From: Pavel Begunkov <asml.silence@gmail.com>
To: "Jens Axboe" <axboe@kernel.dk>, "Keith Busch" <kbusch@kernel.org>,
"Christoph Hellwig" <hch@lst.de>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Alexander Viro" <viro@zeniv.linux.org.uk>,
"Christian Brauner" <brauner@kernel.org>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Sumit Semwal" <sumit.semwal@linaro.org>,
"Christian König" <christian.koenig@amd.com>,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org,
io-uring@vger.kernel.org, linux-media@vger.kernel.org,
dri-devel@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org
Cc: asml.silence@gmail.com, Nitesh Shetty <nj.shetty@samsung.com>,
Kanchan Joshi <joshi.k@samsung.com>,
Anuj Gupta <anuj20.g@samsung.com>,
Tushar Gohad <tushar.gohad@intel.com>,
William Power <william.power@intel.com>,
Phil Cayton <phil.cayton@intel.com>,
Jason Gunthorpe <jgg@nvidia.com>
Subject: [PATCH v3 00/10] Add dmabuf read/write via io_uring
Date: Wed, 29 Apr 2026 16:25:46 +0100 [thread overview]
Message-ID: <cover.1777475843.git.asml.silence@gmail.com> (raw)
The patch set allows to register a dmabuf to an io_uring instance for
a specified file and use it with io_uring read / write requests. The
infrastructure is not tied to io_uring and there could be more users
in the future. A similar idea was attempted some years ago by Keith [1],
from where I borrowed a good number of changes, and later was brough up
by Tushar and Vishal from Intel.
It's an opt-in feature for files, and they need to implement a new
file operation to use it. Only NVMe block devices are supported in this
series. The user API is built on top of io_uring's "registered buffers",
where a dmabuf is registered in a special way, but after it can be used
as any other "registered buffer" with IORING_OP_{READ,WRITE}_FIXED
requests. It's created via a new file operation and the resulted map is
then passed through the I/O stack in a new iterator type. There is some
additional infrastructure to bind it all, which also counts requests
using a dmabuf map and managing lifetimes, which is used to implement
map invalidation.
It was tested for GPU <-> NVMe transfers. Also, as it maintains a
long-term dma mapping, it helps with the IOMMU cost. The numbers
below are for udmabuf reads previously run by Anuj for different
IOMMU modes:
- STRICT: before = 570 KIOPS, after = 5.01 MIOPS
- LAZY: before = 1.93 MIOPS, after = 5.01 MIOPS
- PASSTHROUGH: before = 5.01 MIOPS, after = 5.01 MIOPS
There are some liburing tests that can serve as an example:
git: https://github.com/isilence/liburing.git rw-dmabuf-tests-v3
url: https://github.com/isilence/liburing/tree/rw-dmabuf-tests-v3
[1] https://lore.kernel.org/io-uring/20220805162444.3985535-1-kbusch@fb.com/
v3: - Rework io_uring registration
- Move token/map infrastructure code out of blk-mq
- Simplify callbacks: remove a separate blk-mq table, which was
mostly just forwarding calls (to nvme).
- Don't skip dma sync depending on request direction
- Fix a couple of hangs
- Rename s/dma/dmabuf/
- Other small changes
v2: - Don't pass raw dma addresses, wrap it into a driver specific object
- Split into two objects: token and map
- Implement move_notify
Pavel Begunkov (10):
file: add callback for creating long-term dmabuf maps
iov_iter: add iterator type for dmabuf maps
block: move bvec init into __bio_clone
block: introduce dma map backed bio type
lib: add dmabuf token infrastructure
block: forward create_dmabuf_token to drivers
nvme-pci: implement dma_token backed requests
io_uring/rsrc: introduce buf registration structure
io_uring/rsrc: extend buffer update
io_uring/rsrc: add dmabuf backed registered buffers
block/bio.c | 28 +++-
block/blk-merge.c | 14 ++
block/blk.h | 3 +-
block/fops.c | 16 ++
drivers/nvme/host/pci.c | 282 ++++++++++++++++++++++++++++++++
include/linux/bio.h | 19 ++-
include/linux/blk-mq.h | 9 +
include/linux/blk_types.h | 8 +-
include/linux/fs.h | 2 +
include/linux/io_dmabuf_token.h | 92 +++++++++++
include/linux/io_uring_types.h | 5 +
include/linux/uio.h | 11 ++
include/uapi/linux/io_uring.h | 31 +++-
io_uring/io_uring.c | 3 +-
io_uring/rsrc.c | 266 +++++++++++++++++++++++++-----
io_uring/rsrc.h | 30 +++-
io_uring/rw.c | 4 +-
lib/Kconfig | 4 +
lib/Makefile | 2 +
lib/io_dmabuf_token.c | 272 ++++++++++++++++++++++++++++++
lib/iov_iter.c | 29 +++-
21 files changed, 1071 insertions(+), 59 deletions(-)
create mode 100644 include/linux/io_dmabuf_token.h
create mode 100644 lib/io_dmabuf_token.c
--
2.53.0
next reply other threads:[~2026-04-29 15:26 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-29 15:25 Pavel Begunkov [this message]
2026-04-29 15:25 ` [PATCH v3 01/10] file: add callback for creating long-term dmabuf maps Pavel Begunkov
2026-04-30 6:03 ` Christian König
2026-04-30 18:33 ` Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 02/10] iov_iter: add iterator type for " Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 03/10] block: move bvec init into __bio_clone Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 04/10] block: introduce dma map backed bio type Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 05/10] lib: add dmabuf token infrastructure Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 06/10] block: forward create_dmabuf_token to drivers Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 07/10] nvme-pci: implement dma_token backed requests Pavel Begunkov
2026-04-29 15:29 ` Pavel Begunkov
2026-04-29 16:07 ` Maurizio Lombardi
2026-04-30 18:18 ` Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 08/10] io_uring/rsrc: introduce buf registration structure Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 09/10] io_uring/rsrc: extend buffer update Pavel Begunkov
2026-04-29 15:25 ` [PATCH v3 10/10] io_uring/rsrc: add dmabuf backed registered buffers Pavel Begunkov
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=cover.1777475843.git.asml.silence@gmail.com \
--to=asml.silence@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=anuj20.g@samsung.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@lst.de \
--cc=io-uring@vger.kernel.org \
--cc=jgg@nvidia.com \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=linaro-mm-sig@lists.linaro.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-media@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=nj.shetty@samsung.com \
--cc=phil.cayton@intel.com \
--cc=sagi@grimberg.me \
--cc=sumit.semwal@linaro.org \
--cc=tushar.gohad@intel.com \
--cc=viro@zeniv.linux.org.uk \
--cc=william.power@intel.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