vmstat: make vmstat_updater deferrable again and shut down on idle

Currently the vmstat updater is not deferrable as a result of commit
ba4877b ("vmstat: do not use deferrable delayed work for
vmstat_update").  This in turn can cause multiple interruptions of the
applications because the vmstat updater may run at

Make vmstate_update deferrable again and provide a function that folds
the differentials when the processor is going to idle mode thus
addressing the issue of the above commit in a clean way.

Note that the shepherd thread will continue scanning the differentials
from another processor and will reenable the vmstat workers if it
detects any changes.

Change-Id: Idf256cfacb40b4dc8dbb6795cf06b34e8fec7a06
Fixes: ba4877b ("vmstat: do not use deferrable delayed work for vmstat_update")
Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Git-commit: 0eb77e9
[shashim@codeaurora.org: resolve minor merge conflicts]
Signed-off-by: Shiraz Hashim <shashim@codeaurora.org>

include/linux/vmstat.h

@@ -211,6 +211,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item);
 extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
+void quiet_vmstat(void);
 void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
@@ -272,6 +273,7 @@ static inline void __dec_zone_page_state(struct page *page,
 static inline void refresh_cpu_vm_stats(int cpu) { }
 static inline void refresh_zone_stat_thresholds(void) { }
 static inline void cpu_vm_stats_fold(int cpu) { }
+static inline void quiet_vmstat(void) { }
 
 static inline void drain_zonestat(struct zone *zone,
 			struct per_cpu_pageset *pset) { }

kernel/sched/idle.c

@@ -226,6 +226,7 @@ static void cpu_idle_loop(void)
 		 */
 
 		__current_set_polling();
+		quiet_vmstat();
 		tick_nohz_idle_enter();
 
 		while (!need_resched()) {

mm/vmstat.c

@@ -455,7 +455,7 @@ static int fold_diff(int *diff)
  *
  * The function returns the number of global counters updated.
  */
-static int refresh_cpu_vm_stats(void)
+static int refresh_cpu_vm_stats(bool do_pagesets)
 {
 	struct zone *zone;
 	int i;
@@ -479,33 +479,35 @@ static int refresh_cpu_vm_stats(void)
 #endif
 			}
 		}
-		cond_resched();
 #ifdef CONFIG_NUMA
-		/*
-		 * Deal with draining the remote pageset of this
-		 * processor
-		 *
-		 * Check if there are pages remaining in this pageset
-		 * if not then there is nothing to expire.
-		 */
-		if (!__this_cpu_read(p->expire) ||
+		if (do_pagesets) {
+			cond_resched();
+			/*
+			 * Deal with draining the remote pageset of this
+			 * processor
+			 *
+			 * 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))
-			continue;
-
-		/*
-		 * We never drain zones local to this processor.
-		 */
-		if (zone_to_nid(zone) == numa_node_id()) {
-			__this_cpu_write(p->expire, 0);
-			continue;
-		}
+				continue;
+
+			/*
+			 * We never drain zones local to this processor.
+			 */
+			if (zone_to_nid(zone) == numa_node_id()) {
+				__this_cpu_write(p->expire, 0);
+				continue;
+			}
 
-		if (__this_cpu_dec_return(p->expire))
-			continue;
+			if (__this_cpu_dec_return(p->expire))
+				continue;
 
-		if (__this_cpu_read(p->pcp.count)) {
-			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
-			changes++;
+			if (__this_cpu_read(p->pcp.count)) {
+				drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
+				changes++;
+			}
 		}
 #endif
 	}
@@ -1259,15 +1261,15 @@ static cpumask_var_t cpu_stat_off;
 
 static void vmstat_update(struct work_struct *w)
 {
-	if (refresh_cpu_vm_stats())
+	if (refresh_cpu_vm_stats(true)) {
 		/*
 		 * 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 {
+	} else {
 		/*
 		 * We did not update any counters so the app may be in
 		 * a mode where it does not cause counter updates.
@@ -1289,6 +1291,23 @@ static void vmstat_update(struct work_struct *w)
 	}
 }
 
+/*
+ * Switch off vmstat processing and then fold all the remaining differentials
+ * until the diffs stay at zero. The function is used by NOHZ and can only be
+ * invoked when tick processing is not active.
+ */
+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));
+}
+
 /*
  * Check if the diffs for a certain cpu indicate that
  * an update is needed.
@@ -1321,7 +1340,7 @@ static bool need_update(int cpu)
  */
 static void vmstat_shepherd(struct work_struct *w);
 
-static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);
+static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd);
 
 static void vmstat_shepherd(struct work_struct *w)
 {