diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 4bc701b32ce2..0861f15ec0df 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -336,6 +336,18 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	/*
+	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
+	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
+	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
+	 * synchronize_rcu to ensure all of the users go out of the critical
+	 * section below and see zeroed q_usage_counter.
+	 */
+	rcu_read_lock();
+	if (percpu_ref_is_zero(&q->q_usage_counter)) {
+		rcu_read_unlock();
+		return;
+	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -351,7 +363,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-
+	rcu_read_unlock();
 }
 
 static unsigned int bt_unused_tags(const struct sbitmap_queue *bt)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 24fc09cf7f17..58be2eaa5aaa 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2346,6 +2346,10 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);