1 files changed, 174 insertions, 189 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 030d34e9d117..7e2eb091049a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -69,18 +69,6 @@ struct mem_cgroup_id {
 	refcount_t ref;
 };
 
-/*
- * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremented by the number of pages. This counter is used
- * to trigger some periodic events. This is straightforward and better
- * than using jiffies etc. to handle periodic memcg event.
- */
-enum mem_cgroup_events_target {
-	MEM_CGROUP_TARGET_THRESH,
-	MEM_CGROUP_TARGET_SOFTLIMIT,
-	MEM_CGROUP_NTARGETS,
-};
-
 struct memcg_vmstats_percpu;
 struct memcg_vmstats;
 struct lruvec_stats_percpu;
@@ -96,23 +84,33 @@ struct mem_cgroup_reclaim_iter {
  * per-node information in memory controller.
  */
 struct mem_cgroup_per_node {
-	struct lruvec		lruvec;
+	/* Keep the read-only fields at the start */
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
+						/* use container_of	   */
 
 	struct lruvec_stats_percpu __percpu	*lruvec_stats_percpu;
 	struct lruvec_stats			*lruvec_stats;
-
-	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
-
-	struct mem_cgroup_reclaim_iter	iter;
-
 	struct shrinker_info __rcu	*shrinker_info;
 
+#ifdef CONFIG_MEMCG_V1
+	/*
+	 * Memcg-v1 only stuff in middle as buffer between read mostly fields
+	 * and update often fields to avoid false sharing. If v1 stuff is
+	 * not present, an explicit padding is needed.
+	 */
+
 	struct rb_node		tree_node;	/* RB tree node */
 	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
-	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
-						/* use container_of	   */
+#else
+	CACHELINE_PADDING(_pad1_);
+#endif
+
+	/* Fields which get updated often at the end. */
+	struct lruvec		lruvec;
+	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
+	struct mem_cgroup_reclaim_iter	iter;
 };
 
 struct mem_cgroup_threshold {
@@ -194,14 +192,10 @@ struct mem_cgroup {
 		struct page_counter memsw;	/* v1 only */
 	};
 
-	/* Legacy consumer-oriented counters */
-	struct page_counter kmem;		/* v1 only */
-	struct page_counter tcpmem;		/* v1 only */
-
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+#ifdef CONFIG_ZSWAP
 	unsigned long zswap_max;
 
 	/*
@@ -211,8 +205,6 @@ struct mem_cgroup {
 	bool zswap_writeback;
 #endif
 
-	unsigned long soft_limit;
-
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
@@ -221,13 +213,7 @@ struct mem_cgroup {
 	 */
 	bool oom_group;
 
-	/* protected by memcg_oom_lock */
-	bool		oom_lock;
-	int		under_oom;
-
-	int	swappiness;
-	/* OOM-Killer disable */
-	int		oom_kill_disable;
+	int swappiness;
 
 	/* memory.events and memory.events.local */
 	struct cgroup_file events_file;
@@ -236,29 +222,6 @@ struct mem_cgroup {
 	/* handle for "memory.swap.events" */
 	struct cgroup_file swap_events_file;
 
-	/* protect arrays of thresholds */
-	struct mutex thresholds_lock;
-
-	/* thresholds for memory usage. RCU-protected */
-	struct mem_cgroup_thresholds thresholds;
-
-	/* thresholds for mem+swap usage. RCU-protected */
-	struct mem_cgroup_thresholds memsw_thresholds;
-
-	/* For oom notifier event fd */
-	struct list_head oom_notify;
-
-	/*
-	 * Should we move charges of a task when a task is moved into this
-	 * mem_cgroup ? And what type of charges should we move ?
-	 */
-	unsigned long move_charge_at_immigrate;
-	/* taken only while moving_account > 0 */
-	spinlock_t		move_lock;
-	unsigned long		move_lock_flags;
-
-	CACHELINE_PADDING(_pad1_);
-
 	/* memory.stat */
 	struct memcg_vmstats	*vmstats;
 
@@ -273,11 +236,6 @@ struct mem_cgroup {
 	 */
 	unsigned long		socket_pressure;
 
