[patch 5/5] mm: vmstat_refresh: avoid queueing work item if cpu stats are clean

[Marcelo Tosatti]

It is not necessary to queue work item to run refresh_vm_stats 
on a remote CPU if that CPU has no dirty stats and no per-CPU
allocations for remote nodes.

This fixes sosreport hang (which uses vmstat_refresh) with 
spinning SCHED_FIFO process.

Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

Index: linux-2.6-vmstat-update/mm/vmstat.c
===================================================================
--- linux-2.6-vmstat-update.orig/mm/vmstat.c
+++ linux-2.6-vmstat-update/mm/vmstat.c
@@ -1888,17 +1888,41 @@ static bool need_update(int cpu)
 }
 
 #ifdef CONFIG_PROC_FS
-static void refresh_vm_stats(struct work_struct *work)
+static bool need_drain_remote_zones(int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p;
+
+		p = per_cpu_ptr(zone->pageset, cpu);
+
+		if (!p->pcp.count)
+			continue;
+#ifdef CONFIG_NUMA
+		if (!p->expire)
+			continue;
+#endif
+		if (zone_to_nid(zone) == cpu_to_node(cpu))
+			continue;
+
+		return true;
+	}
+
+	return false;
+}
+
+static long refresh_vm_stats(void *arg)
 {
 	refresh_cpu_vm_stats(true);
+	return 0;
 }
 
 int vmstat_refresh(struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	long val;
-	int err;
-	int i;
+	int i, cpu;
 
 	/*
 	 * The regular update, every sysctl_stat_interval, may come later
@@ -1912,9 +1936,15 @@ int vmstat_refresh(struct ctl_table *tab
 	 * transiently negative values, report an error here if any of
 	 * the stats is negative, so we know to go looking for imbalance.
 	 */
-	err = schedule_on_each_cpu(refresh_vm_stats);
-	if (err)
-		return err;
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (need_update(cpu) || need_drain_remote_zones(cpu))
+			work_on_cpu(cpu, refresh_vm_stats, NULL);
+
+		cond_resched();
+	}
+	put_online_cpus();
+
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
 		/*
 		 * Skip checking stats known to go negative occasionally.