mm: memcontrol: fix recursive statistics correctness & scalabilty

Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.

There are two issues with this:

1. When a cgroup gets deleted, its stats are lost. The state counters
   should all be 0 at that point, of course, but the events are not.
   When this happens, the event counters, which are supposed to be
   monotonic, can go backwards in the parent cgroups.

2. During regular operation, we always have a certain number of lazily
   freed cgroups sitting around that have been deleted, have no tasks,
   but have a few cache pages remaining. These groups' statistics do not
   change until we eventually hit memory pressure, but somebody
   watching, say, memory.stat on an ancestor has to iterate those every
   time.

This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.

Upward propagation happens when the per-cpu caches spill over into the
local atomic counter.  This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate.  In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Johannes Weiner <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
Reviewed-by: Roman Gushchin <[email protected]>
Cc: Michal Hocko <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/memcontrol.h

@@ -128,6 +128,7 @@ struct mem_cgroup_per_node {
 
 	struct lruvec_stat __percpu *lruvec_stat_cpu;
 	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+	atomic_long_t		lruvec_stat_local[NR_VM_NODE_STAT_ITEMS];
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
@@ -279,8 +280,12 @@ struct mem_cgroup {
 	MEMCG_PADDING(_pad2_);
 
 	atomic_long_t		vmstats[MEMCG_NR_STAT];
+	atomic_long_t		vmstats_local[MEMCG_NR_STAT];
+
 	atomic_long_t		vmevents[NR_VM_EVENT_ITEMS];
-	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
+	atomic_long_t		vmevents_local[NR_VM_EVENT_ITEMS];
+
+	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 
 	unsigned long		socket_pressure;
 
@@ -550,14 +555,28 @@ struct mem_cgroup *lock_page_memcg(struct page *page);
 void __unlock_page_memcg(struct mem_cgroup *memcg);
 void unlock_page_memcg(struct page *page);
 
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page_state().
+ */
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+{
+	long x = atomic_long_read(&memcg->vmstats[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
 /*
  * idx can be of type enum memcg_stat_item or node_stat_item.
  * Keep in sync with memcg_exact_page_state().
  */
 static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
 						   int idx)
 {
-	long x = atomic_long_read(&memcg->vmstats[idx]);
+	long x = atomic_long_read(&memcg->vmstats_local[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -609,6 +628,24 @@ static inline void mod_memcg_page_state(struct page *page,
 		mod_memcg_state(page->mem_cgroup, idx, val);
 }
 
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
+{
+	struct mem_cgroup_per_node *pn;
+	long x;
+
+	if (mem_cgroup_disabled())
+		return node_page_state(lruvec_pgdat(lruvec), idx);
+
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	x = atomic_long_read(&pn->lruvec_stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 						    enum node_stat_item idx)
 {
@@ -619,7 +656,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = atomic_long_read(&pn->lruvec_stat[idx]);
+	x = atomic_long_read(&pn->lruvec_stat_local[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -959,6 +996,11 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 {
 }
 
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+{
+	return 0;
+}
+
 static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
 						   int idx)
 {
@@ -989,6 +1031,12 @@ static inline void mod_memcg_page_state(struct page *page,
 {
 }
 
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
+{
+	return node_page_state(lruvec_pgdat(lruvec), idx);
+}
+
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 						    enum node_stat_item idx)
 {