From c787f1baa5031c22cbe20af17b2ee36ad32957ea Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 7 Apr 2023 15:05:34 -0500
Subject: block: Add PR callouts for read keys and reservation

Add callouts for reading keys and reservations. This allows LIO to support
the READ_KEYS and READ_RESERVATION commands so it can export devices to
VMs for software like windows clustering.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-2-michael.christie@oracle.com
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/pr.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pr.h b/include/linux/pr.h
index 94ceec713afe..3003daec28a5 100644
--- a/include/linux/pr.h
+++ b/include/linux/pr.h
@@ -4,6 +4,18 @@
 
 #include <uapi/linux/pr.h>
 
+struct pr_keys {
+	u32	generation;
+	u32	num_keys;
+	u64	keys[];
+};
+
+struct pr_held_reservation {
+	u64		key;
+	u32		generation;
+	enum pr_type	type;
+};
+
 struct pr_ops {
 	int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key,
 			u32 flags);
@@ -14,6 +26,19 @@ struct pr_ops {
 	int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key,
 			enum pr_type type, bool abort);
 	int (*pr_clear)(struct block_device *bdev, u64 key);
+	/*
+	 * pr_read_keys - Read the registered keys and return them in the
+	 * pr_keys->keys array. The keys array will have been allocated at the
+	 * end of the pr_keys struct, and pr_keys->num_keys must be set to the
+	 * number of keys the array can hold. If there are more than can fit
+	 * in the array, success will still be returned and pr_keys->num_keys
+	 * will reflect the total number of keys the device contains, so the
+	 * caller can retry with a larger array.
+	 */
+	int (*pr_read_keys)(struct block_device *bdev,
+			struct pr_keys *keys_info);
+	int (*pr_read_reservation)(struct block_device *bdev,
+			struct pr_held_reservation *rsv);
 };
 
 #endif /* LINUX_PR_H */
-- 
cgit v1.2.3


From 7ba150834b840f6f5cdd07ca69a4ccf39df59a66 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 7 Apr 2023 15:05:35 -0500
Subject: block: Rename BLK_STS_NEXUS to BLK_STS_RESV_CONFLICT

BLK_STS_NEXUS is used for NVMe/SCSI reservation conflicts and DASD's
locking feature which works similar to NVMe/SCSI reservations where a
host can get a lock on a device and when the lock is taken it will get
failures.

This patch renames BLK_STS_NEXUS so it better reflects this type of
use.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-3-michael.christie@oracle.com
Acked-by: Stefan Haberland <sth@linux.ibm.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-core.c          | 2 +-
 drivers/nvme/host/core.c  | 2 +-
 drivers/s390/block/dasd.c | 7 ++++++-
 drivers/scsi/scsi_lib.c   | 2 +-
 include/linux/blk_types.h | 4 ++--
 5 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9e5e0277a4d9..ff8fb7a49389 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -155,7 +155,7 @@ static const struct {
 	[BLK_STS_NOSPC]		= { -ENOSPC,	"critical space allocation" },
 	[BLK_STS_TRANSPORT]	= { -ENOLINK,	"recoverable transport" },
 	[BLK_STS_TARGET]	= { -EREMOTEIO,	"critical target" },
-	[BLK_STS_NEXUS]		= { -EBADE,	"critical nexus" },
+	[BLK_STS_RESV_CONFLICT]	= { -EBADE,	"reservation conflict" },
 	[BLK_STS_MEDIUM]	= { -ENODATA,	"critical medium" },
 	[BLK_STS_PROTECTION]	= { -EILSEQ,	"protection" },
 	[BLK_STS_RESOURCE]	= { -ENOMEM,	"kernel resource" },
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2730b116dc6..535a26ceb205 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -279,7 +279,7 @@ static blk_status_t nvme_error_status(u16 status)
 	case NVME_SC_INVALID_PI:
 		return BLK_STS_PROTECTION;
 	case NVME_SC_RESERVATION_CONFLICT:
-		return BLK_STS_NEXUS;
+		return BLK_STS_RESV_CONFLICT;
 	case NVME_SC_HOST_PATH_ERROR:
 		return BLK_STS_TRANSPORT;
 	case NVME_SC_ZONE_TOO_MANY_ACTIVE:
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index a9c2a8d76c45..ca0df87fa8f4 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2723,7 +2723,12 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr)
 	else if (status == 0) {
 		switch (cqr->intrc) {
 		case -EPERM:
-			error = BLK_STS_NEXUS;
+			/*
+			 * DASD doesn't implement SCSI/NVMe reservations, but it
+			 * implements a locking scheme similar to them. We
+			 * return this error when we no longer have the lock.
+			 */
+			error = BLK_STS_RESV_CONFLICT;
 			break;
 		case -ENOLINK:
 			error = BLK_STS_TRANSPORT;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b7c569a42aa4..e1468483ac7e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -599,7 +599,7 @@ static blk_status_t scsi_result_to_blk_status(int result)
 	case SCSIML_STAT_OK:
 		break;
 	case SCSIML_STAT_RESV_CONFLICT:
-		return BLK_STS_NEXUS;
+		return BLK_STS_RESV_CONFLICT;
 	case SCSIML_STAT_NOSPC:
 		return BLK_STS_NOSPC;
 	case SCSIML_STAT_MED_ERROR:
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 99be590f952f..2b2452086a2f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -96,7 +96,7 @@ typedef u16 blk_short_t;
 #define BLK_STS_NOSPC		((__force blk_status_t)3)
 #define BLK_STS_TRANSPORT	((__force blk_status_t)4)
 #define BLK_STS_TARGET		((__force blk_status_t)5)
-#define BLK_STS_NEXUS		((__force blk_status_t)6)
+#define BLK_STS_RESV_CONFLICT	((__force blk_status_t)6)
 #define BLK_STS_MEDIUM		((__force blk_status_t)7)
 #define BLK_STS_PROTECTION	((__force blk_status_t)8)
 #define BLK_STS_RESOURCE	((__force blk_status_t)9)
@@ -184,7 +184,7 @@ static inline bool blk_path_error(blk_status_t error)
 	case BLK_STS_NOTSUPP:
 	case BLK_STS_NOSPC:
 	case BLK_STS_TARGET:
-	case BLK_STS_NEXUS:
+	case BLK_STS_RESV_CONFLICT:
 	case BLK_STS_MEDIUM:
 	case BLK_STS_PROTECTION:
 		return false;
-- 
cgit v1.2.3


From f2bf2e7e2d526116aab942aaf1b71a949a570ba6 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 7 Apr 2023 15:05:40 -0500
Subject: nvme: Fix reservation status related structs

This fixes the following issues with the reservation status structs:

1. resv10 is bytes 23:10 so it should be 14 bytes.
2. regctl_ds only supports 64 bit host IDs.

These are not currently used, but will be in this patchset which adds
support for the reservation report command.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-8-michael.christie@oracle.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/nvme.h | 38 ++++++++++++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 4fad4aa245fb..57b5b2b8d95b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -759,20 +759,42 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+struct nvme_registered_ctrl {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	hostid;
+	__le64	rkey;
+};
+
 struct nvme_reservation_status {
 	__le32	gen;
 	__u8	rtype;
 	__u8	regctl[2];
 	__u8	resv5[2];
 	__u8	ptpls;
-	__u8	resv10[13];
-	struct {
-		__le16	cntlid;
-		__u8	rcsts;
-		__u8	resv3[5];
-		__le64	hostid;
-		__le64	rkey;
-	} regctl_ds[];
+	__u8	resv10[14];
+	struct nvme_registered_ctrl regctl_ds[];
+};
+
+struct nvme_registered_ctrl_ext {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	rkey;
+	__u8	hostid[16];
+	__u8	rsvd32[32];
+};
+
+struct nvme_reservation_status_ext {
+	__le32	gen;
+	__u8	rtype;
+	__u8	regctl[2];
+	__u8	resv5[2];
+	__u8	ptpls;
+	__u8	resv10[14];
+	__u8	rsvd24[40];
+	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
 enum nvme_async_event_type {
-- 
cgit v1.2.3


From 5fd96a4e15de8442915a912233d800c56f49001d Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 7 Apr 2023 15:05:44 -0500
Subject: nvme: Add pr_ops read_keys support