-	/* Legacy tcp memory accounting */
-	bool			tcpmem_active;
-	int			tcpmem_pressure;
-
-#ifdef CONFIG_MEMCG_KMEM
 	int kmemcg_id;
 	/*
 	 * memcg->objcg is wiped out as a part of the objcg repaprenting
@@ -288,15 +246,6 @@ struct mem_cgroup {
 	struct obj_cgroup	*orig_objcg;
 	/* list of inherited objcgs, protected by objcg_lock */
 	struct list_head objcg_list;
-#endif
-
-	CACHELINE_PADDING(_pad2_);
-
-	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
-	 */
-	atomic_t		moving_account;
-	struct task_struct	*move_lock_task;
 
 	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
 
@@ -306,10 +255,6 @@ struct mem_cgroup {
 	struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
 #endif
 
-	/* List of events which userspace want to receive */
-	struct list_head event_list;
-	spinlock_t event_list_lock;
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	struct deferred_split deferred_split_queue;
 #endif
@@ -319,6 +264,56 @@ struct mem_cgroup {
 	struct lru_gen_mm_list mm_list;
 #endif
 
+#ifdef CONFIG_MEMCG_V1
+	/* Legacy consumer-oriented counters */
+	struct page_counter kmem;		/* v1 only */
+	struct page_counter tcpmem;		/* v1 only */
+
+	unsigned long soft_limit;
+
+	/* protected by memcg_oom_lock */
+	bool oom_lock;
+	int under_oom;
+
+	/* OOM-Killer disable */
+	int oom_kill_disable;
+
+	/* protect arrays of thresholds */
+	struct mutex thresholds_lock;
+
+	/* thresholds for memory usage. RCU-protected */
+	struct mem_cgroup_thresholds thresholds;
+
+	/* thresholds for mem+swap usage. RCU-protected */
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
+
+	/*
+	 * Should we move charges of a task when a task is moved into this
+	 * mem_cgroup ? And what type of charges should we move ?
+	 */
+	unsigned long move_charge_at_immigrate;
+	/* taken only while moving_account > 0 */
+	spinlock_t move_lock;
+	unsigned long move_lock_flags;
+
+	/* Legacy tcp memory accounting */
+	bool tcpmem_active;
+	int tcpmem_pressure;
+
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t moving_account;
+	struct task_struct *move_lock_task;
+
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+#endif /* CONFIG_MEMCG_V1 */
+
 	struct mem_cgroup_per_node *nodeinfo[];
 };
 
@@ -443,11 +438,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 	return __folio_memcg(folio);
 }
 
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return folio_memcg(page_folio(page));
-}
-
 /**
  * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio.
  * @folio: Pointer to the folio.
@@ -540,7 +530,6 @@ retry:
 	return memcg;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
 /*
  * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
  * @folio: Pointer to the folio.
@@ -556,15 +545,6 @@ static inline bool folio_memcg_kmem(struct folio *folio)
 	return folio->memcg_data & MEMCG_DATA_KMEM;
 }
 
-
-#else
-static inline bool folio_memcg_kmem(struct folio *folio)
-{
-	return false;
-}
-
-#endif
-
 static inline bool PageMemcgKmem(struct page *page)
 {
 	return folio_memcg_kmem(page_folio(page));
@@ -949,51 +929,13 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 
 void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
 
-static inline void mem_cgroup_enter_user_fault(void)
-{
-	WARN_ON(current->in_user_fault);
-	current->in_user_fault = 1;
-}
-
-static inline void mem_cgroup_exit_user_fault(void)
-{
-	WARN_ON(!current->in_user_fault);
-	current->in_user_fault = 0;
-}
-
-static inline bool task_in_memcg_oom(struct task_struct *p)
-{
-	return p->memcg_in_oom;
-}
-
-bool mem_cgroup_oom_synchronize(bool wait);
 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);
 
-void folio_memcg_lock(struct folio *folio);
-void folio_memcg_unlock(struct folio *folio);
-
 void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item 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,
 				   enum memcg_stat_item idx, int val)
@@ -1014,7 +956,7 @@ static inline void mod_memcg_page_state(struct page *page,
 		return;
 
 	rcu_read_lock();
-	memcg = page_memcg(page);
+	memcg = folio_memcg(page_folio(page));
 	if (memcg)
 		mod_memcg_state(memcg, idx, val);
 	rcu_read_unlock();
@@ -1120,10 +1062,6 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 
 void split_page_memcg(struct page *head, int old_order, int new_order);
 
