diff --git a/block/blk-mq.c b/block/blk-mq.c
index 542b28a2e6b0..a5ed12bd2b0a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2475,6 +2475,12 @@ void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		return;
 
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	/*
+	 * Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the
+	 * clearing of BLK_MQ_S_STOPPED above and the checking of dispatch
+	 * list in the subsequent routine.
+	 */
+	smp_mb__after_atomic();
 	blk_mq_run_hw_queue(hctx, async);
 }
 EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c6eca452ea2a..c79deb684a95 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -178,6 +178,19 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
 
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
 {
+	/* Fast path: hardware queue is not stopped most of the time. */
+	if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
+		return false;
+
+	/*
+	 * This barrier is used to order adding of dispatch list before and
+	 * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier
+	 * in blk_mq_start_stopped_hw_queue() so that dispatch code could
+	 * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not
+	 * empty to avoid missing dispatching requests.
+	 */
+	smp_mb();
+
 	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
 }