cpuidle: Export the next timer expiration for CPUs

To be able to predict the sleep duration for a CPU entering idle, it
is essential to know the expiration time of the next timer.  Both the
teo and the menu cpuidle governors already use this information for
CPU idle state selection.

Moving forward, a similar prediction needs to be made for a group of
idle CPUs rather than for a single one and the following changes
implement a new genpd governor for that purpose.

In order to support that feature, add a new function called
tick_nohz_get_next_hrtimer() that will return the next hrtimer
expiration time of a given CPU to be invoked after deciding
whether or not to stop the scheduler tick on that CPU.

Make the cpuidle core call tick_nohz_get_next_hrtimer() right
before invoking the ->enter() callback provided by the cpuidle
driver for the given state and store its return value in the
per-CPU struct cpuidle_device, so as to make it available to code
outside of cpuidle.

Note that at the point when cpuidle calls tick_nohz_get_next_hrtimer(),
the governor's ->select() callback has already returned and indicated
whether or not the tick should be stopped, so in fact the value
returned by tick_nohz_get_next_hrtimer() always is the next hrtimer
expiration time for the given CPU, possibly including the tick (if
it hasn't been stopped).

Co-developed-by: Lina Iyer <[email protected]>
Co-developed-by: Daniel Lezcano <[email protected]>
Acked-by: Daniel Lezcano <[email protected]>
Signed-off-by: Ulf Hansson <[email protected]>
[ rjw: Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <[email protected]>

drivers/cpuidle/cpuidle.c

@@ -328,9 +328,23 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		  int index)
 {
+	int ret = 0;
+
+	/*
+	 * Store the next hrtimer, which becomes either next tick or the next
+	 * timer event, whatever expires first. Additionally, to make this data
+	 * useful for consumers outside cpuidle, we rely on that the governor's
+	 * ->select() callback have decided, whether to stop the tick or not.
+	 */
+	WRITE_ONCE(dev->next_hrtimer, tick_nohz_get_next_hrtimer());
+
 	if (cpuidle_state_is_coupled(drv, index))
-		return cpuidle_enter_state_coupled(dev, drv, index);
-	return cpuidle_enter_state(dev, drv, index);
+		ret = cpuidle_enter_state_coupled(dev, drv, index);
+	else
+		ret = cpuidle_enter_state(dev, drv, index);
+
+	WRITE_ONCE(dev->next_hrtimer, 0);
+	return ret;
 }
 
 /**
@@ -511,6 +525,7 @@ static void __cpuidle_device_init(struct cpuidle_device *dev)
 {
 	memset(dev->states_usage, 0, sizeof(dev->states_usage));
 	dev->last_residency = 0;
+	dev->next_hrtimer = 0;
 }
 
 /**

include/linux/cpuidle.h

@@ -83,6 +83,7 @@ struct cpuidle_device {
 	unsigned int		use_deepest_state:1;
 	unsigned int		poll_time_limit:1;
 	unsigned int		cpu;
+	ktime_t			next_hrtimer;
 
 	int			last_residency;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];

include/linux/tick.h

@@ -122,6 +122,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern bool tick_nohz_idle_got_tick(void);
+extern ktime_t tick_nohz_get_next_hrtimer(void);
 extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
@@ -145,7 +146,11 @@ static inline void tick_nohz_idle_restart_tick(void) { }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 static inline bool tick_nohz_idle_got_tick(void) { return false; }
-
+static inline ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	/* Next wake up is the tick period, assume it starts now */
+	return ktime_add(ktime_get(), TICK_NSEC);
+}
 static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
 	*delta_next = TICK_NSEC;

kernel/time/tick-sched.c

@@ -1022,6 +1022,18 @@ bool tick_nohz_idle_got_tick(void)
 	return false;
 }
 
+/**
+ * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
+ * or the tick, whatever that expires first. Note that, if the tick has been
+ * stopped, it returns the next hrtimer.
+ *
+ * Called from power state control code with interrupts disabled
+ */
+ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
+}
+
 /**
  * tick_nohz_get_sleep_length - return the expected length of the current sleep
  * @delta_next: duration until the next event if the tick cannot be stopped