extern char __cpuidle_text_start[], __cpuidle_text_end[];
void sched_idle_set_state(struct cpuidle_state *idle_state)
{
idle_set_state(this_rq(), idle_state);
}
static int __read_mostly cpu_idle_force_poll;
void cpu_idle_poll_ctrl(bool enable)
{
if (enable) {
cpu_idle_force_poll++;
} else {
cpu_idle_force_poll--;
WARN_ON_ONCE(cpu_idle_force_poll < 0);
}
}
#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
static int __init cpu_idle_poll_setup(char *__unused)
{
cpu_idle_force_poll = 1;
return 1;
}
__setup("nohlt", cpu_idle_poll_setup);
static int __init cpu_idle_nopoll_setup(char *__unused)
{
cpu_idle_force_poll = 0;
return 1;
}
__setup("hlt", cpu_idle_nopoll_setup);
#endif
static noinline int __cpuidle cpu_idle_poll(void)
{
instrumentation_begin();
trace_cpu_idle(0, smp_processor_id());
stop_critical_timings();
ct_cpuidle_enter();
raw_local_irq_enable();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
raw_local_irq_disable();
ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
local_irq_enable();
instrumentation_end();
return 1;
}
void __weak arch_cpu_idle_prepare(void) { }
void __weak arch_cpu_idle_enter(void) { }
void __weak arch_cpu_idle_exit(void) { }
void __weak __noreturn arch_cpu_idle_dead(void) { while (1); }
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
}
void __cpuidle default_idle_call(void)
{
instrumentation_begin();
if (!current_clr_polling_and_test()) {
trace_cpu_idle(1, smp_processor_id());
stop_critical_timings();
ct_cpuidle_enter();
arch_cpu_idle();
ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
local_irq_enable();
instrumentation_end();
}
static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
struct cpuidle_device *dev)
{
if (current_clr_polling_and_test())
return -EBUSY;
return cpuidle_enter_s2idle(drv, dev);
}
static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int next_state)
{
if (current_clr_polling_and_test()) {
dev->last_residency_ns = 0;
local_irq_enable();
return -EBUSY;
}
return cpuidle_enter(drv, dev, next_state);
}
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;
if (need_resched()) {
local_irq_enable();
return;
}
if (cpuidle_not_available(drv, dev)) {
tick_nohz_idle_stop_tick();
default_idle_call();
goto exit_idle;
}
if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
u64 max_latency_ns;
if (idle_should_enter_s2idle()) {
entered_state = call_cpuidle_s2idle(drv, dev);
if (entered_state > 0)
goto exit_idle;
max_latency_ns = U64_MAX;
} else {
max_latency_ns = dev->forced_idle_latency_limit_ns;
}
tick_nohz_idle_stop_tick();
next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
call_cpuidle(drv, dev, next_state);
} else {
bool stop_tick = true;
next_state = cpuidle_select(drv, dev, &stop_tick);
if (stop_tick || tick_nohz_tick_stopped())
tick_nohz_idle_stop_tick();
else
tick_nohz_idle_retain_tick();
entered_state = call_cpuidle(drv, dev, next_state);
cpuidle_reflect(dev, entered_state);
}
exit_idle:
__current_set_polling();
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
}
static void do_idle(void)
{
int cpu = smp_processor_id();
nohz_run_idle_balance(cpu);
__current_set_polling();
tick_nohz_idle_enter();
while (!need_resched()) {
rmb();
local_irq_disable();
if (cpu_is_offline(cpu)) {
tick_nohz_idle_stop_tick();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
arch_cpu_idle_enter();
rcu_nocb_flush_deferred_wakeup();
if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
tick_nohz_idle_restart_tick();
cpu_idle_poll();
} else {
cpuidle_idle_call();
}
arch_cpu_idle_exit();
}
preempt_set_need_resched();
tick_nohz_idle_exit();
__current_clr_polling();
smp_mb__after_atomic();
flush_smp_call_function_queue();
schedule_idle();
if (unlikely(klp_patch_pending(current)))
klp_update_patch_state(current);
}
bool cpu_in_idle(unsigned long pc)
{
return pc >= (unsigned long)__cpuidle_text_start &&
pc < (unsigned long)__cpuidle_text_end;
}
struct idle_timer {
struct hrtimer timer;
int done;
};
static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
{
struct idle_timer *it = container_of(timer, struct idle_timer, timer);
WRITE_ONCE(it->done, 1);
set_tsk_need_resched(current);
return HRTIMER_NORESTART;
}
void play_idle_precise(u64 duration_ns, u64 latency_ns)
{
struct idle_timer it;
WARN_ON_ONCE(current->policy != SCHED_FIFO);
WARN_ON_ONCE(current->nr_cpus_allowed != 1);
WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
WARN_ON_ONCE(!duration_ns);
WARN_ON_ONCE(current->mm);
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
cpuidle_use_deepest_state(latency_ns);
it.done = 0;
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
it.timer.function = idle_inject_timer_fn;
hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
HRTIMER_MODE_REL_PINNED_HARD);
while (!READ_ONCE(it.done))
do_idle();
cpuidle_use_deepest_state(0);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
preempt_enable();
}
EXPORT_SYMBOL_GPL(play_idle_precise);
void cpu_startup_entry(enum cpuhp_state state)
{
current->flags |= PF_IDLE;
arch_cpu_idle_prepare();
cpuhp_online_idle(state);
while (1)
do_idle();
}
#ifdef CONFIG_SMP
static int
select_task_rq_idle(struct task_struct *p, int cpu, int flags)
{
return task_cpu(p);
}
static int
balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
return WARN_ON_ONCE(1);
}
#endif
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
{
resched_curr(rq);
}
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
}
#ifdef CONFIG_SMP
static struct task_struct *pick_task_idle(struct rq *rq)
{
return rq->idle;
}
#endif
struct task_struct *pick_next_task_idle(struct rq *rq)
{
struct task_struct *next = rq->idle;
set_next_task_idle(rq, next, true);
return next;
}
static void
dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
{
raw_spin_rq_unlock_irq(rq);
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
dump_stack();
raw_spin_rq_lock_irq(rq);
}
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
}
static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
BUG();
}
static void
prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG();
}
static void update_curr_idle(struct rq *rq)
{
}
DEFINE_SCHED_CLASS(idle) = {
.dequeue_task = dequeue_task_idle,
.check_preempt_curr = check_preempt_curr_idle,
.pick_next_task = pick_next_task_idle,
.put_prev_task = put_prev_task_idle,
.set_next_task = set_next_task_idle,
#ifdef CONFIG_SMP
.balance = balance_idle,
.pick_task = pick_task_idle,
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.task_tick = task_tick_idle,
.prio_changed = prio_changed_idle,
.switched_to = switched_to_idle,
.update_curr = update_curr_idle,
}