1 files changed, 191 insertions, 72 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e34112f6a369..e1644a24009c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -33,6 +33,10 @@ enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
 	MEMCG_PERCPU_B,
+	MEMCG_VMALLOC,
+	MEMCG_KMEM,
+	MEMCG_ZSWAP_B,
+	MEMCG_ZSWAPPED,
 	MEMCG_NR_STAT,
 };
 
@@ -42,6 +46,7 @@ enum memcg_memory_event {
 	MEMCG_MAX,
 	MEMCG_OOM,
 	MEMCG_OOM_KILL,
+	MEMCG_OOM_GROUP_KILL,
 	MEMCG_SWAP_HIGH,
 	MEMCG_SWAP_MAX,
 	MEMCG_SWAP_FAIL,
@@ -75,29 +80,8 @@ enum mem_cgroup_events_target {
 	MEM_CGROUP_NTARGETS,
 };
 
-struct memcg_vmstats_percpu {
-	/* Local (CPU and cgroup) page state & events */
-	long			state[MEMCG_NR_STAT];
-	unsigned long		events[NR_VM_EVENT_ITEMS];
-
-	/* Delta calculation for lockless upward propagation */
-	long			state_prev[MEMCG_NR_STAT];
-	unsigned long		events_prev[NR_VM_EVENT_ITEMS];
-
-	/* Cgroup1: threshold notifications & softlimit tree updates */
-	unsigned long		nr_page_events;
-	unsigned long		targets[MEM_CGROUP_NTARGETS];
-};
-
-struct memcg_vmstats {
-	/* Aggregated (CPU and subtree) page state & events */
-	long			state[MEMCG_NR_STAT];
-	unsigned long		events[NR_VM_EVENT_ITEMS];
-
-	/* Pending child counts during tree propagation */
-	long			state_pending[MEMCG_NR_STAT];
-	unsigned long		events_pending[NR_VM_EVENT_ITEMS];
-};
+struct memcg_vmstats_percpu;
+struct memcg_vmstats;
 
 struct mem_cgroup_reclaim_iter {
 	struct mem_cgroup *position;
@@ -180,15 +164,6 @@ struct mem_cgroup_thresholds {
 	struct mem_cgroup_threshold_ary *spare;
 };
 
-#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
-
 /*
  * Remember four most recent foreign writebacks with dirty pages in this
  * cgroup.  Inode sharing is expected to be uncommon and, even if we miss
@@ -217,7 +192,7 @@ struct obj_cgroup {
 	struct mem_cgroup *memcg;
 	atomic_t nr_charged_bytes;
 	union {
-		struct list_head list;
+		struct list_head list; /* protected by objcg_lock */
 		struct rcu_head rcu;
 	};
 };
@@ -249,6 +224,10 @@ struct mem_cgroup {
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	unsigned long zswap_max;
+#endif
+
 	unsigned long soft_limit;
 
 	/* vmpressure notifications */
@@ -295,10 +274,10 @@ struct mem_cgroup {
 	spinlock_t		move_lock;
 	unsigned long		move_lock_flags;
 
-	MEMCG_PADDING(_pad1_);
+	CACHELINE_PADDING(_pad1_);
 
 	/* memory.stat */
-	struct memcg_vmstats	vmstats;
+	struct memcg_vmstats	*vmstats;
 
 	/* memory.events */
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
@@ -313,10 +292,11 @@ struct mem_cgroup {
 #ifdef CONFIG_MEMCG_KMEM
 	int kmemcg_id;
 	struct obj_cgroup __rcu *objcg;
-	struct list_head objcg_list; /* list of inherited objcgs */
+	/* list of inherited objcgs, protected by objcg_lock */
+	struct list_head objcg_list;
 #endif
 
-	MEMCG_PADDING(_pad2_);
+	CACHELINE_PADDING(_pad2_);
 
 	/*
 	 * set > 0 if pages under this cgroup are moving to other cgroup.
@@ -340,14 +320,20 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
+#ifdef CONFIG_LRU_GEN
+	/* per-memcg mm_struct list */
+	struct lru_gen_mm_list mm_list;
+#endif
+
 	struct mem_cgroup_per_node *nodeinfo[];
 };
 
