@@ -99,31 +99,31 @@ static int find_deepest_state(struct cpuidle_driver *drv,
}
/**
- * cpuidle_use_deepest_state - Set/clear governor override flag.
- * @enable: New value of the flag.
+ * cpuidle_use_state - Force the cpuidle framework to enter an idle state.
+ * @state: An integer for an idle state
*
- * Set/unset the current CPU to use the deepest idle state (override governors
- * going forward if set).
+ * Specify an idle state the cpuidle framework must step in and bypass
+ * the idle state selection process.
*/
-void cpuidle_use_deepest_state(bool enable)
+void cpuidle_use_state(int state)
{
struct cpuidle_device *dev;
preempt_disable();
dev = cpuidle_get_device();
if (dev)
- dev->use_deepest_state = enable;
+ dev->use_state = state;
preempt_enable();
}
/**
* cpuidle_find_deepest_state - Find the deepest available idle state.
- * @drv: cpuidle driver for the given CPU.
- * @dev: cpuidle device for the given CPU.
*/
-int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
- struct cpuidle_device *dev)
+int cpuidle_find_deepest_state(void)
{
+ struct cpuidle_device *dev = cpuidle_get_device();
+ struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
return find_deepest_state(drv, dev, UINT_MAX, 0, false);
}
@@ -554,6 +554,7 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
static void __cpuidle_device_init(struct cpuidle_device *dev)
{
memset(dev->states_usage, 0, sizeof(dev->states_usage));
+ dev->use_state = -1;
dev->last_residency = 0;
dev->next_hrtimer = 0;
}
@@ -80,9 +80,9 @@ struct cpuidle_driver_kobj;
struct cpuidle_device {
unsigned int registered:1;
unsigned int enabled:1;
- unsigned int use_deepest_state:1;
unsigned int poll_time_limit:1;
unsigned int cpu;
+ unsigned int use_state;
ktime_t next_hrtimer;
int last_state_idx;
@@ -200,19 +200,17 @@ static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
#endif
#ifdef CONFIG_CPU_IDLE
-extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
- struct cpuidle_device *dev);
+extern int cpuidle_find_deepest_state(void);
extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
struct cpuidle_device *dev);
-extern void cpuidle_use_deepest_state(bool enable);
+extern void cpuidle_use_state(int state);
#else
-static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
- struct cpuidle_device *dev)
+static inline int cpuidle_find_deepest_state(void)
{return -ENODEV; }
static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
struct cpuidle_device *dev)
{return -ENODEV; }
-static inline void cpuidle_use_deepest_state(bool enable)
+static inline void cpuidle_use_state(int state)
{
}
#endif
@@ -165,7 +165,7 @@ static void cpuidle_idle_call(void)
* until a proper wakeup interrupt happens.
*/
- if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+ if (idle_should_enter_s2idle() || dev->use_state != -1) {
if (idle_should_enter_s2idle()) {
rcu_idle_enter();
@@ -181,8 +181,7 @@ static void cpuidle_idle_call(void)
tick_nohz_idle_stop_tick();
rcu_idle_enter();
- next_state = cpuidle_find_deepest_state(drv, dev);
- call_cpuidle(drv, dev, next_state);
+ call_cpuidle(drv, dev, dev->use_state);
} else {
bool stop_tick = true;
@@ -328,7 +327,7 @@ void play_idle(unsigned long duration_us)
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
- cpuidle_use_deepest_state(true);
+ cpuidle_use_state(cpuidle_find_deepest_state());
it.done = 0;
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -339,7 +338,7 @@ void play_idle(unsigned long duration_us)
while (!READ_ONCE(it.done))
do_idle();
- cpuidle_use_deepest_state(false);
+ cpuidle_use_state(-1);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
The play_idle function has two users, the intel powerclamp and the idle_injection. The idle injection cooling device uses the function via the idle_injection powercap's APIs. Unfortunately, play_idle is currently limited by the idle state depth, by default the deepest idle state is selected. On the ARM[64] platforms, most of the time it is the cluster idle state, the exit latency and the residency can be very high. That reduces the scope of the idle injection usage because the impact on the performances can be very significant and the idle injection would make sense only if the frequency scaling fails to cool down the CPU by dropping the static leakage and force the CPU to regain part of its thermal capacity. If the idle injection cycles are done with a shallow state like a retention state, the cooling effect can give similar results than the cpufreq cooling device. In order to prepare the function to receive an idle state parameter, let's replace the 'use_deepest_state' boolean field with 'use_state' and use this value to enter the specific idle state. The current code keeps the default behavior which is go to the deepest idle state. Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> --- drivers/cpuidle/cpuidle.c | 21 +++++++++++---------- include/linux/cpuidle.h | 12 +++++------- kernel/sched/idle.c | 9 ++++----- 3 files changed, 20 insertions(+), 22 deletions(-) -- 2.17.1