diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 2704a55f8b6e..8b7328666eaa 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -502,8 +502,20 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 		if (queue_dying) {
 			atomic_inc(&m->pg_init_in_progress);
 			activate_or_offline_path(pgpath);
+			return DM_MAPIO_DELAY_REQUEUE;
 		}
-		return DM_MAPIO_DELAY_REQUEUE;
+
+		/*
+		 * blk-mq's SCHED_RESTART can cover this requeue, so we
+		 * needn't deal with it by DELAY_REQUEUE. More importantly,
+		 * we have to return DM_MAPIO_REQUEUE so that blk-mq can
+		 * get the queue busy feedback (via BLK_STS_RESOURCE),
+		 * otherwise I/O merging can suffer.
+		 */
+		if (q->mq_ops)
+			return DM_MAPIO_REQUEUE;
+		else
+			return DM_MAPIO_DELAY_REQUEUE;
 	}
 	clone->bio = clone->biotail = NULL;
 	clone->rq_disk = bdev->bd_disk;