mm/vmstat: convert NUMA statistics to basic NUMA counters

NUMA statistics are maintained on the zone level for hits, misses, foreign
etc but nothing relies on them being perfectly accurate for functional
correctness.  The counters are used by userspace to get a general overview
of a workloads NUMA behaviour but the page allocator incurs a high cost to
maintain perfect accuracy similar to what is required for a vmstat like
NR_FREE_PAGES.  There even is a sysctl vm.numa_stat to allow userspace to
turn off the collection of NUMA statistics like NUMA_HIT.

This patch converts NUMA_HIT and friends to be NUMA events with similar
accuracy to VM events.  There is a possibility that slight errors will be
introduced but the overall trend as seen by userspace will be similar.
The counters are no longer updated from vmstat_refresh context as it is
unnecessary overhead for counters that may never be read by userspace.
Note that counters could be maintained at the node level to save space but
it would have a user-visible impact due to /proc/zoneinfo.

[lkp@intel.com: Fix misplaced closing brace for !CONFIG_NUMA]

Link: https://lkml.kernel.org/r/20210512095458.30632-4-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 74 insertions, 113 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 325771bef5e2..b5d95bf1025d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2150,7 +2150,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 		return page;
 	if (page && page_to_nid(page) == nid) {
 		preempt_disable();
-		__inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT);
+		__count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT);
 		preempt_enable();
 	}
 	return page;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89872ad5e872..4e03109bdae5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3480,12 +3480,12 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 		local_stat = NUMA_OTHER;
 
 	if (zone_to_nid(z) == zone_to_nid(preferred_zone))
-		__inc_numa_state(z, NUMA_HIT);
+		__count_numa_event(z, NUMA_HIT);
 	else {
-		__inc_numa_state(z, NUMA_MISS);
-		__inc_numa_state(preferred_zone, NUMA_FOREIGN);
+		__count_numa_event(z, NUMA_MISS);
+		__count_numa_event(preferred_zone, NUMA_FOREIGN);
 	}
-	__inc_numa_state(z, local_stat);
+	__count_numa_event(z, local_stat);
 #endif
 }
 
@@ -6785,8 +6785,8 @@ void __init setup_per_cpu_pageset(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu);
-		memset(pzstats->vm_numa_stat_diff, 0,
-		       sizeof(pzstats->vm_numa_stat_diff));
+		memset(pzstats->vm_numa_event, 0,
+		       sizeof(pzstats->vm_numa_event));
 	}
 #endif
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f1400ba46beb..0e27b62e487d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -31,8 +31,6 @@
 
 #include "internal.h"
 
-#define NUMA_STATS_THRESHOLD (U16_MAX - 2)
-
 #ifdef CONFIG_NUMA
 int sysctl_vm_numa_stat = ENABLE_NUMA_STAT;
 
@@ -41,11 +39,12 @@ static void zero_zone_numa_counters(struct zone *zone)
 {
 	int item, cpu;
 
-	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) {
-		atomic_long_set(&zone->vm_numa_stat[item], 0);
-		for_each_online_cpu(cpu)
-			per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_stat_diff[item]
+	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) {
+		atomic_long_set(&zone->vm_numa_event[item], 0);
+		for_each_online_cpu(cpu) {
+			per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item]
 						= 0;
+		}
 	}
 }
 
@@ -63,8 +62,8 @@ static void zero_global_numa_counters(void)
 {
 	int item;
 
-	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++)
-		atomic_long_set(&vm_numa_stat[item], 0);
+	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)
+		atomic_long_set(&vm_numa_event[item], 0);
 }
 
 static void invalid_numa_statistics(void)
@@ -161,10 +160,9 @@ void vm_events_fold_cpu(int cpu)
  * vm_stat contains the global counters
  */
 atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
-atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp;
 atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
+atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp;
 EXPORT_SYMBOL(vm_zone_stat);
-EXPORT_SYMBOL(vm_numa_stat);
 EXPORT_SYMBOL(vm_node_stat);
 
 #ifdef CONFIG_SMP
@@ -706,8 +704,7 @@ EXPORT_SYMBOL(dec_node_page_state);
  * Fold a differential into the global counters.
  * Returns the number of counters updated.
  */
-#ifdef CONFIG_NUMA
-static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
+static int fold_diff(int *zone_diff, int *node_diff)
 {
 	int i;
 	int changes = 0;
@@ -718,12 +715,6 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
 			changes++;
 	}
 
