[patch v9 10/10] mm: vmstat_refresh: avoid queueing work item if cpu stats are clean

[patch v9 10/10] mm: vmstat_refresh: avoid queueing work item if cpu stats are clean

[Marcelo Tosatti]

The logic to disable vmstat worker thread, when entering
nohz full, does not cover all scenarios. For example, it is possible
for the following to happen:
References: <20220127172319.428529308@fuller.cnet>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8

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@redhat.com>

---
 mm/vmstat.c |   49 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 5 deletions(-)

Index: linux-2.6/mm/vmstat.c
===================================================================
--- linux-2.6.orig/mm/vmstat.c
+++ linux-2.6/mm/vmstat.c
@@ -1910,6 +1910,31 @@ static bool need_update(int cpu)
 }
 
 #ifdef CONFIG_PROC_FS
+static bool need_drain_remote_zones(int cpu)
+{
+#ifdef CONFIG_NUMA
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pages *pcp;
+
+		pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+		if (!pcp->count)
+			continue;
+
+		if (!pcp->expire)
+			continue;
+
+		if (zone_to_nid(zone) == cpu_to_node(cpu))
+			continue;
+
+		return true;
+	}
+#endif
+
+	return false;
+}
+
 static void refresh_vm_stats(struct work_struct *work)
 {
 	refresh_cpu_vm_stats(true);
@@ -1919,8 +1944,12 @@ int vmstat_refresh(struct ctl_table *tab
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	long val;
-	int err;
-	int i;
+	int i, cpu;
+	struct work_struct __percpu *works;
+
+	works = alloc_percpu(struct work_struct);
+	if (!works)
+		return -ENOMEM;
 
 	/*
 	 * The regular update, every sysctl_stat_interval, may come later
@@ -1934,9 +1963,19 @@ 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;
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct work_struct *work = per_cpu_ptr(works, cpu);
+
+		INIT_WORK(work, refresh_vm_stats);
+		if (need_update(cpu) || need_drain_remote_zones(cpu))
+			schedule_work_on(cpu, work);
+	}
+	for_each_online_cpu(cpu)
+		flush_work(per_cpu_ptr(works, cpu));
+	cpus_read_unlock();
+	free_percpu(works);
+
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
 		/*
 		 * Skip checking stats known to go negative occasionally.