1 files changed, 82 insertions, 42 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5818af8eca5a..7bdcf3020d7a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -21,6 +21,7 @@
 #include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
+#include <linux/shrinker.h>
 
 struct mem_cgroup;
 struct obj_cgroup;
@@ -61,7 +62,6 @@ struct mem_cgroup_reclaim_cookie {
 #ifdef CONFIG_MEMCG
 
 #define MEM_CGROUP_ID_SHIFT	16
-#define MEM_CGROUP_ID_MAX	USHRT_MAX
 
 struct mem_cgroup_id {
 	int id;
@@ -89,17 +89,6 @@ 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];
@@ -112,6 +101,9 @@ struct lruvec_stats {
 	/* Aggregated (CPU and subtree) state */
 	long state[NR_VM_NODE_STAT_ITEMS];
 
+	/* Non-hierarchical (CPU aggregated) state */
+	long state_local[NR_VM_NODE_STAT_ITEMS];
+
 	/* Pending child counts during tree propagation */
 	long state_pending[NR_VM_NODE_STAT_ITEMS];
 };
@@ -151,7 +143,7 @@ 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 {
@@ -284,6 +276,11 @@ struct mem_cgroup {
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
+	/*
+	 * Hint of reclaim pressure for socket memroy management. Note
+	 * that this indicator should NOT be used in legacy cgroup mode
+	 * where socket memory is accounted/charged separately.
+	 */
 	unsigned long		socket_pressure;
 
 	/* Legacy tcp memory accounting */
@@ -292,7 +289,13 @@ 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
@@ -583,7 +586,7 @@ static inline void mem_cgroup_protection(struct mem_cgroup *root,
 	/*
 	 * There is no reclaim protection applied to a targeted reclaim.
 	 * We are special casing this specific case here because
-	 * mem_cgroup_protected calculation is not robust enough to keep
+	 * mem_cgroup_calculate_protection is not robust enough to keep
 	 * the protection invariant for calculated effective values for
 	 * parallel reclaimers with different reclaim target. This is
 	 * especially a problem for tail memcgs (as they have pages on LRU)
@@ -655,6 +658,8 @@ 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);
 
 /**
@@ -679,6 +684,9 @@ 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);
@@ -706,6 +714,10 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 	__mem_cgroup_uncharge_list(page_list);
 }
 
+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);
 
 /**
@@ -762,6 +774,8 @@ 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,
@@ -861,8 +875,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
  * 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.
+ * Returns the parent memcg, or NULL if this is the root.
  */
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
@@ -914,7 +927,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
-void mem_cgroup_handle_over_high(void);
+void mem_cgroup_handle_over_high(gfp_t gfp_mask);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
@@ -1020,14 +1033,12 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 {
 	struct mem_cgroup_per_node *pn;
 	long x = 0;
-	int cpu;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
+	x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -1076,15 +1087,6 @@ 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)
 {
@@ -1158,7 +1160,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
-#define MEM_CGROUP_ID_MAX	0
 
 static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 {
@@ -1246,12 +1247,23 @@ 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)
 {
@@ -1270,6 +1282,16 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 }
 
+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)
+{
+}
+
 static inline void mem_cgroup_migrate(struct folio *old, struct folio *new)
 {
 }
@@ -1307,6 +1329,11 @@ 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)
 {
@@ -1455,7 +1482,7 @@ static inline void mem_cgroup_unlock_pages(void)
 	rcu_read_unlock();
 }
 
-static inline void mem_cgroup_handle_over_high(void)
+static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
 }
 
@@ -1562,11 +1589,6 @@ 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)
 {
@@ -1727,8 +1749,8 @@ 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)
 {
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
-		return true;
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return !!memcg->tcpmem_pressure;
 	do {
 		if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
 			return true;
@@ -1760,8 +1782,26 @@ 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);
-struct obj_cgroup *get_obj_cgroup_from_page(struct page *page);
+/*
+ * 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);
@@ -1845,7 +1885,7 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
 }
 
-static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
+static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
 {
 	return NULL;
 }