/**
* __cpuidle_register_device - internal register function called before register
* and enable routines
* @dev: the cpu
*
* cpuidle_lock mutex must be held before this is called
*/
static int __cpuidle_register_device(struct cpuidle_device *dev)
{
int ret;
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
if (!try_module_get(drv->owner))
return -EINVAL;
per_cpu(cpuidle_devices, dev->cpu) = dev;
list_add(&dev->device_list, &cpuidle_detected_devices);
ret = cpuidle_add_sysfs(dev);
if (ret)
goto err_sysfs;
ret = cpuidle_coupled_register_device(dev);
if (ret)
goto err_coupled;
dev->registered = 1;
return 0;
err_coupled:
cpuidle_remove_sysfs(dev);
err_sysfs:
list_del(&dev->device_list);
per_cpu(cpuidle_devices, dev->cpu) = NULL;
module_put(drv->owner);
return ret;
}
/**
* cpuidle_play_dead - cpu off-lining
*
* Returns in case of an error or no driver
*/
int cpuidle_play_dead(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int i, dead_state = -1;
int power_usage = INT_MAX;
if (!drv)
return -ENODEV;
/* Find lowest-power state that supports long-term idle */
for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
if (s->power_usage < power_usage && s->enter_dead) {
power_usage = s->power_usage;
dead_state = i;
}
}
if (dead_state != -1)
return drv->states[dead_state].enter_dead(dev, dead_state);
return -ENODEV;
}
/**
* cpuidle_enable_device - enables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
int cpuidle_enable_device(struct cpuidle_device *dev)
{
int ret, i;
struct cpuidle_driver *drv;
if (!dev)
return -EINVAL;
if (dev->enabled)
return 0;
drv = cpuidle_get_cpu_driver(dev);
if (!drv || !cpuidle_curr_governor)
return -EIO;
if (!dev->state_count)
dev->state_count = drv->state_count;
if (dev->registered == 0) {
ret = __cpuidle_register_device(dev);
if (ret)
return ret;
}
cpuidle_enter_ops = drv->en_core_tk_irqen ?
cpuidle_enter_tk : cpuidle_enter;
poll_idle_init(drv);
ret = cpuidle_add_device_sysfs(dev);
if (ret)
return ret;
if (cpuidle_curr_governor->enable &&
(ret = cpuidle_curr_governor->enable(drv, dev)))
goto fail_sysfs;
for (i = 0; i < dev->state_count; i++) {
dev->states_usage[i].usage = 0;
dev->states_usage[i].time = 0;
}
dev->last_residency = 0;
smp_wmb();
dev->enabled = 1;
enabled_devices++;
return 0;
fail_sysfs:
cpuidle_remove_device_sysfs(dev);
return ret;
}
/**
* cpuidle_idle_call - the main idle loop
*
* NOTE: no locks or semaphores should be used here
* return non-zero on failure
*/
int cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv;
int next_state, entered_state;
if (off)
return -ENODEV;
if (!initialized)
return -ENODEV;
/* check if the device is ready */
if (!dev || !dev->enabled)
return -EBUSY;
drv = cpuidle_get_cpu_driver(dev);
/* ask the governor for the next state */
next_state = cpuidle_curr_governor->select(drv, dev);
if (next_state < 0)
return -EBUSY;
if (need_resched()) {
dev->last_residency = 0;
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev, next_state);
local_irq_enable();
return 0;
}
trace_cpu_idle_rcuidle(next_state, dev->cpu);
if (drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
&dev->cpu);
if (cpuidle_state_is_coupled(dev, drv, next_state))
entered_state = cpuidle_enter_state_coupled(dev, drv,
next_state);
else
entered_state = cpuidle_enter_state(dev, drv, next_state);
if (drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
&dev->cpu);
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev, entered_state);
return 0;
}
/**
* cpuidle_play_dead - cpu off-lining
*
* Returns in case of an error or no driver
*/
int cpuidle_play_dead(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int i;
if (!drv)
return -ENODEV;
/* Find lowest-power state that supports long-term idle */
for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
if (drv->states[i].enter_dead)
return drv->states[i].enter_dead(dev, i);
return -ENODEV;
}
/**
* cpuidle_idle_call - the main idle loop
*
* NOTE: no locks or semaphores should be used here
* return non-zero on failure
*/
int cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv;
int next_state, entered_state;
if (off)
return -ENODEV;
if (!initialized)
return -ENODEV;
/* check if the device is ready */
if (!dev || !dev->enabled)
return -EBUSY;
drv = cpuidle_get_cpu_driver(dev);
/* ask the governor for the next state */
next_state = cpuidle_curr_governor->select(drv, dev);
if (need_resched()) {
dev->last_residency = 0;
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev, next_state);
local_irq_enable();
return 0;
}
trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu);
trace_cpu_idle_rcuidle(next_state, dev->cpu);
if (cpuidle_state_is_coupled(dev, drv, next_state))
entered_state = cpuidle_enter_state_coupled(dev, drv,
next_state);
else
entered_state = cpuidle_enter_state(dev, drv, next_state);
trace_power_end_rcuidle(dev->cpu);
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev, entered_state);
return 0;
}
/**
* cpuidle_disable_device - disables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
void cpuidle_disable_device(struct cpuidle_device *dev)
{
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
if (!dev || !dev->enabled)
return;
if (!drv || !cpuidle_curr_governor)
return;
dev->enabled = 0;
if (cpuidle_curr_governor->disable)
cpuidle_curr_governor->disable(drv, dev);
cpuidle_remove_device_sysfs(dev);
enabled_devices--;
}
/**
* cpuidle_unregister_device - unregisters a CPU's idle PM feature
* @dev: the cpu
*/
void cpuidle_unregister_device(struct cpuidle_device *dev)
{
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
if (dev->registered == 0)
return;
cpuidle_pause_and_lock();
cpuidle_disable_device(dev);
cpuidle_remove_sysfs(dev);
list_del(&dev->device_list);
per_cpu(cpuidle_devices, dev->cpu) = NULL;
cpuidle_coupled_unregister_device(dev);
cpuidle_resume_and_unlock();
module_put(drv->owner);
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
bool broadcast;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
/*
* Ask the cpuidle framework to choose a convenient idle state.
