Linux block layer
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	Bart Van Assche <bvanassche@acm.org>,
	Damien Le Moal <dlemoal@kernel.org>,
	Hannes Reinecke <hare@suse.de>, Ming Lei <ming.lei@redhat.com>
Subject: [PATCH v6 08/11] block: mq-deadline: Reduce lock contention
Date: Wed, 17 May 2023 10:42:26 -0700	[thread overview]
Message-ID: <20230517174230.897144-9-bvanassche@acm.org> (raw)
In-Reply-To: <20230517174230.897144-1-bvanassche@acm.org>

blk_mq_free_requests() calls dd_finish_request() indirectly. Prevent
nested locking of dd->lock and dd->zone_lock by moving the code for
freeing requests.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 block/mq-deadline.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 56782ee93522..44222d18f6d4 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -757,7 +757,7 @@ static bool dd_bio_merge(struct request_queue *q, struct bio *bio,
  * add rq to rbtree and fifo
  */
 static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			      blk_insert_t flags)
+			      blk_insert_t flags, struct list_head *free)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
@@ -766,7 +766,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio);
 	struct dd_per_prio *per_prio;
 	enum dd_prio prio;
-	LIST_HEAD(free);
 
 	lockdep_assert_held(&dd->lock);
 
@@ -783,10 +782,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		rq->elv.priv[0] = (void *)(uintptr_t)1;
 	}
 
-	if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
-		blk_mq_free_requests(&free);
+	if (blk_mq_sched_try_insert_merge(q, rq, free))
 		return;
-	}
 
 	trace_block_rq_insert(rq);
 
@@ -819,6 +816,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
+	LIST_HEAD(free);
 
 	spin_lock(&dd->lock);
 	while (!list_empty(list)) {
@@ -826,9 +824,11 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		dd_insert_request(hctx, rq, flags);
+		dd_insert_request(hctx, rq, flags, &free);
 	}
 	spin_unlock(&dd->lock);
+
+	blk_mq_free_requests(&free);
 }
 
 /* Callback from inside blk_mq_rq_ctx_init(). */

  parent reply	other threads:[~2023-05-17 17:45 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-17 17:42 [PATCH v6 00/11] mq-deadline: Improve support for zoned block devices Bart Van Assche
2023-05-17 17:42 ` [PATCH v6 01/11] block: mq-deadline: Add a word in a source code comment Bart Van Assche
2023-05-18 23:11   ` Damien Le Moal
2023-05-18 23:20     ` Bart Van Assche
2023-05-18 23:39       ` Damien Le Moal
2023-05-17 17:42 ` [PATCH v6 02/11] block: Simplify blk_req_needs_zone_write_lock() Bart Van Assche
2023-05-17 17:42 ` [PATCH v6 03/11] block: Fix the type of the second bdev_op_is_zoned_write() argument Bart Van Assche
2023-05-17 17:42 ` [PATCH v6 04/11] block: Introduce op_needs_zoned_write_locking() Bart Van Assche
2023-05-18 23:12   ` Damien Le Moal
2023-05-17 17:42 ` [PATCH v6 05/11] block: Introduce blk_rq_is_seq_zoned_write() Bart Van Assche
2023-05-18 23:13   ` Damien Le Moal
2023-05-17 17:42 ` [PATCH v6 06/11] block: mq-deadline: Clean up deadline_check_fifo() Bart Van Assche
2023-05-18 23:14   ` Damien Le Moal
2023-05-17 17:42 ` [PATCH v6 07/11] block: mq-deadline: Simplify deadline_skip_seq_writes() Bart Van Assche
2023-05-17 17:42 ` Bart Van Assche [this message]
2023-05-17 17:42 ` [PATCH v6 09/11] block: mq-deadline: Track the dispatch position Bart Van Assche
2023-05-17 17:42 ` [PATCH v6 10/11] block: mq-deadline: Handle requeued requests correctly Bart Van Assche
2023-05-18 23:15   ` Damien Le Moal
2023-05-17 17:42 ` [PATCH v6 11/11] block: mq-deadline: Fix handling of at-head zoned writes Bart Van Assche
2023-05-19  1:50 ` [PATCH v6 00/11] mq-deadline: Improve support for zoned block devices Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230517174230.897144-9-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=axboe@kernel.dk \
    --cc=dlemoal@kernel.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=ming.lei@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox