From: Christoph Hellwig <hch@lst.de>
To: Jens Axboe <axboe@kernel.dk>,
Christian Brauner <brauner@kernel.org>,
"Darrick J. Wong" <djwong@kernel.org>,
Carlos Maiolino <cem@kernel.org>
Cc: Tal Zussman <tz2294@columbia.edu>,
Anuj Gupta <anuj20.g@samsung.com>,
linux-block@vger.kernel.org, linux-xfs@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: [PATCH 11/17] iomap: better read bounce buffering support
Date: Mon, 31 Aug 2026 09:39:59 +0300 [thread overview]
Message-ID: <20260831064010.2574896-12-hch@lst.de> (raw)
In-Reply-To: <20260831064010.2574896-1-hch@lst.de>
Add helpers to bounce buffer an upper bio into one or more lower bios
using bounce buffers, and to copy the data back on completion.
Compared to the existing IOMAP_DIO_BOUNCE support for read bios, this
has two advantages: by removing the special bounce bio_vec it allows
to the full and "round" size of a single bio, i.e., 1MiB when using
4k pages. This is important for good performance on HDD. Additionally
it allows to bounce buffer a bio from completion conext, and thus
implement a "lazy" bounce buffering scheme, where the data is only
read into a bounce buffer after an initial checksum validation failure,
thus avoiding the bounce buffering I/O for most I/O.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
---
fs/iomap/ioend.c | 90 +++++++++++++++++++++++++++++++++++++++++++
include/linux/iomap.h | 5 +++
2 files changed, 95 insertions(+)
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 332dbfb2230f..ba97eec4ee2c 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -514,6 +514,96 @@ struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
}
EXPORT_SYMBOL_GPL(iomap_split_ioend);
+void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
+ void (*submit_ioend)(struct iomap_ioend *ioend))
+{
+ struct inode *inode = orig_ioend->io_inode;
+ struct bio *orig_bio = &orig_ioend->io_bio;
+ loff_t file_offset = orig_ioend->io_offset;
+ sector_t sector = orig_ioend->io_sector;
+ size_t total_len = round_up(orig_ioend->io_size, minsize);
+
+ WARN_ON_ONCE(!(orig_ioend->io_flags & IOMAP_IOEND_DIRECT));
+
+ /* We can't poll a bio that is not passed on to hardware */
+ orig_bio->bi_opf &= ~REQ_POLLED;
+
+ do {
+ struct iomap_ioend *ioend;
+ struct bio *bio;
+ int error;
+
+ bio = bio_alloc_bioset(orig_bio->bi_bdev,
+ min(total_len / minsize, BIO_MAX_VECS),
+ orig_bio->bi_opf, GFP_KERNEL,
+ &iomap_ioend_split_bioset);
+ error = bio_alloc_bounce_folios(bio, total_len, minsize);
+ if (error) {
+ bio_put(bio);
+ orig_bio->bi_status = errno_to_blk_status(error);
+ break;
+ }
+ bio->bi_ioprio = orig_bio->bi_ioprio;
+ bio->bi_write_hint = orig_bio->bi_write_hint;
+ bio->bi_write_stream = orig_bio->bi_write_stream;
+ bio->bi_iter.bi_sector = sector;
+
+ ioend = iomap_init_ioend(inode, bio, file_offset,
+ orig_ioend->io_flags);
+
+ total_len -= bio->bi_iter.bi_size;
+ file_offset += bio->bi_iter.bi_size;
+ sector += (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+
+ bio->bi_private = orig_bio;
+ bio_inc_remaining(orig_bio);
+ submit_ioend(ioend);
+ } while (total_len > 0);
+
+ bio_endio(&orig_ioend->io_bio);
+}
+EXPORT_SYMBOL_GPL(iomap_bounce_read);
+
+static void iomap_ioend_unbounce(struct iomap_ioend *orig_ioend,
+ struct iomap_ioend *ioend)
+{
+ struct bio *orig_bio = &orig_ioend->io_bio;
+ struct iov_iter to;
+ struct bio_vec *bv;
+ int i;
+
+ iov_iter_bvec(&to, ITER_DEST, orig_bio->bi_io_vec, orig_bio->bi_vcnt,
+ orig_ioend->io_size);
+ to.iov_offset = orig_ioend->io_bvec_offset;
+
+ if (ioend->io_offset != orig_ioend->io_offset) {
+ WARN_ON_ONCE(ioend->io_offset < orig_ioend->io_offset);
+ iov_iter_advance(&to, ioend->io_offset - orig_ioend->io_offset);
+ }
+
+ /* copying to pinned pages should always work */
+ bio_for_each_bvec_all(bv, &ioend->io_bio, i)
