, 208, 63, 3, 280, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 41 2560x1600-85 VESA */ + { NULL, 85, 2560, 1600, 1979, 488, 208, 73, 3, 280, 6, + FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, + /* 42 2560x1600-120 RB VESA */ + { NULL, 120, 2560, 1600, 1809, 80, 48, 85, 3, 32, 6, + FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, }; EXPORT_SYMBOL(vesa_modes); #endif /* CONFIG_FB_MODE_HELPERS */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 09bb7a18d287..882dbd1a87b7 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -726,7 +726,7 @@ extern int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode); /* drivers/video/modedb.c */ -#define VESA_MODEDB_SIZE 34 +#define VESA_MODEDB_SIZE 43 extern void fb_var_to_videomode(struct fb_videomode *mode, const struct fb_var_screeninfo *var); extern void fb_videomode_to_var(struct fb_var_screeninfo *var, -- cgit v1.2.3 From 8f5ee77bb8d162abe28ff8cd56f36e825d143207 Mon Sep 17 00:00:00 2001 From: David Ung Date: Tue, 13 Jan 2015 19:04:26 -0800 Subject: video: fbdev: Check Standard Timing against DMT Add the VESA Display Monitor Timing (DMT) table. During parsing of Standard Timings, it compare the 2 byte STD code with DMT to see what the VESA mode should be. If there is no entry in the vesa_modes table or no match found, it fallsback to the GTF timings. Signed-off-by: David Ung Signed-off-by: Tomi Valkeinen --- drivers/video/fbdev/core/fbmon.c | 76 +++++++++++++++++++---------------- drivers/video/fbdev/core/modedb.c | 84 +++++++++++++++++++++++++++++++++++++++ include/linux/fb.h | 10 +++++ 3 files changed, 136 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index 5b0e313849bd..0f234c15ece3 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -498,44 +498,52 @@ static int get_est_timing(unsigned char *block, struct fb_videomode *mode) static int get_std_timing(unsigned char *block, struct fb_videomode *mode, int ver, int rev) { - int xres, yres = 0, refresh, ratio, i; - - xres = (block[0] + 31) * 8; - if (xres <= 256) - return 0; + int i; - ratio = (block[1] & 0xc0) >> 6; - switch (ratio) { - case 0: - /* in EDID 1.3 the meaning of 0 changed to 16:10 (prior 1:1) */ - if (ver < 1 || (ver == 1 && rev < 3)) - yres = xres; - else - yres = (xres * 10)/16; - break; - case 1: - yres = (xres * 3)/4; - break; - case 2: - yres = (xres * 4)/5; - break; - case 3: - yres = (xres * 9)/16; - break; + for (i = 0; i < DMT_SIZE; i++) { + u32 std_2byte_code = block[0] << 8 | block[1]; + if (std_2byte_code == dmt_modes[i].std_2byte_code) + break; } - refresh = (block[1] & 0x3f) + 60; - - DPRINTK(" %dx%d@%dHz\n", xres, yres, refresh); - for (i = 0; i < VESA_MODEDB_SIZE; i++) { - if (vesa_modes[i].xres == xres && - vesa_modes[i].yres == yres && - vesa_modes[i].refresh == refresh) { - *mode = vesa_modes[i]; - mode->flag |= FB_MODE_IS_STANDARD; - return 1; + + if (i < DMT_SIZE && dmt_modes[i].mode) { + /* DMT mode found */ + *mode = *dmt_modes[i].mode; + mode->flag |= FB_MODE_IS_STANDARD; + DPRINTK(" DMT id=%d\n", dmt_modes[i].dmt_id); + + } else { + int xres, yres = 0, refresh, ratio; + + xres = (block[0] + 31) * 8; + if (xres <= 256) + return 0; + + ratio = (block[1] & 0xc0) >> 6; + switch (ratio) { + case 0: + /* in EDID 1.3 the meaning of 0 changed to 16:10 (prior 1:1) */ + if (ver < 1 || (ver == 1 && rev < 3)) + yres = xres; + else + yres = (xres * 10)/16; + break; + case 1: + yres = (xres * 3)/4; + break; + case 2: + yres = (xres * 4)/5; + break; + case 3: + yres = (xres * 9)/16; + break; } + refresh = (block[1] & 0x3f) + 60; + DPRINTK(" %dx%d@%dHz\n", xres, yres, refresh); + + calc_mode_timings(xres, yres, refresh, mode); } - calc_mode_timings(xres, yres, refresh, mode); + return 1; } diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 0b57c1df73e3..858a97e03200 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -497,6 +497,90 @@ const struct fb_videomode vesa_modes[] = { FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, }; EXPORT_SYMBOL(vesa_modes); + +const struct dmt_videomode dmt_modes[DMT_SIZE] = { + { 0x01, 0x0000, 0x000000, &vesa_modes[0] }, + { 0x02, 0x3119, 0x000000, &vesa_modes[1] }, + { 0x03, 0x0000, 0x000000, &vesa_modes[2] }, + { 0x04, 0x3140, 0x000000, &vesa_modes[3] }, + { 0x05, 0x314c, 0x000000, &vesa_modes[4] }, + { 0x06, 0x314f, 0x000000, &vesa_modes[5] }, + { 0x07, 0x3159, 0x000000, &vesa_modes[6] }, + { 0x08, 0x0000, 0x000000, &vesa_modes[7] }, + { 0x09, 0x4540, 0x000000, &vesa_modes[8] }, + { 0x0a, 0x454c, 0x000000, &vesa_modes[9] }, + { 0x0b, 0x454f, 0x000000, &vesa_modes[10] }, + { 0x0c, 0x4559, 0x000000, &vesa_modes[11] }, + { 0x0d, 0x0000, 0x000000, 0 }, + { 0x0e, 0x0000, 0x000000, 0 }, + { 0x0f, 0x0000, 0x000000, &vesa_modes[12] }, + { 0x10, 0x6140, 0x000000, &vesa_modes[13] }, + { 0x11, 0x614a, 0x000000, &vesa_modes[14] }, + { 0x12, 0x614f, 0x000000, &vesa_modes[15] }, + { 0x13, 0x6159, 0x000000, &vesa_modes[16] }, + { 0x14, 0x0000, 0x000000, 0 }, + { 0x15, 0x714f, 0x000000, &vesa_modes[17] }, + { 0x16, 0x0000, 0x7f1c21, 0 }, + { 0x17, 0x0000, 0x7f1c28, 0 }, + { 0x18, 0x0000, 0x7f1c44, 0 }, + { 0x19, 0x0000, 0x7f1c62, 0 }, + { 0x1a, 0x0000, 0x000000, 0 }, + { 0x1b, 0x0000, 0x8f1821, 0 }, + { 0x1c, 0x8100, 0x8f1828, 0 }, + { 0x1d, 0x810f, 0x8f1844, 0 }, + { 0x1e, 0x8119, 0x8f1862, 0 }, + { 0x1f, 0x0000, 0x000000, 0 }, + { 0x20, 0x8140, 0x000000, &vesa_modes[18] }, + { 0x21, 0x8159, 0x000000, &vesa_modes[19] }, + { 0x22, 0x0000, 0x000000, 0 }, + { 0x23, 0x8180, 0x000000, &vesa_modes[20] }, + { 0x24, 0x818f, 0x000000, &vesa_modes[21] }, + { 0x25, 0x8199, 0x000000, &vesa_modes[22] }, + { 0x26, 0x0000, 0x000000, 0 }, + { 0x27, 0x0000, 0x000000, 0 }, + { 0x28, 0x0000, 0x000000, 0 }, + { 0x29, 0x0000, 0x0c2021, 0 }, + { 0x2a, 0x9040, 0x0c2028, 0 }, + { 0x2b, 0x904f, 0x0c2044, 0 }, + { 0x2c, 0x9059, 0x0c2062, 0 }, + { 0x2d, 0x0000, 0x000000, 0 }, + { 0x2e, 0x9500, 0xc11821, 0 }, + { 0x2f, 0x9500, 0xc11828, 0 }, + { 0x30, 0x950f, 0xc11844, 0 }, + { 0x31, 0x9519, 0xc11868, 0 }, + { 0x32, 0x0000, 0x000000, 0 }, + { 0x33, 0xa940, 0x000000, &vesa_modes[23] }, + { 0x34, 0xa945, 0x000000, &vesa_modes[24] }, + { 0x35, 0xa94a, 0x000000, &vesa_modes[25] }, + { 0x36, 0xa94f, 0x000000, &vesa_modes[26] }, + { 0x37, 0xa959, 0x000000, &vesa_modes[27] }, + { 0x38, 0x0000, 0x000000, 0 }, + { 0x39, 0x0000, 0x0c2821, 0 }, + { 0x3a, 0xb300, 0x0c2828, 0 }, + { 0x3b, 0xb30f, 0x0c2844, 0 }, + { 0x3c, 0xb319, 0x0c2868, 0 }, + { 0x3d, 0x0000, 0x000000, 0 }, + { 0x3e, 0xc140, 0x000000, &vesa_modes[28] }, + { 0x3f, 0xc14f, 0x000000, &vesa_modes[29] }, + { 0x40, 0x0000, 0x000000, 0 }, + { 0x41, 0xc940, 0x000000, &vesa_modes[30] }, + { 0x42, 0xc94f, 0x000000, &vesa_modes[31] }, + { 0x43, 0x0000, 0x000000, 0 }, + { 0x44, 0x0000, 0x572821, &vesa_modes[34] }, + { 0x45, 0xd100, 0x572828, &vesa_modes[35] }, + { 0x46, 0xd10f, 0x572844, &vesa_modes[36] }, + { 0x47, 0xd119, 0x572862, &vesa_modes[37] }, + { 0x48, 0x0000, 0x000000, 0 }, + { 0x49, 0xd140, 0x000000, &vesa_modes[32] }, + { 0x4a, 0xd14f, 0x000000, &vesa_modes[33] }, + { 0x4b, 0x0000, 0x000000, 0 }, + { 0x4c, 0x0000, 0x1f3821, &vesa_modes[38] }, + { 0x4d, 0x0000, 0x1f3828, &vesa_modes[39] }, + { 0x4e, 0x0000, 0x1f3844, &vesa_modes[40] }, + { 0x4f, 0x0000, 0x1f3862, &vesa_modes[41] }, + { 0x50, 0x0000, 0x000000, &vesa_modes[42] }, +}; +EXPORT_SYMBOL(dmt_modes); #endif /* CONFIG_FB_MODE_HELPERS */ /** diff --git a/include/linux/fb.h b/include/linux/fb.h index 882dbd1a87b7..043f3283b71c 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -727,6 +727,8 @@ extern int fb_videomode_from_videomode(const struct videomode *vm, /* drivers/video/modedb.c */ #define VESA_MODEDB_SIZE 43 +#define DMT_SIZE 0x50 + extern void fb_var_to_videomode(struct fb_videomode *mode, const struct fb_var_screeninfo *var); extern void fb_videomode_to_var(struct fb_var_screeninfo *var, @@ -777,9 +779,17 @@ struct fb_videomode { u32 flag; }; +struct dmt_videomode { + u32 dmt_id; + u32 std_2byte_code; + u32 cvt_3byte_code; + const struct fb_videomode *mode; +}; + extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; extern const struct fb_videomode cea_modes[64]; +extern const struct dmt_videomode dmt_modes[]; struct fb_modelist { struct list_head list; -- cgit v1.2.3 From d621e8bae5ac9c67de4de90c5cded12adc8ee1e1 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Wed, 17 Dec 2014 16:51:13 +0100 Subject: gpio/gpiolib-of: Create of_mm_gpiochip_remove Create counterpart of of_mm_gpiochip_add(). This way the modules that can be removable do not duplicate the cleanup code. Suggested-by: Alexandre Courbot Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-of.c | 17 +++++++++++++++++ include/linux/of_gpio.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 604dbe60bdee..3e2c6afeab11 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -204,6 +204,23 @@ err0: } EXPORT_SYMBOL(of_mm_gpiochip_add); +/** + * of_mm_gpiochip_remove - Remove memory mapped GPIO chip (bank) + * @mm_gc: pointer to the of_mm_gpio_chip allocated structure + */ +void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc) +{ + struct gpio_chip *gc = &mm_gc->gc; + + if (!mm_gc) + return; + + gpiochip_remove(gc); + iounmap(mm_gc->regs); + kfree(gc->label); +} +EXPORT_SYMBOL(of_mm_gpiochip_remove); + #ifdef CONFIG_PINCTRL static void of_gpiochip_add_pin_range(struct gpio_chip *chip) { diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 38fc05036015..69dbe312b11b 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -52,6 +52,7 @@ extern int of_get_named_gpio_flags(struct device_node *np, extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); +extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); extern void of_gpiochip_add(struct gpio_chip *gc); extern void of_gpiochip_remove(struct gpio_chip *gc); -- cgit v1.2.3 From 53e41f554a0cbad139ee5072bbb49b4951f680c2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 15 Dec 2014 10:39:47 +0100 Subject: gpio: tc3589x: get rid of platform data This device is only used from the device tree, and the startup() and remove() callbacks are not used anywhere in the kernel, so retire them and the pdata altogether. Cc: Samuel Ortiz Acked-by: Lee Jones Signed-off-by: Linus Walleij --- drivers/gpio/gpio-tc3589x.c | 15 ++------------- include/linux/mfd/tc3589x.h | 12 ------------ 2 files changed, 2 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c index abdcf58935f5..11aed2671065 100644 --- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -232,16 +232,13 @@ static irqreturn_t tc3589x_gpio_irq(int irq, void *dev) static int tc3589x_gpio_probe(struct platform_device *pdev) { struct tc3589x *tc3589x = dev_get_drvdata(pdev->dev.parent); - struct tc3589x_gpio_platform_data *pdata; struct device_node *np = pdev->dev.of_node; struct tc3589x_gpio *tc3589x_gpio; int ret; int irq; - pdata = tc3589x->pdata->gpio; - - if (!(pdata || np)) { - dev_err(&pdev->dev, "No platform data or Device Tree found\n"); + if (!np) { + dev_err(&pdev->dev, "No Device Tree node found\n"); return -EINVAL; } @@ -305,9 +302,6 @@ static int tc3589x_gpio_probe(struct platform_device *pdev) irq, NULL); - if (pdata && pdata->setup) - pdata->setup(tc3589x, tc3589x_gpio->chip.base); - platform_set_drvdata(pdev, tc3589x_gpio); return 0; @@ -316,11 +310,6 @@ static int tc3589x_gpio_probe(struct platform_device *pdev) static int tc3589x_gpio_remove(struct platform_device *pdev) { struct tc3589x_gpio *tc3589x_gpio = platform_get_drvdata(pdev); - struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; - struct tc3589x_gpio_platform_data *pdata = tc3589x->pdata->gpio; - - if (pdata && pdata->remove) - pdata->remove(tc3589x, tc3589x_gpio->chip.base); gpiochip_remove(&tc3589x_gpio->chip); diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index e1c12d84c26a..c203c9c56776 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -162,25 +162,13 @@ struct tc3589x_keypad_platform_data { bool no_autorepeat; }; -/** - * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data - * @setup: callback for board-specific initialization - * @remove: callback for board-specific teardown - */ -struct tc3589x_gpio_platform_data { - void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base); - void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base); -}; - /** * struct tc3589x_platform_data - TC3589x platform data * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) - * @gpio: GPIO-specific platform data * @keypad: keypad-specific platform data */ struct tc3589x_platform_data { unsigned int block; - struct tc3589x_gpio_platform_data *gpio; const struct tc3589x_keypad_platform_data *keypad; }; -- cgit v1.2.3 From d34541bc48eb7d7cb2ead5ff0284acf65af96f17 Mon Sep 17 00:00:00 2001 From: Olliver Schinagl Date: Wed, 7 Jan 2015 09:44:57 +0100 Subject: gpio: Make the vararg hacks not pass magic values Right now, in consumer.h, there's some vararg hacks that pass 0 as the flags. What actually is passed however is GPIOD_ASIS, which naturally is also 0. Using the define/enum rather then the magic 0 makes it the define more readable to a passer by. Signed-off-by: Olliver Schinagl Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index fd85cb120ee0..45afc2dee560 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -340,31 +340,32 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) * etc. */ #define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags) -#define gpiod_get(varargs...) __gpiod_get(varargs, 0) +#define gpiod_get(varargs...) __gpiod_get(varargs, GPIOD_ASIS) #define __gpiod_get_index(dev, con_id, index, flags, ...) \ __gpiod_get_index(dev, con_id, index, flags) -#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, 0) +#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, GPIOD_ASIS) #define __gpiod_get_optional(dev, con_id, flags, ...) \ __gpiod_get_optional(dev, con_id, flags) -#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, 0) +#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, GPIOD_ASIS) #define __gpiod_get_index_optional(dev, con_id, index, flags, ...) \ __gpiod_get_index_optional(dev, con_id, index, flags) #define gpiod_get_index_optional(varargs...) \ - __gpiod_get_index_optional(varargs, 0) + __gpiod_get_index_optional(varargs, GPIOD_ASIS) #define __devm_gpiod_get(dev, con_id, flags, ...) \ __devm_gpiod_get(dev, con_id, flags) -#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, 0) +#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, GPIOD_ASIS) #define __devm_gpiod_get_index(dev, con_id, index, flags, ...) \ __devm_gpiod_get_index(dev, con_id, index, flags) -#define devm_gpiod_get_index(varargs...) __devm_gpiod_get_index(varargs, 0) +#define devm_gpiod_get_index(varargs...) \ + __devm_gpiod_get_index(varargs, GPIOD_ASIS) #define __devm_gpiod_get_optional(dev, con_id, flags, ...) \ __devm_gpiod_get_optional(dev, con_id, flags) #define devm_gpiod_get_optional(varargs...) \ - __devm_gpiod_get_optional(varargs, 0) + __devm_gpiod_get_optional(varargs, GPIOD_ASIS) #define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...) \ __devm_gpiod_get_index_optional(dev, con_id, index, flags) #define devm_gpiod_get_index_optional(varargs...) \ - __devm_gpiod_get_index_optional(varargs, 0) + __devm_gpiod_get_index_optional(varargs, GPIOD_ASIS) #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) -- cgit v1.2.3 From 5cd37193ce8539be1e6ef76be226f4bcc984e0f5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 13 Dec 2014 20:32:04 -0800 Subject: rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors Although cond_resched_rcu_qs() only applies to TASKS_RCU, it is used in places where it would be useful for it to apply to the normal RCU flavors, rcu_preempt, rcu_sched, and rcu_bh. This is especially the case for workloads that aggressively overload the system, particularly those that generate large numbers of RCU updates on systems running NO_HZ_FULL CPUs. This commit therefore communicates quiescent states from cond_resched_rcu_qs() to the normal RCU flavors. Note that it is unfortunately necessary to leave the old ->passed_quiesce mechanism in place to allow quiescent states that apply to only one flavor to be recorded. (Yes, we could decrement ->rcu_qs_ctr_snap in that case, but that is not so good for debugging of RCU internals.) In addition, if one of the RCU flavor's grace period has stalled, this will invoke rcu_momentary_dyntick_idle(), resulting in a heavy-weight quiescent state visible from other CPUs. Reported-by: Sasha Levin Reported-by: Dave Jones Signed-off-by: Paul E. McKenney [ paulmck: Merge commit from Sasha Levin fixing a bug where __this_cpu() was used in preemptible code. ] --- Documentation/RCU/trace.txt | 32 ++++++++++++++++---------------- include/linux/rcupdate.h | 3 ++- include/linux/rcutiny.h | 5 ++++- include/linux/rcutree.h | 2 ++ kernel/rcu/tree.c | 38 +++++++++++++++++++++++++++++++++----- kernel/rcu/tree.h | 2 ++ kernel/rcu/tree_trace.c | 8 ++++++-- 7 files changed, 65 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index b63b9bb3bc0c..08651da15448 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -56,14 +56,14 @@ rcuboost: The output of "cat rcu/rcu_preempt/rcudata" looks as follows: - 0!c=30455 g=30456 pq=1 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 - 1!c=30719 g=30720 pq=1 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 - 2!c=30150 g=30151 pq=1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 - 3 c=31249 g=31250 pq=1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 - 4!c=29502 g=29503 pq=1 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 - 5 c=31201 g=31202 pq=1 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 - 6!c=30253 g=30254 pq=1 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 - 7 c=31178 g=31178 pq=1 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 + 0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 + 1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 + 2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 + 3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 + 4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 + 5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 + 6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 + 7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 This file has one line per CPU, or eight for this 8-CPU system. The fields are as follows: @@ -188,14 +188,14 @@ o "ca" is the number of RCU callbacks that have been adopted by this Kernels compiled with CONFIG_RCU_BOOST=y display the following from /debug/rcu/rcu_preempt/rcudata: - 0!c=12865 g=12866 pq=1 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 - 1 c=14407 g=14408 pq=1 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 - 2 c=14407 g=14408 pq=1 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 - 3 c=14407 g=14408 pq=1 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 - 4 c=14405 g=14406 pq=1 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 - 5!c=14168 g=14169 pq=1 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 - 6 c=14404 g=14405 pq=1 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 - 7 c=14407 g=14408 pq=1 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 + 0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 + 1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 + 2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 + 3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 + 4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 + 5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 + 6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 + 7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 This is similar to the output discussed above, but contains the following additional fields: diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ed4f5939a452..468228750299 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void) extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ + rcu_all_qs(); \ if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) -#define rcu_note_voluntary_context_switch(t) do { } while (0) +#define rcu_note_voluntary_context_switch(t) rcu_all_qs() #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0e5366200154..fabd3fad8516 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -154,7 +154,10 @@ static inline bool rcu_is_watching(void) return true; } - #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ +static inline void rcu_all_qs(void) +{ +} + #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 52953790dcca..ddba927f7316 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -97,4 +97,6 @@ extern int rcu_scheduler_active __read_mostly; bool rcu_is_watching(void); +void rcu_all_qs(void); + #endif /* __LINUX_RCUTREE_H */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 75ce12316b4c..cb00e038c2f2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -219,6 +219,9 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; +DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); +EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); + /* * Let the RCU core know that this CPU has gone through the scheduler, * which is a quiescent state. This is called when the need for a @@ -288,6 +291,22 @@ void rcu_note_context_switch(void) } EXPORT_SYMBOL_GPL(rcu_note_context_switch); +/* + * Register a quiesecent state for all RCU flavors. If there is an + * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight + * dyntick-idle quiescent state visible to other CPUs (but only for those + * RCU flavors in desparate need of a quiescent state, which will normally + * be none of them). Either way, do a lightweight quiescent state for + * all RCU flavors. + */ +void rcu_all_qs(void) +{ + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + rcu_momentary_dyntick_idle(); + this_cpu_inc(rcu_qs_ctr); +} +EXPORT_SYMBOL_GPL(rcu_all_qs); + static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static long qhimark = 10000; /* If this many pending, ignore blimit. */ static long qlowmark = 100; /* Once only this many pending, use blimit. */ @@ -1609,6 +1628,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); rdp->passed_quiesce = 0; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); ACCESS_ONCE(rdp->gpwrap) = false; @@ -2075,8 +2095,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum || rdp->gpwrap) { + if ((rdp->passed_quiesce == 0 && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || + rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2085,6 +2107,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * within the current grace period. */ rdp->passed_quiesce = 0; /* need qs for new gp. */ + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -2129,7 +2152,8 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (!rdp->passed_quiesce) + if (!rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) return; /* @@ -3174,9 +3198,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->qs_pending && !rdp->passed_quiesce) { + rdp->qs_pending && !rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { rdp->n_rp_qs_pending++; - } else if (rdp->qs_pending && rdp->passed_quiesce) { + } else if (rdp->qs_pending && + (rdp->passed_quiesce || + rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; return 1; } @@ -3510,6 +3537,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->gpnum = rnp->completed; rdp->completed = rnp->completed; rdp->passed_quiesce = 0; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->qs_pending = 0; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7472ff388d55..1e7f8b05714e 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -257,6 +257,8 @@ struct rcu_data { /* in order to detect GP end. */ unsigned long gpnum; /* Highest gp number that this CPU */ /* is aware of having started. */ + unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ + /* for rcu_all_qs() invocations. */ bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 5cdc62e1beeb..fbb6240509ea 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -46,6 +46,8 @@ #define RCU_TREE_NONCORE #include "tree.h" +DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); + static int r_open(struct inode *inode, struct file *file, const struct seq_operations *op) { @@ -115,11 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d", + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->passed_quiesce, rdp->qs_pending); + rdp->passed_quiesce, + rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), + rdp->qs_pending); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, -- cgit v1.2.3 From 076c3b8e03e2737659a89660bb8e54e13587d974 Mon Sep 17 00:00:00 2001 From: James Ban Date: Fri, 16 Jan 2015 12:13:27 +0900 Subject: regulator: da9211: fix unmatched of_node This is a patch for fixing unmatched of_node. Signed-off-by: James Ban Signed-off-by: Mark Brown --- drivers/regulator/da9211-regulator.c | 4 ++-- include/linux/regulator/da9211.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index c78d2106d6cb..8e6957c63a69 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -276,7 +276,7 @@ static struct da9211_pdata *da9211_parse_regulators_dt( continue; pdata->init_data[n] = da9211_matches[i].init_data; - + pdata->reg_node[n] = da9211_matches[i].of_node; n++; } @@ -364,7 +364,7 @@ static int da9211_regulator_init(struct da9211 *chip) config.dev = chip->dev; config.driver_data = chip; config.regmap = chip->regmap; - config.of_node = chip->dev->of_node; + config.of_node = chip->pdata->reg_node[i]; chip->rdev[i] = devm_regulator_register(chip->dev, &da9211_regulators[i], &config); diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index 5479394fefce..d1d9d3849bdb 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -32,6 +32,7 @@ struct da9211_pdata { * 2 : 2 phase 2 buck */ int num_buck; + struct device_node *reg_node[DA9211_MAX_REGULATORS]; struct regulator_init_data *init_data[DA9211_MAX_REGULATORS]; }; #endif -- cgit v1.2.3 From 51e537387990dc1f00752103f314fd135cb94bc6 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 21 Nov 2014 11:24:08 -0700 Subject: PCI: Add flag for devices that don't reset on D3hot->D0 transition Per the PCI Power Management spec r1.2, sec 3.2.4, a device that advertises No_Soft_Reset == 0 in the PMCSR register (reported by lspci as "NoSoftRst-") should perform an internal reset when transitioning from D3hot to D0 via software control. Configuration context is lost and the device requires a full reinitialization sequence. Unfortunately the definition of "internal reset", beyond the application of the configuration context, is largely left to the interpretation of the specific device. Some devices don't seem to perform an "internal reset" even if they report No_Soft_Reset == 0. We still need to honor the PCI specification and restore PCI config context in the event that we do a PM reset, so we don't cache and modify the PCI_PM_CTRL_NO_SOFT_RESET bit for the device, but for interfaces where the intention is to reset the device, like pci_reset_function(), we need a mechanism to flag that PM reset (a D3hot->D0 transition) doesn't perform any significant "internal reset" of the device. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 2 +- include/linux/pci.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e9d4fd861ba1..422bc0179e90 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3197,7 +3197,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) { u16 csr; - if (!dev->pm_cap) + if (!dev->pm_cap || dev->dev_flags & PCI_DEV_FLAGS_NO_PM_RESET) return -ENOTTY; pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &csr); diff --git a/include/linux/pci.h b/include/linux/pci.h index 44627f1df4ca..7bed32b3fd54 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -177,6 +177,8 @@ enum pci_dev_flags { PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), /* Do not use bus resets for device */ PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), + /* Do not use PM reset even if device advertises NoSoftRst- */ + PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 6dee60f69d48fcef021b4b53b3431797ec440764 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add new struct list_head to struct file_lock ...that we can use to queue file_locks to per-ctx list_heads. Go ahead and convert locks_delete_lock and locks_dispose_list to use it instead of the fl_block list. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 8 +++++--- include/linux/fs.h | 1 + 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index 59e2f905e4ff..bfe5f17401de 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -207,6 +207,7 @@ static struct kmem_cache *filelock_cache __read_mostly; static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); + INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_block); init_waitqueue_head(&fl->fl_wait); } @@ -243,6 +244,7 @@ EXPORT_SYMBOL_GPL(locks_release_private); void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_block)); BUG_ON(!hlist_unhashed(&fl->fl_link)); @@ -257,8 +259,8 @@ locks_dispose_list(struct list_head *dispose) struct file_lock *fl; while (!list_empty(dispose)) { - fl = list_first_entry(dispose, struct file_lock, fl_block); - list_del_init(&fl->fl_block); + fl = list_first_entry(dispose, struct file_lock, fl_list); + list_del_init(&fl->fl_list); locks_free_lock(fl); } } @@ -691,7 +693,7 @@ static void locks_delete_lock(struct file_lock **thisfl_p, locks_unlink_lock(thisfl_p); if (dispose) - list_add(&fl->fl_block, dispose); + list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..cd6818115162 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -934,6 +934,7 @@ int locks_in_grace(struct net *); */ struct file_lock { struct file_lock *fl_next; /* singly linked list for this inode */ + struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; -- cgit v1.2.3 From 4a075e39c86490cc0f0c10ac6abe3592d1689463 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add a new struct file_locking_context pointer to struct inode The current scheme of using the i_flock list is really difficult to manage. There is also a legitimate desire for a per-inode spinlock to manage these lists that isn't the i_lock. Start conversion to a new scheme to eventually replace the old i_flock list with a new "file_lock_context" object. We start by adding a new i_flctx to struct inode. For now, it lives in parallel with i_flock list, but will eventually replace it. The idea is to allocate a structure to sit in that pointer and act as a locus for all things file locking. We allocate a file_lock_context for an inode when the first lock is added to it, and it's only freed when the inode is freed. We use the i_lock to protect the assignment, but afterward it should mostly be accessed locklessly. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/inode.c | 3 ++- fs/locks.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 11 +++++++++++ 3 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..f30872ade6d7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif - + inode->i_flctx = NULL; this_cpu_inc(nr_inodes); return 0; @@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode) BUG_ON(inode_has_buffers(inode)); security_inode_free(inode); fsnotify_inode_delete(inode); + locks_free_lock_context(inode->i_flctx); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); diff --git a/fs/locks.c b/fs/locks.c index ae1e7cf721d6..526d5fca67c8 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -202,8 +202,49 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); */ static DEFINE_SPINLOCK(blocked_lock_lock); +static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; +static struct file_lock_context * +locks_get_lock_context(struct inode *inode) +{ + struct file_lock_context *new; + + if (likely(inode->i_flctx)) + goto out; + + new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!new) + goto out; + + INIT_LIST_HEAD(&new->flc_flock); + + /* + * Assign the pointer if it's not already assigned. If it is, then + * free the context we just allocated. + */ + spin_lock(&inode->i_lock); + if (likely(!inode->i_flctx)) { + inode->i_flctx = new; + new = NULL; + } + spin_unlock(&inode->i_lock); + + if (new) + kmem_cache_free(flctx_cache, new); +out: + return inode->i_flctx; +} + +void +locks_free_lock_context(struct file_lock_context *ctx) +{ + if (ctx) { + WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + kmem_cache_free(flctx_cache, ctx); + } +} + static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); @@ -2636,6 +2677,9 @@ static int __init filelock_init(void) { int i; + flctx_cache = kmem_cache_create("file_lock_ctx", + sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); + filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); diff --git a/include/linux/fs.h b/include/linux/fs.h index cd6818115162..dec0d38b05de 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -626,6 +626,7 @@ struct inode { #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; + struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { @@ -965,6 +966,10 @@ struct file_lock { } fl_u; }; +struct file_lock_context { + struct list_head flc_flock; +}; + /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) @@ -991,6 +996,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ +void locks_free_lock_context(struct file_lock_context *ctx); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); @@ -1048,6 +1054,11 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline void +locks_free_lock_context(struct file_lock_context *ctx) +{ +} + static inline void locks_init_lock(struct file_lock *fl) { return; -- cgit v1.2.3 From bd61e0a9c852de2d705b6f1bb2cc54c5774db570 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert posix locks to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 58 +++++++++++++--------------- fs/cifs/file.c | 26 +++++-------- fs/lockd/svcsubs.c | 20 ++++++---- fs/locks.c | 108 +++++++++++++++++++++++++++------------------------- fs/nfs/delegation.c | 28 +++++--------- fs/nfs/nfs4state.c | 52 +++++-------------------- fs/nfs/pagelist.c | 8 ++-- fs/nfs/write.c | 30 +++++++-------- fs/nfsd/nfs4state.c | 18 +++++---- fs/read_write.c | 2 +- include/linux/fs.h | 3 +- 11 files changed, 155 insertions(+), 198 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 917656ea8dcf..19beeed83233 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -253,18 +253,15 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) *fcntl_count = 0; *flock_count = 0; - spin_lock(&inode->i_lock); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) - ++(*fcntl_count); - } - ctx = inode->i_flctx; if (ctx) { + spin_lock(&inode->i_lock); + list_for_each_entry(lock, &ctx->flc_posix, fl_list) + ++(*fcntl_count); list_for_each_entry(lock, &ctx->flc_flock, fl_list) ++(*flock_count); + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); } @@ -279,7 +276,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; - struct file_lock_context *ctx; + struct file_lock_context *ctx = inode->i_flctx; int err = 0; int seen_fcntl = 0; int seen_flock = 0; @@ -288,34 +285,31 @@ int ceph_encode_locks_to_buffer(struct inode *inode, dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); + if (!ctx) + return 0; + spin_lock(&inode->i_lock); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) { - ++seen_fcntl; - if (seen_fcntl > num_fcntl_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_fcntl; + if (seen_fcntl > num_fcntl_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } - - ctx = inode->i_flctx; - if (ctx) { - list_for_each_entry(lock, &ctx->flc_flock, fl_list) { - ++seen_flock; - if (seen_flock > num_flock_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_flock; + if (seen_flock > num_flock_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } fail: spin_unlock(&inode->i_lock); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 96b7e9b7706d..ea78f6f81ce2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1109,11 +1109,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } -/* copied from fs/locks.c with a name change */ -#define cifs_for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; \ - lockp = &(*lockp)->fl_next) - struct lock_to_push { struct list_head llist; __u64 offset; @@ -1128,8 +1123,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) { struct inode *inode = cfile->dentry->d_inode; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct file_lock *flock, **before; - unsigned int count = 0, i = 0; + struct file_lock *flock; + struct file_lock_context *flctx = inode->i_flctx; + unsigned int count = 0, i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1137,10 +1133,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) xid = get_xid(); + if (!flctx) + goto out; + spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - if ((*before)->fl_flags & FL_POSIX) - count++; + list_for_each(el, &flctx->flc_posix) { + count++; } spin_unlock(&inode->i_lock); @@ -1151,7 +1149,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) * added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (; i < count; i++) { + for (i = 0; i < count; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; @@ -1162,10 +1160,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) el = locks_to_send.next; spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - flock = *before; - if ((flock->fl_flags & FL_POSIX) == 0) - continue; + list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* * The list ended. We don't have enough allocated @@ -1185,7 +1180,6 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->length = length; lck->type = type; lck->offset = flock->fl_start; - el = el->next; } spin_unlock(&inode->i_lock); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d12ff4e2dbe7..5300bb53835f 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; struct nlm_host *lockhost; + if (!flctx || list_empty_careful(&flctx->flc_posix)) + return 0; again: file->f_locks = 0; spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { - if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); - return 1; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&inode->i_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_lmops == &nlmsvc_lock_operations) { + spin_unlock(&inode->i_lock); + return 1; + } } + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); file->f_locks = 0; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 055df53f19de..e50bb4d9e757 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -157,9 +157,6 @@ static int target_leasetype(struct file_lock *fl) int leases_enable = 1; int lease_break_time = 45; -#define for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next) - /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via @@ -218,6 +215,7 @@ locks_get_lock_context(struct inode *inode) goto out; INIT_LIST_HEAD(&new->flc_flock); + INIT_LIST_HEAD(&new->flc_posix); /* * Assign the pointer if it's not already assigned. If it is, then @@ -241,6 +239,7 @@ locks_free_lock_context(struct file_lock_context *ctx) { if (ctx) { WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); kmem_cache_free(flctx_cache, ctx); } } @@ -809,21 +808,26 @@ void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + struct file_lock_context *ctx; struct inode *inode = file_inode(filp); + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) { + fl->fl_type = F_UNLCK; + return; + } + spin_lock(&inode->i_lock); - for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) { - if (!IS_POSIX(cfl)) - continue; - if (posix_locks_conflict(fl, cfl)) - break; + list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { + if (posix_locks_conflict(fl, cfl)) { + locks_copy_conflock(fl, cfl); + if (cfl->fl_nspid) + fl->fl_pid = pid_vnr(cfl->fl_nspid); + goto out; + } } - if (cfl) { - locks_copy_conflock(fl, cfl); - if (cfl->fl_nspid) - fl->fl_pid = pid_vnr(cfl->fl_nspid); - } else - fl->fl_type = F_UNLCK; + fl->fl_type = F_UNLCK; +out: spin_unlock(&inode->i_lock); return; } @@ -983,16 +987,20 @@ out: static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { - struct file_lock *fl; + struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; - struct file_lock **before; + struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. @@ -1013,8 +1021,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { - for_each_lock(inode, before) { - fl = *before; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!IS_POSIX(fl)) continue; if (!posix_locks_conflict(request, fl)) @@ -1044,29 +1051,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (request->fl_flags & FL_ACCESS) goto out; - /* - * Find the first old lock with the same owner as the new lock. - */ - - before = &inode->i_flock; - - /* First skip locks owned by other processes. */ - while ((fl = *before) && (!IS_POSIX(fl) || - !posix_same_owner(request, fl))) { - before = &fl->fl_next; + /* Find the first old lock with the same owner as the new lock */ + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { + if (posix_same_owner(request, fl)) + break; } /* Process locks with this owner. */ - while ((fl = *before) && posix_same_owner(request, fl)) { - /* Detect adjacent or overlapping regions (if same lock type) - */ + list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { + if (!posix_same_owner(request, fl)) + break; + + /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) - goto next_lock; + continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ @@ -1087,18 +1090,17 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); continue; } request = fl; added = true; - } - else { + } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) - goto next_lock; + continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) @@ -1117,7 +1119,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); continue; } /* @@ -1133,15 +1135,11 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_delete_lock(before, &dispose); - locks_insert_lock(before, request); + locks_insert_lock_ctx(request, &fl->fl_list); + locks_delete_lock_ctx(fl, &dispose); added = true; } } - /* Go on to next lock. - */ - next_lock: - before = &fl->fl_next; } /* @@ -1166,7 +1164,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &fl->fl_list); new_fl = NULL; } if (right) { @@ -1177,7 +1175,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock(before, left); + locks_insert_lock_ctx(left, &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1257,22 +1255,29 @@ EXPORT_SYMBOL(posix_lock_file_wait); */ int locks_mandatory_locked(struct file *file) { + int ret; struct inode *inode = file_inode(file); + struct file_lock_context *ctx; struct file_lock *fl; + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) + return 0; + /* * Search the lock list for this inode for any POSIX locks. */ spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!IS_POSIX(fl)) - continue; + ret = 0; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && - fl->fl_owner != file) + fl->fl_owner != file) { + ret = -EAGAIN; break; + } } spin_unlock(&inode->i_lock); - return fl ? -EAGAIN : 0; + return ret; } /** @@ -2389,13 +2394,14 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { struct file_lock lock; + struct file_lock_context *ctx = file_inode(filp)->i_flctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - if (!file_inode(filp)->i_flock) + if (!ctx || list_empty(&ctx->flc_posix)) return; lock.fl_type = F_UNLCK; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 9f9f67b17e2b..3fb1caa3874d 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,17 +85,17 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ { struct inode *inode = state->inode; struct file_lock *fl; - struct file_lock_context *flctx; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; int status = 0; - if (inode->i_flock == NULL && inode->i_flctx == NULL) + if (flctx == NULL) goto out; - /* Protect inode->i_flock using the i_lock */ + list = &flctx->flc_posix; spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX))) - continue; +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; spin_unlock(&inode->i_lock); @@ -104,19 +104,9 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ goto out; spin_lock(&inode->i_lock); } - - flctx = inode->i_flctx; - if (flctx) { - list_for_each_entry(fl, &flctx->flc_flock, fl_list) { - if (nfs_file_open_context(fl->fl_file) != ctx) - continue; - spin_unlock(&inode->i_lock); - status = nfs4_lock_delegation_recall(fl, state, - stateid); - if (status < 0) - goto out; - spin_lock(&inode->i_lock); - } + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; } spin_unlock(&inode->i_lock); out: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 65c404bf61ae..6084c267f3a0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1367,53 +1367,18 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct file_lock *fl; int status = 0; struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; - if (inode->i_flock == NULL && flctx == NULL) + if (flctx == NULL) return 0; + list = &flctx->flc_posix; + /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - /* Protect inode->i_flock using the BKL */ spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & FL_POSIX)) - continue; - if (nfs_file_open_context(fl->fl_file)->state != state) - continue; - spin_unlock(&inode->i_lock); - status = ops->recover_lock(state, fl); - switch (status) { - case 0: - break; - case -ESTALE: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_NO_GRACE: - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - goto out; - default: - printk(KERN_ERR "NFS: %s: unhandled error %d\n", - __func__, status); - case -ENOMEM: - case -NFS4ERR_DENIED: - case -NFS4ERR_RECLAIM_BAD: - case -NFS4ERR_RECLAIM_CONFLICT: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ - status = 0; - } - spin_lock(&inode->i_lock); - } - - if (!flctx) - goto out_unlock; - - list_for_each_entry(fl, &flctx->flc_flock, fl_list) { +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; spin_unlock(&inode->i_lock); @@ -1445,7 +1410,10 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ } spin_lock(&inode->i_lock); } -out_unlock: + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } spin_unlock(&inode->i_lock); out: up_write(&nfsi->rwsem); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index a3b62e15b444..29c7f33c9cf1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -831,12 +831,10 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, if (prev) { if (!nfs_match_open_context(req->wb_context, prev->wb_context)) return false; - if (req->wb_context->dentry->d_inode->i_flock != NULL && - !nfs_match_lock_context(req->wb_lock_context, - prev->wb_lock_context)) - return false; flctx = req->wb_context->dentry->d_inode->i_flctx; - if (flctx != NULL && !list_empty_careful(&flctx->flc_flock) && + if (flctx != NULL && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock)) && !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e072aeb34195..784c13485b3f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct nfs_lock_context *l_ctx; + struct file_lock_context *flctx = file_inode(file)->i_flctx; struct nfs_page *req; int do_flush, status; /* @@ -1109,12 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page) do_flush = req->wb_page != page || req->wb_context != ctx; /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; - if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { - do_flush |= l_ctx->lockowner.l_owner != current->files - || l_ctx->lockowner.l_pid != current->tgid; - } - if (l_ctx && ctx->dentry->d_inode->i_flctx && - !list_empty_careful(&ctx->dentry->d_inode->i_flctx->flc_flock)) { + if (l_ctx && flctx && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock))) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } @@ -1202,26 +1200,24 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (!inode->i_flock && !flctx) + if (!flctx || (list_empty_careful(&flctx->flc_flock) && + list_empty_careful(&flctx->flc_posix))) return 0; /* Check to see if there are whole file write locks */ - spin_lock(&inode->i_lock); ret = 0; - - fl = inode->i_flock; - if (fl && is_whole_file_wrlock(fl)) { - ret = 1; - goto out; - } - - if (!list_empty(&flctx->flc_flock)) { + spin_lock(&inode->i_lock); + if (!list_empty(&flctx->flc_posix)) { + fl = list_first_entry(&flctx->flc_posix, struct file_lock, + fl_list); + if (is_whole_file_wrlock(fl)) + ret = 1; + } else if (!list_empty(&flctx->flc_flock)) { fl = list_first_entry(&flctx->flc_flock, struct file_lock, fl_list); if (fl->fl_type == F_WRLCK) ret = 1; } -out: spin_unlock(&inode->i_lock); return ret; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c06a1ba80d73..fad821991369 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5556,10 +5556,11 @@ out_nfserr: static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { - struct file_lock **flpp; + struct file_lock *fl; int status = false; struct file *filp = find_any_file(fp); struct inode *inode; + struct file_lock_context *flctx; if (!filp) { /* Any valid lock stateid should have some sort of access */ @@ -5568,15 +5569,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } inode = file_inode(filp); + flctx = inode->i_flctx; - spin_lock(&inode->i_lock); - for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { - if ((*flpp)->fl_owner == (fl_owner_t)lowner) { - status = true; - break; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&inode->i_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_owner == (fl_owner_t)lowner) { + status = true; + break; + } } + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); fput(filp); return status; } diff --git a/fs/read_write.c b/fs/read_write.c index c0805c93b6fa..4060691e78f7 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t return retval; } - if (unlikely(inode->i_flock && mandatory_lock(inode))) { + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { retval = locks_mandatory_area( read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); diff --git a/include/linux/fs.h b/include/linux/fs.h index dec0d38b05de..571f113588e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; + struct list_head flc_posix; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1971,7 +1972,7 @@ static inline int locks_verify_truncate(struct inode *inode, struct file *filp, loff_t size) { - if (inode->i_flock && mandatory_lock(inode)) + if (inode->i_flctx && mandatory_lock(inode)) return locks_mandatory_area( FLOCK_VERIFY_WRITE, inode, filp, size < inode->i_size ? size : inode->i_size, -- cgit v1.2.3 From 8634b51f6ca298fb8b07aa4847340764903533ab Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert lease handling to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 252 +++++++++++++++++++++-------------------------------- include/linux/fs.h | 5 +- 2 files changed, 102 insertions(+), 155 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index e50bb4d9e757..d46e70567b99 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -216,6 +216,7 @@ locks_get_lock_context(struct inode *inode) INIT_LIST_HEAD(&new->flc_flock); INIT_LIST_HEAD(&new->flc_posix); + INIT_LIST_HEAD(&new->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then @@ -240,6 +241,7 @@ locks_free_lock_context(struct file_lock_context *ctx) if (ctx) { WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); + WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); kmem_cache_free(flctx_cache, ctx); } } @@ -677,22 +679,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker) spin_unlock(&blocked_lock_lock); } -/* Insert file lock fl into an inode's lock list at the position indicated - * by pos. At the same time add the lock to the global file lock list. - * - * Must be called with the i_lock held! - */ -static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) -{ - fl->fl_nspid = get_pid(task_tgid(current)); - - /* insert into file's list */ - fl->fl_next = *pos; - *pos = fl; - - locks_insert_global_locks(fl); -} - static void locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) { @@ -701,63 +687,28 @@ locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) locks_insert_global_locks(fl); } -/** - * locks_delete_lock - Delete a lock and then free it. - * @thisfl_p: pointer that points to the fl_next field of the previous - * inode->i_flock list entry - * - * Unlink a lock from all lists and free the namespace reference, but don't - * free it yet. Wake up processes that are blocked waiting for this lock and - * notify the FS that the lock has been cleared. - * - * Must be called with the i_lock held! - */ -static void locks_unlink_lock(struct file_lock **thisfl_p) +static void +locks_unlink_lock_ctx(struct file_lock *fl) { - struct file_lock *fl = *thisfl_p; - locks_delete_global_locks(fl); - - *thisfl_p = fl->fl_next; - fl->fl_next = NULL; - + list_del_init(&fl->fl_list); if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; } - locks_wake_up_blocks(fl); } -/* - * Unlink a lock from all lists and free it. - * - * Must be called with i_lock held! - */ -static void locks_delete_lock(struct file_lock **thisfl_p, - struct list_head *dispose) +static void +locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) { - struct file_lock *fl = *thisfl_p; - - locks_unlink_lock(thisfl_p); + locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } -static void -locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) -{ - locks_delete_global_locks(fl); - if (fl->fl_nspid) { - put_pid(fl->fl_nspid); - fl->fl_nspid = NULL; - } - locks_wake_up_blocks(fl); - list_move(&fl->fl_list, dispose); -} - /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ @@ -1376,7 +1327,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock(before, dispose); + locks_delete_lock_ctx(fl, dispose); } return 0; } @@ -1392,20 +1343,17 @@ static bool past_time(unsigned long then) static void time_out_leases(struct inode *inode, struct list_head *dispose) { - struct file_lock **before; - struct file_lock *fl; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; lockdep_assert_held(&inode->i_lock); - before = &inode->i_flock; - while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(before, F_RDLCK, dispose); + lease_modify(&fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(before, F_UNLCK, dispose); - if (fl == *before) /* lease_modify may have freed fl */ - before = &fl->fl_next; + lease_modify(&fl, F_UNLCK, dispose); } } @@ -1419,11 +1367,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { + struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; lockdep_assert_held(&inode->i_lock); - for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } @@ -1447,7 +1396,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock *new_fl; - struct file_lock *fl, **before; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1457,6 +1407,12 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return PTR_ERR(new_fl); new_fl->fl_flags = type; + /* typically we will check that ctx is non-NULL before calling */ + if (!ctx) { + WARN_ON_ONCE(1); + return error; + } + spin_lock(&inode->i_lock); time_out_leases(inode, &dispose); @@ -1471,9 +1427,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { @@ -1482,17 +1436,16 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { - if (lease_breaking(inode->i_flock)) + if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); } - fl = inode->i_flock; - if (!fl || !IS_LEASE(fl)) + if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { @@ -1502,12 +1455,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) } restart: - break_time = inode->i_flock->fl_break_time; + fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); + break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; - locks_insert_block(inode->i_flock, new_fl); + locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); @@ -1525,10 +1479,8 @@ restart: time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; - error = 0; } - out: spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); @@ -1550,13 +1502,17 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock *flock; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; - if (inode->i_flock) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&inode->i_lock); - flock = inode->i_flock; - if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK)) - has_lease = true; + if (!list_empty(&ctx->flc_lease)) { + fl = list_first_entry(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl->fl_type == F_WRLCK) + has_lease = true; + } spin_unlock(&inode->i_lock); } @@ -1595,20 +1551,22 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; int type = F_UNLCK; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(file_inode(filp), &dispose); - for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl); - fl = fl->fl_next) { - if (fl->fl_file == filp) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&inode->i_lock); + time_out_leases(file_inode(filp), &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file != filp) + continue; type = target_leasetype(fl); break; } + spin_unlock(&inode->i_lock); + locks_dispose_list(&dispose); } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); return type; } @@ -1641,9 +1599,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg) static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct file_lock *fl, **before, **my_before = NULL, *lease; + struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); @@ -1651,6 +1610,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock @@ -1684,13 +1647,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * except for this filp. */ error = -EAGAIN; - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { - my_before = before; + my_fl = fl; continue; } + /* * No exclusive leases if someone else has a lease on * this file: @@ -1705,9 +1667,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr goto out; } - if (my_before != NULL) { - lease = *my_before; - error = lease->fl_lmops->lm_change(my_before, arg, &dispose); + if (my_fl != NULL) { + error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1717,7 +1678,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock(before, lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1729,8 +1690,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr */ smp_mb(); error = check_conflicting_open(dentry, arg); - if (error) - goto out_unlink; + if (error) { + locks_unlink_lock_ctx(lease); + goto out; + } out_setup: if (lease->fl_lmops->lm_setup) @@ -1740,33 +1703,35 @@ out: locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); - if (!error && !my_before) + if (!error && !my_fl) *flp = NULL; return error; -out_unlink: - locks_unlink_lock(before); - goto out; } static int generic_delete_lease(struct file *filp) { int error = -EAGAIN; - struct file_lock *fl, **before; + struct file_lock *fl, *victim = NULL; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx = inode->i_flctx; LIST_HEAD(dispose); + if (!ctx) { + trace_generic_delete_lease(inode, NULL); + return error; + } + spin_lock(&inode->i_lock); - time_out_leases(inode, &dispose); - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { - if (fl->fl_file == filp) + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp) { + victim = fl; break; + } } trace_generic_delete_lease(inode, fl); - if (fl && IS_LEASE(fl)) - error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose); + if (victim) + error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); return error; @@ -2447,56 +2412,37 @@ locks_remove_flock(struct file *filp) fl.fl_ops->fl_release_private(&fl); } +static void +locks_remove_lease(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; + LIST_HEAD(dispose); + + if (!ctx || list_empty(&ctx->flc_lease)) + return; + + spin_lock(&inode->i_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + lease_modify(&fl, F_UNLCK, &dispose); + spin_unlock(&inode->i_lock); + locks_dispose_list(&dispose); +} + /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { - struct inode * inode = file_inode(filp); - struct file_lock *fl; - struct file_lock **before; - LIST_HEAD(dispose); - /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp); - if (!inode->i_flock) - return; - - spin_lock(&inode->i_lock); - before = &inode->i_flock; - - while ((fl = *before) != NULL) { - if (fl->fl_file == filp) { - if (IS_LEASE(fl)) { - lease_modify(before, F_UNLCK, &dispose); - continue; - } - - /* - * There's a leftover lock on the list of a type that - * we didn't expect to see. Most likely a classic - * POSIX lock that ended up not getting released - * properly, or that raced onto the list somehow. Log - * some info about it and then just remove it from - * the list. - */ - WARN(1, "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), inode->i_ino, - fl->fl_type, fl->fl_flags, - fl->fl_start, fl->fl_end); - - locks_delete_lock(before, &dispose); - continue; - } - before = &fl->fl_next; - } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); + /* remove any leases */ + locks_remove_lease(filp); } /** diff --git a/include/linux/fs.h b/include/linux/fs.h index 571f113588e9..2ddec3cf81b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -969,6 +969,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; + struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1990,7 +1991,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } @@ -2003,7 +2004,7 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } -- cgit v1.2.3 From a7231a97467d5a0c36f82f581c76c12c034e4b80 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:56 -0500 Subject: locks: remove i_flock field from struct inode Nothing uses it anymore. Also add a forward declaration for struct file_lock to silence some compiler warnings that the removal triggers. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2ddec3cf81b9..ce0873af0b97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -625,7 +625,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ - struct file_lock *i_flock; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; @@ -886,6 +885,8 @@ static inline struct file *get_file(struct file *f) /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; +struct file_lock; + struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); -- cgit v1.2.3 From 6109c85037e53443f29fd39c0de69f578a1cf285 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: add a dedicated spinlock to protect i_flctx lists We can now add a dedicated spinlock without expanding struct inode. Change to using that to protect the various i_flctx lists. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 8 ++--- fs/cifs/file.c | 8 ++--- fs/lockd/svcsubs.c | 12 ++++---- fs/locks.c | 87 +++++++++++++++++++++++++++-------------------------- fs/nfs/delegation.c | 8 ++--- fs/nfs/nfs4state.c | 8 ++--- fs/nfs/write.c | 4 +-- fs/nfsd/nfs4state.c | 4 +-- include/linux/fs.h | 1 + 9 files changed, 71 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 19beeed83233..0303da8e3233 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -255,12 +255,12 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) ctx = inode->i_flctx; if (ctx) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(lock, &ctx->flc_posix, fl_list) ++(*fcntl_count); list_for_each_entry(lock, &ctx->flc_flock, fl_list) ++(*flock_count); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); @@ -288,7 +288,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, if (!ctx) return 0; - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(lock, &ctx->flc_flock, fl_list) { ++seen_fcntl; if (seen_fcntl > num_fcntl_locks) { @@ -312,7 +312,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, ++l; } fail: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return err; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index ea78f6f81ce2..b65166eb111e 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1136,11 +1136,11 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) if (!flctx) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each(el, &flctx->flc_posix) { count++; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); INIT_LIST_HEAD(&locks_to_send); @@ -1159,7 +1159,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) } el = locks_to_send.next; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* @@ -1181,7 +1181,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->type = type; lck->offset = flock->fl_start; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { int stored_rc; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 5300bb53835f..665ef5a05183 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -171,7 +171,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, return 0; again: file->f_locks = 0; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -183,7 +183,7 @@ again: if (match(lockhost, host)) { struct file_lock lock = *fl; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; @@ -195,7 +195,7 @@ again: goto again; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 0; } @@ -232,14 +232,14 @@ nlm_file_inuse(struct nlm_file *file) return 1; if (flctx && !list_empty_careful(&flctx->flc_posix)) { - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 1; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); } file->f_locks = 0; return 0; diff --git a/fs/locks.c b/fs/locks.c index d46e70567b99..a268d959ccd6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -161,7 +161,7 @@ int lease_break_time = 45; * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via * the file_lock_lglock. Note that alterations to the list also require that - * the relevant i_lock is held. + * the relevant flc_lock is held. */ DEFINE_STATIC_LGLOCK(file_lock_lglock); static DEFINE_PER_CPU(struct hlist_head, file_lock_list); @@ -189,13 +189,13 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); * contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, - * we often hold the i_lock as well. In certain cases, when reading the fields + * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the - * i_lock. + * flc_lock. * * In particular, adding an entry to the fl_block list requires that you hold - * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting - * an entry from the list however only requires the file_lock_lock. + * both the flc_lock and the blocked_lock_lock (acquired in that order). + * Deleting an entry from the list however only requires the file_lock_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); @@ -214,6 +214,7 @@ locks_get_lock_context(struct inode *inode) if (!new) goto out; + spin_lock_init(&new->flc_lock); INIT_LIST_HEAD(&new->flc_flock); INIT_LIST_HEAD(&new->flc_posix); INIT_LIST_HEAD(&new->flc_lease); @@ -557,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) return fl1->fl_owner == fl2->fl_owner; } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { lg_local_lock(&file_lock_lglock); @@ -566,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl) lg_local_unlock(&file_lock_lglock); } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { /* * Avoid taking lock if already unhashed. This is safe since this check - * is done while holding the i_lock, and new insertions into the list + * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) @@ -623,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter) * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * - * Must be called with both the i_lock and blocked_lock_lock held. The fl_block - * list itself is protected by the blocked_lock_lock, but by ensuring that the - * i_lock is also held on insertions we can avoid taking the blocked_lock_lock - * in some cases when we see that the fl_block list is empty. + * Must be called with both the flc_lock and blocked_lock_lock held. The + * fl_block list itself is protected by the blocked_lock_lock, but by ensuring + * that the flc_lock is also held on insertions we can avoid taking the + * blocked_lock_lock in some cases when we see that the fl_block list is empty. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) @@ -638,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker, locks_insert_global_blocked(waiter); } -/* Must be called with i_lock held. */ +/* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) { @@ -650,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker, /* * Wake up processes blocked waiting for blocker. * - * Must be called with the inode->i_lock held! + * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new - * blocked requests are only added to the list under the i_lock, and - * the i_lock is always held here. Note that removal from the fl_block - * list does not require the i_lock, so we must recheck list_empty() + * blocked requests are only added to the list under the flc_lock, and + * the flc_lock is always held here. Note that removal from the fl_block + * list does not require the flc_lock, so we must recheck list_empty() * after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_block)) @@ -768,7 +769,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) return; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { if (posix_locks_conflict(fl, cfl)) { locks_copy_conflock(fl, cfl); @@ -779,7 +780,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) } fl->fl_type = F_UNLCK; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); @@ -880,7 +881,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) return -ENOMEM; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -905,9 +906,9 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) { - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); cond_resched(); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); } find_conflict: @@ -929,7 +930,7 @@ find_conflict: error = 0; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -965,7 +966,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the @@ -1136,7 +1137,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); /* * Free any unused locks. */ @@ -1218,7 +1219,7 @@ int locks_mandatory_locked(struct file *file) /* * Search the lock list for this inode for any POSIX locks. */ - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); ret = 0; list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && @@ -1227,7 +1228,7 @@ int locks_mandatory_locked(struct file *file) break; } } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return ret; } @@ -1346,7 +1347,7 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); @@ -1370,7 +1371,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) @@ -1413,7 +1414,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1463,11 +1464,11 @@ restart: break_time++; locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { @@ -1482,7 +1483,7 @@ restart: error = 0; } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1506,14 +1507,14 @@ void lease_get_mtime(struct inode *inode, struct timespec *time) struct file_lock *fl; if (ctx && !list_empty_careful(&ctx->flc_lease)) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (!list_empty(&ctx->flc_lease)) { fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); if (fl->fl_type == F_WRLCK) has_lease = true; } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); } if (has_lease) @@ -1556,7 +1557,7 @@ int fcntl_getlease(struct file *filp) LIST_HEAD(dispose); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(file_inode(filp), &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file != filp) @@ -1564,7 +1565,7 @@ int fcntl_getlease(struct file *filp) type = target_leasetype(fl); break; } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } return type; @@ -1632,7 +1633,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg); if (error) @@ -1699,7 +1700,7 @@ out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); @@ -1722,7 +1723,7 @@ static int generic_delete_lease(struct file *filp) return error; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { victim = fl; @@ -1732,7 +1733,7 @@ static int generic_delete_lease(struct file *filp) trace_generic_delete_lease(inode, fl); if (victim) error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; } @@ -2423,10 +2424,10 @@ locks_remove_lease(struct file *filp) if (!ctx || list_empty(&ctx->flc_lease)) return; - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) lease_modify(&fl, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 3fb1caa3874d..8cdb2b28a104 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -93,22 +93,22 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ goto out; list = &flctx->flc_posix; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); restart: list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = nfs4_lock_delegation_recall(fl, state, stateid); if (status < 0) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } if (list == &flctx->flc_posix) { list = &flctx->flc_flock; goto restart; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); out: return status; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 6084c267f3a0..a3bb22ab68c5 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1376,12 +1376,12 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); restart: list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = ops->recover_lock(state, fl); switch (status) { case 0: @@ -1408,13 +1408,13 @@ restart: /* kill_proc(fl->fl_pid, SIGLOST, 1); */ status = 0; } - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } if (list == &flctx->flc_posix) { list = &flctx->flc_flock; goto restart; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); out: up_write(&nfsi->rwsem); return status; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 784c13485b3f..4ae66f416eb9 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1206,7 +1206,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino /* Check to see if there are whole file write locks */ ret = 0; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); if (!list_empty(&flctx->flc_posix)) { fl = list_first_entry(&flctx->flc_posix, struct file_lock, fl_list); @@ -1218,7 +1218,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino if (fl->fl_type == F_WRLCK) ret = 1; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return ret; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fad821991369..80242f5bd621 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5572,14 +5572,14 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) flctx = inode->i_flctx; if (flctx && !list_empty_careful(&flctx->flc_posix)) { - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_owner == (fl_owner_t)lowner) { status = true; break; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); } fput(filp); return status; diff --git a/include/linux/fs.h b/include/linux/fs.h index ce0873af0b97..32eafa9b5c9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { }; struct file_lock_context { + spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; -- cgit v1.2.3 From 7448cc37b1a6b620d948aaee3bb30960c06d5d5d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: clean up the lm_change prototype Now that we use standard list_heads for tracking leases, we can have lm_change take a pointer to the lease to be modified instead of a double pointer. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 13 ++++++------- fs/nfsd/nfs4state.c | 3 ++- include/linux/fs.h | 6 +++--- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index a268d959ccd6..864f2460a0ad 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1309,9 +1309,8 @@ static void lease_clear_pending(struct file_lock *fl, int arg) } /* We already had a lease on this file; just change its type */ -int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) +int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { - struct file_lock *fl = *before; int error = assign_type(fl, arg); if (error) @@ -1352,9 +1351,9 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(&fl, F_RDLCK, dispose); + lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(&fl, F_UNLCK, dispose); + lease_modify(fl, F_UNLCK, dispose); } } @@ -1669,7 +1668,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr } if (my_fl != NULL) { - error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose); + error = lease->fl_lmops->lm_change(my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1732,7 +1731,7 @@ static int generic_delete_lease(struct file *filp) } trace_generic_delete_lease(inode, fl); if (victim) - error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; @@ -2426,7 +2425,7 @@ locks_remove_lease(struct file *filp) spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) - lease_modify(&fl, F_UNLCK, &dispose); + lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 80242f5bd621..532a60cca2fb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) } static int -nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose) +nfsd_change_deleg_cb(struct file_lock *onlist, int arg, + struct list_head *dispose) { if (arg & F_UNLCK) return lease_modify(onlist, arg, dispose); diff --git a/include/linux/fs.h b/include/linux/fs.h index 32eafa9b5c9f..94e706a0a408 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -900,7 +900,7 @@ struct lock_manager_operations { void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock **, int, struct list_head *); + int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); }; @@ -1021,7 +1021,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock **, int, struct list_head *); +extern int lease_modify(struct file_lock *, int, struct list_head *); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1153,7 +1153,7 @@ static inline int vfs_setlease(struct file *filp, long arg, return -EINVAL; } -static inline int lease_modify(struct file_lock **before, int arg, +static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; -- cgit v1.2.3 From 9bd0f45b7037fcfa8b575c7e27d0431d6e6dc3bb Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: keep a count of locks on the flctx lists This makes things a bit more efficient in the cifs and ceph lock pushing code. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 11 ++--------- fs/cifs/file.c | 14 ++++---------- fs/locks.c | 45 +++++++++++++++++++++++++++++---------------- include/linux/fs.h | 3 +++ 4 files changed, 38 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 0303da8e3233..06ea5cd05cd9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -242,12 +242,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) /* * Fills in the passed counter variables, so you can prepare pagelist metadata * before calling ceph_encode_locks. - * - * FIXME: add counters to struct file_lock_context so we don't need to do this? */ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) { - struct file_lock *lock; struct file_lock_context *ctx; *fcntl_count = 0; @@ -255,12 +252,8 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) ctx = inode->i_flctx; if (ctx) { - spin_lock(&ctx->flc_lock); - list_for_each_entry(lock, &ctx->flc_posix, fl_list) - ++(*fcntl_count); - list_for_each_entry(lock, &ctx->flc_flock, fl_list) - ++(*flock_count); - spin_unlock(&ctx->flc_lock); + *fcntl_count = ctx->flc_posix_cnt; + *flock_count = ctx->flc_flock_cnt; } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b65166eb111e..8c2ca6f62bad 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1125,7 +1125,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct file_lock *flock; struct file_lock_context *flctx = inode->i_flctx; - unsigned int count = 0, i; + unsigned int i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1136,20 +1136,14 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) if (!flctx) goto out; - spin_lock(&flctx->flc_lock); - list_for_each(el, &flctx->flc_posix) { - count++; - } - spin_unlock(&flctx->flc_lock); - INIT_LIST_HEAD(&locks_to_send); /* - * Allocating count locks is enough because no FL_POSIX locks can be - * added to the list while we are holding cinode->lock_sem that + * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks + * can be added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (i = 0; i < count; i++) { + for (i = 0; i < flctx->flc_posix_cnt; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; diff --git a/fs/locks.c b/fs/locks.c index 864f2460a0ad..bd578700342d 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -681,18 +681,21 @@ static void locks_wake_up_blocks(struct file_lock *blocker) } static void -locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) +locks_insert_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *before) { fl->fl_nspid = get_pid(task_tgid(current)); list_add_tail(&fl->fl_list, before); + ++*counter; locks_insert_global_locks(fl); } static void -locks_unlink_lock_ctx(struct file_lock *fl) +locks_unlink_lock_ctx(struct file_lock *fl, int *counter) { locks_delete_global_locks(fl); list_del_init(&fl->fl_list); + --*counter; if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; @@ -701,9 +704,10 @@ locks_unlink_lock_ctx(struct file_lock *fl) } static void -locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) +locks_delete_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *dispose) { - locks_unlink_lock_ctx(fl); + locks_unlink_lock_ctx(fl, counter); if (dispose) list_add(&fl->fl_list, dispose); else @@ -891,7 +895,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) if (request->fl_type == fl->fl_type) goto out; found = true; - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose); break; } @@ -925,7 +929,7 @@ find_conflict: if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); - locks_insert_lock_ctx(new_fl, &ctx->flc_flock); + locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock); new_fl = NULL; error = 0; @@ -1042,7 +1046,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt, + &dispose); continue; } request = fl; @@ -1071,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); continue; } /* @@ -1087,8 +1093,10 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_insert_lock_ctx(request, &fl->fl_list); - locks_delete_lock_ctx(fl, &dispose); + locks_insert_lock_ctx(request, + &ctx->flc_posix_cnt, &fl->fl_list); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); added = true; } } @@ -1116,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock_ctx(new_fl, &fl->fl_list); + locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt, + &fl->fl_list); new_fl = NULL; } if (right) { @@ -1127,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock_ctx(left, &fl->fl_list); + locks_insert_lock_ctx(left, &ctx->flc_posix_cnt, + &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1311,6 +1321,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg) /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { + struct file_lock_context *flctx; int error = assign_type(fl, arg); if (error) @@ -1320,6 +1331,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) if (arg == F_UNLCK) { struct file *filp = fl->fl_file; + flctx = file_inode(filp)->i_flctx; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); @@ -1327,7 +1339,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock_ctx(fl, dispose); + locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose); } return 0; } @@ -1442,7 +1454,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt, + &dispose); } if (list_empty(&ctx->flc_lease)) @@ -1678,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock_ctx(lease, &ctx->flc_lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1691,7 +1704,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr smp_mb(); error = check_conflicting_open(dentry, arg); if (error) { - locks_unlink_lock_ctx(lease); + locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt); goto out; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 94e706a0a408..f87cb2f03103 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -972,6 +972,9 @@ struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; + int flc_flock_cnt; + int flc_posix_cnt; + int flc_lease_cnt; }; /* The following constant reflects the upper bound of the file/locking space */ -- cgit v1.2.3 From 9d5438f462abd6398cdb7b3211bdcec271873a3b Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Fri, 16 Jan 2015 16:01:10 -0800 Subject: pstore: Add pmsg - user-space accessible pstore object A secured user-space accessible pstore object. Writes to /dev/pmsg0 are appended to the buffer, on reboot the persistent contents are available in /sys/fs/pstore/pmsg-ramoops-[ID]. One possible use is syslogd, or other daemon, can write messages, then on reboot provides a means to triage user-space activities leading up to a panic as a companion to the pstore dmesg or console logs. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/Kconfig | 10 ++++ fs/pstore/Makefile | 2 + fs/pstore/inode.c | 3 ++ fs/pstore/internal.h | 6 +++ fs/pstore/platform.c | 1 + fs/pstore/pmsg.c | 114 +++++++++++++++++++++++++++++++++++++++++++++ fs/pstore/ram.c | 34 +++++++++++++- include/linux/pstore.h | 1 + include/linux/pstore_ram.h | 1 + 9 files changed, 170 insertions(+), 2 deletions(-) create mode 100644 fs/pstore/pmsg.c (limited to 'include/linux') diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 983d9510becc..916b8e23d968 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -21,6 +21,16 @@ config PSTORE_CONSOLE When the option is enabled, pstore will log all kernel messages, even if no oops or panic happened. +config PSTORE_PMSG + bool "Log user space messages" + depends on PSTORE + help + When the option is enabled, pstore will export a character + interface /dev/pmsg0 to log user space messages. On reboot + data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID]. + + If unsure, say N. + config PSTORE_FTRACE bool "Persistent function tracer" depends on PSTORE diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 4c9095c2781e..e647d8e81712 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -7,5 +7,7 @@ obj-y += pstore.o pstore-objs += inode.o platform.o obj-$(CONFIG_PSTORE_FTRACE) += ftrace.o +obj-$(CONFIG_PSTORE_PMSG) += pmsg.o + ramoops-objs += ram.o ram_core.o obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d69586f09ffd..b32ce53d24ee 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -361,6 +361,9 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", psname, id); break; + case PSTORE_TYPE_PMSG: + scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id); + break; case PSTORE_TYPE_UNKNOWN: scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); break; diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 3b3d305277c4..c36ba2cd0b5d 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void); static inline void pstore_register_ftrace(void) {} #endif +#ifdef CONFIG_PSTORE_PMSG +extern void pstore_register_pmsg(void); +#else +static inline void pstore_register_pmsg(void) {} +#endif + extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 0a9b72cdfeca..15ee78c5020b 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -447,6 +447,7 @@ int pstore_register(struct pstore_info *psi) if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) { pstore_register_console(); pstore_register_ftrace(); + pstore_register_pmsg(); } if (pstore_update_ms >= 0) { diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c new file mode 100644 index 000000000000..feb5dd2948b4 --- /dev/null +++ b/fs/pstore/pmsg.c @@ -0,0 +1,114 @@ +/* + * Copyright 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include "internal.h" + +static DEFINE_MUTEX(pmsg_lock); +#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE) + +static ssize_t write_pmsg(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + size_t i, buffer_size; + char *buffer; + + if (!count) + return 0; + + if (!access_ok(VERIFY_READ, buf, count)) + return -EFAULT; + + buffer_size = count; + if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE) + buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE; + buffer = vmalloc(buffer_size); + + mutex_lock(&pmsg_lock); + for (i = 0; i < count; ) { + size_t c = min(count - i, buffer_size); + u64 id; + long ret; + + ret = __copy_from_user(buffer, buf + i, c); + if (unlikely(ret != 0)) { + mutex_unlock(&pmsg_lock); + vfree(buffer); + return -EFAULT; + } + psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, 0, c, + psinfo); + + i += c; + } + + mutex_unlock(&pmsg_lock); + vfree(buffer); + return count; +} + +static const struct file_operations pmsg_fops = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .write = write_pmsg, +}; + +static struct class *pmsg_class; +static int pmsg_major; +#define PMSG_NAME "pmsg" +#undef pr_fmt +#define pr_fmt(fmt) PMSG_NAME ": " fmt + +static char *pmsg_devnode(struct device *dev, umode_t *mode) +{ + if (mode) + *mode = 0220; + return NULL; +} + +void pstore_register_pmsg(void) +{ + struct device *pmsg_device; + + pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops); + if (pmsg_major < 0) { + pr_err("register_chrdev failed\n"); + goto err; + } + + pmsg_class = class_create(THIS_MODULE, PMSG_NAME); + if (IS_ERR(pmsg_class)) { + pr_err("device class file already in use\n"); + goto err_class; + } + pmsg_class->devnode = pmsg_devnode; + + pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0), + NULL, "%s%d", PMSG_NAME, 0); + if (IS_ERR(pmsg_device)) { + pr_err("failed to create device\n"); + goto err_device; + } + return; + +err_device: + class_destroy(pmsg_class); +err_class: + unregister_chrdev(pmsg_major, PMSG_NAME); +err: + return; +} diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 6150e54eed30..39d1373128e9 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE; module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400); MODULE_PARM_DESC(ftrace_size, "size of ftrace log"); +static ulong ramoops_pmsg_size = MIN_MEM_SIZE; +module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400); +MODULE_PARM_DESC(pmsg_size, "size of user space message log"); + static ulong mem_address; module_param(mem_address, ulong, 0400); MODULE_PARM_DESC(mem_address, @@ -82,12 +86,14 @@ struct ramoops_context { struct persistent_ram_zone **przs; struct persistent_ram_zone *cprz; struct persistent_ram_zone *fprz; + struct persistent_ram_zone *mprz; phys_addr_t phys_addr; unsigned long size; unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; + size_t pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; @@ -96,6 +102,7 @@ struct ramoops_context { unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; + unsigned int pmsg_read_cnt; struct pstore_info pstore; }; @@ -109,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; cxt->ftrace_read_cnt = 0; + cxt->pmsg_read_cnt = 0; return 0; } @@ -190,6 +198,9 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt, 1, id, type, PSTORE_TYPE_FTRACE, 0); + if (!prz_ok(prz)) + prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt, + 1, id, type, PSTORE_TYPE_PMSG, 0); if (!prz_ok(prz)) return 0; @@ -258,6 +269,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, return -ENOMEM; persistent_ram_write(cxt->fprz, buf, size); return 0; + } else if (type == PSTORE_TYPE_PMSG) { + if (!cxt->mprz) + return -ENOMEM; + persistent_ram_write(cxt->mprz, buf, size); + return 0; } if (type != PSTORE_TYPE_DMESG) @@ -315,6 +331,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count, case PSTORE_TYPE_FTRACE: prz = cxt->fprz; break; + case PSTORE_TYPE_PMSG: + prz = cxt->mprz; + break; default: return -EINVAL; } @@ -441,7 +460,7 @@ static int ramoops_probe(struct platform_device *pdev) goto fail_out; if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size && - !pdata->ftrace_size)) { + !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); goto fail_out; @@ -453,6 +472,8 @@ static int ramoops_probe(struct platform_device *pdev) pdata->console_size = rounddown_pow_of_two(pdata->console_size); if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); + if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size)) + pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size); cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; @@ -460,12 +481,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; + cxt->pmsg_size = pdata->pmsg_size; cxt->dump_oops = pdata->dump_oops; cxt->ecc_info = pdata->ecc_info; paddr = cxt->phys_addr; - dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size; + dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size + - cxt->pmsg_size; err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz); if (err) goto fail_out; @@ -480,6 +503,10 @@ static int ramoops_probe(struct platform_device *pdev) if (err) goto fail_init_fprz; + err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0); + if (err) + goto fail_init_mprz; + cxt->pstore.data = cxt; /* * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we @@ -523,6 +550,8 @@ fail_buf: kfree(cxt->pstore.buf); fail_clear: cxt->pstore.bufsize = 0; + kfree(cxt->mprz); +fail_init_mprz: kfree(cxt->fprz); fail_init_fprz: kfree(cxt->cprz); @@ -580,6 +609,7 @@ static void ramoops_register_dummy(void) dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; + dummy_data->pmsg_size = ramoops_pmsg_size; dummy_data->dump_oops = dump_oops; /* * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC diff --git a/include/linux/pstore.h b/include/linux/pstore.h index ece0c6bbfcc5..8884f6e507f7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,6 +39,7 @@ enum pstore_type_id { PSTORE_TYPE_PPC_RTAS = 4, PSTORE_TYPE_PPC_OF = 5, PSTORE_TYPE_PPC_COMMON = 6, + PSTORE_TYPE_PMSG = 7, PSTORE_TYPE_UNKNOWN = 255 }; diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 4af3fdc85b01..9c9d6c154c8e 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -81,6 +81,7 @@ struct ramoops_platform_data { unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; + unsigned long pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; }; -- cgit v1.2.3 From f8c58c1136349fdfa9b605c501f2f911622d3a9a Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Tue, 2 Dec 2014 15:42:47 -0800 Subject: mmc: dw_mmc: Protect read-modify-write of INTMASK with a lock We're running into cases where our enabling of the SDIO interrupt in dw_mmc doesn't actually take effect. Specifically, adding patch like this: +++ b/drivers/mmc/host/dw_mmc.c @@ -1076,6 +1076,9 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb) mci_writel(host, INTMASK, (int_mask | SDMMC_INT_SDIO(slot->id))); + int_mask = mci_readl(host, INTMASK); + if (!