X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftime%2Ftick-sched.c;h=d3f1ef4d5cbe7a15fdc1d0b5cd2ee195ea4890fc;hb=2d29c6a075787f2c1bc49b86a084d2b878f72fc4;hp=d36ee2fd1a3b97f4bf418ea1162e050d5660a57e;hpb=4c9dc6412247abf4972080c51cd16a58c4009c19;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d36ee2f..d3f1ef4 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -9,7 +9,7 @@ * * Started by: Thomas Gleixner and Ingo Molnar * - * For licencing details see kernel-base/COPYING + * Distribute under GPLv2. */ #include #include @@ -20,6 +20,7 @@ #include #include #include +#include #include @@ -48,6 +49,13 @@ static void tick_do_update_jiffies64(ktime_t now) unsigned long ticks = 0; ktime_t delta; + /* + * Do a quick check without holding xtime_lock: + */ + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 < tick_period.tv64) + return; + /* Reevalute with xtime_lock held */ write_seqlock(&xtime_lock); @@ -68,6 +76,9 @@ static void tick_do_update_jiffies64(ktime_t now) incr * ticks); } do_timer(++ticks); + + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); } write_sequnlock(&xtime_lock); } @@ -123,7 +134,7 @@ __setup("nohz=", setup_tick_nohz); * 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(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); @@ -133,16 +144,65 @@ void tick_nohz_update_jiffies(void) if (!ts->tick_stopped) return; - touch_softlockup_watchdog(); - - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); now = ktime_get(); + ts->idle_waketime = now; local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); + + touch_softlockup_watchdog(); +} + +static void tick_nohz_stop_idle(int cpu) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + + 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); + } } +static ktime_t tick_nohz_start_idle(struct tick_sched *ts) +{ + ktime_t now, delta; + + 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); + } + ts->idle_entrytime = now; + ts->idle_active = 1; + sched_clock_idle_sleep_event(); + return now; +} + +u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + + 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()); + + return ktime_to_us(ts->idle_sleeptime); +} +EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); + /** * tick_nohz_stop_sched_tick - stop the idle tick from the idle task * @@ -150,12 +210,11 @@ void tick_nohz_update_jiffies(void) * 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) +void tick_nohz_stop_sched_tick(int inidle) { unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags; - unsigned long rt_jiffies; struct tick_sched *ts; - ktime_t last_update, expires, now, delta; + ktime_t last_update, expires, now; struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; int cpu; @@ -163,6 +222,7 @@ void tick_nohz_stop_sched_tick(void) cpu = smp_processor_id(); ts = &per_cpu(tick_cpu_sched, cpu); + now = tick_nohz_start_idle(ts); /* * If this cpu is offline and it is the one which updates @@ -173,17 +233,21 @@ void tick_nohz_stop_sched_tick(void) */ if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = -1; + tick_do_timer_cpu = TICK_DO_TIMER_NONE; } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) goto end; + if (!inidle && !ts->inidle) + goto end; + + ts->inidle = 1; + if (need_resched()) goto end; - cpu = smp_processor_id(); - if (unlikely(local_softirq_pending())) { + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { static int ratelimit; if (ratelimit < 10) { @@ -191,21 +255,10 @@ void tick_nohz_stop_sched_tick(void) local_softirq_pending()); ratelimit++; } + goto end; } - 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); @@ -217,11 +270,7 @@ void tick_nohz_stop_sched_tick(void) next_jiffies = get_next_timer_interrupt(last_jiffies); delta_jiffies = next_jiffies - last_jiffies; - rt_jiffies = rt_needs_cpu(cpu); - if (rt_jiffies && rt_jiffies < delta_jiffies) - delta_jiffies = rt_jiffies; - - if (rcu_needs_cpu(cpu)) + if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu)) delta_jiffies = 1; /* * Do not stop the tick, if we are only one off @@ -233,8 +282,31 @@ void tick_nohz_stop_sched_tick(void) /* 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 + */ + expires = ktime_add_ns(last_update, tick_period.tv64 * + delta_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 = TICK_DO_TIMER_NONE; + if (delta_jiffies > 1) - cpu_set(cpu, nohz_cpu_mask); + 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 @@ -247,26 +319,16 @@ void tick_nohz_stop_sched_tick(void) /* * sched tick not stopped! */ - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); goto out; } - ts->idle_tick = ts->sched_timer.expires; + ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; + 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 = -1; - ts->idle_sleeps++; /* @@ -282,12 +344,7 @@ void tick_nohz_stop_sched_tick(void) goto out; } - /* - * calculate the expiry time for the next timer wheel - * timer - */ - expires = ktime_add_ns(last_update, tick_period.tv64 * - delta_jiffies); + /* Mark expiries */ ts->idle_expires = expires; if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { @@ -304,7 +361,7 @@ void tick_nohz_stop_sched_tick(void) * softirq. */ tick_do_update_jiffies64(ktime_get()); - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); } raise_softirq_irqoff(TIMER_SOFTIRQ); out: @@ -327,6 +384,32 @@ ktime_t