blk-mq: make sure elevator callbacks aren't called for passthrough request

In case of q->elevator, passthrough request can still be marked as
RQF_ELV, so some elevator callbacks will be called for them.

Fix this by splitting RQF_SCHED_TAGS, which is set for all requests that
are issued on a queue that uses an I/O scheduler, and RQF_USE_SCHED for
non-flush, non-passthrough requests on such a queue.

Roughly based on two different patches from
Ming Lei <ming.lei@redhat.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230518053101.760632-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

5 files changed, 44 insertions, 36 deletions

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index ae1b3080b62b..22e39b9a77ec 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -249,6 +249,8 @@ static const char *const rqf_name[] = {
 	RQF_NAME(MIXED_MERGE),
 	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
+	RQF_NAME(SCHED_TAGS),
+	RQF_NAME(USE_SCHED),
 	RQF_NAME(FAILED),
 	RQF_NAME(QUIET),
 	RQF_NAME(IO_STAT),
@@ -258,7 +260,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(TIMED_OUT),
-	RQF_NAME(ELV),
 	RQF_NAME(RESV),
 };
 #undef RQF_NAME
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 4d8d2cd3b473..1326526bb733 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -37,7 +37,7 @@ static inline bool
 blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 			 struct bio *bio)
 {
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = q->elevator;
 
 		if (e->type->ops.allow_merge)
@@ -48,7 +48,7 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 
 static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
 {
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = rq->q->elevator;
 
 		if (e->type->ops.completed_request)
@@ -58,7 +58,7 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
 
 static inline void blk_mq_sched_requeue_request(struct request *rq)
 {
-	if ((rq->rq_flags & RQF_ELV) && !op_is_flush(rq->cmd_flags)) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct request_queue *q = rq->q;
 		struct elevator_queue *e = q->elevator;
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7470c6636dc4..e021740154fe 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -354,12 +354,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		data->rq_flags |= RQF_IO_STAT;
 	rq->rq_flags = data->rq_flags;
 
-	if (!(data->rq_flags & RQF_ELV)) {
-		rq->tag = tag;
-		rq->internal_tag = BLK_MQ_NO_TAG;
-	} else {
+	if (data->rq_flags & RQF_SCHED_TAGS) {
 		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
+	} else {
+		rq->tag = tag;
+		rq->internal_tag = BLK_MQ_NO_TAG;
 	}
 	rq->timeout = 0;
 
@@ -386,14 +386,13 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	WRITE_ONCE(rq->deadline, 0);
 	req_ref_set(rq, 1);
 
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = data->q->elevator;
 
 		INIT_HLIST_NODE(&rq->hash);
 		RB_CLEAR_NODE(&rq->rb_node);
 
-		if (!op_is_flush(data->cmd_flags) &&
-		    e->type->ops.prepare_request)
+		if (e->type->ops.prepare_request)
 			e->type->ops.prepare_request(rq);
 	}
 
@@ -447,26 +446,32 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (q->elevator) {
-		struct elevator_queue *e = q->elevator;
-
-		data->rq_flags |= RQF_ELV;
+		/*
+		 * All requests use scheduler tags when an I/O scheduler is
+		 * enabled for the queue.
+		 */
+		data->rq_flags |= RQF_SCHED_TAGS;
 
 		/*
 		 * Flush/passthrough requests are special and go directly to the
-		 * dispatch list. Don't include reserved tags in the
-		 * limiting, as it isn't useful.
+		 * dispatch list.
 		 */
 		if (!op_is_flush(data->cmd_flags) &&
-		    !blk_op_is_passthrough(data->cmd_flags) &&
-		    e->type->ops.limit_depth &&
-		    !(data->flags & BLK_MQ_REQ_RESERVED))
-			e->type->ops.limit_depth(data->cmd_flags, data);
+		    !blk_op_is_passthrough(data->cmd_flags)) {
+			struct elevator_mq_ops *ops = &q->elevator->type->ops;
+
+			WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED);
+
+			data->rq_flags |= RQF_USE_SCHED;
+			if (ops->limit_depth)
+				ops->limit_depth(data->cmd_flags, data);
+		}
 	}
 
 retry:
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!(data->rq_flags & RQF_ELV))
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
 		blk_mq_tag_busy(data->hctx);
 
 	if (data->flags & BLK_MQ_REQ_RESERVED)
@@ -646,10 +651,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		goto out_queue_exit;
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	if (!q->elevator)
-		blk_mq_tag_busy(data.hctx);
+	if (q->elevator)
+		data.rq_flags |= RQF_SCHED_TAGS;
 	else
-		data.rq_flags |= RQF_ELV;
+		blk_mq_tag_busy(data.hctx);
 
 	if (flags & BLK_MQ_REQ_RESERVED)
 		data.rq_flags |= RQF_RESV;
@@ -694,7 +699,7 @@ void blk_mq_free_request(struct request *rq)
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
-	if ((rq->rq_flags & RQF_ELV) && !op_is_flush(rq->cmd_flags) &&
+	if ((rq->rq_flags & RQF_USE_SCHED) &&
 	    q->elevator->type->ops.finish_request)
 		q->elevator->type->ops.finish_request(rq);
 
@@ -1268,7 +1273,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 
 	if (!plug->multiple_queues && last && last->q != rq->q)
 		plug->multiple_queues = true;
-	if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
+	if (!plug->has_elevator && (rq->rq_flags & RQF_USE_SCHED))
 		plug->has_elevator = true;
 	rq->rq_next = NULL;
 	rq_list_add(&plug->mq_list, rq);
@@ -2620,7 +2625,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		return;
 	}
 
-	if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) {
+	if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, false);
 		return;
@@ -2983,7 +2988,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	}
 
 	hctx = rq->mq_hctx;
-	if ((rq->rq_flags & RQF_ELV) ||
+	if ((rq->rq_flags & RQF_USE_SCHED) ||
 	    (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, true);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index e876584d3516..d15981db34b9 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -226,9 +226,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags)
 
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
-	if (!(data->rq_flags & RQF_ELV))
-		return data->hctx->tags;
-	return data->hctx->sched_tags;
+	if (data->rq_flags & RQF_SCHED_TAGS)
+		return data->hctx->sched_tags;
+	return data->hctx->tags;
 }
 
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 5529e7d28ae6..e4a211957db6 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -38,6 +38,10 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
 /* don't call prep for this one */
 #define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
+/* use hctx->sched_tags */
+#define RQF_SCHED_TAGS		((__force req_flags_t)(1 << 8))
+/* use an I/O scheduler for this request */
+#define RQF_USE_SCHED		((__force req_flags_t)(1 << 9))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
@@ -57,9 +61,7 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
 /* ->timeout has been called, don't expire again */
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
-/* queue has elevator attached */
-#define RQF_ELV			((__force req_flags_t)(1 << 22))
-#define RQF_RESV			((__force req_flags_t)(1 << 23))
+#define RQF_RESV		((__force req_flags_t)(1 << 23))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -842,7 +844,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
-	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
 static inline bool blk_mq_is_reserved_rq(struct request *rq)
@@ -858,7 +860,7 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 				       struct io_comp_batch *iob, int ioerror,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || ioerror ||
+	if (!iob || (req->rq_flags & RQF_USE_SCHED) || ioerror ||
 			(req->end_io && !blk_rq_is_passthrough(req)))
 		return false;