blk-mq: add callback of .cleanup_rq

[ Upstream commit 226b4fc7 ]

SCSI maintains its own driver private data hooked off of each SCSI
request, and the pridate data won't be freed after scsi_queue_rq()
returns BLK_STS_RESOURCE or BLK_STS_DEV_RESOURCE. An upper layer driver
(e.g. dm-rq) may need to retry these SCSI requests, before SCSI has
fully dispatched them, due to a lower level SCSI driver's resource
limitation identified in scsi_queue_rq(). Currently SCSI's per-request
private data is leaked when the upper layer driver (dm-rq) frees and
then retries these requests in response to BLK_STS_RESOURCE or
BLK_STS_DEV_RESOURCE returns from scsi_queue_rq().

This usecase is so specialized that it doesn't warrant training an
existing blk-mq interface (e.g. blk_mq_free_request) to allow SCSI to
account for freeing its driver private data -- doing so would add an
extra branch for handling a special case that all other consumers of
SCSI (and blk-mq) won't ever need to worry about.

So the most pragmatic way forward is to delegate freeing SCSI driver
private data to the upper layer driver (dm-rq).  Do so by adding
new .cleanup_rq callback and calling a new blk_mq_cleanup_rq() method
from dm-rq.  A following commit will implement the .cleanup_rq() hook
in scsi_mq_ops.

Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: <stable@vger.kernel.org>
Fixes: 396eaf21 ("blk-mq: improve DM's blk-mq IO merging via blk_insert_cloned_request feedback")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/md/dm-rq.c

@@ -505,6 +505,7 @@ static int map_request(struct dm_rq_target_io *tio)
 		ret = dm_dispatch_clone_request(clone, rq);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
 			blk_rq_unprep_clone(clone);
+			blk_mq_cleanup_rq(clone);
 			tio->ti->type->release_clone_rq(clone, &tio->info);
 			tio->clone = NULL;
 			if (!rq->q->mq_ops)

include/linux/blk-mq.h

@@ -114,6 +114,7 @@ typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
 typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int);
 typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
+typedef void (cleanup_rq_fn)(struct request *);
 
 
 struct blk_mq_ops {
@@ -165,6 +166,12 @@ struct blk_mq_ops {
 	/* Called from inside blk_get_request() */
 	void (*initialize_rq_fn)(struct request *rq);
 
+	/*
+	 * Called before freeing one request which isn't completed yet,
+	 * and usually for freeing the driver private data
+	 */
+	cleanup_rq_fn		*cleanup_rq;
+
 	map_queues_fn		*map_queues;
 
 #ifdef CONFIG_BLK_DEBUG_FS
@@ -324,4 +331,10 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
 	     ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
 
+static inline void blk_mq_cleanup_rq(struct request *rq)
+{
+	if (rq->q->mq_ops->cleanup_rq)
+		rq->q->mq_ops->cleanup_rq(rq);
+}
+
 #endif