From: Dave Chinner dchinner@redhat.com
mainline inclusion from mainline-v6.1-rc4 commit 9c7babf94a0d686b552e53aded8d4703d1b8b92b category: bugfix bugzilla: 189079, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
Because that's what Christoph wants for this error handling path only XFS uses.
It requires a new iomap export for handling errors over delalloc ranges. This is basically the XFS code as is stands, but even though Christoph wants this as iomap funcitonality, we still have to call it from the filesystem specific ->iomap_end callback, and call into the iomap code with yet another filesystem specific callback to punch the delalloc extent within the defined ranges.
Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Long Li leo.lilong@huawei.com
Conflicts: fs/xfs/xfs_iomap.c fs/iomap/buffered-io.c include/linux/iomap.h --- fs/xfs/xfs_iomap.c | 83 +++++++++++++++++++++++++++++++--------------- 1 file changed, 57 insertions(+), 26 deletions(-)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1ddc1a33effd..f4203e9d7635 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1114,58 +1114,62 @@ xfs_buffered_write_iomap_begin( static int xfs_buffered_write_delalloc_punch( struct inode *inode, - loff_t start_byte, - loff_t end_byte) + loff_t offset, + loff_t length) { struct xfs_mount *mp = XFS_M(inode->i_sb); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte); - xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte); + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length);
return xfs_bmap_punch_delalloc_range(XFS_I(inode), start_fsb, end_fsb - start_fsb); }
+/* + * When a short write occurs, the filesystem may need to remove reserved space + * that was allocated in ->iomap_begin from it's ->iomap_end method. For + * filesystems that use delayed allocation, we need to punch out delalloc + * extents from the range that are not dirty in the page cache. As the write can + * race with page faults, there can be dirty pages over the delalloc extent + * outside the range of a short write but still within the delalloc extent + * allocated for this iomap. + * + * This function uses [start_byte, end_byte) intervals (i.e. open ended) to + * simplify range iterations, but converts them back to {offset,len} tuples for + * the punch callback. + */ static int -xfs_buffered_write_iomap_end( - struct inode *inode, - loff_t offset, - loff_t length, - ssize_t written, - unsigned flags, - struct iomap *iomap) +xfs_iomap_file_buffered_write_punch_delalloc( + struct inode *inode, + struct iomap *iomap, + loff_t pos, + loff_t length, + ssize_t written, + int (*punch)(struct inode *inode, loff_t pos, loff_t length)) { - struct xfs_mount *mp = XFS_M(inode->i_sb); struct xfs_inode *ip = XFS_I(inode); loff_t start_byte; loff_t end_byte; + int blocksize = i_blocksize(inode); int error = 0;
if (iomap->type != IOMAP_DELALLOC) return 0;
- /* - * Behave as if the write failed if drop writes is enabled. Set the NEW - * flag to force delalloc cleanup. - */ - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { - iomap->flags |= IOMAP_F_NEW; - written = 0; - } - /* If we didn't reserve the blocks, we're not allowed to punch them. */ if (!(iomap->flags & IOMAP_F_NEW)) return 0;
/* - * start_fsb refers to the first unused block after a short write. If + * start_byte refers to the first unused block after a short write. If * nothing was written, round offset down to point at the first block in * the range. */ if (unlikely(!written)) - start_byte = round_down(offset, mp->m_sb.sb_blocksize); + start_byte = round_down(pos, blocksize); else - start_byte = round_up(offset + written, mp->m_sb.sb_blocksize); - end_byte = round_up(offset + length, mp->m_sb.sb_blocksize); + start_byte = round_up(pos + written, blocksize); + end_byte = round_up(pos + length, blocksize);
/* Nothing to do if we've written the entire delalloc extent */ if (start_byte >= end_byte) @@ -1179,8 +1183,35 @@ xfs_buffered_write_iomap_end( */ xfs_ilock(ip, XFS_MMAPLOCK_EXCL); truncate_pagecache_range(inode, start_byte, end_byte - 1); - error = xfs_buffered_write_delalloc_punch(inode, start_byte, end_byte); + error = punch(inode, start_byte, end_byte - start_byte); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + + return error; +} + +static int +xfs_buffered_write_iomap_end( + struct inode *inode, + loff_t offset, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_mount *mp = XFS_M(inode->i_sb); + int error; + + /* + * Behave as if the write failed if drop writes is enabled. Set the NEW + * flag to force delalloc cleanup. + */ + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { + iomap->flags |= IOMAP_F_NEW; + written = 0; + } + + error = xfs_iomap_file_buffered_write_punch_delalloc(inode, iomap, offset, + length, written, &xfs_buffered_write_delalloc_punch); if (error && !xfs_is_shutdown(mp)) { xfs_alert(mp, "%s: unable to clean up ino 0x%llx", __func__, XFS_I(inode)->i_ino);