---

yaml
---
r: 31371
b: refs/heads/master
c: 2244b95
h: refs/heads/master
i:
  31369: b8ffe1c
  31367: bec38bf
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: f6ac2354d791195ca40822b84d73d48a4e8b7f2b
+refs/heads/master: 2244b95a7bcf8d24196f8a3a44187ba5dfff754c

trunk/arch/ia64/Kconfig

@@ -70,6 +70,11 @@ config DMA_IS_DMA32
 	bool
 	default y
 
+config DMA_IS_NORMAL
+	bool
+	depends on IA64_SGI_SN2
+	default y
+
 choice
 	prompt "System type"
 	default IA64_GENERIC

trunk/include/linux/mmzone.h

@@ -46,6 +46,9 @@ struct zone_padding {
 #define ZONE_PADDING(name)
 #endif
 
+enum zone_stat_item {
+	NR_VM_ZONE_STAT_ITEMS };
+
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
@@ -55,6 +58,10 @@ struct per_cpu_pages {
 
 struct per_cpu_pageset {
 	struct per_cpu_pages pcp[2];	/* 0: hot.  1: cold */
+#ifdef CONFIG_SMP
+	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
+#endif
+
 #ifdef CONFIG_NUMA
 	unsigned long numa_hit;		/* allocated in intended node */
 	unsigned long numa_miss;	/* allocated in non intended node */
@@ -165,6 +172,8 @@ struct zone {
 	/* A count of how many reclaimers are scanning this zone */
 	atomic_t		reclaim_in_progress;
 
+	/* Zone statistics */
+	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 	/*
 	 * timestamp (in jiffies) of the last zone reclaim that did not
 	 * result in freeing of pages. This is used to avoid repeated scans

trunk/include/linux/vmstat.h

@@ -3,6 +3,9 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
+#include <linux/config.h>
+#include <linux/mmzone.h>
+#include <asm/atomic.h>
 
 /*
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
@@ -134,5 +137,129 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
 
 DECLARE_PER_CPU(struct page_state, page_states);
 
-#endif /* _LINUX_VMSTAT_H */
+/*
+ * Zone based page accounting with per cpu differentials.
+ */
+extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+
+static inline void zone_page_state_add(long x, struct zone *zone,
+				 enum zone_stat_item item)
+{
+	atomic_long_add(x, &zone->vm_stat[item]);
+	atomic_long_add(x, &vm_stat[item]);
+}
+
+static inline unsigned long global_page_state(enum zone_stat_item item)
+{
+	long x = atomic_long_read(&vm_stat[item]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
+static inline unsigned long zone_page_state(struct zone *zone,
+					enum zone_stat_item item)
+{
+	long x = atomic_long_read(&zone->vm_stat[item]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * Determine the per node value of a stat item. This function
+ * is called frequently in a NUMA machine, so try to be as
+ * frugal as possible.
+ */
+static inline unsigned long node_page_state(int node,
+				 enum zone_stat_item item)
+{
+	struct zone *zones = NODE_DATA(node)->node_zones;
+
+	return
+#ifndef CONFIG_DMA_IS_NORMAL
+#if !defined(CONFIG_DMA_IS_DMA32) && BITS_PER_LONG >= 64
+		zone_page_state(&zones[ZONE_DMA32], item) +
+#endif
+		zone_page_state(&zones[ZONE_NORMAL], item) +
+#endif
+#ifdef CONFIG_HIGHMEM
+		zone_page_state(&zones[ZONE_HIGHMEM], item) +
+#endif
+		zone_page_state(&zones[ZONE_DMA], item);
+}
+#else
+#define node_page_state(node, item) global_page_state(item)
+#endif
+
+#define __add_zone_page_state(__z, __i, __d)	\
+		__mod_zone_page_state(__z, __i, __d)
+#define __sub_zone_page_state(__z, __i, __d)	\
+		__mod_zone_page_state(__z, __i,-(__d))
+
+#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
+#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
+
+static inline void zap_zone_vm_stats(struct zone *zone)
+{
+	memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
+}
+
+#ifdef CONFIG_SMP
+void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
+void __inc_zone_page_state(struct page *, enum zone_stat_item);
+void __dec_zone_page_state(struct page *, enum zone_stat_item);
 
+void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
+void inc_zone_page_state(struct page *, enum zone_stat_item);
+void dec_zone_page_state(struct page *, enum zone_stat_item);
+
+extern void inc_zone_state(struct zone *, enum zone_stat_item);
+
+void refresh_cpu_vm_stats(int);
+void refresh_vm_stats(void);
+
+#else /* CONFIG_SMP */
+
+/*
+ * We do not maintain differentials in a single processor configuration.
+ * The functions directly modify the zone and global counters.
+ */
+static inline void __mod_zone_page_state(struct zone *zone,
+			enum zone_stat_item item, int delta)
+{
+	zone_page_state_add(delta, zone, item);
+}
+
+static inline void __inc_zone_page_state(struct page *page,
+			enum zone_stat_item item)
+{
+	atomic_long_inc(&page_zone(page)->vm_stat[item]);
+	atomic_long_inc(&vm_stat[item]);
+}
+
+static inline void __dec_zone_page_state(struct page *page,
+			enum zone_stat_item item)
+{
+	atomic_long_dec(&page_zone(page)->vm_stat[item]);
+	atomic_long_dec(&vm_stat[item]);
+}
+
+/*
+ * We only use atomic operations to update counters. So there is no need to
+ * disable interrupts.
+ */
+#define inc_zone_page_state __inc_zone_page_state
+#define dec_zone_page_state __dec_zone_page_state
+#define mod_zone_page_state __mod_zone_page_state
+
+static inline void refresh_cpu_vm_stats(int cpu) { }
+static inline void refresh_vm_stats(void) { }
+#endif
+
+#endif /* _LINUX_VMSTAT_H */

trunk/mm/page_alloc.c

@@ -2045,6 +2045,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		zone->nr_scan_inactive = 0;
 		zone->nr_active = 0;
 		zone->nr_inactive = 0;
+		zap_zone_vm_stats(zone);
 		atomic_set(&zone->reclaim_in_progress, 0);
 		if (!size)
 			continue;
@@ -2147,6 +2148,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 		}
 
 		local_irq_enable();
+		refresh_cpu_vm_stats(cpu);
 	}
 	return NOTIFY_OK;
 }

trunk/mm/slab.c

@@ -3763,6 +3763,7 @@ static void cache_reap(void *unused)
 	check_irq_on();
 	mutex_unlock(&cache_chain_mutex);
 	next_reap_node();
+	refresh_cpu_vm_stats(smp_processor_id());
 	/* Set up the next iteration */
 	schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
 }