1 files changed, 169 insertions, 112 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index cd0e2413c358..f0c4bec6565b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -28,6 +28,7 @@
 #include <linux/eventfd.h>
 #include <linux/mmzone.h>
 #include <linux/writeback.h>
+#include <linux/page-flags.h>
 
 struct mem_cgroup;
 struct page;
@@ -50,6 +51,9 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_WRITEBACK,	/* # of pages under writeback */
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
+	/* default hierarchy stats */
+	MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_NR_STAT,
 };
 
 struct mem_cgroup_reclaim_cookie {
@@ -85,37 +89,13 @@ enum mem_cgroup_events_target {
 	MEM_CGROUP_NTARGETS,
 };
 
-/*
- * Bits in struct cg_proto.flags
- */
-enum cg_proto_flags {
-	/* Currently active and new sockets should be assigned to cgroups */
-	MEMCG_SOCK_ACTIVE,
-	/* It was ever activated; we must disarm static keys on destruction */
-	MEMCG_SOCK_ACTIVATED,
-};
+#ifdef CONFIG_MEMCG
 
-struct cg_proto {
-	struct page_counter	memory_allocated;	/* Current allocated memory. */
-	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
-	int			memory_pressure;
-	long			sysctl_mem[3];
-	unsigned long		flags;
-	/*
-	 * memcg field is used to find which memcg we belong directly
-	 * Each memcg struct can hold more than one cg_proto, so container_of
-	 * won't really cut.
-	 *
-	 * The elegant solution would be having an inverse function to
-	 * proto_cgroup in struct proto, but that means polluting the structure
-	 * for everybody, instead of just for memcg users.
-	 */
-	struct mem_cgroup	*memcg;
-};
+#define MEM_CGROUP_ID_SHIFT	16
+#define MEM_CGROUP_ID_MAX	USHRT_MAX
 
-#ifdef CONFIG_MEMCG
 struct mem_cgroup_stat_cpu {
-	long count[MEM_CGROUP_STAT_NSTATS];
+	long count[MEMCG_NR_STAT];
 	unsigned long events[MEMCG_NR_EVENTS];
 	unsigned long nr_page_events;
 	unsigned long targets[MEM_CGROUP_NTARGETS];
@@ -174,6 +154,12 @@ struct mem_cgroup_thresholds {
 	struct mem_cgroup_threshold_ary *spare;
 };
 
+enum memcg_kmem_state {
+	KMEM_NONE,
+	KMEM_ALLOCATED,
+	KMEM_ONLINE,
+};
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -185,21 +171,25 @@ struct mem_cgroup {
 
 	/* Accounted resources */
 	struct page_counter memory;
+	struct page_counter swap;
+
+	/* Legacy consumer-oriented counters */
 	struct page_counter memsw;
 	struct page_counter kmem;
+	struct page_counter tcpmem;
 
 	/* Normal memory consumption range */
 	unsigned long low;
 	unsigned long high;
 
+	/* Range enforcement for interrupt charges */
+	struct work_struct high_work;
+
 	unsigned long soft_limit;
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
-	/* css_online() has been completed */
-	int initialized;
-
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -246,14 +236,16 @@ struct mem_cgroup {
 	 */
 	struct mem_cgroup_stat_cpu __percpu *stat;
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct cg_proto tcp_mem;
-#endif
-#if defined(CONFIG_MEMCG_KMEM)
+	unsigned long		socket_pressure;
+
+	/* Legacy tcp memory accounting */
+	bool			tcpmem_active;
+	int			tcpmem_pressure;
+
+#ifndef CONFIG_SLOB
         /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
-	bool kmem_acct_activated;
-	bool kmem_acct_active;
+	enum memcg_kmem_state kmem_state;
 #endif
 
 	int last_scanned_node;
@@ -275,7 +267,13 @@ struct mem_cgroup {
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };
-extern struct cgroup_subsys_state *mem_cgroup_root_css;
+
+extern struct mem_cgroup *root_mem_cgroup;
+
+static inline bool mem_cgroup_disabled(void)
+{
+	return !cgroup_subsys_enabled(memory_cgrp_subsys);
+}
 
