[PATCH 5.16 0031/1017] block: flush plug based on hardware and software queue order

[Greg Kroah-Hartman]

From: Jens Axboe <axboe@xxxxxxxxx>

commit 26fed4ac4eab09c27fbae1859696cc38f0536407 upstream.

We used to sort the plug list if we had multiple queues before dispatching
requests to the IO scheduler. This usually isn't needed, but for certain
workloads that interleave requests to disks, it's a less efficient to
process the plug list one-by-one if everything is interleaved.

Don't sort the list, but skip through it and flush out entries that have
the same target at the same time.

Fixes: df87eb0fce8f ("block: get rid of plug list sorting")
Reported-and-tested-by: Song Liu <song@xxxxxxxxxx>
Reviewed-by: Song Liu <songliubraving@xxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 block/blk-mq.c |   60 +++++++++++++++++++++++++--------------------------------
 1 file changed, 27 insertions(+), 33 deletions(-)

--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2244,13 +2244,35 @@ static void blk_mq_plug_issue_direct(str
 		blk_mq_commit_rqs(hctx, &queued, from_schedule);
 }
 
-void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 {
-	struct blk_mq_hw_ctx *this_hctx;
-	struct blk_mq_ctx *this_ctx;
-	unsigned int depth;
+	struct blk_mq_hw_ctx *this_hctx = NULL;
+	struct blk_mq_ctx *this_ctx = NULL;
+	struct request *requeue_list = NULL;
+	unsigned int depth = 0;
 	LIST_HEAD(list);
 
+	do {
+		struct request *rq = rq_list_pop(&plug->mq_list);
+
+		if (!this_hctx) {
+			this_hctx = rq->mq_hctx;
+			this_ctx = rq->mq_ctx;
+		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+			rq_list_add(&requeue_list, rq);
+			continue;
+		}
+		list_add_tail(&rq->queuelist, &list);
+		depth++;
+	} while (!rq_list_empty(plug->mq_list));
+
+	plug->mq_list = requeue_list;
+	trace_block_unplug(this_hctx->queue, depth, !from_sched);
+	blk_mq_sched_insert_requests(this_hctx, this_ctx, &list, from_sched);
+}
+
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+{
 	if (rq_list_empty(plug->mq_list))
 		return;
 	plug->rq_count = 0;
@@ -2261,37 +2283,9 @@ void blk_mq_flush_plug_list(struct blk_p
 			return;
 	}
 
-	this_hctx = NULL;
-	this_ctx = NULL;
-	depth = 0;
 	do {
-		struct request *rq;
-
-		rq = rq_list_pop(&plug->mq_list);
-
-		if (!this_hctx) {
-			this_hctx = rq->mq_hctx;
-			this_ctx = rq->mq_ctx;
-		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
-			trace_block_unplug(this_hctx->queue, depth,
-						!from_schedule);
-			blk_mq_sched_insert_requests(this_hctx, this_ctx,
-						&list, from_schedule);
-			depth = 0;
-			this_hctx = rq->mq_hctx;
-			this_ctx = rq->mq_ctx;
-
-		}
-
-		list_add(&rq->queuelist, &list);
-		depth++;
+		blk_mq_dispatch_plug_list(plug, from_schedule);
 	} while (!rq_list_empty(plug->mq_list));
-
-	if (!list_empty(&list)) {
-		trace_block_unplug(this_hctx->queue, depth, !from_schedule);
-		blk_mq_sched_insert_requests(this_hctx, this_ctx, &list,
-						from_schedule);
-	}
 }
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,