(int_mask & SDMMC_INT_SDIO(slot->id))) + dev_err(&mmc->class_dev, "failed to enable sdio irq\n"); } else { ...actually triggers the error message. That's because the dw_mci_enable_sdio_irq() unsafely does a read-modify-write of the INTMASK register. We can't just use the standard host->lock since that lock is not irq safe and mmc_signal_sdio_irq() (called from interrupt context) calls dw_mci_enable_sdio_irq(). Add a new irq-safe lock to protect INTMASK. An alternate solution to this is to punt mmc_signal_sdio_irq() to the tasklet and then protect INTMASK modifications by the standard host lock. This seemed like a bit more of a high-latency change. Reported-by: Bing Zhao Signed-off-by: Doug Anderson Reviewed-by: James Hogan Signed-off-by: Ulf Hansson --- drivers/mmc/host/dw_mmc.c | 13 +++++++++++++ include/linux/mmc/dw_mmc.h | 6 ++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index ae10a021765c..64ea04274913 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -759,6 +759,7 @@ disable: static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) { + unsigned long irqflags; int sg_len; u32 temp; @@ -795,9 +796,11 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) mci_writel(host, CTRL, temp); /* Disable RX/TX IRQs, let DMA handle it */ + spin_lock_irqsave(&host->irq_lock, irqflags); temp = mci_readl(host, INTMASK); temp &= ~(SDMMC_INT_RXDR | SDMMC_INT_TXDR); mci_writel(host, INTMASK, temp); + spin_unlock_irqrestore(&host->irq_lock, irqflags); host->dma_ops->start(host, sg_len); @@ -806,6 +809,7 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data) { + unsigned long irqflags; u32 temp; data->error = -EINPROGRESS; @@ -834,9 +838,12 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data) host->part_buf_count = 0; mci_writel(host, RINTSTS, SDMMC_INT_TXDR | SDMMC_INT_RXDR); + + spin_lock_irqsave(&host->irq_lock, irqflags); temp = mci_readl(host, INTMASK); temp |= SDMMC_INT_TXDR | SDMMC_INT_RXDR; mci_writel(host, INTMASK, temp); + spin_unlock_irqrestore(&host->irq_lock, irqflags); temp = mci_readl(host, CTRL); temp &= ~SDMMC_CTRL_DMA_ENABLE; @@ -1284,8 +1291,11 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb) { struct dw_mci_slot *slot = mmc_priv(mmc); struct dw_mci *host = slot->host; + unsigned long irqflags; u32 int_mask; + spin_lock_irqsave(&host->irq_lock, irqflags); + /* Enable/disable Slot Specific SDIO interrupt */ int_mask = mci_readl(host, INTMASK); if (enb) @@ -1293,6 +1303,8 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb) else int_mask &= ~SDMMC_INT_SDIO(slot->sdio_id); mci_writel(host, INTMASK, int_mask); + + spin_unlock_irqrestore(&host->irq_lock, irqflags); } static int dw_mci_execute_tuning(struct mmc_host *mmc, u32 opcode) @@ -2661,6 +2673,7 @@ int dw_mci_probe(struct dw_mci *host) host->quirks = host->pdata->quirks; spin_lock_init(&host->lock); + spin_lock_init(&host->irq_lock); INIT_LIST_HEAD(&host->queue); /* diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 42b724e8d503..471fb3116dbe 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -106,6 +106,11 @@ struct mmc_data; * @cur_slot, @mrq and @state. These must always be updated * at the same time while holding @lock. * + * @irq_lock is an irq-safe spinlock protecting the INTMASK register + * to allow the interrupt handler to modify it directly. Held for only long + * enough to read-modify-write INTMASK and no other locks are grabbed when + * holding this one. + * * The @mrq field of struct dw_mci_slot is also protected by @lock, * and must always be written at the same time as the slot is added to * @queue. @@ -125,6 +130,7 @@ struct mmc_data; */ struct dw_mci { spinlock_t lock; + spinlock_t irq_lock; void __iomem *regs; struct scatterlist *sg; -- cgit v1.2.3 From 61bd8a04b379e4fefbc0b0d06941d3f91071bb8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Dec 2014 08:43:08 +1100 Subject: mmc: omap_hsmmc: remove prepare/complete system suspend support. The only function of these 'prepare' and 'complete' is to disable the 'card detect' irq during suspend. The commit which added this, commit a48ce884d5819d5df2cf1139ab3c43f8e9e419b3 mmc: omap_hsmmc: Introduce omap_hsmmc_prepare/complete justified it by the need to avoid the registration of new devices during suspend. However mmc_pm_notify will set ->rescan_disable in the 'prepare' stage and clear it in the 'complete' stage, so no card detection will actually happen. Also the interrupt will be disabled before final suspend as part of common suspend processing. So this disabling of the interrupt is unnecessary, and interferes with a transition to using common code for card-detect management. Cc: Felipe Balbi Cc: Venkatraman S Cc: Chris Ball Signed-off-by: NeilBrown Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap_hsmmc.c | 50 ---------------------------------- include/linux/platform_data/mmc-omap.h | 4 --- 2 files changed, 54 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 7c71dcdcba8b..537cba8f1de1 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -275,31 +275,6 @@ static int omap_hsmmc_get_cover_state(struct device *dev) return !gpio_get_value_cansleep(mmc->switch_pin); } -#ifdef CONFIG_PM - -static int omap_hsmmc_suspend_cdirq(struct device *dev) -{ - struct omap_hsmmc_host *host = dev_get_drvdata(dev); - - disable_irq(host->card_detect_irq); - return 0; -} - -static int omap_hsmmc_resume_cdirq(struct device *dev) -{ - struct omap_hsmmc_host *host = dev_get_drvdata(dev); - - enable_irq(host->card_detect_irq); - return 0; -} - -#else - -#define omap_hsmmc_suspend_cdirq NULL -#define omap_hsmmc_resume_cdirq NULL - -#endif - #ifdef CONFIG_REGULATOR static int omap_hsmmc_set_power(struct device *dev, int power_on, int vdd) @@ -2234,8 +2209,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev) "Unable to grab MMC CD IRQ\n"); goto err_irq_cd; } - host->suspend = omap_hsmmc_suspend_cdirq; - host->resume = omap_hsmmc_resume_cdirq; } omap_hsmmc_disable_irq(host); @@ -2322,25 +2295,6 @@ static int omap_hsmmc_remove(struct platform_device *pdev) } #ifdef CONFIG_PM -static int omap_hsmmc_prepare(struct device *dev) -{ - struct omap_hsmmc_host *host = dev_get_drvdata(dev); - - if (host->suspend) - return host->suspend(dev); - - return 0; -} - -static void omap_hsmmc_complete(struct device *dev) -{ - struct omap_hsmmc_host *host = dev_get_drvdata(dev); - - if (host->resume) - host->resume(dev); - -} - static int omap_hsmmc_suspend(struct device *dev) { struct omap_hsmmc_host *host = dev_get_drvdata(dev); @@ -2398,8 +2352,6 @@ static int omap_hsmmc_resume(struct device *dev) } #else -#define omap_hsmmc_prepare NULL -#define omap_hsmmc_complete NULL #define omap_hsmmc_suspend NULL #define omap_hsmmc_resume NULL #endif @@ -2484,8 +2436,6 @@ static int omap_hsmmc_runtime_resume(struct device *dev) static struct dev_pm_ops omap_hsmmc_dev_pm_ops = { .suspend = omap_hsmmc_suspend, .resume = omap_hsmmc_resume, - .prepare = omap_hsmmc_prepare, - .complete = omap_hsmmc_complete, .runtime_suspend = omap_hsmmc_runtime_suspend, .runtime_resume = omap_hsmmc_runtime_resume, }; diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h index 5c188f4e9bec..929469291406 100644 --- a/include/linux/platform_data/mmc-omap.h +++ b/include/linux/platform_data/mmc-omap.h @@ -31,10 +31,6 @@ struct omap_mmc_platform_data { void (*cleanup)(struct device *dev); void (*shutdown)(struct device *dev); - /* To handle board related suspend/resume functionality for MMC */ - int (*suspend)(struct device *dev, int slot); - int (*resume)(struct device *dev, int slot); - /* Return context loss count due to PM states changing */ int (*get_context_loss_count)(struct device *dev); -- cgit v1.2.3 From eddbc3abc5bf11bdfc92ef84fd97ec4d379b7278 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 18 Dec 2014 15:44:32 +0100 Subject: mmc: slot-gpio: Remove option to explicitly free requested CD/WP GPIOs The slot-gpio uses the devm*_ managed functions. Still it provide APIs to explicitly free requested CD/WP GPIOs, but these API isn't being used. Therefore let's simplify slot-gpio by removing these unused APIs. If it later turns out we need some of them, we can always consider to restore the code. Signed-off-by: Ulf Hansson --- drivers/mmc/core/slot-gpio.c | 92 ++----------------------------------------- include/linux/mmc/slot-gpio.h | 3 -- 2 files changed, 4 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 69bbf2adb329..a428f10747d2 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -103,11 +103,7 @@ EXPORT_SYMBOL(mmc_gpio_get_cd); * @gpio: gpio number requested * * As devm_* managed functions are used in mmc_gpio_request_ro(), client - * drivers do not need to explicitly call mmc_gpio_free_ro() for freeing up, - * if the requesting and freeing are only needed at probing and unbinding time - * for once. However, if client drivers do something special like runtime - * switching for write-protection, they are responsible for calling - * mmc_gpio_request_ro() and mmc_gpio_free_ro() as a pair on their own. + * drivers do not need to worry about freeing up memory. * * Returns zero on success, else an error. */ @@ -178,11 +174,7 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd_irq); * @debounce: debounce time in microseconds * * As devm_* managed functions are used in mmc_gpio_request_cd(), client - * drivers do not need to explicitly call mmc_gpio_free_cd() for freeing up, - * if the requesting and freeing are only needed at probing and unbinding time - * for once. However, if client drivers do something special like runtime - * switching for card-detection, they are responsible for calling - * mmc_gpio_request_cd() and mmc_gpio_free_cd() as a pair on their own. + * drivers do not need to worry about freeing up memory. * * If GPIO debouncing is desired, set the debounce parameter to a non-zero * value. The caller is responsible for ensuring that the GPIO driver associated @@ -225,55 +217,6 @@ int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio, } EXPORT_SYMBOL(mmc_gpio_request_cd); -/** - * mmc_gpio_free_ro - free the write-protection gpio - * @host: mmc host - * - * It's provided only for cases that client drivers need to manually free - * up the write-protection gpio requested by mmc_gpio_request_ro(). - */ -void mmc_gpio_free_ro(struct mmc_host *host) -{ - struct mmc_gpio *ctx = host->slot.handler_priv; - int gpio; - - if (!ctx || !ctx->ro_gpio) - return; - - gpio = desc_to_gpio(ctx->ro_gpio); - ctx->ro_gpio = NULL; - - devm_gpio_free(&host->class_dev, gpio); -} -EXPORT_SYMBOL(mmc_gpio_free_ro); - -/** - * mmc_gpio_free_cd - free the card-detection gpio - * @host: mmc host - * - * It's provided only for cases that client drivers need to manually free - * up the card-detection gpio requested by mmc_gpio_request_cd(). - */ -void mmc_gpio_free_cd(struct mmc_host *host) -{ - struct mmc_gpio *ctx = host->slot.handler_priv; - int gpio; - - if (!ctx || !ctx->cd_gpio) - return; - - if (host->slot.cd_irq >= 0) { - devm_free_irq(&host->class_dev, host->slot.cd_irq, host); - host->slot.cd_irq = -EINVAL; - } - - gpio = desc_to_gpio(ctx->cd_gpio); - ctx->cd_gpio = NULL; - - devm_gpio_free(&host->class_dev, gpio); -} -EXPORT_SYMBOL(mmc_gpio_free_cd); - /** * mmc_gpiod_request_cd - request a gpio descriptor for card-detection * @host: mmc host @@ -285,8 +228,7 @@ EXPORT_SYMBOL(mmc_gpio_free_cd); * to NULL to ignore * * Use this function in place of mmc_gpio_request_cd() to use the GPIO - * descriptor API. Note that it is paired with mmc_gpiod_free_cd() not - * mmc_gpio_free_cd(). Note also that it must be called prior to mmc_add_host() + * descriptor API. Note that it must be called prior to mmc_add_host() * otherwise the caller must also call mmc_gpiod_request_cd_irq(). * * Returns zero on success, else an error. @@ -339,8 +281,7 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd); * set to NULL to ignore * * Use this function in place of mmc_gpio_request_ro() to use the GPIO - * descriptor API. Note that it is paired with mmc_gpiod_free_ro() not - * mmc_gpio_free_ro(). + * descriptor API. * * Returns zero on success, else an error. */ @@ -380,28 +321,3 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, return 0; } EXPORT_SYMBOL(mmc_gpiod_request_ro); - -/** - * mmc_gpiod_free_cd - free the card-detection gpio descriptor - * @host: mmc host - * - * It's provided only for cases that client drivers need to manually free - * up the card-detection gpio requested by mmc_gpiod_request_cd(). - */ -void mmc_gpiod_free_cd(struct mmc_host *host) -{ - struct mmc_gpio *ctx = host->slot.handler_priv; - - if (!ctx || !ctx->cd_gpio) - return; - - if (host->slot.cd_irq >= 0) { - devm_free_irq(&host->class_dev, host->slot.cd_irq, host); - host->slot.cd_irq = -EINVAL; - } - - devm_gpiod_put(host->parent, ctx->cd_gpio); - - ctx->cd_gpio = NULL; -} -EXPORT_SYMBOL(mmc_gpiod_free_cd); diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index e56fa24c9322..4a36d6954631 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -15,12 +15,10 @@ struct mmc_host; int mmc_gpio_get_ro(struct mmc_host *host); int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio); -void mmc_gpio_free_ro(struct mmc_host *host); int mmc_gpio_get_cd(struct mmc_host *host); int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio, unsigned int debounce); -void mmc_gpio_free_cd(struct mmc_host *host); int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, @@ -28,7 +26,6 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert); -void mmc_gpiod_free_cd(struct mmc_host *host); void mmc_gpiod_request_cd_irq(struct mmc_host *host); #endif -- cgit v1.2.3 From df8aca162e5ff2b20c7a4de3e64e5b96ff838ab0 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 18 Dec 2014 15:44:36 +0100 Subject: mmc: slot-gpio: Rework how to handle allocation of slot-gpio data By moving the allocation of the slot-gpio data into mmc_alloc_host(), we can remove the slot-gpio internal calls to mmc_gpio_alloc(). This means mmc_gpio_alloc() has now only one caller left, which consequence allow us to simplify and remove some of the slot-gpio code. Additionally, this makes the slot-gpio mutex redundant, so let's remove it. Signed-off-by: Ulf Hansson --- drivers/mmc/core/host.c | 20 +++++++------- drivers/mmc/core/slot-gpio.c | 62 ++++++++++---------------------------------- include/linux/mmc/host.h | 2 -- 3 files changed, 23 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index fcb7f06373cf..07636449b4de 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -29,6 +29,7 @@ #include "core.h" #include "host.h" +#include "slot-gpio.h" #define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev) @@ -38,7 +39,6 @@ static DEFINE_SPINLOCK(mmc_host_lock); static void mmc_host_classdev_release(struct device *dev) { struct mmc_host *host = cls_dev_to_mmc_host(dev); - mutex_destroy(&host->slot.lock); spin_lock(&mmc_host_lock); idr_remove(&mmc_host_idr, host->index); spin_unlock(&mmc_host_lock); @@ -478,8 +478,10 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) host->index = err; spin_unlock(&mmc_host_lock); idr_preload_end(); - if (err < 0) - goto free; + if (err < 0) { + kfree(host); + return NULL; + } dev_set_name(&host->class_dev, "mmc%d", host->index); @@ -488,10 +490,12 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) host->class_dev.class = &mmc_host_class; device_initialize(&host->class_dev); - mmc_host_clk_init(host); + if (mmc_gpio_alloc(host)) { + put_device(&host->class_dev); + return NULL; + } - mutex_init(&host->slot.lock); - host->slot.cd_irq = -EINVAL; + mmc_host_clk_init(host); spin_lock_init(&host->lock); init_waitqueue_head(&host->wq); @@ -512,10 +516,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) host->max_blk_count = PAGE_CACHE_SIZE / 512; return host; - -free: - kfree(host); - return NULL; } EXPORT_SYMBOL(mmc_alloc_host); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index ec918c27e77f..1a3edbd47719 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -43,29 +43,17 @@ static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id) int mmc_gpio_alloc(struct mmc_host *host) { size_t len = strlen(dev_name(host->parent)) + 4; - struct mmc_gpio *ctx; - - mutex_lock(&host->slot.lock); - - ctx = host->slot.handler_priv; - if (!ctx) { - /* - * devm_kzalloc() can be called after device_initialize(), even - * before device_add(), i.e., between mmc_alloc_host() and - * mmc_add_host() - */ - ctx = devm_kzalloc(host->parent, sizeof(*ctx) + 2 * len, - GFP_KERNEL); - if (ctx) { - ctx->ro_label = ctx->cd_label + len; - snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent)); - snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent)); - host->slot.handler_priv = ctx; - } + struct mmc_gpio *ctx = devm_kzalloc(host->parent, + sizeof(*ctx) + 2 * len, GFP_KERNEL); + + if (ctx) { + ctx->ro_label = ctx->cd_label + len; + snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent)); + snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent)); + host->slot.handler_priv = ctx; + host->slot.cd_irq = -EINVAL; } - mutex_unlock(&host->slot.lock); - return ctx ? 0 : -ENOMEM; } @@ -111,18 +99,12 @@ EXPORT_SYMBOL(mmc_gpio_get_cd); */ int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio) { - struct mmc_gpio *ctx; + struct mmc_gpio *ctx = host->slot.handler_priv; int ret; if (!gpio_is_valid(gpio)) return -EINVAL; - ret = mmc_gpio_alloc(host); - if (ret < 0) - return ret; - - ctx = host->slot.handler_priv; - ret = devm_gpio_request_one(host->parent, gpio, GPIOF_DIR_IN, ctx->ro_label); if (ret < 0) @@ -187,15 +169,9 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd_irq); int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio, unsigned int debounce) { - struct mmc_gpio *ctx; + struct mmc_gpio *ctx = host->slot.handler_priv; int ret; - ret = mmc_gpio_alloc(host); - if (ret < 0) - return ret; - - ctx = host->slot.handler_priv; - ret = devm_gpio_request_one(host->parent, gpio, GPIOF_DIR_IN, ctx->cd_label); if (ret < 0) @@ -239,16 +215,10 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert) { - struct mmc_gpio *ctx; + struct mmc_gpio *ctx = host->slot.handler_priv; struct gpio_desc *desc; int ret; - ret = mmc_gpio_alloc(host); - if (ret < 0) - return ret; - - ctx = host->slot.handler_priv; - if (!con_id) con_id = ctx->cd_label; @@ -291,16 +261,10 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert) { - struct mmc_gpio *ctx; + struct mmc_gpio *ctx = host->slot.handler_priv; struct gpio_desc *desc; int ret; - ret = mmc_gpio_alloc(host); - if (ret < 0) - return ret; - - ctx = host->slot.handler_priv; - if (!con_id) con_id = ctx->ro_label; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9f322706f7cb..b6bf718c3498 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -166,7 +166,6 @@ struct mmc_async_req { * struct mmc_slot - MMC slot functions * * @cd_irq: MMC/SD-card slot hotplug detection IRQ or -EINVAL - * @lock: protect the @handler_priv pointer * @handler_priv: MMC/SD-card slot context * * Some MMC/SD host controllers implement slot-functions like card and @@ -176,7 +175,6 @@ struct mmc_async_req { */ struct mmc_slot { int cd_irq; - struct mutex lock; void *handler_priv; }; -- cgit v1.2.3 From 04cdbbfa73ebac57a30ec2ebebfd7e9342bbdc44 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 1 Dec 2014 16:53:34 +0100 Subject: mmc: core: Make tuning block patterns static Since previous patches removed the need for the tuning block patterns to be exported, let's move them close to the mmc_send_tuning() API. Those are now intended to be used only by the mmc core. Signed-off-by: Ulf Hansson Reviewed-by: Stephen Boyd Acked-by: Jaehoon Chung --- drivers/mmc/core/mmc.c | 32 -------------------------------- drivers/mmc/core/mmc_ops.c | 30 ++++++++++++++++++++++++++++++ include/linux/mmc/mmc.h | 5 ----- 3 files changed, 30 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index d854bff037a2..0b8ec87fc517 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1155,38 +1155,6 @@ bus_speed: return err; } -const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE] = { - 0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc, - 0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef, - 0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb, - 0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef, - 0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c, - 0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee, - 0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff, - 0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde, -}; -EXPORT_SYMBOL(tuning_blk_pattern_4bit); - -const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE] = { - 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00, - 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc, - 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff, - 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff, - 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd, - 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb, - 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff, - 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff, - 0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, - 0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, - 0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, - 0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, - 0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, - 0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, - 0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, - 0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, -}; -EXPORT_SYMBOL(tuning_blk_pattern_8bit); - /* * Execute tuning sequence to seek the proper bus operating * conditions for HS200 and HS400, which sends CMD21 to the device. diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 3b044c5b029c..0ea042dc7443 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -23,6 +23,36 @@ #define MMC_OPS_TIMEOUT_MS (10 * 60 * 1000) /* 10 minute timeout */ +static const u8 tuning_blk_pattern_4bit[] = { + 0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc, + 0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef, + 0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb, + 0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef, + 0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c, + 0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee, + 0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff, + 0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde, +}; + +static const u8 tuning_blk_pattern_8bit[] = { + 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00, + 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc, + 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff, + 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff, + 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd, + 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb, + 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff, + 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff, + 0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, + 0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, + 0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, + 0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, + 0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, + 0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, + 0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, + 0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, +}; + static inline int __mmc_send_status(struct mmc_card *card, u32 *status, bool ignore_crc) { diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 49ad7a943638..fb97b5cc91cd 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -53,11 +53,6 @@ #define MMC_SEND_TUNING_BLOCK 19 /* adtc R1 */ #define MMC_SEND_TUNING_BLOCK_HS200 21 /* adtc R1 */ -#define MMC_TUNING_BLK_PATTERN_4BIT_SIZE 64 -#define MMC_TUNING_BLK_PATTERN_8BIT_SIZE 128 -extern const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE]; -extern const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE]; - /* class 3 */ #define MMC_WRITE_DAT_UNTIL_STOP 20 /* adtc [31:0] data addr R1 */ -- cgit v1.2.3 From 348487cb28e66b032bae1b38424d81bf5b444408 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Tue, 9 Dec 2014 17:04:05 +0800 Subject: mmc: sdhci: use pipeline mmc requests to improve performance This patch is based on the patches by Per Forlin, Tony Lin and Ryan QIAN. This patch complete the API 'post_req' and 'pre_req' in sdhci host side, Test Env: 1. i.MX6Q-SABREAUTO board, CPU @ 996MHz, use ADMA in uSDHC controller. 2. Test command: $ echo 1 > /proc/sys/vm/drop_caches write to sd card: $ dd if=/dev/zero of=/dev/mmcblk0 bs=1M count=2000 conv=fsync read the sd card: $ dd if=/dev/mmcblk0 of=/dev/null bs=1M count=2000 3. TOSHIBA 16GB SD3.0 card, running at 4 bit, SDR104 @ 198MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~76.7 MB/s | ~23.3 MB/s | |------------------------------------------------ |without this patch | ~60.5 MB/s | ~22.5 MB/s | ------------------------------------------------- 4. SanDisk 8GB SD3.0 card, running at 4 bit, DDR50 @ 50MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~40.5 MB/s | ~15.6 MB/s | |------------------------------------------------ |without this patch | ~36.1 MB/s | ~14.1 MB/s | ------------------------------------------------- 5. Kingston 8GB SD2.0 card, running at 4 bit, High-speed @ 50MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~22.7 MB/s | ~8.2 MB/s | |------------------------------------------------ |without this patch | ~21.3 MB/s | ~8.0 MB/s | ------------------------------------------------- 6. About eMMC, Sandisk 8GB eMMC on i.MX6DL-sabresd board, CPU @ 792MHZ, eMMC running at 8 bit, DDR52 @ 52MHZ. Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~37.3 MB/s | ~10.5 MB/s | |------------------------------------------------ |without this patch | ~33.4 MB/s | ~10.5 MB/s | ------------------------------------------------- Signed-off-by: Haibo Chen Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 99 +++++++++++++++++++++++++++++++++++++++++------ include/linux/mmc/sdhci.h | 6 +++ 2 files changed, 93 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 2558d705c92e..1aab8a120d02 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -53,6 +53,9 @@ static void sdhci_finish_command(struct sdhci_host *); static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode); static void sdhci_tuning_timer(unsigned long data); static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable); +static int sdhci_pre_dma_transfer(struct sdhci_host *host, + struct mmc_data *data, + struct sdhci_host_next *next); #ifdef CONFIG_PM static int sdhci_runtime_pm_get(struct sdhci_host *host); @@ -505,9 +508,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host, goto fail; BUG_ON(host->align_addr & host->align_mask); - host->sg_count = dma_map_sg(mmc_dev(host->mmc), - data->sg, data->sg_len, direction); - if (host->sg_count == 0) + host->sg_count = sdhci_pre_dma_transfer(host, data, NULL); + if (host->sg_count < 0) goto unmap_align; desc = host->adma_table; @@ -645,8 +647,9 @@ static void sdhci_adma_table_post(struct sdhci_host *host, } } - dma_unmap_sg(mmc_dev(host->mmc), data->sg, - data->sg_len, direction); + if (!data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, direction); } static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd) @@ -842,11 +845,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd) } else { int sg_cnt; - sg_cnt = dma_map_sg(mmc_dev(host->mmc), - data->sg, data->sg_len, - (data->flags & MMC_DATA_READ) ? - DMA_FROM_DEVICE : - DMA_TO_DEVICE); + sg_cnt = sdhci_pre_dma_transfer(host, data, NULL); if (sg_cnt == 0) { /* * This only happens when someone fed @@ -959,8 +958,10 @@ static void sdhci_finish_data(struct sdhci_host *host) if (host->flags & SDHCI_USE_ADMA) sdhci_adma_table_post(host, data); else { - dma_unmap_sg(mmc_dev(host->mmc), data->sg, - data->sg_len, (data->flags & MMC_DATA_READ) ? + if (!data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), + data->sg, data->sg_len, + (data->flags & MMC_DATA_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } } @@ -2125,6 +2126,77 @@ static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable) } } +static void sdhci_post_req(struct mmc_host *mmc, struct mmc_request *mrq, + int err) +{ + struct sdhci_host *host = mmc_priv(mmc); + struct mmc_data *data = mrq->data; + + if (host->flags & SDHCI_REQ_USE_DMA) { + if (data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + data->flags & MMC_DATA_WRITE ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); + mrq->data->host_cookie = 0; + } +} + +static int sdhci_pre_dma_transfer(struct sdhci_host *host, + struct mmc_data *data, + struct sdhci_host_next *next) +{ + int sg_count; + + if (!next && data->host_cookie && + data->host_cookie != host->next_data.cookie) { + pr_debug(DRIVER_NAME "[%s] invalid cookie: %d, next-cookie %d\n", + __func__, data->host_cookie, host->next_data.cookie); + data->host_cookie = 0; + } + + /* Check if next job is already prepared */ + if (next || + (!next && data->host_cookie != host->next_data.cookie)) { + sg_count = dma_map_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, + data->flags & MMC_DATA_WRITE ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); + + } else { + sg_count = host->next_data.sg_count; + host->next_data.sg_count = 0; + } + + + if (sg_count == 0) + return -EINVAL; + + if (next) { + next->sg_count = sg_count; + data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie; + } else + host->sg_count = sg_count; + + return sg_count; +} + +static void sdhci_pre_req(struct mmc_host *mmc, struct mmc_request *mrq, + bool is_first_req) +{ + struct sdhci_host *host = mmc_priv(mmc); + + if (mrq->data->host_cookie) { + mrq->data->host_cookie = 0; + return; + } + + if (host->flags & SDHCI_REQ_USE_DMA) + if (sdhci_pre_dma_transfer(host, + mrq->data, + &host->next_data) < 0) + mrq->data->host_cookie = 0; +} + static void sdhci_card_event(struct mmc_host *mmc) { struct sdhci_host *host = mmc_priv(mmc); @@ -2158,6 +2230,8 @@ static void sdhci_card_event(struct mmc_host *mmc) static const struct mmc_host_ops sdhci_ops = { .request = sdhci_request, + .post_req = sdhci_post_req, + .pre_req = sdhci_pre_req, .set_ios = sdhci_set_ios, .get_cd = sdhci_get_cd, .get_ro = sdhci_get_ro, @@ -3015,6 +3089,7 @@ int sdhci_add_host(struct sdhci_host *host) host->max_clk = host->ops->get_max_clock(host); } + host->next_data.cookie = 1; /* * In case of Host Controller v3.00, find out whether clock * multiplier is supported. diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index f767a0de611f..cb8b94ff6a26 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -17,6 +17,11 @@ #include #include +struct sdhci_host_next { + unsigned int sg_count; + s32 cookie; +}; + struct sdhci_host { /* Data set by hardware interface driver */ const char *hw_name; /* Hardware bus name */ @@ -203,6 +208,7 @@ struct sdhci_host { #define SDHCI_TUNING_MODE_1 0 struct timer_list tuning_timer; /* Timer for tuning */ + struct sdhci_host_next next_data; unsigned long private[0] ____cacheline_aligned; }; #endif /* LINUX_MMC_SDHCI_H */ -- cgit v1.2.3 From 83533ab28380f6957af39a7b322e639e42dbdaf1 Mon Sep 17 00:00:00 2001 From: Johan Rudholm Date: Mon, 12 Jan 2015 15:38:04 +0100 Subject: mmc: core: always check status after reset Always check if the card is alive after a successful reset. This allows us to remove mmc_hw_reset_check(), leaving mmc_hw_reset() as the only card reset interface. Signed-off-by: Johan Rudholm Signed-off-by: Ulf Hansson --- drivers/mmc/card/mmc_test.c | 18 +++++++----------- drivers/mmc/core/core.c | 24 +++++------------------- include/linux/mmc/core.h | 1 - 3 files changed, 12 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index 0a7430f94d29..7dac4695163b 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -2342,20 +2342,16 @@ static int mmc_test_hw_reset(struct mmc_test_card *test) struct mmc_host *host = card->host; int err; - err = mmc_hw_reset_check(host); + if (!mmc_card_mmc(card) || !mmc_can_reset(card)) + return RESULT_UNSUP_CARD; + + err = mmc_hw_reset(host); if (!err) return RESULT_OK; + else if (err == -EOPNOTSUPP) + return RESULT_UNSUP_HOST; - if (err == -ENOSYS) - return RESULT_FAIL; - - if (err != -EOPNOTSUPP) - return err; - - if (!mmc_can_reset(card)) - return RESULT_UNSUP_CARD; - - return RESULT_UNSUP_HOST; + return RESULT_FAIL; } static const struct mmc_test_case mmc_test_cases[] = { diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d3bfbdfab052..72070f188cc5 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2286,9 +2286,10 @@ int mmc_can_reset(struct mmc_card *card) } EXPORT_SYMBOL(mmc_can_reset); -static int mmc_do_hw_reset(struct mmc_host *host, int check) +int mmc_hw_reset(struct mmc_host *host) { struct mmc_card *card = host->card; + u32 status; if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset) return -EOPNOTSUPP; @@ -2305,13 +2306,9 @@ static int mmc_do_hw_reset(struct mmc_host *host, int check) host->ops->hw_reset(host); /* If the reset has happened, then a status command will fail */ - if (check) { - u32 status; - - if (!mmc_send_status(card, &status)) { - mmc_host_clk_release(host); - return -ENOSYS; - } + if (!mmc_send_status(card, &status)) { + mmc_host_clk_release(host); + return -ENOSYS; } /* Set initial state and call mmc_set_ios */ @@ -2321,19 +2318,8 @@ static int mmc_do_hw_reset(struct mmc_host *host, int check) return host->bus_ops->power_restore(host); } - -int mmc_hw_reset(struct mmc_host *host) -{ - return mmc_do_hw_reset(host, 0); -} EXPORT_SYMBOL(mmc_hw_reset); -int mmc_hw_reset_check(struct mmc_host *host) -{ - return mmc_do_hw_reset(host, 1); -} -EXPORT_SYMBOL(mmc_hw_reset_check); - static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq) { host->f_init = freq; diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index cb2b0400d284..160448f920ac 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -182,7 +182,6 @@ extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); extern int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount, bool is_rel_write); extern int mmc_hw_reset(struct mmc_host *host); -extern int mmc_hw_reset_check(struct mmc_host *host); extern int mmc_can_reset(struct mmc_card *card); extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *); -- cgit v1.2.3 From c7ea834d81904b71505093f7ec50d036132cf628 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 13 Jan 2015 08:23:18 +1300 Subject: mmc: slot-gpio: Allow host driver to provide isr for card-detect interrupts One of the reasons omap_hsmmc doesn't use the slot-gpio library is that it has some non-standard functionality in the card-detect interrupt service routine. To make it possible for omap_hsmmc (and maybe others) to be converted to use slot-gpio, add 'mmc_gpio_request_cd_isr' which provide an alternate isr to be register by the slot-gpio code. Signed-off-by: NeilBrown Signed-off-by: Ulf Hansson --- drivers/mmc/core/slot-gpio.c | 18 +++++++++++++++++- include/linux/mmc/slot-gpio.h | 2 ++ 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 1a3edbd47719..27117ba47073 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -25,6 +25,7 @@ struct mmc_gpio { struct gpio_desc *cd_gpio; bool override_ro_active_level; bool override_cd_active_level; + irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id); char *ro_label; char cd_label[0]; }; @@ -136,8 +137,10 @@ void mmc_gpiod_request_cd_irq(struct mmc_host *host) irq = -EINVAL; if (irq >= 0) { + if (!ctx->cd_gpio_isr) + ctx->cd_gpio_isr = mmc_gpio_cd_irqt; ret = devm_request_threaded_irq(host->parent, irq, - NULL, mmc_gpio_cd_irqt, + NULL, ctx->cd_gpio_isr, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, ctx->cd_label, host); if (ret < 0) @@ -151,6 +154,19 @@ void mmc_gpiod_request_cd_irq(struct mmc_host *host) } EXPORT_SYMBOL(mmc_gpiod_request_cd_irq); +/* Register an alternate interrupt service routine for + * the card-detect GPIO. + */ +void mmc_gpio_set_cd_isr(struct mmc_host *host, + irqreturn_t (*isr)(int irq, void *dev_id)) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + + WARN_ON(ctx->cd_gpio_isr); + ctx->cd_gpio_isr = isr; +} +EXPORT_SYMBOL(mmc_gpio_set_cd_isr); + /** * mmc_gpio_request_cd - request a gpio for card-detection * @host: mmc host diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 4a36d6954631..3945a8c9d3cb 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -26,6 +26,8 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert); +void mmc_gpio_set_cd_isr(struct mmc_host *host, + irqreturn_t (*isr)(int irq, void *dev_id)); void mmc_gpiod_request_cd_irq(struct mmc_host *host); #endif -- cgit v1.2.3 From c7d7ddee7e24eedde6149eefbcfbfbc7125b9ff0 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 15 Jan 2015 15:09:37 +0100 Subject: ata: libahci: Allow using multiple regulators The current implementation of the libahci allows using multiple PHYs but not multiple regulators. This patch adds the support of multiple regulators. Until now it was mandatory to have a PHY under a subnode, now a port subnode can contain either a regulator or a PHY (or both). In order to be able to asociate a port with a regulator the port are now a platform device in the device tree case. There was only one driver which used directly the regulator field of the ahci_host_priv structure. To preserve the bisectability the change in the ahci_imx driver was done in the same patch. Signed-off-by: Gregory CLEMENT Acked-by: Hans de Goede Signed-off-by: Tejun Heo --- drivers/ata/ahci.h | 2 +- drivers/ata/ahci_imx.c | 14 +-- drivers/ata/libahci_platform.c | 230 +++++++++++++++++++++++++++++------------ include/linux/ahci_platform.h | 2 + 4 files changed, 173 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 40f0e34f17af..275358ae0b3f 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -333,7 +333,7 @@ struct ahci_host_priv { u32 em_msg_type; /* EM message type */ bool got_runtime_pm; /* Did we do pm_runtime_get? */ struct clk *clks[AHCI_MAX_CLKS]; /* Optional */ - struct regulator *target_pwr; /* Optional */ + struct regulator **target_pwrs; /* Optional */ /* * If platform uses PHYs. There is a 1:1 relation between the port number and * the PHY position in this array. diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 35d51c59a370..41632e57d46f 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -221,11 +221,9 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv) if (imxpriv->no_device) return 0; - if (hpriv->target_pwr) { - ret = regulator_enable(hpriv->target_pwr); - if (ret) - return ret; - } + ret = ahci_platform_enable_regulators(hpriv); + if (ret) + return ret; ret = clk_prepare_enable(imxpriv->sata_ref_clk); if (ret < 0) @@ -270,8 +268,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv) disable_clk: clk_disable_unprepare(imxpriv->sata_ref_clk); disable_regulator: - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); return ret; } @@ -291,8 +288,7 @@ static void imx_sata_disable(struct ahci_host_priv *hpriv) clk_disable_unprepare(imxpriv->sata_ref_clk); - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); } static void ahci_imx_error_handler(struct ata_port *ap) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index a147aaadca85..73a086664ee7 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "ahci.h" static void ahci_host_stop(struct ata_host *host); @@ -137,6 +138,59 @@ void ahci_platform_disable_clks(struct ahci_host_priv *hpriv) } EXPORT_SYMBOL_GPL(ahci_platform_disable_clks); +/** + * ahci_platform_enable_regulators - Enable regulators + * @hpriv: host private area to store config values + * + * This function enables all the regulators found in + * hpriv->target_pwrs, if any. If a regulator fails to be enabled, it + * disables all the regulators already enabled in reverse order and + * returns an error. + * + * RETURNS: + * 0 on success otherwise a negative error code + */ +int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv) +{ + int rc, i; + + for (i = 0; i < hpriv->nports; i++) { + if (!hpriv->target_pwrs[i]) + continue; + + rc = regulator_enable(hpriv->target_pwrs[i]); + if (rc) + goto disable_target_pwrs; + } + + return 0; + +disable_target_pwrs: + while (--i >= 0) + if (hpriv->target_pwrs[i]) + regulator_disable(hpriv->target_pwrs[i]); + + return rc; +} +EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators); + +/** + * ahci_platform_disable_regulators - Disable regulators + * @hpriv: host private area to store config values + * + * This function disables all regulators found in hpriv->target_pwrs. + */ +void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv) +{ + int i; + + for (i = 0; i < hpriv->nports; i++) { + if (!hpriv->target_pwrs[i]) + continue; + regulator_disable(hpriv->target_pwrs[i]); + } +} +EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators); /** * ahci_platform_enable_resources - Enable platform resources * @hpriv: host private area to store config values @@ -157,11 +211,9 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv) { int rc; - if (hpriv->target_pwr) { - rc = regulator_enable(hpriv->target_pwr); - if (rc) - return rc; - } + rc = ahci_platform_enable_regulators(hpriv); + if (rc) + return rc; rc = ahci_platform_enable_clks(hpriv); if (rc) @@ -177,8 +229,8 @@ disable_clks: ahci_platform_disable_clks(hpriv); disable_regulator: - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); + return rc; } EXPORT_SYMBOL_GPL(ahci_platform_enable_resources); @@ -199,8 +251,7 @@ void ahci_platform_disable_resources(struct ahci_host_priv *hpriv) ahci_platform_disable_clks(hpriv); - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); } EXPORT_SYMBOL_GPL(ahci_platform_disable_resources); @@ -216,6 +267,68 @@ static void ahci_platform_put_resources(struct device *dev, void *res) for (c = 0; c < AHCI_MAX_CLKS && hpriv->clks[c]; c++) clk_put(hpriv->clks[c]); + /* + * The regulators are tied to child node device and not to the + * SATA device itself. So we can't use devm for automatically + * releasing them. We have to do it manually here. + */ + for (c = 0; c < hpriv->nports; c++) + if (hpriv->target_pwrs && hpriv->target_pwrs[c]) + regulator_put(hpriv->target_pwrs[c]); + +} + +static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port, + struct device *dev, struct device_node *node) +{ + int rc; + + hpriv->phys[port] = devm_of_phy_get(dev, node, NULL); + + if (!IS_ERR(hpriv->phys[port])) + return 0; + + rc = PTR_ERR(hpriv->phys[port]); + switch (rc) { + case -ENOSYS: + /* No PHY support. Check if PHY is required. */ + if (of_find_property(node, "phys", NULL)) { + dev_err(dev, + "couldn't get PHY in node %s: ENOSYS\n", + node->name); + break; + } + case -ENODEV: + /* continue normally */ + hpriv->phys[port] = NULL; + rc = 0; + break; + + default: + dev_err(dev, + "couldn't get PHY in node %s: %d\n", + node->name, rc); + + break; + } + + return rc; +} + +static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port, + struct device *dev) +{ + struct regulator *target_pwr; + int rc = 0; + + target_pwr = regulator_get_optional(dev, "target"); + + if (!IS_ERR(target_pwr)) + hpriv->target_pwrs[port] = target_pwr; + else + rc = PTR_ERR(target_pwr); + + return rc; } /** @@ -240,7 +353,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) struct ahci_host_priv *hpriv; struct clk *clk; struct device_node *child; - int i, enabled_ports = 0, rc = -ENOMEM; + int i, sz, enabled_ports = 0, rc = -ENOMEM, child_nodes; u32 mask_port_map = 0; if (!devres_open_group(dev, NULL, GFP_KERNEL)) @@ -261,14 +374,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) goto err_out; } - hpriv->target_pwr = devm_regulator_get_optional(dev, "target"); - if (IS_ERR(hpriv->target_pwr)) { - rc = PTR_ERR(hpriv->target_pwr); - if (rc == -EPROBE_DEFER) - goto err_out; - hpriv->target_pwr = NULL; - } - for (i = 0; i < AHCI_MAX_CLKS; i++) { /* * For now we must use clk_get(dev, NULL) for the first clock, @@ -290,19 +395,33 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) hpriv->clks[i] = clk; } - hpriv->nports = of_get_child_count(dev->of_node); + hpriv->nports = child_nodes = of_get_child_count(dev->of_node); - if (hpriv->nports) { - hpriv->phys = devm_kzalloc(dev, - hpriv->nports * sizeof(*hpriv->phys), - GFP_KERNEL); - if (!hpriv->phys) { - rc = -ENOMEM; - goto err_out; - } + /* + * If no sub-node was found, we still need to set nports to + * one in order to be able to use the + * ahci_platform_[en|dis]able_[phys|regulators] functions. + */ + if (!child_nodes) + hpriv->nports = 1; + sz = hpriv->nports * sizeof(*hpriv->phys); + hpriv->phys = devm_kzalloc(dev, sz, GFP_KERNEL); + if (!hpriv->phys) { + rc = -ENOMEM; + goto err_out; + } + sz = hpriv->nports * sizeof(*hpriv->target_pwrs); + hpriv->target_pwrs = devm_kzalloc(dev, sz, GFP_KERNEL); + if (!hpriv->target_pwrs) { + rc = -ENOMEM; + goto err_out; + } + + if (child_nodes) { for_each_child_of_node(dev->of_node, child) { u32 port; + struct platform_device *port_dev; if (!of_device_is_available(child)) continue; @@ -316,18 +435,23 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) dev_warn(dev, "invalid port number %d\n", port); continue; } - mask_port_map |= BIT(port); - hpriv->phys[port] = devm_of_phy_get(dev, child, NULL); - if (IS_ERR(hpriv->phys[port])) { - rc = PTR_ERR(hpriv->phys[port]); - dev_err(dev, - "couldn't get PHY in node %s: %d\n", - child->name, rc); - goto err_out; + of_platform_device_create(child, NULL, NULL); + + port_dev = of_find_device_by_node(child); + + if (port_dev) { + rc = ahci_platform_get_regulator(hpriv, port, + &port_dev->dev); + if (rc == -EPROBE_DEFER) + goto err_out; } + rc = ahci_platform_get_phy(hpriv, port, dev, child); + if (rc) + goto err_out; + enabled_ports++; } if (!enabled_ports) { @@ -343,38 +467,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) * If no sub-node was found, keep this for device tree * compatibility */ - struct phy *phy = devm_phy_get(dev, "sata-phy"); - if (!IS_ERR(phy)) { - hpriv->phys = devm_kzalloc(dev, sizeof(*hpriv->phys), - GFP_KERNEL); - if (!hpriv->phys) { - rc = -ENOMEM; - goto err_out; - } - - hpriv->phys[0] = phy; - hpriv->nports = 1; - } else { - rc = PTR_ERR(phy); - switch (rc) { - case -ENOSYS: - /* No PHY support. Check if PHY is required. */ - if (of_find_property(dev->of_node, "phys", NULL)) { - dev_err(dev, "couldn't get sata-phy: ENOSYS\n"); - goto err_out; - } - case -ENODEV: - /* continue normally */ - hpriv->phys = NULL; - break; - - default: - goto err_out; + rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node); + if (rc) + goto err_out; - } - } + rc = ahci_platform_get_regulator(hpriv, 0, dev); + if (rc == -EPROBE_DEFER) + goto err_out; } - pm_runtime_enable(dev); pm_runtime_get_sync(dev); hpriv->got_runtime_pm = true; diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 642d6ae4030c..f65b33809170 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -24,6 +24,8 @@ struct platform_device; int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); +int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); +void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv); int ahci_platform_enable_resources(struct ahci_host_priv *hpriv); void ahci_platform_disable_resources(struct ahci_host_priv *hpriv); struct ahci_host_priv *ahci_platform_get_resources( -- cgit v1.2.3 From 67d0d04a762db4bd610fd628ad683b5d7dc905e7 Mon Sep 17 00:00:00 2001 From: Vincent Yang Date: Tue, 20 Jan 2015 16:05:16 +0800 Subject: mmc: sdhci: add a quirk for tuning work around This patch defines a quirk for tuning work around for some sdhci host controller. It sets both SDHCI_CTRL_EXEC_TUNING and SDHCI_CTRL_TUNED_CLK for tuning. It is a preparation and will be used by Fujitsu SDHCI controller f_sdh30 driver. Signed-off-by: Vincent Yang Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 2 ++ include/linux/mmc/sdhci.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 3e4fe967d7e5..a3ecd20e5510 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1961,6 +1961,8 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2); ctrl |= SDHCI_CTRL_EXEC_TUNING; + if (host->quirks2 & SDHCI_QUIRK2_TUNING_WORK_AROUND) + ctrl |= SDHCI_CTRL_TUNED_CLK; sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2); /* diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index cb8b94ff6a26..933b897ca095 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -111,6 +111,8 @@ struct sdhci_host { #define SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD (1<<10) /* Capability register bit-63 indicates HS400 support */ #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 (1<<11) +/* forced tuned clock */ +#define SDHCI_QUIRK2_TUNING_WORK_AROUND (1<<12) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.2.3 From d3fc5d71ac4dfd28a66689cfd1eea84c4dba8bde Mon Sep 17 00:00:00 2001 From: Vincent Yang Date: Tue, 20 Jan 2015 16:05:17 +0800 Subject: mmc: sdhci: add a quirk for single block transactions This patch defines a quirk to disable the block count for single block transactions. It is a preparation and will be used by Fujitsu SDHCI controller f_sdh30 driver. Signed-off-by: Vincent Yang Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 8 +++++--- include/linux/mmc/sdhci.h | 2 ++ 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index a3ecd20e5510..c9881ca131d5 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -904,7 +904,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd) static void sdhci_set_transfer_mode(struct sdhci_host *host, struct mmc_command *cmd) { - u16 mode; + u16 mode = 0; struct mmc_data *data = cmd->data; if (data == NULL) { @@ -922,9 +922,11 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host, WARN_ON(!host->data); - mode = SDHCI_TRNS_BLK_CNT_EN; + if (!(host->quirks2 & SDHCI_QUIRK2_SUPPORT_SINGLE)) + mode = SDHCI_TRNS_BLK_CNT_EN; + if (mmc_op_multi(cmd->opcode) || data->blocks > 1) { - mode |= SDHCI_TRNS_MULTI; + mode = SDHCI_TRNS_BLK_CNT_EN | SDHCI_TRNS_MULTI; /* * If we are sending CMD23, CMD12 never gets sent * on successful completion (so no Auto-CMD12). diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 933b897ca095..c3e3db196738 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -113,6 +113,8 @@ struct sdhci_host { #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 (1<<11) /* forced tuned clock */ #define SDHCI_QUIRK2_TUNING_WORK_AROUND (1<<12) +/* disable the block count for single block transactions */ +#define SDHCI_QUIRK2_SUPPORT_SINGLE (1<<13) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.2.3 From 94b110aff8679b14f46fd6653ea87b42fe1555be Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:22 +0000 Subject: mmc: tmio: add tmio_mmc_host_alloc/free() Current tmio_mmc driver is using tmio_mmc_data for driver/platform specific data/callback, and it is needed for tmio_mmc_host_probe() function. Because of this style, include/linux/mfd/tmio.h header has tmio driver/framework specific data which is not needed from platform. This patch adds new tmio_mmc_host_alloc/free() as cleanup preparation. tmio driver specific data/callback will be implemented in tmio_mmc_host, and platform specific data/callback will be implemented in tmio_mmc_data in this cleanup. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 14 +++++++++--- drivers/mmc/host/tmio_mmc.c | 10 +++++++-- drivers/mmc/host/tmio_mmc.h | 5 +++-- drivers/mmc/host/tmio_mmc_pio.c | 45 +++++++++++++++++++++++++-------------- include/linux/mfd/tmio.h | 1 - 5 files changed, 51 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 00c8ebdf8ec7..cf062c4d87a9 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -113,7 +113,7 @@ static int sh_mobile_sdhi_wait_idle(struct tmio_mmc_host *host) udelay(1); if (!timeout) { - dev_warn(host->pdata->dev, "timeout waiting for SD bus idle\n"); + dev_warn(&host->pdev->dev, "timeout waiting for SD bus idle\n"); return -EBUSY; } @@ -207,6 +207,12 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) goto eclkget; } + host = tmio_mmc_host_alloc(pdev); + if (!host) { + ret = -ENOMEM; + goto eprobe; + } + mmc_data->clk_enable = sh_mobile_sdhi_clk_enable; mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; @@ -274,9 +280,9 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) /* SD control register space size is 0x100, 0x200 for bus_shift=1 */ mmc_data->bus_shift = resource_size(res) >> 9; - ret = tmio_mmc_host_probe(&host, pdev, mmc_data); + ret = tmio_mmc_host_probe(host, mmc_data); if (ret < 0) - goto eprobe; + goto efree; /* * FIXME: @@ -351,6 +357,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) eirq: tmio_mmc_host_remove(host); +efree: + tmio_mmc_host_free(host); eprobe: eclkget: if (p && p->cleanup) diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c index 2ca0afaab792..a7c2e459187c 100644 --- a/drivers/mmc/host/tmio_mmc.c +++ b/drivers/mmc/host/tmio_mmc.c @@ -92,10 +92,14 @@ static int tmio_mmc_probe(struct platform_device *pdev) pdata->bus_shift = resource_size(res) >> 10; pdata->flags |= TMIO_MMC_HAVE_HIGH_REG; - ret = tmio_mmc_host_probe(&host, pdev, pdata); - if (ret) + host = tmio_mmc_host_alloc(pdev); + if (!host) goto cell_disable; + ret = tmio_mmc_host_probe(host, pdata); + if (ret) + goto host_free; + ret = request_irq(irq, tmio_mmc_irq, IRQF_TRIGGER_FALLING, dev_name(&pdev->dev), host); if (ret) @@ -108,6 +112,8 @@ static int tmio_mmc_probe(struct platform_device *pdev) host_remove: tmio_mmc_host_remove(host); +host_free: + tmio_mmc_host_free(host); cell_disable: if (cell->disable) cell->disable(pdev); diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index a34ecbe1c1ad..60d6747f0df5 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -85,8 +85,9 @@ struct tmio_mmc_host { bool sdio_irq_enabled; }; -int tmio_mmc_host_probe(struct tmio_mmc_host **host, - struct platform_device *pdev, +struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev); +void tmio_mmc_host_free(struct tmio_mmc_host *host); +int tmio_mmc_host_probe(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata); void tmio_mmc_host_remove(struct tmio_mmc_host *host); void tmio_mmc_do_data_irq(struct tmio_mmc_host *host); diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 250bf8c9f998..396be0e95a98 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -1054,12 +1054,37 @@ static void tmio_mmc_of_parse(struct platform_device *pdev, pdata->flags |= TMIO_MMC_WRPROTECT_DISABLE; } -int tmio_mmc_host_probe(struct tmio_mmc_host **host, - struct platform_device *pdev, - struct tmio_mmc_data *pdata) +struct tmio_mmc_host* +tmio_mmc_host_alloc(struct platform_device *pdev) { - struct tmio_mmc_host *_host; + struct tmio_mmc_host *host; struct mmc_host *mmc; + + mmc = mmc_alloc_host(sizeof(struct tmio_mmc_host), &pdev->dev); + if (!mmc) + return NULL; + + host = mmc_priv(mmc); + host->mmc = mmc; + host->pdev = pdev; + + return host; +} +EXPORT_SYMBOL(tmio_mmc_host_alloc); + +void tmio_mmc_host_free(struct tmio_mmc_host *host) +{ + mmc_free_host(host->mmc); + + host->mmc = NULL; +} +EXPORT_SYMBOL(tmio_mmc_host_free); + +int tmio_mmc_host_probe(struct tmio_mmc_host *_host, + struct tmio_mmc_data *pdata) +{ + struct platform_device *pdev = _host->pdev; + struct mmc_host *mmc = _host->mmc; struct resource *res_ctl; int ret; u32 irq_mask = TMIO_MASK_CMD; @@ -1073,19 +1098,11 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host, if (!res_ctl) return -EINVAL; - mmc = mmc_alloc_host(sizeof(struct tmio_mmc_host), &pdev->dev); - if (!mmc) - return -ENOMEM; - ret = mmc_of_parse(mmc); if (ret < 0) goto host_free; - pdata->dev = &pdev->dev; - _host = mmc_priv(mmc); _host->pdata = pdata; - _host->mmc = mmc; - _host->pdev = pdev; platform_set_drvdata(pdev, mmc); _host->set_pwr = pdata->set_pwr; @@ -1192,12 +1209,9 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host, mmc_gpiod_request_cd_irq(mmc); } - *host = _host; - return 0; host_free: - mmc_free_host(mmc); return ret; } @@ -1222,7 +1236,6 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host) pm_runtime_disable(&pdev->dev); iounmap(host->ctl); - mmc_free_host(mmc); } EXPORT_SYMBOL(tmio_mmc_host_remove); diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 57388171610d..c7d9af042d09 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -135,7 +135,6 @@ struct tmio_mmc_data { unsigned long bus_shift; u32 ocr_mask; /* available voltages */ struct tmio_mmc_dma *dma; - struct device *dev; unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From 7ecc09bab1e856e6730a4dd8a3bc1c28bb6ab3be Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:33 +0000 Subject: mmc: tmio: tmio_mmc_host has .dma Current .dma is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 4 ++-- drivers/mmc/host/tmio_mmc.h | 11 +++++++++++ drivers/mmc/host/tmio_mmc_dma.c | 24 +++++++++++------------- include/linux/mfd/tmio.h | 11 ----------- 4 files changed, 24 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index cf062c4d87a9..288e78d2c7a1 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -213,6 +213,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) goto eprobe; } + host->dma = dma_priv; + mmc_data->clk_enable = sh_mobile_sdhi_clk_enable; mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; @@ -241,8 +243,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) dma_priv->alignment_shift = 1; /* 2-byte alignment */ dma_priv->filter = shdma_chan_filter; - mmc_data->dma = dma_priv; - /* * All SDHI blocks support 2-byte and larger block sizes in 4-bit * bus width mode. diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 60d6747f0df5..49a2559ff489 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -40,6 +40,16 @@ struct tmio_mmc_data; +struct tmio_mmc_dma { + void *chan_priv_tx; + void *chan_priv_rx; + int slave_id_tx; + int slave_id_rx; + int alignment_shift; + dma_addr_t dma_rx_offset; + bool (*filter)(struct dma_chan *chan, void *arg); +}; + struct tmio_mmc_host { void __iomem *ctl; struct mmc_command *cmd; @@ -59,6 +69,7 @@ struct tmio_mmc_host { struct platform_device *pdev; struct tmio_mmc_data *pdata; + struct tmio_mmc_dma *dma; /* DMA support */ bool force_pio; diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index 7d077388b9eb..6c214d60bbb6 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -49,11 +49,10 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host) struct scatterlist *sg = host->sg_ptr, *sg_tmp; struct dma_async_tx_descriptor *desc = NULL; struct dma_chan *chan = host->chan_rx; - struct tmio_mmc_data *pdata = host->pdata; dma_cookie_t cookie; int ret, i; bool aligned = true, multiple = true; - unsigned int align = (1 << pdata->dma->alignment_shift) - 1; + unsigned int align = (1 << host->dma->alignment_shift) - 1; for_each_sg(sg, sg_tmp, host->sg_len, i) { if (sg_tmp->offset & align) @@ -126,11 +125,10 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host) struct scatterlist *sg = host->sg_ptr, *sg_tmp; struct dma_async_tx_descriptor *desc = NULL; struct dma_chan *chan = host->chan_tx; - struct tmio_mmc_data *pdata = host->pdata; dma_cookie_t cookie; int ret, i; bool aligned = true, multiple = true; - unsigned int align = (1 << pdata->dma->alignment_shift) - 1; + unsigned int align = (1 << host->dma->alignment_shift) - 1; for_each_sg(sg, sg_tmp, host->sg_len, i) { if (sg_tmp->offset & align) @@ -262,8 +260,8 @@ out: void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata) { /* We can only either use DMA for both Tx and Rx or not use it at all */ - if (!pdata->dma || (!host->pdev->dev.of_node && - (!pdata->dma->chan_priv_tx || !pdata->dma->chan_priv_rx))) + if (!host->dma || (!host->pdev->dev.of_node && + (!host->dma->chan_priv_tx || !host->dma->chan_priv_rx))) return; if (!host->chan_tx && !host->chan_rx) { @@ -280,7 +278,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat dma_cap_set(DMA_SLAVE, mask); host->chan_tx = dma_request_slave_channel_compat(mask, - pdata->dma->filter, pdata->dma->chan_priv_tx, + host->dma->filter, host->dma->chan_priv_tx, &host->pdev->dev, "tx"); dev_dbg(&host->pdev->dev, "%s: TX: got channel %p\n", __func__, host->chan_tx); @@ -288,8 +286,8 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (!host->chan_tx) return; - if (pdata->dma->chan_priv_tx) - cfg.slave_id = pdata->dma->slave_id_tx; + if (host->dma->chan_priv_tx) + cfg.slave_id = host->dma->slave_id_tx; cfg.direction = DMA_MEM_TO_DEV; cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->pdata->bus_shift); cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; @@ -299,7 +297,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat goto ecfgtx; host->chan_rx = dma_request_slave_channel_compat(mask, - pdata->dma->filter, pdata->dma->chan_priv_rx, + host->dma->filter, host->dma->chan_priv_rx, &host->pdev->dev, "rx"); dev_dbg(&host->pdev->dev, "%s: RX: got channel %p\n", __func__, host->chan_rx); @@ -307,10 +305,10 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (!host->chan_rx) goto ereqrx; - if (pdata->dma->chan_priv_rx) - cfg.slave_id = pdata->dma->slave_id_rx; + if (host->dma->chan_priv_rx) + cfg.slave_id = host->dma->slave_id_rx; cfg.direction = DMA_DEV_TO_MEM; - cfg.src_addr = cfg.dst_addr + pdata->dma->dma_rx_offset; + cfg.src_addr = cfg.dst_addr + host->dma->dma_rx_offset; cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; cfg.dst_addr = 0; ret = dmaengine_slave_config(host->chan_rx, &cfg); diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index c7d9af042d09..8d708c7cf681 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -112,16 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); struct dma_chan; -struct tmio_mmc_dma { - void *chan_priv_tx; - void *chan_priv_rx; - int slave_id_tx; - int slave_id_rx; - int alignment_shift; - dma_addr_t dma_rx_offset; - bool (*filter)(struct dma_chan *chan, void *arg); -}; - struct tmio_mmc_host; /* @@ -134,7 +124,6 @@ struct tmio_mmc_data { unsigned long flags; unsigned long bus_shift; u32 ocr_mask; /* available voltages */ - struct tmio_mmc_dma *dma; unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From dfe9a229e0a66b6a00439cea2885ad3b5d3e0840 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:42 +0000 Subject: mmc: tmio: tmio_mmc_host has .write16_hook Current .write16_hook is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 2 +- drivers/mmc/host/tmio_mmc.h | 4 +++- drivers/mmc/host/tmio_mmc_pio.c | 2 +- include/linux/mfd/tmio.h | 3 --- 4 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 288e78d2c7a1..77ff0620912e 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -214,11 +214,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) } host->dma = dma_priv; + host->write16_hook = sh_mobile_sdhi_write16_hook; mmc_data->clk_enable = sh_mobile_sdhi_clk_enable; mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; - mmc_data->write16_hook = sh_mobile_sdhi_write16_hook; mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; if (p) { mmc_data->flags = p->tmio_flags; diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 49a2559ff489..3fa96b11f76c 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -94,6 +94,8 @@ struct tmio_mmc_host { struct mutex ios_lock; /* protect set_ios() context */ bool native_hotplug; bool sdio_irq_enabled; + + int (*write16_hook)(struct tmio_mmc_host *host, int addr); }; struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev); @@ -183,7 +185,7 @@ static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val /* If there is a hook and it returns non-zero then there * is an error and the write should be skipped */ - if (host->pdata->write16_hook && host->pdata->write16_hook(host, addr)) + if (host->write16_hook && host->write16_hook(host, addr)) return; writew(val, host->ctl + (addr << host->pdata->bus_shift)); } diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 396be0e95a98..58f4e47aac8c 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -1092,7 +1092,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host, tmio_mmc_of_parse(pdev, pdata); if (!(pdata->flags & TMIO_MMC_HAS_IDLE_WAIT)) - pdata->write16_hook = NULL; + _host->write16_hook = NULL; res_ctl = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res_ctl) diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 8d708c7cf681..0872ca1e5dc2 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -112,8 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); struct dma_chan; -struct tmio_mmc_host; - /* * data for the MMC controller */ @@ -127,7 +125,6 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - int (*write16_hook)(struct tmio_mmc_host *host, int addr); /* clock management callbacks */ int (*clk_enable)(struct platform_device *pdev, unsigned int *f); void (*clk_disable)(struct platform_device *pdev); -- cgit v1.2.3 From 4fe2ec57a15f98c232536cf04e7c139d830955d4 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:52 +0000 Subject: mmc: tmio: tmio_mmc_host has .clk_enable Current .clk_enable is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 2 +- drivers/mmc/host/tmio_mmc.h | 1 + drivers/mmc/host/tmio_mmc_pio.c | 5 ++--- include/linux/mfd/tmio.h | 1 - 4 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 77ff0620912e..87af77dd660b 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -215,8 +215,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) host->dma = dma_priv; host->write16_hook = sh_mobile_sdhi_write16_hook; + host->clk_enable = sh_mobile_sdhi_clk_enable; - mmc_data->clk_enable = sh_mobile_sdhi_clk_enable; mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 3fa96b11f76c..5cd298665b94 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -96,6 +96,7 @@ struct tmio_mmc_host { bool sdio_irq_enabled; int (*write16_hook)(struct tmio_mmc_host *host, int addr); + int (*clk_enable)(struct platform_device *pdev, unsigned int *f); }; struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev); diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 58f4e47aac8c..38bcf0ca31c5 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -835,13 +835,12 @@ fail: static int tmio_mmc_clk_update(struct tmio_mmc_host *host) { struct mmc_host *mmc = host->mmc; - struct tmio_mmc_data *pdata = host->pdata; int ret; - if (!pdata->clk_enable) + if (!host->clk_enable) return -ENOTSUPP; - ret = pdata->clk_enable(host->pdev, &mmc->f_max); + ret = host->clk_enable(host->pdev, &mmc->f_max); if (!ret) mmc->f_min = mmc->f_max / 512; diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 0872ca1e5dc2..472587a02a42 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -126,7 +126,6 @@ struct tmio_mmc_data { void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); /* clock management callbacks */ - int (*clk_enable)(struct platform_device *pdev, unsigned int *f); void (*clk_disable)(struct platform_device *pdev); int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); -- cgit v1.2.3 From 00452c11ea0e4e5822edf0ac46853933860d0f53 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:01 +0000 Subject: mmc: tmio: tmio_mmc_host has .clk_disable Current .clk_disable is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 2 +- drivers/mmc/host/tmio_mmc.h | 1 + drivers/mmc/host/tmio_mmc_pio.c | 4 ++-- include/linux/mfd/tmio.h | 3 +-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 87af77dd660b..5e02a6a302e7 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -216,8 +216,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) host->dma = dma_priv; host->write16_hook = sh_mobile_sdhi_write16_hook; host->clk_enable = sh_mobile_sdhi_clk_enable; + host->clk_disable = sh_mobile_sdhi_clk_disable; - mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; if (p) { diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 5cd298665b94..28234ec5caa3 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -97,6 +97,7 @@ struct tmio_mmc_host { int (*write16_hook)(struct tmio_mmc_host *host, int addr); int (*clk_enable)(struct platform_device *pdev, unsigned int *f); + void (*clk_disable)(struct platform_device *pdev); }; struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev); diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 38bcf0ca31c5..e33eb8ee5eb5 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -1249,8 +1249,8 @@ int tmio_mmc_host_runtime_suspend(struct device *dev) if (host->clk_cache) tmio_mmc_clk_stop(host); - if (host->pdata->clk_disable) - host->pdata->clk_disable(host->pdev); + if (host->clk_disable) + host->clk_disable(host->pdev); return 0; } diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 472587a02a42..a3f78da70af7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -125,8 +125,7 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - /* clock management callbacks */ - void (*clk_disable)(struct platform_device *pdev); + int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); }; -- cgit v1.2.3 From 85c02ddd591e5252eb1cbe8743a839638d7415fd Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:10 +0000 Subject: mmc: tmio: tmio_mmc_host has .multi_io_quirk Current .multi_io_quirk is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 2 +- drivers/mmc/host/tmio_mmc.h | 2 ++ drivers/mmc/host/tmio_mmc_pio.c | 5 ++--- include/linux/mfd/tmio.h | 3 --- 4 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 5e02a6a302e7..c92efe59284d 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -217,9 +217,9 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) host->write16_hook = sh_mobile_sdhi_write16_hook; host->clk_enable = sh_mobile_sdhi_clk_enable; host->clk_disable = sh_mobile_sdhi_clk_disable; + host->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; - mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; if (p) { mmc_data->flags = p->tmio_flags; mmc_data->ocr_mask = p->tmio_ocr_mask; diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 28234ec5caa3..263256c897ed 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -98,6 +98,8 @@ struct tmio_mmc_host { int (*write16_hook)(struct tmio_mmc_host *host, int addr); int (*clk_enable)(struct platform_device *pdev, unsigned int *f); void (*clk_disable)(struct platform_device *pdev); + int (*multi_io_quirk)(struct mmc_card *card, + unsigned int direction, int blk_size); }; struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev); diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index e33eb8ee5eb5..a31c3573d386 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -1004,10 +1004,9 @@ static int tmio_multi_io_quirk(struct mmc_card *card, unsigned int direction, int blk_size) { struct tmio_mmc_host *host = mmc_priv(card->host); - struct tmio_mmc_data *pdata = host->pdata; - if (pdata->multi_io_quirk) - return pdata->multi_io_quirk(card, direction, blk_size); + if (host->multi_io_quirk) + return host->multi_io_quirk(card, direction, blk_size); return blk_size; } diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index a3f78da70af7..3edaa17d1ccd 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -125,9 +125,6 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - - int (*multi_io_quirk)(struct mmc_card *card, - unsigned int direction, int blk_size); }; /* -- cgit v1.2.3 From 7445bf9e6f4e5d7755e22c7c9b06f4ae0d6160c6 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:20 +0000 Subject: mmc: tmio: tmio_mmc_host has .bus_shift Current .bus_shift is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 5 ++--- drivers/mmc/host/tmio_mmc.c | 5 +++-- drivers/mmc/host/tmio_mmc.h | 17 +++++++++-------- drivers/mmc/host/tmio_mmc_dma.c | 2 +- include/linux/mfd/tmio.h | 1 - 5 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index c92efe59284d..0db2a0a0376b 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -218,6 +218,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) host->clk_enable = sh_mobile_sdhi_clk_enable; host->clk_disable = sh_mobile_sdhi_clk_disable; host->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk; + /* SD control register space size is 0x100, 0x200 for bus_shift=1 */ + host->bus_shift = resource_size(res) >> 9; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; if (p) { @@ -277,9 +279,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) dma_priv->dma_rx_offset = of_data->dma_rx_offset; } - /* SD control register space size is 0x100, 0x200 for bus_shift=1 */ - mmc_data->bus_shift = resource_size(res) >> 9; - ret = tmio_mmc_host_probe(host, mmc_data); if (ret < 0) goto efree; diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c index a7c2e459187c..f746df493892 100644 --- a/drivers/mmc/host/tmio_mmc.c +++ b/drivers/mmc/host/tmio_mmc.c @@ -88,14 +88,15 @@ static int tmio_mmc_probe(struct platform_device *pdev) if (!res) return -EINVAL; - /* SD control register space size is 0x200, 0x400 for bus_shift=1 */ - pdata->bus_shift = resource_size(res) >> 10; pdata->flags |= TMIO_MMC_HAVE_HIGH_REG; host = tmio_mmc_host_alloc(pdev); if (!host) goto cell_disable; + /* SD control register space size is 0x200, 0x400 for bus_shift=1 */ + host->bus_shift = resource_size(res) >> 10; + ret = tmio_mmc_host_probe(host, pdata); if (ret) goto host_free; diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 263256c897ed..a5d30bfa7e64 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -66,6 +66,7 @@ struct tmio_mmc_host { struct scatterlist *sg_orig; unsigned int sg_len; unsigned int sg_off; + unsigned long bus_shift; struct platform_device *pdev; struct tmio_mmc_data *pdata; @@ -169,19 +170,19 @@ int tmio_mmc_host_runtime_resume(struct device *dev); static inline u16 sd_ctrl_read16(struct tmio_mmc_host *host, int addr) { - return readw(host->ctl + (addr << host->pdata->bus_shift)); + return readw(host->ctl + (addr << host->bus_shift)); } static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr, u16 *buf, int count) { - readsw(host->ctl + (addr << host->pdata->bus_shift), buf, count); + readsw(host->ctl + (addr << host->bus_shift), buf, count); } static inline u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr) { - return readw(host->ctl + (addr << host->pdata->bus_shift)) | - readw(host->ctl + ((addr + 2) << host->pdata->bus_shift)) << 16; + return readw(host->ctl + (addr << host->bus_shift)) | + readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16; } static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val) @@ -191,19 +192,19 @@ static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val */ if (host->write16_hook && host->write16_hook(host, addr)) return; - writew(val, host->ctl + (addr << host->pdata->bus_shift)); + writew(val, host->ctl + (addr << host->bus_shift)); } static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr, u16 *buf, int count) { - writesw(host->ctl + (addr << host->pdata->bus_shift), buf, count); + writesw(host->ctl + (addr << host->bus_shift), buf, count); } static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val) { - writew(val, host->ctl + (addr << host->pdata->bus_shift)); - writew(val >> 16, host->ctl + ((addr + 2) << host->pdata->bus_shift)); + writew(val, host->ctl + (addr << host->bus_shift)); + writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift)); } diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index 6c214d60bbb6..ee0131eb078d 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -289,7 +289,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (host->dma->chan_priv_tx) cfg.slave_id = host->dma->slave_id_tx; cfg.direction = DMA_MEM_TO_DEV; - cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->pdata->bus_shift); + cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->bus_shift); cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; cfg.src_addr = 0; ret = dmaengine_slave_config(host->chan_tx, &cfg); diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 3edaa17d1ccd..7a5c27948315 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -120,7 +120,6 @@ struct tmio_mmc_data { unsigned long capabilities; unsigned long capabilities2; unsigned long flags; - unsigned long bus_shift; u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); -- cgit v1.2.3 From e471df0bcaa137f1bbe7c5f75db6ce7566caa292 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:46 +0000 Subject: mmc: tmio: tmio_mmc_data has .alignment_shift Current .alignment_shift is implemented under tmio_mmc_dma. It goes to tmio_mmc_data by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 4 ++-- drivers/mmc/host/tmio_mmc.h | 1 - drivers/mmc/host/tmio_mmc_dma.c | 4 ++-- include/linux/mfd/tmio.h | 1 + 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 0db2a0a0376b..782d8cf942a7 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -241,10 +241,10 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) dma_priv->slave_id_rx = p->dma_slave_rx; } } - - dma_priv->alignment_shift = 1; /* 2-byte alignment */ dma_priv->filter = shdma_chan_filter; + mmc_data->alignment_shift = 1; /* 2-byte alignment */ + /* * All SDHI blocks support 2-byte and larger block sizes in 4-bit * bus width mode. diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index a5d30bfa7e64..9482abceeb9c 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -45,7 +45,6 @@ struct tmio_mmc_dma { void *chan_priv_rx; int slave_id_tx; int slave_id_rx; - int alignment_shift; dma_addr_t dma_rx_offset; bool (*filter)(struct dma_chan *chan, void *arg); }; diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index ee0131eb078d..d2b02de2f378 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -52,7 +52,7 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host) dma_cookie_t cookie; int ret, i; bool aligned = true, multiple = true; - unsigned int align = (1 << host->dma->alignment_shift) - 1; + unsigned int align = (1 << host->pdata->alignment_shift) - 1; for_each_sg(sg, sg_tmp, host->sg_len, i) { if (sg_tmp->offset & align) @@ -128,7 +128,7 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host) dma_cookie_t cookie; int ret, i; bool aligned = true, multiple = true; - unsigned int align = (1 << host->dma->alignment_shift) - 1; + unsigned int align = (1 << host->pdata->alignment_shift) - 1; for_each_sg(sg, sg_tmp, host->sg_len, i) { if (sg_tmp->offset & align) diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 7a5c27948315..28a12d10e509 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -122,6 +122,7 @@ struct tmio_mmc_data { unsigned long flags; u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; + int alignment_shift; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 8b4c8f32da91681c0dcd321c9e3cd14f866c5517 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:56 +0000 Subject: mmc: tmio: tmio_mmc_data has .dma_rx_offset Current .dma_rx_offset is implemented under tmio_mmc_dma. It goes to tmio_mmc_data by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 2 +- drivers/mmc/host/tmio_mmc.h | 1 - drivers/mmc/host/tmio_mmc_dma.c | 2 +- include/linux/mfd/tmio.h | 1 + 4 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 782d8cf942a7..c06e93b77995 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -276,7 +276,7 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) mmc_data->flags |= of_data->tmio_flags; mmc_data->capabilities |= of_data->capabilities; mmc_data->capabilities2 |= of_data->capabilities2; - dma_priv->dma_rx_offset = of_data->dma_rx_offset; + mmc_data->dma_rx_offset = of_data->dma_rx_offset; } ret = tmio_mmc_host_probe(host, mmc_data); diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 9482abceeb9c..c9a84695cff2 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -45,7 +45,6 @@ struct tmio_mmc_dma { void *chan_priv_rx; int slave_id_tx; int slave_id_rx; - dma_addr_t dma_rx_offset; bool (*filter)(struct dma_chan *chan, void *arg); }; diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index d2b02de2f378..634b2700cb77 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -308,7 +308,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (host->dma->chan_priv_rx) cfg.slave_id = host->dma->slave_id_rx; cfg.direction = DMA_DEV_TO_MEM; - cfg.src_addr = cfg.dst_addr + host->dma->dma_rx_offset; + cfg.src_addr = cfg.dst_addr + host->pdata->dma_rx_offset; cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; cfg.dst_addr = 0; ret = dmaengine_slave_config(host->chan_rx, &cfg); diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 28a12d10e509..807ecfb162d7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -123,6 +123,7 @@ struct tmio_mmc_data { u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; int alignment_shift; + dma_addr_t dma_rx_offset; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 010f4aa758f437647799b1fd677a5e2cf31714e9 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:59:24 +0000 Subject: mmc: sh_mobile_sdhi: remove .init/.cleanup No one is using .init/.cleanup callback function. Let's remove these. sdhi_ops and .cd_wakeup are also removed Signed-off-by: Kuninori Morimoto Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 26 +------------------------- include/linux/mmc/sh_mobile_sdhi.h | 15 --------------- 2 files changed, 1 insertion(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index c06e93b77995..48a3be804cc0 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -156,15 +156,6 @@ static int sh_mobile_sdhi_multi_io_quirk(struct mmc_card *card, return blk_size; } -static void sh_mobile_sdhi_cd_wakeup(const struct platform_device *pdev) -{ - mmc_detect_change(platform_get_drvdata(pdev), msecs_to_jiffies(100)); -} - -static const struct sh_mobile_sdhi_ops sdhi_ops = { - .cd_wakeup = sh_mobile_sdhi_cd_wakeup, -}; - static int sh_mobile_sdhi_probe(struct platform_device *pdev) { const struct of_device_id *of_id = @@ -192,19 +183,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) mmc_data = &priv->mmc_data; dma_priv = &priv->dma_priv; - if (p) { - if (p->init) { - ret = p->init(pdev, &sdhi_ops); - if (ret) - return ret; - } - } - priv->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(priv->clk)) { ret = PTR_ERR(priv->clk); dev_err(&pdev->dev, "cannot get clock: %d\n", ret); - goto eclkget; + goto eprobe; } host = tmio_mmc_host_alloc(pdev); @@ -359,9 +342,6 @@ eirq: efree: tmio_mmc_host_free(host); eprobe: -eclkget: - if (p && p->cleanup) - p->cleanup(pdev); return ret; } @@ -369,13 +349,9 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev) { struct mmc_host *mmc = platform_get_drvdata(pdev); struct tmio_mmc_host *host = mmc_priv(mmc); - struct sh_mobile_sdhi_info *p = pdev->dev.platform_data; tmio_mmc_host_remove(host); - if (p && p->cleanup) - p->cleanup(pdev); - return 0; } diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index 68927ae50845..da77e5e2041d 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -3,20 +3,10 @@ #include -struct platform_device; - #define SH_MOBILE_SDHI_IRQ_CARD_DETECT "card_detect" #define SH_MOBILE_SDHI_IRQ_SDCARD "sdcard" #define SH_MOBILE_SDHI_IRQ_SDIO "sdio" -/** - * struct sh_mobile_sdhi_ops - SDHI driver callbacks - * @cd_wakeup: trigger a card-detection run - */ -struct sh_mobile_sdhi_ops { - void (*cd_wakeup)(const struct platform_device *pdev); -}; - struct sh_mobile_sdhi_info { int dma_slave_tx; int dma_slave_rx; @@ -25,11 +15,6 @@ struct sh_mobile_sdhi_info { unsigned long tmio_caps2; u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; - - /* callbacks for board specific setup code */ - int (*init)(struct platform_device *pdev, - const struct sh_mobile_sdhi_ops *ops); - void (*cleanup)(struct platform_device *pdev); }; #endif /* LINUX_MMC_SH_MOBILE_SDHI_H */ -- cgit v1.2.3 From de122cb1745313f331dc7c7923b484343d455e64 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 05:00:39 +0000 Subject: mmc: tmio: remove TMIO_MMC_HAVE_CTL_DMA_REG flag tmio_mmc_host has .enable_dma callback now. We don't need TMIO_MMC_HAVE_CTL_DMA_REG anymore. Let's remove it Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mobile_sdhi.c | 5 ----- drivers/mmc/host/tmio_mmc_dma.c | 3 --- include/linux/mfd/tmio.h | 5 ----- 3 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 7dbcb577f596..6906a905cd54 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -291,11 +291,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) */ mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK; - /* - * All SDHI have DMA control register - */ - mmc_data->flags |= TMIO_MMC_HAVE_CTL_DMA_REG; - if (of_id && of_id->data) { const struct sh_mobile_sdhi_of_data *of_data = of_id->data; mmc_data->flags |= of_data->tmio_flags; diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index aa5f4b6e790d..331bb618e398 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -28,9 +28,6 @@ void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable) if (!host->chan_tx || !host->chan_rx) return; - if (host->pdata->flags & TMIO_MMC_HAVE_CTL_DMA_REG) - sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0); - if (host->dma->enable) host->dma->enable(host, enable); } diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 807ecfb162d7..605812820e48 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -95,11 +95,6 @@ */ #define TMIO_MMC_SDIO_STATUS_QUIRK (1 << 8) -/* - * Some controllers have DMA enable/disable register - */ -#define TMIO_MMC_HAVE_CTL_DMA_REG (1 << 9) - /* * Some controllers allows to set SDx actual clock */ -- cgit v1.2.3 From 1dfb4a0d7615811ec4a61b0a7631c8ddc0baf335 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 13 Jan 2015 08:00:29 +0100 Subject: gpio: stmpe: enforce device tree only mode Require that device tree be used with STMPE (all platforms use this) and enforce OF_GPIO, then delete the platform data. Signed-off-by: Linus Walleij --- drivers/gpio/Kconfig | 1 + drivers/gpio/gpio-stmpe.c | 23 +++-------------------- include/linux/mfd/stmpe.h | 16 ---------------- 3 files changed, 4 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 4187fcbc88fd..22b46567b3bb 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -644,6 +644,7 @@ config GPIO_SX150X config GPIO_STMPE bool "STMPE GPIOs" depends on MFD_STMPE + depends on OF_GPIO select GPIOLIB_IRQCHIP help This enables support for the GPIOs found on the STMPE I/O diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index 85c5b1974294..dabfb99dddef 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -30,7 +30,7 @@ struct stmpe_gpio { struct stmpe *stmpe; struct device *dev; struct mutex irq_lock; - unsigned norequest_mask; + u32 norequest_mask; /* Caches of interrupt control registers for bus_lock */ u8 regs[CACHE_NR_REGS][CACHE_NR_BANKS]; u8 oldregs[CACHE_NR_REGS][CACHE_NR_BANKS]; @@ -340,13 +340,10 @@ static int stmpe_gpio_probe(struct platform_device *pdev) { struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent); struct device_node *np = pdev->dev.of_node; - struct stmpe_gpio_platform_data *pdata; struct stmpe_gpio *stmpe_gpio; int ret; int irq = 0; - pdata = stmpe->pdata->gpio; - irq = platform_get_irq(pdev, 0); stmpe_gpio = kzalloc(sizeof(struct stmpe_gpio), GFP_KERNEL); @@ -360,19 +357,14 @@ static int stmpe_gpio_probe(struct platform_device *pdev) stmpe_gpio->chip = template_chip; stmpe_gpio->chip.ngpio = stmpe->num_gpios; stmpe_gpio->chip.dev = &pdev->dev; -#ifdef CONFIG_OF stmpe_gpio->chip.of_node = np; -#endif stmpe_gpio->chip.base = -1; if (IS_ENABLED(CONFIG_DEBUG_FS)) stmpe_gpio->chip.dbg_show = stmpe_dbg_show; - if (pdata) - stmpe_gpio->norequest_mask = pdata->norequest_mask; - else if (np) - of_property_read_u32(np, "st,norequest-mask", - &stmpe_gpio->norequest_mask); + of_property_read_u32(np, "st,norequest-mask", + &stmpe_gpio->norequest_mask); if (irq < 0) dev_info(&pdev->dev, @@ -414,9 +406,6 @@ static int stmpe_gpio_probe(struct platform_device *pdev) NULL); } - if (pdata && pdata->setup) - pdata->setup(stmpe, stmpe_gpio->chip.base); - platform_set_drvdata(pdev, stmpe_gpio); return 0; @@ -433,15 +422,9 @@ static int stmpe_gpio_remove(struct platform_device *pdev) { struct stmpe_gpio *stmpe_gpio = platform_get_drvdata(pdev); struct stmpe *stmpe = stmpe_gpio->stmpe; - struct stmpe_gpio_platform_data *pdata = stmpe->pdata->gpio; - - if (pdata && pdata->remove) - pdata->remove(stmpe, stmpe_gpio->chip.base); gpiochip_remove(&stmpe_gpio->chip); - stmpe_disable(stmpe, STMPE_BLOCK_GPIO); - kfree(stmpe_gpio); return 0; diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index f742b6717d52..c9d869027300 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -117,20 +117,6 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) -/** - * struct stmpe_gpio_platform_data - STMPE GPIO platform data - * @norequest_mask: bitmask specifying which GPIOs should _not_ be - * requestable due to different usage (e.g. touch, keypad) - * STMPE_GPIO_NOREQ_* macros can be used here. - * @setup: board specific setup callback. - * @remove: board specific remove callback - */ -struct stmpe_gpio_platform_data { - unsigned norequest_mask; - void (*setup)(struct stmpe *stmpe, unsigned gpio_base); - void (*remove)(struct stmpe *stmpe, unsigned gpio_base); -}; - /** * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform * data @@ -182,7 +168,6 @@ struct stmpe_ts_platform_data { * @irq_over_gpio: true if gpio is used to get irq * @irq_gpio: gpio number over which irq will be requested (significant only if * irq_over_gpio is true) - * @gpio: GPIO-specific platform data * @ts: touchscreen-specific platform data */ struct stmpe_platform_data { @@ -194,7 +179,6 @@ struct stmpe_platform_data { int irq_gpio; int autosleep_timeout; - struct stmpe_gpio_platform_data *gpio; struct stmpe_ts_platform_data *ts; }; -- cgit v1.2.3 From 4b6eade76ad19183464b739e9af1efacdb1bbda8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 20 Jan 2015 11:00:53 +0100 Subject: mfd: max77693: Add defines for MAX77693 charger driver Prepare for adding support for Maxim 77693 charger by adding necessary new defines. Signed-off-by: Krzysztof Kozlowski Acked-by: Lee Jones Signed-off-by: Sebastian Reichel --- include/linux/mfd/max77693-private.h | 108 +++++++++++++++++++++++++++++++++++ 1 file changed, 108 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 08dae01258b9..955dd990beaf 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -143,10 +143,118 @@ enum max77693_pmic_reg { #define FLASH_INT_FLED1_SHORT BIT(3) #define FLASH_INT_OVER_CURRENT BIT(4) +/* Fast charge timer in in hours */ +#define DEFAULT_FAST_CHARGE_TIMER 4 +/* microamps */ +#define DEFAULT_TOP_OFF_THRESHOLD_CURRENT 150000 +/* minutes */ +#define DEFAULT_TOP_OFF_TIMER 30 +/* microvolts */ +#define DEFAULT_CONSTANT_VOLT 4200000 +/* microvolts */ +#define DEFAULT_MIN_SYSTEM_VOLT 3600000 +/* celsius */ +#define DEFAULT_THERMAL_REGULATION_TEMP 100 +/* microamps */ +#define DEFAULT_BATTERY_OVERCURRENT 3500000 +/* microvolts */ +#define DEFAULT_CHARGER_INPUT_THRESHOLD_VOLT 4300000 + +/* MAX77693_CHG_REG_CHG_INT_OK register */ +#define CHG_INT_OK_BYP_SHIFT 0 +#define CHG_INT_OK_BAT_SHIFT 3 +#define CHG_INT_OK_CHG_SHIFT 4 +#define CHG_INT_OK_CHGIN_SHIFT 6 +#define CHG_INT_OK_DETBAT_SHIFT 7 +#define CHG_INT_OK_BYP_MASK BIT(CHG_INT_OK_BYP_SHIFT) +#define CHG_INT_OK_BAT_MASK BIT(CHG_INT_OK_BAT_SHIFT) +#define CHG_INT_OK_CHG_MASK BIT(CHG_INT_OK_CHG_SHIFT) +#define CHG_INT_OK_CHGIN_MASK BIT(CHG_INT_OK_CHGIN_SHIFT) +#define CHG_INT_OK_DETBAT_MASK BIT(CHG_INT_OK_DETBAT_SHIFT) + +/* MAX77693_CHG_REG_CHG_DETAILS_00 register */ +#define CHG_DETAILS_00_CHGIN_SHIFT 5 +#define CHG_DETAILS_00_CHGIN_MASK (0x3 << CHG_DETAILS_00_CHGIN_SHIFT) + +/* MAX77693_CHG_REG_CHG_DETAILS_01 register */ +#define CHG_DETAILS_01_CHG_SHIFT 0 +#define CHG_DETAILS_01_BAT_SHIFT 4 +#define CHG_DETAILS_01_TREG_SHIFT 7 +#define CHG_DETAILS_01_CHG_MASK (0xf << CHG_DETAILS_01_CHG_SHIFT) +#define CHG_DETAILS_01_BAT_MASK (0x7 << CHG_DETAILS_01_BAT_SHIFT) +#define CHG_DETAILS_01_TREG_MASK BIT(7) + +/* MAX77693_CHG_REG_CHG_DETAILS_01/CHG field */ +enum max77693_charger_charging_state { + MAX77693_CHARGING_PREQUALIFICATION = 0x0, + MAX77693_CHARGING_FAST_CONST_CURRENT, + MAX77693_CHARGING_FAST_CONST_VOLTAGE, + MAX77693_CHARGING_TOP_OFF, + MAX77693_CHARGING_DONE, + MAX77693_CHARGING_HIGH_TEMP, + MAX77693_CHARGING_TIMER_EXPIRED, + MAX77693_CHARGING_THERMISTOR_SUSPEND, + MAX77693_CHARGING_OFF, + MAX77693_CHARGING_RESERVED, + MAX77693_CHARGING_OVER_TEMP, + MAX77693_CHARGING_WATCHDOG_EXPIRED, +}; + +/* MAX77693_CHG_REG_CHG_DETAILS_01/BAT field */ +enum max77693_charger_battery_state { + MAX77693_BATTERY_NOBAT = 0x0, + /* Dead-battery or low-battery prequalification */ + MAX77693_BATTERY_PREQUALIFICATION, + MAX77693_BATTERY_TIMER_EXPIRED, + MAX77693_BATTERY_GOOD, + MAX77693_BATTERY_LOWVOLTAGE, + MAX77693_BATTERY_OVERVOLTAGE, + MAX77693_BATTERY_OVERCURRENT, + MAX77693_BATTERY_RESERVED, +}; + +/* MAX77693_CHG_REG_CHG_DETAILS_02 register */ +#define CHG_DETAILS_02_BYP_SHIFT 0 +#define CHG_DETAILS_02_BYP_MASK (0xf << CHG_DETAILS_02_BYP_SHIFT) + /* MAX77693 CHG_CNFG_00 register */ #define CHG_CNFG_00_CHG_MASK 0x1 #define CHG_CNFG_00_BUCK_MASK 0x4 +/* MAX77693_CHG_REG_CHG_CNFG_01 register */ +#define CHG_CNFG_01_FCHGTIME_SHIFT 0 +#define CHG_CNFG_01_CHGRSTRT_SHIFT 4 +#define CHG_CNFG_01_PQEN_SHIFT 7 +#define CHG_CNFG_01_FCHGTIME_MASK (0x7 << CHG_CNFG_01_FCHGTIME_SHIFT) +#define CHG_CNFG_01_CHGRSTRT_MASK (0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT) +#define CHG_CNFG_01_PQEN_MAKS BIT(CHG_CNFG_01_PQEN_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_03 register */ +#define CHG_CNFG_03_TOITH_SHIFT 0 +#define CHG_CNFG_03_TOTIME_SHIFT 3 +#define CHG_CNFG_03_TOITH_MASK (0x7 << CHG_CNFG_03_TOITH_SHIFT) +#define CHG_CNFG_03_TOTIME_MASK (0x7 << CHG_CNFG_03_TOTIME_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_04 register */ +#define CHG_CNFG_04_CHGCVPRM_SHIFT 0 +#define CHG_CNFG_04_MINVSYS_SHIFT 5 +#define CHG_CNFG_04_CHGCVPRM_MASK (0x1f << CHG_CNFG_04_CHGCVPRM_SHIFT) +#define CHG_CNFG_04_MINVSYS_MASK (0x7 << CHG_CNFG_04_MINVSYS_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_06 register */ +#define CHG_CNFG_06_CHGPROT_SHIFT 2 +#define CHG_CNFG_06_CHGPROT_MASK (0x3 << CHG_CNFG_06_CHGPROT_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_07 register */ +#define CHG_CNFG_07_REGTEMP_SHIFT 5 +#define CHG_CNFG_07_REGTEMP_MASK (0x3 << CHG_CNFG_07_REGTEMP_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_12 register */ +#define CHG_CNFG_12_B2SOVRC_SHIFT 0 +#define CHG_CNFG_12_VCHGINREG_SHIFT 3 +#define CHG_CNFG_12_B2SOVRC_MASK (0x7 << CHG_CNFG_12_B2SOVRC_SHIFT) +#define CHG_CNFG_12_VCHGINREG_MASK (0x3 << CHG_CNFG_12_VCHGINREG_SHIFT) + /* MAX77693 CHG_CNFG_09 Register */ #define CHG_CNFG_09_CHGIN_ILIM_MASK 0x7F -- cgit v1.2.3 From 39e794bff718188cfb9ace2032cbe4fd86048dc6 Mon Sep 17 00:00:00 2001 From: Yaniv Gardi Date: Thu, 15 Jan 2015 16:32:36 +0200 Subject: phy: qcom-ufs: add support for 20nm phy This change adds a support for a 20nm qcom-ufs phy that is required in platforms that use ufs-qcom controller. Signed-off-by: Yaniv Gardi Reviewed-by: Dov Levenglick Signed-off-by: Christoph Hellwig --- drivers/phy/Makefile | 1 + drivers/phy/phy-qcom-ufs-i.h | 43 +++++- drivers/phy/phy-qcom-ufs-qmp-20nm.c | 257 ++++++++++++++++++++++++++++++++++++ drivers/phy/phy-qcom-ufs-qmp-20nm.h | 235 +++++++++++++++++++++++++++++++++ include/linux/phy/phy-qcom-ufs.h | 59 +++++++++ 5 files changed, 594 insertions(+), 1 deletion(-) create mode 100644 drivers/phy/phy-qcom-ufs-qmp-20nm.c create mode 100644 drivers/phy/phy-qcom-ufs-qmp-20nm.h create mode 100644 include/linux/phy/phy-qcom-ufs.h (limited to 'include/linux') diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile index 335965d3a9b7..781b2fa46d09 100644 --- a/drivers/phy/Makefile +++ b/drivers/phy/Makefile @@ -35,3 +35,4 @@ obj-$(CONFIG_PHY_XGENE) += phy-xgene.o obj-$(CONFIG_PHY_STIH407_USB) += phy-stih407-usb.o obj-$(CONFIG_PHY_STIH41X_USB) += phy-stih41x-usb.o obj-$(CONFIG_PHY_QCOM_UFS) += phy-qcom-ufs.o +obj-$(CONFIG_PHY_QCOM_UFS) += phy-qcom-ufs-qmp-20nm.o diff --git a/drivers/phy/phy-qcom-ufs-i.h b/drivers/phy/phy-qcom-ufs-i.h index dac200f4d639..591a39175e8a 100644 --- a/drivers/phy/phy-qcom-ufs-i.h +++ b/drivers/phy/phy-qcom-ufs-i.h @@ -15,15 +15,56 @@ #ifndef UFS_QCOM_PHY_I_H_ #define UFS_QCOM_PHY_I_H_ +#include #include +#include #include -#include +#include #include #include #include +#define readl_poll_timeout(addr, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + might_sleep_if(timeout_us); \ + for (;;) { \ + (val) = readl(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + (val) = readl(addr); \ + break; \ + } \ + if (sleep_us) \ + usleep_range(DIV_ROUND_UP(sleep_us, 4), sleep_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + +#define UFS_QCOM_PHY_CAL_ENTRY(reg, val) \ + { \ + .reg_offset = reg, \ + .cfg_value = val, \ + } + #define UFS_QCOM_PHY_NAME_LEN 30 +enum { + MASK_SERDES_START = 0x1, + MASK_PCS_READY = 0x1, +}; + +enum { + OFFSET_SERDES_START = 0x0, +}; + +struct ufs_qcom_phy_stored_attributes { + u32 att; + u32 value; +}; + + struct ufs_qcom_phy_calibration { u32 reg_offset; u32 cfg_value; diff --git a/drivers/phy/phy-qcom-ufs-qmp-20nm.c b/drivers/phy/phy-qcom-ufs-qmp-20nm.c new file mode 100644 index 000000000000..8332f96b2c4a --- /dev/null +++ b/drivers/phy/phy-qcom-ufs-qmp-20nm.c @@ -0,0 +1,257 @@ +/* + * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include "phy-qcom-ufs-qmp-20nm.h" + +#define UFS_PHY_NAME "ufs_phy_qmp_20nm" + +static +int ufs_qcom_phy_qmp_20nm_phy_calibrate(struct ufs_qcom_phy *ufs_qcom_phy, + bool is_rate_B) +{ + struct ufs_qcom_phy_calibration *tbl_A, *tbl_B; + int tbl_size_A, tbl_size_B; + u8 major = ufs_qcom_phy->host_ctrl_rev_major; + u16 minor = ufs_qcom_phy->host_ctrl_rev_minor; + u16 step = ufs_qcom_phy->host_ctrl_rev_step; + int err; + + if ((major == 0x1) && (minor == 0x002) && (step == 0x0000)) { + tbl_size_A = ARRAY_SIZE(phy_cal_table_rate_A_1_2_0); + tbl_A = phy_cal_table_rate_A_1_2_0; + } else if ((major == 0x1) && (minor == 0x003) && (step == 0x0000)) { + tbl_size_A = ARRAY_SIZE(phy_cal_table_rate_A_1_3_0); + tbl_A = phy_cal_table_rate_A_1_3_0; + } else { + dev_err(ufs_qcom_phy->dev, "%s: Unknown UFS-PHY version, no calibration values\n", + __func__); + err = -ENODEV; + goto out; + } + + tbl_size_B = ARRAY_SIZE(phy_cal_table_rate_B); + tbl_B = phy_cal_table_rate_B; + + err = ufs_qcom_phy_calibrate(ufs_qcom_phy, tbl_A, tbl_size_A, + tbl_B, tbl_size_B, is_rate_B); + + if (err) + dev_err(ufs_qcom_phy->dev, "%s: ufs_qcom_phy_calibrate() failed %d\n", + __func__, err); + +out: + return err; +} + +static +void ufs_qcom_phy_qmp_20nm_advertise_quirks(struct ufs_qcom_phy *phy_common) +{ + phy_common->quirks = + UFS_QCOM_PHY_QUIRK_HIBERN8_EXIT_AFTER_PHY_PWR_COLLAPSE; +} + +static int ufs_qcom_phy_qmp_20nm_init(struct phy *generic_phy) +{ + struct ufs_qcom_phy_qmp_20nm *phy = phy_get_drvdata(generic_phy); + struct ufs_qcom_phy *phy_common = &phy->common_cfg; + int err = 0; + + err = ufs_qcom_phy_init_clks(generic_phy, phy_common); + if (err) { + dev_err(phy_common->dev, "%s: ufs_qcom_phy_init_clks() failed %d\n", + __func__, err); + goto out; + } + + err = ufs_qcom_phy_init_vregulators(generic_phy, phy_common); + if (err) { + dev_err(phy_common->dev, "%s: ufs_qcom_phy_init_vregulators() failed %d\n", + __func__, err); + goto out; + } + + ufs_qcom_phy_qmp_20nm_advertise_quirks(phy_common); + +out: + return err; +} + +static +void ufs_qcom_phy_qmp_20nm_power_control(struct ufs_qcom_phy *phy, bool val) +{ + bool hibern8_exit_after_pwr_collapse = phy->quirks & + UFS_QCOM_PHY_QUIRK_HIBERN8_EXIT_AFTER_PHY_PWR_COLLAPSE; + + if (val) { + writel_relaxed(0x1, phy->mmio + UFS_PHY_POWER_DOWN_CONTROL); + /* + * Before any transactions involving PHY, ensure PHY knows + * that it's analog rail is powered ON. + */ + mb(); + + if (hibern8_exit_after_pwr_collapse) { + /* + * Give atleast 1us delay after restoring PHY analog + * power. + */ + usleep_range(1, 2); + writel_relaxed(0x0A, phy->mmio + + QSERDES_COM_SYSCLK_EN_SEL_TXBAND); + writel_relaxed(0x08, phy->mmio + + QSERDES_COM_SYSCLK_EN_SEL_TXBAND); + /* + * Make sure workaround is deactivated before proceeding + * with normal PHY operations. + */ + mb(); + } + } else { + if (hibern8_exit_after_pwr_collapse) { + writel_relaxed(0x0A, phy->mmio + + QSERDES_COM_SYSCLK_EN_SEL_TXBAND); + writel_relaxed(0x02, phy->mmio + + QSERDES_COM_SYSCLK_EN_SEL_TXBAND); + /* + * Make sure that above workaround is activated before + * PHY analog power collapse. + */ + mb(); + } + + writel_relaxed(0x0, phy->mmio + UFS_PHY_POWER_DOWN_CONTROL); + /* + * ensure that PHY knows its PHY analog rail is going + * to be powered down + */ + mb(); + } +} + +static +void ufs_qcom_phy_qmp_20nm_set_tx_lane_enable(struct ufs_qcom_phy *phy, u32 val) +{ + writel_relaxed(val & UFS_PHY_TX_LANE_ENABLE_MASK, + phy->mmio + UFS_PHY_TX_LANE_ENABLE); + mb(); +} + +static inline void ufs_qcom_phy_qmp_20nm_start_serdes(struct ufs_qcom_phy *phy) +{ + u32 tmp; + + tmp = readl_relaxed(phy->mmio + UFS_PHY_PHY_START); + tmp &= ~MASK_SERDES_START; + tmp |= (1 << OFFSET_SERDES_START); + writel_relaxed(tmp, phy->mmio + UFS_PHY_PHY_START); + mb(); +} + +static int ufs_qcom_phy_qmp_20nm_is_pcs_ready(struct ufs_qcom_phy *phy_common) +{ + int err = 0; + u32 val; + + err = readl_poll_timeout(phy_common->mmio + UFS_PHY_PCS_READY_STATUS, + val, (val & MASK_PCS_READY), 10, 1000000); + if (err) + dev_err(phy_common->dev, "%s: poll for pcs failed err = %d\n", + __func__, err); + return err; +} + +static struct phy_ops ufs_qcom_phy_qmp_20nm_phy_ops = { + .init = ufs_qcom_phy_qmp_20nm_init, + .exit = ufs_qcom_phy_exit, + .power_on = ufs_qcom_phy_power_on, + .power_off = ufs_qcom_phy_power_off, + .owner = THIS_MODULE, +}; + +static struct ufs_qcom_phy_specific_ops phy_20nm_ops = { + .calibrate_phy = ufs_qcom_phy_qmp_20nm_phy_calibrate, + .start_serdes = ufs_qcom_phy_qmp_20nm_start_serdes, + .is_physical_coding_sublayer_ready = ufs_qcom_phy_qmp_20nm_is_pcs_ready, + .set_tx_lane_enable = ufs_qcom_phy_qmp_20nm_set_tx_lane_enable, + .power_control = ufs_qcom_phy_qmp_20nm_power_control, +}; + +static int ufs_qcom_phy_qmp_20nm_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct phy *generic_phy; + struct ufs_qcom_phy_qmp_20nm *phy; + int err = 0; + + phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL); + if (!phy) { + dev_err(dev, "%s: failed to allocate phy\n", __func__); + err = -ENOMEM; + goto out; + } + + generic_phy = ufs_qcom_phy_generic_probe(pdev, &phy->common_cfg, + &ufs_qcom_phy_qmp_20nm_phy_ops, &phy_20nm_ops); + + if (!generic_phy) { + dev_err(dev, "%s: ufs_qcom_phy_generic_probe() failed\n", + __func__); + err = -EIO; + goto out; + } + + phy_set_drvdata(generic_phy, phy); + + strlcpy(phy->common_cfg.name, UFS_PHY_NAME, + sizeof(phy->common_cfg.name)); + +out: + return err; +} + +static int ufs_qcom_phy_qmp_20nm_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct phy *generic_phy = to_phy(dev); + struct ufs_qcom_phy *ufs_qcom_phy = get_ufs_qcom_phy(generic_phy); + int err = 0; + + err = ufs_qcom_phy_remove(generic_phy, ufs_qcom_phy); + if (err) + dev_err(dev, "%s: ufs_qcom_phy_remove failed = %d\n", + __func__, err); + + return err; +} + +static const struct of_device_id ufs_qcom_phy_qmp_20nm_of_match[] = { + {.compatible = "qcom,ufs-phy-qmp-20nm"}, + {}, +}; +MODULE_DEVICE_TABLE(of, ufs_qcom_phy_qmp_20nm_of_match); + +static struct platform_driver ufs_qcom_phy_qmp_20nm_driver = { + .probe = ufs_qcom_phy_qmp_20nm_probe, + .remove = ufs_qcom_phy_qmp_20nm_remove, + .driver = { + .of_match_table = ufs_qcom_phy_qmp_20nm_of_match, + .name = "ufs_qcom_phy_qmp_20nm", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(ufs_qcom_phy_qmp_20nm_driver); + +MODULE_DESCRIPTION("Universal Flash Storage (UFS) QCOM PHY QMP 20nm"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-qcom-ufs-qmp-20nm.h b/drivers/phy/phy-qcom-ufs-qmp-20nm.h new file mode 100644 index 000000000000..4f3076bb3d71 --- /dev/null +++ b/drivers/phy/phy-qcom-ufs-qmp-20nm.h @@ -0,0 +1,235 @@ +/* + * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef UFS_QCOM_PHY_QMP_20NM_H_ +#define UFS_QCOM_PHY_QMP_20NM_H_ + +#include "phy-qcom-ufs-i.h" + +/* QCOM UFS PHY control registers */ + +#define COM_OFF(x) (0x000 + x) +#define PHY_OFF(x) (0xC00 + x) +#define TX_OFF(n, x) (0x400 + (0x400 * n) + x) +#define RX_OFF(n, x) (0x600 + (0x400 * n) + x) + +/* UFS PHY PLL block registers */ +#define QSERDES_COM_SYS_CLK_CTRL COM_OFF(0x0) +#define QSERDES_COM_PLL_VCOTAIL_EN COM_OFF(0x04) +#define QSERDES_COM_PLL_CNTRL COM_OFF(0x14) +#define QSERDES_COM_PLL_IP_SETI COM_OFF(0x24) +#define QSERDES_COM_CORE_CLK_IN_SYNC_SEL COM_OFF(0x28) +#define QSERDES_COM_BIAS_EN_CLKBUFLR_EN COM_OFF(0x30) +#define QSERDES_COM_PLL_CP_SETI COM_OFF(0x34) +#define QSERDES_COM_PLL_IP_SETP COM_OFF(0x38) +#define QSERDES_COM_PLL_CP_SETP COM_OFF(0x3C) +#define QSERDES_COM_SYSCLK_EN_SEL_TXBAND COM_OFF(0x48) +#define QSERDES_COM_RESETSM_CNTRL COM_OFF(0x4C) +#define QSERDES_COM_RESETSM_CNTRL2 COM_OFF(0x50) +#define QSERDES_COM_PLLLOCK_CMP1 COM_OFF(0x90) +#define QSERDES_COM_PLLLOCK_CMP2 COM_OFF(0x94) +#define QSERDES_COM_PLLLOCK_CMP3 COM_OFF(0x98) +#define QSERDES_COM_PLLLOCK_CMP_EN COM_OFF(0x9C) +#define QSERDES_COM_BGTC COM_OFF(0xA0) +#define QSERDES_COM_DEC_START1 COM_OFF(0xAC) +#define QSERDES_COM_PLL_AMP_OS COM_OFF(0xB0) +#define QSERDES_COM_RES_CODE_UP_OFFSET COM_OFF(0xD8) +#define QSERDES_COM_RES_CODE_DN_OFFSET COM_OFF(0xDC) +#define QSERDES_COM_DIV_FRAC_START1 COM_OFF(0x100) +#define QSERDES_COM_DIV_FRAC_START2 COM_OFF(0x104) +#define QSERDES_COM_DIV_FRAC_START3 COM_OFF(0x108) +#define QSERDES_COM_DEC_START2 COM_OFF(0x10C) +#define QSERDES_COM_PLL_RXTXEPCLK_EN COM_OFF(0x110) +#define QSERDES_COM_PLL_CRCTRL COM_OFF(0x114) +#define QSERDES_COM_PLL_CLKEPDIV COM_OFF(0x118) + +/* TX LANE n (0, 1) registers */ +#define QSERDES_TX_EMP_POST1_LVL(n) TX_OFF(n, 0x08) +#define QSERDES_TX_DRV_LVL(n) TX_OFF(n, 0x0C) +#define QSERDES_TX_LANE_MODE(n) TX_OFF(n, 0x54) + +/* RX LANE n (0, 1) registers */ +#define QSERDES_RX_CDR_CONTROL1(n) RX_OFF(n, 0x0) +#define QSERDES_RX_CDR_CONTROL_HALF(n) RX_OFF(n, 0x8) +#define QSERDES_RX_RX_EQ_GAIN1_LSB(n) RX_OFF(n, 0xA8) +#define QSERDES_RX_RX_EQ_GAIN1_MSB(n) RX_OFF(n, 0xAC) +#define QSERDES_RX_RX_EQ_GAIN2_LSB(n) RX_OFF(n, 0xB0) +#define QSERDES_RX_RX_EQ_GAIN2_MSB(n) RX_OFF(n, 0xB4) +#define QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(n) RX_OFF(n, 0xBC) +#define QSERDES_RX_CDR_CONTROL_QUARTER(n) RX_OFF(n, 0xC) +#define QSERDES_RX_SIGDET_CNTRL(n) RX_OFF(n, 0x100) + +/* UFS PHY registers */ +#define UFS_PHY_PHY_START PHY_OFF(0x00) +#define UFS_PHY_POWER_DOWN_CONTROL PHY_OFF(0x4) +#define UFS_PHY_TX_LANE_ENABLE PHY_OFF(0x44) +#define UFS_PHY_PWM_G1_CLK_DIVIDER PHY_OFF(0x08) +#define UFS_PHY_PWM_G2_CLK_DIVIDER PHY_OFF(0x0C) +#define UFS_PHY_PWM_G3_CLK_DIVIDER PHY_OFF(0x10) +#define UFS_PHY_PWM_G4_CLK_DIVIDER PHY_OFF(0x14) +#define UFS_PHY_CORECLK_PWM_G1_CLK_DIVIDER PHY_OFF(0x34) +#define UFS_PHY_CORECLK_PWM_G2_CLK_DIVIDER PHY_OFF(0x38) +#define UFS_PHY_CORECLK_PWM_G3_CLK_DIVIDER PHY_OFF(0x3C) +#define UFS_PHY_CORECLK_PWM_G4_CLK_DIVIDER PHY_OFF(0x40) +#define UFS_PHY_OMC_STATUS_RDVAL PHY_OFF(0x68) +#define UFS_PHY_LINE_RESET_TIME PHY_OFF(0x28) +#define UFS_PHY_LINE_RESET_GRANULARITY PHY_OFF(0x2C) +#define UFS_PHY_TSYNC_RSYNC_CNTL PHY_OFF(0x48) +#define UFS_PHY_PLL_CNTL PHY_OFF(0x50) +#define UFS_PHY_TX_LARGE_AMP_DRV_LVL PHY_OFF(0x54) +#define UFS_PHY_TX_SMALL_AMP_DRV_LVL PHY_OFF(0x5C) +#define UFS_PHY_TX_LARGE_AMP_POST_EMP_LVL PHY_OFF(0x58) +#define UFS_PHY_TX_SMALL_AMP_POST_EMP_LVL PHY_OFF(0x60) +#define UFS_PHY_CFG_CHANGE_CNT_VAL PHY_OFF(0x64) +#define UFS_PHY_RX_SYNC_WAIT_TIME PHY_OFF(0x6C) +#define UFS_PHY_TX_MIN_SLEEP_NOCONFIG_TIME_CAPABILITY PHY_OFF(0xB4) +#define UFS_PHY_RX_MIN_SLEEP_NOCONFIG_TIME_CAPABILITY PHY_OFF(0xE0) +#define UFS_PHY_TX_MIN_STALL_NOCONFIG_TIME_CAPABILITY PHY_OFF(0xB8) +#define UFS_PHY_RX_MIN_STALL_NOCONFIG_TIME_CAPABILITY PHY_OFF(0xE4) +#define UFS_PHY_TX_MIN_SAVE_CONFIG_TIME_CAPABILITY PHY_OFF(0xBC) +#define UFS_PHY_RX_MIN_SAVE_CONFIG_TIME_CAPABILITY PHY_OFF(0xE8) +#define UFS_PHY_RX_PWM_BURST_CLOSURE_LENGTH_CAPABILITY PHY_OFF(0xFC) +#define UFS_PHY_RX_MIN_ACTIVATETIME_CAPABILITY PHY_OFF(0x100) +#define UFS_PHY_RX_SIGDET_CTRL3 PHY_OFF(0x14c) +#define UFS_PHY_RMMI_ATTR_CTRL PHY_OFF(0x160) +#define UFS_PHY_RMMI_RX_CFGUPDT_L1 (1 << 7) +#define UFS_PHY_RMMI_TX_CFGUPDT_L1 (1 << 6) +#define UFS_PHY_RMMI_CFGWR_L1 (1 << 5) +#define UFS_PHY_RMMI_CFGRD_L1 (1 << 4) +#define UFS_PHY_RMMI_RX_CFGUPDT_L0 (1 << 3) +#define UFS_PHY_RMMI_TX_CFGUPDT_L0 (1 << 2) +#define UFS_PHY_RMMI_CFGWR_L0 (1 << 1) +#define UFS_PHY_RMMI_CFGRD_L0 (1 << 0) +#define UFS_PHY_RMMI_ATTRID PHY_OFF(0x164) +#define UFS_PHY_RMMI_ATTRWRVAL PHY_OFF(0x168) +#define UFS_PHY_RMMI_ATTRRDVAL_L0_STATUS PHY_OFF(0x16C) +#define UFS_PHY_RMMI_ATTRRDVAL_L1_STATUS