/*
* We rearm the timer until we get disabled by the idle code.
* Called with interrupts disabled and timer->base->cpu_base->lock held.
*/
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
{
struct tick_sched *ts =
container_of(timer, struct tick_sched, sched_timer);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
int cpu = smp_processor_id();
#ifdef CONFIG_NO_HZ
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the cpu in charge went
* into a long sleep. If two cpus happen to assign themself to
* this duty, then the jiffies update is still serialized by
* xtime_lock.
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
tick_do_timer_cpu = cpu;
#endif
/* Check, if the jiffies need an update */
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
/*
* Do not call, when we are not in irq context and have
* no valid regs pointer
*/
if (regs) {
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
* time. This happens on complete idle SMP systems while
* waiting on the login prompt. We also increment the "start of
* idle" jiffy stamp so the idle accounting adjustment we do
* when we go busy again does not account too much ticks.
*/
if (ts->tick_stopped) {
touch_softlockup_watchdog();
ts->idle_jiffies++;
}
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
if ((rq_info.init == 1) && (cpu == 0)) {
/*
* update run queue statistics
*/
update_rq_stats();
/*
* wakeup user if needed
*/
wakeup_user();
}
}
hrtimer_forward(timer, now, tick_period);
return HRTIMER_RESTART;
}
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
unsigned long rcu_delta_jiffies;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
now = tick_nohz_start_idle(cpu, ts);
/*
* If this cpu is offline and it is the one which updates
* jiffies, then give up the assignment and let it be taken by
* the cpu which runs the tick timer next. If we don't drop
* this here the jiffies might be stale and do_timer() never
* invoked.
*/
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
return;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
return;
if (need_resched())
return;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
(unsigned int) local_softirq_pending());
ratelimit++;
}
return;
}
ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
} else {
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
if (rcu_delta_jiffies < delta_jiffies) {
next_jiffies = last_jiffies + rcu_delta_jiffies;
delta_jiffies = rcu_delta_jiffies;
}
}
/*
* Do not stop the tick, if we are only one off
* or if the cpu is required for rcu
*/
if (!ts->tick_stopped && delta_jiffies == 1)
goto out;
/* Schedule the tick, if we are at least one jiffie off */
if ((long)delta_jiffies >= 1) {
/*
* If this cpu is the one which updates jiffies, then
* give up the assignment and let it be taken by the
* cpu which runs the tick timer next, which might be
* this cpu as well. If we don't drop this here the
* jiffies might be stale and do_timer() never
* invoked. Keep track of the fact that it was the one
* which had the do_timer() duty last. If this cpu is
* the one which had the do_timer() duty last, we
* limit the sleep time to the timekeeping
* max_deferement value which we retrieved
* above. Otherwise we can sleep as long as we want.
*/
if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
ts->do_timer_last = 1;
} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
time_delta = KTIME_MAX;
ts->do_timer_last = 0;
} else if (!ts->do_timer_last) {
time_delta = KTIME_MAX;
}
/*
* calculate the expiry time for the next timer wheel
* timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
* that there is no timer pending or at least extremely
* far into the future (12 days for HZ=1000). In this
* case we set the expiry to the end of time.
*/
if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
/*
* Calculate the time delta for the next timer event.
* If the time delta exceeds the maximum time delta
* permitted by the current clocksource then adjust
* the time delta accordingly to ensure the
* clocksource does not wrap.
*/
time_delta = min_t(u64, time_delta,
tick_period.tv64 * delta_jiffies);
}
if (time_delta < KTIME_MAX)
expires = ktime_add_ns(last_update, time_delta);
else
expires.tv64 = KTIME_MAX;
/* Skip reprogram of event if its not changed */
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
/*
* nohz_stop_sched_tick can be called several times before
* the nohz_restart_sched_tick is called. This happens when
* interrupts arrive which do not cause a reschedule. In the
* first call we save the current tick time, so we can restart
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
select_nohz_load_balancer(1);
calc_load_enter_idle();
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
ts->idle_sleeps++;
/* Mark expires */
ts->idle_expires = expires;
/*
* If the expiration time == KTIME_MAX, then
* in this case we simply stop the tick timer.
*/
if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
goto out;
} else if (!tick_program_event(expires, 0))
goto out;
/*
* We are past the event already. So we crossed a
* jiffie boundary. Update jiffies and raise the
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
}
void tick_nohz_restart_sched_tick(void)
#endif
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
unsigned long ticks;
#endif
ktime_t now;
local_irq_disable();
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
if (ts->idle_active)
tick_nohz_stop_idle(cpu, now);
if (!ts->inidle || !ts->tick_stopped) {
ts->inidle = 0;
#ifdef CONFIG_DATAPLANE
if (!user_idle)
#endif
local_irq_enable();
return;
}
ts->inidle = 0;
rcu_exit_nohz();
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
cpumask_clear_cpu(cpu, nohz_cpu_mask);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
* accounting. Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
if (ticks && ticks < LONG_MAX)
#ifdef CONFIG_DATAPLANE
{
if (user_idle) {
cputime_t cpu_time = jiffies_to_cputime(ticks);
account_user_time(current, cpu_time,
cputime_to_scaled(cpu_time));
} else {
account_idle_ticks(ticks);
}
}
#else
account_idle_ticks(ticks);
#endif
#endif
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
*/
ts->tick_stopped = 0;
ts->idle_exittime = now;
tick_nohz_restart(ts, now);
#ifdef CONFIG_DATAPLANE
if (!user_idle)
#endif
local_irq_enable();
}
