diff --git a/block/blk-mq.c b/block/blk-mq.c
index 01ec97aa9ec8195435c4666749ea8f3753e3155b..4b2507cdece3ab41be5d787622fe698757772c3e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3990,6 +3990,19 @@ unsigned int blk_mq_rq_cpu(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_rq_cpu);
 
+void blk_mq_cancel_work_sync(struct request_queue *q)
+{
+	if (queue_is_mq(q)) {
+		struct blk_mq_hw_ctx *hctx;
+		int i;
+
+		cancel_delayed_work_sync(&q->requeue_work);
+
+		queue_for_each_hw_ctx(q, hctx, i)
+			cancel_delayed_work_sync(&hctx->run_work);
+	}
+}
+
 static int __init blk_mq_init(void)
 {
 	int i;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index f792a0920ebb13e3857e6a5d3397e13775c67e53..6f87c0681443b52f052a1f638621470a574d5aec 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -129,6 +129,7 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
+void blk_mq_cancel_work_sync(struct request_queue *q);
 void blk_mq_release(struct request_queue *q);
 
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
diff --git a/block/elevator.c b/block/elevator.c
index 4ce6b22813a14690f4bb70795712111fec02e704..27eb70ec277ae90c05177a9d5b774b38b84af28e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -684,12 +684,18 @@ void elevator_init_mq(struct request_queue *q)
 	if (!e)
 		return;
 
+	/*
+	 * We are called before adding disk, when there isn't any FS I/O,
+	 * so freezing queue plus canceling dispatch work is enough to
+	 * drain any dispatch activities originated from passthrough
+	 * requests, then no need to quiesce queue which may add long boot
+	 * latency, especially when lots of disks are involved.
+	 */
 	blk_mq_freeze_queue(q);
-	blk_mq_quiesce_queue(q);
+	blk_mq_cancel_work_sync(q);
 
 	err = blk_mq_init_sched(q, e);
 
-	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 
 	if (err) {