summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2013-10-16 13:47:00 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-10-16 21:35:53 -0700
commit84235de394d9775bfaa7fa9762a59d91fef0c1fc (patch)
treec4066a9859f12ddce7f2f4deae4efa93a2c56f52
parent4942642080ea82d99ab5b653abb9a12b7ba31f4a (diff)
downloadop-kernel-dev-84235de394d9775bfaa7fa9762a59d91fef0c1fc.zip
op-kernel-dev-84235de394d9775bfaa7fa9762a59d91fef0c1fc.tar.gz
fs: buffer: move allocation failure loop into the allocator
Buffer allocation has a very crude indefinite loop around waking the flusher threads and performing global NOFS direct reclaim because it can not handle allocation failures. The most immediate problem with this is that the allocation may fail due to a memory cgroup limit, where flushers + direct reclaim might not make any progress towards resolving the situation at all. Because unlike the global case, a memory cgroup may not have any cache at all, only anonymous pages but no swap. This situation will lead to a reclaim livelock with insane IO from waking the flushers and thrashing unrelated filesystem cache in a tight loop. Use __GFP_NOFAIL allocations for buffers for now. This makes sure that any looping happens in the page allocator, which knows how to orchestrate kswapd, direct reclaim, and the flushers sensibly. It also allows memory cgroups to detect allocations that can't handle failure and will allow them to ultimately bypass the limit if reclaim can not make progress. Reported-by: azurIt <azurit@pobox.sk> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/buffer.c14
-rw-r--r--mm/memcontrol.c2
2 files changed, 14 insertions, 2 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index 4d74335..6024877 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1005,9 +1005,19 @@ grow_dev_page(struct block_device *bdev, sector_t block,
struct buffer_head *bh;
sector_t end_block;
int ret = 0; /* Will call free_more_memory() */
+ gfp_t gfp_mask;
- page = find_or_create_page(inode->i_mapping, index,
- (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
+ gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
+ gfp_mask |= __GFP_MOVABLE;
+ /*
+ * XXX: __getblk_slow() can not really deal with failure and
+ * will endlessly loop on improvised global reclaim. Prefer
+ * looping in the allocator rather than here, at least that
+ * code knows what it's doing.
+ */
+ gfp_mask |= __GFP_NOFAIL;
+
+ page = find_or_create_page(inode->i_mapping, index, gfp_mask);
if (!page)
return ret;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 65fc6a4..34d3ca9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2766,6 +2766,8 @@ done:
return 0;
nomem:
*ptr = NULL;
+ if (gfp_mask & __GFP_NOFAIL)
+ return 0;
return -ENOMEM;
bypass:
*ptr = root_mem_cgroup;
OpenPOWER on IntegriCloud