linux-ext4 - [PATCHv4 3/8] 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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <20250827141258.63501-4-kbusch@meta.com>
Date: Wed, 27 Aug 2025 07:12:53 -0700
From: Keith Busch <kbusch@...a.com>
To: <linux-block@...r.kernel.org>, <linux-fsdevel@...r.kernel.org>
CC: <linux-xfs@...r.kernel.org>, <linux-ext4@...r.kernel.org>, <hch@....de>,
        <axboe@...nel.dk>, Keith Busch <kbusch@...nel.org>
Subject: [PATCHv4 3/8] block: align the bio after building it

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

Instead of ensuring each vector is block size aligned while constructing
the bio, just ensure the entire size is aligned after it's built. This
makes getting bio pages more flexible to accepting device valid io
vectors that would otherwise get rejected by alignment checks.

Signed-off-by: Keith Busch <kbusch@...nel.org>
---
 block/bio.c | 65 ++++++++++++++++++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 25 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 44286db14355f..8703be4748db8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1204,8 +1204,7 @@ static unsigned int get_contig_folio_len(unsigned int *num_pages,
  * For a multi-segment *iter, this function only adds pages from the next
  * non-empty segment of the iov iterator.
  */
-static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
-				    unsigned len_align_mask)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
 	iov_iter_extraction_t extraction_flags = 0;
 	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
@@ -1214,7 +1213,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 	struct page **pages = (struct page **)bv;
 	ssize_t size;
 	unsigned int num_pages, i = 0;
-	size_t offset, folio_offset, left, len, trim;
+	size_t offset, folio_offset, left, len;
 	int ret = 0;
 
 	/*
@@ -1228,13 +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);
@@ -1242,18 +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);
-
-	trim = size & len_align_mask;
-	if (trim) {
-		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);
@@ -1298,11 +1278,44 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 	return ret;
 }
 
+/*
+ * 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
+ * for the next iteration.
+ */
+static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
+			    unsigned len_align_mask)
+{
+	size_t nbytes = bio->bi_iter.bi_size & len_align_mask;
+
+	if (!nbytes)
+		return 0;
+
+	iov_iter_revert(iter, nbytes);
+	bio->bi_iter.bi_size -= nbytes;
+	do {
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (nbytes < bv->bv_len) {
+			bv->bv_len -= nbytes;
+			break;
+		}
+
+		bio_release_page(bio, bv->bv_page);
+		bio->bi_vcnt--;
+		nbytes -= bv->bv_len;
+	} while (nbytes);
+
+	if (!bio->bi_vcnt)
+		return -EFAULT;
+	return 0;
+}
+
 /**
  * bio_iov_iter_get_pages_aligned - add user or kernel pages to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be added
- * @len_align_mask: the mask to align each vector size to, 0 for any length
+ * @len_align_mask: the mask to align the total size to, 0 for any length
  *
  * This takes either an iterator pointing to user memory, or one pointing to
  * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
@@ -1336,10 +1349,12 @@ int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter,
 	if (iov_iter_extract_will_pin(iter))
 		bio_set_flag(bio, BIO_PAGE_PINNED);
 	do {
-		ret = __bio_iov_iter_get_pages(bio, iter, len_align_mask);
+		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
-	return bio->bi_vcnt ? 0 : ret;
+	if (bio->bi_vcnt)
+		return bio_iov_iter_align_down(bio, iter, len_align_mask);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages_aligned);
 
-- 
2.47.3