diff --git a/mm/vmstat.c b/mm/vmstat.c
index cce7c76..1b12d39 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -7,6 +7,7 @@
  *  zoned VM statistics
  *  Copyright (C) 2006 Silicon Graphics, Inc.,
  *		Christoph Lameter <christoph@lameter.com>
+ *  Copyright (C) 2008-2014 Christoph Lameter
  */
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -14,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <linux/vmstat.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
@@ -419,13 +421,22 @@
 EXPORT_SYMBOL(dec_zone_page_state);
 #endif
 
-static inline void fold_diff(int *diff)
+
+/*
+ * Fold a differential into the global counters.
+ * Returns the number of counters updated.
+ */
+static int fold_diff(int *diff)
 {
 	int i;
+	int changes = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (diff[i])
+		if (diff[i]) {
 			atomic_long_add(diff[i], &vm_stat[i]);
+			changes++;
+	}
+	return changes;
 }
 
 /*
@@ -441,12 +452,15 @@
  * statistics in the remote zone struct as well as the global cachelines
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
+ *
+ * The function returns the number of global counters updated.
  */
-static void refresh_cpu_vm_stats(void)
+static int refresh_cpu_vm_stats(void)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int changes = 0;
 
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset __percpu *p = zone->pageset;
@@ -486,15 +500,17 @@
 			continue;
 		}
 
-
 		if (__this_cpu_dec_return(p->expire))
 			continue;
 
-		if (__this_cpu_read(p->pcp.count))
+		if (__this_cpu_read(p->pcp.count)) {
 			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
+			changes++;
+		}
 #endif
 	}
-	fold_diff(global_diff);
+	changes += fold_diff(global_diff);
+	return changes;
 }
 
 /*
@@ -1239,20 +1255,108 @@
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
+static cpumask_var_t cpu_stat_off;
 
 static void vmstat_update(struct work_struct *w)
 {
-	refresh_cpu_vm_stats();
-	schedule_delayed_work(this_cpu_ptr(&vmstat_work),
-		round_jiffies_relative(sysctl_stat_interval));
+	if (refresh_cpu_vm_stats())
+		/*
+		 * Counters were updated so we expect more updates
+		 * to occur in the future. Keep on running the
+		 * update worker thread.
+		 */
+		schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+			round_jiffies_relative(sysctl_stat_interval));
+	else {
+		/*
+		 * We did not update any counters so the app may be in
+		 * a mode where it does not cause counter updates.
+		 * We may be uselessly running vmstat_update.
+		 * Defer the checking for differentials to the
+		 * shepherd thread on a different processor.
+		 */
+		int r;
+		/*
+		 * Shepherd work thread does not race since it never
+		 * changes the bit if its zero but the cpu
+		 * online / off line code may race if
+		 * worker threads are still allowed during
+		 * shutdown / startup.
+		 */
+		r = cpumask_test_and_set_cpu(smp_processor_id(),
+			cpu_stat_off);
+		VM_BUG_ON(r);
+	}
 }
 
-static void start_cpu_timer(int cpu)
+/*
+ * Check if the diffs for a certain cpu indicate that
+ * an update is needed.
+ */
+static bool need_update(int cpu)
 {
-	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
+	struct zone *zone;
 
-	INIT_DEFERRABLE_WORK(work, vmstat_update);
-	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);
+
+		BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
+		/*
+		 * The fast way of checking if there are any vmstat diffs.
+		 * This works because the diffs are byte sized items.
+		 */
+		if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS))
+			return true;
+
+	}
+	return false;
+}
+
+
+/*
+ * Shepherd worker thread that checks the
+ * differentials of processors that have their worker
+ * threads for vm statistics updates disabled because of
+ * inactivity.
+ */
+static void vmstat_shepherd(struct work_struct *w);
+
+static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);
+
+static void vmstat_shepherd(struct work_struct *w)
+{
+	int cpu;
+
+	get_online_cpus();
+	/* Check processors whose vmstat worker threads have been disabled */
+	for_each_cpu(cpu, cpu_stat_off)
+		if (need_update(cpu) &&
+			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+
+			schedule_delayed_work_on(cpu, &per_cpu(vmstat_work, cpu),
+				__round_jiffies_relative(sysctl_stat_interval, cpu));
+
+	put_online_cpus();
+
+	schedule_delayed_work(&shepherd,
+		round_jiffies_relative(sysctl_stat_interval));
+
+}
+
+static void __init start_shepherd_timer(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
+			vmstat_update);
+
+	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
+		BUG();
+	cpumask_copy(cpu_stat_off, cpu_online_mask);
+
+	schedule_delayed_work(&shepherd,
+		round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void vmstat_cpu_dead(int node)
@@ -1283,17 +1387,17 @@
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		refresh_zone_stat_thresholds();
-		start_cpu_timer(cpu);
 		node_set_state(cpu_to_node(cpu), N_CPU);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		per_cpu(vmstat_work, cpu).work.func = NULL;
+		cpumask_clear_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -1313,15 +1417,10 @@
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	int cpu;
-
 	cpu_notifier_register_begin();
 	__register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu) {
-		start_cpu_timer(cpu);
-		node_set_state(cpu_to_node(cpu), N_CPU);
-	}
+	start_shepherd_timer();
 	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS