Nikolay has reported a hang when a memcg reclaim got stuck with the following backtrace: PID: 18308 TASK: ffff883d7c9b0a30 CPU: 1 COMMAND: "rsync" #0 __schedule at ffffffff815ab152 hardkernel#1 schedule at ffffffff815ab76e hardkernel#2 schedule_timeout at ffffffff815ae5e5 hardkernel#3 io_schedule_timeout at ffffffff815aad6a hardkernel#4 bit_wait_io at ffffffff815abfc6 hardkernel#5 __wait_on_bit at ffffffff815abda5 hardkernel#6 wait_on_page_bit at ffffffff8111fd4f hardkernel#7 shrink_page_list at ffffffff81135445 hardkernel#8 shrink_inactive_list at ffffffff81135845 hardkernel#9 shrink_lruvec at ffffffff81135ead hardkernel#10 shrink_zone at ffffffff811360c3 hardkernel#11 shrink_zones at ffffffff81136eff hardkernel#12 do_try_to_free_pages at ffffffff8113712f hardkernel#13 try_to_free_mem_cgroup_pages at ffffffff811372be hardkernel#14 try_charge at ffffffff81189423 hardkernel#15 mem_cgroup_try_charge at ffffffff8118c6f5 hardkernel#16 __add_to_page_cache_locked at ffffffff8112137d hardkernel#17 add_to_page_cache_lru at ffffffff81121618 hardkernel#18 pagecache_get_page at ffffffff8112170b hardkernel#19 grow_dev_page at ffffffff811c8297 hardkernel#20 __getblk_slow at ffffffff811c91d6 hardkernel#21 __getblk_gfp at ffffffff811c92c1 hardkernel#22 ext4_ext_grow_indepth at ffffffff8124565c hardkernel#23 ext4_ext_create_new_leaf at ffffffff81246ca8 hardkernel#24 ext4_ext_insert_extent at ffffffff81246f09 hardkernel#25 ext4_ext_map_blocks at ffffffff8124a848 hardkernel#26 ext4_map_blocks at ffffffff8121a5b7 hardkernel#27 mpage_map_one_extent at ffffffff8121b1fa hardkernel#28 mpage_map_and_submit_extent at ffffffff8121f07b hardkernel#29 ext4_writepages at ffffffff8121f6d5 hardkernel#30 do_writepages at ffffffff8112c490 hardkernel#31 __filemap_fdatawrite_range at ffffffff81120199 hardkernel#32 filemap_flush at ffffffff8112041c hardkernel#33 ext4_alloc_da_blocks at ffffffff81219da1 hardkernel#34 ext4_rename at ffffffff81229b91 hardkernel#35 ext4_rename2 at ffffffff81229e32 hardkernel#36 vfs_rename at ffffffff811a08a5 hardkernel#37 SYSC_renameat2 at ffffffff811a3ffc hardkernel#38 sys_renameat2 at ffffffff811a408e hardkernel#39 sys_rename at ffffffff8119e51e hardkernel#40 system_call_fastpath at ffffffff815afa89 Dave Chinner has properly pointed out that this is a deadlock in the reclaim code because ext4 doesn't submit pages which are marked by PG_writeback right away. The heuristic was introduced by commit e62e384 ("memcg: prevent OOM with too many dirty pages") and it was applied only when may_enter_fs was specified. The code has been changed by c3b94f4 ("memcg: further prevent OOM with too many dirty pages") which has removed the __GFP_FS restriction with a reasoning that we do not get into the fs code. But this is not sufficient apparently because the fs doesn't necessarily submit pages marked PG_writeback for IO right away. ext4_bio_write_page calls io_submit_add_bh but that doesn't necessarily submit the bio. Instead it tries to map more pages into the bio and mpage_map_one_extent might trigger memcg charge which might end up waiting on a page which is marked PG_writeback but hasn't been submitted yet so we would end up waiting for something that never finishes. Fix this issue by replacing __GFP_IO by may_enter_fs check (for case 2) before we go to wait on the writeback. The page fault path, which is the only path that triggers memcg oom killer since 3.12, shouldn't require GFP_NOFS and so we shouldn't reintroduce the premature OOM killer issue which was originally addressed by the heuristic. As per David Chinner the xfs is doing similar thing since 2.6.15 already so ext4 is not the only affected filesystem. Moreover he notes: : For example: IO completion might require unwritten extent conversion : which executes filesystem transactions and GFP_NOFS allocations. The : writeback flag on the pages can not be cleared until unwritten : extent conversion completes. Hence memory reclaim cannot wait on : page writeback to complete in GFP_NOFS context because it is not : safe to do so, memcg reclaim or otherwise. Cc: stable@vger.kernel.org # 3.9+ [tytso@mit.edu: corrected the control flow] Fixes: c3b94f4 ("memcg: further prevent OOM with too many dirty pages") Reported-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

usb-dvb modules on odroid-3.8.y kernel #34

Description

Metadata

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

Issue actions