#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include <linux/module.h>
#include <asm/irq_regs.h>
* value. We do this unconditionally on any cpu, as we don't know whether the
* cpu, which has the update task assigned is in a long sleep.
*/
-void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(ktime_t now)
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- ktime_t now;
-
- if (!ts->tick_stopped)
- return;
- cpu_clear(cpu, nohz_cpu_mask);
- now = ktime_get();
ts->idle_waketime = now;
local_irq_save(flags);
touch_softlockup_watchdog();
}
-void tick_nohz_stop_idle(int cpu)
+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t delta;
if (ts->idle_active) {
- ktime_t now, delta;
- now = ktime_get();
delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- ts->idle_active = 0;
-
- sched_clock_idle_wakeup_event(0);
+ if (nr_iowait_cpu(cpu) > 0)
+ ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+ else
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ ts->idle_entrytime = now;
}
+
+ if (last_update_time)
+ *last_update_time = ktime_to_us(now);
+
}
-static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
+static void tick_nohz_stop_idle(int cpu, ktime_t now)
{
- ktime_t now, delta;
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ update_ts_time_stats(cpu, ts, now, NULL);
+ ts->idle_active = 0;
+
+ sched_clock_idle_wakeup_event(0);
+}
+
+static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+{
+ ktime_t now;
now = ktime_get();
- if (ts->idle_active) {
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- }
+
+ update_ts_time_stats(cpu, ts, now, NULL);
+
ts->idle_entrytime = now;
ts->idle_active = 1;
sched_clock_idle_sleep_event();
return now;
}
+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, idle;
if (!tick_nohz_enabled)
return -1;
- if (ts->idle_active)
- *last_update_time = ktime_to_us(ts->idle_lastupdate);
- else
- *last_update_time = ktime_to_us(ktime_get());
+ now = ktime_get();
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ idle = ts->idle_sleeptime;
+ } else {
+ if (ts->idle_active && !nr_iowait_cpu(cpu)) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+ idle = ktime_add(ts->idle_sleeptime, delta);
+ } else {
+ idle = ts->idle_sleeptime;
+ }
+ }
+
+ return ktime_to_us(idle);
- return ktime_to_us(ts->idle_sleeptime);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
/**
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, iowait;
+
+ if (!tick_nohz_enabled)
+ return -1;
+
+ now = ktime_get();
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ iowait = ts->iowait_sleeptime;
+ } else {
+ if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+ iowait = ktime_add(ts->iowait_sleeptime, delta);
+ } else {
+ iowait = ts->iowait_sleeptime;
+ }
+ }
+
+ return ktime_to_us(iowait);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
+/**
* 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
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);
- now = tick_nohz_start_idle(ts);
+
+ /*
+ * 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(cpu, ts);
/*
* If this cpu is offline and it is the one which updates
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
- if (!inidle && !ts->inidle)
- goto end;
-
- ts->inidle = 1;
-
if (need_resched())
goto end;
- if (unlikely(local_softirq_pending())) {
+ 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());
+ (unsigned int) local_softirq_pending());
ratelimit++;
}
goto end;
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
+ time_delta = timekeeping_max_deferment();
} 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) || printk_needs_cpu(cpu))
+ 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
/* 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);
+ /*
+ * 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
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
- if (select_nohz_load_balancer(1)) {
- /*
- * sched tick not stopped!
- */
- cpu_clear(cpu, nohz_cpu_mask);
- goto out;
- }
+ select_nohz_load_balancer(1);
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
rcu_enter_nohz();
}
- /*
- * 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;
-
ts->idle_sleeps++;
+ /* Mark expires */
+ ts->idle_expires = expires;
+
/*
- * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
- * there is no timer pending or at least extremly far
- * into the future (12 days for HZ=1000). In this case
- * we simply stop the tick timer:
+ * If the expiration time == KTIME_MAX, then
+ * in this case we simply stop the tick timer.
