To be able to predict the sleep duration for a CPU that is entering idle,
knowing when the next timer/tick is going to expire, is extremely useful.
Both the teo and the menu cpuidle governors already makes use of this
information, while selecting an idle state.
Moving forward, the similar prediction needs to be done, but for a group of
idle CPUs rather than for a single idle CPU. Following changes implements a
new genpd governor, which needs this.
Support this, by sharing a new function called
tick_nohz_get_next_hrtimer(), which returns the next hrtimer or the next
tick, whatever that expires first.
Additionally, when cpuidle is about to invoke the ->enter() callback, then
call tick_nohz_get_next_hrtimer() and store its return value in the per CPU
struct cpuidle_device, as to make it available outside cpuidle.
Do note, at the point when cpuidle calls tick_nohz_get_next_hrtimer(), the
governor's ->select() callback has already made a decision whether to stop
the tick or not. In this way, tick_nohz_get_next_hrtimer() actually returns
the next timer expiration, whatever origin.
Cc: Lina Iyer <ilina@xxxxxxxxxxxxxx>
Co-developed-by: Lina Iyer <lina.iyer@xxxxxxxxxx>
Co-developed-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Acked-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Signed-off-by: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
---
Changes in v13:
- As suggested by Rafael, use WRITE|READ_ONCE when writing/reading the
next_hrtimer variable and also avoid it from containing a stale value.
---
drivers/cpuidle/cpuidle.c | 19 +++++++++++++++++--
include/linux/cpuidle.h | 1 +
include/linux/tick.h | 7 ++++++-
kernel/time/tick-sched.c | 12 ++++++++++++
4 files changed, 36 insertions(+), 3 deletions(-)
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 7f108309e871..0f4b7c45df3e 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/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;
}
/**
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3b39472324a3..bb9a0db89f1a 100644
--- a/include/linux/cpuidle.h
+++ b/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];
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 55388ab45fd4..8891b5ac3e40 100644
--- a/include/linux/tick.h
+++ b/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;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6fa52cd6df0b..8d18e03124ff 100644
--- a/kernel/time/tick-sched.c
+++ b/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
--
2.17.1