This patch adds support for the pr_ops read_keys callout by calling the
NVMe Reservation Report helper, then parsing that info to get the
controller's registered keys. Because the callout is only used in the
kernel where the callers, like LIO, do not know about controller/host IDs,
the callout just returns the registered keys which is required by the SCSI
PR in READ KEYS command.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-12-michael.christie@oracle.com
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/nvme/host/pr.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme.h   |  4 +++
 2 files changed, 73 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index cd93d2e5b340..0ee656404437 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -154,10 +154,79 @@ static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
+static int nvme_pr_resv_report(struct block_device *bdev, void *data,
+		u32 data_len, bool *eds)
+{
+	struct nvme_command c = { };
+	int ret;
+
+	c.common.opcode = nvme_cmd_resv_report;
+	c.common.cdw10 = cpu_to_le32(nvme_bytes_to_numd(data_len));
+	c.common.cdw11 = cpu_to_le32(NVME_EXTENDED_DATA_STRUCT);
+	*eds = true;
+
+retry:
+	ret = nvme_send_pr_command(bdev, &c, data, data_len);
+	if (ret == NVME_SC_HOST_ID_INCONSIST &&
+	    c.common.cdw11 == cpu_to_le32(NVME_EXTENDED_DATA_STRUCT)) {
+		c.common.cdw11 = 0;
+		*eds = false;
+		goto retry;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	return nvme_sc_to_pr_err(ret);
+}
+
+static int nvme_pr_read_keys(struct block_device *bdev,
+		struct pr_keys *keys_info)
+{
+	u32 rse_len, num_keys = keys_info->num_keys;
+	struct nvme_reservation_status_ext *rse;
+	int ret, i;
+	bool eds;
+
+	/*
+	 * Assume we are using 128-bit host IDs and allocate a buffer large
+	 * enough to get enough keys to fill the return keys buffer.
+	 */
+	rse_len = struct_size(rse, regctl_eds, num_keys);
+	rse = kzalloc(rse_len, GFP_KERNEL);
+	if (!rse)
+		return -ENOMEM;
+
+	ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds);
+	if (ret)
+		goto free_rse;
+
+	keys_info->generation = le32_to_cpu(rse->gen);
+	keys_info->num_keys = get_unaligned_le16(&rse->regctl);
+
+	num_keys = min(num_keys, keys_info->num_keys);
+	for (i = 0; i < num_keys; i++) {
+		if (eds) {
+			keys_info->keys[i] =
+					le64_to_cpu(rse->regctl_eds[i].rkey);
+		} else {
+			struct nvme_reservation_status *rs;
+
+			rs = (struct nvme_reservation_status *)rse;
+			keys_info->keys[i] = le64_to_cpu(rs->regctl_ds[i].rkey);
+		}
+	}
+
+free_rse:
+	kfree(rse);
+	return ret;
+}
+
 const struct pr_ops nvme_pr_ops = {
 	.pr_register	= nvme_pr_register,
 	.pr_reserve	= nvme_pr_reserve,
 	.pr_release	= nvme_pr_release,
 	.pr_preempt	= nvme_pr_preempt,
 	.pr_clear	= nvme_pr_clear,
+	.pr_read_keys	= nvme_pr_read_keys,
 };
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 57b5b2b8d95b..a617e250d629 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -759,6 +759,10 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+enum nvme_eds {
+	NVME_EXTENDED_DATA_STRUCT	= 0x1,
+};
+
 struct nvme_registered_ctrl {
 	__le16	cntlid;
 	__u8	rcsts;
-- 
cgit v1.2.3


From be1a7cd2d0ed028ffdd60c65e3734e2a1d8b17df Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 7 Apr 2023 15:05:45 -0500
Subject: nvme: Add a nvme_pr_type enum

The next patch adds support to report the reservation type, so we need to
be able to convert from the NVMe PR value we get from the device to the
linux block layer PR value that will be returned to callers. To prepare
for that, this patch adds a nvme_pr_type enum and renames the nvme_pr_type
function.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-13-michael.christie@oracle.com
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/nvme/host/pr.c | 24 ++++++++++++------------
 include/linux/nvme.h   |  9 +++++++++
 2 files changed, 21 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 0ee656404437..732c56b417c2 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -9,24 +9,24 @@
 
 #include "nvme.h"
 
-static char nvme_pr_type(enum pr_type type)
+static enum nvme_pr_type nvme_pr_type_from_blk(enum pr_type type)
 {
 	switch (type) {
 	case PR_WRITE_EXCLUSIVE:
-		return 1;
+		return NVME_PR_WRITE_EXCLUSIVE;
 	case PR_EXCLUSIVE_ACCESS:
-		return 2;
+		return NVME_PR_EXCLUSIVE_ACCESS;
 	case PR_WRITE_EXCLUSIVE_REG_ONLY:
-		return 3;
+		return NVME_PR_WRITE_EXCLUSIVE_REG_ONLY;
 	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
-		return 4;
+		return NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY;
 	case PR_WRITE_EXCLUSIVE_ALL_REGS:
-		return 5;
+		return NVME_PR_WRITE_EXCLUSIVE_ALL_REGS;
 	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
-		return 6;
-	default:
-		return 0;
+		return NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS;
 	}
+
+	return 0;
 }
 
 static int nvme_send_ns_head_pr_command(struct block_device *bdev,
@@ -127,7 +127,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key,
 	if (flags & ~PR_FL_IGNORE_KEY)
 		return -EOPNOTSUPP;
 
-	cdw10 = nvme_pr_type(type) << 8;
+	cdw10 = nvme_pr_type_from_blk(type) << 8;
 	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
 }
@@ -135,7 +135,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key,
 static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
 		enum pr_type type, bool abort)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
+	u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (abort ? 2 : 1);
 
 	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
 }
@@ -149,7 +149,7 @@ static int nvme_pr_clear(struct block_device *bdev, u64 key)
 
 static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3);
+	u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (key ? 0 : 1 << 3);
 
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index a617e250d629..4013abb86642 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -759,6 +759,15 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+enum nvme_pr_type {
+	NVME_PR_WRITE_EXCLUSIVE			= 1,
+	NVME_PR_EXCLUSIVE_ACCESS		= 2,
+	NVME_PR_WRITE_EXCLUSIVE_REG_ONLY	= 3,
+	NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY	= 4,
+	NVME_PR_WRITE_EXCLUSIVE_ALL_REGS	= 5,
+	NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS	= 6,
+};
+
 enum nvme_eds {
 	NVME_EXTENDED_DATA_STRUCT	= 0x1,
 };
-- 
cgit v1.2.3


From dffc480d2df1772d6092f46f2b4c5e0de941bd47 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 11 May 2023 03:13:36 +0200
Subject: scsi: block: Introduce BLK_STS_DURATION_LIMIT

Introduce the new block I/O status BLK_STS_DURATION_LIMIT for LLDDs to
report command that failed due to a command duration limit being
exceeded. This new status is mapped to the ETIME error code to allow users
to differentiate "soft" duration limit failures from other more serious
hardware related errors.

If we compare BLK_STS_DURATION_LIMIT with BLK_STS_TIMEOUT:
-BLK_STS_DURATION_LIMIT means that the drive gave a reply indicating that
the command duration limit was exceeded before the command could be
completed. This I/O status is mapped to ETIME for user space.

