blk-mq-sched: make completed_request() callback more useful

Currently, this callback is called right after put_request() and has no
distinguishable purpose. Instead, let's call it before put_request() as
soon as I/O has completed on the request, before we account it in
blk-stat. With this, Kyber can enable stats when it sees a latency
outlier and make sure the outlier gets accounted.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-mq-sched.h

@@ -82,17 +82,12 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 	return true;
 }
 
-static inline void
-blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static inline void blk_mq_sched_completed_request(struct request *rq)
 {
-	struct elevator_queue *e = hctx->queue->elevator;
+	struct elevator_queue *e = rq->q->elevator;
 
 	if (e && e->type->ops.mq.completed_request)
-		e->type->ops.mq.completed_request(hctx, rq);
-
-	BUG_ON(rq->internal_tag == -1);
-
-	blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+		e->type->ops.mq.completed_request(rq);
 }
 
 static inline void blk_mq_sched_started_request(struct request *rq)

block/blk-mq.c

@@ -350,7 +350,7 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	if (rq->tag != -1)
 		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
-		blk_mq_sched_completed_request(hctx, rq);
+		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
@@ -444,6 +444,9 @@ static void __blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	if (rq->internal_tag != -1)
+		blk_mq_sched_completed_request(rq);
+
 	blk_mq_stat_add(rq);
 
 	if (!q->softirq_done_fn)

include/linux/elevator.h

@@ -106,7 +106,7 @@ struct elevator_mq_ops {
 	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
 	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 (*completed_request)(struct request *);
 	void (*started_request)(struct request *);
 	void (*requeue_request)(struct request *);
 	struct request *(*former_request)(struct request_queue *, struct request *);