diff --git a/block/blk-mq.c b/block/blk-mq.c
index f5c7dbcb954f..90f869a083a4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1180,7 +1180,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		struct blk_mq_queue_data bd;
 
 		rq = list_first_entry(list, struct request, queuelist);
-		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+
+		hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1189,8 +1194,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * we'll re-run it below.
 			 */
 			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
-				if (got_budget)
-					blk_mq_put_dispatch_budget(hctx);
+				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
 				 * will suffice.
@@ -1201,11 +1205,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			}
 		}
 
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
-			blk_mq_put_driver_tag(rq);
-			break;
-		}
-
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -1804,11 +1803,11 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (q->elevator && !bypass_insert)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false))
+	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_dispatch_budget(hctx)) {
-		blk_mq_put_driver_tag(rq);
+	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}