From: "zhaoyifan (H)" <zhaoyifan28@huawei.com>
To: Christoph Hellwig <hch@lst.de>,
Christian Brauner <brauner@kernel.org>,
"Darrick J. Wong" <djwong@kernel.org>
Cc: Kelu Ye <yekelu1@huawei.com>,
Ritesh Harjani <ritesh.list@gmail.com>,
Joanne Koong <joannelkoong@gmail.com>,
Namjae Jeon <linkinjeon@kernel.org>,
Sungjong Seo <sj1557.seo@samsung.com>,
Hyunchul Lee <hyc.lee@gmail.com>,
Konstantin Komarov <almaz.alexandrovich@paragon-software.com>,
Miklos Szeredi <miklos@szeredi.hu>, <fuse-devel@lists.linux.dev>,
<ntfs3@lists.linux.dev>, <linux-erofs@lists.ozlabs.org>,
<linux-xfs@vger.kernel.org>, <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 2/2] iomap: submit read bio after each extent
Date: Wed, 24 Jun 2026 15:42:29 +0800 [thread overview]
Message-ID: <02ca0fdf-590a-42da-a0a2-828dac464a2b@huawei.com> (raw)
In-Reply-To: <20260623135208.1812933-3-hch@lst.de>
The issue where EROFS could merge bios across devices when using iomap
API no longer exists.
Tested-by: Yifan Zhao <zhaoyifan28@huawei.com>
On 2026/6/23 21:51, Christoph Hellwig wrote:
> Currently the iomap buffered read path tries to build up read context
> (i.e. bios for the typical block based case) over multiple iomaps as
> long as the sector matches. This does not take into account files
> that can map to multiple different devices. While this could be fixed
> by a bdev check in iomap_bio_read_folio_range, the building up of I/O
> over iomaps actually was a problem for the not yet merged ext2 iomap
> port, as that does want to send out I/O at the end of an indirect
> block mapped range.
>
> So instead of adding more checks move over to a model where a bio only
> spans a single iomap. Change ->submit_read to be called after each
> iteration, and pass a force argument to indicate that the bio must
> be submitted set on the last iteration. Switch the bio based users
> to always submit, while keeping the single submit for fuse.
>
> Fixes: dfeab2e95a75 ("erofs: add multiple device support")
> Reported-by: Kelu Ye <yekelu1@huawei.com>
> Reported-by: Yifan Zhao <zhaoyifan28@huawei.com>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/exfat/iomap.c | 4 ++--
> fs/fuse/file.c | 6 +++++-
> fs/iomap/bio.c | 11 +++++++----
> fs/iomap/buffered-io.c | 23 +++++++++++++++--------
> fs/ntfs/aops.c | 4 ++--
> fs/ntfs3/inode.c | 4 ++--
> fs/xfs/xfs_aops.c | 5 +++--
> include/linux/iomap.h | 5 +++--
> 8 files changed, 39 insertions(+), 23 deletions(-)
>
> diff --git a/fs/exfat/iomap.c b/fs/exfat/iomap.c
> index 190fc6471f84..58e25c4e8587 100644
> --- a/fs/exfat/iomap.c
> +++ b/fs/exfat/iomap.c
> @@ -251,9 +251,9 @@ static void exfat_iomap_read_end_io(struct bio *bio)
> }
>
> static void exfat_iomap_bio_submit_read(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx, bool force)
> {
> - iomap_bio_submit_read_endio(iter, ctx, exfat_iomap_read_end_io);
> + iomap_bio_submit_read_endio(iter, ctx, force, exfat_iomap_read_end_io);
> }
>
> const struct iomap_read_ops exfat_iomap_bio_read_ops = {
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index e052a0d44dee..6fa3b1f55c95 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -982,13 +982,17 @@ static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter,
> }
>
> static void fuse_iomap_submit_read(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx, bool force)
> {
> struct fuse_fill_read_data *data = ctx->read_ctx;
>
> + if (!force)
> + return;
> +
> if (data->ia)
> fuse_send_readpages(data->ia, data->file, data->nr_bytes,
> data->fc->async_read);
> + ctx->read_ctx = NULL;
> }
>
> static const struct iomap_read_ops fuse_iomap_read_ops = {
> diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c
> index 0f31e35567b4..f71aaaf60301 100644
> --- a/fs/iomap/bio.c
> +++ b/fs/iomap/bio.c
> @@ -79,7 +79,8 @@ u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend)
> }
>
> void iomap_bio_submit_read_endio(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx, bio_end_io_t end_io)
> + struct iomap_read_folio_ctx *ctx, bool force,
> + bio_end_io_t end_io)
> {
> struct bio *bio = ctx->read_ctx;
>
> @@ -87,13 +88,15 @@ void iomap_bio_submit_read_endio(const struct iomap_iter *iter,
> if (iter->iomap.flags & IOMAP_F_INTEGRITY)
> fs_bio_integrity_alloc(bio);
> submit_bio(bio);
> +
> + ctx->read_ctx = NULL;
> }
> EXPORT_SYMBOL_GPL(iomap_bio_submit_read_endio);
>
> static void iomap_bio_submit_read(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx, bool force)
> {
> - return iomap_bio_submit_read_endio(iter, ctx, iomap_read_end_io);
> + return iomap_bio_submit_read_endio(iter, ctx, force, iomap_read_end_io);
> }
>
> static struct bio_set *iomap_read_bio_set(struct iomap_read_folio_ctx *ctx)
> @@ -116,7 +119,7 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,
>
> /* Submit the existing range if there was one. */
> if (ctx->read_ctx)
> - ctx->ops->submit_read(iter, ctx);
> + ctx->ops->submit_read(iter, ctx, true);
>
> /* Same as readahead_gfp_mask: */
> if (ctx->rac)
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 8d4806dc46d4..06a216d37548 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -524,6 +524,13 @@ static void iomap_read_end(struct folio *folio, size_t bytes_submitted)
> }
> }
>
> +static void iomap_submit_read(struct iomap_iter *iter,
> + struct iomap_read_folio_ctx *ctx, bool force)
> +{
> + if (ctx->read_ctx && ctx->ops->submit_read)
> + ctx->ops->submit_read(iter, ctx, force);
> +}
> +
> static int iomap_read_folio_iter(struct iomap_iter *iter,
> struct iomap_read_folio_ctx *ctx, size_t *bytes_submitted)
> {
> @@ -642,12 +649,12 @@ void iomap_read_folio(const struct iomap_ops *ops,
> fsverity_readahead(ctx->vi, folio->index,
> folio_nr_pages(folio));
>
> - while ((ret = iomap_iter(&iter, ops)) > 0)
> + while ((ret = iomap_iter(&iter, ops)) > 0) {
> + iomap_submit_read(&iter, ctx, false);
> iter.status = iomap_read_folio_iter(&iter, ctx,
> &bytes_submitted);
> -
> - if (ctx->read_ctx && ctx->ops->submit_read)
> - ctx->ops->submit_read(&iter, ctx);
> + }
> + iomap_submit_read(&iter, ctx, true);
>
> if (ctx->cur_folio)
> iomap_read_end(ctx->cur_folio, bytes_submitted);
> @@ -718,12 +725,12 @@ void iomap_readahead(const struct iomap_ops *ops,
> fsverity_readahead(ctx->vi, readahead_index(rac),
> readahead_count(rac));
>
> - while (iomap_iter(&iter, ops) > 0)
> + while (iomap_iter(&iter, ops) > 0) {
> + iomap_submit_read(&iter, ctx, false);
> iter.status = iomap_readahead_iter(&iter, ctx,
> &cur_bytes_submitted);
> -
> - if (ctx->read_ctx && ctx->ops->submit_read)
> - ctx->ops->submit_read(&iter, ctx);
> + }
> + iomap_submit_read(&iter, ctx, true);
>
> if (ctx->cur_folio)
> iomap_read_end(ctx->cur_folio, cur_bytes_submitted);
> diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
> index f2bb56506046..c32ecc28cb52 100644
> --- a/fs/ntfs/aops.c
> +++ b/fs/ntfs/aops.c
> @@ -38,9 +38,9 @@ static void ntfs_iomap_read_end_io(struct bio *bio)
> }
>
> static void ntfs_iomap_bio_submit_read(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx, bool force)
> {
> - iomap_bio_submit_read_endio(iter, ctx, ntfs_iomap_read_end_io);
> + iomap_bio_submit_read_endio(iter, ctx, force, ntfs_iomap_read_end_io);
> }
>
> static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
> diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
> index f9600aba1548..110c9b8208e1 100644
> --- a/fs/ntfs3/inode.c
> +++ b/fs/ntfs3/inode.c
> @@ -607,9 +607,9 @@ static void ntfs_iomap_read_end_io(struct bio *bio)
> }
>
> static void ntfs_iomap_bio_submit_read(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx, bool force)
> {
> - iomap_bio_submit_read_endio(iter, ctx, ntfs_iomap_read_end_io);
> + iomap_bio_submit_read_endio(iter, ctx, force, ntfs_iomap_read_end_io);
> }
>
> static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 51293b6f331f..42ebb2265408 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -758,13 +758,14 @@ xfs_vm_bmap(
> static void
> xfs_bio_submit_read(
> const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx)
> + struct iomap_read_folio_ctx *ctx,
> + bool force)
> {
> struct bio *bio = ctx->read_ctx;
>
> /* defer read completions to the ioend workqueue */
> iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
> - iomap_bio_submit_read_endio(iter, ctx, xfs_end_bio);
> + iomap_bio_submit_read_endio(iter, ctx, force, xfs_end_bio);
> }
>
> static const struct iomap_read_ops xfs_iomap_read_ops = {
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 56b43d594e6e..266844b62372 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -528,7 +528,7 @@ struct iomap_read_ops {
> * This is optional.
> */
> void (*submit_read)(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx);
> + struct iomap_read_folio_ctx *ctx, bool force);
>
> /*
> * Optional, allows filesystem to specify own bio_set, so new bio's
> @@ -623,7 +623,8 @@ extern struct bio_set iomap_ioend_bioset;
> int iomap_bio_read_folio_range(const struct iomap_iter *iter,
> struct iomap_read_folio_ctx *ctx, size_t plen);
> void iomap_bio_submit_read_endio(const struct iomap_iter *iter,
> - struct iomap_read_folio_ctx *ctx, bio_end_io_t end_io);
> + struct iomap_read_folio_ctx *ctx, bool force,
> + bio_end_io_t end_io);
>
> extern const struct iomap_read_ops iomap_bio_read_ops;
>
next prev parent reply other threads:[~2026-06-24 7:42 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-23 13:51 don't build bios/contexts over multiple iomaps v2 Christoph Hellwig
2026-06-23 13:51 ` [PATCH 1/2] iomap: consolidate bio submission Christoph Hellwig
2026-06-23 17:04 ` Joanne Koong
2026-06-23 23:57 ` Namjae Jeon
2026-06-23 13:51 ` [PATCH 2/2] iomap: submit read bio after each extent Christoph Hellwig
2026-06-23 17:29 ` Joanne Koong
2026-06-24 7:34 ` Christoph Hellwig
2026-06-23 23:58 ` Namjae Jeon
2026-06-24 7:42 ` zhaoyifan (H) [this message]
-- strict thread matches above, loose matches on Subject: below --
2026-06-25 12:07 don't build bios/contexts over multiple iomaps v3 Christoph Hellwig
2026-06-25 12:07 ` [PATCH 2/2] iomap: submit read bio after each extent Christoph Hellwig
2026-06-25 17:47 ` Darrick J. Wong
2026-06-25 18:32 ` Joanne Koong
2026-06-26 4:33 ` Christoph Hellwig
2026-06-26 6:16 ` Christoph Hellwig
2026-06-26 6:20 ` Darrick J. Wong
2026-06-26 14:51 ` Joanne Koong
2026-06-26 4:31 ` Christoph Hellwig
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=02ca0fdf-590a-42da-a0a2-828dac464a2b@huawei.com \
--to=zhaoyifan28@huawei.com \
--cc=almaz.alexandrovich@paragon-software.com \
--cc=brauner@kernel.org \
--cc=djwong@kernel.org \
--cc=fuse-devel@lists.linux.dev \
--cc=hch@lst.de \
--cc=hyc.lee@gmail.com \
--cc=joannelkoong@gmail.com \
--cc=linkinjeon@kernel.org \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=ntfs3@lists.linux.dev \
--cc=ritesh.list@gmail.com \
--cc=sj1557.seo@samsung.com \
--cc=yekelu1@huawei.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