vmstat: Speedup and Cleanup

Index: linux/mm/vmstat.c
===================================================================
@@ -444,6 +444,18 @@ static int fold_diff(int *diff)
 	return changes;
 }
 
+bool zone_needs_update(struct per_cpu_pageset *p)
+{
+
+	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.
+	 */
+	return memchr_inv(p->vm_stat_diff, 0,
+			NR_VM_ZONE_STAT_ITEMS) != NULL;
+}
+
 /*
  * Update the zone counters for the current cpu.
  *

@@ -470,18 +482,20 @@ static int refresh_cpu_vm_stats(bool do_
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset __percpu *p = zone->pageset;
 
-		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
-			int v;
+		if (unlikely(zone_needs_update(this_cpu_ptr(p)))) {
+			for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
+				int v;
 
-			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
-			if (v) {
+				v = this_cpu_xchg(p->vm_stat_diff[i], 0);
+				if (v) {
 
-				atomic_long_add(v, &zone->vm_stat[i]);
-				global_diff[i] += v;
+					atomic_long_add(v, &zone->vm_stat[i]);
+					global_diff[i] += v;
 #ifdef CONFIG_NUMA
-				/* 3 seconds idle till flush */
-				__this_cpu_write(p->expire, 3);
+					/* 3 seconds idle till flush */
+					__this_cpu_write(p->expire, 3);
 #endif
+				}
 			}
 		}
 #ifdef CONFIG_NUMA

@@ -494,8 +508,8 @@ static int refresh_cpu_vm_stats(bool do_
 			 * Check if there are pages remaining in this pageset
 			 * if not then there is nothing to expire.
 			 */
-			if (!__this_cpu_read(p->expire) ||
-			       !__this_cpu_read(p->pcp.count))
+			if (likely(!__this_cpu_read(p->expire) ||
+			       !__this_cpu_read(p->pcp.count)))
 				continue;
 
 			/*

@@ -1440,19 +1454,12 @@ static bool need_update(int 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))
+		if (zone_needs_update(p))
 			return true;
-
 	}
 	return false;
 }
 
-
 /*
  * Shepherd worker thread that checks the
  * differentials of processors that have their worker

Index: linux/mm/vmstat.c
===================================================================
@@ -1401,7 +1401,6 @@ static const struct file_operations proc
 static struct workqueue_struct *vmstat_wq;
 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)
 {

@@ -1414,15 +1413,6 @@ static void vmstat_update(struct work_st
 		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
 			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.
-		 */
-		cpumask_set_cpu(smp_processor_id(), cpu_stat_off);
 	}
 }
 

@@ -1436,11 +1426,8 @@ void quiet_vmstat(void)
 	if (system_state != SYSTEM_RUNNING)
 		return;
 
-	do {
-		if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
-			cancel_delayed_work(this_cpu_ptr(&vmstat_work));
-
-	} while (refresh_cpu_vm_stats(false));
+	refresh_cpu_vm_stats(false);
+	cancel_delayed_work(this_cpu_ptr(&vmstat_work));
 }
 
 /*

@@ -1476,13 +1463,12 @@ static void vmstat_shepherd(struct work_
 
 	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))
-
-			queue_delayed_work_on(cpu, vmstat_wq,
-				&per_cpu(vmstat_work, cpu), 0);
+	for_each_online_cpu(cpu) {
+		struct delayed_work *worker = &per_cpu(vmstat_work, cpu);
 
+		if (!delayed_work_pending(worker) && need_update(cpu))
+			queue_delayed_work_on(cpu, vmstat_wq, worker, 0);
+	}
 	put_online_cpus();
 
 	schedule_delayed_work(&shepherd,

@@ -1498,10 +1484,6 @@ static void __init start_shepherd_timer(
 		INIT_DELAYED_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);
-
 	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));

@@ -1536,16 +1518,13 @@ static int vmstat_cpuup_callback(struct
 	case CPU_ONLINE_FROZEN:
 		refresh_zone_stat_thresholds();
 		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));
-		cpumask_clear_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN: