/**
* menu_select - selects the next idle state to enter
* @drv: cpuidle driver containing state data
* @dev: the CPU
*/
static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
int i;
int multiplier;
struct timespec t;
if (data->needs_update) {
menu_update(drv, dev);
data->needs_update = 0;
}
data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
data->exit_us = 0;
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0))
return 0;
/* determine the expected residency time, round up */
t = ktime_to_timespec(tick_nohz_get_sleep_length());
data->expected_us =
t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
data->bucket = which_bucket(data->expected_us);
multiplier = performance_multiplier();
/*
* if the correction factor is 0 (eg first time init or cpu hotplug
* etc), we actually want to start out with a unity factor.
*/
if (data->correction_factor[data->bucket] == 0)
data->correction_factor[data->bucket] = RESOLUTION * DECAY;
/*
* Force the result of multiplication to be 64 bits even if both
* operands are 32 bits.
* Make sure to round up for half microseconds.
*/
data->predicted_us = div_round64((uint64_t)data->expected_us *
data->correction_factor[data->bucket],
RESOLUTION * DECAY);
get_typical_interval(data);
/*
* We want to default to C1 (hlt), not to busy polling
* unless the timer is happening really really soon.
*/
if (data->expected_us > 5 &&
!drv->states[CPUIDLE_DRIVER_STATE_START].disabled &&
dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
/*
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
struct cpuidle_state_usage *su = &dev->states_usage[i];
if (s->disabled || su->disable)
continue;
if (s->target_residency > data->predicted_us)
continue;
if (s->exit_latency > latency_req)
continue;
if (s->exit_latency * multiplier > data->predicted_us)
continue;
data->last_state_idx = i;
data->exit_us = s->exit_latency;
}
return data->last_state_idx;
}
/**
* menu_select - selects the next idle state to enter
* @drv: cpuidle driver containing state data
* @dev: the CPU
*/
static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
int power_usage = INT_MAX;
int i;
int multiplier;
struct timespec t;
int repeat = 0, low_predicted = 0;
int cpu = smp_processor_id();
struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
if (data->needs_update) {
menu_update(drv, dev);
data->needs_update = 0;
}
data->last_state_idx = 0;
data->exit_us = 0;
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0))
return 0;
/* determine the expected residency time, round up */
t = ktime_to_timespec(tick_nohz_get_sleep_length());
data->expected_us =
t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
data->bucket = which_bucket(data->expected_us);
multiplier = performance_multiplier();
/*
* if the correction factor is 0 (eg first time init or cpu hotplug
* etc), we actually want to start out with a unity factor.
*/
if (data->correction_factor[data->bucket] == 0)
data->correction_factor[data->bucket] = RESOLUTION * DECAY;
/* Make sure to round up for half microseconds */
data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
RESOLUTION * DECAY);
repeat = get_typical_interval(data);
/*
* We want to default to C1 (hlt), not to busy polling
* unless the timer is happening really really soon.
*/
if (data->expected_us > 5 &&
dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
/*
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
struct cpuidle_state_usage *su = &dev->states_usage[i];
if (su->disable)
continue;
if (s->target_residency > data->predicted_us) {
low_predicted = 1;
continue;
}
if (s->exit_latency > latency_req)
continue;
if (s->exit_latency * multiplier > data->predicted_us)
continue;
if (s->power_usage < power_usage) {
power_usage = s->power_usage;
data->last_state_idx = i;
data->exit_us = s->exit_latency;
}
}
/* not deepest C-state chosen for low predicted residency */
if (low_predicted) {
unsigned int timer_us = 0;
unsigned int perfect_us = 0;
/*
* Set a timer to detect whether this sleep is much
* longer than repeat mode predicted. If the timer
* triggers, the code will evaluate whether to put
* the CPU into a deeper C-state.
* The timer is cancelled on CPU wakeup.
*/
timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
perfect_us = perfect_cstate_ms * 1000;
if (repeat && (4 * timer_us < data->expected_us)) {
hrtimer_start(hrtmr, ns_to_ktime(1000 * timer_us),
HRTIMER_MODE_REL_PINNED);
/* In repeat case, menu hrtimer is started */
per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
} else if (perfect_us < data->expected_us) {
/*
* The next timer is long. This could be because
* we did not make a useful prediction.
* In that case, it makes sense to re-enter
* into a deeper C-state after some time.
*/
hrtimer_start(hrtmr, ns_to_ktime(1000 * timer_us),
HRTIMER_MODE_REL_PINNED);
/* In general case, menu hrtimer is started */
per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_GENERAL;
}
}
return data->last_state_idx;
}
/**
* menu_select - selects the next idle state to enter
* @drv: cpuidle driver containing state data
* @dev: the CPU
*/
static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
int i;
int multiplier;
struct timespec t;
if (data->needs_update) {
menu_update(drv, dev);
data->needs_update = 0;
}
data->last_state_idx = 0;
data->exit_us = 0;
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0))
return 0;
/* determine the expected residency time, round up */
t = ktime_to_timespec(tick_nohz_get_sleep_length());
data->expected_us =
t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
data->bucket = which_bucket(data->expected_us);
multiplier = performance_multiplier();
/*
* if the correction factor is 0 (eg first time init or cpu hotplug
* etc), we actually want to start out with a unity factor.
*/
if (data->correction_factor[data->bucket] == 0)
data->correction_factor[data->bucket] = RESOLUTION * DECAY;
/* Make sure to round up for half microseconds */
#ifdef CONFIG_SKIP_IDLE_CORRELATION
if (dev->skip_idle_correlation)
data->predicted_us = data->expected_us;
else
#endif
data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
RESOLUTION * DECAY);
/* This patch is not checked */
#ifndef CONFIG_CPU_THERMAL_IPA
get_typical_interval(data);
#else
/*
* HACK - Ignore repeating patterns when we're
* forecasting a very large idle period.
*/
if(data->predicted_us < MAX_INTERESTING)
get_typical_interval(data);
#endif
/*
* We want to default to C1 (hlt), not to busy polling
* unless the timer is happening really really soon.
*/
if (data->expected_us > 5 &&
!drv->states[CPUIDLE_DRIVER_STATE_START].disabled &&
dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
/*
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
struct cpuidle_state_usage *su = &dev->states_usage[i];
if (s->disabled || su->disable)
continue;
if (s->target_residency > data->predicted_us)
continue;
if (s->exit_latency > latency_req)
continue;
if (s->exit_latency * multiplier > data->predicted_us)
continue;
data->last_state_idx = i;
data->exit_us = s->exit_latency;
}
return data->last_state_idx;
}
/**
* menu_select - selects the next idle state to enter
* @drv: cpuidle driver containing state data
* @dev: the CPU
*/
static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = this_cpu_ptr(&menu_devices);
int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
int i;
unsigned int interactivity_req;
int repeat = 0, low_predicted = 0;
int cpu = smp_processor_id();
struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
unsigned long nr_iowaiters;
if (data->needs_update) {
menu_update(drv, dev);
data->needs_update = 0;
}
data->last_state_idx = 0;
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0))
return 0;
/* determine the expected residency time, round up */
data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
nr_iowaiters = nr_iowait_cpu(smp_processor_id());
data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
/*
* if the correction factor is 0 (eg first time init or cpu hotplug
* etc), we actually want to start out with a unity factor.
*/
if (data->correction_factor[data->bucket] == 0)
data->correction_factor[data->bucket] = RESOLUTION * DECAY;
/* Make sure to round up for half microseconds */
#ifdef CONFIG_SKIP_IDLE_CORRELATION
if (dev->skip_idle_correlation)
data->predicted_us = data->next_timer_us;
else
#endif
data->predicted_us = div_round64(data->next_timer_us * data->correction_factor[data->bucket],
RESOLUTION * DECAY);
/* This patch is not checked */
#ifndef CONFIG_CPU_THERMAL_IPA
repeat = get_typical_interval(data);
#else
/*
* HACK - Ignore repeating patterns when we're
* forecasting a very large idle period.
*/
if(data->predicted_us < MAX_INTERESTING)
repeat = get_typical_interval(data);
#endif
/*
* Performance multiplier defines a minimum predicted idle
* duration / latency ratio. Adjust the latency limit if
* necessary.
*/
interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters);
if (latency_req > interactivity_req)
latency_req = interactivity_req;
/*
* We want to default to C1 (hlt), not to busy polling
* unless the timer is happening really really soon.
*/
if (data->next_timer_us > 5 &&
!drv->states[CPUIDLE_DRIVER_STATE_START].disabled &&
dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
/*
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
struct cpuidle_state_usage *su = &dev->states_usage[i];
if (s->disabled || su->disable)
continue;
if (s->target_residency > data->predicted_us) {
low_predicted = 1;
continue;
}
if (s->exit_latency > latency_req)
continue;
data->last_state_idx = i;
}
/* not deepest C-state chosen for low predicted residency */
if (low_predicted) {
unsigned int timer_us = 0;
unsigned int perfect_us = 0;
/*
* Set a timer to detect whether this sleep is much
* longer than repeat mode predicted. If the timer
* triggers, the code will evaluate whether to put
* the CPU into a deeper C-state.
* The timer is cancelled on CPU wakeup.
*/
timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
perfect_us = perfect_cstate_ms * 1000;
if (repeat && (4 * timer_us < data->next_timer_us)) {
RCU_NONIDLE(hrtimer_start(hrtmr,
ns_to_ktime(1000 * timer_us),
HRTIMER_MODE_REL_PINNED));
/* In repeat case, menu hrtimer is started */
per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
} else if (perfect_us < data->next_timer_us) {
/*
* The next timer is long. This could be because
* we did not make a useful prediction.
* In that case, it makes sense to re-enter
* into a deeper C-state after some time.
*/
RCU_NONIDLE(hrtimer_start(hrtmr,
ns_to_ktime(1000 * timer_us),
HRTIMER_MODE_REL_PINNED));
/* In general case, menu hrtimer is started */
per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_GENERAL;
}
}
return data->last_state_idx;
}