[PATCH] nohz: do not update idle/iowait counters fromget_cpu_{idle,iowait}_time_us if not asked

[Michal Hocko]

get_cpu_{idle,iowait}_time_us update idle/iowait counters
unconditionally if the given CPU is in the idle loop. This doesn't work
well outside of CPU governors which are singletons so nobody (except for
IRQ) can race with them.
We will need to use both functions from /proc/stat handler to properly
handle nohz idle/iowait times.
Let's update those counters only if the given last_update_time parameter
is non-NULL which means that the caller is interested in updating.

Signed-off-by: Michal Hocko <mhocko@xxxxxxx>
---
 kernel/time/tick-sched.c |   37 +++++++++++++++++++++++++++++++------
 1 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7ab44bc..5bcff38 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -198,7 +198,8 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
 /**
  * get_cpu_idle_time_us - get the total idle time of a cpu
  * @cpu: CPU number to query
- * @last_update_time: variable to store update time in
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
  *
  * Return the cummulative idle time (since boot) for a given
  * CPU, in microseconds.
@@ -211,20 +212,33 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t now, idle;
 
 	if (!tick_nohz_enabled)
 		return -1;
 
-	update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
+	now = ktime_get();
+	if (last_update_time) {
+		update_ts_time_stats(cpu, ts, now, last_update_time);
+		idle = ts->idle_sleeptime;
+	} else {
+		if (ts->idle_active && !nr_iowait_cpu(cpu)) {
+			ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+			idle = ktime_add(ts->idle_sleeptime, delta);
+		} else
+			idle = ts->idle_sleeptime;
+	}
+
+	return ktime_to_us(idle);
 
-	return ktime_to_us(ts->idle_sleeptime);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
 /**
  * get_cpu_iowait_time_us - get the total iowait time of a cpu
  * @cpu: CPU number to query
- * @last_update_time: variable to store update time in
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
  *
  * Return the cummulative iowait time (since boot) for a given
  * CPU, in microseconds.
@@ -237,13 +251,24 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t now, iowait;
 
 	if (!tick_nohz_enabled)
 		return -1;
 
-	update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
+	now = ktime_get();
+	if (last_update_time) {
+		update_ts_time_stats(cpu, ts, now, last_update_time);
+		iowait = ts->iowait_sleeptime;
+	} else {
+		if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
+			ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+			iowait = ktime_add(ts->iowait_sleeptime, delta);
+		} else
+			iowait = ts->iowait_sleeptime;
+	}
 
-	return ktime_to_us(ts->iowait_sleeptime);
+	return ktime_to_us(iowait);
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
-- 
1.7.5.4


-- 
Michal Hocko
SUSE Labs
SUSE LINUX s.r.o.
Lihovarska 1060/12
190 00 Praha 9    
Czech Republic
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/