Linux block layer
 help / color / mirror / Atom feed
From: Tal Zussman <tz2294@columbia.edu>
To: Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
	Johannes Thumshirn <johannes.thumshirn@wdc.com>,
	Luis Chamberlain <mcgrof@kernel.org>,
	Hannes Reinecke <hare@suse.de>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	John Garry <john.g.garry@oracle.com>,
	Christian Brauner <brauner@kernel.org>,
	"Darrick J. Wong" <djwong@kernel.org>,
	Keith Busch <kbusch@kernel.org>,
	"Martin K. Petersen" <martin.petersen@oracle.com>
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	Tal Zussman <tz2294@columbia.edu>
Subject: [PATCH v2 6/7] block: unpin all pages of a bvec in bio_iov_iter_align_down()
Date: Fri, 28 Aug 2026 09:49:55 -0400	[thread overview]
Message-ID: <20260828-blkdev-fixes-v2-6-32f3f40cebed@columbia.edu> (raw)
In-Reply-To: <20260828-blkdev-fixes-v2-0-32f3f40cebed@columbia.edu>

bio_iov_iter_align_down() drops trailing bvecs with unpin_user_page(),
but a bvec built by iov_iter_extract_bvecs() can span several pages of
one folio, each with its own pin. All but the first pin leak.

The partially trimmed bvec has the same problem. Shrinking bv_len does
not release the pins for the pages cut off by the trim, and
__bio_release_pages() only unpins the pages bv_len still covers at
completion.

Both issues occur only with a logical block size above PAGE_SIZE and a
large folio backing the user buffer. On a device with a 64K logical
block size, an O_DIRECT pwritev() from a hugetlb mapping that ends 16K
past a block boundary leaks one huge page per call, whether the
remainder is its own bvec or the tail of a larger one.

Unpin all pages of a dropped bvec with unpin_user_folio(), as
__bio_release_pages() does, and unpin the pages trimmed off the last
bvec as well.

Fixes: 20a0e6276edb ("block: align the bio after building it")
Assisted-by: Claude:claude-fable-5
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
---
 block/bio.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index 898b2f5ef8c8..48fa6b9a6dba 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1196,6 +1196,11 @@ bool bio_iov_iter_set(struct bio *bio, const struct iov_iter *iter)
 	return true;
 }
 
+static unsigned int bvec_nr_pages(const struct bio_vec *bv)
+{
+	return DIV_ROUND_UP(bv->bv_offset + bv->bv_len, PAGE_SIZE);
+}
+
 /*
  * Aligns the bio size to the len_align_mask, releasing excessive bio vecs that
  * __bio_iov_iter_get_pages may have inserted, and reverts the trimmed length
@@ -1205,6 +1210,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 				   struct bio_vec *bv, unsigned len_align_mask)
 {
 	size_t nbytes = bio->bi_iter.bi_size & len_align_mask;
+	unsigned int npages;
 
 	if (!nbytes)
 		return 0;
@@ -1213,14 +1219,24 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 	bio->bi_iter.bi_size -= nbytes;
 	while (nbytes >= bv->bv_len) {
 		if (bio_flagged(bio, BIO_PAGE_PINNED))
-			unpin_user_page(bv->bv_page);
+			unpin_user_folio(bvec_folio(bv),
+					 bvec_nr_pages(bv));
 
 		if (!--bio->bi_vcnt)
 			return -EFAULT;
 		nbytes -= bv->bv_len;
 		bv--;
 	}
+
+	/*
+	 * __bio_release_pages() only unpins the pages still covered by
+	 * bv_len, so drop the pins for the pages trimmed off here.
+	 */
+	npages = bvec_nr_pages(bv);
 	bv->bv_len -= nbytes;
+	npages -= bvec_nr_pages(bv);
+	if (npages && bio_flagged(bio, BIO_PAGE_PINNED))
+		unpin_user_folio(bvec_folio(bv), npages);
 	return 0;
 }
 

-- 
2.39.5


  parent reply	other threads:[~2026-08-28 13:50 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-28 13:49 [PATCH v2 0/7] block device fixes for large block sizes, IOCB_NOWAIT, and direct I/O Tal Zussman
2026-08-28 13:49 ` [PATCH v2 1/7] block: use iomap_dirty_folio for block devices Tal Zussman
2026-08-28 13:49 ` [PATCH v2 2/7] block: take i_rwsem for the direct I/O write fallback Tal Zussman
2026-08-28 13:49 ` [PATCH v2 3/7] block: take i_rwsem for the splice read path Tal Zussman
2026-08-28 13:49 ` [PATCH v2 4/7] block: honor IOCB_NOWAIT in the block device buffered " Tal Zussman
2026-08-28 13:49 ` [PATCH v2 5/7] block: fail atomic writes instead of falling back to buffered I/O Tal Zussman
2026-08-28 13:49 ` Tal Zussman [this message]
2026-08-28 14:36   ` [PATCH v2 6/7] block: unpin all pages of a bvec in bio_iov_iter_align_down() Tal Zussman
2026-08-28 13:49 ` [PATCH v2 7/7] block: remove dead metadata handling from the async direct I/O path Tal Zussman
2026-08-28 15:32 ` [PATCH v2 0/7] block device fixes for large block sizes, IOCB_NOWAIT, and direct I/O Tal Zussman

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=20260828-blkdev-fixes-v2-6-32f3f40cebed@columbia.edu \
    --to=tz2294@columbia.edu \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=djwong@kernel.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=johannes.thumshirn@wdc.com \
    --cc=john.g.garry@oracle.com \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=mcgrof@kernel.org \
    --cc=willy@infradead.org \
    /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