1 files changed, 88 insertions, 35 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e1644a24009c..222d7370134c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -97,6 +97,7 @@ struct shrinker_info {
 	struct rcu_head rcu;
 	atomic_long_t *nr_deferred;
 	unsigned long *map;
+	int map_nr_max;
 };
 
 struct lruvec_stats_percpu {
@@ -466,34 +467,34 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
 }
 
 /*
- * page_memcg_check - get the memory cgroup associated with a page
- * @page: a pointer to the page struct
+ * folio_memcg_check - Get the memory cgroup associated with a folio.
+ * @folio: Pointer to the folio.
  *
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function unlike page_memcg() can take any page
- * as an argument. It has to be used in cases when it's not known if a page
+ * Returns a pointer to the memory cgroup associated with the folio,
+ * or NULL. This function unlike folio_memcg() can take any folio
+ * as an argument. It has to be used in cases when it's not known if a folio
  * has an associated memory cgroup pointer or an object cgroups vector or
  * an object cgroup.
  *
- * For a non-kmem page any of the following ensures page and memcg binding
+ * For a non-kmem folio any of the following ensures folio and memcg binding
  * stability:
  *
- * - the page lock
+ * - the folio lock
  * - LRU isolation
- * - lock_page_memcg()
+ * - lock_folio_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.
+ * For a kmem folio a caller should hold an rcu read lock to protect memcg
+ * associated with a kmem folio from being released.
  */
-static inline struct mem_cgroup *page_memcg_check(struct page *page)
+static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
 {
 	/*
-	 * Because page->memcg_data might be changed asynchronously
-	 * for slab pages, READ_ONCE() should be used here.
+	 * Because folio->memcg_data might be changed asynchronously
+	 * for slabs, READ_ONCE() should be used here.
 	 */
-	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+	unsigned long memcg_data = READ_ONCE(folio->memcg_data);
 
 	if (memcg_data & MEMCG_DATA_OBJCGS)
 		return NULL;
@@ -508,6 +509,13 @@ 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 *page_memcg_check(struct page *page)
+{
+	if (PageTail(page))
+		return NULL;
+	return folio_memcg_check((struct folio *)page);
+}
+
 static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
 {
 	struct mem_cgroup *memcg;
@@ -615,28 +623,32 @@ static inline void mem_cgroup_protection(struct mem_cgroup *root,
 void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 				     struct mem_cgroup *memcg);
 
-static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_unprotected(struct mem_cgroup *target,
+					  struct mem_cgroup *memcg)
 {
 	/*
 	 * The root memcg doesn't account charges, and doesn't support
-	 * protection.
+	 * protection. The target memcg's protection is ignored, see
+	 * mem_cgroup_calculate_protection() and mem_cgroup_protection()
 	 */
-	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
-
+	return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) ||
+		memcg == target;
 }
 
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
-	if (!mem_cgroup_supports_protection(memcg))
+	if (mem_cgroup_unprotected(target, memcg))
 		return false;
 
 	return READ_ONCE(memcg->memory.elow) >=
 		page_counter_read(&memcg->memory);
 }
 
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
-	if (!mem_cgroup_supports_protection(memcg))
+	if (mem_cgroup_unprotected(target, memcg))
 		return false;
 
 	return READ_ONCE(memcg->memory.emin) >=
@@ -790,6 +802,11 @@ static inline void obj_cgroup_put(struct obj_cgroup *objcg)
 	percpu_ref_put(&objcg->refcnt);
 }
 
+static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
+{
+	return !memcg || css_tryget(&memcg->css);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -874,7 +891,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return match;
 }
 
-struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio);
 ino_t page_cgroup_ino(struct page *page);
 
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
@@ -1021,7 +1038,8 @@ 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 mem_cgroup_flush_stats_atomic(void);
+void mem_cgroup_flush_stats_ratelimited(void);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1161,6 +1179,11 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
 	return NULL;
 }
 
+static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline struct mem_cgroup *page_memcg_check(struct page *page)
 {
 	return NULL;
@@ -1209,12 +1232,19 @@ static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 {
 }
 
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_unprotected(struct mem_cgroup *target,
+					  struct mem_cgroup *memcg)
+{
+	return true;
+}
+static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
 	return false;
 }
 
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
 	return false;
 }
@@ -1290,6 +1320,11 @@ static inline void obj_cgroup_put(struct obj_cgroup *objcg)
 {
 }
 
+static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
+{
+	return true;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1502,7 +1537,11 @@ static inline void mem_cgroup_flush_stats(void)
 {
 }
 
-static inline void mem_cgroup_flush_stats_delayed(void)
+static inline void mem_cgroup_flush_stats_atomic(void)
+{
+}
+
+static inline void mem_cgroup_flush_stats_ratelimited(void)
 {
 }
 
@@ -1655,10 +1694,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
 static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 						  struct bdi_writeback *wb)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
 
-	if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+	memcg = folio_memcg(folio);
+	if (unlikely(memcg && &memcg->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
 }
 
@@ -1740,24 +1782,30 @@ 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 struct static_key_false memcg_bpf_enabled_key;
+static inline bool memcg_bpf_enabled(void)
+{
+	return static_branch_likely(&memcg_bpf_enabled_key);
+}
+
+extern struct static_key_false memcg_kmem_online_key;
 
-static inline bool memcg_kmem_enabled(void)
+static inline bool memcg_kmem_online(void)
 {
-	return static_branch_likely(&memcg_kmem_enabled_key);
+	return static_branch_likely(&memcg_kmem_online_key);
 }
 
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)
 {
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_online())
 		return __memcg_kmem_charge_page(page, gfp, order);
 	return 0;
 }
 
 static inline void memcg_kmem_uncharge_page(struct page *page, int order)
 {
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_online())
 		__memcg_kmem_uncharge_page(page, order);
 }
 
@@ -1778,7 +1826,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 	struct mem_cgroup *memcg;
 
-	if (!memcg_kmem_enabled())
+	if (!memcg_kmem_online())
 		return;
 
 	rcu_read_lock();
@@ -1818,7 +1866,12 @@ static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
 	return NULL;
 }
 
-static inline bool memcg_kmem_enabled(void)
+static inline bool memcg_bpf_enabled(void)
+{
+	return false;
+}
+
+static inline bool memcg_kmem_online(void)
 {
 	return false;
 }