Re: [PATCH v3] f2fs: fix the panic in do_checkpoint()

From: Chao Yu
Date: Tue Feb 18 2020 - 01:10:15 EST


On 2020/2/18 11:49, Sahitya Tummala wrote:
> 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@xxxxxxxxxxxxxx>

Reviewed-by: Chao Yu <yuchao0@xxxxxxxxxx>

Thanks,