+ WARN_ON_ONCE(copy_to_iter(bvec_virt(bv), bv->bv_len, &to) !=
+ bv->bv_len);
+}
+
+void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
+ int error)
+{
+ if (error)
+ orig_bio->bi_status = errno_to_blk_status(error);
+ else
+ iomap_ioend_unbounce(iomap_ioend_from_bio(orig_bio), ioend);
+
+ bio_free_folios(&ioend->io_bio);
+ if (bio_integrity(&ioend->io_bio))
+ fs_bio_integrity_free(&ioend->io_bio);
+ bio_put(&ioend->io_bio);
+
+ bio_endio(orig_bio);
+}
+EXPORT_SYMBOL_GPL(iomap_bounce_read_end_io);
+
static int __init iomap_ioend_init(void)
{
const unsigned int nr_mempool_entries = 4 * (PAGE_SIZE / SECTOR_SIZE);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index bffdc217ad85..fbe051f0b032 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -607,6 +607,11 @@ void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
int iomap_writepages(struct iomap_writepage_ctx *wpc);
+void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
+ void (*submit_ioend)(struct iomap_ioend *ioend));
+void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
+ int error);
+
struct iomap_read_folio_ctx {
const struct iomap_read_ops *ops;
struct folio *cur_folio;
--
2.53.0
next prev parent reply other threads:[~2026-08-31 6:41 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-31 6:39 lazy bounce buffering for checksummed reads V2 Christoph Hellwig
2026-08-31 6:39 ` [PATCH 01/17] block: pass a maxlen argument to bio_iov_iter_get_pages Christoph Hellwig
2026-08-31 18:04 ` Darrick J. Wong
2026-08-31 6:39 ` [PATCH 02/17] block: warn on too larger integrity allocations Christoph Hellwig
2026-08-31 18:01 ` Darrick J. Wong
2026-09-01 8:12 ` Christoph Hellwig
2026-08-31 6:39 ` [PATCH 03/17] block: split bio_iov_iter_bounce_write Christoph Hellwig
2026-08-31 17:58 ` Darrick J. Wong
2026-08-31 6:39 ` [PATCH 04/17] block: export fs_bio_integrity_{alloc,free} Christoph Hellwig
2026-08-31 17:57 ` Darrick J. Wong
2026-08-31 6:39 ` [PATCH 05/17] iomap: respect maximum I/O size in iomap_dio_bio_iter_one Christoph Hellwig
2026-08-31 17:55 ` Darrick J. Wong
2026-08-31 6:39 ` [PATCH 06/17] iomap: add a iomap_ioend_flags helper Christoph Hellwig
2026-08-31 6:39 ` [PATCH 07/17] iomap: add a IOMAP_IOEND_INTEGRITY flag Christoph Hellwig
2026-08-31 6:39 ` [PATCH 08/17] iomap,xfs: move T10 PI handling for direct I/O into ->submit_io Christoph Hellwig
2026-08-31 6:39 ` [PATCH 09/17] xfs: move PI generation into xfs_submit_zoned_bio Christoph Hellwig
2026-08-31 17:53 ` Darrick J. Wong
2026-08-31 6:39 ` [PATCH 10/17] block,iomap: fix protection information verification with initial bvec offset Christoph Hellwig
2026-08-31 17:52 ` Darrick J. Wong
2026-09-01 8:12 ` Christoph Hellwig
2026-09-01 14:06 ` Darrick J. Wong
2026-08-31 6:39 ` Christoph Hellwig [this message]
2026-08-31 6:40 ` [PATCH 12/17] xfs: use BIO_COMPLETE_IN_TASK for bounce buffered read I/Os Christoph Hellwig
2026-08-31 6:40 ` [PATCH 13/17] iomap,xfs: move integrity verification to the file system Christoph Hellwig
2026-08-31 6:40 ` [PATCH 14/17] xfs: add support for lazy direct read bounce buffering Christoph Hellwig
2026-08-31 17:47 ` Darrick J. Wong
2026-09-02 18:24 ` Anuj Gupta
2026-08-31 6:40 ` [PATCH 15/17] xfs: add error injection for lazy " Christoph Hellwig
2026-09-02 18:26 ` Anuj Gupta
2026-08-31 6:40 ` [PATCH 16/17] xfs: log a message at mount time when using integrity protection Christoph Hellwig
2026-08-31 6:40 ` [PATCH 17/17] block,iomap: remove the old read side bounce buffering support 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=20260831064010.2574896-12-hch@lst.de \
--to=hch@lst.de \
--cc=anuj20.g@samsung.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=cem@kernel.org \
--cc=djwong@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=tz2294@columbia.edu \
/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).