Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify fix

 - poll() timeout fix

 - a few scripts/ tweaks

 - debugobjects updates

 - the (small) ocfs2 queue

 - Minor fixes to kernel/padata.c

 - Maybe half of the MM queue

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  mm, page_alloc: restore the original nodemask if the fast path allocation failed
  mm, page_alloc: uninline the bad page part of check_new_page()
  mm, page_alloc: don't duplicate code in free_pcp_prepare
  mm, page_alloc: defer debugging checks of pages allocated from the PCP
  mm, page_alloc: defer debugging checks of freed pages until a PCP drain
  cpuset: use static key better and convert to new API
  mm, page_alloc: inline pageblock lookup in page free fast paths
  mm, page_alloc: remove unnecessary variable from free_pcppages_bulk
  mm, page_alloc: pull out side effects from free_pages_check
  mm, page_alloc: un-inline the bad part of free_pages_check
  mm, page_alloc: check multiple page fields with a single branch
  mm, page_alloc: remove field from alloc_context
  mm, page_alloc: avoid looking up the first zone in a zonelist twice
  mm, page_alloc: shortcut watermark checks for order-0 pages
  mm, page_alloc: reduce cost of fair zone allocation policy retry
  mm, page_alloc: shorten the page allocator fast path
  mm, page_alloc: check once if a zone has isolated pageblocks
  mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath
  mm, page_alloc: simplify last cpupid reset
  mm, page_alloc: remove unnecessary initialisation from __alloc_pages_nodemask()
  ...

1 files changed, 27 insertions, 11 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fe787f5c41bd..d71d387868e6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1023,22 +1023,40 @@ out:
  * @lru: index of lru list the page is sitting on
  * @nr_pages: positive when adding or negative when removing
  *
- * This function must be called when a page is added to or removed from an
- * lru list.
+ * This function must be called under lru_lock, just before a page is added
+ * to or just after a page is removed from an lru list (that ordering being
+ * so as to allow it to check that lru_size 0 is consistent with list_empty).
  */
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 				int nr_pages)
 {
 	struct mem_cgroup_per_zone *mz;
 	unsigned long *lru_size;
+	long size;
+	bool empty;
+
+	__update_lru_size(lruvec, lru, nr_pages);
 
 	if (mem_cgroup_disabled())
 		return;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
 	lru_size = mz->lru_size + lru;
-	*lru_size += nr_pages;
-	VM_BUG_ON((long)(*lru_size) < 0);
+	empty = list_empty(lruvec->lists + lru);
+
+	if (nr_pages < 0)
+		*lru_size += nr_pages;
+
+	size = *lru_size;
+	if (WARN_ONCE(size < 0 || empty != !size,
+		"%s(%p, %d, %d): lru_size %ld but %sempty\n",
+		__func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) {
+		VM_BUG_ON(1);
+		*lru_size = 0;
+	}
+
+	if (nr_pages > 0)
+		*lru_size += nr_pages;
 }
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
@@ -1257,6 +1275,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 */
 	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
 		mark_oom_victim(current);
+		try_oom_reaper(current);
 		goto unlock;
 	}
 
@@ -1389,14 +1408,11 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 	mem_cgroup_may_update_nodemask(memcg);
 	node = memcg->last_scanned_node;
 
-	node = next_node(node, memcg->scan_nodes);
-	if (node == MAX_NUMNODES)
-		node = first_node(memcg->scan_nodes);
+	node = next_node_in(node, memcg->scan_nodes);
 	/*
-	 * We call this when we hit limit, not when pages are added to LRU.
-	 * No LRU may hold pages because all pages are UNEVICTABLE or
-	 * memcg is too small and all pages are not on LRU. In that case,
-	 * we use curret node.
+	 * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages
+	 * last time it really checked all the LRUs due to rate limiting.
+	 * Fallback to the current node in that case for simplicity.
 	 */
 	if (unlikely(node == MAX_NUMNODES))
 		node = numa_node_id();