In below race condition, dst page may become writeback status
in __clone_blkaddrs(), it needs to wait writeback before update,
fix it.
Thread A GC Thread
- f2fs_move_file_range
- filemap_write_and_wait_range(dst)
- gc_data_segment
- f2fs_down_write(dst)
- move_data_page
- set_page_writeback(dst_page)
- f2fs_submit_page_write
- f2fs_up_write(dst)
- f2fs_down_write(dst)
- __exchange_data_block
- __clone_blkaddrs
- f2fs_get_new_data_page
- memcpy_page
Fixes: 0a2aa8fbb969 ("f2fs: refactor __exchange_data_block for speed up")
Signed-off-by: Chao Yu <[email protected]>
---
fs/f2fs/file.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index f6edc2fdaafe..911b074f808c 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1328,6 +1328,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
}
+
+ f2fs_wait_on_page_writeback(pdst, DATA, true, true);
+
memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE);
set_page_dirty(pdst);
set_page_private_gcing(pdst);
--
2.40.1
Hello:
This patch was applied to jaegeuk/f2fs.git (dev)
by Jaegeuk Kim <[email protected]>:
On Tue, 26 Mar 2024 19:28:45 +0800 you wrote:
> In below race condition, dst page may become writeback status
> in __clone_blkaddrs(), it needs to wait writeback before update,
> fix it.
>
> Thread A GC Thread
> - f2fs_move_file_range
> - filemap_write_and_wait_range(dst)
> - gc_data_segment
> - f2fs_down_write(dst)
> - move_data_page
> - set_page_writeback(dst_page)
> - f2fs_submit_page_write
> - f2fs_up_write(dst)
> - f2fs_down_write(dst)
> - __exchange_data_block
> - __clone_blkaddrs
> - f2fs_get_new_data_page
> - memcpy_page
>
> [...]
Here is the summary with links:
- [f2fs-dev] f2fs: fix to wait on page writeback in __clone_blkaddrs()
https://git.kernel.org/jaegeuk/f2fs/c/d3876e34e7e7
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html