diff options
Diffstat (limited to 'kernel/time')
-rw-r--r-- | kernel/time/Kconfig | 5 | ||||
-rw-r--r-- | kernel/time/Makefile | 3 | ||||
-rw-r--r-- | kernel/time/alarmtimer.c | 2 | ||||
-rw-r--r-- | kernel/time/clockevents.c | 2 | ||||
-rw-r--r-- | kernel/time/clocksource-wdtest.c | 13 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 12 | ||||
-rw-r--r-- | kernel/time/hrtimer.c | 25 | ||||
-rw-r--r-- | kernel/time/tick-common.c | 40 | ||||
-rw-r--r-- | kernel/time/tick-internal.h | 16 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 405 | ||||
-rw-r--r-- | kernel/time/tick-sched.h | 44 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 9 | ||||
-rw-r--r-- | kernel/time/timer.c | 599 | ||||
-rw-r--r-- | kernel/time/timer_list.c | 10 | ||||
-rw-r--r-- | kernel/time/timer_migration.c | 1810 | ||||
-rw-r--r-- | kernel/time/timer_migration.h | 140 |
16 files changed, 2789 insertions, 346 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index bae8f11070..fc3b1a06c9 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -39,6 +39,11 @@ config GENERIC_CLOCKEVENTS_BROADCAST bool depends on GENERIC_CLOCKEVENTS +# Handle broadcast in default_idle_call() +config GENERIC_CLOCKEVENTS_BROADCAST_IDLE + bool + depends on GENERIC_CLOCKEVENTS_BROADCAST + # Automatically adjust the min. reprogramming time for # clock event device config GENERIC_CLOCKEVENTS_MIN_ADJUST diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 7e875e63ff..4af2a264a1 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -17,6 +17,9 @@ endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_LEGACY_TIMER_TICK) += tick-legacy.o +ifeq ($(CONFIG_SMP),y) + obj-$(CONFIG_NO_HZ_COMMON) += timer_migration.o +endif obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 4657cb8e8b..5abfa43906 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -134,7 +134,7 @@ static struct class_interface alarmtimer_rtc_interface = { static int alarmtimer_rtc_interface_setup(void) { - alarmtimer_rtc_interface.class = rtc_class; + alarmtimer_rtc_interface.class = &rtc_class; return class_interface_register(&alarmtimer_rtc_interface); } static void alarmtimer_rtc_interface_remove(void) diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 960143b183..a7ca458cdd 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -659,7 +659,7 @@ void tick_cleanup_dead_cpu(int cpu) #endif #ifdef CONFIG_SYSFS -static struct bus_type clockevents_subsys = { +static const struct bus_type clockevents_subsys = { .name = "clockevents", .dev_name = "clockevent", }; diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c index df922f49d1..d06185e054 100644 --- a/kernel/time/clocksource-wdtest.c +++ b/kernel/time/clocksource-wdtest.c @@ -104,8 +104,8 @@ static void wdtest_ktime_clocksource_reset(void) static int wdtest_func(void *arg) { unsigned long j1, j2; + int i, max_retries; char *s; - int i; schedule_timeout_uninterruptible(holdoff * HZ); @@ -139,18 +139,19 @@ static int wdtest_func(void *arg) WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); /* Verify tsc-like stability with various numbers of errors injected. */ - for (i = 0; i <= max_cswd_read_retries + 1; i++) { - if (i <= 1 && i < max_cswd_read_retries) + max_retries = clocksource_get_max_watchdog_retry(); + for (i = 0; i <= max_retries + 1; i++) { + if (i <= 1 && i < max_retries) s = ""; - else if (i <= max_cswd_read_retries) + else if (i <= max_retries) s = ", expect message"; else s = ", expect clock skew"; - pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s); + pr_info("--- Watchdog with %dx error injection, %d retries%s.\n", i, max_retries, s); WRITE_ONCE(wdtest_ktime_read_ndelays, i); schedule_timeout_uninterruptible(2 * HZ); WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays)); - WARN_ON_ONCE((i <= max_cswd_read_retries) != + WARN_ON_ONCE((i <= max_retries) != !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE)); wdtest_ktime_clocksource_reset(); } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 3052b1f116..e5b260aa0e 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -210,9 +210,6 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } -ulong max_cswd_read_retries = 2; -module_param(max_cswd_read_retries, ulong, 0644); -EXPORT_SYMBOL_GPL(max_cswd_read_retries); static int verify_n_cpus = 8; module_param(verify_n_cpus, int, 0644); @@ -224,11 +221,12 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { - unsigned int nretries; + unsigned int nretries, max_retries; u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; - for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { + max_retries = clocksource_get_max_watchdog_retry(); + for (nretries = 0; nretries <= max_retries; nretries++) { local_irq_disable(); *wdnow = watchdog->read(watchdog); *csnow = cs->read(cs); @@ -240,7 +238,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); if (wd_delay <= WATCHDOG_MAX_SKEW) { - if (nretries > 1 || nretries >= max_cswd_read_retries) { + if (nretries > 1 || nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } @@ -1468,7 +1466,7 @@ static struct attribute *clocksource_attrs[] = { }; ATTRIBUTE_GROUPS(clocksource); -static struct bus_type clocksource_subsys = { +static const struct bus_type clocksource_subsys = { .name = "clocksource", .dev_name = "clocksource", }; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index edb0f821dc..70625dff62 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -38,6 +38,7 @@ #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> +#include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> @@ -746,7 +747,7 @@ static void hrtimer_switch_to_hres(void) base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; - tick_setup_sched_timer(); + tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } @@ -1021,21 +1022,23 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) } /** - * hrtimer_forward - forward the timer expiry + * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. - * Returns the number of overruns. * - * Can be safely called from the callback function of @timer. If - * called from other contexts @timer must neither be enqueued nor - * running the callback and the caller needs to take care of - * serialization. + * .. note:: + * This only updates the timer expiry value and does not requeue the timer. * - * Note: This only updates the timer expiry value and does not requeue - * the timer. + * There is also a variant of the function hrtimer_forward_now(). + * + * Context: Can be safely called from the callback function of @timer. If called + * from other contexts @timer must neither be enqueued nor running the + * callback and the caller needs to take care of serialization. + * + * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { @@ -2223,10 +2226,8 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, int hrtimers_cpu_dying(unsigned int dying_cpu) { + int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; - int i, ncpu = cpumask_first(cpu_active_mask); - - tick_cancel_sched_timer(dying_cpu); old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index e9138cd7a0..d88b13076b 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -7,6 +7,7 @@ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -84,7 +85,7 @@ int tick_is_oneshot_available(void) */ static void tick_periodic(int cpu) { - if (tick_do_timer_cpu == cpu) { + if (READ_ONCE(tick_do_timer_cpu) == cpu) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); @@ -111,15 +112,13 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); -#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON) /* * The cpu might have transitioned to HIGHRES or NOHZ mode via * update_process_times() -> run_local_timers() -> * hrtimer_run_queues(). */ - if (dev->event_handler != tick_handle_periodic) + if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic) return; -#endif if (!clockevent_state_oneshot(dev)) return; @@ -217,8 +216,8 @@ static void tick_setup_device(struct tick_device *td, * If no cpu took the do_timer update, assign it to * this cpu: */ - if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - tick_do_timer_cpu = cpu; + if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) { + WRITE_ONCE(tick_do_timer_cpu, cpu); tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* @@ -234,7 +233,7 @@ static void tick_setup_device(struct tick_device *td, !tick_nohz_full_cpu(cpu)) { tick_take_do_timer_from_boot(); tick_do_timer_boot_cpu = -1; - WARN_ON(tick_do_timer_cpu != cpu); + WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu); #endif } @@ -398,16 +397,31 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); #ifdef CONFIG_HOTPLUG_CPU +void tick_assert_timekeeping_handover(void) +{ + WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id()); +} /* - * Transfer the do_timer job away from a dying cpu. - * - * Called with interrupts disabled. No locking required. If - * tick_do_timer_cpu is owned by this cpu, nothing can change it. + * Stop the tick and transfer the timekeeping job away from a dying cpu. */ -void tick_handover_do_timer(void) +int tick_cpu_dying(unsigned int dying_cpu) { - if (tick_do_timer_cpu == smp_processor_id()) + /* + * If the current CPU is the timekeeper, it's the only one that can + * safely hand over its duty. Also all online CPUs are in stop + * machine, guaranteed not to be idle, therefore there is no + * concurrency and it's safe to pick any online successor. + */ + if (tick_do_timer_cpu == dying_cpu) tick_do_timer_cpu = cpumask_first(cpu_online_mask); + + /* Make sure the CPU won't try to retake the timekeeping duty */ + tick_sched_timer_dying(dying_cpu); + + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(dying_cpu); + + return 0; } /* diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 481b7ab65e..5f2105e637 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -8,6 +8,11 @@ #include "timekeeping.h" #include "tick-sched.h" +struct timer_events { + u64 local; + u64 global; +}; + #ifdef CONFIG_GENERIC_CLOCKEVENTS # define TICK_DO_TIMER_NONE -1 @@ -137,8 +142,10 @@ static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_ #endif /* !(BROADCAST && ONESHOT) */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); extern void tick_broadcast_offline(unsigned int cpu); #else +static inline void tick_offline_cpu(unsigned int cpu) { } static inline void tick_broadcast_offline(unsigned int cpu) { } #endif @@ -152,8 +159,16 @@ static inline void tick_nohz_init(void) { } #ifdef CONFIG_NO_HZ_COMMON extern unsigned long tick_nohz_active; extern void timers_update_nohz(void); +extern u64 get_jiffies_update(unsigned long *basej); # ifdef CONFIG_SMP extern struct static_key_false timers_migration_enabled; +extern void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, + struct timer_events *tevt, + unsigned int cpu); +extern void timer_lock_remote_bases(unsigned int cpu); +extern void timer_unlock_remote_bases(unsigned int cpu); +extern bool timer_base_is_idle(void); +extern void timer_expire_remote(unsigned int cpu); # endif #else /* CONFIG_NO_HZ_COMMON */ static inline void timers_update_nohz(void) { } @@ -163,6 +178,7 @@ static inline void timers_update_nohz(void) { } DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); +u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle); void timer_clear_idle(void); #define CLOCK_SET_WALL \ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 01fb50c1b1..71a792cd89 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -8,6 +8,7 @@ * * Started by: Thomas Gleixner and Ingo Molnar */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -43,7 +44,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) return &per_cpu(tick_cpu_sched, cpu); } -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a @@ -181,13 +181,32 @@ static ktime_t tick_init_jiffy_update(void) return period; } +static inline int tick_sched_flag_test(struct tick_sched *ts, + unsigned long flag) +{ + return !!(ts->flags & flag); +} + +static inline void tick_sched_flag_set(struct tick_sched *ts, + unsigned long flag) +{ + lockdep_assert_irqs_disabled(); + ts->flags |= flag; +} + +static inline void tick_sched_flag_clear(struct tick_sched *ts, + unsigned long flag) +{ + lockdep_assert_irqs_disabled(); + ts->flags &= ~flag; +} + #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { - int cpu = smp_processor_id(); + int tick_cpu, cpu = smp_processor_id(); -#ifdef CONFIG_NO_HZ_COMMON /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went @@ -198,16 +217,18 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { + tick_cpu = READ_ONCE(tick_do_timer_cpu); + + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif - tick_do_timer_cpu = cpu; + WRITE_ONCE(tick_do_timer_cpu, cpu); + tick_cpu = cpu; } -#endif /* Check if jiffies need an update */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* @@ -225,13 +246,12 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) } } - if (ts->inidle) + if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { -#ifdef CONFIG_NO_HZ_COMMON /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long @@ -240,7 +260,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ - if (ts->tick_stopped) { + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && + tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; @@ -251,11 +272,52 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) */ ts->next_tick = 0; } -#endif + update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } -#endif + +/* + * We rearm the timer until we get disabled by the idle code. + * Called with interrupts disabled. + */ +static enum hrtimer_restart tick_nohz_handler(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(); + + tick_sched_do_timer(ts, now); + + /* + * Do not call when we are not in IRQ context and have + * no valid 'regs' pointer + */ + if (regs) + tick_sched_handle(ts, regs); + else + ts->next_tick = 0; + + /* + * In dynticks mode, tick reprogram is deferred: + * - to the idle task if in dynticks-idle + * - to IRQ exit if in full-dynticks. + */ + if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED))) + return HRTIMER_NORESTART; + + hrtimer_forward(timer, now, TICK_NSEC); + + return HRTIMER_RESTART; +} + +static void tick_sched_timer_cancel(struct tick_sched *ts) +{ + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) + hrtimer_cancel(&ts->sched_timer); + else if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) + tick_program_event(KTIME_MAX, 1); +} #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; @@ -529,7 +591,7 @@ void __tick_nohz_task_switch(void) ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->tick_stopped) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); @@ -551,7 +613,7 @@ bool tick_nohz_cpu_hotpluggable(unsigned int cpu) * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ - if (tick_nohz_full_running && tick_do_timer_cpu == cpu) + if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } @@ -601,7 +663,7 @@ void __init tick_nohz_init(void) pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } -#endif +#endif /* #ifdef CONFIG_NO_HZ_FULL */ /* * NOHZ - aka dynamic tick functionality @@ -626,18 +688,19 @@ bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - return ts->tick_stopped; + return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); - return ts->tick_stopped; + return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted + * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * @@ -663,7 +726,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; - if (WARN_ON_ONCE(!ts->idle_active)) + if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) return; delta = ktime_sub(now, ts->idle_entrytime); @@ -675,7 +738,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; - ts->idle_active = 0; + tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); @@ -685,7 +748,7 @@ static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); - ts->idle_active = 1; + tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); @@ -707,7 +770,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); - if (ts->idle_active && compute_delta) { + if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); @@ -735,7 +798,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, * 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. + * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { @@ -761,7 +824,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); * 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. + * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { @@ -780,7 +843,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { @@ -799,18 +862,41 @@ static inline bool local_timer_softirq_pending(void) return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } -static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) +/* + * Read jiffies and the time when jiffies were updated last + */ +u64 get_jiffies_update(unsigned long *basej) { - u64 basemono, next_tick, delta, expires; unsigned long basejiff; unsigned int seq; + u64 basemono; - /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); + *basej = basejiff; + return basemono; +} + +/** + * tick_nohz_next_event() - return the clock monotonic based next event + * @ts: pointer to tick_sched struct + * @cpu: CPU number + * + * Return: + * *%0 - When the next event is a maximum of TICK_NSEC in the future + * and the tick is not stopped yet + * *%next_event - Next event based on clock monotonic + */ +static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) +{ + u64 basemono, next_tick, delta, expires; + unsigned long basejiff; + int tick_cpu; + + basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; @@ -850,15 +936,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* - * Tell the timer code that the base is not idle, i.e. undo - * the effect of get_next_timer_interrupt(): - */ - timer_clear_idle(); - /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ - if (!ts->tick_stopped) { + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->timer_expires = 0; goto out; } @@ -870,8 +951,9 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); - if (cpu != tick_do_timer_cpu && - (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu != cpu && + (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ @@ -889,13 +971,40 @@ out: static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; - u64 expires = ts->timer_expires; + bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); + int tick_cpu; + u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* + * Now the tick should be stopped definitely - so the timer base needs + * to be marked idle as well to not miss a newly queued timer. + */ + expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle); + if (expires > ts->timer_expires) { + /* + * This path could only happen when the first timer was removed + * between calculating the possible sleep length and now (when + * high resolution mode is not active, timer could also be a + * hrtimer). + * + * We have to stick to the original calculated expiry value to + * not stop the tick for too long with a shallow C-state (which + * was programmed by cpuidle because of an early next expiration + * value). + */ + expires = ts->timer_expires; + } + + /* If the timer base is not idle, retain the not yet stopped tick. */ + if (!timer_idle) + return; + + /* * 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 @@ -903,15 +1012,16 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ - 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) { - ts->do_timer_last = 0; + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu == cpu) { + WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); + tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); + } else if (tick_cpu != TICK_DO_TIMER_NONE) { + tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } /* Skip reprogram of event if it's not changed */ - if (ts->tick_stopped && (expires == ts->next_tick)) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; @@ -929,12 +1039,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * call we save the current tick time, so we can restart the * scheduler tick in tick_nohz_restart_sched_tick(). */ - if (!ts->tick_stopped) { + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); - ts->tick_stopped = 1; + tick_sched_flag_set(ts, TS_FLAG_STOPPED); trace_tick_stop(1, TICK_DEP_MASK_NONE); } @@ -945,14 +1055,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_cancel(&ts->sched_timer); - else - tick_program_event(KTIME_MAX, 1); + tick_sched_timer_cancel(ts); return; } - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { @@ -967,7 +1074,7 @@ static void tick_nohz_retain_tick(struct tick_sched *ts) } #ifdef CONFIG_NO_HZ_FULL -static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) +static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); @@ -991,7 +1098,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ - ts->tick_stopped = 0; + tick_sched_flag_clear(ts, TS_FLAG_STOPPED); tick_nohz_restart(ts, now); } @@ -1002,8 +1109,8 @@ static void __tick_nohz_full_update_tick(struct tick_sched *ts, int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) - tick_nohz_stop_sched_tick(ts, cpu); - else if (ts->tick_stopped) + tick_nohz_full_stop_tick(ts, cpu); + else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_restart_sched_tick(ts, now); #endif } @@ -1013,7 +1120,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (!tick_nohz_full_cpu(smp_processor_id())) return; - if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) + if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return; __tick_nohz_full_update_tick(ts, ktime_get()); @@ -1060,25 +1167,9 @@ static bool report_idle_softirq(void) static bool can_stop_idle_tick(int cpu, struct tick_sched *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 - * gets invoked. - */ - if (unlikely(!cpu_online(cpu))) { - if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - /* - * Make sure the CPU doesn't get fooled by obsolete tick - * deadline if it comes back online later. - */ - ts->next_tick = 0; - return false; - } + WARN_ON_ONCE(cpu_is_offline(cpu)); - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ))) return false; if (need_resched()) @@ -1088,15 +1179,17 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (tick_nohz_full_enabled()) { + int tick_cpu = READ_ONCE(tick_do_timer_cpu); + /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ - if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) + if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } @@ -1128,14 +1221,14 @@ void tick_nohz_idle_stop_tick(void) ts->idle_calls++; if (expires > 0LL) { - int was_stopped = ts->tick_stopped; + int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; - if (!was_stopped && ts->tick_stopped) { + if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } @@ -1147,11 +1240,6 @@ void tick_nohz_idle_stop_tick(void) void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); - /* - * Undo the effect of get_next_timer_interrupt() called from - * tick_nohz_next_event(). - */ - timer_clear_idle(); } /** @@ -1171,7 +1259,7 @@ void tick_nohz_idle_enter(void) WARN_ON_ONCE(ts->timer_expires_base); - ts->inidle = 1; + tick_sched_flag_set(ts, TS_FLAG_INIDLE); tick_nohz_start_idle(ts); local_irq_enable(); @@ -1200,7 +1288,7 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->inidle) + if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); @@ -1208,6 +1296,8 @@ void tick_nohz_irq_exit(void) /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + * + * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { @@ -1226,6 +1316,8 @@ bool tick_nohz_idle_got_tick(void) * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled + * + * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { @@ -1241,6 +1333,8 @@ ktime_t tick_nohz_get_next_hrtimer(void) * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. + * + * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { @@ -1254,7 +1348,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) ktime_t now = ts->idle_entrytime; ktime_t next_event; - WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); *delta_next = ktime_sub(dev->next_event, now); @@ -1278,8 +1372,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. + * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { @@ -1292,6 +1389,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for the current CPU */ unsigned long tick_nohz_get_idle_calls(void) { @@ -1326,7 +1425,7 @@ void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->tick_stopped) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); @@ -1367,12 +1466,12 @@ void tick_nohz_idle_exit(void) local_irq_disable(); - WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); WARN_ON_ONCE(ts->timer_expires_base); - ts->inidle = 0; - idle_active = ts->idle_active; - tick_stopped = ts->tick_stopped; + tick_sched_flag_clear(ts, TS_FLAG_INIDLE); + idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); + tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); if (idle_active || tick_stopped) now = ktime_get(); @@ -1391,38 +1490,22 @@ void tick_nohz_idle_exit(void) * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). - * - * This low-resolution handler still makes use of some hrtimer APIs meanwhile - * for convenience with expiration calculation and forwarding. */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - struct pt_regs *regs = get_irq_regs(); - ktime_t now = ktime_get(); dev->next_event = KTIME_MAX; - tick_sched_do_timer(ts, now); - tick_sched_handle(ts, regs); - - /* - * In dynticks mode, tick reprogram is deferred: - * - to the idle task if in dynticks-idle - * - to IRQ exit if in full-dynticks. - */ - if (likely(!ts->tick_stopped)) { - hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); + if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART)) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); - } - } -static inline void tick_nohz_activate(struct tick_sched *ts, int mode) +static inline void tick_nohz_activate(struct tick_sched *ts) { if (!tick_nohz_enabled) return; - ts->nohz_mode = mode; + tick_sched_flag_set(ts, TS_FLAG_NOHZ); /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); @@ -1433,9 +1516,6 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode) */ static void tick_nohz_switch_to_nohz(void) { - struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - ktime_t next; - if (!tick_nohz_enabled) return; @@ -1444,16 +1524,9 @@ static void tick_nohz_switch_to_nohz(void) /* * Recycle the hrtimer in 'ts', so we can share the - * hrtimer_forward_now() function with the highres code. + * highres code. */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - /* Get the next period */ - next = tick_init_jiffy_update(); - - hrtimer_set_expires(&ts->sched_timer, next); - hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); - tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); - tick_nohz_activate(ts, NOHZ_MODE_LOWRES); + tick_setup_sched_timer(false); } static inline void tick_nohz_irq_enter(void) @@ -1461,10 +1534,10 @@ static inline void tick_nohz_irq_enter(void) struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; - if (!ts->idle_active && !ts->tick_stopped) + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) return; now = ktime_get(); - if (ts->idle_active) + if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. @@ -1473,7 +1546,7 @@ static inline void tick_nohz_irq_enter(void) * rare case (typically stop machine). So we must make sure we have a * last resort. */ - if (ts->tick_stopped) + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_update_jiffies(now); } @@ -1481,7 +1554,7 @@ static inline void tick_nohz_irq_enter(void) static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } -static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { } +static inline void tick_nohz_activate(struct tick_sched *ts) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -1494,45 +1567,6 @@ void tick_irq_enter(void) tick_nohz_irq_enter(); } -/* - * High resolution timer specific code - */ -#ifdef CONFIG_HIGH_RES_TIMERS -/* - * We rearm the timer until we get disabled by the idle code. - * Called with interrupts disabled. - */ -static enum hrtimer_restart tick_nohz_highres_handler(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(); - - tick_sched_do_timer(ts, now); - - /* - * Do not call when we are not in IRQ context and have - * no valid 'regs' pointer - */ - if (regs) - tick_sched_handle(ts, regs); - else - ts->next_tick = 0; - - /* - * In dynticks mode, tick reprogram is deferred: - * - to the idle task if in dynticks-idle - * - to IRQ exit if in full-dynticks. - */ - if (unlikely(ts->tick_stopped)) - return HRTIMER_NORESTART; - - hrtimer_forward(timer, now, TICK_NSEC); - - return HRTIMER_RESTART; -} - static int sched_skew_tick; static int __init skew_tick(char *str) @@ -1545,15 +1579,19 @@ early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer + * @hrtimer: whether to use the hrtimer or not */ -void tick_setup_sched_timer(void) +void tick_setup_sched_timer(bool hrtimer) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - ktime_t now = ktime_get(); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - ts->sched_timer.function = tick_nohz_highres_handler; + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) { + tick_sched_flag_set(ts, TS_FLAG_HIGHRES); + ts->sched_timer.function = tick_nohz_handler; + } /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); @@ -1566,23 +1604,35 @@ void tick_setup_sched_timer(void) hrtimer_add_expires_ns(&ts->sched_timer, offset); } - hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); - tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); + hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); + else + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); + tick_nohz_activate(ts); } -#endif /* HIGH_RES_TIMERS */ -#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -void tick_cancel_sched_timer(int cpu) +/* + * Shut down the tick and make sure the CPU won't try to retake the timekeeping + * duty before disabling IRQs in idle for the last time. + */ +void tick_sched_timer_dying(int cpu) { + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + struct clock_event_device *dev = td->evtdev; ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; -# ifdef CONFIG_HIGH_RES_TIMERS - if (ts->sched_timer.base) - hrtimer_cancel(&ts->sched_timer); -# endif + /* This must happen before hrtimers are migrated! */ + tick_sched_timer_cancel(ts); + + /* + * If the clockevents doesn't support CLOCK_EVT_STATE_ONESHOT_STOPPED, + * make sure not to call low-res tick handler. + */ + if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) + dev->event_handler = clockevents_handle_noop; idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; @@ -1594,7 +1644,6 @@ void tick_cancel_sched_timer(int cpu) ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } -#endif /* * Async notification about clocksource changes @@ -1632,7 +1681,7 @@ int tick_check_oneshot_change(int allow_nohz) if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; - if (ts->nohz_mode != NOHZ_MODE_INACTIVE) + if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 5ed5a9d41d..b4a7822f49 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -14,20 +14,26 @@ struct tick_device { enum tick_device_mode mode; }; -enum tick_nohz_mode { - NOHZ_MODE_INACTIVE, - NOHZ_MODE_LOWRES, - NOHZ_MODE_HIGHRES, -}; +/* The CPU is in the tick idle mode */ +#define TS_FLAG_INIDLE BIT(0) +/* The idle tick has been stopped */ +#define TS_FLAG_STOPPED BIT(1) +/* + * Indicator that the CPU is actively in the tick idle mode; + * it is reset during irq handling phases. + */ +#define TS_FLAG_IDLE_ACTIVE BIT(2) +/* CPU was the last one doing do_timer before going idle */ +#define TS_FLAG_DO_TIMER_LAST BIT(3) +/* NO_HZ is enabled */ +#define TS_FLAG_NOHZ BIT(4) +/* High resolution tick mode */ +#define TS_FLAG_HIGHRES BIT(5) /** * struct tick_sched - sched tick emulation and no idle tick control/stats * - * @inidle: Indicator that the CPU is in the tick idle mode - * @tick_stopped: Indicator that the idle tick has been stopped - * @idle_active: Indicator that the CPU is actively in the tick idle mode; - * it is reset during irq handling phases. - * @do_timer_last: CPU was the last one doing do_timer before going idle + * @flags: State flags gathering the TS_FLAG_* features * @got_idle_tick: Tick timer function has run with @inidle set * @stalled_jiffies: Number of stalled jiffies detected across ticks * @last_tick_jiffies: Value of jiffies seen on last tick @@ -40,8 +46,8 @@ enum tick_nohz_mode { * @next_tick: Next tick to be fired when in dynticks mode. * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_waketime: Time when the idle was interrupted + * @idle_sleeptime_seq: sequence counter for data consistency * @idle_entrytime: Time when the idle call was entered - * @nohz_mode: Mode - one state of tick_nohz_mode * @last_jiffies: Base jiffies snapshot when next event was last computed * @timer_expires_base: Base time clock monotonic for @timer_expires * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) @@ -57,11 +63,7 @@ enum tick_nohz_mode { */ struct tick_sched { /* Common flags */ - unsigned int inidle : 1; - unsigned int tick_stopped : 1; - unsigned int idle_active : 1; - unsigned int do_timer_last : 1; - unsigned int got_idle_tick : 1; + unsigned long flags; /* Tick handling: jiffies stall check */ unsigned int stalled_jiffies; @@ -73,13 +75,13 @@ struct tick_sched { ktime_t next_tick; unsigned long idle_jiffies; ktime_t idle_waketime; + unsigned int got_idle_tick; /* Idle entry */ seqcount_t idle_sleeptime_seq; ktime_t idle_entrytime; /* Tick stop */ - enum tick_nohz_mode nohz_mode; unsigned long last_jiffies; u64 timer_expires_base; u64 timer_expires; @@ -102,11 +104,11 @@ struct tick_sched { extern struct tick_sched *tick_get_tick_sched(int cpu); -extern void tick_setup_sched_timer(void); -#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -extern void tick_cancel_sched_timer(int cpu); +extern void tick_setup_sched_timer(bool hrtimer); +#if defined CONFIG_TICK_ONESHOT +extern void tick_sched_timer_dying(int cpu); #else -static inline void tick_cancel_sched_timer(int cpu) { } +static inline void tick_sched_timer_dying(int cpu) { } #endif #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 8aab7ed414..b58dffc58a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1234,11 +1234,12 @@ int get_device_system_crosststamp(int (*get_time_fn) return ret; /* - * Verify that the clocksource associated with the captured - * system counter value is the same as the currently installed - * timekeeper clocksource + * Verify that the clocksource ID associated with the captured + * system counter value is the same as for the currently + * installed timekeeper clocksource */ - if (tk->tkr_mono.clock != system_counterval.cs) + if (system_counterval.cs_id == CSID_GENERIC || + tk->tkr_mono.clock->id != system_counterval.cs_id) return -ENODEV; cycles = system_counterval.cycles; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 352b161113..3baf2fbe68 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -53,6 +53,7 @@ #include <asm/io.h> #include "tick-internal.h" +#include "timer_migration.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> @@ -63,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of - * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * - * The level granularity is: LVL_CLK_DIV ^ lvl + * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and - * therefor the granularity becomes. + * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading @@ -187,15 +188,66 @@ EXPORT_SYMBOL(jiffies_64); #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON -# define NR_BASES 2 -# define BASE_STD 0 -# define BASE_DEF 1 +/* + * If multiple bases need to be locked, use the base ordering for lock + * nesting, i.e. lowest number first. + */ +# define NR_BASES 3 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 1 +# define BASE_DEF 2 #else # define NR_BASES 1 -# define BASE_STD 0 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 0 # define BASE_DEF 0 #endif +/** + * struct timer_base - Per CPU timer base (number of base depends on config) + * @lock: Lock protecting the timer_base + * @running_timer: When expiring timers, the lock is dropped. To make + * sure not to race against deleting/modifying a + * currently running timer, the pointer is set to the + * timer, which expires at the moment. If no timer is + * running, the pointer is NULL. + * @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around + * timer expiry callback execution and when trying to + * delete a running timer and it wasn't successful in + * the first glance. It prevents priority inversion + * when callback was preempted on a remote CPU and a + * caller tries to delete the running timer. It also + * prevents a life lock, when the task which tries to + * delete a timer preempted the softirq thread which + * is running the timer callback function. + * @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter + * waiting for the end of the timer callback function + * execution. + * @clk: clock of the timer base; is updated before enqueue + * of a timer; during expiry, it is 1 offset ahead of + * jiffies to avoid endless requeuing to current + * jiffies + * @next_expiry: expiry value of the first timer; it is updated when + * finding the next timer and during enqueue; the + * value is not valid, when next_expiry_recalc is set + * @cpu: Number of CPU the timer base belongs to + * @next_expiry_recalc: States, whether a recalculation of next_expiry is + * required. Value is set true, when a timer was + * deleted. + * @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ + * code. This state is only used in standard + * base. Deferrable timers, which are enqueued remotely + * never wake up an idle CPU. So no matter of supporting it + * for this base. + * @timers_pending: Is set, when a timer is pending in the base. It is only + * reliable when next_expiry_recalc is not set. + * @pending_map: bitmap of the timer wheel; each bit reflects a + * bucket of the wheel. When a bit is set, at least a + * single timer is enqueued in the related bucket. + * @vectors: Array of lists; Each array member reflects a bucket + * of the timer wheel. The list contains all timers + * which are enqueued into a specific bucket. + */ struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; @@ -583,11 +635,17 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) /* * We might have to IPI the remote CPU if the base is idle and the - * timer is not deferrable. If the other CPU is on the way to idle - * then it can't set base->is_idle as we hold the base lock: + * timer is pinned. If it is a non pinned timer, it is only queued + * on the remote CPU, when timer was running during queueing. Then + * everything is handled by remote CPU anyway. If the other CPU is + * on the way to idle then it can't set base->is_idle as we hold + * the base lock: */ - if (base->is_idle) + if (base->is_idle) { + WARN_ON_ONCE(!(timer->flags & TIMER_PINNED || + tick_nohz_full_cpu(base->cpu))); wake_up_nohz_cpu(base->cpu); + } } /* @@ -679,7 +737,7 @@ static bool timer_is_static_object(void *addr) } /* - * fixup_init is called when: + * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) @@ -703,7 +761,7 @@ static void stub_timer(struct timer_list *unused) } /* - * fixup_activate is called when: + * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ @@ -725,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) } /* - * fixup_free is called when: + * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) @@ -743,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state) } /* - * fixup_assert_init is called when: + * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) @@ -856,7 +914,7 @@ static void do_init_timer(struct timer_list *timer, * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * - * init_timer_key() must be done to a timer prior calling *any* of the + * init_timer_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, @@ -899,7 +957,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base, static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { - struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = per_cpu_ptr(&timer_bases[index], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -912,7 +973,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = this_cpu_ptr(&timer_bases[index]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -928,17 +992,6 @@ static inline struct timer_base *get_timer_base(u32 tflags) return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } -static inline struct timer_base * -get_target_base(struct timer_base *base, unsigned tflags) -{ -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) - if (static_branch_likely(&timers_migration_enabled) && - !(tflags & TIMER_PINNED)) - return get_timer_cpu_base(tflags, get_nohz_timer_target()); -#endif - return get_timer_this_cpu_base(tflags); -} - static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { @@ -1093,7 +1146,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; - new_base = get_target_base(base, timer->flags); + new_base = get_timer_this_cpu_base(timer->flags); if (base != new_base) { /* @@ -1246,11 +1299,48 @@ void add_timer(struct timer_list *timer) EXPORT_SYMBOL(add_timer); /** + * add_timer_local() - Start a timer on the local CPU + * @timer: The timer to be started + * + * Same as add_timer() except that the timer flag TIMER_PINNED is set. + * + * See add_timer() for further details. + */ +void add_timer_local(struct timer_list *timer) +{ + if (WARN_ON_ONCE(timer_pending(timer))) + return; + timer->flags |= TIMER_PINNED; + __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); +} +EXPORT_SYMBOL(add_timer_local); + +/** + * add_timer_global() - Start a timer without TIMER_PINNED flag set + * @timer: The timer to be started + * + * Same as add_timer() except that the timer flag TIMER_PINNED is unset. + * + * See add_timer() for further details. + */ +void add_timer_global(struct timer_list *timer) +{ + if (WARN_ON_ONCE(timer_pending(timer))) + return; + timer->flags &= ~TIMER_PINNED; + __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); +} +EXPORT_SYMBOL(add_timer_global); + +/** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * - * Same as add_timer() except that it starts the timer on the given CPU. + * Same as add_timer() except that it starts the timer on the given CPU and + * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in + * the next round, add_timer_global() should be used instead as it unsets + * the TIMER_PINNED flag. * * See add_timer() for further details. */ @@ -1264,6 +1354,9 @@ void add_timer_on(struct timer_list *timer, int cpu) if (WARN_ON_ONCE(timer_pending(timer))) return; + /* Make sure timer flags have TIMER_PINNED flag set */ + timer->flags |= TIMER_PINNED; + new_base = get_timer_cpu_base(timer->flags, cpu); /* @@ -1324,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown) * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock - * aquisition. By taking the lock it is ensured that such a newly + * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * @@ -1911,71 +2004,357 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } +static unsigned long next_timer_interrupt(struct timer_base *base, + unsigned long basej) +{ + if (base->next_expiry_recalc) + next_expiry_recalc(base); + + /* + * Move next_expiry for the empty base into the future to prevent an + * unnecessary raise of the timer softirq when the next_expiry value + * will be reached even if there is no timer pending. + * + * This update is also required to make timer_base::next_expiry values + * easy comparable to find out which base holds the first pending timer. + */ + if (!base->timers_pending) + base->next_expiry = basej + NEXT_TIMER_MAX_DELTA; + + return base->next_expiry; +} + +static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem, + struct timer_base *base_local, + struct timer_base *base_global, + struct timer_events *tevt) +{ + unsigned long nextevt, nextevt_local, nextevt_global; + bool local_first; + + nextevt_local = next_timer_interrupt(base_local, basej); + nextevt_global = next_timer_interrupt(base_global, basej); + + local_first = time_before_eq(nextevt_local, nextevt_global); + + nextevt = local_first ? nextevt_local : nextevt_global; + + /* + * If the @nextevt is at max. one tick away, use @nextevt and store + * it in the local expiry value. The next global event is irrelevant in + * this case and can be left as KTIME_MAX. + */ + if (time_before_eq(nextevt, basej + 1)) { + /* If we missed a tick already, force 0 delta */ + if (time_before(nextevt, basej)) + nextevt = basej; + tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; + + /* + * This is required for the remote check only but it doesn't + * hurt, when it is done for both call sites: + * + * * The remote callers will only take care of the global timers + * as local timers will be handled by CPU itself. When not + * updating tevt->global with the already missed first global + * timer, it is possible that it will be missed completely. + * + * * The local callers will ignore the tevt->global anyway, when + * nextevt is max. one tick away. + */ + if (!local_first) + tevt->global = tevt->local; + return nextevt; + } + + /* + * Update tevt.