mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-19 02:04:19 +08:00
5eda430000
Christoph Hellwig pointed out that there's a potentially nasty race when
performing simultaneous nearby directio cow writes:
"Thread 1 writes a range from B to c
" B --------- C
p
"a little later thread 2 writes from A to B
" A --------- B
p
[editor's note: the 'p' denote cowextsize boundaries, which I added to
make this more clear]
"but the code preallocates beyond B into the range where thread
"1 has just written, but ->end_io hasn't been called yet.
"But once ->end_io is called thread 2 has already allocated
"up to the extent size hint into the write range of thread 1,
"so the end_io handler will splice the unintialized blocks from
"that preallocation back into the file right after B."
We can avoid this race by ensuring that thread 1 cannot accidentally
remap the blocks that thread 2 allocated (as part of speculative
preallocation) as part of t2's write preparation in t1's end_io handler.
The way we make this happen is by taking advantage of the unwritten
extent flag as an intermediate step.
Recall that when we begin the process of writing data to shared blocks,
we create a delayed allocation extent in the CoW fork:
D: --RRRRRRSSSRRRRRRRR---
C: ------DDDDDDD---------
When a thread prepares to CoW some dirty data out to disk, it will now
convert the delalloc reservation into an /unwritten/ allocated extent in
the cow fork. The da conversion code tries to opportunistically
allocate as much of a (speculatively prealloc'd) extent as possible, so
we may end up allocating a larger extent than we're actually writing
out:
D: --RRRRRRSSSRRRRRRRR---
U: ------UUUUUUU---------
Next, we convert only the part of the extent that we're actively
planning to write to normal (i.e. not unwritten) status:
D: --RRRRRRSSSRRRRRRRR---
U: ------UURRUUU---------
If the write succeeds, the end_cow function will now scan the relevant
range of the CoW fork for real extents and remap only the real extents
into the data fork:
D: --RRRRRRRRSRRRRRRRR---
U: ------UU--UUU---------
This ensures that we never obliterate valid data fork extents with
unwritten blocks from the CoW fork.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
56 lines
2.4 KiB
C
56 lines
2.4 KiB
C
/*
|
|
* Copyright (C) 2016 Oracle. All Rights Reserved.
|
|
*
|
|
* Author: Darrick J. Wong <darrick.wong@oracle.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version 2
|
|
* of the License, or (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it would be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write the Free Software Foundation,
|
|
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
|
|
*/
|
|
#ifndef __XFS_REFLINK_H
|
|
#define __XFS_REFLINK_H 1
|
|
|
|
extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
|
|
xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
|
|
xfs_extlen_t *flen, bool find_maximal);
|
|
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
|
|
struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
|
|
|
|
extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
|
|
struct xfs_bmbt_irec *imap, bool *shared);
|
|
extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
|
|
xfs_off_t offset, xfs_off_t count);
|
|
extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
|
|
xfs_off_t count);
|
|
extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
|
|
struct xfs_bmbt_irec *imap);
|
|
extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
|
|
xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
|
|
|
|
extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
|
|
struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
|
|
xfs_fileoff_t end_fsb);
|
|
extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
|
|
xfs_off_t count);
|
|
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
|
|
xfs_off_t count);
|
|
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
|
|
extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
|
|
struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
|
|
extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
|
|
struct xfs_trans **tpp);
|
|
extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
|
|
xfs_off_t len);
|
|
|
|
#endif /* __XFS_REFLINK_H */
|