From 226b4fc75c78f9c497c5182d939101b260cfb9f3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 25 Jul 2019 10:04:59 +0800 Subject: [PATCH] blk-mq: add callback of .cleanup_rq 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 Cc: Bart Van Assche Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Mike Snitzer Cc: dm-devel@redhat.com Cc: Fixes: 396eaf21ee17 ("blk-mq: improve DM's blk-mq IO merging via blk_insert_cloned_request feedback") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- drivers/md/dm-rq.c | 1 + include/linux/blk-mq.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index c9e44ac1f9a6..21d5c1784d0c 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -408,6 +408,7 @@ 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; return DM_MAPIO_REQUEUE; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1cdd2788cfa6..21cebe901ac0 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -140,6 +140,7 @@ typedef int (poll_fn)(struct blk_mq_hw_ctx *); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); +typedef void (cleanup_rq_fn)(struct request *); struct blk_mq_ops { @@ -200,6 +201,12 @@ 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; + /* * If set, returns whether or not this queue currently is busy */ @@ -367,4 +374,10 @@ static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, BLK_QC_T_INTERNAL; } +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