-	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
-		if (numa_diff[i]) {
-			atomic_long_add(numa_diff[i], &vm_numa_stat[i]);
-			changes++;
-	}
-
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 		if (node_diff[i]) {
 			atomic_long_add(node_diff[i], &vm_node_stat[i]);
@@ -731,26 +722,34 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
 	}
 	return changes;
 }
-#else
-static int fold_diff(int *zone_diff, int *node_diff)
+
+#ifdef CONFIG_NUMA
+static void fold_vm_zone_numa_events(struct zone *zone)
 {
-	int i;
-	int changes = 0;
+	unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, };
+	int cpu;
+	enum numa_stat_item item;
 
-	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (zone_diff[i]) {
-			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
-			changes++;
-	}
+	for_each_online_cpu(cpu) {
+		struct per_cpu_zonestat *pzstats;
 
-	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-		if (node_diff[i]) {
-			atomic_long_add(node_diff[i], &vm_node_stat[i]);
-			changes++;
+		pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu);
+		for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)
+			zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0);
 	}
-	return changes;
+
+	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)
+		zone_numa_event_add(zone_numa_events[item], zone, item);
 }
-#endif /* CONFIG_NUMA */
+
+void fold_vm_numa_events(void)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone)
+		fold_vm_zone_numa_events(zone);
+}
+#endif
 
 /*
  * Update the zone counters for the current cpu.
@@ -774,9 +773,6 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
 	struct zone *zone;
 	int i;
 	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
-#ifdef CONFIG_NUMA
-	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
-#endif
 	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
 	int changes = 0;
 
@@ -801,17 +797,6 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
 			}
 		}
 #ifdef CONFIG_NUMA
-		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
-			int v;
-
-			v = this_cpu_xchg(pzstats->vm_numa_stat_diff[i], 0);
-			if (v) {
-
-				atomic_long_add(v, &zone->vm_numa_stat[i]);
-				global_numa_diff[i] += v;
-				__this_cpu_write(pcp->expire, 3);
-			}
-		}
 
 		if (do_pagesets) {
 			cond_resched();
@@ -859,12 +844,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
 		}
 	}
 
-#ifdef CONFIG_NUMA
-	changes += fold_diff(global_zone_diff, global_numa_diff,
-			     global_node_diff);
-#else
 	changes += fold_diff(global_zone_diff, global_node_diff);
-#endif
 	return changes;
 }
 
@@ -879,9 +859,6 @@ void cpu_vm_stats_fold(int cpu)
 	struct zone *zone;
 	int i;
 	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
-#ifdef CONFIG_NUMA
-	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
-#endif
 	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
 
 	for_each_populated_zone(zone) {
@@ -889,7 +866,7 @@ void cpu_vm_stats_fold(int cpu)
 
 		pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu);
 
-		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
 			if (pzstats->vm_stat_diff[i]) {
 				int v;
 
@@ -898,17 +875,17 @@ void cpu_vm_stats_fold(int cpu)
 				atomic_long_add(v, &zone->vm_stat[i]);
 				global_zone_diff[i] += v;
 			}
-
+		}
 #ifdef CONFIG_NUMA
-		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
-			if (pzstats->vm_numa_stat_diff[i]) {
-				int v;
+		for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) {
+			if (pzstats->vm_numa_event[i]) {
+				unsigned long v;
 
-				v = pzstats->vm_numa_stat_diff[i];
-				pzstats->vm_numa_stat_diff[i] = 0;
-				atomic_long_add(v, &zone->vm_numa_stat[i]);
-				global_numa_diff[i] += v;
+				v = pzstats->vm_numa_event[i];
+				pzstats->vm_numa_event[i] = 0;
+				zone_numa_event_add(v, zone, i);
 			}
+		}
 #endif
 	}
 
@@ -928,11 +905,7 @@ void cpu_vm_stats_fold(int cpu)
 			}
 	}
 
-#ifdef CONFIG_NUMA
-	fold_diff(global_zone_diff, global_numa_diff, global_node_diff);
-#else
 	fold_diff(global_zone_diff, global_node_diff);
-#endif
 }
 
 /*
@@ -941,43 +914,37 @@ void cpu_vm_stats_fold(int cpu)
  */
 void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats)
 {
+	unsigned long v;
 	int i;
 
