blk-mq-sched: change ->dispatch_requests() to ->dispatch_request()

When we invoke dispatch_requests(), the scheduler empties everything
into the passed in list. This isn't always a good thing, since it
means that we remove items that we could have potentially merged
with.

Change the function to dispatch single requests at the time. If
we do that, we can backoff exactly at the point where the device
can't consume more IO, and leave the rest with the scheduler for
better merging and future dispatch decision making.

Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Tested-by: Hannes Reinecke <hare@suse.com>

block/blk-mq-sched.c

@@ -201,15 +201,22 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 * leave them there for as long as we can. Mark the hw queue as
 	 * needing a restart in that case.
 	 */
-	if (list_empty(&rq_list)) {
-		if (e && e->type->ops.mq.dispatch_requests)
-			e->type->ops.mq.dispatch_requests(hctx, &rq_list);
-		else
-			blk_mq_flush_busy_ctxs(hctx, &rq_list);
-	} else
+	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart(hctx);
-
-	blk_mq_dispatch_rq_list(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else if (!e || !e->type->ops.mq.dispatch_request) {
+		blk_mq_flush_busy_ctxs(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else {
+		do {
+			struct request *rq;
+
+			rq = e->type->ops.mq.dispatch_request(hctx);
+			if (!rq)
+				break;
+			list_add(&rq->queuelist, &rq_list);
+		} while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+	}
 }
 
 void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,

block/blk-mq.c

@@ -998,7 +998,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	 */
 	if (!list_empty(list)) {
 		spin_lock(&hctx->lock);
-		list_splice(list, &hctx->dispatch);
+		list_splice_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*

block/mq-deadline.c

@@ -287,14 +287,16 @@ done:
 	return rq;
 }
 
-static void dd_dispatch_requests(struct blk_mq_hw_ctx *hctx,
-				 struct list_head *rq_list)
+static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
 
 	spin_lock(&dd->lock);
-	blk_mq_sched_move_to_dispatch(hctx, rq_list, __dd_dispatch_request);
+	rq = __dd_dispatch_request(hctx);
 	spin_unlock(&dd->lock);
+
+	return rq;
 }
 
 static void dd_exit_queue(struct elevator_queue *e)
@@ -517,7 +519,7 @@ static struct elv_fs_entry deadline_attrs[] = {
 static struct elevator_type mq_deadline = {
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
-		.dispatch_requests	= dd_dispatch_requests,
+		.dispatch_request	= dd_dispatch_request,
 		.next_request		= elv_rb_latter_request,
 		.former_request		= elv_rb_former_request,
 		.bio_merge		= dd_bio_merge,

include/linux/elevator.h

@@ -92,7 +92,7 @@ struct elevator_mq_ops {
 	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
 	void (*put_request)(struct request *);
 	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
-	void (*dispatch_requests)(struct blk_mq_hw_ctx *, struct list_head *);
+	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
 	bool (*has_work)(struct blk_mq_hw_ctx *);
 	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
 	void (*started_request)(struct request *);