1 files changed, 63 insertions, 72 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a46506f7ec6d..52254679ec48 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -647,43 +647,67 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	touch_softlockup_watchdog_sched();
 }
 
-/*
- * 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)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
 	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 (WARN_ON_ONCE(!ts->idle_active))
+		return;
 
-	if (last_update_time)
-		*last_update_time = ktime_to_us(now);
+	delta = ktime_sub(now, ts->idle_entrytime);
 
-}
+	write_seqcount_begin(&ts->idle_sleeptime_seq);
+	if (nr_iowait_cpu(smp_processor_id()) > 0)
+		ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+	else
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
 
-static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
-{
-	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
+	ts->idle_entrytime = now;
 	ts->idle_active = 0;
+	write_seqcount_end(&ts->idle_sleeptime_seq);
 
 	sched_clock_idle_wakeup_event();
 }
 
 static void tick_nohz_start_idle(struct tick_sched *ts)
 {
+	write_seqcount_begin(&ts->idle_sleeptime_seq);
 	ts->idle_entrytime = ktime_get();
 	ts->idle_active = 1;
+	write_seqcount_end(&ts->idle_sleeptime_seq);
+
 	sched_clock_idle_sleep_event();
 }
 
+static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
+				 bool compute_delta, u64 *last_update_time)
+{
+	ktime_t now, idle;
+	unsigned int seq;
+
+	if (!tick_nohz_active)
+		return -1;
+
+	now = ktime_get();
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
+
+	do {
+		seq = read_seqcount_begin(&ts->idle_sleeptime_seq);
+
+		if (ts->idle_active && compute_delta) {
+			ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+			idle = ktime_add(*sleeptime, delta);
+		} else {
+			idle = *sleeptime;
+		}
+	} while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq));
+
+	return ktime_to_us(idle);
+
+}
+
 /**
  * get_cpu_idle_time_us - get the total idle time of a CPU
  * @cpu: CPU number to query
@@ -691,7 +715,10 @@ static void tick_nohz_start_idle(struct tick_sched *ts)
  * counters if NULL.
  *
  * Return the cumulative idle time (since boot) for a given
- * CPU, in microseconds.
+ * CPU, in microseconds. Note this is partially broken due to
+ * the counter of iowait tasks that can be remotely updated without
+ * any synchronization. Therefore it is possible to observe backward
+ * values within two consecutive reads.
  *
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
@@ -701,27 +728,9 @@ static void tick_nohz_start_idle(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_active)
-		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);
-
-			idle = ktime_add(ts->idle_sleeptime, delta);
-		} else {
-			idle = ts->idle_sleeptime;
-		}
-	}
-
-	return ktime_to_us(idle);
 
+	return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime,
+				     !nr_iowait_cpu(cpu), last_update_time);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
@@ -732,7 +741,10 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
  * counters if NULL.
  *
  * Return the cumulative iowait time (since boot) for a given
- * CPU, in microseconds.
+ * CPU, in microseconds. Note this is partially broken due to
+ * the counter of iowait tasks that can be remotely updated without
+ * any synchronization. Therefore it is possible to observe backward
+ * values within two consecutive reads.
  *
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
@@ -742,26 +754,9 @@ 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_active)
-		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);
-
-			iowait = ktime_add(ts->iowait_sleeptime, delta);
-		} else {
-			iowait = ts->iowait_sleeptime;
-		}
-	}
-
-	return ktime_to_us(iowait);
+	return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime,
+				     nr_iowait_cpu(cpu), last_update_time);
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
@@ -1094,10 +1089,16 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	return true;
 }
 
-static void __tick_nohz_idle_stop_tick(struct tick_sched *ts)
+/**
+ * tick_nohz_idle_stop_tick - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ */
+void tick_nohz_idle_stop_tick(void)
 {
-	ktime_t expires;
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	int cpu = smp_processor_id();
+	ktime_t expires;
 
 	/*
 	 * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the
@@ -1129,16 +1130,6 @@ static void __tick_nohz_idle_stop_tick(struct tick_sched *ts)
 	}
 }
 
-/**
- * tick_nohz_idle_stop_tick - stop the idle tick from the idle task
- *
- * When the next event is more than a tick into the future, stop the idle tick
- */
-void tick_nohz_idle_stop_tick(void)
-{
-	__tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched));
-}
-
 void tick_nohz_idle_retain_tick(void)
 {
 	tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));