-BLK_STS_TIMEOUT means that the drive never gave a reply at all.
This I/O status is mapped to ETIMEDOUT for user space.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Co-developed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20230511011356.227789-4-nks@flawful.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-core.c          | 3 +++
 include/linux/blk_types.h | 6 ++++++
 2 files changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 00c74330fa92..04ad13ec6ead 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -170,6 +170,9 @@ static const struct {
 	[BLK_STS_ZONE_OPEN_RESOURCE]	= { -ETOOMANYREFS, "open zones exceeded" },
 	[BLK_STS_ZONE_ACTIVE_RESOURCE]	= { -EOVERFLOW, "active zones exceeded" },
 
+	/* Command duration limit device-side timeout */
+	[BLK_STS_DURATION_LIMIT]	= { -ETIME, "duration limit exceeded" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 740afe80f297..dfdcd218aaac 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -171,6 +171,12 @@ typedef u16 blk_short_t;
  */
 #define BLK_STS_OFFLINE		((__force blk_status_t)17)
 
+/*
+ * BLK_STS_DURATION_LIMIT is returned from the driver when the target device
+ * aborted the command because it exceeded one of its Command Duration Limits.
+ */
+#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)18)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
-- 
cgit v1.2.3


From 62e4a60e0cdb540b314061469e025fd834ff300c Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 11 May 2023 03:13:47 +0200
Subject: scsi: ata: libata: Detect support for command duration limits

Use the supported capabilities identify device data log page to detect if a
device supports the command duration limits feature. For devices supporting
this feature, set the device flag ATA_DFLAG_CDL. To support SCSI-ATA
translation, retrieve the command duration limits log page 18h and cache
this page content using the cdl array added to the ata_device data
structure.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Co-developed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20230511011356.227789-15-nks@flawful.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-core.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/ata/libata-scsi.c | 17 ++++++++--------
 include/linux/ata.h       |  5 ++++-
 include/linux/libata.h    | 29 +++++++++++++++-----------
 4 files changed, 80 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8bf612bdd61a..83fe037f63b9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2367,6 +2367,54 @@ static void ata_dev_config_trusted(struct ata_device *dev)
 		dev->flags |= ATA_DFLAG_TRUSTED;
 }
 
+static void ata_dev_config_cdl(struct ata_device *dev)
+{
+	struct ata_port *ap = dev->link->ap;
+	unsigned int err_mask;
+	u64 val;
+
+	if (ata_id_major_version(dev->id) < 12)
+		goto not_supported;
+
+	if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) ||
+	    !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES))
+		goto not_supported;
+
+	err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE,
+				     ATA_LOG_SUPPORTED_CAPABILITIES,
+				     ap->sector_buf, 1);
+	if (err_mask)
+		goto not_supported;
+
+	/* Check Command Duration Limit Supported bits */
+	val = get_unaligned_le64(&ap->sector_buf[168]);
+	if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(0)))
+		goto not_supported;
+
+	/* Warn the user if command duration guideline is not supported */
+	if (!(val & BIT_ULL(1)))
+		ata_dev_warn(dev,
+			"Command duration guideline is not supported\n");
+
+	/*
+	 * Command duration limits is supported: cache the CDL log page 18h
+	 * (command duration descriptors).
+	 */
+	err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, ap->sector_buf, 1);
+	if (err_mask) {
+		ata_dev_warn(dev, "Read Command Duration Limits log failed\n");
+		goto not_supported;
+	}
+
+	memcpy(dev->cdl, ap->sector_buf, ATA_LOG_CDL_SIZE);
+	dev->flags |= ATA_DFLAG_CDL;
+
+	return;
+
+not_supported:
+	dev->flags &= ~ATA_DFLAG_CDL;
+}
+
 static int ata_dev_config_lba(struct ata_device *dev)
 {
 	const u16 *id = dev->id;
@@ -2534,13 +2582,14 @@ static void ata_dev_print_features(struct ata_device *dev)
 		return;
 
 	ata_dev_info(dev,
-		     "Features:%s%s%s%s%s%s%s\n",
+		     "Features:%s%s%s%s%s%s%s%s\n",
 		     dev->flags & ATA_DFLAG_FUA ? " FUA" : "",
 		     dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "",
 		     dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "",
 		     dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "",
 		     dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "",
 		     dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "",
+		     dev->flags & ATA_DFLAG_CDL ? " CDL" : "",
 		     dev->cpr_log ? " CPR" : "");
 }
 
@@ -2702,6 +2751,7 @@ int ata_dev_configure(struct ata_device *dev)
 		ata_dev_config_zac(dev);
 		ata_dev_config_trusted(dev);
 		ata_dev_config_cpr(dev);
+		ata_dev_config_cdl(dev);
 		dev->cdb_len = 32;
 
 		if (print_info)
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 072785808751..3434fec8ca5c 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -47,15 +47,14 @@ typedef unsigned int (*ata_xlat_func_t)(struct ata_queued_cmd *qc);
 static struct ata_device *__ata_scsi_find_dev(struct ata_port *ap,
 					const struct scsi_device *scsidev);
 
-#define RW_RECOVERY_MPAGE 0x1
-#define RW_RECOVERY_MPAGE_LEN 12
-#define CACHE_MPAGE 0x8
-#define CACHE_MPAGE_LEN 20
-#define CONTROL_MPAGE 0xa
-#define CONTROL_MPAGE_LEN 12
-#define ALL_MPAGES 0x3f
-#define ALL_SUB_MPAGES 0xff
-
+#define RW_RECOVERY_MPAGE		0x1
+#define RW_RECOVERY_MPAGE_LEN		12
+#define CACHE_MPAGE			0x8
+#define CACHE_MPAGE_LEN			20
+#define CONTROL_MPAGE			0xa
+#define CONTROL_MPAGE_LEN		12
+#define ALL_MPAGES			0x3f
+#define ALL_SUB_MPAGES			0xff
 
 static const u8 def_rw_recovery_mpage[RW_RECOVERY_MPAGE_LEN] = {
 	RW_RECOVERY_MPAGE,
diff --git a/include/linux/ata.h b/include/linux/ata.h
index c224dbddb9b2..1eda46b63dcc 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -322,15 +322,18 @@ enum {
 	ATA_LOG_SATA_NCQ	= 0x10,
 	ATA_LOG_NCQ_NON_DATA	= 0x12,
 	ATA_LOG_NCQ_SEND_RECV	= 0x13,
+	ATA_LOG_CDL		= 0x18,
+	ATA_LOG_CDL_SIZE	= ATA_SECT_SIZE,
 	ATA_LOG_IDENTIFY_DEVICE	= 0x30,
 	ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47,
 
 	/* Identify device log pages: */
+	ATA_LOG_SUPPORTED_CAPABILITIES	= 0x03,
 	ATA_LOG_SECURITY	  = 0x06,
 	ATA_LOG_SATA_SETTINGS	  = 0x08,
 	ATA_LOG_ZONED_INFORMATION = 0x09,
 
-	/* Identify device SATA settings log:*/
+	/* Identify device SATA settings log: */
 	ATA_LOG_DEVSLP_OFFSET	  = 0x30,
 	ATA_LOG_DEVSLP_SIZE	  = 0x08,
 	ATA_LOG_DEVSLP_MDAT	  = 0x00,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 311cd93377c7..e8a45f7f3f5c 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -94,17 +94,18 @@ enum {
 	ATA_DFLAG_DMADIR	= (1 << 10), /* device requires DMADIR */
 	ATA_DFLAG_NCQ_SEND_RECV = (1 << 11), /* device supports NCQ SEND and RECV */
 	ATA_DFLAG_NCQ_PRIO	= (1 << 12), /* device supports NCQ priority */
-	ATA_DFLAG_CFG_MASK	= (1 << 13) - 1,
-
-	ATA_DFLAG_PIO		= (1 << 13), /* device limited to PIO mode */
-	ATA_DFLAG_NCQ_OFF	= (1 << 14), /* device limited to non-NCQ mode */
-	ATA_DFLAG_SLEEPING	= (1 << 15), /* device is sleeping */
-	ATA_DFLAG_DUBIOUS_XFER	= (1 << 16), /* data transfer not verified */
-	ATA_DFLAG_NO_UNLOAD	= (1 << 17), /* device doesn't support unload */
-	ATA_DFLAG_UNLOCK_HPA	= (1 << 18), /* unlock HPA */
-	ATA_DFLAG_INIT_MASK	= (1 << 19) - 1,
-
-	ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 19), /* Priority cmds sent to dev */
+	ATA_DFLAG_CDL		= (1 << 13), /* supports cmd duration limits */
+	ATA_DFLAG_CFG_MASK	= (1 << 14) - 1,
+
+	ATA_DFLAG_PIO		= (1 << 14), /* device limited to PIO mode */
+	ATA_DFLAG_NCQ_OFF	= (1 << 15), /* device limited to non-NCQ mode */
+	ATA_DFLAG_SLEEPING	= (1 << 16), /* device is sleeping */
+	ATA_DFLAG_DUBIOUS_XFER	= (1 << 17), /* data transfer not verified */
+	ATA_DFLAG_NO_UNLOAD	= (1 << 18), /* device doesn't support unload */
+	ATA_DFLAG_UNLOCK_HPA	= (1 << 19), /* unlock HPA */
+	ATA_DFLAG_INIT_MASK	= (1 << 20) - 1,
+
+	ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */
 	ATA_DFLAG_DETACH	= (1 << 24),
 	ATA_DFLAG_DETACHED	= (1 << 25),
 	ATA_DFLAG_DA		= (1 << 26), /* device supports Device Attention */
@@ -115,7 +116,8 @@ enum {
 
 	ATA_DFLAG_FEATURES_MASK	= (ATA_DFLAG_TRUSTED | ATA_DFLAG_DA |	\
 				   ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \
-				   ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA),
+				   ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA | \
+				   ATA_DFLAG_CDL),
 
 	ATA_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */
@@ -709,6 +711,9 @@ struct ata_device {
 	/* Concurrent positioning ranges */
 	struct ata_cpr_log	*cpr_log;
 
+	/* Command Duration Limits log support */
+	u8			cdl[ATA_LOG_CDL_SIZE];
+
 	/* error history */
 	int			spdn_cnt;
 	/* ering is CLEAR_END, read comment above CLEAR_END */
-- 
cgit v1.2.3


From df60f9c64576d6d05b59ec5c34addcd61ef1efb0 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 11 May 2023 03:13:50 +0200
Subject: scsi: ata: libata: Add ATA feature control sub-page translation

Add support for the ATA feature control sub-page of the control mode page
to enable/disable the command duration limits feature using the cdl_ctrl
field of the ATA feature control sub-page.

