Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits)
  stop_machine: Move local variable closer to the usage site in cpu_stop_cpu_callback()
  sched, wait: Use wrapper functions
  sched: Remove a stale comment
  ondemand: Make the iowait-is-busy time a sysfs tunable
  ondemand: Solve a big performance issue by counting IOWAIT time as busy
  sched: Intoduce get_cpu_iowait_time_us()
  sched: Eliminate the ts->idle_lastupdate field
  sched: Fold updating of the last_update_time_info into update_ts_time_stats()
  sched: Update the idle statistics in get_cpu_idle_time_us()
  sched: Introduce a function to update the idle statistics
  sched: Add a comment to get_cpu_idle_time_us()
  cpu_stop: add dummy implementation for UP
  sched: Remove rq argument to the tracepoints
  rcu: need barrier() in UP synchronize_sched_expedited()
  sched: correctly place paranioa memory barriers in synchronize_sched_expedited()
  sched: kill paranoia check in synchronize_sched_expedited()
  sched: replace migration_thread with cpu_stop
  stop_machine: reimplement using cpu_stop
  cpu_stop: implement stop_cpu[s]()
  sched: Fix select_idle_sibling() logic in select_task_rq_fair()
  ...

1 files changed, 70 insertions, 14 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f5..1d7b9bc1c03 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,14 +150,32 @@ 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(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);
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+		if (nr_iowait_cpu() > 0)
+			ts->iowait_sleeptime = ktime_add(ts->iowait_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;
 
-	delta = ktime_sub(now, ts->idle_entrytime);
-	ts->idle_lastupdate = now;
-	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	update_ts_time_stats(ts, now, NULL);
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
@@ -165,20 +183,32 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
-	ktime_t now, delta;
+	ktime_t now;
 
 	now = ktime_get();
-	if (ts->idle_active) {
-		delta = ktime_sub(now, ts->idle_entrytime);
-		ts->idle_lastupdate = now;
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-	}
+
+	update_ts_time_stats(ts, now, NULL);
+
 	ts->idle_entrytime = now;
 	ts->idle_active = 1;
 	sched_clock_idle_sleep_event();
 	return now;
 }
 
+/**
+ * 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
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 	if (!tick_nohz_enabled)
 		return -1;
 
-	if (ts->idle_active)
-		*last_update_time = ktime_to_us(ts->idle_lastupdate);
-	else
-		*last_update_time = ktime_to_us(ktime_get());
+	update_ts_time_stats(ts, ktime_get(), last_update_time);
 
 	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
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (!tick_nohz_enabled)
+		return -1;
+
+	update_ts_time_stats(ts, ktime_get(), last_update_time);
+
+	return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
  *
@@ -262,6 +315,9 @@ void tick_nohz_stop_sched_tick(int inidle)
 		goto end;
 	}
 
+	if (nohz_ratelimit(cpu))
+		goto end;
+
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {