From: Caleb Sander Mateos <csander@purestorage.com>
To: Jens Axboe <axboe@kernel.dk>, Miklos Szeredi <miklos@szeredi.hu>,
Ming Lei <ming.lei@redhat.com>, Keith Busch <kbusch@kernel.org>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Chris Mason <clm@fb.com>, David Sterba <dsterba@suse.com>
Cc: io-uring@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
linux-btrfs@vger.kernel.org, linux-kernel@vger.kernel.org,
Caleb Sander Mateos <csander@purestorage.com>
Subject: [PATCH v4 0/3] io_uring/uring_cmd: avoid double indirect call in task work dispatch
Date: Fri, 31 Oct 2025 14:34:27 -0600 [thread overview]
Message-ID: <20251031203430.3886957-1-csander@purestorage.com> (raw)
Define uring_cmd implementation callback functions to have the
io_req_tw_func_t signature to avoid the additional indirect call and
save 8 bytes in struct io_uring_cmd.
v4:
- Rebase on "io_uring: unify task_work cancelation checks"
- Small cleanup in io_fallback_req_func()
- Avoid intermediate variables where IO_URING_CMD_TASK_WORK_ISSUE_FLAG
is only used once (Christoph)
v3:
- Hide io_kiocb from uring_cmd implementations
- Label the 8 reserved bytes in struct io_uring_cmd (Ming)
v2:
- Define the uring_cmd callbacks with the io_req_tw_func_t signature
to avoid the macro defining a hidden wrapper function (Christoph)
Caleb Sander Mateos (3):
io_uring: only call io_should_terminate_tw() once for ctx
io_uring: add wrapper type for io_req_tw_func_t arg
io_uring/uring_cmd: avoid double indirect call in task work dispatch
block/ioctl.c | 6 ++++--
drivers/block/ublk_drv.c | 18 ++++++++++--------
drivers/nvme/host/ioctl.c | 7 ++++---
fs/btrfs/ioctl.c | 5 +++--
fs/fuse/dev_uring.c | 7 ++++---
include/linux/io_uring/cmd.h | 22 +++++++++++++---------
include/linux/io_uring_types.h | 7 +++++--
io_uring/futex.c | 16 +++++++++-------
io_uring/io_uring.c | 26 ++++++++++++++------------
io_uring/io_uring.h | 4 ++--
io_uring/msg_ring.c | 3 ++-
io_uring/notif.c | 5 +++--
io_uring/poll.c | 11 ++++++-----
io_uring/poll.h | 2 +-
io_uring/rw.c | 5 +++--
io_uring/rw.h | 2 +-
io_uring/timeout.c | 18 +++++++++++-------
io_uring/uring_cmd.c | 17 ++---------------
io_uring/waitid.c | 7 ++++---
19 files changed, 101 insertions(+), 87 deletions(-)
--
2.45.2
next reply other threads:[~2025-10-31 20:34 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-31 20:34 Caleb Sander Mateos [this message]
2025-10-31 20:34 ` [PATCH v4 1/3] io_uring: only call io_should_terminate_tw() once for ctx Caleb Sander Mateos
2025-10-31 20:34 ` [PATCH v4 2/3] io_uring: add wrapper type for io_req_tw_func_t arg Caleb Sander Mateos
2025-10-31 20:34 ` [PATCH v4 3/3] io_uring/uring_cmd: avoid double indirect call in task work dispatch Caleb Sander Mateos
2025-11-03 11:41 ` Christoph Hellwig
2025-11-03 15:31 ` [PATCH v4 0/3] " 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=20251031203430.3886957-1-csander@purestorage.com \
--to=csander@purestorage.com \
--cc=axboe@kernel.dk \
--cc=clm@fb.com \
--cc=dsterba@suse.com \
--cc=hch@lst.de \
--cc=io-uring@vger.kernel.org \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=miklos@szeredi.hu \
--cc=ming.lei@redhat.com \
--cc=sagi@grimberg.me \
/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;
as well as URLs for NNTP newsgroup(s).