1 files changed, 463 insertions, 211 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 42eac4d3321..b37bd49bfd5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -19,6 +19,9 @@
 #include <linux/math64.h>
 #include <linux/writeback.h>
 #include <linux/compaction.h>
+#include <linux/mm_inline.h>
+
+#include "internal.h"
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -52,7 +55,6 @@ void all_vm_events(unsigned long *ret)
 }
 EXPORT_SYMBOL_GPL(all_vm_events);
 
-#ifdef CONFIG_HOTPLUG
 /*
  * Fold the foreign cpu events into our own.
  *
@@ -69,7 +71,6 @@ void vm_events_fold_cpu(int cpu)
 		fold_state->event[i] = 0;
 	}
 }
-#endif /* CONFIG_HOTPLUG */
 
 #endif /* CONFIG_VM_EVENT_COUNTERS */
 
@@ -78,12 +79,36 @@ void vm_events_fold_cpu(int cpu)
  *
  * vm_stat contains the global counters
  */
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
 EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP
 
-static int calculate_threshold(struct zone *zone)
+int calculate_pressure_threshold(struct zone *zone)
+{
+	int threshold;
+	int watermark_distance;
+
+	/*
+	 * As vmstats are not up to date, there is drift between the estimated
+	 * and real values. For high thresholds and a high number of CPUs, it
+	 * is possible for the min watermark to be breached while the estimated
+	 * value looks fine. The pressure threshold is a reduced value such
+	 * that even the maximum amount of drift will not accidentally breach
+	 * the min watermark
+	 */
+	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
+	threshold = max(1, (int)(watermark_distance / num_online_cpus()));
+
+	/*
+	 * Maximum threshold is 125
+	 */
+	threshold = min(125, threshold);
+
+	return threshold;
+}
+
+int calculate_normal_threshold(struct zone *zone)
 {
 	int threshold;
 	int mem;	/* memory in 128 MB units */
@@ -118,7 +143,7 @@ static int calculate_threshold(struct zone *zone)
 	 * 125		1024		10	16-32 GB	9
 	 */
 
-	mem = zone->present_pages >> (27 - PAGE_SHIFT);
+	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
 
 	threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem));
 
@@ -133,7 +158,7 @@ static int calculate_threshold(struct zone *zone)
 /*
  * Refresh the thresholds for each zone.
  */
-static void refresh_zone_stat_thresholds(void)
+void refresh_zone_stat_thresholds(void)
 {
 	struct zone *zone;
 	int cpu;
@@ -142,7 +167,7 @@ static void refresh_zone_stat_thresholds(void)
 	for_each_populated_zone(zone) {
 		unsigned long max_drift, tolerate_drift;
 
-		threshold = calculate_threshold(zone);
+		threshold = calculate_normal_threshold(zone);
 
 		for_each_online_cpu(cpu)
 			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
@@ -161,42 +186,52 @@ static void refresh_zone_stat_thresholds(void)
 	}
 }
 
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+				int (*calculate_pressure)(struct zone *))
+{
+	struct zone *zone;
+	int cpu;
+	int threshold;
+	int i;
+
+	for (i = 0; i < pgdat->nr_zones; i++) {
+		zone = &pgdat->node_zones[i];
+		if (!zone->percpu_drift_mark)
+			continue;
+
+		threshold = (*calculate_pressure)(zone);
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+							= threshold;
+	}
+}
+
 /*
- * For use when we know that interrupts are disabled.
+ * For use when we know that interrupts are disabled,
+ * or when we know that preemption is disabled and that
+ * particular counter cannot be updated from interrupt context.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 				int delta)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-
-	s8 *p = pcp->vm_stat_diff + item;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
 	long x;
+	long t;
 
-	x = delta + *p;
+	x = delta + __this_cpu_read(*p);
 
