Searched hist:"764 d2c80401fcc7ee15933d604c6a783d5addc40" (Results 1 – 1 of 1) sorted by relevance
/openbmc/linux/fs/f2fs/ |
H A D | file.c | diff 764d2c80401fcc7ee15933d604c6a783d5addc40 Tue Nov 11 13:01:01 CST 2014 Jaegeuk Kim <jaegeuk@kernel.org> 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>
|