/*
* Check to see if the scheduling-clock interrupt came from an extended
* quiescent state, and, if so, tell RCU about it.
*/
void rcu_check_callbacks(int cpu, int user)
{
if (!rcu_needs_cpu(0))
return; /* RCU doesn't need anything to be done. */
if (user ||
(idle_cpu(cpu) &&
!in_softirq() &&
hardirq_count() <= (1 << HARDIRQ_SHIFT)))
rcu_qsctr_inc(cpu);
else if (!in_softirq())
rcu_bh_qsctr_inc(cpu);
}
/*
* Stop the HZ tick on the current CPU.
* Only cpu_idle may call this function.
*/
static void stop_hz_timer(void)
{
unsigned long flags;
unsigned long seq, next;
__u64 timer, todval;
int cpu = smp_processor_id();
if (sysctl_hz_timer != 0)
return;
cpu_set(cpu, nohz_cpu_mask);
/*
* Leave the clock comparator set up for the next timer
* tick if either rcu or a softirq is pending.
*/
if (rcu_needs_cpu(cpu) || local_softirq_pending()) {
cpu_clear(cpu, nohz_cpu_mask);
return;
}
/*
* This cpu is going really idle. Set up the clock comparator
* for the next event.
*/
next = next_timer_interrupt();
do {
seq = read_seqbegin_irqsave(&xtime_lock, flags);
timer = ((__u64) next) - ((__u64) jiffies) + jiffies_64;
} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
todval = -1ULL;
/* Be careful about overflows. */
if (timer < (-1ULL / CLK_TICKS_PER_JIFFY)) {
timer = jiffies_timer_cc + timer * CLK_TICKS_PER_JIFFY;
if (timer >= jiffies_timer_cc)
todval = timer;
}
set_clock_comparator(todval);
}
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
* Called either from the idle loop or from irq_exit() when an idle period was
* just interrupted by an interrupt which did not cause a reschedule.
*/
void tick_nohz_stop_sched_tick(int inidle)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
/*
* Call to tick_nohz_start_idle stops the last_update_time from being
* updated. Thus, it must not be called in the event we are called from
* irq_exit() with the prior state different than idle.
*/
if (!inidle && !ts->inidle)
goto end;
/*
* Set ts->inidle unconditionally. Even if the system did not
* switch to NOHZ mode the cpu frequency governers rely on the
* update of the idle time accounting in tick_nohz_start_idle().
*/
ts->inidle = 1;
now = tick_nohz_start_idle(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;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
if (need_resched())
goto end;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
local_softirq_pending());
ratelimit++;
}
goto end;
}
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;
/*
* On SMP we really should only care for the CPU which
* has the do_timer duty assigned. All other CPUs can
* sleep as long as they want.
*/
if (cpu == tick_do_timer_cpu ||
tick_do_timer_cpu == TICK_DO_TIMER_NONE)
time_delta = timekeeping_max_deferment();
else
time_delta = KTIME_MAX;
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu) || 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;
}
/*
* 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) {
/*
* 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);
expires = ktime_add_ns(last_update, time_delta);
} else {
expires.tv64 = KTIME_MAX;
}
/*
* 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.
*/
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
if (delta_jiffies > 1)
cpumask_set_cpu(cpu, nohz_cpu_mask);
/* 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) {
if (select_nohz_load_balancer(1)) {
/*
* sched tick not stopped!
*/
cpumask_clear_cpu(cpu, nohz_cpu_mask);
goto out;
}
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
}
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());
cpumask_clear_cpu(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
end:
local_irq_restore(flags);
}
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 (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
}
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++;
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 {
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;
}
}
if (!ts->tick_stopped && delta_jiffies == 1)
goto out;
if ((long)delta_jiffies >= 1) {
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;
}
if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
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;
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
if (!ts->tick_stopped) {
select_nohz_load_balancer(1);
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
ts->idle_sleeps++;
ts->idle_expires = expires;
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);
if (hrtimer_active(&ts->sched_timer))
goto out;
} else if (!tick_program_event(expires, 0))
goto out;
tick_do_update_jiffies64(ktime_get());
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
}
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
* Called either from the idle loop or from irq_exit() when an idle period was
* just interrupted by an interrupt which did not cause a reschedule.
*/
void tick_nohz_stop_sched_tick(void)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
ktime_t last_update, expires, now, delta;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
if (need_resched())
goto end;
cpu = smp_processor_id();
if (unlikely(local_softirq_pending()))
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
local_softirq_pending());
now = ktime_get();
/*
* When called from irq_exit we need to account the idle sleep time
* correctly.
*/
if (ts->tick_stopped) {
delta = ktime_sub(now, ts->idle_entrytime);
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
}
ts->idle_entrytime = now;
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;
} while (read_seqretry(&xtime_lock, seq));
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
if (rcu_needs_cpu(cpu))
delta_jiffies = 1;
/*
* 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 (delta_jiffies > 1)
cpu_set(cpu, nohz_cpu_mask);
/*
* 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) {
ts->idle_tick = ts->sched_timer.expires;
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
/*
* 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.
*/
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = -1;
/*
* calculate the expiry time for the next timer wheel
* timer
*/
expires = ktime_add_ns(last_update, tick_period.tv64 *
delta_jiffies);
ts->idle_expires = expires;
ts->idle_sleeps++;
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS);
/* 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());
cpu_clear(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
end:
local_irq_restore(flags);
}
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, 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;
}
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) || 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;
}
/*
* 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;
}