[PATCH 1/4] nohz: Only update sleeptime stats locally

[Frederic Weisbecker]

The idle and io sleeptime stats can be updated concurrently from callers
of get_cpu_idle_time_us(), get_cpu_iowait_time_us() and tick_nohz_stop_idle().

Updaters can easily race and mess up with internal datas coherency , for example
when a governor calls a get_cpu_*_time_us() API and the target CPU exits idle at
the same time, because no locking or whatsoever is there to protect against
this concurrency.

To fix this, lets only update the sleeptime stats locally when the CPU
exits from idle. This is the only place where a real update is truly
needed. The callers of get_cpu_*_time_us() can simply add up the pending
sleep time delta to the last sleeptime snapshot in order to get a coherent
result. There is no need for them to also update the stats.

Reported-by: Fernando Luis Vazquez Cao <fernando_b1@xxxxxxxxxxxxx>
Reported-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Fernando Luis Vazquez Cao <fernando_b1@xxxxxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
---
 kernel/time/tick-sched.c |   65 +++++++++++++++------------------------------
 1 files changed, 22 insertions(+), 43 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e77edc9..ede0405 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -408,33 +408,18 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	touch_softlockup_watchdog();
 }
 
-/*
- * Updates the per cpu time idle statistics counters
- */
-static void
-update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
-{
-	ktime_t delta;
-
-	if (ts->idle_active) {
-		delta = ktime_sub(now, ts->idle_entrytime);
-		if (nr_iowait_cpu(cpu) > 0)
-			ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
-		else
-			ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-		ts->idle_entrytime = now;
-	}
-
-	if (last_update_time)
-		*last_update_time = ktime_to_us(now);
-
-}
-
 static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t delta;
 
-	update_ts_time_stats(cpu, ts, now, NULL);
+	/* Updates the per cpu time idle statistics counters */
+	delta = ktime_sub(now, ts->idle_entrytime);
+	if (nr_iowait_cpu(cpu) > 0)
+		ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+	else
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	ts->idle_entrytime = now;
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
@@ -473,17 +458,14 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 		return -1;
 
 	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);
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
 
-			idle = ktime_add(ts->idle_sleeptime, delta);
-		} else {
-			idle = ts->idle_sleeptime;
-		}
+	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);
@@ -514,17 +496,14 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 		return -1;
 
 	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);
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
 
-			iowait = ktime_add(ts->iowait_sleeptime, delta);
-		} else {
-			iowait = ts->iowait_sleeptime;
-		}
+	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(iowait);
-- 
1.7.5.4

--
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/