* values: + * + * If the local queue expires first, then the global event can be + * ignored. If the global queue is empty, nothing to do either. + */ + if (!local_first && base_global->timers_pending) + tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; + + if (base_local->timers_pending) + tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; + + return nextevt; +} + +# ifdef CONFIG_SMP /** - * get_next_timer_interrupt - return the time (clock mono) of the next timer + * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic + * @tevt: Pointer to the storage for the expiry values + * @cpu: Remote CPU * - * Returns the tick aligned clock monotonic time of the next pending - * timer or KTIME_MAX if no timer is pending. + * Stores the next pending local and global timer expiry values in the + * struct pointed to by @tevt. If a queue is empty the corresponding + * field is set to KTIME_MAX. If local event expires before global + * event, global event is set to KTIME_MAX as well. + * + * Caller needs to make sure timer base locks are held (use + * timer_lock_remote_bases() for this purpose). */ -u64 get_next_timer_interrupt(unsigned long basej, u64 basem) +void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, + struct timer_events *tevt, + unsigned int cpu) +{ + struct timer_base *base_local, *base_global; + + /* Preset local / global events */ + tevt->local = tevt->global = KTIME_MAX; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + lockdep_assert_held(&base_local->lock); + lockdep_assert_held(&base_global->lock); + + fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt); +} + +/** + * timer_unlock_remote_bases - unlock timer bases of cpu + * @cpu: Remote CPU + * + * Unlocks the remote timer bases. + */ +void timer_unlock_remote_bases(unsigned int cpu) + __releases(timer_bases[BASE_LOCAL]->lock) + __releases(timer_bases[BASE_GLOBAL]->lock) +{ + struct timer_base *base_local, *base_global; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + raw_spin_unlock(&base_global->lock); + raw_spin_unlock(&base_local->lock); +} + +/** + * timer_lock_remote_bases - lock timer bases of cpu + * @cpu: Remote CPU + * + * Locks the remote timer bases. + */ +void timer_lock_remote_bases(unsigned int cpu) + __acquires(timer_bases[BASE_LOCAL]->lock) + __acquires(timer_bases[BASE_GLOBAL]->lock) +{ + struct timer_base *base_local, *base_global; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + lockdep_assert_irqs_disabled(); + + raw_spin_lock(&base_local->lock); + raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); +} + +/** + * timer_base_is_idle() - Return whether timer base is set idle + * + * Returns value of local timer base is_idle value. + */ +bool timer_base_is_idle(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA; - u64 expires = KTIME_MAX; - bool was_idle; + return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); +} + +static void __run_timer_base(struct timer_base *base); + +/** + * timer_expire_remote() - expire global timers of cpu + * @cpu: Remote CPU + * + * Expire timers of global base of remote CPU. + */ +void timer_expire_remote(unsigned int cpu) +{ + struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + __run_timer_base(base); +} + +static void timer_use_tmigr(unsigned long basej, u64 basem, + unsigned long *nextevt, bool *tick_stop_path, + bool timer_base_idle, struct timer_events *tevt) +{ + u64 next_tmigr; + + if (timer_base_idle) + next_tmigr = tmigr_cpu_new_timer(tevt->global); + else if (tick_stop_path) + next_tmigr = tmigr_cpu_deactivate(tevt->global); + else + next_tmigr = tmigr_quick_check(tevt->global); /* - * Pretend that there is no timer pending if the cpu is offline. - * Possible pending timers will be migrated later to an active cpu. + * If the CPU is the last going idle in timer migration hierarchy, make + * sure the CPU will wake up in time to handle remote timers. + * next_tmigr == KTIME_MAX if other CPUs are still active. */ - if (cpu_is_offline(smp_processor_id())) - return expires; + if (next_tmigr < tevt->local) { + u64 tmp; - raw_spin_lock(&base->lock); - if (base->next_expiry_recalc) - next_expiry_recalc(base); + /* If we missed a tick already, force 0 delta */ + if (next_tmigr < basem) + next_tmigr = basem; + + tmp = div_u64(next_tmigr - basem, TICK_NSEC); + + *nextevt = basej + (unsigned long)tmp; + tevt->local = next_tmigr; + } +} +# else +static void timer_use_tmigr(unsigned long basej, u64 basem, + unsigned long *nextevt, bool *tick_stop_path, + bool timer_base_idle, struct timer_events *tevt) +{ + /* + * Make sure first event is written into tevt->local to not miss a + * timer on !SMP systems. + */ + tevt->local = min_t(u64, tevt->local, tevt->global); +} +# endif /* CONFIG_SMP */ + +static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, + bool *idle) +{ + struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; + struct timer_base *base_local, *base_global; + unsigned long nextevt; + bool idle_is_possible; + + /* + * When the CPU is offline, the tick is cancelled and nothing is supposed + * to try to stop it. + */ + if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { + if (idle) + *idle = true; + return tevt.local; + } + + base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); + base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); + + raw_spin_lock(&base_local->lock); + raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); + + nextevt = fetch_next_timer_interrupt(basej, basem, base_local, + base_global, &tevt); + + /* + * If the next event is only one jiffie ahead there is no need to call + * timer migration hierarchy related functions. The value for the next + * global timer in @tevt struct equals then KTIME_MAX. This is also + * true, when the timer base is idle. + * + * The proper timer migration hierarchy function depends on the callsite + * and whether timer base is idle or not. @nextevt will be updated when + * this CPU needs to handle the first timer migration hierarchy + * event. See timer_use_tmigr() for detailed information. + */ + idle_is_possible = time_after(nextevt, basej + 1); + if (idle_is_possible) + timer_use_tmigr(basej, basem, &nextevt, idle, + base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ - __forward_timer_base(base, basej); + __forward_timer_base(base_local, basej); + __forward_timer_base(base_global, basej); - if (base->timers_pending) { - nextevt = base->next_expiry; + /* + * Set base->is_idle only when caller is timer_base_try_to_set_idle() + */ + if (idle) { + /* + * Bases are idle if the next event is more than a tick + * away. Caution: @nextevt could have changed by enqueueing a + * global timer into timer migration hierarchy. Therefore a new + * check is required here. + * + * If the base is marked idle then any timer add operation must + * forward the base clk itself to keep granularity small. This + * idle logic is only maintained for the BASE_LOCAL and + * BASE_GLOBAL base, deferrable timers may still see large + * granularity skew (by design). + */ + if (!base_local->is_idle && time_after(nextevt, basej + 1)) { + base_local->is_idle = true; + /* + * Global timers queued locally while running in a task + * in nohz_full mode need a self-IPI to kick reprogramming + * in IRQ tail. + */ + if (tick_nohz_full_cpu(base_local->cpu)) + base_global->is_idle = true; + trace_timer_base_idle(true, base_local->cpu); + } + *idle = base_local->is_idle; - /* If we missed a tick already, force 0 delta */ - if (time_before(nextevt, basej)) - nextevt = basej; - expires = basem + (u64)(nextevt - basej) * TICK_NSEC; - } else { /* - * Move next_expiry for the empty base into the future to - * prevent a unnecessary raise of the timer softirq when the - * next_expiry value will be reached even if there is no timer - * pending. + * When timer base is not set idle, undo the effect of + * tmigr_cpu_deactivate() to prevent inconsistent states - active + * timer base but inactive timer migration hierarchy. + * + * When timer base was already marked idle, nothing will be + * changed here. */ - base->next_expiry = nextevt; + if (!base_local->is_idle && idle_is_possible) + tmigr_cpu_activate(); } - /* - * Base is idle if the next event is more than a tick away. - * - * If the base is marked idle then any timer add operation must forward - * the base clk itself to keep granularity small. This idle logic is - * only maintained for the BASE_STD base, deferrable timers may still - * see large granularity skew (by design). - */ - was_idle = base->is_idle; - base->is_idle = time_after(nextevt, basej + 1); - if (was_idle != base->is_idle) - trace_timer_base_idle(base->is_idle, base->cpu); + raw_spin_unlock(&base_global->lock); + raw_spin_unlock(&base_local->lock); - raw_spin_unlock(&base->lock); + return cmp_next_hrtimer_event(basem, tevt.local); +} - return cmp_next_hrtimer_event(basem, expires); +/** + * get_next_timer_interrupt() - return the time (clock mono) of the next timer + * @basej: base time jiffies + * @basem: base time clock monotonic + * + * Returns the tick aligned clock monotonic time of the next pending timer or + * KTIME_MAX if no timer is pending. If timer of global base was queued into + * timer migration hierarchy, first global timer is not taken into account. If + * it was the last CPU of timer migration hierarchy going idle, first global + * event is taken into account. + */ +u64 get_next_timer_interrupt(unsigned long basej, u64 basem) +{ + return __get_next_timer_interrupt(basej, basem, NULL); +} + +/** + * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases + * @basej: base time jiffies + * @basem: base time clock monotonic + * @idle: pointer to store the value of timer_base->is_idle on return; + * *idle contains the information whether tick was already stopped + * + * Returns the tick aligned clock monotonic time of the next pending timer or + * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is + * returned as well. + */ +u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) +{ + if (*idle) + return KTIME_MAX; + + return __get_next_timer_interrupt(basej, basem, idle); } /** @@ -1985,18 +2364,20 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) */ void timer_clear_idle(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * We do this unlocked. The worst outcome is a remote enqueue sending - * a pointless IPI, but taking the lock would just make the window for - * sending the IPI a few instructions smaller for the cost of taking - * the lock in the exit from idle path. + * We do this unlocked. The worst outcome is a remote pinned timer + * enqueue sending a pointless IPI, but taking the lock would just + * make the window for sending the IPI a few instructions smaller + * for the cost of taking the lock in the exit from idle + * path. Required for BASE_LOCAL only. */ - if (base->is_idle) { - base->is_idle = false; - trace_timer_base_idle(false, smp_processor_id()); - } + __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); + if (tick_nohz_full_cpu(smp_processor_id())) + __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); + trace_timer_base_idle(false, smp_processor_id()); + + /* Activate without holding the timer_base->lock */ + tmigr_cpu_activate(); } #endif @@ -2009,11 +2390,10 @@ static inline void __run_timers(struct timer_base *base) struct hlist_head heads[LVL_DEPTH]; int levels; - if (time_before(jiffies, base->next_expiry)) - return; + lockdep_assert_held(&base->lock); - timer_base_lock_expiry(base); - raw_spin_lock_irq(&base->lock); + if (base->running_timer) + return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { @@ -2037,20 +2417,40 @@ static inline void __run_timers(struct timer_base *base) while (levels--) expire_timers(base, heads + levels); } +} + +static void __run_timer_base(struct timer_base *base) +{ + if (time_before(jiffies, base->next_expiry)) + return; + + timer_base_lock_expiry(base); + raw_spin_lock_irq(&base->lock); + __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } +static void run_timer_base(int index) +{ + struct timer_base *base = this_cpu_ptr(&timer_bases[index]); + + __run_timer_base(base); +} + /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + run_timer_base(BASE_LOCAL); + if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { + run_timer_base(BASE_GLOBAL); + run_timer_base(BASE_DEF); - __run_timers(base); - if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) - __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); + if (is_timers_nohz_active()) + tmigr_handle_remote(); + } } /* @@ -2058,19 +2458,18 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) */ static void run_local_timers(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); - /* Raise the softirq only if required. */ - if (time_before(jiffies, base->next_expiry)) { - if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) - return; - /* CPU is awake, so check the deferrable base. */ - base++; - if (time_before(jiffies, base->next_expiry)) + + for (int i = 0; i < NR_BASES; i++, base++) { + /* Raise the softirq only if required. */ + if (time_after_eq(jiffies, base->next_expiry) || + (i == BASE_DEF && tmigr_requires_handle_remote())) { + raise_softirq(TIMER_SOFTIRQ); return; + } } - raise_softirq(TIMER_SOFTIRQ); } /* diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index ed7d6ad694..1c311c46da 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -147,11 +147,15 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) # define P_ns(x) \ SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ (unsigned long long)(ktime_to_ns(ts->x))) +# define P_flag(x, f) \ + SEQ_printf(m, " .