-	if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
+	t = __this_cpu_read(pcp->stat_threshold);
+
+	if (unlikely(x > t || x < -t)) {
 		zone_page_state_add(x, zone, item);
 		x = 0;
 	}
-	*p = x;
+	__this_cpu_write(*p, x);
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
 /*
- * For an unknown interrupt state
- */
-void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_zone_page_state(zone, item, delta);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_zone_page_state);
-
-/*
  * Optimized increment and decrement functions.
  *
  * These are only for a single page and therefore can take a struct page *
@@ -221,16 +256,17 @@ EXPORT_SYMBOL(mod_zone_page_state);
  */
 void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-	s8 *p = pcp->vm_stat_diff + item;
-
-	(*p)++;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	s8 v, t;
 
-	if (unlikely(*p > pcp->stat_threshold)) {
-		int overstep = pcp->stat_threshold / 2;
+	v = __this_cpu_inc_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v > t)) {
+		s8 overstep = t >> 1;
 
-		zone_page_state_add(*p + overstep, zone, item);
-		*p = -overstep;
+		zone_page_state_add(v + overstep, zone, item);
+		__this_cpu_write(*p, -overstep);
 	}
 }
 
@@ -242,16 +278,17 @@ EXPORT_SYMBOL(__inc_zone_page_state);
 
 void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-	s8 *p = pcp->vm_stat_diff + item;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	s8 v, t;
 
-	(*p)--;
+	v = __this_cpu_dec_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v < - t)) {
+		s8 overstep = t >> 1;
 
-	if (unlikely(*p < - pcp->stat_threshold)) {
-		int overstep = pcp->stat_threshold / 2;
-
-		zone_page_state_add(*p - overstep, zone, item);
-		*p = overstep;
+		zone_page_state_add(v - overstep, zone, item);
+		__this_cpu_write(*p, overstep);
 	}
 }
 
@@ -261,6 +298,95 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
 
+#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
+/*
+ * If we have cmpxchg_local support then we do not need to incur the overhead
+ * that comes with local_irq_save/restore if we use this_cpu_cmpxchg.
+ *
+ * mod_state() modifies the zone counter state through atomic per cpu
+ * operations.
+ *
+ * Overstep mode specifies how overstep should handled:
+ *     0       No overstepping
+ *     1       Overstepping half of threshold
+ *     -1      Overstepping minus half of threshold
+*/
+static inline void mod_state(struct zone *zone,
+       enum zone_stat_item item, int delta, int overstep_mode)
+{
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	long o, n, t, z;
+
+	do {
+		z = 0;  /* overflow to zone counters */
+
+		/*
+		 * The fetching of the stat_threshold is racy. We may apply
+		 * a counter threshold to the wrong the cpu if we get
+		 * rescheduled while executing here. However, the next
+		 * counter update will apply the threshold again and
+		 * therefore bring the counter under the threshold again.
+		 *
+		 * Most of the time the thresholds are the same anyways
+		 * for all cpus in a zone.
+		 */
+		t = this_cpu_read(pcp->stat_threshold);
+
+		o = this_cpu_read(*p);
+		n = delta + o;
+
+		if (n > t || n < -t) {
+			int os = overstep_mode * (t >> 1) ;
+
+			/* Overflow must be added to zone counters */
+			z = n + os;
+			n = -os;
+		}
+	} while (this_cpu_cmpxchg(*p, o, n) != o);
+
+	if (z)
+		zone_page_state_add(z, zone, item);
+}
+
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+					int delta)
+{
+	mod_state(zone, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
+void inc_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+	mod_state(zone, item, 1, 1);
+}
+
+void inc_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+	mod_state(page_zone(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_zone_page_state);
+
+void dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+	mod_state(page_zone(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_zone_page_state);
+#else
+/*
+ * Use interrupt disable to serialize counter updates
+ */
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+					int delta)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_zone_page_state(zone, item, delta);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
 void inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	unsigned long flags;
@@ -291,13 +417,19 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
+#endif
+
+static inline void fold_diff(int *diff)
+{
+	int i;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		if (diff[i])
+			atomic_long_add(diff[i], &vm_stat[i]);
+}
 
 /*
- * Update the zone counters for one cpu.
- *
- * The cpu specified must be either the current cpu or a processor that
- * is not online. If it is the current cpu then the execution thread must
- * be pinned to the current cpu.
+ * Update the zone counters for the current cpu.
  *
  * Note that refresh_cpu_vm_stats strives to only access
  * node local memory. The per cpu pagesets on remote zones are placed
@@ -310,33 +442,29 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
  */
-void refresh_cpu_vm_stats(int cpu)
+static void refresh_cpu_vm_stats(void)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
 
 	for_each_populated_zone(zone) {
-		struct per_cpu_pageset *p;
+		struct per_cpu_pageset __percpu *p = zone->pageset;
 
-		p = per_cpu_ptr(zone->pageset, cpu);
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
+			int v;
 
-		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-			if (p->vm_stat_diff[i]) {
-				unsigned long flags;
-				int v;
+			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
+			if (v) {
 
-				local_irq_save(flags);
-				v = p->vm_stat_diff[i];
-				p->vm_stat_diff[i] = 0;
-				local_irq_restore(flags);
 				atomic_long_add(v, &zone->vm_stat[i]);
 				global_diff[i] += v;
 #ifdef CONFIG_NUMA
 				/* 3 seconds idle till flush */
-				p->expire = 3;
+				__this_cpu_write(p->expire, 3);
 #endif
 			}
+		}
 		cond_resched();
 #ifdef CONFIG_NUMA
 		/*
@@ -346,31 +474,75 @@ void refresh_cpu_vm_stats(int cpu)
 		 * Check if there are pages remaining in this pageset
 		 * if not then there is nothing to expire.
 		 */
-		if (!p->expire || !p->pcp.count)
+		if (!__this_cpu_read(p->expire) ||
+			       !__this_cpu_read(p->pcp.count))
 			continue;
 
 		/*
 		 * We never drain zones local to this processor.
 		 */
 		if (zone_to_nid(zone) == numa_node_id()) {
-			p->expire = 0;
+			__this_cpu_write(p->expire, 0);
 			continue;
 		}
 
-		p->expire--;
-		if (p->expire)
+
+		if (__this_cpu_dec_return(p->expire))
 			continue;
 
-		if (p->pcp.count)
-			drain_zone_pages(zone, &p->pcp);
+		if (__this_cpu_read(p->pcp.count))
+			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
 #endif
 	}
+	fold_diff(global_diff);
+}
 
-	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (global_diff[i])
-			atomic_long_add(global_diff[i], &vm_stat[i]);
+/*
+ * Fold the data for an offline cpu into the global array.
+ * There cannot be any access by the offline cpu and therefore
+ * synchronization is simplified.
+ */
+void cpu_vm_stats_fold(int cpu)
+{
+	struct zone *zone;
+	int i;
+	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p;
+
+		p = per_cpu_ptr(zone->pageset, cpu);
+
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+			if (p->vm_stat_diff[i]) {
+				int v;
+
+				v = p->vm_stat_diff[i];
+				p->vm_stat_diff[i] = 0;
+				atomic_long_add(v, &zone->vm_stat[i]);
+				global_diff[i] += v;
+			}
+	}
+
+	fold_diff(global_diff);
 }
 
+/*
+ * this is only called if !populated_zone(zone), which implies no other users of
+ * pset->vm_stat_diff[] exsist.
+ */
+void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
+{
+	int i;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		if (pset->vm_stat_diff[i]) {
+			int v = pset->vm_stat_diff[i];
+			pset->vm_stat_diff[i] = 0;
+			atomic_long_add(v, &zone->vm_stat[i]);
+			atomic_long_add(v, &vm_stat[i]);
+		}
+}
 #endif
 