PHY_OFF(0x170) +#define UFS_PHY_PCS_READY_STATUS PHY_OFF(0x174) + +#define UFS_PHY_TX_LANE_ENABLE_MASK 0x3 + +/* + * This structure represents the 20nm specific phy. + * common_cfg MUST remain the first field in this structure + * in case extra fields are added. This way, when calling + * get_ufs_qcom_phy() of generic phy, we can extract the + * common phy structure (struct ufs_qcom_phy) out of it + * regardless of the relevant specific phy. + */ +struct ufs_qcom_phy_qmp_20nm { + struct ufs_qcom_phy common_cfg; +}; + +static struct ufs_qcom_phy_calibration phy_cal_table_rate_A_1_2_0[] = { + UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_POWER_DOWN_CONTROL, 0x01), + UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_RX_SIGDET_CTRL3, 0x0D), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_VCOTAIL_EN, 0xe1), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CRCTRL, 0xcc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_SYSCLK_EN_SEL_TXBAND, 0x08), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CLKEPDIV, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_RXTXEPCLK_EN, 0x10), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x82), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START2, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START1, 0x80), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START2, 0x80), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START3, 0x40), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x19), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP3, 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP_EN, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL, 0x90), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL2, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(0), 0xf2), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(0), 0x0c), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(0), 0x12), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(1), 0xf2), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(1), 0x0c), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(1), 0x12), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(0), 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(1), 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETI, 0x3f), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETP, 0x1b), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETP, 0x0f), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETI, 0x01), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_EMP_POST1_LVL(0), 0x2F), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_DRV_LVL(0), 0x20), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_EMP_POST1_LVL(1), 0x2F), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_DRV_LVL(1), 0x20), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(0), 0x68), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(1), 0x68), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(1), 0xdc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(0), 0xdc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x3), +}; + +static struct ufs_qcom_phy_calibration phy_cal_table_rate_A_1_3_0[] = { + UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_POWER_DOWN_CONTROL, 0x01), + UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_RX_SIGDET_CTRL3, 0x0D), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_VCOTAIL_EN, 0xe1), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CRCTRL, 0xcc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_SYSCLK_EN_SEL_TXBAND, 0x08), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CLKEPDIV, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_RXTXEPCLK_EN, 0x10), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x82), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START2, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START1, 0x80), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START2, 0x80), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START3, 0x40), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x19), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP3, 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP_EN, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL, 0x90), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL2, 0x03), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(0), 0xf2), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(0), 0x0c), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(0), 0x12), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(1), 0xf2), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(1), 0x0c), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(1), 0x12), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(0), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(0), 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(1), 0xff), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(1), 0x00), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETI, 0x2b), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETP, 0x38), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETP, 0x3c), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RES_CODE_UP_OFFSET, 0x02), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RES_CODE_DN_OFFSET, 0x02), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETI, 0x01), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CNTRL, 0x40), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(0), 0x68), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(1), 0x68), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(1), 0xdc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(0), 0xdc), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x3), +}; + +static struct ufs_qcom_phy_calibration phy_cal_table_rate_B[] = { + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x98), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0x65), + UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x1e), +}; + +#endif diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h new file mode 100644 index 000000000000..9d18e9f948e9 --- /dev/null +++ b/include/linux/phy/phy-qcom-ufs.h @@ -0,0 +1,59 @@ +/* + * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef PHY_QCOM_UFS_H_ +#define PHY_QCOM_UFS_H_ + +#include "phy.h" + +/** + * ufs_qcom_phy_enable_ref_clk() - Enable the phy + * ref clock. + * @phy: reference to a generic phy + * + * returns 0 for success, and non-zero for error. + */ +int ufs_qcom_phy_enable_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_disable_ref_clk() - Disable the phy + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_disable_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); + +int ufs_qcom_phy_enable_iface_clk(struct phy *phy); +void ufs_qcom_phy_disable_iface_clk(struct phy *phy); +int ufs_qcom_phy_start_serdes(struct phy *phy); +int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); +int ufs_qcom_phy_calibrate_phy(struct phy *phy, bool is_rate_B); +int ufs_qcom_phy_is_pcs_ready(struct phy *phy); +void ufs_qcom_phy_save_controller_version(struct phy *phy, + u8 major, u16 minor, u16 step); + +#endif /* PHY_QCOM_UFS_H_ */ -- cgit v1.2.3 From 3c33f5b99d688deafd21d4a770303691c7c3a320 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 20 Jan 2015 09:26:19 -0600 Subject: livepatch: support for repatching a function Add support for patching a function multiple times. If multiple patches affect a function, the function in the most recently enabled patch "wins". This enables a cumulative patch upgrade path, where each patch is a superset of previous patches. This requires restructuring the data a little bit. With the current design, where each klp_func struct has its own ftrace_ops, we'd have to unregister the old ops and then register the new ops, because FTRACE_OPS_FL_IPMODIFY prevents us from having two ops registered for the same function at the same time. That would leave a regression window where the function isn't patched at all (not good for a patch upgrade path). This patch replaces the per-klp_func ftrace_ops with a global klp_ops list, with one ftrace_ops per original function. A single ftrace_ops is shared between all klp_funcs which have the same old_addr. This allows the switch between function versions to happen instantaneously by updating the klp_ops struct's func_stack list. The winner is the klp_func at the top of the func_stack (front of the list). [ jkosina@suse.cz: turn WARN_ON() into WARN_ON_ONCE() in ftrace handler to avoid storm in pathological cases ] Signed-off-by: Josh Poimboeuf Reviewed-by: Jiri Slaby Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 4 +- kernel/livepatch/core.c | 170 ++++++++++++++++++++++++++++++++-------------- 2 files changed, 121 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 950bc615842f..f14c6fb262b4 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -40,8 +40,8 @@ enum klp_state { * @old_addr: a hint conveying at what address the old function * can be found (optional, vmlinux patches only) * @kobj: kobject for sysfs resources - * @fops: ftrace operations structure * @state: tracks function-level patch application state + * @stack_node: list node for klp_ops func_stack list */ struct klp_func { /* external */ @@ -59,8 +59,8 @@ struct klp_func { /* internal */ struct kobject kobj; - struct ftrace_ops *fops; enum klp_state state; + struct list_head stack_node; }; /** diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 2401e7f955d3..bc05d390ce85 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -29,17 +29,53 @@ #include #include -/* - * The klp_mutex protects the klp_patches list and state transitions of any - * structure reachable from the patches list. References to any structure must - * be obtained under mutex protection. +/** + * struct klp_ops - structure for tracking registered ftrace ops structs + * + * A single ftrace_ops is shared between all enabled replacement functions + * (klp_func structs) which have the same old_addr. This allows the switch + * between function versions to happen instantaneously by updating the klp_ops + * struct's func_stack list. The winner is the klp_func at the top of the + * func_stack (front of the list). + * + * @node: node for the global klp_ops list + * @func_stack: list head for the stack of klp_func's (active func is on top) + * @fops: registered ftrace ops struct */ +struct klp_ops { + struct list_head node; + struct list_head func_stack; + struct ftrace_ops fops; +}; +/* + * The klp_mutex protects the global lists and state transitions of any + * structure reachable from them. References to any structure must be obtained + * under mutex protection (except in klp_ftrace_handler(), which uses RCU to + * ensure it gets consistent data). + */ static DEFINE_MUTEX(klp_mutex); + static LIST_HEAD(klp_patches); +static LIST_HEAD(klp_ops); static struct kobject *klp_root_kobj; +static struct klp_ops *klp_find_ops(unsigned long old_addr) +{ + struct klp_ops *ops; + struct klp_func *func; + + list_for_each_entry(ops, &klp_ops, node) { + func = list_first_entry(&ops->func_stack, struct klp_func, + stack_node); + if (func->old_addr == old_addr) + return ops; + } + + return NULL; +} + static bool klp_is_module(struct klp_object *obj) { return obj->name; @@ -267,16 +303,28 @@ static int klp_write_object_relocations(struct module *pmod, static void notrace klp_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, + struct ftrace_ops *fops, struct pt_regs *regs) { - struct klp_func *func = ops->private; + struct klp_ops *ops; + struct klp_func *func; + + ops = container_of(fops, struct klp_ops, fops); + + rcu_read_lock(); + func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, + stack_node); + rcu_read_unlock(); + + if (WARN_ON_ONCE(!func)) + return; klp_arch_set_pc(regs, (unsigned long)func->new_func); } static int klp_disable_func(struct klp_func *func) { + struct klp_ops *ops; int ret; if (WARN_ON(func->state != KLP_ENABLED)) @@ -285,16 +333,28 @@ static int klp_disable_func(struct klp_func *func) if (WARN_ON(!func->old_addr)) return -EINVAL; - ret = unregister_ftrace_function(func->fops); - if (ret) { - pr_err("failed to unregister ftrace handler for function '%s' (%d)\n", - func->old_name, ret); - return ret; - } + ops = klp_find_ops(func->old_addr); + if (WARN_ON(!ops)) + return -EINVAL; - ret = ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0); - if (ret) - pr_warn("function unregister succeeded but failed to clear the filter\n"); + if (list_is_singular(&ops->func_stack)) { + ret = unregister_ftrace_function(&ops->fops); + if (ret) { + pr_err("failed to unregister ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + return ret; + } + + ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); + if (ret) + pr_warn("function unregister succeeded but failed to clear the filter\n"); + + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); + } else { + list_del_rcu(&func->stack_node); + } func->state = KLP_DISABLED; @@ -303,6 +363,7 @@ static int klp_disable_func(struct klp_func *func) static int klp_enable_func(struct klp_func *func) { + struct klp_ops *ops; int ret; if (WARN_ON(!func->old_addr)) @@ -311,22 +372,50 @@ static int klp_enable_func(struct klp_func *func) if (WARN_ON(func->state != KLP_DISABLED)) return -EINVAL; - ret = ftrace_set_filter_ip(func->fops, func->old_addr, 0, 0); - if (ret) { - pr_err("failed to set ftrace filter for function '%s' (%d)\n", - func->old_name, ret); - return ret; - } + ops = klp_find_ops(func->old_addr); + if (!ops) { + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + ops->fops.func = klp_ftrace_handler; + ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS | + FTRACE_OPS_FL_DYNAMIC | + FTRACE_OPS_FL_IPMODIFY; + + list_add(&ops->node, &klp_ops); + + INIT_LIST_HEAD(&ops->func_stack); + list_add_rcu(&func->stack_node, &ops->func_stack); + + ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 0, 0); + if (ret) { + pr_err("failed to set ftrace filter for function '%s' (%d)\n", + func->old_name, ret); + goto err; + } + + ret = register_ftrace_function(&ops->fops); + if (ret) { + pr_err("failed to register ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); + goto err; + } + - ret = register_ftrace_function(func->fops); - if (ret) { - pr_err("failed to register ftrace handler for function '%s' (%d)\n", - func->old_name, ret); - ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0); } else { - func->state = KLP_ENABLED; + list_add_rcu(&func->stack_node, &ops->func_stack); } + func->state = KLP_ENABLED; + + return ret; + +err: + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); return ret; } @@ -582,10 +671,6 @@ static struct kobj_type klp_ktype_patch = { static void klp_kobj_release_func(struct kobject *kobj) { - struct klp_func *func; - - func = container_of(kobj, struct klp_func, kobj); - kfree(func->fops); } static struct kobj_type klp_ktype_func = { @@ -642,28 +727,11 @@ static void klp_free_patch(struct klp_patch *patch) static int klp_init_func(struct klp_object *obj, struct klp_func *func) { - struct ftrace_ops *ops; - int ret; - - ops = kzalloc(sizeof(*ops), GFP_KERNEL); - if (!ops) - return -ENOMEM; - - ops->private = func; - ops->func = klp_ftrace_handler; - ops->flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_DYNAMIC | - FTRACE_OPS_FL_IPMODIFY; - func->fops = ops; + INIT_LIST_HEAD(&func->stack_node); func->state = KLP_DISABLED; - ret = kobject_init_and_add(&func->kobj, &klp_ktype_func, - obj->kobj, func->old_name); - if (ret) { - kfree(func->fops); - return ret; - } - - return 0; + return kobject_init_and_add(&func->kobj, &klp_ktype_func, + obj->kobj, func->old_name); } /* parts of the initialization that is done only when the object is loaded */ -- cgit v1.2.3 From 85cdf36e11557dc367c1361e4b7bb2c4619cae91 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Thu, 1 Jan 2015 18:04:52 +0100 Subject: power: ab8500_fg.c: Remove unused function Remove the function ab8500_fg_reinit() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Acked-by: Arnd Bergmann Signed-off-by: Sebastian Reichel --- drivers/power/ab8500_fg.c | 14 -------------- include/linux/mfd/abx500/ab8500-bm.h | 1 - 2 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c index 69b80bcaa9e7..c908658aa31a 100644 --- a/drivers/power/ab8500_fg.c +++ b/drivers/power/ab8500_fg.c @@ -2435,20 +2435,6 @@ static void ab8500_fg_reinit_work(struct work_struct *work) } } -/** - * ab8500_fg_reinit() - forces FG algorithm to reinitialize with current values - * - * This function can be used to force the FG algorithm to recalculate a new - * voltage based battery capacity. - */ -void ab8500_fg_reinit(void) -{ - struct ab8500_fg *di = ab8500_fg_get(); - /* User won't be notified if a null pointer returned. */ - if (di != NULL) - queue_delayed_work(di->fg_wq, &di->fg_reinit_work, 0); -} - /* Exposure to the sysfs interface */ struct ab8500_fg_sysfs_entry { diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index cc892a8d8d6e..12a5b396921e 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -461,7 +461,6 @@ struct ab8500_fg; #ifdef CONFIG_AB8500_BM extern struct abx500_bm_data ab8500_bm_data; -void ab8500_fg_reinit(void); void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA); struct ab8500_btemp *ab8500_btemp_get(void); int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp); -- cgit v1.2.3 From 9c45101e88b2bf2ce36b8833fcfa784a9149aa74 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 09:21:58 +0100 Subject: quota: Cleanup flags definitions Currently all quota flags were defined just in kernel-private headers. Export flags readable / writeable from userspace to userspace via include/uapi/linux/quota.h. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 2 +- include/linux/dqblk_v1.h | 3 --- include/linux/quota.h | 14 ++++++++------ include/uapi/linux/quota.h | 14 +++++++++++++- 4 files changed, 22 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8f0acef3d184..f8be368b9086 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot) return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || - !(info->dqi_flags & V1_DQF_RSQUASH)); + !(info->dqi_flags & DQF_ROOT_SQUASH)); } /* needs dq_data_lock */ diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h index 3713a7232dd8..c0d4d1e2a45c 100644 --- a/include/linux/dqblk_v1.h +++ b/include/linux/dqblk_v1.h @@ -5,9 +5,6 @@ #ifndef _LINUX_DQBLK_V1_H #define _LINUX_DQBLK_V1_H -/* Root squash turned on */ -#define V1_DQF_RSQUASH 1 - /* Numbers of blocks needed for updates */ #define V1_INIT_ALLOC 1 #define V1_INIT_REWRITE 1 diff --git a/include/linux/quota.h b/include/linux/quota.h index 50978b781a19..0c42113607ce 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,12 +223,14 @@ struct mem_dqinfo { struct super_block; -#define DQF_MASK 0xffff /* Mask for format specific flags */ -#define DQF_GETINFO_MASK 0x1ffff /* Mask for flags passed to userspace */ -#define DQF_SETINFO_MASK 0xffff /* Mask for flags modifiable from userspace */ -#define DQF_SYS_FILE_B 16 -#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) /* Quota file stored as system file */ -#define DQF_INFO_DIRTY_B 31 +/* Mask for flags passed to userspace */ +#define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) +/* Mask for flags modifiable from userspace */ +#define DQF_SETINFO_MASK DQF_ROOT_SQUASH + +enum { + DQF_INFO_DIRTY_B = DQF_PRIVATE, +}; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h index 3b6cfbeb086d..1f49b8341c99 100644 --- a/include/uapi/linux/quota.h +++ b/include/uapi/linux/quota.h @@ -126,10 +126,22 @@ struct if_dqblk { #define IIF_FLAGS 4 #define IIF_ALL (IIF_BGRACE | IIF_IGRACE | IIF_FLAGS) +enum { + DQF_ROOT_SQUASH_B = 0, + DQF_SYS_FILE_B = 16, + /* Kernel internal flags invisible to userspace */ + DQF_PRIVATE +}; + +/* Root squash enabled (for v1 quota format) */ +#define DQF_ROOT_SQUASH (1 << DQF_ROOT_SQUASH_B) +/* Quota stored in a system file */ +#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) + struct if_dqinfo { __u64 dqi_bgrace; __u64 dqi_igrace; - __u32 dqi_flags; + __u32 dqi_flags; /* DFQ_* */ __u32 dqi_valid; }; -- cgit v1.2.3 From c1155c64e603378dccfc21ee0612cf60dd11725b Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Fri, 19 Dec 2014 17:55:13 +0900 Subject: power: charger-manager: Use alarmtimer for battery monitoring in suspend. To guerantee proper charing and managing batteries even in suspend, charger-manager has used rtc device with rtc framework interface. However, it is better to use alarmtimer for cleaner and more appropriate operation. This patch makes driver to use alarmtimer for polling work in suspend and removes all deprecated codes related with using rtc interface. Signed-off-by: Jonghwa Lee Signed-off-by: Sebastian Reichel --- drivers/power/Kconfig | 2 +- drivers/power/charger-manager.c | 289 ++++++++++------------------------ include/linux/power/charger-manager.h | 32 +--- 3 files changed, 84 insertions(+), 239 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index e2569a538501..a79f16afb588 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -315,7 +315,7 @@ config CHARGER_GPIO config CHARGER_MANAGER bool "Battery charger manager for multiple chargers" - depends on REGULATOR && RTC_CLASS + depends on REGULATOR select EXTCON help Say Y to enable charger-manager support, which allows multiple diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 649052e1f2d9..14b0d85318eb 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -69,16 +69,10 @@ static LIST_HEAD(cm_list); static DEFINE_MUTEX(cm_list_mtx); /* About in-suspend (suspend-again) monitoring */ -static struct rtc_device *rtc_dev; -/* - * Backup RTC alarm - * Save the wakeup alarm before entering suspend-to-RAM - */ -static struct rtc_wkalrm rtc_wkalarm_save; -/* Backup RTC alarm time in terms of seconds since 01-01-1970 00:00:00 */ -static unsigned long rtc_wkalarm_save_time; +static struct alarm *cm_timer; + static bool cm_suspended; -static bool cm_rtc_set; +static bool cm_timer_set; static unsigned long cm_suspend_duration_ms; /* About normal (not suspended) monitoring */ @@ -87,9 +81,6 @@ static unsigned long next_polling; /* Next appointed polling time */ static struct workqueue_struct *cm_wq; /* init at driver add */ static struct delayed_work cm_monitor_work; /* init at driver add */ -/* Global charger-manager description */ -static struct charger_global_desc *g_desc; /* init with setup_charger_manager */ - /** * is_batt_present - See if the battery presents in place. * @cm: the Charger Manager representing the battery. @@ -1047,10 +1038,13 @@ static bool cm_setup_timer(void) { struct charger_manager *cm; unsigned int wakeup_ms = UINT_MAX; - bool ret = false; + int timer_req = 0; - mutex_lock(&cm_list_mtx); + if (time_after(next_polling, jiffies)) + CM_MIN_VALID(wakeup_ms, + jiffies_to_msecs(next_polling - jiffies)); + mutex_lock(&cm_list_mtx); list_for_each_entry(cm, &cm_list, entry) { unsigned int fbchk_ms = 0; @@ -1070,162 +1064,38 @@ static bool cm_setup_timer(void) /* Skip if polling is not required for this CM */ if (!is_polling_required(cm) && !cm->emergency_stop) continue; + timer_req++; if (cm->desc->polling_interval_ms == 0) continue; CM_MIN_VALID(wakeup_ms, cm->desc->polling_interval_ms); } - mutex_unlock(&cm_list_mtx); - if (wakeup_ms < UINT_MAX && wakeup_ms > 0) { - pr_info("Charger Manager wakeup timer: %u ms\n", wakeup_ms); - if (rtc_dev) { - struct rtc_wkalrm tmp; - unsigned long time, now; - unsigned long add = DIV_ROUND_UP(wakeup_ms, 1000); - - /* - * Set alarm with the polling interval (wakeup_ms) - * except when rtc_wkalarm_save comes first. - * However, the alarm time should be NOW + - * CM_RTC_SMALL or later. - */ - tmp.enabled = 1; - rtc_read_time(rtc_dev, &tmp.time); - rtc_tm_to_time(&tmp.time, &now); - if (add < CM_RTC_SMALL) - add = CM_RTC_SMALL; - time = now + add; + if (timer_req && cm_timer) { + ktime_t now, add; - ret = true; + /* + * Set alarm with the polling interval (wakeup_ms) + * The alarm time should be NOW + CM_RTC_SMALL or later. + */ + if (wakeup_ms == UINT_MAX || + wakeup_ms < CM_RTC_SMALL * MSEC_PER_SEC) + wakeup_ms = 2 * CM_RTC_SMALL * MSEC_PER_SEC; - if (rtc_wkalarm_save.enabled && - rtc_wkalarm_save_time && - rtc_wkalarm_save_time < time) { - if (rtc_wkalarm_save_time < now + CM_RTC_SMALL) - time = now + CM_RTC_SMALL; - else - time = rtc_wkalarm_save_time; + pr_info("Charger Manager wakeup timer: %u ms\n", wakeup_ms); - /* The timer is not appointed by CM */ - ret = false; - } + now = ktime_get_boottime(); + add = ktime_set(wakeup_ms / MSEC_PER_SEC, + (wakeup_ms % MSEC_PER_SEC) * NSEC_PER_MSEC); + alarm_start(cm_timer, ktime_add(now, add)); - pr_info("Waking up after %lu secs\n", time - now); + cm_suspend_duration_ms = wakeup_ms; - rtc_time_to_tm(time, &tmp.time); - rtc_set_alarm(rtc_dev, &tmp); - cm_suspend_duration_ms += wakeup_ms; - return ret; - } + return true; } - - if (rtc_dev) - rtc_set_alarm(rtc_dev, &rtc_wkalarm_save); return false; } -static void _cm_fbchk_in_suspend(struct charger_manager *cm) -{ - unsigned long jiffy_now = jiffies; - - if (!cm->fullbatt_vchk_jiffies_at) - return; - - if (g_desc && g_desc->assume_timer_stops_in_suspend) - jiffy_now += msecs_to_jiffies(cm_suspend_duration_ms); - - /* Execute now if it's going to be executed not too long after */ - jiffy_now += CM_JIFFIES_SMALL; - - if (time_after_eq(jiffy_now, cm->fullbatt_vchk_jiffies_at)) - fullbatt_vchk(&cm->fullbatt_vchk_work.work); -} - -/** - * cm_suspend_again - Determine whether suspend again or not - * - * Returns true if the system should be suspended again - * Returns false if the system should be woken up - */ -bool cm_suspend_again(void) -{ - struct charger_manager *cm; - bool ret = false; - - if (!g_desc || !g_desc->rtc_only_wakeup || !g_desc->rtc_only_wakeup() || - !cm_rtc_set) - return false; - - if (cm_monitor()) - goto out; - - ret = true; - mutex_lock(&cm_list_mtx); - list_for_each_entry(cm, &cm_list, entry) { - _cm_fbchk_in_suspend(cm); - - if (cm->status_save_ext_pwr_inserted != is_ext_pwr_online(cm) || - cm->status_save_batt != is_batt_present(cm)) { - ret = false; - break; - } - } - mutex_unlock(&cm_list_mtx); - - cm_rtc_set = cm_setup_timer(); -out: - /* It's about the time when the non-CM appointed timer goes off */ - if (rtc_wkalarm_save.enabled) { - unsigned long now; - struct rtc_time tmp; - - rtc_read_time(rtc_dev, &tmp); - rtc_tm_to_time(&tmp, &now); - - if (rtc_wkalarm_save_time && - now + CM_RTC_SMALL >= rtc_wkalarm_save_time) - return false; - } - return ret; -} -EXPORT_SYMBOL_GPL(cm_suspend_again); - -/** - * setup_charger_manager - initialize charger_global_desc data - * @gd: pointer to instance of charger_global_desc - */ -int setup_charger_manager(struct charger_global_desc *gd) -{ - if (!gd) - return -EINVAL; - - if (rtc_dev) - rtc_class_close(rtc_dev); - rtc_dev = NULL; - g_desc = NULL; - - if (!gd->rtc_only_wakeup) { - pr_err("The callback rtc_only_wakeup is not given\n"); - return -EINVAL; - } - - if (gd->rtc_name) { - rtc_dev = rtc_class_open(gd->rtc_name); - if (IS_ERR_OR_NULL(rtc_dev)) { - rtc_dev = NULL; - /* Retry at probe. RTC may be not registered yet */ - } - } else { - pr_warn("No wakeup timer is given for charger manager. " - "In-suspend monitoring won't work.\n"); - } - - g_desc = gd; - return 0; -} -EXPORT_SYMBOL_GPL(setup_charger_manager); - /** * charger_extcon_work - enable/diable charger according to the state * of charger cable @@ -1719,6 +1589,12 @@ static inline struct charger_desc *cm_get_drv_data(struct platform_device *pdev) return dev_get_platdata(&pdev->dev); } +static enum alarmtimer_restart cm_timer_func(struct alarm *alarm, ktime_t now) +{ + cm_timer_set = false; + return ALARMTIMER_NORESTART; +} + static int charger_manager_probe(struct platform_device *pdev) { struct charger_desc *desc = cm_get_drv_data(pdev); @@ -1728,16 +1604,6 @@ static int charger_manager_probe(struct platform_device *pdev) union power_supply_propval val; struct power_supply *fuel_gauge; - if (g_desc && !rtc_dev && g_desc->rtc_name) { - rtc_dev = rtc_class_open(g_desc->rtc_name); - if (IS_ERR_OR_NULL(rtc_dev)) { - rtc_dev = NULL; - dev_err(&pdev->dev, "Cannot get RTC %s\n", - g_desc->rtc_name); - return -ENODEV; - } - } - if (IS_ERR(desc)) { dev_err(&pdev->dev, "No platform data (desc) found\n"); return -ENODEV; @@ -1752,6 +1618,12 @@ static int charger_manager_probe(struct platform_device *pdev) cm->dev = &pdev->dev; cm->desc = desc; + /* Initialize alarm timer */ + if (alarmtimer_get_rtcdev()) { + cm_timer = devm_kzalloc(cm->dev, sizeof(*cm_timer), GFP_KERNEL); + alarm_init(cm_timer, ALARM_BOOTTIME, cm_timer_func); + } + /* * The following two do not need to be errors. * Users may intentionally ignore those two features. @@ -1993,38 +1865,41 @@ static int cm_suspend_noirq(struct device *dev) return ret; } +static bool cm_need_to_awake(void) +{ + struct charger_manager *cm; + + if (cm_timer) + return false; + + mutex_lock(&cm_list_mtx); + list_for_each_entry(cm, &cm_list, entry) { + if (is_charging(cm)) { + mutex_unlock(&cm_list_mtx); + return true; + } + } + mutex_unlock(&cm_list_mtx); + + return false; +} + static int cm_suspend_prepare(struct device *dev) { struct charger_manager *cm = dev_get_drvdata(dev); - if (!cm_suspended) { - if (rtc_dev) { - struct rtc_time tmp; - unsigned long now; - - rtc_read_alarm(rtc_dev, &rtc_wkalarm_save); - rtc_read_time(rtc_dev, &tmp); + if (cm_need_to_awake()) + return -EBUSY; - if (rtc_wkalarm_save.enabled) { - rtc_tm_to_time(&rtc_wkalarm_save.time, - &rtc_wkalarm_save_time); - rtc_tm_to_time(&tmp, &now); - if (now > rtc_wkalarm_save_time) - rtc_wkalarm_save_time = 0; - } else { - rtc_wkalarm_save_time = 0; - } - } + if (!cm_suspended) cm_suspended = true; - } - cancel_delayed_work(&cm->fullbatt_vchk_work); - cm->status_save_ext_pwr_inserted = is_ext_pwr_online(cm); - cm->status_save_batt = is_batt_present(cm); + cm_timer_set = cm_setup_timer(); - if (!cm_rtc_set) { - cm_suspend_duration_ms = 0; - cm_rtc_set = cm_setup_timer(); + if (cm_timer_set) { + cancel_work_sync(&setup_polling); + cancel_delayed_work_sync(&cm_monitor_work); + cancel_delayed_work(&cm->fullbatt_vchk_work); } return 0; @@ -2034,18 +1909,21 @@ static void cm_suspend_complete(struct device *dev) { struct charger_manager *cm = dev_get_drvdata(dev); - if (cm_suspended) { - if (rtc_dev) { - struct rtc_wkalrm tmp; - - rtc_read_alarm(rtc_dev, &tmp); - rtc_wkalarm_save.pending = tmp.pending; - rtc_set_alarm(rtc_dev, &rtc_wkalarm_save); - } + if (cm_suspended) cm_suspended = false; - cm_rtc_set = false; + + if (cm_timer_set) { + ktime_t remain; + + alarm_cancel(cm_timer); + cm_timer_set = false; + remain = alarm_expires_remaining(cm_timer); + cm_suspend_duration_ms -= ktime_to_ms(remain); + schedule_work(&setup_polling); } + _cm_monitor(cm); + /* Re-enqueue delayed work (fullbatt_vchk_work) */ if (cm->fullbatt_vchk_jiffies_at) { unsigned long delay = 0; @@ -2060,21 +1938,18 @@ static void cm_suspend_complete(struct device *dev) } /* - * Account for cm_suspend_duration_ms if - * assume_timer_stops_in_suspend is active + * Account for cm_suspend_duration_ms with assuming that + * timer stops in suspend. */ - if (g_desc && g_desc->assume_timer_stops_in_suspend) { - if (delay > cm_suspend_duration_ms) - delay -= cm_suspend_duration_ms; - else - delay = 0; - } + if (delay > cm_suspend_duration_ms) + delay -= cm_suspend_duration_ms; + else + delay = 0; queue_delayed_work(cm_wq, &cm->fullbatt_vchk_work, msecs_to_jiffies(delay)); } device_set_wakeup_capable(cm->dev, false); - uevent_notify(cm, NULL); } static const struct dev_pm_ops charger_manager_pm = { diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index e97fc656a058..416ebeb6ee1e 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -17,6 +17,7 @@ #include #include +#include enum data_source { CM_BATTERY_PRESENT, @@ -44,29 +45,6 @@ enum cm_event_types { CM_EVENT_OTHERS, }; -/** - * struct charger_global_desc - * @rtc_name: the name of RTC used to wake up the system from suspend. - * @rtc_only_wakeup: - * If the system is woken up by waekup-sources other than the RTC or - * callbacks, Charger Manager should recognize with - * rtc_only_wakeup() returning false. - * If the RTC given to CM is the only wakeup reason, - * rtc_only_wakeup should return true. - * @assume_timer_stops_in_suspend: - * Assume that the jiffy timer stops in suspend-to-RAM. - * When enabled, CM does not rely on jiffies value in - * suspend_again and assumes that jiffies value does not - * change during suspend. - */ -struct charger_global_desc { - char *rtc_name; - - bool (*rtc_only_wakeup)(void); - - bool assume_timer_stops_in_suspend; -}; - /** * struct charger_cable * @extcon_name: the name of extcon device. @@ -266,22 +244,14 @@ struct charger_manager { char psy_name_buf[PSY_NAME_MAX + 1]; struct power_supply charger_psy; - bool status_save_ext_pwr_inserted; - bool status_save_batt; - u64 charging_start_time; u64 charging_end_time; }; #ifdef CONFIG_CHARGER_MANAGER -extern int setup_charger_manager(struct charger_global_desc *gd); -extern bool cm_suspend_again(void); extern void cm_notify_event(struct power_supply *psy, enum cm_event_types type, char *msg); #else -static inline int setup_charger_manager(struct charger_global_desc *gd) -{ return 0; } -static inline bool cm_suspend_again(void) { return false; } static inline void cm_notify_event(struct power_supply *psy, enum cm_event_types type, char *msg) { } #endif -- cgit v1.2.3 From 8116bf4cb62d337c953cfa5369ef4cf83e73140c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 21 Jan 2015 20:44:01 -0500 Subject: locks: update comments that refer to inode->i_flock Signed-off-by: Jeff Layton --- fs/locks.c | 2 +- include/linux/fs.h | 19 ++++++++++--------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index 2fc36b3772a0..4d0d41163a50 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2212,7 +2212,7 @@ again: */ /* * we need that spin_lock here - it prevents reordering between - * update of inode->i_flock and check for it done in close(). + * update of i_flctx->flc_posix and check for it done in close(). * rcu_read_lock() wouldn't do. */ spin_lock(¤t->files->file_lock); diff --git a/include/linux/fs.h b/include/linux/fs.h index f87cb2f03103..ddd2fa7cefd3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -925,12 +925,11 @@ int locks_in_grace(struct net *); * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * - * The i_flock list is ordered by: + * The varous i_flctx lists are ordered by: * - * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX - * 2) lock owner - * 3) lock range start - * 4) lock range end + * 1) lock owner + * 2) lock range start + * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ @@ -1992,8 +1991,9 @@ static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) @@ -2005,8 +2005,9 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) -- cgit v1.2.3 From 30b8b0066cafef274fc92462578ee346211ce7cb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 15 Jan 2015 21:22:39 +0000 Subject: init: Get rid of x86isms The UP local API support can be set up from an early initcall. No need for horrible hackery in the init code. Signed-off-by: Thomas Gleixner Cc: Jiang Liu Cc: Joerg Roedel Cc: Tony Luck Cc: Borislav Petkov Link: http://lkml.kernel.org/r/20150115211703.827943883@linutronix.de Signed-off-by: Thomas Gleixner --- arch/x86/Kconfig | 4 ++++ arch/x86/kernel/apic/apic.c | 7 +++++++ include/linux/smp.h | 7 +++++++ init/main.c | 13 ------------- 4 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba397bde7948..ffcc3ca5862a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -855,6 +855,10 @@ config SCHED_MC source "kernel/Kconfig.preempt" +config UP_LATE_INIT + def_bool y + depends on X86_UP_APIC + config X86_UP_APIC bool "Local APIC support on uniprocessors" depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c681e9ba9e47..19f1bc714ee6 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2267,6 +2267,13 @@ int __init APIC_init_uniprocessor(void) return 0; } +#ifdef CONFIG_UP_LATE_INIT +void __init up_late_init(void) +{ + APIC_init_uniprocessor(); +} +#endif + /* * Power management */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 93dff5fff524..be91db2a7017 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -151,6 +151,13 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } +#ifdef CONFIG_UP_LATE_INIT +extern void __init up_late_init(void); +static inline void smp_init(void) { up_late_init(); } +#else +static inline void smp_init(void) { } +#endif + #endif /* !SMP */ /* diff --git a/init/main.c b/init/main.c index 61b993767db5..179ada15d08a 100644 --- a/init/main.c +++ b/init/main.c @@ -87,10 +87,6 @@ #include #include -#ifdef CONFIG_X86_LOCAL_APIC -#include -#endif - static int kernel_init(void *); extern void init_IRQ(void); @@ -351,15 +347,6 @@ __setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP static const unsigned int setup_max_cpus = NR_CPUS; -#ifdef CONFIG_X86_LOCAL_APIC -static void __init smp_init(void) -{ - APIC_init_uniprocessor(); -} -#else -#define smp_init() do { } while (0) -#endif - static inline void setup_nr_cpu_ids(void) { } static inline void smp_prepare_cpus(unsigned int maxcpus) { } #endif -- cgit v1.2.3 From 1f94a94f67e1083e19fb7b436dd7ca7a4ba03f2b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 9 Jan 2015 20:34:39 -0600 Subject: PCI: Add generic config accessors Many PCI controllers' configuration space accesses are memory-mapped and vary only in address calculation and access checks. There are 2 main access methods: a decoded address space such as ECAM or a single address and data register similar to x86. This implementation can support both cases as well as be used in cases that need additional pre- or post-access handling. Add a new pci_ops member, map_bus, which can do access checks and any necessary setup. It returns the address to use for the configuration space access. The access types supported are 32-bit only accesses or correct byte, word, or dword sized accesses. Tested-by: Thierry Reding Signed-off-by: Rob Herring Signed-off-by: Bjorn Helgaas Reviewed-by: Thierry Reding --- drivers/pci/access.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 11 +++++++ 2 files changed, 98 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 49dd766852ba..d9b64a175990 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -67,6 +67,93 @@ EXPORT_SYMBOL(pci_bus_write_config_byte); EXPORT_SYMBOL(pci_bus_write_config_word); EXPORT_SYMBOL(pci_bus_write_config_dword); +int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where); + if (!addr) { + *val = ~0; + return PCIBIOS_DEVICE_NOT_FOUND; + } + + if (size == 1) + *val = readb(addr); + else if (size == 2) + *val = readw(addr); + else + *val = readl(addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_read); + +int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (size == 1) + writeb(val, addr); + else if (size == 2) + writew(val, addr); + else + writel(val, addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_write); + +int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where & ~0x3); + if (!addr) { + *val = ~0; + return PCIBIOS_DEVICE_NOT_FOUND; + } + + *val = readl(addr); + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_read32); + +int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + void __iomem *addr; + u32 mask, tmp; + + addr = bus->ops->map_bus(bus, devfn, where & ~0x3); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (size == 4) { + writel(val, addr); + return PCIBIOS_SUCCESSFUL; + } else { + mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8)); + } + + tmp = readl(addr) & mask; + tmp |= val << ((where & 0x3) * 8); + writel(tmp, addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_write32); + /** * pci_bus_set_ops - Set raw operations of pci bus * @bus: pci bus struct diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..e7fd51900182 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -560,6 +560,7 @@ static inline int pcibios_err_to_errno(int err) /* Low-level architecture-dependent routines */ struct pci_ops { + void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where); int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val); int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val); }; @@ -857,6 +858,16 @@ int pci_bus_write_config_word(struct pci_bus *bus, unsigned int devfn, int where, u16 val); int pci_bus_write_config_dword(struct pci_bus *bus, unsigned int devfn, int where, u32 val); + +int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); +int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); + struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops); static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val) -- cgit v1.2.3 From 41fbf3b39d5eca01527338b4d0ee15ee1ae1023c Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Wed, 17 Dec 2014 13:11:35 +0800 Subject: ktime.h: Introduce ktime_ms_delta This patch adds a reusable time difference function which returns the difference in millisecond, as often used in some driver code, e.g. mtd/test, media/rc, etc. Signed-off-by: Chunyan Zhang Acked-by: Arnd Bergmann Cc: zhang.lyra@gmail.com Cc: davem@davemloft.net Cc: john.stultz@linaro.org Cc: dborkman@redhat.com Link: http://lkml.kernel.org/r/1418793095-18780-1-git-send-email-zhang.chunyan@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/ktime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index c9d645ad98ff..891ea92a68b0 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -186,6 +186,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) return ktime_to_us(ktime_sub(later, earlier)); } +static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) +{ + return ktime_to_ms(ktime_sub(later, earlier)); +} + static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); -- cgit v1.2.3 From 9bc7491906b4113b4c5ae442157c7dfc4e10cd14 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jan 2015 21:24:10 +0100 Subject: hrtimer: Prevent stale expiry time in hrtimer_interrupt() hrtimer_interrupt() has the following subtle issue: hrtimer_interrupt() lock(cpu_base); expires_next = KTIME_MAX; expire_timers(CLOCK_MONOTONIC); expires = get_next_timer(CLOCK_MONOTONIC); if (expires < expires_next) expires_next = expires; expire_timers(CLOCK_REALTIME); unlock(cpu_base); wakeup() hrtimer_start(CLOCK_MONOTONIC, newtimer); lock(cpu_base(); expires = get_next_timer(CLOCK_REALTIME); if (expires < expires_next) expires_next = expires; So because we already evaluated the next expiring timer of CLOCK_MONOTONIC we ignore that the expiry time of newtimer might be earlier than the overall next expiry time in hrtimer_interrupt(). To solve this, remove the caching of the next expiry value from hrtimer_interrupt() and reevaluate all active clock bases for the next expiry value. To avoid another code duplication, create a shared evaluation function and use it for hrtimer_get_next_event(), hrtimer_force_reprogram() and hrtimer_interrupt(). There is another subtlety in this mechanism: While hrtimer_interrupt() is running, we want to avoid to touch the hardware device because we will reprogram it anyway at the end of hrtimer_interrupt(). This works nicely for hrtimers which get rearmed via the HRTIMER_RESTART mechanism, because we drop out when the callback on that CPU is running. But that fails, if a new timer gets enqueued like in the example above. This has another implication: While hrtimer_interrupt() is running we refuse remote enqueueing of timers - see hrtimer_interrupt() and hrtimer_check_target(). hrtimer_interrupt() tries to prevent this by setting cpu_base->expires to KTIME_MAX, but that fails if a new timer gets queued. Prevent both the hardware access and the remote enqueue explicitely. We can loosen the restriction on the remote enqueue now due to reevaluation of the next expiry value, but that needs a seperate patch. Folded in a fix from Vignesh Radhakrishnan. Reported-and-tested-by: Stanislav Fomichev Based-on-patch-by: Stanislav Fomichev Signed-off-by: Thomas Gleixner Cc: vigneshr@codeaurora.org Cc: john.stultz@linaro.org Cc: viresh.kumar@linaro.org Cc: fweisbec@gmail.com Cc: cl@linux.com Cc: stuart.w.hayes@gmail.com Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1501202049190.5526@nanos Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 2 + kernel/time/hrtimer.c | 108 ++++++++++++++++++++++-------------------------- 2 files changed, 52 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a036d058a249..05f6df1fdf5b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -170,6 +170,7 @@ enum hrtimer_base_type { * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang * @nr_events: Total number of hrtimer interrupt events @@ -185,6 +186,7 @@ struct hrtimer_cpu_base { unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; + int in_hrtirq; int hres_active; int hang_detected; unsigned long nr_events; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 37e50aadd471..b663653a5d5b 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -440,6 +440,37 @@ static inline void debug_deactivate(struct hrtimer *timer) trace_hrtimer_cancel(timer); } +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) +{ + struct hrtimer_clock_base *base = cpu_base->clock_base; + ktime_t expires, expires_next = { .tv64 = KTIME_MAX }; + int i; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + struct timerqueue_node *next; + struct hrtimer *timer; + + next = timerqueue_getnext(&base->active); + if (!next) + continue; + + timer = container_of(next, struct hrtimer, node); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + if (expires.tv64 < expires_next.tv64) + expires_next = expires; + } + /* + * clock_was_set() might have changed base->offset of any of + * the clock bases so the result might be negative. Fix it up + * to prevent a false positive in clockevents_program_event(). + */ + if (expires_next.tv64 < 0) + expires_next.tv64 = 0; + return expires_next; +} +#endif + /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS @@ -488,32 +519,7 @@ static inline int hrtimer_hres_active(void) static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { - int i; - struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t expires, expires_next; - - expires_next.tv64 = KTIME_MAX; - - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { - struct hrtimer *timer; - struct timerqueue_node *next; - - next = timerqueue_getnext(&base->active); - if (!next) - continue; - timer = container_of(next, struct hrtimer, node); - - expires = ktime_sub(hrtimer_get_expires(timer), base->offset); - /* - * clock_was_set() has changed base->offset so the - * result might be negative. Fix it up to prevent a - * false positive in clockevents_program_event() - */ - if (expires.tv64 < 0) - expires.tv64 = 0; - if (expires.tv64 < expires_next.tv64) - expires_next = expires; - } + ktime_t expires_next = __hrtimer_get_next_event(cpu_base); if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) return; @@ -586,6 +592,15 @@ static int hrtimer_reprogram(struct hrtimer *timer, if (expires.tv64 >= cpu_base->expires_next.tv64) return 0; + /* + * When the target cpu of the timer is currently executing + * hrtimer_interrupt(), then we do not touch the clock event + * device. hrtimer_interrupt() will reevaluate all clock bases + * before reprogramming the device. + */ + if (cpu_base->in_hrtirq) + return 0; + /* * If a hang was detected in the last timer interrupt then we * do not schedule a timer which is earlier than the expiry @@ -1104,29 +1119,14 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining); ktime_t hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; + ktime_t mindelta = { .tv64 = KTIME_MAX }; unsigned long flags; - int i; raw_spin_lock_irqsave(&cpu_base->lock, flags); - if (!hrtimer_hres_active()) { - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { - struct hrtimer *timer; - struct timerqueue_node *next; - - next = timerqueue_getnext(&base->active); - if (!next) - continue; - - timer = container_of(next, struct hrtimer, node); - delta.tv64 = hrtimer_get_expires_tv64(timer); - delta = ktime_sub(delta, base->get_time()); - if (delta.tv64 < mindelta.tv64) - mindelta.tv64 = delta.tv64; - } - } + if (!hrtimer_hres_active()) + mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base), + ktime_get()); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); @@ -1253,7 +1253,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) raw_spin_lock(&cpu_base->lock); entry_time = now = hrtimer_update_base(cpu_base); retry: - expires_next.tv64 = KTIME_MAX; + cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via @@ -1291,28 +1291,20 @@ retry: * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ - - if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { - ktime_t expires; - - expires = ktime_sub(hrtimer_get_expires(timer), - base->offset); - if (expires.tv64 < 0) - expires.tv64 = KTIME_MAX; - if (expires.tv64 < expires_next.tv64) - expires_next = expires; + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) break; - } __run_hrtimer(timer, &basenow); } } - + /* Reevaluate the clock bases for the next expiry */ + expires_next = __hrtimer_get_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; + cpu_base->in_hrtirq = 0; raw_spin_unlock(&cpu_base->lock); /* Reprogramming necessary ? */ -- cgit v1.2.3 From a9aaf2915ee265735c28b764551d084e61a694e0 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 13 Jan 2015 11:34:00 +0530 Subject: cpufreq: stats: get rid of per-cpu cpufreq_stats_table All CPUs sharing a cpufreq policy share stats too. For this reason, add a stats pointer to struct cpufreq_policy and drop per-CPU variable cpufreq_stats_table used for accessing cpufreq stats so as to reduce code complexity. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq_stats.c | 62 +++++++++++++++++++---------------------- include/linux/cpufreq.h | 3 ++ 2 files changed, 32 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 6c234f548601..3792b2e2f4a8 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -31,8 +31,6 @@ struct cpufreq_stats { #endif }; -static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table); - static int cpufreq_stats_update(struct cpufreq_stats *stat) { unsigned long long cur_time = get_jiffies_64(); @@ -48,20 +46,15 @@ static int cpufreq_stats_update(struct cpufreq_stats *stat) static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf) { - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; - return sprintf(buf, "%d\n", - per_cpu(cpufreq_stats_table, stat->cpu)->total_trans); + return sprintf(buf, "%d\n", policy->stats->total_trans); } static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) { + struct cpufreq_stats *stat = policy->stats; ssize_t len = 0; int i; - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; + cpufreq_stats_update(stat); for (i = 0; i < stat->state_num; i++) { len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i], @@ -74,12 +67,10 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) #ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { + struct cpufreq_stats *stat = policy->stats; ssize_t len = 0; int i, j; - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; cpufreq_stats_update(stat); len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); len += snprintf(buf + len, PAGE_SIZE - len, " : "); @@ -145,8 +136,9 @@ static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq) static void __cpufreq_stats_free_table(struct cpufreq_policy *policy) { - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); + struct cpufreq_stats *stat = policy->stats; + /* Already freed */ if (!stat) return; @@ -155,7 +147,7 @@ static void __cpufreq_stats_free_table(struct cpufreq_policy *policy) sysfs_remove_group(&policy->kobj, &stats_attr_group); kfree(stat->time_in_state); kfree(stat); - per_cpu(cpufreq_stats_table, policy->cpu) = NULL; + policy->stats = NULL; } static void cpufreq_stats_free_table(unsigned int cpu) @@ -184,7 +176,7 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy) return 0; /* stats already initialized */ - if (per_cpu(cpufreq_stats_table, cpu)) + if (policy->stats) return -EEXIST; stat = kzalloc(sizeof(*stat), GFP_KERNEL); @@ -196,7 +188,7 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy) goto error_out; stat->cpu = cpu; - per_cpu(cpufreq_stats_table, cpu) = stat; + policy->stats = stat; cpufreq_for_each_valid_entry(pos, table) count++; @@ -231,7 +223,7 @@ error_alloc: sysfs_remove_group(&policy->kobj, &stats_attr_group); error_out: kfree(stat); - per_cpu(cpufreq_stats_table, cpu) = NULL; + policy->stats = NULL; return ret; } @@ -254,15 +246,7 @@ static void cpufreq_stats_create_table(unsigned int cpu) static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy) { - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, - policy->last_cpu); - - pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n", - policy->cpu, policy->last_cpu); - per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table, - policy->last_cpu); - per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL; - stat->cpu = policy->cpu; + policy->stats->cpu = policy->cpu; } static int cpufreq_stat_notifier_policy(struct notifier_block *nb, @@ -288,27 +272,36 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; + struct cpufreq_policy *policy = cpufreq_cpu_get(freq->cpu); struct cpufreq_stats *stat; int old_index, new_index; - if (val != CPUFREQ_POSTCHANGE) + if (!policy) { + pr_err("%s: No policy found\n", __func__); return 0; + } - stat = per_cpu(cpufreq_stats_table, freq->cpu); - if (!stat) - return 0; + if (val != CPUFREQ_POSTCHANGE) + goto put_policy; + + if (!policy->stats) { + pr_debug("%s: No stats found\n", __func__); + goto put_policy; + } + + stat = policy->stats; old_index = stat->last_index; new_index = freq_table_get_index(stat, freq->new); /* We can't do stat->time_in_state[-1]= .. */ if (old_index == -1 || new_index == -1) - return 0; + goto put_policy; cpufreq_stats_update(stat); if (old_index == new_index) - return 0; + goto put_policy; spin_lock(&cpufreq_stats_lock); stat->last_index = new_index; @@ -317,6 +310,9 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb, #endif stat->total_trans++; spin_unlock(&cpufreq_stats_lock); + +put_policy: + cpufreq_cpu_put(policy); return 0; } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4d078cebafd2..60b7b496565d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -113,6 +113,9 @@ struct cpufreq_policy { wait_queue_head_t transition_wait; struct task_struct *transition_task; /* Task which is doing the transition */ + /* cpufreq-stats */ + struct cpufreq_stats *stats; + /* For cpufreq driver's internal use */ void *driver_data; }; -- cgit v1.2.3 From 7c418ff099110d987846c8c670479a3b90ed1dcb Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Jan 2015 21:09:08 +0530 Subject: cpufreq: Remove (now) unused 'last_cpu' from struct cpufreq_policy 'last_cpu' was used only from cpufreq-stats and isn't used anymore. Get rid of it. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 3 --- include/linux/cpufreq.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 70b568a253e9..60ef37d569c5 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1086,10 +1086,7 @@ static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu, } down_write(&policy->rwsem); - - policy->last_cpu = policy->cpu; policy->cpu = cpu; - up_write(&policy->rwsem); blocking_notifier_call_chain(&cpufreq_policy_notifier_list, diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 60b7b496565d..7e1a389b4e92 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -66,8 +66,6 @@ struct cpufreq_policy { unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ unsigned int cpu; /* cpu nr of CPU managing this policy */ - unsigned int last_cpu; /* cpu nr of previous CPU that managed - * this policy */ struct clk *clk; struct cpufreq_cpuinfo cpuinfo;/* see above */ -- cgit v1.2.3 From d9f354460db8b58a8395936d323b4ca6e8428b9d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Jan 2015 21:09:10 +0530 Subject: cpufreq: remove CPUFREQ_UPDATE_POLICY_CPU notifications CPUFREQ_UPDATE_POLICY_CPU notifications were used only from cpufreq-stats which doesn't use it anymore. Remove them. This also decrements values of other notification macros defined after CPUFREQ_UPDATE_POLICY_CPU by 1 to remove gaps. Hopefully all users are using macro's instead of direct numbers and so they wouldn't break as macro values are changed now. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 3 --- include/linux/cpufreq.h | 5 ++--- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 60ef37d569c5..ca69f42b8e1e 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1089,9 +1089,6 @@ static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu, policy->cpu = cpu; up_write(&policy->rwsem); - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_UPDATE_POLICY_CPU, policy); - return 0; } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7e1a389b4e92..2ee4888c1f47 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -368,9 +368,8 @@ static inline void cpufreq_resume(void) {} #define CPUFREQ_INCOMPATIBLE (1) #define CPUFREQ_NOTIFY (2) #define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) -#define CPUFREQ_CREATE_POLICY (5) -#define CPUFREQ_REMOVE_POLICY (6) +#define CPUFREQ_CREATE_POLICY (4) +#define CPUFREQ_REMOVE_POLICY (5) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); -- cgit v1.2.3 From 382548a62ade2c003c77a1055b6eb2a47ce30084 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 20 Jan 2015 11:33:09 +0100 Subject: PM / Domains: Remove pm_genpd_dev_need_restore() API There are currently no users of this API, let's remove it. Additionally, if such feature would be needed future wise, a better option is likely use pm_runtime_set_active|suspended() in some form. Signed-off-by: Ulf Hansson Acked-by: Geert Uytterhoeven Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 20 -------------------- include/linux/pm_domain.h | 2 -- 2 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 0d8780c04a5e..c5280f2b798b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1558,26 +1558,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, return ret; } -/** - * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag. - * @dev: Device to set/unset the flag for. - * @val: The new value of the device's "need restore" flag. - */ -void pm_genpd_dev_need_restore(struct device *dev, bool val) -{ - struct pm_subsys_data *psd; - unsigned long flags; - - spin_lock_irqsave(&dev->power.lock, flags); - - psd = dev_to_psd(dev); - if (psd && psd->domain_data) - to_gpd_data(psd->domain_data)->need_restore = val ? 1 : 0; - - spin_unlock_irqrestore(&dev->power.lock, flags); -} -EXPORT_SYMBOL_GPL(pm_genpd_dev_need_restore); - /** * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain. * @genpd: Master PM domain to add the subdomain to. diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a9edab2c787a..ed607760fc20 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -140,7 +140,6 @@ extern int __pm_genpd_name_add_device(const char *domain_name, extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); -extern void pm_genpd_dev_need_restore(struct device *dev, bool val); extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_add_subdomain_names(const char *master_name, @@ -187,7 +186,6 @@ static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline void pm_genpd_dev_need_restore(struct device *dev, bool val) {} static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_sd) { -- cgit v1.2.3 From 566fcec60b7458784d4ed9bca974c5a56dacf214 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 15:32:46 -0500 Subject: NFSv4: Fix an atomicity problem in CLOSE If we are to remove the serialisation of OPEN/CLOSE, then we need to ensure that the stateid sent as part of a CLOSE operation does not change after we test the state in nfs4_close_prepare. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 7 ++++++- fs/nfs/nfs4xdr.c | 4 ++-- include/linux/nfs_xdr.h | 2 +- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c347705b0161..4863dec10865 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2587,6 +2587,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &state->stateid)) { + rpc_restart_call_prepare(task); + goto out_release; + } if (calldata->arg.fmode == 0) break; default: @@ -2619,6 +2624,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); + nfs4_stateid_copy(&calldata->arg.stateid, &state->stateid); /* Calculate the change in open mode */ calldata->arg.fmode = 0; if (state->n_rdwr == 0) { @@ -2757,7 +2763,6 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->inode = state->inode; calldata->state = state; calldata->arg.fh = NFS_FH(state->inode); - calldata->arg.stateid = &state->open_stateid; /* Serialization for the sequence id */ calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask); if (calldata->arg.seqid == NULL) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cb4376b78ed9..7e7be5ab70bb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1125,7 +1125,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg { encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr); encode_nfs4_seqid(xdr, arg->seqid); - encode_nfs4_stateid(xdr, arg->stateid); + encode_nfs4_stateid(xdr, &arg->stateid); } static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr) @@ -1530,7 +1530,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr); - encode_nfs4_stateid(xdr, arg->stateid); + encode_nfs4_stateid(xdr, &arg->stateid); encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->fmode); } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..7e38d641236e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -389,7 +389,7 @@ struct nfs_open_confirmres { struct nfs_closeargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; - nfs4_stateid * stateid; + nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; const u32 * bitmask; -- cgit v1.2.3 From 8b618628b2bf83512fc8df5e8672619d65adfdfb Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 3 Dec 2014 14:43:06 -0500 Subject: ktime: Optimize ktime_divns for constant divisors At least on ARM, do_div() is optimized to turn constant divisors into an inline multiplication by the reciprocal value at compile time. However this optimization is missed entirely whenever ktime_divns() is used and the slow out-of-line division code is used all the time. Let ktime_divns() use do_div() inline whenever the divisor is constant and small enough. This will make things like ktime_to_us() and ktime_to_ms() much faster. Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Nicolas Pitre Acked-by: Arnd Bergmann Signed-off-by: Nicolas Pitre Signed-off-by: John Stultz --- include/linux/ktime.h | 12 +++++++++++- kernel/time/hrtimer.c | 4 ++-- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index c9d645ad98ff..411dd8bfe539 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -166,7 +166,17 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) } #if BITS_PER_LONG < 64 -extern u64 ktime_divns(const ktime_t kt, s64 div); +extern u64 __ktime_divns(const ktime_t kt, s64 div); +static inline u64 ktime_divns(const ktime_t kt, s64 div) +{ + if (__builtin_constant_p(div) && !(div >> 32)) { + u64 ns = kt.tv64; + do_div(ns, div); + return ns; + } else { + return __ktime_divns(kt, div); + } +} #else /* BITS_PER_LONG < 64 */ # define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) #endif diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 37e50aadd471..890535c41c2d 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -266,7 +266,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) /* * Divide a ktime value by a nanosecond value */ -u64 ktime_divns(const ktime_t kt, s64 div) +u64 __ktime_divns(const ktime_t kt, s64 div) { u64 dclc; int sft = 0; @@ -282,7 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div) return dclc; } -EXPORT_SYMBOL_GPL(ktime_divns); +EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* -- cgit v1.2.3 From d08c0cdd26d48751c15aa2b4479a410594fee9ac Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 8 Dec 2014 12:00:09 -0800 Subject: time: Expose getboottime64 for in-kernel uses Adds a timespec64 based getboottime64() implementation that can be used as we convert internal users of getboottime away from using timespecs. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: John Stultz --- include/linux/timekeeping.h | 16 ++++++++++++++-- kernel/time/timekeeping.c | 12 ++++++------ 2 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9b63d13ba82b..91480137aa39 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,6 +33,7 @@ extern time64_t ktime_get_real_seconds(void); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); +extern void getboottime64(struct timespec64 *ts); #if BITS_PER_LONG == 64 /** @@ -72,6 +73,11 @@ static inline struct timespec get_monotonic_coarse(void) { return get_monotonic_coarse64(); } + +static inline void getboottime(struct timespec *ts) +{ + return getboottime64(ts); +} #else /** * Deprecated. Use do_settimeofday64(). @@ -129,9 +135,15 @@ static inline struct timespec get_monotonic_coarse(void) { return timespec64_to_timespec(get_monotonic_coarse64()); } -#endif -extern void getboottime(struct timespec *ts); +static inline void getboottime(struct timespec *ts) +{ + struct timespec64 ts64; + + getboottime64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 6a931852082f..b124af259800 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1659,24 +1659,24 @@ out: } /** - * getboottime - Return the real time of system boot. - * @ts: pointer to the timespec to be set + * getboottime64 - Return the real time of system boot. + * @ts: pointer to the timespec64 to be set * - * Returns the wall-time of boot in a timespec. + * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ -void getboottime(struct timespec *ts) +void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); - *ts = ktime_to_timespec(t); + *ts = ktime_to_timespec64(t); } -EXPORT_SYMBOL_GPL(getboottime); +EXPORT_SYMBOL_GPL(getboottime64); unsigned long get_seconds(void) { -- cgit v1.2.3 From 2e0c78ee5ba4d777ecf22c8f40cc968b4308ca88 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 18 Dec 2014 18:04:34 -0800 Subject: time: Expose get_monotonic_boottime64 for in-kernel use As part of the 2038 conversion process, add a get_monotonic_boottime64 accessor so we can depracate get_monotonic_boottime. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: John Stultz --- include/linux/timekeeping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 91480137aa39..3eaae4754275 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -229,6 +229,11 @@ static inline void get_monotonic_boottime(struct timespec *ts) *ts = ktime_to_timespec(ktime_get_boottime()); } +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai(struct timespec *ts) { *ts = ktime_to_timespec(ktime_get_clocktai()); -- cgit v1.2.3 From 9a4a445e30f0b601ca2d9433274047cbf48ebf9e Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Thu, 22 Jan 2015 02:31:55 +0000 Subject: rtc: Convert rtc_set_ntp_time() to use timespec64 rtc_set_ntp_time() uses timespec which is y2038-unsafe, so modify to use timespec64 which is y2038-safe, then replace rtc_time_to_tm() with rtc_time64_to_tm(). Also adjust all its call sites(only NTP uses it) accordingly. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Xunlei Pang Signed-off-by: John Stultz --- drivers/rtc/systohc.c | 6 +++--- include/linux/rtc.h | 2 +- kernel/time/ntp.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index bf3e242ccc5c..eb71872d0361 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -20,16 +20,16 @@ * * If temporary failure is indicated the caller should try again 'soon' */ -int rtc_set_ntp_time(struct timespec now) +int rtc_set_ntp_time(struct timespec64 now) { struct rtc_device *rtc; struct rtc_time tm; int err = -ENODEV; if (now.tv_nsec < (NSEC_PER_SEC >> 1)) - rtc_time_to_tm(now.tv_sec, &tm); + rtc_time64_to_tm(now.tv_sec, &tm); else - rtc_time_to_tm(now.tv_sec + 1, &tm); + rtc_time64_to_tm(now.tv_sec + 1, &tm); rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); if (rtc) { diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6d6be09a2fe5..dcad7ee0d746 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -161,7 +161,7 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); -extern int rtc_set_ntp_time(struct timespec now); +extern int rtc_set_ntp_time(struct timespec64 now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 87a346fd6d61..183dfe2191c6 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -488,13 +488,13 @@ static void sync_cmos_clock(struct work_struct *work) getnstimeofday64(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec adjust = timespec64_to_timespec(now); + struct timespec64 adjust = now; fail = -ENODEV; if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); #ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock(adjust); + fail = update_persistent_clock(timespec64_to_timespec(adjust)); #endif #ifdef CONFIG_RTC_SYSTOHC if (fail == -ENODEV) -- cgit v1.2.3 From 425c1d4e5b6d4bd700eb94ad8318bdb05431fdc7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 14:57:53 -0500 Subject: NFSv4: Fix lock on-wire reordering issues This patch ensures that the server cannot reorder our LOCK/LOCKU requests if they are sent in parallel on the wire. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 29 ++++++++++++++++++++++++----- fs/nfs/nfs4xdr.c | 6 +++--- include/linux/nfs_xdr.h | 6 +++--- 3 files changed, 30 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f12ded041a42..41e7c2fc046e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5393,7 +5393,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->arg.fl = &p->fl; p->arg.seqid = seqid; p->res.seqid = seqid; - p->arg.stateid = &lsp->ls_stateid; p->lsp = lsp; atomic_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ @@ -5428,6 +5427,9 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &calldata->lsp->ls_stateid)) + rpc_restart_call_prepare(task); break; default: if (nfs4_async_handle_error(task, calldata->server, @@ -5443,6 +5445,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data) if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) goto out_wait; + nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid); if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) { /* Note: exit _without_ running nfs4_locku_done */ goto out_no_action; @@ -5584,7 +5587,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask); if (IS_ERR(p->arg.lock_seqid)) goto out_free_seqid; - p->arg.lock_stateid = &lsp->ls_stateid; p->arg.lock_owner.clientid = server->nfs_client->cl_clientid; p->arg.lock_owner.id = lsp->ls_seqid.owner_id; p->arg.lock_owner.s_dev = server->s_dev; @@ -5615,11 +5617,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) { goto out_release_lock_seqid; } - data->arg.open_stateid = &state->open_stateid; + nfs4_stateid_copy(&data->arg.open_stateid, + &state->open_stateid); data->arg.new_lock_owner = 1; data->res.open_seqid = data->arg.open_seqid; - } else + } else { data->arg.new_lock_owner = 0; + nfs4_stateid_copy(&data->arg.lock_stateid, + &data->lsp->ls_stateid); + } if (!nfs4_valid_open_stateid(state)) { data->rpc_status = -EBADF; task->tk_action = NULL; @@ -5651,7 +5657,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) return; data->rpc_status = task->tk_status; - if (task->tk_status == 0) { + switch (task->tk_status) { + case 0: renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp); if (data->arg.new_lock_owner != 0) { @@ -5660,6 +5667,18 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) rpc_restart_call_prepare(task); + break; + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + if (data->arg.new_lock_owner != 0) { + if (!nfs4_stateid_match(&data->arg.open_stateid, + &lsp->ls_state->open_stateid)) + rpc_restart_call_prepare(task); + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, + &lsp->ls_stateid)) + rpc_restart_call_prepare(task); } dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d05fada4929c..e3018e7a316c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1304,12 +1304,12 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args *p = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ encode_nfs4_seqid(xdr, args->open_seqid); - encode_nfs4_stateid(xdr, args->open_stateid); + encode_nfs4_stateid(xdr, &args->open_stateid); encode_nfs4_seqid(xdr, args->lock_seqid); encode_lockowner(xdr, &args->lock_owner); } else { - encode_nfs4_stateid(xdr, args->lock_stateid); + encode_nfs4_stateid(xdr, &args->lock_stateid); encode_nfs4_seqid(xdr, args->lock_seqid); } } @@ -1333,7 +1333,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr); encode_uint32(xdr, nfs4_lock_type(args->fl, 0)); encode_nfs4_seqid(xdr, args->seqid); - encode_nfs4_stateid(xdr, args->stateid); + encode_nfs4_stateid(xdr, &args->stateid); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, args->fl->fl_start); xdr_encode_hyper(p, nfs4_lock_length(args->fl)); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7e38d641236e..b6a6953c0f09 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -416,9 +416,9 @@ struct nfs_lock_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * lock_seqid; - nfs4_stateid * lock_stateid; + nfs4_stateid lock_stateid; struct nfs_seqid * open_seqid; - nfs4_stateid * open_stateid; + nfs4_stateid open_stateid; struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; @@ -437,7 +437,7 @@ struct nfs_locku_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * seqid; - nfs4_stateid * stateid; + nfs4_stateid stateid; }; struct nfs_locku_res { -- cgit v1.2.3 From c69899a17ca4836230720e65493942d9582a0424 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 16:03:52 -0500 Subject: NFSv4: Update of VFS byte range lock must be atomic with the stateid update Ensure that we test the lock stateid remained unchanged while we were updating the VFS tracking of the byte range lock. Have the process replay the lock to the server if we detect that was not the case. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 37 +++++++++++++++---------------------- include/linux/nfs_xdr.h | 1 + 2 files changed, 16 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 41e7c2fc046e..9f6baf98942c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5420,9 +5420,10 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) switch (task->tk_status) { case 0: renew_lease(calldata->server, calldata->timestamp); - nfs4_update_lock_stateid(calldata->lsp, - &calldata->res.stateid); - break; + do_vfs_lock(calldata->fl.fl_file, &calldata->fl); + if (nfs4_update_lock_stateid(calldata->lsp, + &calldata->res.stateid)) + break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: @@ -5661,6 +5662,13 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) case 0: renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp); + if (data->arg.new_lock) { + data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); + if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) { + rpc_restart_call_prepare(task); + break; + } + } if (data->arg.new_lock_owner != 0) { nfs_confirm_seqid(&lsp->ls_seqid, 0); nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); @@ -5760,7 +5768,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f if (recovery_type == NFS_LOCK_RECLAIM) data->arg.reclaim = NFS_LOCK_RECLAIM; nfs4_set_sequence_privileged(&data->arg.seq_args); - } + } else + data->arg.new_lock = 1; task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -5884,10 +5893,8 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) { - struct nfs4_state_owner *sp = state->owner; struct nfs_inode *nfsi = NFS_I(state->inode); unsigned char fl_flags = request->fl_flags; - unsigned int seq; int status = -ENOLCK; if ((fl_flags & FL_POSIX) && @@ -5907,25 +5914,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock /* ...but avoid races with delegation recall... */ request->fl_flags = fl_flags & ~FL_SLEEP; status = do_vfs_lock(request->fl_file, request); - goto out_unlock; - } - seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - up_read(&nfsi->rwsem); - status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW); - if (status != 0) + up_read(&nfsi->rwsem); goto out; - down_read(&nfsi->rwsem); - if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) { - status = -NFS4ERR_DELAY; - goto out_unlock; } - /* Note: we always want to sleep here! */ - request->fl_flags = fl_flags | FL_SLEEP; - if (do_vfs_lock(request->fl_file, request) < 0) - printk(KERN_WARNING "NFS: %s: VFS is out of sync with lock " - "manager!\n", __func__); -out_unlock: up_read(&nfsi->rwsem); + status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW); out: request->fl_flags = fl_flags; return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b6a6953c0f09..e5c3b620a609 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -422,6 +422,7 @@ struct nfs_lock_args { struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; + unsigned char new_lock : 1; unsigned char new_lock_owner : 1; }; -- cgit v1.2.3 From e9fb8b7e4f6af17e3aa4835281e06fdc920341f9 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 6 Jan 2015 16:48:36 +0000 Subject: compat: Declare compat_sys_sigpending and compat_sys_sigprocmask prototypes __ARCH_WANT_SYS_SIGPENDING or __ARCH_WANT_SYS_SIGPROGMASK may be defined for compat support but the corresponding prototypes are missing from linux/compat.h. Signed-off-by: Catalin Marinas Acked-by: Andrew Morton Cc: Arnd Bergmann --- include/linux/compat.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 7450ca2ac1fc..ab25814690bc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -689,6 +689,15 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); +#ifdef __ARCH_WANT_SYS_SIGPENDING +asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); +#endif + +#ifdef __ARCH_WANT_SYS_SIGPROCMASK +asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, + compat_old_sigset_t __user *oset); +#endif + int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define compat_save_altstack_ex(uss, sp) do { \ -- cgit v1.2.3 From 54e45c169dbce43cf46d00eb1521b655b6e4f9e9 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 6 Jan 2015 16:52:38 +0000 Subject: syscalls: Declare sys_*stat64 prototypes if __ARCH_WANT_(COMPAT_)STAT64 Currently, the sys_stat64, sys_fstat64 and sys_lstat64 prototpyes are only declared if BITS_PER_LONG == 32. Following commit 0753f70f07fb (fs: Build sys_stat64() and friends if __ARCH_WANT_COMPAT_STAT64), the implementation of these functions is allowed on 64-bit systems for compat support. The patch changes the condition on the prototype declaration from BITS_PER_LONG == 32 to defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64). In addition, it moves the sys_fstatat64 prototype under the same #if block Signed-off-by: Catalin Marinas Acked-by: Andrew Morton Cc: Arnd Bergmann --- include/linux/syscalls.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 85893d744901..76d1e38aabe1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -410,12 +410,16 @@ asmlinkage long sys_newlstat(const char __user *filename, struct stat __user *statbuf); asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); -#if BITS_PER_LONG == 32 +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); asmlinkage long sys_lstat64(const char __user *filename, struct stat64 __user *statbuf); +asmlinkage long sys_fstatat64(int dfd, const char __user *filename, + struct stat64 __user *statbuf, int flag); +#endif +#if BITS_PER_LONG == 32 asmlinkage long sys_truncate64(const char __user *path, loff_t length); asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); #endif @@ -771,8 +775,6 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long sys_newfstatat(int dfd, const char __user *filename, struct stat __user *statbuf, int flag); -asmlinkage long sys_fstatat64(int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag); asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, int bufsiz); asmlinkage long sys_utimensat(int dfd, const char __user *filename, -- cgit v1.2.3 From 05c80d75f10ad7d3f95444b65788d6a0bbb4380d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 19 Dec 2014 09:14:20 -0300 Subject: [media] hdmi: add new HDMI 2.0 defines Add new Video InfoFrame colorspace information introduced in HDMI 2.0 and new Audio Coding Extension Types, also from HDMI 2.0. HDMI_CONTENT_TYPE_NONE was renamed to _GRAPHICS since that's what it is called in CEA-861-F. Signed-off-by: Hans Verkuil Reviewed-by: Thierry Reding Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index cbb5790a35cd..5afc0bff2bbe 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -52,12 +52,18 @@ enum hdmi_colorspace { HDMI_COLORSPACE_RGB, HDMI_COLORSPACE_YUV422, HDMI_COLORSPACE_YUV444, + HDMI_COLORSPACE_YUV420, + HDMI_COLORSPACE_RESERVED4, + HDMI_COLORSPACE_RESERVED5, + HDMI_COLORSPACE_RESERVED6, + HDMI_COLORSPACE_IDO_DEFINED, }; enum hdmi_scan_mode { HDMI_SCAN_MODE_NONE, HDMI_SCAN_MODE_OVERSCAN, HDMI_SCAN_MODE_UNDERSCAN, + HDMI_SCAN_MODE_RESERVED, }; enum hdmi_colorimetry { @@ -71,6 +77,7 @@ enum hdmi_picture_aspect { HDMI_PICTURE_ASPECT_NONE, HDMI_PICTURE_ASPECT_4_3, HDMI_PICTURE_ASPECT_16_9, + HDMI_PICTURE_ASPECT_RESERVED, }; enum hdmi_active_aspect { @@ -92,12 +99,18 @@ enum hdmi_extended_colorimetry { HDMI_EXTENDED_COLORIMETRY_S_YCC_601, HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, + + /* The following EC values are only defined in CEA-861-F. */ + HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM, + HDMI_EXTENDED_COLORIMETRY_BT2020, + HDMI_EXTENDED_COLORIMETRY_RESERVED, }; enum hdmi_quantization_range { HDMI_QUANTIZATION_RANGE_DEFAULT, HDMI_QUANTIZATION_RANGE_LIMITED, HDMI_QUANTIZATION_RANGE_FULL, + HDMI_QUANTIZATION_RANGE_RESERVED, }; /* non-uniform picture scaling */ @@ -114,7 +127,7 @@ enum hdmi_ycc_quantization_range { }; enum hdmi_content_type { - HDMI_CONTENT_TYPE_NONE, + HDMI_CONTENT_TYPE_GRAPHICS, HDMI_CONTENT_TYPE_PHOTO, HDMI_CONTENT_TYPE_CINEMA, HDMI_CONTENT_TYPE_GAME, @@ -194,6 +207,7 @@ enum hdmi_audio_coding_type { HDMI_AUDIO_CODING_TYPE_MLP, HDMI_AUDIO_CODING_TYPE_DST, HDMI_AUDIO_CODING_TYPE_WMA_PRO, + HDMI_AUDIO_CODING_TYPE_CXT, }; enum hdmi_audio_sample_size { @@ -216,9 +230,23 @@ enum hdmi_audio_sample_frequency { enum hdmi_audio_coding_type_ext { HDMI_AUDIO_CODING_TYPE_EXT_STREAM, + + /* + * The next three CXT values are defined in CEA-861-E only. + * They do not exist in older versions, and in CEA-861-F they are + * defined as 'Not in use'. + */ HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC, HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2, HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND, + + /* The following CXT values are only defined in CEA-861-F. */ + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_V2, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC, + HDMI_AUDIO_CODING_TYPE_EXT_DRA, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_SURROUND, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC_SURROUND = 10, }; struct hdmi_audio_infoframe { -- cgit v1.2.3 From 2c676f378edb16cb68f7815581c8119fc43a4b85 Mon Sep 17 00:00:00 2001 From: Martin Bugge Date: Fri, 19 Dec 2014 09:14:21 -0300 Subject: [media] hdmi: added unpack and logging functions for InfoFrames When receiving video it is very useful to be able to unpack the InfoFrames. Logging is useful as well, both for transmitters and receivers. Especially when implementing the VIDIOC_LOG_STATUS ioctl (supported by many V4L2 drivers) for a receiver it is important to be able to easily log what the InfoFrame contains. This greatly simplifies debugging. Signed-off-by: Martin Bugge Signed-off-by: Hans Verkuil Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- drivers/video/hdmi.c | 822 ++++++++++++++++++++++++++++++++++++++++++++++++++- include/linux/hdmi.h | 4 + 2 files changed, 819 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c index 9e758a8f890d..a7c6ae4e10e5 100644 --- a/drivers/video/hdmi.c +++ b/drivers/video/hdmi.c @@ -27,10 +27,12 @@ #include #include #include +#include -static void hdmi_infoframe_checksum(void *buffer, size_t size) +#define hdmi_log(fmt, ...) dev_printk(level, dev, fmt, ##__VA_ARGS__) + +static u8 hdmi_infoframe_checksum(u8 *ptr, size_t size) { - u8 *ptr = buffer; u8 csum = 0; size_t i; @@ -38,7 +40,14 @@ static void hdmi_infoframe_checksum(void *buffer, size_t size) for (i = 0; i < size; i++) csum += ptr[i]; - ptr[3] = 256 - csum; + return 256 - csum; +} + +static void hdmi_infoframe_set_checksum(void *buffer, size_t size) +{ + u8 *ptr = buffer; + + ptr[3] = hdmi_infoframe_checksum(buffer, size); } /** @@ -136,7 +145,7 @@ ssize_t hdmi_avi_infoframe_pack(struct hdmi_avi_infoframe *frame, void *buffer, ptr[11] = frame->right_bar & 0xff; ptr[12] = (frame->right_bar >> 8) & 0xff; - hdmi_infoframe_checksum(buffer, length); + hdmi_infoframe_set_checksum(buffer, length); return length; } @@ -206,7 +215,7 @@ ssize_t hdmi_spd_infoframe_pack(struct hdmi_spd_infoframe *frame, void *buffer, ptr[24] = frame->sdi; - hdmi_infoframe_checksum(buffer, length); + hdmi_infoframe_set_checksum(buffer, length); return length; } @@ -281,7 +290,7 @@ ssize_t hdmi_audio_infoframe_pack(struct hdmi_audio_infoframe *frame, if (frame->downmix_inhibit) ptr[4] |= BIT(7); - hdmi_infoframe_checksum(buffer, length); + hdmi_infoframe_set_checksum(buffer, length); return length; } @@ -373,7 +382,7 @@ ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, ptr[9] = (frame->s3d_ext_data & 0xf) << 4; } - hdmi_infoframe_checksum(buffer, length); + hdmi_infoframe_set_checksum(buffer, length); return length; } @@ -434,3 +443,802 @@ hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size) return length; } EXPORT_SYMBOL(hdmi_infoframe_pack); + +static const char *hdmi_infoframe_type_get_name(enum hdmi_infoframe_type type) +{ + if (type < 0x80 || type > 0x9f) + return "Invalid"; + switch (type) { + case HDMI_INFOFRAME_TYPE_VENDOR: + return "Vendor"; + case HDMI_INFOFRAME_TYPE_AVI: + return "Auxiliary Video Information (AVI)"; + case HDMI_INFOFRAME_TYPE_SPD: + return "Source Product Description (SPD)"; + case HDMI_INFOFRAME_TYPE_AUDIO: + return "Audio"; + } + return "Reserved"; +} + +static void hdmi_infoframe_log_header(const char *level, + struct device *dev, + struct hdmi_any_infoframe *frame) +{ + hdmi_log("HDMI infoframe: %s, version %u, length %u\n", + hdmi_infoframe_type_get_name(frame->type), + frame->version, frame->length); +} + +static const char *hdmi_colorspace_get_name(enum hdmi_colorspace colorspace) +{ + switch (colorspace) { + case HDMI_COLORSPACE_RGB: + return "RGB"; + case HDMI_COLORSPACE_YUV422: + return "YCbCr 4:2:2"; + case HDMI_COLORSPACE_YUV444: + return "YCbCr 4:4:4"; + case HDMI_COLORSPACE_YUV420: + return "YCbCr 4:2:0"; + case HDMI_COLORSPACE_RESERVED4: + return "Reserved (4)"; + case HDMI_COLORSPACE_RESERVED5: + return "Reserved (5)"; + case HDMI_COLORSPACE_RESERVED6: + return "Reserved (6)"; + case HDMI_COLORSPACE_IDO_DEFINED: + return "IDO Defined"; + } + return "Invalid"; +} + +static const char *hdmi_scan_mode_get_name(enum hdmi_scan_mode scan_mode) +{ + switch (scan_mode) { + case HDMI_SCAN_MODE_NONE: + return "No Data"; + case HDMI_SCAN_MODE_OVERSCAN: + return "Overscan"; + case HDMI_SCAN_MODE_UNDERSCAN: + return "Underscan"; + case HDMI_SCAN_MODE_RESERVED: + return "Reserved"; + } + return "Invalid"; +} + +static const char *hdmi_colorimetry_get_name(enum hdmi_colorimetry colorimetry) +{ + switch (colorimetry) { + case HDMI_COLORIMETRY_NONE: + return "No Data"; + case HDMI_COLORIMETRY_ITU_601: + return "ITU601"; + case HDMI_COLORIMETRY_ITU_709: + return "ITU709"; + case HDMI_COLORIMETRY_EXTENDED: + return "Extended"; + } + return "Invalid"; +} + +static const char * +hdmi_picture_aspect_get_name(enum hdmi_picture_aspect picture_aspect) +{ + switch (picture_aspect) { + case HDMI_PICTURE_ASPECT_NONE: + return "No Data"; + case HDMI_PICTURE_ASPECT_4_3: + return "4:3"; + case HDMI_PICTURE_ASPECT_16_9: + return "16:9"; + case HDMI_PICTURE_ASPECT_RESERVED: + return "Reserved"; + } + return "Invalid"; +} + +static const char * +hdmi_active_aspect_get_name(enum hdmi_active_aspect active_aspect) +{ + if (active_aspect < 0 || active_aspect > 0xf) + return "Invalid"; + + switch (active_aspect) { + case HDMI_ACTIVE_ASPECT_16_9_TOP: + return "16:9 Top"; + case HDMI_ACTIVE_ASPECT_14_9_TOP: + return "14:9 Top"; + case HDMI_ACTIVE_ASPECT_16_9_CENTER: + return "16:9 Center"; + case HDMI_ACTIVE_ASPECT_PICTURE: + return "Same as Picture"; + case HDMI_ACTIVE_ASPECT_4_3: + return "4:3"; + case HDMI_ACTIVE_ASPECT_16_9: + return "16:9"; + case HDMI_ACTIVE_ASPECT_14_9: + return "14:9"; + case HDMI_ACTIVE_ASPECT_4_3_SP_14_9: + return "4:3 SP 14:9"; + case HDMI_ACTIVE_ASPECT_16_9_SP_14_9: + return "16:9 SP 14:9"; + case HDMI_ACTIVE_ASPECT_16_9_SP_4_3: + return "16:9 SP 4:3"; + } + return "Reserved"; +} + +static const char * +hdmi_extended_colorimetry_get_name(enum hdmi_extended_colorimetry ext_col) +{ + switch (ext_col) { + case HDMI_EXTENDED_COLORIMETRY_XV_YCC_601: + return "xvYCC 601"; + case HDMI_EXTENDED_COLORIMETRY_XV_YCC_709: + return "xvYCC 709"; + case HDMI_EXTENDED_COLORIMETRY_S_YCC_601: + return "sYCC 601"; + case HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601: + return "Adobe YCC 601"; + case HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB: + return "Adobe RGB"; + case HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM: + return "BT.2020 Constant Luminance"; + case HDMI_EXTENDED_COLORIMETRY_BT2020: + return "BT.2020"; + case HDMI_EXTENDED_COLORIMETRY_RESERVED: + return "Reserved"; + } + return "Invalid"; +} + +static const char * +hdmi_quantization_range_get_name(enum hdmi_quantization_range qrange) +{ + switch (qrange) { + case HDMI_QUANTIZATION_RANGE_DEFAULT: + return "Default"; + case HDMI_QUANTIZATION_RANGE_LIMITED: + return "Limited"; + case HDMI_QUANTIZATION_RANGE_FULL: + return "Full"; + case HDMI_QUANTIZATION_RANGE_RESERVED: + return "Reserved"; + } + return "Invalid"; +} + +static const char *hdmi_nups_get_name(enum hdmi_nups nups) +{ + switch (nups) { + case HDMI_NUPS_UNKNOWN: + return "Unknown Non-uniform Scaling"; + case HDMI_NUPS_HORIZONTAL: + return "Horizontally Scaled"; + case HDMI_NUPS_VERTICAL: + return "Vertically Scaled"; + case HDMI_NUPS_BOTH: + return "Horizontally and Vertically Scaled"; + } + return "Invalid"; +} + +static const char * +hdmi_ycc_quantization_range_get_name(enum hdmi_ycc_quantization_range qrange) +{ + switch (qrange) { + case HDMI_YCC_QUANTIZATION_RANGE_LIMITED: + return "Limited"; + case HDMI_YCC_QUANTIZATION_RANGE_FULL: + return "Full"; + } + return "Invalid"; +} + +static const char * +hdmi_content_type_get_name(enum hdmi_content_type content_type) +{ + switch (content_type) { + case HDMI_CONTENT_TYPE_GRAPHICS: + return "Graphics"; + case HDMI_CONTENT_TYPE_PHOTO: + return "Photo"; + case HDMI_CONTENT_TYPE_CINEMA: + return "Cinema"; + case HDMI_CONTENT_TYPE_GAME: + return "Game"; + } + return "Invalid"; +} + +/** + * hdmi_avi_infoframe_log() - log info of HDMI AVI infoframe + * @level: logging level + * @dev: device + * @frame: HDMI AVI infoframe + */ +static void hdmi_avi_infoframe_log(const char *level, + struct device *dev, + struct hdmi_avi_infoframe *frame) +{ + hdmi_infoframe_log_header(level, dev, + (struct hdmi_any_infoframe *)frame); + + hdmi_log(" colorspace: %s\n", + hdmi_colorspace_get_name(frame->colorspace)); + hdmi_log(" scan mode: %s\n", + hdmi_scan_mode_get_name(frame->scan_mode)); + hdmi_log(" colorimetry: %s\n", + hdmi_colorimetry_get_name(frame->colorimetry)); + hdmi_log(" picture aspect: %s\n", + hdmi_picture_aspect_get_name(frame->picture_aspect)); + hdmi_log(" active aspect: %s\n", + hdmi_active_aspect_get_name(frame->active_aspect)); + hdmi_log(" itc: %s\n", frame->itc ? "IT Content" : "No Data"); + hdmi_log(" extended colorimetry: %s\n", + hdmi_extended_colorimetry_get_name(frame->extended_colorimetry)); + hdmi_log(" quantization range: %s\n", + hdmi_quantization_range_get_name(frame->quantization_range)); + hdmi_log(" nups: %s\n", hdmi_nups_get_name(frame->nups)); + hdmi_log(" video code: %u\n", frame->video_code); + hdmi_log(" ycc quantization range: %s\n", + hdmi_ycc_quantization_range_get_name(frame->ycc_quantization_range)); + hdmi_log(" hdmi content type: %s\n", + hdmi_content_type_get_name(frame->content_type)); + hdmi_log(" pixel repeat: %u\n", frame->pixel_repeat); + hdmi_log(" bar top %u, bottom %u, left %u, right %u\n", + frame->top_bar, frame->bottom_bar, + frame->left_bar, frame->right_bar); +} + +static const char *hdmi_spd_sdi_get_name(enum hdmi_spd_sdi sdi) +{ + if (sdi < 0 || sdi > 0xff) + return "Invalid"; + switch (sdi) { + case HDMI_SPD_SDI_UNKNOWN: + return "Unknown"; + case HDMI_SPD_SDI_DSTB: + return "Digital STB"; + case HDMI_SPD_SDI_DVDP: + return "DVD Player"; + case HDMI_SPD_SDI_DVHS: + return "D-VHS"; + case HDMI_SPD_SDI_HDDVR: + return "HDD Videorecorder"; + case HDMI_SPD_SDI_DVC: + return "DVC"; + case HDMI_SPD_SDI_DSC: + return "DSC"; + case HDMI_SPD_SDI_VCD: + return "Video CD"; + case HDMI_SPD_SDI_GAME: + return "Game"; + case HDMI_SPD_SDI_PC: + return "PC General"; + case HDMI_SPD_SDI_BD: + return "Blu-Ray Disc (BD)"; + case HDMI_SPD_SDI_SACD: + return "Super Audio CD"; + case HDMI_SPD_SDI_HDDVD: + return "HD DVD"; + case HDMI_SPD_SDI_PMP: + return "PMP"; + } + return "Reserved"; +} + +/** + * hdmi_spd_infoframe_log() - log info of HDMI SPD infoframe + * @level: logging level + * @dev: device + * @frame: HDMI SPD infoframe + */ +static void hdmi_spd_infoframe_log(const char *level, + struct device *dev, + struct hdmi_spd_infoframe *frame) +{ + u8 buf[17]; + + hdmi_infoframe_log_header(level, dev, + (struct hdmi_any_infoframe *)frame); + + memset(buf, 0, sizeof(buf)); + + strncpy(buf, frame->vendor, 8); + hdmi_log(" vendor: %s\n", buf); + strncpy(buf, frame->product, 16); + hdmi_log(" product: %s\n", buf); + hdmi_log(" source device information: %s (0x%x)\n", + hdmi_spd_sdi_get_name(frame->sdi), frame->sdi); +} + +static const char * +hdmi_audio_coding_type_get_name(enum hdmi_audio_coding_type coding_type) +{ + switch (coding_type) { + case HDMI_AUDIO_CODING_TYPE_STREAM: + return "Refer to Stream Header"; + case HDMI_AUDIO_CODING_TYPE_PCM: + return "PCM"; + case HDMI_AUDIO_CODING_TYPE_AC3: + return "AC-3"; + case HDMI_AUDIO_CODING_TYPE_MPEG1: + return "MPEG1"; + case HDMI_AUDIO_CODING_TYPE_MP3: + return "MP3"; + case HDMI_AUDIO_CODING_TYPE_MPEG2: + return "MPEG2"; + case HDMI_AUDIO_CODING_TYPE_AAC_LC: + return "AAC"; + case HDMI_AUDIO_CODING_TYPE_DTS: + return "DTS"; + case HDMI_AUDIO_CODING_TYPE_ATRAC: + return "ATRAC"; + case HDMI_AUDIO_CODING_TYPE_DSD: + return "One Bit Audio"; + case HDMI_AUDIO_CODING_TYPE_EAC3: + return "Dolby Digital +"; + case HDMI_AUDIO_CODING_TYPE_DTS_HD: + return "DTS-HD"; + case HDMI_AUDIO_CODING_TYPE_MLP: + return "MAT (MLP)"; + case HDMI_AUDIO_CODING_TYPE_DST: + return "DST"; + case HDMI_AUDIO_CODING_TYPE_WMA_PRO: + return "WMA PRO"; + case HDMI_AUDIO_CODING_TYPE_CXT: + return "Refer to CXT"; + } + return "Invalid"; +} + +static const char * +hdmi_audio_sample_size_get_name(enum hdmi_audio_sample_size sample_size) +{ + switch (sample_size) { + case HDMI_AUDIO_SAMPLE_SIZE_STREAM: + return "Refer to Stream Header"; + case HDMI_AUDIO_SAMPLE_SIZE_16: + return "16 bit"; + case HDMI_AUDIO_SAMPLE_SIZE_20: + return "20 bit"; + case HDMI_AUDIO_SAMPLE_SIZE_24: + return "24 bit"; + } + return "Invalid"; +} + +static const char * +hdmi_audio_sample_frequency_get_name(enum hdmi_audio_sample_frequency freq) +{ + switch (freq) { + case HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM: + return "Refer to Stream Header"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_32000: + return "32 kHz"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_44100: + return "44.1 kHz (CD)"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_48000: + return "48 kHz"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_88200: + return "88.2 kHz"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_96000: + return "96 kHz"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_176400: + return "176.4 kHz"; + case HDMI_AUDIO_SAMPLE_FREQUENCY_192000: + return "192 kHz"; + } + return "Invalid"; +} + +static const char * +hdmi_audio_coding_type_ext_get_name(enum hdmi_audio_coding_type_ext ctx) +{ + if (ctx < 0 || ctx > 0x1f) + return "Invalid"; + + switch (ctx) { + case HDMI_AUDIO_CODING_TYPE_EXT_STREAM: + return "Refer to CT"; + case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC: + return "HE AAC"; + case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2: + return "HE AAC v2"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND: + return "MPEG SURROUND"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC: + return "MPEG-4 HE AAC"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_V2: + return "MPEG-4 HE AAC v2"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC: + return "MPEG-4 AAC LC"; + case HDMI_AUDIO_CODING_TYPE_EXT_DRA: + return "DRA"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_SURROUND: + return "MPEG-4 HE AAC + MPEG Surround"; + case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC_SURROUND: + return "MPEG-4 AAC LC + MPEG Surround"; + } + return "Reserved"; +} + +/** + * hdmi_audio_infoframe_log() - log info of HDMI AUDIO infoframe + * @level: logging level + * @dev: device + * @frame: HDMI AUDIO infoframe + */ +static void hdmi_audio_infoframe_log(const char *level, + struct device *dev, + struct hdmi_audio_infoframe *frame) +{ + hdmi_infoframe_log_header(level, dev, + (struct hdmi_any_infoframe *)frame); + + if (frame->channels) + hdmi_log(" channels: %u\n", frame->channels - 1); + else + hdmi_log(" channels: Refer to stream header\n"); + hdmi_log(" coding type: %s\n", + hdmi_audio_coding_type_get_name(frame->coding_type)); + hdmi_log(" sample size: %s\n", + hdmi_audio_sample_size_get_name(frame->sample_size)); + hdmi_log(" sample frequency: %s\n", + hdmi_audio_sample_frequency_get_name(frame->sample_frequency)); + hdmi_log(" coding type ext: %s\n", + hdmi_audio_coding_type_ext_get_name(frame->coding_type_ext)); + hdmi_log(" channel allocation: 0x%x\n", + frame->channel_allocation); + hdmi_log(" level shift value: %u dB\n", + frame->level_shift_value); + hdmi_log(" downmix inhibit: %s\n", + frame->downmix_inhibit ? "Yes" : "No"); +} + +static const char * +hdmi_3d_structure_get_name(enum hdmi_3d_structure s3d_struct) +{ + if (s3d_struct < 0 || s3d_struct > 0xf) + return "Invalid"; + + switch (s3d_struct) { + case HDMI_3D_STRUCTURE_FRAME_PACKING: + return "Frame Packing"; + case HDMI_3D_STRUCTURE_FIELD_ALTERNATIVE: + return "Field Alternative"; + case HDMI_3D_STRUCTURE_LINE_ALTERNATIVE: + return "Line Alternative"; + case HDMI_3D_STRUCTURE_SIDE_BY_SIDE_FULL: + return "Side-by-side (Full)"; + case HDMI_3D_STRUCTURE_L_DEPTH: + return "L + Depth"; + case HDMI_3D_STRUCTURE_L_DEPTH_GFX_GFX_DEPTH: + return "L + Depth + Graphics + Graphics-depth"; + case HDMI_3D_STRUCTURE_TOP_AND_BOTTOM: + return "Top-and-Bottom"; + case HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF: + return "Side-by-side (Half)"; + default: + break; + } + return "Reserved"; +} + +/** + * hdmi_vendor_infoframe_log() - log info of HDMI VENDOR infoframe + * @level: logging level + * @dev: device + * @frame: HDMI VENDOR infoframe + */ +static void +hdmi_vendor_any_infoframe_log(const char *level, + struct device *dev, + union hdmi_vendor_any_infoframe *frame) +{ + struct hdmi_vendor_infoframe *hvf = &frame->hdmi; + + hdmi_infoframe_log_header(level, dev, + (struct hdmi_any_infoframe *)frame); + + if (frame->any.oui != HDMI_IEEE_OUI) { + hdmi_log(" not a HDMI vendor infoframe\n"); + return; + } + if (hvf->vic == 0 && hvf->s3d_struct == HDMI_3D_STRUCTURE_INVALID) { + hdmi_log(" empty frame\n"); + return; + } + + if (hvf->vic) + hdmi_log(" HDMI VIC: %u\n", hvf->vic); + if (hvf->s3d_struct != HDMI_3D_STRUCTURE_INVALID) { + hdmi_log(" 3D structure: %s\n", + hdmi_3d_structure_get_name(hvf->s3d_struct)); + if (hvf->s3d_struct >= HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF) + hdmi_log(" 3D extension data: %d\n", + hvf->s3d_ext_data); + } +} + +/** + * hdmi_infoframe_log() - log info of HDMI infoframe + * @level: logging level + * @dev: device + * @frame: HDMI infoframe + */ +void hdmi_infoframe_log(const char *level, + struct device *dev, + union hdmi_infoframe *frame) +{ + switch (frame->any.type) { + case HDMI_INFOFRAME_TYPE_AVI: + hdmi_avi_infoframe_log(level, dev, &frame->avi); + break; + case HDMI_INFOFRAME_TYPE_SPD: + hdmi_spd_infoframe_log(level, dev, &frame->spd); + break; + case HDMI_INFOFRAME_TYPE_AUDIO: + hdmi_audio_infoframe_log(level, dev, &frame->audio); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + hdmi_vendor_any_infoframe_log(level, dev, &frame->vendor); + break; + } +} +EXPORT_SYMBOL(hdmi_infoframe_log); + +/** + * hdmi_avi_infoframe_unpack() - unpack binary buffer to a HDMI AVI infoframe + * @buffer: source buffer + * @frame: HDMI AVI infoframe + * + * Unpacks the information contained in binary @buffer into a structured + * @frame of the HDMI Auxiliary Video (AVI) information frame. + * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4 + * specification. + * + * Returns 0 on success or a negative error code on failure. + */ +static int hdmi_avi_infoframe_unpack(struct hdmi_avi_infoframe *frame, + void *buffer) +{ + u8 *ptr = buffer; + int ret; + + if (ptr[0] != HDMI_INFOFRAME_TYPE_AVI || + ptr[1] != 2 || + ptr[2] != HDMI_AVI_INFOFRAME_SIZE) + return -EINVAL; + + if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(AVI)) != 0) + return -EINVAL; + + ret = hdmi_avi_infoframe_init(frame); + if (ret) + return ret; + + ptr += HDMI_INFOFRAME_HEADER_SIZE; + + frame->colorspace = (ptr[0] >> 5) & 0x3; + if (ptr[0] & 0x10) + frame->active_aspect = ptr[1] & 0xf; + if (ptr[0] & 0x8) { + frame->top_bar = (ptr[5] << 8) + ptr[6]; + frame->bottom_bar = (ptr[7] << 8) + ptr[8]; + } + if (ptr[0] & 0x4) { + frame->left_bar = (ptr[9] << 8) + ptr[10]; + frame->right_bar = (ptr[11] << 8) + ptr[12]; + } + frame->scan_mode = ptr[0] & 0x3; + + frame->colorimetry = (ptr[1] >> 6) & 0x3; + frame->picture_aspect = (ptr[1] >> 4) & 0x3; + frame->active_aspect = ptr[1] & 0xf; + + frame->itc = ptr[2] & 0x80 ? true : false; + frame->extended_colorimetry = (ptr[2] >> 4) & 0x7; + frame->quantization_range = (ptr[2] >> 2) & 0x3; + frame->nups = ptr[2] & 0x3; + + frame->video_code = ptr[3] & 0x7f; + frame->ycc_quantization_range = (ptr[4] >> 6) & 0x3; + frame->content_type = (ptr[4] >> 4) & 0x3; + + frame->pixel_repeat = ptr[4] & 0xf; + + return 0; +} + +/** + * hdmi_spd_infoframe_unpack() - unpack binary buffer to a HDMI SPD infoframe + * @buffer: source buffer + * @frame: HDMI SPD infoframe + * + * Unpacks the information contained in binary @buffer into a structured + * @frame of the HDMI Source Product Description (SPD) information frame. + * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4 + * specification. + * + * Returns 0 on success or a negative error code on failure. + */ +static int hdmi_spd_infoframe_unpack(struct hdmi_spd_infoframe *frame, + void *buffer) +{ + u8 *ptr = buffer; + int ret; + + if (ptr[0] != HDMI_INFOFRAME_TYPE_SPD || + ptr[1] != 1 || + ptr[2] != HDMI_SPD_INFOFRAME_SIZE) { + return -EINVAL; + } + + if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(SPD)) != 0) + return -EINVAL; + + ptr += HDMI_INFOFRAME_HEADER_SIZE; + + ret = hdmi_spd_infoframe_init(frame, ptr, ptr + 8); + if (ret) + return ret; + + frame->sdi = ptr[24]; + + return 0; +} + +/** + * hdmi_audio_infoframe_unpack() - unpack binary buffer to a HDMI AUDIO infoframe + * @buffer: source buffer + * @frame: HDMI Audio infoframe + * + * Unpacks the information contained in binary @buffer into a structured + * @frame of the HDMI Audio information frame. + * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4 + * specification. + * + * Returns 0 on success or a negative error code on failure. + */ +static int hdmi_audio_infoframe_unpack(struct hdmi_audio_infoframe *frame, + void *buffer) +{ + u8 *ptr = buffer; + int ret; + + if (ptr[0] != HDMI_INFOFRAME_TYPE_AUDIO || + ptr[1] != 1 || + ptr[2] != HDMI_AUDIO_INFOFRAME_SIZE) { + return -EINVAL; + } + + if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(AUDIO)) != 0) + return -EINVAL; + + ret = hdmi_audio_infoframe_init(frame); + if (ret) + return ret; + + ptr += HDMI_INFOFRAME_HEADER_SIZE; + + frame->channels = ptr[0] & 0x7; + frame->coding_type = (ptr[0] >> 4) & 0xf; + frame->sample_size = ptr[1] & 0x3; + frame->sample_frequency = (ptr[1] >> 2) & 0x7; + frame->coding_type_ext = ptr[2] & 0x1f; + frame->channel_allocation = ptr[3]; + frame->level_shift_value = (ptr[4] >> 3) & 0xf; + frame->downmix_inhibit = ptr[4] & 0x80 ? true : false; + + return 0; +} + +/** + * hdmi_vendor_infoframe_unpack() - unpack binary buffer to a HDMI vendor infoframe + * @buffer: source buffer + * @frame: HDMI Vendor infoframe + * + * Unpacks the information contained in binary @buffer into a structured + * @frame of the HDMI Vendor information frame. + * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4 + * specification. + * + * Returns 0 on success or a negative error code on failure. + */ +static int +hdmi_vendor_any_infoframe_unpack(union hdmi_vendor_any_infoframe *frame, + void *buffer) +{ + u8 *ptr = buffer; + size_t length; + int ret; + u8 hdmi_video_format; + struct hdmi_vendor_infoframe *hvf = &frame->hdmi; + + if (ptr[0] != HDMI_INFOFRAME_TYPE_VENDOR || + ptr[1] != 1 || + (ptr[2] != 5 && ptr[2] != 6)) + return -EINVAL; + + length = ptr[2]; + + if (hdmi_infoframe_checksum(buffer, + HDMI_INFOFRAME_HEADER_SIZE + length) != 0) + return -EINVAL; + + ptr += HDMI_INFOFRAME_HEADER_SIZE; + + /* HDMI OUI */ + if ((ptr[0] != 0x03) || + (ptr[1] != 0x0c) || + (ptr[2] != 0x00)) + return -EINVAL; + + hdmi_video_format = ptr[3] >> 5; + + if (hdmi_video_format > 0x2) + return -EINVAL; + + ret = hdmi_vendor_infoframe_init(hvf); + if (ret) + return ret; + + hvf->length = length; + + if (hdmi_video_format == 0x1) { + hvf->vic = ptr[4]; + } else if (hdmi_video_format == 0x2) { + hvf->s3d_struct = ptr[4] >> 4; + if (hvf->s3d_struct >= HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF) { + if (length == 6) + hvf->s3d_ext_data = ptr[5] >> 4; + else + return -EINVAL; + } + } + + return 0; +} + +/** + * hdmi_infoframe_unpack() - unpack binary buffer to a HDMI infoframe + * @buffer: source buffer + * @frame: HDMI infoframe + * + * Unpacks the information contained in binary buffer @buffer into a structured + * @frame of a HDMI infoframe. + * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4 + * specification. + * + * Returns 0 on success or a negative error code on failure. + */ +int hdmi_infoframe_unpack(union hdmi_infoframe *frame, void *buffer) +{ + int ret; + u8 *ptr = buffer; + + switch (ptr[0]) { + case HDMI_INFOFRAME_TYPE_AVI: + ret = hdmi_avi_infoframe_unpack(&frame->avi, buffer); + break; + case HDMI_INFOFRAME_TYPE_SPD: + ret = hdmi_spd_infoframe_unpack(&frame->spd, buffer); + break; + case HDMI_INFOFRAME_TYPE_AUDIO: + ret = hdmi_audio_infoframe_unpack(&frame->audio, buffer); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + ret = hdmi_vendor_any_infoframe_unpack(&frame->vendor, buffer); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} +EXPORT_SYMBOL(hdmi_infoframe_unpack); diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 5afc0bff2bbe..2ff34315a1bb 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -25,6 +25,7 @@ #define __LINUX_HDMI_H_ #include +#include enum hdmi_infoframe_type { HDMI_INFOFRAME_TYPE_VENDOR = 0x81, @@ -327,5 +328,8 @@ union hdmi_infoframe { ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size); +int hdmi_infoframe_unpack(union hdmi_infoframe *frame, void *buffer); +void hdmi_infoframe_log(const char *level, struct device *dev, + union hdmi_infoframe *frame); #endif /* _DRM_HDMI_H */ -- cgit v1.2.3 From dc189053e1a5ae606c56e432dae1afc28261a819 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 19 Dec 2014 09:14:22 -0300 Subject: [media] hdmi: rename HDMI_AUDIO_CODING_TYPE_EXT_STREAM to _EXT_CT As per the suggestion of Thierry Reding rename HDMI_AUDIO_CODING_TYPE_EXT_STREAM to HDMI_AUDIO_CODING_TYPE_EXT_CT to be consistent with the CEA-861 spec. Signed-off-by: Hans Verkuil Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- drivers/video/hdmi.c | 2 +- include/linux/hdmi.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c index a7c6ae4e10e5..162689227a23 100644 --- a/drivers/video/hdmi.c +++ b/drivers/video/hdmi.c @@ -842,7 +842,7 @@ hdmi_audio_coding_type_ext_get_name(enum hdmi_audio_coding_type_ext ctx) return "Invalid"; switch (ctx) { - case HDMI_AUDIO_CODING_TYPE_EXT_STREAM: + case HDMI_AUDIO_CODING_TYPE_EXT_CT: return "Refer to CT"; case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC: return "HE AAC"; diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 2ff34315a1bb..e9744202fa29 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -230,7 +230,8 @@ enum hdmi_audio_sample_frequency { }; enum hdmi_audio_coding_type_ext { - HDMI_AUDIO_CODING_TYPE_EXT_STREAM, + /* Refer to Audio Coding Type (CT) field in Data Byte 1 */ + HDMI_AUDIO_CODING_TYPE_EXT_CT, /* * The next three CXT values are defined in CEA-861-E only. -- cgit v1.2.3 From f27b37f5993a080700ccecdce9960d1563eccd36 Mon Sep 17 00:00:00 2001 From: Bintian Wang Date: Tue, 27 Jan 2015 20:50:29 +0800 Subject: regmap: correct the description of structure element in reg_field Fix incorrect description of structure element "msb", which is described as "reg". Signed-off-by: Bintian Wang Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4419b99d8d6e..116655d92269 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -468,7 +468,7 @@ bool regmap_reg_in_ranges(unsigned int reg, * * @reg: Offset of the register within the regmap bank * @lsb: lsb of the register field. - * @reg: msb of the register field. + * @msb: msb of the register field. * @id_size: port size if it has some ports * @id_offset: address offset for each ports */ -- cgit v1.2.3 From 3aa8793f751d4cfcaca886e75ab30dfb00cf1d88 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 28 Nov 2014 14:38:36 +0100 Subject: mmc: core: Initial support for MMC power sequences System on chip designs may specify a specific MMC power sequence. To successfully detect an (e)MMC/SD/SDIO card, that power sequence must be followed while initializing the card. To be able to handle these SOC specific power sequences, let's add a MMC power sequence interface. It provides the following functions to help the mmc core to deal with these power sequences. mmc_pwrseq_alloc() - Invoked from mmc_of_parse(), to initialize data. mmc_pwrseq_pre_power_on()- Invoked in the beginning of mmc_power_up(). mmc_pwrseq_post_power_on()- Invoked at the end in mmc_power_up(). mmc_pwrseq_power_off()- Invoked from mmc_power_off(). mmc_pwrseq_free() - Invoked from mmc_free_host(), to free data. Each MMC power sequence provider will be responsible to implement a set of callbacks. These callbacks mirrors the functions above. This patch adds the skeleton, following patches will extend the core of the MMC power sequence and add support for a specific simple MMC power sequence. Do note, since the mmc_pwrseq_alloc() is invoked from mmc_of_parse(), host drivers needs to make use of this API to enable the support for MMC power sequences. Moreover the MMC power sequence support depends on CONFIG_OF. Signed-off-by: Ulf Hansson Tested-by: Javier Martinez Canillas Reviewed-by: Javier Martinez Canillas --- drivers/mmc/core/Makefile | 2 +- drivers/mmc/core/core.c | 7 +++++++ drivers/mmc/core/host.c | 4 +++- drivers/mmc/core/pwrseq.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/mmc/core/pwrseq.h | 40 +++++++++++++++++++++++++++++++++++++ include/linux/mmc/host.h | 2 ++ 6 files changed, 103 insertions(+), 2 deletions(-) create mode 100644 drivers/mmc/core/pwrseq.c create mode 100644 drivers/mmc/core/pwrseq.h (limited to 'include/linux') diff --git a/drivers/mmc/core/Makefile b/drivers/mmc/core/Makefile index 38ed210ce2f3..ccdd35f78256 100644 --- a/drivers/mmc/core/Makefile +++ b/drivers/mmc/core/Makefile @@ -8,5 +8,5 @@ mmc_core-y := core.o bus.o host.o \ sdio.o sdio_ops.o sdio_bus.o \ sdio_cis.o sdio_io.o sdio_irq.o \ quirks.o slot-gpio.o - +mmc_core-$(CONFIG_OF) += pwrseq.o mmc_core-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d5c176e87951..1be7055548cb 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -40,6 +40,7 @@ #include "bus.h" #include "host.h" #include "sdio_bus.h" +#include "pwrseq.h" #include "mmc_ops.h" #include "sd_ops.h" @@ -1615,6 +1616,8 @@ void mmc_power_up(struct mmc_host *host, u32 ocr) mmc_host_clk_hold(host); + mmc_pwrseq_pre_power_on(host); + host->ios.vdd = fls(ocr) - 1; host->ios.power_mode = MMC_POWER_UP; /* Set initial state and call mmc_set_ios */ @@ -1645,6 +1648,8 @@ void mmc_power_up(struct mmc_host *host, u32 ocr) */ mmc_delay(10); + mmc_pwrseq_post_power_on(host); + mmc_host_clk_release(host); } @@ -1655,6 +1660,8 @@ void mmc_power_off(struct mmc_host *host) mmc_host_clk_hold(host); + mmc_pwrseq_power_off(host); + host->ios.clock = 0; host->ios.vdd = 0; diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 07636449b4de..8be0df758e68 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -30,6 +30,7 @@ #include "core.h" #include "host.h" #include "slot-gpio.h" +#include "pwrseq.h" #define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev) @@ -448,7 +449,7 @@ int mmc_of_parse(struct mmc_host *host) host->dsr_req = 0; } - return 0; + return mmc_pwrseq_alloc(host); } EXPORT_SYMBOL(mmc_of_parse); @@ -588,6 +589,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + mmc_pwrseq_free(host); put_device(&host->class_dev); } diff --git a/drivers/mmc/core/pwrseq.c b/drivers/mmc/core/pwrseq.c new file mode 100644 index 000000000000..bd087723929f --- /dev/null +++ b/drivers/mmc/core/pwrseq.c @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2014 Linaro Ltd + * + * Author: Ulf Hansson + * + * License terms: GNU General Public License (GPL) version 2 + * + * MMC power sequence management + */ +#include + +#include "pwrseq.h" + + +int mmc_pwrseq_alloc(struct mmc_host *host) +{ + return 0; +} + +void mmc_pwrseq_pre_power_on(struct mmc_host *host) +{ + struct mmc_pwrseq *pwrseq = host->pwrseq; + + if (pwrseq && pwrseq->ops && pwrseq->ops->pre_power_on) + pwrseq->ops->pre_power_on(host); +} + +void mmc_pwrseq_post_power_on(struct mmc_host *host) +{ + struct mmc_pwrseq *pwrseq = host->pwrseq; + + if (pwrseq && pwrseq->ops && pwrseq->ops->post_power_on) + pwrseq->ops->post_power_on(host); +} + +void mmc_pwrseq_power_off(struct mmc_host *host) +{ + struct mmc_pwrseq *pwrseq = host->pwrseq; + + if (pwrseq && pwrseq->ops && pwrseq->ops->power_off) + pwrseq->ops->power_off(host); +} + +void mmc_pwrseq_free(struct mmc_host *host) +{ + struct mmc_pwrseq *pwrseq = host->pwrseq; + + if (pwrseq && pwrseq->ops && pwrseq->ops->free) + pwrseq->ops->free(host); +} diff --git a/drivers/mmc/core/pwrseq.h b/drivers/mmc/core/pwrseq.h new file mode 100644 index 000000000000..12aaf2b4745b --- /dev/null +++ b/drivers/mmc/core/pwrseq.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2014 Linaro Ltd + * + * Author: Ulf Hansson + * + * License terms: GNU General Public License (GPL) version 2 + */ +#ifndef _MMC_CORE_PWRSEQ_H +#define _MMC_CORE_PWRSEQ_H + +struct mmc_pwrseq_ops { + void (*pre_power_on)(struct mmc_host *host); + void (*post_power_on)(struct mmc_host *host); + void (*power_off)(struct mmc_host *host); + void (*free)(struct mmc_host *host); +}; + +struct mmc_pwrseq { + struct mmc_pwrseq_ops *ops; +}; + +#ifdef CONFIG_OF + +int mmc_pwrseq_alloc(struct mmc_host *host); +void mmc_pwrseq_pre_power_on(struct mmc_host *host); +void mmc_pwrseq_post_power_on(struct mmc_host *host); +void mmc_pwrseq_power_off(struct mmc_host *host); +void mmc_pwrseq_free(struct mmc_host *host); + +#else + +static inline int mmc_pwrseq_alloc(struct mmc_host *host) { return 0; } +static inline void mmc_pwrseq_pre_power_on(struct mmc_host *host) {} +static inline void mmc_pwrseq_post_power_on(struct mmc_host *host) {} +static inline void mmc_pwrseq_power_off(struct mmc_host *host) {} +static inline void mmc_pwrseq_free(struct mmc_host *host) {} + +#endif + +#endif diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index b6bf718c3498..0c8cbe5d1550 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -195,6 +195,7 @@ struct mmc_context_info { }; struct regulator; +struct mmc_pwrseq; struct mmc_supply { struct regulator *vmmc; /* Card power supply */ @@ -206,6 +207,7 @@ struct mmc_host { struct device class_dev; int index; const struct mmc_host_ops *ops; + struct mmc_pwrseq *pwrseq; unsigned int f_min; unsigned int f_max; unsigned int f_init; -- cgit v1.2.3 From 667a0a06c99d5291433b869ed35dabdd95ba1453 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 18 Dec 2014 14:48:15 +0000 Subject: mm: provide a find_special_page vma operation The optional find_special_page VMA operation is used to lookup the pages backing a VMA. This is useful in cases where the normal mechanisms for finding the page don't work. This is only called if the PTE is special. One use case is a Xen PV guest mapping foreign pages into userspace. In a Xen PV guest, the PTEs contain MFNs so get_user_pages() (for example) must do an MFN to PFN (M2P) lookup before it can get the page. For foreign pages (those owned by another guest) the M2P lookup returns the PFN as seen by the foreign guest (which would be completely the wrong page for the local guest). This cannot be fixed up improving the M2P lookup since one MFN may be mapped onto two or more pages so getting the right page is impossible given just the MFN. Signed-off-by: David Vrabel Acked-by: Andrew Morton --- include/linux/mm.h | 8 ++++++++ mm/memory.c | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80fc92a49649..9269af7349fe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -290,6 +290,14 @@ struct vm_operations_struct { /* called by sys_remap_file_pages() to populate non-linear mapping */ int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff); + + /* + * Called by vm_normal_page() for special PTEs to find the + * page for @addr. This is useful if the default behavior + * (using pte_page()) would not find the correct page. + */ + struct page *(*find_special_page)(struct vm_area_struct *vma, + unsigned long addr); }; struct mmu_gather; diff --git a/mm/memory.c b/mm/memory.c index 54f3a9b00956..dc2e01a315e2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -754,6 +754,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (HAVE_PTE_SPECIAL) { if (likely(!pte_special(pte))) goto check_pfn; + if (vma->vm_ops && vma->vm_ops->find_special_page) + return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (!is_zero_pfn(pfn)) -- cgit v1.2.3 From d8ac3dd41aea245f65465449efc35dd3ac71e91d Mon Sep 17 00:00:00 2001 From: Jennifer Herbert Date: Mon, 5 Jan 2015 13:24:09 +0000 Subject: mm: add 'foreign' alias for the 'pinned' page flag The foreign page flag will be used by Xen guests to mark pages that have grant mappings of frames from other (foreign) guests. The foreign flag is an alias for the existing (Xen-specific) pinned flag. This is safe because pinned is only used on pages used for page tables and these cannot also be foreign. Signed-off-by: Jennifer Herbert Acked-by: Andrew Morton Signed-off-by: David Vrabel --- include/linux/page-flags.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e1f5fcd79792..5ed7bdaf22d5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -121,8 +121,12 @@ enum pageflags { PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ + /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, + /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, + /* Has a grant mapping of another (foreign) domain's page. */ + PG_foreign = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, @@ -215,6 +219,7 @@ __PAGEFLAG(Slab, slab) PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ +PAGEFLAG(Foreign, foreign); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __SETPAGEFLAG(SwapBacked, swapbacked) -- cgit v1.2.3 From 8c7dd8bce05345ca5fe249b64782e8feeb3b9259 Mon Sep 17 00:00:00 2001 From: James Ban Date: Wed, 28 Jan 2015 09:28:08 +0900 Subject: regulator: da9211: Add gpio control for enable/disable of buck This is a patch for adding gpio control about enable/disable of buck. Signed-off-by: James Ban Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/regulator/da9211.txt | 7 ++++++- drivers/regulator/da9211-regulator.c | 12 ++++++++++++ include/linux/regulator/da9211.h | 1 + 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt index 240019a82f9a..eb618907c7de 100644 --- a/Documentation/devicetree/bindings/regulator/da9211.txt +++ b/Documentation/devicetree/bindings/regulator/da9211.txt @@ -11,6 +11,7 @@ Required properties: BUCKA and BUCKB. Optional properties: +- enable-gpios: platform gpio for control of BUCKA/BUCKB. - Any optional property defined in regulator.txt Example 1) DA9211 @@ -27,6 +28,7 @@ Example 1) DA9211 regulator-max-microvolt = <1570000>; regulator-min-microamp = <2000000>; regulator-max-microamp = <5000000>; + enable-gpios = <&gpio 27 0>; }; BUCKB { regulator-name = "VBUCKB"; @@ -34,11 +36,12 @@ Example 1) DA9211 regulator-max-microvolt = <1570000>; regulator-min-microamp = <2000000>; regulator-max-microamp = <5000000>; + enable-gpios = <&gpio 17 0>; }; }; }; -Example 2) DA92113 +Example 2) DA9213 pmic: da9213@68 { compatible = "dlg,da9213"; reg = <0x68>; @@ -51,6 +54,7 @@ Example 2) DA92113 regulator-max-microvolt = <1570000>; regulator-min-microamp = <3000000>; regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 27 0>; }; BUCKB { regulator-name = "VBUCKB"; @@ -58,6 +62,7 @@ Example 2) DA92113 regulator-max-microvolt = <1570000>; regulator-min-microamp = <3000000>; regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 17 0>; }; }; }; diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index 8e6957c63a69..01343419555e 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include "da9211-regulator.h" @@ -277,6 +278,9 @@ static struct da9211_pdata *da9211_parse_regulators_dt( pdata->init_data[n] = da9211_matches[i].init_data; pdata->reg_node[n] = da9211_matches[i].of_node; + pdata->gpio_ren[n] = + of_get_named_gpio(da9211_matches[i].of_node, + "enable-gpios", 0); n++; } @@ -366,6 +370,14 @@ static int da9211_regulator_init(struct da9211 *chip) config.regmap = chip->regmap; config.of_node = chip->pdata->reg_node[i]; + if (gpio_is_valid(chip->pdata->gpio_ren[i])) { + config.ena_gpio = chip->pdata->gpio_ren[i]; + config.ena_gpio_initialized = true; + } else { + config.ena_gpio = -EINVAL; + config.ena_gpio_initialized = false; + } + chip->rdev[i] = devm_regulator_register(chip->dev, &da9211_regulators[i], &config); if (IS_ERR(chip->rdev[i])) { diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index d1d9d3849bdb..5dd65acc2a69 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -32,6 +32,7 @@ struct da9211_pdata { * 2 : 2 phase 2 buck */ int num_buck; + int gpio_ren[DA9211_MAX_REGULATORS]; struct device_node *reg_node[DA9211_MAX_REGULATORS]; struct regulator_init_data *init_data[DA9211_MAX_REGULATORS]; }; -- cgit v1.2.3 From 018d5ef2048fcab339467bcbebccf588c9bd2531 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 29 Jan 2015 08:30:29 +0900 Subject: ata: ahci_platform: fix owner module reference mismatch for scsi host The owner module reference of the ahci platform's scsi_host is initialized to libahci_platform's one, because these drivers use a scsi_host_template defined in libahci_platform. So these drivers can be unloaded even if the scsi device is being accessed. This fixes it by pushing the scsi_host_template from libahci_platform to all leaf drivers. The scsi_host_template is passed through a new argument of ahci_platform_init_host(). Signed-off-by: Akinobu Mita Signed-off-by: Tejun Heo Cc: Hans de Goede Cc: Christoph Hellwig Cc: "James E.J. Bottomley" Cc: linux-ide@vger.kernel.org Cc: linux-scsi@vger.kernel.org --- drivers/ata/ahci.h | 4 ++++ drivers/ata/ahci_da850.c | 11 +++++++++-- drivers/ata/ahci_imx.c | 11 +++++++++-- drivers/ata/ahci_mvebu.c | 11 +++++++++-- drivers/ata/ahci_platform.c | 11 +++++++++-- drivers/ata/ahci_st.c | 11 +++++++++-- drivers/ata/ahci_sunxi.c | 11 +++++++++-- drivers/ata/ahci_tegra.c | 11 +++++++++-- drivers/ata/ahci_xgene.c | 11 +++++++++-- drivers/ata/libahci_platform.c | 10 ++++------ include/linux/ahci_platform.h | 4 +++- include/linux/libata.h | 6 ++++++ 12 files changed, 89 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 275358ae0b3f..71262e08648e 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -354,6 +354,10 @@ extern int ahci_ignore_sss; extern struct device_attribute *ahci_shost_attrs[]; extern struct device_attribute *ahci_sdev_attrs[]; +/* + * This must be instantiated by the edge drivers. Read the comments + * for ATA_BASE_SHT + */ #define AHCI_SHT(drv_name) \ ATA_NCQ_SHT(drv_name), \ .can_queue = AHCI_MAX_CMDS - 1, \ diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c index ce8a7a6d6c7f..267a3d3e79f4 100644 --- a/drivers/ata/ahci_da850.c +++ b/drivers/ata/ahci_da850.c @@ -16,6 +16,8 @@ #include #include "ahci.h" +#define DRV_NAME "ahci_da850" + /* SATA PHY Control Register offset from AHCI base */ #define SATA_P0PHYCR_REG 0x178 @@ -59,6 +61,10 @@ static const struct ata_port_info ahci_da850_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_da850_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -85,7 +91,8 @@ static int ahci_da850_probe(struct platform_device *pdev) da850_sata_init(dev, pwrdn_reg, hpriv->mmio); - rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -102,7 +109,7 @@ static struct platform_driver ahci_da850_driver = { .probe = ahci_da850_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci_da850", + .name = DRV_NAME, .pm = &ahci_da850_pm_ops, }, }; diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 41632e57d46f..3f3a7db208ae 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -28,6 +28,8 @@ #include #include "ahci.h" +#define DRV_NAME "ahci-imx" + enum { /* Timer 1-ms Register */ IMX_TIMER1MS = 0x00e0, @@ -520,6 +522,10 @@ static u32 imx_ahci_parse_props(struct device *dev, return reg_value; } +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int imx_ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -616,7 +622,8 @@ static int imx_ahci_probe(struct platform_device *pdev) reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000; writel(reg_val, hpriv->mmio + IMX_TIMER1MS); - ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info); + ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info, + &ahci_platform_sht); if (ret) goto disable_sata; @@ -674,7 +681,7 @@ static struct platform_driver imx_ahci_driver = { .probe = imx_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-imx", + .name = DRV_NAME, .of_match_table = imx_ahci_of_match, .pm = &ahci_imx_pm_ops, }, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 64bb08432b69..23716dd8a7ec 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -19,6 +19,8 @@ #include #include "ahci.h" +#define DRV_NAME "ahci-mvebu" + #define AHCI_VENDOR_SPECIFIC_0_ADDR 0xa0 #define AHCI_VENDOR_SPECIFIC_0_DATA 0xa4 @@ -67,6 +69,10 @@ static const struct ata_port_info ahci_mvebu_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_mvebu_probe(struct platform_device *pdev) { struct ahci_host_priv *hpriv; @@ -88,7 +94,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev) ahci_mvebu_mbus_config(hpriv, dram); ahci_mvebu_regret_option(hpriv); - rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -114,7 +121,7 @@ static struct platform_driver ahci_mvebu_driver = { .probe = ahci_mvebu_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-mvebu", + .name = DRV_NAME, .of_match_table = ahci_mvebu_of_match, }, }; diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 18d539837045..78d6ae0b90c4 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -22,6 +22,8 @@ #include #include "ahci.h" +#define DRV_NAME "ahci" + static const struct ata_port_info ahci_port_info = { .flags = AHCI_FLAG_COMMON, .pio_mask = ATA_PIO4, @@ -29,6 +31,10 @@ static const struct ata_port_info ahci_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -46,7 +52,8 @@ static int ahci_probe(struct platform_device *pdev) if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; - rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -75,7 +82,7 @@ static struct platform_driver ahci_driver = { .probe = ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci", + .name = DRV_NAME, .of_match_table = ahci_of_match, .pm = &ahci_pm_ops, }, diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index 2f9e8317cc16..bc971af262e7 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -23,6 +23,8 @@ #include "ahci.h" +#define DRV_NAME "st_ahci" + #define ST_AHCI_OOBR 0xbc #define ST_AHCI_OOBR_WE BIT(31) #define ST_AHCI_OOBR_CWMIN_SHIFT 24 @@ -140,6 +142,10 @@ static const struct ata_port_info st_ahci_port_info = { .port_ops = &st_ahci_port_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int st_ahci_probe(struct platform_device *pdev) { struct st_ahci_drv_data *drv_data; @@ -166,7 +172,8 @@ static int st_ahci_probe(struct platform_device *pdev) if (err) return err; - err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info); + err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info, + &ahci_platform_sht); if (err) { ahci_platform_disable_resources(hpriv); return err; @@ -229,7 +236,7 @@ MODULE_DEVICE_TABLE(of, st_ahci_match); static struct platform_driver st_ahci_driver = { .driver = { - .name = "st_ahci", + .name = DRV_NAME, .pm = &st_ahci_pm_ops, .of_match_table = of_match_ptr(st_ahci_match), }, diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c index e2e0da539a2f..b26437430163 100644 --- a/drivers/ata/ahci_sunxi.c +++ b/drivers/ata/ahci_sunxi.c @@ -27,6 +27,8 @@ #include #include "ahci.h" +#define DRV_NAME "ahci-sunxi" + /* Insmod parameters */ static bool enable_pmp; module_param(enable_pmp, bool, 0); @@ -169,6 +171,10 @@ static const struct ata_port_info ahci_sunxi_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_sunxi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -200,7 +206,8 @@ static int ahci_sunxi_probe(struct platform_device *pdev) if (!enable_pmp) hpriv->flags |= AHCI_HFLAG_NO_PMP; - rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -251,7 +258,7 @@ static struct platform_driver ahci_sunxi_driver = { .probe = ahci_sunxi_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-sunxi", + .name = DRV_NAME, .of_match_table = ahci_sunxi_of_match, .pm = &ahci_sunxi_pm_ops, }, diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c index 032904402c95..3a62eb246d80 100644 --- a/drivers/ata/ahci_tegra.c +++ b/drivers/ata/ahci_tegra.c @@ -31,6 +31,8 @@ #include "ahci.h" +#define DRV_NAME "tegra-ahci" + #define SATA_CONFIGURATION_0 0x180 #define SATA_CONFIGURATION_EN_FPCI BIT(0) @@ -289,6 +291,10 @@ static const struct of_device_id tegra_ahci_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_ahci_of_match); +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int tegra_ahci_probe(struct platform_device *pdev) { struct ahci_host_priv *hpriv; @@ -354,7 +360,8 @@ static int tegra_ahci_probe(struct platform_device *pdev) if (ret) return ret; - ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info); + ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info, + &ahci_platform_sht); if (ret) goto deinit_controller; @@ -370,7 +377,7 @@ static struct platform_driver tegra_ahci_driver = { .probe = tegra_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "tegra-ahci", + .name = DRV_NAME, .of_match_table = tegra_ahci_of_match, }, /* LP0 suspend support not implemented */ diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 7f6887535c1e..e3b8750e8e9d 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -30,6 +30,8 @@ #include #include "ahci.h" +#define DRV_NAME "xgene-ahci" + /* Max # of disk per a controller */ #define MAX_AHCI_CHN_PERCTR 2 @@ -621,6 +623,10 @@ static int xgene_ahci_mux_select(struct xgene_ahci_context *ctx) return val & CFG_SATA_ENET_SELECT_MASK ? -1 : 0; } +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int xgene_ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -698,7 +704,8 @@ static int xgene_ahci_probe(struct platform_device *pdev) skip_clk_phy: hpriv->flags = AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_NCQ; - rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -720,7 +727,7 @@ static struct platform_driver xgene_ahci_driver = { .probe = xgene_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "xgene-ahci", + .name = DRV_NAME, .of_match_table = xgene_ahci_of_match, }, }; diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 504d534ccbfe..077c7a261354 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -35,10 +35,6 @@ struct ata_port_operations ahci_platform_ops = { }; EXPORT_SYMBOL_GPL(ahci_platform_ops); -static struct scsi_host_template ahci_platform_sht = { - AHCI_SHT("ahci_platform"), -}; - /** * ahci_platform_enable_phys - Enable PHYs * @hpriv: host private area to store config values @@ -494,6 +490,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources); * @pdev: platform device pointer for the host * @hpriv: ahci-host private data for the host * @pi_template: template for the ata_port_info to use + * @sht: scsi_host_template to use when registering * * This function does all the usual steps needed to bring up an * ahci-platform host, note any necessary resources (ie clks, phys, etc.) @@ -504,7 +501,8 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources); */ int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template) + const struct ata_port_info *pi_template, + struct scsi_host_template *sht) { struct device *dev = &pdev->dev; struct ata_port_info pi = *pi_template; @@ -588,7 +586,7 @@ int ahci_platform_init_host(struct platform_device *pdev, ahci_init_controller(host); ahci_print_info(host, "platform"); - return ahci_host_activate(host, irq, &ahci_platform_sht); + return ahci_host_activate(host, irq, sht); } EXPORT_SYMBOL_GPL(ahci_platform_init_host); diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index f65b33809170..a270f25ee7c7 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -21,6 +21,7 @@ struct device; struct ata_port_info; struct ahci_host_priv; struct platform_device; +struct scsi_host_template; int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); @@ -32,7 +33,8 @@ struct ahci_host_priv *ahci_platform_get_resources( struct platform_device *pdev); int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template); + const struct ata_port_info *pi_template, + struct scsi_host_template *sht); int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..11beb4196c32 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1338,6 +1338,12 @@ extern const struct ata_port_operations ata_base_port_ops; extern const struct ata_port_operations sata_port_ops; extern struct device_attribute *ata_common_sdev_attrs[]; +/* + * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated + * by the edge drivers. Because the 'module' field of sht must be the + * edge driver's module reference, otherwise the driver can be unloaded + * even if the scsi_device is being accessed. + */ #define ATA_BASE_SHT(drv_name) \ .module = THIS_MODULE, \ .name = drv_name, \ -- cgit v1.2.3 From 17263905399471016cda6c1975044d14291c5ba5 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 29 Jan 2015 08:30:30 +0900 Subject: ata: pata_platform: fix owner module reference mismatch for scsi host The owner module reference of the pata_of_platform's scsi_host is initialized to pata_platform's one, because pata_of_platform driver use a scsi_host_template defined in pata_platform. So this drivers can be unloaded even if the scsi device is being accessed. This fixes it by propagating the scsi_host_template to pata_of_platform driver. The scsi_host_template is passed through a new argument of __pata_platform_probe(). Signed-off-by: Akinobu Mita Signed-off-by: Tejun Heo Cc: Hans de Goede Cc: Christoph Hellwig Cc: "James E.J. Bottomley" Cc: linux-ide@vger.kernel.org Cc: linux-scsi@vger.kernel.org --- drivers/ata/pata_of_platform.c | 10 ++++++++-- drivers/ata/pata_platform.c | 8 +++++--- include/linux/ata_platform.h | 5 ++++- 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c index dcc408abe171..b6b7af894d9d 100644 --- a/drivers/ata/pata_of_platform.c +++ b/drivers/ata/pata_of_platform.c @@ -16,6 +16,12 @@ #include #include +#define DRV_NAME "pata_of_platform" + +static struct scsi_host_template pata_platform_sht = { + ATA_PIO_SHT(DRV_NAME), +}; + static int pata_of_platform_probe(struct platform_device *ofdev) { int ret; @@ -63,7 +69,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev) pio_mask |= (1 << pio_mode) - 1; return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq_res, - reg_shift, pio_mask); + reg_shift, pio_mask, &pata_platform_sht); } static struct of_device_id pata_of_platform_match[] = { @@ -74,7 +80,7 @@ MODULE_DEVICE_TABLE(of, pata_of_platform_match); static struct platform_driver pata_of_platform_driver = { .driver = { - .name = "pata_of_platform", + .name = DRV_NAME, .of_match_table = pata_of_platform_match, }, .probe = pata_of_platform_probe, diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c index 1eedfe46d7c8..c503ded87bb8 100644 --- a/drivers/ata/pata_platform.c +++ b/drivers/ata/pata_platform.c @@ -78,6 +78,7 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr, * @irq_res: Resource representing IRQ and its flags * @ioport_shift: I/O port shift * @__pio_mask: PIO mask + * @sht: scsi_host_template to use when registering * * Register a platform bus IDE interface. Such interfaces are PIO and we * assume do not support IRQ sharing. @@ -99,7 +100,8 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr, */ int __pata_platform_probe(struct device *dev, struct resource *io_res, struct resource *ctl_res, struct resource *irq_res, - unsigned int ioport_shift, int __pio_mask) + unsigned int ioport_shift, int __pio_mask, + struct scsi_host_template *sht) { struct ata_host *host; struct ata_port *ap; @@ -170,7 +172,7 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res, /* activate */ return ata_host_activate(host, irq, irq ? ata_sff_interrupt : NULL, - irq_flags, &pata_platform_sht); + irq_flags, sht); } EXPORT_SYMBOL_GPL(__pata_platform_probe); @@ -216,7 +218,7 @@ static int pata_platform_probe(struct platform_device *pdev) return __pata_platform_probe(&pdev->dev, io_res, ctl_res, irq_res, pp_info ? pp_info->ioport_shift : 0, - pio_mask); + pio_mask, &pata_platform_sht); } static struct platform_driver pata_platform_driver = { diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h index 5c618a084225..619d9e78e644 100644 --- a/include/linux/ata_platform.h +++ b/include/linux/ata_platform.h @@ -10,12 +10,15 @@ struct pata_platform_info { unsigned int ioport_shift; }; +struct scsi_host_template; + extern int __pata_platform_probe(struct device *dev, struct resource *io_res, struct resource *ctl_res, struct resource *irq_res, unsigned int ioport_shift, - int __pio_mask); + int __pio_mask, + struct scsi_host_template *sht); /* * Marvell SATA private data -- cgit v1.2.3 From 61f552141c9c0e88b3fdc7046265781ffd8fa68a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 18 Jan 2015 16:45:42 +0100 Subject: ftrace: let notrace function attribute disable hotpatching if necessary gcc supports an s390 specific function attribute called "hotpatch". It can be used to specify the number of halfwords that shall be added before and after a function and which shall be filled with nops for runtime patching. s390 will use the hotpatch attribute for function tracing, therefore make sure that the notrace function attribute either disables the mcount call or in case of hotpatch nop generation. Acked-by: Steven Rostedt Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- include/linux/compiler.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index d5ad7b1118fc..1ef679f4b88e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -54,7 +54,11 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif +#ifdef CC_USING_HOTPATCH +#define notrace __attribute__((hotpatch(0,0))) +#else #define notrace __attribute__((no_instrument_function)) +#endif /* Intel compiler defines __GNUC__. So we will overwrite implementations * coming from above header files here -- cgit v1.2.3 From 0501be6429e4eb02f417ad83eacd84b8c57b0283 Mon Sep 17 00:00:00 2001 From: Alexey Skidanov Date: Thu, 29 Jan 2015 10:49:43 +0200 Subject: mmc: Resolve BKOPS compatability issue This patch is coming to fix compatibility issue of BKOPS_EN field of EXT_CSD. In eMMC-5.1, BKOPS_EN was changed, and now it has two operational bits: Bit 0 - MANUAL_EN Bit 1 - AUTO_EN In previous eMMC revisions, only Bit 0 was supported. Signed-off-by: Alexey Skidanov Signed-off-by: Ulf Hansson --- drivers/mmc/core/core.c | 2 +- drivers/mmc/core/mmc.c | 8 +++++--- include/linux/mmc/card.h | 2 +- include/linux/mmc/mmc.h | 5 +++++ 4 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 1be7055548cb..0dc64e6e00d4 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -275,7 +275,7 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception) BUG_ON(!card); - if (!card->ext_csd.bkops_en || mmc_card_doing_bkops(card)) + if (!card->ext_csd.man_bkops_en || mmc_card_doing_bkops(card)) return; err = mmc_read_bkops_status(card); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 1fc48a280659..1d41e8541f38 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -483,11 +483,13 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) /* check whether the eMMC card supports BKOPS */ if (ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) { card->ext_csd.bkops = 1; - card->ext_csd.bkops_en = ext_csd[EXT_CSD_BKOPS_EN]; + card->ext_csd.man_bkops_en = + (ext_csd[EXT_CSD_BKOPS_EN] & + EXT_CSD_MANUAL_BKOPS_MASK); card->ext_csd.raw_bkops_status = ext_csd[EXT_CSD_BKOPS_STATUS]; - if (!card->ext_csd.bkops_en) - pr_info("%s: BKOPS_EN bit is not set\n", + if (!card->ext_csd.man_bkops_en) + pr_info("%s: MAN_BKOPS_EN bit is not set\n", mmc_hostname(card->host)); } diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 4d69c00497bd..a6cf4c063e4e 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -83,7 +83,7 @@ struct mmc_ext_csd { bool hpi; /* HPI support bit */ unsigned int hpi_cmd; /* cmd used as HPI */ bool bkops; /* background support bit */ - bool bkops_en; /* background enable bit */ + bool man_bkops_en; /* manual bkops enable bit */ unsigned int data_sector_size; /* 512 bytes or 4KB */ unsigned int data_tag_unit_size; /* DATA TAG UNIT size */ unsigned int boot_ro_lock; /* ro lock support */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index fb97b5cc91cd..124f562118b8 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -427,6 +427,11 @@ struct _mmc_csd { */ #define EXT_CSD_BKOPS_LEVEL_2 0x2 +/* + * BKOPS modes + */ +#define EXT_CSD_MANUAL_BKOPS_MASK 0x01 + /* * MMC_SWITCH access modes */ -- cgit v1.2.3 From f262f28c147051e7aa6daaf4fb5996833ffadff4 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 26 Jan 2015 13:16:27 +0900 Subject: PM / devfreq: event: Add devfreq_event class This patch adds a new class in devfreq, devfreq_event, which provides raw data (e.g., memory bus utilization, GPU utilization) for devfreq governors. - devfreq_event device : Provides raw data for a governor of a devfreq device - devfreq device : Monitors device state and changes frequency/voltage of the device using the raw data from its devfreq_event device. A devfreq device dertermines performance states (normally the frequency and the voltage vlues) based on the results its designtated devfreq governor: e.g., ondemand, performance, powersave. In order to give such results required by a devfreq device, the devfreq governor requires data that indicates the performance requirement given to the devfreq device. The conventional (previous) implementatino of devfreq subsystem requires a devfreq device driver to implement its own mechanism to acquire performance requirement for its governor. However, there had been issues with such requirements: 1. Although performance requirement of such devices is usually acquired from common devices (PMU/PPMU), we do not have any abstract structure to represent them properly. 2. Such performance requirement devices (PMU/PPMU) are actual hardware pieces that may be represented by Device Tree directly while devfreq device itself is a virtual entity that are not considered to be represented by Device Tree according to Device Tree folks. In order to address such issues, a devferq_event device (represented by this patch) provides a template for device drivers representing performance monitoring unit, which gives the basic or raw data for preformance requirement, which in turn, is required by devfreq governors. The following description explains the feature of two kind of devfreq class: - devfreq class (existing) : devfreq consumer device use raw data from devfreq_event device for determining proper current system state and change voltage/frequency dynamically using various governors. - devfreq_event class (new) : Provide measured raw data to devfreq device for governor Cc: MyungJoo Ham Cc: Kyungmin Park Signed-off-by: Chanwoo Choi [Commit message rewritten & conflict resolved by MyungJoo] Signed-off-by: MyungJoo Ham --- drivers/devfreq/Kconfig | 2 + drivers/devfreq/Makefile | 3 + drivers/devfreq/devfreq-event.c | 494 ++++++++++++++++++++++++++++++++++++ drivers/devfreq/event/Kconfig | 25 ++ drivers/devfreq/event/Makefile | 2 + drivers/devfreq/event/exynos-ppmu.c | 374 +++++++++++++++++++++++++++ drivers/devfreq/event/exynos-ppmu.h | 93 +++++++ include/linux/devfreq-event.h | 196 ++++++++++++++ 8 files changed, 1189 insertions(+) create mode 100644 drivers/devfreq/devfreq-event.c create mode 100644 drivers/devfreq/event/Kconfig create mode 100644 drivers/devfreq/event/Makefile create mode 100644 drivers/devfreq/event/exynos-ppmu.c create mode 100644 drivers/devfreq/event/exynos-ppmu.h create mode 100644 include/linux/devfreq-event.h (limited to 'include/linux') diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index 4aab799712bb..51dccb3620ea 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -97,4 +97,6 @@ config ARM_TEGRA_DEVFREQ It reads ACTMON counters of memory controllers and adjusts the operating frequencies and voltages with OPP support. +source "drivers/devfreq/event/Kconfig" + endif # PM_DEVFREQ diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile index 0ea991f3a483..9256c35bcce9 100644 --- a/drivers/devfreq/Makefile +++ b/drivers/devfreq/Makefile @@ -8,3 +8,6 @@ obj-$(CONFIG_DEVFREQ_GOV_USERSPACE) += governor_userspace.o obj-$(CONFIG_ARM_EXYNOS4_BUS_DEVFREQ) += exynos/ obj-$(CONFIG_ARM_EXYNOS5_BUS_DEVFREQ) += exynos/ obj-$(CONFIG_ARM_TEGRA_DEVFREQ) += tegra-devfreq.o + +# DEVFREQ Event Drivers +obj-$(CONFIG_PM_DEVFREQ_EVENT) += event/ diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c new file mode 100644 index 000000000000..f304a0289eda --- /dev/null +++ b/drivers/devfreq/devfreq-event.c @@ -0,0 +1,494 @@ +/* + * devfreq-event: a framework to provide raw data and events of devfreq devices + * + * Copyright (C) 2015 Samsung Electronics + * Author: Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This driver is based on drivers/devfreq/devfreq.c. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static struct class *devfreq_event_class; + +/* The list of all devfreq event list */ +static LIST_HEAD(devfreq_event_list); +static DEFINE_MUTEX(devfreq_event_list_lock); + +#define to_devfreq_event(DEV) container_of(DEV, struct devfreq_event_dev, dev) + +/** + * devfreq_event_enable_edev() - Enable the devfreq-event dev and increase + * the enable_count of devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function increase the enable_count and enable the + * devfreq-event device. The devfreq-event device should be enabled before + * using it by devfreq device. + */ +int devfreq_event_enable_edev(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + mutex_lock(&edev->lock); + if (edev->desc->ops && edev->desc->ops->enable + && edev->enable_count == 0) { + ret = edev->desc->ops->enable(edev); + if (ret < 0) + goto err; + } + edev->enable_count++; +err: + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_enable_edev); + +/** + * devfreq_event_disable_edev() - Disable the devfreq-event dev and decrease + * the enable_count of the devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function decrease the enable_count and disable the + * devfreq-event device. After the devfreq-event device is disabled, + * devfreq device can't use the devfreq-event device for get/set/reset + * operations. + */ +int devfreq_event_disable_edev(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + mutex_lock(&edev->lock); + if (edev->enable_count <= 0) { + dev_warn(&edev->dev, "unbalanced enable_count\n"); + ret = -EIO; + goto err; + } + + if (edev->desc->ops && edev->desc->ops->disable + && edev->enable_count == 1) { + ret = edev->desc->ops->disable(edev); + if (ret < 0) + goto err; + } + edev->enable_count--; +err: + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_disable_edev); + +/** + * devfreq_event_is_enabled() - Check whether devfreq-event dev is enabled or + * not. + * @edev : the devfreq-event device + * + * Note that this function check whether devfreq-event dev is enabled or not. + * If return true, the devfreq-event dev is enabeld. If return false, the + * devfreq-event dev is disabled. + */ +bool devfreq_event_is_enabled(struct devfreq_event_dev *edev) +{ + bool enabled = false; + + if (!edev || !edev->desc) + return enabled; + + mutex_lock(&edev->lock); + + if (edev->enable_count > 0) + enabled = true; + + mutex_unlock(&edev->lock); + + return enabled; +} +EXPORT_SYMBOL_GPL(devfreq_event_is_enabled); + +/** + * devfreq_event_set_event() - Set event to devfreq-event dev to start. + * @edev : the devfreq-event device + * + * Note that this function set the event to the devfreq-event device to start + * for getting the event data which could be various event type. + */ +int devfreq_event_set_event(struct devfreq_event_dev *edev) +{ + int ret; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!edev->desc->ops || !edev->desc->ops->set_event) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EPERM; + + mutex_lock(&edev->lock); + ret = edev->desc->ops->set_event(edev); + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_set_event); + +/** + * devfreq_event_get_event() - Get {load|total}_count from devfreq-event dev. + * @edev : the devfreq-event device + * @edata : the calculated data of devfreq-event device + * + * Note that this function get the calculated event data from devfreq-event dev + * after stoping the progress of whole sequence of devfreq-event dev. + */ +int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + int ret; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!edev->desc->ops || !edev->desc->ops->get_event) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EINVAL; + + edata->total_count = edata->load_count = 0; + + mutex_lock(&edev->lock); + ret = edev->desc->ops->get_event(edev, edata); + if (ret < 0) + edata->total_count = edata->load_count = 0; + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_event); + +/** + * devfreq_event_reset_event() - Reset all opeations of devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function stop all operations of devfreq-event dev and reset + * the current event data to make the devfreq-event device into initial state. + */ +int devfreq_event_reset_event(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EPERM; + + mutex_lock(&edev->lock); + if (edev->desc->ops && edev->desc->ops->reset) + ret = edev->desc->ops->reset(edev); + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_reset_event); + +/** + * devfreq_event_get_edev_by_phandle() - Get the devfreq-event dev from + * devicetree. + * @dev : the pointer to the given device + * @index : the index into list of devfreq-event device + * + * Note that this function return the pointer of devfreq-event device. + */ +struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev, + int index) +{ + struct device_node *node; + struct devfreq_event_dev *edev; + + if (!dev->of_node) { + dev_err(dev, "device does not have a device node entry\n"); + return ERR_PTR(-EINVAL); + } + + node = of_parse_phandle(dev->of_node, "devfreq-events", index); + if (!node) { + dev_err(dev, "failed to get phandle in %s node\n", + dev->of_node->full_name); + return ERR_PTR(-ENODEV); + } + + mutex_lock(&devfreq_event_list_lock); + list_for_each_entry(edev, &devfreq_event_list, node) { + if (!strcmp(edev->desc->name, node->name)) + goto out; + } + edev = NULL; +out: + mutex_unlock(&devfreq_event_list_lock); + + if (!edev) { + dev_err(dev, "unable to get devfreq-event device : %s\n", + node->name); + of_node_put(node); + return ERR_PTR(-ENODEV); + } + + of_node_put(node); + + return edev; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_edev_by_phandle); + +/** + * devfreq_event_get_edev_count() - Get the count of devfreq-event dev + * @dev : the pointer to the given device + * + * Note that this function return the count of devfreq-event devices. + */ +int devfreq_event_get_edev_count(struct device *dev) +{ + int count; + + if (!dev->of_node) { + dev_err(dev, "device does not have a device node entry\n"); + return -EINVAL; + } + + count = of_property_count_elems_of_size(dev->of_node, "devfreq-events", + sizeof(u32)); + if (count < 0 ) { + dev_err(dev, + "failed to get the count of devfreq-event in %s node\n", + dev->of_node->full_name); + return count; + } + + return count; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_edev_count); + +static void devfreq_event_release_edev(struct device *dev) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + kfree(edev); +} + +/** + * devfreq_event_add_edev() - Add new devfreq-event device. + * @dev : the device owning the devfreq-event device being created + * @desc : the devfreq-event device's decriptor which include essential + * data for devfreq-event device. + * + * Note that this function add new devfreq-event device to devfreq-event class + * list and register the device of the devfreq-event device. + */ +struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + struct devfreq_event_dev *edev; + static atomic_t event_no = ATOMIC_INIT(0); + int ret; + + if (!dev || !desc) + return ERR_PTR(-EINVAL); + + if (!desc->name || !desc->ops) + return ERR_PTR(-EINVAL); + + if (!desc->ops->set_event || !desc->ops->get_event) + return ERR_PTR(-EINVAL); + + edev = kzalloc(sizeof(struct devfreq_event_dev), GFP_KERNEL); + if (!edev) + return ERR_PTR(-ENOMEM); + + mutex_init(&edev->lock); + edev->desc = desc; + edev->enable_count = 0; + edev->dev.parent = dev; + edev->dev.class = devfreq_event_class; + edev->dev.release = devfreq_event_release_edev; + + dev_set_name(&edev->dev, "event.%d", atomic_inc_return(&event_no) - 1); + ret = device_register(&edev->dev); + if (ret < 0) { + put_device(&edev->dev); + return ERR_PTR(ret); + } + dev_set_drvdata(&edev->dev, edev); + + INIT_LIST_HEAD(&edev->node); + + mutex_lock(&devfreq_event_list_lock); + list_add(&edev->node, &devfreq_event_list); + mutex_unlock(&devfreq_event_list_lock); + + return edev; +} +EXPORT_SYMBOL_GPL(devfreq_event_add_edev); + +/** + * devfreq_event_remove_edev() - Remove the devfreq-event device registered. + * @dev : the devfreq-event device + * + * Note that this function remove the registered devfreq-event device. + */ +int devfreq_event_remove_edev(struct devfreq_event_dev *edev) +{ + if (!edev) + return -EINVAL; + + WARN_ON(edev->enable_count); + + mutex_lock(&devfreq_event_list_lock); + list_del(&edev->node); + mutex_unlock(&devfreq_event_list_lock); + + device_unregister(&edev->dev); + + return 0; +} +EXPORT_SYMBOL_GPL(devfreq_event_remove_edev); + +static int devm_devfreq_event_match(struct device *dev, void *res, void *data) +{ + struct devfreq_event_dev **r = res; + + if (WARN_ON(!r || !*r)) + return 0; + + return *r == data; +} + +static void devm_devfreq_event_release(struct device *dev, void *res) +{ + devfreq_event_remove_edev(*(struct devfreq_event_dev **)res); +} + +/** + * devm_devfreq_event_add_edev() - Resource-managed devfreq_event_add_edev() + * @dev : the device owning the devfreq-event device being created + * @desc : the devfreq-event device's decriptor which include essential + * data for devfreq-event device. + * + * Note that this function manages automatically the memory of devfreq-event + * device using device resource management and simplify the free operation + * for memory of devfreq-event device. + */ +struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + struct devfreq_event_dev **ptr, *edev; + + ptr = devres_alloc(devm_devfreq_event_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + edev = devfreq_event_add_edev(dev, desc); + if (IS_ERR(edev)) { + devres_free(ptr); + return ERR_PTR(-ENOMEM); + } + + *ptr = edev; + devres_add(dev, ptr); + + return edev; +} +EXPORT_SYMBOL_GPL(devm_devfreq_event_add_edev); + +/** + * devm_devfreq_event_remove_edev()- Resource-managed devfreq_event_remove_edev() + * @dev : the device owning the devfreq-event device being created + * @edev : the devfreq-event device + * + * Note that this function manages automatically the memory of devfreq-event + * device using device resource management. + */ +void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev) +{ + WARN_ON(devres_release(dev, devm_devfreq_event_release, + devm_devfreq_event_match, edev)); +} +EXPORT_SYMBOL_GPL(devm_devfreq_event_remove_edev); + +/* + * Device attributes for devfreq-event class. + */ +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + if (!edev || !edev->desc) + return -EINVAL; + + return sprintf(buf, "%s\n", edev->desc->name); +} +static DEVICE_ATTR_RO(name); + +static ssize_t enable_count_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + if (!edev || !edev->desc) + return -EINVAL; + + return sprintf(buf, "%d\n", edev->enable_count); +} +static DEVICE_ATTR_RO(enable_count); + +static struct attribute *devfreq_event_attrs[] = { + &dev_attr_name.attr, + &dev_attr_enable_count.attr, + NULL, +}; +ATTRIBUTE_GROUPS(devfreq_event); + +static int __init devfreq_event_init(void) +{ + devfreq_event_class = class_create(THIS_MODULE, "devfreq-event"); + if (IS_ERR(devfreq_event_class)) { + pr_err("%s: couldn't create class\n", __FILE__); + return PTR_ERR(devfreq_event_class); + } + + devfreq_event_class->dev_groups = devfreq_event_groups; + + return 0; +} +subsys_initcall(devfreq_event_init); + +static void __exit devfreq_event_exit(void) +{ + class_destroy(devfreq_event_class); +} +module_exit(devfreq_event_exit); + +MODULE_AUTHOR("Chanwoo Choi "); +MODULE_DESCRIPTION("DEVFREQ-Event class support"); +MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig new file mode 100644 index 000000000000..a11720affc31 --- /dev/null +++ b/drivers/devfreq/event/Kconfig @@ -0,0 +1,25 @@ +menuconfig PM_DEVFREQ_EVENT + bool "DEVFREQ-Event device Support" + help + The devfreq-event device provide the raw data and events which + indicate the current state of devfreq-event device. The provided + data from devfreq-event device is used to monitor the state of + device and determine the suitable size of resource to reduce the + wasted resource. + + The devfreq-event device can support the various type of events + (e.g., raw data, utilization, latency, bandwidth). The events + may be used by devfreq governor and other subsystem. + +if PM_DEVFREQ_EVENT + +config DEVFREQ_EVENT_EXYNOS_PPMU + bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver" + depends on ARCH_EXYNOS + select PM_OPP + help + This add the devfreq-event driver for Exynos SoC. It provides PPMU + (Platform Performance Monitoring Unit) counters to estimate the + utilization of each module. + +endif # PM_DEVFREQ_EVENT diff --git a/drivers/devfreq/event/Makefile b/drivers/devfreq/event/Makefile new file mode 100644 index 000000000000..be146ead79cf --- /dev/null +++ b/drivers/devfreq/event/Makefile @@ -0,0 +1,2 @@ +# Exynos DEVFREQ Event Drivers +obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_PPMU) += exynos-ppmu.o diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c new file mode 100644 index 000000000000..135be0aada9d --- /dev/null +++ b/drivers/devfreq/event/exynos-ppmu.c @@ -0,0 +1,374 @@ +/* + * exynos_ppmu.c - EXYNOS PPMU (Platform Performance Monitoring Unit) support + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author : Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This driver is based on drivers/devfreq/exynos/exynos_ppmu.c + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "exynos-ppmu.h" + +struct exynos_ppmu_data { + void __iomem *base; + struct clk *clk; +}; + +struct exynos_ppmu { + struct devfreq_event_dev **edev; + struct devfreq_event_desc *desc; + unsigned int num_events; + + struct device *dev; + struct mutex lock; + + struct exynos_ppmu_data ppmu; +}; + +#define PPMU_EVENT(name) \ + { "ppmu-event0-"#name, PPMU_PMNCNT0 }, \ + { "ppmu-event1-"#name, PPMU_PMNCNT1 }, \ + { "ppmu-event2-"#name, PPMU_PMNCNT2 }, \ + { "ppmu-event3-"#name, PPMU_PMNCNT3 } + +struct __exynos_ppmu_events { + char *name; + int id; +} ppmu_events[] = { + /* For Exynos3250, Exynos4 and Exynos5260 */ + PPMU_EVENT(g3d), + PPMU_EVENT(fsys), + + /* For Exynos4 SoCs and Exynos3250 */ + PPMU_EVENT(dmc0), + PPMU_EVENT(dmc1), + PPMU_EVENT(cpu), + PPMU_EVENT(rightbus), + PPMU_EVENT(leftbus), + PPMU_EVENT(lcd0), + PPMU_EVENT(camif), + + /* Only for Exynos3250 and Exynos5260 */ + PPMU_EVENT(mfc), + + /* Only for Exynos4 SoCs */ + PPMU_EVENT(mfc-left), + PPMU_EVENT(mfc-right), + + /* Only for Exynos5260 SoCs */ + PPMU_EVENT(drex0-s0), + PPMU_EVENT(drex0-s1), + PPMU_EVENT(drex1-s0), + PPMU_EVENT(drex1-s1), + PPMU_EVENT(eagle), + PPMU_EVENT(kfc), + PPMU_EVENT(isp), + PPMU_EVENT(fimc), + PPMU_EVENT(gscl), + PPMU_EVENT(mscl), + PPMU_EVENT(fimd0x), + PPMU_EVENT(fimd1x), + { /* sentinel */ }, +}; + +static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) + if (!strcmp(edev->desc->name, ppmu_events[i].name)) + return ppmu_events[i].id; + + return -EINVAL; +} + +static int exynos_ppmu_disable(struct devfreq_event_dev *edev) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + u32 pmnc; + + /* Disable all counters */ + __raw_writel(PPMU_CCNT_MASK | + PPMU_PMCNT0_MASK | + PPMU_PMCNT1_MASK | + PPMU_PMCNT2_MASK | + PPMU_PMCNT3_MASK, + info->ppmu.base + PPMU_CNTENC); + + /* Disable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~PPMU_PMNC_ENABLE_MASK; + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + return 0; +} + +static int exynos_ppmu_set_event(struct devfreq_event_dev *edev) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + int id = exynos_ppmu_find_ppmu_id(edev); + u32 pmnc, cntens; + + if (id < 0) + return id; + + /* Enable specific counter */ + cntens = __raw_readl(info->ppmu.base + PPMU_CNTENS); + cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id)); + __raw_writel(cntens, info->ppmu.base + PPMU_CNTENS); + + /* Set the event of Read/Write data count */ + __raw_writel(PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT, + info->ppmu.base + PPMU_BEVTxSEL(id)); + + /* Reset cycle counter/performance counter and enable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~(PPMU_PMNC_ENABLE_MASK + | PPMU_PMNC_COUNTER_RESET_MASK + | PPMU_PMNC_CC_RESET_MASK); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT); + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + return 0; +} + +static int exynos_ppmu_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + int id = exynos_ppmu_find_ppmu_id(edev); + u32 pmnc, cntenc; + + if (id < 0) + return -EINVAL; + + /* Disable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~PPMU_PMNC_ENABLE_MASK; + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + /* Read cycle count */ + edata->total_count = __raw_readl(info->ppmu.base + PPMU_CCNT); + + /* Read performance count */ + switch (id) { + case PPMU_PMNCNT0: + case PPMU_PMNCNT1: + case PPMU_PMNCNT2: + edata->load_count + = __raw_readl(info->ppmu.base + PPMU_PMNCT(id)); + break; + case PPMU_PMNCNT3: + edata->load_count = + ((__raw_readl(info->ppmu.base + PPMU_PMCNT3_HIGH) << 8) + | __raw_readl(info->ppmu.base + PPMU_PMCNT3_LOW)); + break; + default: + return -EINVAL; + } + + /* Disable specific counter */ + cntenc = __raw_readl(info->ppmu.base + PPMU_CNTENC); + cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id)); + __raw_writel(cntenc, info->ppmu.base + PPMU_CNTENC); + + dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name, + edata->load_count, edata->total_count); + + return 0; +} + +static struct devfreq_event_ops exynos_ppmu_ops = { + .disable = exynos_ppmu_disable, + .set_event = exynos_ppmu_set_event, + .get_event = exynos_ppmu_get_event, +}; + +static int of_get_devfreq_events(struct device_node *np, + struct exynos_ppmu *info) +{ + struct devfreq_event_desc *desc; + struct device *dev = info->dev; + struct device_node *events_np, *node; + int i, j, count; + + events_np = of_get_child_by_name(np, "events"); + if (!events_np) { + dev_err(dev, + "failed to get child node of devfreq-event devices\n"); + return -EINVAL; + } + + count = of_get_child_count(events_np); + desc = devm_kzalloc(dev, sizeof(*desc) * count, GFP_KERNEL); + if (!desc) + return -ENOMEM; + info->num_events = count; + + j = 0; + for_each_child_of_node(events_np, node) { + for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) { + if (!ppmu_events[i].name) + continue; + + if (!of_node_cmp(node->name, ppmu_events[i].name)) + break; + } + + if (i == ARRAY_SIZE(ppmu_events)) { + dev_warn(dev, + "don't know how to configure events : %s\n", + node->name); + continue; + } + + desc[j].ops = &exynos_ppmu_ops; + desc[j].driver_data = info; + + of_property_read_string(node, "event-name", &desc[j].name); + + j++; + + of_node_put(node); + } + info->desc = desc; + + of_node_put(events_np); + + return 0; +} + +static int exynos_ppmu_parse_dt(struct exynos_ppmu *info) +{ + struct device *dev = info->dev; + struct device_node *np = dev->of_node; + int ret = 0; + + if (!np) { + dev_err(dev, "failed to find devicetree node\n"); + return -EINVAL; + } + + /* Maps the memory mapped IO to control PPMU register */ + info->ppmu.base = of_iomap(np, 0); + if (IS_ERR_OR_NULL(info->ppmu.base)) { + dev_err(dev, "failed to map memory region\n"); + return -ENOMEM; + } + + info->ppmu.clk = devm_clk_get(dev, "ppmu"); + if (IS_ERR(info->ppmu.clk)) { + info->ppmu.clk = NULL; + dev_warn(dev, "cannot get PPMU clock\n"); + } + + ret = of_get_devfreq_events(np, info); + if (ret < 0) { + dev_err(dev, "failed to parse exynos ppmu dt node\n"); + goto err; + } + + return 0; + +err: + iounmap(info->ppmu.base); + + return ret; +} + +static int exynos_ppmu_probe(struct platform_device *pdev) +{ + struct exynos_ppmu *info; + struct devfreq_event_dev **edev; + struct devfreq_event_desc *desc; + int i, ret = 0, size; + + info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + mutex_init(&info->lock); + info->dev = &pdev->dev; + + /* Parse dt data to get resource */ + ret = exynos_ppmu_parse_dt(info); + if (ret < 0) { + dev_err(&pdev->dev, + "failed to parse devicetree for resource\n"); + return ret; + } + desc = info->desc; + + size = sizeof(struct devfreq_event_dev *) * info->num_events; + info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!info->edev) { + dev_err(&pdev->dev, + "failed to allocate memory devfreq-event devices\n"); + return -ENOMEM; + } + edev = info->edev; + platform_set_drvdata(pdev, info); + + for (i = 0; i < info->num_events; i++) { + edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]); + if (IS_ERR(edev)) { + ret = PTR_ERR(edev); + dev_err(&pdev->dev, + "failed to add devfreq-event device\n"); + goto err; + } + } + + clk_prepare_enable(info->ppmu.clk); + + return 0; +err: + iounmap(info->ppmu.base); + + return ret; +} + +static int exynos_ppmu_remove(struct platform_device *pdev) +{ + struct exynos_ppmu *info = platform_get_drvdata(pdev); + + clk_disable_unprepare(info->ppmu.clk); + iounmap(info->ppmu.base); + + return 0; +} + +static struct of_device_id exynos_ppmu_id_match[] = { + { .compatible = "samsung,exynos-ppmu", }, + { /* sentinel */ }, +}; + +static struct platform_driver exynos_ppmu_driver = { + .probe = exynos_ppmu_probe, + .remove = exynos_ppmu_remove, + .driver = { + .name = "exynos-ppmu", + .of_match_table = exynos_ppmu_id_match, + }, +}; +module_platform_driver(exynos_ppmu_driver); + +MODULE_DESCRIPTION("Exynos PPMU(Platform Performance Monitoring Unit) driver"); +MODULE_AUTHOR("Chanwoo Choi "); +MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/event/exynos-ppmu.h b/drivers/devfreq/event/exynos-ppmu.h new file mode 100644 index 000000000000..4e831d48c138 --- /dev/null +++ b/drivers/devfreq/event/exynos-ppmu.h @@ -0,0 +1,93 @@ +/* + * exynos_ppmu.h - EXYNOS PPMU header file + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author : Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __EXYNOS_PPMU_H__ +#define __EXYNOS_PPMU_H__ + +enum ppmu_state { + PPMU_DISABLE = 0, + PPMU_ENABLE, +}; + +enum ppmu_counter { + PPMU_PMNCNT0 = 0, + PPMU_PMNCNT1, + PPMU_PMNCNT2, + PPMU_PMNCNT3, + + PPMU_PMNCNT_MAX, +}; + +enum ppmu_event_type { + PPMU_RO_BUSY_CYCLE_CNT = 0x0, + PPMU_WO_BUSY_CYCLE_CNT = 0x1, + PPMU_RW_BUSY_CYCLE_CNT = 0x2, + PPMU_RO_REQUEST_CNT = 0x3, + PPMU_WO_REQUEST_CNT = 0x4, + PPMU_RO_DATA_CNT = 0x5, + PPMU_WO_DATA_CNT = 0x6, + PPMU_RO_LATENCY = 0x12, + PPMU_WO_LATENCY = 0x16, +}; + +enum ppmu_reg { + /* PPC control register */ + PPMU_PMNC = 0x00, + PPMU_CNTENS = 0x10, + PPMU_CNTENC = 0x20, + PPMU_INTENS = 0x30, + PPMU_INTENC = 0x40, + PPMU_FLAG = 0x50, + + /* Cycle Counter and Performance Event Counter Register */ + PPMU_CCNT = 0x100, + PPMU_PMCNT0 = 0x110, + PPMU_PMCNT1 = 0x120, + PPMU_PMCNT2 = 0x130, + PPMU_PMCNT3_HIGH = 0x140, + PPMU_PMCNT3_LOW = 0x150, + + /* Bus Event Generator */ + PPMU_BEVT0SEL = 0x1000, + PPMU_BEVT1SEL = 0x1100, + PPMU_BEVT2SEL = 0x1200, + PPMU_BEVT3SEL = 0x1300, + PPMU_COUNTER_RESET = 0x1810, + PPMU_READ_OVERFLOW_CNT = 0x1810, + PPMU_READ_UNDERFLOW_CNT = 0x1814, + PPMU_WRITE_OVERFLOW_CNT = 0x1850, + PPMU_WRITE_UNDERFLOW_CNT = 0x1854, + PPMU_READ_PENDING_CNT = 0x1880, + PPMU_WRITE_PENDING_CNT = 0x1884 +}; + +/* PMNC register */ +#define PPMU_PMNC_CC_RESET_SHIFT 2 +#define PPMU_PMNC_COUNTER_RESET_SHIFT 1 +#define PPMU_PMNC_ENABLE_SHIFT 0 +#define PPMU_PMNC_START_MODE_MASK BIT(16) +#define PPMU_PMNC_CC_DIVIDER_MASK BIT(3) +#define PPMU_PMNC_CC_RESET_MASK BIT(2) +#define PPMU_PMNC_COUNTER_RESET_MASK BIT(1) +#define PPMU_PMNC_ENABLE_MASK BIT(0) + +/* CNTENS/CNTENC/INTENS/INTENC/FLAG register */ +#define PPMU_CCNT_MASK BIT(31) +#define PPMU_PMCNT3_MASK BIT(3) +#define PPMU_PMCNT2_MASK BIT(2) +#define PPMU_PMCNT1_MASK BIT(1) +#define PPMU_PMCNT0_MASK BIT(0) + +/* PPMU_PMNCTx/PPMU_BETxSEL registers */ +#define PPMU_PMNCT(x) (PPMU_PMCNT0 + (0x10 * x)) +#define PPMU_BEVTxSEL(x) (PPMU_BEVT0SEL + (0x100 * x)) + +#endif /* __EXYNOS_PPMU_H__ */ diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h new file mode 100644 index 000000000000..602fbbfcfeed --- /dev/null +++ b/include/linux/devfreq-event.h @@ -0,0 +1,196 @@ +/* + * devfreq-event: a framework to provide raw data and events of devfreq devices + * + * Copyright (C) 2014 Samsung Electronics + * Author: Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_DEVFREQ_EVENT_H__ +#define __LINUX_DEVFREQ_EVENT_H__ + +#include + +/** + * struct devfreq_event_dev - the devfreq-event device + * + * @node : Contain the devfreq-event device that have been registered. + * @dev : the device registered by devfreq-event class. dev.parent is + * the device using devfreq-event. + * @lock : a mutex to protect accessing devfreq-event. + * @enable_count: the number of enable function have been called. + * @desc : the description for devfreq-event device. + * + * This structure contains devfreq-event device information. + */ +struct devfreq_event_dev { + struct list_head node; + + struct device dev; + struct mutex lock; + u32 enable_count; + + const struct devfreq_event_desc *desc; +}; + +/** + * struct devfreq_event_data - the devfreq-event data + * + * @load_count : load count of devfreq-event device for the given period. + * @total_count : total count of devfreq-event device for the given period. + * each count may represent a clock cycle, a time unit + * (ns/us/...), or anything the device driver wants. + * Generally, utilization is load_count / total_count. + * + * This structure contains the data of devfreq-event device for polling period. + */ +struct devfreq_event_data { + unsigned long load_count; + unsigned long total_count; +}; + +/** + * struct devfreq_event_ops - the operations of devfreq-event device + * + * @enable : Enable the devfreq-event device. + * @disable : Disable the devfreq-event device. + * @reset : Reset all setting of the devfreq-event device. + * @set_event : Set the specific event type for the devfreq-event device. + * @get_event : Get the result of the devfreq-event devie with specific + * event type. + * + * This structure contains devfreq-event device operations which can be + * implemented by devfreq-event device drivers. + */ +struct devfreq_event_ops { + /* Optional functions */ + int (*enable)(struct devfreq_event_dev *edev); + int (*disable)(struct devfreq_event_dev *edev); + int (*reset)(struct devfreq_event_dev *edev); + + /* Mandatory functions */ + int (*set_event)(struct devfreq_event_dev *edev); + int (*get_event)(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +}; + +/** + * struct devfreq_event_desc - the descriptor of devfreq-event device + * + * @name : the name of devfreq-event device. + * @driver_data : the private data for devfreq-event driver. + * @ops : the operation to control devfreq-event device. + * + * Each devfreq-event device is described with a this structure. + * This structure contains the various data for devfreq-event device. + */ +struct devfreq_event_desc { + const char *name; + void *driver_data; + + struct devfreq_event_ops *ops; +}; + +#if defined(CONFIG_PM_DEVFREQ_EVENT) +extern int devfreq_event_enable_edev(struct devfreq_event_dev *edev); +extern int devfreq_event_disable_edev(struct devfreq_event_dev *edev); +extern bool devfreq_event_is_enabled(struct devfreq_event_dev *edev); +extern int devfreq_event_set_event(struct devfreq_event_dev *edev); +extern int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +extern int devfreq_event_reset_event(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index); +extern int devfreq_event_get_edev_count(struct device *dev); +extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev); +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return edev->desc->driver_data; +} +#else +static inline int devfreq_event_enable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_disable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline bool devfreq_event_is_enabled(struct devfreq_event_dev *edev) +{ + return false; +} + +static inline int devfreq_event_set_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + return -EINVAL; +} + +static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_get_edev_count(struct device *dev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_remove_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devm_devfreq_event_add_edev( + struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev) +{ +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return NULL; +} +#endif /* CONFIG_PM_DEVFREQ_EVENT */ + +#endif /* __LINUX_DEVFREQ_EVENT_H__ */ -- cgit v1.2.3 From 38e478c4489a845a5e8baf7849c286af5fed5b66 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 15:56:21 +0200 Subject: quota: Split ->set_xstate callback into two Split ->set_xstate callback into two callbacks - one for turning quotas on (->quota_enable) and one for turning quotas off (->quota_disable). That way we don't have to pass quotactl command into the callback which seems cleaner. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 20 +++++++++++++---- fs/xfs/xfs_quotaops.c | 59 ++++++++++++++++++++++++++++++++------------------- include/linux/quota.h | 3 ++- 3 files changed, 55 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 6f3856328eea..e2ae2b99e555 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -208,15 +208,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id, return sb->s_qcop->set_dqblk(sb, qid, &fdq); } -static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr) +static int quota_enable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; - if (!sb->s_qcop->set_xstate) + if (!sb->s_qcop->quota_enable) return -ENOSYS; - return sb->s_qcop->set_xstate(sb, flags, cmd); + return sb->s_qcop->quota_enable(sb, flags); +} + +static int quota_disable(struct super_block *sb, void __user *addr) +{ + __u32 flags; + + if (copy_from_user(&flags, addr, sizeof(flags))) + return -EFAULT; + if (!sb->s_qcop->quota_disable) + return -ENOSYS; + return sb->s_qcop->quota_disable(sb, flags); } static int quota_getxstate(struct super_block *sb, void __user *addr) @@ -447,8 +458,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: + return quota_enable(sb, addr); case Q_XQUOTAOFF: - return quota_setxstate(sb, cmd, addr); + return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index a226203fa46a..6923905ab33d 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -64,19 +64,10 @@ xfs_fs_get_xstatev( return xfs_qm_scall_getqstatv(mp, fqs); } -STATIC int -xfs_fs_set_xstate( - struct super_block *sb, - unsigned int uflags, - int op) +static unsigned int +xfs_quota_flags(unsigned int uflags) { - struct xfs_mount *mp = XFS_M(sb); - unsigned int flags = 0; - - if (sb->s_flags & MS_RDONLY) - return -EROFS; - if (!XFS_IS_QUOTA_RUNNING(mp)) - return -ENOSYS; + unsigned int flags = 0; if (uflags & FS_QUOTA_UDQ_ACCT) flags |= XFS_UQUOTA_ACCT; @@ -91,16 +82,39 @@ xfs_fs_set_xstate( if (uflags & FS_QUOTA_PDQ_ENFD) flags |= XFS_PQUOTA_ENFD; - switch (op) { - case Q_XQUOTAON: - return xfs_qm_scall_quotaon(mp, flags); - case Q_XQUOTAOFF: - if (!XFS_IS_QUOTA_ON(mp)) - return -EINVAL; - return xfs_qm_scall_quotaoff(mp, flags); - } + return flags; +} + +STATIC int +xfs_quota_enable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + + return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags)); +} + +STATIC int +xfs_quota_disable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + if (!XFS_IS_QUOTA_ON(mp)) + return -EINVAL; - return -EINVAL; + return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags)); } STATIC int @@ -166,7 +180,8 @@ xfs_fs_set_dqblk( const struct quotactl_ops xfs_quotactl_operations = { .get_xstatev = xfs_fs_get_xstatev, .get_xstate = xfs_fs_get_xstate, - .set_xstate = xfs_fs_set_xstate, + .quota_enable = xfs_quota_enable, + .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, .set_dqblk = xfs_fs_set_dqblk, diff --git a/include/linux/quota.h b/include/linux/quota.h index 227f37f463c9..4da497b807c4 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -371,13 +371,14 @@ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); + int (*quota_enable)(struct super_block *, unsigned int); + int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); - int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); int (*rm_xquota)(struct super_block *, unsigned int); }; -- cgit v1.2.3 From d3b863248577504f6eecca2a464d6ddf86b71584 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 16:07:12 +0200 Subject: quota: Wire up ->quota_{enable,disable} callbacks into Q_QUOTA{ON,OFF} Make Q_QUOTAON / Q_QUOTAOFF quotactl call ->quota_enable / ->quota_disable callback when provided. To match current behavior of ocfs2 & ext4 we make these quotactls turn on / off quota enforcement for appropriate quota type. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 31 +++++++++++++++++++++++++++---- include/linux/quotaops.h | 2 ++ 2 files changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index e2ae2b99e555..ce78a70a596f 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -66,18 +66,43 @@ static int quota_sync_all(int type) return ret; } +unsigned int qtype_enforce_flag(int type) +{ + switch (type) { + case USRQUOTA: + return FS_QUOTA_UDQ_ENFD; + case GRPQUOTA: + return FS_QUOTA_GDQ_ENFD; + case PRJQUOTA: + return FS_QUOTA_PDQ_ENFD; + } + return 0; +} + static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta && + !sb->s_qcop->quota_enable) return -ENOSYS; if (sb->s_qcop->quota_on_meta) return sb->s_qcop->quota_on_meta(sb, type, id); + if (sb->s_qcop->quota_enable) + return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } +static int quota_quotaoff(struct super_block *sb, int type) +{ + if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) + return -ENOSYS; + if (sb->s_qcop->quota_disable) + return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); + return sb->s_qcop->quota_off(sb, type); +} + static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; @@ -440,9 +465,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_QUOTAON: return quota_quotaon(sb, type, cmd, id, path); case Q_QUOTAOFF: - if (!sb->s_qcop->quota_off) - return -ENOSYS; - return sb->s_qcop->quota_off(sb, type); + return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 29e3455f7d41..ff0b665591d0 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -386,4 +386,6 @@ static inline void dquot_release_reservation_block(struct inode *inode, __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } +unsigned int qtype_enforce_flag(int type); + #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 3e2af67e66ff025796af1a8a1fcbb4236304f90c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 6 Oct 2014 18:40:51 +0200 Subject: quota: Add ->quota_{enable,disable} callbacks for VFS quotas Add functions which translate ->quota_enable / ->quota_disable calls into appropriate changes in VFS quota. This will enable filesystems supporting VFS quota files in system inodes to be controlled via Q_XQUOTA[ON|OFF] quotactls for better userspace compatibility. Also provide a vector for quotactl using these functions which can be used by filesystems with quota files stored in hidden system files. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/quotaops.h | 1 + 2 files changed, 92 insertions(+) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 29eb9dc5728a..b47d0c17ea6f 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2385,6 +2385,86 @@ out: } EXPORT_SYMBOL(dquot_quota_on_mount); +static int dquot_quota_enable(struct super_block *sb, unsigned int flags) +{ + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* Accounting cannot be turned on while fs is mounted */ + flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); + if (!flags) + return -EINVAL; + for (type = 0; type < MAXQUOTAS; type++) { + if (!(flags & qtype_enforce_flag(type))) + continue; + /* Can't enforce without accounting */ + if (!sb_has_quota_usage_enabled(sb, type)) + return -EINVAL; + ret = dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + return 0; +out_err: + /* Backout enforcement enablement we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + } + /* Error code translation for better compatibility with XFS */ + if (ret == -EBUSY) + ret = -EEXIST; + return ret; +} + +static int dquot_quota_disable(struct super_block *sb, unsigned int flags) +{ + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* + * We don't support turning off accounting via quotactl. In principle + * quota infrastructure can do this but filesystems don't expect + * userspace to be able to do it. + */ + if (flags & + (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) + return -EOPNOTSUPP; + + /* Filter out limits not enabled */ + for (type = 0; type < MAXQUOTAS; type++) + if (!sb_has_quota_limits_enabled(sb, type)) + flags &= ~qtype_enforce_flag(type); + /* Nothing left? */ + if (!flags) + return -EEXIST; + for (type = 0; type < MAXQUOTAS; type++) { + if (flags & qtype_enforce_flag(type)) { + ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + } + return 0; +out_err: + /* Backout enforcement disabling we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + } + return ret; +} + static inline qsize_t qbtos(qsize_t blocks) { return blocks << QIF_DQBLKSIZE_BITS; @@ -2614,6 +2694,17 @@ const struct quotactl_ops dquot_quotactl_ops = { }; EXPORT_SYMBOL(dquot_quotactl_ops); +const struct quotactl_ops dquot_quotactl_sysfile_ops = { + .quota_enable = dquot_quota_enable, + .quota_disable = dquot_quota_disable, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; +EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); + static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index ff0b665591d0..df73258cca47 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -166,6 +166,7 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_ops; +extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else -- cgit v1.2.3 From aaa3daed156ff3c6acb28c8b18028f8b57d6c91b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 18:35:31 +0200 Subject: quota: Remove quota_on_meta callback There are no more users for quota_on_meta callback. Just remove it. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 5 +---- include/linux/quota.h | 1 - 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index ce78a70a596f..d14a799c7785 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -82,11 +82,8 @@ unsigned int qtype_enforce_flag(int type) static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta && - !sb->s_qcop->quota_enable) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; - if (sb->s_qcop->quota_on_meta) - return sb->s_qcop->quota_on_meta(sb, type, id); if (sb->s_qcop->quota_enable) return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) diff --git a/include/linux/quota.h b/include/linux/quota.h index 4da497b807c4..0938159d65c8 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -369,7 +369,6 @@ struct qc_dqblk { /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); - int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); -- cgit v1.2.3 From b10a08194c2b615955dfab2300331a90ae9344c7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 9 Oct 2014 16:54:13 +0200 Subject: quota: Store maximum space limit in bytes Currently maximum space limit quota format supports is in blocks however since we store space limits in bytes, this is somewhat confusing. So store the maximum limit in bytes as well. Also rename the field to match the new unit and related inode field to match the new naming scheme. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/ocfs2/quota_local.c | 4 ++-- fs/quota/dquot.c | 18 ++++-------------- fs/quota/quota_v1.c | 4 ++-- fs/quota/quota_v2.c | 10 +++++----- include/linux/quota.h | 4 ++-- 5 files changed, 15 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 55f832f553cb..89c0b2620814 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -701,8 +701,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) /* We don't need the lock and we have to acquire quota file locks * which will later depend on this lock */ mutex_unlock(&sb_dqopt(sb)->dqio_mutex); - info->dqi_maxblimit = 0x7fffffffffffffffLL; - info->dqi_maxilimit = 0x7fffffffffffffffLL; + info->dqi_max_spc_limit = 0x7fffffffffffffffLL; + info->dqi_max_ino_limit = 0x7fffffffffffffffLL; oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS); if (!oinfo) { mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota" diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b47d0c17ea6f..0ccd4ba3a246 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2465,16 +2465,6 @@ out_err: return ret; } -static inline qsize_t qbtos(qsize_t blocks) -{ - return blocks << QIF_DQBLKSIZE_BITS; -} - -static inline qsize_t stoqb(qsize_t space) -{ - return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; -} - /* Generic routine for getting common part of quota structure */ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { @@ -2524,13 +2514,13 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) return -EINVAL; if (((di->d_fieldmask & QC_SPC_SOFT) && - stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) || + di->d_spc_softlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_SPC_HARD) && - stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) || + di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_INO_SOFT) && - (di->d_ino_softlimit > dqi->dqi_maxilimit)) || + (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || ((di->d_fieldmask & QC_INO_HARD) && - (di->d_ino_hardlimit > dqi->dqi_maxilimit))) + (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dq_data_lock); diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 469c6848b322..8fe79beced5c 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type) } ret = 0; /* limits are stored as unsigned 32-bit data */ - dqopt->info[type].dqi_maxblimit = 0xffffffff; - dqopt->info[type].dqi_maxilimit = 0xffffffff; + dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + dqopt->info[type].dqi_max_ino_limit = 0xffffffff; dqopt->info[type].dqi_igrace = dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME; dqopt->info[type].dqi_bgrace = diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 54cac436ac72..9cb10d7197f7 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -117,12 +117,12 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ - info->dqi_maxblimit = 0xffffffff; - info->dqi_maxilimit = 0xffffffff; + info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + info->dqi_max_ino_limit = 0xffffffff; } else { - /* used space is stored as unsigned 64-bit value */ - info->dqi_maxblimit = 0xffffffffffffffffULL; /* 2^64-1 */ - info->dqi_maxilimit = 0xffffffffffffffffULL; + /* used space is stored as unsigned 64-bit value in bytes */ + info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */ + info->dqi_max_ino_limit = 0xffffffffffffffffULL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); diff --git a/include/linux/quota.h b/include/linux/quota.h index 0938159d65c8..d534e8ed308a 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -216,8 +216,8 @@ struct mem_dqinfo { unsigned long dqi_flags; unsigned int dqi_bgrace; unsigned int dqi_igrace; - qsize_t dqi_maxblimit; - qsize_t dqi_maxilimit; + qsize_t dqi_max_spc_limit; + qsize_t dqi_max_ino_limit; void *dqi_priv; }; -- cgit v1.2.3 From 284f4902a632584e8d73cf7d9363f819adf7240c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:13 -0500 Subject: xprtrdma: Modernize htonl and ntohl Clean up: Replace htonl and ntohl with the be32 equivalents. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 9 ++++++++ include/linux/sunrpc/svc_rdma.h | 2 -- net/sunrpc/xprtrdma/rpc_rdma.c | 48 ++++++++++++++++++++++------------------- 3 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index b78f16b1dea3..1578ed241c19 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -42,6 +42,9 @@ #include +#define RPCRDMA_VERSION 1 +#define rpcrdma_version cpu_to_be32(RPCRDMA_VERSION) + struct rpcrdma_segment { __be32 rs_handle; /* Registered memory handle */ __be32 rs_length; /* Length of the chunk in bytes */ @@ -115,4 +118,10 @@ enum rpcrdma_proc { RDMA_ERROR = 4 /* An RPC RDMA encoding error */ }; +#define rdma_msg cpu_to_be32(RDMA_MSG) +#define rdma_nomsg cpu_to_be32(RDMA_NOMSG) +#define rdma_msgp cpu_to_be32(RDMA_MSGP) +#define rdma_done cpu_to_be32(RDMA_DONE) +#define rdma_error cpu_to_be32(RDMA_ERROR) + #endif /* _LINUX_SUNRPC_RPC_RDMA_H */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 975da754c778..ddfe88f52219 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -63,8 +63,6 @@ extern atomic_t rdma_stat_rq_prod; extern atomic_t rdma_stat_sq_poll; extern atomic_t rdma_stat_sq_prod; -#define RPCRDMA_VERSION 1 - /* * Contexts are built when an RDMA request is created and are a * record of the resources that can be recovered when the request diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index df01d124936c..a6fb30b0a8cc 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -209,9 +209,11 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, if (cur_rchunk) { /* read */ cur_rchunk->rc_discrim = xdr_one; /* all read chunks have the same "position" */ - cur_rchunk->rc_position = htonl(pos); - cur_rchunk->rc_target.rs_handle = htonl(seg->mr_rkey); - cur_rchunk->rc_target.rs_length = htonl(seg->mr_len); + cur_rchunk->rc_position = cpu_to_be32(pos); + cur_rchunk->rc_target.rs_handle = + cpu_to_be32(seg->mr_rkey); + cur_rchunk->rc_target.rs_length = + cpu_to_be32(seg->mr_len); xdr_encode_hyper( (__be32 *)&cur_rchunk->rc_target.rs_offset, seg->mr_base); @@ -222,8 +224,10 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, cur_rchunk++; r_xprt->rx_stats.read_chunk_count++; } else { /* write/reply */ - cur_wchunk->wc_target.rs_handle = htonl(seg->mr_rkey); - cur_wchunk->wc_target.rs_length = htonl(seg->mr_len); + cur_wchunk->wc_target.rs_handle = + cpu_to_be32(seg->mr_rkey); + cur_wchunk->wc_target.rs_length = + cpu_to_be32(seg->mr_len); xdr_encode_hyper( (__be32 *)&cur_wchunk->wc_target.rs_offset, seg->mr_base); @@ -257,7 +261,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, *iptr++ = xdr_zero; /* encode a NULL reply chunk */ } else { warray->wc_discrim = xdr_one; - warray->wc_nchunks = htonl(nchunks); + warray->wc_nchunks = cpu_to_be32(nchunks); iptr = (__be32 *) cur_wchunk; if (type == rpcrdma_writech) { *iptr++ = xdr_zero; /* finish the write chunk list */ @@ -404,11 +408,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) /* build RDMA header in private area at front */ headerp = (struct rpcrdma_msg *) req->rl_base; - /* don't htonl XID, it's already done in request */ + /* don't byte-swap XID, it's already done in request */ headerp->rm_xid = rqst->rq_xid; - headerp->rm_vers = xdr_one; - headerp->rm_credit = htonl(r_xprt->rx_buf.rb_max_requests); - headerp->rm_type = htonl(RDMA_MSG); + headerp->rm_vers = rpcrdma_version; + headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests); + headerp->rm_type = rdma_msg; /* * Chunks needed for results? @@ -482,11 +486,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) RPCRDMA_INLINE_PAD_VALUE(rqst)); if (padlen) { - headerp->rm_type = htonl(RDMA_MSGP); + headerp->rm_type = rdma_msgp; headerp->rm_body.rm_padded.rm_align = - htonl(RPCRDMA_INLINE_PAD_VALUE(rqst)); + cpu_to_be32(RPCRDMA_INLINE_PAD_VALUE(rqst)); headerp->rm_body.rm_padded.rm_thresh = - htonl(RPCRDMA_INLINE_PAD_THRESH); + cpu_to_be32(RPCRDMA_INLINE_PAD_THRESH); headerp->rm_body.rm_padded.rm_pempty[0] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; @@ -570,7 +574,7 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b unsigned int i, total_len; struct rpcrdma_write_chunk *cur_wchunk; - i = ntohl(**iptrp); /* get array count */ + i = be32_to_cpu(**iptrp); if (i > max) return -1; cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1); @@ -582,11 +586,11 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b xdr_decode_hyper((__be32 *)&seg->rs_offset, &off); dprintk("RPC: %s: chunk %d@0x%llx:0x%x\n", __func__, - ntohl(seg->rs_length), + be32_to_cpu(seg->rs_length), (unsigned long long)off, - ntohl(seg->rs_handle)); + be32_to_cpu(seg->rs_handle)); } - total_len += ntohl(seg->rs_length); + total_len += be32_to_cpu(seg->rs_length); ++cur_wchunk; } /* check and adjust for properly terminated write chunk */ @@ -749,9 +753,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) goto repost; } headerp = (struct rpcrdma_msg *) rep->rr_base; - if (headerp->rm_vers != xdr_one) { + if (headerp->rm_vers != rpcrdma_version) { dprintk("RPC: %s: invalid version %d\n", - __func__, ntohl(headerp->rm_vers)); + __func__, be32_to_cpu(headerp->rm_vers)); goto repost; } @@ -793,7 +797,7 @@ repost: /* check for expected message types */ /* The order of some of these tests is important. */ switch (headerp->rm_type) { - case htonl(RDMA_MSG): + case rdma_msg: /* never expect read chunks */ /* never expect reply chunks (two ways to check) */ /* never expect write chunks without having offered RDMA */ @@ -832,7 +836,7 @@ repost: rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen); break; - case htonl(RDMA_NOMSG): + case rdma_nomsg: /* never expect read or write chunks, always reply chunks */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || headerp->rm_body.rm_chunks[1] != xdr_zero || @@ -853,7 +857,7 @@ badheader: dprintk("%s: invalid rpcrdma reply header (type %d):" " chunks[012] == %d %d %d" " expected chunks <= %d\n", - __func__, ntohl(headerp->rm_type), + __func__, be32_to_cpu(headerp->rm_type), headerp->rm_body.rm_chunks[0], headerp->rm_body.rm_chunks[1], headerp->rm_body.rm_chunks[2], -- cgit v1.2.3 From f2846481b4bf758cf7c3fe8f24b35950306f1db2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:29 -0500 Subject: xprtrdma: Clean up hdrlen Clean up: Replace naked integers with a documenting macro. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 5 ++++- net/sunrpc/xprtrdma/rpc_rdma.c | 12 +++++++----- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 1578ed241c19..f33c5a4d6fe4 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -98,7 +98,10 @@ struct rpcrdma_msg { } rm_body; }; -#define RPCRDMA_HDRLEN_MIN 28 +/* + * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks + */ +#define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) enum rpcrdma_errcode { ERR_VERS = 1, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 150dd7641803..dcf5ebc3d373 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -472,7 +472,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) return -EIO; } - hdrlen = 28; /*sizeof *headerp;*/ + hdrlen = RPCRDMA_HDRLEN_MIN; padlen = 0; /* @@ -748,7 +748,7 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) } return; } - if (rep->rr_len < 28) { + if (rep->rr_len < RPCRDMA_HDRLEN_MIN) { dprintk("RPC: %s: short/invalid reply\n", __func__); goto repost; } @@ -830,8 +830,9 @@ repost: } else { /* else ordinary inline */ rdmalen = 0; - iptr = (__be32 *)((unsigned char *)headerp + 28); - rep->rr_len -= 28; /*sizeof *headerp;*/ + iptr = (__be32 *)((unsigned char *)headerp + + RPCRDMA_HDRLEN_MIN); + rep->rr_len -= RPCRDMA_HDRLEN_MIN; status = rep->rr_len; } /* Fix up the rpc results for upper layer */ @@ -845,7 +846,8 @@ repost: headerp->rm_body.rm_chunks[2] != xdr_one || req->rl_nchunks == 0) goto badheader; - iptr = (__be32 *)((unsigned char *)headerp + 28); + iptr = (__be32 *)((unsigned char *)headerp + + RPCRDMA_HDRLEN_MIN); rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr); if (rdmalen < 0) goto badheader; -- cgit v1.2.3 From 448c7f3830ca283e485aa943279acea6bde8b270 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sun, 1 Feb 2015 11:25:14 -0800 Subject: Input: MT - add support for balanced slot assignment Some devices are not fast enough to differentiate between a fast-moving contact and a new contact. This problem cannot be fully resolved because information is truly missing, but it is possible to safe-guard against obvious mistakes by restricting movement with a maximum displacement. The new problem formulation for dmax > 0 cannot benefit from the speedup for positive definite matrices, but since the convergence is faster, the result is about the same. For a handful of contacts, the latency difference is truly negligible. Suggested-by: Benjamin Tissoires Tested-by: Benjamin Tissoires Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- drivers/input/input-mt.c | 31 ++++++++++++++++++++----------- drivers/input/mouse/alps.c | 2 +- drivers/input/mouse/bcm5974.c | 2 +- drivers/input/mouse/cypress_ps2.c | 2 +- drivers/input/mouse/synaptics.c | 2 +- drivers/input/touchscreen/pixcir_i2c_ts.c | 2 +- include/linux/input/mt.h | 3 ++- 7 files changed, 27 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c index fbe29fcb15c5..cb150a1dbaff 100644 --- a/drivers/input/input-mt.c +++ b/drivers/input/input-mt.c @@ -293,7 +293,7 @@ void input_mt_sync_frame(struct input_dev *dev) } EXPORT_SYMBOL(input_mt_sync_frame); -static int adjust_dual(int *begin, int step, int *end, int eq) +static int adjust_dual(int *begin, int step, int *end, int eq, int mu) { int f, *p, s, c; @@ -311,9 +311,10 @@ static int adjust_dual(int *begin, int step, int *end, int eq) s = *p; c = (f + s + 1) / 2; - if (c == 0 || (c > 0 && !eq)) + if (c == 0 || (c > mu && (!eq || mu > 0))) return 0; - if (s < 0) + /* Improve convergence for positive matrices by penalizing overcovers */ + if (s < 0 && mu <= 0) c *= 2; for (p = begin; p != end; p += step) @@ -322,23 +323,24 @@ static int adjust_dual(int *begin, int step, int *end, int eq) return (c < s && s <= 0) || (f >= 0 && f < c); } -static void find_reduced_matrix(int *w, int nr, int nc, int nrc) +static void find_reduced_matrix(int *w, int nr, int nc, int nrc, int mu) { int i, k, sum; for (k = 0; k < nrc; k++) { for (i = 0; i < nr; i++) - adjust_dual(w + i, nr, w + i + nrc, nr <= nc); + adjust_dual(w + i, nr, w + i + nrc, nr <= nc, mu); sum = 0; for (i = 0; i < nrc; i += nr) - sum += adjust_dual(w + i, 1, w + i + nr, nc <= nr); + sum += adjust_dual(w + i, 1, w + i + nr, nc <= nr, mu); if (!sum) break; } } static int input_mt_set_matrix(struct input_mt *mt, - const struct input_mt_pos *pos, int num_pos) + const struct input_mt_pos *pos, int num_pos, + int mu) { const struct input_mt_pos *p; struct input_mt_slot *s; @@ -352,7 +354,7 @@ static int input_mt_set_matrix(struct input_mt *mt, y = input_mt_get_value(s, ABS_MT_POSITION_Y); for (p = pos; p != pos + num_pos; p++) { int dx = x - p->x, dy = y - p->y; - *w++ = dx * dx + dy * dy; + *w++ = dx * dx + dy * dy - mu; } } @@ -393,17 +395,24 @@ static void input_mt_set_slots(struct input_mt *mt, * @slots: the slot assignment to be filled * @pos: the position array to match * @num_pos: number of positions + * @dmax: maximum ABS_MT_POSITION displacement (zero for infinite) * * Performs a best match against the current contacts and returns * the slot assignment list. New contacts are assigned to unused * slots. * + * The assignments are balanced so that all coordinate displacements are + * below the euclidian distance dmax. If no such assignment can be found, + * some contacts are assigned to unused slots. + * * Returns zero on success, or negative error in case of failure. */ int input_mt_assign_slots(struct input_dev *dev, int *slots, - const struct input_mt_pos *pos, int num_pos) + const struct input_mt_pos *pos, int num_pos, + int dmax) { struct input_mt *mt = dev->mt; + int mu = 2 * dmax * dmax; int nrc; if (!mt || !mt->red) @@ -413,8 +422,8 @@ int input_mt_assign_slots(struct input_dev *dev, int *slots, if (num_pos < 1) return 0; - nrc = input_mt_set_matrix(mt, pos, num_pos); - find_reduced_matrix(mt->red, num_pos, nrc / num_pos, nrc); + nrc = input_mt_set_matrix(mt, pos, num_pos, mu); + find_reduced_matrix(mt->red, num_pos, nrc / num_pos, nrc, mu); input_mt_set_slots(mt, slots, num_pos); return 0; diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index f719f28d370c..f205b8be2ce4 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -435,7 +435,7 @@ static void alps_report_mt_data(struct psmouse *psmouse, int n) struct alps_fields *f = &priv->f; int i, slot[MAX_TOUCHES]; - input_mt_assign_slots(dev, slot, f->mt, n); + input_mt_assign_slots(dev, slot, f->mt, n, 0); for (i = 0; i < n; i++) alps_set_slot(dev, slot[i], f->mt[i].x, f->mt[i].y); diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index c329cdb0b91a..b10709f04615 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -564,7 +564,7 @@ static int report_tp_state(struct bcm5974 *dev, int size) dev->index[n++] = &f[i]; } - input_mt_assign_slots(input, dev->slots, dev->pos, n); + input_mt_assign_slots(input, dev->slots, dev->pos, n, 0); for (i = 0; i < n; i++) report_finger_data(input, dev->slots[i], diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c index 8af34ffe208b..9118a1861a45 100644 --- a/drivers/input/mouse/cypress_ps2.c +++ b/drivers/input/mouse/cypress_ps2.c @@ -538,7 +538,7 @@ static void cypress_process_packet(struct psmouse *psmouse, bool zero_pkt) pos[i].y = contact->y; } - input_mt_assign_slots(input, slots, pos, n); + input_mt_assign_slots(input, slots, pos, n, 0); for (i = 0; i < n; i++) { contact = &report_data.contacts[i]; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index f89de8971bf8..a3692e3b7cab 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -809,7 +809,7 @@ static void synaptics_report_mt_data(struct psmouse *psmouse, pos[i].y = synaptics_invert_y(hw[i]->y); } - input_mt_assign_slots(dev, slot, pos, nsemi); + input_mt_assign_slots(dev, slot, pos, nsemi, 0); for (i = 0; i < nsemi; i++) { input_mt_slot(dev, slot[i]); diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c index 4fb5537fdd42..2c2107147319 100644 --- a/drivers/input/touchscreen/pixcir_i2c_ts.c +++ b/drivers/input/touchscreen/pixcir_i2c_ts.c @@ -126,7 +126,7 @@ static void pixcir_ts_report(struct pixcir_i2c_ts_data *ts, pos[i].y = touch->y; } - input_mt_assign_slots(ts->input, slots, pos, n); + input_mt_assign_slots(ts->input, slots, pos, n, 0); } for (i = 0; i < n; i++) { diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index f583ff639776..d7188de4db96 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -119,7 +119,8 @@ struct input_mt_pos { }; int input_mt_assign_slots(struct input_dev *dev, int *slots, - const struct input_mt_pos *pos, int num_pos); + const struct input_mt_pos *pos, int num_pos, + int dmax); int input_mt_get_slot_by_key(struct input_dev *dev, int key); -- cgit v1.2.3 From fd979c0132074856975a6e79bc2226b99435ec5b Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 30 Jan 2015 13:45:57 -0800 Subject: perf: provide sysfs_show for struct perf_pmu_events_attr (struct perf_pmu_events_attr) is defined in include/linux/perf_event.h, but the only "show" for it is in x86 and contains x86 specific stuff. Make a generic one for those of us who are just using the event_str. Signed-off-by: Cody P Schafer Signed-off-by: Sukadev Bhattiprolu Acked-by: Jiri Olsa Signed-off-by: Michael Ellerman --- include/linux/perf_event.h | 3 +++ kernel/events/core.c | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 486e84ccb1f9..58f59bdb590b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -897,6 +897,9 @@ struct perf_pmu_events_attr { const char *event_str; }; +ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); + #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c1ee7f2bebc..934687f8d51b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8276,6 +8276,18 @@ void __init perf_event_init(void) != 1024); } +ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + if (pmu_attr->event_str) + return sprintf(page, "%s\n", pmu_attr->event_str); + + return 0; +} + static int __init perf_event_sysfs_init(void) { struct pmu *pmu; -- cgit v1.2.3 From f0405b816149665393cc62b9e5082fc2d79714df Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 30 Jan 2015 13:45:58 -0800 Subject: perf: add PMU_EVENT_ATTR_STRING() helper Helper for constructing static struct perf_pmu_events_attr s. Signed-off-by: Cody P Schafer Signed-off-by: Sukadev Bhattiprolu Acked-by: Jiri Olsa Signed-off-by: Michael Ellerman --- include/linux/perf_event.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 58f59bdb590b..1d3631448b91 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -906,6 +906,13 @@ static struct perf_pmu_events_attr _var = { \ .id = _id, \ }; +#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ +static struct perf_pmu_events_attr _var = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = _str, \ +}; + #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ -- cgit v1.2.3 From 3e87523897e18a3e17fc8955ed795188be737ff1 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 2 Feb 2015 09:39:02 -0500 Subject: sched/wait: Remove might_sleep() from wait_event_cmd() The patch e22b886a8a43 ("sched/wait: Add might_sleep() checks") introduced a bug in the raid5 subsystem. The function raid5_quiesce() (and resize_stripes()) uses the 'cmd' part to release and acquire a spinlock (so we call the sleep primitives in atomic context), and therefore we cannot do the might_sleep() check. Remove it. Fixes: e22b886a8a43 ("sched/wait: Add might_sleep() checks") Signed-off-by: Mikulas Patocka Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1502020935580.13510@file01.intranet.prod.int.rdu2.redhat.com Signed-off-by: Ingo Molnar --- include/linux/wait.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 2232ed16635a..37423e0e1379 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -363,7 +363,6 @@ do { \ */ #define wait_event_cmd(wq, condition, cmd1, cmd2) \ do { \ - might_sleep(); \ if (condition) \ break; \ __wait_event_cmd(wq, condition, cmd1, cmd2); \ -- cgit v1.2.3 From f0b66a2cf68ed3613fe72fe01ed309f998e2bbb3 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 3 Feb 2015 09:29:52 -0600 Subject: PCI: Add pci_device_to_OF_node() stub for !CONFIG_OF Add a stub for pci_device_to_OF_node() so drivers don't need to use #ifdef CONFIG_OF around calls to it. Signed-off-by: Kevin Hao Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..fbb5795a8d86 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1847,6 +1847,8 @@ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } static inline void pci_set_bus_of_node(struct pci_bus *bus) { } static inline void pci_release_bus_of_node(struct pci_bus *bus) { } +static inline struct device_node * +pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } #endif /* CONFIG_OF */ #ifdef CONFIG_EEH -- cgit v1.2.3 From 1a04c6e1a26a43305fe124a0978a3e4be861af89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:57 +0800 Subject: nfsv3: introduce nfs3_set_ds_client The flexfiles layout wants to create DS connection over NFSv3. Add nfs3_set_ds_client to allow that to happen. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/internal.h | 4 ++++ fs/nfs/nfs3_fs.h | 2 ++ fs/nfs/nfs3client.c | 34 ++++++++++++++++++++++++++++++++++ fs/nfs/nfs3super.c | 2 +- include/linux/nfs_fs_sb.h | 9 +++++---- 5 files changed, 46 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7d7c36ff09fa..7332ba1f693b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -193,6 +193,10 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, rpc_authflavor_t au_flavor); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); +extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, + unsigned int ds_retrans, rpc_authflavor_t au_flavor); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index 333ae4068506..e134d6548ab7 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); +/* nfs3super.c */ +extern struct nfs_subversion nfs_v3; #endif /* __LINUX_FS_NFS_NFS3_FS_H */ diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 8c1b437c5403..52e2344bf9a1 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -64,3 +64,37 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source, nfs_init_server_aclclient(server); return server; } + +/* + * Set up a pNFS Data Server client over NFSv3. + * + * Return any existing nfs_client that matches server address,port,version + * and minorversion. + * + * For a new nfs_client, use a soft mount (default), a low retrans and a + * low timeout interval so that if a connection is lost, we retry through + * the MDS. + */ +struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, + rpc_authflavor_t au_flavor) +{ + struct nfs_client_initdata cl_init = { + .addr = ds_addr, + .addrlen = ds_addrlen, + .nfs_mod = &nfs_v3, + .proto = ds_proto, + .net = mds_clp->cl_net, + }; + struct rpc_timeout ds_timeout; + struct nfs_client *clp; + + /* Use the MDS nfs_client cl_ipaddr. */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); + clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, + au_flavor); + + return clp; +} +EXPORT_SYMBOL_GPL(nfs3_set_ds_client); diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c index 6af29c2da352..5c4394e4656b 100644 --- a/fs/nfs/nfs3super.c +++ b/fs/nfs/nfs3super.c @@ -7,7 +7,7 @@ #include "nfs3_fs.h" #include "nfs.h" -static struct nfs_subversion nfs_v3 = { +struct nfs_subversion nfs_v3 = { .owner = THIS_MODULE, .nfs_fs = &nfs_fs_type, .rpc_vers = &nfs_version3, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ddea982355f3..5e1273d4de14 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -77,10 +77,6 @@ struct nfs_client { /* Client owner identifier */ const char * cl_owner_id; - /* Our own IP address, as a null-terminated string. - * This is used to generate the mv0 callback address. - */ - char cl_ipaddr[48]; u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; unsigned long cl_mig_gen; @@ -108,6 +104,11 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ #endif /* CONFIG_NFS_V4 */ + /* Our own IP address, as a null-terminated string. + * This is used to generate the mv0 callback address. + */ + char cl_ipaddr[48]; + #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif -- cgit v1.2.3 From abde71f4d3c027a30f8d725e1e22001313b4481a Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Mon, 9 Jun 2014 13:12:20 -0700 Subject: pnfs: Add nfs_rpc_ops in calls to nfs_initiate_pgio Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.c | 4 ++-- fs/nfs/internal.h | 1 + fs/nfs/pagelist.c | 6 ++++-- fs/nfs/read.c | 3 ++- fs/nfs/write.c | 6 +++--- include/linux/nfs_page.h | 1 + 6 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index bc36ed350a68..25c4896887ca 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -501,7 +501,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) hdr->mds_offset = offset; /* Perform an asynchronous read to ds */ - nfs_initiate_pgio(ds_clnt, hdr, + nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode), &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; } @@ -542,7 +542,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->args.offset = filelayout_get_dserver_offset(lseg, offset); /* Perform an asynchronous write */ - nfs_initiate_pgio(ds_clnt, hdr, + nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode), &filelayout_write_call_ops, sync, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5543850268d2..1d15ffa94937 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -251,6 +251,7 @@ void nfs_pgio_header_free(struct nfs_pgio_header *); void nfs_pgio_data_destroy(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *, + const struct nfs_rpc_ops *, const struct rpc_call_ops *, int, int); void nfs_free_request(struct nfs_page *req); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2b5e769beb16..35a2626a6922 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -597,6 +597,7 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) } int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, + const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags) { struct rpc_task *task; @@ -616,7 +617,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, }; int ret = 0; - hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how); + hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how); dprintk("NFS: %5u initiated pgio call " "(req %s/%llu, %u bytes @ offset %llu)\n", @@ -792,7 +793,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) ret = nfs_generic_pgio(desc, hdr); if (ret == 0) ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode), - hdr, desc->pg_rpc_callops, + hdr, NFS_PROTO(hdr->inode), + desc->pg_rpc_callops, desc->pg_ioflags, 0); return ret; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c91a4799c562..092ab499f2b6 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -168,13 +168,14 @@ out: static void nfs_initiate_read(struct nfs_pgio_header *hdr, struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { struct inode *inode = hdr->inode; int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; task_setup_data->flags |= swap_flags; - NFS_PROTO(inode)->read_setup(hdr, msg); + rpc_ops->read_setup(hdr, msg); } static void diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e3..54d4857e0e2b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1240,15 +1240,15 @@ static int flush_task_priority(int how) static void nfs_initiate_write(struct nfs_pgio_header *hdr, struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { - struct inode *inode = hdr->inode; int priority = flush_task_priority(how); task_setup_data->priority = priority; - NFS_PROTO(inode)->write_setup(hdr, msg); + rpc_ops->write_setup(hdr, msg); - nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client, + nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client, &task_setup_data->rpc_client, msg, hdr); } diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 6c3e06ee2fb7..4c3aa809ab95 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -69,6 +69,7 @@ struct nfs_rw_ops { struct inode *); void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *); void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *, + const struct nfs_rpc_ops *, struct rpc_task_setup *, int); }; -- cgit v1.2.3 From 840210fc4872bcbc17ab4f435f28021dce9d0aff Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 24 Jun 2014 10:59:52 -0400 Subject: sunrpc: add rpc_count_iostats_idx Add a call to tally stats for a task under a different statsidx than what's contained in the task structure. This is needed to properly account for pnfs reads/writes when the DS nfs version != the MDS version. Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes --- include/linux/sunrpc/metrics.h | 2 ++ net/sunrpc/stats.c | 26 +++++++++++++++++++------- 2 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index eecb5a71e6c0..89f2ca178873 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -79,6 +79,8 @@ struct rpc_clnt; struct rpc_iostats * rpc_alloc_iostats(struct rpc_clnt *); void rpc_count_iostats(const struct rpc_task *, struct rpc_iostats *); +void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *); void rpc_print_iostats(struct seq_file *, struct rpc_clnt *); void rpc_free_iostats(struct rpc_iostats *); diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 9711a155bc50..2ecb994314c1 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -140,22 +140,20 @@ void rpc_free_iostats(struct rpc_iostats *stats) EXPORT_SYMBOL_GPL(rpc_free_iostats); /** - * rpc_count_iostats - tally up per-task stats + * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task - * @stats: array of stat structures + * @op_metrics: stat structure for OP that will accumulate stats from @task */ -void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) +void rpc_count_iostats_metrics(const struct rpc_task *task, + struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; - struct rpc_iostats *op_metrics; ktime_t delta, now; - if (!stats || !req) + if (!op_metrics || !req) return; now = ktime_get(); - op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx]; - spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; @@ -175,6 +173,20 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) spin_unlock(&op_metrics->om_lock); } +EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); + +/** + * rpc_count_iostats - tally up per-task stats + * @task: completed rpc_task + * @stats: array of stat structures + * + * Uses the statidx from @task + */ +void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) +{ + rpc_count_iostats_metrics(task, + &stats[task->tk_msg.rpc_proc->p_statidx]); +} EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, -- cgit v1.2.3 From aabff4ddcac0d36dd26546f5b905c27682e7bf89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 27 Aug 2014 10:47:14 +0800 Subject: nfs: save server READ/WRITE/COMMIT status Flexfiles layout would want to use them to report DS IO status. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs2xdr.c | 10 +++++++--- fs/nfs/nfs3xdr.c | 3 +++ fs/nfs/nfs4xdr.c | 3 +++ include/linux/nfs_xdr.h | 2 ++ 4 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 5f61b83f4a1c..b4e03ed8599d 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -481,7 +481,8 @@ out_overflow: * void; * }; */ -static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result) +static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result, + __u32 *op_status) { enum nfs_stat status; int error; @@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result) error = decode_stat(xdr, &status); if (unlikely(error)) goto out; + if (op_status) + *op_status = status; if (status != NFS_OK) goto out_default; error = decode_fattr(xdr, result); @@ -808,7 +811,7 @@ out_default: static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, struct nfs_fattr *result) { - return decode_attrstat(xdr, result); + return decode_attrstat(xdr, result, NULL); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_stat(xdr, &status); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS_OK) goto out_default; error = decode_fattr(xdr, result->fattr); @@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, { /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; - return decode_attrstat(xdr, result->fattr); + return decode_attrstat(xdr, result->fattr, &result->op_status); } /** diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 8f4cbe7f4aa8..2a932fdc57cb 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_post_op_attr(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_read3resok(xdr, result); @@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_wcc_data(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_write3resok(xdr, result); @@ -2323,6 +2325,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, error = decode_wcc_data(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_writeverf3(xdr, &result->verf->verifier); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cb4376b78ed9..7d8d7a47f771 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6567,6 +6567,7 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); @@ -6592,6 +6593,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); @@ -6621,6 +6623,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..962f461c065d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -513,6 +513,7 @@ struct nfs_pgio_res { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; __u32 count; + __u32 op_status; int eof; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ @@ -532,6 +533,7 @@ struct nfs_commitargs { struct nfs_commitres { struct nfs4_sequence_res seq_res; + __u32 op_status; struct nfs_fattr *fattr; struct nfs_writeverf *verf; const struct nfs_server *server; -- cgit v1.2.3 From 4579d6b897ee1b2557517fd536fb17eeb13481ad Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:21 +0800 Subject: nfs41: pass iomode through layoutreturn args So that it is possible to return a specific iomode layouts. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4xdr.c | 2 +- fs/nfs/pnfs.c | 1 + include/linux/nfs_xdr.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7d8d7a47f771..3c3ff633dd17 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2012,7 +2012,7 @@ encode_layoutreturn(struct xdr_stream *xdr, p = reserve_space(xdr, 16); *p++ = cpu_to_be32(0); /* reclaim. always 0 for now */ *p++ = cpu_to_be32(args->layout_type); - *p++ = cpu_to_be32(IOMODE_ANY); + *p++ = cpu_to_be32(args->iomode); *p = cpu_to_be32(RETURN_FILE); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, 0); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7e1bac189d1c..1b544c1a746c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -914,6 +914,7 @@ _pnfs_return_layout(struct inode *ino) lrp->args.stateid = stateid; lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; + lrp->args.iomode = IOMODE_ANY; lrp->args.layout = lo; lrp->clp = NFS_SERVER(ino)->nfs_client; lrp->cred = lo->plh_lc_cred; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 962f461c065d..4fd7793d45d1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,6 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; + enum pnfs_iomode iomode; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From 2176bf4269a37a7742230ed6c91668241bfe1b2b Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 10 Sep 2014 15:44:18 -0400 Subject: nfs: introduce pg_cleanup op for pgio descriptors Add a new operation to nfs_pageio_ops that is called on nfs_pageio_complete. Signed-off-by: Weston Andros Adamson --- fs/nfs/pagelist.c | 5 ++++- include/linux/nfs_page.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index c4d175829880..1c031878c752 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1050,7 +1050,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, EXPORT_SYMBOL_GPL(nfs_pageio_resend); /** - * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor + * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor * @desc: pointer to io descriptor */ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) @@ -1062,6 +1062,9 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) if (!nfs_do_recoalesce(desc)) break; } + + if (desc->pg_ops->pg_cleanup) + desc->pg_ops->pg_cleanup(desc); } /** diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 4c3aa809ab95..479c566c4ddc 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,7 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; struct nfs_rw_ops { -- cgit v1.2.3 From 6cccbb6f52dceec5f4faed8846ac05ae830640e6 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 16 Sep 2014 17:35:51 -0400 Subject: nfs: rename pgio header ds_idx to ds_commit_idx 'ds_commit_idx' is a better name - it is used to select the right commit bucket for pnfs. Signed-off-by: Weston Andros Adamson --- fs/nfs/direct.c | 14 ++++++-------- fs/nfs/filelayout/filelayout.c | 4 ++-- include/linux/nfs_xdr.h | 2 +- 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e84f764b9dcd..d7c2d430b04d 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -112,22 +112,22 @@ static inline int put_dreq(struct nfs_direct_req *dreq) * nfs_direct_select_verf - select the right verifier * @dreq - direct request possibly spanning multiple servers * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs - * @ds_idx - index of data server in data server list, only valid if ds_clp set + * @commit_idx - commit bucket index for the DS * * returns the correct verifier to use given the role of the server */ static struct nfs_writeverf * nfs_direct_select_verf(struct nfs_direct_req *dreq, struct nfs_client *ds_clp, - int ds_idx) + int commit_idx) { struct nfs_writeverf *verfp = &dreq->verf; #ifdef CONFIG_NFS_V4_1 if (ds_clp) { /* pNFS is in use, use the DS verf */ - if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets) - verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf; + if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets) + verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf; else WARN_ON_ONCE(1); } @@ -148,8 +148,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq, { struct nfs_writeverf *verfp; - verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, - hdr->ds_idx); + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); WARN_ON_ONCE(verfp->committed >= 0); memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); WARN_ON_ONCE(verfp->committed < 0); @@ -169,8 +168,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq, { struct nfs_writeverf *verfp; - verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, - hdr->ds_idx); + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); if (verfp->committed < 0) { nfs_direct_set_hdr_verf(dreq, hdr); return 0; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 2af32fc39d60..520cbc53e035 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -492,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) /* No multipath support. Use first DS */ atomic_inc(&ds->ds_clp->cl_count); hdr->ds_clp = ds->ds_clp; - hdr->ds_idx = idx; + hdr->ds_commit_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) hdr->args.fh = fh; @@ -536,7 +536,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->pgio_done_cb = filelayout_write_done_cb; atomic_inc(&ds->ds_clp->cl_count); hdr->ds_clp = ds->ds_clp; - hdr->ds_idx = idx; + hdr->ds_commit_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) hdr->args.fh = fh; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4fd7793d45d1..5bc99f04a550 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1328,7 +1328,7 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_idx; /* ds index if ds_clp is set */ + int ds_commit_idx; /* ds index if ds_clp is set */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From a7d42ddb3099727f58366fa006f850a219cce6c8 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 19 Sep 2014 10:55:07 -0400 Subject: nfs: add mirroring support to pgio layer This patch adds mirrored write support to the pgio layer. The default is to use one mirror, but pgio callers may define callbacks to change this to any value up to the (arbitrarily selected) limit of 16. The basic idea is to break out members of nfs_pageio_descriptor that cannot be shared between mirrored DSes and put them in a new structure. Signed-off-by: Weston Andros Adamson --- fs/nfs/direct.c | 17 ++- fs/nfs/internal.h | 1 + fs/nfs/objlayout/objio_osd.c | 3 +- fs/nfs/pagelist.c | 270 +++++++++++++++++++++++++++++++++++-------- fs/nfs/pnfs.c | 26 +++-- fs/nfs/read.c | 30 ++++- fs/nfs/write.c | 10 +- include/linux/nfs_page.h | 20 +++- include/linux/nfs_xdr.h | 1 + 9 files changed, 311 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1ee41d74c31c..0178d4fe8ab7 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -360,8 +360,14 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) spin_lock(&dreq->lock); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) dreq->error = hdr->error; - else - dreq->count += hdr->good_bytes; + else { + /* + * FIXME: right now this only accounts for bytes written + * to the first mirror + */ + if (hdr->pgio_mirror_idx == 0) + dreq->count += hdr->good_bytes; + } spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { @@ -724,7 +730,12 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) dreq->error = hdr->error; } if (dreq->error == 0) { - dreq->count += hdr->good_bytes; + /* + * FIXME: right now this only accounts for bytes written + * to the first mirror + */ + if (hdr->pgio_mirror_idx == 0) + dreq->count += hdr->good_bytes; if (nfs_write_need_commit(hdr)) { if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) request_commit = true; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 05f9a87cdab4..ef1c703e487b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -469,6 +469,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx); +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index d00778077df1..9a5f2ee6001f 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how) static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &pgio->pg_mirrors[pgio->pg_mirror_idx]; unsigned int size; size = pnfs_generic_pg_test(pgio, prev, req); - if (!size || pgio->pg_count + req->wb_bytes > + if (!size || mirror->pg_count + req->wb_bytes > (unsigned long)pgio->pg_layout_private) return 0; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1c031878c752..eec12b75c232 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -46,17 +46,22 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) { - hdr->req = nfs_list_entry(desc->pg_list.next); + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + hdr->req = nfs_list_entry(mirror->pg_list.next); hdr->inode = desc->pg_inode; hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); - hdr->good_bytes = desc->pg_count; + hdr->good_bytes = mirror->pg_count; hdr->dreq = desc->pg_dreq; hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) hdr->completion_ops->init_hdr(hdr); + + hdr->pgio_mirror_idx = desc->pg_mirror_idx; } EXPORT_SYMBOL_GPL(nfs_pgheader_init); @@ -480,7 +485,10 @@ nfs_wait_on_request(struct nfs_page *req) size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) { - if (desc->pg_count > desc->pg_bsize) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + if (mirror->pg_count > mirror->pg_bsize) { /* should never happen */ WARN_ON_ONCE(1); return 0; @@ -490,11 +498,11 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, * Limit the request size so that we can still allocate a page array * for it without upsetting the slab allocator. */ - if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) * + if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) * sizeof(struct page) > PAGE_SIZE) return 0; - return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes); + return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes); } EXPORT_SYMBOL_GPL(nfs_generic_pg_test); @@ -651,10 +659,18 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror; + u32 midx; + set_bit(NFS_IOHDR_REDO, &hdr->flags); nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + /* TODO: Make sure it's right to clean up all mirrors here + * and not just hdr->pgio_mirror_idx */ + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + } return -ENOMEM; } @@ -671,6 +687,17 @@ static void nfs_pgio_release(void *calldata) hdr->completion_ops->completion(hdr); } +static void nfs_pageio_mirror_init(struct nfs_pgio_mirror *mirror, + unsigned int bsize) +{ + INIT_LIST_HEAD(&mirror->pg_list); + mirror->pg_bytes_written = 0; + mirror->pg_count = 0; + mirror->pg_bsize = bsize; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; +} + /** * nfs_pageio_init - initialise a page io descriptor * @desc: pointer to descriptor @@ -687,13 +714,10 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, size_t bsize, int io_flags) { - INIT_LIST_HEAD(&desc->pg_list); - desc->pg_bytes_written = 0; - desc->pg_count = 0; - desc->pg_bsize = bsize; - desc->pg_base = 0; + struct nfs_pgio_mirror *new; + int i; + desc->pg_moreio = 0; - desc->pg_recoalesce = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; desc->pg_completion_ops = compl_ops; @@ -703,6 +727,26 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_lseg = NULL; desc->pg_dreq = NULL; desc->pg_layout_private = NULL; + desc->pg_bsize = bsize; + + desc->pg_mirror_count = 1; + desc->pg_mirror_idx = 0; + + if (pg_ops->pg_get_mirror_count) { + /* until we have a request, we don't have an lseg and no + * idea how many mirrors there will be */ + new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX, + sizeof(struct nfs_pgio_mirror), GFP_KERNEL); + desc->pg_mirrors_dynamic = new; + desc->pg_mirrors = new; + + for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++) + nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize); + } else { + desc->pg_mirrors_dynamic = NULL; + desc->pg_mirrors = desc->pg_mirrors_static; + nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); + } } EXPORT_SYMBOL_GPL(nfs_pageio_init); @@ -738,14 +782,16 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata) int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *req; struct page **pages, *last_page; - struct list_head *head = &desc->pg_list; + struct list_head *head = &mirror->pg_list; struct nfs_commit_info cinfo; unsigned int pagecount, pageused; - pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count); + pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); if (!nfs_pgarray_set(&hdr->page_array, pagecount)) return nfs_pgio_error(desc, hdr); @@ -773,7 +819,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_pgio_rpcsetup(hdr, desc->pg_count, 0, desc->pg_ioflags, &cinfo); + nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo); desc->pg_rpc_callops = &nfs_pgio_common_ops; return 0; } @@ -781,12 +827,17 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio); static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror; struct nfs_pgio_header *hdr; int ret; + mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + /* TODO: make sure this is right with mirroring - or + * should it back out all mirrors? */ + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); @@ -801,6 +852,49 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) return ret; } +/* + * nfs_pageio_setup_mirroring - determine if mirroring is to be used + * by calling the pg_get_mirror_count op + */ +static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + int mirror_count = 1; + + if (!pgio->pg_ops->pg_get_mirror_count) + return 0; + + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) + return -EINVAL; + + if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic)) + return -EINVAL; + + pgio->pg_mirror_count = mirror_count; + + return 0; +} + +/* + * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1) + */ +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; +} + +static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; + pgio->pg_mirrors = pgio->pg_mirrors_static; + kfree(pgio->pg_mirrors_dynamic); + pgio->pg_mirrors_dynamic = NULL; +} + static bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { @@ -867,19 +961,22 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *prev = NULL; - if (desc->pg_count != 0) { - prev = nfs_list_entry(desc->pg_list.prev); + + if (mirror->pg_count != 0) { + prev = nfs_list_entry(mirror->pg_list.prev); } else { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); - desc->pg_base = req->wb_pgbase; + mirror->pg_base = req->wb_pgbase; } if (!nfs_can_coalesce_requests(prev, req, desc)) return 0; nfs_list_remove_request(req); - nfs_list_add_request(req, &desc->pg_list); - desc->pg_count += req->wb_bytes; + nfs_list_add_request(req, &mirror->pg_list); + mirror->pg_count += req->wb_bytes; return 1; } @@ -888,16 +985,19 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, */ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { - if (!list_empty(&desc->pg_list)) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + if (!list_empty(&mirror->pg_list)) { int error = desc->pg_ops->pg_doio(desc); if (error < 0) desc->pg_error = error; else - desc->pg_bytes_written += desc->pg_count; + mirror->pg_bytes_written += mirror->pg_count; } - if (list_empty(&desc->pg_list)) { - desc->pg_count = 0; - desc->pg_base = 0; + if (list_empty(&mirror->pg_list)) { + mirror->pg_count = 0; + mirror->pg_base = 0; } } @@ -915,10 +1015,14 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *subreq; unsigned int bytes_left = 0; unsigned int offset, pgbase; + WARN_ON_ONCE(desc->pg_mirror_idx >= desc->pg_mirror_count); + nfs_page_group_lock(req, false); subreq = req; @@ -938,7 +1042,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_pageio_doio(desc); if (desc->pg_error < 0) return 0; - if (desc->pg_recoalesce) + if (mirror->pg_recoalesce) return 0; /* retry add_request for this subreq */ nfs_page_group_lock(req, false); @@ -976,14 +1080,16 @@ err_ptr: static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; LIST_HEAD(head); do { - list_splice_init(&desc->pg_list, &head); - desc->pg_bytes_written -= desc->pg_count; - desc->pg_count = 0; - desc->pg_base = 0; - desc->pg_recoalesce = 0; + list_splice_init(&mirror->pg_list, &head); + mirror->pg_bytes_written -= mirror->pg_count; + mirror->pg_count = 0; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; + desc->pg_moreio = 0; while (!list_empty(&head)) { @@ -997,11 +1103,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) return 0; break; } - } while (desc->pg_recoalesce); + } while (mirror->pg_recoalesce); return 1; } -int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, +static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { int ret; @@ -1014,9 +1120,78 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, break; ret = nfs_do_recoalesce(desc); } while (ret); + return ret; } +int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + u32 midx; + unsigned int pgbase, offset, bytes; + struct nfs_page *dupreq, *lastreq; + + pgbase = req->wb_pgbase; + offset = req->wb_offset; + bytes = req->wb_bytes; + + nfs_pageio_setup_mirroring(desc, req); + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + if (midx) { + nfs_page_group_lock(req, false); + + /* find the last request */ + for (lastreq = req->wb_head; + lastreq->wb_this_page != req->wb_head; + lastreq = lastreq->wb_this_page) + ; + + dupreq = nfs_create_request(req->wb_context, + req->wb_page, lastreq, pgbase, bytes); + + if (IS_ERR(dupreq)) { + nfs_page_group_unlock(req); + return 0; + } + + nfs_lock_request(dupreq); + nfs_page_group_unlock(req); + dupreq->wb_offset = offset; + dupreq->wb_index = req->wb_index; + } else + dupreq = req; + + desc->pg_mirror_idx = midx; + if (!nfs_pageio_add_request_mirror(desc, dupreq)) + return 0; + } + + return 1; +} + +/* + * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an + * nfs_pageio_descriptor + * @desc: pointer to io descriptor + */ +static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, + u32 mirror_idx) +{ + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; + u32 restore_idx = desc->pg_mirror_idx; + + desc->pg_mirror_idx = mirror_idx; + for (;;) { + nfs_pageio_doio(desc); + if (!mirror->pg_recoalesce) + break; + if (!nfs_do_recoalesce(desc)) + break; + } + desc->pg_mirror_idx = restore_idx; +} + /* * nfs_pageio_resend - Transfer requests to new descriptor and resend * @hdr - the pgio header to move request from @@ -1055,16 +1230,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_resend); */ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) { - for (;;) { - nfs_pageio_doio(desc); - if (!desc->pg_recoalesce) - break; - if (!nfs_do_recoalesce(desc)) - break; - } + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) + nfs_pageio_complete_mirror(desc, midx); if (desc->pg_ops->pg_cleanup) desc->pg_ops->pg_cleanup(desc); + nfs_pageio_cleanup_mirroring(desc); } /** @@ -1080,10 +1253,17 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) */ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) { - if (!list_empty(&desc->pg_list)) { - struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev); - if (index != prev->wb_index + 1) - nfs_pageio_complete(desc); + struct nfs_pgio_mirror *mirror; + struct nfs_page *prev; + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + if (!list_empty(&mirror->pg_list)) { + prev = nfs_list_entry(mirror->pg_list.prev); + if (index != prev->wb_index + 1) + nfs_pageio_complete_mirror(desc, midx); + } } } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 2da2e771fefe..5f7c422ebb5d 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1646,8 +1646,8 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup); * of bytes (maximum @req->wb_bytes) that can be coalesced. */ size_t -pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, - struct nfs_page *req) +pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req) { unsigned int size; u64 seg_end, req_start, seg_left; @@ -1729,10 +1729,12 @@ static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { - list_splice_tail_init(&hdr->pages, &desc->pg_list); + list_splice_tail_init(&hdr->pages, &mirror->pg_list); nfs_pageio_reset_write_mds(desc); - desc->pg_recoalesce = 1; + mirror->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); } @@ -1781,12 +1783,14 @@ EXPORT_SYMBOL_GPL(pnfs_writehdr_free); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); @@ -1795,6 +1799,7 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) ret = nfs_generic_pgio(desc, hdr); if (!ret) pnfs_do_write(desc, hdr, desc->pg_ioflags); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); @@ -1839,10 +1844,13 @@ static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { - list_splice_tail_init(&hdr->pages, &desc->pg_list); + list_splice_tail_init(&hdr->pages, &mirror->pg_list); nfs_pageio_reset_read_mds(desc); - desc->pg_recoalesce = 1; + mirror->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); } @@ -1893,12 +1901,14 @@ EXPORT_SYMBOL_GPL(pnfs_readhdr_free); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 092ab499f2b6..568ecf0a880f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -70,8 +70,15 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_read); void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { + struct nfs_pgio_mirror *mirror; + pgio->pg_ops = &nfs_pgio_rw_ops; - pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; + + /* read path should never have more than one mirror */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); @@ -81,6 +88,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, struct nfs_page *new; unsigned int len; struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; len = nfs_page_length(page); if (len == 0) @@ -97,7 +105,13 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); - NFS_I(inode)->read_io += pgio.pg_bytes_written; + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + return 0; } @@ -352,6 +366,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc = { .pgio = &pgio, }; @@ -387,10 +402,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&pgio); - NFS_I(inode)->read_io += pgio.pg_bytes_written; - npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2bee165fddcf..ceacfeeb28c2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -906,7 +906,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) if (nfs_write_need_commit(hdr)) { memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo, - 0); + hdr->pgio_mirror_idx); goto next; } remove_req: @@ -1304,8 +1304,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_write); void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { + struct nfs_pgio_mirror *mirror; + pgio->pg_ops = &nfs_pgio_rw_ops; - pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; + + nfs_pageio_stop_mirroring(pgio); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 479c566c4ddc..3eb072dbce83 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,8 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, + struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; @@ -74,15 +76,17 @@ struct nfs_rw_ops { struct rpc_task_setup *, int); }; -struct nfs_pageio_descriptor { +struct nfs_pgio_mirror { struct list_head pg_list; unsigned long pg_bytes_written; size_t pg_count; size_t pg_bsize; unsigned int pg_base; - unsigned char pg_moreio : 1, - pg_recoalesce : 1; + unsigned char pg_recoalesce : 1; +}; +struct nfs_pageio_descriptor { + unsigned char pg_moreio : 1; struct inode *pg_inode; const struct nfs_pageio_ops *pg_ops; const struct nfs_rw_ops *pg_rw_ops; @@ -93,8 +97,18 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_direct_req *pg_dreq; void *pg_layout_private; + unsigned int pg_bsize; /* default bsize for mirrors */ + + u32 pg_mirror_count; + struct nfs_pgio_mirror *pg_mirrors; + struct nfs_pgio_mirror pg_mirrors_static[1]; + struct nfs_pgio_mirror *pg_mirrors_dynamic; + u32 pg_mirror_idx; /* current mirror */ }; +/* arbitrarily selected limit to number of mirrors */ +#define NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX 16 + #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) extern struct nfs_page *nfs_create_request(struct nfs_open_context *ctx, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5bc99f04a550..6400a1e01aa4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1329,6 +1329,7 @@ struct nfs_pgio_header { struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_idx; /* ds index if ds_clp is set */ + int pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 15eb67c15342d212b0c8a540b6d6bd2dfad52a63 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 09:30:36 +0800 Subject: nfs41: add range to layoutreturn args So that callers can specify which range to return. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4xdr.c | 6 +++--- fs/nfs/pnfs.c | 4 +++- include/linux/nfs_xdr.h | 2 +- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3c3ff633dd17..56d4c91a48f3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2012,11 +2012,11 @@ encode_layoutreturn(struct xdr_stream *xdr, p = reserve_space(xdr, 16); *p++ = cpu_to_be32(0); /* reclaim. always 0 for now */ *p++ = cpu_to_be32(args->layout_type); - *p++ = cpu_to_be32(args->iomode); + *p++ = cpu_to_be32(args->range.iomode); *p = cpu_to_be32(RETURN_FILE); p = reserve_space(xdr, 16); - p = xdr_encode_hyper(p, 0); - p = xdr_encode_hyper(p, NFS4_MAX_UINT64); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); spin_lock(&args->inode->i_lock); encode_nfs4_stateid(xdr, &args->stateid); spin_unlock(&args->inode->i_lock); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 685af4fb39ca..9549b89e494b 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -916,7 +916,9 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, lrp->args.stateid = stateid; lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; - lrp->args.iomode = iomode; + lrp->args.range.iomode = iomode; + lrp->args.range.offset = 0; + lrp->args.range.length = NFS4_MAX_UINT64; lrp->args.layout = lo; lrp->clp = NFS_SERVER(ino)->nfs_client; lrp->cred = lo->plh_lc_cred; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6400a1e01aa4..363792356d25 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,7 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; - enum pnfs_iomode iomode; + struct pnfs_layout_range range; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From d67ae825a59d639e4d8b82413af84d854617a87e Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Thu, 11 Dec 2014 17:02:04 -0500 Subject: pnfs/flexfiles: Add the FlexFile Layout Driver The flexfile layout is a new layout that extends the file layout. It is currently being drafted as a specification at https://datatracker.ietf.org/doc/draft-ietf-nfsv4-layout-types/ Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes Signed-off-by: Tao Peng --- fs/nfs/Kconfig | 5 + fs/nfs/Makefile | 1 + fs/nfs/flexfilelayout/Makefile | 5 + fs/nfs/flexfilelayout/flexfilelayout.c | 1574 +++++++++++++++++++++++++++++ fs/nfs/flexfilelayout/flexfilelayout.h | 155 +++ fs/nfs/flexfilelayout/flexfilelayoutdev.c | 552 ++++++++++ fs/nfs/idmap.c | 3 +- fs/nfs/nfs4proc.c | 4 +- fs/nfs/pnfs.c | 32 +- fs/nfs/pnfs.h | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_idmap.h | 2 + include/linux/sunrpc/metrics.h | 2 + 13 files changed, 2325 insertions(+), 12 deletions(-) create mode 100644 fs/nfs/flexfilelayout/Makefile create mode 100644 fs/nfs/flexfilelayout/flexfilelayout.c create mode 100644 fs/nfs/flexfilelayout/flexfilelayout.h create mode 100644 fs/nfs/flexfilelayout/flexfilelayoutdev.c (limited to 'include/linux') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 3dece03f2fc8..c7abc10279af 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT depends on NFS_V4_1 && SCSI_OSD_ULD default NFS_V4 +config PNFS_FLEXFILE_LAYOUT + tristate + depends on NFS_V4_1 && NFS_V3 + default m + config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN string "NFSv4.1 Implementation ID Domain" depends on NFS_V4_1 diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 23abffa8a4ce..1e987acf20c9 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -33,3 +33,4 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile new file mode 100644 index 000000000000..1d2c9f6bbcd4 --- /dev/null +++ b/fs/nfs/flexfilelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Flexfile Layout Driver kernel module +# +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o +nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c new file mode 100644 index 000000000000..f29fb7d7e8f8 --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -0,0 +1,1574 @@ +/* + * Module for pnfs flexfile layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#include +#include +#include + +#include +#include + +#include "flexfilelayout.h" +#include "../nfs4session.h" +#include "../internal.h" +#include "../delegation.h" +#include "../nfs4trace.h" +#include "../iostat.h" +#include "../nfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) + +static struct pnfs_layout_hdr * +ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct nfs4_flexfile_layout *ffl; + + ffl = kzalloc(sizeof(*ffl), gfp_flags); + if (ffl) { + INIT_LIST_HEAD(&ffl->error_list); + return &ffl->generic_hdr; + } else + return NULL; +} + +static void +ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct nfs4_ff_layout_ds_err *err, *n; + + list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list, + list) { + list_del(&err->list); + kfree(err); + } + kfree(FF_LAYOUT_FROM_HDR(lo)); +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE); + if (unlikely(p == NULL)) + return -ENOBUFS; + memcpy(stateid, p, NFS4_STATEID_SIZE); + dprintk("%s: stateid id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); + return 0; +} + +static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(devid, p, NFS4_DEVICEID4_SIZE); + nfs4_print_deviceid(devid); + return 0; +} + +static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + fh->size = be32_to_cpup(p++); + if (fh->size > sizeof(struct nfs_fh)) { + printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n", + fh->size); + return -EOVERFLOW; + } + /* fh.data */ + p = xdr_inline_decode(xdr, fh->size); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(&fh->data, p, fh->size); + dprintk("%s: fh len %d\n", __func__, fh->size); + + return 0; +} + +/* + * Currently only stringified uids and gids are accepted. + * I.e., kerberos is not supported to the DSes, so no pricipals. + * + * That means that one common function will suffice, but when + * principals are added, this should be split to accomodate + * calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid(). + */ +static int +decode_name(struct xdr_stream *xdr, u32 *id) +{ + __be32 *p; + int len; + + /* opaque_length(4)*/ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + len = be32_to_cpup(p++); + if (len < 0) + return -EINVAL; + + dprintk("%s: len %u\n", __func__, len); + + /* opaque body */ + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return -ENOBUFS; + + if (!nfs_map_string_to_numeric((char *)p, len, id)) + return -EINVAL; + + return 0; +} + +static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls) +{ + int i; + + if (fls->mirror_array) { + for (i = 0; i < fls->mirror_array_cnt; i++) { + /* normally mirror_ds is freed in + * .free_deviceid_node but we still do it here + * for .alloc_lseg error path */ + if (fls->mirror_array[i]) { + kfree(fls->mirror_array[i]->fh_versions); + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + kfree(fls->mirror_array[i]); + } + } + kfree(fls->mirror_array); + fls->mirror_array = NULL; + } +} + +static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr) +{ + int ret = 0; + + dprintk("--> %s\n", __func__); + + /* FIXME: remove this check when layout segment support is added */ + if (lgr->range.offset != 0 || + lgr->range.length != NFS4_MAX_UINT64) { + dprintk("%s Only whole file layouts supported. Use MDS i/o\n", + __func__); + ret = -EINVAL; + } + + dprintk("--> %s returns %d\n", __func__, ret); + return ret; +} + +static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls) +{ + if (fls) { + ff_layout_free_mirror_array(fls); + kfree(fls); + } +} + +static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls) +{ + struct nfs4_ff_layout_mirror *tmp; + int i, j; + + for (i = 0; i < fls->mirror_array_cnt - 1; i++) { + for (j = i + 1; j < fls->mirror_array_cnt; j++) + if (fls->mirror_array[i]->efficiency < + fls->mirror_array[j]->efficiency) { + tmp = fls->mirror_array[i]; + fls->mirror_array[i] = fls->mirror_array[j]; + fls->mirror_array[j] = tmp; + } + } +} + +static struct pnfs_layout_segment * +ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + struct pnfs_layout_segment *ret; + struct nfs4_ff_layout_segment *fls = NULL; + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + u64 stripe_unit; + u32 mirror_array_cnt; + __be32 *p; + int i, rc; + + dprintk("--> %s\n", __func__); + scratch = alloc_page(gfp_flags); + if (!scratch) + return ERR_PTR(-ENOMEM); + + xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, + lgr->layoutp->len); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* stripe unit and mirror_array_cnt */ + rc = -EIO; + p = xdr_inline_decode(&stream, 8 + 4); + if (!p) + goto out_err_free; + + p = xdr_decode_hyper(p, &stripe_unit); + mirror_array_cnt = be32_to_cpup(p++); + dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__, + stripe_unit, mirror_array_cnt); + + if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT || + mirror_array_cnt == 0) + goto out_err_free; + + rc = -ENOMEM; + fls = kzalloc(sizeof(*fls), gfp_flags); + if (!fls) + goto out_err_free; + + fls->mirror_array_cnt = mirror_array_cnt; + fls->stripe_unit = stripe_unit; + fls->mirror_array = kcalloc(fls->mirror_array_cnt, + sizeof(fls->mirror_array[0]), gfp_flags); + if (fls->mirror_array == NULL) + goto out_err_free; + + for (i = 0; i < fls->mirror_array_cnt; i++) { + struct nfs4_deviceid devid; + struct nfs4_deviceid_node *idnode; + u32 ds_count; + u32 fh_count; + int j; + + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + ds_count = be32_to_cpup(p); + + /* FIXME: allow for striping? */ + if (ds_count != 1) + goto out_err_free; + + fls->mirror_array[i] = + kzalloc(sizeof(struct nfs4_ff_layout_mirror), + gfp_flags); + if (fls->mirror_array[i] == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + spin_lock_init(&fls->mirror_array[i]->lock); + fls->mirror_array[i]->ds_count = ds_count; + + /* deviceid */ + rc = decode_deviceid(&stream, &devid); + if (rc) + goto out_err_free; + + idnode = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode), + &devid, lh->plh_lc_cred, + gfp_flags); + /* + * upon success, mirror_ds is allocated by previous + * getdeviceinfo, or newly by .alloc_deviceid_node + * nfs4_find_get_deviceid failure is indeed getdeviceinfo falure + */ + if (idnode) + fls->mirror_array[i]->mirror_ds = + FF_LAYOUT_MIRROR_DS(idnode); + else + goto out_err_free; + + /* efficiency */ + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fls->mirror_array[i]->efficiency = be32_to_cpup(p); + + /* stateid */ + rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid); + if (rc) + goto out_err_free; + + /* fh */ + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fh_count = be32_to_cpup(p); + + fls->mirror_array[i]->fh_versions = + kzalloc(fh_count * sizeof(struct nfs_fh), + gfp_flags); + if (fls->mirror_array[i]->fh_versions == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + for (j = 0; j < fh_count; j++) { + rc = decode_nfs_fh(&stream, + &fls->mirror_array[i]->fh_versions[j]); + if (rc) + goto out_err_free; + } + + fls->mirror_array[i]->fh_versions_cnt = fh_count; + + /* user */ + rc = decode_name(&stream, &fls->mirror_array[i]->uid); + if (rc) + goto out_err_free; + + /* group */ + rc = decode_name(&stream, &fls->mirror_array[i]->gid); + if (rc) + goto out_err_free; + + dprintk("%s: uid %d gid %d\n", __func__, + fls->mirror_array[i]->uid, + fls->mirror_array[i]->gid); + } + + ff_layout_sort_mirrors(fls); + rc = ff_layout_check_layout(lgr); + if (rc) + goto out_err_free; + + ret = &fls->generic_hdr; + dprintk("<-- %s (success)\n", __func__); +out_free_page: + __free_page(scratch); + return ret; +out_err_free: + _ff_layout_free_lseg(fls); + ret = ERR_PTR(rc); + dprintk("<-- %s (%d)\n", __func__, rc); + goto out_free_page; +} + +static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &layout->plh_segs, pls_list) + if (lseg->pls_range.iomode == IOMODE_RW) + return true; + + return false; +} + +static void +ff_layout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + int i; + + dprintk("--> %s\n", __func__); + + for (i = 0; i < fls->mirror_array_cnt; i++) { + if (fls->mirror_array[i]) { + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + fls->mirror_array[i]->mirror_ds = NULL; + if (fls->mirror_array[i]->cred) { + put_rpccred(fls->mirror_array[i]->cred); + fls->mirror_array[i]->cred = NULL; + } + } + } + + if (lseg->pls_range.iomode == IOMODE_RW) { + struct nfs4_flexfile_layout *ffl; + struct inode *inode; + + ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout); + inode = ffl->generic_hdr.plh_inode; + spin_lock(&inode->i_lock); + if (!ff_layout_has_rw_segments(lseg->pls_layout)) { + ffl->commit_info.nbuckets = 0; + kfree(ffl->commit_info.buckets); + ffl->commit_info.buckets = NULL; + } + spin_unlock(&inode->i_lock); + } + _ff_layout_free_lseg(fls); +} + +/* Return 1 until we have multiple lsegs support */ +static int +ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls) +{ + return 1; +} + +static int +ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + struct pnfs_commit_bucket *buckets; + int size; + + if (cinfo->ds->nbuckets != 0) { + /* This assumes there is only one RW lseg per file. + * To support multiple lseg per file, we need to + * change struct pnfs_commit_bucket to allow dynamic + * increasing nbuckets. + */ + return 0; + } + + size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg); + + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), + gfp_flags); + if (!buckets) + return -ENOMEM; + else { + int i; + + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) + kfree(buckets); + else { + cinfo->ds->buckets = buckets; + cinfo->ds->nbuckets = size; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + /* mark direct verifier as unset */ + buckets[i].direct_verf.committed = + NFS_INVALID_STABLE_HOW; + } + } + spin_unlock(cinfo->lock); + return 0; + } +} + +static struct nfs4_pnfs_ds * +ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio, + int *best_idx) +{ + struct nfs4_ff_layout_segment *fls; + struct nfs4_pnfs_ds *ds; + int idx; + + fls = FF_LAYOUT_LSEG(pgio->pg_lseg); + /* mirrors are sorted by efficiency */ + for (idx = 0; idx < fls->mirror_array_cnt; idx++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false); + if (ds) { + *best_idx = idx; + return ds; + } + } + + return NULL; +} + +static void +ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs_pgio_mirror *pgm; + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_pnfs_ds *ds; + int ds_idx; + + /* Use full layout for now */ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_READ, + GFP_KERNEL); + /* If no lseg, fall back to read through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx); + if (!ds) + goto out_mds; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + + pgio->pg_mirror_idx = ds_idx; + + /* read always uses only one mirror - idx 0 for pgio layer */ + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + + return; +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_read_mds(pgio); +} + +static void +ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs_pgio_mirror *pgm; + struct nfs_commit_info cinfo; + struct nfs4_pnfs_ds *ds; + int i; + int status; + + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + /* If no lseg, fall back to write through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); + if (status < 0) + goto out_mds; + + /* Use a direct mapping of ds_idx to pgio mirror_idx */ + if (WARN_ON_ONCE(pgio->pg_mirror_count != + FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) + goto out_mds; + + for (i = 0; i < pgio->pg_mirror_count; i++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true); + if (!ds) + goto out_mds; + pgm = &pgio->pg_mirrors[i]; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize; + } + + return; + +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); +} + +static unsigned int +ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + if (pgio->pg_lseg) + return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg); + + /* no lseg means that pnfs is not in use, so no mirroring here */ + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); + return 1; +} + +static const struct nfs_pageio_ops ff_layout_pg_read_ops = { + .pg_init = ff_layout_pg_init_read, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops ff_layout_pg_write_ops = { + .pg_init = ff_layout_pg_init_write, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_writepages, + .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (retry_pnfs) { + dprintk("%s Reset task %5u for i/o through pNFS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + if (!hdr->dreq) { + struct nfs_open_context *ctx; + + ctx = nfs_list_entry(hdr->pages.next)->wb_context; + set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); + hdr->completion_ops->error_cleanup(&hdr->pages); + } else { + nfs_direct_set_resched_writes(hdr->dreq); + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = 0; + } + return; + } + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_write_done_resend_to_mds(hdr); + } +} + +static void ff_layout_reset_read(struct nfs_pgio_header *hdr) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_read_done_resend_to_mds(hdr); + } +} + +static int ff_layout_async_handle_error_v4(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct pnfs_layout_hdr *lo = lseg->pls_layout; + struct inode *inode = lo->plh_inode; + struct nfs_server *mds_server = NFS_SERVER(inode); + + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + struct nfs_client *mds_client = mds_server->nfs_client; + struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; + + if (task->tk_status >= 0) + return 0; + + switch (task->tk_status) { + /* MDS state errors */ + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + if (state == NULL) + break; + nfs_remove_bad_delegation(state->inode); + case -NFS4ERR_OPENMODE: + if (state == NULL) + break; + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + } + nfs4_schedule_lease_recovery(mds_client); + goto wait_on_recovery; + /* DS session errors */ + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR %d, Reset session. Exchangeid " + "flags 0x%x\n", __func__, task->tk_status, + clp->cl_exchange_flags); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + break; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX); + break; + case -NFS4ERR_RETRY_UNCACHED_REP: + break; + /* Invalidate Layout errors */ + case -NFS4ERR_PNFS_NO_LAYOUT: + case -ESTALE: /* mapped NFS4ERR_STALE */ + case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ + case -EISDIR: /* mapped NFS4ERR_ISDIR */ + case -NFS4ERR_FHEXPIRED: + case -NFS4ERR_WRONG_TYPE: + dprintk("%s Invalid layout error %d\n", __func__, + task->tk_status); + /* + * Destroy layout so new i/o will get a new layout. + * Layout will not be destroyed until all current lseg + * references are put. Mark layout as invalid to resend failed + * i/o and all i/o waiting on the slot table to the MDS until + * layout is destroyed and a new valid layout is obtained. + */ + pnfs_destroy_layout(NFS_I(inode)); + rpc_wake_up(&tbl->slot_tbl_waitq); + goto reset; + /* RPC connection errors */ + case -ECONNREFUSED: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EIO: + case -ETIMEDOUT: + case -EPIPE: + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + rpc_wake_up(&tbl->slot_tbl_waitq); + /* fall through */ + default: + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + } +out: + task->tk_status = 0; + return -EAGAIN; +out_bad_stateid: + task->tk_status = -EIO; + return 0; +wait_on_recovery: + rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) + rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); + goto out; +} + +/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ +static int ff_layout_async_handle_error_v3(struct rpc_task *task, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + + if (task->tk_status >= 0) + return 0; + + if (task->tk_status != -EJUKEBOX) { + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; + else + return -NFS4ERR_RESET_TO_MDS; + } + + if (task->tk_status == -EJUKEBOX) + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + task->tk_status = 0; + rpc_restart_call(task); + rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); + return -EAGAIN; +} + +static int ff_layout_async_handle_error(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + int vers = clp->cl_nfs_mod->rpc_vers->number; + + switch (vers) { + case 3: + return ff_layout_async_handle_error_v3(task, lseg, idx); + case 4: + return ff_layout_async_handle_error_v4(task, state, clp, + lseg, idx); + default: + /* should never happen */ + WARN_ON_ONCE(1); + return 0; + } +} + +static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, + int idx, u64 offset, u64 length, + u32 status, int opnum) +{ + struct nfs4_ff_layout_mirror *mirror; + int err; + + mirror = FF_LAYOUT_COMP(lseg, idx); + err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, offset, length, status, opnum, + GFP_NOIO); + dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status); +} + +/* NFS_PROTO call done callback routines */ + +static int ff_layout_read_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_read(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_READ); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &hdr->lseg->pls_layout->plh_flags); + pnfs_read_resend_pnfs(hdr); + return task->tk_status; + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + ff_layout_reset_read(hdr); + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + return 0; +} + +/* + * We reference the rpc_cred of the first WRITE that triggers the need for + * a LAYOUTCOMMIT, and use it to send the layoutcommit compound. + * rfc5661 is not clear about which credential should be used. + * + * Flexlayout client should treat DS replied FILE_SYNC as DATA_SYNC, so + * to follow http://www.rfc-editor.org/errata_search.php?rfc=5661&eid=2751 + * we always send layoutcommit after DS writes. + */ +static void +ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr) +{ + pnfs_set_layoutcommit(hdr); + dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); +} + +static bool +ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) +{ + /* No mirroring for now */ + struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx); + + return ff_layout_test_devid_unavailable(node); +} + +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + if (ff_layout_has_available_ds(hdr->lseg)) + pnfs_read_resend_pnfs(hdr); + else + ff_layout_reset_read(hdr); + rpc_exit(task, 0); + return -EAGAIN; + } + hdr->pgio_done_cb = ff_layout_read_done_cb; + + return 0; +} + +/* + * Call ops for the async read/write cases + * In the case of dense layouts, the offset needs to be reset to its + * original value. + */ +static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static int ff_layout_setup_sequence(struct nfs_client *ds_clp, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + if (ds_clp->cl_session) + return nfs41_setup_sequence(ds_clp->cl_session, + args, + res, + task); + return nfs40_setup_sequence(ds_clp->cl_slot_tbl, + args, + res, + task); +} + +static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_read_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_read_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); +} + +static int ff_layout_write_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_write(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_WRITE); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) { + pnfs_set_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, true); + } else { + pnfs_clear_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, false); + } + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (hdr->res.verf->committed == NFS_FILE_SYNC || + hdr->res.verf->committed == NFS_DATA_SYNC) + ff_layout_set_layoutcommit(hdr); + + return 0; +} + +static int ff_layout_commit_done_cb(struct rpc_task *task, + struct nfs_commit_data *data) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_commit_ds(data, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !data->res.op_status) + data->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && data->res.op_status) + ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index, + data->args.offset, data->args.count, + data->res.op_status, OP_COMMIT); + err = ff_layout_async_handle_error(task, NULL, data->ds_clp, + data->lseg, data->ds_commit_index); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = data->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, data->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) + pnfs_set_retry_layoutget(data->lseg->pls_layout); + else + pnfs_clear_retry_layoutget(data->lseg->pls_layout); + pnfs_generic_prepare_to_resend_writes(data); + return -EAGAIN; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (data->verf.committed == NFS_UNSTABLE) + pnfs_commit_set_layoutcommit(data); + + return 0; +} + +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + bool retry_pnfs; + + retry_pnfs = ff_layout_has_available_ds(hdr->lseg); + dprintk("%s task %u reset io to %s\n", __func__, + task->tk_pid, retry_pnfs ? "pNFS" : "MDS"); + ff_layout_reset_write(hdr, retry_pnfs); + rpc_exit(task, 0); + return -EAGAIN; + } + + return 0; +} + +static void ff_layout_write_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_write_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_write_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); +} + +static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) +{ + rpc_call_start(task); +} + +static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + ff_layout_setup_sequence(wdata->ds_clp, + &wdata->args.seq_args, + &wdata->res.seq_res, + task); +} + +static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *cdata = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); +} + +static const struct rpc_call_ops ff_layout_read_call_ops_v3 = { + .rpc_call_prepare = ff_layout_read_prepare_v3, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_read_call_ops_v4 = { + .rpc_call_prepare = ff_layout_read_prepare_v4, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v3 = { + .rpc_call_prepare = ff_layout_write_prepare_v3, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v4 = { + .rpc_call_prepare = ff_layout_write_prepare_v4, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = { + .rpc_call_prepare = ff_layout_commit_prepare_v3, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = { + .rpc_call_prepare = ff_layout_commit_prepare_v4, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static enum pnfs_try_status +ff_layout_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + u32 idx = hdr->pgio_mirror_idx; + int vers; + struct nfs_fh *fh; + + dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + __func__, hdr->inode->i_ino, + hdr->args.pgbase, (size_t)hdr->args.count, offset); + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); + if (!ds) + goto out_failed; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + goto out_failed; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + goto out_failed; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__, + ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers); + + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + hdr->mds_offset = offset; + + /* Perform an asynchronous read to ds */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_read_call_ops_v3 : + &ff_layout_read_call_ops_v4, + 0, RPC_TASK_SOFTCONN); + + return PNFS_ATTEMPTED; + +out_failed: + if (ff_layout_has_available_ds(lseg)) + return PNFS_TRY_AGAIN; + return PNFS_NOT_ATTEMPTED; +} + +/* Perform async writes. */ +static enum pnfs_try_status +ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + int vers; + struct nfs_fh *fh; + int idx = hdr->pgio_mirror_idx; + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + return PNFS_NOT_ATTEMPTED; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n", + __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, + offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), + vers); + + hdr->pgio_done_cb = ff_layout_write_done_cb; + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + hdr->ds_commit_idx = idx; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + + /* Perform an asynchronous write */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_write_call_ops_v3 : + &ff_layout_write_call_ops_v4, + sync, RPC_TASK_SOFTCONN); + return PNFS_ATTEMPTED; +} + +static void +ff_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) +{ + struct list_head *list; + struct pnfs_commit_bucket *buckets; + + spin_lock(cinfo->lock); + buckets = cinfo->ds->buckets; + list = &buckets[ds_commit_idx].written; + if (list_empty(list)) { + /* Non-empty buckets hold a reference on the lseg. That ref + * is normally transferred to the COMMIT call and released + * there. It could also be released if the last req is pulled + * off due to a rewrite, in which case it will be done in + * pnfs_common_clear_request_commit + */ + WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL); + buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg); + } + set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; + + /* nfs_request_add_commit_list(). We need to add req to list without + * dropping cinfo lock. + */ + set_bit(PG_CLEAN, &(req)->wb_flags); + nfs_list_add_request(req, list); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); + if (!cinfo->dreq) { + inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); + inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, + BDI_RECLAIMABLE); + __mark_inode_dirty(req->wb_context->dentry->d_inode, + I_DIRTY_DATASYNC); + } +} + +static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + return i; +} + +static struct nfs_fh * +select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg); + + /* FIXME: Assume that there is only one NFS version available + * for the DS. + */ + return &flseg->mirror_array[i]->fh_versions[0]; +} + +static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) +{ + struct pnfs_layout_segment *lseg = data->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + u32 idx; + int vers; + struct nfs_fh *fh; + + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + goto out_err; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + data->inode); + if (IS_ERR(ds_clnt)) + goto out_err; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred); + if (IS_ERR(ds_cred)) + goto out_err; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__, + data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count), + vers); + data->commit_done_cb = ff_layout_commit_done_cb; + data->cred = ds_cred; + atomic_inc(&ds->ds_clp->cl_count); + data->ds_clp = ds->ds_clp; + fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); + if (fh) + data->args.fh = fh; + return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_commit_call_ops_v3 : + &ff_layout_commit_call_ops_v4, + how, RPC_TASK_SOFTCONN); +out_err: + pnfs_generic_prepare_to_resend_writes(data); + pnfs_generic_commit_release(data); + return -EAGAIN; +} + +static int +ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo) +{ + return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo, + ff_layout_initiate_commit); +} + +static struct pnfs_ds_commit_info * +ff_layout_get_ds_info(struct inode *inode) +{ + struct pnfs_layout_hdr *layout = NFS_I(inode)->layout; + + if (layout == NULL) + return NULL; + + return &FF_LAYOUT_FROM_HDR(layout)->commit_info; +} + +static void +ff_layout_free_deveiceid_node(struct nfs4_deviceid_node *d) +{ + nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds, + id_node)); +} + +static int ff_layout_encode_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct pnfs_layout_hdr *hdr = &flo->generic_hdr; + __be32 *start; + int count = 0, ret = 0; + + start = xdr_reserve_space(xdr, 4); + if (unlikely(!start)) + return -E2BIG; + + /* This assume we always return _ALL_ layouts */ + spin_lock(&hdr->plh_inode->i_lock); + ret = ff_layout_encode_ds_ioerr(flo, xdr, &count, &args->range); + spin_unlock(&hdr->plh_inode->i_lock); + + *start = cpu_to_be32(count); + + return ret; +} + +/* report nothing for now */ +static void ff_layout_encode_iostats(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + if (likely(p)) + *p = cpu_to_be32(0); +} + +static struct nfs4_deviceid_node * +ff_layout_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds *dsaddr; + + dsaddr = nfs4_ff_alloc_deviceid_node(server, pdev, gfp_flags); + if (!dsaddr) + return NULL; + return &dsaddr->id_node; +} + +static void +ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo); + __be32 *start; + + dprintk("%s: Begin\n", __func__); + start = xdr_reserve_space(xdr, 4); + BUG_ON(!start); + + if (ff_layout_encode_ioerr(flo, xdr, args)) + goto out; + + ff_layout_encode_iostats(flo, xdr, args); +out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); + dprintk("%s: Return\n", __func__); +} + +static struct pnfs_layoutdriver_type flexfilelayout_type = { + .id = LAYOUT_FLEX_FILES, + .name = "LAYOUT_FLEX_FILES", + .owner = THIS_MODULE, + .alloc_layout_hdr = ff_layout_alloc_layout_hdr, + .free_layout_hdr = ff_layout_free_layout_hdr, + .alloc_lseg = ff_layout_alloc_lseg, + .free_lseg = ff_layout_free_lseg, + .pg_read_ops = &ff_layout_pg_read_ops, + .pg_write_ops = &ff_layout_pg_write_ops, + .get_ds_info = ff_layout_get_ds_info, + .free_deviceid_node = ff_layout_free_deveiceid_node, + .mark_request_commit = ff_layout_mark_request_commit, + .clear_request_commit = pnfs_generic_clear_request_commit, + .scan_commit_lists = pnfs_generic_scan_commit_lists, + .recover_commit_reqs = pnfs_generic_recover_commit_reqs, + .commit_pagelist = ff_layout_commit_pagelist, + .read_pagelist = ff_layout_read_pagelist, + .write_pagelist = ff_layout_write_pagelist, + .alloc_deviceid_node = ff_layout_alloc_deviceid_node, + .encode_layoutreturn = ff_layout_encode_layoutreturn, +}; + +static int __init nfs4flexfilelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&flexfilelayout_type); +} + +static void __exit nfs4flexfilelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&flexfilelayout_type); +} + +MODULE_ALIAS("nfs-layouttype4-4"); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("The NFSv4 flexfile layout driver"); + +module_init(nfs4flexfilelayout_init); +module_exit(nfs4flexfilelayout_exit); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h new file mode 100644 index 000000000000..070f20445b2d --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -0,0 +1,155 @@ +/* + * NFSv4 flexfile layout driver data structures. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H +#define FS_NFS_NFS4FLEXFILELAYOUT_H + +#include "../pnfs.h" + +/* XXX: Let's filter out insanely large mirror count for now to avoid oom + * due to network error etc. */ +#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096 + +struct nfs4_ff_ds_version { + u32 version; + u32 minor_version; + u32 rsize; + u32 wsize; + bool tightly_coupled; +}; + +/* chained in global deviceid hlist */ +struct nfs4_ff_layout_ds { + struct nfs4_deviceid_node id_node; + u32 ds_versions_cnt; + struct nfs4_ff_ds_version *ds_versions; + struct nfs4_pnfs_ds *ds; +}; + +struct nfs4_ff_layout_ds_err { + struct list_head list; /* linked in mirror error_list */ + u64 offset; + u64 length; + int status; + enum nfs_opnum4 opnum; + nfs4_stateid stateid; + struct nfs4_deviceid deviceid; +}; + +struct nfs4_ff_layout_mirror { + u32 ds_count; + u32 efficiency; + struct nfs4_ff_layout_ds *mirror_ds; + u32 fh_versions_cnt; + struct nfs_fh *fh_versions; + nfs4_stateid stateid; + struct nfs4_string user_name; + struct nfs4_string group_name; + u32 uid; + u32 gid; + struct rpc_cred *cred; + spinlock_t lock; +}; + +struct nfs4_ff_layout_segment { + struct pnfs_layout_segment generic_hdr; + u64 stripe_unit; + u32 mirror_array_cnt; + struct nfs4_ff_layout_mirror **mirror_array; +}; + +struct nfs4_flexfile_layout { + struct pnfs_layout_hdr generic_hdr; + struct pnfs_ds_commit_info commit_info; + struct list_head error_list; /* nfs4_ff_layout_ds_err */ +}; + +static inline struct nfs4_flexfile_layout * +FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct nfs4_flexfile_layout, generic_hdr); +} + +static inline struct nfs4_ff_layout_segment * +FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_ff_layout_segment, + generic_hdr); +} + +static inline struct nfs4_deviceid_node * +FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL) + return NULL; + return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node; +} + +static inline struct nfs4_ff_layout_ds * +FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node) +{ + return container_of(node, struct nfs4_ff_layout_ds, id_node); +} + +static inline struct nfs4_ff_layout_mirror * +FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt) + return NULL; + return FF_LAYOUT_LSEG(lseg)->mirror_array[idx]; +} + +static inline u32 +FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg) +{ + return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt; +} + +static inline bool +ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) +{ + return nfs4_test_deviceid_unavailable(node); +} + +static inline int +nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx) +{ + return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version; +} + +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags); +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags); +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range); +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx); + +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return); + +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, + u32 ds_idx, + struct nfs_client *ds_clp, + struct inode *inode); +struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, + u32 ds_idx, struct rpc_cred *mdscred); +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); +#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */ diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c new file mode 100644 index 000000000000..3bbb16b3066f --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -0,0 +1,552 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#include +#include +#include +#include + +#include "../internal.h" +#include "../nfs4session.h" +#include "flexfilelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; +static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; + +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + if (mirror_ds) + nfs4_put_deviceid_node(&mirror_ds->id_node); +} + +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + nfs4_print_deviceid(&mirror_ds->id_node.deviceid); + nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds); +} + +/* Decode opaque device data and construct new_ds using it */ +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags) +{ + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + struct list_head dsaddrs; + struct nfs4_pnfs_ds_addr *da; + struct nfs4_ff_layout_ds *new_ds = NULL; + struct nfs4_ff_ds_version *ds_versions = NULL; + u32 mp_count; + u32 version_count; + __be32 *p; + int i, ret = -ENOMEM; + + /* set up xdr stream */ + scratch = alloc_page(gfp_flags); + if (!scratch) + goto out_err; + + new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags); + if (!new_ds) + goto out_scratch; + + nfs4_init_deviceid_node(&new_ds->id_node, + server, + &pdev->dev_id); + INIT_LIST_HEAD(&dsaddrs); + + xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* multipath count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + mp_count = be32_to_cpup(p); + dprintk("%s: multipath ds count %d\n", __func__, mp_count); + + for (i = 0; i < mp_count; i++) { + /* multipath ds */ + da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, + &stream, gfp_flags); + if (da) + list_add_tail(&da->da_node, &dsaddrs); + } + if (list_empty(&dsaddrs)) { + dprintk("%s: no suitable DS addresses found\n", + __func__); + ret = -ENOMEDIUM; + goto out_err_drain_dsaddrs; + } + + /* version count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + version_count = be32_to_cpup(p); + dprintk("%s: version count %d\n", __func__, version_count); + + ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version), + gfp_flags); + if (!ds_versions) + goto out_scratch; + + for (i = 0; i < version_count; i++) { + /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + + * tightly_coupled(4) */ + p = xdr_inline_decode(&stream, 20); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + ds_versions[i].version = be32_to_cpup(p++); + ds_versions[i].minor_version = be32_to_cpup(p++); + ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].tightly_coupled = be32_to_cpup(p); + + if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE; + if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE; + + if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) { + dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__, + i, ds_versions[i].version, + ds_versions[i].minor_version); + ret = -EPROTONOSUPPORT; + goto out_err_drain_dsaddrs; + } + + dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n", + __func__, i, ds_versions[i].version, + ds_versions[i].minor_version, + ds_versions[i].rsize, + ds_versions[i].wsize, + ds_versions[i].tightly_coupled); + } + + new_ds->ds_versions = ds_versions; + new_ds->ds_versions_cnt = version_count; + + new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + if (!new_ds->ds) + goto out_err_drain_dsaddrs; + + /* If DS was already in cache, free ds addrs */ + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + __free_page(scratch); + return new_ds; + +out_err_drain_dsaddrs: + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + kfree(ds_versions); +out_scratch: + __free_page(scratch); +out_err: + kfree(new_ds); + + dprintk("%s ERROR: returning %d\n", __func__, ret); + return NULL; +} + +static u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end : NFS4_MAX_UINT64; +} + +static void extend_ds_error(struct nfs4_ff_layout_ds_err *err, + u64 offset, u64 length) +{ + u64 end; + + end = max_t(u64, end_offset(err->offset, err->length), + end_offset(offset, length)); + err->offset = min_t(u64, err->offset, offset); + err->length = end - err->offset; +} + +static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, + struct nfs4_deviceid *deviceid) +{ + return err->status == status && err->opnum == opnum && + nfs4_stateid_match(&err->stateid, stateid) && + !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) && + end_offset(err->offset, err->length) >= offset && + err->offset <= end_offset(offset, length); +} + +static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old, + struct nfs4_ff_layout_ds_err *new) +{ + if (!ds_error_can_merge(old, new->offset, new->length, new->status, + new->opnum, &new->stateid, &new->deviceid)) + return false; + + extend_ds_error(old, new->offset, new->length); + return true; +} + +static bool +ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_ds_err *dserr) +{ + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (merge_ds_error(err, dserr)) { + return true; + } + } + + list_add(&dserr->list, &flo->error_list); + return false; +} + +static bool +ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, struct nfs4_deviceid *deviceid) +{ + bool found = false; + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (ds_error_can_merge(err, offset, length, status, opnum, + stateid, deviceid)) { + found = true; + extend_ds_error(err, offset, length); + break; + } + } + + return found; +} + +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds_err *dserr; + bool needfree; + + if (status == 0) + return 0; + + if (mirror->mirror_ds == NULL) + return -EINVAL; + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + if (ff_layout_update_ds_error(flo, offset, length, status, opnum, + &mirror->stateid, + &mirror->mirror_ds->id_node.deviceid)) { + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + return 0; + } + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + dserr = kmalloc(sizeof(*dserr), gfp_flags); + if (!dserr) + return -ENOMEM; + + INIT_LIST_HEAD(&dserr->list); + dserr->offset = offset; + dserr->length = length; + dserr->status = status; + dserr->opnum = opnum; + nfs4_stateid_copy(&dserr->stateid, &mirror->stateid); + memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid, + NFS4_DEVICEID4_SIZE); + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + needfree = ff_layout_add_ds_error_locked(flo, dserr); + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + if (needfree) + kfree(dserr); + + return 0; +} + +/* currently we only support AUTH_NONE and AUTH_SYS */ +static rpc_authflavor_t +nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror) +{ + if (mirror->uid == (u32)-1) + return RPC_AUTH_NULL; + return RPC_AUTH_UNIX; +} + +/* fetch cred for NFSv3 DS */ +static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror, + struct nfs4_pnfs_ds *ds) +{ + if (ds->ds_clp && !mirror->cred && + mirror->mirror_ds->ds_versions[0].version == 3) { + struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth; + struct rpc_cred *cred; + struct auth_cred acred = { + .uid = make_kuid(&init_user_ns, mirror->uid), + .gid = make_kgid(&init_user_ns, mirror->gid), + }; + + /* AUTH_NULL ignores acred */ + cred = auth->au_ops->lookup_cred(auth, &acred, 0); + if (IS_ERR(cred)) { + dprintk("%s: lookup_cred failed with %ld\n", + __func__, PTR_ERR(cred)); + return PTR_ERR(cred); + } else { + mirror->cred = cred; + } + } + return 0; +} + +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx); + struct nfs_fh *fh = NULL; + struct nfs4_deviceid_node *devid; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n", + __func__, mirror_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + /* FIXME: For now assume there is only 1 version available for the DS */ + fh = &mirror->fh_versions[0]; +out: + return fh; +} + +/* Upon return, either ds is connected, or ds is NULL */ +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct nfs4_pnfs_ds *ds = NULL; + struct nfs4_deviceid_node *devid; + struct inode *ino = lseg->pls_layout->plh_inode; + struct nfs_server *s = NFS_SERVER(ino); + unsigned int max_payload; + rpc_authflavor_t flavor; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", + __func__, ds_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + devid = &mirror->mirror_ds->id_node; + if (ff_layout_test_devid_unavailable(devid)) + goto out; + + ds = mirror->mirror_ds->ds; + /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ + smp_rmb(); + if (ds->ds_clp) + goto out; + + flavor = nfs4_ff_layout_choose_authflavor(mirror); + + /* FIXME: For now we assume the server sent only one version of NFS + * to use for the DS. + */ + nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + dataserver_retrans, + mirror->mirror_ds->ds_versions[0].version, + mirror->mirror_ds->ds_versions[0].minor_version, + flavor); + + /* connect success, check rsize/wsize limit */ + if (ds->ds_clp) { + max_payload = + nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient), + NULL); + if (mirror->mirror_ds->ds_versions[0].rsize > max_payload) + mirror->mirror_ds->ds_versions[0].rsize = max_payload; + if (mirror->mirror_ds->ds_versions[0].wsize > max_payload) + mirror->mirror_ds->ds_versions[0].wsize = max_payload; + } else { + ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, lseg->pls_range.offset, + lseg->pls_range.length, NFS4ERR_NXIO, + OP_ILLEGAL, GFP_NOIO); + if (fail_return) { + pnfs_error_mark_layout_for_return(ino, lseg); + if (ff_layout_has_available_ds(lseg)) + pnfs_set_retry_layoutget(lseg->pls_layout); + else + pnfs_clear_retry_layoutget(lseg->pls_layout); + + } else { + if (ff_layout_has_available_ds(lseg)) + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lseg->pls_layout->plh_flags); + else { + pnfs_error_mark_layout_for_return(ino, lseg); + pnfs_clear_retry_layoutget(lseg->pls_layout); + } + } + } + + if (ff_layout_update_mirror_cred(mirror, ds)) + ds = NULL; +out: + return ds; +} + +struct rpc_cred * +ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct rpc_cred *mdscred) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct rpc_cred *cred = ERR_PTR(-EINVAL); + + if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true)) + goto out; + + if (mirror && mirror->cred) + cred = mirror->cred; + else + cred = mdscred; +out: + return cred; +} + +/** +* Find or create a DS rpc client with th MDS server rpc client auth flavor +* in the nfs_client cl_ds_clients list. +*/ +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct nfs_client *ds_clp, struct inode *inode) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + + switch (mirror->mirror_ds->ds_versions[0].version) { + case 3: + /* For NFSv3 DS, flavor is set when creating DS connections */ + return ds_clp->cl_rpcclient; + case 4: + return nfs4_find_or_create_ds_client(ds_clp, inode); + default: + BUG(); + } +} + +static bool is_range_intersecting(u64 offset1, u64 length1, + u64 offset2, u64 length2) +{ + u64 end1 = end_offset(offset1, length1); + u64 end2 = end_offset(offset2, length2); + + return (end1 == NFS4_MAX_UINT64 || end1 > offset2) && + (end2 == NFS4_MAX_UINT64 || end2 > offset1); +} + +/* called with inode i_lock held */ +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range) +{ + struct nfs4_ff_layout_ds_err *err, *n; + __be32 *p; + + list_for_each_entry_safe(err, n, &flo->error_list, list) { + if (!is_range_intersecting(err->offset, err->length, + range->offset, range->length)) + continue; + /* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE) + * + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4) + */ + p = xdr_reserve_space(xdr, + 24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + p = xdr_encode_hyper(p, err->offset); + p = xdr_encode_hyper(p, err->length); + p = xdr_encode_opaque_fixed(p, &err->stateid, + NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, &err->deviceid, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(err->status); + *p++ = cpu_to_be32(err->opnum); + *count += 1; + list_del(&err->list); + kfree(err); + dprintk("%s: offset %llu length %llu status %d op %d count %d\n", + __func__, err->offset, err->length, err->status, + err->opnum, *count); + } + + return 0; +} + +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_deviceid_node *devid; + int idx; + + for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) { + mirror = FF_LAYOUT_COMP(lseg, idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + if (!ff_layout_test_devid_unavailable(devid)) + return true; + } + } + + return false; +} + +module_param(dataserver_retrans, uint, 0644); +MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client " + "retries a request before it attempts further " + " recovery action."); +module_param(dataserver_timeo, uint, 0644); +MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the " + "NFSv4.1 client waits for a response from a " + " data server before it retries an NFS request."); diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 2f5db844c172..857e2a99acc8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f nfs_fattr_free_group_name(fattr); } -static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) { unsigned long val; char buf[16]; @@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re *res = val; return 1; } +EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric); static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 44c600aac907..ca6dda0f68bb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7796,9 +7796,7 @@ static void nfs4_layoutreturn_release(void *calldata) spin_lock(&lo->plh_inode->i_lock); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); - smp_mb__after_atomic(); - wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + pnfs_clear_layoutreturn_waitbit(lo); clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c4c9fe606ae6..0fb0f1920a1f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -910,7 +910,9 @@ send_layoutget(struct pnfs_layout_hdr *lo, pnfs_layout_io_set_failed(lo, range->iomode); } return NULL; - } + } else + pnfs_layout_clear_fail_bit(lo, + pnfs_iomode_to_fail_bit(range->iomode)); return lseg; } @@ -930,6 +932,13 @@ static void pnfs_clear_layoutcommit(struct inode *inode, } } +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) +{ + clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); + smp_mb__after_atomic(); + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, enum pnfs_iomode iomode, bool sync) @@ -943,6 +952,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, status = -ENOMEM; spin_lock(&ino->i_lock); lo->plh_block_lgets--; + pnfs_clear_layoutreturn_waitbit(lo); rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq); spin_unlock(&ino->i_lock); pnfs_put_layout_hdr(lo); @@ -1418,6 +1428,15 @@ static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) TASK_UNINTERRUPTIBLE); } +static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) +{ + unsigned long *bitlock = &lo->plh_flags; + + clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET); +} + /* * Layout segment is retreived from the server if not cached. * The appropriate layout segment is referenced and returned to the caller. @@ -1499,6 +1518,8 @@ lookup_again: spin_unlock(&ino->i_lock); dprintk("%s wait for layoutreturn\n", __func__); if (pnfs_prepare_to_retry_layoutget(lo)) { + if (first) + pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); goto lookup_again; @@ -1533,13 +1554,8 @@ lookup_again: pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); out_put_layout_hdr: - if (first) { - unsigned long *bitlock = &lo->plh_flags; - - clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock); - smp_mb__after_atomic(); - wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET); - } + if (first) + pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); out: dprintk("%s: inode %s/%llu pNFS layout segment %s for " diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 49a466708400..7642021484bf 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -278,6 +278,7 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, u64 count, enum pnfs_iomode iomode, gfp_t gfp_flags); +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo); void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp); int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 022b761dbf0a..de7c91ca427e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -516,6 +516,7 @@ enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, LAYOUT_BLOCK_VOLUME = 3, + LAYOUT_FLEX_FILES = 4, }; /* used for both layout return and recall */ diff --git a/include/linux/nfs_idmap.h b/include/linux/nfs_idmap.h index 0f4b79da6584..333844e38f66 100644 --- a/include/linux/nfs_idmap.h +++ b/include/linux/nfs_idmap.h @@ -73,5 +73,7 @@ int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t); int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t); +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res); + extern unsigned int nfs_idmap_cache_timeout; #endif /* NFS_IDMAP_H */ diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 89f2ca178873..7e61a17030a4 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -89,6 +89,8 @@ void rpc_free_iostats(struct rpc_iostats *); static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; } static inline void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) {} +static inline void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *) {} static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {} static inline void rpc_free_iostats(struct rpc_iostats *stats) {} -- cgit v1.2.3 From 344d635b9a41b19837ccf8083a99ea688027019c Mon Sep 17 00:00:00 2001 From: Brad Griffis Date: Tue, 3 Feb 2015 11:44:12 -0800 Subject: Input: ti_am335x_tsc - remove udelay in interrupt handler TSC interrupt handler had udelay to avoid reporting of false pen-up interrupt to user space. This patch implements workaround suggesting in Advisory 1.0.31 of silicon errata for am335x, thus eliminating udelay and touchscreen lag. This also improves performance of touchscreen and eliminates sudden jump of cursor at touch release. IDLECONFIG and CHARGECONFIG registers are to be configured with same values in order to eliminate false pen-up events. This workaround may result in false pen-down to be detected, hence considerable charge step delay needs to be added. The charge delay is set to 0xB000 (in terms of ADC clock cycles) by default. TSC steps are disabled at the end of every sampling cycle and EOS bit is set. Once the EOS bit is set, the TSC steps need to be re-enabled to begin next sampling cycle. Signed-off-by: Brad Griffis [vigneshr@ti.com: Ported the patch from v3.12 to v3.19rc1] Signed-off-by: Vignesh R Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/ti_am335x_tsc.c | 67 ++++++++++++++----------------- include/linux/mfd/ti_am335x_tscadc.h | 3 +- 2 files changed, 33 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c index dfbb9fe6a270..0625c102a1d0 100644 --- a/drivers/input/touchscreen/ti_am335x_tsc.c +++ b/drivers/input/touchscreen/ti_am335x_tsc.c @@ -173,11 +173,9 @@ static void titsc_step_config(struct titsc *ts_dev) titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY); } - /* Charge step configuration */ - config = ts_dev->bit_xp | ts_dev->bit_yn | - STEPCHARGE_RFP_XPUL | STEPCHARGE_RFM_XNUR | - STEPCHARGE_INM_AN1 | STEPCHARGE_INP(ts_dev->inp_yp); + /* Make CHARGECONFIG same as IDLECONFIG */ + config = titsc_readl(ts_dev, REG_IDLECONFIG); titsc_writel(ts_dev, REG_CHARGECONFIG, config); titsc_writel(ts_dev, REG_CHARGEDELAY, CHARGEDLY_OPENDLY); @@ -261,12 +259,34 @@ static irqreturn_t titsc_irq(int irq, void *dev) { struct titsc *ts_dev = dev; struct input_dev *input_dev = ts_dev->input; - unsigned int status, irqclr = 0; + unsigned int fsm, status, irqclr = 0; unsigned int x = 0, y = 0; unsigned int z1, z2, z; - unsigned int fsm; - status = titsc_readl(ts_dev, REG_IRQSTATUS); + status = titsc_readl(ts_dev, REG_RAWIRQSTATUS); + if (status & IRQENB_HW_PEN) { + ts_dev->pen_down = true; + titsc_writel(ts_dev, REG_IRQWAKEUP, 0x00); + titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN); + irqclr |= IRQENB_HW_PEN; + } + + if (status & IRQENB_PENUP) { + fsm = titsc_readl(ts_dev, REG_ADCFSM); + if (fsm == ADCFSM_STEPID) { + ts_dev->pen_down = false; + input_report_key(input_dev, BTN_TOUCH, 0); + input_report_abs(input_dev, ABS_PRESSURE, 0); + input_sync(input_dev); + } else { + ts_dev->pen_down = true; + } + irqclr |= IRQENB_PENUP; + } + + if (status & IRQENB_EOS) + irqclr |= IRQENB_EOS; + /* * ADC and touchscreen share the IRQ line. * FIFO1 interrupts are used by ADC. Handle FIFO0 IRQs here only @@ -297,37 +317,11 @@ static irqreturn_t titsc_irq(int irq, void *dev) } irqclr |= IRQENB_FIFO0THRES; } - - /* - * Time for sequencer to settle, to read - * correct state of the sequencer. - */ - udelay(SEQ_SETTLE); - - status = titsc_readl(ts_dev, REG_RAWIRQSTATUS); - if (status & IRQENB_PENUP) { - /* Pen up event */ - fsm = titsc_readl(ts_dev, REG_ADCFSM); - if (fsm == ADCFSM_STEPID) { - ts_dev->pen_down = false; - input_report_key(input_dev, BTN_TOUCH, 0); - input_report_abs(input_dev, ABS_PRESSURE, 0); - input_sync(input_dev); - } else { - ts_dev->pen_down = true; - } - irqclr |= IRQENB_PENUP; - } - - if (status & IRQENB_HW_PEN) { - - titsc_writel(ts_dev, REG_IRQWAKEUP, 0x00); - titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN); - } - if (irqclr) { titsc_writel(ts_dev, REG_IRQSTATUS, irqclr); - am335x_tsc_se_set_cache(ts_dev->mfd_tscadc, ts_dev->step_mask); + if (status & IRQENB_EOS) + am335x_tsc_se_set_cache(ts_dev->mfd_tscadc, + ts_dev->step_mask); return IRQ_HANDLED; } return IRQ_NONE; @@ -417,6 +411,7 @@ static int titsc_probe(struct platform_device *pdev) } titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES); + titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_EOS); err = titsc_config_wires(ts_dev); if (err) { dev_err(&pdev->dev, "wrong i/p wire configuration\n"); diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index e2e70053470e..3f4e994ace2b 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -52,6 +52,7 @@ /* IRQ enable */ #define IRQENB_HW_PEN BIT(0) +#define IRQENB_EOS BIT(1) #define IRQENB_FIFO0THRES BIT(2) #define IRQENB_FIFO0OVRRUN BIT(3) #define IRQENB_FIFO0UNDRFLW BIT(4) @@ -107,7 +108,7 @@ /* Charge delay */ #define CHARGEDLY_OPEN_MASK (0x3FFFF << 0) #define CHARGEDLY_OPEN(val) ((val) << 0) -#define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(1) +#define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ #define CNTRLREG_TSCSSENB BIT(0) -- cgit v1.2.3 From a49170b552423a3e85fc4f0d778c707402ee4863 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:42:58 +0800 Subject: ACPI: Return translation offset when parsing ACPI address space resources Change function acpi_dev_resource_address_space() and acpi_dev_resource_ext_address_space() to return address space translation offset. It's based on a patch from Yinghai Lu . Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 58 +++++++++++++++++++++++------------------- drivers/pnp/pnpacpi/rsparser.c | 29 +++++++++++---------- include/linux/acpi.h | 9 +++++-- 3 files changed, 54 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 57891a621b96..c902c8eece81 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -184,13 +184,14 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) } EXPORT_SYMBOL_GPL(acpi_dev_resource_io); -static bool acpi_decode_space(struct resource *res, +static bool acpi_decode_space(struct resource_win *win, struct acpi_resource_address *addr, struct acpi_address64_attribute *attr) { u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16; bool wp = addr->info.mem.write_protect; u64 len = attr->address_length; + struct resource *res = &win->res; /* * Filter out invalid descriptor according to ACPI Spec 5.0, section @@ -218,6 +219,8 @@ static bool acpi_decode_space(struct resource *res, return false; } + win->offset = attr->translation_offset; + if (addr->producer_consumer == ACPI_PRODUCER) res->flags |= IORESOURCE_WINDOW; @@ -230,27 +233,28 @@ static bool acpi_decode_space(struct resource *res, /** * acpi_dev_resource_address_space - Extract ACPI address space information. * @ares: Input ACPI resource object. - * @res: Output generic resource object. + * @win: Output generic resource object. * * Check if the given ACPI resource object represents an address space resource * and if that's the case, use the information in it to populate the generic - * resource object pointed to by @res. + * resource object pointed to by @win. * * Return: - * 1) false with res->flags setting to zero: not the expected resource type - * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource + * 1) false with win->res.flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned + * resource * 3) true: valid assigned resource */ bool acpi_dev_resource_address_space(struct acpi_resource *ares, - struct resource *res) + struct resource_win *win) { struct acpi_resource_address64 addr; - res->flags = 0; + win->res.flags = 0; if (ACPI_FAILURE(acpi_resource_to_address64(ares, &addr))) return false; - return acpi_decode_space(res, (struct acpi_resource_address *)&addr, + return acpi_decode_space(win, (struct acpi_resource_address *)&addr, &addr.address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space); @@ -258,29 +262,30 @@ EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space); /** * acpi_dev_resource_ext_address_space - Extract ACPI address space information. * @ares: Input ACPI resource object. - * @res: Output generic resource object. + * @win: Output generic resource object. * * Check if the given ACPI resource object represents an extended address space * resource and if that's the case, use the information in it to populate the - * generic resource object pointed to by @res. + * generic resource object pointed to by @win. * * Return: - * 1) false with res->flags setting to zero: not the expected resource type - * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource + * 1) false with win->res.flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned + * resource * 3) true: valid assigned resource */ bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, - struct resource *res) + struct resource_win *win) { struct acpi_resource_extended_address64 *ext_addr; - res->flags = 0; + win->res.flags = 0; if (ares->type != ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64) return false; ext_addr = &ares->data.ext_address64; - return acpi_decode_space(res, (struct acpi_resource_address *)ext_addr, + return acpi_decode_space(win, (struct acpi_resource_address *)ext_addr, &ext_addr->address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_ext_address_space); @@ -441,7 +446,7 @@ struct res_proc_context { int error; }; -static acpi_status acpi_dev_new_resource_entry(struct resource *r, +static acpi_status acpi_dev_new_resource_entry(struct resource_win *win, struct res_proc_context *c) { struct resource_list_entry *rentry; @@ -451,7 +456,7 @@ static acpi_status acpi_dev_new_resource_entry(struct resource *r, c->error = -ENOMEM; return AE_NO_MEMORY; } - rentry->res = *r; + rentry->res = win->res; list_add_tail(&rentry->node, c->list); c->count++; return AE_OK; @@ -461,7 +466,8 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, void *context) { struct res_proc_context *c = context; - struct resource r; + struct resource_win win; + struct resource *res = &win.res; int i; if (c->preproc) { @@ -476,18 +482,18 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, } } - memset(&r, 0, sizeof(r)); + memset(&win, 0, sizeof(win)); - if (acpi_dev_resource_memory(ares, &r) - || acpi_dev_resource_io(ares, &r) - || acpi_dev_resource_address_space(ares, &r) - || acpi_dev_resource_ext_address_space(ares, &r)) - return acpi_dev_new_resource_entry(&r, c); + if (acpi_dev_resource_memory(ares, res) + || acpi_dev_resource_io(ares, res) + || acpi_dev_resource_address_space(ares, &win) + || acpi_dev_resource_ext_address_space(ares, &win)) + return acpi_dev_new_resource_entry(&win, c); - for (i = 0; acpi_dev_resource_interrupt(ares, i, &r); i++) { + for (i = 0; acpi_dev_resource_interrupt(ares, i, res); i++) { acpi_status status; - status = acpi_dev_new_resource_entry(&r, c); + status = acpi_dev_new_resource_entry(&win, c); if (ACPI_FAILURE(status)) return status; } diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 2d9bc789af0f..ff0356fb378f 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -180,20 +180,21 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, struct pnp_dev *dev = data; struct acpi_resource_dma *dma; struct acpi_resource_vendor_typed *vendor_typed; - struct resource r = {0}; + struct resource_win win = {{0}, 0}; + struct resource *r = &win.res; int i, flags; - if (acpi_dev_resource_address_space(res, &r) - || acpi_dev_resource_ext_address_space(res, &r)) { - pnp_add_resource(dev, &r); + if (acpi_dev_resource_address_space(res, &win) + || acpi_dev_resource_ext_address_space(res, &win)) { + pnp_add_resource(dev, &win.res); return AE_OK; } - r.flags = 0; - if (acpi_dev_resource_interrupt(res, 0, &r)) { - pnpacpi_add_irqresource(dev, &r); - for (i = 1; acpi_dev_resource_interrupt(res, i, &r); i++) - pnpacpi_add_irqresource(dev, &r); + r->flags = 0; + if (acpi_dev_resource_interrupt(res, 0, r)) { + pnpacpi_add_irqresource(dev, r); + for (i = 1; acpi_dev_resource_interrupt(res, i, r); i++) + pnpacpi_add_irqresource(dev, r); if (i > 1) { /* @@ -209,7 +210,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, } } return AE_OK; - } else if (r.flags & IORESOURCE_DISABLED) { + } else if (r->flags & IORESOURCE_DISABLED) { pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED); return AE_OK; } @@ -218,13 +219,13 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, case ACPI_RESOURCE_TYPE_MEMORY24: case ACPI_RESOURCE_TYPE_MEMORY32: case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: - if (acpi_dev_resource_memory(res, &r)) - pnp_add_resource(dev, &r); + if (acpi_dev_resource_memory(res, r)) + pnp_add_resource(dev, r); break; case ACPI_RESOURCE_TYPE_IO: case ACPI_RESOURCE_TYPE_FIXED_IO: - if (acpi_dev_resource_io(res, &r)) - pnp_add_resource(dev, &r); + if (acpi_dev_resource_io(res, r)) + pnp_add_resource(dev, r); break; case ACPI_RESOURCE_TYPE_DMA: dma = &res->data.dma; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d459cd17b477..be9eaee8f4ae 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -285,12 +285,17 @@ extern int pnpacpi_disabled; #define PXM_INVAL (-1) +struct resource_win { + struct resource res; + resource_size_t offset; +}; + bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -- cgit v1.2.3 From 93286f4798590e711aa395503401f8632fb74f9a Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:43:00 +0800 Subject: ACPI: Add field offset to struct resource_list_entry Add field offset to struct resource_list_entry to host address space translation offset so it could be used to represent bridge resources. Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 1 + include/linux/acpi.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 4dc8cfb2e94e..1c3abae6f2fa 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -472,6 +472,7 @@ static acpi_status acpi_dev_new_resource_entry(struct resource_win *win, return AE_NO_MEMORY; } rentry->res = win->res; + rentry->offset = win->offset; list_add_tail(&rentry->node, c->list); c->count++; return AE_OK; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index be9eaee8f4ae..21dac3cb62d2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -303,6 +303,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource_list_entry { struct list_head node; struct resource res; + resource_size_t offset; }; void acpi_dev_free_resource_list(struct list_head *list); -- cgit v1.2.3 From 62d1141ff34e35de496ba06491c8e854b23b3f3e Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:43:01 +0800 Subject: ACPI: Introduce helper function acpi_dev_filter_resource_type() Introduce helper function acpi_dev_filter_resource_type(), which may be used by acpi_dev_get_resources() to filer out resource based on resource type. Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/acpi.h | 8 +++++++ 2 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 1c3abae6f2fa..3ea0d17eb951 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -569,3 +569,58 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, return c.count; } EXPORT_SYMBOL_GPL(acpi_dev_get_resources); + +/** + * acpi_dev_filter_resource_type - Filter ACPI resource according to resource + * types + * @ares: Input ACPI resource object. + * @types: Valid resource types of IORESOURCE_XXX + * + * This is a hepler function to support acpi_dev_get_resources(), which filters + * ACPI resource objects according to resource types. + */ +int acpi_dev_filter_resource_type(struct acpi_resource *ares, + unsigned long types) +{ + unsigned long type = 0; + + switch (ares->type) { + case ACPI_RESOURCE_TYPE_MEMORY24: + case ACPI_RESOURCE_TYPE_MEMORY32: + case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: + type = IORESOURCE_MEM; + break; + case ACPI_RESOURCE_TYPE_IO: + case ACPI_RESOURCE_TYPE_FIXED_IO: + type = IORESOURCE_IO; + break; + case ACPI_RESOURCE_TYPE_IRQ: + case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: + type = IORESOURCE_IRQ; + break; + case ACPI_RESOURCE_TYPE_DMA: + case ACPI_RESOURCE_TYPE_FIXED_DMA: + type = IORESOURCE_DMA; + break; + case ACPI_RESOURCE_TYPE_GENERIC_REGISTER: + type = IORESOURCE_REG; + break; + case ACPI_RESOURCE_TYPE_ADDRESS16: + case ACPI_RESOURCE_TYPE_ADDRESS32: + case ACPI_RESOURCE_TYPE_ADDRESS64: + case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: + if (ares->data.address.resource_type == ACPI_MEMORY_RANGE) + type = IORESOURCE_MEM; + else if (ares->data.address.resource_type == ACPI_IO_RANGE) + type = IORESOURCE_IO; + else if (ares->data.address.resource_type == + ACPI_BUS_NUMBER_RANGE) + type = IORESOURCE_BUS; + break; + default: + break; + } + + return (type & types) ? 0 : 1; +} +EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 21dac3cb62d2..e818decb631f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -310,6 +310,14 @@ void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); +int acpi_dev_filter_resource_type(struct acpi_resource *ares, + unsigned long types); + +static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, + void *arg) +{ + return acpi_dev_filter_resource_type(ares, (unsigned long)arg); +} int acpi_check_resource_conflict(const struct resource *res); -- cgit v1.2.3 From 03a9a42a1a7e5b3e7919ddfacc1d1cc81882a955 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 18:12:28 -0500 Subject: SUNRPC: NULL utsname dereference on NFS umount during namespace cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix an Oopsable condition when nsm_mon_unmon is called as part of the namespace cleanup, which now apparently happens after the utsname has been freed. Link: http://lkml.kernel.org/r/20150125220604.090121ae@neptune.home Reported-by: Bruno Prémont Cc: stable@vger.kernel.org # 3.18 Signed-off-by: Trond Myklebust --- fs/lockd/mon.c | 13 +++++++++---- include/linux/sunrpc/clnt.h | 3 ++- net/sunrpc/clnt.c | 12 +++++++----- net/sunrpc/rpcb_clnt.c | 8 ++++++-- 4 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1cc6ec51e6b1..47a32b6d9b90 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm) return (struct sockaddr *)&nsm->sm_addr; } -static struct rpc_clnt *nsm_create(struct net *net) +static struct rpc_clnt *nsm_create(struct net *net, const char *nodename) { struct sockaddr_in sin = { .sin_family = AF_INET, @@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net) .address = (struct sockaddr *)&sin, .addrsize = sizeof(sin), .servername = "rpc.statd", + .nodename = nodename, .program = &nsm_program, .version = NSM_VERSION, .authflavor = RPC_AUTH_NULL, @@ -102,7 +103,7 @@ out: return clnt; } -static struct rpc_clnt *nsm_client_get(struct net *net) +static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename) { struct rpc_clnt *clnt, *new; struct lockd_net *ln = net_generic(net, lockd_net_id); @@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net) if (clnt != NULL) goto out; - clnt = new = nsm_create(net); + clnt = new = nsm_create(net, nodename); if (IS_ERR(clnt)) goto out; @@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host) struct nsm_res res; int status; struct rpc_clnt *clnt; + const char *nodename = NULL; dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name); if (nsm->sm_monitored) return 0; + if (host->h_rpcclnt) + nodename = host->h_rpcclnt->cl_nodename; + /* * Choose whether to record the caller_name or IP address of * this peer in the local rpc.statd's database. */ nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf; - clnt = nsm_client_get(host->net); + clnt = nsm_client_get(host->net, nodename); if (IS_ERR(clnt)) { status = PTR_ERR(clnt); dprintk("lockd: failed to create NSM upcall transport, " diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index d86acc63b25f..598ba80ec30c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -57,7 +57,7 @@ struct rpc_clnt { const struct rpc_timeout *cl_timeout; /* Timeout strategy */ int cl_nodelen; /* nodename length */ - char cl_nodename[UNX_MAXNODENAME]; + char cl_nodename[UNX_MAXNODENAME+1]; struct rpc_pipe_dir_head cl_pipedir_objects; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; @@ -112,6 +112,7 @@ struct rpc_create_args { struct sockaddr *saddress; const struct rpc_timeout *timeout; const char *servername; + const char *nodename; const struct rpc_program *program; u32 prognumber; /* overrides program->number */ u32 version; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 05da12a33945..3f5d4d48f0cb 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -286,10 +286,8 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { - clnt->cl_nodelen = strlen(nodename); - if (clnt->cl_nodelen > UNX_MAXNODENAME) - clnt->cl_nodelen = UNX_MAXNODENAME; - memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen); + clnt->cl_nodelen = strlcpy(clnt->cl_nodename, + nodename, sizeof(clnt->cl_nodename)); } static int rpc_client_register(struct rpc_clnt *clnt, @@ -365,6 +363,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, const struct rpc_version *version; struct rpc_clnt *clnt = NULL; const struct rpc_timeout *timeout; + const char *nodename = args->nodename; int err; /* sanity check the name before trying to print it */ @@ -420,8 +419,10 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, atomic_set(&clnt->cl_count, 1); + if (nodename == NULL) + nodename = utsname()->nodename; /* save the nodename */ - rpc_clnt_set_nodename(clnt, utsname()->nodename); + rpc_clnt_set_nodename(clnt, nodename); err = rpc_client_register(clnt, args->authflavor, args->client_name); if (err) @@ -576,6 +577,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, if (xprt == NULL) goto out_err; args->servername = xprt->servername; + args->nodename = clnt->cl_nodename; new = rpc_new_client(args, xprt, clnt); if (IS_ERR(new)) { diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 05202012bcfc..cf5770d8f49a 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -355,7 +355,8 @@ out: return result; } -static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, +static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename, + const char *hostname, struct sockaddr *srvaddr, size_t salen, int proto, u32 version) { @@ -365,6 +366,7 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, .address = srvaddr, .addrsize = salen, .servername = hostname, + .nodename = nodename, .program = &rpcb_program, .version = version, .authflavor = RPC_AUTH_UNIX, @@ -740,7 +742,9 @@ void rpcb_getport_async(struct rpc_task *task) dprintk("RPC: %5u %s: trying rpcbind version %u\n", task->tk_pid, __func__, bind_version); - rpcb_clnt = rpcb_create(xprt->xprt_net, xprt->servername, sap, salen, + rpcb_clnt = rpcb_create(xprt->xprt_net, + clnt->cl_nodename, + xprt->servername, sap, salen, xprt->prot, bind_version); if (IS_ERR(rpcb_clnt)) { status = PTR_ERR(rpcb_clnt); -- cgit v1.2.3 From c1dbe2fbb33ef425a81e1a7cffd17c113c87cdbc Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 27 Jan 2015 21:13:39 +0100 Subject: PM / Domains: Remove reference counting for the generic_pm_domain_data The reference counting was needed when genpd supported PM domain device callbacks. Since this option has been removed, let's also remove the reference counting of the struct generic_pm_domain_data. Signed-off-by: Ulf Hansson Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 10 ++-------- include/linux/pm_domain.h | 1 - 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index f9e7df554b2f..351df5bbd9c9 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1456,7 +1456,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, gpd_data = gpd_data_new; dev->power.subsys_data->domain_data = &gpd_data->base; } - gpd_data->refcount++; if (td) gpd_data->td = *td; @@ -1504,7 +1503,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, { struct generic_pm_domain_data *gpd_data; struct pm_domain_data *pdd; - bool remove = false; int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1533,10 +1531,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, pdd = dev->power.subsys_data->domain_data; list_del_init(&pdd->list_node); gpd_data = to_gpd_data(pdd); - if (--gpd_data->refcount == 0) { - dev->power.subsys_data->domain_data = NULL; - remove = true; - } + dev->power.subsys_data->domain_data = NULL; spin_unlock_irq(&dev->power.lock); @@ -1547,8 +1542,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, genpd_release_lock(genpd); dev_pm_put_subsys_data(dev); - if (remove) - genpd_free_dev_data(dev, gpd_data); + genpd_free_dev_data(dev, gpd_data); return 0; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index ed607760fc20..e160a0bba28d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -114,7 +114,6 @@ struct generic_pm_domain_data { struct gpd_timing_data td; struct notifier_block nb; struct mutex lock; - unsigned int refcount; int need_restore; }; -- cgit v1.2.3 From c0356db7d1b66840882744cbd9d9c5960b2d88c7 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 27 Jan 2015 21:13:42 +0100 Subject: PM / Domains: Eliminate the mutex for the generic_pm_domain_data While adding devices to their PM domains, dev_pm_qos_add_notifier() was invoked while allocating the generic_pm_domain_data for the device. Since the generic_pm_domain_data's device pointer will be assigned after allocation, the ->genpd_dev_pm_qos_notifier() callback could be called prior having a valid pointer to the device. Similar scenario existed while removing a device from a genpd. To cope with these scenarios a mutex was used to protect the pointer to the device. By re-order the sequence for when dev_pm_qos_add|remove_notifier() are invoked, we make sure the ->genpd_dev_pm_qos_notifier() callback are always called with a valid device pointer available. In this way, we eliminate the need for protecting the pointer and thus we can remove the mutex from the struct generic_pm_domain_data. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 37 ++++++++++++++----------------------- include/linux/pm_domain.h | 1 - 2 files changed, 14 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 88198ba919d9..1f026c18bc5c 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -344,14 +344,7 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, struct device *dev; gpd_data = container_of(nb, struct generic_pm_domain_data, nb); - - mutex_lock(&gpd_data->lock); dev = gpd_data->base.dev; - if (!dev) { - mutex_unlock(&gpd_data->lock); - return NOTIFY_DONE; - } - mutex_unlock(&gpd_data->lock); for (;;) { struct generic_pm_domain *genpd; @@ -1392,16 +1385,12 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev) if (!gpd_data) return NULL; - mutex_init(&gpd_data->lock); - gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; - dev_pm_qos_add_notifier(dev, &gpd_data->nb); return gpd_data; } static void genpd_free_dev_data(struct device *dev, struct generic_pm_domain_data *gpd_data) { - dev_pm_qos_remove_notifier(dev, &gpd_data->nb); kfree(gpd_data); } @@ -1414,7 +1403,7 @@ static void genpd_free_dev_data(struct device *dev, int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct gpd_timing_data *td) { - struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL; + struct generic_pm_domain_data *gpd_data; int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1422,8 +1411,8 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) return -EINVAL; - gpd_data_new = genpd_alloc_dev_data(dev); - if (!gpd_data_new) + gpd_data = genpd_alloc_dev_data(dev); + if (!gpd_data) return -ENOMEM; genpd_acquire_lock(genpd); @@ -1445,7 +1434,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, goto out; } - gpd_data = gpd_data_new; dev->power.subsys_data->domain_data = &gpd_data->base; if (td) @@ -1461,19 +1449,20 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, genpd->device_count++; genpd->max_off_time_changed = true; - mutex_lock(&gpd_data->lock); gpd_data->base.dev = dev; list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); gpd_data->need_restore = -1; gpd_data->td.constraint_changed = true; gpd_data->td.effective_constraint_ns = -1; - mutex_unlock(&gpd_data->lock); + gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; out: genpd_release_lock(genpd); - if (gpd_data != gpd_data_new) - genpd_free_dev_data(dev, gpd_data_new); + if (ret) + genpd_free_dev_data(dev, gpd_data); + else + dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; } @@ -1509,6 +1498,11 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, || pd_to_genpd(dev->pm_domain) != genpd) return -EINVAL; + /* The above validation also means we have existing domain_data. */ + pdd = dev->power.subsys_data->domain_data; + gpd_data = to_gpd_data(pdd); + dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + genpd_acquire_lock(genpd); if (genpd->prepared_count > 0) { @@ -1525,16 +1519,12 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, spin_lock_irq(&dev->power.lock); dev->pm_domain = NULL; - pdd = dev->power.subsys_data->domain_data; list_del_init(&pdd->list_node); - gpd_data = to_gpd_data(pdd); dev->power.subsys_data->domain_data = NULL; spin_unlock_irq(&dev->power.lock); - mutex_lock(&gpd_data->lock); pdd->dev = NULL; - mutex_unlock(&gpd_data->lock); genpd_release_lock(genpd); @@ -1545,6 +1535,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, out: genpd_release_lock(genpd); + dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; } diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index e160a0bba28d..080e778118ba 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -113,7 +113,6 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; - struct mutex lock; int need_restore; }; -- cgit v1.2.3 From 1e95e3b2da424db68d0a465273f1901a990c6277 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 29 Jan 2015 18:39:05 +0100 Subject: PM: Convert dev_pm_put_subsys_data() into a void function Clients using the dev_pm_put_subsys_data() API isn't interested of a return value. They care only of decreasing a reference to the device's pm_subsys_data. So, let's convert the API to a void function, which anyway seems like reasonable thing to do. Signed-off-by: Ulf Hansson Acked-by: Geert Uytterhoeven Signed-off-by: Rafael J. Wysocki --- drivers/base/power/common.c | 14 ++++---------- include/linux/pm.h | 2 +- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index a1ee51d43da1..f32b802b98f4 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -56,13 +56,11 @@ EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data); * @dev: Device to handle. * * If the reference counter of power.subsys_data is zero after dropping the - * reference, power.subsys_data is removed. Return 1 if that happens or 0 - * otherwise. + * reference, power.subsys_data is removed. */ -int dev_pm_put_subsys_data(struct device *dev) +void dev_pm_put_subsys_data(struct device *dev) { struct pm_subsys_data *psd; - int ret = 1; spin_lock_irq(&dev->power.lock); @@ -70,18 +68,14 @@ int dev_pm_put_subsys_data(struct device *dev) if (!psd) goto out; - if (--psd->refcount == 0) { + if (--psd->refcount == 0) dev->power.subsys_data = NULL; - } else { + else psd = NULL; - ret = 0; - } out: spin_unlock_irq(&dev->power.lock); kfree(psd); - - return ret; } EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); diff --git a/include/linux/pm.h b/include/linux/pm.h index 8b5976364619..e2f1be6dd9dd 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -597,7 +597,7 @@ struct dev_pm_info { extern void update_pm_runtime_accounting(struct device *dev); extern int dev_pm_get_subsys_data(struct device *dev); -extern int dev_pm_put_subsys_data(struct device *dev); +extern void dev_pm_put_subsys_data(struct device *dev); /* * Power domains provide callbacks that are executed during system suspend, -- cgit v1.2.3 From 44fc0e5eec00db5fba748803c95920098089c4cc Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 30 Jan 2015 13:14:36 +0200 Subject: sched/wait: Introduce wait_on_bit_timeout() Add a new wait_on_bit_timeout() helper, basically the same as wait_on_bit() except that it also takes a 'timeout' parameter. All the building blocks like bit_wait_timeout() and out_of_line_wait_on_bit_timeout() are already in place so the addition is rather simple. Signed-off-by: Johan Hedberg Signed-off-by: Peter Zijlstra (Intel) Cc: davem@davemloft.net Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1422616476-2917-2-git-send-email-johan.hedberg@gmail.com Signed-off-by: Ingo Molnar --- include/linux/wait.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 37423e0e1379..537d58eea8a0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -989,6 +989,32 @@ wait_on_bit_io(void *word, int bit, unsigned mode) mode); } +/** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address -- cgit v1.2.3 From 2fde4f94e0a9531251e706fa57131b51b0df042e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 7 Jan 2015 15:01:54 +0000 Subject: perf: Decouple unthrottling and rotating Currently the adjusments made as part of perf_event_task_tick() use the percpu rotation lists to iterate over any active PMU contexts, but these are not used by the context rotation code, having been replaced by separate (per-context) hrtimer callbacks. However, some manipulation of the rotation lists (i.e. removal of contexts) has remained in perf_rotate_context(). This leads to the following issues: * Contexts are not always removed from the rotation lists. Removal of PMUs which have been placed in rotation lists, but have not been removed by a hrtimer callback can result in corruption of the rotation lists (when memory backing the context is freed). This has been observed to result in hangs when PMU drivers built as modules are inserted and removed around the creation of events for said PMUs. * Contexts which do not require rotation may be removed from the rotation lists as a result of a hrtimer, and will not be considered by the unthrottling code in perf_event_task_tick. This patch fixes the issue by updating the rotation ist when events are scheduled in/out, ensuring that each rotation list stays in sync with the HW state. As each event holds a refcount on the module of its PMU, this ensures that when a PMU module is unloaded none of its CPU contexts can be in a rotation list. By maintaining a list of perf_event_contexts rather than perf_event_cpu_contexts, we don't need separate paths to handle the cpu and task contexts, which also makes the code a little simpler. As the rotation_list variables are not used for rotation, these are renamed to active_ctx_list, which better matches their current function. perf_pmu_rotate_{start,stop} are renamed to perf_pmu_ctx_{activate,deactivate}. Reported-by: Johannes Jensen Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Cc: Will Deacon Cc: Arnaldo Carvalho de Melo Cc: Fengguang Wu Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20150129134511.GR17721@leverpostej Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- kernel/events/core.c | 81 +++++++++++++++++----------------------------- 2 files changed, 30 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 216653466a67..5cad0e6f3552 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -469,6 +469,7 @@ struct perf_event_context { */ struct mutex mutex; + struct list_head active_ctx_list; struct list_head pinned_groups; struct list_head flexible_groups; struct list_head event_list; @@ -519,7 +520,6 @@ struct perf_cpu_context { int exclusive; struct hrtimer hrtimer; ktime_t hrtimer_interval; - struct list_head rotation_list; struct pmu *unique_pmu; struct perf_cgroup *cgrp; }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 37cc20e8aa3b..7f2fbb8b5069 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -872,22 +872,32 @@ void perf_pmu_enable(struct pmu *pmu) pmu->pmu_enable(pmu); } -static DEFINE_PER_CPU(struct list_head, rotation_list); +static DEFINE_PER_CPU(struct list_head, active_ctx_list); /* - * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized - * because they're strictly cpu affine and rotate_start is called with IRQs - * disabled, while rotate_context is called from IRQ context. + * perf_event_ctx_activate(), perf_event_ctx_deactivate(), and + * perf_event_task_tick() are fully serialized because they're strictly cpu + * affine and perf_event_ctx{activate,deactivate} are called with IRQs + * disabled, while perf_event_task_tick is called from IRQ context. */ -static void perf_pmu_rotate_start(struct pmu *pmu) +static void perf_event_ctx_activate(struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - struct list_head *head = this_cpu_ptr(&rotation_list); + struct list_head *head = this_cpu_ptr(&active_ctx_list); WARN_ON(!irqs_disabled()); - if (list_empty(&cpuctx->rotation_list)) - list_add(&cpuctx->rotation_list, head); + WARN_ON(!list_empty(&ctx->active_ctx_list)); + + list_add(&ctx->active_ctx_list, head); +} + +static void perf_event_ctx_deactivate(struct perf_event_context *ctx) +{ + WARN_ON(!irqs_disabled()); + + WARN_ON(list_empty(&ctx->active_ctx_list)); + + list_del_init(&ctx->active_ctx_list); } static void get_ctx(struct perf_event_context *ctx) @@ -1233,8 +1243,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_branch_stack++; list_add_rcu(&event->event_entry, &ctx->event_list); - if (!ctx->nr_events) - perf_pmu_rotate_start(ctx->pmu); ctx->nr_events++; if (event->attr.inherit_stat) ctx->nr_stat++; @@ -1561,7 +1569,8 @@ event_sched_out(struct perf_event *event, if (!is_software_event(event)) cpuctx->active_oncpu--; - ctx->nr_active--; + if (!--ctx->nr_active) + perf_event_ctx_deactivate(ctx); if (event->attr.freq && event->attr.sample_freq) ctx->nr_freq--; if (event->attr.exclusive || !cpuctx->active_oncpu) @@ -1885,7 +1894,8 @@ event_sched_in(struct perf_event *event, if (!is_software_event(event)) cpuctx->active_oncpu++; - ctx->nr_active++; + if (!ctx->nr_active++) + perf_event_ctx_activate(ctx); if (event->attr.freq && event->attr.sample_freq) ctx->nr_freq++; @@ -2742,12 +2752,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); - - /* - * Since these rotations are per-cpu, we need to ensure the - * cpu-context we got scheduled on is actually rotating. - */ - perf_pmu_rotate_start(ctx->pmu); } /* @@ -3035,25 +3039,18 @@ static void rotate_ctx(struct perf_event_context *ctx) list_rotate_left(&ctx->flexible_groups); } -/* - * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized - * because they're strictly cpu affine and rotate_start is called with IRQs - * disabled, while rotate_context is called from IRQ context. - */ static int perf_rotate_context(struct perf_cpu_context *cpuctx) { struct perf_event_context *ctx = NULL; - int rotate = 0, remove = 1; + int rotate = 0; if (cpuctx->ctx.nr_events) { - remove = 0; if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active) rotate = 1; } ctx = cpuctx->task_ctx; if (ctx && ctx->nr_events) { - remove = 0; if (ctx->nr_events != ctx->nr_active) rotate = 1; } @@ -3077,8 +3074,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx) perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); done: - if (remove) - list_del_init(&cpuctx->rotation_list); return rotate; } @@ -3096,9 +3091,8 @@ bool perf_event_can_stop_tick(void) void perf_event_task_tick(void) { - struct list_head *head = this_cpu_ptr(&rotation_list); - struct perf_cpu_context *cpuctx, *tmp; - struct perf_event_context *ctx; + struct list_head *head = this_cpu_ptr(&active_ctx_list); + struct perf_event_context *ctx, *tmp; int throttled; WARN_ON(!irqs_disabled()); @@ -3106,14 +3100,8 @@ void perf_event_task_tick(void) __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); - list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) { - ctx = &cpuctx->ctx; + list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) perf_adjust_freq_unthr_context(ctx, throttled); - - ctx = cpuctx->task_ctx; - if (ctx) - perf_adjust_freq_unthr_context(ctx, throttled); - } } static int event_enable_on_exec(struct perf_event *event, @@ -3272,6 +3260,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx) { raw_spin_lock_init(&ctx->lock); mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->active_ctx_list); INIT_LIST_HEAD(&ctx->pinned_groups); INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); @@ -6954,7 +6943,6 @@ skip_type: __perf_cpu_hrtimer_init(cpuctx, cpu); - INIT_LIST_HEAD(&cpuctx->rotation_list); cpuctx->unique_pmu = pmu; } @@ -8384,7 +8372,7 @@ static void __init perf_event_init_all_cpus(void) for_each_possible_cpu(cpu) { swhash = &per_cpu(swevent_htable, cpu); mutex_init(&swhash->hlist_mutex); - INIT_LIST_HEAD(&per_cpu(rotation_list, cpu)); + INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu)); } } @@ -8405,22 +8393,11 @@ static void perf_event_init_cpu(int cpu) } #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC -static void perf_pmu_rotate_stop(struct pmu *pmu) -{ - struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - - WARN_ON(!irqs_disabled()); - - list_del_init(&cpuctx->rotation_list); -} - static void __perf_event_exit_context(void *__info) { struct remove_event re = { .detach_group = true }; struct perf_event_context *ctx = __info; - perf_pmu_rotate_stop(ctx->pmu); - rcu_read_lock(); list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) __perf_remove_from_context(&re); -- cgit v1.2.3 From 12cf89b550d13eb7cb86ef182bd6c04345a33a1f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 3 Feb 2015 16:45:18 -0600 Subject: livepatch: rename config to CONFIG_LIVEPATCH Rename CONFIG_LIVE_PATCHING to CONFIG_LIVEPATCH to make the naming of the config and the code more consistent. Signed-off-by: Josh Poimboeuf Reviewed-by: Jingoo Han Signed-off-by: Jiri Kosina --- arch/x86/Kconfig | 2 +- arch/x86/include/asm/livepatch.h | 4 ++-- arch/x86/kernel/Makefile | 2 +- include/linux/livepatch.h | 4 ++-- kernel/livepatch/Kconfig | 6 +++--- kernel/livepatch/Makefile | 2 +- samples/Kconfig | 4 ++-- samples/livepatch/Makefile | 2 +- 8 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 29b095231276..11970b076862 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -17,7 +17,7 @@ config X86_64 depends on 64BIT select X86_DEV_DMA_OPS select ARCH_USE_CMPXCHG_LOCKREF - select HAVE_LIVE_PATCHING + select HAVE_LIVEPATCH ### Arch settings config X86 diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index 26e58134c8cb..a455a53d789a 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -24,7 +24,7 @@ #include #include -#ifdef CONFIG_LIVE_PATCHING +#ifdef CONFIG_LIVEPATCH static inline int klp_check_compiler_support(void) { #ifndef CC_USING_FENTRY @@ -40,7 +40,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } #else -#error Live patching support is disabled; check CONFIG_LIVE_PATCHING +#error Live patching support is disabled; check CONFIG_LIVEPATCH #endif #endif /* _ASM_X86_LIVEPATCH_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 316b34e74c15..732223496968 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -63,7 +63,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_LIVE_PATCHING) += livepatch.o +obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index f14c6fb262b4..95023fd8b00d 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,7 +24,7 @@ #include #include -#if IS_ENABLED(CONFIG_LIVE_PATCHING) +#if IS_ENABLED(CONFIG_LIVEPATCH) #include @@ -128,6 +128,6 @@ extern int klp_unregister_patch(struct klp_patch *); extern int klp_enable_patch(struct klp_patch *); extern int klp_disable_patch(struct klp_patch *); -#endif /* CONFIG_LIVE_PATCHING */ +#endif /* CONFIG_LIVEPATCH */ #endif /* _LINUX_LIVEPATCH_H_ */ diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig index 347ee2221137..045022557936 100644 --- a/kernel/livepatch/Kconfig +++ b/kernel/livepatch/Kconfig @@ -1,15 +1,15 @@ -config HAVE_LIVE_PATCHING +config HAVE_LIVEPATCH bool help Arch supports kernel live patching -config LIVE_PATCHING +config LIVEPATCH bool "Kernel Live Patching" depends on DYNAMIC_FTRACE_WITH_REGS depends on MODULES depends on SYSFS depends on KALLSYMS_ALL - depends on HAVE_LIVE_PATCHING + depends on HAVE_LIVEPATCH help Say Y here if you want to support kernel live patching. This option has no runtime impact until a kernel "patch" diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile index 7c1f00861428..e8780c0901d9 100644 --- a/kernel/livepatch/Makefile +++ b/kernel/livepatch/Makefile @@ -1,3 +1,3 @@ -obj-$(CONFIG_LIVE_PATCHING) += livepatch.o +obj-$(CONFIG_LIVEPATCH) += livepatch.o livepatch-objs := core.o diff --git a/samples/Kconfig b/samples/Kconfig index 0aed20df5f0b..224ebb46bed5 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -63,9 +63,9 @@ config SAMPLE_RPMSG_CLIENT to communicate with an AMP-configured remote processor over the rpmsg bus. -config SAMPLE_LIVE_PATCHING +config SAMPLE_LIVEPATCH tristate "Build live patching sample -- loadable modules only" - depends on LIVE_PATCHING && m + depends on LIVEPATCH && m help Builds a sample live patch that replaces the procfs handler for /proc/cmdline to print "this has been live patched". diff --git a/samples/livepatch/Makefile b/samples/livepatch/Makefile index 7f1cdc131a02..10319d7ea0b1 100644 --- a/samples/livepatch/Makefile +++ b/samples/livepatch/Makefile @@ -1 +1 @@ -obj-$(CONFIG_SAMPLE_LIVE_PATCHING) += livepatch-sample.o +obj-$(CONFIG_SAMPLE_LIVEPATCH) += livepatch-sample.o -- cgit v1.2.3 From 509102760da3a21831e763560ba4715760e3fbda Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 4 Feb 2015 11:45:28 +0100 Subject: regulator: Fix build breakage on !REGULATOR Add missing stubs for regulator_suspend_prepare() and regulator_suspend_finish() to fix exynos_defconfig build without REGULATOR: arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_finish': arch/arm/mach-exynos/suspend.c:537: undefined reference to `regulator_suspend_finish' arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_prepare': arch/arm/mach-exynos/suspend.c:520: undefined reference to `regulator_suspend_prepare' make: *** [vmlinux] Error 1 Signed-off-by: Krzysztof Kozlowski Reported-by: Joerg Roedel Reported-by: Marek Szyprowski Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 0b08d05d470b..b07562e082c4 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -191,15 +191,22 @@ struct regulator_init_data { void *driver_data; /* core does not touch this */ }; -int regulator_suspend_prepare(suspend_state_t state); -int regulator_suspend_finish(void); - #ifdef CONFIG_REGULATOR void regulator_has_full_constraints(void); +int regulator_suspend_prepare(suspend_state_t state); +int regulator_suspend_finish(void); #else static inline void regulator_has_full_constraints(void) { } +static inline int regulator_suspend_prepare(suspend_state_t state) +{ + return 0; +} +static inline int regulator_suspend_finish(void) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 6ae373394c4257bad562817aa60464ff7fe8f9c4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 14:21:14 -0500 Subject: NFSv4.1: Ask for no delegation on OPEN if using O_DIRECT If we're using NFSv4.1, then we have the ability to let the server know whether or not we believe that returning a delegation as part of our OPEN request would be useful. The feature needs to be used with care, since the client sending the request doesn't necessarily know how other clients are using that file, and how they may be affected by the delegation. For this reason, our initial use of the feature will be to let the server know when the client believes that handing out a delegation would not be useful. The first application for this function is when opening the file using O_DIRECT. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 30 +++++++++++++++++++ fs/nfs/nfs4xdr.c | 79 +++++++++++++++++++++++++++++++++---------------- include/linux/nfs_xdr.h | 2 ++ 3 files changed, 85 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6e1c9b2d92c5..cd4295d84d54 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -940,6 +940,31 @@ static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, return true; } +static u32 +nfs4_map_atomic_open_share(struct nfs_server *server, + fmode_t fmode, int openflags) +{ + u32 res = 0; + + switch (fmode & (FMODE_READ | FMODE_WRITE)) { + case FMODE_READ: + res = NFS4_SHARE_ACCESS_READ; + break; + case FMODE_WRITE: + res = NFS4_SHARE_ACCESS_WRITE; + break; + case FMODE_READ|FMODE_WRITE: + res = NFS4_SHARE_ACCESS_BOTH; + } + if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1)) + goto out; + /* Want no delegation if we're using O_DIRECT */ + if (openflags & O_DIRECT) + res |= NFS4_SHARE_WANT_NO_DELEG; +out: + return res; +} + static enum open_claim_type4 nfs4_map_atomic_open_claim(struct nfs_server *server, enum open_claim_type4 claim) @@ -1002,6 +1027,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, atomic_inc(&sp->so_count); p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); + p->o_arg.share_access = nfs4_map_atomic_open_share(server, + fmode, flags); /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS * will return permission denied for all bits until close */ if (!(flags & O_EXCL)) { @@ -2695,6 +2722,9 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; } } + calldata->arg.share_access = + nfs4_map_atomic_open_share(NFS_SERVER(inode), + calldata->arg.fmode, 0); nfs_fattr_init(calldata->res.fattr); calldata->timestamp = jiffies; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index a2329d69502b..e23a0a664e12 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1351,24 +1351,12 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc encode_string(xdr, name->len, name->name); } -static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) +static void encode_share_access(struct xdr_stream *xdr, u32 share_access) { __be32 *p; p = reserve_space(xdr, 8); - switch (fmode & (FMODE_READ|FMODE_WRITE)) { - case FMODE_READ: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ); - break; - case FMODE_WRITE: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE); - break; - case FMODE_READ|FMODE_WRITE: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH); - break; - default: - *p++ = cpu_to_be32(0); - } + *p++ = cpu_to_be32(share_access); *p = cpu_to_be32(0); /* for linux, share_deny = 0 always */ } @@ -1380,7 +1368,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena * owner 4 = 32 */ encode_nfs4_seqid(xdr, arg->seqid); - encode_share_access(xdr, arg->fmode); + encode_share_access(xdr, arg->share_access); p = reserve_space(xdr, 36); p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(24); @@ -1535,7 +1523,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr); encode_nfs4_stateid(xdr, &arg->stateid); encode_nfs4_seqid(xdr, arg->seqid); - encode_share_access(xdr, arg->fmode); + encode_share_access(xdr, arg->share_access); } static void @@ -4935,20 +4923,13 @@ out_overflow: return -EIO; } -static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +static int decode_rw_delegation(struct xdr_stream *xdr, + uint32_t delegation_type, + struct nfs_openres *res) { __be32 *p; - uint32_t delegation_type; int status; - p = xdr_inline_decode(xdr, 4); - if (unlikely(!p)) - goto out_overflow; - delegation_type = be32_to_cpup(p); - if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { - res->delegation_type = 0; - return 0; - } status = decode_stateid(xdr, &res->delegation); if (unlikely(status)) return status; @@ -4972,6 +4953,52 @@ out_overflow: return -EIO; } +static int decode_no_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t why_no_delegation; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + why_no_delegation = be32_to_cpup(p); + switch (why_no_delegation) { + case WND4_CONTENTION: + case WND4_RESOURCE: + xdr_inline_decode(xdr, 4); + /* Ignore for now */ + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t delegation_type; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + delegation_type = be32_to_cpup(p); + res->delegation_type = 0; + switch (delegation_type) { + case NFS4_OPEN_DELEGATE_NONE: + return 0; + case NFS4_OPEN_DELEGATE_READ: + case NFS4_OPEN_DELEGATE_WRITE: + return decode_rw_delegation(xdr, delegation_type, res); + case NFS4_OPEN_DELEGATE_NONE_EXT: + return decode_no_delegation(xdr, res); + } + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) { __be32 *p; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 81401125ab2d..2c35e2affa6f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -326,6 +326,7 @@ struct nfs_openargs { struct nfs_seqid * seqid; int open_flags; fmode_t fmode; + u32 share_access; u32 access; __u64 clientid; struct stateowner_id id; @@ -393,6 +394,7 @@ struct nfs_closeargs { nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; + u32 share_access; const u32 * bitmask; }; -- cgit v1.2.3 From 9064bf3c3cdf92f6b9ac6634ff570dedf0035992 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 Feb 2015 17:03:35 -0600 Subject: spi: spi-pxa2xx: only include mach/dma.h for legacy DMA Move the include of mach/dma.h to the legacy PXA DMA code where it is used. This enables building spi-pxa2xx on ARM64. Signed-off-by: Rob Herring Signed-off-by: Mark Brown --- drivers/spi/spi-pxa2xx-pxadma.c | 1 + include/linux/spi/pxa2xx_spi.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c index 6c82d496b58e..3fecaaa5b0a5 100644 --- a/drivers/spi/spi-pxa2xx-pxadma.c +++ b/drivers/spi/spi-pxa2xx-pxadma.c @@ -25,6 +25,7 @@ #include #include +#include #include "spi-pxa2xx.h" #define DMA_INT_MASK (DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR) diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index d5a316550177..46d8fa942631 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -57,7 +57,6 @@ struct pxa2xx_spi_chip { #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) #include -#include extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); -- cgit v1.2.3 From 90e97820619dc912b52cc9d103272819d8b51259 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 5 Feb 2015 13:44:43 +0800 Subject: resources: Move struct resource_list_entry from ACPI into resource core Currently ACPI, PCI and pnp all implement the same resource list management with different data structure. We need to transfer from one data structure into another when passing resources from one subsystem into another subsystem. So move struct resource_list_entry from ACPI into resource core and rename it as resource_entry, then it could be reused by different subystems and avoid the data structure conversion. Introduce dedicated header file resource_ext.h instead of embedding it into ioport.h to avoid header file inclusion order issues. Signed-off-by: Jiang Liu Acked-by: Vinod Koul Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpi_lpss.c | 8 ++--- drivers/acpi/acpi_platform.c | 4 +-- drivers/acpi/resource.c | 17 ++++------ drivers/dma/acpi-dma.c | 10 +++--- include/linux/acpi.h | 12 +------ include/linux/resource_ext.h | 77 ++++++++++++++++++++++++++++++++++++++++++++ kernel/resource.c | 25 ++++++++++++++ 7 files changed, 120 insertions(+), 33 deletions(-) create mode 100644 include/linux/resource_ext.h (limited to 'include/linux') diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 4f3febf8a589..dfd1b8095dad 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -313,7 +313,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev, { struct lpss_device_desc *dev_desc; struct lpss_private_data *pdata; - struct resource_list_entry *rentry; + struct resource_entry *rentry; struct list_head resource_list; struct platform_device *pdev; int ret; @@ -333,12 +333,12 @@ static int acpi_lpss_create_device(struct acpi_device *adev, goto err_out; list_for_each_entry(rentry, &resource_list, node) - if (resource_type(&rentry->res) == IORESOURCE_MEM) { + if (resource_type(rentry->res) == IORESOURCE_MEM) { if (dev_desc->prv_size_override) pdata->mmio_size = dev_desc->prv_size_override; else - pdata->mmio_size = resource_size(&rentry->res); - pdata->mmio_base = ioremap(rentry->res.start, + pdata->mmio_size = resource_size(rentry->res); + pdata->mmio_base = ioremap(rentry->res->start, pdata->mmio_size); break; } diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 6ba8beb6b9d2..1284138e42ab 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -45,7 +45,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) struct platform_device *pdev = NULL; struct acpi_device *acpi_parent; struct platform_device_info pdevinfo; - struct resource_list_entry *rentry; + struct resource_entry *rentry; struct list_head resource_list; struct resource *resources = NULL; int count; @@ -71,7 +71,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) } count = 0; list_for_each_entry(rentry, &resource_list, node) - resources[count++] = rentry->res; + resources[count++] = *rentry->res; acpi_dev_free_resource_list(&resource_list); } diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 3ea0d17eb951..4752b9939987 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -444,12 +444,7 @@ EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt); */ void acpi_dev_free_resource_list(struct list_head *list) { - struct resource_list_entry *rentry, *re; - - list_for_each_entry_safe(rentry, re, list, node) { - list_del(&rentry->node); - kfree(rentry); - } + resource_list_free(list); } EXPORT_SYMBOL_GPL(acpi_dev_free_resource_list); @@ -464,16 +459,16 @@ struct res_proc_context { static acpi_status acpi_dev_new_resource_entry(struct resource_win *win, struct res_proc_context *c) { - struct resource_list_entry *rentry; + struct resource_entry *rentry; - rentry = kmalloc(sizeof(*rentry), GFP_KERNEL); + rentry = resource_list_create_entry(NULL, 0); if (!rentry) { c->error = -ENOMEM; return AE_NO_MEMORY; } - rentry->res = win->res; + *rentry->res = win->res; rentry->offset = win->offset; - list_add_tail(&rentry->node, c->list); + resource_list_add_tail(rentry, c->list); c->count++; return AE_OK; } @@ -534,7 +529,7 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, * returned as the final error code. * * The resultant struct resource objects are put on the list pointed to by - * @list, that must be empty initially, as members of struct resource_list_entry + * @list, that must be empty initially, as members of struct resource_entry * objects. Callers of this routine should use %acpi_dev_free_resource_list() to * free that list. * diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c index de361a156b34..5a635646e05c 100644 --- a/drivers/dma/acpi-dma.c +++ b/drivers/dma/acpi-dma.c @@ -43,7 +43,7 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp, { const struct acpi_csrt_shared_info *si; struct list_head resource_list; - struct resource_list_entry *rentry; + struct resource_entry *rentry; resource_size_t mem = 0, irq = 0; int ret; @@ -56,10 +56,10 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp, return 0; list_for_each_entry(rentry, &resource_list, node) { - if (resource_type(&rentry->res) == IORESOURCE_MEM) - mem = rentry->res.start; - else if (resource_type(&rentry->res) == IORESOURCE_IRQ) - irq = rentry->res.start; + if (resource_type(rentry->res) == IORESOURCE_MEM) + mem = rentry->res->start; + else if (resource_type(rentry->res) == IORESOURCE_IRQ) + irq = rentry->res->start; } acpi_dev_free_resource_list(&resource_list); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e818decb631f..e53822148b6a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -27,6 +27,7 @@ #include #include /* for struct resource */ +#include #include #include @@ -285,11 +286,6 @@ extern int pnpacpi_disabled; #define PXM_INVAL (-1) -struct resource_win { - struct resource res; - resource_size_t offset; -}; - bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, @@ -300,12 +296,6 @@ unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -struct resource_list_entry { - struct list_head node; - struct resource res; - resource_size_t offset; -}; - void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h new file mode 100644 index 000000000000..e2bf63d881d4 --- /dev/null +++ b/include/linux/resource_ext.h @@ -0,0 +1,77 @@ +/* + * Copyright (C) 2015, Intel Corporation + * Author: Jiang Liu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#ifndef _LINUX_RESOURCE_EXT_H +#define _LINUX_RESOURCE_EXT_H +#include +#include +#include +#include + +/* Represent resource window for bridge devices */ +struct resource_win { + struct resource res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ +}; + +/* + * Common resource list management data structure and interfaces to support + * ACPI, PNP and PCI host bridge etc. + */ +struct resource_entry { + struct list_head node; + struct resource *res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ + struct resource __res; /* Default storage for res */ +}; + +extern struct resource_entry * +resource_list_create_entry(struct resource *res, size_t extra_size); +extern void resource_list_free(struct list_head *head); + +static inline void resource_list_add(struct resource_entry *entry, + struct list_head *head) +{ + list_add(&entry->node, head); +} + +static inline void resource_list_add_tail(struct resource_entry *entry, + struct list_head *head) +{ + list_add_tail(&entry->node, head); +} + +static inline void resource_list_del(struct resource_entry *entry) +{ + list_del(&entry->node); +} + +static inline void resource_list_free_entry(struct resource_entry *entry) +{ + kfree(entry); +} + +static inline void +resource_list_destroy_entry(struct resource_entry *entry) +{ + resource_list_del(entry); + resource_list_free_entry(entry); +} + +#define resource_list_for_each_entry(entry, list) \ + list_for_each_entry((entry), (list), node) + +#define resource_list_for_each_entry_safe(entry, tmp, list) \ + list_for_each_entry_safe((entry), (tmp), (list), node) + +#endif /* _LINUX_RESOURCE_EXT_H */ diff --git a/kernel/resource.c b/kernel/resource.c index 0bcebffc4e77..19f2357dfda3 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -1529,6 +1530,30 @@ int iomem_is_exclusive(u64 addr) return err; } +struct resource_entry *resource_list_create_entry(struct resource *res, + size_t extra_size) +{ + struct resource_entry *entry; + + entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL); + if (entry) { + INIT_LIST_HEAD(&entry->node); + entry->res = res ? res : &entry->__res; + } + + return entry; +} +EXPORT_SYMBOL(resource_list_create_entry); + +void resource_list_free(struct list_head *head) +{ + struct resource_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, head, node) + resource_list_destroy_entry(entry); +} +EXPORT_SYMBOL(resource_list_free); + static int __init strict_iomem(char *str) { if (strstr(str, "relaxed")) -- cgit v1.2.3 From 14d76b68f2819a1d0b50236a7e9e9f2ea69869d9 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 5 Feb 2015 13:44:44 +0800 Subject: PCI: Use common resource list management code instead of private implementation Use common resource list management data structure and interfaces instead of private implementation. Signed-off-by: Jiang Liu Acked-by: Will Deacon Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- arch/arm/kernel/bios32.c | 5 ++--- arch/x86/pci/bus_numa.c | 4 ++-- drivers/pci/bus.c | 18 ++++++------------ drivers/pci/host-bridge.c | 8 ++++---- drivers/pci/host/pci-host-generic.c | 4 ++-- drivers/pci/host/pci-xgene.c | 4 ++-- drivers/pci/host/pcie-xilinx.c | 4 ++-- drivers/pci/probe.c | 10 +++++----- include/linux/pci.h | 9 ++------- 9 files changed, 27 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index a4effd6d8f2f..016991792b0b 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -422,17 +422,16 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) static int pcibios_init_resources(int busnr, struct pci_sys_data *sys) { int ret; - struct pci_host_bridge_window *window; + struct resource_entry *window; if (list_empty(&sys->resources)) { pci_add_resource_offset(&sys->resources, &iomem_resource, sys->mem_offset); } - list_for_each_entry(window, &sys->resources, list) { + resource_list_for_each_entry(window, &sys->resources) if (resource_type(window->res) == IORESOURCE_IO) return 0; - } sys->io_res.start = (busnr * SZ_64K) ? : pcibios_min_io; sys->io_res.end = (busnr + 1) * SZ_64K - 1; diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index f3a2cfc14125..7bcf06a7cd12 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -31,7 +31,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) { struct pci_root_info *info = x86_find_pci_root_info(bus); struct pci_root_res *root_res; - struct pci_host_bridge_window *window; + struct resource_entry *window; bool found = false; if (!info) @@ -41,7 +41,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) bus); /* already added by acpi ? */ - list_for_each_entry(window, resources, list) + resource_list_for_each_entry(window, resources) if (window->res->flags & IORESOURCE_BUS) { found = true; break; diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 8fb16188cd82..90fa3a78fb7c 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -20,17 +20,16 @@ void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset) { - struct pci_host_bridge_window *window; + struct resource_entry *entry; - window = kzalloc(sizeof(struct pci_host_bridge_window), GFP_KERNEL); - if (!window) { + entry = resource_list_create_entry(res, 0); + if (!entry) { printk(KERN_ERR "PCI: can't add host bridge window %pR\n", res); return; } - window->res = res; - window->offset = offset; - list_add_tail(&window->list, resources); + entry->offset = offset; + resource_list_add_tail(entry, resources); } EXPORT_SYMBOL(pci_add_resource_offset); @@ -42,12 +41,7 @@ EXPORT_SYMBOL(pci_add_resource); void pci_free_resource_list(struct list_head *resources) { - struct pci_host_bridge_window *window, *tmp; - - list_for_each_entry_safe(window, tmp, resources, list) { - list_del(&window->list); - kfree(window); - } + resource_list_free(resources); } EXPORT_SYMBOL(pci_free_resource_list); diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index 0e5f3c95af5b..39b2dbe585aa 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -35,10 +35,10 @@ void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region, struct resource *res) { struct pci_host_bridge *bridge = find_pci_host_bridge(bus); - struct pci_host_bridge_window *window; + struct resource_entry *window; resource_size_t offset = 0; - list_for_each_entry(window, &bridge->windows, list) { + resource_list_for_each_entry(window, &bridge->windows) { if (resource_contains(window->res, res)) { offset = window->offset; break; @@ -60,10 +60,10 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res, struct pci_bus_region *region) { struct pci_host_bridge *bridge = find_pci_host_bridge(bus); - struct pci_host_bridge_window *window; + struct resource_entry *window; resource_size_t offset = 0; - list_for_each_entry(window, &bridge->windows, list) { + resource_list_for_each_entry(window, &bridge->windows) { struct pci_bus_region bus_region; if (resource_type(res) != resource_type(window->res)) diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c index 6eb1aa75bd37..aee3c620ecf9 100644 --- a/drivers/pci/host/pci-host-generic.c +++ b/drivers/pci/host/pci-host-generic.c @@ -149,14 +149,14 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci) struct device *dev = pci->host.dev.parent; struct device_node *np = dev->of_node; resource_size_t iobase; - struct pci_host_bridge_window *win; + struct resource_entry *win; err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources, &iobase); if (err) return err; - list_for_each_entry(win, &pci->resources, list) { + resource_list_for_each_entry(win, &pci->resources) { struct resource *parent, *res = win->res; switch (resource_type(res)) { diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c index b1d0596457c5..a704257bab7f 100644 --- a/drivers/pci/host/pci-xgene.c +++ b/drivers/pci/host/pci-xgene.c @@ -401,11 +401,11 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, struct list_head *res, resource_size_t io_base) { - struct pci_host_bridge_window *window; + struct resource_entry *window; struct device *dev = port->dev; int ret; - list_for_each_entry(window, res, list) { + resource_list_for_each_entry(window, res) { struct resource *res = window->res; u64 restype = resource_type(res); diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c index ef3ebaf9a738..601261df7663 100644 --- a/drivers/pci/host/pcie-xilinx.c +++ b/drivers/pci/host/pcie-xilinx.c @@ -737,7 +737,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port) resource_size_t offset; struct of_pci_range_parser parser; struct of_pci_range range; - struct pci_host_bridge_window *win; + struct resource_entry *win; int err = 0, mem_resno = 0; /* Get the ranges */ @@ -807,7 +807,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port) free_resources: release_child_resources(&iomem_resource); - list_for_each_entry(win, &port->resources, list) + resource_list_for_each_entry(win, &port->resources) devm_kfree(dev, win->res); pci_free_resource_list(&port->resources); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 23212f8ae09b..8d2f400e96cb 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1895,7 +1895,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, int error; struct pci_host_bridge *bridge; struct pci_bus *b, *b2; - struct pci_host_bridge_window *window, *n; + struct resource_entry *window, *n; struct resource *res; resource_size_t offset; char bus_addr[64]; @@ -1959,8 +1959,8 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, printk(KERN_INFO "PCI host bridge to bus %s\n", dev_name(&b->dev)); /* Add initial resources to the bus */ - list_for_each_entry_safe(window, n, resources, list) { - list_move_tail(&window->list, &bridge->windows); + resource_list_for_each_entry_safe(window, n, resources) { + list_move_tail(&window->node, &bridge->windows); res = window->res; offset = window->offset; if (res->flags & IORESOURCE_BUS) @@ -2060,12 +2060,12 @@ void pci_bus_release_busn_res(struct pci_bus *b) struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources) { - struct pci_host_bridge_window *window; + struct resource_entry *window; bool found = false; struct pci_bus *b; int max; - list_for_each_entry(window, resources, list) + resource_list_for_each_entry(window, resources) if (window->res->flags & IORESOURCE_BUS) { found = true; break; diff --git a/include/linux/pci.h b/include/linux/pci.h index 9603094ed59b..faa60fa26314 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -397,16 +398,10 @@ static inline int pci_channel_offline(struct pci_dev *pdev) return (pdev->error_state != pci_channel_io_normal); } -struct pci_host_bridge_window { - struct list_head list; - struct resource *res; /* host bridge aperture (CPU address) */ - resource_size_t offset; /* bus address + offset = CPU address */ -}; - struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* root bus */ - struct list_head windows; /* pci_host_bridge_windows */ + struct list_head windows; /* resource_entry */ void (*release_fn)(struct pci_host_bridge *); void *release_data; }; -- cgit v1.2.3 From ecf5636dcd59cd5508641f995cc4c2bafedbb995 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 5 Feb 2015 13:44:48 +0800 Subject: ACPI: Add interfaces to parse IOAPIC ID for IOAPIC hotplug We need to parse APIC ID for IOAPIC registration for IOAPIC hotplug. ACPI _MAT method and MADT table are used to figure out IOAPIC ID, just like parsing CPU APIC ID for CPU hotplug. [ tglx: Fixed docbook comment ] Signed-off-by: Yinghai Lu Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Joerg Roedel Cc: Greg Kroah-Hartman Cc: Benjamin Herrenschmidt Cc: Rafael J. Wysocki Cc: Bjorn Helgaas Cc: Randy Dunlap Cc: Borislav Petkov Cc: Len Brown Link: http://lkml.kernel.org/r/1414387308-27148-8-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- drivers/acpi/processor_core.c | 123 ++++++++++++++++++++++++++++++++++++++---- include/linux/acpi.h | 4 ++ 2 files changed, 118 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 02e48394276c..7962651cdbd4 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -4,6 +4,10 @@ * * Alex Chiang * - Unified x86/ia64 implementations + * + * I/O APIC hotplug support + * Yinghai Lu + * Jiang Liu */ #include #include @@ -12,6 +16,21 @@ #define _COMPONENT ACPI_PROCESSOR_COMPONENT ACPI_MODULE_NAME("processor_core"); +static struct acpi_table_madt *get_madt_table(void) +{ + static struct acpi_table_madt *madt; + static int read_madt; + + if (!read_madt) { + if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0, + (struct acpi_table_header **)&madt))) + madt = NULL; + read_madt++; + } + + return madt; +} + static int map_lapic_id(struct acpi_subtable_header *entry, u32 acpi_id, int *apic_id) { @@ -67,17 +86,10 @@ static int map_lsapic_id(struct acpi_subtable_header *entry, static int map_madt_entry(int type, u32 acpi_id) { unsigned long madt_end, entry; - static struct acpi_table_madt *madt; - static int read_madt; int phys_id = -1; /* CPU hardware ID */ + struct acpi_table_madt *madt; - if (!read_madt) { - if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0, - (struct acpi_table_header **)&madt))) - madt = NULL; - read_madt++; - } - + madt = get_madt_table(); if (!madt) return phys_id; @@ -203,3 +215,96 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) return acpi_map_cpuid(phys_id, acpi_id); } EXPORT_SYMBOL_GPL(acpi_get_cpuid); + +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base, + u64 *phys_addr, int *ioapic_id) +{ + struct acpi_madt_io_apic *ioapic = (struct acpi_madt_io_apic *)entry; + + if (ioapic->global_irq_base != gsi_base) + return 0; + + *phys_addr = ioapic->address; + *ioapic_id = ioapic->id; + return 1; +} + +static int parse_madt_ioapic_entry(u32 gsi_base, u64 *phys_addr) +{ + struct acpi_subtable_header *hdr; + unsigned long madt_end, entry; + struct acpi_table_madt *madt; + int apic_id = -1; + + madt = get_madt_table(); + if (!madt) + return apic_id; + + entry = (unsigned long)madt; + madt_end = entry + madt->header.length; + + /* Parse all entries looking for a match. */ + entry += sizeof(struct acpi_table_madt); + while (entry + sizeof(struct acpi_subtable_header) < madt_end) { + hdr = (struct acpi_subtable_header *)entry; + if (hdr->type == ACPI_MADT_TYPE_IO_APIC && + get_ioapic_id(hdr, gsi_base, phys_addr, &apic_id)) + break; + else + entry += hdr->length; + } + + return apic_id; +} + +static int parse_mat_ioapic_entry(acpi_handle handle, u32 gsi_base, + u64 *phys_addr) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_subtable_header *header; + union acpi_object *obj; + int apic_id = -1; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) + goto exit; + + if (!buffer.length || !buffer.pointer) + goto exit; + + obj = buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER || + obj->buffer.length < sizeof(struct acpi_subtable_header)) + goto exit; + + header = (struct acpi_subtable_header *)obj->buffer.pointer; + if (header->type == ACPI_MADT_TYPE_IO_APIC) + get_ioapic_id(header, gsi_base, phys_addr, &apic_id); + +exit: + kfree(buffer.pointer); + return apic_id; +} + +/** + * acpi_get_ioapic_id - Get IOAPIC ID and physical address matching @gsi_base + * @handle: ACPI object for IOAPIC device + * @gsi_base: GSI base to match with + * @phys_addr: Pointer to store physical address of matching IOAPIC record + * + * Walk resources returned by ACPI_MAT method, then ACPI MADT table, to search + * for an ACPI IOAPIC record matching @gsi_base. + * Return IOAPIC id and store physical address in @phys_addr if found a match, + * otherwise return <0. + */ +int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr) +{ + int apic_id; + + apic_id = parse_mat_ioapic_entry(handle, gsi_base, phys_addr); + if (apic_id == -1) + apic_id = parse_madt_ioapic_entry(gsi_base, phys_addr); + + return apic_id; +} +#endif /* CONFIG_ACPI_HOTPLUG_IOAPIC */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e53822148b6a..24c7aa8b1d20 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -152,6 +152,10 @@ int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); +#endif + int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); -- cgit v1.2.3 From 472e259449819d939b5a5188b6f4c7d59aa4304c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:50:30 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutcommit If we're sending an asynchronous layoutcommit, then we need to ensure that the inode and the super block remain pinned. Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- fs/nfs/nfs4proc.c | 19 +++++++++++-------- include/linux/nfs_xdr.h | 1 + 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index dd892a4e7eb3..e092b8540e2e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7989,6 +7989,7 @@ static void nfs4_layoutcommit_release(void *calldata) nfs_post_op_update_inode_force_wcc(data->args.inode, data->res.fattr); put_rpccred(data->cred); + nfs_iput_and_deactive(data->inode); kfree(data); } @@ -8013,7 +8014,6 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) .rpc_message = &msg, .callback_ops = &nfs4_layoutcommit_ops, .callback_data = data, - .flags = RPC_TASK_ASYNC, }; struct rpc_task *task; int status = 0; @@ -8024,18 +8024,21 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) data->args.lastbytewritten, data->args.inode->i_ino); + if (!sync) { + data->inode = nfs_igrab_and_active(data->args.inode); + if (data->inode == NULL) { + nfs4_layoutcommit_release(data); + return -EAGAIN; + } + task_setup_data.flags = RPC_TASK_ASYNC; + } nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); - if (sync == false) - goto out; - status = nfs4_wait_for_completion_rpc_task(task); - if (status != 0) - goto out; - status = task->tk_status; + if (sync) + status = task->tk_status; trace_nfs4_layoutcommit(data->args.inode, status); -out: dprintk("%s: status %d\n", __func__, status); rpc_put_task(task); return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2c35e2affa6f..bb0d56f737e0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -285,6 +285,7 @@ struct nfs4_layoutcommit_data { struct nfs_fattr fattr; struct list_head lseg_list; struct rpc_cred *cred; + struct inode *inode; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; }; -- cgit v1.2.3 From 5a0ec8acb945e302ce819b4a9787796ccf284548 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:35:16 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutreturns If we're sending an asynchronous layoutreturn, then we need to ensure that the inode and the super block remain pinned. Cc: Peng Tao Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- fs/nfs/nfs4proc.c | 19 +++++++++++-------- include/linux/nfs_xdr.h | 1 + 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e092b8540e2e..2e7c9f7a6f7c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7856,6 +7856,7 @@ static void nfs4_layoutreturn_release(void *calldata) lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_put_layout_hdr(lrp->args.layout); + nfs_iput_and_deactive(lrp->inode); kfree(calldata); dprintk("<-- %s\n", __func__); } @@ -7880,23 +7881,25 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) .rpc_message = &msg, .callback_ops = &nfs4_layoutreturn_call_ops, .callback_data = lrp, - .flags = RPC_TASK_ASYNC, }; int status = 0; dprintk("--> %s\n", __func__); + if (!sync) { + lrp->inode = nfs_igrab_and_active(lrp->args.inode); + if (!lrp->inode) { + nfs4_layoutreturn_release(lrp); + return -EAGAIN; + } + task_setup_data.flags |= RPC_TASK_ASYNC; + } nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); - if (sync == false) - goto out; - status = nfs4_wait_for_completion_rpc_task(task); - if (status != 0) - goto out; - status = task->tk_status; + if (sync) + status = task->tk_status; trace_nfs4_layoutreturn(lrp->args.inode, status); -out: dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bb0d56f737e0..38d96ba935c2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -310,6 +310,7 @@ struct nfs4_layoutreturn { struct nfs4_layoutreturn_res res; struct rpc_cred *cred; struct nfs_client *clp; + struct inode *inode; int rpc_status; }; -- cgit v1.2.3 From a05d59a5673339ef6936d6940cdf68172ce75b9f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 6 Feb 2015 14:30:50 -0500 Subject: tracing: Add condition check to RCU lockdep checks The trace_tlb_flush() tracepoint can be called when a CPU is going offline. When a CPU is offline, RCU is no longer watching that CPU and since the tracepoint is protected by RCU, it must not be called. To prevent the tlb_flush tracepoint from being called when the CPU is offline, it was converted to a TRACE_EVENT_CONDITION where the condition checks if the CPU is online before calling the tracepoint. Unfortunately, this was not enough to stop lockdep from complaining about it. Even though the RCU protected code of the tracepoint will never be called, the condition is hidden within the tracepoint, and even though the condition prevents RCU code from being called, the lockdep checks are outside the tracepoint (this is to test tracepoints even when they are not enabled). Even though tracepoints should be checked to be RCU safe when they are not enabled, the condition should still be considered when checking RCU. Link: http://lkml.kernel.org/r/CA+icZUUGiGDoL5NU8RuxKzFjoLjEKRtUWx=JB8B9a0EQv-eGzQ@mail.gmail.com Fixes: 3a630178fd5f "tracing: generate RCU warnings even when tracepoints are disabled" Cc: stable@vger.kernel.org # 3.18+ Acked-by: Dave Hansen Reported-by: Sedat Dilek Tested-by: Sedat Dilek Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index e08e21e5f601..c72851328ca9 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -173,7 +173,7 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond),,); \ - if (IS_ENABLED(CONFIG_LOCKDEP)) { \ + if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ rcu_read_lock_sched_notrace(); \ rcu_dereference_sched(__tracepoint_##name.funcs);\ rcu_read_unlock_sched_notrace(); \ -- cgit v1.2.3 From 718ba5b87343df303017585200ee182e937eabfc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 18:19:25 -0500 Subject: SUNRPC: Add helpers to prevent socket create from racing The socket lock is currently held by the task that is requesting the connection be established. While that is efficient in the case where the connection happens quickly, it is racy in the case where it doesn't. What we really want is for the connect helper to be able to block access to the socket while it is being set up. This patch does so by arranging to transfer the socket lock from the task that is requesting the connect attempt, and then releasing that lock once everything is done. This scheme also gives us automatic protection against collisions with the RPC close code, so we can kill the cancel_delayed_work_sync() call in xs_close(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ net/sunrpc/xprt.c | 37 +++++++++++++++++++++++++++++++++---- net/sunrpc/xprtsock.c | 7 +++++-- 3 files changed, 41 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9d27ac45b909..2926e618dbc6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); int xs_swapper(struct rpc_xprt *xprt, int enable); +bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); +void xprt_unlock_connect(struct rpc_xprt *, void *); + /* * Reserved bit positions in xprt->state */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ebbefad21a37..ff3574df8344 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -690,6 +690,37 @@ out_abort: spin_unlock(&xprt->transport_lock); } +bool xprt_lock_connect(struct rpc_xprt *xprt, + struct rpc_task *task, + void *cookie) +{ + bool ret = false; + + spin_lock_bh(&xprt->transport_lock); + if (!test_bit(XPRT_LOCKED, &xprt->state)) + goto out; + if (xprt->snd_task != task) + goto out; + xprt->snd_task = cookie; + ret = true; +out: + spin_unlock_bh(&xprt->transport_lock); + return ret; +} + +void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) +{ + spin_lock_bh(&xprt->transport_lock); + if (xprt->snd_task != cookie) + goto out; + if (!test_bit(XPRT_LOCKED, &xprt->state)) + goto out; + xprt->snd_task =NULL; + xprt->ops->release_xprt(xprt, NULL); +out: + spin_unlock_bh(&xprt->transport_lock); +} + /** * xprt_connect - schedule a transport connect operation * @task: RPC task that is requesting the connect @@ -712,9 +743,7 @@ void xprt_connect(struct rpc_task *task) if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) xprt->ops->close(xprt); - if (xprt_connected(xprt)) - xprt_release_write(xprt, task); - else { + if (!xprt_connected(xprt)) { task->tk_rqstp->rq_bytes_sent = 0; task->tk_timeout = task->tk_rqstp->rq_timeout; rpc_sleep_on(&xprt->pending, task, xprt_connect_status); @@ -726,6 +755,7 @@ void xprt_connect(struct rpc_task *task) xprt->stat.connect_start = jiffies; xprt->ops->connect(xprt, task); } + xprt_release_write(xprt, task); } static void xprt_connect_status(struct rpc_task *task) @@ -758,7 +788,6 @@ static void xprt_connect_status(struct rpc_task *task) dprintk("RPC: %5u xprt_connect_status: error %d connecting to " "server %s\n", task->tk_pid, -task->tk_status, xprt->servername); - xprt_release_write(xprt, task); task->tk_status = -EIO; } } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0fa7ed93dc20..e57d8ed2c4d8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -852,8 +852,6 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); - cancel_delayed_work_sync(&transport->connect_worker); - xs_reset_transport(transport); xprt->reestablish_timeout = 0; @@ -2101,6 +2099,7 @@ static void xs_udp_setup_socket(struct work_struct *work) trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); } @@ -2286,6 +2285,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case 0: case -EINPROGRESS: case -EALREADY: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); return; case -EINVAL: @@ -2303,6 +2303,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) out_eagain: status = -EAGAIN; out: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); } @@ -2325,6 +2326,8 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); + if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", -- cgit v1.2.3 From 4efdd92c921135175a85452cd41273d9e2788db3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 15:34:28 -0500 Subject: SUNRPC: Remove TCP client connection reset hack Instead we rely on SO_REUSEPORT to provide the reconnection semantics that we need for NFSv2/v3. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprtsock.c | 67 +-------------------------------------------- 2 files changed, 1 insertion(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2926e618dbc6..86af854338b5 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -363,7 +363,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) -#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e53a5ca03daf..dbf279cd4494 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -796,8 +796,6 @@ static void xs_error_report(struct sock *sk) dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); - if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state)) - goto out; xprt_wake_pending_tasks(xprt, err); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2102,57 +2100,6 @@ out: xprt_wake_pending_tasks(xprt, status); } -/* - * We need to preserve the port number so the reply cache on the server can - * find our cached RPC replies when we get around to reconnecting. - */ -static void xs_abort_connection(struct sock_xprt *transport) -{ - int result; - struct sockaddr any; - - dprintk("RPC: disconnecting xprt %p to reuse port\n", transport); - - /* - * Disconnect the transport socket by doing a connect operation - * with AF_UNSPEC. This should return immediately... - */ - memset(&any, 0, sizeof(any)); - any.sa_family = AF_UNSPEC; - result = kernel_connect(transport->sock, &any, sizeof(any), 0); - trace_rpc_socket_reset_connection(&transport->xprt, - transport->sock, result); - if (!result) - xs_sock_reset_connection_flags(&transport->xprt); - dprintk("RPC: AF_UNSPEC connect return code %d\n", result); -} - -static void xs_tcp_reuse_connection(struct sock_xprt *transport) -{ - unsigned int state = transport->inet->sk_state; - - if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) { - /* we don't need to abort the connection if the socket - * hasn't undergone a shutdown - */ - if (transport->inet->sk_shutdown == 0) - return; - dprintk("RPC: %s: TCP_CLOSEd and sk_shutdown set to %d\n", - __func__, transport->inet->sk_shutdown); - } - if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) { - /* we don't need to abort the connection if the socket - * hasn't undergone a shutdown - */ - if (transport->inet->sk_shutdown == 0) - return; - dprintk("RPC: %s: ESTABLISHED/SYN_SENT " - "sk_shutdown set to %d\n", - __func__, transport->inet->sk_shutdown); - } - xs_abort_connection(transport); -} - static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -2245,18 +2192,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) status = PTR_ERR(sock); goto out; } - } else { - int abort_and_exit; - - abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, - &xprt->state); - /* "close" the socket, preserving the local port */ - set_bit(XPRT_CONNECTION_REUSE, &xprt->state); - xs_tcp_reuse_connection(transport); - clear_bit(XPRT_CONNECTION_REUSE, &xprt->state); - - if (abort_and_exit) - goto out_eagain; } dprintk("RPC: worker connecting xprt %p via %s to " @@ -2296,9 +2231,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EADDRINUSE: case -ENOBUFS: /* retry with existing socket, after a delay */ + xs_tcp_force_close(xprt); goto out; } -out_eagain: status = -EAGAIN; out: xprt_unlock_connect(xprt, transport); -- cgit v1.2.3 From 505936f59f1e4cd0ff92ae5abc7aae64fb74dbdb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 16:00:01 -0500 Subject: SUNRPC: Cleanup to remove remaining uses of XPRT_CONNECTION_ABORT Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprtsock.c | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 86af854338b5..ae39d478a272 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c65f74019288..2f8db3499a17 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -804,7 +804,6 @@ static void xs_error_report(struct sock *sk) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_atomic(); - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); @@ -1904,7 +1903,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport) struct socket *sock; int status = -EIO; - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); if (status < 0) { @@ -2149,7 +2147,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) int status = -EIO; if (!sock) { - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP, true); -- cgit v1.2.3 From 9e2b9f37760e129cee053cc7b6e7288acc2a7134 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 19:21:27 -0500 Subject: SUNRPC: Remove the redundant XPRT_CONNECTION_CLOSE flag Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprt.c | 1 - net/sunrpc/xprtsock.c | 1 - 3 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ae39d478a272..8b93ef53df3c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ff3574df8344..e3015aede0d9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -683,7 +683,6 @@ xprt_init_autodisconnect(unsigned long data) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); - set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); queue_work(rpciod_workqueue, &xprt->task_cleanup); return; out_abort: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0279e8ffb14a..c72b13e2bdf5 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -804,7 +804,6 @@ static void xs_error_report(struct sock *sk) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_atomic(); - clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_atomic(); -- cgit v1.2.3 From 6ee8e25fc3e916193bce4ebb43d5439e1e2144ab Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 10 Feb 2015 14:08:32 -0800 Subject: fsnotify: fix handling of renames in audit Commit e9fd702a58c4 ("audit: convert audit watches to use fsnotify instead of inotify") broke handling of renames in audit. Audit code wants to update inode number of an inode corresponding to watched name in a directory. When something gets renamed into a directory to a watched name, inotify previously passed moved inode to audit code however new fsnotify code passes directory inode where the change happened. That confuses audit and it starts watching parent directory instead of a file in a directory. This can be observed for example by doing: cd /tmp touch foo bar auditctl -w /tmp/foo touch foo mv bar foo touch foo In audit log we see events like: type=CONFIG_CHANGE msg=audit(1423563584.155:90): auid=1000 ses=2 op="updated rules" path="/tmp/foo" key=(null) list=4 res=1 ... type=PATH msg=audit(1423563584.155:91): item=2 name="bar" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE type=PATH msg=audit(1423563584.155:91): item=3 name="foo" inode=1046842 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE type=PATH msg=audit(1423563584.155:91): item=4 name="foo" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=CREATE ... and that's it - we see event for the first touch after creating the audit rule, we see events for rename but we don't see any event for the last touch. However we start seeing events for unrelated stuff happening in /tmp. Fix the problem by passing moved inode as data in the FS_MOVED_FROM and FS_MOVED_TO events instead of the directory where the change happens. This doesn't introduce any new problems because noone besides audit_watch.c cares about the passed value: fs/notify/fanotify/fanotify.c cares only about FSNOTIFY_EVENT_PATH events. fs/notify/dnotify/dnotify.c doesn't care about passed 'data' value at all. fs/notify/inotify/inotify_fsnotify.c uses 'data' only for FSNOTIFY_EVENT_PATH. kernel/audit_tree.c doesn't care about passed 'data' at all. kernel/audit_watch.c expects moved inode as 'data'. Fixes: e9fd702a58c49db ("audit: convert audit watches to use fsnotify instead of inotify") Signed-off-by: Jan Kara Cc: Paul Moore Cc: Eric Paris Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1c804b057fb1..7ee1774edee5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); - fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); + fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name, + fs_cookie); + fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name, + fs_cookie); if (target) fsnotify_link_count(target); -- cgit v1.2.3 From ccaafd7fd039aebc9359a9799f8558b01f1c2adc Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 10 Feb 2015 14:09:35 -0800 Subject: mm: don't use compound_head() in virt_to_head_page() compound_head() is implemented with assumption that there would be race condition when checking tail flag. This assumption is only true when we try to access arbitrary positioned struct page. The situation that virt_to_head_page() is called is different case. We call virt_to_head_page() only in the range of allocated pages, so there is no race condition on tail flag. In this case, we don't need to handle race condition and we can reduce overhead slightly. This patch implements compound_head_fast() which is similar with compound_head() except tail flag race handling. And then, virt_to_head_page() uses this optimized function to improve performance. I saw 1.8% win in a fast-path loop over kmem_cache_alloc/free, (14.063 ns -> 13.810 ns) if target object is on tail page. Signed-off-by: Joonsoo Kim Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dd5ea3016fc4..2c6fd3c5424a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -446,6 +446,12 @@ static inline struct page *compound_head_by_tail(struct page *tail) return tail; } +/* + * Since either compound page could be dismantled asynchronously in THP + * or we access asynchronously arbitrary positioned struct page, there + * would be tail flag race. To handle this race, we should call + * smp_rmb() before checking tail flag. compound_head_by_tail() did it. + */ static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) @@ -453,6 +459,18 @@ static inline struct page *compound_head(struct page *page) return page; } +/* + * If we access compound page synchronously such as access to + * allocated page, there is no need to handle tail flag race, so we can + * check tail flag directly without any synchronization primitive. + */ +static inline struct page *compound_head_fast(struct page *page) +{ + if (unlikely(PageTail(page))) + return page->first_page; + return page; +} + /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test @@ -531,7 +549,14 @@ static inline void get_page(struct page *page) static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); - return compound_head(page); + + /* + * We don't need to worry about synchronization of tail flag + * when we call virt_to_head_page() since it is only called for + * already allocated page and this page won't be freed until + * this virt_to_head_page() is finished. So use _fast variant. + */ + return compound_head_fast(page); } /* -- cgit v1.2.3 From c8d78c1823f46519473949d33f0d1d33fe21ea16 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:46 -0800 Subject: mm: replace remap_file_pages() syscall with emulation remap_file_pages(2) was invented to be able efficiently map parts of huge file into limited 32-bit virtual address space such as in database workloads. Nonlinear mappings are pain to support and it seems there's no legitimate use-cases nowadays since 64-bit systems are widely available. Let's drop it and get rid of all these special-cased code. The patch replaces the syscall with emulation which creates new VMA on each remap_file_pages(), unless they it can be merged with an adjacent one. I didn't find *any* real code that uses remap_file_pages(2) to test emulation impact on. I've checked Debian code search and source of all packages in ALT Linux. No real users: libc wrappers, mentions in strace, gdb, valgrind and this kind of stuff. There are few basic tests in LTP for the syscall. They work just fine with emulation. To test performance impact, I've written small test case which demonstrate pretty much worst case scenario: map 4G shmfs file, write to begin of every page pgoff of the page, remap pages in reverse order, read every page. The test creates 1 million of VMAs if emulation is in use, so I had to set vm.max_map_count to 1100000 to avoid -ENOMEM. Before: 23.3 ( +- 4.31% ) seconds After: 43.9 ( +- 0.85% ) seconds Slowdown: 1.88x I believe we can live with that. Test case: #define _GNU_SOURCE #include #include #include #include #define MB (1024UL * 1024) #define SIZE (4096 * MB) int main(int argc, char **argv) { unsigned long *p; long i, pass; for (pass = 0; pass < 10; pass++) { p = mmap(NULL, SIZE, PROT_READ|PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (p == MAP_FAILED) { perror("mmap"); return -1; } for (i = 0; i < SIZE / 4096; i++) p[i * 4096 / sizeof(*p)] = i; for (i = 0; i < SIZE / 4096; i++) { if (remap_file_pages(p + i * 4096 / sizeof(*p), 4096, 0, (SIZE - 4096 * (i + 1)) >> 12, 0)) { perror("remap_file_pages"); return -1; } } for (i = SIZE / 4096 - 1; i >= 0; i--) assert(p[i * 4096 / sizeof(*p)] == SIZE / 4096 - i - 1); munmap(p, SIZE); } return 0; } [akpm@linux-foundation.org: fix spello] [sasha.levin@oracle.com: initialize populate before usage] [sasha.levin@oracle.com: grab file ref to prevent race while mmaping] Signed-off-by: "Kirill A. Shutemov" Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Jones Cc: Linus Torvalds Cc: Armin Rigo Signed-off-by: Sasha Levin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/remap_file_pages.txt | 7 +- include/linux/fs.h | 8 +- mm/Makefile | 2 +- mm/fremap.c | 283 ---------------------------------- mm/mmap.c | 69 +++++++++ mm/nommu.c | 8 - 6 files changed, 79 insertions(+), 298 deletions(-) delete mode 100644 mm/fremap.c (limited to 'include/linux') diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt index 560e4363a55d..f609142f406a 100644 --- a/Documentation/vm/remap_file_pages.txt +++ b/Documentation/vm/remap_file_pages.txt @@ -18,10 +18,9 @@ on 32-bit systems to map files bigger than can linearly fit into 32-bit virtual address space. This use-case is not critical anymore since 64-bit systems are widely available. -The plan is to deprecate the syscall and replace it with an emulation. -The emulation will create new VMAs instead of nonlinear mappings. It's -going to work slower for rare users of remap_file_pages() but ABI is -preserved. +The syscall is deprecated and replaced it with an emulation now. The +emulation creates new VMAs instead of nonlinear mappings. It's going to +work slower for rare users of remap_file_pages() but ABI is preserved. One side effect of emulation (apart from performance) is that user can hit vm.max_map_count limit more easily due to additional VMAs. See comment for diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..60c4996df7f3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2481,8 +2481,12 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, - unsigned long size, pgoff_t pgoff); +static inline int generic_file_remap_pages(struct vm_area_struct *vma, + unsigned long addr, unsigned long size, pgoff_t pgoff) +{ + BUG(); + return 0; +} int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/Makefile b/mm/Makefile index 4bf586e66378..3548460ab7b6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -3,7 +3,7 @@ # mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o diff --git a/mm/fremap.c b/mm/fremap.c deleted file mode 100644 index 2805d71cf476..000000000000 --- a/mm/fremap.c +++ /dev/null @@ -1,283 +0,0 @@ -/* - * linux/mm/fremap.c - * - * Explicit pagetable population and nonlinear (random) mappings support. - * - * started by Ingo Molnar, Copyright (C) 2002, 2003 - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include "internal.h" - -static int mm_counter(struct page *page) -{ - return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; -} - -static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - struct page *page; - swp_entry_t entry; - - if (pte_present(pte)) { - flush_cache_page(vma, addr, pte_pfn(pte)); - pte = ptep_clear_flush_notify(vma, addr, ptep); - page = vm_normal_page(vma, addr, pte); - if (page) { - if (pte_dirty(pte)) - set_page_dirty(page); - update_hiwater_rss(mm); - dec_mm_counter(mm, mm_counter(page)); - page_remove_rmap(page); - page_cache_release(page); - } - } else { /* zap_pte() is not called when pte_none() */ - if (!pte_file(pte)) { - update_hiwater_rss(mm); - entry = pte_to_swp_entry(pte); - if (non_swap_entry(entry)) { - if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - dec_mm_counter(mm, mm_counter(page)); - } - } else { - free_swap_and_cache(entry); - dec_mm_counter(mm, MM_SWAPENTS); - } - } - pte_clear_not_present_full(mm, addr, ptep, 0); - } -} - -/* - * Install a file pte to a given virtual memory address, release any - * previously existing mapping. - */ -static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long pgoff, pgprot_t prot) -{ - int err = -ENOMEM; - pte_t *pte, ptfile; - spinlock_t *ptl; - - pte = get_locked_pte(mm, addr, &ptl); - if (!pte) - goto out; - - ptfile = pgoff_to_pte(pgoff); - - if (!pte_none(*pte)) - zap_pte(mm, vma, addr, pte); - - set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); - /* - * We don't need to run update_mmu_cache() here because the "file pte" - * being installed by install_file_pte() is not a real pte - it's a - * non-present entry (like a swap entry), noting what file offset should - * be mapped there when there's a fault (in a non-linear vma where - * that's not obvious). - */ - pte_unmap_unlock(pte, ptl); - err = 0; -out: - return err; -} - -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - struct mm_struct *mm = vma->vm_mm; - int err; - - do { - err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot); - if (err) - return err; - - size -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } while (size); - - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - -/** - * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma - * @start: start of the remapped virtual memory range - * @size: size of the remapped virtual memory range - * @prot: new protection bits of the range (see NOTE) - * @pgoff: to-be-mapped page of the backing store file - * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO. - * - * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma - * (shared backing store file). - * - * This syscall works purely via pagetables, so it's the most efficient - * way to map the same (large) file into a given virtual window. Unlike - * mmap()/mremap() it does not create any new vmas. The new mappings are - * also safe across swapout. - * - * NOTE: the @prot parameter right now is ignored (but must be zero), - * and the vma's default protection is used. Arbitrary protections - * might be implemented in the future. - */ -SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, - unsigned long, prot, unsigned long, pgoff, unsigned long, flags) -{ - struct mm_struct *mm = current->mm; - struct address_space *mapping; - struct vm_area_struct *vma; - int err = -EINVAL; - int has_write_lock = 0; - vm_flags_t vm_flags = 0; - - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " - "See Documentation/vm/remap_file_pages.txt.