blk-mq: use the I/O scheduler for writes from the flush state machine

Send write requests issued by the flush state machine through the normal
I/O submission path including the I/O scheduler (if present) so that I/O
scheduler policies are applied to writes with the FUA flag set.

Separate the I/O scheduler members from the flush members in struct
request since now a request may pass through both an I/O scheduler
and the flush machinery.

Note that the actual flush requests, which have no bio attached to the
request still bypass the I/O schedulers.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
[hch: rebased]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20230519044050.107790-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 13 insertions, 18 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c0b394096b6b..aac67bc3d368 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -458,7 +458,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		 * Flush/passthrough requests are special and go directly to the
 		 * dispatch list.
 		 */
-		if (!op_is_flush(data->cmd_flags) &&
+		if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH &&
 		    !blk_op_is_passthrough(data->cmd_flags)) {
 			struct elevator_mq_ops *ops = &q->elevator->type->ops;
 
@@ -2497,7 +2497,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
 		 * dispatch it given we prioritize requests in hctx->dispatch.
 		 */
 		blk_mq_request_bypass_insert(rq, flags);
-	} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
+	} else if (req_op(rq) == REQ_OP_FLUSH) {
 		/*
 		 * Firstly normal IO request is inserted to scheduler queue or
 		 * sw queue, meantime we add flush request to dispatch queue(
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 49d14b1acfa5..935201c89743 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -169,25 +169,20 @@ struct request {
 		void *completion_data;
 	};
 
-
 	/*
 	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.  Flush requests are
-	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the elevator data.
+	 * more they have to dynamically allocate it.
 	 */
-	union {
-		struct {
-			struct io_cq		*icq;
-			void			*priv[2];
-		} elv;
-
-		struct {
-			unsigned int		seq;
-			struct list_head	list;
-			rq_end_io_fn		*saved_end_io;
-		} flush;
-	};
+	struct {
+		struct io_cq		*icq;
+		void			*priv[2];
+	} elv;
+
+	struct {
+		unsigned int		seq;
+		struct list_head	list;
+		rq_end_io_fn		*saved_end_io;
+	} flush;
 
 	union {
 		struct __call_single_data csd;