1 files changed, 217 insertions, 55 deletions

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 322dcbfcc933..b2ccb6845595 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -10,15 +10,8 @@
 #include <linux/static_key.h>
 #include <linux/mmdebug.h>
 
-extern int sysctl_stat_interval;
-
 #ifdef CONFIG_NUMA
-#define ENABLE_NUMA_STAT   1
-#define DISABLE_NUMA_STAT   0
-extern int sysctl_vm_numa_stat;
 DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
-int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
 struct reclaim_stat {
@@ -32,12 +25,16 @@ struct reclaim_stat {
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
 	unsigned nr_lazyfree_fail;
+	unsigned nr_demoted;
 };
 
-enum writeback_stat_item {
+/* Stat data for system wide items */
+enum vm_stat_item {
 	NR_DIRTY_THRESHOLD,
 	NR_DIRTY_BG_THRESHOLD,
-	NR_VM_WRITEBACK_STAT_ITEMS,
+	NR_MEMMAP_PAGES,	/* page metadata allocated through buddy allocator */
+	NR_MEMMAP_BOOT_PAGES,	/* page metadata allocated through boot allocator */
+	NR_VM_STAT_ITEMS,
 };
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
@@ -125,10 +122,10 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
 #endif
 
-#ifdef CONFIG_DEBUG_VM_VMACACHE
-#define count_vm_vmacache_event(x) count_vm_event(x)
+#ifdef CONFIG_PER_VMA_LOCK_STATS
+#define count_vm_vma_lock_event(x) count_vm_event(x)
 #else
-#define count_vm_vmacache_event(x) do {} while (0)
+#define count_vm_vma_lock_event(x) do {} while (0)
 #endif
 
 #define __count_zid_vm_events(item, zid, delta) \
@@ -138,34 +135,27 @@ static inline void vm_events_fold_cpu(int cpu)
  * Zone and node-based page accounting with per cpu differentials.
  */
 extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
-extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
 extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
+extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
 
 #ifdef CONFIG_NUMA
-static inline void zone_numa_state_add(long x, struct zone *zone,
-				 enum numa_stat_item item)
+static inline void zone_numa_event_add(long x, struct zone *zone,
+				enum numa_stat_item item)
 {
-	atomic_long_add(x, &zone->vm_numa_stat[item]);
-	atomic_long_add(x, &vm_numa_stat[item]);
+	atomic_long_add(x, &zone->vm_numa_event[item]);
+	atomic_long_add(x, &vm_numa_event[item]);
 }
 
-static inline unsigned long global_numa_state(enum numa_stat_item item)
+static inline unsigned long zone_numa_event_state(struct zone *zone,
+					enum numa_stat_item item)
 {
-	long x = atomic_long_read(&vm_numa_stat[item]);
-
-	return x;
+	return atomic_long_read(&zone->vm_numa_event[item]);
 }
 
-static inline unsigned long zone_numa_state_snapshot(struct zone *zone,
-					enum numa_stat_item item)
+static inline unsigned long
+global_numa_event_state(enum numa_stat_item item)
 {
-	long x = atomic_long_read(&zone->vm_numa_stat[item]);
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item];
-
-	return x;
+	return atomic_long_read(&vm_numa_event[item]);
 }
 #endif /* CONFIG_NUMA */
 
@@ -236,7 +226,7 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 #ifdef CONFIG_SMP
 	int cpu;
 	for_each_online_cpu(cpu)
-		x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];
+		x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item];
 
 	if (x < 0)
 		x = 0;
@@ -245,18 +235,38 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 }
 
 #ifdef CONFIG_NUMA
-extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
+/* See __count_vm_event comment on why raw_cpu_inc is used. */
+static inline void
+__count_numa_event(struct zone *zone, enum numa_stat_item item)
+{
+	struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats;
+
+	raw_cpu_inc(pzstats->vm_numa_event[item]);
+}
+
+static inline void
+__count_numa_events(struct zone *zone, enum numa_stat_item item, long delta)
+{
+	struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats;
+
+	raw_cpu_add(pzstats->vm_numa_event[item], delta);
+}
+
 extern unsigned long sum_zone_node_page_state(int node,
 					      enum zone_stat_item item);
-extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
+extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item);
 extern unsigned long node_page_state(struct pglist_data *pgdat,
 						enum node_stat_item item);
 extern unsigned long node_page_state_pages(struct pglist_data *pgdat,
 					   enum node_stat_item item);
+extern void fold_vm_numa_events(void);
 #else
 #define sum_zone_node_page_state(node, item) global_zone_page_state(item)
 #define node_page_state(node, item) global_node_page_state(item)
 #define node_page_state_pages(node, item) global_node_page_state_pages(item)
+static inline void fold_vm_numa_events(void)
+{
+}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP
@@ -287,11 +297,7 @@ void quiet_vmstat(void);
 void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
-struct ctl_table;
-int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp,
-		loff_t *ppos);
-
-void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
+void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *);
 
 int calculate_pressure_threshold(struct zone *zone);
 int calculate_normal_threshold(struct zone *zone);
@@ -313,6 +319,12 @@ static inline void __mod_node_page_state(struct pglist_data *pgdat,
 			enum node_stat_item item, int delta)
 {
 	if (vmstat_item_in_bytes(item)) {
+		/*
+		 * Only cgroups use subpage accounting right now; at
+		 * the global level, these items still change in
+		 * multiples of whole pages. Store them as pages
+		 * internally to keep the per-cpu counters compact.
+		 */
 		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
 		delta >>= PAGE_SHIFT;
 	}
@@ -393,15 +405,79 @@ static inline void cpu_vm_stats_fold(int cpu) { }
 static inline void quiet_vmstat(void) { }
 
 static inline void drain_zonestat(struct zone *zone,
-			struct per_cpu_pageset *pset) { }
+			struct per_cpu_zonestat *pzstats) { }
 #endif		/* CONFIG_SMP */
 
-static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
-					     int migratetype)
+static inline void __zone_stat_mod_folio(struct folio *folio,
+		enum zone_stat_item item, long nr)
+{
+	__mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void __zone_stat_add_folio(struct folio *folio,
+		enum zone_stat_item item)
+{
+	__mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __zone_stat_sub_folio(struct folio *folio,
+		enum zone_stat_item item)
+{
+	__mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void zone_stat_mod_folio(struct folio *folio,
+		enum zone_stat_item item, long nr)
+{
+	mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void zone_stat_add_folio(struct folio *folio,
+		enum zone_stat_item item)
+{
+	mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void zone_stat_sub_folio(struct folio *folio,
+		enum zone_stat_item item)
+{
+	mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void __node_stat_mod_folio(struct folio *folio,
+		enum node_stat_item item, long nr)
+{
+	__mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void __node_stat_add_folio(struct folio *folio,
+		enum node_stat_item item)
+{
+	__mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __node_stat_sub_folio(struct folio *folio,
+		enum node_stat_item item)
+{
+	__mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void node_stat_mod_folio(struct folio *folio,
+		enum node_stat_item item, long nr)
+{
+	mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void node_stat_add_folio(struct folio *folio,
+		enum node_stat_item item)
+{
+	mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void node_stat_sub_folio(struct folio *folio,
+		enum node_stat_item item)
 {
-	__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
-	if (is_migrate_cma(migratetype))
-		__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
+	mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
 }
 
 extern const char * const vmstat_text[];
@@ -422,7 +498,7 @@ static inline const char *numa_stat_name(enum numa_stat_item item)
 static inline const char *node_stat_name(enum node_stat_item item)
 {
 	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
-			   NR_VM_NUMA_STAT_ITEMS +
+			   NR_VM_NUMA_EVENT_ITEMS +
 			   item];
 }
 
@@ -431,23 +507,109 @@ static inline const char *lru_list_name(enum lru_list lru)
 	return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
 }
 
-static inline const char *writeback_stat_name(enum writeback_stat_item item)
-{
-	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
-			   NR_VM_NUMA_STAT_ITEMS +
-			   NR_VM_NODE_STAT_ITEMS +
-			   item];
-}
-
 #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
 static inline const char *vm_event_name(enum vm_event_item item)
 {
 	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
-			   NR_VM_NUMA_STAT_ITEMS +
+			   NR_VM_NUMA_EVENT_ITEMS +
 			   NR_VM_NODE_STAT_ITEMS +
-			   NR_VM_WRITEBACK_STAT_ITEMS +
+			   NR_VM_STAT_ITEMS +
 			   item];
 }
 #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
 
+#ifdef CONFIG_MEMCG
+
+void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			int val);
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_state(lruvec, idx, val);
+	local_irq_restore(flags);
+}
+
+void __lruvec_stat_mod_folio(struct folio *folio,
+			     enum node_stat_item idx, int val);
+
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__lruvec_stat_mod_folio(folio, idx, val);
+	local_irq_restore(flags);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	lruvec_stat_mod_folio(page_folio(page), idx, val);
+}
+
+#else
+
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void __lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(folio_pgdat(folio), idx, val);
+}
+
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(folio_pgdat(folio), idx, val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(page_pgdat(page), idx, val);
+}
+
+#endif /* CONFIG_MEMCG */
+
+static inline void __lruvec_stat_add_folio(struct folio *folio,
+					   enum node_stat_item idx)
+{
+	__lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void __lruvec_stat_sub_folio(struct folio *folio,
+					   enum node_stat_item idx)
+{
+	__lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
+
+static inline void lruvec_stat_add_folio(struct folio *folio,
+					 enum node_stat_item idx)
+{
+	lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void lruvec_stat_sub_folio(struct folio *folio,
+					 enum node_stat_item idx)
+{
+	lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
+
+void memmap_boot_pages_add(long delta);
+void memmap_pages_add(long delta);
 #endif /* _LINUX_VMSTAT_H */