linux-kernel - [PATCH 2/7] block: align the bio after building it

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250801234736.1913170-3-kbusch@meta.com>
Date: Fri, 1 Aug 2025 16:47:31 -0700
From: Keith Busch <kbusch@...a.com>
To: <linux-block@...r.kernel.org>, <linux-fsdevel@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>
CC: <snitzer@...nel.org>, <axboe@...nel.dk>, <dw@...idwei.uk>,
        <brauner@...nel.org>, Keith Busch <kbusch@...nel.org>
Subject: [PATCH 2/7] block: align the bio after building it

From: Keith Busch <kbusch@...nel.org>

Ensure the entire size is aligned after it's built instead of ensuring
each vector is block size aligned while constructing it. This makes it
more flexible to accepting device valid vectors that would otherwise get
rejected by overzealous alignment checks.

Signed-off-by: Keith Busch <kbusch@...nel.org>
---
 block/bio.c | 58 +++++++++++++++++++++++++++++++++++------------------
 1 file changed, 39 insertions(+), 19 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 92c512e876c8d..c050903e1be0c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1227,13 +1227,6 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
 		extraction_flags |= ITER_ALLOW_P2PDMA;
 
-	/*
-	 * Each segment in the iov is required to be a block size multiple.
-	 * However, we may not be able to get the entire segment if it spans
-	 * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the
-	 * result to ensure the bio's total size is correct. The remainder of
-	 * the iov data will be picked up in the next bio iteration.
-	 */
 	size = iov_iter_extract_pages(iter, &pages,
 				      UINT_MAX - bio->bi_iter.bi_size,
 				      nr_pages, extraction_flags, &offset);
@@ -1241,18 +1234,6 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return size ? size : -EFAULT;
 
 	nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
-
-	if (bio->bi_bdev) {
-		size_t trim = size & (bdev_logical_block_size(bio->bi_bdev) - 1);
-		iov_iter_revert(iter, trim);
-		size -= trim;
-	}
-
-	if (unlikely(!size)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	for (left = size, i = 0; left > 0; left -= len, i += num_pages) {
 		struct page *page = pages[i];
 		struct folio *folio = page_folio(page);
@@ -1297,6 +1278,44 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	return ret;
 }
 
+static inline void bio_revert(struct bio *bio, unsigned int nbytes)
+{
+	bio->bi_iter.bi_size -= nbytes;
+
+	while (nbytes) {
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (nbytes < bv->bv_len) {
+			bv->bv_len -= nbytes;
+			return;
+		}
+
+		bio_release_page(bio, bv->bv_page);
+		bio->bi_vcnt--;
+		nbytes -= bv->bv_len;
+       }
+}
+
+static int bio_align_to_lbs(struct bio *bio, struct iov_iter *iter)
+{
+	struct block_device *bdev = bio->bi_bdev;
+	size_t nbytes;
+
+	if (!bdev)
+		return 0;
+
+	nbytes = bio->bi_iter.bi_size & (bdev_logical_block_size(bdev) - 1);
+	if (!nbytes)
+		return 0;
+
+	bio_revert(bio, nbytes);
+	iov_iter_revert(iter, nbytes);
+	if (!bio->bi_iter.bi_size)
+		return -EFAULT;
+
+	return 0;
+}
+
 /**
  * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
@@ -1336,6 +1355,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
+	ret = bio_align_to_lbs(bio, iter);
 	return bio->bi_vcnt ? 0 : ret;
 }
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
-- 
2.47.3