diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1af6b8a9da5a..f21d922ecfaf 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1646,6 +1646,42 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
+/*
+ * Is the request queue handled by an IO scheduler that does not respect
+ * hardware queues when dispatching?
+ */
+static bool blk_mq_has_sqsched(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.dispatch_request &&
+	    !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
+		return true;
+	return false;
+}
+
+/*
+ * Return prefered queue to dispatch from (if any) for non-mq aware IO
+ * scheduler.
+ */
+static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	/*
+	 * If the IO scheduler does not respect hardware queues when
+	 * dispatching, we just don't bother with multiple HW queues and
+	 * dispatch from hctx for the current CPU since running multiple queues
+	 * just causes lock contention inside the scheduler and pointless cache
+	 * bouncing.
+	 */
+	hctx = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT,
+				     raw_smp_processor_id());
+	if (!blk_mq_hctx_stopped(hctx))
+		return hctx;
+	return NULL;
+}
+
 /**
  * blk_mq_run_hw_queues - Run all hardware queues in a request queue.
  * @q: Pointer to the request queue to run.
@@ -1653,14 +1689,23 @@ EXPORT_SYMBOL(blk_mq_run_hw_queue);
  */
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx, *sq_hctx;
 	int i;
 
+	sq_hctx = NULL;
+	if (blk_mq_has_sqsched(q))
+		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
 			continue;
-
-		blk_mq_run_hw_queue(hctx, async);
+		/*
+		 * Dispatch from this hctx either if there's no hctx preferred
+		 * by IO scheduler or if it has requests that bypass the
+		 * scheduler.
+		 */
+		if (!sq_hctx || sq_hctx == hctx ||
+		    !list_empty_careful(&hctx->dispatch))
+			blk_mq_run_hw_queue(hctx, async);
 	}
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queues);
@@ -1672,14 +1717,23 @@ EXPORT_SYMBOL(blk_mq_run_hw_queues);
  */
 void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx, *sq_hctx;
 	int i;
 
+	sq_hctx = NULL;
+	if (blk_mq_has_sqsched(q))
+		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
 			continue;
-
-		blk_mq_delay_run_hw_queue(hctx, msecs);
+		/*
+		 * Dispatch from this hctx either if there's no hctx preferred
+		 * by IO scheduler or if it has requests that bypass the
+		 * scheduler.
+		 */
+		if (!sq_hctx || sq_hctx == hctx ||
+		    !list_empty_careful(&hctx->dispatch))
+			blk_mq_delay_run_hw_queue(hctx, msecs);
 	}
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index dc89199bc8c6..c25c41d0d061 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -1029,6 +1029,7 @@ static struct elevator_type kyber_sched = {
 #endif
 	.elevator_attrs = kyber_sched_attrs,
 	.elevator_name = "kyber",
+	.elevator_features = ELEVATOR_F_MQ_AWARE,
 	.elevator_owner = THIS_MODULE,
 };
 
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index bacc40a0bdf3..1fe8e105b83b 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -172,6 +172,8 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t);
 
 /* Supports zoned block devices sequential write constraint */
 #define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
+/* Supports scheduling on multiple hardware queues */
+#define ELEVATOR_F_MQ_AWARE		(1U << 1)
 
 #endif /* CONFIG_BLOCK */
 #endif