From: Caleb Sander Mateos <csander@purestorage.com>
To: Jens Axboe <axboe@kernel.dk>,
Pavel Begunkov <asml.silence@gmail.com>,
Ming Lei <ming.lei@redhat.com>, Keith Busch <kbusch@kernel.org>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>
Cc: Xinyu Zhang <xizhang@purestorage.com>,
io-uring@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-nvme@lists.infradead.org,
Caleb Sander Mateos <csander@purestorage.com>
Subject: [PATCH 0/3] Consistently look up fixed buffers before going async
Date: Fri, 21 Mar 2025 12:48:16 -0600 [thread overview]
Message-ID: <20250321184819.3847386-1-csander@purestorage.com> (raw)
To use ublk zero copy, an application submits a sequence of io_uring
operations:
(1) Register a ublk request's buffer into the fixed buffer table
(2) Use the fixed buffer in some I/O operation
(3) Unregister the buffer from the fixed buffer table
The ordering of these operations is critical; if the fixed buffer lookup
occurs before the register or after the unregister operation, the I/O
will fail with EFAULT or even corrupt a different ublk request's buffer.
It is possible to guarantee the correct order by linking the operations,
but that adds overhead and doesn't allow multiple I/O operations to
execute in parallel using the same ublk request's buffer. Ideally, the
application could just submit the register, I/O, and unregister SQEs in
the desired order without links and io_uring would ensure the ordering.
This mostly works, leveraging the fact that each io_uring SQE is prepped
and issued non-blocking in order (barring link, drain, and force-async
flags). But it requires the fixed buffer lookup to occur during the
initial non-blocking issue.
This patch series fixes the 2 gaps where the initial issue can return
EAGAIN before looking up the fixed buffer:
- IORING_OP_SEND_ZC using IORING_RECVSEND_POLL_FIRST
- IORING_OP_URING_CMD, of which NVMe passthru is currently the only
fixed buffer user. blk_mq_alloc_request() can return EAGAIN before
io_uring_cmd_import_fixed() is called to look up the fixed buffer.
Caleb Sander Mateos (3):
io_uring/net: only import send_zc buffer once
io_uring/net: import send_zc fixed buffer before going async
io_uring/uring_cmd: import fixed buffer before going async
drivers/nvme/host/ioctl.c | 10 ++++------
include/linux/io_uring/cmd.h | 6 ++----
io_uring/net.c | 13 ++++++++-----
io_uring/rsrc.c | 6 ++++++
io_uring/rsrc.h | 2 ++
io_uring/uring_cmd.c | 10 +++++++---
6 files changed, 29 insertions(+), 18 deletions(-)
--
2.45.2
next reply other threads:[~2025-03-21 18:48 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-21 18:48 Caleb Sander Mateos [this message]
2025-03-21 18:48 ` [PATCH 1/3] io_uring/net: only import send_zc buffer once Caleb Sander Mateos
2025-03-21 20:38 ` Pavel Begunkov
2025-03-21 20:44 ` Caleb Sander Mateos
2025-03-21 18:48 ` [PATCH 2/3] io_uring/net: import send_zc fixed buffer before going async Caleb Sander Mateos
2025-03-21 18:48 ` [PATCH 3/3] io_uring/uring_cmd: import " Caleb Sander Mateos
2025-03-21 20:35 ` Pavel Begunkov
2025-03-21 21:38 ` Caleb Sander Mateos
2025-03-22 12:18 ` Pavel Begunkov
2025-03-21 19:53 ` [PATCH 0/3] Consistently look up fixed buffers " Jens Axboe
2025-03-21 20:24 ` Pavel Begunkov
2025-03-21 21:24 ` Caleb Sander Mateos
2025-03-22 12:33 ` Pavel Begunkov
2025-03-22 7:42 ` Ming Lei
2025-03-22 7:33 ` Ming Lei
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=20250321184819.3847386-1-csander@purestorage.com \
--to=csander@purestorage.com \
--cc=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=io-uring@vger.kernel.org \
--cc=kbusch@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=ming.lei@redhat.com \
--cc=sagi@grimberg.me \
--cc=xizhang@purestorage.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