Both mode sense and mode select translation are supported. For mode sense,
the ata device flag ATA_DFLAG_CDL_ENABLED is used to cache the status of
the command duration limits feature. Enabling this feature is done using a
SET FEATURES command with a cdl action set to 1 when the page cdl_ctrl
field value is 0x2 (T2A and T2B pages supported). If this field is 0, CDL
is disabled using the SET FEATURES command with a cdl action set to 0.

Since a device CDL and NCQ priority features should not be used
simultaneously, ata_mselect_control_ata_feature() returns an error when
attempting to enable CDL with the device priority feature enabled.
Conversely, the function ata_ncq_prio_enable_store() used to enable the use
of the device NCQ priority feature through sysfs is modified to return an
error if the device CDL feature is enabled.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Co-developed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20230511011356.227789-18-nks@flawful.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-core.c |  40 ++++++++++-
 drivers/ata/libata-sata.c |  11 ++-
 drivers/ata/libata-scsi.c | 167 +++++++++++++++++++++++++++++++++++++++-------
 include/linux/ata.h       |   3 +
 include/linux/libata.h    |   1 +
 5 files changed, 193 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 83fe037f63b9..cd7aaf202397 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2371,13 +2371,15 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 {
 	struct ata_port *ap = dev->link->ap;
 	unsigned int err_mask;
+	bool cdl_enabled;
 	u64 val;
 
 	if (ata_id_major_version(dev->id) < 12)
 		goto not_supported;
 
 	if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) ||
-	    !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES))
+	    !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES) ||
+	    !ata_identify_page_supported(dev, ATA_LOG_CURRENT_SETTINGS))
 		goto not_supported;
 
 	err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE,
@@ -2396,6 +2398,40 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 		ata_dev_warn(dev,
 			"Command duration guideline is not supported\n");
 
+	/*
+	 * If CDL is marked as enabled, make sure the feature is enabled too.
+	 * Conversely, if CDL is disabled, make sure the feature is turned off.
+	 */
+	err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE,
+				     ATA_LOG_CURRENT_SETTINGS,
+				     ap->sector_buf, 1);
+	if (err_mask)
+		goto not_supported;
+
+	val = get_unaligned_le64(&ap->sector_buf[8]);
+	cdl_enabled = val & BIT_ULL(63) && val & BIT_ULL(21);
+	if (dev->flags & ATA_DFLAG_CDL_ENABLED) {
+		if (!cdl_enabled) {
+			/* Enable CDL on the device */
+			err_mask = ata_dev_set_feature(dev, SETFEATURES_CDL, 1);
+			if (err_mask) {
+				ata_dev_err(dev,
+					    "Enable CDL feature failed\n");
+				goto not_supported;
+			}
+		}
+	} else {
+		if (cdl_enabled) {
+			/* Disable CDL on the device */
+			err_mask = ata_dev_set_feature(dev, SETFEATURES_CDL, 0);
+			if (err_mask) {
+				ata_dev_err(dev,
+					    "Disable CDL feature failed\n");
+				goto not_supported;
+			}
+		}
+	}
+
 	/*
 	 * Command duration limits is supported: cache the CDL log page 18h
 	 * (command duration descriptors).
@@ -2412,7 +2448,7 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 	return;
 
 not_supported:
-	dev->flags &= ~ATA_DFLAG_CDL;
+	dev->flags &= ~(ATA_DFLAG_CDL | ATA_DFLAG_CDL_ENABLED);
 }
 
 static int ata_dev_config_lba(struct ata_device *dev)
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index f3e7396e3191..57cb33060c9d 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -907,10 +907,17 @@ static ssize_t ata_ncq_prio_enable_store(struct device *device,
 		goto unlock;
 	}
 
-	if (input)
+	if (input) {
+		if (dev->flags & ATA_DFLAG_CDL_ENABLED) {
+			ata_dev_err(dev,
+				"CDL must be disabled to enable NCQ priority\n");
+			rc = -EINVAL;
+			goto unlock;
+		}
 		dev->flags |= ATA_DFLAG_NCQ_PRIO_ENABLED;
-	else
+	} else {
 		dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLED;
+	}
 
 unlock:
 	spin_unlock_irq(ap->lock);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 4a4c6405d52e..91db4e7f4906 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -58,6 +58,8 @@ static struct ata_device *__ata_scsi_find_dev(struct ata_port *ap,
 #define CDL_T2A_SUB_MPAGE		0x07
 #define CDL_T2B_SUB_MPAGE		0x08
 #define CDL_T2_SUB_MPAGE_LEN		232
+#define ATA_FEATURE_SUB_MPAGE		0xf2
+#define ATA_FEATURE_SUB_MPAGE_LEN	16
 
 static const u8 def_rw_recovery_mpage[RW_RECOVERY_MPAGE_LEN] = {
 	RW_RECOVERY_MPAGE,
@@ -2286,6 +2288,31 @@ static unsigned int ata_msense_control_spgt2(struct ata_device *dev, u8 *buf,
 	return CDL_T2_SUB_MPAGE_LEN;
 }
 
+/*
+ * Simulate MODE SENSE control mode page, sub-page f2h
+ * (ATA feature control mode page).
+ */
+static unsigned int ata_msense_control_ata_feature(struct ata_device *dev,
+						   u8 *buf)
+{
+	/* PS=0, SPF=1 */
+	buf[0] = CONTROL_MPAGE | (1 << 6);
+	buf[1] = ATA_FEATURE_SUB_MPAGE;
+
+	/*
+	 * The first four bytes of ATA Feature Control mode page are a header.
+	 * The PAGE LENGTH field is the size of the page excluding the header.
+	 */
+	put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
+
+	if (dev->flags & ATA_DFLAG_CDL)
+		buf[4] = 0x02; /* Support T2A and T2B pages */
+	else
+		buf[4] = 0;
+
+	return ATA_FEATURE_SUB_MPAGE_LEN;
+}
+
 /**
  *	ata_msense_control - Simulate MODE SENSE control mode page
  *	@dev: ATA device of interest
@@ -2309,10 +2336,13 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf,
 	case CDL_T2A_SUB_MPAGE:
 	case CDL_T2B_SUB_MPAGE:
 		return ata_msense_control_spgt2(dev, buf, spg);
+	case ATA_FEATURE_SUB_MPAGE:
+		return ata_msense_control_ata_feature(dev, buf);
 	case ALL_SUB_MPAGES:
 		n = ata_msense_control_spg0(dev, buf, changeable);
 		n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
 		n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
+		n += ata_msense_control_ata_feature(dev, buf + n);
 		return n;
 	default:
 		return 0;
@@ -2391,7 +2421,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf)
 	spg = scsicmd[3];
 
 	/*
-	 * Supported subpages: all subpages and sub-pages 07h and 08h of
+	 * Supported subpages: all subpages and sub-pages 07h, 08h and f2h of
 	 * the control page.
 	 */
 	if (spg) {
@@ -2400,6 +2430,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf)
 			break;
 		case CDL_T2A_SUB_MPAGE:
 		case CDL_T2B_SUB_MPAGE:
+		case ATA_FEATURE_SUB_MPAGE:
 			if (dev->flags & ATA_DFLAG_CDL && pg == CONTROL_MPAGE)
 				break;
 			fallthrough;
@@ -3708,20 +3739,11 @@ static int ata_mselect_caching(struct ata_queued_cmd *qc,
 	return 0;
 }
 