 #ifdef CONFIG_NUMA
@@ -379,8 +551,12 @@ void refresh_cpu_vm_stats(int cpu)
  * z 	    = the zone from which the allocation occurred.
  *
  * Must be called with interrupts disabled.
+ *
+ * When __GFP_OTHER_NODE is set assume the node of the preferred
+ * zone is the local node. This is useful for daemons who allocate
+ * memory on behalf of other processes.
  */
-void zone_statistics(struct zone *preferred_zone, struct zone *z)
+void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags)
 {
 	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
 		__inc_zone_state(z, NUMA_HIT);
@@ -388,7 +564,8 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z)
 		__inc_zone_state(z, NUMA_MISS);
 		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
 	}
-	if (z->node == numa_node_id())
+	if (z->node == ((flags & __GFP_OTHER_NODE) ?
+			preferred_zone->node : numa_node_id()))
 		__inc_zone_state(z, NUMA_LOCAL);
 	else
 		__inc_zone_state(z, NUMA_OTHER);
@@ -484,7 +661,12 @@ static char * const migratetype_names[MIGRATE_TYPES] = {
 	"Reclaimable",
 	"Movable",
 	"Reserve",
+#ifdef CONFIG_CMA
+	"CMA",
+#endif
+#ifdef CONFIG_MEMORY_ISOLATION
 	"Isolate",
+#endif
 };
 
 static void *frag_start(struct seq_file *m, loff_t *pos)
@@ -530,6 +712,171 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 }
 #endif
 