 /*
- * size of first charge trial. "32" comes from vmscan.c's magic value.
- * TODO: maybe necessary to use big numbers in big irons.
+ * size of first charge trial.
+ * TODO: maybe necessary to use big numbers in big irons or dynamic based of the
+ * workload.
  */
-#define MEMCG_CHARGE_BATCH 32U
+#define MEMCG_CHARGE_BATCH 64U
 
 extern struct mem_cgroup *root_mem_cgroup;
 
@@ -434,6 +420,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
  * - LRU isolation
  * - lock_page_memcg()
  * - exclusive reference
+ * - mem_cgroup_trylock_pages()
  *
  * For a kmem folio a caller should hold an rcu read lock to protect memcg
  * associated with a kmem folio from being released.
@@ -495,6 +482,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
  * - LRU isolation
  * - lock_page_memcg()
  * - exclusive reference
+ * - mem_cgroup_trylock_pages()
  *
  * For a kmem page a caller should hold an rcu read lock to protect memcg
  * associated with a kmem page from being released.
@@ -520,6 +508,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+retry:
+	memcg = obj_cgroup_memcg(objcg);
+	if (unlikely(!css_tryget(&memcg->css)))
+		goto retry;
+	rcu_read_unlock();
+
+	return memcg;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
@@ -665,7 +667,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
-int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
+int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
 				  gfp_t gfp, swp_entry_t entry);
 void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
 
@@ -813,6 +815,15 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 }
 struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
 
+#ifdef CONFIG_SHRINKER_DEBUG
+static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg)
+{
+	return memcg ? cgroup_ino(memcg->css.cgroup) : 0;
+}
+
+struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino);
+#endif
+
 static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
 {
 	return mem_cgroup_from_css(seq_css(m));
@@ -838,9 +849,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
  */
 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);
+	return mem_cgroup_from_css(memcg->css.parent);
 }
 
 static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
@@ -921,10 +930,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 					    struct mem_cgroup *oom_domain);
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
-#ifdef CONFIG_MEMCG_SWAP
-extern bool cgroup_memory_noswap;
-#endif
-
 void folio_memcg_lock(struct folio *folio);
 void folio_memcg_unlock(struct folio *folio);
 void lock_page_memcg(struct page *page);
@@ -932,6 +937,23 @@ void unlock_page_memcg(struct page *page);
 
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
 
+/* try to stablize folio_memcg() for all the pages in a memcg */
+static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
+{
+	rcu_read_lock();
+
+	if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account))
+		return true;
+
+	rcu_read_unlock();
+	return false;
+}
+
+static inline void mem_cgroup_unlock_pages(void)
+{
+	rcu_read_unlock();
+}
+
 /* 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)
@@ -943,21 +965,39 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
-static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+static inline void mod_memcg_page_state(struct page *page,
+					int idx, int val)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = page_memcg(page);
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
+	rcu_read_unlock();
 }
 
+unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
+
 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);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
@@ -981,6 +1021,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 }
 
 void mem_cgroup_flush_stats(void);
+void mem_cgroup_flush_stats_delayed(void);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1029,6 +1070,15 @@ static inline void count_memcg_page_event(struct page *page,
 		count_memcg_events(memcg, idx, 1);
 }
 
+static inline void count_memcg_folio_events(struct folio *folio,
+		enum vm_event_item idx, unsigned long nr)
+{
+	struct mem_cgroup *memcg = folio_memcg(folio);
+
+	if (memcg)
+		count_memcg_events(memcg, idx, nr);
+}
+
 static inline void count_memcg_event_mm(struct mm_struct *mm,
 					enum vm_event_item idx)
 {
@@ -1175,7 +1225,7 @@ static inline int mem_cgroup_charge(struct folio *folio,
 	return 0;
 }
 
-static inline int mem_cgroup_swapin_charge_page(struct page *page,
+static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
 			struct mm_struct *mm, gfp_t gfp, swp_entry_t entry)
 {
 	return 0;
@@ -1236,6 +1286,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
 	return NULL;
 }
 
+static inline void obj_cgroup_put(struct obj_cgroup *objcg)
+{
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1296,6 +1350,18 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 	return NULL;
 }
 
+#ifdef CONFIG_SHRINKER_DEBUG
+static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
+static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino)
+{
+	return NULL;
+}
+#endif
+
 static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
 {
 	return NULL;
@@ -1354,6 +1420,18 @@ static inline void folio_memcg_unlock(struct folio *folio)
 {
 }
 
+static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
+{
+	/* to match folio_memcg_rcu() */
+	rcu_read_lock();
+	return true;
+}
+
+static inline void mem_cgroup_unlock_pages(void)
+{
+	rcu_read_unlock();
+}
+
 static inline void mem_cgroup_handle_over_high(void)
 {
 }
@@ -1398,6 +1476,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 {
 }
 
+static inline void mod_memcg_page_state(struct page *page,
+					int idx, int val)
+{
+}
+
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
 	return 0;
@@ -1419,6 +1502,10 @@ static inline void mem_cgroup_flush_stats(void)
 {
 }
 
+static inline void mem_cgroup_flush_stats_delayed(void)
+{
+}
+
 static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
 					    enum node_stat_item idx, int val)
 {
@@ -1457,6 +1544,11 @@ static inline void count_memcg_page_event(struct page *page,
 {
 }
 
+static inline void count_memcg_folio_events(struct folio *folio,
+		enum vm_event_item idx, unsigned long nr)
+{
+}
+
 static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
@@ -1643,24 +1735,13 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
 struct obj_cgroup *get_obj_cgroup_from_current(void);
+struct obj_cgroup *get_obj_cgroup_from_page(struct page *page);
 
 int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
 void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
 
 extern struct static_key_false memcg_kmem_enabled_key;
 
-extern int memcg_nr_cache_ids;
-void memcg_get_cache_ids(void);
-void memcg_put_cache_ids(void);
-
-/*
- * Helper macro to loop through all memcg-specific caches. Callers must still
- * check if the cache is valid (it is either valid or NULL).
- * the slab_mutex must be held when looping through those caches
- */
-#define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
-
 static inline bool memcg_kmem_enabled(void)
 {
 	return static_branch_likely(&memcg_kmem_enabled_key);
@@ -1684,12 +1765,27 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order)
  * A helper for accessing memcg's kmem_id, used for getting
  * corresponding LRU lists.
  */
-static inline int memcg_cache_id(struct mem_cgroup *memcg)
+static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 {
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
 struct mem_cgroup *mem_cgroup_from_obj(void *p);
+struct mem_cgroup *mem_cgroup_from_slab_obj(void *p);
+
+static inline void count_objcg_event(struct obj_cgroup *objcg,
+				     enum vm_event_item idx)
+{
+	struct mem_cgroup *memcg;
+
+	if (!memcg_kmem_enabled())
+		return;
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	count_memcg_events(memcg, idx, 1);
+	rcu_read_unlock();
+}
 
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
@@ -1717,32 +1813,55 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
 }
 
-#define for_each_memcg_cache_index(_idx)	\
-	for (; NULL; )
+static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
 
 static inline bool memcg_kmem_enabled(void)
 {
 	return false;
 }
 
-static inline int memcg_cache_id(struct mem_cgroup *memcg)
+static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 {
 	return -1;
 }
 
-static inline void memcg_get_cache_ids(void)
+static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
 {
+	return NULL;
 }
 
-static inline void memcg_put_cache_ids(void)
+static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
 {
+	return NULL;
 }
 
-static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
+static inline void count_objcg_event(struct obj_cgroup *objcg,
+				     enum vm_event_item idx)
 {
-       return NULL;
 }
 
 #endif /* CONFIG_MEMCG_KMEM */
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
+void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
+void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+#else
+static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
+{
+	return true;
+}
+static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg,
+					   size_t size)
+{
+}
+static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
+					     size_t size)
+{
+}
+#endif
+
 #endif /* _LINUX_MEMCONTROL_H */