From: Caleb Sander Mateos <csander@purestorage.com>
To: Ming Lei <ming.lei@redhat.com>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org,
Caleb Sander Mateos <csander@purestorage.com>
Subject: [PATCH v2 12/14] ublk: optimize UBLK_IO_UNREGISTER_IO_BUF on daemon task
Date: Fri, 20 Jun 2025 09:10:06 -0600 [thread overview]
Message-ID: <20250620151008.3976463-13-csander@purestorage.com> (raw)
In-Reply-To: <20250620151008.3976463-1-csander@purestorage.com>
ublk_io_release() performs an expensive atomic refcount decrement. This
atomic operation is unnecessary in the common case where the request's
buffer is registered and unregistered on the daemon task before handling
UBLK_IO_COMMIT_AND_FETCH_REQ for the I/O. So if ublk_io_release() is
called on the daemon task and task_registered_buffers is positive, just
decrement task_registered_buffers (nonatomically). ublk_sub_req_ref()
will apply this decrement when it atomically subtracts from io->ref.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
---
drivers/block/ublk_drv.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index b2925e15279a..199028f36ec8 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2012,11 +2012,18 @@ static void ublk_io_release(void *priv)
{
struct request *rq = priv;
struct ublk_queue *ubq = rq->mq_hctx->driver_data;
struct ublk_io *io = &ubq->ios[rq->tag];
- ublk_put_req_ref(ubq, io, rq);
+ /*
+ * task_registered_buffers may be 0 if buffers were registered off task
+ * but unregistered on task. Or after UBLK_IO_COMMIT_AND_FETCH_REQ.
+ */
+ if (current == io->task && io->task_registered_buffers)
+ io->task_registered_buffers--;
+ else
+ ublk_put_req_ref(ubq, io, rq);
}
static int ublk_register_io_buf(struct io_uring_cmd *cmd,
const struct ublk_queue *ubq,
struct ublk_io *io,
--
2.45.2
next prev parent reply other threads:[~2025-06-20 15:10 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-20 15:09 [PATCH v2 00/14] ublk: allow off-daemon zero-copy buffer registration Caleb Sander Mateos
2025-06-20 15:09 ` [PATCH v2 01/14] ublk: use vmalloc for ublk_device's __queues Caleb Sander Mateos
2025-06-23 7:20 ` Ming Lei
2025-06-20 15:09 ` [PATCH v2 02/14] ublk: remove struct ublk_rq_data Caleb Sander Mateos
2025-06-23 8:02 ` Ming Lei
2025-06-20 15:09 ` [PATCH v2 03/14] ublk: check cmd_op first Caleb Sander Mateos
2025-06-20 15:09 ` [PATCH v2 04/14] ublk: handle UBLK_IO_FETCH_REQ earlier Caleb Sander Mateos
2025-06-20 15:09 ` [PATCH v2 05/14] ublk: remove task variable from __ublk_ch_uring_cmd() Caleb Sander Mateos
2025-06-20 15:10 ` [PATCH v2 06/14] ublk: consolidate UBLK_IO_FLAG_{ACTIVE,OWNED_BY_SRV} checks Caleb Sander Mateos
2025-06-20 15:10 ` [PATCH v2 07/14] ublk: move ublk_prep_cancel() to case UBLK_IO_COMMIT_AND_FETCH_REQ Caleb Sander Mateos
2025-06-20 15:10 ` [PATCH v2 08/14] ublk: don't take ublk_queue in ublk_unregister_io_buf() Caleb Sander Mateos
2025-06-23 8:29 ` Ming Lei
2025-06-20 15:10 ` [PATCH v2 09/14] ublk: allow UBLK_IO_(UN)REGISTER_IO_BUF on any task Caleb Sander Mateos
2025-06-23 9:07 ` Ming Lei
2025-06-20 15:10 ` [PATCH v2 10/14] ublk: return early if blk_should_fake_timeout() Caleb Sander Mateos
2025-06-23 9:08 ` Ming Lei
2025-06-20 15:10 ` [PATCH v2 11/14] ublk: optimize UBLK_IO_REGISTER_IO_BUF on daemon task Caleb Sander Mateos
2025-06-23 9:44 ` Ming Lei
2025-06-20 15:10 ` Caleb Sander Mateos [this message]
2025-06-23 9:45 ` [PATCH v2 12/14] ublk: optimize UBLK_IO_UNREGISTER_IO_BUF " Ming Lei
2025-06-20 15:10 ` [PATCH v2 13/14] ublk: remove ubq checks from ublk_{get,put}_req_ref() Caleb Sander Mateos
2025-06-23 9:49 ` Ming Lei
2025-06-20 15:10 ` [PATCH v2 14/14] ublk: cache-align struct ublk_io Caleb Sander Mateos
2025-06-23 9:49 ` Ming Lei
2025-06-27 0:47 ` [PATCH v2 00/14] ublk: allow off-daemon zero-copy buffer registration Jens Axboe
2025-06-27 0:48 ` 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=20250620151008.3976463-13-csander@purestorage.com \
--to=csander@purestorage.com \
--cc=axboe@kernel.dk \
--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