+#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
+#ifdef CONFIG_ZONE_DMA
+#define TEXT_FOR_DMA(xx) xx "_dma",
+#else
+#define TEXT_FOR_DMA(xx)
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+#define TEXT_FOR_DMA32(xx) xx "_dma32",
+#else
+#define TEXT_FOR_DMA32(xx)
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#define TEXT_FOR_HIGHMEM(xx) xx "_high",
+#else
+#define TEXT_FOR_HIGHMEM(xx)
+#endif
+
+#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
+					TEXT_FOR_HIGHMEM(xx) xx "_movable",
+
+const char * const vmstat_text[] = {
+	/* Zoned VM counters */
+	"nr_free_pages",
+	"nr_alloc_batch",
+	"nr_inactive_anon",
+	"nr_active_anon",
+	"nr_inactive_file",
+	"nr_active_file",
+	"nr_unevictable",
+	"nr_mlock",
+	"nr_anon_pages",
+	"nr_mapped",
+	"nr_file_pages",
+	"nr_dirty",
+	"nr_writeback",
+	"nr_slab_reclaimable",
+	"nr_slab_unreclaimable",
+	"nr_page_table_pages",
+	"nr_kernel_stack",
+	"nr_unstable",
+	"nr_bounce",
+	"nr_vmscan_write",
+	"nr_vmscan_immediate_reclaim",
+	"nr_writeback_temp",
+	"nr_isolated_anon",
+	"nr_isolated_file",
+	"nr_shmem",
+	"nr_dirtied",
+	"nr_written",
+
+#ifdef CONFIG_NUMA
+	"numa_hit",
+	"numa_miss",
+	"numa_foreign",
+	"numa_interleave",
+	"numa_local",
+	"numa_other",
+#endif
+	"workingset_refault",
+	"workingset_activate",
+	"workingset_nodereclaim",
+	"nr_anon_transparent_hugepages",
+	"nr_free_cma",
+	"nr_dirty_threshold",
+	"nr_dirty_background_threshold",
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+	"pgpgin",
+	"pgpgout",
+	"pswpin",
+	"pswpout",
+
+	TEXTS_FOR_ZONES("pgalloc")
+
+	"pgfree",
+	"pgactivate",
+	"pgdeactivate",
+
+	"pgfault",
+	"pgmajfault",
+
+	TEXTS_FOR_ZONES("pgrefill")
+	TEXTS_FOR_ZONES("pgsteal_kswapd")
+	TEXTS_FOR_ZONES("pgsteal_direct")
+	TEXTS_FOR_ZONES("pgscan_kswapd")
+	TEXTS_FOR_ZONES("pgscan_direct")
+	"pgscan_direct_throttle",
+
+#ifdef CONFIG_NUMA
+	"zone_reclaim_failed",
+#endif
+	"pginodesteal",
+	"slabs_scanned",
+	"kswapd_inodesteal",
+	"kswapd_low_wmark_hit_quickly",
+	"kswapd_high_wmark_hit_quickly",
+	"pageoutrun",
+	"allocstall",
+
+	"pgrotated",
+
+	"drop_pagecache",
+	"drop_slab",
+
+#ifdef CONFIG_NUMA_BALANCING
+	"numa_pte_updates",
+	"numa_huge_pte_updates",
+	"numa_hint_faults",
+	"numa_hint_faults_local",
+	"numa_pages_migrated",
+#endif
+#ifdef CONFIG_MIGRATION
+	"pgmigrate_success",
+	"pgmigrate_fail",
+#endif
+#ifdef CONFIG_COMPACTION
+	"compact_migrate_scanned",
+	"compact_free_scanned",
+	"compact_isolated",
+	"compact_stall",
+	"compact_fail",
+	"compact_success",
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+	"htlb_buddy_alloc_success",
+	"htlb_buddy_alloc_fail",
+#endif
+	"unevictable_pgs_culled",
+	"unevictable_pgs_scanned",
+	"unevictable_pgs_rescued",
+	"unevictable_pgs_mlocked",
+	"unevictable_pgs_munlocked",
+	"unevictable_pgs_cleared",
+	"unevictable_pgs_stranded",
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	"thp_fault_alloc",
+	"thp_fault_fallback",
+	"thp_collapse_alloc",
+	"thp_collapse_alloc_failed",
+	"thp_split",
+	"thp_zero_page_alloc",
+	"thp_zero_page_alloc_failed",
+#endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
+#ifdef CONFIG_SMP
+	"nr_tlb_remote_flush",
+	"nr_tlb_remote_flush_received",
+#endif /* CONFIG_SMP */
+	"nr_tlb_local_flush_all",
+	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
+
+#ifdef CONFIG_DEBUG_VM_VMACACHE
+	"vmacache_find_calls",
+	"vmacache_find_hits",
+#endif
+#endif /* CONFIG_VM_EVENTS_COUNTERS */
+};
+#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
+
+
 #ifdef CONFIG_PROC_FS
 static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
 						struct zone *zone)
@@ -600,7 +947,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
 	int mtype;
 	unsigned long pfn;
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long count[MIGRATE_TYPES] = { 0, };
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
@@ -652,7 +999,7 @@ static int pagetypeinfo_show(struct seq_file *m, void *arg)
 	pg_data_t *pgdat = (pg_data_t *)arg;
 
 	/* check memoryless node */
-	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
+	if (!node_state(pgdat->node_id, N_MEMORY))
 		return 0;
 
 	seq_printf(m, "Page block order: %d\n", pageblock_order);
@@ -702,125 +1049,6 @@ static const struct file_operations pagetypeinfo_file_ops = {
 	.release	= seq_release,
 };
 
