1 files changed, 37 insertions, 7 deletions

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 3cf555f12700..553a317a0e6e 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -360,13 +360,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 				       bool has_sched,
 				       struct request *rq)
 {
-	/* dispatch flush rq directly */
-	if (rq->rq_flags & RQF_FLUSH_SEQ) {
-		spin_lock(&hctx->lock);
-		list_add(&rq->queuelist, &hctx->dispatch);
-		spin_unlock(&hctx->lock);
+	/*
+	 * dispatch flush and passthrough rq directly
+	 *
+	 * passthrough request has to be added to hctx->dispatch directly.
+	 * For some reason, device may be in one situation which can't
+	 * handle FS request, so STS_RESOURCE is always returned and the
+	 * FS request will be added to hctx->dispatch. However passthrough
+	 * request may be required at that time for fixing the problem. If
+	 * passthrough request is added to scheduler queue, there isn't any
+	 * chance to dispatch it given we prioritize requests in hctx->dispatch.
+	 */
+	if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
 		return true;
-	}
 
 	if (has_sched)
 		rq->rq_flags |= RQF_SORTED;
@@ -390,8 +396,32 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 
 	WARN_ON(e && (rq->tag != -1));
 
-	if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
+	if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
+		/*
+		 * Firstly normal IO request is inserted to scheduler queue or
+		 * sw queue, meantime we add flush request to dispatch queue(
+		 * hctx->dispatch) directly and there is at most one in-flight
+		 * flush request for each hw queue, so it doesn't matter to add
+		 * flush request to tail or front of the dispatch queue.
+		 *
+		 * Secondly in case of NCQ, flush request belongs to non-NCQ
+		 * command, and queueing it will fail when there is any
+		 * in-flight normal IO request(NCQ command). When adding flush
+		 * rq to the front of hctx->dispatch, it is easier to introduce
+		 * extra time to flush rq's latency because of S_SCHED_RESTART
+		 * compared with adding to the tail of dispatch queue, then
+		 * chance of flush merge is increased, and less flush requests
+		 * will be issued to controller. It is observed that ~10% time
+		 * is saved in blktests block/004 on disk attached to AHCI/NCQ
+		 * drive when adding flush rq to the front of hctx->dispatch.
+		 *
+		 * Simply queue flush rq to the front of hctx->dispatch so that
+		 * intensive flush workloads can benefit in case of NCQ HW.
+		 */
+		at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head;
+		blk_mq_request_bypass_insert(rq, at_head, false);
 		goto run;
+	}
 
 	if (e && e->type->ops.insert_requests) {
 		LIST_HEAD(list);