-/**
- *	ata_mselect_control - Simulate MODE SELECT for control page
- *	@qc: Storage for translated ATA taskfile
- *	@buf: input buffer
- *	@len: number of valid bytes in the input buffer
- *	@fp: out parameter for the failed field on error
- *
- *	Prepare a taskfile to modify caching information for the device.
- *
- *	LOCKING:
- *	None.
+/*
+ * Simulate MODE SELECT control mode page, sub-page 0.
  */
-static int ata_mselect_control(struct ata_queued_cmd *qc,
-			       const u8 *buf, int len, u16 *fp)
+static int ata_mselect_control_spg0(struct ata_queued_cmd *qc,
+				    const u8 *buf, int len, u16 *fp)
 {
 	struct ata_device *dev = qc->dev;
 	u8 mpage[CONTROL_MPAGE_LEN];
@@ -3759,6 +3781,83 @@ static int ata_mselect_control(struct ata_queued_cmd *qc,
 	return 0;
 }
 
+/*
+ * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * page) into a SET FEATURES command.
+ */
+static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+						    const u8 *buf, int len,
+						    u16 *fp)
+{
+	struct ata_device *dev = qc->dev;
+	struct ata_taskfile *tf = &qc->tf;
+	u8 cdl_action;
+
+	/*
+	 * The first four bytes of ATA Feature Control mode page are a header,
+	 * so offsets in mpage are off by 4 compared to buf.  Same for len.
+	 */
+	if (len != ATA_FEATURE_SUB_MPAGE_LEN - 4) {
+		*fp = min(len, ATA_FEATURE_SUB_MPAGE_LEN - 4);
+		return -EINVAL;
+	}
+
+	/* Check cdl_ctrl */
+	switch (buf[0] & 0x03) {
+	case 0:
+		/* Disable CDL */
+		cdl_action = 0;
+		dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
+		break;
+	case 0x02:
+		/* Enable CDL T2A/T2B: NCQ priority must be disabled */
+		if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
+			ata_dev_err(dev,
+				"NCQ priority must be disabled to enable CDL\n");
+			return -EINVAL;
+		}
+		cdl_action = 1;
+		dev->flags |= ATA_DFLAG_CDL_ENABLED;
+		break;
+	default:
+		*fp = 0;
+		return -EINVAL;
+	}
+
+	tf->flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+	tf->protocol = ATA_PROT_NODATA;
+	tf->command = ATA_CMD_SET_FEATURES;
+	tf->feature = SETFEATURES_CDL;
+	tf->nsect = cdl_action;
+
+	return 1;
+}
+
+/**
+ *	ata_mselect_control - Simulate MODE SELECT for control page
+ *	@qc: Storage for translated ATA taskfile
+ *	@buf: input buffer
+ *	@len: number of valid bytes in the input buffer
+ *	@fp: out parameter for the failed field on error
+ *
+ *	Prepare a taskfile to modify caching information for the device.
+ *
+ *	LOCKING:
+ *	None.
+ */
+static int ata_mselect_control(struct ata_queued_cmd *qc, u8 spg,
+			       const u8 *buf, int len, u16 *fp)
+{
+	switch (spg) {
+	case 0:
+		return ata_mselect_control_spg0(qc, buf, len, fp);
+	case ATA_FEATURE_SUB_MPAGE:
+		return ata_mselect_control_ata_feature(qc, buf, len, fp);
+	default:
+		return -EINVAL;
+	}
+}
+
 /**
  *	ata_scsi_mode_select_xlat - Simulate MODE SELECT 6, 10 commands
  *	@qc: Storage for translated ATA taskfile
@@ -3776,7 +3875,7 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 	const u8 *cdb = scmd->cmnd;
 	u8 pg, spg;
 	unsigned six_byte, pg_len, hdr_len, bd_len;
-	int len;
+	int len, ret;
 	u16 fp = (u16)-1;
 	u8 bp = 0xff;
 	u8 buffer[64];
@@ -3861,13 +3960,29 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 	}
 
 	/*
-	 * No mode subpages supported (yet) but asking for _all_
-	 * subpages may be valid
+	 * Supported subpages: all subpages and ATA feature sub-page f2h of
+	 * the control page.
 	 */
-	if (spg && (spg != ALL_SUB_MPAGES)) {
-		fp = (p[0] & 0x40) ? 1 : 0;
-		fp += hdr_len + bd_len;
-		goto invalid_param;
+	if (spg) {
+		switch (spg) {
+		case ALL_SUB_MPAGES:
+			/* All subpages is not supported for the control page */
+			if (pg == CONTROL_MPAGE) {
+				fp = (p[0] & 0x40) ? 1 : 0;
+				fp += hdr_len + bd_len;
+				goto invalid_param;
+			}
+			break;
+		case ATA_FEATURE_SUB_MPAGE:
+			if (qc->dev->flags & ATA_DFLAG_CDL &&
+			    pg == CONTROL_MPAGE)
+				break;
+			fallthrough;
+		default:
+			fp = (p[0] & 0x40) ? 1 : 0;
+			fp += hdr_len + bd_len;
+			goto invalid_param;
+		}
 	}
 	if (pg_len > len)
 		goto invalid_param_len;
@@ -3880,14 +3995,16 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 		}
 		break;
 	case CONTROL_MPAGE:
-		if (ata_mselect_control(qc, p, pg_len, &fp) < 0) {
+		ret = ata_mselect_control(qc, spg, p, pg_len, &fp);
+		if (ret < 0) {
 			fp += hdr_len + bd_len;
 			goto invalid_param;
-		} else {
-			goto skip; /* No ATA command to send */
 		}
+		if (!ret)
+			goto skip; /* No ATA command to send */
 		break;
-	default:		/* invalid page code */
+	default:
+		/* Invalid page code */
 		fp = bd_len + hdr_len;
 		goto invalid_param;
 	}
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 1eda46b63dcc..21108471c6af 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -329,6 +329,7 @@ enum {
 
 	/* Identify device log pages: */
 	ATA_LOG_SUPPORTED_CAPABILITIES	= 0x03,
+	ATA_LOG_CURRENT_SETTINGS  = 0x04,
 	ATA_LOG_SECURITY	  = 0x06,
 	ATA_LOG_SATA_SETTINGS	  = 0x08,
 	ATA_LOG_ZONED_INFORMATION = 0x09,
@@ -418,6 +419,8 @@ enum {
 	SETFEATURES_SATA_ENABLE = 0x10, /* Enable use of SATA feature */
 	SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */
 
+	SETFEATURES_CDL		= 0x0d, /* Enable/disable cmd duration limits */
+
 	/* SETFEATURE Sector counts for SATA features */
 	SATA_FPDMA_OFFSET	= 0x01,	/* FPDMA non-zero buffer offsets */
 	SATA_FPDMA_AA		= 0x02, /* FPDMA Setup FIS Auto-Activate */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e8a45f7f3f5c..385ca23d5ad0 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -106,6 +106,7 @@ enum {
 	ATA_DFLAG_INIT_MASK	= (1 << 20) - 1,
 
 	ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */
+	ATA_DFLAG_CDL_ENABLED	= (1 << 21), /* cmd duration limits is enabled */
 	ATA_DFLAG_DETACH	= (1 << 24),
 	ATA_DFLAG_DETACHED	= (1 << 25),
 	ATA_DFLAG_DA		= (1 << 26), /* device supports Device Attention */
-- 
cgit v1.2.3


From eafe804bda7ba01da562c43351068b8a76a579af Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 11 May 2023 03:13:51 +0200
Subject: scsi: ata: libata: Set read/write commands CDL index

For devices supporting the command duration limits feature, translate the
dld field of read and write operation to set the command duration limit
index field of the command task file when the duration limit feature is
enabled.

The function ata_set_tf_cdl() is introduced to do this. For unqueued (non
NCQ) read and write operations, this function sets the command duration
limit index set as the lower 3 bits of the feature field.  For queued NCQ
read/write commands, the index is set as the lower 3 bits of the auxiliary
field.

