NOHZ

kernel/time/tick-sched.c — idle accounting, stop 조건·전환, 복귀
kernel/sched/fair.c — tick 정지 후 NOHZ idle balance 표시

void tick_nohz_idle_enter(void)
{
	struct tick_sched *ts;

	lockdep_assert_irqs_enabled();

	local_irq_disable();

	ts = this_cpu_ptr(&tick_cpu_sched);

	WARN_ON_ONCE(ts->timer_expires_base);

	ts->inidle = 1;
	tick_nohz_start_idle(ts);

	local_irq_enable();
}

void tick_nohz_idle_stop_tick(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	int cpu = smp_processor_id();
	ktime_t expires;

	/*
	 * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the
	 * tick timer expiration time is known already.
	 */
	if (ts->timer_expires_base)
		expires = ts->timer_expires;
	else if (can_stop_idle_tick(cpu, ts))
		expires = tick_nohz_next_event(ts, cpu);
	else
		return;

	ts->idle_calls++;

	if (expires > 0LL) {
		int was_stopped = ts->tick_stopped;

		tick_nohz_stop_tick(ts, cpu);

		ts->idle_sleeps++;
		ts->idle_expires = expires;

		if (!was_stopped && ts->tick_stopped) {
			ts->idle_jiffies = ts->last_jiffies;
			nohz_balance_enter_idle(cpu);
		}
	} else {
		tick_nohz_retain_tick(ts);
	}
}

void nohz_balance_enter_idle(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	SCHED_WARN_ON(cpu != smp_processor_id());

	/* If this CPU is going down, then nothing needs to be done: */
	if (!cpu_active(cpu))
		return;

	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
	if (!housekeeping_cpu(cpu, HK_TYPE_SCHED))
		return;

	/*
	 * Can be set safely without rq->lock held
	 * If a clear happens, it will have evaluated last additions because
	 * rq->lock is held during the check and the clear
	 */
	rq->has_blocked_load = 1;

	/*
	 * The tick is still stopped but load could have been added in the
	 * meantime. We set the nohz.has_blocked flag to trig a check of the
	 * *_avg. The CPU is already part of nohz.idle_cpus_mask so the clear
	 * of nohz.has_blocked can only happen after checking the new load
	 */
	if (rq->nohz_tick_stopped)
		goto out;

	/* If we're a completely isolated CPU, we don't play: */
	if (on_null_domain(rq))
		return;

	rq->nohz_tick_stopped = 1;

	cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
	atomic_inc(&nohz.nr_cpus);

	/*
	 * Ensures that if nohz_idle_balance() fails to observe our
	 * @idle_cpus_mask store, it must observe the @has_blocked
	 * and @needs_update stores.
	 */
	smp_mb__after_atomic();

	set_cpu_sd_state_idle(cpu);

	WRITE_ONCE(nohz.needs_update, 1);
out:
	/*
	 * Each time a cpu enter idle, we assume that it has blocked load and
	 * enable the periodic update of the load of idle cpus
	 */
	WRITE_ONCE(nohz.has_blocked, 1);
}