Merge branch 'akpm-current/current'

1 files changed, 83 insertions, 14 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d99b71bc2c66..808cdb7056ef 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -35,6 +35,7 @@ struct mem_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
+struct oom_control;
 
 /* Cgroup-specific page state, on top of universal node page state */
 enum memcg_stat_item {
@@ -53,9 +54,17 @@ enum memcg_memory_event {
 	MEMCG_HIGH,
 	MEMCG_MAX,
 	MEMCG_OOM,
+	MEMCG_SWAP_MAX,
+	MEMCG_SWAP_FAIL,
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
+enum mem_cgroup_protection {
+	MEMCG_PROT_NONE,
+	MEMCG_PROT_LOW,
+	MEMCG_PROT_MIN,
+};
+
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
 	int priority;
@@ -179,8 +188,7 @@ struct mem_cgroup {
 	struct page_counter kmem;
 	struct page_counter tcpmem;
 
-	/* Normal memory consumption range */
-	unsigned long low;
+	/* Upper bound of normal memory consumption range */
 	unsigned long high;
 
 	/* Range enforcement for interrupt charges */
@@ -204,10 +212,20 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
+	/*
+	 * Treat the sub-tree as an indivisible memory consumer,
+	 * kill all belonging tasks if the memory cgroup selected
+	 * as OOM victim.
+	 */
+	bool oom_group;
+
 	/* memory.events */
 	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
 	struct cgroup_file events_file;
 
+	/* handle for "memory.swap.events" */
+	struct cgroup_file swap_events_file;
+
 	/* protect arrays of thresholds */
 	struct mutex thresholds_lock;
 
@@ -285,7 +303,8 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
+enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
+						struct mem_cgroup *memcg);
 
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
@@ -341,13 +360,19 @@ out:
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
-struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
+struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+	css_put(&memcg->css);
+}
+
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -402,6 +427,9 @@ static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
 }
 
+void mm_update_memcg(struct mm_struct *mm, struct mem_cgroup *new);
+void mm_sync_memcg_from_task(struct task_struct *tsk);
+
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 				   struct mem_cgroup *memcg)
 {
@@ -409,7 +437,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	bool match = false;
 
 	rcu_read_lock();
-	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	task_memcg = rcu_dereference(mm->memcg);
 	if (task_memcg)
 		match = mem_cgroup_is_descendant(task_memcg, memcg);
 	rcu_read_unlock();
@@ -462,11 +490,13 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 
 void mem_cgroup_handle_over_high(void);
 
-unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg);
+unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
+
 static inline void mem_cgroup_oom_enable(void)
 {
 	WARN_ON(current->memcg_may_oom);
@@ -486,6 +516,13 @@ static inline bool task_in_memcg_oom(struct task_struct *p)
 
 bool mem_cgroup_oom_synchronize(bool wait);
 
+bool mem_cgroup_select_oom_victim(struct oom_control *oc);
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return memcg->oom_group;
+}
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -693,7 +730,7 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 		return;
 
 	rcu_read_lock();
-	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	memcg = rcu_dereference(mm->memcg);
 	if (likely(memcg)) {
 		count_memcg_events(memcg, idx, 1);
 		if (idx == OOM_KILL)
@@ -730,10 +767,10 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 {
 }
 
-static inline bool mem_cgroup_low(struct mem_cgroup *root,
-				  struct mem_cgroup *memcg)
+static inline enum mem_cgroup_protection mem_cgroup_protected(
+	struct mem_cgroup *root, struct mem_cgroup *memcg)
 {
-	return false;
+	return MEMCG_PROT_NONE;
 }
 
 static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
@@ -781,6 +818,14 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 	return &pgdat->lruvec;
 }
 
+static inline void mm_update_memcg(struct mm_struct *mm, struct mem_cgroup *new)
+{
+}
+
+static inline void mm_sync_memcg_from_task(struct task_struct *tsk)
+{
+}
+
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {
@@ -793,6 +838,15 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+	return NULL;
+}
+
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+}
+
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -853,13 +907,19 @@ mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 	return 0;
 }
 
-static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 {
 	return 0;
 }
 
 static inline void
-mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
+					struct task_struct *p)
+{
+}
+
+static inline void
+mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
 }
 
@@ -985,6 +1045,16 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline bool mem_cgroup_select_oom_victim(struct oom_control *oc)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return false;
+}
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
@@ -1093,7 +1163,6 @@ static inline void dec_lruvec_page_state(struct page *page,
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
 void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 			 unsigned long *pheadroom, unsigned long *pdirty,