*/
- if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
- ts->idle_expires.tv64 = KTIME_MAX;
+ if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
- /*
- * 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;
-
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
- HRTIMER_MODE_ABS);
+ HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
goto out;
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
- cpu_clear(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
return ts->sleep_length;
}
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+ hrtimer_cancel(&ts->sched_timer);
+ hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+
+ while (1) {
+ /* Forward the time to expire in the future */
+ hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+ hrtimer_start_expires(&ts->sched_timer,
+ HRTIMER_MODE_ABS_PINNED);
+ /* Check, if the timer was already in the past */
+ if (hrtimer_active(&ts->sched_timer))
+ break;
+ } else {
+ if (!tick_program_event(
+ hrtimer_get_expires(&ts->sched_timer), 0))
+ break;
+ }
+ /* Reread time and update jiffies */
+ now = ktime_get();
+ tick_do_update_jiffies64(now);
+ }
+}
+
/**
* tick_nohz_restart_sched_tick - restart the idle tick from the idle task
*
{
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();
- tick_nohz_stop_idle(cpu);
+ 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;
/* Update jiffies first */
select_nohz_load_balancer(0);
- now = ktime_get();
tick_do_update_jiffies64(now);
- cpu_clear(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
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
- if (ticks && ticks < LONG_MAX) {
- add_preempt_count(HARDIRQ_OFFSET);
- account_system_time(current, HARDIRQ_OFFSET,
- jiffies_to_cputime(ticks));
- sub_preempt_count(HARDIRQ_OFFSET);
- }
+ if (ticks && ticks < LONG_MAX)
+ account_idle_ticks(ticks);
+#endif
touch_softlockup_watchdog();
/*
*/
ts->tick_stopped = 0;
ts->idle_exittime = now;
- hrtimer_cancel(&ts->sched_timer);
- hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
- while (1) {
- /* Forward the time to expire in the future */
- hrtimer_forward(&ts->sched_timer, now, tick_period);
+ tick_nohz_restart(ts, now);
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
- hrtimer_start_expires(&ts->sched_timer,
- HRTIMER_MODE_ABS);
- /* Check, if the timer was already in the past */
- if (hrtimer_active(&ts->sched_timer))
- break;
- } else {
- if (!tick_program_event(
- hrtimer_get_expires(&ts->sched_timer), 0))
- break;
- }
- /* Update jiffies and reread time */
- tick_do_update_jiffies64(now);
- now = ktime_get();
- }
local_irq_enable();
}
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
- /* Do not restart, when we are in the idle loop */
- if (ts->tick_stopped)
- return;
-
while (tick_nohz_reprogram(ts, now)) {
now = ktime_get();
tick_do_update_jiffies64(now);
next = ktime_add(next, tick_period);
}
local_irq_enable();
+}
+
+/*
+ * When NOHZ is enabled and the tick is stopped, we need to kick the
+ * tick timer from irq_enter() so that the jiffies update is kept
+ * alive during long running softirqs. That's ugly as hell, but
+ * correctness is key even if we need to fix the offending softirq in
+ * the first place.
+ *
+ * Note, this is different to tick_nohz_restart. We just kick the
+ * timer and do not touch the other magic bits which need to be done
+ * when idle is left.
+ */
+static void tick_nohz_kick_tick(int cpu, ktime_t now)
+{
+#if 0
+ /* Switch back to 2.6.27 behaviour */
- printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
- smp_processor_id());
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t delta;
+
+ /*
+ * Do not touch the tick device, when the next expiry is either
+ * already reached or less/equal than the tick period.
+ */
+ delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
+ if (delta.tv64 <= tick_period.tv64)
+ return;
+
+ tick_nohz_restart(ts, now);
+#endif
+}
+
+static inline void tick_check_nohz(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now;
+
+ if (!ts->idle_active && !ts->tick_stopped)
+ return;
+ now = ktime_get();
+ if (ts->idle_active)
+ tick_nohz_stop_idle(cpu, now);
+ if (ts->tick_stopped) {
+ tick_nohz_update_jiffies(now);
+ tick_nohz_kick_tick(cpu, now);
+ }
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
+static inline void tick_check_nohz(int cpu) { }
#endif /* NO_HZ */
/*
+ * Called from irq_enter to notify about the possible interruption of idle()
+ */
+void tick_check_idle(int cpu)
+{
+ tick_check_oneshot_broadcast(cpu);
+ tick_check_nohz(cpu);
+}
+
+/*
* High resolution timer specific code
*/
#ifdef CONFIG_HIGH_RES_TIMERS
profile_tick(CPU_PROFILING);
}
- /* Do not restart, when we are in the idle loop */
- if (ts->tick_stopped)
- return HRTIMER_NORESTART;
-
hrtimer_forward(timer, now, tick_period);
return HRTIMER_RESTART;
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now = ktime_get();
- u64 offset;
/*
* Emulate tick processing via per-CPU hrtimers:
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
ts->sched_timer.function = tick_sched_timer;
- ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
- offset = ktime_to_ns(tick_period) >> 1;
- do_div(offset, num_possible_cpus());
- offset *= smp_processor_id();
- hrtimer_add_expires_ns(&ts->sched_timer, offset);
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
- hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS);
+ hrtimer_start_expires(&ts->sched_timer,
+ HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
break;