-#ifdef CONFIG_ZONE_DMA
-#define TEXT_FOR_DMA(xx) xx "_dma",
-#else
-#define TEXT_FOR_DMA(xx)
-#endif
-
-#ifdef CONFIG_ZONE_DMA32
-#define TEXT_FOR_DMA32(xx) xx "_dma32",
-#else
-#define TEXT_FOR_DMA32(xx)
-#endif
-
-#ifdef CONFIG_HIGHMEM
-#define TEXT_FOR_HIGHMEM(xx) xx "_high",
-#else
-#define TEXT_FOR_HIGHMEM(xx)
-#endif
-
-#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
-					TEXT_FOR_HIGHMEM(xx) xx "_movable",
-
-static const char * const vmstat_text[] = {
-	/* Zoned VM counters */
-	"nr_free_pages",
-	"nr_inactive_anon",
-	"nr_active_anon",
-	"nr_inactive_file",
-	"nr_active_file",
-	"nr_unevictable",
-	"nr_mlock",
-	"nr_anon_pages",
-	"nr_mapped",
-	"nr_file_pages",
-	"nr_dirty",
-	"nr_writeback",
-	"nr_slab_reclaimable",
-	"nr_slab_unreclaimable",
-	"nr_page_table_pages",
-	"nr_kernel_stack",
-	"nr_unstable",
-	"nr_bounce",
-	"nr_vmscan_write",
-	"nr_writeback_temp",
-	"nr_isolated_anon",
-	"nr_isolated_file",
-	"nr_shmem",
-	"nr_dirtied",
-	"nr_written",
-	"nr_dirty_threshold",
-	"nr_dirty_background_threshold",
-
-#ifdef CONFIG_NUMA
-	"numa_hit",
-	"numa_miss",
-	"numa_foreign",
-	"numa_interleave",
-	"numa_local",
-	"numa_other",
-#endif
-
-#ifdef CONFIG_VM_EVENT_COUNTERS
-	"pgpgin",
-	"pgpgout",
-	"pswpin",
-	"pswpout",
-
-	TEXTS_FOR_ZONES("pgalloc")
-
-	"pgfree",
-	"pgactivate",
-	"pgdeactivate",
-
-	"pgfault",
-	"pgmajfault",
-
-	TEXTS_FOR_ZONES("pgrefill")
-	TEXTS_FOR_ZONES("pgsteal")
-	TEXTS_FOR_ZONES("pgscan_kswapd")
-	TEXTS_FOR_ZONES("pgscan_direct")
-
-#ifdef CONFIG_NUMA
-	"zone_reclaim_failed",
-#endif
-	"pginodesteal",
-	"slabs_scanned",
-	"kswapd_steal",
-	"kswapd_inodesteal",
-	"kswapd_low_wmark_hit_quickly",
-	"kswapd_high_wmark_hit_quickly",
-	"kswapd_skip_congestion_wait",
-	"pageoutrun",
-	"allocstall",
-
-	"pgrotated",
-
-#ifdef CONFIG_COMPACTION
-	"compact_blocks_moved",
-	"compact_pages_moved",
-	"compact_pagemigrate_failed",
-	"compact_stall",
-	"compact_fail",
-	"compact_success",
-#endif
-
-#ifdef CONFIG_HUGETLB_PAGE
-	"htlb_buddy_alloc_success",
-	"htlb_buddy_alloc_fail",
-#endif
-	"unevictable_pgs_culled",
-	"unevictable_pgs_scanned",
-	"unevictable_pgs_rescued",
-	"unevictable_pgs_mlocked",
-	"unevictable_pgs_munlocked",
-	"unevictable_pgs_cleared",
-	"unevictable_pgs_stranded",
-	"unevictable_pgs_mlockfreed",
-#endif
-};
-
 static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 							struct zone *zone)
 {
@@ -833,14 +1061,16 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        high     %lu"
 		   "\n        scanned  %lu"
 		   "\n        spanned  %lu"
-		   "\n        present  %lu",
-		   zone_nr_free_pages(zone),
+		   "\n        present  %lu"
+		   "\n        managed  %lu",
+		   zone_page_state(zone, NR_FREE_PAGES),
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
 		   zone->pages_scanned,
 		   zone->spanned_pages,
-		   zone->present_pages);
+		   zone->present_pages,
+		   zone->managed_pages);
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
 		seq_printf(m, "\n    %-12s %lu", vmstat_text[i],
@@ -876,7 +1106,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n  all_unreclaimable: %u"
 		   "\n  start_pfn:         %lu"
 		   "\n  inactive_ratio:    %u",
-		   zone->all_unreclaimable,
+		   !zone_reclaimable(zone),
 		   zone->zone_start_pfn,
 		   zone->inactive_ratio);
 	seq_putc(m, '\n');
@@ -1001,24 +1231,38 @@ int sysctl_stat_interval __read_mostly = HZ;
 
