linux-kernel - [PATCH] iomap: keep on increasing i_size in iomap_write

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-next>] [day] [month] [year] [list]
Message-Id: <20240603112222.2109341-1-yi.zhang@huaweicloud.com>
Date: Mon,  3 Jun 2024 19:22:22 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: linux-xfs@...r.kernel.org,
	linux-fsdevel@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
	djwong@...nel.org,
	hch@...radead.org,
	brauner@...nel.org,
	david@...morbit.com,
	chandanbabu@...nel.org,
	jack@...e.cz,
	yi.zhang@...wei.com,
	yi.zhang@...weicloud.com,
	chengzhihao1@...wei.com,
	yukuai3@...wei.com
Subject: [PATCH] iomap: keep on increasing i_size in iomap_write_end()

From: Zhang Yi <yi.zhang@...wei.com>

Commit '943bc0882ceb ("iomap: don't increase i_size if it's not a write
operation")' breaks xfs with realtime device on generic/561, the problem
is when unaligned truncate down a xfs realtime inode with rtextsize > 1
fs block, xfs only zero out the EOF block but doesn't zero out the tail
blocks that aligned to rtextsize, so if we don't increase i_size in
iomap_write_end(), it could expose stale data after we do an append
write beyond the aligned EOF block.

xfs should zero out the tail blocks when truncate down, but before we
finish that, let's fix the issue by just revert the changes in
iomap_write_end().

Fixes: 943bc0882ceb ("iomap: don't increase i_size if it's not a write operation")
Reported-by: Chandan Babu R <chandanbabu@...nel.org>
Link: https://lore.kernel.org/linux-xfs/0b92a215-9d9b-3788-4504-a520778953c2@huaweicloud.com
Signed-off-by: Zhang Yi <yi.zhang@...wei.com>
---
 fs/iomap/buffered-io.c | 53 +++++++++++++++++++-----------------------
 1 file changed, 24 insertions(+), 29 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c5802a459334..bd70fcbc168e 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -877,22 +877,37 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 		size_t copied, struct folio *folio)
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	loff_t old_size = iter->inode->i_size;
+	size_t written;
 
 	if (srcmap->type == IOMAP_INLINE) {
 		iomap_write_end_inline(iter, folio, pos, copied);
-		return true;
+		written = copied;
+	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
+		written = block_write_end(NULL, iter->inode->i_mapping, pos,
+					len, copied, &folio->page, NULL);
+		WARN_ON_ONCE(written != copied && written != 0);
+	} else {
+		written = __iomap_write_end(iter->inode, pos, len, copied,
+					    folio) ? copied : 0;
 	}
 
-	if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
-		size_t bh_written;
-
-		bh_written = block_write_end(NULL, iter->inode->i_mapping, pos,
-					len, copied, &folio->page, NULL);
-		WARN_ON_ONCE(bh_written != copied && bh_written != 0);
-		return bh_written == copied;
+	/*
+	 * Update the in-memory inode size after copying the data into the page
+	 * cache.  It's up to the file system to write the updated size to disk,
+	 * preferably after I/O completion so that no stale data is exposed.
+	 * Only once that's done can we unlock and release the folio.
+	 */
+	if (pos + written > old_size) {
+		i_size_write(iter->inode, pos + written);
+		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
 	}
+	__iomap_put_folio(iter, pos, written, folio);
 
-	return __iomap_write_end(iter->inode, pos, len, copied, folio);
+	if (old_size < pos)
+		pagecache_isize_extended(iter->inode, old_size, pos);
+
+	return written == copied;
 }
 
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
@@ -907,7 +922,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 
 	do {
 		struct folio *folio;
-		loff_t old_size;
 		size_t offset;		/* Offset into folio */
 		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
@@ -959,23 +973,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		written = iomap_write_end(iter, pos, bytes, copied, folio) ?
 			  copied : 0;
 
-		/*
-		 * Update the in-memory inode size after copying the data into
-		 * the page cache.  It's up to the file system to write the
-		 * updated size to disk, preferably after I/O completion so that
-		 * no stale data is exposed.  Only once that's done can we
-		 * unlock and release the folio.
-		 */
-		old_size = iter->inode->i_size;
-		if (pos + written > old_size) {
-			i_size_write(iter->inode, pos + written);
-			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
-		}
-		__iomap_put_folio(iter, pos, written, folio);
-
-		if (old_size < pos)
-			pagecache_isize_extended(iter->inode, old_size, pos);
-
 		cond_resched();
 		if (unlikely(written == 0)) {
 			/*
@@ -1346,7 +1343,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 			bytes = folio_size(folio) - offset;
 
 		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
-		__iomap_put_folio(iter, pos, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
@@ -1412,7 +1408,6 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		folio_mark_accessed(folio);
 
 		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
-		__iomap_put_folio(iter, pos, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
-- 
2.39.2