1 files changed, 69 insertions, 129 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a805474df4ab..5d8ca6e02e39 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,7 +52,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
 	MEMCG_SLAB_RECLAIMABLE,
 	MEMCG_SLAB_UNRECLAIMABLE,
 	MEMCG_SOCK,
@@ -60,7 +60,7 @@ enum mem_cgroup_stat_index {
 };
 
 struct mem_cgroup_reclaim_cookie {
-	struct zone *zone;
+	pg_data_t *pgdat;
 	int priority;
 	unsigned int generation;
 };
@@ -97,6 +97,11 @@ enum mem_cgroup_events_target {
 #define MEM_CGROUP_ID_SHIFT	16
 #define MEM_CGROUP_ID_MAX	USHRT_MAX
 
+struct mem_cgroup_id {
+	int id;
+	atomic_t ref;
+};
+
 struct mem_cgroup_stat_cpu {
 	long count[MEMCG_NR_STAT];
 	unsigned long events[MEMCG_NR_EVENTS];
@@ -113,7 +118,7 @@ struct mem_cgroup_reclaim_iter {
 /*
  * per-zone information in memory controller.
  */
-struct mem_cgroup_per_zone {
+struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
@@ -127,10 +132,6 @@ struct mem_cgroup_per_zone {
 						/* use container_of	   */
 };
 
-struct mem_cgroup_per_node {
-	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
-};
-
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	unsigned long threshold;
@@ -172,6 +173,9 @@ enum memcg_kmem_state {
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
 
+	/* Private memcg ID. Used to ID objects that outlive the cgroup */
+	struct mem_cgroup_id id;
+
 	/* Accounted resources */
 	struct page_counter memory;
 	struct page_counter swap;
@@ -306,8 +310,46 @@ void mem_cgroup_uncharge_list(struct list_head *page_list);
 
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+static struct mem_cgroup_per_node *
+mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
+{
+	return memcg->nodeinfo[nid];
+}
+
+/**
+ * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
+ * @node: node of the wanted lruvec
+ * @memcg: memcg of the wanted lruvec
+ *
+ * Returns the lru list vector holding pages for a given @node or a given
+ * @memcg and @zone. This can be the node lruvec, if the memory controller
+ * is disabled.
+ */
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *mz;
+	struct lruvec *lruvec;
+
+	if (mem_cgroup_disabled()) {
+		lruvec = node_lruvec(pgdat);
+		goto out;
+	}
+
+	mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->pgdat here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->pgdat != pgdat))
+		lruvec->pgdat = pgdat;
+	return lruvec;
+}
+
+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);
@@ -330,22 +372,9 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 	if (mem_cgroup_disabled())
 		return 0;
 
-	return memcg->css.id;
-}
-
-/**
- * mem_cgroup_from_id - look up a memcg from an id
- * @id: the id to look up
- *
- * Caller must hold rcu_read_lock() and use css_tryget() as necessary.
- */
-static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
-{
-	struct cgroup_subsys_state *css;
-
-	css = css_from_id(id, &memory_cgrp_subsys);
-	return mem_cgroup_from_css(css);
+	return memcg->id.id;
 }
+struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
 
 /**
  * parent_mem_cgroup - find the accounting parent of a memcg
@@ -409,9 +438,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	return mz->lru_size[lru];
 }
 
@@ -482,7 +511,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
@@ -573,16 +602,16 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
-static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
-						    struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
 {
-	return &zone->lruvec;
+	return node_lruvec(pgdat);
 }
 
 static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
-						    struct zone *zone)
+						    struct pglist_data *pgdat)
 {
-	return &zone->lruvec;
+	return &pgdat->lruvec;
 }
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
@@ -686,7 +715,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 }
 
 static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
 					    unsigned long *total_scanned)
 {
@@ -754,6 +783,13 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 }
 #endif
 
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
+void memcg_kmem_put_cache(struct kmem_cache *cachep);
+int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+			    struct mem_cgroup *memcg);
+int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
+void memcg_kmem_uncharge(struct page *page, int order);
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 extern struct static_key_false memcg_kmem_enabled_key;
 
@@ -775,22 +811,6 @@ static inline bool memcg_kmem_enabled(void)
 }
 
 /*
- * In general, we'll do everything in our power to not incur in any overhead
- * for non-memcg users for the kmem functions. Not even a function call, if we
- * can avoid it.
- *
- * Therefore, we'll inline all those functions so that in the best case, we'll
- * see that kmemcg is off for everybody and proceed quickly.  If it is on,
- * we'll still do most of the flag checking inline. We check a lot of
- * conditions, but because they are pretty simple, they are expected to be
- * fast.
- */
-int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
-			      struct mem_cgroup *memcg);
-int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
-void __memcg_kmem_uncharge(struct page *page, int order);
-
-/*
  * helper for accessing a memcg's index. It will be used as an index in the
  * child cache array in kmem_cache, and also to derive its name. This function
  * will return -1 when this is not a kmem-limited memcg.
@@ -800,67 +820,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
-void __memcg_kmem_put_cache(struct kmem_cache *cachep);
-
-static inline bool __memcg_kmem_bypass(void)
-{
-	if (!memcg_kmem_enabled())
-		return true;
-	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
-		return true;
-	return false;
-}
-
-/**
- * memcg_kmem_charge: charge a kmem page
- * @page: page to charge
- * @gfp: reclaim mode
- * @order: allocation order
- *
- * Returns 0 on success, an error code on failure.
- */
-static __always_inline int memcg_kmem_charge(struct page *page,
-					     gfp_t gfp, int order)
-{
-	if (__memcg_kmem_bypass())
-		return 0;
-	if (!(gfp & __GFP_ACCOUNT))
-		return 0;
-	return __memcg_kmem_charge(page, gfp, order);
-}
-
-/**
- * memcg_kmem_uncharge: uncharge a kmem page
- * @page: page to uncharge
- * @order: allocation order
- */
-static __always_inline void memcg_kmem_uncharge(struct page *page, int order)
-{
-	if (memcg_kmem_enabled())
-		__memcg_kmem_uncharge(page, order);
-}
-
-/**
- * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
- * @cachep: the original global kmem cache
- *
- * All memory allocated from a per-memcg cache is charged to the owner memcg.
- */
-static __always_inline struct kmem_cache *
-memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	if (__memcg_kmem_bypass())
-		return cachep;
-	return __memcg_kmem_get_cache(cachep, gfp);
-}
-
-static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
-{
-	if (memcg_kmem_enabled())
-		__memcg_kmem_put_cache(cachep);
-}
-
 /**
  * memcg_kmem_update_page_stat - update kmem page state statistics
  * @page: the page
@@ -883,15 +842,6 @@ static inline bool memcg_kmem_enabled(void)
 	return false;
 }
 
-static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
-{
-	return 0;
-}
-
-static inline void memcg_kmem_uncharge(struct page *page, int order)
-{
-}
-
 static inline int memcg_cache_id(struct mem_cgroup *memcg)
 {
 	return -1;
@@ -905,16 +855,6 @@ static inline void memcg_put_cache_ids(void)
 {
 }
 
-static inline struct kmem_cache *
-memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	return cachep;
-}
-
-static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
-{
-}
-
 static inline void memcg_kmem_update_page_stat(struct page *page,
 				enum mem_cgroup_stat_index idx, int val)
 {