static void irqtime_account_idle_ticks(int ticks)
{
int i;
struct rq *rq = this_rq();
for (i = 0; i < ticks; i++)
irqtime_account_process_tick(current, 0, rq);
}
/*
* When a guest is interrupted for a longer amount of time, missed clock
* ticks are not redelivered later. Due to that, this function may on
* occasion account more time than the calling functions think elapsed.
*/
static __always_inline u64 steal_account_process_time(u64 maxtime)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
u64 steal;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
steal = min(steal, maxtime);
account_steal_time(steal);
this_rq()->prev_steal_time += steal;
return steal;
}
#endif
return 0;
}
static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
u64 steal, st = 0;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
st = steal_ticks(steal);
this_rq()->prev_steal_time += st * TICK_NSEC;
account_steal_time(st);
return st;
}
#endif
return false;
}
/*
* Account for idle time.
* @cputime: the cpu time spent in idle wait
*/
void account_idle_time(cputime_t cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
struct rq *rq = this_rq();
if (atomic_read(&rq->nr_iowait) > 0)
cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
else
cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
static struct rq *this_rq_lock(void)
{
struct rq *rq;
local_irq_disable();
rq = this_rq();
raw_spin_lock(&rq->lock);
return rq;
}
static inline runqueue_t *this_rq_lock(void)
{
runqueue_t *rq;
local_irq_disable();
rq = this_rq();
spin_lock(&rq->lock);
return rq;
}
/*
* When a guest is interrupted for a longer amount of time, missed clock
* ticks are not redelivered later. Due to that, this function may on
* occasion account more time than the calling functions think elapsed.
*/
static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
cputime_t steal_cputime;
u64 steal;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
steal_cputime = min(nsecs_to_cputime(steal), maxtime);
account_steal_time(steal_cputime);
this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime);
return steal_cputime;
}
#endif
return 0;
}
/*
* Called to set the hrtick timer state.
*
* called with rq->lock held and irqs disabled
*/
void hrtick_start(struct rq *rq, int delay)
{
struct hrtimer *timer = &rq->hrtick_timer;
int time = ktime_add_ns(timer->base->get_time(), delay);
hrtimer_set_expires(timer, time);
if (rq == this_rq()) {
hrtimer_restart(timer);
} else if (!rq->hrtick_csd_pending) {
smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
rq->hrtick_csd_pending = 1;
}
}
static inline void
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
mm = next->mm;
oldmm = prev->active_mm;
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
* one hypercall.
*/
arch_start_context_switch(prev);
if (!mm) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
if (!prev->mm) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
/*
* Since the runqueue lock will be released by the next
* task (which is an invalid locking op but in the case
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
#endif
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
barrier();
/*
* this_rq must be evaluated again because prev may have moved
* CPUs since it called schedule(), thus the 'rq' on its stack
* frame will be invalid.
*/
finish_task_switch(this_rq(), prev);
}
void calc_load_enter_idle(void)
{
struct rq *this_rq = this_rq();
long delta;
/*
* We're going into NOHZ mode, if there's any pending delta, fold it
* into the pending idle delta.
*/
delta = calc_load_fold_active(this_rq);
if (delta) {
int idx = calc_load_write_idx();
atomic_long_add(delta, &calc_load_idle[idx]);
}
}
void calc_load_nohz_start(void)
{
struct rq *this_rq = this_rq();
long delta;
/*
* We're going into NO_HZ mode, if there's any pending delta, fold it
* into the pending NO_HZ delta.
*/
delta = calc_load_fold_active(this_rq, 0);
if (delta) {
int idx = calc_load_write_idx();
atomic_long_add(delta, &calc_load_nohz[idx]);
}
}
void calc_load_exit_idle(void)
{
struct rq *this_rq = this_rq();
/*
* If we're still before the sample window, we're done.
*/
if (time_before(jiffies, this_rq->calc_load_update))
return;
/*
* We woke inside or after the sample window, this means we're already
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
/*
* Account a single tick of cpu time.
* @p: the process that the cpu time gets accounted to
* @user_tick: indicates if the tick is a user or a system tick
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
if (sched_clock_irqtime) {
irqtime_account_process_tick(p, user_tick, rq);
return;
}
if (steal_account_process_tick())
return;
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
one_jiffy_scaled);
else
account_idle_time(cputime_one_jiffy);
}
/**
* 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 = __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 specific 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;
/* 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)
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();
}
unsigned long this_cpu_load(void)
{
struct rq *this = this_rq();
return this->cpu_load[0];
}
/**
* 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;
}
/**
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
*/
void sched_idle_set_state(struct cpuidle_state *idle_state)
{
idle_set_state(this_rq(), idle_state);
}