diff options
| author | Sahitya Tummala <stummala@codeaurora.org> | 2020-02-18 09:19:07 +0530 |
|---|---|---|
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2020-02-27 10:16:44 -0800 |
| commit | bf22c3cc8ce71454dddd772284773306a68031d8 (patch) | |
| tree | 76b1135bc0e70b3d89a9bd3947cdc95b7ee5bad6 /fs/f2fs/super.c | |
| parent | dc5a941223edd803f476a153abd950cc3a83c3e1 (diff) | |
| download | linux-bf22c3cc8ce71454dddd772284773306a68031d8.tar.gz | |
f2fs: fix the panic in do_checkpoint()
There could be a scenario where f2fs_sync_meta_pages() will not
ensure that all F2FS_DIRTY_META pages are submitted for IO. Thus,
resulting in the below panic in do_checkpoint() -
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
!f2fs_cp_error(sbi));
This can happen in a low-memory condition, where shrinker could
also be doing the writepage operation (stack shown below)
at the same time when checkpoint is running on another core.
schedule
down_write
f2fs_submit_page_write -> by this time, this page in page cache is tagged
as PAGECACHE_TAG_WRITEBACK and PAGECACHE_TAG_DIRTY
is cleared, due to which f2fs_sync_meta_pages()
cannot sync this page in do_checkpoint() path.
f2fs_do_write_meta_page
__f2fs_write_meta_page
f2fs_write_meta_page
shrink_page_list
shrink_inactive_list
shrink_node_memcg
shrink_node
kswapd
Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs/f2fs/super.c')
| -rw-r--r-- | fs/f2fs/super.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 65a7a432dfee..686f5402660e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1172,7 +1172,7 @@ static void f2fs_put_super(struct super_block *sb) /* our cp_error case, we can wait for any writeback page */ f2fs_flush_merged_writes(sbi); - f2fs_wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); f2fs_bug_on(sbi, sbi->fsync_node_num); |