diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/sched/idle.c | 150 |
1 files changed, 134 insertions, 16 deletions
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index b7976a127178..8f4390a079c7 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -63,6 +63,136 @@ void __weak arch_cpu_idle(void) local_irq_enable(); } +/** + * cpuidle_idle_call - the main idle function + * + * NOTE: no locks or semaphores should be used here + * return non-zero on failure + */ +static int 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, ret; + bool broadcast; + + /* + * Check if the idle task must be rescheduled. If it is the + * case, exit the function after re-enabling the local irq and + * set again the polling flag + */ + if (current_clr_polling_and_test()) { + local_irq_enable(); + __current_set_polling(); + return 0; + } + + /* + * 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 + */ + ret = cpuidle_enabled(drv, dev); + + if (!ret) { + /* + * Ask the governor to choose an idle state it thinks + * it is convenient to go to. There is *always* a + * convenient idle state + */ + next_state = cpuidle_select(drv, dev); + + /* + * 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(); + } else { + broadcast = !!(drv->states[next_state].flags & + CPUIDLE_FLAG_TIMER_STOP); + + if (broadcast) + /* + * 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 + */ + ret = clockevents_notify( + CLOCK_EVT_NOTIFY_BROADCAST_ENTER, + &dev->cpu); + + if (!ret) { + 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); + } + } + } + + /* + * We can't use the cpuidle framework, let's use the default + * idle routine + */ + if (ret) + arch_cpu_idle(); + + __current_set_polling(); + + /* + * It is up to the idle functions to enable back the local + * interrupt + */ + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); + + rcu_idle_exit(); + start_critical_timings(); + + return 0; +} + /* * Generic idle loop implementation */ @@ -90,23 +220,11 @@ static void cpu_idle_loop(void) * know that the IPI is going to arrive right * away */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) { + if (cpu_idle_force_poll || tick_check_broadcast_expired()) cpu_idle_poll(); - } else { - if (!current_clr_polling_and_test()) { - stop_critical_timings(); - rcu_idle_enter(); - if (cpuidle_idle_call()) - arch_cpu_idle(); - if (WARN_ON_ONCE(irqs_disabled())) - local_irq_enable(); - rcu_idle_exit(); - start_critical_timings(); - } else { - local_irq_enable(); - } - __current_set_polling(); - } + else + cpuidle_idle_call(); + arch_cpu_idle_exit(); } |