The flag ATA_QCFLAG_HAS_CDL is introduced to indicate that a command
taskfile has a non zero cdl field.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Co-developed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20230511011356.227789-19-nks@flawful.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-core.c | 32 +++++++++++++++++++++++++++++---
 drivers/ata/libata-scsi.c | 16 +++++++++++++++-
 drivers/ata/libata.h      |  2 +-
 include/linux/libata.h    |  1 +
 4 files changed, 46 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index cd7aaf202397..e63773740fc2 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -665,12 +665,29 @@ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev)
 	return block;
 }
 
+/*
+ * Set a taskfile command duration limit index.
+ */
+static inline void ata_set_tf_cdl(struct ata_queued_cmd *qc, int cdl)
+{
+	struct ata_taskfile *tf = &qc->tf;
+
+	if (tf->protocol == ATA_PROT_NCQ)
+		tf->auxiliary |= cdl;
+	else
+		tf->feature |= cdl;
+
+	/* Mark this command as having a CDL */
+	qc->flags |= ATA_QCFLAG_HAS_CDL;
+}
+
 /**
  *	ata_build_rw_tf - Build ATA taskfile for given read/write request
  *	@qc: Metadata associated with the taskfile to build
  *	@block: Block address
  *	@n_block: Number of blocks
  *	@tf_flags: RW/FUA etc...
+ *	@cdl: Command duration limit index
  *	@class: IO priority class
  *
  *	LOCKING:
@@ -685,7 +702,7 @@ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev)
  *	-EINVAL if the request is invalid.
  */
 int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block,
-		    unsigned int tf_flags, int class)
+		    unsigned int tf_flags, int cdl, int class)
 {
 	struct ata_taskfile *tf = &qc->tf;
 	struct ata_device *dev = qc->dev;
@@ -724,11 +741,20 @@ int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block,
 		if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED &&
 		    class == IOPRIO_CLASS_RT)
 			tf->hob_nsect |= ATA_PRIO_HIGH << ATA_SHIFT_PRIO;
+
+		if ((dev->flags & ATA_DFLAG_CDL_ENABLED) && cdl)
+			ata_set_tf_cdl(qc, cdl);
+
 	} else if (dev->flags & ATA_DFLAG_LBA) {
 		tf->flags |= ATA_TFLAG_LBA;
 
-		/* We need LBA48 for FUA writes */
-		if (!(tf->flags & ATA_TFLAG_FUA) && lba_28_ok(block, n_block)) {
+		if ((dev->flags & ATA_DFLAG_CDL_ENABLED) && cdl)
+			ata_set_tf_cdl(qc, cdl);
+
+		/* Both FUA writes and a CDL index require 48-bit commands */
+		if (!(tf->flags & ATA_TFLAG_FUA) &&
+		    !(qc->flags & ATA_QCFLAG_HAS_CDL) &&
+		    lba_28_ok(block, n_block)) {
 			/* use LBA28 */
 			tf->device |= (block >> 24) & 0xf;
 		} else if (lba_48_ok(block, n_block)) {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 91db4e7f4906..69fc0d2c2123 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1380,6 +1380,18 @@ static inline void scsi_16_lba_len(const u8 *cdb, u64 *plba, u32 *plen)
 	*plen = get_unaligned_be32(&cdb[10]);
 }
 
+/**
+ *	scsi_dld - Get duration limit descriptor index
+ *	@cdb: SCSI command to translate
+ *
+ *	Returns the dld bits indicating the index of a command duration limit
+ *	descriptor.
+ */
+static inline int scsi_dld(const u8 *cdb)
+{
+	return ((cdb[1] & 0x01) << 2) | ((cdb[14] >> 6) & 0x03);
+}
+
 /**
  *	ata_scsi_verify_xlat - Translate SCSI VERIFY command into an ATA one
  *	@qc: Storage for translated ATA taskfile
@@ -1548,6 +1560,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc)
 	struct request *rq = scsi_cmd_to_rq(scmd);
 	int class = IOPRIO_PRIO_CLASS(req_get_ioprio(rq));
 	unsigned int tf_flags = 0;
+	int dld = 0;
 	u64 block;
 	u32 n_block;
 	int rc;
@@ -1598,6 +1611,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc)
 			goto invalid_fld;
 		}
 		scsi_16_lba_len(cdb, &block, &n_block);
+		dld = scsi_dld(cdb);
 		if (cdb[1] & (1 << 3))
 			tf_flags |= ATA_TFLAG_FUA;
 		if (!ata_check_nblocks(scmd, n_block))
@@ -1622,7 +1636,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc)
 	qc->flags |= ATA_QCFLAG_IO;
 	qc->nbytes = n_block * scmd->device->sector_size;
 
-	rc = ata_build_rw_tf(qc, block, n_block, tf_flags, class);
+	rc = ata_build_rw_tf(qc, block, n_block, tf_flags, dld, class);
 	if (likely(rc == 0))
 		return 0;
 
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 926d0d33cd29..cf993885d2b2 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -45,7 +45,7 @@ static inline void ata_force_cbl(struct ata_port *ap) { }
 extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
 extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
 extern int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block,
-			   unsigned int tf_flags, int class);
+			   unsigned int tf_flags, int dld, int class);
 extern u64 ata_tf_read_block(const struct ata_taskfile *tf,
 			     struct ata_device *dev);
 extern unsigned ata_exec_internal(struct ata_device *dev,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 385ca23d5ad0..f679abd2e61f 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -209,6 +209,7 @@ enum {
 	ATA_QCFLAG_CLEAR_EXCL	= (1 << 5), /* clear excl_link on completion */
 	ATA_QCFLAG_QUIET	= (1 << 6), /* don't report device error */
 	ATA_QCFLAG_RETRY	= (1 << 7), /* retry after failure */
+	ATA_QCFLAG_HAS_CDL	= (1 << 8), /* qc has CDL a descriptor set */
 
 	ATA_QCFLAG_EH		= (1 << 16), /* cmd aborted and owned by EH */
 	ATA_QCFLAG_SENSE_VALID	= (1 << 17), /* sense data valid */
-- 
cgit v1.2.3


From 18bd7718b5c489b3161b6c2ab4685d57c1e2da3b Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Thu, 11 May 2023 03:13:52 +0200
Subject: scsi: ata: libata: Handle completion of CDL commands using policy 0xD

A CDL timeout for policy 0xF is defined as a NCQ error, just with a CDL
specific sk/asc/ascq in the sense data. Therefore, the existing code in
libata does not need to be modified to handle a policy 0xF CDL timeout.

For Command Duration Limits policy 0xD:

  The device shall complete the command without error with the additional
  sense code set to DATA CURRENTLY UNAVAILABLE.

Since a CDL timeout for policy 0xD is not an error, we cannot use the NCQ
Command Error log (10h).

Instead, we need to read the Sense Data for Successful NCQ Commands log
(0Fh).

In the success case, just like in the error case, we cannot simply read a
log page from the interrupt handler itself, since reading a log page
involves sending a READ LOG DMA EXT or READ LOG EXT command.

Therefore, we add a new EH action ATA_EH_GET_SUCCESS_SENSE.  When a command
completes without error, and when the ATA_SENSE bit is set, this new action
is set as pending, and EH is scheduled.

This way, similar to the NCQ error case, the log page will be read from EH
context.

An alternative would have been to add a new kthread or workqueue to handle
this. However, extending EH can be done with minimal changes and avoids the
need to synchronize a new kthread/workqueue with EH.

Co-developed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20230511011356.227789-20-nks@flawful.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-core.c |  88 +++++++++++++++++++++++++++++++++++++-
 drivers/ata/libata-eh.c   | 105 +++++++++++++++++++++++++++++++++++++++++++++-
 drivers/ata/libata-sata.c |  92 ++++++++++++++++++++++++++++++++++++++++
 include/linux/ata.h       |   3 ++
 include/linux/libata.h    |  11 ++++-
 5 files changed, 295 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index e63773740fc2..ddc3d9f8fa02 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -677,8 +677,12 @@ static inline void ata_set_tf_cdl(struct ata_queued_cmd *qc, int cdl)
 	else
 		tf->feature |= cdl;
 
-	/* Mark this command as having a CDL */
-	qc->flags |= ATA_QCFLAG_HAS_CDL;
+	/*
+	 * Mark this command as having a CDL and request the result
+	 * task file so that we can inspect the sense data available
+	 * bit on completion.
+	 */
+	qc->flags |= ATA_QCFLAG_HAS_CDL | ATA_QCFLAG_RESULT_TF;
 }
 
 /**
@@ -2424,6 +2428,24 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 		ata_dev_warn(dev,
 			"Command duration guideline is not supported\n");
 
+	/*
+	 * We must have support for the sense data for successful NCQ commands
+	 * log indicated by the successful NCQ command sense data supported bit.
+	 */
+	val = get_unaligned_le64(&ap->sector_buf[8]);
+	if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(47))) {
+		ata_dev_warn(dev,
+			"CDL supported but Successful NCQ Command Sense Data is not supported\n");
+		goto not_supported;
+	}
+
+	/* Without NCQ autosense, the successful NCQ commands log is useless. */
+	if (!ata_id_has_ncq_autosense(dev->id)) {
+		ata_dev_warn(dev,
+			"CDL supported but NCQ autosense is not supported\n");
+		goto not_supported;
+	}
+
 	/*
 	 * If CDL is marked as enabled, make sure the feature is enabled too.
 	 * Conversely, if CDL is disabled, make sure the feature is turned off.
@@ -2458,6 +2480,35 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 		}
 	}
 
+	/*
+	 * While CDL itself has to be enabled using sysfs, CDL requires that
+	 * sense data for successful NCQ commands is enabled to work properly.
+	 * Just like ata_dev_config_sense_reporting(), enable it unconditionally
+	 * if supported.
+	 */
+	if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(18))) {
+		err_mask = ata_dev_set_feature(dev,
+					SETFEATURE_SENSE_DATA_SUCC_NCQ, 0x1);
+		if (err_mask) {
+			ata_dev_warn(dev,
+				     "failed to enable Sense Data for successful NCQ commands, Emask 0x%x\n",
+				     err_mask);
+			goto not_supported;
+		}
+	}
+
+	/*
+	 * Allocate a buffer to handle reading the sense data for successful
+	 * NCQ Commands log page for commands using a CDL with one of the limit
+	 * policy set to 0xD (successful completion with sense data available
+	 * bit set).
+	 */
+	if (!ap->ncq_sense_buf) {
+		ap->ncq_sense_buf = kmalloc(ATA_LOG_SENSE_NCQ_SIZE, GFP_KERNEL);
+		if (!ap->ncq_sense_buf)
+			goto not_supported;
+	}
+
 	/*
 	 * Command duration limits is supported: cache the CDL log page 18h
 	 * (command duration descriptors).
@@ -2475,6 +2526,8 @@ static void ata_dev_config_cdl(struct ata_device *dev)
 
 not_supported:
 	dev->flags &= ~(ATA_DFLAG_CDL | ATA_DFLAG_CDL_ENABLED);
+	kfree(ap->ncq_sense_buf);
+	ap->ncq_sense_buf = NULL;
 }
 
 static int ata_dev_config_lba(struct ata_device *dev)
@@ -4878,6 +4931,36 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 			fill_result_tf(qc);
 
 		trace_ata_qc_complete_done(qc);
+
+		/*
+		 * For CDL commands that completed without an error, check if
+		 * we have sense data (ATA_SENSE is set). If we do, then the
+		 * command may have been aborted by the device due to a limit
+		 * timeout using the policy 0xD. For these commands, invoke EH
+		 * to get the command sense data.
+		 */
+		if (qc->result_tf.status & ATA_SENSE &&
+		    ((ata_is_ncq(qc->tf.protocol) &&
+		      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
+		     (!(ata_is_ncq(qc->tf.protocol) &&
+			ata_id_sense_reporting_enabled(dev->id))))) {
+			/*
+			 * Tell SCSI EH to not overwrite scmd->result even if
+			 * this command is finished with result SAM_STAT_GOOD.
+			 */
+			qc->scsicmd->flags |= SCMD_FORCE_EH_SUCCESS;
+			qc->flags |= ATA_QCFLAG_EH_SUCCESS_CMD;
+			ehi->dev_action[dev->devno] |= ATA_EH_GET_SUCCESS_SENSE;
+
+			/*
+			 * set pending so that ata_qc_schedule_eh() does not
+			 * trigger fast drain, and freeze the port.
+			 */
+			ap->pflags |= ATA_PFLAG_EH_PENDING;
+			ata_qc_schedule_eh(qc);
+			return;
+		}
+
 		/* Some commands need post-processing after successful
 		 * completion.
 		 */
@@ -5510,6 +5593,7 @@ static void ata_host_release(struct kref *kref)
 
 		kfree(ap->pmp_link);
 		kfree(ap->slave_link);
+		kfree(ap->ncq_sense_buf);
 		kfree(ap);
 		host->ports[i] = NULL;
 	}
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 598ae07195b6..05af292eb8ce 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1917,6 +1917,99 @@ static inline bool ata_eh_quiet(struct ata_queued_cmd *qc)
 	return qc->flags & ATA_QCFLAG_QUIET;
 }
 
+static int ata_eh_read_sense_success_non_ncq(struct ata_link *link)
+{
+	struct ata_port *ap = link->ap;
+	struct ata_queued_cmd *qc;
+
+	qc = __ata_qc_from_tag(ap, link->active_tag);
+	if (!qc)
+		return -EIO;
+
+	if (!(qc->flags & ATA_QCFLAG_EH) ||
+	    !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) ||
+	    qc->err_mask)
+		return -EIO;
+
+	if (!ata_eh_request_sense(qc))
+		return -EIO;
+
+	/*
+	 * If we have sense data, call scsi_check_sense() in order to set the
+	 * correct SCSI ML byte (if any). No point in checking the return value,
+	 * since the command has already completed successfully.
+	 */
+	scsi_check_sense(qc->scsicmd);
+
+	return 0;
+}
+
+static void ata_eh_get_success_sense(struct ata_link *link)
+{
+	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_device *dev = link->device;
+	struct ata_port *ap = link->ap;
+	struct ata_queued_cmd *qc;
+	int tag, ret = 0;
+
+	if (!(ehc->i.dev_action[dev->devno] & ATA_EH_GET_SUCCESS_SENSE))
+		return;
+
+	/* if frozen, we can't do much */
+	if (ata_port_is_frozen(ap)) {
+		ata_dev_warn(dev,
+			"successful sense data available but port frozen\n");
+		goto out;
+	}
+
+	/*
+	 * If the link has sactive set, then we have outstanding NCQ commands
+	 * and have to read the Successful NCQ Commands log to get the sense
+	 * data. Otherwise, we are dealing with a non-NCQ command and use
+	 * request sense ext command to retrieve the sense data.
+	 */
+	if (link->sactive)
+		ret = ata_eh_read_sense_success_ncq_log(link);
+	else
+		ret = ata_eh_read_sense_success_non_ncq(link);
+	if (ret)
+		goto out;
+
+	ata_eh_done(link, dev, ATA_EH_GET_SUCCESS_SENSE);
+	return;
+
+out:
+	/*
+	 * If we failed to get sense data for a successful command that ought to
+	 * have sense data, we cannot simply return BLK_STS_OK to user space.
+	 * This is because we can't know if the sense data that we couldn't get
+	 * was actually "DATA CURRENTLY UNAVAILABLE". Reporting such a command
+	 * as success to user space would result in a silent data corruption.
+	 * Thus, add a bogus ABORTED_COMMAND sense data to such commands, such
+	 * that SCSI will report these commands as BLK_STS_IOERR to user space.
+	 */
+	ata_qc_for_each_raw(ap, qc, tag) {
+		if (!(qc->flags & ATA_QCFLAG_EH) ||
+		    !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) ||
+		    qc->err_mask ||
+		    ata_dev_phys_link(qc->dev) != link)
+			continue;
+
+		/* We managed to get sense for this success command, skip. */
+		if (qc->flags & ATA_QCFLAG_SENSE_VALID)
+			continue;
+
+		/* This success command did not have any sense data, skip. */
+		if (!(qc->result_tf.status & ATA_SENSE))
+			continue;
+
+		/* This success command had sense data, but we failed to get. */
+		ata_scsi_set_sense(dev, qc->scsicmd, ABORTED_COMMAND, 0, 0);
+		qc->flags |= ATA_QCFLAG_SENSE_VALID;
+	}
+	ata_eh_done(link, dev, ATA_EH_GET_SUCCESS_SENSE);
+}
+
 /**
  *	ata_eh_link_autopsy - analyze error and determine recovery action
  *	@link: host link to perform autopsy on
@@ -1957,6 +2050,14 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 	/* analyze NCQ failure */
 	ata_eh_analyze_ncq_error(link);
 
