summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2016-10-27 17:46:56 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-11-10 16:36:32 +0100
commit299991298b043a54d689cce659bff8ef4e9c200c (patch)
tree897da5f0e9786082af582eac90fcdec465189c05
parent9fa32e04f8107af05d6d557a27a4687ec02ff6e5 (diff)
mm: memcontrol: do not recurse in direct reclaim
commit 89a2848381b5fcd9c4d9c0cd97680e3b28730e31 upstream. On 4.0, we saw a stack corruption from a page fault entering direct memory cgroup reclaim, calling into btrfs_releasepage(), which then tried to allocate an extent and recursed back into a kmem charge ad nauseam: [...] btrfs_releasepage+0x2c/0x30 try_to_release_page+0x32/0x50 shrink_page_list+0x6da/0x7a0 shrink_inactive_list+0x1e5/0x510 shrink_lruvec+0x605/0x7f0 shrink_zone+0xee/0x320 do_try_to_free_pages+0x174/0x440 try_to_free_mem_cgroup_pages+0xa7/0x130 try_charge+0x17b/0x830 memcg_charge_kmem+0x40/0x80 new_slab+0x2d9/0x5a0 __slab_alloc+0x2fd/0x44f kmem_cache_alloc+0x193/0x1e0 alloc_extent_state+0x21/0xc0 __clear_extent_bit+0x2b5/0x400 try_release_extent_mapping+0x1a3/0x220 __btrfs_releasepage+0x31/0x70 btrfs_releasepage+0x2c/0x30 try_to_release_page+0x32/0x50 shrink_page_list+0x6da/0x7a0 shrink_inactive_list+0x1e5/0x510 shrink_lruvec+0x605/0x7f0 shrink_zone+0xee/0x320 do_try_to_free_pages+0x174/0x440 try_to_free_mem_cgroup_pages+0xa7/0x130 try_charge+0x17b/0x830 mem_cgroup_try_charge+0x65/0x1c0 handle_mm_fault+0x117f/0x1510 __do_page_fault+0x177/0x420 do_page_fault+0xc/0x10 page_fault+0x22/0x30 On later kernels, kmem charging is opt-in rather than opt-out, and that particular kmem allocation in btrfs_releasepage() is no longer being charged and won't recurse and overrun the stack anymore. But it's not impossible for an accounted allocation to happen from the memcg direct reclaim context, and we needed to reproduce this crash many times before we even got a useful stack trace out of it. Like other direct reclaimers, mark tasks in memcg reclaim PF_MEMALLOC to avoid recursing into any other form of direct reclaim. Then let recursive charges from PF_MEMALLOC contexts bypass the cgroup limit. Link: http://lkml.kernel.org/r/20161025141050.GA13019@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--mm/memcontrol.c9
-rw-r--r--mm/vmscan.c2
2 files changed, 11 insertions, 0 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6b90d184e9c0..5d9c8a3136bc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2055,6 +2055,15 @@ retry:
current->flags & PF_EXITING))
goto force;
+ /*
+ * Prevent unbounded recursion when reclaim operations need to
+ * allocate memory. This might exceed the limits temporarily,
+ * but we prefer facilitating memory reclaim and getting back
+ * under the limit over triggering OOM kills in these cases.
+ */
+ if (unlikely(current->flags & PF_MEMALLOC))
+ goto force;
+
if (unlikely(task_in_memcg_oom(current)))
goto nomem;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0838e9f02b11..de1c59d8daa3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2910,7 +2910,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
sc.may_writepage,
sc.gfp_mask);
+ current->flags |= PF_MEMALLOC;
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+ current->flags &= ~PF_MEMALLOC;
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);