lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening PHC | |
Open Source and information security mailing list archives
| ||
|
Date: Mon, 17 Feb 2020 14:37:17 +0800 From: Chao Yu <yuchao0@...wei.com> To: Sahitya Tummala <stummala@...eaurora.org>, Jaegeuk Kim <jaegeuk@...nel.org>, <linux-f2fs-devel@...ts.sourceforge.net> CC: <linux-kernel@...r.kernel.org> Subject: Re: [PATCH V2] f2fs: fix the panic in do_checkpoint() On 2020/2/17 11:43, 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@...eaurora.org> Looks good to me. Reviewed-by: Chao Yu <yuchao0@...wei.com> BTW, I can't apply this based dev branch of Jaegeuk's tree, could you rebase it? Thanks,
Powered by blists - more mailing lists