+	/*
+	 * Check if this was a successful command that simply needs sense data.
+	 * Since the sense data is not part of the completion, we need to fetch
+	 * it using an additional command. Since this can't be done from irq
+	 * context, the sense data for successful commands are fetched by EH.
+	 */
+	ata_eh_get_success_sense(link);
+
 	/* any real error trumps AC_ERR_OTHER */
 	if (ehc->i.err_mask & ~AC_ERR_OTHER)
 		ehc->i.err_mask &= ~AC_ERR_OTHER;
@@ -1966,6 +2067,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_EH) ||
 		    qc->flags & ATA_QCFLAG_RETRY ||
+		    qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD ||
 		    ata_dev_phys_link(qc->dev) != link)
 			continue;
 
@@ -3825,7 +3927,8 @@ void ata_eh_finish(struct ata_port *ap)
 			else
 				ata_eh_qc_complete(qc);
 		} else {
-			if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
+			if (qc->flags & ATA_QCFLAG_SENSE_VALID ||
+			    qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) {
 				ata_eh_qc_complete(qc);
 			} else {
 				/* feed zero TF to sense generation */
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 57cb33060c9d..7de4d8901fac 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -11,7 +11,9 @@
 #include <linux/module.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
 #include <linux/libata.h>
+#include <asm/unaligned.h>
 
 #include "libata.h"
 #include "libata-transport.h"
@@ -1408,6 +1410,95 @@ static int ata_eh_read_log_10h(struct ata_device *dev,
 	return 0;
 }
 
+/**
+ *	ata_eh_read_sense_success_ncq_log - Read the sense data for successful
+ *					    NCQ commands log
+ *	@link: ATA link to get sense data for
+ *
+ *	Read the sense data for successful NCQ commands log page to obtain
+ *	sense data for all NCQ commands that completed successfully with
+ *	the sense data available bit set.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+int ata_eh_read_sense_success_ncq_log(struct ata_link *link)
+{
+	struct ata_device *dev = link->device;
+	struct ata_port *ap = dev->link->ap;
+	u8 *buf = ap->ncq_sense_buf;
+	struct ata_queued_cmd *qc;
+	unsigned int err_mask, tag;
+	u8 *sense, sk = 0, asc = 0, ascq = 0;
+	u64 sense_valid, val;
+	int ret = 0;
+
+	err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2);
+	if (err_mask) {
+		ata_dev_err(dev,
+			"Failed to read Sense Data for Successful NCQ Commands log\n");
+		return -EIO;
+	}
+
+	/* Check the log header */
+	val = get_unaligned_le64(&buf[0]);
+	if ((val & 0xffff) != 1 || ((val >> 16) & 0xff) != 0x0f) {
+		ata_dev_err(dev,
+			"Invalid Sense Data for Successful NCQ Commands log\n");
+		return -EIO;
+	}
+
+	sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) |
+		((u64)buf[10] << 16) | ((u64)buf[11] << 24);
+
+	ata_qc_for_each_raw(ap, qc, tag) {
+		if (!(qc->flags & ATA_QCFLAG_EH) ||
+		    !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) ||
+		    qc->err_mask ||
+		    ata_dev_phys_link(qc->dev) != link)
+			continue;
+
+		/*
+		 * If the command does not have any sense data, clear ATA_SENSE.
+		 * Keep ATA_QCFLAG_EH_SUCCESS_CMD so that command is finished.
+		 */
+		if (!(sense_valid & (1ULL << tag))) {
+			qc->result_tf.status &= ~ATA_SENSE;
+			continue;
+		}
+
+		sense = &buf[32 + 24 * tag];
+		sk = sense[0];
+		asc = sense[1];
+		ascq = sense[2];
+
+		if (!ata_scsi_sense_is_valid(sk, asc, ascq)) {
+			ret = -EIO;
+			continue;
+		}
+
+		/* Set sense without also setting scsicmd->result */
+		scsi_build_sense_buffer(dev->flags & ATA_DFLAG_D_SENSE,
+					qc->scsicmd->sense_buffer, sk,
+					asc, ascq);
+		qc->flags |= ATA_QCFLAG_SENSE_VALID;
+
+		/*
+		 * If we have sense data, call scsi_check_sense() in order to
+		 * set the correct SCSI ML byte (if any). No point in checking
+		 * the return value, since the command has already completed
+		 * successfully.
+		 */
+		scsi_check_sense(qc->scsicmd);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ata_eh_read_sense_success_ncq_log);
+
 /**
  *	ata_eh_analyze_ncq_error - analyze NCQ error
  *	@link: ATA link to analyze NCQ error for
@@ -1488,6 +1579,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 
 	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_EH) ||
+		    qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD ||
 		    ata_dev_phys_link(qc->dev) != link)
 			continue;
 
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 21108471c6af..792e10a09787 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -325,6 +325,8 @@ enum {
 	ATA_LOG_CDL		= 0x18,
 	ATA_LOG_CDL_SIZE	= ATA_SECT_SIZE,
 	ATA_LOG_IDENTIFY_DEVICE	= 0x30,
+	ATA_LOG_SENSE_NCQ	= 0x0F,
+	ATA_LOG_SENSE_NCQ_SIZE	= ATA_SECT_SIZE * 2,
 	ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47,
 
 	/* Identify device log pages: */
@@ -431,6 +433,7 @@ enum {
 	SATA_DEVSLP		= 0x09,	/* Device Sleep */
 
 	SETFEATURE_SENSE_DATA	= 0xC3, /* Sense Data Reporting feature */
+	SETFEATURE_SENSE_DATA_SUCC_NCQ = 0xC4, /* Sense Data for successful NCQ commands */
 
 	/* feature values for SET_MAX */
 	ATA_SET_MAX_ADDR	= 0x00,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index f679abd2e61f..5c8ef33b0af2 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -214,6 +214,7 @@ enum {
 	ATA_QCFLAG_EH		= (1 << 16), /* cmd aborted and owned by EH */
 	ATA_QCFLAG_SENSE_VALID	= (1 << 17), /* sense data valid */
 	ATA_QCFLAG_EH_SCHEDULED = (1 << 18), /* EH scheduled (obsolete) */
+	ATA_QCFLAG_EH_SUCCESS_CMD = (1 << 19), /* EH should fetch sense for this successful cmd */
 
 	/* host set flags */
 	ATA_HOST_SIMPLEX	= (1 << 0),	/* Host is simplex, one DMA channel per host only */
@@ -312,8 +313,10 @@ enum {
 	ATA_EH_RESET		= ATA_EH_SOFTRESET | ATA_EH_HARDRESET,
 	ATA_EH_ENABLE_LINK	= (1 << 3),
 	ATA_EH_PARK		= (1 << 5), /* unload heads and stop I/O */
+	ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */
 
-	ATA_EH_PERDEV_MASK	= ATA_EH_REVALIDATE | ATA_EH_PARK,
+	ATA_EH_PERDEV_MASK	= ATA_EH_REVALIDATE | ATA_EH_PARK |
+				  ATA_EH_GET_SUCCESS_SENSE,
 	ATA_EH_ALL_ACTIONS	= ATA_EH_REVALIDATE | ATA_EH_RESET |
 				  ATA_EH_ENABLE_LINK,
 
@@ -867,6 +870,7 @@ struct ata_port {
 	struct ata_acpi_gtm	__acpi_init_gtm; /* use ata_acpi_init_gtm() */
 #endif
 	/* owned by EH */
+	u8			*ncq_sense_buf;
 	u8			sector_buf[ATA_SECT_SIZE] ____cacheline_aligned;
 };
 
@@ -1185,6 +1189,7 @@ extern int sata_link_hardreset(struct ata_link *link,
 			bool *online, int (*check_ready)(struct ata_link *));
 extern int sata_link_resume(struct ata_link *link, const unsigned long *params,
 			    unsigned long deadline);
+extern int ata_eh_read_sense_success_ncq_log(struct ata_link *link);
 extern void ata_eh_analyze_ncq_error(struct ata_link *link);
 #else
 static inline const unsigned long *
@@ -1222,6 +1227,10 @@ static inline int sata_link_resume(struct ata_link *link,
 {
 	return -EOPNOTSUPP;
 }
+static inline int ata_eh_read_sense_success_ncq_log(struct ata_link *link)
+{
+	return -EOPNOTSUPP;
+}
 static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { }
 #endif
 extern int sata_link_debounce(struct ata_link *link,
-- 
cgit v1.2.3