diff --git a/block/blk-core.c b/block/blk-core.c
index 223f32826e62..b8d1aa2d1008 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2397,7 +2397,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		 * bypass a potential scheduler on the bottom device for
 		 * insert.
 		 */
-		blk_mq_request_bypass_insert(rq);
+		blk_mq_request_bypass_insert(rq, true);
 		return BLK_STS_OK;
 	}
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6eacc1dea8b7..021562bd5d2c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1492,7 +1492,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq)
+void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
@@ -1501,7 +1501,8 @@ void blk_mq_request_bypass_insert(struct request *rq)
 	list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
-	blk_mq_run_hw_queue(hctx, false);
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, false);
 }
 
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
diff --git a/block/blk-mq.h b/block/blk-mq.h
index f97aceff76e9..9fffec0ad8e9 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -56,7 +56,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq);
+void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);