From: David Laight <david.laight.linux@gmail.com>
To: Pavel Begunkov <asml.silence@gmail.com>
Cc: "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,
"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: Re: [PATCH v3 02/10] iov_iter: add iterator type for dmabuf maps
Date: Wed, 13 May 2026 11:05:57 +0100 [thread overview]
Message-ID: <20260513110557.705bdeed@pumpkin> (raw)
In-Reply-To: <20a233d2f35274817aa643cc0fe113707eb47e72.1777475843.git.asml.silence@gmail.com>
On Wed, 29 Apr 2026 16:25:48 +0100
Pavel Begunkov <asml.silence@gmail.com> wrote:
> Introduce a new iterator type for dmabuf maps. The map in an opaque
> object with internals and format specific to the subsystem / driver, and
> only it can use that subsystem / driver for issuing IO. The task of the
> middle layers is to pass the map / iterator further down, maybe doing
> basic splitting and length checking. The iterator can only be used by
> operations of the file the associated map was created for.
>
> Suggested-by: Keith Busch <kbusch@kernel.org>
> Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
> ---
> include/linux/uio.h | 11 +++++++++++
> lib/iov_iter.c | 29 +++++++++++++++++++++++------
> 2 files changed, 34 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/uio.h b/include/linux/uio.h
> index a9bc5b3067e3..75051aed70de 100644
> --- a/include/linux/uio.h
> +++ b/include/linux/uio.h
> @@ -12,6 +12,7 @@
>
> struct page;
> struct folio_queue;
> +struct io_dmabuf_map;
>
> typedef unsigned int __bitwise iov_iter_extraction_t;
>
> @@ -29,6 +30,7 @@ enum iter_type {
> ITER_FOLIOQ,
> ITER_XARRAY,
> ITER_DISCARD,
> + ITER_DMABUF_MAP,
> };
>
> #define ITER_SOURCE 1 // == WRITE
> @@ -71,6 +73,7 @@ struct iov_iter {
> const struct folio_queue *folioq;
> struct xarray *xarray;
> void __user *ubuf;
> + struct io_dmabuf_map *dmabuf_map;
> };
> size_t count;
> };
> @@ -155,6 +158,11 @@ static inline bool iov_iter_is_xarray(const struct iov_iter *i)
> return iov_iter_type(i) == ITER_XARRAY;
> }
>
> +static inline bool iov_iter_is_dmabuf_map(const struct iov_iter *i)
> +{
> + return iov_iter_type(i) == ITER_DMABUF_MAP;
> +}
> +
> static inline unsigned char iov_iter_rw(const struct iov_iter *i)
> {
> return i->data_source ? WRITE : READ;
> @@ -300,6 +308,9 @@ void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction,
> unsigned int first_slot, unsigned int offset, size_t count);
> void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
> loff_t start, size_t count);
> +void iov_iter_dmabuf_map(struct iov_iter *i, unsigned int direction,
> + struct io_dmabuf_map *map,
> + loff_t off, size_t count);
> ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
> size_t maxsize, unsigned maxpages, size_t *start);
> ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
> diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> index 243662af1af7..e2253684b991 100644
> --- a/lib/iov_iter.c
> +++ b/lib/iov_iter.c
> @@ -575,7 +575,8 @@ void iov_iter_advance(struct iov_iter *i, size_t size)
> {
> if (unlikely(i->count < size))
> size = i->count;
> - if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) {
> + if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i)) ||
> + unlikely(iov_iter_is_dmabuf_map(i))) {
Doesn't the extra check add more code to all the non-ubuf cases?
This could be fixed by either making iter_type a bitmask (with one bit set)
or writing an iter_is_one_of(i, ITER_xxx, ITER_yyy) define that uses
'(1 << i->iter_type) & ((1 << ITER_xxx) | ...)'
(look at the the nolibc printf code for an example).
> i->iov_offset += size;
> i->count -= size;
> } else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) {
> @@ -631,7 +632,8 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
> return;
> }
> unroll -= i->iov_offset;
> - if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) {
> + if (iov_iter_is_xarray(i) || iter_is_ubuf(i) ||
iter_is_ubuf() should have been first here.