 static void vmstat_update(struct work_struct *w)
 {
-	refresh_cpu_vm_stats(smp_processor_id());
-	schedule_delayed_work(&__get_cpu_var(vmstat_work),
+	refresh_cpu_vm_stats();
+	schedule_delayed_work(this_cpu_ptr(&vmstat_work),
 		round_jiffies_relative(sysctl_stat_interval));
 }
 
-static void __cpuinit start_cpu_timer(int cpu)
+static void start_cpu_timer(int cpu)
 {
 	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
-	INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+	INIT_DEFERRABLE_WORK(work, vmstat_update);
 	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
+static void vmstat_cpu_dead(int node)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (cpu_to_node(cpu) == node)
+			goto end;
+
+	node_clear_state(node, N_CPU);
+end:
+	put_online_cpus();
+}
+
 /*
  * Use the cpu notifier to insure that the thresholds are recalculated
  * when necessary.
  */
-static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
+static int vmstat_cpuup_callback(struct notifier_block *nfb,
 		unsigned long action,
 		void *hcpu)
 {
@@ -1033,7 +1277,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu));
+		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
 		per_cpu(vmstat_work, cpu).work.func = NULL;
 		break;
 	case CPU_DOWN_FAILED:
@@ -1043,6 +1287,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		refresh_zone_stat_thresholds();
+		vmstat_cpu_dead(cpu_to_node(cpu));
 		break;
 	default:
 		break;
@@ -1050,7 +1295,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata vmstat_notifier =
+static struct notifier_block vmstat_notifier =
 	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
@@ -1059,11 +1304,14 @@ static int __init setup_vmstat(void)
 #ifdef CONFIG_SMP
 	int cpu;
 
-	refresh_zone_stat_thresholds();
-	register_cpu_notifier(&vmstat_notifier);
+	cpu_notifier_register_begin();
+	__register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
 		start_cpu_timer(cpu);
+		node_set_state(cpu_to_node(cpu), N_CPU);
+	}
+	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
@@ -1078,7 +1326,6 @@ module_init(setup_vmstat)
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
 #include <linux/debugfs.h>
 
-static struct dentry *extfrag_debug_root;
 
 /*
  * Return an index indicating how much of the available free memory is
@@ -1135,7 +1382,7 @@ static int unusable_show(struct seq_file *m, void *arg)
 	pg_data_t *pgdat = (pg_data_t *)arg;
 
 	/* check memoryless node */
-	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
+	if (!node_state(pgdat->node_id, N_MEMORY))
 		return 0;
 
 	walk_zones_in_node(m, pgdat, unusable_show_print);
@@ -1216,19 +1463,24 @@ static const struct file_operations extfrag_file_ops = {
 
 static int __init extfrag_debug_init(void)
 {
+	struct dentry *extfrag_debug_root;
+
 	extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
 	if (!extfrag_debug_root)
 		return -ENOMEM;
 
 	if (!debugfs_create_file("unusable_index", 0444,
 			extfrag_debug_root, NULL, &unusable_file_ops))
-		return -ENOMEM;
+		goto fail;
 
 	if (!debugfs_create_file("extfrag_index", 0444,
 			extfrag_debug_root, NULL, &extfrag_file_ops))
-		return -ENOMEM;
+		goto fail;
 
 	return 0;
+fail:
+	debugfs_remove_recursive(extfrag_debug_root);
+	return -ENOMEM;
 }
 
 module_init(extfrag_debug_init);