 /**
  * mem_cgroup_events - count memory events against a cgroup
@@ -294,32 +292,72 @@ static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 bool mem_cgroup_low(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);
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      bool lrucare);
-void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
+			      bool lrucare, bool compound);
+void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
+		bool compound);
 void mem_cgroup_uncharge(struct page *page);
 void mem_cgroup_uncharge_list(struct list_head *page_list);
 
-void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage);
+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 *);
 
 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 *parent_mem_cgroup(struct mem_cgroup *memcg);
 
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+#define mem_cgroup_from_counter(counter, member)	\
+	container_of(counter, struct mem_cgroup, member)
+
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
+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);
+}
+
+/**
+ * parent_mem_cgroup - find the accounting parent of a memcg
+ * @memcg: memcg whose parent to find
+ *
+ * Returns the parent memcg, or NULL if this is the root or the memory
+ * controller is in legacy no-hierarchy mode.
+ */
+static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+{
+	if (!memcg->memory.parent)
+		return NULL;
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
+}
+
 static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 			      struct mem_cgroup *root)
 {
@@ -347,9 +385,11 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 ino_t page_cgroup_ino(struct page *page);
 
-static inline bool mem_cgroup_disabled(void)
+static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
-	return !cgroup_subsys_enabled(memory_cgrp_subsys);
+	if (mem_cgroup_disabled())
+		return true;
+	return !!(memcg->css.flags & CSS_ONLINE);
 }
 
 /*
@@ -360,20 +400,6 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 		int nr_pages);
 
-static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup *memcg;
-
-	if (mem_cgroup_disabled())
-		return true;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	memcg = mz->memcg;
-
-	return !!(memcg->css.flags & CSS_ONLINE);
-}
-
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
@@ -430,36 +456,43 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
+void lock_page_memcg(struct page *page);
+void unlock_page_memcg(struct page *page);
 
 /**
  * mem_cgroup_update_page_stat - update page state statistics
- * @memcg: memcg to account against
+ * @page: the page
  * @idx: page state item to account
  * @val: number of pages (positive or negative)
  *
- * See mem_cgroup_begin_page_stat() for locking requirements.
+ * The @page must be locked or the caller must use lock_page_memcg()
+ * to prevent double accounting when the page is concurrently being
+ * moved to another memcg:
+ *
+ *   lock_page(page) or lock_page_memcg(page)
+ *   if (TestClearPageState(page))
+ *     mem_cgroup_update_page_stat(page, state, -1);
+ *   unlock_page(page) or unlock_page_memcg(page)
  */
-static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_stat_index idx, int val)
 {
-	VM_BUG_ON(!rcu_read_lock_held());
+	VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page)));
 
-	if (memcg)
-		this_cpu_add(memcg->stat->count[idx], val);
+	if (page->mem_cgroup)
+		this_cpu_add(page->mem_cgroup->stat->count[idx], val);
 }
 
-static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
-	mem_cgroup_update_page_stat(memcg, idx, 1);
+	mem_cgroup_update_page_stat(page, idx, 1);
 }
 
-static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_dec_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
-	mem_cgroup_update_page_stat(memcg, idx, -1);
+	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
@@ -497,8 +530,17 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
 #else /* CONFIG_MEMCG */
+
+#define MEM_CGROUP_ID_SHIFT	0
+#define MEM_CGROUP_ID_MAX	0
+
 struct mem_cgroup;
 
+static inline bool mem_cgroup_disabled(void)
+{
+	return true;
+}
+
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)
@@ -513,7 +555,8 @@ static inline bool mem_cgroup_low(struct mem_cgroup *root,
 
 static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask,
-					struct mem_cgroup **memcgp)
+					struct mem_cgroup **memcgp,
+					bool compound)
 {
 	*memcgp = NULL;
 	return 0;
@@ -521,12 +564,13 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 
 static inline void mem_cgroup_commit_charge(struct page *page,
 					    struct mem_cgroup *memcg,
-					    bool lrucare)
+					    bool lrucare, bool compound)
 {
 }
 
 static inline void mem_cgroup_cancel_charge(struct page *page,
-					    struct mem_cgroup *memcg)
+					    struct mem_cgroup *memcg,
+					    bool compound)
 {
 }
 
