[PATCH v6 20/27] scsi-multipath: add scsi_mpath_{start,end}_request()

From: John Garry <[email protected]>

Add scsi_mpath_{start,end}_request() to handle updating private multipath
request data, like nvme_mpath_{start,end}_request().

New member Scsi_Host.mpath_nr_active is added. This is required for queue
depth multipath iopolicy.

For NVMe, this count is per controller. The reason is that many NSes may
be connected to a controller, so congestion should be judged at
controller level.

SCSI has no definition of a controller, but SCSI host is a comparable
concept.

Indeed, many SCSI disks may be connected to the same SCSI host, so it
makes sense to count number of active requests at this point. However,
for a transport like iSCSI Initiator over TCP/IP, we have a separate SCSI
host per SCSI device (so there the count would be same at SCSI device
level).

Signed-off-by: John Garry <[email protected]>
---
 drivers/scsi/scsi_lib.c       |  8 +++-
 drivers/scsi/scsi_multipath.c | 69 +++++++++++++++++++++++++++++++++++
 include/scsi/scsi_cmnd.h      |  9 ++++-
 include/scsi/scsi_host.h      |  4 ++
 include/scsi/scsi_multipath.h | 11 ++++++
 5 files changed, 99 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41d201b7e7def..baafca4eea866 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -669,7 +669,10 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
 	struct scsi_device *sdev = cmd->device;
 	struct request_queue *q = sdev->request_queue;
 
-	if (blk_update_request(req, error, bytes))
+	if (sdev->scsi_mpath_dev && is_mpath_request(req)) {
+		if (scsi_mpath_end_request(req, error, bytes))
+			return true;
+	} else if (blk_update_request(req, error, bytes))
 		return true;
 
 	if (q->limits.features & BLK_FEAT_ADD_RANDOM)
@@ -1917,6 +1920,9 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
 	cmd->submitter = SUBMITTED_BY_BLOCK_LAYER;
 
+	if (sdev->scsi_mpath_dev && is_mpath_request(req))
+		scsi_mpath_start_request(req);
+
 	blk_mq_start_request(req);
 	if (blk_mq_is_reserved_rq(req)) {
 		reason = shost->hostt->queue_reserved_command(shost, cmd);
diff --git a/drivers/scsi/scsi_multipath.c b/drivers/scsi/scsi_multipath.c
index 2a05f177a1dcd..0adc5adb4b234 100644
--- a/drivers/scsi/scsi_multipath.c
+++ b/drivers/scsi/scsi_multipath.c
@@ -562,6 +562,75 @@ void scsi_mpath_put_head(struct scsi_mpath_head *scsi_mpath_head)
 }
 EXPORT_SYMBOL_GPL(scsi_mpath_put_head);
 
