summaryrefslogtreecommitdiffstats
path: root/fs/xfs
diff options
context:
space:
mode:
authorZhang Yi <yi.zhang@huawei.com>2024-04-25 15:13:30 +0200
committerChandan Babu R <chandanbabu@kernel.org>2024-04-29 13:53:11 +0200
commit5ce5674187c345dc31534d2024c09ad8ef29b7ba (patch)
tree6a3739ba0080cb3a7652bab39e5e4482fc1d8743 /fs/xfs
parentxfs: make xfs_bmapi_convert_delalloc() to allocate the target offset (diff)
downloadlinux-5ce5674187c345dc31534d2024c09ad8ef29b7ba.tar.xz
linux-5ce5674187c345dc31534d2024c09ad8ef29b7ba.zip
xfs: convert delayed extents to unwritten when zeroing post eof blocks
Current clone operation could be non-atomic if the destination of a file is beyond EOF, user could get a file with corrupted (zeroed) data on crash. The problem is about preallocations. If you write some data into a file: [A...B) and XFS decides to preallocate some post-eof blocks, then it can create a delayed allocation reservation: [A.........D) The writeback path tries to convert delayed extents to real ones by allocating blocks. If there aren't enough contiguous free space, we can end up with two extents, the first real and the second still delalloc: [A....C)[C.D) After that, both the in-memory and the on-disk file sizes are still B. If we clone into the range [E...F) from another file: [A....C)[C.D) [E...F) then xfs_reflink_zero_posteof() calls iomap_zero_range() to zero out the range [B, E) beyond EOF and flush it. Since [C, D) is still a delalloc extent, its pagecache will be zeroed and both the in-memory and on-disk size will be updated to D after flushing but before cloning. This is wrong, because the user can see the size change and read the zeroes while the clone operation is ongoing. We need to keep the in-memory and on-disk size before the clone operation starts, so instead of writing zeroes through the page cache for delayed ranges beyond EOF, we convert these ranges to unwritten and invalidate any cached data over that range beyond EOF. Suggested-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: "Darrick J. Wong" <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_iomap.c29
1 files changed, 29 insertions, 0 deletions
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 555603ef4234..ec43aa7cec60 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1040,6 +1040,24 @@ xfs_buffered_write_iomap_begin(
}
/*
+ * For zeroing, trim a delalloc extent that extends beyond the EOF
+ * block. If it starts beyond the EOF block, convert it to an
+ * unwritten extent.
+ */
+ if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb &&
+ isnullstartblock(imap.br_startblock)) {
+ xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
+
+ if (offset_fsb >= eof_fsb)
+ goto convert_delay;
+ if (end_fsb > eof_fsb) {
+ end_fsb = eof_fsb;
+ xfs_trim_extent(&imap, offset_fsb,
+ end_fsb - offset_fsb);
+ }
+ }
+
+ /*
* Search the COW fork extent list even if we did not find a data fork
* extent. This serves two purposes: first this implements the
* speculative preallocation using cowextsize, so that we also unshare
@@ -1184,6 +1202,17 @@ found_imap:
xfs_iunlock(ip, lockmode);
return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq);
+convert_delay:
+ xfs_iunlock(ip, lockmode);
+ truncate_pagecache(inode, offset);
+ error = xfs_bmapi_convert_delalloc(ip, XFS_DATA_FORK, offset,
+ iomap, NULL);
+ if (error)
+ return error;
+
+ trace_xfs_iomap_alloc(ip, offset, count, XFS_DATA_FORK, &imap);
+ return 0;
+
found_cow:
seq = xfs_iomap_inode_sequence(ip, 0);
if (imap.br_startoff <= offset_fsb) {