* Fall back to the default arch idle method on errors.
*/
next_state = cpuidle_select(drv, dev);
if (next_state < 0) {
use_default:
/*
* We can't use the cpuidle framework, let's use the default
* idle routine.
*/
if (current_clr_polling_and_test())
local_irq_enable();
else
arch_cpu_idle();
goto exit_idle;
}
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
/*
* Tell the time framework to switch to a broadcast timer
* because our local timer will be shutdown. If a local timer
* is used from another cpu as a broadcast timer, this call may
* fail if it is not available
*/
if (broadcast &&
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
goto use_default;
trace_cpu_idle_rcuidle(next_state, dev->cpu);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
if (broadcast)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
/*
* Check if the cpuidle framework is ready, otherwise fallback
* to the default arch specific idle method
*/
next_state = cpuidle_select(drv, dev);
if (next_state < 0) {
default_idle_call();
goto exit_idle;
}
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
/* Take note of the planned idle state. */
idle_set_state(this_rq(), &drv->states[next_state]);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
/* The cpu is no longer idle or about to enter idle. */
idle_set_state(this_rq(), NULL);
if (entered_state == -EBUSY) {
default_idle_call();
goto exit_idle;
}
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
if (cpuidle_not_available(drv, dev)) {
default_idle_call();
goto exit_idle;
}
/*
* Suspend-to-idle ("freeze") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in iterrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
if (idle_should_freeze()) {
entered_state = cpuidle_enter_freeze(drv, dev);
if (entered_state > 0) {
local_irq_enable();
goto exit_idle;
}
next_state = cpuidle_find_deepest_state(drv, dev);
call_cpuidle(drv, dev, next_state);
} else {
/*
* Ask the cpuidle framework to choose a convenient idle state.
*/
next_state = cpuidle_select(drv, dev);
entered_state = call_cpuidle(drv, dev, next_state);
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
}
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
unsigned int broadcast;
bool reflect;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
if (cpuidle_not_available(drv, dev))
goto use_default;
/*
* Suspend-to-idle ("freeze") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in iterrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
if (idle_should_freeze()) {
entered_state = cpuidle_enter_freeze(drv, dev);
if (entered_state >= 0) {
local_irq_enable();
goto exit_idle;
}
reflect = false;
next_state = cpuidle_find_deepest_state(drv, dev);
} else {
reflect = true;
/*
* Ask the cpuidle framework to choose a convenient idle state.
*/
next_state = cpuidle_select(drv, dev);
}
/* Fall back to the default arch idle method on errors. */
if (next_state < 0)
goto use_default;
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP;
/*
* Tell the time framework to switch to a broadcast timer
* because our local timer will be shutdown. If a local timer
* is used from another cpu as a broadcast timer, this call may
* fail if it is not available
*/
if (broadcast && tick_broadcast_enter())
goto use_default;
/* Take note of the planned idle state. */
idle_set_state(this_rq(), &drv->states[next_state]);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
/* The cpu is no longer idle or about to enter idle. */
idle_set_state(this_rq(), NULL);
if (broadcast)
tick_broadcast_exit();
/*
* Give the governor an opportunity to reflect on the outcome
*/
if (reflect)
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
return;
use_default:
/*
* We can't use the cpuidle framework, let's use the default
* idle routine.
*/
if (current_clr_polling_and_test())
local_irq_enable();
else
arch_cpu_idle();
goto exit_idle;
}