1 files changed, 110 insertions, 47 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e4e24da16d2c..394fd0a887ae 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -14,6 +14,7 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/kernel.h>
 #include <linux/page_counter.h>
 #include <linux/vmpressure.h>
 #include <linux/eventfd.h>
@@ -21,6 +22,7 @@
 #include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
+#include <linux/shrinker.h>
 
 struct mem_cgroup;
 struct obj_cgroup;
@@ -88,17 +90,6 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
-/*
- * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
- * shrinkers, which have elements charged to this memcg.
- */
-struct shrinker_info {
-	struct rcu_head rcu;
-	atomic_long_t *nr_deferred;
-	unsigned long *map;
-	int map_nr_max;
-};
-
 struct lruvec_stats_percpu {
 	/* Local (CPU and cgroup) state */
 	long state[NR_VM_NODE_STAT_ITEMS];
@@ -153,7 +144,7 @@ struct mem_cgroup_threshold_ary {
 	/* Size of entries[] */
 	unsigned int size;
 	/* Array of thresholds */
-	struct mem_cgroup_threshold entries[];
+	struct mem_cgroup_threshold entries[] __counted_by(size);
 };
 
 struct mem_cgroup_thresholds {
@@ -229,6 +220,12 @@ struct mem_cgroup {
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	unsigned long zswap_max;
+
+	/*
+	 * Prevent pages from this memcg from being written back from zswap to
+	 * swap, and from being swapped out on zswap store failures.
+	 */
+	bool zswap_writeback;
 #endif
 
 	unsigned long soft_limit;
@@ -299,7 +296,13 @@ struct mem_cgroup {
 
 #ifdef CONFIG_MEMCG_KMEM
 	int kmemcg_id;
-	struct obj_cgroup __rcu *objcg;
+	/*
+	 * memcg->objcg is wiped out as a part of the objcg repaprenting
+	 * process. memcg->orig_objcg preserves a pointer (and a reference)
+	 * to the original objcg until the end of live of memcg.
+	 */
+	struct obj_cgroup __rcu	*objcg;
+	struct obj_cgroup	*orig_objcg;
 	/* list of inherited objcgs, protected by objcg_lock */
 	struct list_head objcg_list;
 #endif
@@ -328,7 +331,7 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* per-memcg mm_struct list */
 	struct lru_gen_mm_list mm_list;
 #endif
@@ -662,6 +665,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 		page_counter_read(&memcg->memory);
 }
 
+void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg);
+
 int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
 
 /**
@@ -686,6 +691,9 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
+int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
+		long nr_pages);
+
 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);
@@ -705,14 +713,16 @@ static inline void mem_cgroup_uncharge(struct folio *folio)
 	__mem_cgroup_uncharge(folio);
 }
 
-void __mem_cgroup_uncharge_list(struct list_head *page_list);
-static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+void __mem_cgroup_uncharge_folios(struct folio_batch *folios);
+static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 {
 	if (mem_cgroup_disabled())
 		return;
-	__mem_cgroup_uncharge_list(page_list);
+	__mem_cgroup_uncharge_folios(folios);
 }
 
+void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages);
+void mem_cgroup_replace_folio(struct folio *old, struct folio *new);
 void mem_cgroup_migrate(struct folio *old, struct folio *new);
 
 /**
@@ -769,6 +779,8 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
+struct mem_cgroup *get_mem_cgroup_from_current(void);
+
 struct lruvec *folio_lruvec_lock(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
@@ -814,6 +826,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return !memcg || css_tryget(&memcg->css);
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return !memcg || css_tryget_online(&memcg->css);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -1039,8 +1056,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
-void mem_cgroup_flush_stats(void);
-void mem_cgroup_flush_stats_ratelimited(void);
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1080,15 +1097,6 @@ static inline void count_memcg_events(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
-static inline void count_memcg_page_event(struct page *page,
-					  enum vm_event_item idx)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		count_memcg_events(memcg, idx, 1);
-}
-
 static inline void count_memcg_folio_events(struct folio *folio,
 		enum vm_event_item idx, unsigned long nr)
 {
@@ -1153,7 +1161,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 	rcu_read_unlock();
 }
 
-void split_page_memcg(struct page *head, unsigned int nr);
+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,
@@ -1189,6 +1197,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	return NULL;
+}
+
 static inline bool folio_memcg_kmem(struct folio *folio)
 {
 	return false;
@@ -1249,12 +1262,23 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 	return false;
 }
 
+static inline void mem_cgroup_commit_charge(struct folio *folio,
+		struct mem_cgroup *memcg)
+{
+}
+
 static inline int mem_cgroup_charge(struct folio *folio,
 		struct mm_struct *mm, gfp_t gfp)
 {
 	return 0;
 }
 
+static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg,
+		gfp_t gfp, long nr_pages)
+{
+	return 0;
+}
+
 static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
 			struct mm_struct *mm, gfp_t gfp, swp_entry_t entry)
 {
@@ -1269,7 +1293,17 @@ static inline void mem_cgroup_uncharge(struct folio *folio)
 {
 }
 
-static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
+{
+}
+
+static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
+		unsigned int nr_pages)
+{
+}
+
+static inline void mem_cgroup_replace_folio(struct folio *old,
+		struct folio *new)
 {
 }
 
@@ -1310,6 +1344,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+{
+	return NULL;
+}
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
 {
@@ -1325,6 +1364,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return true;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1524,11 +1568,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void mem_cgroup_flush_stats(void)
+static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
 }
 
-static inline void mem_cgroup_flush_stats_ratelimited(void)
+static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 }
 
@@ -1565,11 +1609,6 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg,
 {
 }
 
-static inline void count_memcg_page_event(struct page *page,
-					  int idx)
-{
-}
-
 static inline void count_memcg_folio_events(struct folio *folio,
 		enum vm_event_item idx, unsigned long nr)
 {
@@ -1580,7 +1619,7 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
 
-static inline void split_page_memcg(struct page *head, unsigned int nr)
+static inline void split_page_memcg(struct page *head, int old_order, int new_order)
 {
 }
 
@@ -1654,18 +1693,18 @@ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
 	return folio_lruvec_lock_irq(folio);
 }
 
-/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio,
-		struct lruvec *locked_lruvec, unsigned long *flags)
+/* Don't lock again iff folio's lruvec locked */
+static inline void folio_lruvec_relock_irqsave(struct folio *folio,
+		struct lruvec **lruvecp, unsigned long *flags)
 {
-	if (locked_lruvec) {
-		if (folio_matches_lruvec(folio, locked_lruvec))
-			return locked_lruvec;
+	if (*lruvecp) {
+		if (folio_matches_lruvec(folio, *lruvecp))
+			return;
 
-		unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
+		unlock_page_lruvec_irqrestore(*lruvecp, *flags);
 	}
 
-	return folio_lruvec_lock_irqsave(folio, flags);
+	*lruvecp = folio_lruvec_lock_irqsave(folio, flags);
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -1763,9 +1802,27 @@ 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);
 
-struct obj_cgroup *get_obj_cgroup_from_current(void);
+/*
+ * The returned objcg pointer is safe to use without additional
+ * protection within a scope. The scope is defined either by
+ * the current task (similar to the "current" global variable)
+ * or by set_active_memcg() pair.
+ * Please, use obj_cgroup_get() to get a reference if the pointer
+ * needs to be used outside of the local scope.
+ */
+struct obj_cgroup *current_obj_cgroup(void);
 struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio);
 
+static inline struct obj_cgroup *get_obj_cgroup_from_current(void)
+{
+	struct obj_cgroup *objcg = current_obj_cgroup();
+
+	if (objcg)
+		obj_cgroup_get(objcg);
+
+	return objcg;
+}
+
 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);
 
@@ -1889,6 +1946,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 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);
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
 #else
 static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 {
@@ -1902,6 +1960,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
 					     size_t size)
 {
 }
+static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return true;
+}
 #endif
 
 #endif /* _LINUX_MEMCONTROL_H */