-	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
 		if (pzstats->vm_stat_diff[i]) {
-			int v = pzstats->vm_stat_diff[i];
+			v = pzstats->vm_stat_diff[i];
 			pzstats->vm_stat_diff[i] = 0;
-			atomic_long_add(v, &zone->vm_stat[i]);
-			atomic_long_add(v, &vm_zone_stat[i]);
+			zone_page_state_add(v, zone, i);
 		}
+	}
 
 #ifdef CONFIG_NUMA
-	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
-		if (pzstats->vm_numa_stat_diff[i]) {
-			int v = pzstats->vm_numa_stat_diff[i];
-
-			pzstats->vm_numa_stat_diff[i] = 0;
-			atomic_long_add(v, &zone->vm_numa_stat[i]);
-			atomic_long_add(v, &vm_numa_stat[i]);
+	for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) {
+		if (pzstats->vm_numa_event[i]) {
+			v = pzstats->vm_numa_event[i];
+			pzstats->vm_numa_event[i] = 0;
+			zone_numa_event_add(v, zone, i);
 		}
+	}
 #endif
 }
 #endif
 
 #ifdef CONFIG_NUMA
-void __inc_numa_state(struct zone *zone,
+/* See __count_vm_event comment on why raw_cpu_inc is used. */
+void __count_numa_event(struct zone *zone,
 				 enum numa_stat_item item)
 {
 	struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats;
-	u16 __percpu *p = pzstats->vm_numa_stat_diff + item;
-	u16 v;
-
-	v = __this_cpu_inc_return(*p);
 
-	if (unlikely(v > NUMA_STATS_THRESHOLD)) {
-		zone_numa_state_add(v, zone, item);
-		__this_cpu_write(*p, 0);
-	}
+	raw_cpu_inc(pzstats->vm_numa_event[item]);
 }
 
 /*
@@ -998,19 +965,16 @@ unsigned long sum_zone_node_page_state(int node,
 	return count;
 }
 
-/*
- * Determine the per node value of a numa stat item. To avoid deviation,
- * the per cpu stat number in vm_numa_stat_diff[] is also included.
- */
-unsigned long sum_zone_numa_state(int node,
+/* Determine the per node value of a numa stat item. */
+unsigned long sum_zone_numa_event_state(int node,
 				 enum numa_stat_item item)
 {
 	struct zone *zones = NODE_DATA(node)->node_zones;
-	int i;
 	unsigned long count = 0;
+	int i;
 
 	for (i = 0; i < MAX_NR_ZONES; i++)
-		count += zone_numa_state_snapshot(zones + i, item);
+		count += zone_numa_event_state(zones + i, item);
 
 	return count;
 }
@@ -1689,9 +1653,9 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 			   zone_page_state(zone, i));
 
 #ifdef CONFIG_NUMA
-	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
+	for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++)
 		seq_printf(m, "\n      %-12s %lu", numa_stat_name(i),
-			   zone_numa_state_snapshot(zone, i));
+			   zone_numa_event_state(zone, i));
 #endif
 
 	seq_printf(m, "\n  pagesets");
@@ -1745,7 +1709,7 @@ static const struct seq_operations zoneinfo_op = {
 };
 
 #define NR_VMSTAT_ITEMS (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 + \
 			 (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \
@@ -1760,6 +1724,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 		return NULL;
 
 	BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS);
+	fold_vm_numa_events();
 	v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL);
 	m->private = v;
 	if (!v)
@@ -1769,9 +1734,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 	v += NR_VM_ZONE_STAT_ITEMS;
 
 #ifdef CONFIG_NUMA
-	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
-		v[i] = global_numa_state(i);
-	v += NR_VM_NUMA_STAT_ITEMS;
+	for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++)
+		v[i] = global_numa_event_state(i);
+	v += NR_VM_NUMA_EVENT_ITEMS;
 #endif
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
@@ -1941,11 +1906,7 @@ static bool need_update(int cpu)
 		if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS *
 			       sizeof(pzstats->vm_stat_diff[0])))
 			return true;
-#ifdef CONFIG_NUMA
-		if (memchr_inv(pzstats->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS *
-			       sizeof(pzstats->vm_numa_stat_diff[0])))
-			return true;
-#endif
+
 		if (last_pgdat == zone->zone_pgdat)
 			continue;
 		last_pgdat = zone->zone_pgdat;