%-15s: %d\n", #x, !!(ts->flags & (f))) + { struct tick_sched *ts = tick_get_tick_sched(cpu); - P(nohz_mode); + P_flag(nohz, TS_FLAG_NOHZ); + P_flag(highres, TS_FLAG_HIGHRES); P_ns(last_tick); - P(tick_stopped); + P_flag(tick_stopped, TS_FLAG_STOPPED); P(idle_jiffies); P(idle_calls); P(idle_sleeps); @@ -256,7 +260,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) static inline void timer_list_header(struct seq_file *m, u64 now) { - SEQ_printf(m, "Timer List Version: v0.9\n"); + SEQ_printf(m, "Timer List Version: v0.10\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c new file mode 100644 index 0000000000..84413114db --- /dev/null +++ b/kernel/time/timer_migration.c @@ -0,0 +1,1810 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Infrastructure for migratable timers + * + * Copyright(C) 2022 linutronix GmbH + */ +#include <linux/cpuhotplug.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/spinlock.h> +#include <linux/timerqueue.h> +#include <trace/events/ipi.h> + +#include "timer_migration.h" +#include "tick-internal.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/timer_migration.h> + +/* + * The timer migration mechanism is built on a hierarchy of groups. The + * lowest level group contains CPUs, the next level groups of CPU groups + * and so forth. The CPU groups are kept per node so for the normal case + * lock contention won't happen across nodes. Depending on the number of + * CPUs per node even the next level might be kept as groups of CPU groups + * per node and only the levels above cross the node topology. + * + * Example topology for a two node system with 24 CPUs each. + * + * LVL 2 [GRP2:0] + * GRP1:0 = GRP1:M + * + * LVL 1 [GRP1:0] [GRP1:1] + * GRP0:0 - GRP0:2 GRP0:3 - GRP0:5 + * + * LVL 0 [GRP0:0] [GRP0:1] [GRP0:2] [GRP0:3] [GRP0:4] [GRP0:5] + * CPUS 0-7 8-15 16-23 24-31 32-39 40-47 + * + * The groups hold a timer queue of events sorted by expiry time. These + * queues are updated when CPUs go in idle. When they come out of idle + * ignore flag of events is set. + * + * Each group has a designated migrator CPU/group as long as a CPU/group is + * active in the group. This designated role is necessary to avoid that all + * active CPUs in a group try to migrate expired timers from other CPUs, + * which would result in massive lock bouncing. + * + * When a CPU is awake, it checks in it's own timer tick the group + * hierarchy up to the point where it is assigned the migrator role or if + * no CPU is active, it also checks the groups where no migrator is set + * (TMIGR_NONE). + * + * If it finds expired timers in one of the group queues it pulls them over + * from the idle CPU and runs the timer function. After that it updates the + * group and the parent groups if required. + * + * CPUs which go idle arm their CPU local timer hardware for the next local + * (pinned) timer event. If the next migratable timer expires after the + * next local timer or the CPU has no migratable timer pending then the + * CPU does not queue an event in the LVL0 group. If the next migratable + * timer expires before the next local timer then the CPU queues that timer + * in the LVL0 group. In both cases the CPU marks itself idle in the LVL0 + * group. + * + * When CPU comes out of idle and when a group has at least a single active + * child, the ignore flag of the tmigr_event is set. This indicates, that + * the event is ignored even if it is still enqueued in the parent groups + * timer queue. It will be removed when touching the timer queue the next + * time. This spares locking in active path as the lock protects (after + * setup) only event information. For more information about locking, + * please read the section "Locking rules". + * + * If the CPU is the migrator of the group then it delegates that role to + * the next active CPU in the group or sets migrator to TMIGR_NONE when + * there is no active CPU in the group. This delegation needs to be + * propagated up the hierarchy so hand over from other leaves can happen at + * all hierarchy levels w/o doing a search. + * + * When the last CPU in the system goes idle, then it drops all migrator + * duties up to the top level of the hierarchy (LVL2 in the example). It + * then has to make sure, that it arms it's own local hardware timer for + * the earliest event in the system. + * + * + * Lifetime rules: + * --------------- + * + * The groups are built up at init time or when CPUs come online. They are + * not destroyed when a group becomes empty due to offlining. The group + * just won't participate in the hierarchy management anymore. Destroying + * groups would result in interesting race conditions which would just make + * the whole mechanism slow and complex. + * + * + * Locking rules: + * -------------- + * + * For setting up new groups and handling events it's required to lock both + * child and parent group. The lock ordering is always bottom up. This also + * includes the per CPU locks in struct tmigr_cpu. For updating the migrator and + * active CPU/group information atomic_try_cmpxchg() is used instead and only + * the per CPU tmigr_cpu->lock is held. + * + * During the setup of groups tmigr_level_list is required. It is protected by + * @tmigr_mutex. + * + * When @timer_base->lock as well as tmigr related locks are required, the lock + * ordering is: first @timer_base->lock, afterwards tmigr related locks. + * + * + * Protection of the tmigr group state information: + * ------------------------------------------------ + * + * The state information with the list of active children and migrator needs to + * be protected by a sequence counter. It prevents a race when updates in child + * groups are propagated in changed order. The state update is performed + * lockless and group wise. The following scenario describes what happens + * without updating the sequence counter: + * + * Therefore, let's take three groups and four CPUs (CPU2 and CPU3 as well + * as GRP0:1 will not change during the scenario): + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU0 migrator = CPU2 + * active = CPU0 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * active idle active idle + * + * + * 1. CPU0 goes idle. As the update is performed group wise, in the first step + * only GRP0:0 is updated. The update of GRP1:0 is pending as CPU0 has to + * walk the hierarchy. + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * --> migrator = TMIGR_NONE migrator = CPU2 + * --> active = active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * --> idle idle active idle + * + * 2. While CPU0 goes idle and continues to update the state, CPU1 comes out of + * idle. CPU1 updates GRP0:0. The update for GRP1:0 is pending as CPU1 also + * has to walk the hierarchy. Both CPUs (CPU0 and CPU1) now walk the + * hierarchy to perform the needed update from their point of view. The + * currently visible state looks the following: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * --> migrator = CPU1 migrator = CPU2 + * --> active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle --> active active idle + * + * 3. Here is the race condition: CPU1 managed to propagate its changes (from + * step 2) through the hierarchy to GRP1:0 before CPU0 (step 1) did. The + * active members of GRP1:0 remain unchanged after the update since it is + * still valid from CPU1 current point of view: + * + * LVL 1 [GRP1:0] + * --> migrator = GRP0:1 + * --> active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU1 migrator = CPU2 + * active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle active active idle + * + * 4. Now CPU0 finally propagates its changes (from step 1) to GRP1:0. + * + * LVL 1 [GRP1:0] + * --> migrator = GRP0:1 + * --> active = GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU1 migrator = CPU2 + * active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle active active idle + * + * + * The race of CPU0 vs. CPU1 led to an inconsistent state in GRP1:0. CPU1 is + * active and is correctly listed as active in GRP0:0. However GRP1:0 does not + * have GRP0:0 listed as active, which is wrong. The sequence counter has been + * added to avoid inconsistent states during updates. The state is updated + * atomically only if all members, including the sequence counter, match the + * expected value (compare-and-exchange). + * + * Looking back at the previous example with the addition of the sequence + * counter: The update as performed by CPU0 in step 4 will fail. CPU1 changed + * the sequence number during the update in step 3 so the expected old value (as + * seen by CPU0 before starting the walk) does not match. + * + * Prevent race between new event and last CPU going inactive + * ---------------------------------------------------------- + * + * When the last CPU is going idle and there is a concurrent update of a new + * first global timer of an idle CPU, the group and child states have to be read + * while holding the lock in tmigr_update_events(). The following scenario shows + * what happens, when this is not done. + * + * 1. Only CPU2 is active: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 2. Now CPU 2 goes idle (and has no global timer, that has to be handled) and + * propagates that to GRP0:1: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE --> migrator = TMIGR_NONE + * active = --> active = + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle --> idle idle + * + * 3. Now the idle state is propagated up to GRP1:0. As this is now the last + * child going idle in top level group, the expiry of the next group event + * has to be handed back to make sure no event is lost. As there is no event + * enqueued, KTIME_MAX is handed back to CPU2. + * + * LVL 1 [GRP1:0] + * --> migrator = TMIGR_NONE + * --> active = + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle --> idle idle + * + * 4. CPU 0 has a new timer queued from idle and it expires at TIMER0. CPU0 + * propagates that to GRP0:0: + * + * LVL 1 [GRP1:0] + * migrator = TMIGR_NONE + * active = + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * --> next_expiry = TIMER0 next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle idle idle + * + * 5. GRP0:0 is not active, so the new timer has to be propagated to + * GRP1:0. Therefore the GRP1:0 state has to be read. When the stalled value + * (from step 2) is read, the timer is enqueued into GRP1:0, but nothing is + * handed back to CPU0, as it seems that there is still an active child in + * top level group. + * + * LVL 1 [GRP1:0] + * migrator = TMIGR_NONE + * active = + * --> next_expiry = TIMER0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * next_expiry = TIMER0 next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle idle idle + * + * This is prevented by reading the state when holding the lock (when a new + * timer has to be propagated from idle path):: + * + * CPU2 (tmigr_inactive_up()) CPU0 (tmigr_new_timer_up()) + * -------------------------- --------------------------- + * // step 3: + * cmpxchg(&GRP1:0->state); + * tmigr_update_events() { + * spin_lock(&GRP1:0->lock); + * // ... update events ... + * // hand back first expiry when GRP1:0 is idle + * spin_unlock(&GRP1:0->lock); + * // ^^^ release state modification + * } + * tmigr_update_events() { + * spin_lock(&GRP1:0->lock) + * // ^^^ acquire state modification + * group_state = atomic_read(&GRP1:0->state) + * // .... update events ... + * // hand back first expiry when GRP1:0 is idle + * spin_unlock(&GRP1:0->lock) <3> + * // ^^^ makes state visible for other + * // callers of tmigr_new_timer_up() + * } + * + * When CPU0 grabs the lock directly after cmpxchg, the first timer is reported + * back to CPU0 and also later on to CPU2. So no timer is missed. A concurrent + * update of the group state from active path is no problem, as the upcoming CPU + * will take care of the group events. + * + * Required event and timerqueue update after a remote expiry: + * ----------------------------------------------------------- + * + * After expiring timers of a remote CPU, a walk through the hierarchy and + * update of events and timerqueues is required. It is obviously needed if there + * is a 'new' global timer but also if there is no new global timer but the + * remote CPU is still idle. + * + * 1. CPU0 and CPU1 are idle and have both a global timer expiring at the same + * time. So both have an event enqueued in the timerqueue of GRP0:0. CPU3 is + * also idle and has no global timer pending. CPU2 is the only active CPU and + * thus also the migrator: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = evt-GRP0:0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * groupevt.cpu = CPU0 groupevt.cpu = + * timerqueue = evt-CPU0, timerqueue = + * evt-CPU1 + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 2. CPU2 starts to expire remote timers. It starts with LVL0 group + * GRP0:1. There is no event queued in the timerqueue, so CPU2 continues with + * the parent of GRP0:1: GRP1:0. In GRP1:0 it dequeues the first event. It + * looks at tmigr_event::cpu struct member and expires the pending timer(s) + * of CPU0. + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * --> groupevt.cpu = CPU0 groupevt.cpu = + * timerqueue = evt-CPU0, timerqueue = + * evt-CPU1 + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 3. Some work has to be done after expiring the timers of CPU0. If we stop + * here, then CPU1's pending global timer(s) will not expire in time and the + * timerqueue of GRP0:0 has still an event for CPU0 enqueued which has just + * been processed. So it is required to walk the hierarchy from CPU0's point + * of view and update it accordingly. CPU0's event will be removed from the + * timerqueue because it has no pending timer. If CPU0 would have a timer + * pending then it has to expire after CPU1's first timer because all timers + * from this period were just expired. Either way CPU1's event will be first + * in GRP0:0's timerqueue and therefore set in the CPU field of the group + * event which is then enqueued in GRP1:0's timerqueue as GRP0:0 is still not + * active: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = evt-GRP0:0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * --> groupevt.cpu = CPU1 groupevt.cpu = + * --> timerqueue = evt-CPU1 timerqueue = + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * Now CPU2 (migrator) will continue step 2 at GRP1:0 and will expire the + * timer(s) of CPU1. + * + * The hierarchy walk in step 3 can be skipped if the migrator notices that a + * CPU of GRP0:0 is active again. The CPU will mark GRP0:0 active and take care + * of the group as migrator and any needed updates within the hierarchy. + */ + +static DEFINE_MUTEX(tmigr_mutex); +static struct list_head *tmigr_level_list __read_mostly; + +static unsigned int tmigr_hierarchy_levels __read_mostly; +static unsigned int tmigr_crossnode_level __read_mostly; + +static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); + +#define TMIGR_NONE 0xFF +#define BIT_CNT 8 + +static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc) +{ + return !