tick_nohz_get_sleep_length(void) 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); + /* 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(); + } +} + /** * tick_nohz_restart_sched_tick - restart the idle tick from the idle task * @@ -336,24 +419,31 @@ void tick_nohz_restart_sched_tick(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); +#ifndef CONFIG_VIRT_CPU_ACCOUNTING unsigned long ticks; - ktime_t now, delta; +#endif + ktime_t now; - if (!ts->tick_stopped) + local_irq_disable(); + tick_nohz_stop_idle(cpu); + + if (!ts->inidle || !ts->tick_stopped) { + ts->inidle = 0; + local_irq_enable(); return; + } - /* Update jiffies first */ - now = ktime_get(); + ts->inidle = 0; - local_irq_disable(); + rcu_exit_nohz(); + + /* Update jiffies first */ select_nohz_load_balancer(0); + now = ktime_get(); tick_do_update_jiffies64(now); - cpu_clear(cpu, nohz_cpu_mask); - - /* Account the idle time */ - delta = ktime_sub(now, ts->idle_entrytime); - ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); + 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 @@ -363,46 +453,26 @@ void tick_nohz_restart_sched_tick(void) /* * 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(); /* * Cancel the scheduled timer and restore the tick */ ts->tick_stopped = 0; - hrtimer_cancel(&ts->sched_timer); - ts->sched_timer.expires = ts->idle_tick; + ts->idle_exittime = now; - 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(&ts->sched_timer, - ts->sched_timer.expires, - HRTIMER_MODE_ABS); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - break; - } else { - if (!tick_program_event(ts->sched_timer.expires, 0)) - break; - } - /* Update jiffies and reread time */ - tick_do_update_jiffies64(now); - now = ktime_get(); - } local_irq_enable(); } static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { hrtimer_forward(&ts->sched_timer, now, tick_period); - return tick_program_event(ts->sched_timer.expires, 0); + return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); } /* @@ -424,7 +494,7 @@ static void tick_nohz_handler(struct clock_event_device *dev) * this duty, then the jiffies update is still serialized by * xtime_lock. */ - if (unlikely(tick_do_timer_cpu == -1)) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) tick_do_timer_cpu = cpu; /* Check, if the jiffies need an update */ @@ -447,10 +517,6 @@ static void tick_nohz_handler(struct clock_event_device *dev) 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); @@ -485,7 +551,7 @@ static void tick_nohz_switch_to_nohz(void) next = tick_init_jiffy_update(); for (;;) { - ts->sched_timer.expires = next; + hrtimer_set_expires(&ts->sched_timer, next); if (!tick_program_event(next, 0)) break; next = ktime_add(next, tick_period); @@ -496,6 +562,41 @@ static void tick_nohz_switch_to_nohz(void) smp_processor_id()); } +/* + * 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) +{ +#if 0 + /* Switch back to 2.6.27 behaviour */ + + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t delta, now; + + if (!ts->tick_stopped) + return; + + /* + * Do not touch the tick device, when the next expiry is either + * already reached or less/equal than the tick period. + */ + now = ktime_get(); + delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); + if (delta.tv64 <= tick_period.tv64) + return; + + tick_nohz_restart(ts, now); +#endif +} + #else static inline void tick_nohz_switch_to_nohz(void) { } @@ -503,6 +604,19 @@ static inline void tick_nohz_switch_to_nohz(void) { } #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); +#ifdef CONFIG_NO_HZ + tick_nohz_stop_idle(cpu); + tick_nohz_update_jiffies(); + tick_nohz_kick_tick(cpu); +#endif +} + +/* * High resolution timer specific code */ #ifdef CONFIG_HIGH_RES_TIMERS @@ -526,7 +640,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) * this duty, then the jiffies update is still serialized by * xtime_lock. */ - if (unlikely(tick_do_timer_cpu == -1)) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) tick_do_timer_cpu = cpu; #endif @@ -555,10 +669,6 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) 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; @@ -578,19 +688,17 @@ void tick_setup_sched_timer(void) */ 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_NO_SOFTIRQ; /* Get the next period (per cpu) */ - ts->sched_timer.expires = tick_init_jiffy_update(); + 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(); - ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset); + hrtimer_add_expires_ns(&ts->sched_timer, offset); for (;;) { hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start(&ts->sched_timer, ts->sched_timer.expires, - HRTIMER_MODE_ABS); + 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; @@ -602,17 +710,21 @@ void tick_setup_sched_timer(void) ts->nohz_mode = NOHZ_MODE_HIGHRES; #endif } +#endif /* HIGH_RES_TIMERS */ +#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); +# ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); - ts->tick_stopped = 0; +# endif + ts->nohz_mode = NOHZ_MODE_INACTIVE; } -#endif /* HIGH_RES_TIMERS */ +#endif /** * Async notification about clocksource changes @@ -653,7 +765,7 @@ int tick_check_oneshot_change(int allow_nohz) if (ts->nohz_mode != NOHZ_MODE_INACTIVE) return 0; - if (!timekeeping_is_continuous() || !tick_is_oneshot_available()) + if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz)