[PATCH V4] scsi: core: only re-run queue in scsi_end_request() if device queue is busy

[Ming Lei <ming.lei@redhat.com>]

Now the request queue is run in scsi_end_request() unconditionally if both
target queue and host queue is ready. We should have re-run request queue
only after this device queue becomes busy for restarting this LUN only.

Recently Long Li reported that cost of run queue may be very heavy in
case of high queue depth. So improve this situation by only running
the request queue when this LUN is busy.

Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Long Li <longli@microsoft.com>
Cc: John Garry <john.garry@huawei.com>
Cc: linux-block@vger.kernel.org
Reported-by: Long Li <longli@microsoft.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
V4:
	- fix one race reported by Kashyap, and simplify the implementation
	a bit; also pass Kashyap's both function and performance test
V3:
	- add one smp_mb() in scsi_mq_get_budget() and comment

V2:
	- commit log change, no any code change
	- add reported-by tag

 drivers/scsi/scsi_lib.c    | 51 +++++++++++++++++++++++++++++++++++---
 include/scsi/scsi_device.h |  1 +
 2 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7c6dd6f75190..a62c29058d26 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -551,8 +551,27 @@ static void scsi_run_queue_async(struct scsi_device *sdev)
 	if (scsi_target(sdev)->single_lun ||
 	    !list_empty(&sdev->host->starved_list))
 		kblockd_schedule_work(&sdev->requeue_work);
-	else
-		blk_mq_run_hw_queues(sdev->request_queue, true);
+	else {
+		/*
+		 * smp_mb() implied in either rq->end_io or blk_mq_free_request
+		 * is for ordering writing .device_busy in scsi_device_unbusy()
+		 * and reading sdev->restarts.
+		 */
+		int old = atomic_read(&sdev->restarts);
+
+		if (old) {
+			/*
+			 * ->restarts has to be kept as non-zero if there is
+			 *  new budget contention comes.
+			 *
+			 *  No need to run queue when either another re-run
+			 *  queue wins in updating ->restarts or one new budget
+			 *  contention comes.
+			 */
+			if (atomic_cmpxchg(&sdev->restarts, old, 0) == old)
+				blk_mq_run_hw_queues(sdev->request_queue, true);
+		}
+	}
 }
 
 /* Returns false when no more bytes to process, true if there are more */
@@ -1611,8 +1630,34 @@ static void scsi_mq_put_budget(struct request_queue *q)
 static bool scsi_mq_get_budget(struct request_queue *q)
 {
 	struct scsi_device *sdev = q->queuedata;
+	int ret = scsi_dev_queue_ready(q, sdev);
+
+	if (ret)
+		return true;
+
+	atomic_inc(&sdev->restarts);
 
-	return scsi_dev_queue_ready(q, sdev);
+	/*
+	 * Order writing .restarts and reading .device_busy, and make sure
+	 * .restarts is visible to scsi_end_request(). Its pair is implied by
+	 * __blk_mq_end_request() in scsi_end_request() for ordering
+	 * writing .device_busy in scsi_device_unbusy() and reading .restarts.
+	 *
+	 */
+	smp_mb__after_atomic();
+
+	/*
+	 * If all in-flight requests originated from this LUN are completed
+	 * before setting .restarts, sdev->device_busy will be observed as
+	 * zero, then blk_mq_delay_run_hw_queues() will dispatch this request
+	 * soon. Otherwise, completion of one of these request will observe
+	 * the .restarts flag, and the request queue will be run for handling
+	 * this request, see scsi_end_request().
+	 */
+	if (unlikely(atomic_read(&sdev->device_busy) == 0 &&
+				!scsi_device_blocked(sdev)))
+		blk_mq_delay_run_hw_queues(sdev->request_queue, SCSI_QUEUE_DELAY);
+	return false;
 }
 
 static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index bc5909033d13..1a5c9a3df6d6 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -109,6 +109,7 @@ struct scsi_device {
 	atomic_t device_busy;		/* commands actually active on LLDD */
 	atomic_t device_blocked;	/* Device returned QUEUE_FULL. */
 
+	atomic_t restarts;
 	spinlock_t list_lock;
 	struct list_head starved_entry;
 	unsigned short queue_depth;	/* How deep of a queue we want */
-- 
2.25.2