1 files changed, 159 insertions, 77 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 69966c461d1c..365d5079d1cb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -48,13 +48,13 @@ enum memcg_stat_item {
 	MEMCG_NR_STAT,
 };
 
-/* Cgroup-specific events, on top of universal VM events */
-enum memcg_event_item {
-	MEMCG_LOW = NR_VM_EVENT_ITEMS,
+enum memcg_memory_event {
+	MEMCG_LOW,
 	MEMCG_HIGH,
 	MEMCG_MAX,
 	MEMCG_OOM,
-	MEMCG_NR_EVENTS,
+	MEMCG_OOM_KILL,
+	MEMCG_NR_MEMORY_EVENTS,
 };
 
 struct mem_cgroup_reclaim_cookie {
@@ -88,7 +88,7 @@ enum mem_cgroup_events_target {
 
 struct mem_cgroup_stat_cpu {
 	long count[MEMCG_NR_STAT];
-	unsigned long events[MEMCG_NR_EVENTS];
+	unsigned long events[NR_VM_EVENT_ITEMS];
 	unsigned long nr_page_events;
 	unsigned long targets[MEM_CGROUP_NTARGETS];
 };
@@ -108,7 +108,10 @@ struct lruvec_stat {
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
-	struct lruvec_stat __percpu *lruvec_stat;
+
+	struct lruvec_stat __percpu *lruvec_stat_cpu;
+	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
@@ -153,6 +156,15 @@ enum memcg_kmem_state {
 	KMEM_ONLINE,
 };
 
+#if defined(CONFIG_SMP)
+struct memcg_padding {
+	char x[0];
+} ____cacheline_internodealigned_in_smp;
+#define MEMCG_PADDING(name)      struct memcg_padding name;
+#else
+#define MEMCG_PADDING(name)
+#endif
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -199,7 +211,7 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
-	/* handle for "memory.events" */
+	/* memory.events */
 	struct cgroup_file events_file;
 
 	/* protect arrays of thresholds */
@@ -219,18 +231,26 @@ struct mem_cgroup {
 	 * mem_cgroup ? And what type of charges should we move ?
 	 */
 	unsigned long move_charge_at_immigrate;
-	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
-	 */
-	atomic_t		moving_account;
 	/* taken only while moving_account > 0 */
 	spinlock_t		move_lock;
-	struct task_struct	*move_lock_task;
 	unsigned long		move_lock_flags;
+
+	MEMCG_PADDING(_pad1_);
+
 	/*
-	 * percpu counter.
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
 	 */
-	struct mem_cgroup_stat_cpu __percpu *stat;
+	atomic_t		moving_account;
+	struct task_struct	*move_lock_task;
+
+	/* memory.stat */
+	struct mem_cgroup_stat_cpu __percpu *stat_cpu;
+
+	MEMCG_PADDING(_pad2_);
+
+	atomic_long_t		stat[MEMCG_NR_STAT];
+	atomic_long_t		events[NR_VM_EVENT_ITEMS];
+	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
 
 	unsigned long		socket_pressure;
 
@@ -265,6 +285,12 @@ struct mem_cgroup {
 	/* WARNING: nodeinfo must be the last member here */
 };
 
+/*
+ * size of first charge trial. "32" comes from vmscan.c's magic value.
+ * TODO: maybe necessary to use big numbers in big irons.
+ */
+#define MEMCG_CHARGE_BATCH 32U
+
 extern struct mem_cgroup *root_mem_cgroup;
 
 static inline bool mem_cgroup_disabled(void)
@@ -272,13 +298,6 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
-				    enum memcg_event_item event)
-{
-	this_cpu_inc(memcg->stat->events[event]);
-	cgroup_file_notify(&memcg->events_file);
-}
-
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
@@ -488,36 +507,47 @@ 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 */
+/*
+ * 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 val = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		val += per_cpu(memcg->stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	long x = atomic_long_read(&memcg->stat[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 */
 static inline void __mod_memcg_state(struct mem_cgroup *memcg,
 				     int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		__this_cpu_add(memcg->stat->count[idx], val);
+	long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->count[idx], x);
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
 				   int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->count[idx], val);
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_memcg_state(memcg, idx, val);
+	local_irq_restore(flags);
 }
 
 /**
@@ -555,89 +585,116 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
-	long val = 0;
-	int cpu;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		val += per_cpu(pn->lruvec_stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	x = atomic_long_read(&pn->lruvec_stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
 				      enum node_stat_item idx, int val)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
+	/* Update node */
 	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
 	if (mem_cgroup_disabled())
 		return;
+
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+
+	/* Update memcg */
 	__mod_memcg_state(pn->memcg, idx, val);
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+
+	/* Update lruvec */
+	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &pn->lruvec_stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
+	unsigned long flags;
 
-	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
-	if (mem_cgroup_disabled())
-		return;
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	mod_memcg_state(pn->memcg, idx, val);
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	local_irq_save(flags);
+	__mod_lruvec_state(lruvec, idx, val);
+	local_irq_restore(flags);
 }
 
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
+	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
-	__mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!page->mem_cgroup) {
+		__mod_node_page_state(pgdat, idx, val);
 		return;
-	__mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+	}
+
+	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+	__mod_lruvec_state(lruvec, idx, val);
 }
 
 static inline void mod_lruvec_page_state(struct page *page,
 					 enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
+	unsigned long flags;
 
-	mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
-		return;
-	mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	local_irq_save(flags);
+	__mod_lruvec_page_state(page, idx, val);
+	local_irq_restore(flags);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
+static inline void __count_memcg_events(struct mem_cgroup *memcg,
+					enum vm_event_item idx,
+					unsigned long count)
+{
+	unsigned long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
+	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->events[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->events[idx], x);
+}
+
 static inline void count_memcg_events(struct mem_cgroup *memcg,
 				      enum vm_event_item idx,
 				      unsigned long count)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->events[idx], count);
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__count_memcg_events(memcg, idx, count);
+	local_irq_restore(flags);
 }
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void count_memcg_page_event(struct page *page,
-					  int idx)
+					  enum vm_event_item idx)
 {
 	if (page->mem_cgroup)
 		count_memcg_events(page->mem_cgroup, idx, 1);
@@ -653,13 +710,33 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (likely(memcg)) {
-		this_cpu_inc(memcg->stat->events[idx]);
-		if (idx == OOM_KILL)
-			cgroup_file_notify(&memcg->events_file);
-	}
+	if (likely(memcg))
+		count_memcg_events(memcg, idx, 1);
+	rcu_read_unlock();
+}
+
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+				      enum memcg_memory_event event)
+{
+	atomic_long_inc(&memcg->memory_events[event]);
+	cgroup_file_notify(&memcg->events_file);
+}
+
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+					 enum memcg_memory_event event)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (likely(memcg))
+		memcg_memory_event(memcg, event);
 	rcu_read_unlock();
 }
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
@@ -676,8 +753,13 @@ static inline bool mem_cgroup_disabled(void)
 	return true;
 }
 
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
-				    enum memcg_event_item event)
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+				      enum memcg_memory_event event)
+{
+}
+
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+					 enum memcg_memory_event event)
 {
 }