[patch 2/2] sched/idle: Make default_idle_call() NOHZ aware

[Thomas Gleixner]

Guests fall back to default_idle_call() as there is no cpuidle driver
available to them by default. That causes a problem in fully loaded
scenarios where CPUs go briefly idle for a couple of microseconds:

tick_nohz_idle_stop_tick() is invoked unconditionally which means unless
there is timer pending in the next tick, the tick is stopped and a couple
of microseconds later when the idle condition goes away restarted. That
requires to program the clockevent device twice which implies a VM exit for
each reprogramming.

It was suggested to remove the tick_nohz_idle_stop_tick() invocation from
the default idle code, but would be counterproductive. It would not allow
the host to go into deeper idle states when the guest CPU is fully idle as
it has to maintain the periodic tick.

Cure this by implementing a trivial moving average filter which keeps track
of the recent idle recidency time and only stop the tick when the average
is larger than a tick.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxx>
---
 kernel/sched/idle.c |   65 +++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 57 insertions(+), 8 deletions(-)

--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -105,12 +105,7 @@ static inline void cond_tick_broadcast_e
 static inline void cond_tick_broadcast_exit(void) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE */
 
-/**
- * default_idle_call - Default CPU idle routine.
- *
- * To use when the cpuidle framework cannot be used.
- */
-static void __cpuidle default_idle_call(void)
+static void __cpuidle __default_idle_call(void)
 {
 	instrumentation_begin();
 	if (!current_clr_polling_and_test()) {
@@ -130,6 +125,61 @@ static void __cpuidle default_idle_call(
 	instrumentation_end();
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
+
+/* Limit to 4 entries so it fits in a cache line */
+#define IDLE_DUR_ENTRIES	4
+#define IDLE_DUR_MASK		(IDLE_DUR_ENTRIES - 1)
+
+struct idle_nohz_data {
+	u64		duration[IDLE_DUR_ENTRIES];
+	u64		entry_time;
+	u64		sum;
+	unsigned int	idx;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct idle_nohz_data, nohz_data);
+
+/**
+ * default_idle_call - Default CPU idle routine.
+ *
+ * To use when the cpuidle framework cannot be used.
+ */
+static void default_idle_call(void)
+{
+	struct idle_nohz_data *nd = this_cpu_ptr(&nohz_data);
+	unsigned int idx = nd->idx;
+	s64 delta;
+
+	/*
+	 * If the CPU spends more than a tick on average in idle, try to stop
+	 * the tick.
+	 */
+	if (nd->sum > TICK_NSEC * IDLE_DUR_ENTRIES)
+		tick_nohz_idle_stop_tick();
+
+	__default_idle_call();
+
+	/*
+	 * Build a moving average of the time spent in idle to prevent stopping
+	 * the tick on a loaded system which only goes idle briefly.
+	 */
+	delta = max(sched_clock() - nd->entry_time, 0);
+	nd->sum += delta - nd->duration[idx];
+	nd->duration[idx] = delta;
+	nd->idx = (idx + 1) & IDLE_DUR_MASK;
+}
+
+static void default_idle_enter(void)
+{
+	this_cpu_write(nohz_data.entry_time, sched_clock());
+}
+
+#else  /* CONFIG_NO_HZ_COMMON */
+static inline void default_idle_call(void { __default_idle_call(); }
+static inline void default_idle_enter(void) { }
+#endif /* !CONFIG_NO_HZ_COMMON */
+
 static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev,
 			       u64 max_latency_ns)
@@ -186,8 +236,6 @@ static void cpuidle_idle_call(void)
 	}
 
 	if (cpuidle_not_available(drv, dev)) {
-		tick_nohz_idle_stop_tick();
-
 		default_idle_call();
 		goto exit_idle;
 	}
@@ -276,6 +324,7 @@ static void do_idle(void)
 
 	__current_set_polling();
 	tick_nohz_idle_enter();
+	default_idle_enter();
 
 	while (!need_resched()) {