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-						gfp_t gfp_mask,
-						unsigned long *total_scanned);
-
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
@@ -1133,11 +1071,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 	return NULL;
 }
 
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return NULL;
-}
-
 static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
@@ -1439,48 +1372,10 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
 }
 
-static inline void folio_memcg_lock(struct folio *folio)
-{
-}
-
-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(gfp_t gfp_mask)
 {
 }
 
-static inline void mem_cgroup_enter_user_fault(void)
-{
-}
-
-static inline void mem_cgroup_exit_user_fault(void)
-{
-}
-
-static inline bool task_in_memcg_oom(struct task_struct *p)
-{
-	return false;
-}
-
-static inline bool mem_cgroup_oom_synchronize(bool wait)
-{
-	return false;
-}
-
 static inline struct mem_cgroup *mem_cgroup_get_oom_group(
 	struct task_struct *victim, struct mem_cgroup *oom_domain)
 {
@@ -1574,14 +1469,6 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 static inline void split_page_memcg(struct page *head, int old_order, int new_order)
 {
 }
-
-static inline
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-					    gfp_t gfp_mask,
-					    unsigned long *total_scanned)
-{
-	return 0;
-}
 #endif /* CONFIG_MEMCG */
 
 /*
@@ -1589,7 +1476,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
  * if MEMCG_DATA_OBJEXTS is set.
  */
 struct slabobj_ext {
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	struct obj_cgroup *objcg;
 #endif
 #ifdef CONFIG_MEM_ALLOC_PROFILING
@@ -1636,7 +1523,7 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
 }
 
-/* Test requires a stable page->memcg binding, see page_memcg() */
+/* Test requires a stable folio->memcg binding, see folio_memcg() */
 static inline bool folio_matches_lruvec(struct folio *folio,
 		struct lruvec *lruvec)
 {
@@ -1734,8 +1621,10 @@ void mem_cgroup_sk_alloc(struct sock *sk);
 void mem_cgroup_sk_free(struct sock *sk);
 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
+#ifdef CONFIG_MEMCG_V1
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return !!memcg->tcpmem_pressure;
+#endif /* CONFIG_MEMCG_V1 */
 	do {
 		if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
 			return true;
@@ -1762,7 +1651,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg,
 }
 #endif
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 bool mem_cgroup_kmem_disabled(void);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
@@ -1905,9 +1794,9 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 }
 
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG */
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+#if defined(CONFIG_MEMCG) && 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);
@@ -1932,4 +1821,100 @@ static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
 }
 #endif
 
+
+/* Cgroup v1-related declarations */
+
+#ifdef CONFIG_MEMCG_V1
+unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					gfp_t gfp_mask,
+					unsigned long *total_scanned);
+
+bool mem_cgroup_oom_synchronize(bool wait);
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return p->memcg_in_oom;
+}
+
+void folio_memcg_lock(struct folio *folio);
+void folio_memcg_unlock(struct folio *folio);
+
+/* 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();
+}
+
+static inline void mem_cgroup_enter_user_fault(void)
+{
+	WARN_ON(current->in_user_fault);
+	current->in_user_fault = 1;
+}
+
+static inline void mem_cgroup_exit_user_fault(void)
+{
+	WARN_ON(!current->in_user_fault);
+	current->in_user_fault = 0;
+}
+
+#else /* CONFIG_MEMCG_V1 */
+static inline
+unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					gfp_t gfp_mask,
+					unsigned long *total_scanned)
+{
+	return 0;
+}
+
+static inline void folio_memcg_lock(struct folio *folio)
+{
+}
+
+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 bool task_in_memcg_oom(struct task_struct *p)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(bool wait)
+{
+	return false;
+}
+
+static inline void mem_cgroup_enter_user_fault(void)
+{
+}
+
+static inline void mem_cgroup_exit_user_fault(void)
+{
+}
+
+#endif /* CONFIG_MEMCG_V1 */
+
 #endif /* _LINUX_MEMCONTROL_H */