diff options
author | Sahitya Tummala <stummala@codeaurora.org> | 2020-02-18 06:49:07 +0300 |
---|---|---|
committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2020-02-27 21:16:44 +0300 |
commit | bf22c3cc8ce71454dddd772284773306a68031d8 (patch) | |
tree | 76b1135bc0e70b3d89a9bd3947cdc95b7ee5bad6 /fs/f2fs/compress.c | |
parent | dc5a941223edd803f476a153abd950cc3a83c3e1 (diff) | |
download | linux-bf22c3cc8ce71454dddd772284773306a68031d8.tar.xz |
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/compress.c')
0 files changed, 0 insertions, 0 deletions