(tmc->tmgroup && tmc->online); +} + +/* + * Returns true, when @childmask corresponds to the group migrator or when the + * group is not active - so no migrator is set. + */ +static bool tmigr_check_migrator(struct tmigr_group *group, u8 childmask) +{ + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE)) + return true; + + return false; +} + +static bool tmigr_check_migrator_and_lonely(struct tmigr_group *group, u8 childmask) +{ + bool lonely, migrator = false; + unsigned long active; + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE)) + migrator = true; + + active = s.active; + lonely = bitmap_weight(&active, BIT_CNT) <= 1; + + return (migrator && lonely); +} + +static bool tmigr_check_lonely(struct tmigr_group *group) +{ + unsigned long active; + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + active = s.active; + + return bitmap_weight(&active, BIT_CNT) <= 1; +} + +typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *); + +static void __walk_groups(up_f up, void *data, + struct tmigr_cpu *tmc) +{ + struct tmigr_group *child = NULL, *group = tmc->tmgroup; + + do { + WARN_ON_ONCE(group->level >= tmigr_hierarchy_levels); + + if (up(group, child, data)) + break; + + child = group; + group = group->parent; + } while (group); +} + +static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc) +{ + lockdep_assert_held(&tmc->lock); + + __walk_groups(up, data, tmc); +} + +/** + * struct tmigr_walk - data required for walking the hierarchy + * @nextexp: Next CPU event expiry information which is handed into + * the timer migration code by the timer code + * (get_next_timer_interrupt()) + * @firstexp: Contains the first event expiry information when last + * active CPU of hierarchy is on the way to idle to make + * sure CPU will be back in time. + * @evt: Pointer to tmigr_event which needs to be queued (of idle + * child group) + * @childmask: childmask of child group + * @remote: Is set, when the new timer path is executed in + * tmigr_handle_remote_cpu() + */ +struct tmigr_walk { + u64 nextexp; + u64 firstexp; + struct tmigr_event *evt; + u8 childmask; + bool remote; +}; + +/** + * struct tmigr_remote_data - data required for remote expiry hierarchy walk + * @basej: timer base in jiffies + * @now: timer base monotonic + * @firstexp: returns expiry of the first timer in the idle timer + * migration hierarchy to make sure the timer is handled in + * time; it is stored in the per CPU tmigr_cpu struct of + * CPU which expires remote timers + * @childmask: childmask of child group + * @check: is set if there is the need to handle remote timers; + * required in tmigr_requires_handle_remote() only + * @tmc_active: this flag indicates, whether the CPU which triggers + * the hierarchy walk is !idle in the timer migration + * hierarchy. When the CPU is idle and the whole hierarchy is + * idle, only the first event of the top level has to be + * considered. + */ +struct tmigr_remote_data { + unsigned long basej; + u64 now; + u64 firstexp; + u8 childmask; + bool check; + bool tmc_active; +}; + +/* + * Returns the next event of the timerqueue @group->events + * + * Removes timers with ignore flag and update next_expiry of the group. Values + * of the group event are updated in tmigr_update_events() only. + */ +static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group) +{ + struct timerqueue_node *node = NULL; + struct tmigr_event *evt = NULL; + + lockdep_assert_held(&group->lock); + + WRITE_ONCE(group->next_expiry, KTIME_MAX); + + while ((node = timerqueue_getnext(&group->events))) { + evt = container_of(node, struct tmigr_event, nextevt); + + if (!evt->ignore) { + WRITE_ONCE(group->next_expiry, evt->nextevt.expires); + return evt; + } + + /* + * Remove next timers with ignore flag, because the group lock + * is held anyway + */ + if (!timerqueue_del(&group->events, node)) + break; + } + + return NULL; +} + +/* + * Return the next event (with the expiry equal or before @now) + * + * Event, which is returned, is also removed from the queue. + */ +static struct tmigr_event *tmigr_next_expired_groupevt(struct tmigr_group *group, + u64 now) +{ + struct tmigr_event *evt = tmigr_next_groupevt(group); + + if (!evt || now < evt->nextevt.expires) + return NULL; + + /* + * The event is ready to expire. Remove it and update next group event. + */ + timerqueue_del(&group->events, &evt->nextevt); + tmigr_next_groupevt(group); + + return evt; +} + +static u64 tmigr_next_groupevt_expires(struct tmigr_group *group) +{ + struct tmigr_event *evt; + + evt = tmigr_next_groupevt(group); + + if (!evt) + return KTIME_MAX; + else + return evt->nextevt.expires; +} + +static bool tmigr_active_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + union tmigr_state curstate, newstate; + struct tmigr_walk *data = ptr; + bool walk_done; + u8 childmask; + + childmask = data->childmask; + /* + * No memory barrier is required here in contrast to + * tmigr_inactive_up(), as the group state change does not depend on the + * child state. + */ + curstate.state = atomic_read(&group->migr_state); + + do { + newstate = curstate; + walk_done = true; + + if (newstate.migrator == TMIGR_NONE) { + newstate.migrator = childmask; + + /* Changes need to be propagated */ + walk_done = false; + } + + newstate.active |= childmask; + newstate.seq++; + + } while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)); + + if ((walk_done == false) && group->parent) + data->childmask = group->childmask; + + /* + * The group is active (again). The group event might be still queued + * into the parent group's timerqueue but can now be handled by the + * migrator of this group. Therefore the ignore flag for the group event + * is updated to reflect this. + * + * The update of the ignore flag in the active path is done lockless. In + * worst case the migrator of the parent group observes the change too + * late and expires remotely all events belonging to this group. The + * lock is held while updating the ignore flag in idle path. So this + * state change will not be lost. + */ + group->groupevt.ignore = true; + + trace_tmigr_group_set_cpu_active(group, newstate, childmask); + + return walk_done; +} + +static void __tmigr_cpu_activate(struct tmigr_cpu *tmc) +{ + struct tmigr_walk data; + + data.childmask = tmc->childmask; + + trace_tmigr_cpu_active(tmc); + + tmc->cpuevt.ignore = true; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + walk_groups(&tmigr_active_up, &data, tmc); +} + +/** + * tmigr_cpu_activate() - set this CPU active in timer migration hierarchy + * + * Call site timer_clear_idle() is called with interrupts disabled. + */ +void tmigr_cpu_activate(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + if (tmigr_is_not_available(tmc)) + return; + + if (WARN_ON_ONCE(!tmc->idle)) + return; + + raw_spin_lock(&tmc->lock); + tmc->idle = false; + __tmigr_cpu_activate(tmc); + raw_spin_unlock(&tmc->lock); +} + +/* + * Returns true, if there is nothing to be propagated to the next level + * + * @data->firstexp is set to expiry of first gobal event of the (top level of + * the) hierarchy, but only when hierarchy is completely idle. + * + * The child and group states need to be read under the lock, to prevent a race + * against a concurrent tmigr_inactive_up() run when the last CPU goes idle. See + * also section "Prevent race between new event and last CPU going inactive" in + * the documentation at the top. + * + * This is the only place where the group event expiry value is set. + */ +static +bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, + struct tmigr_walk *data) +{ + struct tmigr_event *evt, *first_childevt; + union tmigr_state childstate, groupstate; + bool remote = data->remote; + bool walk_done = false; + u64 nextexp; + + if (child) { + raw_spin_lock(&child->lock); + raw_spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING); + + childstate.state = atomic_read(&child->migr_state); + groupstate.state = atomic_read(&group->migr_state); + + if (childstate.active) { + walk_done = true; + goto unlock; + } + + first_childevt = tmigr_next_groupevt(child); + nextexp = child->next_expiry; + evt = &child->groupevt; + + evt->ignore = (nextexp == KTIME_MAX) ? true : false; + } else { + nextexp = data->nextexp; + + first_childevt = evt = data->evt; + + /* + * Walking the hierarchy is required in any case when a + * remote expiry was done before. This ensures to not lose + * already queued events in non active groups (see section + * "Required event and timerqueue update after a remote + * expiry" in the documentation at the top). + * + * The two call sites which are executed without a remote expiry + * before, are not prevented from propagating changes through + * the hierarchy by the return: + * - When entering this path by tmigr_new_timer(), @evt->ignore + * is never set. + * - tmigr_inactive_up() takes care of the propagation by + * itself and ignores the return value. But an immediate + * return is possible if there is a parent, sparing group + * locking at this level, because the upper walking call to + * the parent will take care about removing this event from + * within the group and update next_expiry accordingly. + * + * However if there is no parent, ie: the hierarchy has only a + * single level so @group is the top level group, make sure the + * first event information of the group is updated properly and + * also handled properly, so skip this fast return path. + */ + if (evt->ignore && !remote && group->parent) + return true; + + raw_spin_lock(&group->lock); + + childstate.state = 0; + groupstate.state = atomic_read(&group->migr_state); + } + + /* + * If the child event is already queued in the group, remove it from the + * queue when the expiry time changed only or when it could be ignored. + */ + if (timerqueue_node_queued(&evt->nextevt)) { + if ((evt->nextevt.expires == nextexp) && !evt->ignore) { + /* Make sure not to miss a new CPU event with the same expiry */ + evt->cpu = first_childevt->cpu; + goto check_toplvl; + } + + if (!timerqueue_del(&group->events, &evt->nextevt)) + WRITE_ONCE(group->next_expiry, KTIME_MAX); + } + + if (evt->ignore) { + /* + * When the next child event could be ignored (nextexp is + * KTIME_MAX) and there was no remote timer handling before or + * the group is already active, there is no need to walk the + * hierarchy even if there is a parent group. + * + * The other way round: even if the event could be ignored, but + * if a remote timer handling was executed before and the group + * is not active, walking the hierarchy is required to not miss + * an enqueued timer in the non active group. The enqueued timer + * of the group needs to be propagated to a higher level to + * ensure it is handled. + */ + if (!remote || groupstate.active) + walk_done = true; + } else { + evt->nextevt.expires = nextexp; + evt->cpu = first_childevt->cpu; + + if (timerqueue_add(&group->events, &evt->nextevt)) + WRITE_ONCE(group->next_expiry, nextexp); + } + +check_toplvl: + if (!group->parent && (groupstate.migrator == TMIGR_NONE)) { + walk_done = true; + + /* + * Nothing to do when update was done during remote timer + * handling. First timer in top level group which needs to be + * handled when top level group is not active, is calculated + * directly in tmigr_handle_remote_up(). + */ + if (remote) + goto unlock; + + /* + * The top level group is idle and it has to be ensured the + * global timers are handled in time. (This could be optimized + * by keeping track of the last global scheduled event and only + * arming it on the CPU if the new event is earlier. Not sure if + * its worth the complexity.) + */ + data->firstexp = tmigr_next_groupevt_expires(group); + } + + trace_tmigr_update_events(child, group, childstate, groupstate, + nextexp); + +unlock: + raw_spin_unlock(&group->lock); + + if (child) + raw_spin_unlock(&child->lock); + + return walk_done; +} + +static bool tmigr_new_timer_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_walk *data = ptr; + + return tmigr_update_events(group, child, data); +} + +/* + * Returns the expiry of the next timer that needs to be handled. KTIME_MAX is + * returned, if an active CPU will handle all the timer migration hierarchy + * timers. + */ +static u64 tmigr_new_timer(struct tmigr_cpu *tmc, u64 nextexp) +{ + struct tmigr_walk data = { .nextexp = nextexp, + .firstexp = KTIME_MAX, + .evt = &tmc->cpuevt }; + + lockdep_assert_held(&tmc->lock); + + if (tmc->remote) + return KTIME_MAX; + + trace_tmigr_cpu_new_timer(tmc); + + tmc->cpuevt.ignore = false; + data.remote = false; + + walk_groups(&tmigr_new_timer_up, &data, tmc); + + /* If there is a new first global event, make sure it is handled */ + return data.firstexp; +} + +static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now, + unsigned long jif) +{ + struct timer_events tevt; + struct tmigr_walk data; + struct tmigr_cpu *tmc; + + tmc = per_cpu_ptr(&tmigr_cpu, cpu); + + raw_spin_lock_irq(&tmc->lock); + + /* + * If the remote CPU is offline then the timers have been migrated to + * another CPU. + * + * If tmigr_cpu::remote is set, at the moment another CPU already + * expires the timers of the remote CPU. + * + * If tmigr_event::ignore is set, then the CPU returns from idle and + * takes care of its timers. + * + * If the next event expires in the future, then the event has been + * updated and there are no timers to expire right now. The CPU which + * updated the event takes care when hierarchy is completely + * idle. Otherwise the migrator does it as the event is enqueued. + */ + if (!tmc->online || tmc->remote || tmc->cpuevt.ignore || + now < tmc->cpuevt.nextevt.expires) { + raw_spin_unlock_irq(&tmc->lock); + return; + } + + trace_tmigr_handle_remote_cpu(tmc); + + tmc->remote = true; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* Drop the lock to allow the remote CPU to exit idle */ + raw_spin_unlock_irq(&tmc->lock); + + if (cpu != smp_processor_id()) + timer_expire_remote(cpu); + + /* + * Lock ordering needs to be preserved - timer_base locks before tmigr + * related locks (see section "Locking rules" in the documentation at + * the top). During fetching the next timer interrupt, also tmc->lock + * needs to be held. Otherwise there is a possible race window against + * the CPU itself when it comes out of idle, updates the first timer in + * the hierarchy and goes back to idle. + * + * timer base locks are dropped as fast as possible: After checking + * whether the remote CPU went offline in the meantime and after + * fetching the next remote timer interrupt. Dropping the locks as fast + * as possible keeps the locking region small and prevents holding + * several (unnecessary) locks during walking the hierarchy for updating + * the timerqueue and group events. + */ + local_irq_disable(); + timer_lock_remote_bases(cpu); + raw_spin_lock(&tmc->lock); + + /* + * When the CPU went offline in the meantime, no hierarchy walk has to + * be done for updating the queued events, because the walk was + * already done during marking the CPU offline in the hierarchy. + * + * When the CPU is no longer idle, the CPU takes care of the timers and + * also of the timers in the hierarchy. + * + * (See also section "Required event and timerqueue update after a + * remote expiry" in the documentation at the top) + */ + if (!tmc->online || !tmc->idle) { + timer_unlock_remote_bases(cpu); + goto unlock; + } + + /* next event of CPU */ + fetch_next_timer_interrupt_remote(jif, now, &tevt, cpu); + timer_unlock_remote_bases(cpu); + + data.nextexp = tevt.global; + data.firstexp = KTIME_MAX; + data.evt = &tmc->cpuevt; + data.remote = true; + + /* + * The update is done even when there is no 'new' global timer pending + * on the remote CPU (see section "Required event and timerqueue update + * after a remote expiry" in the documentation at the top) + */ + walk_groups(&tmigr_new_timer_up, &data, tmc); + +unlock: + tmc->remote = false; + raw_spin_unlock_irq(&tmc->lock); +} + +static bool tmigr_handle_remote_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_remote_data *data = ptr; + struct tmigr_event *evt; + unsigned long jif; + u8 childmask; + u64 now; + + jif = data->basej; + now = data->now; + + childmask = data->childmask; + + trace_tmigr_handle_remote(group); +again: + /* + * Handle the group only if @childmask is the migrator or if the + * group has no migrator. Otherwise the group is active and is + * handled by its own migrator. + */ + if (!tmigr_check_migrator(group, childmask)) + return true; + + raw_spin_lock_irq(&group->lock); + + evt = tmigr_next_expired_groupevt(group, now); + + if (evt) { + unsigned int remote_cpu = evt->cpu; + + raw_spin_unlock_irq(&group->lock); + + tmigr_handle_remote_cpu(remote_cpu, now, jif); + + /* check if there is another event, that needs to be handled */ + goto again; + } + + /* + * Update of childmask for the next level and keep track of the expiry + * of the first event that needs to be handled (group->next_expiry was + * updated by tmigr_next_expired_groupevt(), next was set by + * tmigr_handle_remote_cpu()). + */ + data->childmask = group->childmask; + data->firstexp = group->next_expiry; + + raw_spin_unlock_irq(&group->lock); + + return false; +} + +/** + * tmigr_handle_remote() - Handle global timers of remote idle CPUs + * + * Called from the timer soft interrupt with interrupts enabled. + */ +void tmigr_handle_remote(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_remote_data data; + + if (tmigr_is_not_available(tmc)) + return; + + data.childmask = tmc->childmask; + data.firstexp = KTIME_MAX; + + /* + * NOTE: This is a doubled check because the migrator test will be done + * in tmigr_handle_remote_up() anyway. Keep this check to speed up the + * return when nothing has to be done. + */ + if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) { + /* + * If this CPU was an idle migrator, make sure to clear its wakeup + * value so it won't chase timers that have already expired elsewhere. + * This avoids endless requeue from tmigr_new_timer(). + */ + if (READ_ONCE(tmc->wakeup) == KTIME_MAX) + return; + } + + data.now = get_jiffies_update(&data.basej); + + /* + * Update @tmc->wakeup only at the end and do not reset @tmc->wakeup to + * KTIME_MAX. Even if tmc->lock is not held during the whole remote + * handling, tmc->wakeup is fine to be stale as it is called in + * interrupt context and tick_nohz_next_event() is executed in interrupt + * exit path only after processing the last pending interrupt. + */ + + __walk_groups(&tmigr_handle_remote_up, &data, tmc); + + raw_spin_lock_irq(&tmc->lock); + WRITE_ONCE(tmc->wakeup, data.firstexp); + raw_spin_unlock_irq(&tmc->lock); +} + +static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_remote_data *data = ptr; + u8 childmask; + + childmask = data->childmask; + + /* + * Handle the group only if the child is the migrator or if the group + * has no migrator. Otherwise the group is active and is handled by its + * own migrator. + */ + if (!tmigr_check_migrator(group, childmask)) + return true; + + /* + * When there is a parent group and the CPU which triggered the + * hierarchy walk is not active, proceed the walk to reach the top level + * group before reading the next_expiry value. + */ + if (group->parent && !data->tmc_active) + goto out; + + /* + * The lock is required on 32bit architectures to read the variable + * consistently with a concurrent writer. On 64bit the lock is not + * required because the read operation is not split and so it is always + * consistent. + */ + if (IS_ENABLED(CONFIG_64BIT)) { + data->firstexp = READ_ONCE(group->next_expiry); + if (data->now >= data->firstexp) { + data->check = true; + return true; + } + } else { + raw_spin_lock(&group->lock); + data->firstexp = group->next_expiry; + if (data->now >= group->next_expiry) { + data->check = true; + raw_spin_unlock(&group->lock); + return true; + } + raw_spin_unlock(&group->lock); + } + +out: + /* Update of childmask for the next level */ + data->childmask = group->childmask; + return false; +} + +/** + * tmigr_requires_handle_remote() - Check the need of remote timer handling + * + * Must be called with interrupts disabled. + */ +bool tmigr_requires_handle_remote(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_remote_data data; + unsigned long jif; + bool ret = false; + + if (tmigr_is_not_available(tmc)) + return ret; + + data.now = get_jiffies_update(&jif); + data.childmask = tmc->childmask; + data.firstexp = KTIME_MAX; + data.tmc_active = !tmc->idle; + data.check = false; + + /* + * If the CPU is active, walk the hierarchy to check whether a remote + * expiry is required. + * + * Check is done lockless as interrupts are disabled and @tmc->idle is + * set only by the local CPU. + */ + if (!tmc->idle) { + __walk_groups(&tmigr_requires_handle_remote_up, &data, tmc); + + return data.check; + } + + /* + * When the CPU is idle, compare @tmc->wakeup with @data.now. The lock + * is required on 32bit architectures to read the variable consistently + * with a concurrent writer. On 64bit the lock is not required because + * the read operation is not split and so it is always consistent. + */ + if (IS_ENABLED(CONFIG_64BIT)) { + if (data.now >= READ_ONCE(tmc->wakeup)) + return true; + } else { + raw_spin_lock(&tmc->lock); + if (data.now >= tmc->wakeup) + ret = true; + raw_spin_unlock(&tmc->lock); + } + + return ret; +} + +/** + * tmigr_cpu_new_timer() - enqueue next global timer into hierarchy (idle tmc) + * @nextexp: Next expiry of global timer (or KTIME_MAX if not) + * + * The CPU is already deactivated in the timer migration + * hierarchy. tick_nohz_get_sleep_length() calls tick_nohz_next_event() + * and thereby the timer idle path is executed once more. @tmc->wakeup + * holds the first timer, when the timer migration hierarchy is + * completely idle. + * + * Returns the first timer that needs to be handled by this CPU or KTIME_MAX if + * nothing needs to be done. + */ +u64 tmigr_cpu_new_timer(u64 nextexp) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + u64 ret; + + if (tmigr_is_not_available(tmc)) + return nextexp; + + raw_spin_lock(&tmc->lock); + + ret = READ_ONCE(tmc->wakeup); + if (nextexp != KTIME_MAX) { + if (nextexp != tmc->cpuevt.nextevt.expires || + tmc->cpuevt.ignore) { + ret = tmigr_new_timer(tmc, nextexp); + } + } + /* + * Make sure the reevaluation of timers in idle path will not miss an + * event. + */ + WRITE_ONCE(tmc->wakeup, ret); + + trace_tmigr_cpu_new_timer_idle(tmc, nextexp); + raw_spin_unlock(&tmc->lock); + return ret; +} + +static bool tmigr_inactive_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + union tmigr_state curstate, newstate, childstate; + struct tmigr_walk *data = ptr; + bool walk_done; + u8 childmask; + + childmask = data->childmask; + childstate.state = 0; + + /* + * The memory barrier is paired with the cmpxchg() in tmigr_active_up() + * to make sure the updates of child and group states are ordered. The + * ordering is mandatory, as the group state change depends on the child + * state. + */ + curstate.state = atomic_read_acquire(&group->migr_state); + + for (;;) { + if (child) + childstate.state = atomic_read(&child->migr_state); + + newstate = curstate; + walk_done = true; + + /* Reset active bit when the child is no longer active */ + if (!childstate.active) + newstate.active &= ~childmask; + + if (newstate.migrator == childmask) { + /* + * Find a new migrator for the group, because the child + * group is idle! + */ + if (!childstate.active) { + unsigned long new_migr_bit, active = newstate.active; + + new_migr_bit = find_first_bit(&active, BIT_CNT); + + if (new_migr_bit != BIT_CNT) { + newstate.migrator = BIT(new_migr_bit); + } else { + newstate.migrator = TMIGR_NONE; + + /* Changes need to be propagated */ + walk_done = false; + } + } + } + + newstate.seq++; + + WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active)); + + if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, + newstate.state)) + break; + + /* + * The memory barrier is paired with the cmpxchg() in + * tmigr_active_up() to make sure the updates of child and group + * states are ordered. It is required only when the above + * try_cmpxchg() fails. + */ + smp_mb__after_atomic(); + } + + data->remote = false; + + /* Event Handling */ + tmigr_update_events(group, child, data); + + if (group->parent && (walk_done == false)) + data->childmask = group->childmask; + + /* + * data->firstexp was set by tmigr_update_events() and contains the + * expiry of the first global event which needs to be handled. It + * differs from KTIME_MAX if: + * - group is the top level group and + * - group is idle (which means CPU was the last active CPU in the + * hierarchy) and + * - there is a pending event in the hierarchy + */ + WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent); + + trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); + + return walk_done; +} + +static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp) +{ + struct tmigr_walk data = { .nextexp = nextexp, + .firstexp = KTIME_MAX, + .evt = &tmc->cpuevt, + .childmask = tmc->childmask }; + + /* + * If nextexp is KTIME_MAX, the CPU event will be ignored because the + * local timer expires before the global timer, no global timer is set + * or CPU goes offline. + */ + if (nextexp != KTIME_MAX) + tmc->cpuevt.ignore = false; + + walk_groups(&tmigr_inactive_up, &data, tmc); + return data.firstexp; +} + +/** + * tmigr_cpu_deactivate() - Put current CPU into inactive state + * @nextexp: The next global timer expiry of the current CPU + * + * Must be called with interrupts disabled. + * + * Return: the next event expiry of the current CPU or the next event expiry + * from the hierarchy if this CPU is the top level migrator or the hierarchy is + * completely idle. + */ +u64 tmigr_cpu_deactivate(u64 nextexp) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + u64 ret; + + if (tmigr_is_not_available(tmc)) + return nextexp; + + raw_spin_lock(&tmc->lock); + + ret = __tmigr_cpu_deactivate(tmc, nextexp); + + tmc->idle = true; + + /* + * Make sure the reevaluation of timers in idle path will not miss an + * event. + */ + WRITE_ONCE(tmc->wakeup, ret); + + trace_tmigr_cpu_idle(tmc, nextexp); + raw_spin_unlock(&tmc->lock); + return ret; +} + +/** + * tmigr_quick_check() - Quick forecast of next tmigr event when CPU wants to + * go idle + * @nextevt: The next global timer expiry of the current CPU + * + * Return: + * * KTIME_MAX - when it is probable that nothing has to be done (not + * the only one in the level 0 group; and if it is the + * only one in level 0 group, but there are more than a + * single group active on the way to top level) + * * nextevt - when CPU is offline and has to handle timer on his own + * or when on the way to top in every group only a single + * child is active but @nextevt is before the lowest + * next_expiry encountered while walking up to top level. + * * next_expiry - value of lowest expiry encountered while walking groups + * if only a single child is active on each and @nextevt + * is after this lowest expiry. + */ +u64 tmigr_quick_check(u64 nextevt) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_group *group = tmc->tmgroup; + + if (tmigr_is_not_available(tmc)) + return nextevt; + + if (WARN_ON_ONCE(tmc->idle)) + return nextevt; + + if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask)) + return KTIME_MAX; + + do { + if (!tmigr_check_lonely(group)) { + return KTIME_MAX; + } else { + /* + * Since current CPU is active, events may not be sorted + * from bottom to the top because the CPU's event is ignored + * up to the top and its sibling's events not propagated upwards. + * Thus keep track of the lowest observed expiry. + */ + nextevt = min_t(u64, nextevt, READ_ONCE(group->next_expiry)); + if (!group->parent) + return nextevt; + } + group = group->parent; + } while (group); + + return KTIME_MAX; +} + +static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, + int node) +{ + union tmigr_state s; + + raw_spin_lock_init(&group->lock); + + group->level = lvl; + group->numa_node = lvl < tmigr_crossnode_level ? node : NUMA_NO_NODE; + + group->num_children = 0; + + s.migrator = TMIGR_NONE; + s.active = 0; + s.seq = 0; + atomic_set(&group->migr_state, s.state); + + timerqueue_init_head(&group->events); + timerqueue_init(&group->groupevt.nextevt); + group->groupevt.nextevt.expires = KTIME_MAX; + WRITE_ONCE(group->next_expiry, KTIME_MAX); + group->groupevt.ignore = true; +} + +static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node, + unsigned int lvl) +{ + struct tmigr_group *tmp, *group = NULL; + + lockdep_assert_held(&tmigr_mutex); + + /* Try to attach to an existing group first */ + list_for_each_entry(tmp, &tmigr_level_list[lvl], list) { + /* + * If @lvl is below the cross NUMA node level, check whether + * this group belongs to the same NUMA node. + */ + if (lvl < tmigr_crossnode_level && tmp->numa_node != node) + continue; + + /* Capacity left? */ + if (tmp->num_children >= TMIGR_CHILDREN_PER_GROUP) + continue; + + /* + * TODO: A possible further improvement: Make sure that all CPU + * siblings end up in the same group of the lowest level of the + * hierarchy. Rely on the topology sibling mask would be a + * reasonable solution. + */ + + group = tmp; + break; + } + + if (group) + return group; + + /* Allocate and set up a new group */ + group = kzalloc_node(sizeof(*group), GFP_KERNEL, node); + if (!group) + return ERR_PTR(-ENOMEM); + + tmigr_init_group(group, lvl, node); + + /* Setup successful. Add it to the hierarchy */ + list_add(&group->list, &tmigr_level_list[lvl]); + trace_tmigr_group_set(group); + return group; +} + +static void tmigr_connect_child_parent(struct tmigr_group *child, + struct tmigr_group *parent) +{ + union tmigr_state childstate; + + raw_spin_lock_irq(&child->lock); + raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); + + child->parent = parent; + child->childmask = BIT(parent->num_children++); + + raw_spin_unlock(&parent->lock); + raw_spin_unlock_irq(&child->lock); + + trace_tmigr_connect_child_parent(child); + + /* + * To prevent inconsistent states, active children need to be active in + * the new parent as well. Inactive children are already marked inactive + * in the parent group: + * + * * When new groups were created by tmigr_setup_groups() starting from + * the lowest level (and not higher then one level below the current + * top level), then they are not active. They will be set active when + * the new online CPU comes active. + * + * * But if a new group above the current top level is required, it is + * mandatory to propagate the active state of the already existing + * child to the new parent. So tmigr_connect_child_parent() is + * executed with the formerly top level group (child) and the newly + * created group (parent). + */ + childstate.state = atomic_read(&child->migr_state); + if (childstate.migrator != TMIGR_NONE) { + struct tmigr_walk data; + + data.childmask = child->childmask; + + /* + * There is only one new level per time. When connecting the + * child and the parent and set the child active when the parent + * is inactive, the parent needs to be the uppermost + * level. Otherwise there went something wrong! + */ + WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); + } +} + +static int tmigr_setup_groups(unsigned int cpu, unsigned int node) +{ + struct tmigr_group *group, *child, **stack; + int top = 0, err = 0, i = 0; + struct list_head *lvllist; + + stack = kcalloc(tmigr_hierarchy_levels, sizeof(*stack), GFP_KERNEL); + if (!stack) + return -ENOMEM; + + do { + group = tmigr_get_group(cpu, node, i); + if (IS_ERR(group)) { + err = PTR_ERR(group); + break; + } + + top = i; + stack[i++] = group; + + /* + * When booting only less CPUs of a system than CPUs are + * available, not all calculated hierarchy levels are required. + * + * The loop is aborted as soon as the highest level, which might + * be different from tmigr_hierarchy_levels, contains only a + * single group. + */ + if (group->parent || i == tmigr_hierarchy_levels || + (list_empty(&tmigr_level_list[i]) && + list_is_singular(&tmigr_level_list[i - 1]))) + break; + + } while (i < tmigr_hierarchy_levels); + + while (i > 0) { + group = stack[--i]; + + if (err < 0) { + list_del(&group->list); + kfree(group); + continue; + } + + WARN_ON_ONCE(i != group->level); + + /* + * Update tmc -> group / child -> group connection + */ + if (i == 0) { + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + raw_spin_lock_irq(&group->lock); + + tmc->tmgroup = group; + tmc->childmask = BIT(group->num_children++); + + raw_spin_unlock_irq(&group->lock); + + trace_tmigr_connect_cpu_parent(tmc); + + /* There are no children that need to be connected */ + continue; + } else { + child = stack[i - 1]; + tmigr_connect_child_parent(child, group); + } + + /* check if uppermost level was newly created */ + if (top != i) + continue; + + WARN_ON_ONCE(top == 0); + + lvllist = &tmigr_level_list[top]; + if (group->num_children == 1 && list_is_singular(lvllist)) { + lvllist = &tmigr_level_list[top - 1]; + list_for_each_entry(child, lvllist, list) { + if (child->parent) + continue; + + tmigr_connect_child_parent(child, group); + } + } + } + + kfree(stack); + + return err; +} + +static int tmigr_add_cpu(unsigned int cpu) +{ + int node = cpu_to_node(cpu); + int ret; + + mutex_lock(&tmigr_mutex); + ret = tmigr_setup_groups(cpu, node); + mutex_unlock(&tmigr_mutex); + + return ret; +} + +static int tmigr_cpu_online(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int ret; + + /* First online attempt? Initialize CPU data */ + if (!tmc->tmgroup) { + raw_spin_lock_init(&tmc->lock); + + ret = tmigr_add_cpu(cpu); + if (ret < 0) + return ret; + + if (tmc->childmask == 0) + return -EINVAL; + + timerqueue_init(&tmc->cpuevt.nextevt); + tmc->cpuevt.nextevt.expires = KTIME_MAX; + tmc->cpuevt.ignore = true; + tmc->cpuevt.cpu = cpu; + + tmc->remote = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + } + raw_spin_lock_irq(&tmc->lock); + trace_tmigr_cpu_online(tmc); + tmc->idle = timer_base_is_idle(); + if (!tmc->idle) + __tmigr_cpu_activate(tmc); + tmc->online = true; + raw_spin_unlock_irq(&tmc->lock); + return 0; +} + +/* + * tmigr_trigger_active() - trigger a CPU to become active again + * + * This function is executed on a CPU which is part of cpu_online_mask, when the + * last active CPU in the hierarchy is offlining. With this, it is ensured that + * the other CPU is active and takes over the migrator duty. + */ +static long tmigr_trigger_active(void *unused) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + WARN_ON_ONCE(!tmc->online || tmc->idle); + + return 0; +} + +static int tmigr_cpu_offline(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int migrator; + u64 firstexp; + + raw_spin_lock_irq(&tmc->lock); + tmc->online = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* + * CPU has to handle the local events on his own, when on the way to + * offline; Therefore nextevt value is set to KTIME_MAX + */ + firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); + trace_tmigr_cpu_offline(tmc); + raw_spin_unlock_irq(&tmc->lock); + + if (firstexp != KTIME_MAX) { + migrator = cpumask_any_but(cpu_online_mask, cpu); + work_on_cpu(migrator, tmigr_trigger_active, NULL); + } + + return 0; +} + +static int __init tmigr_init(void) +{ + unsigned int cpulvl, nodelvl, cpus_per_node, i; + unsigned int nnodes = num_possible_nodes(); + unsigned int ncpus = num_possible_cpus(); + int ret = -ENOMEM; + + BUILD_BUG_ON_NOT_POWER_OF_2(TMIGR_CHILDREN_PER_GROUP); + + /* Nothing to do if running on UP */ + if (ncpus == 1) + return 0; + + /* + * Calculate the required hierarchy levels. Unfortunately there is no + * reliable information available, unless all possible CPUs have been + * brought up and all NUMA nodes are populated. + * + * Estimate the number of levels with the number of possible nodes and + * the number of possible CPUs. Assume CPUs are spread evenly across + * nodes. We cannot rely on cpumask_of_node() because it only works for + * online CPUs. + */ + cpus_per_node = DIV_ROUND_UP(ncpus, nnodes); + + /* Calc the hierarchy levels required to hold the CPUs of a node */ + cpulvl = DIV_ROUND_UP(order_base_2(cpus_per_node), + ilog2(TMIGR_CHILDREN_PER_GROUP)); + + /* Calculate the extra levels to connect all nodes */ + nodelvl = DIV_ROUND_UP(order_base_2(nnodes), + ilog2(TMIGR_CHILDREN_PER_GROUP)); + + tmigr_hierarchy_levels = cpulvl + nodelvl; + + /* + * If a NUMA node spawns more than one CPU level group then the next + * level(s) of the hierarchy contains groups which handle all CPU groups + * of the same NUMA node. The level above goes across NUMA nodes. Store + * this information for the setup code to decide in which level node + * matching is no longer required. + */ + tmigr_crossnode_level = cpulvl; + + tmigr_level_list = kcalloc(tmigr_hierarchy_levels, sizeof(struct list_head), GFP_KERNEL); + if (!tmigr_level_list) + goto err; + + for (i = 0; i < tmigr_hierarchy_levels; i++) + INIT_LIST_HEAD(&tmigr_level_list[i]); + + pr_info("Timer migration: %d hierarchy levels; %d children per group;" + " %d crossnode level\n", + tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP, + tmigr_crossnode_level); + + ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", + tmigr_cpu_online, tmigr_cpu_offline); + if (ret) + goto err; + + return 0; + +err: + pr_err("Timer migration setup failed\n"); + return ret; +} +late_initcall(tmigr_init); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h new file mode 100644 index 0000000000..6c37d94a37 --- /dev/null +++ b/kernel/time/timer_migration.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _KERNEL_TIME_MIGRATION_H +#define _KERNEL_TIME_MIGRATION_H + +/* Per group capacity. Must be a power of 2! */ +#define TMIGR_CHILDREN_PER_GROUP 8 + +/** + * struct tmigr_event - a timer event associated to a CPU + * @nextevt: The node to enqueue an event in the parent group queue + * @cpu: The CPU to which this event belongs + * @ignore: Hint whether the event could be ignored; it is set when + * CPU or group is active; + */ +struct tmigr_event { + struct timerqueue_node nextevt; + unsigned int cpu; + bool ignore; +}; + +/** + * struct tmigr_group - timer migration hierarchy group + * @lock: Lock protecting the event information and group hierarchy + * information during setup + * @parent: Pointer to the parent group + * @groupevt: Next event of the group which is only used when the + * group is !active. The group event is then queued into + * the parent timer queue. + * Ignore bit of @groupevt is set when the group is active. + * @next_expiry: Base monotonic expiry time of the next event of the + * group; It is used for the racy lockless check whether a + * remote expiry is required; it is always reliable + * @events: Timer queue for child events queued in the group + * @migr_state: State of the group (see union tmigr_state) + * @level: Hierarchy level of the group; Required during setup + * @numa_node: Required for setup only to make sure CPU and low level + * group information is NUMA local. It is set to NUMA node + * as long as the group level is per NUMA node (level < + * tmigr_crossnode_level); otherwise it is set to + * NUMA_NO_NODE + * @num_children: Counter of group children to make sure the group is only + * filled with TMIGR_CHILDREN_PER_GROUP; Required for setup + * only + * @childmask: childmask of the group in the parent group; is set + * during setup and will never change; can be read + * lockless + * @list: List head that is added to the per level + * tmigr_level_list; is required during setup when a + * new group needs to be connected to the existing + * hierarchy groups + */ +struct tmigr_group { + raw_spinlock_t lock; + struct tmigr_group *parent; + struct tmigr_event groupevt; + u64 next_expiry; + struct timerqueue_head events; + atomic_t migr_state; + unsigned int level; + int numa_node; + unsigned int num_children; + u8 childmask; + struct list_head list; +}; + +/** + * struct tmigr_cpu - timer migration per CPU group + * @lock: Lock protecting the tmigr_cpu group information + * @online: Indicates whether the CPU is online; In deactivate path + * it is required to know whether the migrator in the top + * level group is to be set offline, while a timer is + * pending. Then another online CPU needs to be notified to + * take over the migrator role. Furthermore the information + * is required in CPU hotplug path as the CPU is able to go + * idle before the timer migration hierarchy hotplug AP is + * reached. During this phase, the CPU has to handle the + * global timers on its own and must not act as a migrator. + * @idle: Indicates whether the CPU is idle in the timer migration + * hierarchy + * @remote: Is set when timers of the CPU are expired remotely + * @tmgroup: Pointer to the parent group + * @childmask: childmask of tmigr_cpu in the parent group + * @wakeup: Stores the first timer when the timer migration + * hierarchy is completely idle and remote expiry was done; + * is returned to timer code in the idle path and is only + * used in idle path. + * @cpuevt: CPU event which could be enqueued into the parent group + */ +struct tmigr_cpu { + raw_spinlock_t lock; + bool online; + bool idle; + bool remote; + struct tmigr_group *tmgroup; + u8 childmask; + u64 wakeup; + struct tmigr_event cpuevt; +}; + +/** + * union tmigr_state - state of tmigr_group + * @state: Combined version of the state - only used for atomic + * read/cmpxchg function + * @struct: Split version of the state - only use the struct members to + * update information to stay independent of endianness + */ +union tmigr_state { + u32 state; + /** + * struct - split state of tmigr_group + * @active: Contains each childmask bit of the active children + * @migrator: Contains childmask of the child which is migrator + * @seq: Sequence counter needs to be increased when an update + * to the tmigr_state is done. It prevents a race when + * updates in the child groups are propagated in changed + * order. Detailed information about the scenario is + * given in the documentation at the begin of + * timer_migration.c. + */ + struct { + u8 active; + u8 migrator; + u16 seq; + } __packed; +}; + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void tmigr_handle_remote(void); +extern bool tmigr_requires_handle_remote(void); +extern void tmigr_cpu_activate(void); +extern u64 tmigr_cpu_deactivate(u64 nextevt); +extern u64 tmigr_cpu_new_timer(u64 nextevt); +extern u64 tmigr_quick_check(u64 nextevt); +#else +static inline void tmigr_handle_remote(void) { } +static inline bool tmigr_requires_handle_remote(void) { return false; } +static inline void tmigr_cpu_activate(void) { } +#endif + +#endif |