\n", - current->comm, current->pid); - - if (prot) - return err; - /* - * Sanitize the syscall parameters: - */ - start = start & PAGE_MASK; - size = size & PAGE_MASK; - - /* Does the address range wrap, or is the span zero-sized? */ - if (start + size <= start) - return err; - - /* Does pgoff wrap? */ - if (pgoff + (size >> PAGE_SHIFT) < pgoff) - return err; - - /* Can we represent this offset inside this architecture's pte's? */ -#if PTE_FILE_MAX_BITS < BITS_PER_LONG - if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS)) - return err; -#endif - - /* We need down_write() to change vma->vm_flags. */ - down_read(&mm->mmap_sem); - retry: - vma = find_vma(mm, start); - - /* - * Make sure the vma is shared, that it supports prefaulting, - * and that the remapped range is valid and fully within - * the single existing vma. - */ - if (!vma || !(vma->vm_flags & VM_SHARED)) - goto out; - - if (!vma->vm_ops || !vma->vm_ops->remap_pages) - goto out; - - if (start < vma->vm_start || start + size > vma->vm_end) - goto out; - - /* Must set VM_NONLINEAR before any pages are populated. */ - if (!(vma->vm_flags & VM_NONLINEAR)) { - /* - * vm_private_data is used as a swapout cursor - * in a VM_NONLINEAR vma. - */ - if (vma->vm_private_data) - goto out; - - /* Don't need a nonlinear mapping, exit success */ - if (pgoff == linear_page_index(vma, start)) { - err = 0; - goto out; - } - - if (!has_write_lock) { -get_write_lock: - up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); - has_write_lock = 1; - goto retry; - } - mapping = vma->vm_file->f_mapping; - /* - * page_mkclean doesn't work on nonlinear vmas, so if - * dirty pages need to be accounted, emulate with linear - * vmas. - */ - if (mapping_cap_account_dirty(mapping)) { - unsigned long addr; - struct file *file = get_file(vma->vm_file); - /* mmap_region may free vma; grab the info now */ - vm_flags = vma->vm_flags; - - addr = mmap_region(file, start, size, vm_flags, pgoff); - fput(file); - if (IS_ERR_VALUE(addr)) { - err = addr; - } else { - BUG_ON(addr != start); - err = 0; - } - goto out_freed; - } - i_mmap_lock_write(mapping); - flush_dcache_mmap_lock(mapping); - vma->vm_flags |= VM_NONLINEAR; - vma_interval_tree_remove(vma, &mapping->i_mmap); - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - flush_dcache_mmap_unlock(mapping); - i_mmap_unlock_write(mapping); - } - - if (vma->vm_flags & VM_LOCKED) { - /* - * drop PG_Mlocked flag for over-mapped range - */ - if (!has_write_lock) - goto get_write_lock; - vm_flags = vma->vm_flags; - munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = vm_flags; - } - - mmu_notifier_invalidate_range_start(mm, start, start + size); - err = vma->vm_ops->remap_pages(vma, start, size, pgoff); - mmu_notifier_invalidate_range_end(mm, start, start + size); - - /* - * We can't clear VM_NONLINEAR because we'd have to do - * it after ->populate completes, and that would prevent - * downgrading the lock. (Locks can't be upgraded). - */ - -out: - if (vma) - vm_flags = vma->vm_flags; -out_freed: - if (likely(!has_write_lock)) - up_read(&mm->mmap_sem); - else - up_write(&mm->mmap_sem); - if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) - mm_populate(start, size); - - return err; -} diff --git a/mm/mmap.c b/mm/mmap.c index 7f684d5a8087..e023dc5e59a8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2634,6 +2634,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) return vm_munmap(addr, len); } + +/* + * Emulation of deprecated remap_file_pages() syscall. + */ +SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +{ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; + struct file *file; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + down_write(&mm->mmap_sem); + vma = find_vma(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) + goto out; + + if (start < vma->vm_start || start + size > vma->vm_end) + goto out; + + if (pgoff == linear_page_index(vma, start)) { + ret = 0; + goto out; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) { + flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ + munlock_vma_pages_range(vma, start, start + size); + } + + file = get_file(vma->vm_file); + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); + fput(file); +out: + up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + static inline void verify_mm_writelocked(struct mm_struct *mm) { #ifdef CONFIG_DEBUG_VM diff --git a/mm/nommu.c b/mm/nommu.c index 28bd8c4dff6f..541bed64e348 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1984,14 +1984,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_map_pages); -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { -- cgit v1.2.3 From 8a5f14a23177061ec11daeaa3d09d0765d785c47 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:49 -0800 Subject: mm: drop support of non-linear mapping from unmap/zap codepath We have remap_file_pages(2) emulation in -mm tree for few release cycles and we plan to have it mainline in v3.20. This patchset removes rest of VM_NONLINEAR infrastructure. Patches 1-8 take care about generic code. They are pretty straight-forward and can be applied without other of patches. Rest patches removes pte_file()-related stuff from architecture-specific code. It usually frees up one bit in non-present pte. I've tried to reuse that bit for swap offset, where I was able to figure out how to do that. For obvious reason I cannot test all that arch-specific code and would like to see acks from maintainers. In total, remap_file_pages(2) required about 1.4K lines of not-so-trivial kernel code. That's too much for functionality nobody uses. Tested-by: Felipe Balbi This patch (of 38): We don't create non-linear mappings anymore. Let's drop code which handles them on unmap/zap. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/madvise.c | 9 +----- mm/memory.c | 82 ++++++++++++++---------------------------------------- 3 files changed, 22 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2c6fd3c5424a..600ef5ed4698 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1146,7 +1146,6 @@ extern void user_shm_unlock(size_t, struct user_struct *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct vm_area_struct *nonlinear_vma; /* Check page->index if set */ struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ diff --git a/mm/madvise.c b/mm/madvise.c index a271adc93289..917754d26c17 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -278,14 +278,7 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) return -EINVAL; - if (unlikely(vma->vm_flags & VM_NONLINEAR)) { - struct zap_details details = { - .nonlinear_vma = vma, - .last_index = ULONG_MAX, - }; - zap_page_range(vma, start, end - start, &details); - } else - zap_page_range(vma, start, end - start, NULL); + zap_page_range(vma, start, end - start, NULL); return 0; } diff --git a/mm/memory.c b/mm/memory.c index 2c3536cc6c63..9a3e73b69dad 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1082,6 +1082,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; pte_t *start_pte; pte_t *pte; + swp_entry_t entry; again: init_rss_vec(rss); @@ -1107,28 +1108,12 @@ again: if (details->check_mapping && details->check_mapping != page->mapping) continue; - /* - * Each page->index must be checked when - * invalidating or truncating nonlinear. - */ - if (details->nonlinear_vma && - (page->index < details->first_index || - page->index > details->last_index)) - continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (unlikely(details) && details->nonlinear_vma - && linear_page_index(details->nonlinear_vma, - addr) != page->index) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(ptent)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, addr, pte, ptfile); - } if (PageAnon(page)) rss[MM_ANONPAGES]--; else { @@ -1151,33 +1136,25 @@ again: } continue; } - /* - * If details->check_mapping, we leave swap entries; - * if details->nonlinear_vma, we leave file entries. - */ + /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; - if (pte_file(ptent)) { - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) - print_bad_pte(vma, addr, ptent, NULL); - } else { - swp_entry_t entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) - rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; + entry = pte_to_swp_entry(ptent); + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; - page = migration_entry_to_page(entry); + page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; - } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1277,7 +1254,7 @@ static void unmap_page_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; - if (details && !details->check_mapping && !details->nonlinear_vma) + if (details && !details->check_mapping) details = NULL; BUG_ON(addr >= end); @@ -1371,7 +1348,7 @@ void unmap_vmas(struct mmu_gather *tlb, * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * Caller must protect the VMA list */ @@ -1397,7 +1374,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * The range must fit into one VMA. */ @@ -2331,25 +2308,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, } } -static inline void unmap_mapping_range_list(struct list_head *head, - struct zap_details *details) -{ - struct vm_area_struct *vma; - - /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. - */ - list_for_each_entry(vma, head, shared.nonlinear) { - details->nonlinear_vma = vma; - unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); - } -} - /** - * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified page range in the underlying + * file. + * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE @@ -2378,7 +2341,6 @@ void unmap_mapping_range(struct address_space *mapping, } details.check_mapping = even_cows? NULL: mapping; - details.nonlinear_vma = NULL; details.first_index = hba; details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) @@ -2388,8 +2350,6 @@ void unmap_mapping_range(struct address_space *mapping, i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) - unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL(unmap_mapping_range); -- cgit v1.2.3 From 9b4bdd2ffab9557ac43af7dff02e7dab1c8c58bd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:51 -0800 Subject: mm: drop support of non-linear mapping from fault codepath We don't create non-linear mappings anymore. Let's drop code which handles them on page fault. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 16 ++++++-------- mm/memory.c | 65 ++++++++---------------------------------------------- 2 files changed, 16 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 600ef5ed4698..376e5c325dee 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -206,21 +206,19 @@ extern unsigned int kobjsize(const void *objp); extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ -#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ -#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ -#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ -#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ -#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ -#define FAULT_FLAG_TRIED 0x40 /* second try */ -#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */ +#define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */ +#define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */ +#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */ +#define FAULT_FLAG_TRIED 0x20 /* Second try */ +#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * - * pgoff should be used in favour of virtual_address, if possible. If pgoff - * is used, one may implement ->remap_pages to get nonlinear mapping support. + * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ diff --git a/mm/memory.c b/mm/memory.c index 9a3e73b69dad..43a53743cbb4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1899,12 +1899,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, EXPORT_SYMBOL_GPL(apply_to_page_range); /* - * handle_pte_fault chooses page fault handler according to an entry - * which was read non-atomically. Before making any commitment, on - * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault - * must check under lock before unmapping the pte and proceeding - * (but do_wp_page is only called after already making such a check; + * handle_pte_fault chooses page fault handler according to an entry which was + * read non-atomically. Before making any commitment, on those architectures + * or configurations (e.g. i386 with PAE) which might give a mix of unmatched + * parts, do_swap_page must check under lock before unmapping the pte and + * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, @@ -2710,8 +2709,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) - entry = pte_mksoft_dirty(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); @@ -2846,8 +2843,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && - fault_around_bytes >> PAGE_SHIFT > 1) { + if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) @@ -2992,7 +2988,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { @@ -3009,46 +3005,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -/* - * Fault of a previously existing named mapping. Repopulate the pte - * from the encoded file_pte if possible. This enables swappable - * nonlinear vmas. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with pte unmapped and unlocked. - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). - */ -static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) -{ - pgoff_t pgoff; - - flags |= FAULT_FLAG_NONLINEAR; - - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return 0; - - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_SIGBUS; - } - - pgoff = pte_to_pgoff(orig_pte); - if (!(flags & FAULT_FLAG_WRITE)) - return do_read_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - if (!(vma->vm_flags & VM_SHARED)) - return do_cow_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); -} - static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) @@ -3176,15 +3132,12 @@ static int handle_pte_fault(struct mm_struct *mm, if (pte_none(entry)) { if (vma->vm_ops) { if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, - pte, pmd, flags, entry); + return do_fault(mm, vma, address, pte, + pmd, flags, entry); } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } - if (pte_file(entry)) - return do_nonlinear_fault(mm, vma, address, - pte, pmd, flags, entry); return do_swap_page(mm, vma, address, pte, pmd, flags, entry); } -- cgit v1.2.3 From d83a08db5ba6072caa658745881f4baa9bad6a08 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:54 -0800 Subject: mm: drop vm_ops->remap_pages and generic_file_remap_pages() stub Nobody uses it anymore. [akpm@linux-foundation.org: fix filemap_xip.c] Signed-off-by: Kirill A. Shutemov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_file.c | 2 -- fs/btrfs/file.c | 1 - fs/ceph/addr.c | 1 - fs/cifs/file.c | 1 - fs/ext4/file.c | 1 - fs/f2fs/file.c | 1 - fs/fuse/file.c | 1 - fs/gfs2/file.c | 1 - fs/nfs/file.c | 1 - fs/nilfs2/file.c | 1 - fs/ocfs2/mmap.c | 1 - fs/ubifs/file.c | 1 - fs/xfs/xfs_file.c | 1 - include/linux/fs.h | 6 ------ include/linux/mm.h | 3 --- mm/filemap.c | 1 - mm/filemap_xip.c | 1 - mm/shmem.c | 1 - 18 files changed, 26 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 5594505e6e73..b40133796b87 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -831,7 +831,6 @@ static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { @@ -839,7 +838,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4090259569b..a606ab551296 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = btrfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c81c0e004588..24be059fd1f8 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1569,7 +1569,6 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = ceph_filemap_fault, .page_mkwrite = ceph_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 74f12877493a..294ff302a237 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3248,7 +3248,6 @@ static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = cifs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8131be8c0af3..7cb592386121 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -195,7 +195,6 @@ static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3c27e0ecb3bc..5674ba13102b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -92,7 +92,6 @@ static const struct vm_operations_struct f2fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int get_parent_ino(struct inode *inode, nid_t *pino) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 760b2c552197..d769e594855b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2062,7 +2062,6 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = fuse_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6e600abf694a..ec9c2d33477a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -498,7 +498,6 @@ static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = gfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /** diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 2ab6f00dba5b..94712fc781fa 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -646,7 +646,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 3a03e0aea1fb..a8c728acb7a8 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -128,7 +128,6 @@ static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nilfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 10d66c75cecb..9581d190f6e1 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,7 +173,6 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 538519ee37d9..035e51011444 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,7 +1536,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ubifs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 13e974e6a889..ac7f1e8f92b3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1384,5 +1384,4 @@ static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = xfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 60c4996df7f3..47f557c7ef7e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2481,12 +2481,6 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -static inline int generic_file_remap_pages(struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/include/linux/mm.h b/include/linux/mm.h index 376e5c325dee..2ddd9d1d6268 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -285,9 +285,6 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif - /* called by sys_remap_file_pages() to populate non-linear mapping */ - int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff); }; struct mmu_gather; diff --git a/mm/filemap.c b/mm/filemap.c index 673e4581a2e5..bf7a27142704 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2087,7 +2087,6 @@ const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 0d105aeff82f..70c09da1a419 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -301,7 +301,6 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) diff --git a/mm/shmem.c b/mm/shmem.c index 993e6ba689cc..b3e403181981 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3201,7 +3201,6 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif - .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, -- cgit v1.2.3 From 27ba0644ea9dfe6e7693abc85837b60e40583b96 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:59 -0800 Subject: rmap: drop support of non-linear mappings We don't create non-linear mappings anymore. Let's drop code which handles them in rmap. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cachetlb.txt | 8 +- fs/inode.c | 1 - include/linux/fs.h | 4 +- include/linux/mm.h | 6 -- include/linux/mm_types.h | 4 +- include/linux/rmap.h | 2 - kernel/fork.c | 8 +- mm/migrate.c | 32 ------- mm/mmap.c | 24 ++--- mm/rmap.c | 225 +-------------------------------------------- mm/swap.c | 4 +- 11 files changed, 18 insertions(+), 300 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index d79b008e4a32..3f9f808b5119 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -317,10 +317,10 @@ maps this page at its virtual address. about doing this. The idea is, first at flush_dcache_page() time, if - page->mapping->i_mmap is an empty tree and ->i_mmap_nonlinear - an empty list, just mark the architecture private page flag bit. - Later, in update_mmu_cache(), a check is made of this flag bit, - and if set the flush is done and the flag bit is cleared. + page->mapping->i_mmap is an empty tree, just mark the architecture + private page flag bit. Later, in update_mmu_cache(), a check is + made of this flag bit, and if set the flush is done and the flag + bit is cleared. IMPORTANT NOTE: It is often important, if you defer the flush, that the actual flush occurs on the same CPU diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..c760fac33c92 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -355,7 +355,6 @@ void address_space_init_once(struct address_space *mapping) INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT; - INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); } EXPORT_SYMBOL(address_space_init_once); diff --git a/include/linux/fs.h b/include/linux/fs.h index 47f557c7ef7e..60acab209701 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -401,7 +401,6 @@ struct address_space { spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root i_mmap; /* tree of private and shared mappings */ - struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -493,8 +492,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap) || - !list_empty(&mapping->i_mmap_nonlinear); + return !RB_EMPTY_ROOT(&mapping->i_mmap); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ddd9d1d6268..18391eec4864 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1796,12 +1796,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) -static inline void vma_nonlinear_insert(struct vm_area_struct *vma, - struct list_head *list) -{ - list_add_tail(&vma->shared.nonlinear, list); -} - void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6d34aa266a8c..3b1d20fb0848 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -273,15 +273,13 @@ struct vm_area_struct { /* * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree, or - * linkage of vma in the address_space->i_mmap_nonlinear list. + * linkage into the address_space->i_mmap interval tree. */ union { struct { struct rb_node rb; unsigned long rb_subtree_last; } linear; - struct list_head nonlinear; } shared; /* diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d9d7e7e56352..b38f559130d5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -246,7 +246,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition - * file_nonlinear: for handling file nonlinear mapping * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ @@ -255,7 +254,6 @@ struct rmap_walk_control { int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); - int (*file_nonlinear)(struct page *, struct address_space *, void *arg); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; diff --git a/kernel/fork.c b/kernel/fork.c index 4dc2ddade9f1..b379d9abddc7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -438,12 +438,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ - if (unlikely(tmp->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(tmp, - &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert_after(tmp, mpnt, - &mapping->i_mmap); + vma_interval_tree_insert_after(tmp, mpnt, + &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } diff --git a/mm/migrate.c b/mm/migrate.c index 344cdf692fc8..6e284bcca8bb 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -178,37 +178,6 @@ out: return SWAP_AGAIN; } -/* - * Congratulations to trinity for discovering this bug. - * mm/fremap.c's remap_file_pages() accepts any range within a single vma to - * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then - * replace the specified range by file ptes throughout (maybe populated after). - * If page migration finds a page within that range, while it's still located - * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: - * zap_pte() clears the temporary migration entry before mmap_sem is dropped. - * But if the migrating page is in a part of the vma outside the range to be - * remapped, then it will not be cleared, and remove_migration_ptes() needs to - * deal with it. Fortunately, this part of the vma is of course still linear, - * so we just need to use linear location on the nonlinear list. - */ -static int remove_linear_migration_ptes_from_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long addr; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (addr >= vma->vm_start && addr < vma->vm_end) - remove_migration_pte(page, vma, addr, arg); - } - return SWAP_AGAIN; -} - /* * Get rid of all migration entries and replace them by * references to the indicated page. @@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, - .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); diff --git a/mm/mmap.c b/mm/mmap.c index e023dc5e59a8..14d84666e8ba 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.nonlinear); - else - vma_interval_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } @@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -789,14 +783,11 @@ again: remove_next = 1 + (end > next->vm_end); if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) { - root = &mapping->i_mmap; - uprobe_munmap(vma, vma->vm_start, vma->vm_end); + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); - if (adjust_next) - uprobe_munmap(next, next->vm_start, - next->vm_end); - } + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { @@ -3177,8 +3168,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of - * altering the vma layout (for example populate_range() with - * nonlinear vmas). It's also needed in write mode to avoid new + * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row diff --git a/mm/rmap.c b/mm/rmap.c index 71cd5bd0c17d..70b32498d4f2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -590,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -1274,7 +1273,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); - BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ @@ -1316,211 +1314,6 @@ out_mlock: return ret; } -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, - struct vm_area_struct *vma, struct page *check_page) -{ - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; - struct page *page; - unsigned long address; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - unsigned long end; - int ret = SWAP_AGAIN; - int locked_vma = 0; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return ret; - - mmun_start = address; - mmun_end = end; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - /* - * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - if (page == check_page) { - /* we know we have check_page locked */ - mlock_vma_page(page); - ret = SWAP_MLOCK; - } else if (trylock_page(page)) { - /* - * If we can lock the page, perform mlock. - * Otherwise leave the page alone, it will be - * eventually encountered again later. - */ - mlock_vma_page(page); - unlock_page(page); - } - continue; /* don't unmap */ - } - - /* - * No need for _notify because we're within an - * mmu_notifier_invalidate_range_ {start|end} scope. - */ - if (ptep_clear_flush_young(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); - - /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(pteval)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, address, pte, ptfile); - } - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*mapcount)--; - } - pte_unmap_unlock(pte - 1, ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (locked_vma) - up_read(&vma->vm_mm->mmap_sem); - return ret; -} - -static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - return SWAP_FAIL; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - return ret; - - cond_resched(); - - max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; - if (max_nl_cursor == 0) - max_nl_cursor = CLUSTER_SIZE; - - do { - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - while (cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - return ret; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * in locked vmas). Reset cursor on all unreserved nonlinear - * vmas, now forgetting on which ones it had fallen behind. - */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) - vma->vm_private_data = NULL; - - return ret; -} - bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1566,7 +1359,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .file_nonlinear = try_to_unmap_nonlinear, .anon_lock = page_lock_anon_vma_read, }; @@ -1612,12 +1404,6 @@ int try_to_munlock(struct page *page) .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, - /* - * We don't bother to try to find the munlocked page in - * nonlinears. It's costly. Instead, later, page reclaim logic - * may call try_to_unmap() and recover PG_mlocked lazily. - */ - .file_nonlinear = NULL, .anon_lock = page_lock_anon_vma_read, }; @@ -1748,13 +1534,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; } - if (!rwc->file_nonlinear) - goto done; - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto done; - - ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: i_mmap_unlock_read(mapping); return ret; diff --git a/mm/swap.c b/mm/swap.c index 8a12b33936b4..5b3087228b99 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1140,10 +1140,8 @@ void __init swap_setup(void) if (bdi_init(swapper_spaces[0].backing_dev_info)) panic("Failed to init swap bdi"); - for (i = 0; i < MAX_SWAPFILES; i++) { + for (i = 0; i < MAX_SWAPFILES; i++) spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } #endif /* Use a smaller cluster for small-memory machines */ -- cgit v1.2.3 From ac51b934f3912582d3c897c6c4d09b32ea57b2c7 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:10:02 -0800 Subject: mm: replace vma->sharead.linear with vma->shared After removing vma->shared.nonlinear we have only one member of vma->shared union, which doesn't make much sense. This patch drops the union and move struct vma->shared.linear to vma->shared. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 8 +++----- mm/interval_tree.c | 34 +++++++++++++++++----------------- 2 files changed, 20 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3b1d20fb0848..07c8bd3f7b48 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -275,11 +275,9 @@ struct vm_area_struct { * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. */ - union { - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } linear; + struct { + struct rb_node rb; + unsigned long rb_subtree_last; } shared; /* diff --git a/mm/interval_tree.c b/mm/interval_tree.c index 8da581fa9060..f2c2492681bf 100644 --- a/mm/interval_tree.c +++ b/mm/interval_tree.c @@ -21,8 +21,8 @@ static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1; } -INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb, - unsigned long, shared.linear.rb_subtree_last, +INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, + unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ @@ -36,26 +36,26 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); - if (!prev->shared.linear.rb.rb_right) { + if (!prev->shared.rb.rb_right) { parent = prev; - link = &prev->shared.linear.rb.rb_right; + link = &prev->shared.rb.rb_right; } else { - parent = rb_entry(prev->shared.linear.rb.rb_right, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; - while (parent->shared.linear.rb.rb_left) { - parent = rb_entry(parent->shared.linear.rb.rb_left, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; + parent = rb_entry(prev->shared.rb.rb_right, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + while (parent->shared.rb.rb_left) { + parent = rb_entry(parent->shared.rb.rb_left, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; } - link = &parent->shared.linear.rb.rb_left; + link = &parent->shared.rb.rb_left; } - node->shared.linear.rb_subtree_last = last; - rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link); - rb_insert_augmented(&node->shared.linear.rb, root, + node->shared.rb_subtree_last = last; + rb_link_node(&node->shared.rb, &parent->shared.rb, link); + rb_insert_augmented(&node->shared.rb, root, &vma_interval_tree_augment); } -- cgit v1.2.3 From 0661a33611fca12570cba48d9344ce68834ee86c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:10:04 -0800 Subject: mm: remove rest usage of VM_NONLINEAR and pte_file() One bit in ->vm_flags is unused now! Signed-off-by: Kirill A. Shutemov Cc: Dan Carpenter Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_vma_manager.c | 3 +- include/linux/mm.h | 1 - include/linux/swapops.h | 4 +- mm/debug.c | 1 - mm/gup.c | 2 +- mm/ksm.c | 2 +- mm/madvise.c | 4 +- mm/memcontrol.c | 7 +--- mm/memory.c | 78 +++++++++++++++++++-------------------- mm/mincore.c | 9 +---- mm/mprotect.c | 2 +- mm/mremap.c | 2 - mm/msync.c | 5 +-- 13 files changed, 49 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index 63b471205072..68c1f32fb086 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -50,8 +50,7 @@ * * You must not use multiple offset managers on a single address_space. * Otherwise, mm-core will be unable to tear down memory mappings as the VM will - * no longer be linear. Please use VM_NONLINEAR in that case and implement your - * own offset managers. + * no longer be linear. * * This offset manager works on page-based addresses. That is, every argument * and return code (with the exception of drm_vma_node_offset_addr()) is given diff --git a/include/linux/mm.h b/include/linux/mm.h index 18391eec4864..a0da685bdb82 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -138,7 +138,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ -#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_ARCH_2 0x02000000 #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6adfb7bfbf44..50cbc876be56 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry) /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { - return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte); + return !pte_none(pte) && !pte_present_nonuma(pte); } #endif @@ -66,7 +66,6 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; - BUG_ON(pte_file(pte)); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); @@ -82,7 +81,6 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry) swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); - BUG_ON(pte_file(__swp_entry_to_pte(arch_entry))); return __swp_entry_to_pte(arch_entry); } diff --git a/mm/debug.c b/mm/debug.c index 0e58f3211f89..d69cb5a7ba9a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -130,7 +130,6 @@ static const struct trace_print_flags vmaflags_names[] = { {VM_ACCOUNT, "account" }, {VM_NORESERVE, "noreserve" }, {VM_HUGETLB, "hugetlb" }, - {VM_NONLINEAR, "nonlinear" }, #if defined(CONFIG_X86) {VM_PAT, "pat" }, #elif defined(CONFIG_PPC) diff --git a/mm/gup.c b/mm/gup.c index 8dd50ce6326f..12bc2bc33da7 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -55,7 +55,7 @@ retry: */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; - if (pte_none(pte) || pte_file(pte)) + if (pte_none(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) diff --git a/mm/ksm.c b/mm/ksm.c index 15647fb0394f..4162dce2eb44 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1748,7 +1748,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, */ if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP)) + VM_HUGETLB | VM_MIXEDMAP)) return 0; /* just ignore the advice */ #ifdef VM_SAO diff --git a/mm/madvise.c b/mm/madvise.c index 917754d26c17..d79fb5e8f80a 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -155,7 +155,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, pte = *(orig_pte + ((index - start) / PAGE_SIZE)); pte_unmap_unlock(orig_pte, ptl); - if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + if (pte_present(pte) || pte_none(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) @@ -296,7 +296,7 @@ static long madvise_remove(struct vm_area_struct *vma, *prev = NULL; /* tell sys_madvise we drop mmap_sem */ - if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) + if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB)) return -EINVAL; f = vma->vm_file; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2f6893c2f01b..8b58701b9647 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4926,10 +4926,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, return NULL; mapping = vma->vm_file->f_mapping; - if (pte_none(ptent)) - pgoff = linear_page_index(vma, addr); - else /* pte_file(ptent) is true */ - pgoff = pte_to_pgoff(ptent); + pgoff = linear_page_index(vma, addr); /* page is moved even if it's not RSS of this task(page-faulted). */ #ifdef CONFIG_SWAP @@ -4961,7 +4958,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, page = mc_handle_present_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, addr, ptent, &ent); - else if (pte_none(ptent) || pte_file(ptent)) + else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent); if (!page && !ent.val) diff --git a/mm/memory.c b/mm/memory.c index 43a53743cbb4..9aa09217fe20 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -811,42 +811,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { - if (!pte_file(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + set_pte_at(src_mm, addr, src_pte, pte); } } goto out_set_pte; @@ -1020,11 +1018,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | - VM_PFNMAP | VM_MIXEDMAP))) { - if (!vma->anon_vma) - return 0; - } + if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !vma->anon_vma) + return 0; if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); diff --git a/mm/mincore.c b/mm/mincore.c index c8c528b36641..46527c023e0c 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -124,17 +124,13 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { pte_t pte = *ptep; - pgoff_t pgoff; next = addr + PAGE_SIZE; if (pte_none(pte)) mincore_unmapped_range(vma, addr, next, vec); else if (pte_present(pte)) *vec = 1; - else if (pte_file(pte)) { - pgoff = pte_to_pgoff(pte); - *vec = mincore_page(vma->vm_file->f_mapping, pgoff); - } else { /* pte is a swap entry */ + else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); if (non_swap_entry(entry)) { @@ -145,9 +141,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, *vec = 1; } else { #ifdef CONFIG_SWAP - pgoff = entry.val; *vec = mincore_page(swap_address_space(entry), - pgoff); + entry.val); #else WARN_ON(1); *vec = 1; diff --git a/mm/mprotect.c b/mm/mprotect.c index ace93454ce8e..33121662f08b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -105,7 +105,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } if (updated) pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { + } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { diff --git a/mm/mremap.c b/mm/mremap.c index 17fa018f5f39..57dadc025c64 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -81,8 +81,6 @@ static pte_t move_soft_dirty_pte(pte_t pte) pte = pte_mksoft_dirty(pte); else if (is_swap_pte(pte)) pte = pte_swp_mksoft_dirty(pte); - else if (pte_file(pte)) - pte = pte_file_mksoft_dirty(pte); #endif return pte; } diff --git a/mm/msync.c b/mm/msync.c index 992a1673d488..bb04d53ae852 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -86,10 +86,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - if (vma->vm_flags & VM_NONLINEAR) - error = vfs_fsync(file, 1); - else - error = vfs_fsync_range(file, fstart, fend, 1); + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; -- cgit v1.2.3 From 753162cd849c45580fb5aaa7f3597c81e74e391c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 10 Feb 2015 14:11:36 -0800 Subject: mm: hugetlb: fix type of hugetlb_treat_as_movable variable hugetlb_treat_as_movable declared as unsigned long, but proc_dointvec() used for parsing it: static struct ctl_table vm_table[] = { ... { .procname = "hugepages_treat_as_movable", .data = &hugepages_treat_as_movable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, This seems harmless, but it's better to use int type here. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Manfred Spraul Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 431b7fc605c9..7d7856359920 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -86,7 +86,7 @@ void free_huge_page(struct page *page); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); #endif -extern unsigned long hugepages_treat_as_movable; +extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 85032de5e20f..be0e5d0db5ec 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -35,7 +35,7 @@ #include #include "internal.h" -unsigned long hugepages_treat_as_movable; +int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; -- cgit v1.2.3 From dbf22eb6d8675fc173154d9f1bd1bd0fda53a001 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:41 -0800 Subject: memcg: zap __memcg_{charge,uncharge}_slab They are simple wrappers around memcg_{charge,uncharge}_kmem, so let's zap them and call these functions directly. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 21 +++------------------ mm/slab.h | 4 ++-- 3 files changed, 8 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7c95af8d552c..18ccb2988979 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -403,8 +403,9 @@ void memcg_update_array_size(int num_groups); struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order); -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order); +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages); +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); int __memcg_cleanup_cache_params(struct kmem_cache *s); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8b58701b9647..e229e3ad615c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2495,8 +2495,8 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); } -static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, - unsigned long nr_pages) +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages) { struct page_counter *counter; int ret = 0; @@ -2533,8 +2533,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, return ret; } -static void memcg_uncharge_kmem(struct mem_cgroup *memcg, - unsigned long nr_pages) +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages) { page_counter_uncharge(&memcg->memory, nr_pages); if (do_swap_account) @@ -2767,20 +2766,6 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, current->memcg_kmem_skip_account = 0; } -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) -{ - unsigned int nr_pages = 1 << order; - - return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); -} - -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) -{ - unsigned int nr_pages = 1 << order; - - memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages); -} - /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. diff --git a/mm/slab.h b/mm/slab.h index 1cf4005482dd..90430d6f665e 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -235,7 +235,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s, return 0; if (is_root_cache(s)) return 0; - return __memcg_charge_slab(s, gfp, order); + return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order); } static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) @@ -244,7 +244,7 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) return; if (is_root_cache(s)) return; - __memcg_uncharge_slab(s, order); + memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order); } #else static inline bool is_root_cache(struct kmem_cache *s) -- cgit v1.2.3 From 3e0350a36414a73c5c2d1e354f8c0ab4ace1296d Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:44 -0800 Subject: memcg: zap memcg_name argument of memcg_create_kmem_cache Instead of passing the name of the memory cgroup which the cache is created for in the memcg_name_argument, let's obtain it immediately in memcg_create_kmem_cache. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 3 +-- mm/memcontrol.c | 5 +---- mm/slab_common.c | 9 +++++---- 3 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9a139b637069..eca9ed303a1b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -117,8 +117,7 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, - struct kmem_cache *, - const char *); + struct kmem_cache *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e229e3ad615c..baf7eb27e3ae 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2607,8 +2607,6 @@ void memcg_update_array_size(int num) static void memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *root_cache) { - static char memcg_name_buf[NAME_MAX + 1]; /* protected by - memcg_slab_mutex */ struct kmem_cache *cachep; int id; @@ -2624,8 +2622,7 @@ static void memcg_register_cache(struct mem_cgroup *memcg, if (cache_from_memcg_idx(root_cache, id)) return; - cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); - cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); + cachep = memcg_create_kmem_cache(memcg, root_cache); /* * If we could not create a memcg cache, do not complain, because * that's not critical at all as we can always proceed with the root diff --git a/mm/slab_common.c b/mm/slab_common.c index 67f182c10f24..1b782a2d3b3d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -430,16 +430,15 @@ EXPORT_SYMBOL(kmem_cache_create); * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. - * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache, - const char *memcg_name) + struct kmem_cache *root_cache) { + static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ struct kmem_cache *s = NULL; char *cache_name; @@ -448,8 +447,10 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); + cgroup_name(mem_cgroup_css(memcg)->cgroup, + memcg_name_buf, sizeof(memcg_name_buf)); cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), memcg_name); + memcg_cache_id(memcg), memcg_name_buf); if (!cache_name) goto out_unlock; -- cgit v1.2.3 From d5b3cf7139b8770af4ed8bb36a1ab9d290ac39e9 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:47 -0800 Subject: memcg: zap memcg_slab_caches and memcg_slab_mutex mem_cgroup->memcg_slab_caches is a list of kmem caches corresponding to the given cgroup. Currently, it is only used on css free in order to destroy all caches corresponding to the memory cgroup being freed. The list is protected by memcg_slab_mutex. The mutex is also used to protect kmem_cache->memcg_params->memcg_caches arrays and synchronizes kmem_cache_destroy vs memcg_unregister_all_caches. However, we can perfectly get on without these two. To destroy all caches corresponding to a memory cgroup, we can walk over the global list of kmem caches, slab_caches, and we can do all the synchronization stuff using the slab_mutex instead of the memcg_slab_mutex. This patch therefore gets rid of the memcg_slab_caches and memcg_slab_mutex. Apart from this nice cleanup, it also: - assures that rcu_barrier() is called once at max when a root cache is destroyed or a memory cgroup is freed, no matter how many caches have SLAB_DESTROY_BY_RCU flag set; - fixes the race between kmem_cache_destroy and kmem_cache_create that exists, because memcg_cleanup_cache_params, which is called from kmem_cache_destroy after checking that kmem_cache->refcount=0, releases the slab_mutex, which gives kmem_cache_create a chance to make an alias to a cache doomed to be destroyed. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Acked-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 - include/linux/slab.h | 6 +- mm/memcontrol.c | 156 +++++---------------------------------------- mm/slab_common.c | 142 +++++++++++++++++++++++++++++------------ 4 files changed, 120 insertions(+), 186 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 18ccb2988979..fb212e1d700d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -407,8 +407,6 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, unsigned long nr_pages); void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); -int __memcg_cleanup_cache_params(struct kmem_cache *s); - /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. * @gfp: the gfp allocation flags. diff --git a/include/linux/slab.h b/include/linux/slab.h index eca9ed303a1b..2e3b448cfa2d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -116,8 +116,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, - struct kmem_cache *); +void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); +void memcg_destroy_kmem_caches(struct mem_cgroup *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); @@ -490,7 +490,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * Child caches will hold extra metadata needed for its operation. Fields are: * * @memcg: pointer to the memcg this cache belongs to - * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from */ struct memcg_cache_params { @@ -502,7 +501,6 @@ struct memcg_cache_params { }; struct { struct mem_cgroup *memcg; - struct list_head list; struct kmem_cache *root_cache; }; }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index baf7eb27e3ae..f3f8a4f52a0c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -343,9 +343,6 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list, but per-memcg; - * protected by memcg_slab_mutex */ - struct list_head memcg_slab_caches; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -2476,25 +2473,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM -/* - * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or - * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. - */ -static DEFINE_MUTEX(memcg_slab_mutex); - -/* - * This is a bit cumbersome, but it is rarely used and avoids a backpointer - * in the memcg_cache_params struct. - */ -static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) -{ - struct kmem_cache *cachep; - - VM_BUG_ON(p->is_root_cache); - cachep = p->root_cache; - return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); -} - int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, unsigned long nr_pages) { @@ -2578,10 +2556,7 @@ static int memcg_alloc_cache_id(void) else if (size > MEMCG_CACHES_MAX_SIZE) size = MEMCG_CACHES_MAX_SIZE; - mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(size); - mutex_unlock(&memcg_slab_mutex); - if (err) { ida_simple_remove(&kmem_limited_groups, id); return err; @@ -2604,120 +2579,20 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = num; } -static void memcg_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - struct kmem_cache *cachep; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - id = memcg_cache_id(memcg); - - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, id)) - return; - - cachep = memcg_create_kmem_cache(memcg, root_cache); - /* - * If we could not create a memcg cache, do not complain, because - * that's not critical at all as we can always proceed with the root - * cache. - */ - if (!cachep) - return; - - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - - /* - * Since readers won't lock (see cache_from_memcg_idx()), we need a - * barrier here to ensure nobody will see the kmem_cache partially - * initialized. - */ - smp_wmb(); - - BUG_ON(root_cache->memcg_params->memcg_caches[id]); - root_cache->memcg_params->memcg_caches[id] = cachep; -} - -static void memcg_unregister_cache(struct kmem_cache *cachep) -{ - struct kmem_cache *root_cache; - struct mem_cgroup *memcg; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - BUG_ON(is_root_cache(cachep)); - - root_cache = cachep->memcg_params->root_cache; - memcg = cachep->memcg_params->memcg; - id = memcg_cache_id(memcg); - - BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); - root_cache->memcg_params->memcg_caches[id] = NULL; - - list_del(&cachep->memcg_params->list); - - kmem_cache_destroy(cachep); -} - -int __memcg_cleanup_cache_params(struct kmem_cache *s) -{ - struct kmem_cache *c; - int i, failed = 0; - - mutex_lock(&memcg_slab_mutex); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; - - memcg_unregister_cache(c); - - if (cache_from_memcg_idx(s, i)) - failed++; - } - mutex_unlock(&memcg_slab_mutex); - return failed; -} - -static void memcg_unregister_all_caches(struct mem_cgroup *memcg) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *params, *tmp; - - if (!memcg_kmem_is_active(memcg)) - return; - - mutex_lock(&memcg_slab_mutex); - list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { - cachep = memcg_params_to_cache(params); - memcg_unregister_cache(cachep); - } - mutex_unlock(&memcg_slab_mutex); -} - -struct memcg_register_cache_work { +struct memcg_kmem_cache_create_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_register_cache_func(struct work_struct *w) +static void memcg_kmem_cache_create_func(struct work_struct *w) { - struct memcg_register_cache_work *cw = - container_of(w, struct memcg_register_cache_work, work); + struct memcg_kmem_cache_create_work *cw = + container_of(w, struct memcg_kmem_cache_create_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - mutex_lock(&memcg_slab_mutex); - memcg_register_cache(memcg, cachep); - mutex_unlock(&memcg_slab_mutex); + memcg_create_kmem_cache(memcg, cachep); css_put(&memcg->css); kfree(cw); @@ -2726,10 +2601,10 @@ static void memcg_register_cache_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct memcg_register_cache_work *cw; + struct memcg_kmem_cache_create_work *cw; cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (!cw) @@ -2739,18 +2614,18 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; + INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_register_cache will recurse. + * in __memcg_schedule_kmem_cache_create will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -2759,7 +2634,7 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ current->memcg_kmem_skip_account = 1; - __memcg_schedule_register_cache(memcg, cachep); + __memcg_schedule_kmem_cache_create(memcg, cachep); current->memcg_kmem_skip_account = 0; } @@ -2807,7 +2682,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) * could happen with the slab_mutex held. So it's better to * defer everything. */ - memcg_schedule_register_cache(memcg, cachep); + memcg_schedule_kmem_cache_create(memcg, cachep); out: css_put(&memcg->css); return cachep; @@ -4136,7 +4011,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) static void memcg_destroy_kmem(struct mem_cgroup *memcg) { - memcg_unregister_all_caches(memcg); + memcg_destroy_kmem_caches(memcg); mem_cgroup_sockets_destroy(memcg); } #else @@ -4664,7 +4539,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&memcg->event_list_lock); #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); #endif return &memcg->css; diff --git a/mm/slab_common.c b/mm/slab_common.c index 1b782a2d3b3d..6e1e4cf65836 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -425,6 +425,49 @@ out_unlock: } EXPORT_SYMBOL(kmem_cache_create); +static int do_kmem_cache_shutdown(struct kmem_cache *s, + struct list_head *release, bool *need_rcu_barrier) +{ + if (__kmem_cache_shutdown(s) != 0) { + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + return -EBUSY; + } + + if (s->flags & SLAB_DESTROY_BY_RCU) + *need_rcu_barrier = true; + +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) { + struct kmem_cache *root_cache = s->memcg_params->root_cache; + int memcg_id = memcg_cache_id(s->memcg_params->memcg); + + BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s); + root_cache->memcg_params->memcg_caches[memcg_id] = NULL; + } +#endif + list_move(&s->list, release); + return 0; +} + +static void do_kmem_cache_release(struct list_head *release, + bool need_rcu_barrier) +{ + struct kmem_cache *s, *s2; + + if (need_rcu_barrier) + rcu_barrier(); + + list_for_each_entry_safe(s, s2, release, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + } +} + #ifdef CONFIG_MEMCG_KMEM /* * memcg_create_kmem_cache - Create a cache for a memory cgroup. @@ -435,10 +478,11 @@ EXPORT_SYMBOL(kmem_cache_create); * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) +void memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ + int memcg_id = memcg_cache_id(memcg); struct kmem_cache *s = NULL; char *cache_name; @@ -447,6 +491,14 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, memcg_id)) + goto out_unlock; + cgroup_name(mem_cgroup_css(memcg)->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, @@ -458,49 +510,73 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); + /* + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. + */ if (IS_ERR(s)) { kfree(cache_name); - s = NULL; + goto out_unlock; } + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); + root_cache->memcg_params->memcg_caches[memcg_id] = s; + out_unlock: mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - return s; } -static int memcg_cleanup_cache_params(struct kmem_cache *s) +void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) { - int rc; + LIST_HEAD(release); + bool need_rcu_barrier = false; + struct kmem_cache *s, *s2; - if (!s->memcg_params || - !s->memcg_params->is_root_cache) - return 0; + get_online_cpus(); + get_online_mems(); - mutex_unlock(&slab_mutex); - rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); + list_for_each_entry_safe(s, s2, &slab_caches, list) { + if (is_root_cache(s) || s->memcg_params->memcg != memcg) + continue; + /* + * The cgroup is about to be freed and therefore has no charges + * left. Hence, all its caches must be empty by now. + */ + BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier)); + } + mutex_unlock(&slab_mutex); - return rc; -} -#else -static int memcg_cleanup_cache_params(struct kmem_cache *s) -{ - return 0; + put_online_mems(); + put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) { + memcg_free_cache_params(s); kfree(s->name); kmem_cache_free(kmem_cache, s); } void kmem_cache_destroy(struct kmem_cache *s) { + int i; + LIST_HEAD(release); + bool need_rcu_barrier = false; + bool busy = false; + get_online_cpus(); get_online_mems(); @@ -510,35 +586,23 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; - if (memcg_cleanup_cache_params(s) != 0) - goto out_unlock; + for_each_memcg_cache_index(i) { + struct kmem_cache *c = cache_from_memcg_idx(s, i); - if (__kmem_cache_shutdown(s) != 0) { - printk(KERN_ERR "kmem_cache_destroy %s: " - "Slab cache still has objects\n", s->name); - dump_stack(); - goto out_unlock; + if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier)) + busy = true; } - list_del(&s->list); - - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_remove(s); -#else - slab_kmem_cache_release(s); -#endif - goto out; + if (!busy) + do_kmem_cache_shutdown(s, &release, &need_rcu_barrier); out_unlock: mutex_unlock(&slab_mutex); -out: + put_online_mems(); put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } EXPORT_SYMBOL(kmem_cache_destroy); -- cgit v1.2.3 From e4b294c2d8f73af4cd41ff30638ad0e4769dc56a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:24:46 -0800 Subject: mm: add fields for compound destructor and order into struct page Currently, we use lru.next/lru.prev plus cast to access or set destructor and order of compound page. Let's replace it with explicit fields in struct page. Signed-off-by: Kirill A. Shutemov Acked-by: Jerome Marchand Acked-by: Christoph Lameter Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++----- include/linux/mm_types.h | 8 ++++++++ 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 65db4aee738a..8dd4fde9d2e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -627,29 +627,28 @@ int split_free_page(struct page *page); * prototype for that function and accessor functions. * These are _only_ valid on the head of a PG_compound page. */ -typedef void compound_page_dtor(struct page *); static inline void set_compound_page_dtor(struct page *page, compound_page_dtor *dtor) { - page[1].lru.next = (void *)dtor; + page[1].compound_dtor = dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { - return (compound_page_dtor *)page[1].lru.next; + return page[1].compound_dtor; } static inline int compound_order(struct page *page) { if (!PageHead(page)) return 0; - return (unsigned long)page[1].lru.prev; + return page[1].compound_order; } static inline void set_compound_order(struct page *page, unsigned long order) { - page[1].lru.prev = (void *)order; + page[1].compound_order = order; } #ifdef CONFIG_MMU diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 07c8bd3f7b48..20ff2105b564 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -28,6 +28,8 @@ struct mem_cgroup; IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) +typedef void compound_page_dtor(struct page *); + /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -142,6 +144,12 @@ struct page { struct rcu_head rcu_head; /* Used by SLAB * when destroying via RCU */ + /* First tail page of compound page */ + struct { + compound_page_dtor *compound_dtor; + unsigned long compound_order; + }; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page->ptl */ #endif -- cgit v1.2.3 From 1d148e218a0d0566b1c06f2f45f1436d53b049b2 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:48 -0800 Subject: mm: add VM_BUG_ON_PAGE() to page_mapcount() Add VM_BUG_ON_PAGE() for slab pages. _mapcount is an union with slab struct in struct page, so we must avoid accessing _mapcount if this page is a slab page. Also remove the unneeded bracket. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8dd4fde9d2e5..c6bf813a6b3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -484,7 +484,8 @@ static inline void page_mapcount_reset(struct page *page) static inline int page_mapcount(struct page *page) { - return atomic_read(&(page)->_mapcount) + 1; + VM_BUG_ON_PAGE(PageSlab(page), page); + return atomic_read(&page->_mapcount) + 1; } static inline int page_count(struct page *page) -- cgit v1.2.3 From 56873f43abdcd574b25105867a990f067747b2f4 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:51 -0800 Subject: mm:add KPF_ZERO_PAGE flag for /proc/kpageflags Add KPF_ZERO_PAGE flag for zero_page, so that userspace processes can detect zero_page in /proc/kpageflags, and then do memory analysis more accurately. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/pagemap.txt | 8 ++++++++ fs/proc/page.c | 16 +++++++++++++--- include/linux/huge_mm.h | 12 ++++++++++++ include/uapi/linux/kernel-page-flags.h | 1 + mm/huge_memory.c | 7 +------ tools/vm/page-types.c | 1 + 6 files changed, 36 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 5948e455c4d2..6fbd55ef6b45 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -62,6 +62,8 @@ There are three components to pagemap: 20. NOPAGE 21. KSM 22. THP + 23. BALLOON + 24. ZERO_PAGE Short descriptions to the page flags: @@ -102,6 +104,12 @@ Short descriptions to the page flags: 22. THP contiguous pages which construct transparent hugepages +23. BALLOON + balloon compaction page + +24. ZERO_PAGE + zero page for pfn_zero or huge_zero page + [IO related page flags] 1. ERROR IO error occurred 3. UPTODATE page has up-to-date data diff --git a/fs/proc/page.c b/fs/proc/page.c index 1e3187da1fed..7eee2d8b97d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || - PageAnon(compound_head(page)))) - u |= 1 << KPF_THP; + else if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + if (PageLRU(head) || PageAnon(head)) + u |= 1 << KPF_THP; + else if (is_huge_zero_page(head)) { + u |= 1 << KPF_ZERO_PAGE; + u |= 1 << KPF_THP; + } + } else if (is_zero_pfn(page_to_pfn(page))) + u |= 1 << KPF_ZERO_PAGE; + /* * Caveats on high order pages: page->_count will only be set diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ad9051bab267..f10b20f05159 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,6 +157,13 @@ static inline int hpage_nr_pages(struct page *page) extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); +extern struct page *huge_zero_page; + +static inline bool is_huge_zero_page(struct page *page) +{ + return ACCESS_ONCE(huge_zero_page) == page; +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -206,6 +213,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str return 0; } +static inline bool is_huge_zero_page(struct page *page) +{ + return false; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 2f96d233c980..a6c4962e5d46 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -32,6 +32,7 @@ #define KPF_KSM 21 #define KPF_THP 22 #define KPF_BALLOON 23 +#define KPF_ZERO_PAGE 24 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 817a875f2b8c..889713180980 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -171,12 +171,7 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static struct page *huge_zero_page __read_mostly; - -static inline bool is_huge_zero_page(struct page *page) -{ - return ACCESS_ONCE(huge_zero_page) == page; -} +struct page *huge_zero_page __read_mostly; static inline bool is_huge_zero_pmd(pmd_t pmd) { diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 264fbc297e0b..8bdf16b8ba60 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,6 +133,7 @@ static const char * const page_flag_names[] = { [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", + [KPF_ZERO_PAGE] = "z:zero_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", -- cgit v1.2.3 From 93aa7d95248d04b934eb8e89717c7b8d6400bf2b Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:24:59 -0800 Subject: swap: remove unused mem_cgroup_uncharge_swapcache declaration The body of this function was removed by commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API"). Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 15 --------------- mm/shmem.c | 2 +- 2 files changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 34e8b60ab973..7067eca501e2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -437,16 +437,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_MEMCG -extern void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); -#else -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) -{ -} -#endif - #else /* CONFIG_SWAP */ #define swap_address_space(entry) (NULL) @@ -547,11 +537,6 @@ static inline swp_entry_t get_swap_page(void) return entry; } -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) -{ -} - #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ diff --git a/mm/shmem.c b/mm/shmem.c index b3e403181981..864c878401e6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1131,7 +1131,7 @@ repeat: * truncated or holepunched since swap was confirmed. * shmem_undo_range() will have done some of the * unaccounting, now delete_from_swap_cache() will do - * the rest (including mem_cgroup_uncharge_swapcache). + * the rest. * Reset swap.val? No, leave it so "failed" goes back to * "repeat": reading a hole and writing should succeed. */ -- cgit v1.2.3 From 6de226191d12fce30331ebf024ca3ed24834f0ee Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:25:01 -0800 Subject: mm: memcontrol: track move_lock state internally The complexity of memcg page stat synchronization is currently leaking into the callsites, forcing them to keep track of the move_lock state and the IRQ flags. Simplify the API by tracking it in the memcg. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 +++----- mm/memcontrol.c | 68 ++++++++++++++++++++++++++-------------------- mm/page-writeback.c | 12 +++----- mm/rmap.c | 12 +++----- 4 files changed, 51 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fb212e1d700d..76b4084b8d08 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -138,12 +138,10 @@ static inline bool mem_cgroup_disabled(void) return false; } -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, - unsigned long *flags); -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags); +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val); +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) @@ -285,14 +283,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, unsigned long *flags) +static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { return NULL; } -static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, - bool *locked, unsigned long *flags) +static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f3f8a4f52a0c..028d07c79104 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -325,9 +325,11 @@ struct mem_cgroup { /* * set > 0 if pages under this cgroup are moving to other cgroup. */ - atomic_t moving_account; + atomic_t moving_account; /* taken only while moving_account > 0 */ - spinlock_t move_lock; + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; /* * percpu counter. */ @@ -1977,34 +1979,33 @@ cleanup: /** * mem_cgroup_begin_page_stat - begin a page state statistics transaction * @page: page that is going to change accounted state - * @locked: &memcg->move_lock slowpath was taken - * @flags: IRQ-state flags for &memcg->move_lock * * This function must mark the beginning of an accounted page state * change to prevent double accounting when the page is concurrently * being moved to another memcg: * - * memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + * memcg = mem_cgroup_begin_page_stat(page); * if (TestClearPageState(page)) * mem_cgroup_update_page_stat(memcg, state, -1); - * mem_cgroup_end_page_stat(memcg, locked, flags); - * - * The RCU lock is held throughout the transaction. The fast path can - * get away without acquiring the memcg->move_lock (@locked is false) - * because page moving starts with an RCU grace period. - * - * The RCU lock also protects the memcg from being freed when the page - * state that is going to change is the only thing preventing the page - * from being uncharged. E.g. end-writeback clearing PageWriteback(), - * which allows migration to go ahead and uncharge the page before the - * account transaction might be complete. + * mem_cgroup_end_page_stat(memcg); */ -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, - unsigned long *flags) +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { struct mem_cgroup *memcg; + unsigned long flags; + /* + * The RCU lock is held throughout the transaction. The fast + * path can get away without acquiring the memcg->move_lock + * because page moving starts with an RCU grace period. + * + * The RCU lock also protects the memcg from being freed when + * the page state that is going to change is the only thing + * preventing the page from being uncharged. + * E.g. end-writeback clearing PageWriteback(), which allows + * migration to go ahead and uncharge the page before the + * account transaction might be complete. + */ rcu_read_lock(); if (mem_cgroup_disabled()) @@ -2014,16 +2015,22 @@ again: if (unlikely(!memcg)) return NULL; - *locked = false; if (atomic_read(&memcg->moving_account) <= 0) return memcg; - spin_lock_irqsave(&memcg->move_lock, *flags); + spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page->mem_cgroup) { - spin_unlock_irqrestore(&memcg->move_lock, *flags); + spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } - *locked = true; + + /* + * When charge migration first begins, we can have locked and + * unlocked page stat updates happening concurrently. Track + * the task who has the lock for mem_cgroup_end_page_stat(). + */ + memcg->move_lock_task = current; + memcg->move_lock_flags = flags; return memcg; } @@ -2031,14 +2038,17 @@ again: /** * mem_cgroup_end_page_stat - finish a page state statistics transaction * @memcg: the memcg that was accounted against - * @locked: value received from mem_cgroup_begin_page_stat() - * @flags: value received from mem_cgroup_begin_page_stat() */ -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags) +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { - if (memcg && *locked) - spin_unlock_irqrestore(&memcg->move_lock, *flags); + if (memcg && memcg->move_lock_task == current) { + unsigned long flags = memcg->move_lock_flags; + + memcg->move_lock_task = NULL; + memcg->move_lock_flags = 0; + + spin_unlock_irqrestore(&memcg->move_lock, flags); + } rcu_read_unlock(); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6f4335238e33..fb71e9deca85 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2308,12 +2308,10 @@ EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2338,19 +2336,17 @@ int test_clear_page_writeback(struct page *page) dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2380,7 +2376,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } diff --git a/mm/rmap.c b/mm/rmap.c index 70b32498d4f2..5e3e09081164 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1085,24 +1085,20 @@ void page_add_new_anon_rmap(struct page *page, void page_add_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); } - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } static void page_remove_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) @@ -1123,7 +1119,7 @@ static void page_remove_file_rmap(struct page *page) if (unlikely(PageMlocked(page))) clear_page_mlock(page); out: - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } /** -- cgit v1.2.3 From 44628d9755e249aab9a6e1a17407d2f4278047ee Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 11 Feb 2015 15:25:10 -0800 Subject: mm: fix typo of MIGRATE_RESERVE in comment Found it when I want to jump to the definition of MIGRATE_RESERVE ctags. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f0856d14b21..b41829701334 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -426,7 +426,7 @@ struct zone { const char *name; /* - * Number of MIGRATE_RESEVE page block. To maintain for just + * Number of MIGRATE_RESERVE page block. To maintain for just * optimization. Protected by zone->lock. */ int nr_migrate_reserve_block; -- cgit v1.2.3 From e66f17ff71772b209eed39de35aaa99ba819c93d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:25:22 -0800 Subject: mm/hugetlb: take page table lock in follow_huge_pmd() We have a race condition between move_pages() and freeing hugepages, where move_pages() calls follow_page(FOLL_GET) for hugepages internally and tries to get its refcount without preventing concurrent freeing. This race crashes the kernel, so this patch fixes it by moving FOLL_GET code for hugepages into follow_huge_pmd() with taking the page table lock. This patch intentionally removes page==NULL check after pte_page. This is justified because pte_page() never returns NULL for any architectures or configurations. This patch changes the behavior of follow_huge_pmd() for tail pages and then tail pages can be pinned/returned. So the caller must be changed to properly handle the returned tail pages. We could have a choice to add the similar locking to follow_huge_(addr|pud) for consistency, but it's not necessary because currently these functions don't support FOLL_GET flag, so let's leave it for future development. Here is the reproducer: $ cat movepages.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 #define PS 0x1000 int main(int argc, char *argv[]) { int i; int nr_hp = strtol(argv[1], NULL, 0); int nr_p = nr_hp * HPS / PS; int ret; void **addrs; int *status; int *nodes; pid_t pid; pid = strtol(argv[2], NULL, 0); addrs = malloc(sizeof(char *) * nr_p + 1); status = malloc(sizeof(char *) * nr_p + 1); nodes = malloc(sizeof(char *) * nr_p + 1); while (1) { for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 1; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 0; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); } return 0; } $ cat hugepage.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 int main(int argc, char *argv[]) { int nr_hp = strtol(argv[1], NULL, 0); char *p; while (1) { p = mmap((void *)ADDR_INPUT, nr_hp * HPS, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (p != (void *)ADDR_INPUT) { perror("mmap"); break; } memset(p, 0, nr_hp * HPS); munmap(p, nr_hp * HPS); } } $ sysctl vm.nr_hugepages=40 $ ./hugepage 10 & $ ./movepages 10 $(pgrep -f hugepage) Fixes: e632a938d914 ("mm: migrate: add hugepage migration code to move_pages()") Signed-off-by: Naoya Horiguchi Reported-by: Hugh Dickins Cc: James Hogan Cc: David Rientjes Cc: Mel Gorman Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Luiz Capitulino Cc: Nishanth Aravamudan Cc: Lee Schermerhorn Cc: Steve Capper Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 ++++---- include/linux/swapops.h | 4 ++++ mm/gup.c | 25 ++++++++----------------- mm/hugetlb.c | 48 ++++++++++++++++++++++++++++++++++-------------- mm/migrate.c | 5 +++-- 5 files changed, 53 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7d7856359920..7b5785032049 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write); + pmd_t *pmd, int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write); + pud_t *pud, int flags); int pmd_huge(pmd_t pmd); int pud_huge(pud_t pmd); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, @@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) static inline void hugetlb_show_meminfo(void) { } -#define follow_huge_pmd(mm, addr, pmd, write) NULL -#define follow_huge_pud(mm, addr, pud, write) NULL +#define follow_huge_pmd(mm, addr, pmd, flags) NULL +#define follow_huge_pud(mm, addr, pud, flags) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define pud_huge(x) 0 diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 50cbc876be56..831a3168ab35 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -135,6 +135,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry) *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); } +extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, @@ -148,6 +150,8 @@ static inline int is_migration_entry(swp_entry_t swp) } #define migration_entry_to_page(swp) NULL static inline void make_migration_entry_read(swp_entry_t *entryp) { } +static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, diff --git a/mm/gup.c b/mm/gup.c index 12bc2bc33da7..1a8ab05918e0 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - if (flags & FOLL_GET) - return NULL; - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - return page; + page = follow_huge_pud(mm, address, pud, flags); + if (page) + return page; + return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); @@ -179,19 +179,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - if (flags & FOLL_GET) { - /* - * Refcount on tail pages are not well-defined and - * shouldn't be taken. The caller should handle a NULL - * return when trying to follow tail pages. - */ - if (PageHead(page)) - get_page(page); - else - page = NULL; - } - return page; + page = follow_huge_pmd(mm, address, pmd, flags); + if (page) + return page; + return no_page_table(vma, flags); } if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) return no_page_table(vma, flags); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d96b8bfa748f..5aca3707450f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3675,28 +3675,48 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page * __weak follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) + pmd_t *pmd, int flags) { - struct page *page; - - if (!pmd_present(*pmd)) - return NULL; - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + struct page *page = NULL; + spinlock_t *ptl; +retry: + ptl = pmd_lockptr(mm, pmd); + spin_lock(ptl); + /* + * make sure that the address range covered by this pmd is not + * unmapped from other threads. + */ + if (!pmd_huge(*pmd)) + goto out; + if (pmd_present(*pmd)) { + page = pte_page(*(pte_t *)pmd) + + ((address & ~PMD_MASK) >> PAGE_SHIFT); + if (flags & FOLL_GET) + get_page(page); + } else { + if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pmd, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); return page; } struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) + pud_t *pud, int flags) { - struct page *page; + if (flags & FOLL_GET) + return NULL; - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); - return page; + return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); } #ifdef CONFIG_MEMORY_FAILURE diff --git a/mm/migrate.c b/mm/migrate.c index 6e284bcca8bb..f98067e5d353 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -197,7 +197,7 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, +void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { pte_t pte; @@ -1236,7 +1236,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm, goto put_and_set; if (PageHuge(page)) { - isolate_huge_page(page, &pagelist); + if (PageHead(page)) + isolate_huge_page(page, &pagelist); goto put_and_set; } -- cgit v1.2.3 From 1a6d53a105406d97396c87511afd6f09b4dc8ad2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:44 -0800 Subject: mm: reduce try_to_compact_pages parameters Expand the usage of the struct alloc_context introduced in the previous patch also for calling try_to_compact_pages(), to reduce the number of its parameters. Since the function is in different compilation unit, we need to move alloc_context definition in the shared mm/internal.h header. With this change we get simpler code and small savings of code size and stack usage: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-27 (-27) function old new delta __alloc_pages_direct_compact 283 256 -27 add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-13 (-13) function old new delta try_to_compact_pages 582 569 -13 Stack usage of __alloc_pages_direct_compact goes from 24 to none (per scripts/checkstack.pl). Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 17 +++++++++-------- mm/compaction.c | 23 +++++++++++------------ mm/internal.h | 22 ++++++++++++++++++++++ mm/page_alloc.c | 27 ++------------------------- 4 files changed, 44 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3238ffa33f68..f2efda2e6ac6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,6 +21,8 @@ /* Zone lock or lru_lock was contended in async compaction */ #define COMPACT_CONTENDED_LOCK 2 +struct alloc_context; /* in mm/internal.h */ + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -30,10 +32,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); extern int fragmentation_index(struct zone *zone, unsigned int order); -extern unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *mask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx); +extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, @@ -101,10 +102,10 @@ static inline bool compaction_restarting(struct zone *zone, int order) } #else -static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, + unsigned int order, int alloc_flags, + const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { return COMPACT_CONTINUE; } diff --git a/mm/compaction.c b/mm/compaction.c index 546e571e9d60..9c7e6909dd29 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1335,22 +1335,20 @@ int sysctl_extfrag_threshold = 500; /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation - * @zonelist: The zonelist used for the current allocation - * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation - * @nodemask: The allowed nodes to allocate from + * @order: The order of the current allocation + * @alloc_flags: The allocation flags of the current allocation + * @ac: The context of current allocation * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that determines if compaction was aborted due to * need_resched() or lock contention * * This is the main entry point for direct page compaction. */ -unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { - enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; @@ -1365,8 +1363,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_SKIPPED; /* Compact each zone in the list */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, - nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { int status; int zone_contended; @@ -1374,7 +1372,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, continue; status = compact_zone_order(zone, order, gfp_mask, mode, - &zone_contended, alloc_flags, classzone_idx); + &zone_contended, alloc_flags, + ac->classzone_idx); rc = max(status, rc); /* * It takes at least one zone that wasn't lock contended @@ -1384,7 +1383,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), - classzone_idx, alloc_flags)) { + ac->classzone_idx, alloc_flags)) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller diff --git a/mm/internal.h b/mm/internal.h index efad241f7014..c4d6c9b43491 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -109,6 +109,28 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); * in mm/page_alloc.c */ +/* + * Structure for holding the mostly immutable allocation parameters passed + * between functions involved in allocations, including the alloc_pages* + * family of functions. + * + * nodemask, migratetype and high_zoneidx are initialized only once in + * __alloc_pages_nodemask() and then never change. + * + * zonelist, preferred_zone and classzone_idx are set first in + * __alloc_pages_nodemask() for the fast path, and might be later changed + * in __alloc_pages_slowpath(). All other functions pass the whole strucure + * by a const pointer. + */ +struct alloc_context { + struct zonelist *zonelist; + nodemask_t *nodemask; + struct zone *preferred_zone; + int classzone_idx; + int migratetype; + enum zone_type high_zoneidx; +}; + /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4aead0bd8d44..d664eb922a7d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -232,27 +232,6 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif -/* - * Structure for holding the mostly immutable allocation parameters passed - * between alloc_pages* family of functions. - * - * nodemask, migratetype and high_zoneidx are initialized only once in - * __alloc_pages_nodemask() and then never change. - * - * zonelist, preferred_zone and classzone_idx are set first in - * __alloc_pages_nodemask() for the fast path, and might be later changed - * in __alloc_pages_slowpath(). All other functions pass the whole strucure - * by a const pointer. - */ -struct alloc_context { - struct zonelist *zonelist; - nodemask_t *nodemask; - struct zone *preferred_zone; - int classzone_idx; - int migratetype; - enum zone_type high_zoneidx; -}; - int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) @@ -2429,10 +2408,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; current->flags |= PF_MEMALLOC; - compact_result = try_to_compact_pages(ac->zonelist, order, gfp_mask, - ac->nodemask, mode, - contended_compaction, - alloc_flags, ac->classzone_idx); + compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + mode, contended_compaction); current->flags &= ~PF_MEMALLOC; switch (compact_result) { -- cgit v1.2.3 From 05891fb06517d19ae5357c9dc44e96bbe0300a3c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:47 -0800 Subject: mm: microoptimize zonelist operations next_zones_zonelist() returns a zoneref pointer, as well as a zone pointer via extra parameter. Since the latter can be trivially obtained by dereferencing the former, the overhead of the extra parameter is unjustified. This patch thus removes the zone parameter from next_zones_zonelist(). Both callers happen to be in the same header file, so it's simple to add the zoneref dereference inline. We save some bytes of code size. add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-105 (-105) function old new delta nr_free_zone_pages 129 115 -14 __alloc_pages_nodemask 2300 2285 -15 get_page_from_freelist 2652 2576 -76 add/remove: 0/0 grow/shrink: 1/0 up/down: 10/0 (10) function old new delta try_to_compact_pages 569 579 +10 Signed-off-by: Vlastimil Babka Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++------ mm/mmzone.c | 4 +--- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b41829701334..f279d9c158cd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -970,7 +970,6 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the @@ -980,8 +979,7 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone); + nodemask_t *nodes); /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist @@ -1000,8 +998,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, nodemask_t *nodes, struct zone **zone) { - return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes, - zone); + struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs, + highest_zoneidx, nodes); + *zone = zonelist_zone(z); + return z; } /** @@ -1018,7 +1018,8 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ zone; \ - z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \ + z = next_zones_zonelist(++z, highidx, nodemask), \ + zone = zonelist_zone(z)) \ /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index diff --git a/mm/mmzone.c b/mm/mmzone.c index bf34fb8556db..7d87ebb0d632 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -54,8 +54,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) /* Returns the next zone at or below highest_zoneidx in a zonelist */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone) + nodemask_t *nodes) { /* * Find the next suitable zone to use for the allocation. @@ -69,7 +68,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, (z->zone && !zref_in_nodemask(z, nodes))) z++; - *zone = zonelist_zone(z); return z; } -- cgit v1.2.3 From 90cbc2508827e1e15dca23361c33cc26dd2b9e99 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:25:55 -0800 Subject: vmscan: force scan offline memory cgroups Since commit b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined groups") pages charged to a memory cgroup are not reparented when the cgroup is removed. Instead, they are supposed to be reclaimed in a regular way, along with pages accounted to online memory cgroups. However, an lruvec of an offline memory cgroup will sooner or later get so small that it will be scanned only at low scan priorities (see get_scan_count()). Therefore, if there are enough reclaimable pages in big lruvecs, pages accounted to offline memory cgroups will never be scanned at all, wasting memory. Fix this by unconditionally forcing scanning dead lruvecs from kswapd. [akpm@linux-foundation.org: fix build] Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ mm/memcontrol.c | 14 ++++++++++++++ mm/vmscan.c | 8 ++++++-- 3 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 76b4084b8d08..353537a5981a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -102,6 +102,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); +bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -266,6 +267,11 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + return true; +} + static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 028d07c79104..6187ca4d5dc2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1367,6 +1367,20 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return inactive * inactive_ratio < active; } +bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) diff --git a/mm/vmscan.c b/mm/vmscan.c index f756a202d5d5..b6dfa0081a8e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1903,8 +1903,12 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && !zone_reclaimable(zone)) - force_scan = true; + if (current_is_kswapd()) { + if (!zone_reclaimable(zone)) + force_scan = true; + if (!mem_cgroup_lruvec_online(lruvec)) + force_scan = true; + } if (!global_reclaim(sc)) force_scan = true; -- cgit v1.2.3 From 650c5e565492f9092552bfe4d65935196c7d9567 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:03 -0800 Subject: mm: page_counter: pull "-1" handling out of page_counter_memparse() The unified hierarchy interface for memory cgroups will no longer use "-1" to mean maximum possible resource value. In preparation for this, make the string an argument and let the caller supply it. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 3 ++- mm/hugetlb_cgroup.c | 2 +- mm/memcontrol.c | 4 ++-- mm/page_counter.c | 7 ++++--- net/ipv4/tcp_memcontrol.c | 2 +- 5 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 955421575d16..17fa4f8de3a6 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -41,7 +41,8 @@ int page_counter_try_charge(struct page_counter *counter, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_limit(struct page_counter *counter, unsigned long limit); -int page_counter_memparse(const char *buf, unsigned long *nr_pages); +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages); static inline void page_counter_reset_watermark(struct page_counter *counter) { diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 037e1c00a5b7..6e0057439a46 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -279,7 +279,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, return -EINVAL; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index dc5c4cd0afdf..6453ea5a27aa 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3414,7 +3414,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, int ret; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; @@ -3786,7 +3786,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, unsigned long usage; int i, size, ret; - ret = page_counter_memparse(args, &threshold); + ret = page_counter_memparse(args, "-1", &threshold); if (ret) return ret; diff --git a/mm/page_counter.c b/mm/page_counter.c index a009574fbba9..11b4beda14ba 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -166,18 +166,19 @@ int page_counter_limit(struct page_counter *counter, unsigned long limit) /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse + * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ -int page_counter_memparse(const char *buf, unsigned long *nr_pages) +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages) { - char unlimited[] = "-1"; char *end; u64 bytes; - if (!strncmp(buf, unlimited, sizeof(unlimited))) { + if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 272327134a1b..c2a75c6957a1 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -120,7 +120,7 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, switch (of_cft(of)->private) { case RES_LIMIT: /* see memcontrol.c */ - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) break; mutex_lock(&tcp_limit_mutex); -- cgit v1.2.3 From 241994ed8649f7300667be8b13a9e04ae04e05a1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:06 -0800 Subject: mm: memcontrol: default hierarchy interface for memory Introduce the basic control files to account, partition, and limit memory using cgroups in default hierarchy mode. This interface versioning allows us to address fundamental design issues in the existing memory cgroup interface, further explained below. The old interface will be maintained indefinitely, but a clearer model and improved workload performance should encourage existing users to switch over to the new one eventually. The control files are thus: - memory.current shows the current consumption of the cgroup and its descendants, in bytes. - memory.low configures the lower end of the cgroup's expected memory consumption range. The kernel considers memory below that boundary to be a reserve - the minimum that the workload needs in order to make forward progress - and generally avoids reclaiming it, unless there is an imminent risk of entering an OOM situation. - memory.high configures the upper end of the cgroup's expected memory consumption range. A cgroup whose consumption grows beyond this threshold is forced into direct reclaim, to work off the excess and to throttle new allocations heavily, but is generally allowed to continue and the OOM killer is not invoked. - memory.max configures the hard maximum amount of memory that the cgroup is allowed to consume before the OOM killer is invoked. - memory.events shows event counters that indicate how often the cgroup was reclaimed while below memory.low, how often it was forced to reclaim excess beyond memory.high, how often it hit memory.max, and how often it entered OOM due to memory.max. This allows users to identify configuration problems when observing a degradation in workload performance. An overcommitted system will have an increased rate of low boundary breaches, whereas increased rates of high limit breaches, maximum hits, or even OOM situations will indicate internally overcommitted cgroups. For existing users of memory cgroups, the following deviations from the current interface are worth pointing out and explaining: - The original lower boundary, the soft limit, is defined as a limit that is per default unset. As a result, the set of cgroups that global reclaim prefers is opt-in, rather than opt-out. The costs for optimizing these mostly negative lookups are so high that the implementation, despite its enormous size, does not even provide the basic desirable behavior. First off, the soft limit has no hierarchical meaning. All configured groups are organized in a global rbtree and treated like equal peers, regardless where they are located in the hierarchy. This makes subtree delegation impossible. Second, the soft limit reclaim pass is so aggressive that it not just introduces high allocation latencies into the system, but also impacts system performance due to overreclaim, to the point where the feature becomes self-defeating. The memory.low boundary on the other hand is a top-down allocated reserve. A cgroup enjoys reclaim protection when it and all its ancestors are below their low boundaries, which makes delegation of subtrees possible. Secondly, new cgroups have no reserve per default and in the common case most cgroups are eligible for the preferred reclaim pass. This allows the new low boundary to be efficiently implemented with just a minor addition to the generic reclaim code, without the need for out-of-band data structures and reclaim passes. Because the generic reclaim code considers all cgroups except for the ones running low in the preferred first reclaim pass, overreclaim of individual groups is eliminated as well, resulting in much better overall workload performance. - The original high boundary, the hard limit, is defined as a strict limit that can not budge, even if the OOM killer has to be called. But this generally goes against the goal of making the most out of the available memory. The memory consumption of workloads varies during runtime, and that requires users to overcommit. But doing that with a strict upper limit requires either a fairly accurate prediction of the working set size or adding slack to the limit. Since working set size estimation is hard and error prone, and getting it wrong results in OOM kills, most users tend to err on the side of a looser limit and end up wasting precious resources. The memory.high boundary on the other hand can be set much more conservatively. When hit, it throttles allocations by forcing them into direct reclaim to work off the excess, but it never invokes the OOM killer. As a result, a high boundary that is chosen too aggressively will not terminate the processes, but instead it will lead to gradual performance degradation. The user can monitor this and make corrections until the minimal memory footprint that still gives acceptable performance is found. In extreme cases, with many concurrent allocations and a complete breakdown of reclaim progress within the group, the high boundary can be exceeded. But even then it's mostly better to satisfy the allocation from the slack available in other groups or the rest of the system than killing the group. Otherwise, memory.max is there to limit this type of spillover and ultimately contain buggy or even malicious applications. - The original control file names are unwieldy and inconsistent in many different ways. For example, the upper boundary hit count is exported in the memory.failcnt file, but an OOM event count has to be manually counted by listening to memory.oom_control events, and lower boundary / soft limit events have to be counted by first setting a threshold for that value and then counting those events. Also, usage and limit files encode their units in the filename. That makes the filenames very long, even though this is not information that a user needs to be reminded of every time they type out those names. To address these naming issues, as well as to signal clearly that the new interface carries a new configuration model, the naming conventions in it necessarily differ from the old interface. - The original limit files indicate the state of an unset limit with a very high number, and a configured limit can be unset by echoing -1 into those files. But that very high number is implementation and architecture dependent and not very descriptive. And while -1 can be understood as an underflow into the highest possible value, -2 or -10M etc. do not work, so it's not inconsistent. memory.low, memory.high, and memory.max will use the string "infinity" to indicate and set the highest possible value. [akpm@linux-foundation.org: use seq_puts() for basic strings] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/unified-hierarchy.txt | 79 ++++++++++ include/linux/memcontrol.h | 32 ++++ mm/memcontrol.c | 229 ++++++++++++++++++++++++++-- mm/vmscan.c | 22 ++- 4 files changed, 348 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt index 4f4563277864..71daa35ec2d9 100644 --- a/Documentation/cgroups/unified-hierarchy.txt +++ b/Documentation/cgroups/unified-hierarchy.txt @@ -327,6 +327,85 @@ supported and the interface files "release_agent" and - use_hierarchy is on by default and the cgroup file for the flag is not created. +- The original lower boundary, the soft limit, is defined as a limit + that is per default unset. As a result, the set of cgroups that + global reclaim prefers is opt-in, rather than opt-out. The costs + for optimizing these mostly negative lookups are so high that the + implementation, despite its enormous size, does not even provide the + basic desirable behavior. First off, the soft limit has no + hierarchical meaning. All configured groups are organized in a + global rbtree and treated like equal peers, regardless where they + are located in the hierarchy. This makes subtree delegation + impossible. Second, the soft limit reclaim pass is so aggressive + that it not just introduces high allocation latencies into the + system, but also impacts system performance due to overreclaim, to + the point where the feature becomes self-defeating. + + The memory.low boundary on the other hand is a top-down allocated + reserve. A cgroup enjoys reclaim protection when it and all its + ancestors are below their low boundaries, which makes delegation of + subtrees possible. Secondly, new cgroups have no reserve per + default and in the common case most cgroups are eligible for the + preferred reclaim pass. This allows the new low boundary to be + efficiently implemented with just a minor addition to the generic + reclaim code, without the need for out-of-band data structures and + reclaim passes. Because the generic reclaim code considers all + cgroups except for the ones running low in the preferred first + reclaim pass, overreclaim of individual groups is eliminated as + well, resulting in much better overall workload performance. + +- The original high boundary, the hard limit, is defined as a strict + limit that can not budge, even if the OOM killer has to be called. + But this generally goes against the goal of making the most out of + the available memory. The memory consumption of workloads varies + during runtime, and that requires users to overcommit. But doing + that with a strict upper limit requires either a fairly accurate + prediction of the working set size or adding slack to the limit. + Since working set size estimation is hard and error prone, and + getting it wrong results in OOM kills, most users tend to err on the + side of a looser limit and end up wasting precious resources. + + The memory.high boundary on the other hand can be set much more + conservatively. When hit, it throttles allocations by forcing them + into direct reclaim to work off the excess, but it never invokes the + OOM killer. As a result, a high boundary that is chosen too + aggressively will not terminate the processes, but instead it will + lead to gradual performance degradation. The user can monitor this + and make corrections until the minimal memory footprint that still + gives acceptable performance is found. + + In extreme cases, with many concurrent allocations and a complete + breakdown of reclaim progress within the group, the high boundary + can be exceeded. But even then it's mostly better to satisfy the + allocation from the slack available in other groups or the rest of + the system than killing the group. Otherwise, memory.max is there + to limit this type of spillover and ultimately contain buggy or even + malicious applications. + +- The original control file names are unwieldy and inconsistent in + many different ways. For example, the upper boundary hit count is + exported in the memory.failcnt file, but an OOM event count has to + be manually counted by listening to memory.oom_control events, and + lower boundary / soft limit events have to be counted by first + setting a threshold for that value and then counting those events. + Also, usage and limit files encode their units in the filename. + That makes the filenames very long, even though this is not + information that a user needs to be reminded of every time they type + out those names. + + To address these naming issues, as well as to signal clearly that + the new interface carries a new configuration model, the naming + conventions in it necessarily differ from the old interface. + +- The original limit files indicate the state of an unset limit with a + Very High Number, and a configured limit can be unset by echoing -1 + into those files. But that very high number is implementation and + architecture dependent and not very descriptive. And while -1 can + be understood as an underflow into the highest possible value, -2 or + -10M etc. do not work, so it's not consistent. + + memory.low, memory.high, and memory.max will use the string + "infinity" to indicate and set the highest possible value. 5. Planned Changes diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 353537a5981a..6cfd934c7c9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,7 +52,27 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; +enum mem_cgroup_events_index { + MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ + MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ + MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ + MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ + MEM_CGROUP_EVENTS_NSTATS, + /* default hierarchy events */ + MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS, + MEMCG_HIGH, + MEMCG_MAX, + MEMCG_OOM, + MEMCG_NR_EVENTS, +}; + #ifdef CONFIG_MEMCG +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr); + +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); + int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -175,6 +195,18 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; +static inline void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ +} + +static inline bool mem_cgroup_low(struct mem_cgroup *root, + struct mem_cgroup *memcg) +{ + return false; +} + static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6453ea5a27aa..ee97c9ac62c0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -97,14 +97,6 @@ static const char * const mem_cgroup_stat_names[] = { "swap", }; -enum mem_cgroup_events_index { - MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ - MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ - MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ - MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ - MEM_CGROUP_EVENTS_NSTATS, -}; - static const char * const mem_cgroup_events_names[] = { "pgpgin", "pgpgout", @@ -138,7 +130,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEM_CGROUP_STAT_NSTATS]; - unsigned long events[MEM_CGROUP_EVENTS_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -284,6 +276,10 @@ struct mem_cgroup { struct page_counter memsw; struct page_counter kmem; + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + unsigned long soft_limit; /* vmpressure notifications */ @@ -2315,6 +2311,8 @@ retry: if (!(gfp_mask & __GFP_WAIT)) goto nomem; + mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); + nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -2356,6 +2354,8 @@ retry: if (fatal_signal_pending(current)) goto bypass; + mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages)); nomem: if (!(gfp_mask & __GFP_NOFAIL)) @@ -2367,6 +2367,16 @@ done_restock: css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); + /* + * If the hierarchy is above the normal consumption range, + * make the charging task trim their excess contribution. + */ + do { + if (page_counter_read(&memcg->memory) <= memcg->high) + continue; + mem_cgroup_events(memcg, MEMCG_HIGH, 1); + try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + } while ((memcg = parent_mem_cgroup(memcg))); done: return ret; } @@ -4276,7 +4286,7 @@ out_kfree: return ret; } -static struct cftype mem_cgroup_files[] = { +static struct cftype mem_cgroup_legacy_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), @@ -4552,6 +4562,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent_css == NULL) { root_mem_cgroup = memcg; page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4597,6 +4608,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (parent->use_hierarchy) { page_counter_init(&memcg->memory, &parent->memory); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, &parent->memsw); page_counter_init(&memcg->kmem, &parent->kmem); @@ -4607,6 +4619,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) */ } else { page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4682,6 +4695,8 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX); mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX); memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX); + memcg->low = 0; + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; } @@ -5267,6 +5282,147 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) mem_cgroup_from_css(root_css)->use_hierarchy = true; } +static u64 memory_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_usage(mem_cgroup_from_css(css), false); +} + +static int memory_low_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long low = ACCESS_ONCE(memcg->low); + + if (low == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long low; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &low); + if (err) + return err; + + memcg->low = low; + + return nbytes; +} + +static int memory_high_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long high = ACCESS_ONCE(memcg->high); + + if (high == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &high); + if (err) + return err; + + memcg->high = high; + + return nbytes; +} + +static int memory_max_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long max = ACCESS_ONCE(memcg->memory.limit); + + if (max == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &max); + if (err) + return err; + + err = mem_cgroup_resize_limit(memcg, max); + if (err) + return err; + + return nbytes; +} + +static int memory_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW)); + seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH)); + seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX)); + seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM)); + + return 0; +} + +static struct cftype memory_files[] = { + { + .name = "current", + .read_u64 = memory_current_read, + }, + { + .name = "low", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_low_show, + .write = memory_low_write, + }, + { + .name = "high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_high_show, + .write = memory_high_write, + }, + { + .name = "max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_max_show, + .write = memory_max_write, + }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_events_show, + }, + { } /* terminate */ +}; + struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, .css_online = mem_cgroup_css_online, @@ -5277,7 +5433,8 @@ struct cgroup_subsys memory_cgrp_subsys = { .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, - .legacy_cftypes = mem_cgroup_files, + .dfl_cftypes = memory_files, + .legacy_cftypes = mem_cgroup_legacy_files, .early_init = 0, }; @@ -5312,6 +5469,56 @@ static void __init enable_swap_cgroup(void) } #endif +/** + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); +} + +/** + * mem_cgroup_low - check if memory consumption is below the normal range + * @root: the highest ancestor to consider + * @memcg: the memory cgroup to check + * + * Returns %true if memory consumption of @memcg, and that of all + * configurable ancestors up to @root, is below the normal range. + */ +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return false; + + /* + * The toplevel group doesn't have a configurable range, so + * it's never low when looked at directly, and it is not + * considered an ancestor when assessing the hierarchy. + */ + + if (memcg == root_mem_cgroup) + return false; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; + + while (memcg != root) { + memcg = parent_mem_cgroup(memcg); + + if (memcg == root_mem_cgroup) + break; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; + } + return true; +} + #ifdef CONFIG_MEMCG_SWAP /** * mem_cgroup_swapout - transfer a memsw charge to swap diff --git a/mm/vmscan.c b/mm/vmscan.c index b6dfa0081a8e..8e645ee52045 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -91,6 +91,9 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; + /* Can cgroups be reclaimed below their normal consumption range? */ + unsigned int may_thrash:1; + unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ @@ -2294,6 +2297,12 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, struct lruvec *lruvec; int swappiness; + if (mem_cgroup_low(root, memcg)) { + if (!sc->may_thrash) + continue; + mem_cgroup_events(memcg, MEMCG_LOW, 1); + } + lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); @@ -2315,8 +2324,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, mem_cgroup_iter_break(root, memcg); break; } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } while ((memcg = mem_cgroup_iter(root, memcg, &reclaim))); /* * Shrink the slab caches in the same proportion that @@ -2519,10 +2527,11 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { + int initial_priority = sc->priority; unsigned long total_scanned = 0; unsigned long writeback_threshold; bool zones_reclaimable; - +retry: delayacct_freepages_start(); if (global_reclaim(sc)) @@ -2572,6 +2581,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (sc->compaction_ready) return 1; + /* Untapped cgroup reserves? Don't OOM, retry. */ + if (!sc->may_thrash) { + sc->priority = initial_priority; + sc->may_thrash = 1; + goto retry; + } + /* Any of the zones still reclaimable? Don't OOM. */ if (zones_reclaimable) return 1; -- cgit v1.2.3 From 49550b605587924b3336386caae53200c68969d3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:12 -0800 Subject: oom: add helpers for setting and clearing TIF_MEMDIE This patchset addresses a race which was described in the changelog for 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend"): : PM freezer relies on having all tasks frozen by the time devices are : getting frozen so that no task will touch them while they are getting : frozen. But OOM killer is allowed to kill an already frozen task in order : to handle OOM situtation. In order to protect from late wake ups OOM : killer is disabled after all tasks are frozen. This, however, still keeps : a window open when a killed task didn't manage to die by the time : freeze_processes finishes. The original patch hasn't closed the race window completely because that would require a more complex solution as it can be seen by this patchset. The primary motivation was to close the race condition between OOM killer and PM freezer _completely_. As Tejun pointed out, even though the race condition is unlikely the harder it would be to debug weird bugs deep in the PM freezer when the debugging options are reduced considerably. I can only speculate what might happen when a task is still runnable unexpectedly. On a plus side and as a side effect the oom enable/disable has a better (full barrier) semantic without polluting hot paths. I have tested the series in KVM with 100M RAM: - many small tasks (20M anon mmap) which are triggering OOM continually - s2ram which resumes automatically is triggered in a loop echo processors > /sys/power/pm_test while true do echo mem > /sys/power/state sleep 1s done - simple module which allocates and frees 20M in 8K chunks. If it sees freezing(current) then it tries another round of allocation before calling try_to_freeze - debugging messages of PM stages and OOM killer enable/disable/fail added and unmark_oom_victim is delayed by 1s after it clears TIF_MEMDIE and before it wakes up waiters. - rebased on top of the current mmotm which means some necessary updates in mm/oom_kill.c. mark_tsk_oom_victim is now called under task_lock but I think this should be OK because __thaw_task shouldn't interfere with any locking down wake_up_process. Oleg? As expected there are no OOM killed tasks after oom is disabled and allocations requested by the kernel thread are failing after all the tasks are frozen and OOM disabled. I wasn't able to catch a race where oom_killer_disable would really have to wait but I kinda expected the race is really unlikely. [ 242.609330] Killed process 2992 (mem_eater) total-vm:24412kB, anon-rss:2164kB, file-rss:4kB [ 243.628071] Unmarking 2992 OOM victim. oom_victims: 1 [ 243.636072] (elapsed 2.837 seconds) done. [ 243.641985] Trying to disable OOM killer [ 243.643032] Waiting for concurent OOM victims [ 243.644342] OOM killer disabled [ 243.645447] Freezing remaining freezable tasks ... (elapsed 0.005 seconds) done. [ 243.652983] Suspending console(s) (use no_console_suspend to debug) [ 243.903299] kmem_eater: page allocation failure: order:1, mode:0x204010 [...] [ 243.992600] PM: suspend of devices complete after 336.667 msecs [ 243.993264] PM: late suspend of devices complete after 0.660 msecs [ 243.994713] PM: noirq suspend of devices complete after 1.446 msecs [ 243.994717] ACPI: Preparing to enter system sleep state S3 [ 243.994795] PM: Saving platform NVS memory [ 243.994796] Disabling non-boot CPUs ... The first 2 patches are simple cleanups for OOM. They should go in regardless the rest IMO. Patches 3 and 4 are trivial printk -> pr_info conversion and they should go in ditto. The main patch is the last one and I would appreciate acks from Tejun and Rafael. I think the OOM part should be OK (except for __thaw_task vs. task_lock where a look from Oleg would appreciated) but I am not so sure I haven't screwed anything in the freezer code. I have found several surprises there. This patch (of 5): This patch is just a preparatory and it doesn't introduce any functional change. Note: I am utterly unhappy about lowmemory killer abusing TIF_MEMDIE just to wait for the oom victim and to prevent from new killing. This is just a side effect of the flag. The primary meaning is to give the oom victim access to the memory reserves and that shouldn't be necessary here. Signed-off-by: Michal Hocko Cc: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/lowmemorykiller.c | 7 ++++++- include/linux/oom.h | 4 ++++ kernel/exit.c | 2 +- mm/memcontrol.c | 2 +- mm/oom_kill.c | 23 ++++++++++++++++++++--- 5 files changed, 32 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c index b545d3d1da3e..feafa172b155 100644 --- a/drivers/staging/android/lowmemorykiller.c +++ b/drivers/staging/android/lowmemorykiller.c @@ -160,7 +160,12 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc) selected->pid, selected->comm, selected_oom_score_adj, selected_tasksize); lowmem_deathpending_timeout = jiffies + HZ; - set_tsk_thread_flag(selected, TIF_MEMDIE); + /* + * FIXME: lowmemorykiller shouldn't abuse global OOM killer + * infrastructure. There is no real reason why the selected + * task should have access to the memory reserves. + */ + mark_tsk_oom_victim(selected); send_sig(SIGKILL, selected, 0); rem += selected_tasksize; } diff --git a/include/linux/oom.h b/include/linux/oom.h index 76200984d1e2..b42b80f88c3a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -47,6 +47,10 @@ static inline bool oom_task_origin(const struct task_struct *p) return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); } +extern void mark_tsk_oom_victim(struct task_struct *tsk); + +extern void unmark_oom_victim(void); + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff --git a/kernel/exit.c b/kernel/exit.c index 6806c55475ee..02b3d1ab2ec0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,7 @@ static void exit_mm(struct task_struct *tsk) task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); - clear_thread_flag(TIF_MEMDIE); + unmark_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 11c9e6a1dad5..fe4d258ef32b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1556,7 +1556,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * quickly exit and free its memory. */ if (fatal_signal_pending(current) || task_will_free_mem(current)) { - set_thread_flag(TIF_MEMDIE); + mark_tsk_oom_victim(current); return; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 294493a7ae4b..80b34e285f96 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -416,6 +416,23 @@ void note_oom_kill(void) atomic_inc(&oom_kills); } +/** + * mark_tsk_oom_victim - marks the given taks as OOM victim. + * @tsk: task to mark + */ +void mark_tsk_oom_victim(struct task_struct *tsk) +{ + set_tsk_thread_flag(tsk, TIF_MEMDIE); +} + +/** + * unmark_oom_victim - unmarks the current task as OOM victim. + */ +void unmark_oom_victim(void) +{ + clear_thread_flag(TIF_MEMDIE); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon @@ -440,7 +457,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ task_lock(p); if (p->mm && task_will_free_mem(p)) { - set_tsk_thread_flag(p, TIF_MEMDIE); + mark_tsk_oom_victim(p); task_unlock(p); put_task_struct(p); return; @@ -495,7 +512,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; - set_tsk_thread_flag(victim, TIF_MEMDIE); + mark_tsk_oom_victim(victim); pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), @@ -652,7 +669,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ if (current->mm && (fatal_signal_pending(current) || task_will_free_mem(current))) { - set_thread_flag(TIF_MEMDIE); + mark_tsk_oom_victim(current); return; } -- cgit v1.2.3 From c32b3cbe0d067a9cfae85aa70ba1e97ceba0ced7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:24 -0800 Subject: oom, PM: make OOM detection in the freezer path raceless Commit 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend") has left a race window when OOM killer manages to note_oom_kill after freeze_processes checks the counter. The race window is quite small and really unlikely and partial solution deemed sufficient at the time of submission. Tejun wasn't happy about this partial solution though and insisted on a full solution. That requires the full OOM and freezer's task freezing exclusion, though. This is done by this patch which introduces oom_sem RW lock and turns oom_killer_disable() into a full OOM barrier. oom_killer_disabled check is moved from the allocation path to the OOM level and we take oom_sem for reading for both the check and the whole OOM invocation. oom_killer_disable() takes oom_sem for writing so it waits for all currently running OOM killer invocations. Then it disable all the further OOMs by setting oom_killer_disabled and checks for any oom victims. Victims are counted via mark_tsk_oom_victim resp. unmark_oom_victim. The last victim wakes up all waiters enqueued by oom_killer_disable(). Therefore this function acts as the full OOM barrier. The page fault path is covered now as well although it was assumed to be safe before. As per Tejun, "We used to have freezing points deep in file system code which may be reacheable from page fault." so it would be better and more robust to not rely on freezing points here. Same applies to the memcg OOM killer. out_of_memory tells the caller whether the OOM was allowed to trigger and the callers are supposed to handle the situation. The page allocation path simply fails the allocation same as before. The page fault path will retry the fault (more on that later) and Sysrq OOM trigger will simply complain to the log. Normally there wouldn't be any unfrozen user tasks after try_to_freeze_tasks so the function will not block. But if there was an OOM killer racing with try_to_freeze_tasks and the OOM victim didn't finish yet then we have to wait for it. This should complete in a finite time, though, because - the victim cannot loop in the page fault handler (it would die on the way out from the exception) - it cannot loop in the page allocator because all the further allocation would fail and __GFP_NOFAIL allocations are not acceptable at this stage - it shouldn't be blocked on any locks held by frozen tasks (try_to_freeze expects lockless context) and kernel threads and work queues are not frozen yet Signed-off-by: Michal Hocko Suggested-by: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/tty/sysrq.c | 5 +- include/linux/oom.h | 14 ++---- kernel/exit.c | 3 +- kernel/power/process.c | 50 ++++--------------- mm/memcontrol.c | 2 +- mm/oom_kill.c | 132 +++++++++++++++++++++++++++++++++++++++++-------- mm/page_alloc.c | 17 +------ 7 files changed, 132 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 0071469ecbf1..259a4d5a4e8f 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -355,8 +355,9 @@ static struct sysrq_key_op sysrq_term_op = { static void moom_callback(struct work_struct *ignored) { - out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL, - 0, NULL, true); + if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), + GFP_KERNEL, 0, NULL, true)) + pr_info("OOM request ignored because killer is disabled\n"); } static DECLARE_WORK(moom_work, moom_callback); diff --git a/include/linux/oom.h b/include/linux/oom.h index b42b80f88c3a..d5771bed59c9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -72,22 +72,14 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill); -extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disabled; - -static inline void oom_killer_disable(void) -{ - oom_killer_disabled = true; -} - -static inline void oom_killer_enable(void) -{ - oom_killer_disabled = false; -} +extern bool oom_killer_disable(void); +extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); diff --git a/kernel/exit.c b/kernel/exit.c index 02b3d1ab2ec0..feff10bbb307 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,8 @@ static void exit_mm(struct task_struct *tsk) task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); - unmark_oom_victim(); + if (test_thread_flag(TIF_MEMDIE)) + unmark_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/kernel/power/process.c b/kernel/power/process.c index 3ac45f192e9f..564f786df470 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -108,30 +108,6 @@ static int try_to_freeze_tasks(bool user_only) return todo ? -EBUSY : 0; } -static bool __check_frozen_processes(void) -{ - struct task_struct *g, *p; - - for_each_process_thread(g, p) - if (p != current && !freezer_should_skip(p) && !frozen(p)) - return false; - - return true; -} - -/* - * Returns true if all freezable tasks (except for current) are frozen already - */ -static bool check_frozen_processes(void) -{ - bool ret; - - read_lock(&tasklist_lock); - ret = __check_frozen_processes(); - read_unlock(&tasklist_lock); - return ret; -} - /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -142,7 +118,6 @@ static bool check_frozen_processes(void) int freeze_processes(void) { int error; - int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -157,29 +132,22 @@ int freeze_processes(void) pm_wakeup_clear(); pr_info("Freezing user space processes ... "); pm_freezing = true; - oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { __usermodehelper_set_disable_depth(UMH_DISABLED); - oom_killer_disable(); - - /* - * There might have been an OOM kill while we were - * freezing tasks and the killed task might be still - * on the way out so we have to double check for race. - */ - if (oom_kills_count() != oom_kills_saved && - !check_frozen_processes()) { - __usermodehelper_set_disable_depth(UMH_ENABLED); - pr_cont("OOM in progress."); - error = -EBUSY; - } else { - pr_cont("done."); - } + pr_cont("done."); } pr_cont("\n"); BUG_ON(in_atomic()); + /* + * Now that the whole userspace is frozen we need to disbale + * the OOM killer to disallow any further interference with + * killable tasks. + */ + if (!error && !oom_killer_disable()) + error = -EBUSY; + if (error) thaw_processes(); return error; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fe4d258ef32b..fbf64e6f64e4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1930,7 +1930,7 @@ bool mem_cgroup_oom_synchronize(bool handle) if (!memcg) return false; - if (!handle) + if (!handle || oom_killer_disabled) goto cleanup; owait.memcg = memcg; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3cbd76b8c13b..b8df76ee2be3 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -398,30 +398,27 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } /* - * Number of OOM killer invocations (including memcg OOM killer). - * Primarily used by PM freezer to check for potential races with - * OOM killed frozen task. + * Number of OOM victims in flight */ -static atomic_t oom_kills = ATOMIC_INIT(0); +static atomic_t oom_victims = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); -int oom_kills_count(void) -{ - return atomic_read(&oom_kills); -} - -void note_oom_kill(void) -{ - atomic_inc(&oom_kills); -} +bool oom_killer_disabled __read_mostly; +static DECLARE_RWSEM(oom_sem); /** * mark_tsk_oom_victim - marks the given taks as OOM victim. * @tsk: task to mark + * + * Has to be called with oom_sem taken for read and never after + * oom has been disabled already. */ void mark_tsk_oom_victim(struct task_struct *tsk) { - set_tsk_thread_flag(tsk, TIF_MEMDIE); - + WARN_ON(oom_killer_disabled); + /* OOM killer might race with memcg OOM */ + if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free @@ -429,14 +426,70 @@ void mark_tsk_oom_victim(struct task_struct *tsk) * that TIF_MEMDIE tasks should be ignored. */ __thaw_task(tsk); + atomic_inc(&oom_victims); } /** * unmark_oom_victim - unmarks the current task as OOM victim. + * + * Wakes up all waiters in oom_killer_disable() */ void unmark_oom_victim(void) { - clear_thread_flag(TIF_MEMDIE); + if (!test_and_clear_thread_flag(TIF_MEMDIE)) + return; + + down_read(&oom_sem); + /* + * There is no need to signal the lasst oom_victim if there + * is nobody who cares. + */ + if (!atomic_dec_return(&oom_victims) && oom_killer_disabled) + wake_up_all(&oom_victims_wait); + up_read(&oom_sem); +} + +/** + * oom_killer_disable - disable OOM killer + * + * Forces all page allocations to fail rather than trigger OOM killer. + * Will block and wait until all OOM victims are killed. + * + * The function cannot be called when there are runnable user tasks because + * the userspace would see unexpected allocation failures as a result. Any + * new usage of this function should be consulted with MM people. + * + * Returns true if successful and false if the OOM killer cannot be + * disabled. + */ +bool oom_killer_disable(void) +{ + /* + * Make sure to not race with an ongoing OOM killer + * and that the current is not the victim. + */ + down_write(&oom_sem); + if (test_thread_flag(TIF_MEMDIE)) { + up_write(&oom_sem); + return false; + } + + oom_killer_disabled = true; + up_write(&oom_sem); + + wait_event(oom_victims_wait, !atomic_read(&oom_victims)); + + return true; +} + +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) +{ + down_write(&oom_sem); + oom_killer_disabled = false; + up_write(&oom_sem); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -637,7 +690,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) } /** - * out_of_memory - kill the "best" process when we run out of memory + * __out_of_memory - kill the "best" process when we run out of memory * @zonelist: zonelist pointer * @gfp_mask: memory allocation flags * @order: amount of memory being requested as a power of 2 @@ -649,7 +702,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *nodemask, bool force_kill) { const nodemask_t *mpol_mask; @@ -718,6 +771,32 @@ out: schedule_timeout_killable(1); } +/** + * out_of_memory - tries to invoke OOM killer. + * @zonelist: zonelist pointer + * @gfp_mask: memory allocation flags + * @order: amount of memory being requested as a power of 2 + * @nodemask: nodemask passed to page allocator + * @force_kill: true if a task must be killed, even if others are exiting + * + * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable() + * when it returns false. Otherwise returns true. + */ +bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, + int order, nodemask_t *nodemask, bool force_kill) +{ + bool ret = false; + + down_read(&oom_sem); + if (!oom_killer_disabled) { + __out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill); + ret = true; + } + up_read(&oom_sem); + + return ret; +} + /* * The pagefault handler calls here because it is out of memory, so kill a * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a @@ -727,12 +806,25 @@ void pagefault_out_of_memory(void) { struct zonelist *zonelist; + down_read(&oom_sem); if (mem_cgroup_oom_synchronize(true)) - return; + goto unlock; zonelist = node_zonelist(first_memory_node, GFP_KERNEL); if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) { - out_of_memory(NULL, 0, 0, NULL, false); + if (!oom_killer_disabled) + __out_of_memory(NULL, 0, 0, NULL, false); + else + /* + * There shouldn't be any user tasks runable while the + * OOM killer is disabled so the current task has to + * be a racing OOM victim for which oom_killer_disable() + * is waiting for. + */ + WARN_ON(test_thread_flag(TIF_MEMDIE)); + oom_zonelist_unlock(zonelist, GFP_KERNEL); } +unlock: + up_read(&oom_sem); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 641d5a9a8617..134e25525044 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -244,8 +244,6 @@ void set_pageblock_migratetype(struct page *page, int migratetype) PB_migrate, PB_migrate_end); } -bool oom_killer_disabled __read_mostly; - #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { @@ -2317,9 +2315,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, *did_some_progress = 0; - if (oom_killer_disabled) - return NULL; - /* * Acquire the per-zone oom lock for each zone. If that * fails, somebody else is making progress for us. @@ -2330,14 +2325,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, return NULL; } - /* - * PM-freezer should be notified that there might be an OOM killer on - * its way to kill and wake somebody up. This is too early and we might - * end up not killing anything but false positives are acceptable. - * See freeze_processes. - */ - note_oom_kill(); - /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if @@ -2372,8 +2359,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false); - *did_some_progress = 1; + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + *did_some_progress = 1; out: oom_zonelist_unlock(ac->zonelist, gfp_mask); return page; -- cgit v1.2.3 From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:26:50 -0800 Subject: mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include #include #include #include #include #include #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov Reported-by: Dave Hansen Cc: Hugh Dickins Reviewed-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: David Rientjes Tested-by: Sedat Dilek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 12 ++++++------ arch/x86/mm/pgtable.c | 14 +++++++++----- fs/proc/task_mmu.c | 9 ++++++--- include/linux/mm.h | 24 ++++++++++++++++++++++++ include/linux/mm_types.h | 3 ++- kernel/fork.c | 3 +++ mm/debug.c | 3 ++- mm/hugetlb.c | 8 ++++++-- mm/memory.c | 15 +++++++++------ mm/mmap.c | 4 +++- mm/oom_kill.c | 9 +++++---- 11 files changed, 75 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 4415aa915681..e9c706e4627a 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -555,12 +555,12 @@ this is causing problems for your system/application. oom_dump_tasks -Enables a system-wide task dump (excluding kernel threads) to be -produced when the kernel performs an OOM-killing and includes such -information as pid, uid, tgid, vm size, rss, nr_ptes, swapents, -oom_score_adj score, and name. This is helpful to determine why the -OOM killer was invoked, to identify the rogue task that caused it, -and to determine why the OOM killer chose the task it did to kill. +Enables a system-wide task dump (excluding kernel threads) to be produced +when the kernel performs an OOM-killing and includes such information as +pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, swapents, oom_score_adj +score, and name. This is helpful to determine why the OOM killer was +invoked, to identify the rogue task that caused it, and to determine why +the OOM killer chose the task it did to kill. If this is set to zero, this information is suppressed. On very large systems with thousands of tasks it may not be feasible to dump diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 6fb6927f9e76..7b22adaad4f1 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) #endif /* CONFIG_X86_PAE */ -static void free_pmds(pmd_t *pmds[]) +static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; @@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[]) if (pmds[i]) { pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); + mm_dec_nr_pmds(mm); } } -static int preallocate_pmds(pmd_t *pmds[]) +static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; @@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[]) pmd = NULL; failed = true; } + if (pmd) + mm_inc_nr_pmds(mm); pmds[i] = pmd; } if (failed) { - free_pmds(pmds); + free_pmds(mm, pmds); return -ENOMEM; } @@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); + mm_dec_nr_pmds(mm); } } } @@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) mm->pgd = pgd; - if (preallocate_pmds(pmds) != 0) + if (preallocate_pmds(mm, pmds) != 0) goto out_free_pgd; if (paravirt_pgd_alloc(mm) != 0) @@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; out_free_pmds: - free_pmds(pmds); + free_pmds(mm, pmds); out_free_pgd: free_page((unsigned long)pgd); out: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6396f88c6687..e6e0abeb5d12 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -21,7 +21,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap; + unsigned long data, text, lib, swap, ptes, pmds; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; /* @@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); + ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes); + pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm); seq_printf(m, "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" @@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" "VmPTE:\t%8lu kB\n" + "VmPMD:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), total_vm << (PAGE_SHIFT-10), @@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, - (PTRS_PER_PTE * sizeof(pte_t) * - atomic_long_read(&mm->nr_ptes)) >> 10, + ptes >> 10, + pmds >> 10, swap << (PAGE_SHIFT-10)); } diff --git a/include/linux/mm.h b/include/linux/mm.h index c6bf813a6b3d..644990b83cda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, { return 0; } + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return 0; +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} +static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} + #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return atomic_long_read(&mm->nr_pmds); +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) +{ + atomic_long_inc(&mm->nr_pmds); +} + +static inline void mm_dec_nr_pmds(struct mm_struct *mm) +{ + atomic_long_dec(&mm->nr_pmds); +} #endif int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 20ff2105b564..199a03aab8dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -363,7 +363,8 @@ struct mm_struct { pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - atomic_long_t nr_ptes; /* Page table pages */ + atomic_long_t nr_ptes; /* PTE page table pages */ + atomic_long_t nr_pmds; /* PMD page table pages */ int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some counters */ diff --git a/kernel/fork.c b/kernel/fork.c index b379d9abddc7..c99098c52641 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -555,6 +555,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); +#ifndef __PAGETABLE_PMD_FOLDED + atomic_long_set(&mm->nr_pmds, 0); +#endif mm->map_count = 0; mm->locked_vm = 0; mm->pinned_vm = 0; diff --git a/mm/debug.c b/mm/debug.c index d69cb5a7ba9a..3eb3ac2fcee7 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -173,7 +173,7 @@ void dump_mm(const struct mm_struct *mm) "get_unmapped_area %p\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n" + "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" @@ -206,6 +206,7 @@ void dump_mm(const struct mm_struct *mm) mm->pgd, atomic_read(&mm->mm_users), atomic_read(&mm->mm_count), atomic_long_read((atomic_long_t *)&mm->nr_ptes), + mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fd28d6ba5e5d..0a9ac6c26832 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3598,6 +3598,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { + mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -3609,11 +3610,13 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); spin_lock(ptl); - if (pud_none(*pud)) + if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else + } else { put_page(virt_to_page(spte)); + mm_inc_nr_pmds(mm); + } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -3644,6 +3647,7 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); + mm_dec_nr_pmds(mm); *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } diff --git a/mm/memory.c b/mm/memory.c index d63849b5188f..bbe6a73a899d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -3322,15 +3323,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) /* Another has populated it */ - pmd_free(mm, new); - else + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); -#else - if (pgd_present(*pud)) /* Another has populated it */ + } else /* Another has populated it */ pmd_free(mm, new); - else +#else + if (!pgd_present(*pud)) { + mm_inc_nr_pmds(mm); pgd_populate(mm, pud, new); + } else /* Another has populated it */ + pmd_free(mm, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; diff --git a/mm/mmap.c b/mm/mmap.c index 14d84666e8ba..6a7d36d133fb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2853,7 +2853,9 @@ void exit_mmap(struct mm_struct *mm) vm_unacct_memory(nr_accounted); WARN_ON(atomic_long_read(&mm->nr_ptes) > - (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + round_up(FIRST_USER_ADDRESS, PMD_SIZE) >> PMD_SHIFT); + WARN_ON(mm_nr_pmds(mm) > + round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT); } /* Insert vm structure into process list sorted by address diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b8df76ee2be3..642f38cb175a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -169,8 +169,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + - get_mm_counter(p->mm, MM_SWAPENTS); + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm); task_unlock(p); /* @@ -351,7 +351,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n"); rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) @@ -367,10 +367,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), atomic_long_read(&task->mm->nr_ptes), + mm_nr_pmds(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); -- cgit v1.2.3 From 16c4a097a035c01809aa0c0abd458ca1fe4ff3d0 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:01 -0800 Subject: mm/compaction: enhance tracepoint output for compaction begin/end We now have tracepoint for begin event of compaction and it prints start position of both scanners, but, tracepoint for end event of compaction doesn't print finish position of both scanners. It'd be also useful to know finish position of both scanners so this patch add it. It will help to find odd behavior or problem on compaction internal logic. And mode is added to both begin/end tracepoint output, since according to mode, compaction behavior is quite different. And lastly, status format is changed to string rather than status number for readability. [akpm@linux-foundation.org: fix sparse warning] Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 1 + include/trace/events/compaction.h | 49 ++++++++++++++++++++++++++++----------- mm/compaction.c | 15 ++++++++++-- 3 files changed, 49 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index f2efda2e6ac6..db64cae06530 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,7 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ /* No contention detected */ diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 1337d9e01e3d..839f6fac921a 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -85,46 +85,67 @@ TRACE_EVENT(mm_compaction_migratepages, ); TRACE_EVENT(mm_compaction_begin, - TP_PROTO(unsigned long zone_start, unsigned long migrate_start, - unsigned long free_start, unsigned long zone_end), + TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, + unsigned long free_pfn, unsigned long zone_end, bool sync), - TP_ARGS(zone_start, migrate_start, free_start, zone_end), + TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync), TP_STRUCT__entry( __field(unsigned long, zone_start) - __field(unsigned long, migrate_start) - __field(unsigned long, free_start) + __field(unsigned long, migrate_pfn) + __field(unsigned long, free_pfn) __field(unsigned long, zone_end) + __field(bool, sync) ), TP_fast_assign( __entry->zone_start = zone_start; - __entry->migrate_start = migrate_start; - __entry->free_start = free_start; + __entry->migrate_pfn = migrate_pfn; + __entry->free_pfn = free_pfn; __entry->zone_end = zone_end; + __entry->sync = sync; ), - TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx", + TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s", __entry->zone_start, - __entry->migrate_start, - __entry->free_start, - __entry->zone_end) + __entry->migrate_pfn, + __entry->free_pfn, + __entry->zone_end, + __entry->sync ? "sync" : "async") ); TRACE_EVENT(mm_compaction_end, - TP_PROTO(int status), + TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, + unsigned long free_pfn, unsigned long zone_end, bool sync, + int status), - TP_ARGS(status), + TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status), TP_STRUCT__entry( + __field(unsigned long, zone_start) + __field(unsigned long, migrate_pfn) + __field(unsigned long, free_pfn) + __field(unsigned long, zone_end) + __field(bool, sync) __field(int, status) ), TP_fast_assign( + __entry->zone_start = zone_start; + __entry->migrate_pfn = migrate_pfn; + __entry->free_pfn = free_pfn; + __entry->zone_end = zone_end; + __entry->sync = sync; __entry->status = status; ), - TP_printk("status=%d", __entry->status) + TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s", + __entry->zone_start, + __entry->migrate_pfn, + __entry->free_pfn, + __entry->zone_end, + __entry->sync ? "sync" : "async", + compaction_status_string[__entry->status]) ); #endif /* _TRACE_COMPACTION_H */ diff --git a/mm/compaction.c b/mm/compaction.c index 9c7e6909dd29..66f7c365e888 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -34,6 +34,15 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA +#ifdef CONFIG_TRACEPOINTS +static const char *const compaction_status_string[] = { + "deferred", + "skipped", + "continue", + "partial", + "complete", +}; +#endif #define CREATE_TRACE_POINTS #include @@ -1197,7 +1206,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } - trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync); migrate_prep_local(); @@ -1299,7 +1309,8 @@ out: zone->compact_cached_free_pfn = free_pfn; } - trace_mm_compaction_end(ret); + trace_mm_compaction_end(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync, ret); return ret; } -- cgit v1.2.3 From 837d026d560c5ef26abeca0441713d82e4e82cad Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:06 -0800 Subject: mm/compaction: more trace to understand when/why compaction start/finish It is not well analyzed that when/why compaction start/finish or not. With these new tracepoints, we can know much more about start/finish reason of compaction. I can find following bug with these tracepoint. http://www.spinics.net/lists/linux-mm/msg81582.html Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 ++ include/trace/events/compaction.h | 74 +++++++++++++++++++++++++++++++++++++++ mm/compaction.c | 38 +++++++++++++++++--- 3 files changed, 111 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index db64cae06530..501d7513aac1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,9 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* For more detailed tracepoint output */ +#define COMPACT_NO_SUITABLE_PAGE 5 +#define COMPACT_NOT_SUITABLE_ZONE 6 /* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 139020b55612..d46535801f63 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -164,6 +164,80 @@ TRACE_EVENT(mm_compaction_end, compaction_status_string[__entry->status]) ); +TRACE_EVENT(mm_compaction_try_to_compact_pages, + + TP_PROTO( + int order, + gfp_t gfp_mask, + enum migrate_mode mode), + + TP_ARGS(order, gfp_mask, mode), + + TP_STRUCT__entry( + __field(int, order) + __field(gfp_t, gfp_mask) + __field(enum migrate_mode, mode) + ), + + TP_fast_assign( + __entry->order = order; + __entry->gfp_mask = gfp_mask; + __entry->mode = mode; + ), + + TP_printk("order=%d gfp_mask=0x%x mode=%d", + __entry->order, + __entry->gfp_mask, + (int)__entry->mode) +); + +DECLARE_EVENT_CLASS(mm_compaction_suitable_template, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret), + + TP_STRUCT__entry( + __field(int, nid) + __field(char *, name) + __field(int, order) + __field(int, ret) + ), + + TP_fast_assign( + __entry->nid = zone_to_nid(zone); + __entry->name = (char *)zone->name; + __entry->order = order; + __entry->ret = ret; + ), + + TP_printk("node=%d zone=%-8s order=%d ret=%s", + __entry->nid, + __entry->name, + __entry->order, + compaction_status_string[__entry->ret]) +); + +DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret) +); + +DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret) +); + #endif /* _TRACE_COMPACTION_H */ /* This part must be outside protection */ diff --git a/mm/compaction.c b/mm/compaction.c index b12df9fe10b4..b6ede459c1bb 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -41,6 +41,8 @@ static const char *const compaction_status_string[] = { "continue", "partial", "complete", + "no_suitable_page", + "not_suitable_zone", }; #endif @@ -1049,7 +1051,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } -static int compact_finished(struct zone *zone, struct compact_control *cc, +static int __compact_finished(struct zone *zone, struct compact_control *cc, const int migratetype) { unsigned int order; @@ -1104,7 +1106,20 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, return COMPACT_PARTIAL; } - return COMPACT_CONTINUE; + return COMPACT_NO_SUITABLE_PAGE; +} + +static int compact_finished(struct zone *zone, struct compact_control *cc, + const int migratetype) +{ + int ret; + + ret = __compact_finished(zone, cc, migratetype); + trace_mm_compaction_finished(zone, cc->order, ret); + if (ret == COMPACT_NO_SUITABLE_PAGE) + ret = COMPACT_CONTINUE; + + return ret; } /* @@ -1114,7 +1129,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, * COMPACT_PARTIAL - If the allocation would succeed without compaction * COMPACT_CONTINUE - If compaction should run now */ -unsigned long compaction_suitable(struct zone *zone, int order, +static unsigned long __compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx) { int fragindex; @@ -1158,11 +1173,24 @@ unsigned long compaction_suitable(struct zone *zone, int order, */ fragindex = fragmentation_index(zone, order); if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - return COMPACT_SKIPPED; + return COMPACT_NOT_SUITABLE_ZONE; return COMPACT_CONTINUE; } +unsigned long compaction_suitable(struct zone *zone, int order, + int alloc_flags, int classzone_idx) +{ + unsigned long ret; + + ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx); + trace_mm_compaction_suitable(zone, order, ret); + if (ret == COMPACT_NOT_SUITABLE_ZONE) + ret = COMPACT_SKIPPED; + + return ret; +} + static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; @@ -1376,6 +1404,8 @@ unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, if (!order || !may_enter_fs || !may_perform_io) return COMPACT_SKIPPED; + trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode); + /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, ac->nodemask) { -- cgit v1.2.3 From 24e2716f63e613cf15d3beba3faa0711bcacc427 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:09 -0800 Subject: mm/compaction: add tracepoint to observe behaviour of compaction defer Compaction deferring logic is heavy hammer that block the way to the compaction. It doesn't consider overall system state, so it could prevent user from doing compaction falsely. In other words, even if system has enough range of memory to compact, compaction would be skipped due to compaction deferring logic. This patch add new tracepoint to understand work of deferring logic. This will also help to check compaction success and fail. Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 65 +++-------------------------------- include/trace/events/compaction.h | 56 ++++++++++++++++++++++++++++++ mm/compaction.c | 71 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 132 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 501d7513aac1..a014559e4a49 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -44,66 +44,11 @@ extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx); -/* Do not skip compaction more than 64 times */ -#define COMPACT_MAX_DEFER_SHIFT 6 - -/* - * Compaction is deferred when compaction fails to result in a page - * allocation success. 1 << compact_defer_limit compactions are skipped up - * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT - */ -static inline void defer_compaction(struct zone *zone, int order) -{ - zone->compact_considered = 0; - zone->compact_defer_shift++; - - if (order < zone->compact_order_failed) - zone->compact_order_failed = order; - - if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) - zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; -} - -/* Returns true if compaction should be skipped this time */ -static inline bool compaction_deferred(struct zone *zone, int order) -{ - unsigned long defer_limit = 1UL << zone->compact_defer_shift; - - if (order < zone->compact_order_failed) - return false; - - /* Avoid possible overflow */ - if (++zone->compact_considered > defer_limit) - zone->compact_considered = defer_limit; - - return zone->compact_considered < defer_limit; -} - -/* - * Update defer tracking counters after successful compaction of given order, - * which means an allocation either succeeded (alloc_success == true) or is - * expected to succeed. - */ -static inline void compaction_defer_reset(struct zone *zone, int order, - bool alloc_success) -{ - if (alloc_success) { - zone->compact_considered = 0; - zone->compact_defer_shift = 0; - } - if (order >= zone->compact_order_failed) - zone->compact_order_failed = order + 1; -} - -/* Returns true if restarting compaction after many failures */ -static inline bool compaction_restarting(struct zone *zone, int order) -{ - if (order < zone->compact_order_failed) - return false; - - return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && - zone->compact_considered >= 1UL << zone->compact_defer_shift; -} +extern void defer_compaction(struct zone *zone, int order); +extern bool compaction_deferred(struct zone *zone, int order); +extern void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success); +extern bool compaction_restarting(struct zone *zone, int order); #else static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index d46535801f63..9a6a3fe0fb51 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -238,6 +238,62 @@ DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable, TP_ARGS(zone, order, ret) ); +#ifdef CONFIG_COMPACTION +DECLARE_EVENT_CLASS(mm_compaction_defer_template, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order), + + TP_STRUCT__entry( + __field(int, nid) + __field(char *, name) + __field(int, order) + __field(unsigned int, considered) + __field(unsigned int, defer_shift) + __field(int, order_failed) + ), + + TP_fast_assign( + __entry->nid = zone_to_nid(zone); + __entry->name = (char *)zone->name; + __entry->order = order; + __entry->considered = zone->compact_considered; + __entry->defer_shift = zone->compact_defer_shift; + __entry->order_failed = zone->compact_order_failed; + ), + + TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu", + __entry->nid, + __entry->name, + __entry->order, + __entry->order_failed, + __entry->considered, + 1UL << __entry->defer_shift) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); +#endif + #endif /* _TRACE_COMPACTION_H */ /* This part must be outside protection */ diff --git a/mm/compaction.c b/mm/compaction.c index b6ede459c1bb..b68736c8a1ce 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -124,6 +124,77 @@ static struct page *pageblock_pfn_to_page(unsigned long start_pfn, } #ifdef CONFIG_COMPACTION + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * allocation success. 1 << compact_defer_limit compactions are skipped up + * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT + */ +void defer_compaction(struct zone *zone, int order) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + if (order < zone->compact_order_failed) + zone->compact_order_failed = order; + + if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) + zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; + + trace_mm_compaction_defer_compaction(zone, order); +} + +/* Returns true if compaction should be skipped this time */ +bool compaction_deferred(struct zone *zone, int order) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + if (order < zone->compact_order_failed) + return false; + + /* Avoid possible overflow */ + if (++zone->compact_considered > defer_limit) + zone->compact_considered = defer_limit; + + if (zone->compact_considered >= defer_limit) + return false; + + trace_mm_compaction_deferred(zone, order); + + return true; +} + +/* + * Update defer tracking counters after successful compaction of given order, + * which means an allocation either succeeded (alloc_success == true) or is + * expected to succeed. + */ +void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success) +{ + if (alloc_success) { + zone->compact_considered = 0; + zone->compact_defer_shift = 0; + } + if (order >= zone->compact_order_failed) + zone->compact_order_failed = order + 1; + + trace_mm_compaction_defer_reset(zone, order); +} + +/* Returns true if restarting compaction after many failures */ +bool compaction_restarting(struct zone *zone, int order) +{ + if (order < zone->compact_order_failed) + return false; + + return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && + zone->compact_considered >= 1UL << zone->compact_defer_shift; +} + /* Returns true if the pageblock should be scanned for pages to isolate. */ static inline bool isolation_suitable(struct compact_control *cc, struct page *page) -- cgit v1.2.3 From 077fcf116c8c2bd7ee9487b645aa3b50368db7e1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 11 Feb 2015 15:27:12 -0800 Subject: mm/thp: allocate transparent hugepages on local node This make sure that we try to allocate hugepages from local node if allowed by mempolicy. If we can't, we fallback to small page allocation based on mempolicy. This is based on the observation that allocating pages on local node is more beneficial than allocating hugepages on remote node. With this patch applied we may find transparent huge page allocation failures if the current node doesn't have enough freee hugepages. Before this patch such failures result in us retrying the allocation on other nodes in the numa node mask. [akpm@linux-foundation.org: fix comment, add CONFIG_TRANSPARENT_HUGEPAGE dependency] Signed-off-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++ mm/huge_memory.c | 24 +++++++----------- mm/mempolicy.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b840e3b2770d..60110e06419d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -335,11 +335,15 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node); +extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) #define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 889713180980..0531ea7dd7cf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -761,15 +761,6 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp) return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp; } -static inline struct page *alloc_hugepage_vma(int defrag, - struct vm_area_struct *vma, - unsigned long haddr, int nd, - gfp_t extra_gfp) -{ - return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp), - HPAGE_PMD_ORDER, vma, haddr, nd); -} - /* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, @@ -790,6 +781,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { + gfp_t gfp; struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; @@ -824,8 +816,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, } return 0; } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1113,10 +1105,12 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && - !transparent_hugepage_debug_cow()) - new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - else + !transparent_hugepage_debug_cow()) { + gfp_t gfp; + + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + } else new_page = NULL; if (unlikely(!new_page)) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e0961b8c39c..8a32873fdbf7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2030,6 +2030,78 @@ retry_cpuset: return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * alloc_hugepage_vma: Allocate a hugepage for a VMA + * @gfp: + * %GFP_USER user allocation. + * %GFP_KERNEL kernel allocations, + * %GFP_HIGHMEM highmem/user allocations, + * %GFP_FS allocation should not call back into a file system. + * %GFP_ATOMIC don't sleep. + * + * @vma: Pointer to VMA or NULL if not available. + * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @order: Order of the hugepage for gfp allocation. + * + * This functions allocate a huge page from the kernel page pool and applies + * a NUMA policy associated with the VMA or the current process. + * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage + * only from the current node if the current node is part of the node mask. + * If we can't allocate a hugepage we fail the allocation and don' try to fallback + * to other nodes in the node mask. If the current node is not part of node mask + * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can + * fallback to nodes in the policy node mask. + * + * When VMA is not NULL caller must hold down_read on the mmap_sem of the + * mm_struct of the VMA to prevent it from going away. Should be used for + * all allocations for pages that will be mapped into + * user space. Returns NULL when no page can be allocated. + * + * Should be called with vma->vm_mm->mmap_sem held. + * + */ +struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order) +{ + struct page *page; + nodemask_t *nmask; + struct mempolicy *pol; + int node = numa_node_id(); + unsigned int cpuset_mems_cookie; + +retry_cpuset: + pol = get_vma_policy(vma, addr); + cpuset_mems_cookie = read_mems_allowed_begin(); + /* + * For interleave policy, we don't worry about + * current node. Otherwise if current node is + * in nodemask, try to allocate hugepage from + * the current node. Don't fall back to other nodes + * for THP. + */ + if (unlikely(pol->mode == MPOL_INTERLEAVE)) + goto alloc_with_fallback; + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + if (unlikely(!page && + read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; + } +alloc_with_fallback: + mpol_cond_put(pol); + /* + * if current node is not part of node mask, try + * the allocation from any node, and we can do retry + * in that case. + */ + return alloc_pages_vma(gfp, order, vma, addr, node); +} +#endif + /** * alloc_pages_current - Allocate pages. * -- cgit v1.2.3 From be97a41b291e495d6cb767b3ee0f84ed05804892 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:27:15 -0800 Subject: mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma The previous commit ("mm/thp: Allocate transparent hugepages on local node") introduced alloc_hugepage_vma() to mm/mempolicy.c to perform a special policy for THP allocations. The function has the same interface as alloc_pages_vma(), shares a lot of boilerplate code and a long comment. This patch merges the hugepage special case into alloc_pages_vma. The extra if condition should be cheap enough price to pay. We also prevent a (however unlikely) race with parallel mems_allowed update, which could make hugepage allocation restart only within the fallback call to alloc_hugepage_vma() and not reconsider the special rule in alloc_hugepage_vma(). Also by making sure mpol_cond_put(pol) is always called before actual allocation attempt, we can use a single exit path within the function. Also update the comment for missing node parameter and obsolete reference to mm_sem. Signed-off-by: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 +++--- mm/mempolicy.c | 118 +++++++++++++++------------------------------------- 2 files changed, 39 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 60110e06419d..51bd1e72a917 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -334,22 +334,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); -extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, - unsigned long addr, int order); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order); extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8a32873fdbf7..acbbf4c821e2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1988,120 +1988,68 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must hold down_read on the mmap_sem of the * mm_struct of the VMA to prevent it from going away. Should be used for - * all allocations for pages that will be mapped into - * user space. Returns NULL when no page can be allocated. - * - * Should be called with the mm_sem of the vma hold. + * all allocations for pages that will be mapped into user space. Returns + * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; unsigned int cpuset_mems_cookie; + struct zonelist *zl; + nodemask_t *nmask; retry_cpuset: pol = get_vma_policy(vma, addr); cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(pol->mode == MPOL_INTERLEAVE)) { + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage && + pol->mode != MPOL_INTERLEAVE)) { + /* + * For hugepage allocation and non-interleave policy which + * allows the current node, we only try to allocate from the + * current node and don't fall back to other nodes, as the + * cost of remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + goto out; + } + } + + if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - - return page; + goto out; } - page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol, node), - policy_nodemask(gfp, pol)); + + nmask = policy_nodemask(gfp, pol); + zl = policy_zonelist(gfp, pol, node); mpol_cond_put(pol); + page = __alloc_pages_nodemask(gfp, order, zl, nmask); +out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/** - * alloc_hugepage_vma: Allocate a hugepage for a VMA - * @gfp: - * %GFP_USER user allocation. - * %GFP_KERNEL kernel allocations, - * %GFP_HIGHMEM highmem/user allocations, - * %GFP_FS allocation should not call back into a file system. - * %GFP_ATOMIC don't sleep. - * - * @vma: Pointer to VMA or NULL if not available. - * @addr: Virtual Address of the allocation. Must be inside the VMA. - * @order: Order of the hugepage for gfp allocation. - * - * This functions allocate a huge page from the kernel page pool and applies - * a NUMA policy associated with the VMA or the current process. - * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage - * only from the current node if the current node is part of the node mask. - * If we can't allocate a hugepage we fail the allocation and don' try to fallback - * to other nodes in the node mask. If the current node is not part of node mask - * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can - * fallback to nodes in the policy node mask. - * - * When VMA is not NULL caller must hold down_read on the mmap_sem of the - * mm_struct of the VMA to prevent it from going away. Should be used for - * all allocations for pages that will be mapped into - * user space. Returns NULL when no page can be allocated. - * - * Should be called with vma->vm_mm->mmap_sem held. - * - */ -struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, - unsigned long addr, int order) -{ - struct page *page; - nodemask_t *nmask; - struct mempolicy *pol; - int node = numa_node_id(); - unsigned int cpuset_mems_cookie; - -retry_cpuset: - pol = get_vma_policy(vma, addr); - cpuset_mems_cookie = read_mems_allowed_begin(); - /* - * For interleave policy, we don't worry about - * current node. Otherwise if current node is - * in nodemask, try to allocate hugepage from - * the current node. Don't fall back to other nodes - * for THP. - */ - if (unlikely(pol->mode == MPOL_INTERLEAVE)) - goto alloc_with_fallback; - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(node, *nmask)) { - mpol_cond_put(pol); - page = alloc_pages_exact_node(node, gfp, order); - if (unlikely(!page && - read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - return page; - } -alloc_with_fallback: - mpol_cond_put(pol); - /* - * if current node is not part of node mask, try - * the allocation from any node, and we can do retry - * in that case. - */ - return alloc_pages_vma(gfp, order, vma, addr, node); -} -#endif - /** * alloc_pages_current - Allocate pages. * -- cgit v1.2.3 From f0818f472d8d527a96ec9cc2c3a56223497f9dd3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:17 -0800 Subject: mm: gup: add get_user_pages_locked and get_user_pages_unlocked FAULT_FOLL_ALLOW_RETRY allows the page fault to drop the mmap_sem for reading to reduce the mmap_sem contention (for writing), like while waiting for I/O completion. The problem is that right now practically no get_user_pages call uses FAULT_FOLL_ALLOW_RETRY, so we're not leveraging that nifty feature. Andres fixed it for the KVM page fault. However get_user_pages_fast remains uncovered, and 99% of other get_user_pages aren't using it either (the only exception being FOLL_NOWAIT in KVM which is really nonblocking and in fact it doesn't even release the mmap_sem). So this patchsets extends the optimization Andres did in the KVM page fault to the whole kernel. It makes most important places (including gup_fast) to use FAULT_FOLL_ALLOW_RETRY to reduce the mmap_sem hold times during I/O. The only few places that remains uncovered are drivers like v4l and other exceptions that tends to work on their own memory and they're not working on random user memory (for example like O_DIRECT that uses gup_fast and is fully covered by this patch). A follow up patch should probably also add a printk_once warning to get_user_pages that should go obsolete and be phased out eventually. The "vmas" parameter of get_user_pages makes it fundamentally incompatible with FAULT_FOLL_ALLOW_RETRY (vmas array becomes meaningless the moment the mmap_sem is released). While this is just an optimization, this becomes an absolute requirement for the userfaultfd feature http://lwn.net/Articles/615086/ . The userfaultfd allows to block the page fault, and in order to do so I need to drop the mmap_sem first. So this patch also ensures that all memory where userfaultfd could be registered by KVM, the very first fault (no matter if it is a regular page fault, or a get_user_pages) always has FAULT_FOLL_ALLOW_RETRY set. Then the userfaultfd blocks and it is waken only when the pagetable is already mapped. The second fault attempt after the wakeup doesn't need FAULT_FOLL_ALLOW_RETRY, so it's ok to retry without it. This patch (of 5): We can leverage the VM_FAULT_RETRY functionality in the page fault paths better by using either get_user_pages_locked or get_user_pages_unlocked. The former allows conversion of get_user_pages invocations that will have to pass a "&locked" parameter to know if the mmap_sem was dropped during the call. Example from: down_read(&mm->mmap_sem); do_something() get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); to: int locked = 1; down_read(&mm->mmap_sem); do_something() get_user_pages_locked(tsk, mm, ..., pages, &locked); if (locked) up_read(&mm->mmap_sem); The latter is suitable only as a drop in replacement of the form: down_read(&mm->mmap_sem); get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); into: get_user_pages_unlocked(tsk, mm, ..., pages); Where tsk, mm, the intermediate "..." paramters and "pages" can be any value as before. Just the last parameter of get_user_pages (vmas) must be NULL for get_user_pages_locked|unlocked to be usable (the latter original form wouldn't have been safe anyway if vmas wasn't null, for the former we just make it explicit by dropping the parameter). If vmas is not NULL these two methods cannot be used. Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Peter Feiner Reviewed-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++ mm/gup.c | 177 +++++++++++++++++++++++++++++++++++++++++++++++++---- mm/nommu.c | 23 +++++++ 3 files changed, 196 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 644990b83cda..fc499e675475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1261,6 +1261,13 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked); +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct kvec; diff --git a/mm/gup.c b/mm/gup.c index 1a8ab05918e0..71a37738a326 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -575,6 +575,165 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return 0; } +static __always_inline long __get_user_pages_locked(struct task_struct *tsk, + struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + int write, int force, + struct page **pages, + struct vm_area_struct **vmas, + int *locked, bool notify_drop) +{ + int flags = FOLL_TOUCH; + long ret, pages_done; + bool lock_dropped; + + if (locked) { + /* if VM_FAULT_RETRY can be returned, vmas become invalid */ + BUG_ON(vmas); + /* check caller initialized locked */ + BUG_ON(*locked != 1); + } + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + pages_done = 0; + lock_dropped = false; + for (;;) { + ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages, + vmas, locked); + if (!locked) + /* VM_FAULT_RETRY couldn't trigger, bypass */ + return ret; + + /* VM_FAULT_RETRY cannot return errors */ + if (!*locked) { + BUG_ON(ret < 0); + BUG_ON(ret >= nr_pages); + } + + if (!pages) + /* If it's a prefault don't insist harder */ + return ret; + + if (ret > 0) { + nr_pages -= ret; + pages_done += ret; + if (!nr_pages) + break; + } + if (*locked) { + /* VM_FAULT_RETRY didn't trigger */ + if (!pages_done) + pages_done = ret; + break; + } + /* VM_FAULT_RETRY triggered, so seek to the faulting offset */ + pages += ret; + start += ret << PAGE_SHIFT; + + /* + * Repeat on the address that fired VM_FAULT_RETRY + * without FAULT_FLAG_ALLOW_RETRY but with + * FAULT_FLAG_TRIED. + */ + *locked = 1; + lock_dropped = true; + down_read(&mm->mmap_sem); + ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED, + pages, NULL, NULL); + if (ret != 1) { + BUG_ON(ret > 1); + if (!pages_done) + pages_done = ret; + break; + } + nr_pages--; + pages_done++; + if (!nr_pages) + break; + pages++; + start += PAGE_SIZE; + } + if (notify_drop && lock_dropped && *locked) { + /* + * We must let the caller know we temporarily dropped the lock + * and so the critical section protected by it was lost. + */ + up_read(&mm->mmap_sem); + *locked = 0; + } + return pages_done; +} + +/* + * We can leverage the VM_FAULT_RETRY functionality in the page fault + * paths better by using either get_user_pages_locked() or + * get_user_pages_unlocked(). + * + * get_user_pages_locked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * to: + * + * int locked = 1; + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * if (locked) + * up_read(&mm->mmap_sem); + */ +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, locked, true); +} +EXPORT_SYMBOL(get_user_pages_locked); + +/* + * get_user_pages_unlocked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * with: + * + * get_user_pages_unlocked(tsk, mm, ..., pages); + * + * It is functionally equivalent to get_user_pages_fast so + * get_user_pages_fast should be used instead, if the two parameters + * "tsk" and "mm" are respectively equal to current and current->mm, + * or if "force" shall be set to 1 (get_user_pages_fast misses the + * "force" parameter). + */ +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + long ret; + int locked = 1; + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, &locked, false); + if (locked) + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /* * get_user_pages() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or @@ -624,22 +783,18 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, * use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. + * + * get_user_pages should be phased out in favor of + * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing + * should use get_user_pages because it cannot pass + * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, vmas, NULL, false); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/nommu.c b/mm/nommu.c index 541bed64e348..bfb690b0f986 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -214,6 +214,29 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); +} +EXPORT_SYMBOL(get_user_pages_locked); + +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + long ret; + down_read(&mm->mmap_sem); + ret = get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping -- cgit v1.2.3 From 0fd71a56f41d4ffabeda1dae9ff5ed4f34d4e935 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:20 -0800 Subject: mm: gup: add __get_user_pages_unlocked to customize gup_flags Some callers (like KVM) may want to set the gup_flags like FOLL_HWPOSION to get a proper -EHWPOSION retval instead of -EFAULT to take a more appropriate action if get_user_pages runs into a memory failure. Signed-off-by: Andrea Arcangeli Reviewed-by: Kirill A. Shutemov Cc: Andres Lagar-Cavilla Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ mm/gup.c | 44 ++++++++++++++++++++++++++++++++------------ mm/nommu.c | 16 +++++++++++++--- 3 files changed, 49 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fc499e675475..3696b3bd1d7e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1265,6 +1265,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, int *locked); +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags); long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages); diff --git a/mm/gup.c b/mm/gup.c index 71a37738a326..dad5875fb766 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -582,9 +582,9 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, int write, int force, struct page **pages, struct vm_area_struct **vmas, - int *locked, bool notify_drop) + int *locked, bool notify_drop, + unsigned int flags) { - int flags = FOLL_TOUCH; long ret, pages_done; bool lock_dropped; @@ -698,10 +698,36 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, int *locked) { return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, locked, true); + pages, NULL, locked, true, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages_locked); +/* + * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to + * pass additional gup_flags as last parameter (like FOLL_HWPOISON). + * + * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the + * caller if required (just like with __get_user_pages). "FOLL_GET", + * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed + * according to the parameters "pages", "write", "force" + * respectively. + */ +__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) +{ + long ret; + int locked = 1; + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, &locked, false, gup_flags); + if (locked) + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(__get_user_pages_unlocked); + /* * get_user_pages_unlocked() is suitable to replace the form: * @@ -723,14 +749,8 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages) { - long ret; - int locked = 1; - down_read(&mm->mmap_sem); - ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, &locked, false); - if (locked) - up_read(&mm->mmap_sem); - return ret; + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages_unlocked); @@ -794,7 +814,7 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int force, struct page **pages, struct vm_area_struct **vmas) { return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, vmas, NULL, false); + pages, vmas, NULL, false, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/nommu.c b/mm/nommu.c index bfb690b0f986..4d1b8a199867 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -224,9 +224,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages_locked); -long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) { long ret; down_read(&mm->mmap_sem); @@ -235,6 +236,15 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, up_read(&mm->mmap_sem); return ret; } +EXPORT_SYMBOL(__get_user_pages_unlocked); + +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, 0); +} EXPORT_SYMBOL(get_user_pages_unlocked); /** -- cgit v1.2.3 From 0664e57ff0c68cbca012a45a38288fa277eb6795 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:28 -0800 Subject: mm: gup: kvm use get_user_pages_unlocked Use the more generic get_user_pages_unlocked which has the additional benefit of passing FAULT_FLAG_ALLOW_RETRY at the very first page fault (which allows the first page fault in an unmapped area to be always able to block indefinitely by being allowed to release the mmap_sem). Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Kirill A. Shutemov Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kvm_host.h | 11 ----------- virt/kvm/async_pf.c | 2 +- virt/kvm/kvm_main.c | 50 ++++-------------------------------------------- 3 files changed, 5 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 26f106022c88..d189ee098aa2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -200,17 +200,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -/* - * Carry out a gup that requires IO. Allow the mm to relinquish the mmap - * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL - * controls whether we retry the gup one more time to completion in that case. - * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp - * handler. - */ -int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, bool write_fault, - struct page **pagep); - enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 5ff7f7f2689a..44660aee335f 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -80,7 +80,7 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); - kvm_get_user_page_io(NULL, mm, addr, 1, NULL); + get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL); kvm_async_page_present_sync(vcpu, apf); spin_lock(&vcpu->async_pf.lock); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1cc6e2e19982..458b9b14b15c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1128,43 +1128,6 @@ static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL); } -int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, bool write_fault, - struct page **pagep) -{ - int npages; - int locked = 1; - int flags = FOLL_TOUCH | FOLL_HWPOISON | - (pagep ? FOLL_GET : 0) | - (write_fault ? FOLL_WRITE : 0); - - /* - * If retrying the fault, we get here *not* having allowed the filemap - * to wait on the page lock. We should now allow waiting on the IO with - * the mmap semaphore released. - */ - down_read(&mm->mmap_sem); - npages = __get_user_pages(tsk, mm, addr, 1, flags, pagep, NULL, - &locked); - if (!locked) { - VM_BUG_ON(npages); - - if (!pagep) - return 0; - - /* - * The previous call has now waited on the IO. Now we can - * retry and complete. Pass TRIED to ensure we do not re - * schedule async IO (see e.g. filemap_fault). - */ - down_read(&mm->mmap_sem); - npages = __get_user_pages(tsk, mm, addr, 1, flags | FOLL_TRIED, - pagep, NULL, NULL); - } - up_read(&mm->mmap_sem); - return npages; -} - static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE; @@ -1227,15 +1190,10 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, npages = get_user_page_nowait(current, current->mm, addr, write_fault, page); up_read(¤t->mm->mmap_sem); - } else { - /* - * By now we have tried gup_fast, and possibly async_pf, and we - * are certainly not atomic. Time to retry the gup, allowing - * mmap semaphore to be relinquished in the case of IO. - */ - npages = kvm_get_user_page_io(current, current->mm, addr, - write_fault, page); - } + } else + npages = __get_user_pages_unlocked(current, current->mm, addr, 1, + write_fault, 0, page, + FOLL_TOUCH|FOLL_HWPOISON); if (npages != 1) return npages; -- cgit v1.2.3 From 0b1fbfe50006c41014cc25660c0e735d21c34939 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:34 -0800 Subject: mm/pagewalk: remove pgd_entry() and pud_entry() Currently no user of page table walker sets ->pgd_entry() or ->pud_entry(), so checking their existence in each loop is just wasting CPU cycle. So let's remove it to reduce overhead. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ mm/pagewalk.c | 9 ++------- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3696b3bd1d7e..f6106d3f3dab 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1164,8 +1164,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, /** * mm_walk - callbacks for walk_page_range - * @pgd_entry: if set, called for each non-empty PGD (top-level) entry - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to @@ -1179,10 +1177,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *pgd, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pud_entry)(pud_t *pud, unsigned long addr, - unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_entry)(pte_t *pte, unsigned long addr, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index b264bda46e1b..b793ef149da2 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -86,9 +86,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, break; continue; } - if (walk->pud_entry) - err = walk->pud_entry(pud, addr, next, walk); - if (!err && (walk->pmd_entry || walk->pte_entry)) + if (walk->pmd_entry || walk->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) break; @@ -237,10 +235,7 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd++; continue; } - if (walk->pgd_entry) - err = walk->pgd_entry(pgd, addr, next, walk); - if (!err && - (walk->pud_entry || walk->pmd_entry || walk->pte_entry)) + if (walk->pmd_entry || walk->pte_entry) err = walk_pud_range(pgd, addr, next, walk); if (err) break; -- cgit v1.2.3 From fafaa4264eba49fd10695c193a82760558d093f4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:37 -0800 Subject: pagewalk: improve vma handling Current implementation of page table walker has a fundamental problem in vma handling, which started when we tried to handle vma(VM_HUGETLB). Because it's done in pgd loop, considering vma boundary makes code complicated and bug-prone. From the users viewpoint, some user checks some vma-related condition to determine whether the user really does page walk over the vma. In order to solve these, this patch moves vma check outside pgd loop and introduce a new callback ->test_walk(). Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +++- mm/pagewalk.c | 206 ++++++++++++++++++++++++++++++----------------------- 2 files changed, 129 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6106d3f3dab..3891a368e5e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1171,10 +1171,16 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry - * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry - * is used. + * @test_walk: caller specific callback function to determine whether + * we walk over the current vma or not. A positive returned + * value means "do page table walk over the current vma," + * and a negative one means "abort current page table walk + * right now." 0 means "skip the current vma." + * @mm: mm_struct representing the target process of page table walk + * @vma: vma currently walked (NULL if walking outside vmas) + * @private: private data for callbacks' usage * - * (see walk_page_range for more details) + * (see the comment on walk_page_range() for more details) */ struct mm_walk { int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -1186,7 +1192,10 @@ struct mm_walk { int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); + int (*test_walk)(unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; + struct vm_area_struct *vma; void *private; }; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index b793ef149da2..d9cc3caae802 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -59,7 +59,7 @@ again: continue; split_huge_page_pmd_mm(walk->mm, addr, pmd); - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + if (pmd_trans_unstable(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); if (err) @@ -95,6 +95,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_pgd_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pgd_t *pgd; + unsigned long next; + int err = 0; + + pgd = pgd_offset(walk->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(pgd, addr, next, walk); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + return err; +} + #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, unsigned long end) @@ -103,10 +129,10 @@ static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, return boundary < end ? boundary : end; } -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { + struct vm_area_struct *vma = walk->vma; struct hstate *h = hstate_vma(vma); unsigned long next; unsigned long hmask = huge_page_mask(h); @@ -119,15 +145,14 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, if (pte && walk->hugetlb_entry) err = walk->hugetlb_entry(pte, hmask, addr, next, walk); if (err) - return err; + break; } while (addr = next, addr != end); - return 0; + return err; } #else /* CONFIG_HUGETLB_PAGE */ -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; @@ -135,112 +160,115 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, #endif /* CONFIG_HUGETLB_PAGE */ +/* + * Decide whether we really walk over the current vma on [@start, @end) + * or skip it via the returned value. Return 0 if we do walk over the + * current vma, and return 1 if we skip the vma. Negative values means + * error, where we abort the current walk. + * + * Default check (only VM_PFNMAP check for now) is used when the caller + * doesn't define test_walk() callback. + */ +static int walk_page_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + if (walk->test_walk) + return walk->test_walk(start, end, walk); + + /* + * Do not walk over vma(VM_PFNMAP), because we have no valid struct + * page backing a VM_PFNMAP range. See also commit a9ff785e4437. + */ + if (vma->vm_flags & VM_PFNMAP) + return 1; + return 0; +} + +static int __walk_page_range(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + int err = 0; + struct vm_area_struct *vma = walk->vma; + + if (vma && is_vm_hugetlb_page(vma)) { + if (walk->hugetlb_entry) + err = walk_hugetlb_range(start, end, walk); + } else + err = walk_pgd_range(start, end, walk); + + return err; +} /** - * walk_page_range - walk a memory map's page tables with a callback - * @addr: starting address - * @end: ending address - * @walk: set of callbacks to invoke for each level of the tree - * - * Recursively walk the page table for the memory area in a VMA, - * calling supplied callbacks. Callbacks are called in-order (first - * PGD, first PUD, first PMD, first PTE, second PTE... second PMD, - * etc.). If lower-level callbacks are omitted, walking depth is reduced. + * walk_page_range - walk page table with caller specific callbacks * - * Each callback receives an entry pointer and the start and end of the - * associated range, and a copy of the original mm_walk for access to - * the ->private or ->mm fields. + * Recursively walk the page table tree of the process represented by @walk->mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. * - * Usually no locks are taken, but splitting transparent huge page may - * take page table lock. And the bottom level iterator will map PTE - * directories from highmem if necessary. + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @walk->test_walk() are used for this + * purpose. * - * If any callback returns a non-zero value, the walk is aborted and - * the return value is propagated back to the caller. Otherwise 0 is returned. + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @walk->private should be helpful. * - * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry - * is !NULL. + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold + * @walk->mm->mmap_sem, because these function traverse vma list and/or + * access to vma's data. */ -int walk_page_range(unsigned long addr, unsigned long end, +int walk_page_range(unsigned long start, unsigned long end, struct mm_walk *walk) { - pgd_t *pgd; - unsigned long next; int err = 0; + unsigned long next; + struct vm_area_struct *vma; - if (addr >= end) - return err; + if (start >= end) + return -EINVAL; if (!walk->mm) return -EINVAL; VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm); - pgd = pgd_offset(walk->mm, addr); + vma = find_vma(walk->mm, start); do { - struct vm_area_struct *vma = NULL; + if (!vma) { /* after the last vma */ + walk->vma = NULL; + next = end; + } else if (start < vma->vm_start) { /* outside vma */ + walk->vma = NULL; + next = min(end, vma->vm_start); + } else { /* inside vma */ + walk->vma = vma; + next = min(end, vma->vm_end); + vma = vma->vm_next; - next = pgd_addr_end(addr, end); - - /* - * This function was not intended to be vma based. - * But there are vma special cases to be handled: - * - hugetlb vma's - * - VM_PFNMAP vma's - */ - vma = find_vma(walk->mm, addr); - if (vma) { - /* - * There are no page structures backing a VM_PFNMAP - * range, so do not allow split_huge_page_pmd(). - */ - if ((vma->vm_start <= addr) && - (vma->vm_flags & VM_PFNMAP)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); + err = walk_page_test(start, next, walk); + if (err > 0) continue; - } - /* - * Handle hugetlb vma individually because pagetable - * walk for the hugetlb page is dependent on the - * architecture and we can't handled it in the same - * manner as non-huge pages. - */ - if (walk->hugetlb_entry && (vma->vm_start <= addr) && - is_vm_hugetlb_page(vma)) { - if (vma->vm_end < next) - next = vma->vm_end; - /* - * Hugepage is very tightly coupled with vma, - * so walk through hugetlb entries within a - * given vma. - */ - err = walk_hugetlb_range(vma, addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); - continue; - } - } - - if (pgd_none_or_clear_bad(pgd)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); - if (err) + if (err < 0) break; - pgd++; - continue; } - if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + if (walk->vma || walk->pte_hole) + err = __walk_page_range(start, next, walk); if (err) break; - pgd++; - } while (addr = next, addr < end); - + } while (start = next, start < end); return err; } -- cgit v1.2.3 From 900fc5f197b05253ae9433fb9a066c3f37d08f69 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:40 -0800 Subject: pagewalk: add walk_page_vma() Introduce walk_page_vma(), which is useful for the callers which want to walk over a given vma. It's used by later patches. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/pagewalk.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3891a368e5e0..a4d24f3c5430 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1201,6 +1201,7 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d9cc3caae802..4c9a653ba563 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -272,3 +272,21 @@ int walk_page_range(unsigned long start, unsigned long end, } while (start = next, start < end); return err; } + +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk) +{ + int err; + + if (!walk->mm) + return -EINVAL; + + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + VM_BUG_ON(!vma); + walk->vma = vma; + err = walk_page_test(vma->vm_start, vma->vm_end, walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(vma->vm_start, vma->vm_end, walk); +} -- cgit v1.2.3 From 94f759d62b2c6a9d124b0622077b1ddcfac43fb5 Mon Sep 17 00:00:00 2001 From: Sergei Rogachev Date: Wed, 11 Feb 2015 15:28:34 -0800 Subject: mm/page_owner.c: remove unnecessary stack_trace field Page owner uses the page_ext structure to keep meta-information for every page in the system. The structure also contains a field of type 'struct stack_trace', page owner uses this field during invocation of the function save_stack_trace. It is easy to notice that keeping a copy of this structure for every page in the system is very inefficiently in terms of memory. The patch removes this unnecessary field of page_ext and forces page owner to use a stack_trace structure allocated on the stack. [akpm@linux-foundation.org: use struct initializers] Signed-off-by: Sergei Rogachev Acked-by: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 2 +- mm/page_owner.c | 26 ++++++++++++++------------ 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index d2a2c84c72d0..c42981cd99aa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -40,7 +40,7 @@ struct page_ext { #ifdef CONFIG_PAGE_OWNER unsigned int order; gfp_t gfp_mask; - struct stack_trace trace; + unsigned int nr_entries; unsigned long trace_entries[8]; #endif }; diff --git a/mm/page_owner.c b/mm/page_owner.c index 9ab4a9b5bc09..0993f5f36b01 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -59,20 +59,19 @@ void __reset_page_owner(struct page *page, unsigned int order) void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { - struct page_ext *page_ext; - struct stack_trace *trace; - - page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(page); + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = ARRAY_SIZE(page_ext->trace_entries), + .entries = &page_ext->trace_entries[0], + .skip = 3, + }; - trace = &page_ext->trace; - trace->nr_entries = 0; - trace->max_entries = ARRAY_SIZE(page_ext->trace_entries); - trace->entries = &page_ext->trace_entries[0]; - trace->skip = 3; - save_stack_trace(&page_ext->trace); + save_stack_trace(&trace); page_ext->order = order; page_ext->gfp_mask = gfp_mask; + page_ext->nr_entries = trace.nr_entries; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } @@ -84,6 +83,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, int ret; int pageblock_mt, page_mt; char *kbuf; + struct stack_trace trace = { + .nr_entries = page_ext->nr_entries, + .entries = &page_ext->trace_entries[0], + }; kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) @@ -121,8 +124,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; - ret += snprint_stack_trace(kbuf + ret, count - ret, - &page_ext->trace, 0); + ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0); if (ret >= count) goto err; -- cgit v1.2.3