diff options
| author | Jaegeuk Kim <jaegeuk@kernel.org> | 2014-11-11 20:01:01 +0100 |
|---|---|---|
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2014-11-11 23:15:48 +0100 |
| commit | 764d2c80401fcc7ee15933d604c6a783d5addc40 (patch) | |
| tree | 4f2c237c79c273d32326cd72dcad2801009f702a /fs/f2fs/inline.c | |
| parent | f2fs: reduce the number of inline_data inode before clearing it (diff) | |
| download | linux-764d2c80401fcc7ee15933d604c6a783d5addc40.tar.xz linux-764d2c80401fcc7ee15933d604c6a783d5addc40.zip | |
f2fs: fix deadlock to grab 0'th data page
The scenario is like this.
One trhead triggers:
f2fs_write_data_pages
lock_page
f2fs_write_data_page
f2fs_lock_op <- wait
The other thread triggers:
f2fs_truncate
truncate_blocks
f2fs_lock_op
truncate_partial_data_page
lock_page <- wait for locking the page
This patch resolves this bug by relocating truncate_partial_data_page.
This function is just to truncate user data page and not related to FS
consistency as well.
And, we don't need to call truncate_inline_data. Rather than that,
f2fs_write_data_page will finally update inline_data later.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs/f2fs/inline.c')
0 files changed, 0 insertions, 0 deletions