+void scsi_mpath_start_request(struct request *req)
+{
+	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
+	struct scsi_device *sdev = scmd->device;
+	struct scsi_mpath_device *scsi_mpath_dev = sdev->scsi_mpath_dev;
+	struct scsi_mpath_head *scsi_mpath_head =
+				scsi_mpath_dev->scsi_mpath_head;
+	struct bio *clone = req->bio, *master;
+	struct mpath_head *mpath_head = &scsi_mpath_head->mpath_head;
+	struct gendisk *disk = mpath_head->disk;
+
+	if (mpath_qd_iopolicy(&scsi_mpath_head->iopolicy) &&
+	    !(scmd->flags & SCMD_MPATH_CNT_ACTIVE)) {
+		struct Scsi_Host *shost = sdev->host;
+
+		atomic_inc(&shost->mpath_nr_active);
+		scmd->flags |= SCMD_MPATH_CNT_ACTIVE;
+	}
+
+	if (blk_rq_is_passthrough(req) || !blk_queue_io_stat(disk->queue))
+		return;
+
+	if (!clone) {
+		scmd->flags &= ~SCMD_MPATH_IO_STATS;
+		return;
+	}
+
+	if (scmd->flags & SCMD_MPATH_IO_STATS)
+		return;
+
+	master = clone->bi_private;
+
+	scmd->flags |= SCMD_MPATH_IO_STATS;
+	scmd->start_time = bdev_start_io_acct(master->bi_bdev, req_op(req),
+				jiffies);
+	scmd->start_bytes = blk_rq_bytes(req);
+}
+
+bool scsi_mpath_end_request(struct request *req, blk_status_t error,
+				unsigned int nr_bytes)
+{
+	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
+	struct scsi_device *sdev = scmd->device;
+	struct block_device *bi_bdev = NULL;
+
+	if (scmd->flags & SCMD_MPATH_IO_STATS) {
+		struct bio *clone = req->bio, *master = clone->bi_private;
+
+		bi_bdev = master->bi_bdev;
+	}
+
+	if (blk_update_request(req, error, nr_bytes))
+		return true;
+
+	if (scmd->flags & SCMD_MPATH_CNT_ACTIVE) {
+		struct Scsi_Host *shost = sdev->host;
+
+		atomic_dec_if_positive(&shost->mpath_nr_active);
+	}
+
+	if (!(scmd->flags & SCMD_MPATH_IO_STATS))
+		return false;
+	bdev_end_io_acct(bi_bdev, req_op(req),
+			 scmd->start_bytes >> SECTOR_SHIFT,
+			 scmd->start_time);
+
+	return false;
+}
+
 int __init scsi_multipath_init(void)
 {
 	return class_register(&scsi_mpath_device_class);
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 8ecfb94049db5..52227e2cd9749 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -58,8 +58,11 @@ struct scsi_pointer {
  */
 #define SCMD_FORCE_EH_SUCCESS	(1 << 3)
 #define SCMD_FAIL_IF_RECOVERING	(1 << 4)
+#define SCMD_MPATH_IO_STATS	(1 << 5)
+#define SCMD_MPATH_CNT_ACTIVE	(1 << 6)
 /* flags preserved across unprep / reprep */
-#define SCMD_PRESERVED_FLAGS	(SCMD_INITIALIZED | SCMD_FAIL_IF_RECOVERING)
+#define SCMD_PRESERVED_FLAGS	(SCMD_INITIALIZED | SCMD_FAIL_IF_RECOVERING | \
+				SCMD_MPATH_IO_STATS | SCMD_MPATH_CNT_ACTIVE)
 
 /* for scmd->state */
 #define SCMD_STATE_COMPLETE	0
@@ -139,6 +142,10 @@ struct scsi_cmnd {
 					 * to release this memory.  (The memory
 					 * obtained by scsi_malloc is guaranteed
 					 * to be at an address < 16Mb). */
+	#ifdef CONFIG_SCSI_MULTIPATH
+	unsigned long		start_time;
+	unsigned int		start_bytes;
+	#endif
 
 	int result;		/* Status code from lower level driver */
 };
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 7e2011830ba4b..cf4fff3ea1a8e 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -753,6 +753,10 @@ struct Scsi_Host {
 	/* Delay for runtime autosuspend */
 	int rpm_autosuspend_delay;
 
+	#ifdef CONFIG_SCSI_MULTIPATH
+	atomic_t mpath_nr_active;
+	#endif
+
 	/*
 	 * We should ensure that this is aligned, both for better performance
 	 * and also because some compilers (m68k) don't automatically force
diff --git a/include/scsi/scsi_multipath.h b/include/scsi/scsi_multipath.h
index cc77e63c43da3..c3398e9f03f16 100644
--- a/include/scsi/scsi_multipath.h
+++ b/include/scsi/scsi_multipath.h
@@ -56,6 +56,9 @@ int scsi_mpath_get_head(struct scsi_mpath_head *scsi_mpath_head);
 void scsi_mpath_put_head(struct scsi_mpath_head *scsi_mpath_head);
 void scsi_mpath_dev_clear_path(struct scsi_mpath_device *scsi_mpath_dev);
 void scsi_mpath_revalidate_paths(struct scsi_mpath_device *scsi_mpath_dev);
+void scsi_mpath_start_request(struct request *req);
+bool scsi_mpath_end_request(struct request *req, blk_status_t error,
+			       unsigned int nr_bytes);
 #else /* CONFIG_SCSI_MULTIPATH */
 
 struct scsi_mpath_head {
@@ -98,6 +101,14 @@ static inline
 void scsi_mpath_revalidate_paths(struct scsi_mpath_device *scsi_mpath_dev)
 {
 }
+static inline void scsi_mpath_start_request(struct request *req)
+{
+}
+static inline bool scsi_mpath_end_request(struct request *req, blk_status_t error,
+			       unsigned int nr_bytes)
+{
+	return false;
+}
 static inline void scsi_mpath_add_sysfs_link(struct scsi_device *sdev)
 {
 }
-- 
2.43.7