BACKPORT: FROMGIT: block: Improve performance for BLK_MQ_F_BLOCKING drivers

blk_mq_run_queue() runs the queue asynchronously if BLK_MQ_F_BLOCKING
has been set. This is suboptimal since running the queue asynchronously
is slower than running the queue synchronously. This patch modifies
blk_mq_run_queue() as follows if BLK_MQ_F_BLOCKING has been set:
- Run the queue synchronously if it is allowed to sleep.
- Run the queue asynchronously if it is not allowed to sleep.
Additionally, blk_mq_run_hw_queue(hctx, false) calls are modified into
blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING) if the caller
may be invoked from atomic context.

The following caller chains have been reviewed:

blk_mq_run_hw_queue(hctx, false)
  blk_mq_get_tag()      /* may sleep, hence the functions it calls may also sleep */
  blk_execute_rq()             /* may sleep */
  blk_mq_run_hw_queues(q, async=false)
    blk_freeze_queue_start()   /* may sleep */
    blk_mq_requeue_work()      /* may sleep */
    scsi_kick_queue()
      scsi_requeue_run_queue() /* may sleep */
      scsi_run_host_queues()
        scsi_ioctl_reset()     /* may sleep */
  blk_mq_insert_requests(hctx, ctx, list, run_queue_async=false)
    blk_mq_dispatch_plug_list(plug, from_sched=false)
      blk_mq_flush_plug_list(plug, from_schedule=false)
        __blk_flush_plug(plug, from_schedule=false)
	blk_add_rq_to_plug()
	  blk_mq_submit_bio()  /* may sleep if REQ_NOWAIT has not been set */
  blk_mq_plug_issue_direct()
    blk_mq_flush_plug_list()   /* see above */
  blk_mq_dispatch_plug_list(plug, from_sched=false)
    blk_mq_flush_plug_list()   /* see above */
  blk_mq_try_issue_directly()
    blk_mq_submit_bio()        /* may sleep if REQ_NOWAIT has not been set */
  blk_mq_try_issue_list_directly(hctx, list)
    blk_mq_insert_requests() /* see above */

Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Change-Id: I597e0fa587057ac22e52f73351cbfa1de2c72a6b
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230721172731.955724-4-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bug: 291379528
(cherry picked from commit 65a558f66c git://git.kernel.dk/linux-block for-next)
Signed-off-by: Bart Van Assche <bvanassche@google.com>

block/blk-exec.c

@@ -59,7 +59,10 @@ void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set
 	 */
-	blk_mq_sched_insert_request(rq, at_head, true, false);
+	blk_mq_sched_insert_request(rq, at_head, true,
+				    rq->mq_hctx->flags & BLK_MQ_F_BLOCKING &&
+				    rq->cmd_flags & REQ_NOWAIT);
+
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 

block/blk-mq.c

@@ -1561,11 +1561,9 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 	if (unlikely(blk_mq_hctx_stopped(hctx)))
 		return;
 
-	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		if (cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
-			__blk_mq_run_hw_queue(hctx);
-			return;
-		}
+	if (!async && cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
+		__blk_mq_run_hw_queue(hctx);
+		return;
 	}
 
 	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
@@ -1768,7 +1766,7 @@ void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
 
-	blk_mq_run_hw_queue(hctx, false);
+	blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING);
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queue);
 
@@ -1798,7 +1796,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_start_stopped_hw_queue(hctx, async);
+		blk_mq_start_stopped_hw_queue(hctx, async ||
+					(hctx->flags & BLK_MQ_F_BLOCKING));
 }
 EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
 

drivers/scsi/scsi_lib.c

@@ -328,7 +328,8 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)
 	 * but in most cases, we will be first. Ideally, each LU on the
 	 * target would get some limited time or requests on the target.
 	 */
-	blk_mq_run_hw_queues(current_sdev->request_queue, false);
+	blk_mq_run_hw_queues(current_sdev->request_queue,
+			     shost->queuecommand_may_block);
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (starget->starget_sdev_user)