-- David
> + iov_iter_is_dmabuf_map(i)) {
> BUG(); /* We should never go beyond the start of the specified
> * range since we might then be straying into pages that
> * aren't pinned.
> @@ -775,6 +777,20 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
> }
> EXPORT_SYMBOL(iov_iter_xarray);
>
> +void iov_iter_dmabuf_map(struct iov_iter *i, unsigned int direction,
> + struct io_dmabuf_map *map,
> + loff_t off, size_t count)
> +{
> + WARN_ON(direction & ~(READ | WRITE));
> + *i = (struct iov_iter){
> + .iter_type = ITER_DMABUF_MAP,
> + .data_source = direction,
> + .dmabuf_map = map,
> + .count = count,
> + .iov_offset = off,
> + };
> +}
> +
> /**
> * iov_iter_discard - Initialise an I/O iterator that discards data
> * @i: The iterator to initialise.
> @@ -841,7 +857,7 @@ static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
>
> unsigned long iov_iter_alignment(const struct iov_iter *i)
> {
> - if (likely(iter_is_ubuf(i))) {
> + if (likely(iter_is_ubuf(i)) || iov_iter_is_dmabuf_map(i)) {
> size_t size = i->count;
> if (size)
> return ((unsigned long)i->ubuf + i->iov_offset) | size;
> @@ -872,7 +888,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
> size_t size = i->count;
> unsigned k;
>
> - if (iter_is_ubuf(i))
> + if (iter_is_ubuf(i) || iov_iter_is_dmabuf_map(i))
> return 0;
>
> if (WARN_ON(!iter_is_iovec(i)))
> @@ -1469,11 +1485,12 @@ EXPORT_SYMBOL_GPL(import_ubuf);
> void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
> {
> if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) &&
> - !iter_is_ubuf(i)) && !iov_iter_is_kvec(i))
> + !iter_is_ubuf(i) && !iov_iter_is_kvec(i) &&
> + !iov_iter_is_dmabuf_map(i)))
> return;
> i->iov_offset = state->iov_offset;
> i->count = state->count;
> - if (iter_is_ubuf(i))
> + if (iter_is_ubuf(i) || iov_iter_is_dmabuf_map(i))
> return;
> /*
> * For the *vec iters, nr_segs + iov is constant - if we increment
next prev parent reply other threads:[~2026-05-13 10:06 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-29 15:25 [PATCH v3 00/10] Add dmabuf read/write via io_uring Pavel Begunkov
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
2026-05-04 7:14 ` Christian König
2026-05-13 8:11 ` Christoph Hellwig
2026-04-29 15:25 ` [PATCH v3 02/10] iov_iter: add iterator type for " Pavel Begunkov
2026-05-13 8:11 ` Christoph Hellwig
2026-05-13 10:05 ` David Laight [this message]
2026-04-29 15:25 ` [PATCH v3 03/10] block: move bvec init into __bio_clone Pavel Begunkov
2026-05-13 8:12 ` Christoph Hellwig
2026-04-29 15:25 ` [PATCH v3 04/10] block: introduce dma map backed bio type Pavel Begunkov
2026-05-13 8:19 ` Christoph Hellwig
2026-05-13 8:39 ` Christoph Hellwig
2026-04-29 15:25 ` [PATCH v3 05/10] lib: add dmabuf token infrastructure Pavel Begunkov
2026-05-13 8:24 ` Christoph Hellwig
2026-04-29 15:25 ` [PATCH v3 06/10] block: forward create_dmabuf_token to drivers Pavel Begunkov
2026-05-13 8:25 ` Christoph Hellwig
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
2026-05-13 8:38 ` Christoph Hellwig
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
2026-05-04 15:29 ` [PATCH v3 00/10] Add dmabuf read/write via io_uring Ming Lei
2026-05-06 9:02 ` Pavel Begunkov
2026-05-07 9:50 ` Ming Lei
2026-05-12 9:30 ` Pavel Begunkov
2026-05-12 7:00 ` Christoph Hellwig
2026-05-12 9:30 ` 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=20260513110557.705bdeed@pumpkin \
--to=david.laight.linux@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=anuj20.g@samsung.com \
--cc=asml.silence@gmail.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