@@ -538,7 +582,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 }
 
-static inline void mem_cgroup_replace_page(struct page *old, struct page *new)
+static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
@@ -579,18 +623,25 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
 {
 }
 
-static inline bool mem_cgroup_disabled(void)
+static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 {
-	return true;
+	return 0;
 }
 
-static inline bool
-mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	WARN_ON_ONCE(id);
+	/* XXX: This should always return root_mem_cgroup */
+	return NULL;
+}
+
+static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
 	return true;
 }
 
-static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+static inline bool
+mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 {
 	return true;
 }
@@ -612,12 +663,11 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
+static inline void lock_page_memcg(struct page *page)
 {
-	return NULL;
 }
 
-static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
+static inline void unlock_page_memcg(struct page *page)
 {
 }
 
@@ -643,12 +693,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
 	return false;
 }
 
-static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
 }
 
-static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_dec_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
 }
@@ -671,12 +721,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-enum {
-	UNDER_LIMIT,
-	SOFT_LIMIT,
-	OVER_LIMIT,
-};
-
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
@@ -703,20 +747,33 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 struct sock;
-#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 void sock_update_memcg(struct sock *sk);
 void sock_release_memcg(struct sock *sk);
-#else
-static inline void sock_update_memcg(struct sock *sk)
+bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
+void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
+#ifdef CONFIG_MEMCG
+extern struct static_key_false memcg_sockets_enabled_key;
+#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
+static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
+		return true;
+	do {
+		if (time_before(jiffies, memcg->socket_pressure))
+			return true;
+	} while ((memcg = parent_mem_cgroup(memcg)));
+	return false;
 }
-static inline void sock_release_memcg(struct sock *sk)
+#else
+#define mem_cgroup_sockets_enabled 0
+static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
+	return false;
 }
-#endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
+#endif
 
-#ifdef CONFIG_MEMCG_KMEM
-extern struct static_key memcg_kmem_enabled_key;
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
+extern struct static_key_false memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
@@ -732,12 +789,12 @@ void memcg_put_cache_ids(void);
 
 static inline bool memcg_kmem_enabled(void)
 {
-	return static_key_false(&memcg_kmem_enabled_key);
+	return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
-static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
 {
-	return memcg->kmem_acct_active;
+	return memcg->kmem_state == KMEM_ONLINE;
 }
 
 /*
@@ -757,7 +814,7 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge(struct page *page, int order);
 
 /*
- * helper for acessing a memcg's index. It will be used as an index in the
+ * 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.
  */
@@ -766,15 +823,13 @@ 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);
+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(gfp_t gfp)
+static inline bool __memcg_kmem_bypass(void)
 {
 	if (!memcg_kmem_enabled())
 		return true;
-	if (gfp & __GFP_NOACCOUNT)
-		return true;
 	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
 		return true;
 	return false;
@@ -791,7 +846,9 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp)
 static __always_inline int memcg_kmem_charge(struct page *page,
 					     gfp_t gfp, int order)
 {
-	if (__memcg_kmem_bypass(gfp))
+	if (__memcg_kmem_bypass())
+		return 0;
+	if (!(gfp & __GFP_ACCOUNT))
 		return 0;
 	return __memcg_kmem_charge(page, gfp, order);
 }
@@ -810,16 +867,15 @@ static __always_inline void memcg_kmem_uncharge(struct page *page, int order)
 /**
  * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
  * @cachep: the original global kmem cache
- * @gfp: allocation flags.
  *
  * 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(gfp))
+	if (__memcg_kmem_bypass())
 		return cachep;
-	return __memcg_kmem_get_cache(cachep);
+	return __memcg_kmem_get_cache(cachep, gfp);
 }
 
 static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
@@ -836,7 +892,7 @@ static inline bool memcg_kmem_enabled(void)
 	return false;
 }
 
-static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
 {
 	return false;
 }
@@ -872,5 +928,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
+
 #endif /* _LINUX_MEMCONTROL_H */